Merge branch 'x86-stage-3-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-stage-3-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (190 commits)
  Revert "cpuacct: reduce one NULL check in fast-path"
  Revert "x86: don't compile vsmp_64 for 32bit"
  x86: Correct behaviour of irq affinity
  x86: early_ioremap_init(), use __fix_to_virt(), because we are sure it's safe
  x86: use default_cpu_mask_to_apicid for 64bit
  x86: fix set_extra_move_desc calling
  x86, PAT, PCI: Change vma prot in pci_mmap to reflect inherited prot
  x86/dmi: fix dmi_alloc() section mismatches
  x86: e820 fix various signedness issues in setup.c and e820.c
  x86: apic/io_apic.c define msi_ir_chip and ir_ioapic_chip all the time
  x86: irq.c keep CONFIG_X86_LOCAL_APIC interrupts together
  x86: irq.c use same path for show_interrupts
  x86: cpu/cpu.h cleanup
  x86: Fix a couple of sparse warnings in arch/x86/kernel/apic/io_apic.c
  Revert "x86: create a non-zero sized bm_pte only when needed"
  x86: pci-nommu.c cleanup
  x86: io_delay.c cleanup
  x86: rtc.c cleanup
  x86: i8253 cleanup
  x86: kdebugfs.c cleanup
  ...

3 files changed, 404 insertions, 222 deletions

diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 5f333403c2ea..d313039e2fdf 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -31,6 +31,8 @@
 #include <linux/iova.h>
 #include <linux/intel-iommu.h>
 #include <linux/timer.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
 
 #undef PREFIX
 #define PREFIX "DMAR:"
@@ -509,6 +511,7 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 		return -ENOMEM;
 
 	iommu->seq_id = iommu_allocated++;
+	sprintf (iommu->name, "dmar%d", iommu->seq_id);
 
 	iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE);
 	if (!iommu->reg) {
@@ -751,6 +754,42 @@ int qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
 }
 
 /*
+ * Disable Queued Invalidation interface.
+ */
+void dmar_disable_qi(struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	u32 sts;
+	cycles_t start_time = get_cycles();
+
+	if (!ecap_qis(iommu->ecap))
+		return;
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	sts =  dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	if (!(sts & DMA_GSTS_QIES))
+		goto end;
+
+	/*
+	 * Give a chance to HW to complete the pending invalidation requests.
+	 */
+	while ((readl(iommu->reg + DMAR_IQT_REG) !=
+		readl(iommu->reg + DMAR_IQH_REG)) &&
+		(DMAR_OPERATION_TIMEOUT > (get_cycles() - start_time)))
+		cpu_relax();
+
+	iommu->gcmd &= ~DMA_GCMD_QIE;
+
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl,
+		      !(sts & DMA_GSTS_QIES), sts);
+end:
+	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.
@@ -770,20 +809,20 @@ int dmar_enable_qi(struct intel_iommu *iommu)
 	if (iommu->qi)
 		return 0;
 
-	iommu->qi = kmalloc(sizeof(*qi), GFP_KERNEL);
+	iommu->qi = kmalloc(sizeof(*qi), GFP_ATOMIC);
 	if (!iommu->qi)
 		return -ENOMEM;
 
 	qi = iommu->qi;
 
-	qi->desc = (void *)(get_zeroed_page(GFP_KERNEL));
+	qi->desc = (void *)(get_zeroed_page(GFP_ATOMIC));
 	if (!qi->desc) {
 		kfree(qi);
 		iommu->qi = 0;
 		return -ENOMEM;
 	}
 
-	qi->desc_status = kmalloc(QI_LENGTH * sizeof(int), GFP_KERNEL);
+	qi->desc_status = kmalloc(QI_LENGTH * sizeof(int), GFP_ATOMIC);
 	if (!qi->desc_status) {
 		free_page((unsigned long) qi->desc);
 		kfree(qi);
@@ -812,3 +851,254 @@ int dmar_enable_qi(struct intel_iommu *iommu)
 
 	return 0;
 }
+
+/* iommu interrupt handling. Most stuff are MSI-like. */
+
+enum faulttype {
+	DMA_REMAP,
+	INTR_REMAP,
+	UNKNOWN,
+};
+
+static const char *dma_remap_fault_reasons[] =
+{
+	"Software",
+	"Present bit in root entry is clear",
+	"Present bit in context entry is clear",
+	"Invalid context entry",
+	"Access beyond MGAW",
+	"PTE Write access is not set",
+	"PTE Read access is not set",
+	"Next page table ptr is invalid",
+	"Root table address invalid",
+	"Context table ptr is invalid",
+	"non-zero reserved fields in RTP",
+	"non-zero reserved fields in CTP",
+	"non-zero reserved fields in PTE",
+};
+
+static const char *intr_remap_fault_reasons[] =
+{
+	"Detected reserved fields in the decoded interrupt-remapped request",
+	"Interrupt index exceeded the interrupt-remapping table size",
+	"Present field in the IRTE entry is clear",
+	"Error accessing interrupt-remapping table pointed by IRTA_REG",
+	"Detected reserved fields in the IRTE entry",
+	"Blocked a compatibility format interrupt request",
+	"Blocked an interrupt request due to source-id verification failure",
+};
+
+#define MAX_FAULT_REASON_IDX 	(ARRAY_SIZE(fault_reason_strings) - 1)
+
+const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
+{
+	if (fault_reason >= 0x20 && (fault_reason <= 0x20 +
+				     ARRAY_SIZE(intr_remap_fault_reasons))) {
+		*fault_type = INTR_REMAP;
+		return intr_remap_fault_reasons[fault_reason - 0x20];
+	} else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) {
+		*fault_type = DMA_REMAP;
+		return dma_remap_fault_reasons[fault_reason];
+	} else {
+		*fault_type = UNKNOWN;
+		return "Unknown";
+	}
+}
+
+void dmar_msi_unmask(unsigned int irq)
+{
+	struct intel_iommu *iommu = get_irq_data(irq);
+	unsigned long flag;
+
+	/* unmask it */
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(0, iommu->reg + DMAR_FECTL_REG);
+	/* Read a reg to force flush the post write */
+	readl(iommu->reg + DMAR_FECTL_REG);
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_mask(unsigned int irq)
+{
+	unsigned long flag;
+	struct intel_iommu *iommu = get_irq_data(irq);
+
+	/* mask it */
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(DMA_FECTL_IM, iommu->reg + DMAR_FECTL_REG);
+	/* Read a reg to force flush the post write */
+	readl(iommu->reg + DMAR_FECTL_REG);
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_write(int irq, struct msi_msg *msg)
+{
+	struct intel_iommu *iommu = get_irq_data(irq);
+	unsigned long flag;
+
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(msg->data, iommu->reg + DMAR_FEDATA_REG);
+	writel(msg->address_lo, iommu->reg + DMAR_FEADDR_REG);
+	writel(msg->address_hi, iommu->reg + DMAR_FEUADDR_REG);
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_read(int irq, struct msi_msg *msg)
+{
+	struct intel_iommu *iommu = get_irq_data(irq);
+	unsigned long flag;
+
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	msg->data = readl(iommu->reg + DMAR_FEDATA_REG);
+	msg->address_lo = readl(iommu->reg + DMAR_FEADDR_REG);
+	msg->address_hi = readl(iommu->reg + DMAR_FEUADDR_REG);
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
+		u8 fault_reason, u16 source_id, unsigned long long addr)
+{
+	const char *reason;
+	int fault_type;
+
+	reason = dmar_get_fault_reason(fault_reason, &fault_type);
+
+	if (fault_type == INTR_REMAP)
+		printk(KERN_ERR "INTR-REMAP: Request device [[%02x:%02x.%d] "
+		       "fault index %llx\n"
+			"INTR-REMAP:[fault reason %02d] %s\n",
+			(source_id >> 8), PCI_SLOT(source_id & 0xFF),
+			PCI_FUNC(source_id & 0xFF), addr >> 48,
+			fault_reason, reason);
+	else
+		printk(KERN_ERR
+		       "DMAR:[%s] Request device [%02x:%02x.%d] "
+		       "fault addr %llx \n"
+		       "DMAR:[fault reason %02d] %s\n",
+		       (type ? "DMA Read" : "DMA Write"),
+		       (source_id >> 8), PCI_SLOT(source_id & 0xFF),
+		       PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
+	return 0;
+}
+
+#define PRIMARY_FAULT_REG_LEN (16)
+irqreturn_t dmar_fault(int irq, void *dev_id)
+{
+	struct intel_iommu *iommu = dev_id;
+	int reg, fault_index;
+	u32 fault_status;
+	unsigned long flag;
+
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
+	if (fault_status)
+		printk(KERN_ERR "DRHD: handling fault status reg %x\n",
+		       fault_status);
+
+	/* TBD: ignore advanced fault log currently */
+	if (!(fault_status & DMA_FSTS_PPF))
+		goto clear_rest;
+
+	fault_index = dma_fsts_fault_record_index(fault_status);
+	reg = cap_fault_reg_offset(iommu->cap);
+	while (1) {
+		u8 fault_reason;
+		u16 source_id;
+		u64 guest_addr;
+		int type;
+		u32 data;
+
+		/* highest 32 bits */
+		data = readl(iommu->reg + reg +
+				fault_index * PRIMARY_FAULT_REG_LEN + 12);
+		if (!(data & DMA_FRCD_F))
+			break;
+
+		fault_reason = dma_frcd_fault_reason(data);
+		type = dma_frcd_type(data);
+
+		data = readl(iommu->reg + reg +
+				fault_index * PRIMARY_FAULT_REG_LEN + 8);
+		source_id = dma_frcd_source_id(data);
+
+		guest_addr = dmar_readq(iommu->reg + reg +
+				fault_index * PRIMARY_FAULT_REG_LEN);
+		guest_addr = dma_frcd_page_addr(guest_addr);
+		/* clear the fault */
+		writel(DMA_FRCD_F, iommu->reg + reg +
+			fault_index * PRIMARY_FAULT_REG_LEN + 12);
+
+		spin_unlock_irqrestore(&iommu->register_lock, flag);
+
+		dmar_fault_do_one(iommu, type, fault_reason,
+				source_id, guest_addr);
+
+		fault_index++;
+		if (fault_index > cap_num_fault_regs(iommu->cap))
+			fault_index = 0;
+		spin_lock_irqsave(&iommu->register_lock, flag);
+	}
+clear_rest:
+	/* clear all the other faults */
+	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
+	writel(fault_status, iommu->reg + DMAR_FSTS_REG);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+	return IRQ_HANDLED;
+}
+
+int dmar_set_interrupt(struct intel_iommu *iommu)
+{
+	int irq, ret;
+
+	/*
+	 * Check if the fault interrupt is already initialized.
+	 */
+	if (iommu->irq)
+		return 0;
+
+	irq = create_irq();
+	if (!irq) {
+		printk(KERN_ERR "IOMMU: no free vectors\n");
+		return -EINVAL;
+	}
+
+	set_irq_data(irq, iommu);
+	iommu->irq = irq;
+
+	ret = arch_setup_dmar_msi(irq);
+	if (ret) {
+		set_irq_data(irq, NULL);
+		iommu->irq = 0;
+		destroy_irq(irq);
+		return 0;
+	}
+
+	ret = request_irq(irq, dmar_fault, 0, iommu->name, iommu);
+	if (ret)
+		printk(KERN_ERR "IOMMU: can't request irq\n");
+	return ret;
+}
+
+int __init enable_drhd_fault_handling(void)
+{
+	struct dmar_drhd_unit *drhd;
+
+	/*
+	 * Enable fault control interrupt.
+	 */
+	for_each_drhd_unit(drhd) {
+		int ret;
+		struct intel_iommu *iommu = drhd->iommu;
+		ret = dmar_set_interrupt(iommu);
+
+		if (ret) {
+			printk(KERN_ERR "DRHD %Lx: failed to enable fault, "
+			       " interrupt, ret %d\n",
+			       (unsigned long long)drhd->reg_base_addr, ret);
+			return -1;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index f3f686581a90..ef167b8b047d 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -1004,194 +1004,6 @@ static int iommu_disable_translation(struct intel_iommu *iommu)
 	return 0;
 }
 
-/* iommu interrupt handling. Most stuff are MSI-like. */
-
-static const char *fault_reason_strings[] =
-{
-	"Software",
-	"Present bit in root entry is clear",
-	"Present bit in context entry is clear",
-	"Invalid context entry",
-	"Access beyond MGAW",
-	"PTE Write access is not set",
-	"PTE Read access is not set",
-	"Next page table ptr is invalid",
-	"Root table address invalid",
-	"Context table ptr is invalid",
-	"non-zero reserved fields in RTP",
-	"non-zero reserved fields in CTP",
-	"non-zero reserved fields in PTE",
-};
-#define MAX_FAULT_REASON_IDX 	(ARRAY_SIZE(fault_reason_strings) - 1)
-
-const char *dmar_get_fault_reason(u8 fault_reason)
-{
-	if (fault_reason > MAX_FAULT_REASON_IDX)
-		return "Unknown";
-	else
-		return fault_reason_strings[fault_reason];
-}
-
-void dmar_msi_unmask(unsigned int irq)
-{
-	struct intel_iommu *iommu = get_irq_data(irq);
-	unsigned long flag;
-
-	/* unmask it */
-	spin_lock_irqsave(&iommu->register_lock, flag);
-	writel(0, iommu->reg + DMAR_FECTL_REG);
-	/* Read a reg to force flush the post write */
-	readl(iommu->reg + DMAR_FECTL_REG);
-	spin_unlock_irqrestore(&iommu->register_lock, flag);
-}
-
-void dmar_msi_mask(unsigned int irq)
-{
-	unsigned long flag;
-	struct intel_iommu *iommu = get_irq_data(irq);
-
-	/* mask it */
-	spin_lock_irqsave(&iommu->register_lock, flag);
-	writel(DMA_FECTL_IM, iommu->reg + DMAR_FECTL_REG);
-	/* Read a reg to force flush the post write */
-	readl(iommu->reg + DMAR_FECTL_REG);
-	spin_unlock_irqrestore(&iommu->register_lock, flag);
-}
-
-void dmar_msi_write(int irq, struct msi_msg *msg)
-{
-	struct intel_iommu *iommu = get_irq_data(irq);
-	unsigned long flag;
-
-	spin_lock_irqsave(&iommu->register_lock, flag);
-	writel(msg->data, iommu->reg + DMAR_FEDATA_REG);
-	writel(msg->address_lo, iommu->reg + DMAR_FEADDR_REG);
-	writel(msg->address_hi, iommu->reg + DMAR_FEUADDR_REG);
-	spin_unlock_irqrestore(&iommu->register_lock, flag);
-}
-
-void dmar_msi_read(int irq, struct msi_msg *msg)
-{
-	struct intel_iommu *iommu = get_irq_data(irq);
-	unsigned long flag;
-
-	spin_lock_irqsave(&iommu->register_lock, flag);
-	msg->data = readl(iommu->reg + DMAR_FEDATA_REG);
-	msg->address_lo = readl(iommu->reg + DMAR_FEADDR_REG);
-	msg->address_hi = readl(iommu->reg + DMAR_FEUADDR_REG);
-	spin_unlock_irqrestore(&iommu->register_lock, flag);
-}
-
-static int iommu_page_fault_do_one(struct intel_iommu *iommu, int type,
-		u8 fault_reason, u16 source_id, unsigned long long addr)
-{
-	const char *reason;
-
-	reason = dmar_get_fault_reason(fault_reason);
-
-	printk(KERN_ERR
-		"DMAR:[%s] Request device [%02x:%02x.%d] "
-		"fault addr %llx \n"
-		"DMAR:[fault reason %02d] %s\n",
-		(type ? "DMA Read" : "DMA Write"),
-		(source_id >> 8), PCI_SLOT(source_id & 0xFF),
-		PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
-	return 0;
-}
-
-#define PRIMARY_FAULT_REG_LEN (16)
-static irqreturn_t iommu_page_fault(int irq, void *dev_id)
-{
-	struct intel_iommu *iommu = dev_id;
-	int reg, fault_index;
-	u32 fault_status;
-	unsigned long flag;
-
-	spin_lock_irqsave(&iommu->register_lock, flag);
-	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
-
-	/* TBD: ignore advanced fault log currently */
-	if (!(fault_status & DMA_FSTS_PPF))
-		goto clear_overflow;
-
-	fault_index = dma_fsts_fault_record_index(fault_status);
-	reg = cap_fault_reg_offset(iommu->cap);
-	while (1) {
-		u8 fault_reason;
-		u16 source_id;
-		u64 guest_addr;
-		int type;
-		u32 data;
-
-		/* highest 32 bits */
-		data = readl(iommu->reg + reg +
-				fault_index * PRIMARY_FAULT_REG_LEN + 12);
-		if (!(data & DMA_FRCD_F))
-			break;
-
-		fault_reason = dma_frcd_fault_reason(data);
-		type = dma_frcd_type(data);
-
-		data = readl(iommu->reg + reg +
-				fault_index * PRIMARY_FAULT_REG_LEN + 8);
-		source_id = dma_frcd_source_id(data);
-
-		guest_addr = dmar_readq(iommu->reg + reg +
-				fault_index * PRIMARY_FAULT_REG_LEN);
-		guest_addr = dma_frcd_page_addr(guest_addr);
-		/* clear the fault */
-		writel(DMA_FRCD_F, iommu->reg + reg +
-			fault_index * PRIMARY_FAULT_REG_LEN + 12);
-
-		spin_unlock_irqrestore(&iommu->register_lock, flag);
-
-		iommu_page_fault_do_one(iommu, type, fault_reason,
-				source_id, guest_addr);
-
-		fault_index++;
-		if (fault_index > cap_num_fault_regs(iommu->cap))
-			fault_index = 0;
-		spin_lock_irqsave(&iommu->register_lock, flag);
-	}
-clear_overflow:
-	/* clear primary fault overflow */
-	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
-	if (fault_status & DMA_FSTS_PFO)
-		writel(DMA_FSTS_PFO, iommu->reg + DMAR_FSTS_REG);
-
-	spin_unlock_irqrestore(&iommu->register_lock, flag);
-	return IRQ_HANDLED;
-}
-
-int dmar_set_interrupt(struct intel_iommu *iommu)
-{
-	int irq, ret;
-
-	irq = create_irq();
-	if (!irq) {
-		printk(KERN_ERR "IOMMU: no free vectors\n");
-		return -EINVAL;
-	}
-
-	set_irq_data(irq, iommu);
-	iommu->irq = irq;
-
-	ret = arch_setup_dmar_msi(irq);
-	if (ret) {
-		set_irq_data(irq, NULL);
-		iommu->irq = 0;
-		destroy_irq(irq);
-		return 0;
-	}
-
-	/* Force fault register is cleared */
-	iommu_page_fault(irq, iommu);
-
-	ret = request_irq(irq, iommu_page_fault, 0, iommu->name, iommu);
-	if (ret)
-		printk(KERN_ERR "IOMMU: can't request irq\n");
-	return ret;
-}
 
 static int iommu_init_domains(struct intel_iommu *iommu)
 {
@@ -1987,7 +1799,7 @@ static int __init init_dmars(void)
 	struct dmar_rmrr_unit *rmrr;
 	struct pci_dev *pdev;
 	struct intel_iommu *iommu;
-	int i, ret, unit = 0;
+	int i, ret;
 
 	/*
 	 * for each drhd
@@ -2043,11 +1855,40 @@ static int __init init_dmars(void)
 		}
 	}
 
+	/*
+	 * Start from the sane iommu hardware state.
+	 */
+	for_each_drhd_unit(drhd) {
+		if (drhd->ignored)
+			continue;
+
+		iommu = drhd->iommu;
+
+		/*
+		 * If the queued invalidation is already initialized by us
+		 * (for example, while enabling interrupt-remapping) then
+		 * we got the things already rolling from a sane state.
+		 */
+		if (iommu->qi)
+			continue;
+
+		/*
+		 * Clear any previous faults.
+		 */
+		dmar_fault(-1, iommu);
+		/*
+		 * Disable queued invalidation if supported and already enabled
+		 * before OS handover.
+		 */
+		dmar_disable_qi(iommu);
+	}
+
 	for_each_drhd_unit(drhd) {
 		if (drhd->ignored)
 			continue;
 
 		iommu = drhd->iommu;
+
 		if (dmar_enable_qi(iommu)) {
 			/*
 			 * Queued Invalidate not enabled, use Register Based
@@ -2109,7 +1950,6 @@ static int __init init_dmars(void)
 		if (drhd->ignored)
 			continue;
 		iommu = drhd->iommu;
-		sprintf (iommu->name, "dmar%d", unit++);
 
 		iommu_flush_write_buffer(iommu);
 
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index 9d07a05d26f1..b041a409f4a7 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -117,21 +117,22 @@ int get_irte(int irq, struct irte *entry)
 {
 	int index;
 	struct irq_2_iommu *irq_iommu;
+	unsigned long flags;
 
 	if (!entry)
 		return -1;
 
-	spin_lock(&irq_2_ir_lock);
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 	irq_iommu = valid_irq_2_iommu(irq);
 	if (!irq_iommu) {
-		spin_unlock(&irq_2_ir_lock);
+		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 		return -1;
 	}
 
 	index = irq_iommu->irte_index + irq_iommu->sub_handle;
 	*entry = *(irq_iommu->iommu->ir_table->base + index);
 
-	spin_unlock(&irq_2_ir_lock);
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 	return 0;
 }
 
@@ -141,6 +142,7 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 	struct irq_2_iommu *irq_iommu;
 	u16 index, start_index;
 	unsigned int mask = 0;
+	unsigned long flags;
 	int i;
 
 	if (!count)
@@ -170,7 +172,7 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 		return -1;
 	}
 
-	spin_lock(&irq_2_ir_lock);
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 	do {
 		for (i = index; i < index + count; i++)
 			if  (table->base[i].present)
@@ -182,7 +184,7 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 		index = (index + count) % INTR_REMAP_TABLE_ENTRIES;
 
 		if (index == start_index) {
-			spin_unlock(&irq_2_ir_lock);
+			spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 			printk(KERN_ERR "can't allocate an IRTE\n");
 			return -1;
 		}
@@ -193,7 +195,7 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 
 	irq_iommu = irq_2_iommu_alloc(irq);
 	if (!irq_iommu) {
-		spin_unlock(&irq_2_ir_lock);
+		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 		printk(KERN_ERR "can't allocate irq_2_iommu\n");
 		return -1;
 	}
@@ -203,7 +205,7 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 	irq_iommu->sub_handle = 0;
 	irq_iommu->irte_mask = mask;
 
-	spin_unlock(&irq_2_ir_lock);
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
 	return index;
 }
@@ -223,30 +225,32 @@ int map_irq_to_irte_handle(int irq, u16 *sub_handle)
 {
 	int index;
 	struct irq_2_iommu *irq_iommu;
+	unsigned long flags;
 
-	spin_lock(&irq_2_ir_lock);
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 	irq_iommu = valid_irq_2_iommu(irq);
 	if (!irq_iommu) {
-		spin_unlock(&irq_2_ir_lock);
+		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 		return -1;
 	}
 
 	*sub_handle = irq_iommu->sub_handle;
 	index = irq_iommu->irte_index;
-	spin_unlock(&irq_2_ir_lock);
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 	return index;
 }
 
 int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 {
 	struct irq_2_iommu *irq_iommu;
+	unsigned long flags;
 
-	spin_lock(&irq_2_ir_lock);
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 
 	irq_iommu = irq_2_iommu_alloc(irq);
 
 	if (!irq_iommu) {
-		spin_unlock(&irq_2_ir_lock);
+		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 		printk(KERN_ERR "can't allocate irq_2_iommu\n");
 		return -1;
 	}
@@ -256,7 +260,7 @@ int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 	irq_iommu->sub_handle = subhandle;
 	irq_iommu->irte_mask = 0;
 
-	spin_unlock(&irq_2_ir_lock);
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
 	return 0;
 }
@@ -264,11 +268,12 @@ int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index)
 {
 	struct irq_2_iommu *irq_iommu;
+	unsigned long flags;
 
-	spin_lock(&irq_2_ir_lock);
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 	irq_iommu = valid_irq_2_iommu(irq);
 	if (!irq_iommu) {
-		spin_unlock(&irq_2_ir_lock);
+		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 		return -1;
 	}
 
@@ -277,7 +282,7 @@ int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index)
 	irq_iommu->sub_handle = 0;
 	irq_2_iommu(irq)->irte_mask = 0;
 
-	spin_unlock(&irq_2_ir_lock);
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
 	return 0;
 }
@@ -289,11 +294,12 @@ int modify_irte(int irq, struct irte *irte_modified)
 	struct irte *irte;
 	struct intel_iommu *iommu;
 	struct irq_2_iommu *irq_iommu;
+	unsigned long flags;
 
-	spin_lock(&irq_2_ir_lock);
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 	irq_iommu = valid_irq_2_iommu(irq);
 	if (!irq_iommu) {
-		spin_unlock(&irq_2_ir_lock);
+		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 		return -1;
 	}
 
@@ -302,11 +308,11 @@ int modify_irte(int irq, struct irte *irte_modified)
 	index = irq_iommu->irte_index + irq_iommu->sub_handle;
 	irte = &iommu->ir_table->base[index];
 
-	set_64bit((unsigned long *)irte, irte_modified->low | (1 << 1));
+	set_64bit((unsigned long *)irte, irte_modified->low);
 	__iommu_flush_cache(iommu, irte, sizeof(*irte));
 
 	rc = qi_flush_iec(iommu, index, 0);
-	spin_unlock(&irq_2_ir_lock);
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
 	return rc;
 }
@@ -317,11 +323,12 @@ int flush_irte(int irq)
 	int index;
 	struct intel_iommu *iommu;
 	struct irq_2_iommu *irq_iommu;
+	unsigned long flags;
 
-	spin_lock(&irq_2_ir_lock);
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 	irq_iommu = valid_irq_2_iommu(irq);
 	if (!irq_iommu) {
-		spin_unlock(&irq_2_ir_lock);
+		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 		return -1;
 	}
 
@@ -330,7 +337,7 @@ int flush_irte(int irq)
 	index = irq_iommu->irte_index + irq_iommu->sub_handle;
 
 	rc = qi_flush_iec(iommu, index, irq_iommu->irte_mask);
-	spin_unlock(&irq_2_ir_lock);
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
 	return rc;
 }
@@ -363,11 +370,12 @@ int free_irte(int irq)
 	struct irte *irte;
 	struct intel_iommu *iommu;
 	struct irq_2_iommu *irq_iommu;
+	unsigned long flags;
 
-	spin_lock(&irq_2_ir_lock);
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 	irq_iommu = valid_irq_2_iommu(irq);
 	if (!irq_iommu) {
-		spin_unlock(&irq_2_ir_lock);
+		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 		return -1;
 	}
 
@@ -378,7 +386,7 @@ int free_irte(int irq)
 
 	if (!irq_iommu->sub_handle) {
 		for (i = 0; i < (1 << irq_iommu->irte_mask); i++)
-			set_64bit((unsigned long *)irte, 0);
+			set_64bit((unsigned long *)(irte + i), 0);
 		rc = qi_flush_iec(iommu, index, irq_iommu->irte_mask);
 	}
 
@@ -387,7 +395,7 @@ int free_irte(int irq)
 	irq_iommu->sub_handle = 0;
 	irq_iommu->irte_mask = 0;
 
-	spin_unlock(&irq_2_ir_lock);
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
 	return rc;
 }
@@ -439,12 +447,12 @@ static int setup_intr_remapping(struct intel_iommu *iommu, int mode)
 	struct page *pages;
 
 	ir_table = iommu->ir_table = kzalloc(sizeof(struct ir_table),
-					     GFP_KERNEL);
+					     GFP_ATOMIC);
 
 	if (!iommu->ir_table)
 		return -ENOMEM;
 
-	pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, INTR_REMAP_PAGE_ORDER);
+	pages = alloc_pages(GFP_ATOMIC | __GFP_ZERO, INTR_REMAP_PAGE_ORDER);
 
 	if (!pages) {
 		printk(KERN_ERR "failed to allocate pages of order %d\n",
@@ -459,11 +467,55 @@ static int setup_intr_remapping(struct intel_iommu *iommu, int mode)
 	return 0;
 }
 
+/*
+ * Disable Interrupt Remapping.
+ */
+static void disable_intr_remapping(struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	u32 sts;
+
+	if (!ecap_ir_support(iommu->ecap))
+		return;
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	if (!(sts & DMA_GSTS_IRES))
+		goto end;
+
+	iommu->gcmd &= ~DMA_GCMD_IRE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, !(sts & DMA_GSTS_IRES), sts);
+
+end:
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
 int __init enable_intr_remapping(int eim)
 {
 	struct dmar_drhd_unit *drhd;
 	int setup = 0;
 
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		/*
+		 * Clear previous faults.
+		 */
+		dmar_fault(-1, iommu);
+
+		/*
+		 * Disable intr remapping and queued invalidation, if already
+		 * enabled prior to OS handover.
+		 */
+		disable_intr_remapping(iommu);
+
+		dmar_disable_qi(iommu);
+	}
+
 	/*
 	 * check for the Interrupt-remapping support
 	 */