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

* git://git.infradead.org/iommu-2.6:
  intel-iommu: Set a more specific taint flag for invalid BIOS DMAR tables
  intel-iommu: Combine the BIOS DMAR table warning messages
  panic: Add taint flag TAINT_FIRMWARE_WORKAROUND ('I')
  panic: Allow warnings to set different taint flags
  intel-iommu: intel_iommu_map_range failed at very end of address space
  intel-iommu: errors with smaller iommu widths
  intel-iommu: Fix boot inside 64bit virtualbox with io-apic disabled
  intel-iommu: use physfn to search drhd for VF
  intel-iommu: Print out iommu seq_id
  intel-iommu: Don't complain that ACPI_DMAR_SCOPE_TYPE_IOAPIC is not supported
  intel-iommu: Avoid global flushes with caching mode.
  intel-iommu: Use correct domain ID when caching mode is enabled
  intel-iommu mistakenly uses offset_pfn when caching mode is enabled
  intel-iommu: use for_each_set_bit()
  intel-iommu: Fix section mismatch dmar_ir_support() uses dmar_tbl.

Documentation/oops-tracing.txt

@@ -256,9 +256,13 @@ characters, each representing a particular tainted value.
   9: 'A' if the ACPI table has been overridden.
 
  10: 'W' if a warning has previously been issued by the kernel.
+     (Though some warnings may set more specific taint flags.)
 
  11: 'C' if a staging driver has been loaded.
 
+ 12: 'I' if the kernel is working around a severe bug in the platform
+     firmware (BIOS or similar).
+
 The primary reason for the 'Tainted: ' string is to tell kernel
 debuggers if this is a clean kernel or if anything unusual has
 occurred.  Tainting is permanent: even if an offending module is

arch/parisc/include/asm/bug.h

@@ -44,7 +44,7 @@
 #endif
 
 #ifdef CONFIG_DEBUG_BUGVERBOSE
-#define __WARN()							\
+#define __WARN_TAINT(taint)						\
 	do {								\
 		asm volatile("\n"					\
 			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
@@ -54,11 +54,11 @@
 			     "\t.org 2b+%c3\n"				\
 			     "\t.popsection"				\
 			     : : "i" (__FILE__), "i" (__LINE__),	\
-			     "i" (BUGFLAG_WARNING),			\
+			     "i" (BUGFLAG_TAINT(taint)), 		\
 			     "i" (sizeof(struct bug_entry)) );		\
 	} while(0)
 #else
-#define __WARN()							\
+#define __WARN_TAINT(taint)						\
 	do {								\
 		asm volatile("\n"					\
 			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
@@ -67,7 +67,7 @@
 			     "\t.short %c0\n"				\
 			     "\t.org 2b+%c1\n"				\
 			     "\t.popsection"				\
-			     : : "i" (BUGFLAG_WARNING),			\
+			     : : "i" (BUGFLAG_TAINT(taint)),		\
 			     "i" (sizeof(struct bug_entry)) );		\
 	} while(0)
 #endif

arch/powerpc/include/asm/bug.h

@@ -85,12 +85,12 @@
 	}							\
 } while (0)
 
-#define __WARN() do {						\
+#define __WARN_TAINT(taint) do {				\
 	__asm__ __volatile__(					\
 		"1:	twi 31,0,0\n"				\
 		_EMIT_BUG_ENTRY					\
 		: : "i" (__FILE__), "i" (__LINE__),		\
-		  "i" (BUGFLAG_WARNING),			\
+		  "i" (BUGFLAG_TAINT(taint)),			\
 		  "i" (sizeof(struct bug_entry)));		\
 } while (0)
 
@@ -104,7 +104,7 @@
 		"1:	"PPC_TLNEI"	%4,0\n"			\
 		_EMIT_BUG_ENTRY					\
 		: : "i" (__FILE__), "i" (__LINE__),		\
-		  "i" (BUGFLAG_WARNING),			\
+		  "i" (BUGFLAG_TAINT(TAINT_WARN)),		\
 		  "i" (sizeof(struct bug_entry)),		\
 		  "r" (__ret_warn_on));				\
 	}							\

arch/s390/include/asm/bug.h

@@ -46,18 +46,18 @@
 	unreachable();					\
 } while (0)
 
-#define __WARN() do {					\
-	__EMIT_BUG(BUGFLAG_WARNING);			\
+#define __WARN_TAINT(taint) do {			\
+	__EMIT_BUG(BUGFLAG_TAINT(taint));		\
 } while (0)
 
 #define WARN_ON(x) ({					\
 	int __ret_warn_on = !!(x);			\
 	if (__builtin_constant_p(__ret_warn_on)) {	\
 		if (__ret_warn_on)			\
-			__EMIT_BUG(BUGFLAG_WARNING);	\
+			__WARN();			\
 	} else {					\
 		if (unlikely(__ret_warn_on))		\
-			__EMIT_BUG(BUGFLAG_WARNING);	\
+			__WARN();			\
 	}						\
 	unlikely(__ret_warn_on);			\
 })

arch/sh/include/asm/bug.h

@@ -48,7 +48,7 @@ do {							\
 		   "i" (sizeof(struct bug_entry)));	\
 } while (0)
 
-#define __WARN()					\
+#define __WARN_TAINT(taint)				\
 do {							\
 	__asm__ __volatile__ (				\
 		"1:\t.short %O0\n"			\
@@ -57,7 +57,7 @@ do {							\
 		 : "n" (TRAPA_BUG_OPCODE),		\
 		   "i" (__FILE__),			\
 		   "i" (__LINE__),			\
-		   "i" (BUGFLAG_WARNING),		\
+		   "i" (BUGFLAG_TAINT(taint)),		\
 		   "i" (sizeof(struct bug_entry)));	\
 } while (0)
 

drivers/pci/dmar.c

@@ -131,9 +131,10 @@ static int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
 		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
 		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE)
 			(*cnt)++;
-		else
+		else if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_IOAPIC) {
 			printk(KERN_WARNING PREFIX
-				"Unsupported device scope\n");
+			       "Unsupported device scope\n");
+		}
 		start += scope->length;
 	}
 	if (*cnt == 0)
@@ -309,6 +310,8 @@ int dmar_find_matched_atsr_unit(struct pci_dev *dev)
 	struct acpi_dmar_atsr *atsr;
 	struct dmar_atsr_unit *atsru;
 
+	dev = pci_physfn(dev);
+
 	list_for_each_entry(atsru, &dmar_atsr_units, list) {
 		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
 		if (atsr->segment == pci_domain_nr(dev->bus))
@@ -358,12 +361,14 @@ dmar_parse_one_rhsa(struct acpi_dmar_header *header)
 			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));
+	WARN_TAINT(
+		1, TAINT_FIRMWARE_WORKAROUND,
+		"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;
 }
@@ -507,7 +512,7 @@ parse_dmar_table(void)
 	return ret;
 }
 
-int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
+static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
 			  struct pci_dev *dev)
 {
 	int index;
@@ -530,6 +535,8 @@ dmar_find_matched_drhd_unit(struct pci_dev *dev)
 	struct dmar_drhd_unit *dmaru = NULL;
 	struct acpi_dmar_hardware_unit *drhd;
 
+	dev = pci_physfn(dev);
+
 	list_for_each_entry(dmaru, &dmar_drhd_units, list) {
 		drhd = container_of(dmaru->hdr,
 				    struct acpi_dmar_hardware_unit,
@@ -614,7 +621,17 @@ int __init dmar_table_init(void)
 	return 0;
 }
 
-static int bios_warned;
+static void warn_invalid_dmar(u64 addr, const char *message)
+{
+	WARN_TAINT_ONCE(
+		1, TAINT_FIRMWARE_WORKAROUND,
+		"Your BIOS is broken; DMAR reported at address %llx%s!\n"
+		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+		addr, message,
+		dmi_get_system_info(DMI_BIOS_VENDOR),
+		dmi_get_system_info(DMI_BIOS_VERSION),
+		dmi_get_system_info(DMI_PRODUCT_VERSION));
+}
 
 int __init check_zero_address(void)
 {
@@ -640,13 +657,7 @@ int __init check_zero_address(void)
 
 			drhd = (void *)entry_header;
 			if (!drhd->address) {
-				/* Promote an attitude of violence to a BIOS engineer today */
-				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;
+				warn_invalid_dmar(0, "");
 				goto failed;
 			}
 
@@ -659,14 +670,8 @@ int __init check_zero_address(void)
 			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;
+				warn_invalid_dmar(drhd->address,
+						  " returns all ones");
 				goto failed;
 			}
 		}
@@ -731,14 +736,7 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 	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;
-		}
+		warn_invalid_dmar(0, "");
 		return -EINVAL;
 	}
 
@@ -758,16 +756,7 @@ 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) {
-		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;
-		}
+		warn_invalid_dmar(drhd->reg_base_addr, " returns all ones");
 		goto err_unmap;
 	}
 
@@ -806,7 +795,8 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 	}
 
 	ver = readl(iommu->reg + DMAR_VER_REG);
-	pr_info("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n",
+	pr_info("IOMMU %d: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n",
+		iommu->seq_id,
 		(unsigned long long)drhd->reg_base_addr,
 		DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
 		(unsigned long long)iommu->cap,
@@ -1457,9 +1447,11 @@ int dmar_reenable_qi(struct intel_iommu *iommu)
 /*
  * Check interrupt remapping support in DMAR table description.
  */
-int dmar_ir_support(void)
+int __init dmar_ir_support(void)
 {
 	struct acpi_table_dmar *dmar;
 	dmar = (struct acpi_table_dmar *)dmar_tbl;
+	if (!dmar)
+		return 0;
 	return dmar->flags & 0x1;
 }

drivers/pci/intel-iommu.c

@@ -491,13 +491,11 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain)
 
 	domain->iommu_coherency = 1;
 
-	i = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
-	for (; i < g_num_of_iommus; ) {
+	for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) {
 		if (!ecap_coherent(g_iommus[i]->ecap)) {
 			domain->iommu_coherency = 0;
 			break;
 		}
-		i = find_next_bit(&domain->iommu_bmp, g_num_of_iommus, i+1);
 	}
 }
 
@@ -507,13 +505,11 @@ static void domain_update_iommu_snooping(struct dmar_domain *domain)
 
 	domain->iommu_snooping = 1;
 
-	i = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
-	for (; i < g_num_of_iommus; ) {
+	for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) {
 		if (!ecap_sc_support(g_iommus[i]->ecap)) {
 			domain->iommu_snooping = 0;
 			break;
 		}
-		i = find_next_bit(&domain->iommu_bmp, g_num_of_iommus, i+1);
 	}
 }
 
@@ -1068,7 +1064,7 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 }
 
 static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
-				  unsigned long pfn, unsigned int pages)
+				  unsigned long pfn, unsigned int pages, int map)
 {
 	unsigned int mask = ilog2(__roundup_pow_of_two(pages));
 	uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT;
@@ -1089,10 +1085,10 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
 						DMA_TLB_PSI_FLUSH);
 
 	/*
-	 * In caching mode, domain ID 0 is reserved for non-present to present
-	 * mapping flush. Device IOTLB doesn't need to be flushed in this case.
+	 * In caching mode, changes of pages from non-present to present require
+	 * flush. However, device IOTLB doesn't need to be flushed in this case.
 	 */
-	if (!cap_caching_mode(iommu->cap) || did)
+	if (!cap_caching_mode(iommu->cap) || !map)
 		iommu_flush_dev_iotlb(iommu->domains[did], addr, mask);
 }
 
@@ -1154,7 +1150,8 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 	unsigned long nlongs;
 
 	ndomains = cap_ndoms(iommu->cap);
-	pr_debug("Number of Domains supportd <%ld>\n", ndomains);
+	pr_debug("IOMMU %d: Number of Domains supportd <%ld>\n", iommu->seq_id,
+			ndomains);
 	nlongs = BITS_TO_LONGS(ndomains);
 
 	spin_lock_init(&iommu->lock);
@@ -1194,8 +1191,7 @@ void free_dmar_iommu(struct intel_iommu *iommu)
 	unsigned long flags;
 
 	if ((iommu->domains) && (iommu->domain_ids)) {
-		i = find_first_bit(iommu->domain_ids, cap_ndoms(iommu->cap));
-		for (; i < cap_ndoms(iommu->cap); ) {
+		for_each_set_bit(i, iommu->domain_ids, cap_ndoms(iommu->cap)) {
 			domain = iommu->domains[i];
 			clear_bit(i, iommu->domain_ids);
 
@@ -1207,9 +1203,6 @@ void free_dmar_iommu(struct intel_iommu *iommu)
 					domain_exit(domain);
 			}
 			spin_unlock_irqrestore(&domain->iommu_lock, flags);
-
-			i = find_next_bit(iommu->domain_ids,
-				cap_ndoms(iommu->cap), i+1);
 		}
 	}
 
@@ -1292,14 +1285,11 @@ static void iommu_detach_domain(struct dmar_domain *domain,
 
 	spin_lock_irqsave(&iommu->lock, flags);
 	ndomains = cap_ndoms(iommu->cap);
-	num = find_first_bit(iommu->domain_ids, ndomains);
-	for (; num < ndomains; ) {
+	for_each_set_bit(num, iommu->domain_ids, ndomains) {
 		if (iommu->domains[num] == domain) {
 			found = 1;
 			break;
 		}
-		num = find_next_bit(iommu->domain_ids,
-				    cap_ndoms(iommu->cap), num+1);
 	}
 
 	if (found) {
@@ -1485,15 +1475,12 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
 
 		/* find an available domain id for this device in iommu */
 		ndomains = cap_ndoms(iommu->cap);
-		num = find_first_bit(iommu->domain_ids, ndomains);
-		for (; num < ndomains; ) {
+		for_each_set_bit(num, iommu->domain_ids, ndomains) {
 			if (iommu->domains[num] == domain) {
 				id = num;
 				found = 1;
 				break;
 			}
-			num = find_next_bit(iommu->domain_ids,
-					    cap_ndoms(iommu->cap), num+1);
 		}
 
 		if (found == 0) {
@@ -1558,7 +1545,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
 					   (((u16)bus) << 8) | devfn,
 					   DMA_CCMD_MASK_NOBIT,
 					   DMA_CCMD_DEVICE_INVL);
-		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_DSI_FLUSH);
+		iommu->flush.flush_iotlb(iommu, domain->id, 0, 0, DMA_TLB_DSI_FLUSH);
 	} else {
 		iommu_flush_write_buffer(iommu);
 	}
@@ -2333,14 +2320,16 @@ int __init init_dmars(void)
 			 */
 			iommu->flush.flush_context = __iommu_flush_context;
 			iommu->flush.flush_iotlb = __iommu_flush_iotlb;
-			printk(KERN_INFO "IOMMU 0x%Lx: using Register based "
+			printk(KERN_INFO "IOMMU %d 0x%Lx: using Register based "
 			       "invalidation\n",
+				iommu->seq_id,
 			       (unsigned long long)drhd->reg_base_addr);
 		} else {
 			iommu->flush.flush_context = qi_flush_context;
 			iommu->flush.flush_iotlb = qi_flush_iotlb;
-			printk(KERN_INFO "IOMMU 0x%Lx: using Queued "
+			printk(KERN_INFO "IOMMU %d 0x%Lx: using Queued "
 			       "invalidation\n",
+				iommu->seq_id,
 			       (unsigned long long)drhd->reg_base_addr);
 		}
 	}
@@ -2621,7 +2610,7 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr,
 
 	/* it's a non-present to present mapping. Only flush if caching mode */
 	if (cap_caching_mode(iommu->cap))
-		iommu_flush_iotlb_psi(iommu, 0, mm_to_dma_pfn(iova->pfn_lo), size);
+		iommu_flush_iotlb_psi(iommu, domain->id, mm_to_dma_pfn(iova->pfn_lo), size, 1);
 	else
 		iommu_flush_write_buffer(iommu);
 
@@ -2661,15 +2650,24 @@ static void flush_unmaps(void)
 		if (!deferred_flush[i].next)
 			continue;
 
-		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
+		/* In caching mode, global flushes turn emulation expensive */
+		if (!cap_caching_mode(iommu->cap))
+			iommu->flush.flush_iotlb(iommu, 0, 0, 0,
 					 DMA_TLB_GLOBAL_FLUSH);
 		for (j = 0; j < deferred_flush[i].next; j++) {
 			unsigned long mask;
 			struct iova *iova = deferred_flush[i].iova[j];
-
-			mask = ilog2(mm_to_dma_pfn(iova->pfn_hi - iova->pfn_lo + 1));
-			iommu_flush_dev_iotlb(deferred_flush[i].domain[j],
-					(uint64_t)iova->pfn_lo << PAGE_SHIFT, mask);
+			struct dmar_domain *domain = deferred_flush[i].domain[j];
+
+			/* On real hardware multiple invalidations are expensive */
+			if (cap_caching_mode(iommu->cap))
+				iommu_flush_iotlb_psi(iommu, domain->id,
+				iova->pfn_lo, iova->pfn_hi - iova->pfn_lo + 1, 0);
+			else {
+				mask = ilog2(mm_to_dma_pfn(iova->pfn_hi - iova->pfn_lo + 1));
+				iommu_flush_dev_iotlb(deferred_flush[i].domain[j],
+						(uint64_t)iova->pfn_lo << PAGE_SHIFT, mask);
+			}
 			__free_iova(&deferred_flush[i].domain[j]->iovad, iova);
 		}
 		deferred_flush[i].next = 0;
@@ -2750,7 +2748,7 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
 
 	if (intel_iommu_strict) {
 		iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
-				      last_pfn - start_pfn + 1);
+				      last_pfn - start_pfn + 1, 0);
 		/* free iova */
 		__free_iova(&domain->iovad, iova);
 	} else {
@@ -2840,7 +2838,7 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
 
 	if (intel_iommu_strict) {
 		iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
-				      last_pfn - start_pfn + 1);
+				      last_pfn - start_pfn + 1, 0);
 		/* free iova */
 		__free_iova(&domain->iovad, iova);
 	} else {
@@ -2874,7 +2872,6 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne
 	struct dmar_domain *domain;
 	size_t size = 0;
 	int prot = 0;
-	size_t offset_pfn = 0;
 	struct iova *iova = NULL;
 	int ret;
 	struct scatterlist *sg;
@@ -2928,7 +2925,7 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne
 
 	/* it's a non-present to present mapping. Only flush if caching mode */
 	if (cap_caching_mode(iommu->cap))
-		iommu_flush_iotlb_psi(iommu, 0, start_vpfn, offset_pfn);
+		iommu_flush_iotlb_psi(iommu, domain->id, start_vpfn, size, 1);
 	else
 		iommu_flush_write_buffer(iommu);
 
@@ -3436,22 +3433,6 @@ static void vm_domain_remove_all_dev_info(struct dmar_domain *domain)
 /* domain id for virtual machine, it won't be set in context */
 static unsigned long vm_domid;
 
-static int vm_domain_min_agaw(struct dmar_domain *domain)
-{
-	int i;
-	int min_agaw = domain->agaw;
-
-	i = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
-	for (; i < g_num_of_iommus; ) {
-		if (min_agaw > g_iommus[i]->agaw)
-			min_agaw = g_iommus[i]->agaw;
-
-		i = find_next_bit(&domain->iommu_bmp, g_num_of_iommus, i+1);
-	}
-
-	return min_agaw;
-}
-
 static struct dmar_domain *iommu_alloc_vm_domain(void)
 {
 	struct dmar_domain *domain;
@@ -3512,8 +3493,7 @@ static void iommu_free_vm_domain(struct dmar_domain *domain)
 		iommu = drhd->iommu;
 
 		ndomains = cap_ndoms(iommu->cap);
-		i = find_first_bit(iommu->domain_ids, ndomains);
-		for (; i < ndomains; ) {
+		for_each_set_bit(i, iommu->domain_ids, ndomains) {
 			if (iommu->domains[i] == domain) {
 				spin_lock_irqsave(&iommu->lock, flags);
 				clear_bit(i, iommu->domain_ids);
@@ -3521,7 +3501,6 @@ static void iommu_free_vm_domain(struct dmar_domain *domain)
 				spin_unlock_irqrestore(&iommu->lock, flags);
 				break;
 			}
-			i = find_next_bit(iommu->domain_ids, ndomains, i+1);
 		}
 	}
 }
@@ -3582,7 +3561,6 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct intel_iommu *iommu;
 	int addr_width;
-	u64 end;
 
 	/* normally pdev is not mapped */
 	if (unlikely(domain_context_mapped(pdev))) {
@@ -3605,14 +3583,30 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 
 	/* check if this iommu agaw is sufficient for max mapped address */
 	addr_width = agaw_to_width(iommu->agaw);
-	end = DOMAIN_MAX_ADDR(addr_width);
-	end = end & VTD_PAGE_MASK;
-	if (end < dmar_domain->max_addr) {
-		printk(KERN_ERR "%s: iommu agaw (%d) is not "
+	if (addr_width > cap_mgaw(iommu->cap))
+		addr_width = cap_mgaw(iommu->cap);
+
+	if (dmar_domain->max_addr > (1LL << addr_width)) {
+		printk(KERN_ERR "%s: iommu width (%d) is not "
 		       "sufficient for the mapped address (%llx)\n",
-		       __func__, iommu->agaw, dmar_domain->max_addr);
+		       __func__, addr_width, dmar_domain->max_addr);
 		return -EFAULT;
 	}
+	dmar_domain->gaw = addr_width;
+
+	/*
+	 * Knock out extra levels of page tables if necessary
+	 */
+	while (iommu->agaw < dmar_domain->agaw) {
+		struct dma_pte *pte;
+
+		pte = dmar_domain->pgd;
+		if (dma_pte_present(pte)) {
+			free_pgtable_page(dmar_domain->pgd);
+			dmar_domain->pgd = (struct dma_pte *)dma_pte_addr(pte);
+		}
+		dmar_domain->agaw--;
+	}
 
 	return domain_add_dev_info(dmar_domain, pdev, CONTEXT_TT_MULTI_LEVEL);
 }
@@ -3632,7 +3626,6 @@ static int intel_iommu_map(struct iommu_domain *domain,
 {
 	struct dmar_domain *dmar_domain = domain->priv;
 	u64 max_addr;
-	int addr_width;
 	int prot = 0;
 	size_t size;
 	int ret;
@@ -3647,18 +3640,14 @@ static int intel_iommu_map(struct iommu_domain *domain,
 	size     = PAGE_SIZE << gfp_order;
 	max_addr = iova + size;
 	if (dmar_domain->max_addr < max_addr) {
-		int min_agaw;
 		u64 end;
 
 		/* check if minimum agaw is sufficient for mapped address */
-		min_agaw = vm_domain_min_agaw(dmar_domain);
-		addr_width = agaw_to_width(min_agaw);
-		end = DOMAIN_MAX_ADDR(addr_width);
-		end = end & VTD_PAGE_MASK;
+		end = __DOMAIN_MAX_ADDR(dmar_domain->gaw) + 1;
 		if (end < max_addr) {
-			printk(KERN_ERR "%s: iommu agaw (%d) is not "
+			printk(KERN_ERR "%s: iommu width (%d) is not "
 			       "sufficient for the mapped address (%llx)\n",
-			       __func__, min_agaw, max_addr);
+			       __func__, dmar_domain->gaw, max_addr);
 			return -EFAULT;
 		}
 		dmar_domain->max_addr = max_addr;

drivers/pci/intr_remapping.c

@@ -832,9 +832,9 @@ static int ir_parse_ioapic_hpet_scope(struct acpi_dmar_header *header,
 				return -1;
 			}
 
-			printk(KERN_INFO "IOAPIC id %d under DRHD base"
-			       " 0x%Lx\n", scope->enumeration_id,
-			       drhd->address);
+			printk(KERN_INFO "IOAPIC id %d under DRHD base "
+			       " 0x%Lx IOMMU %d\n", scope->enumeration_id,
+			       drhd->address, iommu->seq_id);
 
 			ir_parse_one_ioapic_scope(scope, iommu);
 		} else if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_HPET) {

include/asm-generic/bug.h

@@ -25,7 +25,10 @@ struct bug_entry {
 };
 #endif		/* __ASSEMBLY__ */
 
-#define BUGFLAG_WARNING	(1<<0)
+#define BUGFLAG_WARNING		(1 << 0)
+#define BUGFLAG_TAINT(taint)	(BUGFLAG_WARNING | ((taint) << 8))
+#define BUG_GET_TAINT(bug)	((bug)->flags >> 8)
+
 #endif	/* CONFIG_GENERIC_BUG */
 
 /*
@@ -56,17 +59,25 @@ struct bug_entry {
  * appear at runtime.  Use the versions with printk format strings
  * to provide better diagnostics.
  */
-#ifndef __WARN
+#ifndef __WARN_TAINT
 #ifndef __ASSEMBLY__
 extern void warn_slowpath_fmt(const char *file, const int line,
 		const char *fmt, ...) __attribute__((format(printf, 3, 4)));
+extern void warn_slowpath_fmt_taint(const char *file, const int line,
+				    unsigned taint, const char *fmt, ...)
+	__attribute__((format(printf, 4, 5)));
 extern void warn_slowpath_null(const char *file, const int line);
 #define WANT_WARN_ON_SLOWPATH
 #endif
 #define __WARN()		warn_slowpath_null(__FILE__, __LINE__)
 #define __WARN_printf(arg...)	warn_slowpath_fmt(__FILE__, __LINE__, arg)
+#define __WARN_printf_taint(taint, arg...)				\
+	warn_slowpath_fmt_taint(__FILE__, __LINE__, taint, arg)
 #else
+#define __WARN()		__WARN_TAINT(TAINT_WARN)
 #define __WARN_printf(arg...)	do { printk(arg); __WARN(); } while (0)
+#define __WARN_printf_taint(taint, arg...)				\
+	do { printk(arg); __WARN_TAINT(taint); } while (0)
 #endif
 
 #ifndef WARN_ON
@@ -87,6 +98,13 @@ extern void warn_slowpath_null(const char *file, const int line);
 })
 #endif
 
+#define WARN_TAINT(condition, taint, format...) ({			\
+	int __ret_warn_on = !!(condition);				\
+	if (unlikely(__ret_warn_on))					\
+		__WARN_printf_taint(taint, format);			\
+	unlikely(__ret_warn_on);					\
+})
+
 #else /* !CONFIG_BUG */
 #ifndef HAVE_ARCH_BUG
 #define BUG() do {} while(0)
@@ -110,6 +128,8 @@ extern void warn_slowpath_null(const char *file, const int line);
 })
 #endif
 
+#define WARN_TAINT(condition, taint, format...) WARN_ON(condition)
+
 #endif
 
 #define WARN_ON_ONCE(condition)	({				\
@@ -132,6 +152,16 @@ extern void warn_slowpath_null(const char *file, const int line);
 	unlikely(__ret_warn_once);				\
 })
 
+#define WARN_TAINT_ONCE(condition, taint, format...)	({	\
+	static bool __warned;					\
+	int __ret_warn_once = !!(condition);			\
+								\
+	if (unlikely(__ret_warn_once))				\
+		if (WARN_TAINT(!__warned, taint, format))	\
+			__warned = true;			\
+	unlikely(__ret_warn_once);				\
+})
+
 #define WARN_ON_RATELIMIT(condition, state)			\
 		WARN_ON((condition) && __ratelimit(state))
 

include/linux/kernel.h

@@ -346,6 +346,7 @@ extern enum system_states {
 #define TAINT_OVERRIDDEN_ACPI_TABLE	8
 #define TAINT_WARN			9
 #define TAINT_CRAP			10
+#define TAINT_FIRMWARE_WORKAROUND	11
 
 extern void dump_stack(void) __cold;
 

include/linux/pci.h

@@ -334,6 +334,16 @@ struct pci_dev {
 #endif
 };
 
+static inline struct pci_dev *pci_physfn(struct pci_dev *dev)
+{
+#ifdef CONFIG_PCI_IOV
+	if (dev->is_virtfn)
+		dev = dev->physfn;
+#endif
+
+	return dev;
+}
+
 extern struct pci_dev *alloc_pci_dev(void);
 
 #define pci_dev_b(n) list_entry(n, struct pci_dev, bus_list)

kernel/panic.c

@@ -178,6 +178,7 @@ static const struct tnt tnts[] = {
 	{ TAINT_OVERRIDDEN_ACPI_TABLE,	'A', ' ' },
 	{ TAINT_WARN,			'W', ' ' },
 	{ TAINT_CRAP,			'C', ' ' },
+	{ TAINT_FIRMWARE_WORKAROUND,	'I', ' ' },
 };
 
 /**
@@ -194,6 +195,7 @@ static const struct tnt tnts[] = {
  *  'A' - ACPI table overridden.
  *  'W' - Taint on warning.
  *  'C' - modules from drivers/staging are loaded.
+ *  'I' - Working around severe firmware bug.
  *
  *	The string is overwritten by the next call to print_tainted().
  */
@@ -365,7 +367,8 @@ struct slowpath_args {
 	va_list args;
 };
 
-static void warn_slowpath_common(const char *file, int line, void *caller, struct slowpath_args *args)
+static void warn_slowpath_common(const char *file, int line, void *caller,
+				 unsigned taint, struct slowpath_args *args)
 {
 	const char *board;
 
@@ -381,7 +384,7 @@ static void warn_slowpath_common(const char *file, int line, void *caller, struc
 	print_modules();
 	dump_stack();
 	print_oops_end_marker();
-	add_taint(TAINT_WARN);
+	add_taint(taint);
 }
 
 void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...)
@@ -390,14 +393,29 @@ void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...)
 
 	args.fmt = fmt;
 	va_start(args.args, fmt);
-	warn_slowpath_common(file, line, __builtin_return_address(0), &args);
+	warn_slowpath_common(file, line, __builtin_return_address(0),
+			     TAINT_WARN, &args);
 	va_end(args.args);
 }
 EXPORT_SYMBOL(warn_slowpath_fmt);
 
+void warn_slowpath_fmt_taint(const char *file, int line,
+			     unsigned taint, const char *fmt, ...)
+{
+	struct slowpath_args args;
+
+	args.fmt = fmt;
+	va_start(args.args, fmt);
+	warn_slowpath_common(file, line, __builtin_return_address(0),
+			     taint, &args);
+	va_end(args.args);
+}
+EXPORT_SYMBOL(warn_slowpath_fmt_taint);
+
 void warn_slowpath_null(const char *file, int line)
 {
-	warn_slowpath_common(file, line, __builtin_return_address(0), NULL);
+	warn_slowpath_common(file, line, __builtin_return_address(0),
+			     TAINT_WARN, NULL);
 }
 EXPORT_SYMBOL(warn_slowpath_null);
 #endif

lib/bug.c

@@ -165,7 +165,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 			       (void *)bugaddr);
 
 		show_regs(regs);
-		add_taint(TAINT_WARN);
+		add_taint(BUG_GET_TAINT(bug));
 		return BUG_TRAP_TYPE_WARN;
 	}