Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git

12 files changed, 188 insertions, 152 deletions

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/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 1722bb161841fe..beadcffcc22373 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -473,6 +473,12 @@ 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)
 {
@@ -485,6 +491,20 @@ 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);
@@ -495,6 +515,7 @@ 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 559db9259e65c7..21e2ec192d5a57 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>
@@ -183,7 +182,6 @@ struct apple_dart_master_cfg {
 
 static struct platform_driver apple_dart_driver;
 static const struct iommu_ops apple_dart_iommu_ops;
-static const struct iommu_flush_ops apple_dart_tlb_ops;
 
 static struct apple_dart_domain *to_dart_domain(struct iommu_domain *dom)
 {
@@ -338,22 +336,6 @@ static void apple_dart_iotlb_sync_map(struct iommu_domain *domain,
 	apple_dart_domain_flush_tlb(to_dart_domain(domain));
 }
 
-static void apple_dart_tlb_flush_all(void *cookie)
-{
-	apple_dart_domain_flush_tlb(cookie);
-}
-
-static void apple_dart_tlb_flush_walk(unsigned long iova, size_t size,
-				      size_t granule, void *cookie)
-{
-	apple_dart_domain_flush_tlb(cookie);
-}
-
-static const struct iommu_flush_ops apple_dart_tlb_ops = {
-	.tlb_flush_all = apple_dart_tlb_flush_all,
-	.tlb_flush_walk = apple_dart_tlb_flush_walk,
-};
-
 static phys_addr_t apple_dart_iova_to_phys(struct iommu_domain *domain,
 					   dma_addr_t iova)
 {
@@ -435,7 +417,6 @@ static int apple_dart_finalize_domain(struct iommu_domain *domain,
 		.ias = 32,
 		.oas = 36,
 		.coherent_walk = 1,
-		.tlb = &apple_dart_tlb_ops,
 		.iommu_dev = dart->dev,
 	};
 
@@ -596,7 +577,6 @@ 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 */
@@ -661,16 +641,34 @@ static int apple_dart_of_xlate(struct device *dev, struct of_phandle_args *args)
 	return -EINVAL;
 }
 
+static DEFINE_MUTEX(apple_dart_groups_lock);
+
+static void apple_dart_release_group(void *iommu_data)
+{
+	int i, sid;
+	struct apple_dart_stream_map *stream_map;
+	struct apple_dart_master_cfg *group_master_cfg = iommu_data;
+
+	mutex_lock(&apple_dart_groups_lock);
+
+	for_each_stream_map(i, group_master_cfg, stream_map)
+		for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS)
+			stream_map->dart->sid2group[sid] = NULL;
+
+	kfree(iommu_data);
+	mutex_unlock(&apple_dart_groups_lock);
+}
+
 static struct iommu_group *apple_dart_device_group(struct device *dev)
 {
-	static DEFINE_MUTEX(lock);
 	int i, sid;
 	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
 	struct apple_dart_stream_map *stream_map;
+	struct apple_dart_master_cfg *group_master_cfg;
 	struct iommu_group *group = NULL;
 	struct iommu_group *res = ERR_PTR(-EINVAL);
 
-	mutex_lock(&lock);
+	mutex_lock(&apple_dart_groups_lock);
 
 	for_each_stream_map(i, cfg, stream_map) {
 		for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) {
@@ -698,6 +696,20 @@ static struct iommu_group *apple_dart_device_group(struct device *dev)
 #endif
 		group = generic_device_group(dev);
 
+	res = ERR_PTR(-ENOMEM);
+	if (!group)
+		goto out;
+
+	group_master_cfg = kzalloc(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);
+
 	for_each_stream_map(i, cfg, stream_map)
 		for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS)
 			stream_map->dart->sid2group[sid] = group;
@@ -705,7 +717,7 @@ static struct iommu_group *apple_dart_device_group(struct device *dev)
 	res = group;
 
 out:
-	mutex_unlock(&lock);
+	mutex_unlock(&apple_dart_groups_lock);
 	return res;
 }
 
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 896bea04c347e6..de5040b6552956 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--)
@@ -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;
+
+		/* 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);
+	}
 
-	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)
+	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;
@@ -1019,12 +990,12 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		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 +1068,14 @@ 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/dmar.c b/drivers/iommu/intel/dmar.c
index 0ec5514c99807f..b7708b93f3fa18 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1942,18 +1942,18 @@ 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)
-		pr_err("[INTR-REMAP] Request device [0x%02x:0x%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n",
+		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)
-		pr_err("[%s NO_PASID] Request device [0x%02x:0x%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n",
+		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),
 		       PCI_FUNC(source_id & 0xFF), addr,
 		       fault_reason, reason);
 	else
-		pr_err("[%s PASID 0x%x] Request device [0x%02x:0x%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n",
+		pr_err("[%s PASID 0x%x] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n",
 		       type ? "DMA Read" : "DMA Write", pasid,
 		       source_id >> 8, PCI_SLOT(source_id & 0xFF),
 		       PCI_FUNC(source_id & 0xFF), addr,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 3303d707bab4bd..a80f13867bed93 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1953,8 +1953,7 @@ 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/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/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 87c40517e82274..019672b3da1d3c 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;