Merge tag 'iommu-updates-v4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "Nothing big this time. In particular:

   - Debugging code for Tegra-GART

   - Improvement in Intel VT-d fault printing to prevent soft-lockups
     when on fault storms

   - Improvements in AMD IOMMU event reporting

   - NUMA aware allocation in io-pgtable code for ARM

   - Various other small fixes and cleanups all over the place"

* tag 'iommu-updates-v4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu/io-pgtable-arm: Make allocations NUMA-aware
  iommu/amd: Prevent possible null pointer dereference and infinite loop
  iommu/amd: Fix grammar of comments
  iommu: Clean up the comments for iommu_group_alloc
  iommu/vt-d: Remove unnecessary parentheses
  iommu/vt-d: Clean up pasid quirk for pre-production devices
  iommu/vt-d: Clean up unused variable in find_or_alloc_domain
  iommu/vt-d: Fix iotlb psi missing for mappings
  iommu/vt-d: Introduce __mapping_notify_one()
  iommu: Remove extra NULL check when call strtobool()
  iommu/amd: Update logging information for new event type
  iommu/amd: Update the PASID information printed to the system log
  iommu/tegra: gart: Fix gart_iommu_unmap()
  iommu/tegra: gart: Add debugging facility
  iommu/io-pgtable-arm: Use for_each_set_bit to simplify code
  iommu/qcom: Simplify getting .drvdata
  iommu: Remove depends on HAS_DMA in case of platform dependency
  iommu/vt-d: Ratelimit each dmar fault printing

12 files changed, 122 insertions, 116 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 5b714a062fa7..8ea77efb2e29 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -23,7 +23,7 @@ config IOMMU_IO_PGTABLE
 config IOMMU_IO_PGTABLE_LPAE
 	bool "ARMv7/v8 Long Descriptor Format"
 	select IOMMU_IO_PGTABLE
-	depends on HAS_DMA && (ARM || ARM64 || (COMPILE_TEST && !GENERIC_ATOMIC64))
+	depends on ARM || ARM64 || (COMPILE_TEST && !GENERIC_ATOMIC64)
 	help
 	  Enable support for the ARM long descriptor pagetable format.
 	  This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page
@@ -42,7 +42,7 @@ config IOMMU_IO_PGTABLE_LPAE_SELFTEST
 config IOMMU_IO_PGTABLE_ARMV7S
 	bool "ARMv7/v8 Short Descriptor Format"
 	select IOMMU_IO_PGTABLE
-	depends on HAS_DMA && (ARM || ARM64 || COMPILE_TEST)
+	depends on ARM || ARM64 || COMPILE_TEST
 	help
 	  Enable support for the ARM Short-descriptor pagetable format.
 	  This supports 32-bit virtual and physical addresses mapped using
@@ -377,7 +377,6 @@ config QCOM_IOMMU
 	# Note: iommu drivers cannot (yet?) be built as modules
 	bool "Qualcomm IOMMU Support"
 	depends on ARCH_QCOM || (COMPILE_TEST && !GENERIC_ATOMIC64)
-	depends on HAS_DMA
 	select IOMMU_API
 	select IOMMU_IO_PGTABLE_LPAE
 	select ARM_DMA_USE_IOMMU
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index d60c7dc62905..1912e9106fbe 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -547,7 +547,7 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 {
 	struct device *dev = iommu->iommu.dev;
-	int type, devid, domid, flags;
+	int type, devid, pasid, flags, tag;
 	volatile u32 *event = __evt;
 	int count = 0;
 	u64 address;
@@ -555,7 +555,7 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 retry:
 	type    = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
 	devid   = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
-	domid   = (event[1] >> EVENT_DOMID_SHIFT) & EVENT_DOMID_MASK;
+	pasid   = PPR_PASID(*(u64 *)&event[0]);
 	flags   = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
 	address = (u64)(((u64)event[3]) << 32) | event[2];
 
@@ -570,7 +570,7 @@ retry:
 	}
 
 	if (type == EVENT_TYPE_IO_FAULT) {
-		amd_iommu_report_page_fault(devid, domid, address, flags);
+		amd_iommu_report_page_fault(devid, pasid, address, flags);
 		return;
 	} else {
 		dev_err(dev, "AMD-Vi: Event logged [");
@@ -578,10 +578,9 @@ retry:
 
 	switch (type) {
 	case EVENT_TYPE_ILL_DEV:
-		dev_err(dev, "ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x "
-			"address=0x%016llx flags=0x%04x]\n",
+		dev_err(dev, "ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x pasid=0x%05x address=0x%016llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
-			address, flags);
+			pasid, address, flags);
 		dump_dte_entry(devid);
 		break;
 	case EVENT_TYPE_DEV_TAB_ERR:
@@ -591,34 +590,38 @@ retry:
 			address, flags);
 		break;
 	case EVENT_TYPE_PAGE_TAB_ERR:
-		dev_err(dev, "PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
-			"domain=0x%04x address=0x%016llx flags=0x%04x]\n",
+		dev_err(dev, "PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x domain=0x%04x address=0x%016llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
-			domid, address, flags);
+			pasid, address, flags);
 		break;
 	case EVENT_TYPE_ILL_CMD:
 		dev_err(dev, "ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address);
 		dump_command(address);
 		break;
 	case EVENT_TYPE_CMD_HARD_ERR:
-		dev_err(dev, "COMMAND_HARDWARE_ERROR address=0x%016llx "
-			"flags=0x%04x]\n", address, flags);
+		dev_err(dev, "COMMAND_HARDWARE_ERROR address=0x%016llx flags=0x%04x]\n",
+			address, flags);
 		break;
 	case EVENT_TYPE_IOTLB_INV_TO:
-		dev_err(dev, "IOTLB_INV_TIMEOUT device=%02x:%02x.%x "
-			"address=0x%016llx]\n",
+		dev_err(dev, "IOTLB_INV_TIMEOUT device=%02x:%02x.%x address=0x%016llx]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			address);
 		break;
 	case EVENT_TYPE_INV_DEV_REQ:
-		dev_err(dev, "INVALID_DEVICE_REQUEST device=%02x:%02x.%x "
-			"address=0x%016llx flags=0x%04x]\n",
+		dev_err(dev, "INVALID_DEVICE_REQUEST device=%02x:%02x.%x pasid=0x%05x address=0x%016llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
-			address, flags);
+			pasid, address, flags);
+		break;
+	case EVENT_TYPE_INV_PPR_REQ:
+		pasid = ((event[0] >> 16) & 0xFFFF)
+			| ((event[1] << 6) & 0xF0000);
+		tag = event[1] & 0x03FF;
+		dev_err(dev, "INVALID_PPR_REQUEST device=%02x:%02x.%x pasid=0x%05x address=0x%016llx flags=0x%04x]\n",
+			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			pasid, address, flags);
 		break;
 	default:
-		dev_err(dev, KERN_ERR "UNKNOWN event[0]=0x%08x event[1]=0x%08x "
-			"event[2]=0x%08x event[3]=0x%08x\n",
+		dev_err(dev, "UNKNOWN event[0]=0x%08x event[1]=0x%08x event[2]=0x%08x event[3]=0x%08x\n",
 			event[0], event[1], event[2], event[3]);
 	}
 
@@ -1914,15 +1917,6 @@ static void do_detach(struct iommu_dev_data *dev_data)
 	struct amd_iommu *iommu;
 	u16 alias;
 
-	/*
-	 * First check if the device is still attached. It might already
-	 * be detached from its domain because the generic
-	 * iommu_detach_group code detached it and we try again here in
-	 * our alias handling.
-	 */
-	if (!dev_data->domain)
-		return;
-
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
 	alias = dev_data->alias;
 
@@ -1942,8 +1936,8 @@ static void do_detach(struct iommu_dev_data *dev_data)
 }
 
 /*
- * If a device is not yet associated with a domain, this function does
- * assigns it visible for the hardware
+ * If a device is not yet associated with a domain, this function makes the
+ * device visible in the domain
  */
 static int __attach_device(struct iommu_dev_data *dev_data,
 			   struct protection_domain *domain)
@@ -2064,8 +2058,8 @@ static bool pci_pri_tlp_required(struct pci_dev *pdev)
 }
 
 /*
- * If a device is not yet associated with a domain, this function
- * assigns it visible for the hardware
+ * If a device is not yet associated with a domain, this function makes the
+ * device visible in the domain
  */
 static int attach_device(struct device *dev,
 			 struct protection_domain *domain)
@@ -2127,9 +2121,6 @@ static void __detach_device(struct iommu_dev_data *dev_data)
 	 */
 	WARN_ON(!irqs_disabled());
 
-	if (WARN_ON(!dev_data->domain))
-		return;
-
 	domain = dev_data->domain;
 
 	spin_lock(&domain->lock);
@@ -2151,6 +2142,15 @@ static void detach_device(struct device *dev)
 	dev_data = get_dev_data(dev);
 	domain   = dev_data->domain;
 
+	/*
+	 * First check if the device is still attached. It might already
+	 * be detached from its domain because the generic
+	 * iommu_detach_group code detached it and we try again here in
+	 * our alias handling.
+	 */
+	if (WARN_ON(!dev_data->domain))
+		return;
+
 	/* lock device table */
 	spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
 	__detach_device(dev_data);
@@ -2796,6 +2796,7 @@ static void cleanup_domain(struct protection_domain *domain)
 	while (!list_empty(&domain->dev_list)) {
 		entry = list_first_entry(&domain->dev_list,
 					 struct iommu_dev_data, list);
+		BUG_ON(!entry->domain);
 		__detach_device(entry);
 	}
 
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 1c9b080276c9..986cbe0cc189 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -133,6 +133,7 @@
 #define EVENT_TYPE_CMD_HARD_ERR	0x6
 #define EVENT_TYPE_IOTLB_INV_TO	0x7
 #define EVENT_TYPE_INV_DEV_REQ	0x8
+#define EVENT_TYPE_INV_PPR_REQ	0x9
 #define EVENT_DEVID_MASK	0xffff
 #define EVENT_DEVID_SHIFT	0
 #define EVENT_DOMID_MASK	0xffff
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 460bed4fc5b1..4321f7704b23 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1618,17 +1618,13 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 	int reg, fault_index;
 	u32 fault_status;
 	unsigned long flag;
-	bool ratelimited;
 	static DEFINE_RATELIMIT_STATE(rs,
 				      DEFAULT_RATELIMIT_INTERVAL,
 				      DEFAULT_RATELIMIT_BURST);
 
-	/* Disable printing, simply clear the fault when ratelimited */
-	ratelimited = !__ratelimit(&rs);
-
 	raw_spin_lock_irqsave(&iommu->register_lock, flag);
 	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
-	if (fault_status && !ratelimited)
+	if (fault_status && __ratelimit(&rs))
 		pr_err("DRHD: handling fault status reg %x\n", fault_status);
 
 	/* TBD: ignore advanced fault log currently */
@@ -1638,6 +1634,8 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 	fault_index = dma_fsts_fault_record_index(fault_status);
 	reg = cap_fault_reg_offset(iommu->cap);
 	while (1) {
+		/* Disable printing, simply clear the fault when ratelimited */
+		bool ratelimited = !__ratelimit(&rs);
 		u8 fault_reason;
 		u16 source_id;
 		u64 guest_addr;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 772b404a6604..89e49a429c57 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -485,37 +485,14 @@ static int dmar_forcedac;
 static int intel_iommu_strict;
 static int intel_iommu_superpage = 1;
 static int intel_iommu_ecs = 1;
-static int intel_iommu_pasid28;
 static int iommu_identity_mapping;
 
 #define IDENTMAP_ALL		1
 #define IDENTMAP_GFX		2
 #define IDENTMAP_AZALIA		4
 
-/* Broadwell and Skylake have broken ECS support — normal so-called "second
- * level" translation of DMA requests-without-PASID doesn't actually happen
- * unless you also set the NESTE bit in an extended context-entry. Which of
- * course means that SVM doesn't work because it's trying to do nested
- * translation of the physical addresses it finds in the process page tables,
- * through the IOVA->phys mapping found in the "second level" page tables.
- *
- * The VT-d specification was retroactively changed to change the definition
- * of the capability bits and pretend that Broadwell/Skylake never happened...
- * but unfortunately the wrong bit was changed. It's ECS which is broken, but
- * for some reason it was the PASID capability bit which was redefined (from
- * bit 28 on BDW/SKL to bit 40 in future).
- *
- * So our test for ECS needs to eschew those implementations which set the old
- * PASID capabiity bit 28, since those are the ones on which ECS is broken.
- * Unless we are working around the 'pasid28' limitations, that is, by putting
- * the device into passthrough mode for normal DMA and thus masking the bug.
- */
-#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \
-			    (intel_iommu_pasid28 || !ecap_broken_pasid(iommu->ecap)))
-/* PASID support is thus enabled if ECS is enabled and *either* of the old
- * or new capability bits are set. */
-#define pasid_enabled(iommu) (ecs_enabled(iommu) &&			\
-			      (ecap_pasid(iommu->ecap) || ecap_broken_pasid(iommu->ecap)))
+#define ecs_enabled(iommu)	(intel_iommu_ecs && ecap_ecs(iommu->ecap))
+#define pasid_enabled(iommu)	(ecs_enabled(iommu) && ecap_pasid(iommu->ecap))
 
 int intel_iommu_gfx_mapped;
 EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
@@ -578,11 +555,6 @@ static int __init intel_iommu_setup(char *str)
 			printk(KERN_INFO
 				"Intel-IOMMU: disable extended context table support\n");
 			intel_iommu_ecs = 0;
-		} else if (!strncmp(str, "pasid28", 7)) {
-			printk(KERN_INFO
-				"Intel-IOMMU: enable pre-production PASID support\n");
-			intel_iommu_pasid28 = 1;
-			iommu_identity_mapping |= IDENTMAP_GFX;
 		} else if (!strncmp(str, "tboot_noforce", 13)) {
 			printk(KERN_INFO
 				"Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
@@ -1606,6 +1578,18 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 		iommu_flush_dev_iotlb(domain, addr, mask);
 }
 
+/* Notification for newly created mappings */
+static inline void __mapping_notify_one(struct intel_iommu *iommu,
+					struct dmar_domain *domain,
+					unsigned long pfn, unsigned int pages)
+{
+	/* It's a non-present to present mapping. Only flush if caching mode */
+	if (cap_caching_mode(iommu->cap))
+		iommu_flush_iotlb_psi(iommu, domain, pfn, pages, 0, 1);
+	else
+		iommu_flush_write_buffer(iommu);
+}
+
 static void iommu_flush_iova(struct iova_domain *iovad)
 {
 	struct dmar_domain *domain;
@@ -2340,18 +2324,47 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 	return 0;
 }
 
+static int domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
+                         struct scatterlist *sg, unsigned long phys_pfn,
+                         unsigned long nr_pages, int prot)
+{
+       int ret;
+       struct intel_iommu *iommu;
+
+       /* Do the real mapping first */
+       ret = __domain_mapping(domain, iov_pfn, sg, phys_pfn, nr_pages, prot);
+       if (ret)
+               return ret;
+
+       /* Notify about the new mapping */
+       if (domain_type_is_vm(domain)) {
+	       /* VM typed domains can have more than one IOMMUs */
+	       int iommu_id;
+	       for_each_domain_iommu(iommu_id, domain) {
+		       iommu = g_iommus[iommu_id];
+		       __mapping_notify_one(iommu, domain, iov_pfn, nr_pages);
+	       }
+       } else {
+	       /* General domains only have one IOMMU */
+	       iommu = domain_get_iommu(domain);
+	       __mapping_notify_one(iommu, domain, iov_pfn, nr_pages);
+       }
+
+       return 0;
+}
+
 static inline int domain_sg_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 				    struct scatterlist *sg, unsigned long nr_pages,
 				    int prot)
 {
-	return __domain_mapping(domain, iov_pfn, sg, 0, nr_pages, prot);
+	return domain_mapping(domain, iov_pfn, sg, 0, nr_pages, prot);
 }
 
 static inline int domain_pfn_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 				     unsigned long phys_pfn, unsigned long nr_pages,
 				     int prot)
 {
-	return __domain_mapping(domain, iov_pfn, NULL, phys_pfn, nr_pages, prot);
+	return domain_mapping(domain, iov_pfn, NULL, phys_pfn, nr_pages, prot);
 }
 
 static void domain_context_clear_one(struct intel_iommu *iommu, u8 bus, u8 devfn)
@@ -2534,7 +2547,7 @@ static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw)
 	struct device_domain_info *info = NULL;
 	struct dmar_domain *domain = NULL;
 	struct intel_iommu *iommu;
-	u16 req_id, dma_alias;
+	u16 dma_alias;
 	unsigned long flags;
 	u8 bus, devfn;
 
@@ -2542,8 +2555,6 @@ static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw)
 	if (!iommu)
 		return NULL;
 
-	req_id = ((u16)bus << 8) | devfn;
-
 	if (dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(dev);
 
@@ -2657,9 +2668,9 @@ static int iommu_domain_identity_map(struct dmar_domain *domain,
 	 */
 	dma_pte_clear_range(domain, first_vpfn, last_vpfn);
 
-	return domain_pfn_mapping(domain, first_vpfn, first_vpfn,
-				  last_vpfn - first_vpfn + 1,
-				  DMA_PTE_READ|DMA_PTE_WRITE);
+	return __domain_mapping(domain, first_vpfn, NULL,
+				first_vpfn, last_vpfn - first_vpfn + 1,
+				DMA_PTE_READ|DMA_PTE_WRITE);
 }
 
 static int domain_prepare_identity_map(struct device *dev,
@@ -3626,14 +3637,6 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
 	if (ret)
 		goto error;
 
-	/* it's a non-present to present mapping. Only flush if caching mode */
-	if (cap_caching_mode(iommu->cap))
-		iommu_flush_iotlb_psi(iommu, domain,
-				      mm_to_dma_pfn(iova_pfn),
-				      size, 0, 1);
-	else
-		iommu_flush_write_buffer(iommu);
-
 	start_paddr = (phys_addr_t)iova_pfn << PAGE_SHIFT;
 	start_paddr += paddr & ~PAGE_MASK;
 	return start_paddr;
@@ -3820,12 +3823,6 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
 		return 0;
 	}
 
-	/* it's a non-present to present mapping. Only flush if caching mode */
-	if (cap_caching_mode(iommu->cap))
-		iommu_flush_iotlb_psi(iommu, domain, start_vpfn, size, 0, 1);
-	else
-		iommu_flush_write_buffer(iommu);
-
 	return nelems;
 }
 
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index e8cd984cf9c8..45f6e581cd56 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -319,7 +319,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 	} else
 		pasid_max = 1 << 20;
 
-	if ((flags & SVM_FLAG_SUPERVISOR_MODE)) {
+	if (flags & SVM_FLAG_SUPERVISOR_MODE) {
 		if (!ecap_srs(iommu->ecap))
 			return -EINVAL;
 	} else if (pasid) {
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 10e4a3d11c02..50e3a9fcf43e 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -898,8 +898,7 @@ static int __init arm_v7s_do_selftests(void)
 
 	/* Full unmap */
 	iova = 0;
-	i = find_first_bit(&cfg.pgsize_bitmap, BITS_PER_LONG);
-	while (i != BITS_PER_LONG) {
+	for_each_set_bit(i, &cfg.pgsize_bitmap, BITS_PER_LONG) {
 		size = 1UL << i;
 
 		if (ops->unmap(ops, iova, size) != size)
@@ -916,8 +915,6 @@ static int __init arm_v7s_do_selftests(void)
 			return __FAIL(ops);
 
 		iova += SZ_16M;
-		i++;
-		i = find_next_bit(&cfg.pgsize_bitmap, BITS_PER_LONG, i);
 	}
 
 	free_io_pgtable_ops(ops);
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 39c2a056da21..010a254305dd 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -231,12 +231,17 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
 				    struct io_pgtable_cfg *cfg)
 {
 	struct device *dev = cfg->iommu_dev;
+	int order = get_order(size);
+	struct page *p;
 	dma_addr_t dma;
-	void *pages = alloc_pages_exact(size, gfp | __GFP_ZERO);
+	void *pages;
 
-	if (!pages)
+	VM_BUG_ON((gfp & __GFP_HIGHMEM));
+	p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order);
+	if (!p)
 		return NULL;
 
+	pages = page_address(p);
 	if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) {
 		dma = dma_map_single(dev, pages, size, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, dma))
@@ -256,7 +261,7 @@ out_unmap:
 	dev_err(dev, "Cannot accommodate DMA translation for IOMMU page tables\n");
 	dma_unmap_single(dev, dma, size, DMA_TO_DEVICE);
 out_free:
-	free_pages_exact(pages, size);
+	__free_pages(p, order);
 	return NULL;
 }
 
@@ -266,7 +271,7 @@ static void __arm_lpae_free_pages(void *pages, size_t size,
 	if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA))
 		dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages),
 				 size, DMA_TO_DEVICE);
-	free_pages_exact(pages, size);
+	free_pages((unsigned long)pages, get_order(size));
 }
 
 static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep,
@@ -1120,8 +1125,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 
 		/* Full unmap */
 		iova = 0;
-		j = find_first_bit(&cfg->pgsize_bitmap, BITS_PER_LONG);
-		while (j != BITS_PER_LONG) {
+		for_each_set_bit(j, &cfg->pgsize_bitmap, BITS_PER_LONG) {
 			size = 1UL << j;
 
 			if (ops->unmap(ops, iova, size) != size)
@@ -1138,8 +1142,6 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 				return __FAIL(ops, i);
 
 			iova += SZ_1G;
-			j++;
-			j = find_next_bit(&cfg->pgsize_bitmap, BITS_PER_LONG, j);
 		}
 
 		free_io_pgtable_ops(ops);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index d2aa23202bb9..63b37563db7e 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -116,9 +116,11 @@ static void __iommu_detach_group(struct iommu_domain *domain,
 static int __init iommu_set_def_domain_type(char *str)
 {
 	bool pt;
+	int ret;
 
-	if (!str || strtobool(str, &pt))
-		return -EINVAL;
+	ret = kstrtobool(str, &pt);
+	if (ret)
+		return ret;
 
 	iommu_def_domain_type = pt ? IOMMU_DOMAIN_IDENTITY : IOMMU_DOMAIN_DMA;
 	return 0;
@@ -322,7 +324,6 @@ static struct kobj_type iommu_group_ktype = {
 
 /**
  * iommu_group_alloc - Allocate a new group
- * @name: Optional name to associate with group, visible in sysfs
  *
  * This function is called by an iommu driver to allocate a new iommu
  * group.  The iommu group represents the minimum granularity of the iommu.
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 65b9c99707f8..fe88a4880d3a 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -885,16 +885,14 @@ static int qcom_iommu_device_remove(struct platform_device *pdev)
 
 static int __maybe_unused qcom_iommu_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct qcom_iommu_dev *qcom_iommu = platform_get_drvdata(pdev);
+	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev);
 
 	return qcom_iommu_enable_clocks(qcom_iommu);
 }
 
 static int __maybe_unused qcom_iommu_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct qcom_iommu_dev *qcom_iommu = platform_get_drvdata(pdev);
+	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev);
 
 	qcom_iommu_disable_clocks(qcom_iommu);
 
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index b62f790ad1ba..89ec24c6952c 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -72,6 +72,8 @@ struct gart_domain {
 
 static struct gart_device *gart_handle; /* unique for a system */
 
+static bool gart_debug;
+
 #define GART_PTE(_pfn)						\
 	(GART_ENTRY_PHYS_ADDR_VALID | ((_pfn) << PAGE_SHIFT))
 
@@ -271,6 +273,7 @@ static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova,
 	struct gart_device *gart = gart_domain->gart;
 	unsigned long flags;
 	unsigned long pfn;
+	unsigned long pte;
 
 	if (!gart_iova_range_valid(gart, iova, bytes))
 		return -EINVAL;
@@ -282,6 +285,14 @@ static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova,
 		spin_unlock_irqrestore(&gart->pte_lock, flags);
 		return -EINVAL;
 	}
+	if (gart_debug) {
+		pte = gart_read_pte(gart, iova);
+		if (pte & GART_ENTRY_PHYS_ADDR_VALID) {
+			spin_unlock_irqrestore(&gart->pte_lock, flags);
+			dev_err(gart->dev, "Page entry is in-use\n");
+			return -EBUSY;
+		}
+	}
 	gart_set_pte(gart, iova, GART_PTE(pfn));
 	FLUSH_GART_REGS(gart);
 	spin_unlock_irqrestore(&gart->pte_lock, flags);
@@ -302,7 +313,7 @@ static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 	gart_set_pte(gart, iova, 0);
 	FLUSH_GART_REGS(gart);
 	spin_unlock_irqrestore(&gart->pte_lock, flags);
-	return 0;
+	return bytes;
 }
 
 static phys_addr_t gart_iommu_iova_to_phys(struct iommu_domain *domain,
@@ -515,7 +526,9 @@ static void __exit tegra_gart_exit(void)
 
 subsys_initcall(tegra_gart_init);
 module_exit(tegra_gart_exit);
+module_param(gart_debug, bool, 0644);
 
+MODULE_PARM_DESC(gart_debug, "Enable GART debugging");
 MODULE_DESCRIPTION("IOMMU API for GART in Tegra20");
 MODULE_AUTHOR("Hiroshi DOYU <hdoyu@nvidia.com>");
 MODULE_ALIAS("platform:tegra-gart");
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index ef169d67df92..1df940196ab2 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -121,7 +121,6 @@
 #define ecap_srs(e)		((e >> 31) & 0x1)
 #define ecap_ers(e)		((e >> 30) & 0x1)
 #define ecap_prs(e)		((e >> 29) & 0x1)
-#define ecap_broken_pasid(e)	((e >> 28) & 0x1)
 #define ecap_dis(e)		((e >> 27) & 0x1)
 #define ecap_nest(e)		((e >> 26) & 0x1)
 #define ecap_mts(e)		((e >> 25) & 0x1)