Merge tag 'iommu-updates-v3.19' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "This time with:

   - A new IOMMU-API call: iommu_map_sg() to map multiple non-contiguous
     pages into an IO address space with only one API call.  This allows
     certain optimizations in the IOMMU driver.

   - DMAR device hotplug in the Intel VT-d driver.  It is now possible
     to hotplug the IOMMU itself.

   - A new IOMMU driver for the Rockchip ARM platform.

   - Couple of cleanups and improvements in the OMAP IOMMU driver.

   - Nesting support for the ARM-SMMU driver.

   - Various other small cleanups and improvements.

  Please note that this time some branches were also pulled into other
  trees, like the DRI and the Tegra tree.  The VT-d branch was also
  pulled into tip/x86/apic.

  Some patches for the AMD IOMMUv2 driver are not in the IOMMU tree but
  were merged by Andrew (or finally ended up in the DRI tree)"

* tag 'iommu-updates-v3.19' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (42 commits)
  iommu: Decouple iommu_map_sg from CPU page size
  iommu/vt-d: Fix an off-by-one bug in __domain_mapping()
  pci, ACPI, iommu: Enhance pci_root to support DMAR device hotplug
  iommu/vt-d: Enhance intel-iommu driver to support DMAR unit hotplug
  iommu/vt-d: Enhance error recovery in function intel_enable_irq_remapping()
  iommu/vt-d: Enhance intel_irq_remapping driver to support DMAR unit hotplug
  iommu/vt-d: Search for ACPI _DSM method for DMAR hotplug
  iommu/vt-d: Implement DMAR unit hotplug framework
  iommu/vt-d: Dynamically allocate and free seq_id for DMAR units
  iommu/vt-d: Introduce helper function dmar_walk_resources()
  iommu/arm-smmu: add support for DOMAIN_ATTR_NESTING attribute
  iommu/arm-smmu: Play nice on non-ARM/SMMU systems
  iommu/amd: remove compiler warning due to IOMMU_CAP_NOEXEC
  iommu/arm-smmu: add IOMMU_CAP_NOEXEC to the ARM SMMU driver
  iommu: add capability IOMMU_CAP_NOEXEC
  iommu/arm-smmu: change IOMMU_EXEC to IOMMU_NOEXEC
  iommu/amd: Fix accounting of device_state
  x86/vt-d: Fix incorrect bit operations in setting values
  iommu/rockchip: Allow to compile with COMPILE_TEST
  iommu/ipmmu-vmsa: Return proper error if devm_request_irq fails
  ...

17 files changed, 2346 insertions, 976 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 6dbfbc209491..30f0e61341c5 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -144,13 +144,26 @@ config OMAP_IOMMU
 	select IOMMU_API
 
 config OMAP_IOMMU_DEBUG
-       tristate "Export OMAP IOMMU internals in DebugFS"
-       depends on OMAP_IOMMU && DEBUG_FS
-       help
-         Select this to see extensive information about
-         the internal state of OMAP IOMMU in debugfs.
+	bool "Export OMAP IOMMU internals in DebugFS"
+	depends on OMAP_IOMMU && DEBUG_FS
+	---help---
+	  Select this to see extensive information about
+	  the internal state of OMAP IOMMU in debugfs.
+
+	  Say N unless you know you need this.
 
-         Say N unless you know you need this.
+config ROCKCHIP_IOMMU
+	bool "Rockchip IOMMU Support"
+	depends on ARM
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
+	select IOMMU_API
+	select ARM_DMA_USE_IOMMU
+	help
+	  Support for IOMMUs found on Rockchip rk32xx SOCs.
+	  These IOMMUs allow virtualization of the address space used by most
+	  cores within the multimedia subsystem.
+	  Say Y here if you are using a Rockchip SoC that includes an IOMMU
+	  device.
 
 config TEGRA_IOMMU_GART
 	bool "Tegra GART IOMMU Support"
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 16edef74b8ee..7b976f294a69 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -11,8 +11,8 @@ obj-$(CONFIG_INTEL_IOMMU) += iova.o intel-iommu.o
 obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
 obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o
 obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o
-obj-$(CONFIG_OMAP_IOMMU) += omap-iommu2.o
 obj-$(CONFIG_OMAP_IOMMU_DEBUG) += omap-iommu-debug.o
+obj-$(CONFIG_ROCKCHIP_IOMMU) += rockchip-iommu.o
 obj-$(CONFIG_TEGRA_IOMMU_GART) += tegra-gart.o
 obj-$(CONFIG_TEGRA_IOMMU_SMMU) += tegra-smmu.o
 obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 2d84c9edf3b8..b205f76d7129 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3411,6 +3411,8 @@ static bool amd_iommu_capable(enum iommu_cap cap)
 		return true;
 	case IOMMU_CAP_INTR_REMAP:
 		return (irq_remapping_enabled == 1);
+	case IOMMU_CAP_NOEXEC:
+		return false;
 	}
 
 	return false;
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 90d734bbf467..a2d87a60c27f 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -279,10 +279,8 @@ static void free_pasid_state(struct pasid_state *pasid_state)
 
 static void put_pasid_state(struct pasid_state *pasid_state)
 {
-	if (atomic_dec_and_test(&pasid_state->count)) {
-		put_device_state(pasid_state->device_state);
+	if (atomic_dec_and_test(&pasid_state->count))
 		wake_up(&pasid_state->wq);
-	}
 }
 
 static void put_pasid_state_wait(struct pasid_state *pasid_state)
@@ -291,9 +289,7 @@ static void put_pasid_state_wait(struct pasid_state *pasid_state)
 
 	prepare_to_wait(&pasid_state->wq, &wait, TASK_UNINTERRUPTIBLE);
 
-	if (atomic_dec_and_test(&pasid_state->count))
-		put_device_state(pasid_state->device_state);
-	else
+	if (!atomic_dec_and_test(&pasid_state->count))
 		schedule();
 
 	finish_wait(&pasid_state->wq, &wait);
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index e393ae01b5d2..b8aac1389a96 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -404,9 +404,16 @@ struct arm_smmu_cfg {
 #define ARM_SMMU_CB_ASID(cfg)		((cfg)->cbndx)
 #define ARM_SMMU_CB_VMID(cfg)		((cfg)->cbndx + 1)
 
+enum arm_smmu_domain_stage {
+	ARM_SMMU_DOMAIN_S1 = 0,
+	ARM_SMMU_DOMAIN_S2,
+	ARM_SMMU_DOMAIN_NESTED,
+};
+
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
 	struct arm_smmu_cfg		cfg;
+	enum arm_smmu_domain_stage	stage;
 	spinlock_t			lock;
 };
 
@@ -906,19 +913,46 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (smmu_domain->smmu)
 		goto out_unlock;
 
-	if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) {
+	/*
+	 * Mapping the requested stage onto what we support is surprisingly
+	 * complicated, mainly because the spec allows S1+S2 SMMUs without
+	 * support for nested translation. That means we end up with the
+	 * following table:
+	 *
+	 * Requested        Supported        Actual
+	 *     S1               N              S1
+	 *     S1             S1+S2            S1
+	 *     S1               S2             S2
+	 *     S1               S1             S1
+	 *     N                N              N
+	 *     N              S1+S2            S2
+	 *     N                S2             S2
+	 *     N                S1             S1
+	 *
+	 * Note that you can't actually request stage-2 mappings.
+	 */
+	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
+	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S2))
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+
+	switch (smmu_domain->stage) {
+	case ARM_SMMU_DOMAIN_S1:
+		cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
+		start = smmu->num_s2_context_banks;
+		break;
+	case ARM_SMMU_DOMAIN_NESTED:
 		/*
 		 * We will likely want to change this if/when KVM gets
 		 * involved.
 		 */
-		cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
-		start = smmu->num_s2_context_banks;
-	} else if (smmu->features & ARM_SMMU_FEAT_TRANS_S1) {
-		cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
-		start = smmu->num_s2_context_banks;
-	} else {
+	case ARM_SMMU_DOMAIN_S2:
 		cfg->cbar = CBAR_TYPE_S2_TRANS;
 		start = 0;
+		break;
+	default:
+		ret = -EINVAL;
+		goto out_unlock;
 	}
 
 	ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
@@ -1281,7 +1315,7 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 				   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;
+	pteval_t pteval = ARM_SMMU_PTE_PAGE | ARM_SMMU_PTE_AF;
 
 	if (pmd_none(*pmd)) {
 		/* Allocate a new set of tables */
@@ -1315,10 +1349,11 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 			pteval |= ARM_SMMU_PTE_MEMATTR_NC;
 	}
 
+	if (prot & IOMMU_NOEXEC)
+		pteval |= ARM_SMMU_PTE_XN;
+
 	/* If no access, create a faulting entry to avoid TLB fills */
-	if (prot & IOMMU_EXEC)
-		pteval &= ~ARM_SMMU_PTE_XN;
-	else if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
+	if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
 		pteval &= ~ARM_SMMU_PTE_PAGE;
 
 	pteval |= ARM_SMMU_PTE_SH_IS;
@@ -1568,6 +1603,8 @@ static bool arm_smmu_capable(enum iommu_cap cap)
 		return true;
 	case IOMMU_CAP_INTR_REMAP:
 		return true; /* MSIs are just memory writes */
+	case IOMMU_CAP_NOEXEC:
+		return true;
 	default:
 		return false;
 	}
@@ -1644,21 +1681,57 @@ static void arm_smmu_remove_device(struct device *dev)
 	iommu_group_remove_device(dev);
 }
 
+static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
+				    enum iommu_attr attr, void *data)
+{
+	struct arm_smmu_domain *smmu_domain = domain->priv;
+
+	switch (attr) {
+	case DOMAIN_ATTR_NESTING:
+		*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
+		return 0;
+	default:
+		return -ENODEV;
+	}
+}
+
+static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
+				    enum iommu_attr attr, void *data)
+{
+	struct arm_smmu_domain *smmu_domain = domain->priv;
+
+	switch (attr) {
+	case DOMAIN_ATTR_NESTING:
+		if (smmu_domain->smmu)
+			return -EPERM;
+		if (*(int *)data)
+			smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+		else
+			smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+
+		return 0;
+	default:
+		return -ENODEV;
+	}
+}
+
 static const struct iommu_ops arm_smmu_ops = {
-	.capable	= arm_smmu_capable,
-	.domain_init	= arm_smmu_domain_init,
-	.domain_destroy	= arm_smmu_domain_destroy,
-	.attach_dev	= arm_smmu_attach_dev,
-	.detach_dev	= arm_smmu_detach_dev,
-	.map		= arm_smmu_map,
-	.unmap		= arm_smmu_unmap,
-	.map_sg		= default_iommu_map_sg,
-	.iova_to_phys	= arm_smmu_iova_to_phys,
-	.add_device	= arm_smmu_add_device,
-	.remove_device	= arm_smmu_remove_device,
-	.pgsize_bitmap	= (SECTION_SIZE |
-			   ARM_SMMU_PTE_CONT_SIZE |
-			   PAGE_SIZE),
+	.capable		= arm_smmu_capable,
+	.domain_init		= arm_smmu_domain_init,
+	.domain_destroy		= arm_smmu_domain_destroy,
+	.attach_dev		= arm_smmu_attach_dev,
+	.detach_dev		= arm_smmu_detach_dev,
+	.map			= arm_smmu_map,
+	.unmap			= arm_smmu_unmap,
+	.map_sg			= default_iommu_map_sg,
+	.iova_to_phys		= arm_smmu_iova_to_phys,
+	.add_device		= arm_smmu_add_device,
+	.remove_device		= arm_smmu_remove_device,
+	.domain_get_attr	= arm_smmu_domain_get_attr,
+	.domain_set_attr	= arm_smmu_domain_set_attr,
+	.pgsize_bitmap		= (SECTION_SIZE |
+				   ARM_SMMU_PTE_CONT_SIZE |
+				   PAGE_SIZE),
 };
 
 static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
@@ -2073,8 +2146,20 @@ static struct platform_driver arm_smmu_driver = {
 
 static int __init arm_smmu_init(void)
 {
+	struct device_node *np;
 	int ret;
 
+	/*
+	 * Play nice with systems that don't have an ARM SMMU by checking that
+	 * an ARM SMMU exists in the system before proceeding with the driver
+	 * and IOMMU bus operation registration.
+	 */
+	np = of_find_matching_node(NULL, arm_smmu_of_match);
+	if (!np)
+		return 0;
+
+	of_node_put(np);
+
 	ret = platform_driver_register(&arm_smmu_driver);
 	if (ret)
 		return ret;
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index c5c61cabd6e3..9847613085e1 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -44,6 +44,14 @@
 
 #include "irq_remapping.h"
 
+typedef int (*dmar_res_handler_t)(struct acpi_dmar_header *, void *);
+struct dmar_res_callback {
+	dmar_res_handler_t	cb[ACPI_DMAR_TYPE_RESERVED];
+	void			*arg[ACPI_DMAR_TYPE_RESERVED];
+	bool			ignore_unhandled;
+	bool			print_entry;
+};
+
 /*
  * Assumptions:
  * 1) The hotplug framework guarentees that DMAR unit will be hot-added
@@ -62,11 +70,12 @@ 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 unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
 
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
 static void free_iommu(struct intel_iommu *iommu);
 
-static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
+static void dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 {
 	/*
 	 * add INCLUDE_ALL at the tail, so scan the list will find it at
@@ -344,24 +353,45 @@ static struct notifier_block dmar_pci_bus_nb = {
 	.priority = INT_MIN,
 };
 
+static struct dmar_drhd_unit *
+dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list)
+		if (dmaru->segment == drhd->segment &&
+		    dmaru->reg_base_addr == drhd->address)
+			return dmaru;
+
+	return NULL;
+}
+
 /**
  * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
  * structure which uniquely represent one DMA remapping hardware unit
  * present in the platform
  */
-static int __init
-dmar_parse_one_drhd(struct acpi_dmar_header *header)
+static int dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_hardware_unit *drhd;
 	struct dmar_drhd_unit *dmaru;
 	int ret = 0;
 
 	drhd = (struct acpi_dmar_hardware_unit *)header;
-	dmaru = kzalloc(sizeof(*dmaru), GFP_KERNEL);
+	dmaru = dmar_find_dmaru(drhd);
+	if (dmaru)
+		goto out;
+
+	dmaru = kzalloc(sizeof(*dmaru) + header->length, GFP_KERNEL);
 	if (!dmaru)
 		return -ENOMEM;
 
-	dmaru->hdr = header;
+	/*
+	 * If header is allocated from slab by ACPI _DSM method, we need to
+	 * copy the content because the memory buffer will be freed on return.
+	 */
+	dmaru->hdr = (void *)(dmaru + 1);
+	memcpy(dmaru->hdr, header, header->length);
 	dmaru->reg_base_addr = drhd->address;
 	dmaru->segment = drhd->segment;
 	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
@@ -381,6 +411,11 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header)
 		return ret;
 	}
 	dmar_register_drhd_unit(dmaru);
+
+out:
+	if (arg)
+		(*(int *)arg)++;
+
 	return 0;
 }
 
@@ -393,7 +428,8 @@ static void dmar_free_drhd(struct dmar_drhd_unit *dmaru)
 	kfree(dmaru);
 }
 
-static int __init dmar_parse_one_andd(struct acpi_dmar_header *header)
+static int __init dmar_parse_one_andd(struct acpi_dmar_header *header,
+				      void *arg)
 {
 	struct acpi_dmar_andd *andd = (void *)header;
 
@@ -414,8 +450,7 @@ static int __init dmar_parse_one_andd(struct acpi_dmar_header *header)
 }
 
 #ifdef CONFIG_ACPI_NUMA
-static int __init
-dmar_parse_one_rhsa(struct acpi_dmar_header *header)
+static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_rhsa *rhsa;
 	struct dmar_drhd_unit *drhd;
@@ -442,6 +477,8 @@ dmar_parse_one_rhsa(struct acpi_dmar_header *header)
 
 	return 0;
 }
+#else
+#define	dmar_parse_one_rhsa		dmar_res_noop
 #endif
 
 static void __init
@@ -503,6 +540,52 @@ static int __init dmar_table_detect(void)
 	return (ACPI_SUCCESS(status) ? 1 : 0);
 }
 
+static int dmar_walk_remapping_entries(struct acpi_dmar_header *start,
+				       size_t len, struct dmar_res_callback *cb)
+{
+	int ret = 0;
+	struct acpi_dmar_header *iter, *next;
+	struct acpi_dmar_header *end = ((void *)start) + len;
+
+	for (iter = start; iter < end && ret == 0; iter = next) {
+		next = (void *)iter + iter->length;
+		if (iter->length == 0) {
+			/* Avoid looping forever on bad ACPI tables */
+			pr_debug(FW_BUG "Invalid 0-length structure\n");
+			break;
+		} else if (next > end) {
+			/* Avoid passing table end */
+			pr_warn(FW_BUG "record passes table end\n");
+			ret = -EINVAL;
+			break;
+		}
+
+		if (cb->print_entry)
+			dmar_table_print_dmar_entry(iter);
+
+		if (iter->type >= ACPI_DMAR_TYPE_RESERVED) {
+			/* continue for forward compatibility */
+			pr_debug("Unknown DMAR structure type %d\n",
+				 iter->type);
+		} else if (cb->cb[iter->type]) {
+			ret = cb->cb[iter->type](iter, cb->arg[iter->type]);
+		} else if (!cb->ignore_unhandled) {
+			pr_warn("No handler for DMAR structure type %d\n",
+				iter->type);
+			ret = -EINVAL;
+		}
+	}
+
+	return ret;
+}
+
+static inline int dmar_walk_dmar_table(struct acpi_table_dmar *dmar,
+				       struct dmar_res_callback *cb)
+{
+	return dmar_walk_remapping_entries((void *)(dmar + 1),
+			dmar->header.length - sizeof(*dmar), cb);
+}
+
 /**
  * parse_dmar_table - parses the DMA reporting table
  */
@@ -510,9 +593,18 @@ static int __init
 parse_dmar_table(void)
 {
 	struct acpi_table_dmar *dmar;
-	struct acpi_dmar_header *entry_header;
 	int ret = 0;
 	int drhd_count = 0;
+	struct dmar_res_callback cb = {
+		.print_entry = true,
+		.ignore_unhandled = true,
+		.arg[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &drhd_count,
+		.cb[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &dmar_parse_one_drhd,
+		.cb[ACPI_DMAR_TYPE_RESERVED_MEMORY] = &dmar_parse_one_rmrr,
+		.cb[ACPI_DMAR_TYPE_ROOT_ATS] = &dmar_parse_one_atsr,
+		.cb[ACPI_DMAR_TYPE_HARDWARE_AFFINITY] = &dmar_parse_one_rhsa,
+		.cb[ACPI_DMAR_TYPE_NAMESPACE] = &dmar_parse_one_andd,
+	};
 
 	/*
 	 * Do it again, earlier dmar_tbl mapping could be mapped with
@@ -536,51 +628,10 @@ parse_dmar_table(void)
 	}
 
 	pr_info("Host address width %d\n", dmar->width + 1);
-
-	entry_header = (struct acpi_dmar_header *)(dmar + 1);
-	while (((unsigned long)entry_header) <
-			(((unsigned long)dmar) + dmar_tbl->length)) {
-		/* Avoid looping forever on bad ACPI tables */
-		if (entry_header->length == 0) {
-			pr_warn("Invalid 0-length structure\n");
-			ret = -EINVAL;
-			break;
-		}
-
-		dmar_table_print_dmar_entry(entry_header);
-
-		switch (entry_header->type) {
-		case ACPI_DMAR_TYPE_HARDWARE_UNIT:
-			drhd_count++;
-			ret = dmar_parse_one_drhd(entry_header);
-			break;
-		case ACPI_DMAR_TYPE_RESERVED_MEMORY:
-			ret = dmar_parse_one_rmrr(entry_header);
-			break;
-		case ACPI_DMAR_TYPE_ROOT_ATS:
-			ret = dmar_parse_one_atsr(entry_header);
-			break;
-		case ACPI_DMAR_TYPE_HARDWARE_AFFINITY:
-#ifdef CONFIG_ACPI_NUMA
-			ret = dmar_parse_one_rhsa(entry_header);
-#endif
-			break;
-		case ACPI_DMAR_TYPE_NAMESPACE:
-			ret = dmar_parse_one_andd(entry_header);
-			break;
-		default:
-			pr_warn("Unknown DMAR structure type %d\n",
-				entry_header->type);
-			ret = 0; /* for forward compatibility */
-			break;
-		}
-		if (ret)
-			break;
-
-		entry_header = ((void *)entry_header + entry_header->length);
-	}
-	if (drhd_count == 0)
+	ret = dmar_walk_dmar_table(dmar, &cb);
+	if (ret == 0 && drhd_count == 0)
 		pr_warn(FW_BUG "No DRHD structure found in DMAR table\n");
+
 	return ret;
 }
 
@@ -778,76 +829,68 @@ static void warn_invalid_dmar(u64 addr, const char *message)
 		dmi_get_system_info(DMI_PRODUCT_VERSION));
 }
 
-static int __init check_zero_address(void)
+static int __ref
+dmar_validate_one_drhd(struct acpi_dmar_header *entry, void *arg)
 {
-	struct acpi_table_dmar *dmar;
-	struct acpi_dmar_header *entry_header;
 	struct acpi_dmar_hardware_unit *drhd;
+	void __iomem *addr;
+	u64 cap, ecap;
 
-	dmar = (struct acpi_table_dmar *)dmar_tbl;
-	entry_header = (struct acpi_dmar_header *)(dmar + 1);
-
-	while (((unsigned long)entry_header) <
-			(((unsigned long)dmar) + dmar_tbl->length)) {
-		/* Avoid looping forever on bad ACPI tables */
-		if (entry_header->length == 0) {
-			pr_warn("Invalid 0-length structure\n");
-			return 0;
-		}
+	drhd = (void *)entry;
+	if (!drhd->address) {
+		warn_invalid_dmar(0, "");
+		return -EINVAL;
+	}
 
-		if (entry_header->type == ACPI_DMAR_TYPE_HARDWARE_UNIT) {
-			void __iomem *addr;
-			u64 cap, ecap;
+	if (arg)
+		addr = ioremap(drhd->address, VTD_PAGE_SIZE);
+	else
+		addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
+	if (!addr) {
+		pr_warn("IOMMU: can't validate: %llx\n", drhd->address);
+		return -EINVAL;
+	}
 
-			drhd = (void *)entry_header;
-			if (!drhd->address) {
-				warn_invalid_dmar(0, "");
-				goto failed;
-			}
+	cap = dmar_readq(addr + DMAR_CAP_REG);
+	ecap = dmar_readq(addr + DMAR_ECAP_REG);
 
-			addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
-			if (!addr ) {
-				printk("IOMMU: can't validate: %llx\n", drhd->address);
-				goto failed;
-			}
-			cap = dmar_readq(addr + DMAR_CAP_REG);
-			ecap = dmar_readq(addr + DMAR_ECAP_REG);
-			early_iounmap(addr, VTD_PAGE_SIZE);
-			if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
-				warn_invalid_dmar(drhd->address,
-						  " returns all ones");
-				goto failed;
-			}
-		}
+	if (arg)
+		iounmap(addr);
+	else
+		early_iounmap(addr, VTD_PAGE_SIZE);
 
-		entry_header = ((void *)entry_header + entry_header->length);
+	if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
+		warn_invalid_dmar(drhd->address, " returns all ones");
+		return -EINVAL;
 	}
-	return 1;
 
-failed:
 	return 0;
 }
 
 int __init detect_intel_iommu(void)
 {
 	int ret;
+	struct dmar_res_callback validate_drhd_cb = {
+		.cb[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &dmar_validate_one_drhd,
+		.ignore_unhandled = true,
+	};
 
 	down_write(&dmar_global_lock);
 	ret = dmar_table_detect();
 	if (ret)
-		ret = check_zero_address();
-	{
-		if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
-			iommu_detected = 1;
-			/* Make sure ACS will be enabled */
-			pci_request_acs();
-		}
+		ret = !dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl,
+					    &validate_drhd_cb);
+	if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
+		iommu_detected = 1;
+		/* Make sure ACS will be enabled */
+		pci_request_acs();
+	}
 
 #ifdef CONFIG_X86
-		if (ret)
-			x86_init.iommu.iommu_init = intel_iommu_init;
+	if (ret)
+		x86_init.iommu.iommu_init = intel_iommu_init;
 #endif
-	}
+
 	early_acpi_os_unmap_memory((void __iomem *)dmar_tbl, dmar_tbl_size);
 	dmar_tbl = NULL;
 	up_write(&dmar_global_lock);
@@ -931,11 +974,32 @@ out:
 	return err;
 }
 
+static int dmar_alloc_seq_id(struct intel_iommu *iommu)
+{
+	iommu->seq_id = find_first_zero_bit(dmar_seq_ids,
+					    DMAR_UNITS_SUPPORTED);
+	if (iommu->seq_id >= DMAR_UNITS_SUPPORTED) {
+		iommu->seq_id = -1;
+	} else {
+		set_bit(iommu->seq_id, dmar_seq_ids);
+		sprintf(iommu->name, "dmar%d", iommu->seq_id);
+	}
+
+	return iommu->seq_id;
+}
+
+static void dmar_free_seq_id(struct intel_iommu *iommu)
+{
+	if (iommu->seq_id >= 0) {
+		clear_bit(iommu->seq_id, dmar_seq_ids);
+		iommu->seq_id = -1;
+	}
+}
+
 static int alloc_iommu(struct dmar_drhd_unit *drhd)
 {
 	struct intel_iommu *iommu;
 	u32 ver, sts;
-	static int iommu_allocated = 0;
 	int agaw = 0;
 	int msagaw = 0;
 	int err;
@@ -949,13 +1013,16 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	if (!iommu)
 		return -ENOMEM;
 
-	iommu->seq_id = iommu_allocated++;
-	sprintf (iommu->name, "dmar%d", iommu->seq_id);
+	if (dmar_alloc_seq_id(iommu) < 0) {
+		pr_err("IOMMU: failed to allocate seq_id\n");
+		err = -ENOSPC;
+		goto error;
+	}
 
 	err = map_iommu(iommu, drhd->reg_base_addr);
 	if (err) {
 		pr_err("IOMMU: failed to map %s\n", iommu->name);
-		goto error;
+		goto error_free_seq_id;
 	}
 
 	err = -EINVAL;
@@ -1005,9 +1072,11 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 
 	return 0;
 
- err_unmap:
+err_unmap:
 	unmap_iommu(iommu);
- error:
+error_free_seq_id:
+	dmar_free_seq_id(iommu);
+error:
 	kfree(iommu);
 	return err;
 }
@@ -1031,6 +1100,7 @@ static void free_iommu(struct intel_iommu *iommu)
 	if (iommu->reg)
 		unmap_iommu(iommu);
 
+	dmar_free_seq_id(iommu);
 	kfree(iommu);
 }
 
@@ -1661,12 +1731,17 @@ int __init dmar_ir_support(void)
 	return dmar->flags & 0x1;
 }
 
+/* Check whether DMAR units are in use */
+static inline bool dmar_in_use(void)
+{
+	return irq_remapping_enabled || intel_iommu_enabled;
+}
+
 static int __init dmar_free_unused_resources(void)
 {
 	struct dmar_drhd_unit *dmaru, *dmaru_n;
 
-	/* DMAR units are in use */
-	if (irq_remapping_enabled || intel_iommu_enabled)
+	if (dmar_in_use())
 		return 0;
 
 	if (dmar_dev_scope_status != 1 && !list_empty(&dmar_drhd_units))
@@ -1684,3 +1759,242 @@ static int __init dmar_free_unused_resources(void)
 
 late_initcall(dmar_free_unused_resources);
 IOMMU_INIT_POST(detect_intel_iommu);
+
+/*
+ * DMAR Hotplug Support
+ * For more details, please refer to Intel(R) Virtualization Technology
+ * for Directed-IO Architecture Specifiction, Rev 2.2, Section 8.8
+ * "Remapping Hardware Unit Hot Plug".
+ */
+static u8 dmar_hp_uuid[] = {
+	/* 0000 */    0xA6, 0xA3, 0xC1, 0xD8, 0x9B, 0xBE, 0x9B, 0x4C,
+	/* 0008 */    0x91, 0xBF, 0xC3, 0xCB, 0x81, 0xFC, 0x5D, 0xAF
+};
+
+/*
+ * Currently there's only one revision and BIOS will not check the revision id,
+ * so use 0 for safety.
+ */
+#define	DMAR_DSM_REV_ID			0
+#define	DMAR_DSM_FUNC_DRHD		1
+#define	DMAR_DSM_FUNC_ATSR		2
+#define	DMAR_DSM_FUNC_RHSA		3
+
+static inline bool dmar_detect_dsm(acpi_handle handle, int func)
+{
+	return acpi_check_dsm(handle, dmar_hp_uuid, DMAR_DSM_REV_ID, 1 << func);
+}
+
+static int dmar_walk_dsm_resource(acpi_handle handle, int func,
+				  dmar_res_handler_t handler, void *arg)
+{
+	int ret = -ENODEV;
+	union acpi_object *obj;
+	struct acpi_dmar_header *start;
+	struct dmar_res_callback callback;
+	static int res_type[] = {
+		[DMAR_DSM_FUNC_DRHD] = ACPI_DMAR_TYPE_HARDWARE_UNIT,
+		[DMAR_DSM_FUNC_ATSR] = ACPI_DMAR_TYPE_ROOT_ATS,
+		[DMAR_DSM_FUNC_RHSA] = ACPI_DMAR_TYPE_HARDWARE_AFFINITY,
+	};
+
+	if (!dmar_detect_dsm(handle, func))
+		return 0;
+
+	obj = acpi_evaluate_dsm_typed(handle, dmar_hp_uuid, DMAR_DSM_REV_ID,
+				      func, NULL, ACPI_TYPE_BUFFER);
+	if (!obj)
+		return -ENODEV;
+
+	memset(&callback, 0, sizeof(callback));
+	callback.cb[res_type[func]] = handler;
+	callback.arg[res_type[func]] = arg;
+	start = (struct acpi_dmar_header *)obj->buffer.pointer;
+	ret = dmar_walk_remapping_entries(start, obj->buffer.length, &callback);
+
+	ACPI_FREE(obj);
+
+	return ret;
+}
+
+static int dmar_hp_add_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	int ret;
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (!dmaru)
+		return -ENODEV;
+
+	ret = dmar_ir_hotplug(dmaru, true);
+	if (ret == 0)
+		ret = dmar_iommu_hotplug(dmaru, true);
+
+	return ret;
+}
+
+static int dmar_hp_remove_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	int i, ret;
+	struct device *dev;
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (!dmaru)
+		return 0;
+
+	/*
+	 * All PCI devices managed by this unit should have been destroyed.
+	 */
+	if (!dmaru->include_all && dmaru->devices && dmaru->devices_cnt)
+		for_each_active_dev_scope(dmaru->devices,
+					  dmaru->devices_cnt, i, dev)
+			return -EBUSY;
+
+	ret = dmar_ir_hotplug(dmaru, false);
+	if (ret == 0)
+		ret = dmar_iommu_hotplug(dmaru, false);
+
+	return ret;
+}
+
+static int dmar_hp_release_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (dmaru) {
+		list_del_rcu(&dmaru->list);
+		synchronize_rcu();
+		dmar_free_drhd(dmaru);
+	}
+
+	return 0;
+}
+
+static int dmar_hotplug_insert(acpi_handle handle)
+{
+	int ret;
+	int drhd_count = 0;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_validate_one_drhd, (void *)1);
+	if (ret)
+		goto out;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_parse_one_drhd, (void *)&drhd_count);
+	if (ret == 0 && drhd_count == 0) {
+		pr_warn(FW_BUG "No DRHD structures in buffer returned by _DSM method\n");
+		goto out;
+	} else if (ret) {
+		goto release_drhd;
+	}
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_RHSA,
+				     &dmar_parse_one_rhsa, NULL);
+	if (ret)
+		goto release_drhd;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+				     &dmar_parse_one_atsr, NULL);
+	if (ret)
+		goto release_atsr;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_hp_add_drhd, NULL);
+	if (!ret)
+		return 0;
+
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+			       &dmar_hp_remove_drhd, NULL);
+release_atsr:
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+			       &dmar_release_one_atsr, NULL);
+release_drhd:
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+			       &dmar_hp_release_drhd, NULL);
+out:
+	return ret;
+}
+
+static int dmar_hotplug_remove(acpi_handle handle)
+{
+	int ret;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+				     &dmar_check_one_atsr, NULL);
+	if (ret)
+		return ret;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_hp_remove_drhd, NULL);
+	if (ret == 0) {
+		WARN_ON(dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+					       &dmar_release_one_atsr, NULL));
+		WARN_ON(dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+					       &dmar_hp_release_drhd, NULL));
+	} else {
+		dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				       &dmar_hp_add_drhd, NULL);
+	}
+
+	return ret;
+}
+
+static acpi_status dmar_get_dsm_handle(acpi_handle handle, u32 lvl,
+				       void *context, void **retval)
+{
+	acpi_handle *phdl = retval;
+
+	if (dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD)) {
+		*phdl = handle;
+		return AE_CTRL_TERMINATE;
+	}
+
+	return AE_OK;
+}
+
+static int dmar_device_hotplug(acpi_handle handle, bool insert)
+{
+	int ret;
+	acpi_handle tmp = NULL;
+	acpi_status status;
+
+	if (!dmar_in_use())