Merge tag 'iommu-updates-v5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - Intel IOMMU Updates fro Lu Baolu:
     - Dump DMAR translation structure when DMA fault occurs
     - An optimization in the page table manipulation code
     - Use second level for GPA->HPA translation
     - Various cleanups

 - Arm SMMU Updates from Will
     - Minor optimisations to SMMUv3 command creation and submission
     - Numerous new compatible string for Qualcomm SMMUv2 implementations

 - Fixes for the SWIOTLB based implemenation of dma-iommu code for
   untrusted devices

 - Add support for r8a779a0 to the Renesas IOMMU driver and DT matching
   code for r8a77980

 - A couple of cleanups and fixes for the Apple DART IOMMU driver

 - Make use of generic report_iommu_fault() interface in the AMD IOMMU
   driver

 - Various smaller fixes and cleanups

* tag 'iommu-updates-v5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (35 commits)
  iommu/dma: Fix incorrect error return on iommu deferred attach
  iommu/dart: Initialize DART_STREAMS_ENABLE
  iommu/dma: Use kvcalloc() instead of kvzalloc()
  iommu/tegra-smmu: Use devm_bitmap_zalloc when applicable
  iommu/dart: Use kmemdup instead of kzalloc and memcpy
  iommu/vt-d: Avoid duplicate removing in __domain_mapping()
  iommu/vt-d: Convert the return type of first_pte_in_page to bool
  iommu/vt-d: Clean up unused PASID updating functions
  iommu/vt-d: Delete dev_has_feat callback
  iommu/vt-d: Use second level for GPA->HPA translation
  iommu/vt-d: Check FL and SL capability sanity in scalable mode
  iommu/vt-d: Remove duplicate identity domain flag
  iommu/vt-d: Dump DMAR translation structure when DMA fault occurs
  iommu/vt-d: Do not falsely log intel_iommu is unsupported kernel option
  iommu/arm-smmu-qcom: Request direct mapping for modem device
  iommu: arm-smmu-qcom: Add compatible for QCM2290
  dt-bindings: arm-smmu: Add compatible for QCM2290 SoC
  iommu/arm-smmu-qcom: Add SM6350 SMMU compatible
  dt-bindings: arm-smmu: Add compatible for SM6350 SoC
  iommu/arm-smmu-v3: Properly handle the return value of arm_smmu_cmdq_build_cmd()
  ...

24 files changed, 367 insertions, 243 deletions

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index 03f2b2d4db3089..f66a3effba73c1 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -33,10 +33,12 @@ properties:
       - description: Qcom SoCs implementing "arm,mmu-500"
         items:
           - enum:
+              - qcom,qcm2290-smmu-500
               - qcom,sc7180-smmu-500
               - qcom,sc7280-smmu-500
               - qcom,sc8180x-smmu-500
               - qcom,sdm845-smmu-500
+              - qcom,sm6350-smmu-500
               - qcom,sm8150-smmu-500
               - qcom,sm8250-smmu-500
               - qcom,sm8350-smmu-500
diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml
index 02c69a95c33285..ce0c715205c6cc 100644
--- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml
+++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml
@@ -43,6 +43,7 @@ properties:
               - renesas,ipmmu-r8a77980 # R-Car V3H
               - renesas,ipmmu-r8a77990 # R-Car E3
               - renesas,ipmmu-r8a77995 # R-Car D3
+              - renesas,ipmmu-r8a779a0 # R-Car V3U
 
   reg:
     maxItems: 1
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index b7267b9e452f26..6053674f91320a 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -108,8 +108,6 @@ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
  */
 #define PASID_DISABLED	0
 
-static inline void update_pasid(void) { }
-
 /* Trap handling */
 extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
 extern void fpu_sync_fpstate(struct fpu *fpu);
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 8dbe61e2b3c152..867535eb0ce971 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -138,6 +138,8 @@
 #define EVENT_DOMID_MASK_HI	0xf0000
 #define EVENT_FLAGS_MASK	0xfff
 #define EVENT_FLAGS_SHIFT	0x10
+#define EVENT_FLAG_RW		0x020
+#define EVENT_FLAG_I		0x008
 
 /* feature control bits */
 #define CONTROL_IOMMU_EN        0x00ULL
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 9e5da037d949f5..461f1844ed1fbd 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -474,6 +474,12 @@ static void amd_iommu_report_rmp_fault(volatile u32 *event)
 		pci_dev_put(pdev);
 }
 
+#define IS_IOMMU_MEM_TRANSACTION(flags)		\
+	(((flags) & EVENT_FLAG_I) == 0)
+
+#define IS_WRITE_REQUEST(flags)			\
+	((flags) & EVENT_FLAG_RW)
+
 static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 					u64 address, int flags)
 {
@@ -486,6 +492,20 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 		dev_data = dev_iommu_priv_get(&pdev->dev);
 
 	if (dev_data) {
+		/*
+		 * If this is a DMA fault (for which the I(nterrupt)
+		 * bit will be unset), allow report_iommu_fault() to
+		 * prevent logging it.
+		 */
+		if (IS_IOMMU_MEM_TRANSACTION(flags)) {
+			if (!report_iommu_fault(&dev_data->domain->domain,
+						&pdev->dev, address,
+						IS_WRITE_REQUEST(flags) ?
+							IOMMU_FAULT_WRITE :
+							IOMMU_FAULT_READ))
+				goto out;
+		}
+
 		if (__ratelimit(&dev_data->rs)) {
 			pci_err(pdev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n",
 				domain_id, address, flags);
@@ -496,6 +516,7 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 			domain_id, address, flags);
 	}
 
+out:
 	if (pdev)
 		pci_dev_put(pdev);
 }
diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index fdfa39ec2a4d4a..96d4a1f8de7977 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -15,7 +15,6 @@
 #include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/dev_printk.h>
-#include <linux/dma-iommu.h>
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
@@ -70,6 +69,8 @@
 #define DART_ERROR_ADDR_HI 0x54
 #define DART_ERROR_ADDR_LO 0x50
 
+#define DART_STREAMS_ENABLE 0xfc
+
 #define DART_TCR(sid) (0x100 + 4 * (sid))
 #define DART_TCR_TRANSLATE_ENABLE BIT(7)
 #define DART_TCR_BYPASS0_ENABLE BIT(8)
@@ -301,6 +302,9 @@ static int apple_dart_hw_reset(struct apple_dart *dart)
 	apple_dart_hw_disable_dma(&stream_map);
 	apple_dart_hw_clear_all_ttbrs(&stream_map);
 
+	/* enable all streams globally since TCR is used to control isolation */
+	writel(DART_STREAM_ALL, dart->regs + DART_STREAMS_ENABLE);
+
 	/* clear any pending errors before the interrupt is unmasked */
 	writel(readl(dart->regs + DART_ERROR), dart->regs + DART_ERROR);
 
@@ -578,7 +582,6 @@ static struct iommu_domain *apple_dart_domain_alloc(unsigned int type)
 	if (!dart_domain)
 		return NULL;
 
-	iommu_get_dma_cookie(&dart_domain->domain);
 	mutex_init(&dart_domain->init_lock);
 
 	/* no need to allocate pgtbl_ops or do any other finalization steps */
@@ -702,13 +705,12 @@ static struct iommu_group *apple_dart_device_group(struct device *dev)
 	if (!group)
 		goto out;
 
-	group_master_cfg = kzalloc(sizeof(*group_master_cfg), GFP_KERNEL);
+	group_master_cfg = kmemdup(cfg, sizeof(*group_master_cfg), GFP_KERNEL);
 	if (!group_master_cfg) {
 		iommu_group_put(group);
 		goto out;
 	}
 
-	memcpy(group_master_cfg, cfg, sizeof(*group_master_cfg));
 	iommu_group_set_iommudata(group, group_master_cfg,
 		apple_dart_release_group);
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index a388e318f86e0b..f5848b351b1935 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -409,10 +409,7 @@ static void __arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu,
 		dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);
 
 	/* Convert the erroneous command into a CMD_SYNC */
-	if (arm_smmu_cmdq_build_cmd(cmd, &cmd_sync)) {
-		dev_err(smmu->dev, "failed to convert to CMD_SYNC\n");
-		return;
-	}
+	arm_smmu_cmdq_build_cmd(cmd, &cmd_sync);
 
 	queue_write(Q_ENT(q, cons), cmd, q->ent_dwords);
 }
@@ -860,7 +857,7 @@ static int __arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
 {
 	u64 cmd[CMDQ_ENT_DWORDS];
 
-	if (arm_smmu_cmdq_build_cmd(cmd, ent)) {
+	if (unlikely(arm_smmu_cmdq_build_cmd(cmd, ent))) {
 		dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
 			 ent->opcode);
 		return -EINVAL;
@@ -885,11 +882,20 @@ static void arm_smmu_cmdq_batch_add(struct arm_smmu_device *smmu,
 				    struct arm_smmu_cmdq_batch *cmds,
 				    struct arm_smmu_cmdq_ent *cmd)
 {
+	int index;
+
 	if (cmds->num == CMDQ_BATCH_ENTRIES) {
 		arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, false);
 		cmds->num = 0;
 	}
-	arm_smmu_cmdq_build_cmd(&cmds->cmds[cmds->num * CMDQ_ENT_DWORDS], cmd);
+
+	index = cmds->num * CMDQ_ENT_DWORDS;
+	if (unlikely(arm_smmu_cmdq_build_cmd(&cmds->cmds[index], cmd))) {
+		dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
+			 cmd->opcode);
+		return;
+	}
+
 	cmds->num++;
 }
 
@@ -1764,10 +1770,11 @@ static int arm_smmu_atc_inv_master(struct arm_smmu_master *master)
 {
 	int i;
 	struct arm_smmu_cmdq_ent cmd;
-	struct arm_smmu_cmdq_batch cmds = {};
+	struct arm_smmu_cmdq_batch cmds;
 
 	arm_smmu_atc_inv_to_cmd(0, 0, 0, &cmd);
 
+	cmds.num = 0;
 	for (i = 0; i < master->num_streams; i++) {
 		cmd.atc.sid = master->streams[i].id;
 		arm_smmu_cmdq_batch_add(master->smmu, &cmds, &cmd);
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 55690af1b25d0d..ca736b065dd0bc 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -231,6 +231,7 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,sc7180-mdss" },
 	{ .compatible = "qcom,sc7180-mss-pil" },
 	{ .compatible = "qcom,sc7280-mdss" },
+	{ .compatible = "qcom,sc7280-mss-pil" },
 	{ .compatible = "qcom,sc8180x-mdss" },
 	{ .compatible = "qcom,sdm845-mdss" },
 	{ .compatible = "qcom,sdm845-mss-pil" },
@@ -403,12 +404,14 @@ static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
 
 static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 	{ .compatible = "qcom,msm8998-smmu-v2" },
+	{ .compatible = "qcom,qcm2290-smmu-500" },
 	{ .compatible = "qcom,sc7180-smmu-500" },
 	{ .compatible = "qcom,sc7280-smmu-500" },
 	{ .compatible = "qcom,sc8180x-smmu-500" },
 	{ .compatible = "qcom,sdm630-smmu-v2" },
 	{ .compatible = "qcom,sdm845-smmu-500" },
 	{ .compatible = "qcom,sm6125-smmu-500" },
+	{ .compatible = "qcom,sm6350-smmu-500" },
 	{ .compatible = "qcom,sm8150-smmu-500" },
 	{ .compatible = "qcom,sm8250-smmu-500" },
 	{ .compatible = "qcom,sm8350-smmu-500" },
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 896bea04c347e6..b42e38a0dbe26e 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -98,9 +98,6 @@ static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
 /**
  * iommu_get_dma_cookie - Acquire DMA-API resources for a domain
  * @domain: IOMMU domain to prepare for DMA-API usage
- *
- * IOMMU drivers should normally call this from their domain_alloc
- * callback when domain->type == IOMMU_DOMAIN_DMA.
  */
 int iommu_get_dma_cookie(struct iommu_domain *domain)
 {
@@ -113,7 +110,6 @@ int iommu_get_dma_cookie(struct iommu_domain *domain)
 
 	return 0;
 }
-EXPORT_SYMBOL(iommu_get_dma_cookie);
 
 /**
  * iommu_get_msi_cookie - Acquire just MSI remapping resources
@@ -151,8 +147,6 @@ EXPORT_SYMBOL(iommu_get_msi_cookie);
  * iommu_put_dma_cookie - Release a domain's DMA mapping resources
  * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() or
  *          iommu_get_msi_cookie()
- *
- * IOMMU drivers should normally call this from their domain_free callback.
  */
 void iommu_put_dma_cookie(struct iommu_domain *domain)
 {
@@ -172,7 +166,6 @@ void iommu_put_dma_cookie(struct iommu_domain *domain)
 	kfree(cookie);
 	domain->iova_cookie = NULL;
 }
-EXPORT_SYMBOL(iommu_put_dma_cookie);
 
 /**
  * iommu_dma_get_resv_regions - Reserved region driver helper
@@ -317,6 +310,11 @@ static bool dev_is_untrusted(struct device *dev)
 	return dev_is_pci(dev) && to_pci_dev(dev)->untrusted;
 }
 
+static bool dev_use_swiotlb(struct device *dev)
+{
+	return IS_ENABLED(CONFIG_SWIOTLB) && dev_is_untrusted(dev);
+}
+
 /* sysfs updates are serialised by the mutex of the group owning @domain */
 int iommu_dma_init_fq(struct iommu_domain *domain)
 {
@@ -510,23 +508,6 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 	iommu_dma_free_iova(cookie, dma_addr, size, &iotlb_gather);
 }
 
-static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr,
-		size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	struct iommu_domain *domain = iommu_get_dma_domain(dev);
-	phys_addr_t phys;
-
-	phys = iommu_iova_to_phys(domain, dma_addr);
-	if (WARN_ON(!phys))
-		return;
-
-	__iommu_dma_unmap(dev, dma_addr, size);
-
-	if (unlikely(is_swiotlb_buffer(dev, phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
-}
-
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 		size_t size, int prot, u64 dma_mask)
 {
@@ -553,52 +534,6 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 	return iova + iova_off;
 }
 
-static dma_addr_t __iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys,
-		size_t org_size, dma_addr_t dma_mask, bool coherent,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	int prot = dma_info_to_prot(dir, coherent, attrs);
-	struct iommu_domain *domain = iommu_get_dma_domain(dev);
-	struct iommu_dma_cookie *cookie = domain->iova_cookie;
-	struct iova_domain *iovad = &cookie->iovad;
-	size_t aligned_size = org_size;
-	void *padding_start;
-	size_t padding_size;
-	dma_addr_t iova;
-
-	/*
-	 * If both the physical buffer start address and size are
-	 * page aligned, we don't need to use a bounce page.
-	 */
-	if (IS_ENABLED(CONFIG_SWIOTLB) && dev_is_untrusted(dev) &&
-	    iova_offset(iovad, phys | org_size)) {
-		aligned_size = iova_align(iovad, org_size);
-		phys = swiotlb_tbl_map_single(dev, phys, org_size,
-					      aligned_size, dir, attrs);
-
-		if (phys == DMA_MAPPING_ERROR)
-			return DMA_MAPPING_ERROR;
-
-		/* Cleanup the padding area. */
-		padding_start = phys_to_virt(phys);
-		padding_size = aligned_size;
-
-		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-		    (dir == DMA_TO_DEVICE ||
-		     dir == DMA_BIDIRECTIONAL)) {
-			padding_start += org_size;
-			padding_size -= org_size;
-		}
-
-		memset(padding_start, 0, padding_size);
-	}
-
-	iova = __iommu_dma_map(dev, phys, aligned_size, prot, dma_mask);
-	if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(dev, phys))
-		swiotlb_tbl_unmap_single(dev, phys, org_size, dir, attrs);
-	return iova;
-}
-
 static void __iommu_dma_free_pages(struct page **pages, int count)
 {
 	while (count--)
@@ -616,7 +551,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 	if (!order_mask)
 		return NULL;
 
-	pages = kvzalloc(count * sizeof(*pages), GFP_KERNEL);
+	pages = kvcalloc(count, sizeof(*pages), GFP_KERNEL);
 	if (!pages)
 		return NULL;
 
@@ -794,7 +729,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev,
 {
 	phys_addr_t phys;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
+	if (dev_is_dma_coherent(dev) && !dev_use_swiotlb(dev))
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
@@ -810,7 +745,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev,
 {
 	phys_addr_t phys;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
+	if (dev_is_dma_coherent(dev) && !dev_use_swiotlb(dev))
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
@@ -828,17 +763,13 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev,
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
-		return;
-
-	for_each_sg(sgl, sg, nelems, i) {
-		if (!dev_is_dma_coherent(dev))
+	if (dev_use_swiotlb(dev))
+		for_each_sg(sgl, sg, nelems, i)
+			iommu_dma_sync_single_for_cpu(dev, sg_dma_address(sg),
+						      sg->length, dir);
+	else if (!dev_is_dma_coherent(dev))
+		for_each_sg(sgl, sg, nelems, i)
 			arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
-
-		if (is_swiotlb_buffer(dev, sg_phys(sg)))
-			swiotlb_sync_single_for_cpu(dev, sg_phys(sg),
-						    sg->length, dir);
-	}
 }
 
 static void iommu_dma_sync_sg_for_device(struct device *dev,
@@ -848,17 +779,14 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
-		return;
-
-	for_each_sg(sgl, sg, nelems, i) {
-		if (is_swiotlb_buffer(dev, sg_phys(sg)))
-			swiotlb_sync_single_for_device(dev, sg_phys(sg),
-						       sg->length, dir);
-
-		if (!dev_is_dma_coherent(dev))
+	if (dev_use_swiotlb(dev))
+		for_each_sg(sgl, sg, nelems, i)
+			iommu_dma_sync_single_for_device(dev,
+							 sg_dma_address(sg),
+							 sg->length, dir);
+	else if (!dev_is_dma_coherent(dev))
+		for_each_sg(sgl, sg, nelems, i)
 			arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
-	}
 }
 
 static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
@@ -867,22 +795,66 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 {
 	phys_addr_t phys = page_to_phys(page) + offset;
 	bool coherent = dev_is_dma_coherent(dev);
-	dma_addr_t dma_handle;
+	int prot = dma_info_to_prot(dir, coherent, attrs);
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	dma_addr_t iova, dma_mask = dma_get_mask(dev);
+
+	/*
+	 * If both the physical buffer start address and size are
+	 * page aligned, we don't need to use a bounce page.
+	 */
+	if (dev_use_swiotlb(dev) && iova_offset(iovad, phys | size)) {
+		void *padding_start;
+		size_t padding_size, aligned_size;
+
+		aligned_size = iova_align(iovad, size);
+		phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size,
+					      iova_mask(iovad), dir, attrs);
+
+		if (phys == DMA_MAPPING_ERROR)
+			return DMA_MAPPING_ERROR;
 
-	dma_handle = __iommu_dma_map_swiotlb(dev, phys, size, dma_get_mask(dev),
-			coherent, dir, attrs);
-	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-	    dma_handle != DMA_MAPPING_ERROR)
+		/* Cleanup the padding area. */
+		padding_start = phys_to_virt(phys);
+		padding_size = aligned_size;
+
+		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+		    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) {
+			padding_start += size;
+			padding_size -= size;
+		}
+
+		memset(padding_start, 0, padding_size);
+	}
+
+	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		arch_sync_dma_for_device(phys, size, dir);
-	return dma_handle;
+
+	iova = __iommu_dma_map(dev, phys, size, prot, dma_mask);
+	if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(dev, phys))
+		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
+	return iova;
 }
 
 static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		iommu_dma_sync_single_for_cpu(dev, dma_handle, size, dir);
-	__iommu_dma_unmap_swiotlb(dev, dma_handle, size, dir, attrs);
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	phys_addr_t phys;
+
+	phys = iommu_iova_to_phys(domain, dma_handle);
+	if (WARN_ON(!phys))
+		return;
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && !dev_is_dma_coherent(dev))
+		arch_sync_dma_for_cpu(phys, size, dir);
+
+	__iommu_dma_unmap(dev, dma_handle, size);
+
+	if (unlikely(is_swiotlb_buffer(dev, phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
 }
 
 /*
@@ -967,7 +939,7 @@ static void iommu_dma_unmap_sg_swiotlb(struct device *dev, struct scatterlist *s
 	int i;
 
 	for_each_sg(sg, s, nents, i)
-		__iommu_dma_unmap_swiotlb(dev, sg_dma_address(s),
+		iommu_dma_unmap_page(dev, sg_dma_address(s),
 				sg_dma_len(s), dir, attrs);
 }
 
@@ -978,9 +950,8 @@ static int iommu_dma_map_sg_swiotlb(struct device *dev, struct scatterlist *sg,
 	int i;
 
 	for_each_sg(sg, s, nents, i) {
-		sg_dma_address(s) = __iommu_dma_map_swiotlb(dev, sg_phys(s),
-				s->length, dma_get_mask(dev),
-				dev_is_dma_coherent(dev), dir, attrs);
+		sg_dma_address(s) = iommu_dma_map_page(dev, sg_page(s),
+				s->offset, s->length, dir, attrs);
 		if (sg_dma_address(s) == DMA_MAPPING_ERROR)
 			goto out_unmap;
 		sg_dma_len(s) = s->length;
@@ -1016,15 +987,16 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 
 	if (static_branch_unlikely(&iommu_deferred_attach_enabled)) {
 		ret = iommu_deferred_attach(dev, domain);
-		goto out;
+		if (ret)
+			goto out;
 	}
 
+	if (dev_use_swiotlb(dev))
+		return iommu_dma_map_sg_swiotlb(dev, sg, nents, dir, attrs);
+
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		iommu_dma_sync_sg_for_device(dev, sg, nents, dir);
 
-	if (dev_is_untrusted(dev))
-		return iommu_dma_map_sg_swiotlb(dev, sg, nents, dir, attrs);
-
 	/*
 	 * Work out how much IOVA space we need, and align the segments to
 	 * IOVA granules for the IOMMU driver to handle. With some clever
@@ -1097,14 +1069,14 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 	struct scatterlist *tmp;
 	int i;
 
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
-
-	if (dev_is_untrusted(dev)) {
+	if (dev_use_swiotlb(dev)) {
 		iommu_dma_unmap_sg_swiotlb(dev, sg, nents, dir, attrs);
 		return;
 	}
 
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
+
 	/*
 	 * The scatterlist segments are mapped into a single
 	 * contiguous IOVA allocation, so this is incredibly easy.
diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig
index 0ddb77115be7d0..247d0f2d5fdf77 100644
--- a/drivers/iommu/intel/Kconfig
+++ b/drivers/iommu/intel/Kconfig
@@ -6,6 +6,9 @@ config DMAR_TABLE
 config DMAR_PERF
 	bool
 
+config DMAR_DEBUG
+	bool
+
 config INTEL_IOMMU
 	bool "Support for Intel IOMMU using DMA Remapping Devices"
 	depends on PCI_MSI && ACPI && (X86 || IA64)
@@ -31,6 +34,7 @@ config INTEL_IOMMU_DEBUGFS
 	bool "Export Intel IOMMU internals in Debugfs"
 	depends on IOMMU_DEBUGFS
 	select DMAR_PERF
+	select DMAR_DEBUG
 	help
 	  !!!WARNING!!!
 
diff --git a/drivers/iommu/intel/cap_audit.c b/drivers/iommu/intel/cap_audit.c
index b12e421a2f1ab7..b39d223926a491 100644
--- a/drivers/iommu/intel/cap_audit.c
+++ b/drivers/iommu/intel/cap_audit.c
@@ -163,6 +163,14 @@ static int cap_audit_static(struct intel_iommu *iommu, enum cap_audit_type type)
 			check_irq_capabilities(iommu, i);
 	}
 
+	/*
+	 * If the system is sane to support scalable mode, either SL or FL
+	 * should be sane.
+	 */
+	if (intel_cap_smts_sanity() &&
+	    !intel_cap_flts_sanity() && !intel_cap_slts_sanity())
+		return -EOPNOTSUPP;
+
 out:
 	rcu_read_unlock();
 	return 0;
@@ -203,3 +211,8 @@ bool intel_cap_flts_sanity(void)
 {
 	return ecap_flts(intel_iommu_ecap_sanity);
 }
+
+bool intel_cap_slts_sanity(void)
+{
+	return ecap_slts(intel_iommu_ecap_sanity);
+}
diff --git a/drivers/iommu/intel/cap_audit.h b/drivers/iommu/intel/cap_audit.h
index 74cfccae0e8173..d07b75938961fb 100644
--- a/drivers/iommu/intel/cap_audit.h
+++ b/drivers/iommu/intel/cap_audit.h
@@ -111,6 +111,7 @@ bool intel_cap_smts_sanity(void);
 bool intel_cap_pasid_sanity(void);
 bool intel_cap_nest_sanity(void);
 bool intel_cap_flts_sanity(void);
+bool intel_cap_slts_sanity(void);
 
 static inline bool scalable_mode_support(void)
 {
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index b7708b93f3fa18..915bff76fe9658 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1941,12 +1941,16 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
 
 	reason = dmar_get_fault_reason(fault_reason, &fault_type);
 
-	if (fault_type == INTR_REMAP)
+	if (fault_type == INTR_REMAP) {
 		pr_err("[INTR-REMAP] Request device [%02x:%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n",
 		       source_id >> 8, PCI_SLOT(source_id & 0xFF),
 		       PCI_FUNC(source_id & 0xFF), addr >> 48,
 		       fault_reason, reason);
-	else if (pasid == INVALID_IOASID)
+
+		return 0;
+	}
+
+	if (pasid == INVALID_IOASID)
 		pr_err("[%s NO_PASID] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n",
 		       type ? "DMA Read" : "DMA Write",
 		       source_id >> 8, PCI_SLOT(source_id & 0xFF),
@@ -1959,6 +1963,8 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
 		       PCI_FUNC(source_id & 0xFF), addr,
 		       fault_reason, reason);
 
+	dmar_fault_dump_ptes(iommu, source_id, addr, pasid);
+
 	return 0;
 }
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index d75f59ae28e6e5..0bde0c8b41269c 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -156,6 +156,8 @@ static struct intel_iommu **g_iommus;
 
 static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
+static inline struct device_domain_info *
+dmar_search_domain_by_dev_info(int segment, int bus, int devfn);
 
 /*
  * set to 1 to panic kernel if can't successfully enable VT-d
@@ -412,6 +414,7 @@ static int __init intel_iommu_setup(char *str)
 {
 	if (!str)
 		return -EINVAL;
+
 	while (*str) {
 		if (!strncmp(str, "on", 2)) {
 			dmar_disabled = 0;
@@ -441,13 +444,16 @@ static int __init intel_iommu_setup(char *str)
 		} else if (!strncmp(str, "tboot_noforce", 13)) {
 			pr_info("Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
 			intel_iommu_tboot_noforce = 1;
+		} else {
+			pr_notice("Unknown option - '%s'\n", str);
 		}
 
 		str += strcspn(str, ",");
 		while (*str == ',')
 			str++;
 	}
-	return 0;
+
+	return 1;
 }
 __setup("intel_iommu=", intel_iommu_setup);
 
@@ -522,7 +528,7 @@ static inline void free_devinfo_mem(void *vaddr)
 
 static inline int domain_type_is_si(struct dmar_domain *domain)
 {
-	return domain->flags & DOMAIN_FLAG_STATIC_IDENTITY;
+	return domain->domain.type == IOMMU_DOMAIN_IDENTITY;
 }
 
 static inline bool domain_use_first_level(struct dmar_domain *domain)
@@ -992,6 +998,117 @@ out:
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
+#ifdef CONFIG_DMAR_DEBUG
+static void pgtable_walk(struct intel_iommu *iommu, unsigned long pfn, u8 bus, u8 devfn)
+{
+	struct device_domain_info *info;
+	struct dma_pte *parent, *pte;
+	struct dmar_domain *domain;
+	int offset, level;
+
+	info = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn);
+	if (!info || !info->domain) {
+		pr_info("device [%02x:%02x.%d] not probed\n",
+			bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+		return;
+	}
+
+	domain = info->domain;
+	level = agaw_to_level(domain->agaw);
+	parent = domain->pgd;
+	if (!parent) {
+		pr_info("no page table setup\n");
+		return;
+	}
+
+	while (1) {
+		offset = pfn_level_offset(pfn, level);
+		pte = &parent[offset];
+		if (!pte || (dma_pte_superpage(pte) || !dma_pte_present(pte))) {
+			pr_info("PTE not present at level %d\n", level);
+			break;
+		}
+
+		pr_info("pte level: %d, pte value: 0x%016llx\n", level, pte->val);
+
+		if (level == 1)
+			break;
+
+		parent = phys_to_virt(dma_pte_addr(pte));
+		level--;
+	}
+}
+
+void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
+			  unsigned long long addr, u32 pasid)
+{
+	struct pasid_dir_entry *dir, *pde;
+	struct pasid_entry *entries, *pte;
+	struct context_entry *ctx_entry;
+	struct root_entry *rt_entry;
+	u8 devfn = source_id & 0xff;
+	u8 bus = source_id >> 8;
+	int i, dir_index, index;
+
+	pr_info("Dump %s table entries for IOVA 0x%llx\n", iommu->name, addr);
+
+	/* root entry dump */
+	rt_entry = &iommu->root_entry[bus];
+	if (!rt_entry) {
+		pr_info("root table entry is not present\n");
+		return;
+	}
+
+	if (sm_supported(iommu))
+		pr_info("scalable mode root entry: hi 0x%016llx, low 0x%016llx\n",
+			rt_entry->hi, rt_entry->lo);
+	else
+		pr_info("root entry: 0x%016llx", rt_entry->lo);
+
+	/* context entry dump */
+	ctx_entry = iommu_context_addr(iommu, bus, devfn, 0);
+	if (!ctx_entry) {
+		pr_info("context table entry is not present\n");
+		return;
+	}
+
+	pr_info("context entry: hi 0x%016llx, low 0x%016llx\n",
+		ctx_entry->hi, ctx_entry->lo);
+
+	/* legacy mode does not require PASID entries */
+	if (!sm_supported(iommu))
+		goto pgtable_walk;
+
+	/* get the pointer to pasid directory entry */
+	dir = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK);
+	if (!dir) {
+		pr_info("pasid directory entry is not present\n");
+		return;
+	}
+	/* For request-without-pasid, get the pasid from context entry */
+	if (intel_iommu_sm && pasid == INVALID_IOASID)
+		pasid = PASID_RID2PASID;
+
+	dir_index = pasid >> PASID_PDE_SHIFT;
+	pde = &dir[dir_index];
+	pr_info("pasid dir entry: 0x%016llx\n", pde->val);
+
+	/* get the pointer to the pasid table entry */
+	entries = get_pasid_table_from_pde(pde);
+	if (!entries) {
+		pr_info("pasid table entry is not present\n");
+		return;
+	}
+	index = pasid & PASID_PTE_MASK;
+	pte = &entries[index];
+	for (i = 0; i < ARRAY_SIZE(pte->val); i++)
+		pr_info("pasid table entry[%d]: 0x%016llx\n", i, pte->val[i]);
+
+pgtable_walk:
+	pgtable_walk(iommu, addr >> VTD_PAGE_SHIFT, bus, devfn);
+}
+#endif
+
 static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 				      unsigned long pfn, int *target_level)
 {
@@ -1874,12 +1991,21 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
  * Check and return whether first level is used by default for
  * DMA translation.
  */
-static bool first_level_by_default(void)
+static bool first_level_by_default(unsigned int type)
 {
-	return scalable_mode_support() && intel_cap_flts_sanity();
+	/* Only SL is available in legacy mode */
+	if (!scalable_mode_support())
+		return false;
+
+	/* Only level (either FL or SL) is available, just use it */
+	if (intel_cap_flts_sanity() ^ intel_cap_slts_sanity())
+		return intel_cap_flts_sanity();
+
+	/* Both levels are available, decide it based on domain type */
+	return type != IOMMU_DOMAIN_UNMANAGED;
 }
 
-static struct dmar_domain *alloc_domain(int flags)
+static struct dmar_domain *alloc_domain(unsigned int type)
 {
 	struct dmar_domain *domain;
 
@@ -1889,8 +2015,7 @@ static struct dmar_domain *alloc_domain(int flags)
 
 	memset(domain, 0, sizeof(*domain));
 	domain->nid = NUMA_NO_NODE;
-	domain->flags = flags;
-	if (first_level_by_default())
+	if (first_level_by_default(type))
 		domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
@@ -2354,12 +2479,17 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 				return -ENOMEM;
 			first_pte = pte;
 
+			lvl_pages = lvl_to_nr_pages(largepage_lvl);
+
 			/* It is large page*/
 			if (largepage_lvl > 1) {
 				unsigned long end_pfn;
+				unsigned long pages_to_remove;
 
 				pteval |= DMA_PTE_LARGE_PAGE;
-				end_pfn = ((iov_pfn + nr_pages) & level_mask(largepage_lvl)) - 1;
+				pages_to_remove = min_t(unsigned long, nr_pages,
+							nr_pte_to_next_page(pte) * lvl_pages);
+				end_pfn = iov_pfn + pages_to_remove - 1;
 				switch_to_super_page(domain, iov_pfn, end_pfn, largepage_lvl);
 			} else {
 				pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE;
@@ -2381,10 +2511,6 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			WARN_ON(1);
 		}
 
-		lvl_pages = lvl_to_nr_pages(largepage_lvl);
-
-		BUG_ON(nr_pages < lvl_pages);
-
 		nr_pages -= lvl_pages;
 		iov_pfn += lvl_pages;
 		phys_pfn += lvl_pages;
@@ -2708,7 +2834,7 @@ static int __init si_domain_init(int hw)
 	struct device *dev;
 	int i, nid, ret;
 
-	si_domain = alloc_domain(DOMAIN_FLAG_STATIC_IDENTITY);
+	si_domain = alloc_domain(IOMMU_DOMAIN_IDENTITY);
 	if (!si_domain)
 		return -EFAULT;
 
@@ -4517,7 +4643,7 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 	case IOMMU_DOMAIN_DMA:
 	case IOMMU_DOMAIN_DMA_FQ:
 	case IOMMU_DOMAIN_UNMANAGED:
-		dmar_domain = alloc_domain(0);
+		dmar_domain = alloc_domain(type);
 		if (!dmar_domain) {
 			pr_err("Can't allocate dmar_domain\n");
 			return NULL;
@@ -5386,62 +5512,14 @@ static int intel_iommu_disable_sva(struct device *dev)
 	return ret;
 }
 
-/*
- * A PCI express designated vendor specific extended capability is defined
- * in the section 3.7 of Intel scalable I/O virtualization technical spec
- * for system software and tools to detect endpoint devices supporting the
- * Intel scalable IO virtualization without host driver dependency.
- *
- * Returns the address of the matching extended capability structure within
- * the device's PCI configuration space or 0 if the device does not support
- * it.
- */
-static int siov_find_pci_dvsec(struct pci_dev *pdev)
-{
-	int pos;
-	u16 vendor, id;
-
-	pos = pci_find_next_ext_capability(pdev, 0, 0x23);
-	while (pos) {
-		pci_read_config_word(pdev, pos + 4, &vendor);
-		pci_read_config_word(pdev, pos + 8, &id);
-		if (vendor == PCI_VENDOR_ID_INTEL && id == 5)
-			return pos;
-
-		pos = pci_find_next_ext_capability(pdev, pos, 0x23);
-	}
-
-	return 0;
-}
-
-static bool
-intel_iommu_dev_has_feat(struct device *dev, enum iommu_dev_features feat)
+static int intel_iommu_enable_iopf(struct device *dev)
 {
 	struct device_domain_info *info = get_domain_info(dev);
 
-	if (feat == IOMMU_DEV_FEAT_AUX) {
-		int ret;
-
-		if (!dev_is_pci(dev) || dmar_disabled ||
-		    !scalable_mode_support() || !pasid_mode_support())
-			return false;
-
-		ret = pci_pasid_features(to_pci_dev(dev));
-		if (ret < 0)
-			return false;
-
-		return !!siov_find_pci_dvsec(to_pci_dev(dev));
-	}
-
-	if (feat == IOMMU_DEV_FEAT_IOPF)
-		return info && info->pri_supported;
-
-	if (feat == IOMMU_DEV_FEAT_SVA)
-		return info && (info->iommu->flags & VTD_FLAG_SVM_CAPABLE) &&
-			info->pasid_supported && info->pri_supported &&
-			info->ats_supported;
+	if (info && info->pri_supported)
+		return 0;
 
-	return false;
+	return -ENODEV;
 }
 
 static int
@@ -5452,7 +5530,7 @@ intel_iommu_dev_enable_feat(struct device *dev, enum iommu_dev_features feat)
 		return intel_iommu_enable_auxd(dev);
 
 	case IOMMU_DEV_FEAT_IOPF:
-		return intel_iommu_dev_has_feat(dev, feat) ? 0 : -ENODEV;
+		return intel_iommu_enable_iopf(dev);
 
 	case IOMMU_DEV_FEAT_SVA:
 		return intel_iommu_enable_sva(dev);
@@ -5578,7 +5656,6 @@ const struct iommu_ops intel_iommu_ops = {
 	.get_resv_regions	= intel_iommu_get_resv_regions,
 	.put_resv_regions	= generic_iommu_put_resv_regions,
 	.device_group		= intel_iommu_device_group,
-	.dev_has_feat		= intel_iommu_dev_has_feat,
 	.dev_feat_enabled	= intel_iommu_dev_feat_enabled,
 	.dev_enable_feat	= intel_iommu_dev_enable_feat,
 	.dev_disable_feat	= intel_iommu_dev_disable_feat,
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 0c228787704f36..5b5d69b04fcc8d 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -505,21 +505,6 @@ out:
 	return ret;
 }
 
-static void _load_pasid(void *unused)
-{
-	update_pasid();
-}
-
-static void load_pasid(struct mm_struct *mm, u32 pasid)
-{
-	mutex_lock(&mm->context.lock);
-
-	/* Update PASID MSR on all CPUs running the mm's tasks. */
-	on_each_cpu_mask(mm_cpumask(mm), _load_pasid, NULL, true);
-
-	mutex_unlock(&mm->context.lock);
-}
-
 static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm,
 				 unsigned int flags)
 {
@@ -614,10 +599,6 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 	if (ret)
 		goto free_sdev;
 
-	/* The newly allocated pasid is loaded to the mm. */
-	if (!(flags & SVM_FLAG_SUPERVISOR_MODE) && list_empty(&svm->devs))
-		load_pasid(mm, svm->pasid);
-
 	list_add_rcu(&sdev->list, &svm->devs);
 success:
 	return &sdev->sva;
@@ -670,11 +651,8 @@ static int intel_svm_unbind_mm(struct device *dev, u32 pasid)
 			kfree_rcu(sdev, rcu);
 
 			if (list_empty(&svm->devs)) {
-				if (svm->notifier.ops) {
+				if (svm->notifier.ops)
 					mmu_notifier_unregister(&svm->notifier, mm);
-					/* Clear mm's pasid. */
-					load_pasid(mm, PASID_DISABLED);
-				}
 				pasid_private_remove(svm->pasid);
 				/* We mandate that no page faults may be outstanding
 				 * for the PASID when intel_svm_unbind_mm() is called.
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index e80261d17a4996..dd7863e453a5f4 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1954,8 +1954,7 @@ static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
 	/* Assume all sizes by default; the driver may override this later */
 	domain->pgsize_bitmap  = bus->iommu_ops->pgsize_bitmap;
 
-	/* Temporarily avoid -EEXIST while drivers still get their own cookies */
-	if (iommu_is_dma_domain(domain) && !domain->iova_cookie && iommu_get_dma_cookie(domain)) {
+	if (iommu_is_dma_domain(domain) && iommu_get_dma_cookie(domain)) {
 		iommu_domain_free(domain);
 		domain = NULL;
 	}
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index d38ff29a76e8f8..ca752bdc710f6a 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -33,10 +33,10 @@
 #define arm_iommu_detach_device(...)	do {} while (0)
 #endif
 
-#define IPMMU_CTX_MAX		8U
+#define IPMMU_CTX_MAX		16U
 #define IPMMU_CTX_INVALID	-1
 
-#define IPMMU_UTLB_MAX		48U
+#define IPMMU_UTLB_MAX		64U
 
 struct ipmmu_features {
 	bool use_ns_alias_offset;
@@ -189,8 +189,12 @@ static void ipmmu_write(struct ipmmu_vmsa_device *mmu, unsigned int offset,
 static unsigned int ipmmu_ctx_reg(struct ipmmu_vmsa_device *mmu,
 				  unsigned int context_id, unsigned int reg)
 {
-	return mmu->features->ctx_offset_base +
-	       context_id * mmu->features->ctx_offset_stride + reg;
+	unsigned int base = mmu->features->ctx_offset_base;
+
+	if (context_id > 7)
+		base += 0x800 - 8 * 0x40;
+
+	return base + context_id * mmu->features->ctx_offset_stride + reg;
 }
 
 static u32 ipmmu_ctx_read(struct ipmmu_vmsa_device *mmu,
@@ -922,6 +926,20 @@ static const struct ipmmu_features ipmmu_features_rcar_gen3 = {
 	.utlb_offset_base = 0,
 };
 
+static const struct ipmmu_features ipmmu_features_r8a779a0 = {
+	.use_ns_alias_offset = false,
+	.has_cache_leaf_nodes = true,
+	.number_of_contexts = 16,
+	.num_utlbs = 64,
+	.setup_imbuscr = false,
+	.twobit_imttbcr_sl0 = true,
+	.reserved_context = true,
+	.cache_snoop = false,
+	.ctx_offset_base = 0x10000,
+	.ctx_offset_stride = 0x1040,
+	.utlb_offset_base = 0x3000,
+};
+
 static const struct of_device_id ipmmu_of_ids[] = {
 	{
 		.compatible = "renesas,ipmmu-vmsa",
@@ -954,12 +972,18 @@ static const struct of_device_id ipmmu_of_ids[] = {
 		.compatible = "renesas,ipmmu-r8a77970",
 		.data = &ipmmu_features_rcar_gen3,
 	}, {
+		.compatible = "renesas,ipmmu-r8a77980",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
 		.compatible = "renesas,ipmmu-r8a77990",
 		.data = &ipmmu_features_rcar_gen3,
 	}, {
 		.compatible = "renesas,ipmmu-r8a77995",
 		.data = &ipmmu_features_rcar_gen3,
 	}, {
+		.compatible = "renesas,ipmmu-r8a779a0",
+		.data = &ipmmu_features_r8a779a0,
+	}, {
 		/* Terminator */
 	},
 };
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index d837adfd1da552..25b834104790cd 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -550,7 +550,9 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 	phys_addr_t pa;
 
 	pa = dom->iop->iova_to_phys(dom->iop, iova);
-	if (dom->data->enable_4GB && pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
+	if (IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT) &&
+	    dom->data->enable_4GB &&
+	    pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
 		pa &= ~BIT_ULL(32);
 
 	return pa;
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 0a281833f6117b..e900e3c46903b1 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -1079,7 +1079,6 @@ struct tegra_smmu *tegra_smmu_probe(struct device *dev,
 				    struct tegra_mc *mc)
 {
 	struct tegra_smmu *smmu;
-	size_t size;
 	u32 value;
 	int err;
 
@@ -1097,9 +1096,7 @@ struct tegra_smmu *tegra_smmu_probe(struct device *dev,
 	 */
 	mc->smmu = smmu;
 
-	size = BITS_TO_LONGS(soc->num_asids) * sizeof(long);
-
-	smmu->asids = devm_kzalloc(dev, size, GFP_KERNEL);
+	smmu->asids = devm_bitmap_zalloc(dev, soc->num_asids, GFP_KERNEL);
 	if (!smmu->asids)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index e56a5faac395c6..cbdff897998070 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -380,7 +380,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 */
 	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
 
-	map = swiotlb_tbl_map_single(dev, phys, size, size, dir, attrs);
+	map = swiotlb_tbl_map_single(dev, phys, size, size, 0, dir, attrs);
 	if (map == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index e04436a7ff271d..45e903d8473355 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -131,6 +131,14 @@ static inline int dmar_res_noop(struct acpi_dmar_header *hdr, void *arg)
 	return 0;
 }
 
+#ifdef CONFIG_DMAR_DEBUG
+void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
+			  unsigned long long addr, u32 pasid);
+#else
+static inline void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
+					unsigned long long addr, u32 pasid) {}
+#endif
+
 #ifdef CONFIG_INTEL_IOMMU
 extern int iommu_detected, no_iommu;
 extern int intel_iommu_init(void);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 05a65eb155f766..69230fd695eadb 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -517,9 +517,6 @@ struct context_entry {
 	u64 hi;
 };
 
-/* si_domain contains mulitple devices */
-#define DOMAIN_FLAG_STATIC_IDENTITY		BIT(0)
-
 /*
  * When VT-d works in the scalable mode, it allows DMA translation to
  * happen through either first level or second level page table. This
@@ -708,9 +705,15 @@ static inline bool dma_pte_superpage(struct dma_pte *pte)
 	return (pte->val & DMA_PTE_LARGE_PAGE);
 }
 
-static inline int first_pte_in_page(struct dma_pte *pte)
+static inline bool first_pte_in_page(struct dma_pte *pte)
+{
+	return IS_ALIGNED((unsigned long)pte, VTD_PAGE_SIZE);
+}
+
+static inline int nr_pte_to_next_page(struct dma_pte *pte)
 {
-	return !((unsigned long)pte & ~VTD_PAGE_MASK);
+	return first_pte_in_page(pte) ? BIT_ULL(VTD_STRIDE_SHIFT) :
+		(struct dma_pte *)ALIGN((unsigned long)pte, VTD_PAGE_SIZE) - pte;
 }
 
 extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index b0cb2a9973f495..569272871375c4 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -45,7 +45,8 @@ extern void __init swiotlb_update_mem_attributes(void);
 
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
 		size_t mapping_size, size_t alloc_size,
-		enum dma_data_direction dir, unsigned long attrs);
+		unsigned int alloc_aligned_mask, enum dma_data_direction dir,
+		unsigned long attrs);
 
 extern void swiotlb_tbl_unmap_single(struct device *hwdev,
 				     phys_addr_t tlb_addr,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index c4ca040fdb051f..6fab31ea47d6c5 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -459,7 +459,7 @@ static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index)
  * allocate a buffer from that IO TLB pool.
  */
 static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
-			      size_t alloc_size)
+			      size_t alloc_size, unsigned int alloc_align_mask)
 {
 	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
 	unsigned long boundary_mask = dma_get_seg_boundary(dev);
@@ -483,6 +483,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
 	if (alloc_size >= PAGE_SIZE)
 		stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT));
+	stride = max(stride, (alloc_align_mask >> IO_TLB_SHIFT) + 1);
 
 	spin_lock_irqsave(&mem->lock, flags);
 	if (unlikely(nslots > mem->nslabs - mem->used))
@@ -541,7 +542,8 @@ found:
 
 phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		size_t mapping_size, size_t alloc_size,
-		enum dma_data_direction dir, unsigned long attrs)
+		unsigned int alloc_align_mask, enum dma_data_direction dir,
+		unsigned long attrs)
 {
 	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
 	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
@@ -561,7 +563,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
 
-	index = swiotlb_find_slots(dev, orig_addr, alloc_size + offset);
+	index = swiotlb_find_slots(dev, orig_addr,
+				   alloc_size + offset, alloc_align_mask);
 	if (index == -1) {
 		if (!(attrs & DMA_ATTR_NO_WARN))
 			dev_warn_ratelimited(dev,
@@ -675,7 +678,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
 			      swiotlb_force);
 
-	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir,
+	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir,
 			attrs);
 	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
@@ -759,7 +762,7 @@ struct page *swiotlb_alloc(struct device *dev, size_t size)
 	if (!mem)
 		return NULL;
 
-	index = swiotlb_find_slots(dev, 0, size);
+	index = swiotlb_find_slots(dev, 0, size, 0);
 	if (index == -1)
 		return NULL;