Merge tag 'iommu-updates-v4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "The updates include:

   - rate limiting for the VT-d fault handler

   - remove statistics code from the AMD IOMMU driver.  It is unused and
     should be replaced by something more generic if needed

   - per-domain pagesize-bitmaps in IOMMU core code to support systems
     with different types of IOMMUs

   - support for ACPI devices in the AMD IOMMU driver

   - 4GB mode support for Mediatek IOMMU driver

   - ARM-SMMU updates from Will Deacon:
      - support for 64k pages with SMMUv1 implementations (e.g MMU-401)
      - remove open-coded 64-bit MMIO accessors
      - initial support for 16-bit VMIDs, as supported by some ThunderX
        SMMU implementations
      - a couple of errata workarounds for silicon in the field

   - various fixes here and there"

* tag 'iommu-updates-v4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (44 commits)
  iommu/arm-smmu: Use per-domain page sizes.
  iommu/amd: Remove statistics code
  iommu/dma: Finish optimising higher-order allocations
  iommu: Allow selecting page sizes per domain
  iommu: of: enforce const-ness of struct iommu_ops
  iommu: remove unused priv field from struct iommu_ops
  iommu/dma: Implement scatterlist segment merging
  iommu/arm-smmu: Clear cache lock bit of ACR
  iommu/arm-smmu: Support SMMUv1 64KB supplement
  iommu/arm-smmu: Decouple context format from kernel config
  iommu/arm-smmu: Tidy up 64-bit/atomic I/O accesses
  io-64-nonatomic: Add relaxed accessor variants
  iommu/arm-smmu: Work around MMU-500 prefetch errata
  iommu/arm-smmu: Convert ThunderX workaround to new method
  iommu/arm-smmu: Differentiate specific implementations
  iommu/arm-smmu: Workaround for ThunderX erratum #27704
  iommu/arm-smmu: Add support for 16 bit VMID
  iommu/amd: Move get_device_id() and friends to beginning of file
  iommu/amd: Don't use IS_ERR_VALUE to check integer values
  iommu/amd: Signedness bug in acpihid_device_group()
  ...

21 files changed, 893 insertions, 395 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index dd1dc39f84ff..ad0860383cb3 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -76,8 +76,7 @@ config IOMMU_DMA
 
 config FSL_PAMU
 	bool "Freescale IOMMU support"
-	depends on PPC32
-	depends on PPC_E500MC || COMPILE_TEST
+	depends on PPC_E500MC || (COMPILE_TEST && PPC)
 	select IOMMU_API
 	select GENERIC_ALLOCATOR
 	help
@@ -124,16 +123,6 @@ config AMD_IOMMU
 	  your BIOS for an option to enable it or if you have an IVRS ACPI
 	  table.
 
-config AMD_IOMMU_STATS
-	bool "Export AMD IOMMU statistics to debugfs"
-	depends on AMD_IOMMU
-	select DEBUG_FS
-	---help---
-	  This option enables code in the AMD IOMMU driver to collect various
-	  statistics about whats happening in the driver and exports that
-	  information to userspace via debugfs.
-	  If unsure, say N.
-
 config AMD_IOMMU_V2
 	tristate "AMD IOMMU Version 2 driver"
 	depends on AMD_IOMMU
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 3839fd2865a6..634f636393d5 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -19,6 +19,8 @@
 
 #include <linux/ratelimit.h>
 #include <linux/pci.h>
+#include <linux/acpi.h>
+#include <linux/amba/bus.h>
 #include <linux/pci-ats.h>
 #include <linux/bitmap.h>
 #include <linux/slab.h>
@@ -72,6 +74,7 @@ static DEFINE_SPINLOCK(dev_data_list_lock);
 
 LIST_HEAD(ioapic_map);
 LIST_HEAD(hpet_map);
+LIST_HEAD(acpihid_map);
 
 /*
  * Domain for untranslated devices - only allocated
@@ -162,18 +165,65 @@ struct dma_ops_domain {
  *
  ****************************************************************************/
 
-static struct protection_domain *to_pdomain(struct iommu_domain *dom)
+static inline int match_hid_uid(struct device *dev,
+				struct acpihid_map_entry *entry)
 {
-	return container_of(dom, struct protection_domain, domain);
+	const char *hid, *uid;
+
+	hid = acpi_device_hid(ACPI_COMPANION(dev));
+	uid = acpi_device_uid(ACPI_COMPANION(dev));
+
+	if (!hid || !(*hid))
+		return -ENODEV;
+
+	if (!uid || !(*uid))
+		return strcmp(hid, entry->hid);
+
+	if (!(*entry->uid))
+		return strcmp(hid, entry->hid);
+
+	return (strcmp(hid, entry->hid) || strcmp(uid, entry->uid));
 }
 
-static inline u16 get_device_id(struct device *dev)
+static inline u16 get_pci_device_id(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 
 	return PCI_DEVID(pdev->bus->number, pdev->devfn);
 }
 
+static inline int get_acpihid_device_id(struct device *dev,
+					struct acpihid_map_entry **entry)
+{
+	struct acpihid_map_entry *p;
+
+	list_for_each_entry(p, &acpihid_map, list) {
+		if (!match_hid_uid(dev, p)) {
+			if (entry)
+				*entry = p;
+			return p->devid;
+		}
+	}
+	return -EINVAL;
+}
+
+static inline int get_device_id(struct device *dev)
+{
+	int devid;
+
+	if (dev_is_pci(dev))
+		devid = get_pci_device_id(dev);
+	else
+		devid = get_acpihid_device_id(dev, NULL);
+
+	return devid;
+}
+
+static struct protection_domain *to_pdomain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct protection_domain, domain);
+}
+
 static struct iommu_dev_data *alloc_dev_data(u16 devid)
 {
 	struct iommu_dev_data *dev_data;
@@ -222,6 +272,7 @@ static u16 get_alias(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	u16 devid, ivrs_alias, pci_alias;
 
+	/* The callers make sure that get_device_id() does not fail here */
 	devid = get_device_id(dev);
 	ivrs_alias = amd_iommu_alias_table[devid];
 	pci_for_each_dma_alias(pdev, __last_alias, &pci_alias);
@@ -289,6 +340,29 @@ static struct iommu_dev_data *get_dev_data(struct device *dev)
 	return dev->archdata.iommu;
 }
 
+/*
+* Find or create an IOMMU group for a acpihid device.
+*/
+static struct iommu_group *acpihid_device_group(struct device *dev)
+{
+	struct acpihid_map_entry *p, *entry = NULL;
+	int devid;
+
+	devid = get_acpihid_device_id(dev, &entry);
+	if (devid < 0)
+		return ERR_PTR(devid);
+
+	list_for_each_entry(p, &acpihid_map, list) {
+		if ((devid == p->devid) && p->group)
+			entry->group = p->group;
+	}
+
+	if (!entry->group)
+		entry->group = generic_device_group(dev);
+
+	return entry->group;
+}
+
 static bool pci_iommuv2_capable(struct pci_dev *pdev)
 {
 	static const int caps[] = {
@@ -340,9 +414,11 @@ static void init_unity_mappings_for_device(struct device *dev,
 					   struct dma_ops_domain *dma_dom)
 {
 	struct unity_map_entry *e;
-	u16 devid;
+	int devid;
 
 	devid = get_device_id(dev);
+	if (devid < 0)
+		return;
 
 	list_for_each_entry(e, &amd_iommu_unity_map, list) {
 		if (!(devid >= e->devid_start && devid <= e->devid_end))
@@ -357,16 +433,14 @@ static void init_unity_mappings_for_device(struct device *dev,
  */
 static bool check_device(struct device *dev)
 {
-	u16 devid;
+	int devid;
 
 	if (!dev || !dev->dma_mask)
 		return false;
 
-	/* No PCI device */
-	if (!dev_is_pci(dev))
-		return false;
-
 	devid = get_device_id(dev);
+	if (devid < 0)
+		return false;
 
 	/* Out of our scope? */
 	if (devid > amd_iommu_last_bdf)
@@ -401,22 +475,26 @@ out:
 
 static int iommu_init_device(struct device *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
 	struct iommu_dev_data *dev_data;
+	int devid;
 
 	if (dev->archdata.iommu)
 		return 0;
 
-	dev_data = find_dev_data(get_device_id(dev));
+	devid = get_device_id(dev);
+	if (devid < 0)
+		return devid;
+
+	dev_data = find_dev_data(devid);
 	if (!dev_data)
 		return -ENOMEM;
 
 	dev_data->alias = get_alias(dev);
 
-	if (pci_iommuv2_capable(pdev)) {
+	if (dev_is_pci(dev) && pci_iommuv2_capable(to_pci_dev(dev))) {
 		struct amd_iommu *iommu;
 
-		iommu              = amd_iommu_rlookup_table[dev_data->devid];
+		iommu = amd_iommu_rlookup_table[dev_data->devid];
 		dev_data->iommu_v2 = iommu->is_iommu_v2;
 	}
 
@@ -430,9 +508,13 @@ static int iommu_init_device(struct device *dev)
 
 static void iommu_ignore_device(struct device *dev)
 {
-	u16 devid, alias;
+	u16 alias;
+	int devid;
 
 	devid = get_device_id(dev);
+	if (devid < 0)
+		return;
+
 	alias = get_alias(dev);
 
 	memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
@@ -444,8 +526,14 @@ static void iommu_ignore_device(struct device *dev)
 
 static void iommu_uninit_device(struct device *dev)
 {
-	struct iommu_dev_data *dev_data = search_dev_data(get_device_id(dev));
+	int devid;
+	struct iommu_dev_data *dev_data;
 
+	devid = get_device_id(dev);
+	if (devid < 0)
+		return;
+
+	dev_data = search_dev_data(devid);
 	if (!dev_data)
 		return;
 
@@ -466,70 +554,6 @@ static void iommu_uninit_device(struct device *dev)
 	 */
 }
 
-#ifdef CONFIG_AMD_IOMMU_STATS
-
-/*
- * Initialization code for statistics collection
- */
-
-DECLARE_STATS_COUNTER(compl_wait);
-DECLARE_STATS_COUNTER(cnt_map_single);
-DECLARE_STATS_COUNTER(cnt_unmap_single);
-DECLARE_STATS_COUNTER(cnt_map_sg);
-DECLARE_STATS_COUNTER(cnt_unmap_sg);
-DECLARE_STATS_COUNTER(cnt_alloc_coherent);
-DECLARE_STATS_COUNTER(cnt_free_coherent);
-DECLARE_STATS_COUNTER(cross_page);
-DECLARE_STATS_COUNTER(domain_flush_single);
-DECLARE_STATS_COUNTER(domain_flush_all);
-DECLARE_STATS_COUNTER(alloced_io_mem);
-DECLARE_STATS_COUNTER(total_map_requests);
-DECLARE_STATS_COUNTER(complete_ppr);
-DECLARE_STATS_COUNTER(invalidate_iotlb);
-DECLARE_STATS_COUNTER(invalidate_iotlb_all);
-DECLARE_STATS_COUNTER(pri_requests);
-
-static struct dentry *stats_dir;
-static struct dentry *de_fflush;
-
-static void amd_iommu_stats_add(struct __iommu_counter *cnt)
-{
-	if (stats_dir == NULL)
-		return;
-
-	cnt->dent = debugfs_create_u64(cnt->name, 0444, stats_dir,
-				       &cnt->value);
-}
-
-static void amd_iommu_stats_init(void)
-{
-	stats_dir = debugfs_create_dir("amd-iommu", NULL);
-	if (stats_dir == NULL)
-		return;
-
-	de_fflush  = debugfs_create_bool("fullflush", 0444, stats_dir,
-					 &amd_iommu_unmap_flush);
-
-	amd_iommu_stats_add(&compl_wait);
-	amd_iommu_stats_add(&cnt_map_single);
-	amd_iommu_stats_add(&cnt_unmap_single);
-	amd_iommu_stats_add(&cnt_map_sg);
-	amd_iommu_stats_add(&cnt_unmap_sg);
-	amd_iommu_stats_add(&cnt_alloc_coherent);
-	amd_iommu_stats_add(&cnt_free_coherent);
-	amd_iommu_stats_add(&cross_page);
-	amd_iommu_stats_add(&domain_flush_single);
-	amd_iommu_stats_add(&domain_flush_all);
-	amd_iommu_stats_add(&alloced_io_mem);
-	amd_iommu_stats_add(&total_map_requests);
-	amd_iommu_stats_add(&complete_ppr);
-	amd_iommu_stats_add(&invalidate_iotlb);
-	amd_iommu_stats_add(&invalidate_iotlb_all);
-	amd_iommu_stats_add(&pri_requests);
-}
-
-#endif
-
 /****************************************************************************
  *
  * Interrupt handling functions
@@ -652,8 +676,6 @@ static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u64 *raw)
 {
 	struct amd_iommu_fault fault;
 
-	INC_STATS_COUNTER(pri_requests);
-
 	if (PPR_REQ_TYPE(raw[0]) != PPR_REQ_FAULT) {
 		pr_err_ratelimited("AMD-Vi: Unknown PPR request received\n");
 		return;
@@ -2283,13 +2305,17 @@ static bool pci_pri_tlp_required(struct pci_dev *pdev)
 static int attach_device(struct device *dev,
 			 struct protection_domain *domain)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_dev *pdev;
 	struct iommu_dev_data *dev_data;
 	unsigned long flags;
 	int ret;
 
 	dev_data = get_dev_data(dev);
 
+	if (!dev_is_pci(dev))
+		goto skip_ats_check;
+
+	pdev = to_pci_dev(dev);
 	if (domain->flags & PD_IOMMUV2_MASK) {
 		if (!dev_data->passthrough)
 			return -EINVAL;
@@ -2308,6 +2334,7 @@ static int attach_device(struct device *dev,
 		dev_data->ats.qdep    = pci_ats_queue_depth(pdev);
 	}
 
+skip_ats_check:
 	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
 	ret = __attach_device(dev_data, domain);
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
@@ -2364,6 +2391,9 @@ static void detach_device(struct device *dev)
 	__detach_device(dev_data);
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 
+	if (!dev_is_pci(dev))
+		return;
+
 	if (domain->flags & PD_IOMMUV2_MASK && dev_data->iommu_v2)
 		pdev_iommuv2_disable(to_pci_dev(dev));
 	else if (dev_data->ats.enabled)
@@ -2377,13 +2407,15 @@ static int amd_iommu_add_device(struct device *dev)
 	struct iommu_dev_data *dev_data;
 	struct iommu_domain *domain;
 	struct amd_iommu *iommu;
-	u16 devid;
-	int ret;
+	int ret, devid;
 
 	if (!check_device(dev) || get_dev_data(dev))
 		return 0;
 
 	devid = get_device_id(dev);
+	if (devid < 0)
+		return devid;
+
 	iommu = amd_iommu_rlookup_table[devid];
 
 	ret = iommu_init_device(dev);
@@ -2421,18 +2453,29 @@ out:
 static void amd_iommu_remove_device(struct device *dev)
 {
 	struct amd_iommu *iommu;
-	u16 devid;
+	int devid;
 
 	if (!check_device(dev))
 		return;
 
 	devid = get_device_id(dev);
+	if (devid < 0)
+		return;
+
 	iommu = amd_iommu_rlookup_table[devid];
 
 	iommu_uninit_device(dev);
 	iommu_completion_wait(iommu);
 }
 
+static struct iommu_group *amd_iommu_device_group(struct device *dev)
+{
+	if (dev_is_pci(dev))
+		return pci_device_group(dev);
+
+	return acpihid_device_group(dev);
+}
+
 /*****************************************************************************
  *
  * The next functions belong to the dma_ops mapping/unmapping code.
@@ -2597,11 +2640,6 @@ static dma_addr_t __map_single(struct device *dev,
 	pages = iommu_num_pages(paddr, size, PAGE_SIZE);
 	paddr &= PAGE_MASK;
 
-	INC_STATS_COUNTER(total_map_requests);
-
-	if (pages > 1)
-		INC_STATS_COUNTER(cross_page);
-
 	if (align)
 		align_mask = (1UL << get_order(size)) - 1;
 
@@ -2622,8 +2660,6 @@ static dma_addr_t __map_single(struct device *dev,
 	}
 	address += offset;
 
-	ADD_STATS_COUNTER(alloced_io_mem, size);
-
 	if (unlikely(amd_iommu_np_cache)) {
 		domain_flush_pages(&dma_dom->domain, address, size);
 		domain_flush_complete(&dma_dom->domain);
@@ -2671,8 +2707,6 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
 		start += PAGE_SIZE;
 	}
 
-	SUB_STATS_COUNTER(alloced_io_mem, size);
-
 	dma_ops_free_addresses(dma_dom, dma_addr, pages);
 }
 
@@ -2688,8 +2722,6 @@ static dma_addr_t map_page(struct device *dev, struct page *page,
 	struct protection_domain *domain;
 	u64 dma_mask;
 
-	INC_STATS_COUNTER(cnt_map_single);
-
 	domain = get_domain(dev);
 	if (PTR_ERR(domain) == -EINVAL)
 		return (dma_addr_t)paddr;
@@ -2710,8 +2742,6 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
 {
 	struct protection_domain *domain;
 
-	INC_STATS_COUNTER(cnt_unmap_single);
-
 	domain = get_domain(dev);
 	if (IS_ERR(domain))
 		return;
@@ -2734,8 +2764,6 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 	int mapped_elems = 0;
 	u64 dma_mask;
 
-	INC_STATS_COUNTER(cnt_map_sg);
-
 	domain = get_domain(dev);
 	if (IS_ERR(domain))
 		return 0;
@@ -2781,8 +2809,6 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
 	struct scatterlist *s;
 	int i;
 
-	INC_STATS_COUNTER(cnt_unmap_sg);
-
 	domain = get_domain(dev);
 	if (IS_ERR(domain))
 		return;
@@ -2805,8 +2831,6 @@ static void *alloc_coherent(struct device *dev, size_t size,
 	struct protection_domain *domain;
 	struct page *page;
 
-	INC_STATS_COUNTER(cnt_alloc_coherent);
-
 	domain = get_domain(dev);
 	if (PTR_ERR(domain) == -EINVAL) {
 		page = alloc_pages(flag, get_order(size));
@@ -2860,8 +2884,6 @@ static void free_coherent(struct device *dev, size_t size,
 	struct protection_domain *domain;
 	struct page *page;
 
-	INC_STATS_COUNTER(cnt_free_coherent);
-
 	page = virt_to_page(virt_addr);
 	size = PAGE_ALIGN(size);
 
@@ -2926,7 +2948,17 @@ static struct dma_map_ops amd_iommu_dma_ops = {
 
 int __init amd_iommu_init_api(void)
 {
-	return bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
+	int err = 0;
+
+	err = bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
+	if (err)
+		return err;
+#ifdef CONFIG_ARM_AMBA
+	err = bus_set_iommu(&amba_bustype, &amd_iommu_ops);
+	if (err)
+		return err;
+#endif
+	return 0;
 }
 
 int __init amd_iommu_init_dma_ops(void)
@@ -2943,8 +2975,6 @@ int __init amd_iommu_init_dma_ops(void)
 	if (!swiotlb)
 		dma_ops = &nommu_dma_ops;
 
-	amd_iommu_stats_init();
-
 	if (amd_iommu_unmap_flush)
 		pr_info("AMD-Vi: IO/TLB flush on unmap enabled\n");
 	else
@@ -3098,12 +3128,14 @@ static void amd_iommu_detach_device(struct iommu_domain *dom,
 {
 	struct iommu_dev_data *dev_data = dev->archdata.iommu;
 	struct amd_iommu *iommu;
-	u16 devid;
+	int devid;
 
 	if (!check_device(dev))
 		return;
 
 	devid = get_device_id(dev);
+	if (devid < 0)
+		return;
 
 	if (dev_data->domain != NULL)
 		detach_device(dev);
@@ -3221,9 +3253,11 @@ static void amd_iommu_get_dm_regions(struct device *dev,
 				     struct list_head *head)
 {
 	struct unity_map_entry *entry;
-	u16 devid;
+	int devid;
 
 	devid = get_device_id(dev);
+	if (devid < 0)
+		return;
 
 	list_for_each_entry(entry, &amd_iommu_unity_map, list) {
 		struct iommu_dm_region *region;
@@ -3270,7 +3304,7 @@ static const struct iommu_ops amd_iommu_ops = {
 	.iova_to_phys = amd_iommu_iova_to_phys,
 	.add_device = amd_iommu_add_device,
 	.remove_device = amd_iommu_remove_device,
-	.device_group = pci_device_group,
+	.device_group = amd_iommu_device_group,
 	.get_dm_regions = amd_iommu_get_dm_regions,
 	.put_dm_regions = amd_iommu_put_dm_regions,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
@@ -3431,8 +3465,6 @@ out:
 static int __amd_iommu_flush_page(struct protection_domain *domain, int pasid,
 				  u64 address)
 {
-	INC_STATS_COUNTER(invalidate_iotlb);
-
 	return __flush_pasid(domain, pasid, address, false);
 }
 
@@ -3453,8 +3485,6 @@ EXPORT_SYMBOL(amd_iommu_flush_page);
 
 static int __amd_iommu_flush_tlb(struct protection_domain *domain, int pasid)
 {
-	INC_STATS_COUNTER(invalidate_iotlb_all);
-
 	return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
 			     true);
 }
@@ -3574,8 +3604,6 @@ int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
 	struct amd_iommu *iommu;
 	struct iommu_cmd cmd;
 
-	INC_STATS_COUNTER(complete_ppr);
-
 	dev_data = get_dev_data(&pdev->dev);
 	iommu    = amd_iommu_rlookup_table[dev_data->devid];
 
@@ -3925,6 +3953,9 @@ static struct irq_domain *get_irq_domain(struct irq_alloc_info *info)
 	case X86_IRQ_ALLOC_TYPE_MSI:
 	case X86_IRQ_ALLOC_TYPE_MSIX:
 		devid = get_device_id(&info->msi_dev->dev);
+		if (devid < 0)
+			return NULL;
+
 		iommu = amd_iommu_rlookup_table[devid];
 		if (iommu)
 			return iommu->msi_domain;
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index bf4959f4225b..9e0034196e10 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -44,7 +44,7 @@
  */
 #define IVRS_HEADER_LENGTH 48
 
-#define ACPI_IVHD_TYPE                  0x10
+#define ACPI_IVHD_TYPE_MAX_SUPPORTED	0x40
 #define ACPI_IVMD_TYPE_ALL              0x20
 #define ACPI_IVMD_TYPE                  0x21
 #define ACPI_IVMD_TYPE_RANGE            0x22
@@ -58,6 +58,11 @@
 #define IVHD_DEV_EXT_SELECT             0x46
 #define IVHD_DEV_EXT_SELECT_RANGE       0x47
 #define IVHD_DEV_SPECIAL		0x48
+#define IVHD_DEV_ACPI_HID		0xf0
+
+#define UID_NOT_PRESENT                 0
+#define UID_IS_INTEGER                  1
+#define UID_IS_CHARACTER                2
 
 #define IVHD_SPECIAL_IOAPIC		1
 #define IVHD_SPECIAL_HPET		2
@@ -99,7 +104,11 @@ struct ivhd_header {
 	u64 mmio_phys;
 	u16 pci_seg;
 	u16 info;
-	u32 efr;
+	u32 efr_attr;
+
+	/* Following only valid on IVHD type 11h and 40h */
+	u64 efr_reg; /* Exact copy of MMIO_EXT_FEATURES */
+	u64 res;
 } __attribute__((packed));
 
 /*
@@ -111,6 +120,11 @@ struct ivhd_entry {
 	u16 devid;
 	u8 flags;
 	u32 ext;
+	u32 hidh;
+	u64 cid;
+	u8 uidf;
+	u8 uidl;
+	u8 uid;
 } __attribute__((packed));
 
 /*
@@ -133,6 +147,7 @@ bool amd_iommu_irq_remap __read_mostly;
 
 static bool amd_iommu_detected;
 static bool __initdata amd_iommu_disabled;
+static int amd_iommu_target_ivhd_type;
 
 u16 amd_iommu_last_bdf;			/* largest PCI device id we have
 					   to handle */
@@ -218,8 +233,12 @@ enum iommu_init_state {
 #define EARLY_MAP_SIZE		4
 static struct devid_map __initdata early_ioapic_map[EARLY_MAP_SIZE];
 static struct devid_map __initdata early_hpet_map[EARLY_MAP_SIZE];
+static struct acpihid_map_entry __initdata early_acpihid_map[EARLY_MAP_SIZE];
+
 static int __initdata early_ioapic_map_size;
 static int __initdata early_hpet_map_size;
+static int __initdata early_acpihid_map_size;
+
 static bool __initdata cmdline_maps;
 
 static enum iommu_init_state init_state = IOMMU_START_STATE;
@@ -394,6 +413,22 @@ static void __init iommu_unmap_mmio_space(struct amd_iommu *iommu)
 	release_mem_region(iommu->mmio_phys, iommu->mmio_phys_end);
 }
 
+static inline u32 get_ivhd_header_size(struct ivhd_header *h)
+{
+	u32 size = 0;
+
+	switch (h->type) {
+	case 0x10:
+		size = 24;
+		break;
+	case 0x11:
+	case 0x40:
+		size = 40;
+		break;
+	}
+	return size;
+}
+
 /****************************************************************************
  *
  * The functions below belong to the first pass of AMD IOMMU ACPI table
@@ -408,7 +443,15 @@ static void __init iommu_unmap_mmio_space(struct amd_iommu *iommu)
  */
 static inline int ivhd_entry_length(u8 *ivhd)
 {
-	return 0x04 << (*ivhd >> 6);
+	u32 type = ((struct ivhd_entry *)ivhd)->type;
+
+	if (type < 0x80) {
+		return 0x04 << (*ivhd >> 6);
+	} else if (type == IVHD_DEV_ACPI_HID) {
+		/* For ACPI_HID, offset 21 is uid len */
+		return *((u8 *)ivhd + 21) + 22;
+	}
+	return 0;
 }
 
 /*
@@ -420,7 +463,14 @@ static int __init find_last_devid_from_ivhd(struct ivhd_header *h)
 	u8 *p = (void *)h, *end = (void *)h;
 	struct ivhd_entry *dev;
 
-	p += sizeof(*h);
+	u32 ivhd_size = get_ivhd_header_size(h);
+
+	if (!ivhd_size) {
+		pr_err("AMD-Vi: Unsupported IVHD type %#x\n", h->type);
+		return -EINVAL;
+	}
+
+	p += ivhd_size;
 	end += h->length;
 
 	while (p < end) {
@@ -448,6 +498,22 @@ static int __init find_last_devid_from_ivhd(struct ivhd_header *h)
 	return 0;
 }
 
+static int __init check_ivrs_checksum(struct acpi_table_header *table)
+{
+	int i;
+	u8 checksum = 0, *p = (u8 *)table;
+
+	for (i = 0; i < table->length; ++i)
+		checksum += p[i];
+	if (checksum != 0) {
+		/* ACPI table corrupt */
+		pr_err(FW_BUG "AMD-Vi: IVRS invalid checksum\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 /*
  * Iterate over all IVHD entries in the ACPI table and find the highest device
  * id which we need to handle. This is the first of three functions which parse
@@ -455,31 +521,19 @@ static int __init find_last_devid_from_ivhd(struct ivhd_header *h)
  */
 static int __init find_last_devid_acpi(struct acpi_table_header *table)
 {
-	int i;
-	u8 checksum = 0, *p = (u8 *)table, *end = (u8 *)table;
+	u8 *p = (u8 *)table, *end = (u8 *)table;
 	struct ivhd_header *h;
 
-	/*
-	 * Validate checksum here so we don't need to do it when
-	 * we actually parse the table
-	 */
-	for (i = 0; i < table->length; ++i)
-		checksum += p[i];
-	if (checksum != 0)
-		/* ACPI table corrupt */
-		return -ENODEV;
-
 	p += IVRS_HEADER_LENGTH;
 
 	end += table->length;
 	while (p < end) {
 		h = (struct ivhd_header *)p;
-		switch (h->type) {
-		case ACPI_IVHD_TYPE:
-			find_last_devid_from_ivhd(h);
-			break;
-		default:
-			break;
+		if (h->type == amd_iommu_target_ivhd_type) {
+			int ret = find_last_devid_from_ivhd(h);
+
+			if (ret)
+				return ret;
 		}
 		p += h->length;
 	}
@@ -724,6 +778,42 @@ static int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
 	return 0;
 }
 
+static int __init add_acpi_hid_device(u8 *hid, u8 *uid, u16 *devid,
+				      bool cmd_line)
+{
+	struct acpihid_map_entry *entry;
+	struct list_head *list = &acpihid_map;
+
+	list_for_each_entry(entry, list, list) {
+		if (strcmp(entry->hid, hid) ||
+		    (*uid && *entry->uid && strcmp(entry->uid, uid)) ||
+		    !entry->cmd_line)
+			continue;
+
+		pr_info("AMD-Vi: Command-line override for hid:%s uid:%s\n",
+			hid, uid);
+		*devid = entry->devid;
+		return 0;
+	}
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	memcpy(entry->uid, uid, strlen(uid));
+	memcpy(entry->hid, hid, strlen(hid));
+	entry->devid = *devid;
+	entry->cmd_line	= cmd_line;
+	entry->root_devid = (entry->devid & (~0x7));
+
+	pr_info("AMD-Vi:%s, add hid:%s, uid:%s, rdevid:%d\n",
+		entry->cmd_line ? "cmd" : "ivrs",
+		entry->hid, entry->uid, entry->root_devid);
+
+	list_add_tail(&entry->list, list);
+	return 0;
+}
+
 static int __init add_early_maps(void)
 {
 	int i, ret;
@@ -746,6 +836,15 @@ static int __init add_early_maps(void)
 			return ret;
 	}
 
+	for (i = 0; i < early_acpihid_map_size; ++i) {
+		ret = add_acpi_hid_device(early_acpihid_map[i].hid,
+					  early_acpihid_map[i].uid,
+					  &early_acpihid_map[i].devid,
+					  early_acpihid_map[i].cmd_line);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 
@@ -785,6 +884,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 	u32 dev_i, ext_flags = 0;
 	bool alias = false;
 	struct ivhd_entry *e;
+	u32 ivhd_size;
 	int ret;
 
 
@@ -800,7 +900,14 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 	/*
 	 * Done. Now parse the device entries
 	 */
-	p += sizeof(struct ivhd_header);
+	ivhd_size = get_ivhd_header_size(h);
+	if (!ivhd_size) {
+		pr_err("AMD-Vi: Unsupported IVHD type %#x\n", h->type);
+		return -EINVAL;
+	}
+
+	p += ivhd_size;
+
 	end += h->length;
 
 
@@ -958,6 +1065,70 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 
 			break;
 		}
+		case IVHD_DEV_ACPI_HID: {
+			u16 devid;
+			u8 hid[ACPIHID_HID_LEN] = {0};
+			u8 uid[ACPIHID_UID_LEN] = {0};
+			int ret;
+
+			if (h->type != 0x40) {
+				pr_err(FW_BUG "Invalid IVHD device type %#x\n",
+				       e->type);
+				break;
+			}
+
+			memcpy(hid, (u8 *)(&e->ext), ACPIHID_HID_LEN - 1);
+			hid[ACPIHID_HID_LEN - 1] = '\0';
+
+			if (!(*hid)) {
+				pr_err(FW_BUG "Invalid HID.\n");
+				break;
+			}
+
+			switch (e->uidf) {
+			case UID_NOT_PRESENT:
+
+				if (e->uidl != 0)
+					pr_warn(FW_BUG "Invalid UID length.\n");
+
+				break;
+			case UID_IS_INTEGER:
+
+				sprintf(uid, "%d", e->uid);
+
+				break;
+			case UID_IS_CHARACTER:
+
+				memcpy(uid, (u8 *)(&e->uid), ACPIHID_UID_LEN - 1);
+				uid[ACPIHID_UID_LEN - 1] = '\0';
+
+				break;
+			default:
+				break;
+			}
+
+			DUMP_printk("  DEV_ACPI_HID(%s[%s])\t\tdevid: %02x:%02x.%x\n",
+				    hid, uid,
+				    PCI_BUS_NUM(devid),
+				    PCI_SLOT(devid),
+				    PCI_FUNC(devid));
+
+			devid  = e->devid;
+			flags = e->flags;
+
+			ret = add_acpi_hid_device(hid, uid, &devid, false);
+			if (ret)
+				return ret;
+
+			/*
+			 * add_special_device might update the devid in case a
+			 * command-line override is present. So call
+			 * set_dev_entry_from_acpi after add_special_device.
+			 */
+			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
+