Merge tag 'iommu-updates-v3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "This time the updates contain:

   - Tracepoints for certain IOMMU-API functions to make their use
     easier to debug
   - A tracepoint for IOMMU page faults to make it easier to get them in
     user space
   - Updates and fixes for the new ARM SMMU driver after the first
     hardware showed up
   - Various other fixes and cleanups in other IOMMU drivers"

* tag 'iommu-updates-v3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (26 commits)
  iommu/shmobile: Enable the driver on all ARM platforms
  iommu/tegra-smmu: Staticize tegra_smmu_pm_ops
  iommu/tegra-gart: Staticize tegra_gart_pm_ops
  iommu/vt-d: Use list_for_each_entry_safe() for dmar_domain->devices traversal
  iommu/vt-d: Use for_each_drhd_unit() instead of list_for_each_entry()
  iommu/vt-d: Fixed interaction of VFIO_IOMMU_MAP_DMA with IOMMU address limits
  iommu/arm-smmu: Clear global and context bank fault status registers
  iommu/arm-smmu: Print context fault information
  iommu/arm-smmu: Check for num_context_irqs > 0 to avoid divide by zero exception
  iommu/arm-smmu: Refine check for proper size of mapped region
  iommu/arm-smmu: Switch to subsys_initcall for driver registration
  iommu/arm-smmu: use relaxed accessors where possible
  iommu/arm-smmu: replace devm_request_and_ioremap by devm_ioremap_resource
  iommu: Remove stack trace from broken irq remapping warning
  iommu: Change iommu driver to call io_page_fault trace event
  iommu: Add iommu_error class event to iommu trace
  iommu/tegra: gart: cleanup devm_* functions usage
  iommu/tegra: Print phys_addr_t using %pa
  iommu: No need to pass '0x' when '%pa' is used
  iommu: Change iommu driver to call unmap trace event
  ...

12 files changed, 270 insertions, 72 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index c880eba..9fd51e5 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -206,7 +206,7 @@ config SHMOBILE_IPMMU_TLB
 config SHMOBILE_IOMMU
 	bool "IOMMU for Renesas IPMMU/IPMMUI"
 	default n
-	depends on (ARM && ARCH_SHMOBILE)
+	depends on ARM || COMPILE_TEST
 	select IOMMU_API
 	select ARM_DMA_USE_IOMMU
 	select SHMOBILE_IPMMU
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 14c1f47..5d58bf1 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -1,4 +1,5 @@
 obj-$(CONFIG_IOMMU_API) += iommu.o
+obj-$(CONFIG_IOMMU_API) += iommu-traces.o
 obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 2349d62..1abfb56 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -590,6 +590,9 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 		ret = IRQ_HANDLED;
 		resume = RESUME_RETRY;
 	} else {
+		dev_err_ratelimited(smmu->dev,
+		    "Unhandled context fault: iova=0x%08lx, fsynr=0x%x, cb=%d\n",
+		    iova, fsynr, root_cfg->cbndx);
 		ret = IRQ_NONE;
 		resume = RESUME_TERMINATE;
 	}
@@ -778,7 +781,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 #ifdef __BIG_ENDIAN
 	reg |= SCTLR_E;
 #endif
-	writel(reg, cb_base + ARM_SMMU_CB_SCTLR);
+	writel_relaxed(reg, cb_base + ARM_SMMU_CB_SCTLR);
 }
 
 static int arm_smmu_init_domain_context(struct iommu_domain *domain,
@@ -1562,9 +1565,13 @@ static struct iommu_ops arm_smmu_ops = {
 static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 {
 	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
-	void __iomem *sctlr_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB_SCTLR;
+	void __iomem *cb_base;
 	int i = 0;
-	u32 scr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sCR0);
+	u32 reg;
+
+	/* Clear Global FSR */
+	reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR);
+	writel(reg, gr0_base + ARM_SMMU_GR0_sGFSR);
 
 	/* Mark all SMRn as invalid and all S2CRn as bypass */
 	for (i = 0; i < smmu->num_mapping_groups; ++i) {
@@ -1572,33 +1579,38 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 		writel_relaxed(S2CR_TYPE_BYPASS, gr0_base + ARM_SMMU_GR0_S2CR(i));
 	}
 
-	/* Make sure all context banks are disabled */
-	for (i = 0; i < smmu->num_context_banks; ++i)
-		writel_relaxed(0, sctlr_base + ARM_SMMU_CB(smmu, i));
+	/* Make sure all context banks are disabled and clear CB_FSR  */
+	for (i = 0; i < smmu->num_context_banks; ++i) {
+		cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, i);
+		writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);
+		writel_relaxed(FSR_FAULT, cb_base + ARM_SMMU_CB_FSR);
+	}
 
 	/* Invalidate the TLB, just in case */
 	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_STLBIALL);
 	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLH);
 	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLNSNH);
 
+	reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_sCR0);
+
 	/* Enable fault reporting */
-	scr0 |= (sCR0_GFRE | sCR0_GFIE | sCR0_GCFGFRE | sCR0_GCFGFIE);
+	reg |= (sCR0_GFRE | sCR0_GFIE | sCR0_GCFGFRE | sCR0_GCFGFIE);
 
 	/* Disable TLB broadcasting. */
-	scr0 |= (sCR0_VMIDPNE | sCR0_PTM);
+	reg |= (sCR0_VMIDPNE | sCR0_PTM);
 
 	/* Enable client access, but bypass when no mapping is found */
-	scr0 &= ~(sCR0_CLIENTPD | sCR0_USFCFG);
+	reg &= ~(sCR0_CLIENTPD | sCR0_USFCFG);
 
 	/* Disable forced broadcasting */
-	scr0 &= ~sCR0_FB;
+	reg &= ~sCR0_FB;
 
 	/* Don't upgrade barriers */
-	scr0 &= ~(sCR0_BSU_MASK << sCR0_BSU_SHIFT);
+	reg &= ~(sCR0_BSU_MASK << sCR0_BSU_SHIFT);
 
 	/* Push the button */
 	arm_smmu_tlb_sync(smmu);
-	writel(scr0, gr0_base + ARM_SMMU_GR0_sCR0);
+	writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_sCR0);
 }
 
 static int arm_smmu_id_size_to_bits(int size)
@@ -1703,13 +1715,12 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID1);
 	smmu->pagesize = (id & ID1_PAGESIZE) ? SZ_64K : SZ_4K;
 
-	/* Check that we ioremapped enough */
+	/* Check for size mismatch of SMMU address space from mapped region */
 	size = 1 << (((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
 	size *= (smmu->pagesize << 1);
-	if (smmu->size < size)
-		dev_warn(smmu->dev,
-			 "device is 0x%lx bytes but only mapped 0x%lx!\n",
-			 size, smmu->size);
+	if (smmu->size != size)
+		dev_warn(smmu->dev, "SMMU address space size (0x%lx) differs "
+			"from mapped region size (0x%lx)!\n", size, smmu->size);
 
 	smmu->num_s2_context_banks = (id >> ID1_NUMS2CB_SHIFT) &
 				      ID1_NUMS2CB_MASK;
@@ -1784,15 +1795,10 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	smmu->dev = dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "missing base address/size\n");
-		return -ENODEV;
-	}
-
+	smmu->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(smmu->base))
+		return PTR_ERR(smmu->base);
 	smmu->size = resource_size(res);
-	smmu->base = devm_request_and_ioremap(dev, res);
-	if (!smmu->base)
-		return -EADDRNOTAVAIL;
 
 	if (of_property_read_u32(dev->of_node, "#global-interrupts",
 				 &smmu->num_global_irqs)) {
@@ -1807,12 +1813,11 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 			smmu->num_context_irqs++;
 	}
 
-	if (num_irqs < smmu->num_global_irqs) {
-		dev_warn(dev, "found %d interrupts but expected at least %d\n",
-			 num_irqs, smmu->num_global_irqs);
-		smmu->num_global_irqs = num_irqs;
+	if (!smmu->num_context_irqs) {
+		dev_err(dev, "found %d interrupts but expected at least %d\n",
+			num_irqs, smmu->num_global_irqs + 1);
+		return -ENODEV;
 	}
-	smmu->num_context_irqs = num_irqs - smmu->num_global_irqs;
 
 	smmu->irqs = devm_kzalloc(dev, sizeof(*smmu->irqs) * num_irqs,
 				  GFP_KERNEL);
@@ -1936,7 +1941,7 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
 		free_irq(smmu->irqs[i], smmu);
 
 	/* Turn the thing off */
-	writel(sCR0_CLIENTPD, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_sCR0);
+	writel_relaxed(sCR0_CLIENTPD, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_sCR0);
 	return 0;
 }
 
@@ -1984,7 +1989,7 @@ static void __exit arm_smmu_exit(void)
 	return platform_driver_unregister(&arm_smmu_driver);
 }
 
-module_init(arm_smmu_init);
+subsys_initcall(arm_smmu_init);
 module_exit(arm_smmu_exit);
 
 MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 9009469..8b452c9 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -403,7 +403,7 @@ dmar_find_matched_drhd_unit(struct pci_dev *dev)
 
 	dev = pci_physfn(dev);
 
-	list_for_each_entry(dmaru, &dmar_drhd_units, list) {
+	for_each_drhd_unit(dmaru) {
 		drhd = container_of(dmaru->hdr,
 				    struct acpi_dmar_hardware_unit,
 				    header);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 15e9b57..43b9bfe 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -782,7 +782,11 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 	int offset;
 
 	BUG_ON(!domain->pgd);
-	BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width);
+
+	if (addr_width < BITS_PER_LONG && pfn >> addr_width)
+		/* Address beyond IOMMU's addressing capabilities. */
+		return NULL;
+
 	parent = domain->pgd;
 
 	while (level > 0) {
@@ -3777,11 +3781,10 @@ static void iommu_detach_dependent_devices(struct intel_iommu *iommu,
 static void domain_remove_one_dev_info(struct dmar_domain *domain,
 					  struct pci_dev *pdev)
 {
-	struct device_domain_info *info;
+	struct device_domain_info *info, *tmp;
 	struct intel_iommu *iommu;
 	unsigned long flags;
 	int found = 0;
-	struct list_head *entry, *tmp;
 
 	iommu = device_to_iommu(pci_domain_nr(pdev->bus), pdev->bus->number,
 				pdev->devfn);
@@ -3789,8 +3792,7 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain,
 		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);
+	list_for_each_entry_safe(info, tmp, &domain->devices, link) {
 		if (info->segment == pci_domain_nr(pdev->bus) &&
 		    info->bus == pdev->bus->number &&
 		    info->devfn == pdev->devfn) {
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index ab86902..bab10b1 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -525,12 +525,13 @@ static int __init intel_irq_remapping_supported(void)
 	if (disable_irq_remap)
 		return 0;
 	if (irq_remap_broken) {
-		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
-			   "This system BIOS has enabled interrupt remapping\n"
-			   "on a chipset that contains an erratum making that\n"
-			   "feature unstable.  To maintain system stability\n"
-			   "interrupt remapping is being disabled.  Please\n"
-			   "contact your BIOS vendor for an update\n");
+		printk(KERN_WARNING
+			"This system BIOS has enabled interrupt remapping\n"
+			"on a chipset that contains an erratum making that\n"
+			"feature unstable.  To maintain system stability\n"
+			"interrupt remapping is being disabled.  Please\n"
+			"contact your BIOS vendor for an update\n");
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 		disable_irq_remap = 1;
 		return 0;
 	}
diff --git a/drivers/iommu/iommu-traces.c b/drivers/iommu/iommu-traces.c
new file mode 100644
index 0000000..bf3b317
--- /dev/null
+++ b/drivers/iommu/iommu-traces.c
@@ -0,0 +1,27 @@
+/*
+ * iommu trace points
+ *
+ * Copyright (C) 2013 Shuah Khan <shuah.kh@samsung.com>
+ *
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/iommu.h>
+
+/* iommu_group_event */
+EXPORT_TRACEPOINT_SYMBOL_GPL(add_device_to_group);
+EXPORT_TRACEPOINT_SYMBOL_GPL(remove_device_from_group);
+
+/* iommu_device_event */
+EXPORT_TRACEPOINT_SYMBOL_GPL(attach_device_to_domain);
+EXPORT_TRACEPOINT_SYMBOL_GPL(detach_device_from_domain);
+
+/* iommu_map_unmap */
+EXPORT_TRACEPOINT_SYMBOL_GPL(map);
+EXPORT_TRACEPOINT_SYMBOL_GPL(unmap);
+
+/* iommu_error */
+EXPORT_TRACEPOINT_SYMBOL_GPL(io_page_fault);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index fbe9ca7..e5555fc 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -29,6 +29,7 @@
 #include <linux/idr.h>
 #include <linux/notifier.h>
 #include <linux/err.h>
+#include <trace/events/iommu.h>
 
 static struct kset *iommu_group_kset;
 static struct ida iommu_group_ida;
@@ -363,6 +364,8 @@ rename:
 	/* Notify any listeners about change to group. */
 	blocking_notifier_call_chain(&group->notifier,
 				     IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev);
+
+	trace_add_device_to_group(group->id, dev);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iommu_group_add_device);
@@ -399,6 +402,8 @@ void iommu_group_remove_device(struct device *dev)
 	sysfs_remove_link(group->devices_kobj, device->name);
 	sysfs_remove_link(&dev->kobj, "iommu_group");
 
+	trace_remove_device_from_group(group->id, dev);
+
 	kfree(device->name);
 	kfree(device);
 	dev->iommu_group = NULL;
@@ -680,10 +685,14 @@ EXPORT_SYMBOL_GPL(iommu_domain_free);
 
 int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
 {
+	int ret;
 	if (unlikely(domain->ops->attach_dev == NULL))
 		return -ENODEV;
 
-	return domain->ops->attach_dev(domain, dev);
+	ret = domain->ops->attach_dev(domain, dev);
+	if (!ret)
+		trace_attach_device_to_domain(dev);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
@@ -693,6 +702,7 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
 		return;
 
 	domain->ops->detach_dev(domain, dev);
+	trace_detach_device_from_domain(dev);
 }
 EXPORT_SYMBOL_GPL(iommu_detach_device);
 
@@ -807,17 +817,17 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	 * size of the smallest page supported by the hardware
 	 */
 	if (!IS_ALIGNED(iova | paddr | size, min_pagesz)) {
-		pr_err("unaligned: iova 0x%lx pa 0x%pa size 0x%zx min_pagesz 0x%x\n",
+		pr_err("unaligned: iova 0x%lx pa %pa size 0x%zx min_pagesz 0x%x\n",
 		       iova, &paddr, size, min_pagesz);
 		return -EINVAL;
 	}
 
-	pr_debug("map: iova 0x%lx pa 0x%pa size 0x%zx\n", iova, &paddr, size);
+	pr_debug("map: iova 0x%lx pa %pa size 0x%zx\n", iova, &paddr, size);
 
 	while (size) {
 		size_t pgsize = iommu_pgsize(domain, iova | paddr, size);
 
-		pr_debug("mapping: iova 0x%lx pa 0x%pa pgsize 0x%zx\n",
+		pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n",
 			 iova, &paddr, pgsize);
 
 		ret = domain->ops->map(domain, iova, paddr, pgsize, prot);
@@ -832,6 +842,8 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	/* unroll mapping in case something went wrong */
 	if (ret)
 		iommu_unmap(domain, orig_iova, orig_size - size);
+	else
+		trace_map(iova, paddr, size);
 
 	return ret;
 }
@@ -880,6 +892,7 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 		unmapped += unmapped_page;
 	}
 
+	trace_unmap(iova, 0, size);
 	return unmapped;
 }
 EXPORT_SYMBOL_GPL(iommu_unmap);
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index 108c0e9..dba1a9f 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -252,7 +252,7 @@ static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova,
 	spin_lock_irqsave(&gart->pte_lock, flags);
 	pfn = __phys_to_pfn(pa);
 	if (!pfn_valid(pfn)) {
-		dev_err(gart->dev, "Invalid page: %08x\n", pa);
+		dev_err(gart->dev, "Invalid page: %pa\n", &pa);
 		spin_unlock_irqrestore(&gart->pte_lock, flags);
 		return -EINVAL;
 	}
@@ -295,8 +295,8 @@ static phys_addr_t gart_iommu_iova_to_phys(struct iommu_domain *domain,
 
 	pa = (pte & GART_PAGE_MASK);
 	if (!pfn_valid(__phys_to_pfn(pa))) {
-		dev_err(gart->dev, "No entry for %08llx:%08x\n",
-			 (unsigned long long)iova, pa);
+		dev_err(gart->dev, "No entry for %08llx:%pa\n",
+			 (unsigned long long)iova, &pa);
 		gart_dump_table(gart);
 		return -EINVAL;
 	}
@@ -351,7 +351,6 @@ static int tegra_gart_probe(struct platform_device *pdev)
 	struct gart_device *gart;
 	struct resource *res, *res_remap;
 	void __iomem *gart_regs;
-	int err;
 	struct device *dev = &pdev->dev;
 
 	if (gart_handle)
@@ -376,8 +375,7 @@ static int tegra_gart_probe(struct platform_device *pdev)
 	gart_regs = devm_ioremap(dev, res->start, resource_size(res));
 	if (!gart_regs) {
 		dev_err(dev, "failed to remap GART registers\n");
-		err = -ENXIO;
-		goto fail;
+		return -ENXIO;
 	}
 
 	gart->dev = &pdev->dev;
@@ -391,8 +389,7 @@ static int tegra_gart_probe(struct platform_device *pdev)
 	gart->savedata = vmalloc(sizeof(u32) * gart->page_count);
 	if (!gart->savedata) {
 		dev_err(dev, "failed to allocate context save area\n");
-		err = -ENOMEM;
-		goto fail;
+		return -ENOMEM;
 	}
 
 	platform_set_drvdata(pdev, gart);
@@ -401,32 +398,20 @@ static int tegra_gart_probe(struct platform_device *pdev)
 	gart_handle = gart;
 	bus_set_iommu(&platform_bus_type, &gart_iommu_ops);
 	return 0;
-
-fail:
-	if (gart_regs)
-		devm_iounmap(dev, gart_regs);
-	if (gart && gart->savedata)
-		vfree(gart->savedata);
-	devm_kfree(dev, gart);
-	return err;
 }
 
 static int tegra_gart_remove(struct platform_device *pdev)
 {
 	struct gart_device *gart = platform_get_drvdata(pdev);
-	struct device *dev = gart->dev;
 
 	writel(0, gart->regs + GART_CONFIG);
 	if (gart->savedata)
 		vfree(gart->savedata);
-	if (gart->regs)
-		devm_iounmap(dev, gart->regs);
-	devm_kfree(dev, gart);
 	gart_handle = NULL;
 	return 0;
 }
 
-const struct dev_pm_ops tegra_gart_pm_ops = {
+static const struct dev_pm_ops tegra_gart_pm_ops = {
 	.suspend	= tegra_gart_suspend,
 	.resume		= tegra_gart_resume,
 };
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index e066560..605b5b4 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -731,7 +731,7 @@ static int smmu_iommu_map(struct iommu_domain *domain, unsigned long iova,
 	unsigned long pfn = __phys_to_pfn(pa);
 	unsigned long flags;
 
-	dev_dbg(as->smmu->dev, "[%d] %08lx:%08x\n", as->asid, iova, pa);
+	dev_dbg(as->smmu->dev, "[%d] %08lx:%pa\n", as->asid, iova, &pa);
 
 	if (!pfn_valid(pfn))
 		return -ENOMEM;
@@ -1254,7 +1254,7 @@ static int tegra_smmu_remove(struct platform_device *pdev)
 	return 0;
 }
 
-const struct dev_pm_ops tegra_smmu_pm_ops = {
+static const struct dev_pm_ops tegra_smmu_pm_ops = {
 	.suspend	= tegra_smmu_suspend,
 	.resume		= tegra_smmu_resume,
 };
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 7ea319e..a444c79 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -22,6 +22,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/types.h>
+#include <trace/events/iommu.h>
 
 #define IOMMU_READ	(1)
 #define IOMMU_WRITE	(2)
@@ -227,6 +228,7 @@ static inline int report_iommu_fault(struct iommu_domain *domain,
 		ret = domain->handler(domain, dev, iova, flags,
 						domain->handler_token);
 
+	trace_io_page_fault(dev, iova, flags);
 	return ret;
 }
 
diff --git a/include/trace/events/iommu.h b/include/trace/events/iommu.h
new file mode 100644
index 0000000..a8f5c32
--- /dev/null
+++ b/include/trace/events/iommu.h
@@ -0,0 +1,162 @@
+/*
+ * iommu trace points
+ *
+ * Copyright (C) 2013 Shuah Khan <shuah.kh@samsung.com>
+ *
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM iommu
+
+#if !defined(_TRACE_IOMMU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IOMMU_H
+
+#include <linux/tracepoint.h>
+#include <linux/pci.h>
+
+struct device;
+
+DECLARE_EVENT_CLASS(iommu_group_event,
+
+	TP_PROTO(int group_id, struct device *dev),
+
+	TP_ARGS(group_id, dev),
+
+	TP_STRUCT__entry(
+		__field(int, gid)
+		__string(device, dev_name(dev))
+	),
+
+	TP_fast_assign(
+		__entry->gid = group_id;
+		__assign_str(device, dev_name(dev));
+	),
+
+	TP_printk("IOMMU: groupID=%d device=%s",
+			__entry->gid, __get_str(device)
+	)
+);
+
+DEFINE_EVENT(iommu_group_event, add_device_to_group,
+
+	TP_PROTO(int group_id, struct device *dev),
+
+	TP_ARGS(group_id, dev)
+
+);
+
+DEFINE_EVENT(iommu_group_event, remove_device_from_group,
+
+	TP_PROTO(int group_id, struct device *dev),
+
+	TP_ARGS(group_id, dev)
+);
+
+DECLARE_EVENT_CLASS(iommu_device_event,
+
+	TP_PROTO(struct device *dev),
+
+	TP_ARGS(dev),
+
+	TP_STRUCT__entry(
+		__string(device, dev_name(dev))
+	),
+
+	TP_fast_assign(
+		__assign_str(device, dev_name(dev));
+	),
+
+	TP_printk("IOMMU: device=%s", __get_str(device)
+	)
+);
+
+DEFINE_EVENT(iommu_device_event, attach_device_to_domain,
+
+	TP_PROTO(struct device *dev),
+
+	TP_ARGS(dev)
+);
+
+DEFINE_EVENT(iommu_device_event, detach_device_from_domain,
+
+	TP_PROTO(struct device *dev),
+
+	TP_ARGS(dev)
+);
+
+DECLARE_EVENT_CLASS(iommu_map_unmap,
+
+	TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size),
+
+	TP_ARGS(iova, paddr, size),
+
+	TP_STRUCT__entry(
+		__field(u64, iova)
+		__field(u64, paddr)
+		__field(int, size)
+	),
+
+	TP_fast_assign(
+		__entry->iova = iova;
+		__entry->paddr = paddr;
+		__entry->size = size;
+	),
+
+	TP_printk("IOMMU: iova=0x%016llx paddr=0x%016llx size=0x%x",
+			__entry->iova, __entry->paddr, __entry->size
+	)
+);
+
+DEFINE_EVENT(iommu_map_unmap, map,
+
+	TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size),
+
+	TP_ARGS(iova, paddr, size)
+);
+
+DEFINE_EVENT_PRINT(iommu_map_unmap, unmap,
+
+	TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size),
+
+	TP_ARGS(iova, paddr, size),
+
+	TP_printk("IOMMU: iova=0x%016llx size=0x%x",
+			__entry->iova, __entry->size
+	)
+);
+
+DECLARE_EVENT_CLASS(iommu_error,
+
+	TP_PROTO(struct device *dev, unsigned long iova, int flags),
+
+	TP_ARGS(dev, iova, flags),
+
+	TP_STRUCT__entry(
+		__string(device, dev_name(dev))
+		__string(driver, dev_driver_string(dev))
+		__field(u64, iova)
+		__field(int, flags)
+	),
+
+	TP_fast_assign(
+		__assign_str(device, dev_name(dev));
+		__assign_str(driver, dev_driver_string(dev));
+		__entry->iova = iova;
+		__entry->flags = flags;
+	),
+
+	TP_printk("IOMMU:%s %s iova=0x%016llx flags=0x%04x",
+			__get_str(driver), __get_str(device),
+			__entry->iova, __entry->flags
+	)
+);
+
+DEFINE_EVENT(iommu_error, io_page_fault,
+
+	TP_PROTO(struct device *dev, unsigned long iova, int flags),
+
+	TP_ARGS(dev, iova, flags)
+);
+#endif /* _TRACE_IOMMU_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>