Merge branch 'linus' into genirq

8 files changed, 1159 insertions, 315 deletions

diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 7d63f8ced24..4b47f4ece5b 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -26,6 +26,8 @@ obj-$(CONFIG_HT_IRQ) += htirq.o
 # Build Intel IOMMU support
 obj-$(CONFIG_DMAR) += dmar.o iova.o intel-iommu.o
 
+obj-$(CONFIG_INTR_REMAP) += dmar.o intr_remapping.o
+
 #
 # Some architectures use the generic PCI setup functions
 #
diff --git a/drivers/pci/dma_remapping.h b/drivers/pci/dma_remapping.h
new file mode 100644
index 00000000000..bff5c65f81d
--- /dev/null
+++ b/drivers/pci/dma_remapping.h
@@ -0,0 +1,157 @@
+#ifndef _DMA_REMAPPING_H
+#define _DMA_REMAPPING_H
+
+/*
+ * We need a fixed PAGE_SIZE of 4K irrespective of
+ * arch PAGE_SIZE for IOMMU page tables.
+ */
+#define PAGE_SHIFT_4K		(12)
+#define PAGE_SIZE_4K		(1UL << PAGE_SHIFT_4K)
+#define PAGE_MASK_4K		(((u64)-1) << PAGE_SHIFT_4K)
+#define PAGE_ALIGN_4K(addr)	(((addr) + PAGE_SIZE_4K - 1) & PAGE_MASK_4K)
+
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT_4K)
+#define DMA_32BIT_PFN		IOVA_PFN(DMA_32BIT_MASK)
+#define DMA_64BIT_PFN		IOVA_PFN(DMA_64BIT_MASK)
+
+
+/*
+ * 0: Present
+ * 1-11: Reserved
+ * 12-63: Context Ptr (12 - (haw-1))
+ * 64-127: Reserved
+ */
+struct root_entry {
+	u64	val;
+	u64	rsvd1;
+};
+#define ROOT_ENTRY_NR (PAGE_SIZE_4K/sizeof(struct root_entry))
+static inline bool root_present(struct root_entry *root)
+{
+	return (root->val & 1);
+}
+static inline void set_root_present(struct root_entry *root)
+{
+	root->val |= 1;
+}
+static inline void set_root_value(struct root_entry *root, unsigned long value)
+{
+	root->val |= value & PAGE_MASK_4K;
+}
+
+struct context_entry;
+static inline struct context_entry *
+get_context_addr_from_root(struct root_entry *root)
+{
+	return (struct context_entry *)
+		(root_present(root)?phys_to_virt(
+		root->val & PAGE_MASK_4K):
+		NULL);
+}
+
+/*
+ * low 64 bits:
+ * 0: present
+ * 1: fault processing disable
+ * 2-3: translation type
+ * 12-63: address space root
+ * high 64 bits:
+ * 0-2: address width
+ * 3-6: aval
+ * 8-23: domain id
+ */
+struct context_entry {
+	u64 lo;
+	u64 hi;
+};
+#define context_present(c) ((c).lo & 1)
+#define context_fault_disable(c) (((c).lo >> 1) & 1)
+#define context_translation_type(c) (((c).lo >> 2) & 3)
+#define context_address_root(c) ((c).lo & PAGE_MASK_4K)
+#define context_address_width(c) ((c).hi &  7)
+#define context_domain_id(c) (((c).hi >> 8) & ((1 << 16) - 1))
+
+#define context_set_present(c) do {(c).lo |= 1;} while (0)
+#define context_set_fault_enable(c) \
+	do {(c).lo &= (((u64)-1) << 2) | 1;} while (0)
+#define context_set_translation_type(c, val) \
+	do { \
+		(c).lo &= (((u64)-1) << 4) | 3; \
+		(c).lo |= ((val) & 3) << 2; \
+	} while (0)
+#define CONTEXT_TT_MULTI_LEVEL 0
+#define context_set_address_root(c, val) \
+	do {(c).lo |= (val) & PAGE_MASK_4K;} while (0)
+#define context_set_address_width(c, val) do {(c).hi |= (val) & 7;} while (0)
+#define context_set_domain_id(c, val) \
+	do {(c).hi |= ((val) & ((1 << 16) - 1)) << 8;} while (0)
+#define context_clear_entry(c) do {(c).lo = 0; (c).hi = 0;} while (0)
+
+/*
+ * 0: readable
+ * 1: writable
+ * 2-6: reserved
+ * 7: super page
+ * 8-11: available
+ * 12-63: Host physcial address
+ */
+struct dma_pte {
+	u64 val;
+};
+#define dma_clear_pte(p)	do {(p).val = 0;} while (0)
+
+#define DMA_PTE_READ (1)
+#define DMA_PTE_WRITE (2)
+
+#define dma_set_pte_readable(p) do {(p).val |= DMA_PTE_READ;} while (0)
+#define dma_set_pte_writable(p) do {(p).val |= DMA_PTE_WRITE;} while (0)
+#define dma_set_pte_prot(p, prot) \
+		do {(p).val = ((p).val & ~3) | ((prot) & 3); } while (0)
+#define dma_pte_addr(p) ((p).val & PAGE_MASK_4K)
+#define dma_set_pte_addr(p, addr) do {\
+		(p).val |= ((addr) & PAGE_MASK_4K); } while (0)
+#define dma_pte_present(p) (((p).val & 3) != 0)
+
+struct intel_iommu;
+
+struct dmar_domain {
+	int	id;			/* domain id */
+	struct intel_iommu *iommu;	/* back pointer to owning iommu */
+
+	struct list_head devices; 	/* all devices' list */
+	struct iova_domain iovad;	/* iova's that belong to this domain */
+
+	struct dma_pte	*pgd;		/* virtual address */
+	spinlock_t	mapping_lock;	/* page table lock */
+	int		gaw;		/* max guest address width */
+
+	/* adjusted guest address width, 0 is level 2 30-bit */
+	int		agaw;
+
+#define DOMAIN_FLAG_MULTIPLE_DEVICES 1
+	int		flags;
+};
+
+/* PCI domain-device relationship */
+struct device_domain_info {
+	struct list_head link;	/* link to domain siblings */
+	struct list_head global; /* link to global list */
+	u8 bus;			/* PCI bus numer */
+	u8 devfn;		/* PCI devfn number */
+	struct pci_dev *dev; /* it's NULL for PCIE-to-PCI bridge */
+	struct dmar_domain *domain; /* pointer to domain */
+};
+
+extern int init_dmars(void);
+extern void free_dmar_iommu(struct intel_iommu *iommu);
+
+extern int dmar_disabled;
+
+#ifndef CONFIG_DMAR_GFX_WA
+static inline void iommu_prepare_gfx_mapping(void)
+{
+	return;
+}
+#endif /* !CONFIG_DMAR_GFX_WA */
+
+#endif
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 8bf86ae2333..bd2c01674f5 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -19,13 +19,16 @@
  * Author: Shaohua Li <shaohua.li@intel.com>
  * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
  *
- * This file implements early detection/parsing of DMA Remapping Devices
+ * This file implements early detection/parsing of Remapping Devices
  * reported to OS through BIOS via DMA remapping reporting (DMAR) ACPI
  * tables.
+ *
+ * These routines are used by both DMA-remapping and Interrupt-remapping
  */
 
 #include <linux/pci.h>
 #include <linux/dmar.h>
+#include <linux/timer.h>
 #include "iova.h"
 #include "intel-iommu.h"
 
@@ -37,7 +40,6 @@
  * these units are not supported by the architecture.
  */
 LIST_HEAD(dmar_drhd_units);
-LIST_HEAD(dmar_rmrr_units);
 
 static struct acpi_table_header * __initdata dmar_tbl;
 
@@ -53,11 +55,6 @@ static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 		list_add(&drhd->list, &dmar_drhd_units);
 }
 
-static void __init dmar_register_rmrr_unit(struct dmar_rmrr_unit *rmrr)
-{
-	list_add(&rmrr->list, &dmar_rmrr_units);
-}
-
 static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
 					   struct pci_dev **dev, u16 segment)
 {
@@ -172,19 +169,37 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header)
 	struct acpi_dmar_hardware_unit *drhd;
 	struct dmar_drhd_unit *dmaru;
 	int ret = 0;
-	static int include_all;
 
 	dmaru = kzalloc(sizeof(*dmaru), GFP_KERNEL);
 	if (!dmaru)
 		return -ENOMEM;
 
+	dmaru->hdr = header;
 	drhd = (struct acpi_dmar_hardware_unit *)header;
 	dmaru->reg_base_addr = drhd->address;
 	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
 
+	ret = alloc_iommu(dmaru);
+	if (ret) {
+		kfree(dmaru);
+		return ret;
+	}
+	dmar_register_drhd_unit(dmaru);
+	return 0;
+}
+
+static int __init
+dmar_parse_dev(struct dmar_drhd_unit *dmaru)
+{
+	struct acpi_dmar_hardware_unit *drhd;
+	static int include_all;
+	int ret;
+
+	drhd = (struct acpi_dmar_hardware_unit *) dmaru->hdr;
+
 	if (!dmaru->include_all)
 		ret = dmar_parse_dev_scope((void *)(drhd + 1),
-				((void *)drhd) + header->length,
+				((void *)drhd) + drhd->header.length,
 				&dmaru->devices_cnt, &dmaru->devices,
 				drhd->segment);
 	else {
@@ -197,37 +212,59 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header)
 		include_all = 1;
 	}
 
-	if (ret || (dmaru->devices_cnt == 0 && !dmaru->include_all))
+	if (ret || (dmaru->devices_cnt == 0 && !dmaru->include_all)) {
+		list_del(&dmaru->list);
 		kfree(dmaru);
-	else
-		dmar_register_drhd_unit(dmaru);
+	}
 	return ret;
 }
 
+#ifdef CONFIG_DMAR
+LIST_HEAD(dmar_rmrr_units);
+
+static void __init dmar_register_rmrr_unit(struct dmar_rmrr_unit *rmrr)
+{
+	list_add(&rmrr->list, &dmar_rmrr_units);
+}
+
+
 static int __init
 dmar_parse_one_rmrr(struct acpi_dmar_header *header)
 {
 	struct acpi_dmar_reserved_memory *rmrr;
 	struct dmar_rmrr_unit *rmrru;
-	int ret = 0;
 
 	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
 	if (!rmrru)
 		return -ENOMEM;
 
+	rmrru->hdr = header;
 	rmrr = (struct acpi_dmar_reserved_memory *)header;
 	rmrru->base_address = rmrr->base_address;
 	rmrru->end_address = rmrr->end_address;
+
+	dmar_register_rmrr_unit(rmrru);
+	return 0;
+}
+
+static int __init
+rmrr_parse_dev(struct dmar_rmrr_unit *rmrru)
+{
+	struct acpi_dmar_reserved_memory *rmrr;
+	int ret;
+
+	rmrr = (struct acpi_dmar_reserved_memory *) rmrru->hdr;
 	ret = dmar_parse_dev_scope((void *)(rmrr + 1),
-		((void *)rmrr) + header->length,
+		((void *)rmrr) + rmrr->header.length,
 		&rmrru->devices_cnt, &rmrru->devices, rmrr->segment);
 
-	if (ret || (rmrru->devices_cnt == 0))
+	if (ret || (rmrru->devices_cnt == 0)) {
+		list_del(&rmrru->list);
 		kfree(rmrru);
-	else
-		dmar_register_rmrr_unit(rmrru);
+	}
 	return ret;
 }
+#endif
 
 static void __init
 dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
@@ -252,6 +289,7 @@ dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
 	}
 }
 
+
 /**
  * parse_dmar_table - parses the DMA reporting table
  */
@@ -284,7 +322,9 @@ parse_dmar_table(void)
 			ret = dmar_parse_one_drhd(entry_header);
 			break;
 		case ACPI_DMAR_TYPE_RESERVED_MEMORY:
+#ifdef CONFIG_DMAR
 			ret = dmar_parse_one_rmrr(entry_header);
+#endif
 			break;
 		default:
 			printk(KERN_WARNING PREFIX
@@ -300,15 +340,77 @@ parse_dmar_table(void)
 	return ret;
 }
 
+int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
+			  struct pci_dev *dev)
+{
+	int index;
+
+	while (dev) {
+		for (index = 0; index < cnt; index++)
+			if (dev == devices[index])
+				return 1;
 
-int __init dmar_table_init(void)
+		/* Check our parent */
+		dev = dev->bus->self;
+	}
+
+	return 0;
+}
+
+struct dmar_drhd_unit *
+dmar_find_matched_drhd_unit(struct pci_dev *dev)
 {
+	struct dmar_drhd_unit *drhd = NULL;
+
+	list_for_each_entry(drhd, &dmar_drhd_units, list) {
+		if (drhd->include_all || dmar_pci_device_match(drhd->devices,
+						drhd->devices_cnt, dev))
+			return drhd;
+	}
+
+	return NULL;
+}
+
+int __init dmar_dev_scope_init(void)
+{
+	struct dmar_drhd_unit *drhd;
+	int ret = -ENODEV;
+
+	for_each_drhd_unit(drhd) {
+		ret = dmar_parse_dev(drhd);
+		if (ret)
+			return ret;
+	}
+
+#ifdef CONFIG_DMAR
+	{
+		struct dmar_rmrr_unit *rmrr;
+		for_each_rmrr_units(rmrr) {
+			ret = rmrr_parse_dev(rmrr);
+			if (ret)
+				return ret;
+		}
+	}
+#endif
+
+	return ret;
+}
 
+
+int __init dmar_table_init(void)
+{
+	static int dmar_table_initialized;
 	int ret;
 
+	if (dmar_table_initialized)
+		return 0;
+
+	dmar_table_initialized = 1;
+
 	ret = parse_dmar_table();
 	if (ret) {
-		printk(KERN_INFO PREFIX "parse DMAR table failure.\n");
+		if (ret != -ENODEV)
+			printk(KERN_INFO PREFIX "parse DMAR table failure.\n");
 		return ret;
 	}
 
@@ -317,9 +419,14 @@ int __init dmar_table_init(void)
 		return -ENODEV;
 	}
 
+#ifdef CONFIG_DMAR
 	if (list_empty(&dmar_rmrr_units))
 		printk(KERN_INFO PREFIX "No RMRR found\n");
+#endif
 
+#ifdef CONFIG_INTR_REMAP
+	parse_ioapics_under_ir();
+#endif
 	return 0;
 }
 
@@ -341,3 +448,255 @@ int __init early_dmar_detect(void)
 
 	return (ACPI_SUCCESS(status) ? 1 : 0);
 }
+
+void __init detect_intel_iommu(void)
+{
+	int ret;
+
+	ret = early_dmar_detect();
+
+#ifdef CONFIG_DMAR
+	{
+		struct acpi_table_dmar *dmar;
+		/*
+		 * for now we will disable dma-remapping when interrupt
+		 * remapping is enabled.
+		 * When support for queued invalidation for IOTLB invalidation
+		 * is added, we will not need this any more.
+		 */
+		dmar = (struct acpi_table_dmar *) dmar_tbl;
+		if (ret && cpu_has_x2apic && dmar->flags & 0x1) {
+			printk(KERN_INFO
+			       "Queued invalidation will be enabled to support "
+			       "x2apic and Intr-remapping.\n");
+			printk(KERN_INFO
+			       "Disabling IOMMU detection, because of missing "
+			       "queued invalidation support for IOTLB "
+			       "invalidation\n");
+			printk(KERN_INFO
+			       "Use \"nox2apic\", if you want to use Intel "
+			       " IOMMU for DMA-remapping and don't care about "
+			       " x2apic support\n");
+
+			dmar_disabled = 1;
+			return;
+		}
+
+		if (ret && !no_iommu && !iommu_detected && !swiotlb &&
+		    !dmar_disabled)
+			iommu_detected = 1;
+	}
+#endif
+}
+
+
+int alloc_iommu(struct dmar_drhd_unit *drhd)
+{
+	struct intel_iommu *iommu;
+	int map_size;
+	u32 ver;
+	static int iommu_allocated = 0;
+
+	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
+	if (!iommu)
+		return -ENOMEM;
+
+	iommu->seq_id = iommu_allocated++;
+
+	iommu->reg = ioremap(drhd->reg_base_addr, PAGE_SIZE_4K);
+	if (!iommu->reg) {
+		printk(KERN_ERR "IOMMU: can't map the region\n");
+		goto error;
+	}
+	iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG);
+	iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);
+
+	/* the registers might be more than one page */
+	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
+		cap_max_fault_reg_offset(iommu->cap));
+	map_size = PAGE_ALIGN_4K(map_size);
+	if (map_size > PAGE_SIZE_4K) {
+		iounmap(iommu->reg);
+		iommu->reg = ioremap(drhd->reg_base_addr, map_size);
+		if (!iommu->reg) {
+			printk(KERN_ERR "IOMMU: can't map the region\n");
+			goto error;
+		}
+	}
+
+	ver = readl(iommu->reg + DMAR_VER_REG);
+	pr_debug("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n",
+		drhd->reg_base_addr, DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
+		iommu->cap, iommu->ecap);
+
+	spin_lock_init(&iommu->register_lock);
+
+	drhd->iommu = iommu;
+	return 0;
+error:
+	kfree(iommu);
+	return -1;
+}
+
+void free_iommu(struct intel_iommu *iommu)
+{
+	if (!iommu)
+		return;
+
+#ifdef CONFIG_DMAR
+	free_dmar_iommu(iommu);
+#endif
+
+	if (iommu->reg)
+		iounmap(iommu->reg);
+	kfree(iommu);
+}
+
+/*
+ * Reclaim all the submitted descriptors which have completed its work.
+ */
+static inline void reclaim_free_desc(struct q_inval *qi)
+{
+	while (qi->desc_status[qi->free_tail] == QI_DONE) {
+		qi->desc_status[qi->free_tail] = QI_FREE;
+		qi->free_tail = (qi->free_tail + 1) % QI_LENGTH;
+		qi->free_cnt++;
+	}
+}
+
+/*
+ * Submit the queued invalidation descriptor to the remapping
+ * hardware unit and wait for its completion.
+ */
+void qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
+{
+	struct q_inval *qi = iommu->qi;
+	struct qi_desc *hw, wait_desc;
+	int wait_index, index;
+	unsigned long flags;
+
+	if (!qi)
+		return;
+
+	hw = qi->desc;
+
+	spin_lock(&qi->q_lock);
+	while (qi->free_cnt < 3) {
+		spin_unlock(&qi->q_lock);
+		cpu_relax();
+		spin_lock(&qi->q_lock);
+	}
+
+	index = qi->free_head;
+	wait_index = (index + 1) % QI_LENGTH;
+
+	qi->desc_status[index] = qi->desc_status[wait_index] = QI_IN_USE;
+
+	hw[index] = *desc;
+
+	wait_desc.low = QI_IWD_STATUS_DATA(2) | QI_IWD_STATUS_WRITE | QI_IWD_TYPE;
+	wait_desc.high = virt_to_phys(&qi->desc_status[wait_index]);
+
+	hw[wait_index] = wait_desc;
+
+	__iommu_flush_cache(iommu, &hw[index], sizeof(struct qi_desc));
+	__iommu_flush_cache(iommu, &hw[wait_index], sizeof(struct qi_desc));
+
+	qi->free_head = (qi->free_head + 2) % QI_LENGTH;
+	qi->free_cnt -= 2;
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+	/*
+	 * update the HW tail register indicating the presence of
+	 * new descriptors.
+	 */
+	writel(qi->free_head << 4, iommu->reg + DMAR_IQT_REG);
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	while (qi->desc_status[wait_index] != QI_DONE) {
+		spin_unlock(&qi->q_lock);
+		cpu_relax();
+		spin_lock(&qi->q_lock);
+	}
+
+	qi->desc_status[index] = QI_DONE;
+
+	reclaim_free_desc(qi);
+	spin_unlock(&qi->q_lock);
+}
+
+/*
+ * Flush the global interrupt entry cache.
+ */
+void qi_global_iec(struct intel_iommu *iommu)
+{
+	struct qi_desc desc;
+
+	desc.low = QI_IEC_TYPE;
+	desc.high = 0;
+
+	qi_submit_sync(&desc, iommu);
+}
+
+/*
+ * Enable Queued Invalidation interface. This is a must to support
+ * interrupt-remapping. Also used by DMA-remapping, which replaces
+ * register based IOTLB invalidation.
+ */
+int dmar_enable_qi(struct intel_iommu *iommu)
+{
+	u32 cmd, sts;
+	unsigned long flags;
+	struct q_inval *qi;
+
+	if (!ecap_qis(iommu->ecap))
+		return -ENOENT;
+
+	/*
+	 * queued invalidation is already setup and enabled.
+	 */
+	if (iommu->qi)
+		return 0;
+
+	iommu->qi = kmalloc(sizeof(*qi), GFP_KERNEL);
+	if (!iommu->qi)
+		return -ENOMEM;
+
+	qi = iommu->qi;
+
+	qi->desc = (void *)(get_zeroed_page(GFP_KERNEL));
+	if (!qi->desc) {
+		kfree(qi);
+		iommu->qi = 0;
+		return -ENOMEM;
+	}
+
+	qi->desc_status = kmalloc(QI_LENGTH * sizeof(int), GFP_KERNEL);
+	if (!qi->desc_status) {
+		free_page((unsigned long) qi->desc);
+		kfree(qi);
+		iommu->qi = 0;
+		return -ENOMEM;
+	}
+
+	qi->free_head = qi->free_tail = 0;
+	qi->free_cnt = QI_LENGTH;
+
+	spin_lock_init(&qi->q_lock);
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+	/* write zero to the tail reg */
+	writel(0, iommu->reg + DMAR_IQT_REG);
+
+	dmar_writeq(iommu->reg + DMAR_IQA_REG, virt_to_phys(qi->desc));
+
+	cmd = iommu->gcmd | DMA_GCMD_QIE;
+	iommu->gcmd |= DMA_GCMD_QIE;
+	writel(cmd, iommu->reg + DMAR_GCMD_REG);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl, (sts & DMA_GSTS_QIES), sts);
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	return 0;
+}
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index c3edcdc08e7..389fdd6f4a9 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -49,8 +49,6 @@
 
 #define DEFAULT_DOMAIN_ADDRESS_WIDTH 48
 
-#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000) /* 10sec */
-
 #define DOMAIN_MAX_ADDR(gaw) ((((u64)1) << gaw) - 1)
 
 
@@ -58,8 +56,6 @@ static void flush_unmaps_timeout(unsigned long data);
 
 DEFINE_TIMER(unmap_timer,  flush_unmaps_timeout, 0, 0);
 
-static struct intel_iommu *g_iommus;
-
 #define HIGH_WATER_MARK 250
 struct deferred_flush_tables {
 	int next;
@@ -80,7 +76,7 @@ static long list_size;
 
 static void domain_remove_dev_info(struct dmar_domain *domain);
 
-static int dmar_disabled;
+int dmar_disabled;
 static int __initdata dmar_map_gfx = 1;
 static int dmar_forcedac;
 static int intel_iommu_strict;
@@ -185,13 +181,6 @@ void free_iova_mem(struct iova *iova)
 	kmem_cache_free(iommu_iova_cache, iova);
 }
 
-static inline void __iommu_flush_cache(
-	struct intel_iommu *iommu, void *addr, int size)
-{
-	if (!ecap_coherent(iommu->ecap))
-		clflush_cache_range(addr, size);
-}
-
 /* Gets context entry for a given bus and devfn */
 static struct context_entry * device_to_context_entry(struct intel_iommu *iommu,
 		u8 bus, u8 devfn)
@@ -488,19 +477,6 @@ static int iommu_alloc_root_entry(struct intel_iommu *iommu)
 	return 0;
 }
 
-#define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \
-{\
-	cycles_t start_time = get_cycles();\
-	while (1) {\
-		sts = op (iommu->reg + offset);\
-		if (cond)\
-			break;\
-		if (DMAR_OPERATION_TIMEOUT < (get_cycles() - start_time))\
-			panic("DMAR hardware is malfunctioning\n");\
-		cpu_relax();\
-	}\
-}
-
 static void iommu_set_root_entry(struct intel_iommu *iommu)
 {
 	void *addr;
@@ -990,6 +966,8 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 		return -ENOMEM;
 	}
 
+	spin_lock_init(&iommu->lock);
+
 	/*
 	 * if Caching mode is set, then invalid translations are tagged
 	 * with domainid 0. Hence we need to pre-allocate it.
@@ -998,62 +976,15 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 		set_bit(0, iommu->domain_ids);
 	return 0;
 }
-static struct intel_iommu *alloc_iommu(struct intel_iommu *iommu,
-					struct dmar_drhd_unit *drhd)
-{
-	int ret;
-	int map_size;
-	u32 ver;
-
-	iommu->reg = ioremap(drhd->reg_base_addr, PAGE_SIZE_4K);
-	if (!iommu->reg) {
-		printk(KERN_ERR "IOMMU: can't map the region\n");
-		goto error;
-	}
-	iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG);
-	iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);
-
-	/* the registers might be more than one page */
-	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
-		cap_max_fault_reg_offset(iommu->cap));
-	map_size = PAGE_ALIGN_4K(map_size);
-	if (map_size > PAGE_SIZE_4K) {
-		iounmap(iommu->reg);
-		iommu->reg = ioremap(drhd->reg_base_addr, map_size);
-		if (!iommu->reg) {
-			printk(KERN_ERR "IOMMU: can't map the region\n");
-			goto error;
-		}
-	}
-
-	ver = readl(iommu->reg + DMAR_VER_REG);
-	pr_debug("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n",
-		drhd->reg_base_addr, DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
-		iommu->cap, iommu->ecap);
-	ret = iommu_init_domains(iommu);
-	if (ret)
-		goto error_unmap;
-	spin_lock_init(&iommu->lock);
-	spin_lock_init(&iommu->register_lock);
 
-	drhd->iommu = iommu;
-	return iommu;
-error_unmap:
-	iounmap(iommu->reg);
-error:
-	kfree(iommu);
-	return NULL;
-}
 
 static void domain_exit(struct dmar_domain *domain);
-static void free_iommu(struct intel_iommu *iommu)
+
+void free_dmar_iommu(struct intel_iommu *iommu)
 {
 	struct dmar_domain *domain;
 	int i;
 
-	if (!iommu)
-		return;
-
 	i = find_first_bit(iommu->domain_ids, cap_ndoms(iommu->cap));
 	for (; i < cap_ndoms(iommu->cap); ) {
 		domain = iommu->domains[i];
@@ -1078,10 +1009,6 @@ static void free_iommu(struct intel_iommu *iommu)
 
 	/* free context mapping */
 	free_context_table(iommu);
-
-	if (iommu->reg)
-		iounmap(iommu->reg);
-	kfree(iommu);
 }
 
 static struct dmar_domain * iommu_alloc_domain(struct intel_iommu *iommu)
@@ -1426,37 +1353,6 @@ find_domain(struct pci_dev *pdev)
 	return NULL;
 }
 
-static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
-     struct pci_dev *dev)
-{
-	int index;
-
-	while (dev) {
-		for (index = 0; index < cnt; index++)
-			if (dev == devices[index])
-				return 1;
-
-		/* Check our parent */
-		dev = dev->bus->self;
-	}
-
-	return 0;
-}
-
-static struct dmar_drhd_unit *
-dmar_find_matched_drhd_unit(struct pci_dev *dev)
-{
-	struct dmar_drhd_unit *drhd = NULL;
-
-	list_for_each_entry(drhd, &dmar_drhd_units, list) {
-		if (drhd->include_all || dmar_pci_device_match(drhd->devices,
-						drhd->devices_cnt, dev))
-			return drhd;
-	}
-
-	return NULL;
-}
-
 /* domain is initialized */
 static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw)
 {
@@ -1729,8 +1625,6 @@ int __init init_dmars(void)
 	 * endfor
 	 */
 	for_each_drhd_unit(drhd) {
-		if (drhd->ignored)
-			continue;
 		g_num_of_iommus++;
 		/*
 		 * lock not needed as this is only incremented in the single
@@ -1739,12 +1633,6 @@ int __init init_dmars(void)
 		 */
 	}
 
-	g_iommus = kzalloc(g_num_of_iommus * sizeof(*iommu), GFP_KERNEL);
-	if (!g_iommus) {
-		ret = -ENOMEM;
-		goto error;
-	}
-
 	deferred_flush = kzalloc(g_num_of_iommus *
 		sizeof(struct deferred_flush_tables), GFP_KERNEL);
 	if (!deferred_flush) {
@@ -1752,16 +1640,15 @@ int __init init_dmars(void)
 		goto error;
 	}
 
-	i = 0;
 	for_each_drhd_unit(drhd) {
 		if (drhd->ignored)
 			continue;
-		iommu = alloc_iommu(&g_iommus[i], drhd);
-		i++;
-		if (!iommu) {
-			ret = -ENOMEM;
+
+		iommu = drhd->iommu;
+
+		ret = iommu_init_domains(iommu);
+		if (ret)
 			goto error;
-		}
 
 		/*
 		 * TBD:
@@ -1845,7 +1732,6 @@ error:
 		iommu = drhd->iommu;
 		free_iommu(iommu);
 	}
-	kfree(g_iommus);
 	return ret;
 }
 
@@ -2002,7 +1888,10 @@ static void flush_unmaps(void)
 	/* just flush them all */
 	for (i = 0; i < g_num_of_iommus; i++) {
 		if (deferred_flush[i].next) {
-			iommu_flush_iotlb_global(&g_iommus[i], 0);
+			struct intel_iommu *iommu =
+				deferred_flush[i].domain[0]->iommu;
+
+			iommu_flush_iotlb_global(iommu, 0);
 			for (j = 0; j < deferred_flush[i].next; j++) {
 				__free_iova(&deferred_flush[i].domain[j]->iovad,
 						deferred_flush[i].iova[j]);
@@ -2032,7 +1921,8 @@ static void add_unmap(struct dmar_domain *dom, struct iova *iova)
 	if (list_size == HIGH_WATER_MARK)
 		flush_unmaps();
 
-	iommu_id = dom->iommu - g_iommus;
+	iommu_id = dom->iommu->seq_id;
+
 	next = deferred_flush[iommu_id].next;
 	deferred_flush[iommu_id].domain[next] = dom;
 	deferred_flush[iommu_id].iova[next] = iova;
@@ -2348,38 +2238,6 @@ static void __init iommu_exit_mempool(void)
 
 }
 
-static int blacklist_iommu(const struct dmi_system_id *id)
-{
-	printk(KERN_INFO "%s detected; disabling IOMMU\n",
-	       id->ident);
-	dmar_disabled = 1;
-	return 0;
-}
-
-static struct dmi_system_id __initdata intel_iommu_dmi_table[] = {
-	{	/* Some DG33BU BIOS revisions advertised non-existent VT-d */
-		.callback = blacklist_iommu,
-		.ident = "Intel DG33BU",
-		{	DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"),
-			DMI_MATCH(DMI_BOARD_NAME, "DG33BU"),
-		}
-	},
-	{ }
-};
-
-
-void __init detect_intel_iommu(void)
-{
-	if (swiotlb || no_iommu || iommu_detected || dmar_disabled)
-		return;
-	if (early_dmar_detect()) {
-		dmi_check_system(intel_iommu_dmi_table);
-		if (dmar_disabled)
-			return;
-		iommu_detected = 1;
-	}
-}
-
 static void __init init_no_remapping_devices(void)
 {
 	struct dmar_drhd_unit *drhd;
@@ -2426,12 +2284,19 @@ int __init intel_iommu_init(void)
 {
 	int ret = 0;
 
-	if (no_iommu || swiotlb || dmar_disabled)
-		return -ENODEV;
-
 	if (dmar_table_init())
 		return 	-ENODEV;
 
+	if (dmar_dev_scope_init())
+		return 	-ENODEV;
+
+	/*
+	 * Check the need for DMA-remapping initialization now.
+	 * Above initialization will also be used by Interrupt-remapping.
+	 */
+	if (no_iommu || swiotlb || dmar_disabled)
+		return -ENODEV;
+
 	iommu_init_mempool();
 	dmar_init_reserved_ranges();
 
diff --git a/drivers/pci/intel-iommu.h b/drivers/pci/intel-iommu.h
index afc0ad96122..2142c01e014 100644
--- a/drivers/pci/intel-iommu.h
+++ b/drivers/pci/intel-iommu.h
@@ -27,19 +27,8 @@
 #include <linux/sysdev.h>
 #include "iova.h"
 #include <linux/io.h>
-
-/*
- * We need a fixed PAGE_SIZE of 4K irrespective of
- * arch PAGE_SIZE for IOMMU page tables.
- */
-#define PAGE_SHIFT_4K		(12)
-#define PAGE_SIZE_4K		(1UL << PAGE_SHIFT_4K)
-#define PAGE_MASK_4K		(((u64)-1) << PAGE_SHIFT_4K)
-#define PAGE_ALIGN_4K(addr)	(((addr) + PAGE_SIZE_4K - 1) & PAGE_MASK_4K)
-
-#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT_4K)
-#define DMA_32BIT_PFN		IOVA_PFN(DMA_32BIT_MASK)
-#define DMA_64BIT_PFN		IOVA_PFN(DMA_64BIT_MASK)
+#include <asm/cacheflush.h>
+#include "dma_remapping.h"
 
 /*
  * Intel IOMMU register specification per version 1.0 public spec.
@@ -63,6 +52,11 @@
 #define	DMAR_PLMLIMIT_REG 0x6c	/* PMRR low limit */
 #define	DMAR_PHMBASE_REG 0x70	/* pmrr high base addr */
 #define	DMAR_PHMLIMIT_REG 0x78	/* pmrr high limit */
+#define DMAR_IQH_REG	0x80	/* Invalidation queue head register */
+#define DMAR_IQT_REG	0x88	/* Invalidation queue tail register */
+#define DMAR_IQA_REG	0x90	/* Invalidation queue addr register */
+#define DMAR_ICS_REG	0x98	/* Invalidation complete status register */
+#define DMAR_IRTA_REG	0xb8    /* Interrupt remapping table addr register */
 
 #define OFFSET_STRIDE		(9)
 /*
@@ -126,6 +120,10 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define ecap_max_iotlb_offset(e) \
 	(ecap_iotlb_offset(e) + ecap_niotlb_iunits(e) * 16)
 #define ecap_coherent(e)	((e) & 0x1)
+#define ecap_qis(e)		((e) & 0x2)
+#define ecap_eim_support(e)	((e >> 4) & 0x1)
+#define ecap_ir_support(e)	((e >> 3) & 0x1)
+#define ecap_max_handle_mask(e) ((e >> 20) & 0xf)
 
 
 /* IOTLB_REG */
@@ -141,6 +139,17 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define DMA_TLB_IH_NONLEAF (((u64)1) << 6)
 #define DMA_TLB_MAX_SIZE (0x3f)
 
+/* INVALID_DESC */
+#define DMA_ID_TLB_GLOBAL_FLUSH	(((u64)1) << 3)
+#define DMA_ID_TLB_DSI_FLUSH	(((u64)2) << 3)
+#define DMA_ID_TLB_PSI_FLUSH	(((u64)3) << 3)
+#define DMA_ID_TLB_READ_DRAIN	(((u64)1) << 7)
+#define DMA_ID_TLB_WRITE_DRAIN	(((u64)1) << 6)
+#define DMA_ID_TLB_DID(id)	(((u64)((id & 0xffff) << 16)))
+#define DMA_ID_TLB_IH_NONLEAF	(((u64)1) << 6)
+#define DMA_ID_TLB_ADDR(addr)	(addr)
+#define DMA_ID_TLB_ADDR_MASK(mask)	(mask)
+
 /* PMEN_REG */
 #define DMA_PMEN_EPM (((u32)1)<<31)
 #define DMA_PMEN_PRS (((u32)1)<<0)
@@ -151,6 +160,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define DMA_GCMD_SFL (((u32)1) << 29)
 #define DMA_GCMD_EAFL (((u32)1) << 28)
 #define DMA_GCMD_WBF (((u32)1) << 27)
+#define DMA_GCMD_QIE (((u32)1) << 26)
+#define DMA_GCMD_SIRTP (((u32)1) << 24)
+#define DMA_GCMD_IRE (((u32) 1) << 25)
 
 /* GSTS_REG */
 #define DMA_GSTS_TES (((u32)1) << 31)
@@ -158,6 +170,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define DMA_GSTS_FLS (((u32)1) << 29)
 #define DMA_GSTS_AFLS (((u32)1) << 28)
 #define DMA_GSTS_WBFS (((u32)1) << 27)
+#define DMA_GSTS_QIES (((u32)1) << 26)
+#define DMA_GSTS_IRTPS (((u32)1) << 24)
+#define DMA_GSTS_IRES (((u32)1) << 25)
 
 /* CCMD_REG */
 #define DMA_CCMD_ICC (((u64)1) << 63)
@@ -187,158 +202,106 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define dma_frcd_source_id(c) (c & 0xffff)
 #define dma_frcd_page_addr(d) (d & (((u64)-1) << 12)) /* low 64 bit */
 
-/*
- * 0: Present
- * 1-11: Reserved
- * 12-63: Context Ptr (12 - (haw-1))
- * 64-127: Reserved
- */
-struct root_entry {
-	u64	val;
-	u64	rsvd1;
-};
-#define ROOT_ENTRY_NR (PAGE_SIZE_4K/sizeof(struct root_entry))
-static inline bool root_present(struct root_entry *root)
-{
-	return (root->val & 1);
-}
-static inline void set_root_present(struct root_entry *root)
-{
-	root->val |= 1;
-}
-static inline void set_root_value(struct root_entry *root, unsigned long value)
-{
-	root->val |= value & PAGE_MASK_4K;
+#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000) /* 10sec */
+
+#define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \
+{\
+	cycles_t start_time = get_cycles();\
+	while (1) {\
+		sts = op (iommu->reg + offset);\
+		if (cond)\
+			break;\
+		if (DMAR_OPERATION_TIMEOUT < (get_cycles() - start_time))\
+			panic("DMAR hardware is malfunctioning\n");\
+		cpu_relax();\
+	}\
 }
 
-struct context_entry;
-static inline struct context_entry *
-get_context_addr_from_root(struct root_entry *root)
-{
-	return (struct context_entry *)
-		(root_present(root)?phys_to_virt(
-		root->val & PAGE_MASK_4K):
-		NULL);
-}
-
-/*
- * low 64 bits:
- * 0: present
- * 1: fault processing disable
- * 2-3: translation type
- * 12-63: address space root
- * high 64 bits:
- * 0-2: address width
- * 3-6: aval
- * 8-23: domain id
- */
-struct context_entry {
-	u64 lo;
-	u64 hi;
-};
-#define context_present(c) ((c).lo & 1)
-#define context_fault_disable(c) (((c).lo >> 1) & 1)
-#define context_translation_type(c) (((c).lo >> 2) & 3)
-#define context_address_root(c) ((c).lo & PAGE_MASK_4K)
-#define context_address_width(c) ((c).hi &  7)
-#define context_domain_id(c) (((c).hi >> 8) & ((1 << 16) - 1))
-
-#define context_set_present(c) do {(c).lo |= 1;} while (0)
-#define context_set_fault_enable(c) \
-	do {(c).lo &= (((u64)-1) << 2) | 1;} while (0)
-#define context_set_translation_type(c, val) \
-	do { \
-		(c).lo &= (((u64)-1) << 4) | 3; \
-		(c).lo |= ((val) & 3) << 2; \
-	} while (0)
-#define CONTEXT_TT_MULTI_LEVEL 0
-#define context_set_address_root(c, val) \
-	do {(c).lo |= (val) & PAGE_MASK_4K;} while (0)
-#define context_set_address_width(c, val) do {(c).hi |= (val) & 7;} while (0)
-#define context_set_domain_id(c, val) \
-	do {(c).hi |= ((val) & ((1 << 16) - 1)) << 8;} while (0)
-#define context_clear_entry(c) do {(c).lo = 0; (c).hi = 0;} while (0)
+#define QI_LENGTH	256	/* queue length */
 
-/*
- * 0: readable
- * 1: writable
- * 2-6: reserved
- * 7: super page
- * 8-11: available
- * 12-63: Host physcial address
- */
-struct dma_pte {
-	u64 val;
+enum {
+	QI_FREE,
+	QI_IN_USE,
+	QI_DONE
 };
-#define dma_clear_pte(p)	do {(p).val = 0;} while (0)
-
-#define DMA_PTE_READ (1)
-#define DMA_PTE_WRITE (2)
 
-#define dma_set_pte_readable(p) do {(p).val |= DMA_PTE_READ;} while (0)
-#define dma_set_pte_writable(p) do {(p).val |= DMA_PTE_WRITE;} while (0)
-#define dma_set_pte_prot(p, prot) \
-		do {(p).val = ((p).val & ~3) | ((prot) & 3); } while (0)
-#define dma_pte_addr(p) ((p).val & PAGE_MASK_4K)
-#define dma_set_pte_addr(p, addr) do {\
-		(p).val |= ((addr) & PAGE_MASK_4K); } while (0)
-#define dma_pte_present(p) (((p).val & 3) != 0)
+#define QI_CC_TYPE		0x1
+#define QI_IOTLB_TYPE		0x2
+#define QI_DIOTLB_TYPE		0x3
+#define QI_IEC_TYPE		0x4
+#define QI_IWD_TYPE		0x5
 
-struct intel_iommu;
+#define QI_IEC_SELECTIVE	(((u64)1) << 4)
+#define QI_IEC_IIDEX(idx)	(((u64)(idx & 0xffff) << 32))
+#define QI_IEC_IM(m)		(((u64)(m & 0x1f) << 27))
 
-struct dmar_domain {
-	int	id;			/* domain id */
-	struct intel_iommu *iommu;	/* back pointer to owning iommu */
+#define QI_IWD_STATUS_DATA(d)	(((u64)d) << 32)
+#define QI_IWD_STATUS_WRITE	(((u64)1) << 5)
 
-	struct list_head devices; 	/* all devices' list */
-	struct iova_domain iovad;	/* iova's that belong to this domain */
+struct qi_desc {
+	u64 low, high;
+};
 
-	struct dma_pte	*pgd;		/* virtual address */
-	spinlock_t	mapping_lock;	/* page table lock */
-	int		gaw;		/* max guest address width */
+struct q_inval {
+	spinlock_t      q_lock;
+	struct qi_desc  *desc;          /* invalidation queue */
+	int             *desc_status;   /* desc status */
+	int             free_head;      /* first free entry */
+	int             free_tail;      /* last free entry */
+	int             free_cnt;
+};
 
-	/* adjusted guest address width, 0 is level 2 30-bit */
-	int		agaw;
+#ifdef CONFIG_INTR_REMAP
+/* 1MB - maximum possible interrupt remapping table size */
+#define INTR_REMAP_PAGE_ORDER	8
+#define INTR_REMAP_TABLE_REG_SIZE	0xf
 
-#define DOMAIN_FLAG_MULTIPLE_DEVICES 1
-	int		flags;
-};
+#define INTR_REMAP_TABLE_ENTRIES	65536
 
-/* PCI domain-device relationship */
-struct device_domain_info {
-	struct list_head link;	/* link to domain siblings */
-	struct list_head global; /* link to global list */
-	u8 bus;			/* PCI bus numer */
-	u8 devfn;		/* PCI devfn number */
-	struct pci_dev *dev; /* it's NULL for PCIE-to-PCI bridge */
-	struct dmar_domain *domain; /* pointer to domain */
+struct ir_table {
+	struct irte *base;
 };
-
-extern int init_dmars(void);
+#endif
 
 struct intel_iommu {
 	void __iomem	*reg; /* Pointer to hardware regs, virtual addr */
 	u64		cap;
 	u64		ecap;
-	unsigned long 	*domain_ids; /* bitmap of domains */
-	struct dmar_domain **domains; /* ptr to domains */
 	int		seg;
 	u32		gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */
-	spinlock_t	lock; /* protect context, domain ids */
 	spinlock_t	register_lock; /* protect register handling */
+	int		seq_id;	/* sequence id of the iommu */
+
+#ifdef CONFIG_DMAR
+	unsigned long 	*domain_ids; /* bitmap of domains */
+	struct dmar_domain **domains; /* ptr to domains */
+	spinlock_t	lock; /* protect context, domain ids */
 	struct root_entry *root_entry; /* virtual address */
 
 	unsigned int irq;
 	unsigned char name[7];    /* Device Name */
 	struct msi_msg saved_msg;
 	struct sys_device sysdev;
+#endif
+	struct q_inval  *qi;            /* Queued invalidation info */
+#ifdef CONFIG_INTR_REMAP
+	struct ir_table *ir_table;	/* Interrupt remapping info */
+#endif
 };
 
-#ifndef CONFIG_DMAR_GFX_WA
-static inline void iommu_prepare_gfx_mapping(void)
+static inline void __iommu_flush_cache(
+	struct intel_iommu *iommu, void *addr, int size)
 {
-	return;
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(addr, size);
 }
-#endif /* !CONFIG_DMAR_GFX_WA */
 
+extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
+
+extern int alloc_iommu(struct dmar_drhd_unit *drhd);
+extern void free_iommu(struct intel_iommu *iommu);
+extern int dmar_enable_qi(struct intel_iommu *iommu);
+extern void qi_global_iec(struct intel_iommu *iommu);
+
+extern void qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);
 #endif
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
new file mode 100644
index 00000000000..bb642cc5e18
--- /dev/null
+++ b/drivers/pci/intr_remapping.c
@@ -0,0 +1,471 @@
+#include <linux/dmar.h>
+#include <linux/spinlock.h>
+#include <linux/jiffies.h>
+#include <linux/pci.h>
+#include <linux/irq.h>
+#include <asm/io_apic.h>
+#include "intel-iommu.h"
+#include "intr_remapping.h"
+
+static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
+static int ir_ioapic_num;
+int intr_remapping_enabled;
+
+static struct {
+	struct intel_iommu *iommu;
+	u16 irte_index;
+	u16 sub_handle;
+	u8  irte_mask;
+} irq_2_iommu[NR_IRQS];
+
+static DEFINE_SPINLOCK(irq_2_ir_lock);
+
+int irq_remapped(int irq)
+{
+	if (irq > NR_IRQS)
+		return 0;
+
+	if (!irq_2_iommu[irq].iommu)
+		return 0;
+
+	return 1;
+}
+
+int get_irte(int irq, struct irte *entry)
+{
+	int index;
+
+	if (!entry || irq > NR_IRQS)
+		return -1;
+
+	spin_lock(&irq_2_ir_lock);
+	if (!irq_2_iommu[irq].iommu) {
+		spin_unlock(&irq_2_ir_lock);
+		return -1;
+	}
+
+	index = irq_2_iommu[irq].irte_index + irq_2_iommu[irq].sub_handle;
+	*entry = *(irq_2_iommu[irq].iommu->ir_table->base + index);
+
+	spin_unlock(&irq_2_ir_lock);
+	return 0;
+}
+
+int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
+{
+	struct ir_table *table = iommu->ir_table;
+	u16 index, start_index;
+	unsigned int mask = 0;
+	int i;
+
+	if (!count)
+		return -1;
+
+	/*
+	 * start the IRTE search from index 0.
+	 */
+	index = start_index = 0;
+
+	if (count > 1) {
+		count = __roundup_pow_of_two(count);
+		mask = ilog2(count);
+	}
+
+	if (mask > ecap_max_handle_mask(iommu->ecap)) {
+		printk(KERN_ERR
+		       "Requested mask %x exceeds the max invalidation handle"
+		       " mask value %Lx\n", mask,
+		       ecap_max_handle_mask(iommu->ecap));
+		return -1;
+	}
+
+	spin_lock(&irq_2_ir_lock);
+	do {
+		for (i = index; i < index + count; i++)
+			if  (table->base[i].present)
+				break;
+		/* empty index found */
+		if (i == index + count)
+			break;
+
+		index = (index + count) % INTR_REMAP_TABLE_ENTRIES;
+
+		if (index == start_index) {
+			spin_unlock(&irq_2_ir_lock);
+			printk(KERN_ERR "can't allocate an IRTE\n");
+			return -1;
+		}
+	} while (1);
+
+	for (i = index; i < index + count; i++)
+		table->base[i].present = 1;
+
+	irq_2_iommu[irq].iommu = iommu;
+	irq_2_iommu[irq].irte_index =  index;
+	irq_2_iommu[irq].sub_handle = 0;
+	irq_2_iommu[irq].irte_mask = mask;
+
+	spin_unlock(&irq_2_ir_lock);
+
+	return index;
+}
+
+static void qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
+{
+	struct qi_desc desc;
+
+	desc.low = QI_IEC_IIDEX(index) | QI_IEC_TYPE | QI_IEC_IM(mask)
+		   | QI_IEC_SELECTIVE;
+	desc.high = 0;
+
+	qi_submit_sync(&desc, iommu);
+}
+
+int map_irq_to_irte_handle(int irq, u16 *sub_handle)
+{
+	int index;
+
+	spin_lock(&irq_2_ir_lock);
+	if (irq >= NR_IRQS || !irq_2_iommu[irq].iommu) {
+		spin_unlock(&irq_2_ir_lock);
+		return -1;
+	}
+
+	*sub_handle = irq_2_iommu[irq].sub_handle;
+	index = irq_2_iommu[irq].irte_index;
+	spin_unlock(&irq_2_ir_lock);
+	return index;
+}
+
+int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
+{
+	spin_lock(&irq_2_ir_lock);
+	if (irq >= NR_IRQS || irq_2_iommu[irq].iommu) {
+		spin_unlock(&irq_2_ir_lock);
+		return -1;
+	}
+
+	irq_2_iommu[irq].iommu = iommu;
+	irq_2_iommu[irq].irte_index = index;
+	irq_2_iommu[irq].sub_handle = subhandle;
+	irq_2_iommu[irq].irte_mask = 0;
+
+	spin_unlock(&irq_2_ir_lock);
+
+	return 0;
+}
+
+int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index)
+{
+	spin_lock(&irq_2_ir_lock);
+	if (irq >= NR_IRQS || !irq_2_iommu[irq].iommu) {
+		spin_unlock(&irq_2_ir_lock);
+		return -1;
+	}
+
+	irq_2_iommu[irq].iommu = NULL;
+	irq_2_iommu[irq].irte_index = 0;
+	irq_2_iommu[irq].sub_handle = 0;
+	irq_2_iommu[irq].irte_mask = 0;
+
+	spin_unlock(&irq_2_ir_lock);
+
+	return 0;
+}
+
+int modify_irte(int irq, struct irte *irte_modified)
+{
+	int index;
+	struct irte *irte;
+	struct intel_iommu *iommu;
+
+	spin_lock(&irq_2_ir_lock);
+	if (irq >= NR_IRQS || !irq_2_iommu[irq].iommu) {
+		spin_unlock(&irq_2_ir_lock);
+		return -1;
+	}
+
+	iommu = irq_2_iommu[irq].iommu;
+
+	index = irq_2_iommu[irq].irte_index + irq_2_iommu[irq].sub_handle;
+	irte = &iommu->ir_table->base[index];
+
+	set_64bit((unsigned long *)irte, irte_modified->low | (1 << 1));
+	__iommu_flush_cache(iommu, irte, sizeof(*irte));
+
+	qi_flush_iec(iommu, index, 0);
+
+	spin_unlock(&irq_2_ir_lock);
+	return 0;
+}
+
+int flush_irte(int irq)
+{
+	int index;
+	struct intel_iommu *iommu;
+
+	spin_lock(&irq_2_ir_lock);
+	if (irq >= NR_IRQS || !irq_2_iommu[irq].iommu) {
+		spin_unlock(&irq_2_ir_lock);
+		return -1;
+	}
+
+	iommu = irq_2_iommu[irq].iommu;
+
+	index = irq_2_iommu[irq].irte_index + irq_2_iommu[irq].sub_handle;
+
+	qi_flush_iec(iommu, index, irq_2_iommu[irq].irte_mask);
+	spin_unlock(&irq_2_ir_lock);
+
+	return 0;
+}
+
+struct intel_iommu *map_ioapic_to_ir(int apic)
+{
+	int i;
+
+	for (i = 0; i < MAX_IO_APICS; i++)
+		if (ir_ioapic[i].id == apic)
+			return ir_ioapic[i].iommu;
+	return NULL;
+}
+
+struct intel_iommu *map_dev_to_ir(struct pci_dev *dev)
+{
+	struct dmar_drhd_unit *drhd;
+
+	drhd = dmar_find_matched_drhd_unit(dev);
+	if (!drhd)
+		return NULL;
+
+	return drhd->iommu;
+}
+
+int free_irte(int irq)
+{
+	int index, i;
+	struct irte *irte;
+	struct intel_iommu *iommu;
+
+	spin_lock(&irq_2_ir_lock);
+	if (irq >= NR_IRQS || !irq_2_iommu[irq].iommu) {
+		spin_unlock(&irq_2_ir_lock);
+		return -1;
+	}
+
+	iommu = irq_2_iommu[irq].iommu;
+
+	index = irq_2_iommu[irq].irte_index + irq_2_iommu[irq].sub_handle;
+	irte = &iommu->ir_table->base[index];
+
+	if (!irq_2_iommu[irq].sub_handle) {
+		for (i = 0; i < (1 << irq_2_iommu[irq].irte_mask); i++)
+			set_64bit((unsigned long *)irte, 0);
+		qi_flush_iec(iommu, index, irq_2_iommu[irq].irte_mask);
+	}
+
+	irq_2_iommu[irq].iommu = NULL;
+	irq_2_iommu[irq].irte_index = 0;
+	irq_2_iommu[irq].sub_handle = 0;
+	irq_2_iommu[irq].irte_mask = 0;
+
+	spin_unlock(&irq_2_ir_lock);
+
+	return 0;
+}
+
+static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode)
+{
+	u64 addr;
+	u32 cmd, sts;
+	unsigned long flags;
+
+	addr = virt_to_phys((void *)iommu->ir_table->base);
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	dmar_writeq(iommu->reg + DMAR_IRTA_REG,
+		    (addr) | IR_X2APIC_MODE(mode) | INTR_REMAP_TABLE_REG_SIZE);
+
+	/* Set interrupt-remapping table pointer */
+	cmd = iommu->gcmd | DMA_GCMD_SIRTP;
+	writel(cmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_IRTPS), sts);
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	/*
+	 * global invalidation of interrupt entry cache before enabling
+	 * interrupt-remapping.
+	 */
+	qi_global_iec(iommu);
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	/* Enable interrupt-remapping */
+	cmd = iommu->gcmd | DMA_GCMD_IRE;
+	iommu->gcmd |= DMA_GCMD_IRE;
+	writel(cmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_IRES), sts);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+
+static int setup_intr_remapping(struct intel_iommu *iommu, int mode)
+{
+	struct ir_table *ir_table;
+	struct page *pages;
+
+	ir_table = iommu->ir_table = kzalloc(sizeof(struct ir_table),
+					     GFP_KERNEL);
+
+	if (!iommu->ir_table)
+		return -ENOMEM;
+
+	pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, INTR_REMAP_PAGE_ORDER);
+
+	if (!pages) {
+		printk(KERN_ERR "failed to allocate pages of order %d\n",
+		       INTR_REMAP_PAGE_ORDER);
+		kfree(iommu->ir_table);
+		return -ENOMEM;
+	}
+
+	ir_table->base = page_address(pages);
+
+	iommu_set_intr_remapping(iommu, mode);
+	return 0;
+}
+
+int __init enable_intr_remapping(int eim)
+{
+	struct dmar_drhd_unit *drhd;
+	int setup = 0;
+
+	/*
+	 * check for the Interrupt-remapping support
+	 */
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		if (eim && !ecap_eim_support(iommu->ecap)) {
+			printk(KERN_INFO "DRHD %Lx: EIM not supported by DRHD, "
+			       " ecap %Lx\n", drhd->reg_base_addr, iommu->ecap);
+			return -1;
+		}
+	}
+
+	/*
+	 * Enable queued invalidation for all the DRHD's.
+	 */
+	for_each_drhd_unit(drhd) {
+		int ret;
+		struct intel_iommu *iommu = drhd->iommu;
+		ret = dmar_enable_qi(iommu);
+
+		if (ret) {
+			printk(KERN_ERR "DRHD %Lx: failed to enable queued, "
+			       " invalidation, ecap %Lx, ret %d\n",
+			       drhd->reg_base_addr, iommu->ecap, ret);
+			return -1;
+		}
+	}
+
+	/*
+	 * Setup Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		if (setup_intr_remapping(iommu, eim))
+			goto error;
+
+		setup = 1;
+	}
+
+	if (!setup)
+		goto error;
+
+	intr_remapping_enabled = 1;
+
+	return 0;
+
+error:
+	/*
+	 * handle error condition gracefully here!
+	 */
+	return -1;
+}
+
+static int ir_parse_ioapic_scope(struct acpi_dmar_header *header,
+				 struct intel_iommu *iommu)
+{
+	struct acpi_dmar_hardware_unit *drhd;
+	struct acpi_dmar_device_scope *scope;
+	void *start, *end;
+
+	drhd = (struct acpi_dmar_hardware_unit *)header;
+
+	start = (void *)(drhd + 1);
+	end = ((void *)drhd) + header->length;
+
+	while (start < end) {
+		scope = start;
+		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_IOAPIC) {
+			if (ir_ioapic_num == MAX_IO_APICS) {
+				printk(KERN_WARNING "Exceeded Max IO APICS\n");
+				return -1;
+			}
+
+			printk(KERN_INFO "IOAPIC id %d under DRHD base"
+			       " 0x%Lx\n", scope->enumeration_id,
+			       drhd->address);
+
+			ir_ioapic[ir_ioapic_num].iommu = iommu;
+			ir_ioapic[ir_ioapic_num].id = scope->enumeration_id;
+			ir_ioapic_num++;
+		}
+		start += scope->length;
+	}
+
+	return 0;
+}
+
+/*
+ * Finds the assocaition between IOAPIC's and its Interrupt-remapping
+ * hardware unit.
+ */
+int __init parse_ioapics_under_ir(void)
+{
+	struct dmar_drhd_unit *drhd;
+	int ir_supported = 0;
+
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (ecap_ir_support(iommu->ecap)) {
+			if (ir_parse_ioapic_scope(drhd->hdr, iommu))
+				return -1;
+
+			ir_supported = 1;
+		}
+	}
+
+	if (ir_supported && ir_ioapic_num != nr_ioapics) {
+		printk(KERN_WARNING
+		       "Not all IO-APIC's listed under remapping hardware\n");
+		return -1;
+	}
+
+	return ir_supported;
+}
diff --git a/drivers/pci/intr_remapping.h b/drivers/pci/intr_remapping.h
new file mode 100644
index 00000000000..05f2635bbe4
--- /dev/null
+++ b/drivers/pci/intr_remapping.h
@@ -0,0 +1,8 @@
+#include "intel-iommu.h"
+
+struct ioapic_scope {
+	struct intel_iommu *iommu;
+	unsigned int id;
+};
+
+#define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0)
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 9c718583a23..77baff022f7 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -16,6 +16,7 @@
 
 
 #include <linux/kernel.h>
+#include <linux/sched.h>
 #include <linux/pci.h>
 #include <linux/stat.h>
 #include <linux/topology.h>
@@ -484,6 +485,21 @@ pci_mmap_legacy_mem(struct kobject *kobj, struct bin_attribute *attr,
 #endif /* HAVE_PCI_LEGACY */
 
 #ifdef HAVE_PCI_MMAP
+
+static int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma)
+{
+	unsigned long nr, start, size;
+
+	nr = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	start = vma->vm_pgoff;
+	size = pci_resource_len(pdev, resno) >> PAGE_SHIFT;
+	if (start < size && size - start >= nr)
+		return 1;
+	WARN(1, "process \"%s\" tried to map 0x%08lx-0x%08lx on %s BAR %d (size 0x%08lx)\n",
+		current->comm, start, start+nr, pci_name(pdev), resno, size);
+	return 0;
+}
+
 /**
  * pci_mmap_resource - map a PCI resource into user memory space
  * @kobj: kobject for mapping
@@ -510,6 +526,9 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 	if (i >= PCI_ROM_RESOURCE)
 		return -ENODEV;
 
+	if (!pci_mmap_fits(pdev, i, vma))
+		return -EINVAL;
+
 	/* pci_mmap_page_range() expects the same kind of entry as coming
 	 * from /proc/bus/pci/ which is a "user visible" value. If this is
 	 * different from the resource itself, arch will do necessary fixup.