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

* git://git.infradead.org/iommu-2.6:
  drivers/pci/intr_remapping.c: include acpi.h
  intel-iommu: Fix oops in device_to_iommu() when devices not found.
  intel-iommu: Handle PCI domains appropriately.
  intel-iommu: Fix device-to-iommu mapping for PCI-PCI bridges.
  x2apic/intr-remap: decouple interrupt remapping from x2apic
  x86, dmar: check if it's initialized before disable queue invalidation
  intel-iommu: set compatibility format interrupt
  Intel IOMMU Suspend/Resume Support - Interrupt Remapping
  Intel IOMMU Suspend/Resume Support - Queued Invalidation
  Intel IOMMU Suspend/Resume Support - DMAR
  intel-iommu: Add for_each_iommu() and for_each_active_iommu() macros

3 files changed, 348 insertions, 46 deletions

diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index d313039..25a00ce 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -180,6 +180,7 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header)
 	dmaru->hdr = header;
 	drhd = (struct acpi_dmar_hardware_unit *)header;
 	dmaru->reg_base_addr = drhd->address;
+	dmaru->segment = drhd->segment;
 	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
 
 	ret = alloc_iommu(dmaru);
@@ -790,14 +791,41 @@ end:
 }
 
 /*
+ * Enable queued invalidation.
+ */
+static void __dmar_enable_qi(struct intel_iommu *iommu)
+{
+	u32 cmd, sts;
+	unsigned long flags;
+	struct q_inval *qi = iommu->qi;
+
+	qi->free_head = qi->free_tail = 0;
+	qi->free_cnt = QI_LENGTH;
+
+	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);
+}
+
+/*
  * 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))
@@ -835,19 +863,7 @@ int dmar_enable_qi(struct intel_iommu *iommu)
 
 	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);
+	__dmar_enable_qi(iommu);
 
 	return 0;
 }
@@ -1102,3 +1118,28 @@ int __init enable_drhd_fault_handling(void)
 
 	return 0;
 }
+
+/*
+ * Re-enable Queued Invalidation interface.
+ */
+int dmar_reenable_qi(struct intel_iommu *iommu)
+{
+	if (!ecap_qis(iommu->ecap))
+		return -ENOENT;
+
+	if (!iommu->qi)
+		return -ENOENT;
+
+	/*
+	 * First disable queued invalidation.
+	 */
+	dmar_disable_qi(iommu);
+	/*
+	 * Then enable queued invalidation again. Since there is no pending
+	 * invalidation requests now, it's safe to re-enable queued
+	 * invalidation.
+	 */
+	__dmar_enable_qi(iommu);
+
+	return 0;
+}
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 23e56a5..dcda521 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -36,6 +36,7 @@
 #include <linux/iova.h>
 #include <linux/iommu.h>
 #include <linux/intel-iommu.h>
+#include <linux/sysdev.h>
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
 #include "pci.h"
@@ -247,7 +248,8 @@ struct dmar_domain {
 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 */
+	int segment;		/* PCI domain */
+	u8 bus;			/* PCI bus number */
 	u8 devfn;		/* PCI devfn number */
 	struct pci_dev *dev; /* it's NULL for PCIE-to-PCI bridge */
 	struct dmar_domain *domain; /* pointer to domain */
@@ -467,7 +469,7 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
 	domain_update_iommu_snooping(domain);
 }
 
-static struct intel_iommu *device_to_iommu(u8 bus, u8 devfn)
+static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
 	int i;
@@ -475,12 +477,20 @@ static struct intel_iommu *device_to_iommu(u8 bus, u8 devfn)
 	for_each_drhd_unit(drhd) {
 		if (drhd->ignored)
 			continue;
+		if (segment != drhd->segment)
+			continue;
 
-		for (i = 0; i < drhd->devices_cnt; i++)
+		for (i = 0; i < drhd->devices_cnt; i++) {
 			if (drhd->devices[i] &&
 			    drhd->devices[i]->bus->number == bus &&
 			    drhd->devices[i]->devfn == devfn)
 				return drhd->iommu;
+			if (drhd->devices[i] &&
+			    drhd->devices[i]->subordinate &&
+			    drhd->devices[i]->subordinate->number <= bus &&
+			    drhd->devices[i]->subordinate->subordinate >= bus)
+				return drhd->iommu;
+		}
 
 		if (drhd->include_all)
 			return drhd->iommu;
@@ -1312,7 +1322,7 @@ static void domain_exit(struct dmar_domain *domain)
 }
 
 static int domain_context_mapping_one(struct dmar_domain *domain,
-		u8 bus, u8 devfn)
+				      int segment, u8 bus, u8 devfn)
 {
 	struct context_entry *context;
 	unsigned long flags;
@@ -1327,7 +1337,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 		bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
 	BUG_ON(!domain->pgd);
 
-	iommu = device_to_iommu(bus, devfn);
+	iommu = device_to_iommu(segment, bus, devfn);
 	if (!iommu)
 		return -ENODEV;
 
@@ -1417,8 +1427,8 @@ domain_context_mapping(struct dmar_domain *domain, struct pci_dev *pdev)
 	int ret;
 	struct pci_dev *tmp, *parent;
 
-	ret = domain_context_mapping_one(domain, pdev->bus->number,
-		pdev->devfn);
+	ret = domain_context_mapping_one(domain, pci_domain_nr(pdev->bus),
+					 pdev->bus->number, pdev->devfn);
 	if (ret)
 		return ret;
 
@@ -1429,18 +1439,23 @@ domain_context_mapping(struct dmar_domain *domain, struct pci_dev *pdev)
 	/* Secondary interface's bus number and devfn 0 */
 	parent = pdev->bus->self;
 	while (parent != tmp) {
-		ret = domain_context_mapping_one(domain, parent->bus->number,
-			parent->devfn);
+		ret = domain_context_mapping_one(domain,
+						 pci_domain_nr(parent->bus),
+						 parent->bus->number,
+						 parent->devfn);
 		if (ret)
 			return ret;
 		parent = parent->bus->self;
 	}
 	if (tmp->is_pcie) /* this is a PCIE-to-PCI bridge */
 		return domain_context_mapping_one(domain,
-			tmp->subordinate->number, 0);
+					pci_domain_nr(tmp->subordinate),
+					tmp->subordinate->number, 0);
 	else /* this is a legacy PCI bridge */
 		return domain_context_mapping_one(domain,
-			tmp->bus->number, tmp->devfn);
+						  pci_domain_nr(tmp->bus),
+						  tmp->bus->number,
+						  tmp->devfn);
 }
 
 static int domain_context_mapped(struct pci_dev *pdev)
@@ -1449,12 +1464,12 @@ static int domain_context_mapped(struct pci_dev *pdev)
 	struct pci_dev *tmp, *parent;
 	struct intel_iommu *iommu;
 
-	iommu = device_to_iommu(pdev->bus->number, pdev->devfn);
+	iommu = device_to_iommu(pci_domain_nr(pdev->bus), pdev->bus->number,
+				pdev->devfn);
 	if (!iommu)
 		return -ENODEV;
 
-	ret = device_context_mapped(iommu,
-		pdev->bus->number, pdev->devfn);
+	ret = device_context_mapped(iommu, pdev->bus->number, pdev->devfn);
 	if (!ret)
 		return ret;
 	/* dependent device mapping */
@@ -1465,17 +1480,17 @@ static int domain_context_mapped(struct pci_dev *pdev)
 	parent = pdev->bus->self;
 	while (parent != tmp) {
 		ret = device_context_mapped(iommu, parent->bus->number,
-			parent->devfn);
+					    parent->devfn);
 		if (!ret)
 			return ret;
 		parent = parent->bus->self;
 	}
 	if (tmp->is_pcie)
-		return device_context_mapped(iommu,
-			tmp->subordinate->number, 0);
+		return device_context_mapped(iommu, tmp->subordinate->number,
+					     0);
 	else
-		return device_context_mapped(iommu,
-			tmp->bus->number, tmp->devfn);
+		return device_context_mapped(iommu, tmp->bus->number,
+					     tmp->devfn);
 }
 
 static int
@@ -1542,7 +1557,7 @@ static void domain_remove_dev_info(struct dmar_domain *domain)
 			info->dev->dev.archdata.iommu = NULL;
 		spin_unlock_irqrestore(&device_domain_lock, flags);
 
-		iommu = device_to_iommu(info->bus, info->devfn);
+		iommu = device_to_iommu(info->segment, info->bus, info->devfn);
 		iommu_detach_dev(iommu, info->bus, info->devfn);
 		free_devinfo_mem(info);
 
@@ -1577,11 +1592,14 @@ static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw)
 	struct pci_dev *dev_tmp;
 	unsigned long flags;
 	int bus = 0, devfn = 0;
+	int segment;
 
 	domain = find_domain(pdev);
 	if (domain)
 		return domain;
 
+	segment = pci_domain_nr(pdev->bus);
+
 	dev_tmp = pci_find_upstream_pcie_bridge(pdev);
 	if (dev_tmp) {
 		if (dev_tmp->is_pcie) {
@@ -1593,7 +1611,8 @@ static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw)
 		}
 		spin_lock_irqsave(&device_domain_lock, flags);
 		list_for_each_entry(info, &device_domain_list, global) {
-			if (info->bus == bus && info->devfn == devfn) {
+			if (info->segment == segment &&
+			    info->bus == bus && info->devfn == devfn) {
 				found = info->domain;
 				break;
 			}
@@ -1631,6 +1650,7 @@ static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw)
 			domain_exit(domain);
 			goto error;
 		}
+		info->segment = segment;
 		info->bus = bus;
 		info->devfn = devfn;
 		info->dev = NULL;
@@ -1642,7 +1662,8 @@ static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw)
 		found = NULL;
 		spin_lock_irqsave(&device_domain_lock, flags);
 		list_for_each_entry(tmp, &device_domain_list, global) {
-			if (tmp->bus == bus && tmp->devfn == devfn) {
+			if (tmp->segment == segment &&
+			    tmp->bus == bus && tmp->devfn == devfn) {
 				found = tmp->domain;
 				break;
 			}
@@ -1662,6 +1683,7 @@ found_domain:
 	info = alloc_devinfo_mem();
 	if (!info)
 		goto error;
+	info->segment = segment;
 	info->bus = pdev->bus->number;
 	info->devfn = pdev->devfn;
 	info->dev = pdev;
@@ -1946,6 +1968,15 @@ static int __init init_dmars(void)
 		}
 	}
 
+#ifdef CONFIG_INTR_REMAP
+	if (!intr_remapping_enabled) {
+		ret = enable_intr_remapping(0);
+		if (ret)
+			printk(KERN_ERR
+			       "IOMMU: enable interrupt remapping failed\n");
+	}
+#endif
+
 	/*
 	 * For each rmrr
 	 *   for each dev attached to rmrr
@@ -2597,6 +2628,150 @@ static void __init init_no_remapping_devices(void)
 	}
 }
 
+#ifdef CONFIG_SUSPEND
+static int init_iommu_hw(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+
+	for_each_active_iommu(iommu, drhd)
+		if (iommu->qi)
+			dmar_reenable_qi(iommu);
+
+	for_each_active_iommu(iommu, drhd) {
+		iommu_flush_write_buffer(iommu);
+
+		iommu_set_root_entry(iommu);
+
+		iommu->flush.flush_context(iommu, 0, 0, 0,
+						DMA_CCMD_GLOBAL_INVL, 0);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
+						DMA_TLB_GLOBAL_FLUSH, 0);
+		iommu_disable_protect_mem_regions(iommu);
+		iommu_enable_translation(iommu);
+	}
+
+	return 0;
+}
+
+static void iommu_flush_all(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	for_each_active_iommu(iommu, drhd) {
+		iommu->flush.flush_context(iommu, 0, 0, 0,
+						DMA_CCMD_GLOBAL_INVL, 0);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
+						DMA_TLB_GLOBAL_FLUSH, 0);
+	}
+}
+
+static int iommu_suspend(struct sys_device *dev, pm_message_t state)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+	unsigned long flag;
+
+	for_each_active_iommu(iommu, drhd) {
+		iommu->iommu_state = kzalloc(sizeof(u32) * MAX_SR_DMAR_REGS,
+						 GFP_ATOMIC);
+		if (!iommu->iommu_state)
+			goto nomem;
+	}
+
+	iommu_flush_all();
+
+	for_each_active_iommu(iommu, drhd) {
+		iommu_disable_translation(iommu);
+
+		spin_lock_irqsave(&iommu->register_lock, flag);
+
+		iommu->iommu_state[SR_DMAR_FECTL_REG] =
+			readl(iommu->reg + DMAR_FECTL_REG);
+		iommu->iommu_state[SR_DMAR_FEDATA_REG] =
+			readl(iommu->reg + DMAR_FEDATA_REG);
+		iommu->iommu_state[SR_DMAR_FEADDR_REG] =
+			readl(iommu->reg + DMAR_FEADDR_REG);
+		iommu->iommu_state[SR_DMAR_FEUADDR_REG] =
+			readl(iommu->reg + DMAR_FEUADDR_REG);
+
+		spin_unlock_irqrestore(&iommu->register_lock, flag);
+	}
+	return 0;
+
+nomem:
+	for_each_active_iommu(iommu, drhd)
+		kfree(iommu->iommu_state);
+
+	return -ENOMEM;
+}
+
+static int iommu_resume(struct sys_device *dev)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+	unsigned long flag;
+
+	if (init_iommu_hw()) {
+		WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
+		return -EIO;
+	}
+
+	for_each_active_iommu(iommu, drhd) {
+
+		spin_lock_irqsave(&iommu->register_lock, flag);
+
+		writel(iommu->iommu_state[SR_DMAR_FECTL_REG],
+			iommu->reg + DMAR_FECTL_REG);
+		writel(iommu->iommu_state[SR_DMAR_FEDATA_REG],
+			iommu->reg + DMAR_FEDATA_REG);
+		writel(iommu->iommu_state[SR_DMAR_FEADDR_REG],
+			iommu->reg + DMAR_FEADDR_REG);
+		writel(iommu->iommu_state[SR_DMAR_FEUADDR_REG],
+			iommu->reg + DMAR_FEUADDR_REG);
+
+		spin_unlock_irqrestore(&iommu->register_lock, flag);
+	}
+
+	for_each_active_iommu(iommu, drhd)
+		kfree(iommu->iommu_state);
+
+	return 0;
+}
+
+static struct sysdev_class iommu_sysclass = {
+	.name		= "iommu",
+	.resume		= iommu_resume,
+	.suspend	= iommu_suspend,
+};
+
+static struct sys_device device_iommu = {
+	.cls	= &iommu_sysclass,
+};
+
+static int __init init_iommu_sysfs(void)
+{
+	int error;
+
+	error = sysdev_class_register(&iommu_sysclass);
+	if (error)
+		return error;
+
+	error = sysdev_register(&device_iommu);
+	if (error)
+		sysdev_class_unregister(&iommu_sysclass);
+
+	return error;
+}
+
+#else
+static int __init init_iommu_sysfs(void)
+{
+	return 0;
+}
+#endif	/* CONFIG_PM */
+
 int __init intel_iommu_init(void)
 {
 	int ret = 0;
@@ -2632,6 +2807,7 @@ int __init intel_iommu_init(void)
 	init_timer(&unmap_timer);
 	force_iommu = 1;
 	dma_ops = &intel_dma_ops;
+	init_iommu_sysfs();
 
 	register_iommu(&intel_iommu_ops);
 
@@ -2648,6 +2824,7 @@ static int vm_domain_add_dev_info(struct dmar_domain *domain,
 	if (!info)
 		return -ENOMEM;
 
+	info->segment = pci_domain_nr(pdev->bus);
 	info->bus = pdev->bus->number;
 	info->devfn = pdev->devfn;
 	info->dev = pdev;
@@ -2677,15 +2854,15 @@ static void iommu_detach_dependent_devices(struct intel_iommu *iommu,
 		parent = pdev->bus->self;
 		while (parent != tmp) {
 			iommu_detach_dev(iommu, parent->bus->number,
-				parent->devfn);
+					 parent->devfn);
 			parent = parent->bus->self;
 		}
 		if (tmp->is_pcie) /* this is a PCIE-to-PCI bridge */
 			iommu_detach_dev(iommu,
 				tmp->subordinate->number, 0);
 		else /* this is a legacy PCI bridge */
-			iommu_detach_dev(iommu,
-				tmp->bus->number, tmp->devfn);
+			iommu_detach_dev(iommu, tmp->bus->number,
+					 tmp->devfn);
 	}
 }
 
@@ -2698,13 +2875,15 @@ static void vm_domain_remove_one_dev_info(struct dmar_domain *domain,
 	int found = 0;
 	struct list_head *entry, *tmp;
 
-	iommu = device_to_iommu(pdev->bus->number, pdev->devfn);
+	iommu = device_to_iommu(pci_domain_nr(pdev->bus), pdev->bus->number,
+				pdev->devfn);
 	if (!iommu)
 		return;
 
 	spin_lock_irqsave(&device_domain_lock, flags);
 	list_for_each_safe(entry, tmp, &domain->devices) {
 		info = list_entry(entry, struct device_domain_info, link);
+		/* No need to compare PCI domain; it has to be the same */
 		if (info->bus == pdev->bus->number &&
 		    info->devfn == pdev->devfn) {
 			list_del(&info->link);
@@ -2729,7 +2908,8 @@ static void vm_domain_remove_one_dev_info(struct dmar_domain *domain,
 		 * owned by this domain, clear this iommu in iommu_bmp
 		 * update iommu count and coherency
 		 */
-		if (device_to_iommu(info->bus, info->devfn) == iommu)
+		if (iommu == device_to_iommu(info->segment, info->bus,
+					    info->devfn))
 			found = 1;
 	}
 
@@ -2762,7 +2942,7 @@ static void vm_domain_remove_all_dev_info(struct dmar_domain *domain)
 
 		spin_unlock_irqrestore(&device_domain_lock, flags1);
 
-		iommu = device_to_iommu(info->bus, info->devfn);
+		iommu = device_to_iommu(info->segment, info->bus, info->devfn);
 		iommu_detach_dev(iommu, info->bus, info->devfn);
 		iommu_detach_dependent_devices(iommu, info->dev);
 
@@ -2950,7 +3130,8 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 		}
 	}
 
-	iommu = device_to_iommu(pdev->bus->number, pdev->devfn);
+	iommu = device_to_iommu(pci_domain_nr(pdev->bus), pdev->bus->number,
+				pdev->devfn);
 	if (!iommu)
 		return -ENODEV;
 
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index b041a40..f5e0ea7 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -9,6 +9,7 @@
 #include <asm/cpu.h>
 #include <linux/intel-iommu.h>
 #include "intr_remapping.h"
+#include <acpi/acpi.h>
 
 static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
 static int ir_ioapic_num;
@@ -415,12 +416,27 @@ static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode)
 
 	/* Set interrupt-remapping table pointer */
 	cmd = iommu->gcmd | DMA_GCMD_SIRTP;
+	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);
 
+	if (mode == 0) {
+		spin_lock_irqsave(&iommu->register_lock, flags);
+
+		/* enable comaptiblity format interrupt pass through */
+		cmd = iommu->gcmd | DMA_GCMD_CFI;
+		iommu->gcmd |= DMA_GCMD_CFI;
+		writel(cmd, iommu->reg + DMAR_GCMD_REG);
+
+		IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+			      readl, (sts & DMA_GSTS_CFIS), sts);
+
+		spin_unlock_irqrestore(&iommu->register_lock, flags);
+	}
+
 	/*
 	 * global invalidation of interrupt entry cache before enabling
 	 * interrupt-remapping.
@@ -470,7 +486,7 @@ static int setup_intr_remapping(struct intel_iommu *iommu, int mode)
 /*
  * Disable Interrupt Remapping.
  */
-static void disable_intr_remapping(struct intel_iommu *iommu)
+static void iommu_disable_intr_remapping(struct intel_iommu *iommu)
 {
 	unsigned long flags;
 	u32 sts;
@@ -478,6 +494,12 @@ static void disable_intr_remapping(struct intel_iommu *iommu)
 	if (!ecap_ir_support(iommu->ecap))
 		return;
 
+	/*
+	 * global invalidation of interrupt entry cache before disabling
+	 * interrupt-remapping.
+	 */
+	qi_global_iec(iommu);
+
 	spin_lock_irqsave(&iommu->register_lock, flags);
 
 	sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
@@ -503,6 +525,13 @@ int __init enable_intr_remapping(int eim)
 		struct intel_iommu *iommu = drhd->iommu;
 
 		/*
+		 * If the queued invalidation is already initialized,
+		 * shouldn't disable it.
+		 */
+		if (iommu->qi)
+			continue;
+
+		/*
 		 * Clear previous faults.
 		 */
 		dmar_fault(-1, iommu);
@@ -511,7 +540,7 @@ int __init enable_intr_remapping(int eim)
 		 * Disable intr remapping and queued invalidation, if already
 		 * enabled prior to OS handover.
 		 */
-		disable_intr_remapping(iommu);
+		iommu_disable_intr_remapping(iommu);
 
 		dmar_disable_qi(iommu);
 	}
@@ -639,3 +668,54 @@ int __init parse_ioapics_under_ir(void)
 
 	return ir_supported;
 }
+
+void disable_intr_remapping(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+
+	/*
+	 * Disable Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_iommu(iommu, drhd) {
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		iommu_disable_intr_remapping(iommu);
+	}
+}
+
+int reenable_intr_remapping(int eim)
+{
+	struct dmar_drhd_unit *drhd;
+	int setup = 0;
+	struct intel_iommu *iommu = NULL;
+
+	for_each_iommu(iommu, drhd)
+		if (iommu->qi)
+			dmar_reenable_qi(iommu);
+
+	/*
+	 * Setup Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_iommu(iommu, drhd) {
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		/* Set up interrupt remapping for iommu.*/
+		iommu_set_intr_remapping(iommu, eim);
+		setup = 1;
+	}
+
+	if (!setup)
+		goto error;
+
+	return 0;
+
+error:
+	/*
+	 * handle error condition gracefully here!
+	 */
+	return -1;
+}
+