Merge tag 'iommu-updates-v3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU upates from Joerg Roedel:
 "This time a few more updates queued up.

   - Rework VT-d code to support ACPI devices

   - Improvements for memory and PCI hotplug support in the VT-d driver

   - Device-tree support for OMAP IOMMU

   - Convert OMAP IOMMU to use devm_* interfaces

   - Fixed PASID support for AMD IOMMU

   - Other random cleanups and fixes for OMAP, ARM-SMMU and SHMOBILE
     IOMMU

  Most of the changes are in the VT-d driver because some rework was
  necessary for better hotplug and ACPI device support"

* tag 'iommu-updates-v3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (75 commits)
  iommu/vt-d: Fix error handling in ANDD processing
  iommu/vt-d: returning free pointer in get_domain_for_dev()
  iommu/vt-d: Only call dmar_acpi_dev_scope_init() if DRHD units present
  iommu/vt-d: Check for NULL pointer in dmar_acpi_dev_scope_init()
  iommu/amd: Fix logic to determine and checking max PASID
  iommu/vt-d: Include ACPI devices in iommu=pt
  iommu/vt-d: Finally enable translation for non-PCI devices
  iommu/vt-d: Remove to_pci_dev() in intel_map_page()
  iommu/vt-d: Remove pdev from intel_iommu_attach_device()
  iommu/vt-d: Remove pdev from iommu_no_mapping()
  iommu/vt-d: Make domain_add_dev_info() take struct device
  iommu/vt-d: Make domain_remove_one_dev_info() take struct device
  iommu/vt-d: Rename 'hwdev' variables to 'dev' now that that's the norm
  iommu/vt-d: Remove some pointless to_pci_dev() calls
  iommu/vt-d: Make get_valid_domain_for_dev() take struct device
  iommu/vt-d: Make iommu_should_identity_map() take struct device
  iommu/vt-d: Handle RMRRs for non-PCI devices
  iommu/vt-d: Make get_domain_for_dev() take struct device
  iommu/vt-d: Make domain_context_mapp{ed,ing}() take struct device
  iommu/vt-d: Make device_to_iommu() cope with non-PCI devices
  ...

Documentation/devicetree/bindings/iommu/arm,smmu.txt

@@ -48,6 +48,12 @@ conditions.
                   from the mmu-masters towards memory) node for this
                   SMMU.
 
+- calxeda,smmu-secure-config-access : Enable proper handling of buggy
+                  implementations that always use secure access to
+                  SMMU configuration registers. In this case non-secure
+                  aliases of secure registers have to be used during
+                  SMMU configuration.
+
 Example:
 
         smmu {

Documentation/devicetree/bindings/iommu/ti,omap-iommu.txt

@@ -0,0 +1,26 @@
+OMAP2+ IOMMU
+
+Required properties:
+- compatible : Should be one of,
+		"ti,omap2-iommu" for OMAP2/OMAP3 IOMMU instances
+		"ti,omap4-iommu" for OMAP4/OMAP5 IOMMU instances
+		"ti,dra7-iommu" for DRA7xx IOMMU instances
+- ti,hwmods  : Name of the hwmod associated with the IOMMU instance
+- reg        : Address space for the configuration registers
+- interrupts : Interrupt specifier for the IOMMU instance
+
+Optional properties:
+- ti,#tlb-entries : Number of entries in the translation look-aside buffer.
+                    Should be either 8 or 32 (default: 32)
+- ti,iommu-bus-err-back : Indicates the IOMMU instance supports throwing
+		          back a bus error response on MMU faults.
+
+Example:
+	/* OMAP3 ISP MMU */
+	mmu_isp: mmu@480bd400 {
+		compatible = "ti,omap2-iommu";
+		reg = <0x480bd400 0x80>;
+		interrupts = <24>;
+		ti,hwmods = "mmu_isp";
+		ti,#tlb-entries = <8>;
+	};

arch/arm/mach-omap2/omap-iommu.c

@@ -10,6 +10,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/of.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/err.h>
@@ -58,6 +59,10 @@ static int __init omap_iommu_dev_init(struct omap_hwmod *oh, void *unused)
 
 static int __init omap_iommu_init(void)
 {
+	/* If dtb is there, the devices will be created dynamically */
+	if (of_have_populated_dt())
+		return -ENODEV;
+
 	return omap_hwmod_for_each_by_class("mmu", omap_iommu_dev_init, NULL);
 }
 /* must be ready before omap3isp is probed */

drivers/iommu/Kconfig

@@ -207,7 +207,7 @@ config SHMOBILE_IOMMU
 	bool "IOMMU for Renesas IPMMU/IPMMUI"
 	default n
 	depends on ARM
-	depends on SH_MOBILE || COMPILE_TEST
+	depends on ARCH_SHMOBILE || COMPILE_TEST
 	select IOMMU_API
 	select ARM_DMA_USE_IOMMU
 	select SHMOBILE_IPMMU

drivers/iommu/amd_iommu.c

@@ -963,7 +963,7 @@ static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, int pasid,
 
 	address &= ~(0xfffULL);
 
-	cmd->data[0]  = pasid & PASID_MASK;
+	cmd->data[0]  = pasid;
 	cmd->data[1]  = domid;
 	cmd->data[2]  = lower_32_bits(address);
 	cmd->data[3]  = upper_32_bits(address);
@@ -982,10 +982,10 @@ static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, int pasid,
 	address &= ~(0xfffULL);
 
 	cmd->data[0]  = devid;
-	cmd->data[0] |= (pasid & 0xff) << 16;
+	cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
 	cmd->data[0] |= (qdep  & 0xff) << 24;
 	cmd->data[1]  = devid;
-	cmd->data[1] |= ((pasid >> 8) & 0xfff) << 16;
+	cmd->data[1] |= (pasid & 0xff) << 16;
 	cmd->data[2]  = lower_32_bits(address);
 	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
 	cmd->data[3]  = upper_32_bits(address);
@@ -1001,7 +1001,7 @@ static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, int pasid,
 
 	cmd->data[0]  = devid;
 	if (gn) {
-		cmd->data[1]  = pasid & PASID_MASK;
+		cmd->data[1]  = pasid;
 		cmd->data[2]  = CMD_INV_IOMMU_PAGES_GN_MASK;
 	}
 	cmd->data[3]  = tag & 0x1ff;

drivers/iommu/amd_iommu_init.c

@@ -150,7 +150,7 @@ int amd_iommus_present;
 bool amd_iommu_np_cache __read_mostly;
 bool amd_iommu_iotlb_sup __read_mostly = true;
 
-u32 amd_iommu_max_pasids __read_mostly = ~0;
+u32 amd_iommu_max_pasid __read_mostly = ~0;
 
 bool amd_iommu_v2_present __read_mostly;
 bool amd_iommu_pc_present __read_mostly;
@@ -1231,14 +1231,16 @@ static int iommu_init_pci(struct amd_iommu *iommu)
 
 	if (iommu_feature(iommu, FEATURE_GT)) {
 		int glxval;
-		u32 pasids;
-		u64 shift;
+		u32 max_pasid;
+		u64 pasmax;
 
-		shift   = iommu->features & FEATURE_PASID_MASK;
-		shift >>= FEATURE_PASID_SHIFT;
-		pasids  = (1 << shift);
+		pasmax = iommu->features & FEATURE_PASID_MASK;
+		pasmax >>= FEATURE_PASID_SHIFT;
+		max_pasid  = (1 << (pasmax + 1)) - 1;
 
-		amd_iommu_max_pasids = min(amd_iommu_max_pasids, pasids);
+		amd_iommu_max_pasid = min(amd_iommu_max_pasid, max_pasid);
+
+		BUG_ON(amd_iommu_max_pasid & ~PASID_MASK);
 
 		glxval   = iommu->features & FEATURE_GLXVAL_MASK;
 		glxval >>= FEATURE_GLXVAL_SHIFT;

drivers/iommu/amd_iommu_types.h

@@ -99,7 +99,12 @@
 #define FEATURE_GLXVAL_SHIFT	14
 #define FEATURE_GLXVAL_MASK	(0x03ULL << FEATURE_GLXVAL_SHIFT)
 
-#define PASID_MASK		0x000fffff
+/* Note:
+ * The current driver only support 16-bit PASID.
+ * Currently, hardware only implement upto 16-bit PASID
+ * even though the spec says it could have upto 20 bits.
+ */
+#define PASID_MASK		0x0000ffff
 
 /* MMIO status bits */
 #define MMIO_STATUS_EVT_INT_MASK	(1 << 1)
@@ -697,8 +702,8 @@ extern unsigned long *amd_iommu_pd_alloc_bitmap;
  */
 extern u32 amd_iommu_unmap_flush;
 
-/* Smallest number of PASIDs supported by any IOMMU in the system */
-extern u32 amd_iommu_max_pasids;
+/* Smallest max PASID supported by any IOMMU in the system */
+extern u32 amd_iommu_max_pasid;
 
 extern bool amd_iommu_v2_present;
 

drivers/iommu/arm-smmu.c

@@ -48,7 +48,7 @@
 #include <asm/pgalloc.h>
 
 /* Maximum number of stream IDs assigned to a single device */
-#define MAX_MASTER_STREAMIDS		8
+#define MAX_MASTER_STREAMIDS		MAX_PHANDLE_ARGS
 
 /* Maximum number of context banks per SMMU */
 #define ARM_SMMU_MAX_CBS		128
@@ -60,6 +60,16 @@
 #define ARM_SMMU_GR0(smmu)		((smmu)->base)
 #define ARM_SMMU_GR1(smmu)		((smmu)->base + (smmu)->pagesize)
 
+/*
+ * SMMU global address space with conditional offset to access secure
+ * aliases of non-secure registers (e.g. nsCR0: 0x400, nsGFSR: 0x448,
+ * nsGFSYNR0: 0x450)
+ */
+#define ARM_SMMU_GR0_NS(smmu)						\
+	((smmu)->base +							\
+		((smmu->options & ARM_SMMU_OPT_SECURE_CFG_ACCESS)	\
+			? 0x400 : 0))
+
 /* Page table bits */
 #define ARM_SMMU_PTE_XN			(((pteval_t)3) << 53)
 #define ARM_SMMU_PTE_CONT		(((pteval_t)1) << 52)
@@ -351,6 +361,9 @@ struct arm_smmu_device {
 #define ARM_SMMU_FEAT_TRANS_S2		(1 << 3)
 #define ARM_SMMU_FEAT_TRANS_NESTED	(1 << 4)
 	u32				features;
+
+#define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0)
+	u32				options;
 	int				version;
 
 	u32				num_context_banks;
@@ -401,6 +414,29 @@ struct arm_smmu_domain {
 static DEFINE_SPINLOCK(arm_smmu_devices_lock);
 static LIST_HEAD(arm_smmu_devices);
 
+struct arm_smmu_option_prop {
+	u32 opt;
+	const char *prop;
+};
+
+static struct arm_smmu_option_prop arm_smmu_options [] = {
+	{ ARM_SMMU_OPT_SECURE_CFG_ACCESS, "calxeda,smmu-secure-config-access" },
+	{ 0, NULL},
+};
+
+static void parse_driver_options(struct arm_smmu_device *smmu)
+{
+	int i = 0;
+	do {
+		if (of_property_read_bool(smmu->dev->of_node,
+						arm_smmu_options[i].prop)) {
+			smmu->options |= arm_smmu_options[i].opt;
+			dev_notice(smmu->dev, "option %s\n",
+				arm_smmu_options[i].prop);
+		}
+	} while (arm_smmu_options[++i].opt);
+}
+
 static struct arm_smmu_master *find_smmu_master(struct arm_smmu_device *smmu,
 						struct device_node *dev_node)
 {
@@ -614,16 +650,16 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
 {
 	u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
 	struct arm_smmu_device *smmu = dev;
-	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+	void __iomem *gr0_base = ARM_SMMU_GR0_NS(smmu);
 
 	gfsr = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR);
-	if (!gfsr)
-		return IRQ_NONE;
-
 	gfsynr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR0);
 	gfsynr1 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR1);
 	gfsynr2 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR2);
 
+	if (!gfsr)
+		return IRQ_NONE;
+
 	dev_err_ratelimited(smmu->dev,
 		"Unexpected global fault, this could be serious\n");
 	dev_err_ratelimited(smmu->dev,
@@ -642,7 +678,7 @@ static void arm_smmu_flush_pgtable(struct arm_smmu_device *smmu, void *addr,
 
 	/* Ensure new page tables are visible to the hardware walker */
 	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) {
-		dsb();
+		dsb(ishst);
 	} else {
 		/*
 		 * If the SMMU can't walk tables in the CPU caches, treat them
@@ -990,9 +1026,8 @@ static void arm_smmu_free_pgtables(struct arm_smmu_domain *smmu_domain)
 
 	/*
 	 * Recursively free the page tables for this domain. We don't
-	 * care about speculative TLB filling, because the TLB will be
-	 * nuked next time this context bank is re-allocated and no devices
-	 * currently map to these tables.
+	 * care about speculative TLB filling because the tables should
+	 * not be active in any context bank at this point (SCTLR.M is 0).
 	 */
 	pgd = pgd_base;
 	for (i = 0; i < PTRS_PER_PGD; ++i) {
@@ -1218,7 +1253,7 @@ static bool arm_smmu_pte_is_contiguous_range(unsigned long addr,
 
 static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 				   unsigned long addr, unsigned long end,
-				   unsigned long pfn, int flags, int stage)
+				   unsigned long pfn, int prot, int stage)
 {
 	pte_t *pte, *start;
 	pteval_t pteval = ARM_SMMU_PTE_PAGE | ARM_SMMU_PTE_AF | ARM_SMMU_PTE_XN;
@@ -1240,28 +1275,28 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 
 	if (stage == 1) {
 		pteval |= ARM_SMMU_PTE_AP_UNPRIV | ARM_SMMU_PTE_nG;
-		if (!(flags & IOMMU_WRITE) && (flags & IOMMU_READ))
+		if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ))
 			pteval |= ARM_SMMU_PTE_AP_RDONLY;
 
-		if (flags & IOMMU_CACHE)
+		if (prot & IOMMU_CACHE)
 			pteval |= (MAIR_ATTR_IDX_CACHE <<
 				   ARM_SMMU_PTE_ATTRINDX_SHIFT);
 	} else {
 		pteval |= ARM_SMMU_PTE_HAP_FAULT;
-		if (flags & IOMMU_READ)
+		if (prot & IOMMU_READ)
 			pteval |= ARM_SMMU_PTE_HAP_READ;
-		if (flags & IOMMU_WRITE)
+		if (prot & IOMMU_WRITE)
 			pteval |= ARM_SMMU_PTE_HAP_WRITE;
-		if (flags & IOMMU_CACHE)
+		if (prot & IOMMU_CACHE)
 			pteval |= ARM_SMMU_PTE_MEMATTR_OIWB;
 		else
 			pteval |= ARM_SMMU_PTE_MEMATTR_NC;
 	}
 
 	/* If no access, create a faulting entry to avoid TLB fills */
-	if (flags & IOMMU_EXEC)
+	if (prot & IOMMU_EXEC)
 		pteval &= ~ARM_SMMU_PTE_XN;
-	else if (!(flags & (IOMMU_READ | IOMMU_WRITE)))
+	else if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
 		pteval &= ~ARM_SMMU_PTE_PAGE;
 
 	pteval |= ARM_SMMU_PTE_SH_IS;
@@ -1323,7 +1358,7 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 
 static int arm_smmu_alloc_init_pmd(struct arm_smmu_device *smmu, pud_t *pud,
 				   unsigned long addr, unsigned long end,
-				   phys_addr_t phys, int flags, int stage)
+				   phys_addr_t phys, int prot, int stage)
 {
 	int ret;
 	pmd_t *pmd;
@@ -1347,7 +1382,7 @@ static int arm_smmu_alloc_init_pmd(struct arm_smmu_device *smmu, pud_t *pud,
 	do {
 		next = pmd_addr_end(addr, end);
 		ret = arm_smmu_alloc_init_pte(smmu, pmd, addr, end, pfn,
-					      flags, stage);
+					      prot, stage);
 		phys += next - addr;
 	} while (pmd++, addr = next, addr < end);
 
@@ -1356,7 +1391,7 @@ static int arm_smmu_alloc_init_pmd(struct arm_smmu_device *smmu, pud_t *pud,
 
 static int arm_smmu_alloc_init_pud(struct arm_smmu_device *smmu, pgd_t *pgd,
 				   unsigned long addr, unsigned long end,
-				   phys_addr_t phys, int flags, int stage)
+				   phys_addr_t phys, int prot, int stage)
 {
 	int ret = 0;
 	pud_t *pud;
@@ -1380,7 +1415,7 @@ static int arm_smmu_alloc_init_pud(struct arm_smmu_device *smmu, pgd_t *pgd,
 	do {
 		next = pud_addr_end(addr, end);
 		ret = arm_smmu_alloc_init_pmd(smmu, pud, addr, next, phys,
-					      flags, stage);
+					      prot, stage);
 		phys += next - addr;
 	} while (pud++, addr = next, addr < end);
 
@@ -1389,7 +1424,7 @@ static int arm_smmu_alloc_init_pud(struct arm_smmu_device *smmu, pgd_t *pgd,
 
 static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
 				   unsigned long iova, phys_addr_t paddr,
-				   size_t size, int flags)
+				   size_t size, int prot)
 {
 	int ret, stage;
 	unsigned long end;
@@ -1397,7 +1432,7 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
 	struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
 	pgd_t *pgd = root_cfg->pgd;
 	struct arm_smmu_device *smmu = root_cfg->smmu;
-	unsigned long irqflags;
+	unsigned long flags;
 
 	if (root_cfg->cbar == CBAR_TYPE_S2_TRANS) {
 		stage = 2;
@@ -1420,14 +1455,14 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
 	if (paddr & ~output_mask)
 		return -ERANGE;
 
-	spin_lock_irqsave(&smmu_domain->lock, irqflags);
+	spin_lock_irqsave(&smmu_domain->lock, flags);
 	pgd += pgd_index(iova);
 	end = iova + size;
 	do {
 		unsigned long next = pgd_addr_end(iova, end);
 
 		ret = arm_smmu_alloc_init_pud(smmu, pgd, iova, next, paddr,
-					      flags, stage);
+					      prot, stage);
 		if (ret)
 			goto out_unlock;
 
@@ -1436,13 +1471,13 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
 	} while (pgd++, iova != end);
 
 out_unlock:
-	spin_unlock_irqrestore(&smmu_domain->lock, irqflags);
+	spin_unlock_irqrestore(&smmu_domain->lock, flags);
 
 	return ret;
 }
 
 static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
-			phys_addr_t paddr, size_t size, int flags)
+			phys_addr_t paddr, size_t size, int prot)
 {
 	struct arm_smmu_domain *smmu_domain = domain->priv;
 
@@ -1453,7 +1488,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
 	if ((phys_addr_t)iova & ~smmu_domain->output_mask)
 		return -ERANGE;
 
-	return arm_smmu_handle_mapping(smmu_domain, iova, paddr, size, flags);
+	return arm_smmu_handle_mapping(smmu_domain, iova, paddr, size, prot);
 }
 
 static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
@@ -1597,9 +1632,9 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	int i = 0;
 	u32 reg;
 
-	/* Clear Global FSR */
-	reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR);
-	writel(reg, gr0_base + ARM_SMMU_GR0_sGFSR);
+	/* clear global FSR */
+	reg = readl_relaxed(ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sGFSR);
+	writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sGFSR);
 
 	/* Mark all SMRn as invalid and all S2CRn as bypass */
 	for (i = 0; i < smmu->num_mapping_groups; ++i) {
@@ -1619,7 +1654,7 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLH);
 	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLNSNH);
 
-	reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_sCR0);
+	reg = readl_relaxed(ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
 
 	/* Enable fault reporting */
 	reg |= (sCR0_GFRE | sCR0_GFIE | sCR0_GCFGFRE | sCR0_GCFGFIE);
@@ -1638,7 +1673,7 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 
 	/* Push the button */
 	arm_smmu_tlb_sync(smmu);
-	writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_sCR0);
+	writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
 }
 
 static int arm_smmu_id_size_to_bits(int size)
@@ -1885,6 +1920,8 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	if (err)
 		goto out_put_parent;
 
+	parse_driver_options(smmu);
+
 	if (smmu->version > 1 &&
 	    smmu->num_context_banks != smmu->num_context_irqs) {
 		dev_err(dev,
@@ -1969,7 +2006,7 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
 		free_irq(smmu->irqs[i], smmu);
 
 	/* Turn the thing off */
-	writel_relaxed(sCR0_CLIENTPD, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_sCR0);
+	writel(sCR0_CLIENTPD,ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
 	return 0;
 }
 

drivers/iommu/dmar.c

@@ -43,14 +43,24 @@
 
 #include "irq_remapping.h"
 
-/* No locks are needed as DMA remapping hardware unit
- * list is constructed at boot time and hotplug of
- * these units are not supported by the architecture.
+/*
+ * Assumptions:
+ * 1) The hotplug framework guarentees that DMAR unit will be hot-added
+ *    before IO devices managed by that unit.
+ * 2) The hotplug framework guarantees that DMAR unit will be hot-removed
+ *    after IO devices managed by that unit.
+ * 3) Hotplug events are rare.
+ *
+ * Locking rules for DMA and interrupt remapping related global data structures:
+ * 1) Use dmar_global_lock in process context
+ * 2) Use RCU in interrupt context
  */
+DECLARE_RWSEM(dmar_global_lock);
 LIST_HEAD(dmar_drhd_units);
 
 struct acpi_table_header * __initdata dmar_tbl;
 static acpi_size dmar_tbl_size;
+static int dmar_dev_scope_status = 1;
 
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
 static void free_iommu(struct intel_iommu *iommu);
@@ -62,73 +72,20 @@ static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 	 * the very end.
 	 */
 	if (drhd->include_all)
-		list_add_tail(&drhd->list, &dmar_drhd_units);
+		list_add_tail_rcu(&drhd->list, &dmar_drhd_units);
 	else
-		list_add(&drhd->list, &dmar_drhd_units);
+		list_add_rcu(&drhd->list, &dmar_drhd_units);
 }
 
-static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
-					   struct pci_dev **dev, u16 segment)
-{
-	struct pci_bus *bus;
-	struct pci_dev *pdev = NULL;
-	struct acpi_dmar_pci_path *path;
-	int count;
-
-	bus = pci_find_bus(segment, scope->bus);
-	path = (struct acpi_dmar_pci_path *)(scope + 1);
-	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
-		/ sizeof(struct acpi_dmar_pci_path);
-
-	while (count) {
-		if (pdev)
-			pci_dev_put(pdev);
-		/*
-		 * Some BIOSes list non-exist devices in DMAR table, just
-		 * ignore it
-		 */
-		if (!bus) {
-			pr_warn("Device scope bus [%d] not found\n", scope->bus);
-			break;
-		}
-		pdev = pci_get_slot(bus, PCI_DEVFN(path->device, path->function));
-		if (!pdev) {
-			/* warning will be printed below */
-			break;
-		}
-		path ++;
-		count --;
-		bus = pdev->subordinate;
-	}
-	if (!pdev) {
-		pr_warn("Device scope device [%04x:%02x:%02x.%02x] not found\n",
-			segment, scope->bus, path->device, path->function);
-		return 0;
-	}
-	if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT && \
-			pdev->subordinate) || (scope->entry_type == \
-			ACPI_DMAR_SCOPE_TYPE_BRIDGE && !pdev->subordinate)) {
-		pci_dev_put(pdev);
-		pr_warn("Device scope type does not match for %s\n",
-			pci_name(pdev));
-		return -EINVAL;
-	}
-	*dev = pdev;
-	return 0;
-}
-
-int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
-				struct pci_dev ***devices, u16 segment)
+void *dmar_alloc_dev_scope(void *start, void *end, int *cnt)
 {
 	struct acpi_dmar_device_scope *scope;
-	void * tmp = start;
-	int index;
-	int ret;
 
 	*cnt = 0;
 	while (start < end) {
 		scope = start;
-		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
+		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ACPI ||
+		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
 		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE)
 			(*cnt)++;
 		else if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_IOAPIC &&
@@ -138,43 +95,236 @@ int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
 		start += scope->length;
 	}
 	if (*cnt == 0)
-		return 0;
+		return NULL;
 
-	*devices = kcalloc(*cnt, sizeof(struct pci_dev *), GFP_KERNEL);
-	if (!*devices)
-		return -ENOMEM;
+	return kcalloc(*cnt, sizeof(struct dmar_dev_scope), GFP_KERNEL);
+}
 
-	start = tmp;
-	index = 0;
-	while (start < end) {
+void dmar_free_dev_scope(struct dmar_dev_scope **devices, int *cnt)
+{
+	int i;
+	struct device *tmp_dev;
+
+	if (*devices && *cnt) {
+		for_each_active_dev_scope(*devices, *cnt, i, tmp_dev)
+			put_device(tmp_dev);
+		kfree(*devices);
+	}
+
+	*devices = NULL;
+	*cnt = 0;
+}
+
+/* Optimize out kzalloc()/kfree() for normal cases */
+static char dmar_pci_notify_info_buf[64];
+
+static struct dmar_pci_notify_info *
+dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
+{
+	int level = 0;
+	size_t size;
+	struct pci_dev *tmp;
+	struct dmar_pci_notify_info *info;
+
+	BUG_ON(dev->is_virtfn);
+
+	/* Only generate path[] for device addition event */
+	if (event == BUS_NOTIFY_ADD_DEVICE)
+		for (tmp = dev; tmp; tmp = tmp->bus->self)
+			level++;
+
+	size = sizeof(*info) + level * sizeof(struct acpi_dmar_pci_path);
+	if (size <= sizeof(dmar_pci_notify_info_buf)) {
+		info = (struct dmar_pci_notify_info *)dmar_pci_notify_info_buf;
+	} else {
+		info = kzalloc(size, GFP_KERNEL);
+		if (!info) {
+			pr_warn("Out of memory when allocating notify_info "
+				"for %s.\n", pci_name(dev));
+			if (dmar_dev_scope_status == 0)
+				dmar_dev_scope_status = -ENOMEM;
+			return NULL;
+		}
+	}
+
+	info->event = event;
+	info->dev = dev;
+	info->seg = pci_domain_nr(dev->bus);
+	info->level = level;
+	if (event == BUS_NOTIFY_ADD_DEVICE) {
+		for (tmp = dev, level--; tmp; tmp = tmp->bus->self) {
+			info->path[level].device = PCI_SLOT(tmp->devfn);
+			info->path[level].function = PCI_FUNC(tmp->devfn);
+			if (pci_is_root_bus(tmp->bus))
+				info->bus = tmp->bus->number;
+		}
+	}
+
+	return info;
+}
+
+static inline void dmar_free_pci_notify_info(struct dmar_pci_notify_info *info)
+{
+	if ((void *)info != dmar_pci_notify_info_buf)
+		kfree(info);
+}
+
+static bool dmar_match_pci_path(struct dmar_pci_notify_info *info, int bus,
+				struct acpi_dmar_pci_path *path, int count)
+{
+	int i;
+
+	if (info->bus != bus)
+		return false;
+	if (info->level != count)
+		return false;
+
+	for (i = 0; i < count; i++) {
+		if (path[i].device != info->path[i].device ||
+		    path[i].function != info->path[i].function)
+			return false;
+	}
+
+	return true;
+}
+
+/* Return: > 0 if match found, 0 if no match found, < 0 if error happens */
+int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
+			  void *start, void*end, u16 segment,
+			  struct dmar_dev_scope *devices,
+			  int devices_cnt)
+{
+	int i, level;
+	struct device *tmp, *dev = &info->dev->dev;
+	struct acpi_dmar_device_scope *scope;
+	struct acpi_dmar_pci_path *path;
+
+	if (segment != info->seg)
+		return 0;
+
+	for (; start < end; start += scope->length) {
 		scope = start;
-		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
-		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE) {
-			ret = dmar_parse_one_dev_scope(scope,
-				&(*devices)[index], segment);
-			if (ret) {
-				dmar_free_dev_scope(devices, cnt);
-				return ret;
-			}
-			index ++;
+		if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_ENDPOINT &&
+		    scope->entry_type != ACPI_DMAR_SCOPE_TYPE_BRIDGE)
+			continue;
+
+		path = (struct acpi_dmar_pci_path *)(scope + 1);
+		level = (scope->length - sizeof(*scope)) / sizeof(*path);
+		if (!dmar_match_pci_path(info, scope->bus, path, level))
+			continue;
+
+		if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT) ^
+		    (info->dev->hdr_type == PCI_HEADER_TYPE_NORMAL)) {
+			pr_warn("Device scope type does not match for %s\n",
+				pci_name(info->dev));
+			return -EINVAL;
 		}
-		start += scope->length;
+
+		for_each_dev_scope(devices, devices_cnt, i, tmp)
+			if (tmp == NULL) {
+				devices[i].bus = info->dev->bus->number;
+				devices[i].devfn = info->dev->devfn;
+				rcu_assign_pointer(devices[i].dev,
+						   get_device(dev));
+				return 1;
+			}
+		BUG_ON(i >= devices_cnt);
 	}
 
 	return 0;
 }
 
-void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt)
+int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment,
+			  struct dmar_dev_scope *devices, int count)
 {
-	if (*devices && *cnt) {
-		while (--*cnt >= 0)
-			pci_dev_put((*devices)[*cnt]);
-		kfree(*devices);
-		*devices = NULL;
-		*cnt = 0;
+	int index;
+	struct device *tmp;
+
+	if (info->seg != segment)
+		return 0;
+
+	for_each_active_dev_scope(devices, count, index, tmp)
+		if (tmp == &info->dev->dev) {
+			rcu_assign_pointer(devices[index].dev, NULL);
+			synchronize_rcu();
+			put_device(tmp);
+			return 1;
+		}
+
+	return 0;
+}
+
+static int dmar_pci_bus_add_dev(struct dmar_pci_notify_info *info)
+{
+	int ret = 0;
+	struct dmar_drhd_unit *dmaru;
+	struct acpi_dmar_hardware_unit *drhd;
+
+	for_each_drhd_unit(dmaru) {
+		if (dmaru->include_all)
+			continue;
+
+		drhd = container_of(dmaru->hdr,
+				    struct acpi_dmar_hardware_unit, header);
+		ret = dmar_insert_dev_scope(info, (void *)(drhd + 1),
+				((void *)drhd) + drhd->header.length,
+				dmaru->segment,
+				dmaru->devices, dmaru->devices_cnt);
+		if (ret != 0)
+			break;
 	}
+	if (ret >= 0)
+		ret = dmar_iommu_notify_scope_dev(info);
+	if (ret < 0 && dmar_dev_scope_status == 0)
+		dmar_dev_scope_status = ret;
+
+	return ret;
 }
 
+static void  dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	for_each_drhd_unit(dmaru)
+		if (dmar_remove_dev_scope(info, dmaru->segment,
+			dmaru->devices, dmaru->devices_cnt))
+			break;
+	dmar_iommu_notify_scope_dev(info);
+}
+
+static int dmar_pci_bus_notifier(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct pci_dev *pdev = to_pci_dev(data);
+	struct dmar_pci_notify_info *info;
+
+	/* Only care about add/remove events for physical functions */
+	if (pdev->is_virtfn)
+		return NOTIFY_DONE;
+	if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_DEL_DEVICE)
+		return NOTIFY_DONE;
+
+	info = dmar_alloc_pci_notify_info(pdev, action);
+	if (!info)
+		return NOTIFY_DONE;
+
+	down_write(&dmar_global_lock);
+	if (action == BUS_NOTIFY_ADD_DEVICE)
+		dmar_pci_bus_add_dev(info);
+	else if (action == BUS_NOTIFY_DEL_DEVICE)
+		dmar_pci_bus_del_dev(info);
+	up_write(&dmar_global_lock);
+
+	dmar_free_pci_notify_info(info);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block dmar_pci_bus_nb = {
+	.notifier_call = dmar_pci_bus_notifier,
+	.priority = INT_MIN,
+};
+
 /**
  * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
  * structure which uniquely represent one DMA remapping hardware unit
@@ -196,9 +346,18 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header)
 	dmaru->reg_base_addr = drhd->address;
 	dmaru->segment = drhd->segment;
 	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
+	dmaru->devices = dmar_alloc_dev_scope((void *)(drhd + 1),
+					      ((void *)drhd) + drhd->header.length,
+					      &dmaru->devices_cnt);
+	if (dmaru->devices_cnt && dmaru->devices == NULL) {
+		kfree(dmaru);
+		return -ENOMEM;
+	}
 
 	ret = alloc_iommu(dmaru);
 	if (ret) {
+		dmar_free_dev_scope(&dmaru->devices,
+				    &dmaru->devices_cnt);
 		kfree(dmaru);
 		return ret;
 	}
@@ -215,19 +374,24 @@ static void dmar_free_drhd(struct dmar_drhd_unit *dmaru)
 	kfree(dmaru);
 }
 
-static int __init dmar_parse_dev(struct dmar_drhd_unit *dmaru)
+static int __init dmar_parse_one_andd(struct acpi_dmar_header *header)
 {
-	struct acpi_dmar_hardware_unit *drhd;
-
-	drhd = (struct acpi_dmar_hardware_unit *) dmaru->hdr;
-
-	if (dmaru->include_all)
-		return 0;
+	struct acpi_dmar_andd *andd = (void *)header;
+
+	/* Check for NUL termination within the designated length */
+	if (strnlen(andd->object_name, header->length - 8) == header->length - 8) {
+		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
+			   "Your BIOS is broken; ANDD object name is not NUL-terminated\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));
+		return -EINVAL;
+	}
+	pr_info("ANDD device: %x name: %s\n", andd->device_number,
+		andd->object_name);
 
-	return dmar_parse_dev_scope((void *)(drhd + 1),
-				    ((void *)drhd) + drhd->header.length,
-				    &dmaru->devices_cnt, &dmaru->devices,
-				    drhd->segment);
+	return 0;
 }
 
 #ifdef CONFIG_ACPI_NUMA
@@ -293,6 +457,10 @@ dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
 		       (unsigned long long)rhsa->base_address,
 		       rhsa->proximity_domain);
 		break;
+	case ACPI_DMAR_TYPE_ANDD:
+		/* We don't print this here because we need to sanity-check
+		   it first. So print it in dmar_parse_one_andd() instead. */
+		break;
 	}
 }
 
@@ -378,6 +546,9 @@ parse_dmar_table(void)
 			ret = dmar_parse_one_rhsa(entry_header);
 #endif
 			break;
+		case ACPI_DMAR_TYPE_ANDD:
+			ret = dmar_parse_one_andd(entry_header);
+			break;
 		default:
 			pr_warn("Unknown DMAR structure type %d\n",
 				entry_header->type);
@@ -394,14 +565,15 @@ parse_dmar_table(void)
 	return ret;
 }
 
-static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
-			  struct pci_dev *dev)
+static int dmar_pci_device_match(struct dmar_dev_scope devices[],
+				 int cnt, struct pci_dev *dev)
 {
 	int index;
+	struct device *tmp;
 
 	while (dev) {
-		for (index = 0; index < cnt; index++)
-			if (dev == devices[index])
+		for_each_active_dev_scope(devices, cnt, index, tmp)
+			if (dev_is_pci(tmp) && dev == to_pci_dev(tmp))
 				return 1;
 
 		/* Check our parent */
@@ -414,11 +586,12 @@ static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
 struct dmar_drhd_unit *
 dmar_find_matched_drhd_unit(struct pci_dev *dev)
 {
-	struct dmar_drhd_unit *dmaru = NULL;
+	struct dmar_drhd_unit *dmaru;
 	struct acpi_dmar_hardware_unit *drhd;
 
 	dev = pci_physfn(dev);
 
+	rcu_read_lock();
 	for_each_drhd_unit(dmaru) {
 		drhd = container_of(dmaru->hdr,
 				    struct acpi_dmar_hardware_unit,
@@ -426,44 +599,128 @@ dmar_find_matched_drhd_unit(struct pci_dev *dev)
 
 		if (dmaru->include_all &&
 		    drhd->segment == pci_domain_nr(dev->bus))
-			return dmaru;
+			goto out;
 
 		if (dmar_pci_device_match(dmaru->devices,
 					  dmaru->devices_cnt, dev))
-			return dmaru;
+			goto out;
 	}
+	dmaru = NULL;
+out:
+	rcu_read_unlock();
 
-	return NULL;
+	return dmaru;
 }
 
-int __init dmar_dev_scope_init(void)
+static void __init dmar_acpi_insert_dev_scope(u8 device_number,
+					      struct acpi_device *adev)
 {
-	static int dmar_dev_scope_initialized;
-	struct dmar_drhd_unit *drhd;
-	int ret = -ENODEV;
-
-	if (dmar_dev_scope_initialized)
-		return dmar_dev_scope_initialized;
+	struct dmar_drhd_unit *dmaru;
+	struct acpi_dmar_hardware_unit *drhd;
+	struct acpi_dmar_device_scope *scope;
+	struct device *tmp;
+	int i;
+	struct acpi_dmar_pci_path *path;
 
-	if (list_empty(&dmar_drhd_units))
-		goto fail;
+	for_each_drhd_unit(dmaru) {
+		drhd = container_of(dmaru->hdr,
+				    struct acpi_dmar_hardware_unit,
+				    header);
 
-	list_for_each_entry(drhd, &dmar_drhd_units, list) {
-		ret = dmar_parse_dev(drhd);
-		if (ret)
-			goto fail;
+		for (scope = (void *)(drhd + 1);
+		     (unsigned long)scope < ((unsigned long)drhd) + drhd->header.length;
+		     scope = ((void *)scope) + scope->length) {
+			if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_ACPI)
+				continue;
+			if (scope->enumeration_id != device_number)
+				continue;
+
+			path = (void *)(scope + 1);
+			pr_info("ACPI device \"%s\" under DMAR at %llx as %02x:%02x.%d\n",
+				dev_name(&adev->dev), dmaru->reg_base_addr,
+				scope->bus, path->device, path->function);
+			for_each_dev_scope(dmaru->devices, dmaru->devices_cnt, i, tmp)
+				if (tmp == NULL) {
+					dmaru->devices[i].bus = scope->bus;
+					dmaru->devices[i].devfn = PCI_DEVFN(path->device,
+									    path->function);
+					rcu_assign_pointer(dmaru->devices[i].dev,
+							   get_device(&adev->dev));
+					return;
+				}
+			BUG_ON(i >= dmaru->devices_cnt);
+		}
 	}
+	pr_warn("No IOMMU scope found for ANDD enumeration ID %d (%s)\n",
+		device_number, dev_name(&adev->dev));
+}
 
-	ret = dmar_parse_rmrr_atsr_dev();
-	if (ret)
-		goto fail;
+static int __init dmar_acpi_dev_scope_init(void)
+{
+	struct acpi_dmar_andd *andd;
+
+	if (dmar_tbl == NULL)
+		return -ENODEV;
 
-	dmar_dev_scope_initialized = 1;
+	for (andd = (void *)dmar_tbl + sizeof(struct acpi_table_dmar);
+	     ((unsigned long)andd) < ((unsigned long)dmar_tbl) + dmar_tbl->length;
+	     andd = ((void *)andd) + andd->header.length) {
+		if (andd->header.type == ACPI_DMAR_TYPE_ANDD) {
+			acpi_handle h;
+			struct acpi_device *adev;
+
+			if (!ACPI_SUCCESS(acpi_get_handle(ACPI_ROOT_OBJECT,
+							  andd->object_name,
+							  &h))) {
+				pr_err("Failed to find handle for ACPI object %s\n",
+				       andd->object_name);
+				continue;
+			}
+			acpi_bus_get_device(h, &adev);
+			if (!adev) {
+				pr_err("Failed to get device for ACPI object %s\n",
+				       andd->object_name);
+				continue;
+			}
+			dmar_acpi_insert_dev_scope(andd->device_number, adev);
+		}
+	}
 	return 0;
+}
 
-fail:
-	dmar_dev_scope_initialized = ret;
-	return ret;
+int __init dmar_dev_scope_init(void)
+{
+	struct pci_dev *dev = NULL;
+	struct dmar_pci_notify_info *info;
+
+	if (dmar_dev_scope_status != 1)
+		return dmar_dev_scope_status;
+
+	if (list_empty(&dmar_drhd_units)) {
+		dmar_dev_scope_status = -ENODEV;
+	} else {
+		dmar_dev_scope_status = 0;
+
+		dmar_acpi_dev_scope_init();
+
+		for_each_pci_dev(dev) {
+			if (dev->is_virtfn)
+				continue;
+
+			info = dmar_alloc_pci_notify_info(dev,
+					BUS_NOTIFY_ADD_DEVICE);
+			if (!info) {
+				return dmar_dev_scope_status;
+			} else {
+				dmar_pci_bus_add_dev(info);
+				dmar_free_pci_notify_info(info);
+			}
+		}
+
+		bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+	}
+
+	return dmar_dev_scope_status;
 }
 
 
@@ -557,6 +814,7 @@ int __init detect_intel_iommu(void)
 {
 	int ret;
 
+	down_write(&dmar_global_lock);
 	ret = dmar_table_detect();
 	if (ret)
 		ret = check_zero_address();
@@ -574,6 +832,7 @@ int __init detect_intel_iommu(void)
 	}
 	early_acpi_os_unmap_memory((void __iomem *)dmar_tbl, dmar_tbl_size);
 	dmar_tbl = NULL;
+	up_write(&dmar_global_lock);
 
 	return ret ? 1 : -ENODEV;
 }
@@ -696,6 +955,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	}
 	iommu->agaw = agaw;
 	iommu->msagaw = msagaw;
+	iommu->segment = drhd->segment;
 
 	iommu->node = -1;
 
@@ -1386,10 +1646,15 @@ static int __init dmar_free_unused_resources(void)
 	if (irq_remapping_enabled || intel_iommu_enabled)
 		return 0;
 
+	if (dmar_dev_scope_status != 1 && !list_empty(&dmar_drhd_units))
+		bus_unregister_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+
+	down_write(&dmar_global_lock);
 	list_for_each_entry_safe(dmaru, dmaru_n, &dmar_drhd_units, list) {
 		list_del(&dmaru->list);
 		dmar_free_drhd(dmaru);
 	}
+	up_write(&dmar_global_lock);
 
 	return 0;
 }

drivers/iommu/intel-iommu.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, Intel Corporation.
+ * Copyright © 2006-2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -10,15 +10,11 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
- *
- * Copyright (C) 2006-2008 Intel Corporation
- * Author: Ashok Raj <ashok.raj@intel.com>
- * Author: Shaohua Li <shaohua.li@intel.com>
- * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
- * Author: Fenghua Yu <fenghua.yu@intel.com>
+ * Authors: David Woodhouse <dwmw2@infradead.org>,
+ *          Ashok Raj <ashok.raj@intel.com>,
+ *          Shaohua Li <shaohua.li@intel.com>,
+ *          Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>,
+ *          Fenghua Yu <fenghua.yu@intel.com>
  */
 
 #include <linux/init.h>
@@ -33,6 +29,7 @@
 #include <linux/dmar.h>
 #include <linux/dma-mapping.h>
 #include <linux/mempool.h>
+#include <linux/memory.h>
 #include <linux/timer.h>
 #include <linux/iova.h>
 #include <linux/iommu.h>
@@ -372,14 +369,36 @@ struct dmar_domain {
 struct device_domain_info {
 	struct list_head link;	/* link to domain siblings */
 	struct list_head global; /* link to global list */
-	int segment;		/* PCI domain */
 	u8 bus;			/* PCI bus number */
 	u8 devfn;		/* PCI devfn number */
-	struct pci_dev *dev; /* it's NULL for PCIe-to-PCI bridge */
+	struct device *dev; /* it's NULL for PCIe-to-PCI bridge */
 	struct intel_iommu *iommu; /* IOMMU used by this device */
 	struct dmar_domain *domain; /* pointer to domain */
 };
 
+struct dmar_rmrr_unit {
+	struct list_head list;		/* list of rmrr units	*/
+	struct acpi_dmar_header *hdr;	/* ACPI header		*/
+	u64	base_address;		/* reserved base address*/
+	u64	end_address;		/* reserved end address */
+	struct dmar_dev_scope *devices;	/* target devices */
+	int	devices_cnt;		/* target device count */
+};
+
+struct dmar_atsr_unit {
+	struct list_head list;		/* list of ATSR units */
+	struct acpi_dmar_header *hdr;	/* ACPI header */
+	struct dmar_dev_scope *devices;	/* target devices */
+	int devices_cnt;		/* target device count */
+	u8 include_all:1;		/* include all ports */
+};
+
+static LIST_HEAD(dmar_atsr_units);
+static LIST_HEAD(dmar_rmrr_units);
+
+#define for_each_rmrr_units(rmrr) \
+	list_for_each_entry(rmrr, &dmar_rmrr_units, list)
+
 static void flush_unmaps_timeout(unsigned long data);
 
 static DEFINE_TIMER(unmap_timer,  flush_unmaps_timeout, 0, 0);
@@ -389,6 +408,7 @@ struct deferred_flush_tables {
 	int next;
 	struct iova *iova[HIGH_WATER_MARK];
 	struct dmar_domain *domain[HIGH_WATER_MARK];
+	struct page *freelist[HIGH_WATER_MARK];
 };
 
 static struct deferred_flush_tables *deferred_flush;
@@ -402,7 +422,12 @@ static LIST_HEAD(unmaps_to_do);
 static int timer_on;
 static long list_size;
 
+static void domain_exit(struct dmar_domain *domain);
 static void domain_remove_dev_info(struct dmar_domain *domain);
+static void domain_remove_one_dev_info(struct dmar_domain *domain,
+				       struct device *dev);
+static void iommu_detach_dependent_devices(struct intel_iommu *iommu,
+					   struct device *dev);
 
 #ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON
 int dmar_disabled = 0;
@@ -566,18 +591,31 @@ static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
 
 static void domain_update_iommu_coherency(struct dmar_domain *domain)
 {
-	int i;
-
-	i = find_first_bit(domain->iommu_bmp, g_num_of_iommus);
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	int i, found = 0;
 
-	domain->iommu_coherency = i < g_num_of_iommus ? 1 : 0;
+	domain->iommu_coherency = 1;
 
 	for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus) {
+		found = 1;
 		if (!ecap_coherent(g_iommus[i]->ecap)) {
 			domain->iommu_coherency = 0;
 			break;
 		}
 	}
+	if (found)
+		return;
+
+	/* No hardware attached; use lowest common denominator */
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!ecap_coherent(iommu->ecap)) {
+			domain->iommu_coherency = 0;
+			break;
+		}
+	}
+	rcu_read_unlock();
 }
 
 static void domain_update_iommu_snooping(struct dmar_domain *domain)
@@ -606,12 +644,15 @@ static void domain_update_iommu_superpage(struct dmar_domain *domain)
 	}
 
 	/* set iommu_superpage to the smallest common denominator */
+	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
 		mask &= cap_super_page_val(iommu->cap);
 		if (!mask) {
 			break;
 		}
 	}
+	rcu_read_unlock();
+
 	domain->iommu_superpage = fls(mask);
 }
 
@@ -623,32 +664,56 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
 	domain_update_iommu_superpage(domain);
 }
 
-static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
+static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
+	struct intel_iommu *iommu;
+	struct device *tmp;
+	struct pci_dev *ptmp, *pdev = NULL;
+	u16 segment;
 	int i;
 
-	for_each_active_drhd_unit(drhd) {
-		if (segment != drhd->segment)
+	if (dev_is_pci(dev)) {
+		pdev = to_pci_dev(dev);
+		segment = pci_domain_nr(pdev->bus);
+	} else if (ACPI_COMPANION(dev))
+		dev = &ACPI_COMPANION(dev)->dev;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (pdev && segment != drhd->segment)
 			continue;
 
-		for (i = 0; i < drhd->devices_cnt; i++) {
-			if (drhd->devices[i] &&
-			    drhd->devices[i]->bus->number == bus &&
-			    drhd->devices[i]->devfn == devfn)
-				return drhd->iommu;
-			if (drhd->devices[i] &&
-			    drhd->devices[i]->subordinate &&
-			    drhd->devices[i]->subordinate->number <= bus &&
-			    drhd->devices[i]->subordinate->busn_res.end >= bus)
-				return drhd->iommu;
+		for_each_active_dev_scope(drhd->devices,
+					  drhd->devices_cnt, i, tmp) {
+			if (tmp == dev) {
+				*bus = drhd->devices[i].bus;
+				*devfn = drhd->devices[i].devfn;
+				goto out;
+			}
+
+			if (!pdev || !dev_is_pci(tmp))
+				continue;
+
+			ptmp = to_pci_dev(tmp);
+			if (ptmp->subordinate &&
+			    ptmp->subordinate->number <= pdev->bus->number &&
+			    ptmp->subordinate->busn_res.end >= pdev->bus->number)
+				goto got_pdev;
 		}
 
-		if (drhd->include_all)
-			return drhd->iommu;
+		if (pdev && drhd->include_all) {
+		got_pdev:
+			*bus = pdev->bus->number;
+			*devfn = pdev->devfn;
+			goto out;
+		}
 	}
+	iommu = NULL;
+ out:
+	rcu_read_unlock();
 
-	return NULL;
+	return iommu;
 }
 
 static void domain_flush_cache(struct dmar_domain *domain,
@@ -748,7 +813,7 @@ out:
 }
 
 static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
-				      unsigned long pfn, int target_level)
+				      unsigned long pfn, int *target_level)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 	struct dma_pte *parent, *pte = NULL;
@@ -763,14 +828,14 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 
 	parent = domain->pgd;
 
-	while (level > 0) {
+	while (1) {
 		void *tmp_page;
 
 		offset = pfn_level_offset(pfn, level);
 		pte = &parent[offset];
-		if (!target_level && (dma_pte_superpage(pte) || !dma_pte_present(pte)))
+		if (!*target_level && (dma_pte_superpage(pte) || !dma_pte_present(pte)))
 			break;
-		if (level == target_level)
+		if (level == *target_level)
 			break;
 
 		if (!dma_pte_present(pte)) {
@@ -791,10 +856,16 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 				domain_flush_cache(domain, pte, sizeof(*pte));
 			}
 		}
+		if (level == 1)
+			break;
+
 		parent = phys_to_virt(dma_pte_addr(pte));
 		level--;
 	}
 
+	if (!*target_level)
+		*target_level = level;
+
 	return pte;
 }
 
@@ -832,7 +903,7 @@ static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
 }
 
 /* clear last level pte, a tlb flush should be followed */
-static int dma_pte_clear_range(struct dmar_domain *domain,
+static void dma_pte_clear_range(struct dmar_domain *domain,
 				unsigned long start_pfn,
 				unsigned long last_pfn)
 {
@@ -862,8 +933,6 @@ static int dma_pte_clear_range(struct dmar_domain *domain,
 				   (void *)pte - (void *)first_pte);
 
 	} while (start_pfn && start_pfn <= last_pfn);
-
-	return min_t(int, (large_page - 1) * 9, MAX_AGAW_PFN_WIDTH);
 }
 
 static void dma_pte_free_level(struct dmar_domain *domain, int level,
@@ -921,6 +990,123 @@ static void dma_pte_free_pagetable(struct dmar_domain *domain,
 	}
 }
 
+/* When a page at a given level is being unlinked from its parent, we don't
+   need to *modify* it at all. All we need to do is make a list of all the
+   pages which can be freed just as soon as we've flushed the IOTLB and we
+   know the hardware page-walk will no longer touch them.
+   The 'pte' argument is the *parent* PTE, pointing to the page that is to
+   be freed. */
+static struct page *dma_pte_list_pagetables(struct dmar_domain *domain,
+					    int level, struct dma_pte *pte,
+					    struct page *freelist)
+{
+	struct page *pg;
+
+	pg = pfn_to_page(dma_pte_addr(pte) >> PAGE_SHIFT);
+	pg->freelist = freelist;
+	freelist = pg;
+
+	if (level == 1)
+		return freelist;
+
+	for (pte = page_address(pg); !first_pte_in_page(pte); pte++) {
+		if (dma_pte_present(pte) && !dma_pte_superpage(pte))
+			freelist = dma_pte_list_pagetables(domain, level - 1,
+							   pte, freelist);
+	}
+
+	return freelist;
+}
+
+static struct page *dma_pte_clear_level(struct dmar_domain *domain, int level,
+					struct dma_pte *pte, unsigned long pfn,
+					unsigned long start_pfn,
+					unsigned long last_pfn,
+					struct page *freelist)
+{
+	struct dma_pte *first_pte = NULL, *last_pte = NULL;
+
+	pfn = max(start_pfn, pfn);
+	pte = &pte[pfn_level_offset(pfn, level)];
+
+	do {
+		unsigned long level_pfn;
+
+		if (!dma_pte_present(pte))
+			goto next;
+
+		level_pfn = pfn & level_mask(level);
+
+		/* If range covers entire pagetable, free it */
+		if (start_pfn <= level_pfn &&
+		    last_pfn >= level_pfn + level_size(level) - 1) {
+			/* These suborbinate page tables are going away entirely. Don't
+			   bother to clear them; we're just going to *free* them. */
+			if (level > 1 && !dma_pte_superpage(pte))
+				freelist = dma_pte_list_pagetables(domain, level - 1, pte, freelist);
+
+			dma_clear_pte(pte);
+			if (!first_pte)
+				first_pte = pte;
+			last_pte = pte;
+		} else if (level > 1) {
+			/* Recurse down into a level that isn't *entirely* obsolete */
+			freelist = dma_pte_clear_level(domain, level - 1,
+						       phys_to_virt(dma_pte_addr(pte)),
+						       level_pfn, start_pfn, last_pfn,
+						       freelist);
+		}
+next:
+		pfn += level_size(level);
+	} while (!first_pte_in_page(++pte) && pfn <= last_pfn);
+
+	if (first_pte)
+		domain_flush_cache(domain, first_pte,
+				   (void *)++last_pte - (void *)first_pte);
+
+	return freelist;
+}
+
+/* We can't just free the pages because the IOMMU may still be walking
+   the page tables, and may have cached the intermediate levels. The
+   pages can only be freed after the IOTLB flush has been done. */
+struct page *domain_unmap(struct dmar_domain *domain,
+			  unsigned long start_pfn,
+			  unsigned long last_pfn)
+{
+	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
+	struct page *freelist = NULL;
+
+	BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
+	BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width);
+	BUG_ON(start_pfn > last_pfn);
+
+	/* we don't need lock here; nobody else touches the iova range */
+	freelist = dma_pte_clear_level(domain, agaw_to_level(domain->agaw),
+				       domain->pgd, 0, start_pfn, last_pfn, NULL);
+
+	/* free pgd */
+	if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
+		struct page *pgd_page = virt_to_page(domain->pgd);
+		pgd_page->freelist = freelist;
+		freelist = pgd_page;
+
+		domain->pgd = NULL;
+	}
+
+	return freelist;
+}
+
+void dma_free_pagelist(struct page *freelist)
+{
+	struct page *pg;
+
+	while ((pg = freelist)) {
+		freelist = pg->freelist;
+		free_pgtable_page(page_address(pg));
+	}
+}
+
 /* iommu handling */
 static int iommu_alloc_root_entry(struct intel_iommu *iommu)
 {
@@ -1030,7 +1216,7 @@ static void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
 		break;
 	case DMA_TLB_PSI_FLUSH:
 		val = DMA_TLB_PSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did);
-		/* Note: always flush non-leaf currently */
+		/* IH bit is passed in as part of address */
 		val_iva = size_order | addr;
 		break;
 	default:
@@ -1069,13 +1255,14 @@ static void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
 			(unsigned long long)DMA_TLB_IAIG(val));
 }
 
-static struct device_domain_info *iommu_support_dev_iotlb(
-	struct dmar_domain *domain, int segment, u8 bus, u8 devfn)
+static struct device_domain_info *
+iommu_support_dev_iotlb (struct dmar_domain *domain, struct intel_iommu *iommu,
+			 u8 bus, u8 devfn)
 {
 	int found = 0;
 	unsigned long flags;
 	struct device_domain_info *info;
-	struct intel_iommu *iommu = device_to_iommu(segment, bus, devfn);
+	struct pci_dev *pdev;
 
 	if (!ecap_dev_iotlb_support(iommu->ecap))
 		return NULL;
@@ -1091,34 +1278,35 @@ static struct device_domain_info *iommu_support_dev_iotlb(
 		}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
-	if (!found || !info->dev)
+	if (!found || !info->dev || !dev_is_pci(info->dev))
 		return NULL;
 
-	if (!pci_find_ext_capability(info->dev, PCI_EXT_CAP_ID_ATS))
-		return NULL;
+	pdev = to_pci_dev(info->dev);
 
-	if (!dmar_find_matched_atsr_unit(info->dev))
+	if (!pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ATS))
 		return NULL;
 
-	info->iommu = iommu;
+	if (!dmar_find_matched_atsr_unit(pdev))
+		return NULL;
 
 	return info;
 }
 
 static void iommu_enable_dev_iotlb(struct device_domain_info *info)
 {
-	if (!info)
+	if (!info || !dev_is_pci(info->dev))
 		return;
 
-	pci_enable_ats(info->dev, VTD_PAGE_SHIFT);
+	pci_enable_ats(to_pci_dev(info->dev), VTD_PAGE_SHIFT);
 }
 
 static void iommu_disable_dev_iotlb(struct device_domain_info *info)
 {
-	if (!info->dev || !pci_ats_enabled(info->dev))
+	if (!info->dev || !dev_is_pci(info->dev) ||
+	    !pci_ats_enabled(to_pci_dev(info->dev)))
 		return;
 
-	pci_disable_ats(info->dev);
+	pci_disable_ats(to_pci_dev(info->dev));
 }
 
 static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
@@ -1130,24 +1318,31 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 
 	spin_lock_irqsave(&device_domain_lock, flags);
 	list_for_each_entry(info, &domain->devices, link) {
-		if (!info->dev || !pci_ats_enabled(info->dev))
+		struct pci_dev *pdev;
+		if (!info->dev || !dev_is_pci(info->dev))
+			continue;
+
+		pdev = to_pci_dev(info->dev);
+		if (!pci_ats_enabled(pdev))
 			continue;
 
 		sid = info->bus << 8 | info->devfn;
-		qdep = pci_ats_queue_depth(info->dev);
+		qdep = pci_ats_queue_depth(pdev);
 		qi_flush_dev_iotlb(info->iommu, sid, qdep, addr, mask);
 	}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
 static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
-				  unsigned long pfn, unsigned int pages, int map)
+				  unsigned long pfn, unsigned int pages, int ih, int map)
 {
 	unsigned int mask = ilog2(__roundup_pow_of_two(pages));
 	uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT;
 
 	BUG_ON(pages == 0);
 
+	if (ih)
+		ih = 1 << 6;
 	/*
 	 * Fallback to domain selective flush if no PSI support or the size is
 	 * too big.
@@ -1158,7 +1353,7 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
 		iommu->flush.flush_iotlb(iommu, did, 0, 0,
 						DMA_TLB_DSI_FLUSH);
 	else
-		iommu->flush.flush_iotlb(iommu, did, addr, mask,
+		iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
 						DMA_TLB_PSI_FLUSH);
 
 	/*
@@ -1261,10 +1456,6 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 	return 0;
 }
 
-
-static void domain_exit(struct dmar_domain *domain);
-static void vm_domain_exit(struct dmar_domain *domain);
-
 static void free_dmar_iommu(struct intel_iommu *iommu)
 {
 	struct dmar_domain *domain;
@@ -1273,18 +1464,21 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 
 	if ((iommu->domains) && (iommu->domain_ids)) {
 		for_each_set_bit(i, iommu->domain_ids, cap_ndoms(iommu->cap)) {
+			/*
+			 * Domain id 0 is reserved for invalid translation
+			 * if hardware supports caching mode.
+			 */
+			if (cap_caching_mode(iommu->cap) && i == 0)
+				continue;
+
 			domain = iommu->domains[i];
 			clear_bit(i, iommu->domain_ids);
 
 			spin_lock_irqsave(&domain->iommu_lock, flags);
 			count = --domain->iommu_count;
 			spin_unlock_irqrestore(&domain->iommu_lock, flags);
-			if (count == 0) {
-				if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE)
-					vm_domain_exit(domain);
-				else
-					domain_exit(domain);
-			}
+			if (count == 0)
+				domain_exit(domain);
 		}
 	}
 
@@ -1298,21 +1492,14 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 
 	g_iommus[iommu->seq_id] = NULL;
 
-	/* if all iommus are freed, free g_iommus */
-	for (i = 0; i < g_num_of_iommus; i++) {
-		if (g_iommus[i])
-			break;
-	}
-
-	if (i == g_num_of_iommus)
-		kfree(g_iommus);
-
 	/* free context mapping */
 	free_context_table(iommu);
 }
 
-static struct dmar_domain *alloc_domain(void)
+static struct dmar_domain *alloc_domain(bool vm)
 {
+	/* domain id for virtual machine, it won't be set in context */
+	static atomic_t vm_domid = ATOMIC_INIT(0);
 	struct dmar_domain *domain;
 
 	domain = alloc_domain_mem();
@@ -1320,8 +1507,15 @@ static struct dmar_domain *alloc_domain(void)
 		return NULL;
 
 	domain->nid = -1;
+	domain->iommu_count = 0;
 	memset(domain->iommu_bmp, 0, sizeof(domain->iommu_bmp));
 	domain->flags = 0;
+	spin_lock_init(&domain->iommu_lock);
+	INIT_LIST_HEAD(&domain->devices);
+	if (vm) {
+		domain->id = atomic_inc_return(&vm_domid);
+		domain->flags = DOMAIN_FLAG_VIRTUAL_MACHINE;
+	}
 
 	return domain;
 }
@@ -1345,6 +1539,7 @@ static int iommu_attach_domain(struct dmar_domain *domain,
 	}
 
 	domain->id = num;
+	domain->iommu_count++;
 	set_bit(num, iommu->domain_ids);
 	set_bit(iommu->seq_id, domain->iommu_bmp);
 	iommu->domains[num] = domain;
@@ -1358,22 +1553,16 @@ static void iommu_detach_domain(struct dmar_domain *domain,
 {
 	unsigned long flags;
 	int num, ndomains;
-	int found = 0;
 
 	spin_lock_irqsave(&iommu->lock, flags);
 	ndomains = cap_ndoms(iommu->cap);
 	for_each_set_bit(num, iommu->domain_ids, ndomains) {
 		if (iommu->domains[num] == domain) {
-			found = 1;
+			clear_bit(num, iommu->domain_ids);
+			iommu->domains[num] = NULL;
 			break;
 		}
 	}
-
-	if (found) {
-		clear_bit(num, iommu->domain_ids);
-		clear_bit(iommu->seq_id, domain->iommu_bmp);
-		iommu->domains[num] = NULL;
-	}
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
@@ -1445,8 +1634,6 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	unsigned long sagaw;
 
 	init_iova_domain(&domain->iovad, DMA_32BIT_PFN);
-	spin_lock_init(&domain->iommu_lock);
-
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
@@ -1465,7 +1652,6 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 			return -ENODEV;
 	}
 	domain->agaw = agaw;
-	INIT_LIST_HEAD(&domain->devices);
 
 	if (ecap_coherent(iommu->ecap))
 		domain->iommu_coherency = 1;
@@ -1477,8 +1663,11 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	else
 		domain->iommu_snooping = 0;
 
-	domain->iommu_superpage = fls(cap_super_page_val(iommu->cap));
-	domain->iommu_count = 1;
+	if (intel_iommu_superpage)
+		domain->iommu_superpage = fls(cap_super_page_val(iommu->cap));
+	else
+		domain->iommu_superpage = 0;
+
 	domain->nid = iommu->node;
 
 	/* always allocate the top pgd */
@@ -1493,6 +1682,7 @@ static void domain_exit(struct dmar_domain *domain)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
+	struct page *freelist = NULL;
 
 	/* Domain 0 is reserved, so dont process it */
 	if (!domain)
@@ -1502,29 +1692,33 @@ static void domain_exit(struct dmar_domain *domain)
 	if (!intel_iommu_strict)
 		flush_unmaps_timeout(0);
 
+	/* remove associated devices */
 	domain_remove_dev_info(domain);
+
 	/* destroy iovas */
 	put_iova_domain(&domain->iovad);
 
-	/* clear ptes */
-	dma_pte_clear_range(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
-
-	/* free page tables */
-	dma_pte_free_pagetable(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
+	freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
 
+	/* clear attached or cached domains */
+	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd)
-		if (test_bit(iommu->seq_id, domain->iommu_bmp))
+		if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE ||
+		    test_bit(iommu->seq_id, domain->iommu_bmp))
 			iommu_detach_domain(domain, iommu);
+	rcu_read_unlock();
+
+	dma_free_pagelist(freelist);
 
 	free_domain_mem(domain);
 }
 
-static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
-				 u8 bus, u8 devfn, int translation)
+static int domain_context_mapping_one(struct dmar_domain *domain,
+				      struct intel_iommu *iommu,
+				      u8 bus, u8 devfn, int translation)
 {
 	struct context_entry *context;
 	unsigned long flags;
-	struct intel_iommu *iommu;
 	struct dma_pte *pgd;
 	unsigned long num;
 	unsigned long ndomains;
@@ -1539,10 +1733,6 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
 	BUG_ON(translation != CONTEXT_TT_PASS_THROUGH &&
 	       translation != CONTEXT_TT_MULTI_LEVEL);
 
-	iommu = device_to_iommu(segment, bus, devfn);
-	if (!iommu)
-		return -ENODEV;
-
 	context = device_to_context_entry(iommu, bus, devfn);
 	if (!context)
 		return -ENOMEM;
@@ -1600,7 +1790,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
 	context_set_domain_id(context, id);
 
 	if (translation != CONTEXT_TT_PASS_THROUGH) {
-		info = iommu_support_dev_iotlb(domain, segment, bus, devfn);
+		info = iommu_support_dev_iotlb(domain, iommu, bus, devfn);
 		translation = info ? CONTEXT_TT_DEV_IOTLB :
 				     CONTEXT_TT_MULTI_LEVEL;
 	}
@@ -1650,27 +1840,32 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
 }
 
 static int
-domain_context_mapping(struct dmar_domain *domain, struct pci_dev *pdev,
-			int translation)
+domain_context_mapping(struct dmar_domain *domain, struct device *dev,
+		       int translation)
 {
 	int ret;
-	struct pci_dev *tmp, *parent;
+	struct pci_dev *pdev, *tmp, *parent;
+	struct intel_iommu *iommu;
+	u8 bus, devfn;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
 
-	ret = domain_context_mapping_one(domain, pci_domain_nr(pdev->bus),
-					 pdev->bus->number, pdev->devfn,
+	ret = domain_context_mapping_one(domain, iommu, bus, devfn,
 					 translation);
-	if (ret)
+	if (ret || !dev_is_pci(dev))
 		return ret;
 
 	/* dependent device mapping */
+	pdev = to_pci_dev(dev);
 	tmp = pci_find_upstream_pcie_bridge(pdev);
 	if (!tmp)
 		return 0;
 	/* Secondary interface's bus number and devfn 0 */
 	parent = pdev->bus->self;
 	while (parent != tmp) {
-		ret = domain_context_mapping_one(domain,
-						 pci_domain_nr(parent->bus),
+		ret = domain_context_mapping_one(domain, iommu,
 						 parent->bus->number,
 						 parent->devfn, translation);
 		if (ret)
@@ -1678,33 +1873,33 @@ domain_context_mapping(struct dmar_domain *domain, struct pci_dev *pdev,
 		parent = parent->bus->self;
 	}
 	if (pci_is_pcie(tmp)) /* this is a PCIe-to-PCI bridge */
-		return domain_context_mapping_one(domain,
-					pci_domain_nr(tmp->subordinate),
+		return domain_context_mapping_one(domain, iommu,
 					tmp->subordinate->number, 0,
 					translation);
 	else /* this is a legacy PCI bridge */
-		return domain_context_mapping_one(domain,
-						  pci_domain_nr(tmp->bus),
+		return domain_context_mapping_one(domain, iommu,
 						  tmp->bus->number,
 						  tmp->devfn,
 						  translation);
 }
 
-static int domain_context_mapped(struct pci_dev *pdev)
+static int domain_context_mapped(struct device *dev)
 {
 	int ret;
-	struct pci_dev *tmp, *parent;
+	struct pci_dev *pdev, *tmp, *parent;
 	struct intel_iommu *iommu;
+	u8 bus, devfn;
 
-	iommu = device_to_iommu(pci_domain_nr(pdev->bus), pdev->bus->number,
-				pdev->devfn);
+	iommu = device_to_iommu(dev, &bus, &devfn);
 	if (!iommu)
 		return -ENODEV;
 
-	ret = device_context_mapped(iommu, pdev->bus->number, pdev->devfn);
-	if (!ret)
+	ret = device_context_mapped(iommu, bus, devfn);
+	if (!ret || !dev_is_pci(dev))
 		return ret;
+
 	/* dependent device mapping */
+	pdev = to_pci_dev(dev);
 	tmp = pci_find_upstream_pcie_bridge(pdev);
 	if (!tmp)
 		return ret;
@@ -1800,7 +1995,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		if (!pte) {
 			largepage_lvl = hardware_largepage_caps(domain, iov_pfn, phys_pfn, sg_res);
 
-			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, largepage_lvl);
+			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl);
 			if (!pte)
 				return -ENOMEM;
 			/* It is large page*/
@@ -1899,14 +2094,13 @@ static inline void unlink_domain_info(struct device_domain_info *info)
 	list_del(&info->link);
 	list_del(&info->global);
 	if (info->dev)
-		info->dev->dev.archdata.iommu = NULL;
+		info->dev->archdata.iommu = NULL;
 }
 
 static void domain_remove_dev_info(struct dmar_domain *domain)
 {
 	struct device_domain_info *info;
-	unsigned long flags;
-	struct intel_iommu *iommu;
+	unsigned long flags, flags2;
 
 	spin_lock_irqsave(&device_domain_lock, flags);
 	while (!list_empty(&domain->devices)) {
@@ -1916,10 +2110,23 @@ static void domain_remove_dev_info(struct dmar_domain *domain)
 		spin_unlock_irqrestore(&device_domain_lock, flags);
 
 		iommu_disable_dev_iotlb(info);
-		iommu = device_to_iommu(info->segment, info->bus, info->devfn);
-		iommu_detach_dev(iommu, info->bus, info->devfn);
-		free_devinfo_mem(info);
+		iommu_detach_dev(info->iommu, info->bus, info->devfn);
+
+		if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) {
+			iommu_detach_dependent_devices(info->iommu, info->dev);
+			/* clear this iommu in iommu_bmp, update iommu count
+			 * and capabilities
+			 */
+			spin_lock_irqsave(&domain->iommu_lock, flags2);
+			if (test_and_clear_bit(info->iommu->seq_id,
+					       domain->iommu_bmp)) {
+				domain->iommu_count--;
+				domain_update_iommu_cap(domain);
+			}
+			spin_unlock_irqrestore(&domain->iommu_lock, flags2);
+		}
 
+		free_devinfo_mem(info);
 		spin_lock_irqsave(&device_domain_lock, flags);
 	}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
@@ -1927,155 +2134,151 @@ static void domain_remove_dev_info(struct dmar_domain *domain)
 
 /*
  * find_domain
- * Note: we use struct pci_dev->dev.archdata.iommu stores the info
+ * Note: we use struct device->archdata.iommu stores the info
  */
-static struct dmar_domain *
-find_domain(struct pci_dev *pdev)
+static struct dmar_domain *find_domain(struct device *dev)
 {
 	struct device_domain_info *info;
 
 	/* No lock here, assumes no domain exit in normal case */
-	info = pdev->dev.archdata.iommu;
+	info = dev->archdata.iommu;
 	if (info)
 		return info->domain;
 	return NULL;
 }
 
+static inline struct device_domain_info *
+dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
+{
+	struct device_domain_info *info;
+
+	list_for_each_entry(info, &device_domain_list, global)
+		if (info->iommu->segment == segment && info->bus == bus &&
+		    info->devfn == devfn)
+			return info;
+
+	return NULL;
+}
+
+static struct dmar_domain *dmar_insert_dev_info(struct intel_iommu *iommu,
+						int bus, int devfn,
+						struct device *dev,
+						struct dmar_domain *domain)
+{
+	struct dmar_domain *found = NULL;
+	struct device_domain_info *info;
+	unsigned long flags;
+
+	info = alloc_devinfo_mem();
+	if (!info)
+		return NULL;
+
+	info->bus = bus;
+	info->devfn = devfn;
+	info->dev = dev;
+	info->domain = domain;
+	info->iommu = iommu;
+	if (!dev)
+		domain->flags |= DOMAIN_FLAG_P2P_MULTIPLE_DEVICES;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	if (dev)
+		found = find_domain(dev);
+	else {
+		struct device_domain_info *info2;
+		info2 = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn);
+		if (info2)
+			found = info2->domain;
+	}
+	if (found) {
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+		free_devinfo_mem(info);
+		/* Caller must free the original domain */
+		return found;
+	}
+
+	list_add(&info->link, &domain->devices);
+	list_add(&info->global, &device_domain_list);
+	if (dev)
+		dev->archdata.iommu = info;
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	return domain;
+}
+
 /* domain is initialized */
-static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw)
+static struct dmar_domain *get_domain_for_dev(struct device *dev, int gaw)
 {
-	struct dmar_domain *domain, *found = NULL;
-	struct intel_iommu *iommu;
-	struct dmar_drhd_unit *drhd;
-	struct device_domain_info *info, *tmp;
-	struct pci_dev *dev_tmp;
+	struct dmar_domain *domain, *free = NULL;
+	struct intel_iommu *iommu = NULL;
+	struct device_domain_info *info;
+	struct pci_dev *dev_tmp = NULL;
 	unsigned long flags;
-	int bus = 0, devfn = 0;
-	int segment;
-	int ret;
+	u8 bus, devfn, bridge_bus, bridge_devfn;
 
-	domain = find_domain(pdev);
+	domain = find_domain(dev);
 	if (domain)
 		return domain;
 
-	segment = pci_domain_nr(pdev->bus);
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+		u16 segment;
 
-	dev_tmp = pci_find_upstream_pcie_bridge(pdev);
-	if (dev_tmp) {
-		if (pci_is_pcie(dev_tmp)) {
-			bus = dev_tmp->subordinate->number;
-			devfn = 0;
-		} else {
-			bus = dev_tmp->bus->number;
-			devfn = dev_tmp->devfn;
-		}
-		spin_lock_irqsave(&device_domain_lock, flags);
-		list_for_each_entry(info, &device_domain_list, global) {
-			if (info->segment == segment &&
-			    info->bus == bus && info->devfn == devfn) {
-				found = info->domain;
-				break;
+		segment = pci_domain_nr(pdev->bus);
+		dev_tmp = pci_find_upstream_pcie_bridge(pdev);
+		if (dev_tmp) {
+			if (pci_is_pcie(dev_tmp)) {
+				bridge_bus = dev_tmp->subordinate->number;
+				bridge_devfn = 0;
+			} else {
+				bridge_bus = dev_tmp->bus->number;
+				bridge_devfn = dev_tmp->devfn;
 			}
-		}
-		spin_unlock_irqrestore(&device_domain_lock, flags);
-		/* pcie-pci bridge already has a domain, uses it */
-		if (found) {
-			domain = found;
-			goto found_domain;
+			spin_lock_irqsave(&device_domain_lock, flags);
+			info = dmar_search_domain_by_dev_info(segment, bus, devfn);
+			if (info) {
+				iommu = info->iommu;
+				domain = info->domain;
+			}
+			spin_unlock_irqrestore(&device_domain_lock, flags);
+			/* pcie-pci bridge already has a domain, uses it */
+			if (info)
+				goto found_domain;
 		}
 	}
 
-	domain = alloc_domain();
-	if (!domain)
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
 		goto error;
 
-	/* Allocate new domain for the device */
-	drhd = dmar_find_matched_drhd_unit(pdev);
-	if (!drhd) {
-		printk(KERN_ERR "IOMMU: can't find DMAR for device %s\n",
-			pci_name(pdev));
-		free_domain_mem(domain);
-		return NULL;
-	}
-	iommu = drhd->iommu;
-
-	ret = iommu_attach_domain(domain, iommu);
-	if (ret) {
+	/* Allocate and initialize new domain for the device */
+	domain = alloc_domain(false);
+	if (!domain)
+		goto error;
+	if (iommu_attach_domain(domain, iommu)) {
 		free_domain_mem(domain);
+		domain = NULL;
 		goto error;
 	}
-
-	if (domain_init(domain, gaw)) {
-		domain_exit(domain);
+	free = domain;
+	if (domain_init(domain, gaw))
 		goto error;
-	}
 
 	/* register pcie-to-pci device */
 	if (dev_tmp) {
-		info = alloc_devinfo_mem();
-		if (!info) {
-			domain_exit(domain);
+		domain = dmar_insert_dev_info(iommu, bridge_bus, bridge_devfn,
+					      NULL, domain);
+		if (!domain)
 			goto error;
-		}
-		info->segment = segment;
-		info->bus = bus;
-		info->devfn = devfn;
-		info->dev = NULL;
-		info->domain = domain;
-		/* This domain is shared by devices under p2p bridge */
-		domain->flags |= DOMAIN_FLAG_P2P_MULTIPLE_DEVICES;
-
-		/* pcie-to-pci bridge already has a domain, uses it */
-		found = NULL;
-		spin_lock_irqsave(&device_domain_lock, flags);
-		list_for_each_entry(tmp, &device_domain_list, global) {
-			if (tmp->segment == segment &&
-			    tmp->bus == bus && tmp->devfn == devfn) {
-				found = tmp->domain;
-				break;
-			}
-		}
-		if (found) {
-			spin_unlock_irqrestore(&device_domain_lock, flags);
-			free_devinfo_mem(info);
-			domain_exit(domain);
-			domain = found;
-		} else {
-			list_add(&info->link, &domain->devices);
-			list_add(&info->global, &device_domain_list);
-			spin_unlock_irqrestore(&device_domain_lock, flags);
-		}
 	}
 
 found_domain:
-	info = alloc_devinfo_mem();
-	if (!info)
-		goto error;
-	info->segment = segment;
-	info->bus = pdev->bus->number;
-	info->devfn = pdev->devfn;
-	info->dev = pdev;
-	info->domain = domain;
-	spin_lock_irqsave(&device_domain_lock, flags);
-	/* somebody is fast */
-	found = find_domain(pdev);
-	if (found != NULL) {
-		spin_unlock_irqrestore(&device_domain_lock, flags);
-		if (found != domain) {
-			domain_exit(domain);
-			domain = found;
-		}
-		free_devinfo_mem(info);
-		return domain;
-	}
-	list_add(&info->link, &domain->devices);
-	list_add(&info->global, &device_domain_list);
-	pdev->dev.archdata.iommu = info;
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-	return domain;
+	domain = dmar_insert_dev_info(iommu, bus, devfn, dev, domain);
 error:
-	/* recheck it here, maybe others set it */
-	return find_domain(pdev);
+	if (free != domain)
+		domain_exit(free);
+
+	return domain;
 }
 
 static int iommu_identity_mapping;
@@ -2109,14 +2312,14 @@ static int iommu_domain_identity_map(struct dmar_domain *domain,
 				  DMA_PTE_READ|DMA_PTE_WRITE);
 }
 
-static int iommu_prepare_identity_map(struct pci_dev *pdev,
+static int iommu_prepare_identity_map(struct device *dev,
 				      unsigned long long start,
 				      unsigned long long end)
 {
 	struct dmar_domain *domain;
 	int ret;
 
-	domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
+	domain = get_domain_for_dev(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
 	if (!domain)
 		return -ENOMEM;
 
@@ -2126,13 +2329,13 @@ static int iommu_prepare_identity_map(struct pci_dev *pdev,
 	   up to start with in si_domain */
 	if (domain == si_domain && hw_pass_through) {
 		printk("Ignoring identity map for HW passthrough device %s [0x%Lx - 0x%Lx]\n",
-		       pci_name(pdev), start, end);
+		       dev_name(dev), start, end);
 		return 0;
 	}
 
 	printk(KERN_INFO
 	       "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n",
-	       pci_name(pdev), start, end);
+	       dev_name(dev), start, end);
 	
 	if (end < start) {
 		WARN(1, "Your BIOS is broken; RMRR ends before it starts!\n"
@@ -2160,7 +2363,7 @@ static int iommu_prepare_identity_map(struct pci_dev *pdev,
 		goto error;
 
 	/* context entry init */
-	ret = domain_context_mapping(domain, pdev, CONTEXT_TT_MULTI_LEVEL);
+	ret = domain_context_mapping(domain, dev, CONTEXT_TT_MULTI_LEVEL);
 	if (ret)
 		goto error;
 
@@ -2172,12 +2375,12 @@ static int iommu_prepare_identity_map(struct pci_dev *pdev,
 }
 
 static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr,
-	struct pci_dev *pdev)
+					 struct device *dev)
 {
-	if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
+	if (dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
 		return 0;
-	return iommu_prepare_identity_map(pdev, rmrr->base_address,
-		rmrr->end_address);
+	return iommu_prepare_identity_map(dev, rmrr->base_address,
+					  rmrr->end_address);
 }
 
 #ifdef CONFIG_INTEL_IOMMU_FLOPPY_WA
@@ -2191,7 +2394,7 @@ static inline void iommu_prepare_isa(void)
 		return;
 
 	printk(KERN_INFO "IOMMU: Prepare 0-16MiB unity mapping for LPC\n");
-	ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024 - 1);
+	ret = iommu_prepare_identity_map(&pdev->dev, 0, 16*1024*1024 - 1);
 
 	if (ret)
 		printk(KERN_ERR "IOMMU: Failed to create 0-16MiB identity map; "
@@ -2213,10 +2416,12 @@ static int __init si_domain_init(int hw)
 	struct intel_iommu *iommu;
 	int nid, ret = 0;
 
-	si_domain = alloc_domain();
+	si_domain = alloc_domain(false);
 	if (!si_domain)
 		return -EFAULT;
 
+	si_domain->flags = DOMAIN_FLAG_STATIC_IDENTITY;
+
 	for_each_active_iommu(iommu, drhd) {
 		ret = iommu_attach_domain(si_domain, iommu);
 		if (ret) {
@@ -2230,7 +2435,6 @@ static int __init si_domain_init(int hw)
 		return -EFAULT;
 	}
 
-	si_domain->flags = DOMAIN_FLAG_STATIC_IDENTITY;
 	pr_debug("IOMMU: identity mapping domain is domain %d\n",
 		 si_domain->id);
 
@@ -2252,16 +2456,14 @@ static int __init si_domain_init(int hw)
 	return 0;
 }
 
-static void domain_remove_one_dev_info(struct dmar_domain *domain,
-					  struct pci_dev *pdev);
-static int identity_mapping(struct pci_dev *pdev)
+static int identity_mapping(struct device *dev)
 {
 	struct device_domain_info *info;
 
 	if (likely(!iommu_identity_mapping))
 		return 0;
 
-	info = pdev->dev.archdata.iommu;
+	info = dev->archdata.iommu;
 	if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
 		return (info->domain == si_domain);
 
@@ -2269,111 +2471,112 @@ static int identity_mapping(struct pci_dev *pdev)
 }
 
 static int domain_add_dev_info(struct dmar_domain *domain,
-			       struct pci_dev *pdev,
-			       int translation)
+			       struct device *dev, int translation)
 {
-	struct device_domain_info *info;
-	unsigned long flags;
+	struct dmar_domain *ndomain;
+	struct intel_iommu *iommu;
+	u8 bus, devfn;
 	int ret;
 
-	info = alloc_devinfo_mem();
-	if (!info)
-		return -ENOMEM;
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
 
-	info->segment = pci_domain_nr(pdev->bus);
-	info->bus = pdev->bus->number;
-	info->devfn = pdev->devfn;
-	info->dev = pdev;
-	info->domain = domain;
+	ndomain = dmar_insert_dev_info(iommu, bus, devfn, dev, domain);
+	if (ndomain != domain)
+		return -EBUSY;
 
-	spin_lock_irqsave(&device_domain_lock, flags);
-	list_add(&info->link, &domain->devices);
-	list_add(&info->global, &device_domain_list);
-	pdev->dev.archdata.iommu = info;
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-
-	ret = domain_context_mapping(domain, pdev, translation);
+	ret = domain_context_mapping(domain, dev, translation);
 	if (ret) {
-		spin_lock_irqsave(&device_domain_lock, flags);
-		unlink_domain_info(info);
-		spin_unlock_irqrestore(&device_domain_lock, flags);
-		free_devinfo_mem(info);
+		domain_remove_one_dev_info(domain, dev);
 		return ret;
 	}
 
 	return 0;
 }
 
-static bool device_has_rmrr(struct pci_dev *dev)
+static bool device_has_rmrr(struct device *dev)
 {
 	struct dmar_rmrr_unit *rmrr;
+	struct device *tmp;
 	int i;
 
+	rcu_read_lock();
 	for_each_rmrr_units(rmrr) {
-		for (i = 0; i < rmrr->devices_cnt; i++) {
-			/*
-			 * Return TRUE if this RMRR contains the device that
-			 * is passed in.
-			 */
-			if (rmrr->devices[i] == dev)
+		/*
+		 * Return TRUE if this RMRR contains the device that
+		 * is passed in.
+		 */
+		for_each_active_dev_scope(rmrr->devices,
+					  rmrr->devices_cnt, i, tmp)
+			if (tmp == dev) {
+				rcu_read_unlock();
 				return true;
-		}
+			}
 	}
+	rcu_read_unlock();
 	return false;
 }
 
-static int iommu_should_identity_map(struct pci_dev *pdev, int startup)
+static int iommu_should_identity_map(struct device *dev, int startup)
 {
 
-	/*
-	 * We want to prevent any device associated with an RMRR from
-	 * getting placed into the SI Domain. This is done because
-	 * problems exist when devices are moved in and out of domains
-	 * and their respective RMRR info is lost. We exempt USB devices
-	 * from this process due to their usage of RMRRs that are known
-	 * to not be needed after BIOS hand-off to OS.
-	 */
-	if (device_has_rmrr(pdev) &&
-	    (pdev->class >> 8) != PCI_CLASS_SERIAL_USB)
-		return 0;
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
 
-	if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev))
-		return 1;
+		/*
+		 * We want to prevent any device associated with an RMRR from
+		 * getting placed into the SI Domain. This is done because
+		 * problems exist when devices are moved in and out of domains
+		 * and their respective RMRR info is lost. We exempt USB devices
+		 * from this process due to their usage of RMRRs that are known
+		 * to not be needed after BIOS hand-off to OS.
+		 */
+		if (device_has_rmrr(dev) &&
+		    (pdev->class >> 8) != PCI_CLASS_SERIAL_USB)
+			return 0;
 
-	if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev))
-		return 1;
+		if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev))
+			return 1;
 
-	if (!(iommu_identity_mapping & IDENTMAP_ALL))
-		return 0;
+		if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev))
+			return 1;
 
-	/*
-	 * We want to start off with all devices in the 1:1 domain, and
-	 * take them out later if we find they can't access all of memory.
-	 *
-	 * However, we can't do this for PCI devices behind bridges,
-	 * because all PCI devices behind the same bridge will end up
-	 * with the same source-id on their transactions.
-	 *
-	 * Practically speaking, we can't change things around for these
-	 * devices at run-time, because we can't be sure there'll be no
-	 * DMA transactions in flight for any of their siblings.
-	 * 
-	 * So PCI devices (unless they're on the root bus) as well as
-	 * their parent PCI-PCI or PCIe-PCI bridges must be left _out_ of
-	 * the 1:1 domain, just in _case_ one of their siblings turns out
-	 * not to be able to map all of memory.
-	 */
-	if (!pci_is_pcie(pdev)) {
-		if (!pci_is_root_bus(pdev->bus))
+		if (!(iommu_identity_mapping & IDENTMAP_ALL))
 			return 0;
-		if (pdev->class >> 8 == PCI_CLASS_BRIDGE_PCI)
+
+		/*
+		 * We want to start off with all devices in the 1:1 domain, and
+		 * take them out later if we find they can't access all of memory.
+		 *
+		 * However, we can't do this for PCI devices behind bridges,
+		 * because all PCI devices behind the same bridge will end up
+		 * with the same source-id on their transactions.
+		 *
+		 * Practically speaking, we can't change things around for these
+		 * devices at run-time, because we can't be sure there'll be no
+		 * DMA transactions in flight for any of their siblings.
+		 *
+		 * So PCI devices (unless they're on the root bus) as well as
+		 * their parent PCI-PCI or PCIe-PCI bridges must be left _out_ of
+		 * the 1:1 domain, just in _case_ one of their siblings turns out
+		 * not to be able to map all of memory.
+		 */
+		if (!pci_is_pcie(pdev)) {
+			if (!pci_is_root_bus(pdev->bus))
+				return 0;
+			if (pdev->class >> 8 == PCI_CLASS_BRIDGE_PCI)
+				return 0;
+		} else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_PCI_BRIDGE)
 			return 0;
-	} else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_PCI_BRIDGE)
-		return 0;
+	} else {
+		if (device_has_rmrr(dev))
+			return 0;
+	}
 
-	/* 
+	/*
 	 * At boot time, we don't yet know if devices will be 64-bit capable.
-	 * Assume that they will -- if they turn out not to be, then we can 
+	 * Assume that they will — if they turn out not to be, then we can
 	 * take them out of the 1:1 domain later.
 	 */
 	if (!startup) {
@@ -2381,42 +2584,77 @@ static int iommu_should_identity_map(struct pci_dev *pdev, int startup)
 		 * If the device's dma_mask is less than the system's memory
 		 * size then this is not a candidate for identity mapping.
 		 */
-		u64 dma_mask = pdev->dma_mask;
+		u64 dma_mask = *dev->dma_mask;
 
-		if (pdev->dev.coherent_dma_mask &&
-		    pdev->dev.coherent_dma_mask < dma_mask)
-			dma_mask = pdev->dev.coherent_dma_mask;
+		if (dev->coherent_dma_mask &&
+		    dev->coherent_dma_mask < dma_mask)
+			dma_mask = dev->coherent_dma_mask;
 
-		return dma_mask >= dma_get_required_mask(&pdev->dev);
+		return dma_mask >= dma_get_required_mask(dev);
 	}
 
 	return 1;
 }
 
+static int __init dev_prepare_static_identity_mapping(struct device *dev, int hw)
+{
+	int ret;
+
+	if (!iommu_should_identity_map(dev, 1))
+		return 0;
+
+	ret = domain_add_dev_info(si_domain, dev,
+				  hw ? CONTEXT_TT_PASS_THROUGH :
+				       CONTEXT_TT_MULTI_LEVEL);
+	if (!ret)
+		pr_info("IOMMU: %s identity mapping for device %s\n",
+			hw ? "hardware" : "software", dev_name(dev));
+	else if (ret == -ENODEV)
+		/* device not associated with an iommu */
+		ret = 0;
+
+	return ret;
+}
+
+
 static int __init iommu_prepare_static_identity_mapping(int hw)
 {
 	struct pci_dev *pdev = NULL;
-	int ret;
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	struct device *dev;
+	int i;
+	int ret = 0;
 
 	ret = si_domain_init(hw);
 	if (ret)
 		return -EFAULT;
 
 	for_each_pci_dev(pdev) {
-		if (iommu_should_identity_map(pdev, 1)) {
-			ret = domain_add_dev_info(si_domain, pdev,
-					     hw ? CONTEXT_TT_PASS_THROUGH :
-						  CONTEXT_TT_MULTI_LEVEL);
-			if (ret) {
-				/* device not associated with an iommu */
-				if (ret == -ENODEV)
-					continue;
-				return ret;
+		ret = dev_prepare_static_identity_mapping(&pdev->dev, hw);
+		if (ret)
+			return ret;
+	}
+
+	for_each_active_iommu(iommu, drhd)
+		for_each_active_dev_scope(drhd->devices, drhd->devices_cnt, i, dev) {
+			struct acpi_device_physical_node *pn;
+			struct acpi_device *adev;
+
+			if (dev->bus != &acpi_bus_type)
+				continue;
+				
+			adev= to_acpi_device(dev);
+			mutex_lock(&adev->physical_node_lock);
+			list_for_each_entry(pn, &adev->physical_node_list, node) {
+				ret = dev_prepare_static_identity_mapping(pn->dev, hw);
+				if (ret)
+					break;
 			}
-			pr_info("IOMMU: %s identity mapping for device %s\n",
-				hw ? "hardware" : "software", pci_name(pdev));
+			mutex_unlock(&adev->physical_node_lock);
+			if (ret)
+				return ret;
 		}
-	}
 
 	return 0;
 }
@@ -2425,7 +2663,7 @@ static int __init init_dmars(void)
 {
 	struct dmar_drhd_unit *drhd;
 	struct dmar_rmrr_unit *rmrr;
-	struct pci_dev *pdev;
+	struct device *dev;
 	struct intel_iommu *iommu;
 	int i, ret;
 
@@ -2461,7 +2699,7 @@ static int __init init_dmars(void)
 		sizeof(struct deferred_flush_tables), GFP_KERNEL);
 	if (!deferred_flush) {
 		ret = -ENOMEM;
-		goto error;
+		goto free_g_iommus;
 	}
 
 	for_each_active_iommu(iommu, drhd) {
@@ -2469,7 +2707,7 @@ static int __init init_dmars(void)
 
 		ret = iommu_init_domains(iommu);
 		if (ret)
-			goto error;
+			goto free_iommu;
 
 		/*
 		 * TBD:
@@ -2479,7 +2717,7 @@ static int __init init_dmars(void)
 		ret = iommu_alloc_root_entry(iommu);
 		if (ret) {
 			printk(KERN_ERR "IOMMU: allocate root entry failed\n");
-			goto error;
+			goto free_iommu;
 		}
 		if (!ecap_pass_through(iommu->ecap))
 			hw_pass_through = 0;
@@ -2548,7 +2786,7 @@ static int __init init_dmars(void)
 		ret = iommu_prepare_static_identity_mapping(hw_pass_through);
 		if (ret) {
 			printk(KERN_CRIT "Failed to setup IOMMU pass-through\n");
-			goto error;
+			goto free_iommu;
 		}
 	}
 	/*
@@ -2567,15 +2805,10 @@ static int __init init_dmars(void)
 	 */
 	printk(KERN_INFO "IOMMU: Setting RMRR:\n");
 	for_each_rmrr_units(rmrr) {
-		for (i = 0; i < rmrr->devices_cnt; i++) {
-			pdev = rmrr->devices[i];
-			/*
-			 * some BIOS lists non-exist devices in DMAR
-			 * table.
-			 */
-			if (!pdev)
-				continue;
-			ret = iommu_prepare_rmrr_dev(rmrr, pdev);
+		/* some BIOS lists non-exist devices in DMAR table. */
+		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
+					  i, dev) {
+			ret = iommu_prepare_rmrr_dev(rmrr, dev);
 			if (ret)
 				printk(KERN_ERR
 				       "IOMMU: mapping reserved region failed\n");
@@ -2606,7 +2839,7 @@ static int __init init_dmars(void)
 
 		ret = dmar_set_interrupt(iommu);
 		if (ret)
-			goto error;
+			goto free_iommu;
 
 		iommu_set_root_entry(iommu);
 
@@ -2615,17 +2848,20 @@ static int __init init_dmars(void)
 
 		ret = iommu_enable_translation(iommu);
 		if (ret)
-			goto error;
+			goto free_iommu;
 
 		iommu_disable_protect_mem_regions(iommu);
 	}
 
 	return 0;
-error:
+
+free_iommu:
 	for_each_active_iommu(iommu, drhd)
 		free_dmar_iommu(iommu);
 	kfree(deferred_flush);
+free_g_iommus:
 	kfree(g_iommus);
+error:
 	return ret;
 }
 
@@ -2634,7 +2870,6 @@ static struct iova *intel_alloc_iova(struct device *dev,
 				     struct dmar_domain *domain,
 				     unsigned long nrpages, uint64_t dma_mask)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
 	struct iova *iova = NULL;
 
 	/* Restrict dma_mask to the width that the iommu can handle */
@@ -2654,34 +2889,31 @@ static struct iova *intel_alloc_iova(struct device *dev,
 	iova = alloc_iova(&domain->iovad, nrpages, IOVA_PFN(dma_mask), 1);
 	if (unlikely(!iova)) {
 		printk(KERN_ERR "Allocating %ld-page iova for %s failed",
-		       nrpages, pci_name(pdev));
+		       nrpages, dev_name(dev));
 		return NULL;
 	}
 
 	return iova;
 }
 
-static struct dmar_domain *__get_valid_domain_for_dev(struct pci_dev *pdev)
+static struct dmar_domain *__get_valid_domain_for_dev(struct device *dev)
 {
 	struct dmar_domain *domain;
 	int ret;
 
-	domain = get_domain_for_dev(pdev,
-			DEFAULT_DOMAIN_ADDRESS_WIDTH);
+	domain = get_domain_for_dev(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
 	if (!domain) {
-		printk(KERN_ERR
-			"Allocating domain for %s failed", pci_name(pdev));
+		printk(KERN_ERR "Allocating domain for %s failed",
+		       dev_name(dev));
 		return NULL;
 	}
 
 	/* make sure context mapping is ok */
-	if (unlikely(!domain_context_mapped(pdev))) {
-		ret = domain_context_mapping(domain, pdev,
-					     CONTEXT_TT_MULTI_LEVEL);
+	if (unlikely(!domain_context_mapped(dev))) {
+		ret = domain_context_mapping(domain, dev, CONTEXT_TT_MULTI_LEVEL);
 		if (ret) {
-			printk(KERN_ERR
-				"Domain context map for %s failed",
-				pci_name(pdev));
+			printk(KERN_ERR "Domain context map for %s failed",
+			       dev_name(dev));
 			return NULL;
 		}
 	}
@@ -2689,51 +2921,46 @@ static struct dmar_domain *__get_valid_domain_for_dev(struct pci_dev *pdev)
 	return domain;
 }
 
-static inline struct dmar_domain *get_valid_domain_for_dev(struct pci_dev *dev)
+static inline struct dmar_domain *get_valid_domain_for_dev(struct device *dev)
 {
 	struct device_domain_info *info;
 
 	/* No lock here, assumes no domain exit in normal case */
-	info = dev->dev.archdata.iommu;
+	info = dev->archdata.iommu;
 	if (likely(info))
 		return info->domain;
 
 	return __get_valid_domain_for_dev(dev);
 }
 
-static int iommu_dummy(struct pci_dev *pdev)
+static int iommu_dummy(struct device *dev)
 {
-	return pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
+	return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
 }
 
-/* Check if the pdev needs to go through non-identity map and unmap process.*/
+/* Check if the dev needs to go through non-identity map and unmap process.*/
 static int iommu_no_mapping(struct device *dev)
 {
-	struct pci_dev *pdev;
 	int found;
 
-	if (unlikely(!dev_is_pci(dev)))
-		return 1;
-
-	pdev = to_pci_dev(dev);
-	if (iommu_dummy(pdev))
+	if (iommu_dummy(dev))
 		return 1;
 
 	if (!iommu_identity_mapping)
 		return 0;
 
-	found = identity_mapping(pdev);
+	found = identity_mapping(dev);
 	if (found) {
-		if (iommu_should_identity_map(pdev, 0))
+		if (iommu_should_identity_map(dev, 0))
 			return 1;
 		else {
 			/*
 			 * 32 bit DMA is removed from si_domain and fall back
 			 * to non-identity mapping.
 			 */
-			domain_remove_one_dev_info(si_domain, pdev);
+			domain_remove_one_dev_info(si_domain, dev);
 			printk(KERN_INFO "32bit %s uses non-identity mapping\n",
-			       pci_name(pdev));
+			       dev_name(dev));
 			return 0;
 		}
 	} else {
@@ -2741,15 +2968,15 @@ static int iommu_no_mapping(struct device *dev)
 		 * In case of a detached 64 bit DMA device from vm, the device
 		 * is put into si_domain for identity mapping.
 		 */
-		if (iommu_should_identity_map(pdev, 0)) {
+		if (iommu_should_identity_map(dev, 0)) {
 			int ret;
-			ret = domain_add_dev_info(si_domain, pdev,
+			ret = domain_add_dev_info(si_domain, dev,
 						  hw_pass_through ?
 						  CONTEXT_TT_PASS_THROUGH :
 						  CONTEXT_TT_MULTI_LEVEL);
 			if (!ret) {
 				printk(KERN_INFO "64bit %s uses identity mapping\n",
-				       pci_name(pdev));
+				       dev_name(dev));
 				return 1;
 			}
 		}
@@ -2758,10 +2985,9 @@ static int iommu_no_mapping(struct device *dev)
 	return 0;
 }
 
-static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr,
+static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
 				     size_t size, int dir, u64 dma_mask)
 {
-	struct pci_dev *pdev = to_pci_dev(hwdev);
 	struct dmar_domain *domain;
 	phys_addr_t start_paddr;
 	struct iova *iova;
@@ -2772,17 +2998,17 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr,
 
 	BUG_ON(dir == DMA_NONE);
 
-	if (iommu_no_mapping(hwdev))
+	if (iommu_no_mapping(dev))
 		return paddr;
 
-	domain = get_valid_domain_for_dev(pdev);
+	domain = get_valid_domain_for_dev(dev);
 	if (!domain)
 		return 0;
 
 	iommu = domain_get_iommu(domain);
 	size = aligned_nrpages(paddr, size);
 
-	iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), dma_mask);
+	iova = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size), dma_mask);
 	if (!iova)
 		goto error;
 
@@ -2808,7 +3034,7 @@ 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, domain->id, mm_to_dma_pfn(iova->pfn_lo), size, 1);
+		iommu_flush_iotlb_psi(iommu, domain->id, mm_to_dma_pfn(iova->pfn_lo), size, 0, 1);
 	else
 		iommu_flush_write_buffer(iommu);
 
@@ -2820,7 +3046,7 @@ error:
 	if (iova)
 		__free_iova(&domain->iovad, iova);
 	printk(KERN_ERR"Device %s request: %zx@%llx dir %d --- failed\n",
-		pci_name(pdev), size, (unsigned long long)paddr, dir);
+		dev_name(dev), size, (unsigned long long)paddr, dir);
 	return 0;
 }
 
@@ -2830,7 +3056,7 @@ static dma_addr_t intel_map_page(struct device *dev, struct page *page,
 				 struct dma_attrs *attrs)
 {
 	return __intel_map_single(dev, page_to_phys(page) + offset, size,
-				  dir, to_pci_dev(dev)->dma_mask);
+				  dir, *dev->dma_mask);
 }
 
 static void flush_unmaps(void)
@@ -2860,13 +3086,16 @@ static void flush_unmaps(void)
 			/* 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);
+					iova->pfn_lo, iova->pfn_hi - iova->pfn_lo + 1,
+					!deferred_flush[i].freelist[j], 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);
+			if (deferred_flush[i].freelist[j])
+				dma_free_pagelist(deferred_flush[i].freelist[j]);
 		}
 		deferred_flush[i].next = 0;
 	}
@@ -2883,7 +3112,7 @@ static void flush_unmaps_timeout(unsigned long data)
 	spin_unlock_irqrestore(&async_umap_flush_lock, flags);
 }
 
-static void add_unmap(struct dmar_domain *dom, struct iova *iova)
+static void add_unmap(struct dmar_domain *dom, struct iova *iova, struct page *freelist)
 {
 	unsigned long flags;
 	int next, iommu_id;
@@ -2899,6 +3128,7 @@ static void add_unmap(struct dmar_domain *dom, struct iova *iova)
 	next = deferred_flush[iommu_id].next;
 	deferred_flush[iommu_id].domain[next] = dom;
 	deferred_flush[iommu_id].iova[next] = iova;
+	deferred_flush[iommu_id].freelist[next] = freelist;
 	deferred_flush[iommu_id].next++;
 
 	if (!timer_on) {
@@ -2913,16 +3143,16 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
 			     size_t size, enum dma_data_direction dir,
 			     struct dma_attrs *attrs)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
 	struct dmar_domain *domain;
 	unsigned long start_pfn, last_pfn;
 	struct iova *iova;
 	struct intel_iommu *iommu;
+	struct page *freelist;
 
 	if (iommu_no_mapping(dev))
 		return;
 
-	domain = find_domain(pdev);
+	domain = find_domain(dev);
 	BUG_ON(!domain);
 
 	iommu = domain_get_iommu(domain);
@@ -2936,21 +3166,18 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
 	last_pfn = mm_to_dma_pfn(iova->pfn_hi + 1) - 1;
 
 	pr_debug("Device %s unmapping: pfn %lx-%lx\n",
-		 pci_name(pdev), start_pfn, last_pfn);
-
-	/*  clear the whole page */
-	dma_pte_clear_range(domain, start_pfn, last_pfn);
+		 dev_name(dev), start_pfn, last_pfn);
 
-	/* free page tables */
-	dma_pte_free_pagetable(domain, start_pfn, last_pfn);
+	freelist = domain_unmap(domain, start_pfn, last_pfn);
 
 	if (intel_iommu_strict) {
 		iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
-				      last_pfn - start_pfn + 1, 0);
+				      last_pfn - start_pfn + 1, !freelist, 0);
 		/* free iova */
 		__free_iova(&domain->iovad, iova);
+		dma_free_pagelist(freelist);
 	} else {
-		add_unmap(domain, iova);
+		add_unmap(domain, iova, freelist);
 		/*
 		 * queue up the release of the unmap to save the 1/6th of the
 		 * cpu used up by the iotlb flush operation...
@@ -2958,7 +3185,7 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
 	}
 }
 
-static void *intel_alloc_coherent(struct device *hwdev, size_t size,
+static void *intel_alloc_coherent(struct device *dev, size_t size,
 				  dma_addr_t *dma_handle, gfp_t flags,
 				  struct dma_attrs *attrs)
 {
@@ -2968,10 +3195,10 @@ static void *intel_alloc_coherent(struct device *hwdev, size_t size,
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
 
-	if (!iommu_no_mapping(hwdev))
+	if (!iommu_no_mapping(dev))
 		flags &= ~(GFP_DMA | GFP_DMA32);
-	else if (hwdev->coherent_dma_mask < dma_get_required_mask(hwdev)) {
-		if (hwdev->coherent_dma_mask < DMA_BIT_MASK(32))
+	else if (dev->coherent_dma_mask < dma_get_required_mask(dev)) {
+		if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
 			flags |= GFP_DMA;
 		else
 			flags |= GFP_DMA32;
@@ -2982,16 +3209,16 @@ static void *intel_alloc_coherent(struct device *hwdev, size_t size,
 		return NULL;
 	memset(vaddr, 0, size);
 
-	*dma_handle = __intel_map_single(hwdev, virt_to_bus(vaddr), size,
+	*dma_handle = __intel_map_single(dev, virt_to_bus(vaddr), size,
 					 DMA_BIDIRECTIONAL,
-					 hwdev->coherent_dma_mask);
+					 dev->coherent_dma_mask);
 	if (*dma_handle)
 		return vaddr;
 	free_pages((unsigned long)vaddr, order);
 	return NULL;
 }
 
-static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
+static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
 				dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	int order;
@@ -2999,24 +3226,24 @@ static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
 
-	intel_unmap_page(hwdev, dma_handle, size, DMA_BIDIRECTIONAL, NULL);
+	intel_unmap_page(dev, dma_handle, size, DMA_BIDIRECTIONAL, NULL);
 	free_pages((unsigned long)vaddr, order);
 }
 
-static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
+static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
 			   int nelems, enum dma_data_direction dir,
 			   struct dma_attrs *attrs)
 {
-	struct pci_dev *pdev = to_pci_dev(hwdev);
 	struct dmar_domain *domain;
 	unsigned long start_pfn, last_pfn;
 	struct iova *iova;
 	struct intel_iommu *iommu;
+	struct page *freelist;
 
-	if (iommu_no_mapping(hwdev))
+	if (iommu_no_mapping(dev))
 		return;
 
-	domain = find_domain(pdev);
+	domain = find_domain(dev);
 	BUG_ON(!domain);
 
 	iommu = domain_get_iommu(domain);
@@ -3029,19 +3256,16 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
 	start_pfn = mm_to_dma_pfn(iova->pfn_lo);
 	last_pfn = mm_to_dma_pfn(iova->pfn_hi + 1) - 1;
 
-	/*  clear the whole page */
-	dma_pte_clear_range(domain, start_pfn, last_pfn);
-
-	/* free page tables */
-	dma_pte_free_pagetable(domain, start_pfn, last_pfn);
+	freelist = domain_unmap(domain, start_pfn, last_pfn);
 
 	if (intel_iommu_strict) {
 		iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
-				      last_pfn - start_pfn + 1, 0);
+				      last_pfn - start_pfn + 1, !freelist, 0);
 		/* free iova */
 		__free_iova(&domain->iovad, iova);
+		dma_free_pagelist(freelist);
 	} else {
-		add_unmap(domain, iova);
+		add_unmap(domain, iova, freelist);
 		/*
 		 * queue up the release of the unmap to save the 1/6th of the
 		 * cpu used up by the iotlb flush operation...
@@ -3063,11 +3287,10 @@ static int intel_nontranslate_map_sg(struct device *hddev,
 	return nelems;
 }
 
-static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems,
+static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nelems,
 			enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	int i;
-	struct pci_dev *pdev = to_pci_dev(hwdev);
 	struct dmar_domain *domain;
 	size_t size = 0;
 	int prot = 0;
@@ -3078,10 +3301,10 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne
 	struct intel_iommu *iommu;
 
 	BUG_ON(dir == DMA_NONE);
-	if (iommu_no_mapping(hwdev))
-		return intel_nontranslate_map_sg(hwdev, sglist, nelems, dir);
+	if (iommu_no_mapping(dev))
+		return intel_nontranslate_map_sg(dev, sglist, nelems, dir);
 
-	domain = get_valid_domain_for_dev(pdev);
+	domain = get_valid_domain_for_dev(dev);
 	if (!domain)
 		return 0;
 
@@ -3090,8 +3313,8 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne
 	for_each_sg(sglist, sg, nelems, i)
 		size += aligned_nrpages(sg->offset, sg->length);
 
-	iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size),
-				pdev->dma_mask);
+	iova = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size),
+				*dev->dma_mask);
 	if (!iova) {
 		sglist->dma_length = 0;
 		return 0;
@@ -3124,7 +3347,7 @@ 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, domain->id, start_vpfn, size, 1);
+		iommu_flush_iotlb_psi(iommu, domain->id, start_vpfn, size, 0, 1);
 	else
 		iommu_flush_write_buffer(iommu);
 
@@ -3259,29 +3482,28 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quir
 static void __init init_no_remapping_devices(void)
 {
 	struct dmar_drhd_unit *drhd;
+	struct device *dev;
+	int i;
 
 	for_each_drhd_unit(drhd) {
 		if (!drhd->include_all) {
-			int i;
-			for (i = 0; i < drhd->devices_cnt; i++)
-				if (drhd->devices[i] != NULL)
-					break;
-			/* ignore DMAR unit if no pci devices exist */
+			for_each_active_dev_scope(drhd->devices,
+						  drhd->devices_cnt, i, dev)
+				break;
+			/* ignore DMAR unit if no devices exist */
 			if (i == drhd->devices_cnt)
 				drhd->ignored = 1;
 		}
 	}
 
 	for_each_active_drhd_unit(drhd) {
-		int i;
 		if (drhd->include_all)
 			continue;
 
-		for (i = 0; i < drhd->devices_cnt; i++)
-			if (drhd->devices[i] &&
-			    !IS_GFX_DEVICE(drhd->devices[i]))
+		for_each_active_dev_scope(drhd->devices,
+					  drhd->devices_cnt, i, dev)
+			if (!dev_is_pci(dev) || !IS_GFX_DEVICE(to_pci_dev(dev)))
 				break;
-
 		if (i < drhd->devices_cnt)
 			continue;
 
@@ -3291,11 +3513,9 @@ static void __init init_no_remapping_devices(void)
 			intel_iommu_gfx_mapped = 1;
 		} else {
 			drhd->ignored = 1;
-			for (i = 0; i < drhd->devices_cnt; i++) {
-				if (!drhd->devices[i])
-					continue;
-				drhd->devices[i]->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
-			}
+			for_each_active_dev_scope(drhd->devices,
+						  drhd->devices_cnt, i, dev)
+				dev->archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
 		}
 	}
 }
@@ -3438,13 +3658,6 @@ static void __init init_iommu_pm_ops(void)
 static inline void init_iommu_pm_ops(void) {}
 #endif	/* CONFIG_PM */
 
-LIST_HEAD(dmar_rmrr_units);
-
-static void __init dmar_register_rmrr_unit(struct dmar_rmrr_unit *rmrr)
-{
-	list_add(&rmrr->list, &dmar_rmrr_units);
-}
-
 
 int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header)
 {
@@ -3459,25 +3672,19 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header)
 	rmrr = (struct acpi_dmar_reserved_memory *)header;
 	rmrru->base_address = rmrr->base_address;
 	rmrru->end_address = rmrr->end_address;
+	rmrru->devices = dmar_alloc_dev_scope((void *)(rmrr + 1),
+				((void *)rmrr) + rmrr->header.length,
+				&rmrru->devices_cnt);
+	if (rmrru->devices_cnt && rmrru->devices == NULL) {
+		kfree(rmrru);
+		return -ENOMEM;
+	}
 
-	dmar_register_rmrr_unit(rmrru);
-	return 0;
-}
-
-static int __init
-rmrr_parse_dev(struct dmar_rmrr_unit *rmrru)
-{
-	struct acpi_dmar_reserved_memory *rmrr;
+	list_add(&rmrru->list, &dmar_rmrr_units);
 
-	rmrr = (struct acpi_dmar_reserved_memory *) rmrru->hdr;
-	return dmar_parse_dev_scope((void *)(rmrr + 1),
-				    ((void *)rmrr) + rmrr->header.length,
-				    &rmrru->devices_cnt, &rmrru->devices,
-				    rmrr->segment);
+	return 0;
 }
 
-static LIST_HEAD(dmar_atsr_units);
-
 int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
 {
 	struct acpi_dmar_atsr *atsr;
@@ -3490,26 +3697,21 @@ int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
 
 	atsru->hdr = hdr;
 	atsru->include_all = atsr->flags & 0x1;
+	if (!atsru->include_all) {
+		atsru->devices = dmar_alloc_dev_scope((void *)(atsr + 1),
+				(void *)atsr + atsr->header.length,
+				&atsru->devices_cnt);
+		if (atsru->devices_cnt && atsru->devices == NULL) {
+			kfree(atsru);
+			return -ENOMEM;
+		}
+	}
 
-	list_add(&atsru->list, &dmar_atsr_units);
+	list_add_rcu(&atsru->list, &dmar_atsr_units);
 
 	return 0;
 }
 
-static int __init atsr_parse_dev(struct dmar_atsr_unit *atsru)
-{
-	struct acpi_dmar_atsr *atsr;
-
-	if (atsru->include_all)
-		return 0;
-
-	atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
-	return dmar_parse_dev_scope((void *)(atsr + 1),
-				    (void *)atsr + atsr->header.length,
-				    &atsru->devices_cnt, &atsru->devices,
-				    atsr->segment);
-}
-
 static void intel_iommu_free_atsr(struct dmar_atsr_unit *atsru)
 {
 	dmar_free_dev_scope(&atsru->devices, &atsru->devices_cnt);
@@ -3535,62 +3737,97 @@ static void intel_iommu_free_dmars(void)
 
 int dmar_find_matched_atsr_unit(struct pci_dev *dev)
 {
-	int i;
+	int i, ret = 1;
 	struct pci_bus *bus;
+	struct pci_dev *bridge = NULL;
+	struct device *tmp;
 	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))
-			goto found;
-	}
-
-	return 0;
-
-found:
 	for (bus = dev->bus; bus; bus = bus->parent) {
-		struct pci_dev *bridge = bus->self;
-
+		bridge = bus->self;
 		if (!bridge || !pci_is_pcie(bridge) ||
 		    pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE)
 			return 0;
-
-		if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT) {
-			for (i = 0; i < atsru->devices_cnt; i++)
-				if (atsru->devices[i] == bridge)
-					return 1;
+		if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT)
 			break;
-		}
 	}
+	if (!bridge)
+		return 0;
 
-	if (atsru->include_all)
-		return 1;
+	rcu_read_lock();
+	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list) {
+		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
+		if (atsr->segment != pci_domain_nr(dev->bus))
+			continue;
 
-	return 0;
+		for_each_dev_scope(atsru->devices, atsru->devices_cnt, i, tmp)
+			if (tmp == &bridge->dev)
+				goto out;
+
+		if (atsru->include_all)
+			goto out;
+	}
+	ret = 0;
+out:
+	rcu_read_unlock();
+
+	return ret;
 }
 
-int __init dmar_parse_rmrr_atsr_dev(void)
+int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 {
-	struct dmar_rmrr_unit *rmrr;
-	struct dmar_atsr_unit *atsr;
 	int ret = 0;
+	struct dmar_rmrr_unit *rmrru;
+	struct dmar_atsr_unit *atsru;
+	struct acpi_dmar_atsr *atsr;
+	struct acpi_dmar_reserved_memory *rmrr;
 
-	list_for_each_entry(rmrr, &dmar_rmrr_units, list) {
-		ret = rmrr_parse_dev(rmrr);
-		if (ret)
-			return ret;
+	if (!intel_iommu_enabled && system_state != SYSTEM_BOOTING)
+		return 0;
+
+	list_for_each_entry(rmrru, &dmar_rmrr_units, list) {
+		rmrr = container_of(rmrru->hdr,
+				    struct acpi_dmar_reserved_memory, header);
+		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
+			ret = dmar_insert_dev_scope(info, (void *)(rmrr + 1),
+				((void *)rmrr) + rmrr->header.length,
+				rmrr->segment, rmrru->devices,
+				rmrru->devices_cnt);
+			if (ret > 0)
+				break;
+			else if(ret < 0)
+				return ret;
+		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+			if (dmar_remove_dev_scope(info, rmrr->segment,
+				rmrru->devices, rmrru->devices_cnt))
+				break;
+		}
 	}
 
-	list_for_each_entry(atsr, &dmar_atsr_units, list) {
-		ret = atsr_parse_dev(atsr);
-		if (ret)
-			return ret;
+	list_for_each_entry(atsru, &dmar_atsr_units, list) {
+		if (atsru->include_all)
+			continue;
+
+		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
+		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
+			ret = dmar_insert_dev_scope(info, (void *)(atsr + 1),
+					(void *)atsr + atsr->header.length,
+					atsr->segment, atsru->devices,
+					atsru->devices_cnt);
+			if (ret > 0)
+				break;
+			else if(ret < 0)
+				return ret;
+		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+			if (dmar_remove_dev_scope(info, atsr->segment,
+					atsru->devices, atsru->devices_cnt))
+				break;
+		}
 	}
 
-	return ret;
+	return 0;
 }
 
 /*
@@ -3603,24 +3840,26 @@ static int device_notifier(struct notifier_block *nb,
 				  unsigned long action, void *data)
 {
 	struct device *dev = data;
-	struct pci_dev *pdev = to_pci_dev(dev);
 	struct dmar_domain *domain;
 
-	if (iommu_no_mapping(dev))
+	if (iommu_dummy(dev))
 		return 0;
 
-	domain = find_domain(pdev);
-	if (!domain)
+	if (action != BUS_NOTIFY_UNBOUND_DRIVER &&
+	    action != BUS_NOTIFY_DEL_DEVICE)
 		return 0;
 
-	if (action == BUS_NOTIFY_UNBOUND_DRIVER && !iommu_pass_through) {
-		domain_remove_one_dev_info(domain, pdev);
+	domain = find_domain(dev);
+	if (!domain)
+		return 0;
 
-		if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) &&
-		    !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) &&
-		    list_empty(&domain->devices))
-			domain_exit(domain);
-	}
+	down_read(&dmar_global_lock);
+	domain_remove_one_dev_info(domain, dev);
+	if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) &&
+	    !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) &&
+	    list_empty(&domain->devices))
+		domain_exit(domain);
+	up_read(&dmar_global_lock);
 
 	return 0;
 }
@@ -3629,6 +3868,75 @@ static struct notifier_block device_nb = {
 	.notifier_call = device_notifier,
 };
 
+static int intel_iommu_memory_notifier(struct notifier_block *nb,
+				       unsigned long val, void *v)
+{
+	struct memory_notify *mhp = v;
+	unsigned long long start, end;
+	unsigned long start_vpfn, last_vpfn;
+
+	switch (val) {
+	case MEM_GOING_ONLINE:
+		start = mhp->start_pfn << PAGE_SHIFT;
+		end = ((mhp->start_pfn + mhp->nr_pages) << PAGE_SHIFT) - 1;
+		if (iommu_domain_identity_map(si_domain, start, end)) {
+			pr_warn("dmar: failed to build identity map for [%llx-%llx]\n",
+				start, end);
+			return NOTIFY_BAD;
+		}
+		break;
+
+	case MEM_OFFLINE:
+	case MEM_CANCEL_ONLINE:
+		start_vpfn = mm_to_dma_pfn(mhp->start_pfn);
+		last_vpfn = mm_to_dma_pfn(mhp->start_pfn + mhp->nr_pages - 1);
+		while (start_vpfn <= last_vpfn) {
+			struct iova *iova;
+			struct dmar_drhd_unit *drhd;
+			struct intel_iommu *iommu;
+			struct page *freelist;
+
+			iova = find_iova(&si_domain->iovad, start_vpfn);
+			if (iova == NULL) {
+				pr_debug("dmar: failed get IOVA for PFN %lx\n",
+					 start_vpfn);
+				break;
+			}
+
+			iova = split_and_remove_iova(&si_domain->iovad, iova,
+						     start_vpfn, last_vpfn);
+			if (iova == NULL) {
+				pr_warn("dmar: failed to split IOVA PFN [%lx-%lx]\n",
+					start_vpfn, last_vpfn);
+				return NOTIFY_BAD;
+			}
+
+			freelist = domain_unmap(si_domain, iova->pfn_lo,
+					       iova->pfn_hi);
+
+			rcu_read_lock();
+			for_each_active_iommu(iommu, drhd)
+				iommu_flush_iotlb_psi(iommu, si_domain->id,
+					iova->pfn_lo,
+					iova->pfn_hi - iova->pfn_lo + 1,
+					!freelist, 0);
+			rcu_read_unlock();
+			dma_free_pagelist(freelist);
+
+			start_vpfn = iova->pfn_hi + 1;
+			free_iova_mem(iova);
+		}
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block intel_iommu_memory_nb = {
+	.notifier_call = intel_iommu_memory_notifier,
+	.priority = 0
+};
+
 int __init intel_iommu_init(void)
 {
 	int ret = -ENODEV;
@@ -3638,6 +3946,13 @@ int __init intel_iommu_init(void)
 	/* VT-d is required for a TXT/tboot launch, so enforce that */
 	force_on = tboot_force_iommu();
 
+	if (iommu_init_mempool()) {
+		if (force_on)
+			panic("tboot: Failed to initialize iommu memory\n");
+		return -ENOMEM;
+	}
+
+	down_write(&dmar_global_lock);
 	if (dmar_table_init()) {
 		if (force_on)
 			panic("tboot: Failed to initialize DMAR table\n");
@@ -3660,12 +3975,6 @@ int __init intel_iommu_init(void)
 	if (no_iommu || dmar_disabled)
 		goto out_free_dmar;
 
-	if (iommu_init_mempool()) {
-		if (force_on)
-			panic("tboot: Failed to initialize iommu memory\n");
-		goto out_free_dmar;
-	}
-
 	if (list_empty(&dmar_rmrr_units))
 		printk(KERN_INFO "DMAR: No RMRR found\n");
 
@@ -3675,7 +3984,7 @@ int __init intel_iommu_init(void)
 	if (dmar_init_reserved_ranges()) {
 		if (force_on)
 			panic("tboot: Failed to reserve iommu ranges\n");
-		goto out_free_mempool;
+		goto out_free_reserved_range;
 	}
 
 	init_no_remapping_devices();
@@ -3687,6 +3996,7 @@ int __init intel_iommu_init(void)
 		printk(KERN_ERR "IOMMU: dmar init failed\n");
 		goto out_free_reserved_range;
 	}
+	up_write(&dmar_global_lock);
 	printk(KERN_INFO
 	"PCI-DMA: Intel(R) Virtualization Technology for Directed I/O\n");
 
@@ -3699,8 +4009,9 @@ int __init intel_iommu_init(void)
 	init_iommu_pm_ops();
 
 	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
-
 	bus_register_notifier(&pci_bus_type, &device_nb);
+	if (si_domain && !hw_pass_through)
+		register_memory_notifier(&intel_iommu_memory_nb);
 
 	intel_iommu_enabled = 1;
 
@@ -3708,21 +4019,23 @@ int __init intel_iommu_init(void)
 
 out_free_reserved_range:
 	put_iova_domain(&reserved_iova_list);
-out_free_mempool:
-	iommu_exit_mempool();
 out_free_dmar:
 	intel_iommu_free_dmars();
+	up_write(&dmar_global_lock);
+	iommu_exit_mempool();
 	return ret;
 }
 
 static void iommu_detach_dependent_devices(struct intel_iommu *iommu,
-					   struct pci_dev *pdev)
+					   struct device *dev)
 {
-	struct pci_dev *tmp, *parent;
+	struct pci_dev *tmp, *parent, *pdev;
 
-	if (!iommu || !pdev)
+	if (!iommu || !dev || !dev_is_pci(dev))
 		return;
 
+	pdev = to_pci_dev(dev);
+
 	/* dependent device detach */
 	tmp = pci_find_upstream_pcie_bridge(pdev);
 	/* Secondary interface's bus number and devfn 0 */
@@ -3743,29 +4056,28 @@ static void iommu_detach_dependent_devices(struct intel_iommu *iommu,
 }
 
 static void domain_remove_one_dev_info(struct dmar_domain *domain,
-					  struct pci_dev *pdev)
+				       struct device *dev)
 {
 	struct device_domain_info *info, *tmp;
 	struct intel_iommu *iommu;
 	unsigned long flags;
 	int found = 0;
+	u8 bus, devfn;
 
-	iommu = device_to_iommu(pci_domain_nr(pdev->bus), pdev->bus->number,
-				pdev->devfn);
+	iommu = device_to_iommu(dev, &bus, &devfn);
 	if (!iommu)
 		return;
 
 	spin_lock_irqsave(&device_domain_lock, flags);
 	list_for_each_entry_safe(info, tmp, &domain->devices, link) {
-		if (info->segment == pci_domain_nr(pdev->bus) &&
-		    info->bus == pdev->bus->number &&
-		    info->devfn == pdev->devfn) {
+		if (info->iommu == iommu && info->bus == bus &&
+		    info->devfn == devfn) {
 			unlink_domain_info(info);
 			spin_unlock_irqrestore(&device_domain_lock, flags);
 
 			iommu_disable_dev_iotlb(info);
 			iommu_detach_dev(iommu, info->bus, info->devfn);
-			iommu_detach_dependent_devices(iommu, pdev);
+			iommu_detach_dependent_devices(iommu, dev);
 			free_devinfo_mem(info);
 
 			spin_lock_irqsave(&device_domain_lock, flags);
@@ -3780,8 +4092,7 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain,
 		 * owned by this domain, clear this iommu in iommu_bmp
 		 * update iommu count and coherency
 		 */
-		if (iommu == device_to_iommu(info->segment, info->bus,
-					    info->devfn))
+		if (info->iommu == iommu)
 			found = 1;
 	}
 
@@ -3805,67 +4116,11 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain,
 	}
 }
 
-static void vm_domain_remove_all_dev_info(struct dmar_domain *domain)
-{
-	struct device_domain_info *info;
-	struct intel_iommu *iommu;
-	unsigned long flags1, flags2;
-
-	spin_lock_irqsave(&device_domain_lock, flags1);
-	while (!list_empty(&domain->devices)) {
-		info = list_entry(domain->devices.next,
-			struct device_domain_info, link);
-		unlink_domain_info(info);
-		spin_unlock_irqrestore(&device_domain_lock, flags1);
-
-		iommu_disable_dev_iotlb(info);
-		iommu = device_to_iommu(info->segment, info->bus, info->devfn);
-		iommu_detach_dev(iommu, info->bus, info->devfn);
-		iommu_detach_dependent_devices(iommu, info->dev);
-
-		/* clear this iommu in iommu_bmp, update iommu count
-		 * and capabilities
-		 */
-		spin_lock_irqsave(&domain->iommu_lock, flags2);
-		if (test_and_clear_bit(iommu->seq_id,
-				       domain->iommu_bmp)) {
-			domain->iommu_count--;
-			domain_update_iommu_cap(domain);
-		}
-		spin_unlock_irqrestore(&domain->iommu_lock, flags2);
-
-		free_devinfo_mem(info);
-		spin_lock_irqsave(&device_domain_lock, flags1);
-	}
-	spin_unlock_irqrestore(&device_domain_lock, flags1);
-}
-
-/* domain id for virtual machine, it won't be set in context */
-static atomic_t vm_domid = ATOMIC_INIT(0);
-
-static struct dmar_domain *iommu_alloc_vm_domain(void)
-{
-	struct dmar_domain *domain;
-
-	domain = alloc_domain_mem();
-	if (!domain)
-		return NULL;
-
-	domain->id = atomic_inc_return(&vm_domid);
-	domain->nid = -1;
-	memset(domain->iommu_bmp, 0, sizeof(domain->iommu_bmp));
-	domain->flags = DOMAIN_FLAG_VIRTUAL_MACHINE;
-
-	return domain;
-}
-
 static int md_domain_init(struct dmar_domain *domain, int guest_width)
 {
 	int adjust_width;
 
 	init_iova_domain(&domain->iovad, DMA_32BIT_PFN);
-	spin_lock_init(&domain->iommu_lock);
-
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
@@ -3873,9 +4128,6 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 	adjust_width = guestwidth_to_adjustwidth(guest_width);
 	domain->agaw = width_to_agaw(adjust_width);
 
-	INIT_LIST_HEAD(&domain->devices);
-
-	domain->iommu_count = 0;
 	domain->iommu_coherency = 0;
 	domain->iommu_snooping = 0;
 	domain->iommu_superpage = 0;
@@ -3890,53 +4142,11 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 	return 0;
 }
 
-static void iommu_free_vm_domain(struct dmar_domain *domain)
-{
-	unsigned long flags;
-	struct dmar_drhd_unit *drhd;
-	struct intel_iommu *iommu;
-	unsigned long i;
-	unsigned long ndomains;
-
-	for_each_active_iommu(iommu, drhd) {
-		ndomains = cap_ndoms(iommu->cap);
-		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);
-				iommu->domains[i] = NULL;
-				spin_unlock_irqrestore(&iommu->lock, flags);
-				break;
-			}
-		}
-	}
-}
-
-static void vm_domain_exit(struct dmar_domain *domain)
-{
-	/* Domain 0 is reserved, so dont process it */
-	if (!domain)
-		return;
-
-	vm_domain_remove_all_dev_info(domain);
-	/* destroy iovas */
-	put_iova_domain(&domain->iovad);
-
-	/* clear ptes */
-	dma_pte_clear_range(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
-
-	/* free page tables */
-	dma_pte_free_pagetable(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
-
-	iommu_free_vm_domain(domain);
-	free_domain_mem(domain);
-}
-
 static int intel_iommu_domain_init(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain;
 
-	dmar_domain = iommu_alloc_vm_domain();
+	dmar_domain = alloc_domain(true);
 	if (!dmar_domain) {
 		printk(KERN_ERR
 			"intel_iommu_domain_init: dmar_domain == NULL\n");
@@ -3945,7 +4155,7 @@ static int intel_iommu_domain_init(struct iommu_domain *domain)
 	if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
 		printk(KERN_ERR
 			"intel_iommu_domain_init() failed\n");
-		vm_domain_exit(dmar_domain);
+		domain_exit(dmar_domain);
 		return -ENOMEM;
 	}
 	domain_update_iommu_cap(dmar_domain);
@@ -3963,33 +4173,32 @@ static void intel_iommu_domain_destroy(struct iommu_domain *domain)
 	struct dmar_domain *dmar_domain = domain->priv;
 
 	domain->priv = NULL;
-	vm_domain_exit(dmar_domain);
+	domain_exit(dmar_domain);
 }
 
 static int intel_iommu_attach_device(struct iommu_domain *domain,
 				     struct device *dev)
 {
 	struct dmar_domain *dmar_domain = domain->priv;
-	struct pci_dev *pdev = to_pci_dev(dev);
 	struct intel_iommu *iommu;
 	int addr_width;
+	u8 bus, devfn;
 
-	/* normally pdev is not mapped */
-	if (unlikely(domain_context_mapped(pdev))) {
+	/* normally dev is not mapped */
+	if (unlikely(domain_context_mapped(dev))) {
 		struct dmar_domain *old_domain;
 
-		old_domain = find_domain(pdev);
+		old_domain = find_domain(dev);
 		if (old_domain) {
 			if (dmar_domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE ||
 			    dmar_domain->flags & DOMAIN_FLAG_STATIC_IDENTITY)
-				domain_remove_one_dev_info(old_domain, pdev);
+				domain_remove_one_dev_info(old_domain, dev);
 			else
 				domain_remove_dev_info(old_domain);
 		}
 	}
 
-	iommu = device_to_iommu(pci_domain_nr(pdev->bus), pdev->bus->number,
-				pdev->devfn);
+	iommu = device_to_iommu(dev, &bus, &devfn);
 	if (!iommu)
 		return -ENODEV;
 
@@ -4021,16 +4230,15 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 		dmar_domain->agaw--;
 	}
 
-	return domain_add_dev_info(dmar_domain, pdev, CONTEXT_TT_MULTI_LEVEL);
+	return domain_add_dev_info(dmar_domain, dev, CONTEXT_TT_MULTI_LEVEL);
 }
 
 static void intel_iommu_detach_device(struct iommu_domain *domain,
 				      struct device *dev)
 {
 	struct dmar_domain *dmar_domain = domain->priv;
-	struct pci_dev *pdev = to_pci_dev(dev);
 
-	domain_remove_one_dev_info(dmar_domain, pdev);
+	domain_remove_one_dev_info(dmar_domain, dev);
 }
 
 static int intel_iommu_map(struct iommu_domain *domain,
@@ -4072,18 +4280,51 @@ static int intel_iommu_map(struct iommu_domain *domain,
 }
 
 static size_t intel_iommu_unmap(struct iommu_domain *domain,
-			     unsigned long iova, size_t size)
+				unsigned long iova, size_t size)
 {
 	struct dmar_domain *dmar_domain = domain->priv;
-	int order;
+	struct page *freelist = NULL;
+	struct intel_iommu *iommu;
+	unsigned long start_pfn, last_pfn;
+	unsigned int npages;
+	int iommu_id, num, ndomains, level = 0;
+
+	/* Cope with horrid API which requires us to unmap more than the
+	   size argument if it happens to be a large-page mapping. */
+	if (!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level))
+		BUG();
+
+	if (size < VTD_PAGE_SIZE << level_to_offset_bits(level))
+		size = VTD_PAGE_SIZE << level_to_offset_bits(level);
+
+	start_pfn = iova >> VTD_PAGE_SHIFT;
+	last_pfn = (iova + size - 1) >> VTD_PAGE_SHIFT;
+
+	freelist = domain_unmap(dmar_domain, start_pfn, last_pfn);
+
+	npages = last_pfn - start_pfn + 1;
+
+	for_each_set_bit(iommu_id, dmar_domain->iommu_bmp, g_num_of_iommus) {
+               iommu = g_iommus[iommu_id];
+
+               /*
+                * find bit position of dmar_domain
+                */
+               ndomains = cap_ndoms(iommu->cap);
+               for_each_set_bit(num, iommu->domain_ids, ndomains) {
+                       if (iommu->domains[num] == dmar_domain)
+                               iommu_flush_iotlb_psi(iommu, num, start_pfn,
+						     npages, !freelist, 0);
+	       }
+
+	}
 
-	order = dma_pte_clear_range(dmar_domain, iova >> VTD_PAGE_SHIFT,
-			    (iova + size - 1) >> VTD_PAGE_SHIFT);
+	dma_free_pagelist(freelist);
 
 	if (dmar_domain->max_addr == iova + size)
 		dmar_domain->max_addr = iova;
 
-	return PAGE_SIZE << order;
+	return size;
 }
 
 static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
@@ -4091,9 +4332,10 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 {
 	struct dmar_domain *dmar_domain = domain->priv;
 	struct dma_pte *pte;
+	int level = 0;
 	u64 phys = 0;
 
-	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, 0);
+	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level);
 	if (pte)
 		phys = dma_pte_addr(pte);
 
@@ -4121,9 +4363,9 @@ static int intel_iommu_add_device(struct device *dev)
 	struct pci_dev *bridge, *dma_pdev = NULL;
 	struct iommu_group *group;
 	int ret;
+	u8 bus, devfn;
 
-	if (!device_to_iommu(pci_domain_nr(pdev->bus),
-			     pdev->bus->number, pdev->devfn))
+	if (!device_to_iommu(dev, &bus, &devfn))
 		return -ENODEV;
 
 	bridge = pci_find_upstream_pcie_bridge(pdev);

drivers/iommu/intel_irq_remapping.c

@@ -38,6 +38,17 @@ static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
 static struct hpet_scope ir_hpet[MAX_HPET_TBS];
 static int ir_ioapic_num, ir_hpet_num;
 
+/*
+ * Lock ordering:
+ * ->dmar_global_lock
+ *	->irq_2_ir_lock
+ *		->qi->q_lock
+ *	->iommu->register_lock
+ * Note:
+ * intel_irq_remap_ops.{supported,prepare,enable,disable,reenable} are called
+ * in single-threaded environment with interrupt disabled, so no need to tabke
+ * the dmar_global_lock.
+ */
 static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
 
 static int __init parse_ioapics_under_ir(void);
@@ -307,12 +318,14 @@ static int set_ioapic_sid(struct irte *irte, int apic)
 	if (!irte)
 		return -1;
 
+	down_read(&dmar_global_lock);
 	for (i = 0; i < MAX_IO_APICS; i++) {
 		if (ir_ioapic[i].id == apic) {
 			sid = (ir_ioapic[i].bus << 8) | ir_ioapic[i].devfn;
 			break;
 		}
 	}
+	up_read(&dmar_global_lock);
 
 	if (sid == 0) {
 		pr_warning("Failed to set source-id of IOAPIC (%d)\n", apic);
@@ -332,12 +345,14 @@ static int set_hpet_sid(struct irte *irte, u8 id)
 	if (!irte)
 		return -1;
 
+	down_read(&dmar_global_lock);
 	for (i = 0; i < MAX_HPET_TBS; i++) {
 		if (ir_hpet[i].id == id) {
 			sid = (ir_hpet[i].bus << 8) | ir_hpet[i].devfn;
 			break;
 		}
 	}
+	up_read(&dmar_global_lock);
 
 	if (sid == 0) {
 		pr_warning("Failed to set source-id of HPET block (%d)\n", id);
@@ -794,10 +809,16 @@ static int __init parse_ioapics_under_ir(void)
 
 static int __init ir_dev_scope_init(void)
 {
+	int ret;
+
 	if (!irq_remapping_enabled)
 		return 0;
 
-	return dmar_dev_scope_init();
+	down_write(&dmar_global_lock);
+	ret = dmar_dev_scope_init();
+	up_write(&dmar_global_lock);
+
+	return ret;
 }
 rootfs_initcall(ir_dev_scope_init);
 
@@ -878,23 +899,27 @@ static int intel_setup_ioapic_entry(int irq,
 				    struct io_apic_irq_attr *attr)
 {
 	int ioapic_id = mpc_ioapic_id(attr->ioapic);
-	struct intel_iommu *iommu = map_ioapic_to_ir(ioapic_id);
+	struct intel_iommu *iommu;
 	struct IR_IO_APIC_route_entry *entry;
 	struct irte irte;
 	int index;
 
+	down_read(&dmar_global_lock);
+	iommu = map_ioapic_to_ir(ioapic_id);
 	if (!iommu) {
 		pr_warn("No mapping iommu for ioapic %d\n", ioapic_id);
-		return -ENODEV;
-	}
-
-	entry = (struct IR_IO_APIC_route_entry *)route_entry;
-
-	index = alloc_irte(iommu, irq, 1);
-	if (index < 0) {
-		pr_warn("Failed to allocate IRTE for ioapic %d\n", ioapic_id);
-		return -ENOMEM;
+		index = -ENODEV;
+	} else {
+		index = alloc_irte(iommu, irq, 1);
+		if (index < 0) {
+			pr_warn("Failed to allocate IRTE for ioapic %d\n",
+				ioapic_id);
+			index = -ENOMEM;
+		}
 	}
+	up_read(&dmar_global_lock);
+	if (index < 0)
+		return index;
 
 	prepare_irte(&irte, vector, destination);
 
@@ -913,6 +938,7 @@ static int intel_setup_ioapic_entry(int irq,
 		irte.avail, irte.vector, irte.dest_id,
 		irte.sid, irte.sq, irte.svt);
 
+	entry = (struct IR_IO_APIC_route_entry *)route_entry;
 	memset(entry, 0, sizeof(*entry));
 
 	entry->index2	= (index >> 15) & 0x1;
@@ -1043,20 +1069,23 @@ static int intel_msi_alloc_irq(struct pci_dev *dev, int irq, int nvec)
 	struct intel_iommu *iommu;
 	int index;
 
+	down_read(&dmar_global_lock);
 	iommu = map_dev_to_ir(dev);
 	if (!iommu) {
 		printk(KERN_ERR
 		       "Unable to map PCI %s to iommu\n", pci_name(dev));
-		return -ENOENT;
+		index = -ENOENT;
+	} else {
+		index = alloc_irte(iommu, irq, nvec);
+		if (index < 0) {
+			printk(KERN_ERR
+			       "Unable to allocate %d IRTE for PCI %s\n",
+			       nvec, pci_name(dev));
+			index = -ENOSPC;
+		}
 	}
+	up_read(&dmar_global_lock);
 
-	index = alloc_irte(iommu, irq, nvec);
-	if (index < 0) {
-		printk(KERN_ERR
-		       "Unable to allocate %d IRTE for PCI %s\n", nvec,
-		       pci_name(dev));
-		return -ENOSPC;
-	}
 	return index;
 }
 
@@ -1064,33 +1093,40 @@ static int intel_msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
 			       int index, int sub_handle)
 {
 	struct intel_iommu *iommu;
+	int ret = -ENOENT;
 
+	down_read(&dmar_global_lock);
 	iommu = map_dev_to_ir(pdev);
-	if (!iommu)
-		return -ENOENT;
-	/*
-	 * setup the mapping between the irq and the IRTE
-	 * base index, the sub_handle pointing to the
-	 * appropriate interrupt remap table entry.
-	 */
-	set_irte_irq(irq, iommu, index, sub_handle);
+	if (iommu) {
+		/*
+		 * setup the mapping between the irq and the IRTE
+		 * base index, the sub_handle pointing to the
+		 * appropriate interrupt remap table entry.
+		 */
+		set_irte_irq(irq, iommu, index, sub_handle);
+		ret = 0;
+	}
+	up_read(&dmar_global_lock);
 
-	return 0;
+	return ret;
 }
 
 static int intel_setup_hpet_msi(unsigned int irq, unsigned int id)
 {
-	struct intel_iommu *iommu = map_hpet_to_ir(id);
+	int ret = -1;
+	struct intel_iommu *iommu;
 	int index;
 
-	if (!iommu)
-		return -1;
-
-	index = alloc_irte(iommu, irq, 1);
-	if (index < 0)
-		return -1;
+	down_read(&dmar_global_lock);
+	iommu = map_hpet_to_ir(id);
+	if (iommu) {
+		index = alloc_irte(iommu, irq, 1);
+		if (index >= 0)
+			ret = 0;
+	}
+	up_read(&dmar_global_lock);
 
-	return 0;
+	return ret;
 }
 
 struct irq_remap_ops intel_irq_remap_ops = {

drivers/iommu/iova.c

@@ -342,19 +342,30 @@ __is_range_overlap(struct rb_node *node,
 	return 0;
 }
 
+static inline struct iova *
+alloc_and_init_iova(unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct iova *iova;
+
+	iova = alloc_iova_mem();
+	if (iova) {
+		iova->pfn_lo = pfn_lo;
+		iova->pfn_hi = pfn_hi;
+	}
+
+	return iova;
+}
+
 static struct iova *
 __insert_new_range(struct iova_domain *iovad,
 	unsigned long pfn_lo, unsigned long pfn_hi)
 {
 	struct iova *iova;
 
-	iova = alloc_iova_mem();
-	if (!iova)
-		return iova;
+	iova = alloc_and_init_iova(pfn_lo, pfn_hi);
+	if (iova)
+		iova_insert_rbtree(&iovad->rbroot, iova);
 
-	iova->pfn_hi = pfn_hi;
-	iova->pfn_lo = pfn_lo;
-	iova_insert_rbtree(&iovad->rbroot, iova);
 	return iova;
 }
 
@@ -433,3 +444,44 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 	}
 	spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
 }
+
+struct iova *
+split_and_remove_iova(struct iova_domain *iovad, struct iova *iova,
+		      unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	unsigned long flags;
+	struct iova *prev = NULL, *next = NULL;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	if (iova->pfn_lo < pfn_lo) {
+		prev = alloc_and_init_iova(iova->pfn_lo, pfn_lo - 1);
+		if (prev == NULL)
+			goto error;
+	}
+	if (iova->pfn_hi > pfn_hi) {
+		next = alloc_and_init_iova(pfn_hi + 1, iova->pfn_hi);
+		if (next == NULL)
+			goto error;
+	}
+
+	__cached_rbnode_delete_update(iovad, iova);
+	rb_erase(&iova->node, &iovad->rbroot);
+
+	if (prev) {
+		iova_insert_rbtree(&iovad->rbroot, prev);
+		iova->pfn_lo = pfn_lo;
+	}
+	if (next) {
+		iova_insert_rbtree(&iovad->rbroot, next);
+		iova->pfn_hi = pfn_hi;
+	}
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+
+	return iova;
+
+error:
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	if (prev)
+		free_iova_mem(prev);
+	return NULL;
+}

drivers/iommu/omap-iommu.c

@@ -23,6 +23,9 @@
 #include <linux/spinlock.h>
 #include <linux/io.h>
 #include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/of_iommu.h>
+#include <linux/of_irq.h>
 
 #include <asm/cacheflush.h>
 
@@ -146,13 +149,10 @@ static int iommu_enable(struct omap_iommu *obj)
 	struct platform_device *pdev = to_platform_device(obj->dev);
 	struct iommu_platform_data *pdata = pdev->dev.platform_data;
 
-	if (!pdata)
-		return -EINVAL;
-
 	if (!arch_iommu)
 		return -ENODEV;
 
-	if (pdata->deassert_reset) {
+	if (pdata && pdata->deassert_reset) {
 		err = pdata->deassert_reset(pdev, pdata->reset_name);
 		if (err) {
 			dev_err(obj->dev, "deassert_reset failed: %d\n", err);
@@ -172,14 +172,11 @@ static void iommu_disable(struct omap_iommu *obj)
 	struct platform_device *pdev = to_platform_device(obj->dev);
 	struct iommu_platform_data *pdata = pdev->dev.platform_data;
 
-	if (!pdata)
-		return;
-
 	arch_iommu->disable(obj);
 
 	pm_runtime_put_sync(obj->dev);
 
-	if (pdata->assert_reset)
+	if (pdata && pdata->assert_reset)
 		pdata->assert_reset(pdev, pdata->reset_name);
 }
 
@@ -523,7 +520,8 @@ static void flush_iopte_range(u32 *first, u32 *last)
 static void iopte_free(u32 *iopte)
 {
 	/* Note: freed iopte's must be clean ready for re-use */
-	kmem_cache_free(iopte_cachep, iopte);
+	if (iopte)
+		kmem_cache_free(iopte_cachep, iopte);
 }
 
 static u32 *iopte_alloc(struct omap_iommu *obj, u32 *iopgd, u32 da)
@@ -863,7 +861,7 @@ static int device_match_by_alias(struct device *dev, void *data)
  **/
 static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd)
 {
-	int err = -ENOMEM;
+	int err;
 	struct device *dev;
 	struct omap_iommu *obj;
 
@@ -871,7 +869,7 @@ static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd)
 				(void *)name,
 				device_match_by_alias);
 	if (!dev)
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	obj = to_iommu(dev);
 
@@ -890,8 +888,10 @@ static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd)
 		goto err_enable;
 	flush_iotlb_all(obj);
 
-	if (!try_module_get(obj->owner))
+	if (!try_module_get(obj->owner)) {
+		err = -ENODEV;
 		goto err_module;
+	}
 
 	spin_unlock(&obj->iommu_lock);
 
@@ -940,17 +940,41 @@ static int omap_iommu_probe(struct platform_device *pdev)
 	struct omap_iommu *obj;
 	struct resource *res;
 	struct iommu_platform_data *pdata = pdev->dev.platform_data;
+	struct device_node *of = pdev->dev.of_node;
 
-	obj = kzalloc(sizeof(*obj) + MMU_REG_SIZE, GFP_KERNEL);
+	obj = devm_kzalloc(&pdev->dev, sizeof(*obj) + MMU_REG_SIZE, GFP_KERNEL);
 	if (!obj)
 		return -ENOMEM;
 
-	obj->nr_tlb_entries = pdata->nr_tlb_entries;
-	obj->name = pdata->name;
+	if (of) {
+		obj->name = dev_name(&pdev->dev);
+		obj->nr_tlb_entries = 32;
+		err = of_property_read_u32(of, "ti,#tlb-entries",
+					   &obj->nr_tlb_entries);
+		if (err && err != -EINVAL)
+			return err;
+		if (obj->nr_tlb_entries != 32 && obj->nr_tlb_entries != 8)
+			return -EINVAL;
+		/*
+		 * da_start and da_end are needed for omap-iovmm, so hardcode
+		 * these values as used by OMAP3 ISP - the only user for
+		 * omap-iovmm
+		 */
+		obj->da_start = 0;
+		obj->da_end = 0xfffff000;
+		if (of_find_property(of, "ti,iommu-bus-err-back", NULL))
+			obj->has_bus_err_back = MMU_GP_REG_BUS_ERR_BACK_EN;
+	} else {
+		obj->nr_tlb_entries = pdata->nr_tlb_entries;
+		obj->name = pdata->name;
+		obj->da_start = pdata->da_start;
+		obj->da_end = pdata->da_end;
+	}
+	if (obj->da_end <= obj->da_start)
+		return -EINVAL;
+
 	obj->dev = &pdev->dev;
 	obj->ctx = (void *)obj + sizeof(*obj);
-	obj->da_start = pdata->da_start;
-	obj->da_end = pdata->da_end;
 
 	spin_lock_init(&obj->iommu_lock);
 	mutex_init(&obj->mmap_lock);
@@ -958,33 +982,18 @@ static int omap_iommu_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&obj->mmap);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		err = -ENODEV;
-		goto err_mem;
-	}
-
-	res = request_mem_region(res->start, resource_size(res),
-				 dev_name(&pdev->dev));
-	if (!res) {
-		err = -EIO;
-		goto err_mem;
-	}
-
-	obj->regbase = ioremap(res->start, resource_size(res));
-	if (!obj->regbase) {
-		err = -ENOMEM;
-		goto err_ioremap;
-	}
+	obj->regbase = devm_ioremap_resource(obj->dev, res);
+	if (IS_ERR(obj->regbase))
+		return PTR_ERR(obj->regbase);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		err = -ENODEV;
-		goto err_irq;
-	}
-	err = request_irq(irq, iommu_fault_handler, IRQF_SHARED,
-			  dev_name(&pdev->dev), obj);
+	if (irq < 0)
+		return -ENODEV;
+
+	err = devm_request_irq(obj->dev, irq, iommu_fault_handler, IRQF_SHARED,
+			       dev_name(obj->dev), obj);
 	if (err < 0)
-		goto err_irq;
+		return err;
 	platform_set_drvdata(pdev, obj);
 
 	pm_runtime_irq_safe(obj->dev);
@@ -992,42 +1001,34 @@ static int omap_iommu_probe(struct platform_device *pdev)
 
 	dev_info(&pdev->dev, "%s registered\n", obj->name);
 	return 0;
-
-err_irq:
-	iounmap(obj->regbase);
-err_ioremap:
-	release_mem_region(res->start, resource_size(res));
-err_mem:
-	kfree(obj);
-	return err;
 }
 
 static int omap_iommu_remove(struct platform_device *pdev)
 {
-	int irq;
-	struct resource *res;
 	struct omap_iommu *obj = platform_get_drvdata(pdev);
 
 	iopgtable_clear_entry_all(obj);
 
-	irq = platform_get_irq(pdev, 0);
-	free_irq(irq, obj);
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(res->start, resource_size(res));
-	iounmap(obj->regbase);
-
 	pm_runtime_disable(obj->dev);
 
 	dev_info(&pdev->dev, "%s removed\n", obj->name);
-	kfree(obj);
 	return 0;
 }
 
+static struct of_device_id omap_iommu_of_match[] = {
+	{ .compatible = "ti,omap2-iommu" },
+	{ .compatible = "ti,omap4-iommu" },
+	{ .compatible = "ti,dra7-iommu"	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, omap_iommu_of_match);
+
 static struct platform_driver omap_iommu_driver = {
 	.probe	= omap_iommu_probe,
 	.remove	= omap_iommu_remove,
 	.driver	= {
 		.name	= "omap-iommu",
+		.of_match_table = of_match_ptr(omap_iommu_of_match),
 	},
 };
 
@@ -1253,6 +1254,49 @@ static int omap_iommu_domain_has_cap(struct iommu_domain *domain,
 	return 0;
 }
 
+static int omap_iommu_add_device(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data;
+	struct device_node *np;
+
+	/*
+	 * Allocate the archdata iommu structure for DT-based devices.
+	 *
+	 * TODO: Simplify this when removing non-DT support completely from the
+	 * IOMMU users.
+	 */
+	if (!dev->of_node)
+		return 0;
+
+	np = of_parse_phandle(dev->of_node, "iommus", 0);
+	if (!np)
+		return 0;
+
+	arch_data = kzalloc(sizeof(*arch_data), GFP_KERNEL);
+	if (!arch_data) {
+		of_node_put(np);
+		return -ENOMEM;
+	}
+
+	arch_data->name = kstrdup(dev_name(dev), GFP_KERNEL);
+	dev->archdata.iommu = arch_data;
+
+	of_node_put(np);
+
+	return 0;
+}
+
+static void omap_iommu_remove_device(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+
+	if (!dev->of_node || !arch_data)
+		return;
+
+	kfree(arch_data->name);
+	kfree(arch_data);
+}
+
 static struct iommu_ops omap_iommu_ops = {
 	.domain_init	= omap_iommu_domain_init,
 	.domain_destroy	= omap_iommu_domain_destroy,
@@ -1262,6 +1306,8 @@ static struct iommu_ops omap_iommu_ops = {
 	.unmap		= omap_iommu_unmap,
 	.iova_to_phys	= omap_iommu_iova_to_phys,
 	.domain_has_cap	= omap_iommu_domain_has_cap,
+	.add_device	= omap_iommu_add_device,
+	.remove_device	= omap_iommu_remove_device,
 	.pgsize_bitmap	= OMAP_IOMMU_PGSIZES,
 };
 

drivers/iommu/omap-iommu.h

@@ -52,6 +52,8 @@ struct omap_iommu {
 	void *ctx; /* iommu context: registres saved area */
 	u32 da_start;
 	u32 da_end;
+
+	int has_bus_err_back;
 };
 
 struct cr_regs {
@@ -130,6 +132,7 @@ static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev)
 #define MMU_READ_CAM		0x68
 #define MMU_READ_RAM		0x6c
 #define MMU_EMU_FAULT_AD	0x70
+#define MMU_GP_REG		0x88
 
 #define MMU_REG_SIZE		256
 
@@ -163,6 +166,8 @@ static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev)
 #define MMU_RAM_MIXED_MASK	(1 << MMU_RAM_MIXED_SHIFT)
 #define MMU_RAM_MIXED		MMU_RAM_MIXED_MASK
 
+#define MMU_GP_REG_BUS_ERR_BACK_EN	0x1
+
 /*
  * utilities for super page(16MB, 1MB, 64KB and 4KB)
  */

drivers/iommu/omap-iommu2.c

@@ -98,6 +98,9 @@ static int omap2_iommu_enable(struct omap_iommu *obj)
 
 	iommu_write_reg(obj, pa, MMU_TTB);
 
+	if (obj->has_bus_err_back)
+		iommu_write_reg(obj, MMU_GP_REG_BUS_ERR_BACK_EN, MMU_GP_REG);
+
 	__iommu_set_twl(obj, true);
 
 	return 0;

include/acpi/actbl2.h

@@ -424,7 +424,8 @@ enum acpi_dmar_type {
 	ACPI_DMAR_TYPE_RESERVED_MEMORY = 1,
 	ACPI_DMAR_TYPE_ATSR = 2,
 	ACPI_DMAR_HARDWARE_AFFINITY = 3,
-	ACPI_DMAR_TYPE_RESERVED = 4	/* 4 and greater are reserved */
+	ACPI_DMAR_TYPE_ANDD = 4,
+	ACPI_DMAR_TYPE_RESERVED = 5	/* 5 and greater are reserved */
 };
 
 /* DMAR Device Scope structure */
@@ -445,7 +446,8 @@ enum acpi_dmar_scope_type {
 	ACPI_DMAR_SCOPE_TYPE_BRIDGE = 2,
 	ACPI_DMAR_SCOPE_TYPE_IOAPIC = 3,
 	ACPI_DMAR_SCOPE_TYPE_HPET = 4,
-	ACPI_DMAR_SCOPE_TYPE_RESERVED = 5	/* 5 and greater are reserved */
+	ACPI_DMAR_SCOPE_TYPE_ACPI = 5,
+	ACPI_DMAR_SCOPE_TYPE_RESERVED = 6	/* 6 and greater are reserved */
 };
 
 struct acpi_dmar_pci_path {
@@ -507,6 +509,15 @@ struct acpi_dmar_rhsa {
 	u32 proximity_domain;
 };
 
+/* 4: ACPI Namespace Device Declaration Structure */
+
+struct acpi_dmar_andd {
+	struct acpi_dmar_header header;
+	u8 reserved[3];
+	u8 device_number;
+	u8 object_name[];
+};
+
 /*******************************************************************************
  *
  * HPET - High Precision Event Timer table

include/linux/dmar.h

@@ -25,6 +25,8 @@
 #include <linux/types.h>
 #include <linux/msi.h>
 #include <linux/irqreturn.h>
+#include <linux/rwsem.h>
+#include <linux/rcupdate.h>
 
 struct acpi_dmar_header;
 
@@ -34,13 +36,19 @@ struct acpi_dmar_header;
 
 struct intel_iommu;
 
+struct dmar_dev_scope {
+	struct device __rcu *dev;
+	u8 bus;
+	u8 devfn;
+};
+
 #ifdef CONFIG_DMAR_TABLE
 extern struct acpi_table_header *dmar_tbl;
 struct dmar_drhd_unit {
 	struct list_head list;		/* list of drhd units	*/
 	struct  acpi_dmar_header *hdr;	/* ACPI header		*/
 	u64	reg_base_addr;		/* register base address*/
-	struct	pci_dev **devices; 	/* target device array	*/
+	struct	dmar_dev_scope *devices;/* target device array	*/
 	int	devices_cnt;		/* target device count	*/
 	u16	segment;		/* PCI domain		*/
 	u8	ignored:1; 		/* ignore drhd		*/
@@ -48,33 +56,66 @@ struct dmar_drhd_unit {
 	struct intel_iommu *iommu;
 };
 
+struct dmar_pci_notify_info {
+	struct pci_dev			*dev;
+	unsigned long			event;
+	int				bus;
+	u16				seg;
+	u16				level;
+	struct acpi_dmar_pci_path	path[];
+}  __attribute__((packed));
+
+extern struct rw_semaphore dmar_global_lock;
 extern struct list_head dmar_drhd_units;
 
 #define for_each_drhd_unit(drhd) \
-	list_for_each_entry(drhd, &dmar_drhd_units, list)
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)
 
 #define for_each_active_drhd_unit(drhd)					\
-	list_for_each_entry(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
 		if (drhd->ignored) {} else
 
 #define for_each_active_iommu(i, drhd)					\
-	list_for_each_entry(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
 		if (i=drhd->iommu, drhd->ignored) {} else
 
 #define for_each_iommu(i, drhd)						\
-	list_for_each_entry(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
 		if (i=drhd->iommu, 0) {} else 
 
+static inline bool dmar_rcu_check(void)
+{
+	return rwsem_is_locked(&dmar_global_lock) ||
+	       system_state == SYSTEM_BOOTING;
+}
+
+#define	dmar_rcu_dereference(p)	rcu_dereference_check((p), dmar_rcu_check())
+
+#define	for_each_dev_scope(a, c, p, d)	\
+	for ((p) = 0; ((d) = (p) < (c) ? dmar_rcu_dereference((a)[(p)].dev) : \
+			NULL, (p) < (c)); (p)++)
+
+#define	for_each_active_dev_scope(a, c, p, d)	\
+	for_each_dev_scope((a), (c), (p), (d))	if (!(d)) { continue; } else
+
 extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
 extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
-				struct pci_dev ***devices, u16 segment);
-extern void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt);
-
+				struct dmar_dev_scope **devices, u16 segment);
+extern void *dmar_alloc_dev_scope(void *start, void *end, int *cnt);
+extern void dmar_free_dev_scope(struct dmar_dev_scope **devices, int *cnt);
+extern int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
+				 void *start, void*end, u16 segment,
+				 struct dmar_dev_scope *devices,
+				 int devices_cnt);
+extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info,
+				 u16 segment, struct dmar_dev_scope *devices,
+				 int count);
 /* Intel IOMMU detection */
 extern int detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
 #else
+struct dmar_pci_notify_info;
 static inline int detect_intel_iommu(void)
 {
 	return -ENODEV;
@@ -138,30 +179,9 @@ extern int arch_setup_dmar_msi(unsigned int irq);
 
 #ifdef CONFIG_INTEL_IOMMU
 extern int iommu_detected, no_iommu;
-extern struct list_head dmar_rmrr_units;
-struct dmar_rmrr_unit {
-	struct list_head list;		/* list of rmrr units	*/
-	struct acpi_dmar_header *hdr;	/* ACPI header		*/
-	u64	base_address;		/* reserved base address*/
-	u64	end_address;		/* reserved end address */
-	struct pci_dev **devices;	/* target devices */
-	int	devices_cnt;		/* target device count */
-};
-
-#define for_each_rmrr_units(rmrr) \
-	list_for_each_entry(rmrr, &dmar_rmrr_units, list)
-
-struct dmar_atsr_unit {
-	struct list_head list;		/* list of ATSR units */
-	struct acpi_dmar_header *hdr;	/* ACPI header */
-	struct pci_dev **devices;	/* target devices */
-	int devices_cnt;		/* target device count */
-	u8 include_all:1;		/* include all ports */
-};
-
-int dmar_parse_rmrr_atsr_dev(void);
 extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header);
 extern int dmar_parse_one_atsr(struct acpi_dmar_header *header);
+extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info);
 extern int intel_iommu_init(void);
 #else /* !CONFIG_INTEL_IOMMU: */
 static inline int intel_iommu_init(void) { return -ENODEV; }
@@ -173,7 +193,7 @@ static inline int dmar_parse_one_atsr(struct acpi_dmar_header *header)
 {
 	return 0;
 }
-static inline int dmar_parse_rmrr_atsr_dev(void)
+static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 {
 	return 0;
 }

include/linux/intel-iommu.h

@@ -319,6 +319,7 @@ struct intel_iommu {
 	int		agaw; /* agaw of this iommu */
 	int		msagaw; /* max sagaw of this iommu */
 	unsigned int 	irq;
+	u16		segment;     /* PCI segment# */
 	unsigned char 	name[13];    /* Device Name */
 
 #ifdef CONFIG_INTEL_IOMMU

include/linux/iova.h

@@ -47,5 +47,7 @@ void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to);
 void init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit);
 struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
 void put_iova_domain(struct iova_domain *iovad);
+struct iova *split_and_remove_iova(struct iova_domain *iovad,
+	struct iova *iova, unsigned long pfn_lo, unsigned long pfn_hi);
 
 #endif