1 files changed, 86 insertions, 114 deletions

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 896bea04c347..b42e38a0dbe2 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.