1 files changed, 66 insertions, 41 deletions

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 50f48e9e4598..63859a101ed8 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -79,7 +79,7 @@ static int dma_set_decrypted(struct device *dev, void *vaddr, size_t size)
 {
 	if (!force_dma_unencrypted(dev))
 		return 0;
-	return set_memory_decrypted((unsigned long)vaddr, 1 << get_order(size));
+	return set_memory_decrypted((unsigned long)vaddr, PFN_UP(size));
 }
 
 static int dma_set_encrypted(struct device *dev, void *vaddr, size_t size)
@@ -88,7 +88,7 @@ static int dma_set_encrypted(struct device *dev, void *vaddr, size_t size)
 
 	if (!force_dma_unencrypted(dev))
 		return 0;
-	ret = set_memory_encrypted((unsigned long)vaddr, 1 << get_order(size));
+	ret = set_memory_encrypted((unsigned long)vaddr, PFN_UP(size));
 	if (ret)
 		pr_warn_ratelimited("leaking DMA memory that can't be re-encrypted\n");
 	return ret;
@@ -115,7 +115,7 @@ static struct page *dma_direct_alloc_swiotlb(struct device *dev, size_t size)
 }
 
 static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
-		gfp_t gfp)
+		gfp_t gfp, bool allow_highmem)
 {
 	int node = dev_to_node(dev);
 	struct page *page = NULL;
@@ -129,9 +129,12 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
 					   &phys_limit);
 	page = dma_alloc_contiguous(dev, size, gfp);
-	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
-		dma_free_contiguous(dev, page, size);
-		page = NULL;
+	if (page) {
+		if (!dma_coherent_ok(dev, page_to_phys(page), size) ||
+		    (!allow_highmem && PageHighMem(page))) {
+			dma_free_contiguous(dev, page, size);
+			page = NULL;
+		}
 	}
 again:
 	if (!page)
@@ -189,7 +192,7 @@ static void *dma_direct_alloc_no_mapping(struct device *dev, size_t size,
 {
 	struct page *page;
 
-	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO, true);
 	if (!page)
 		return NULL;
 
@@ -262,31 +265,31 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
 
 	/* we always manually zero the memory once we are done */
-	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO, true);
 	if (!page)
 		return NULL;
+
+	/*
+	 * dma_alloc_contiguous can return highmem pages depending on a
+	 * combination the cma= arguments and per-arch setup.  These need to be
+	 * remapped to return a kernel virtual address.
+	 */
 	if (PageHighMem(page)) {
-		/*
-		 * Depending on the cma= arguments and per-arch setup,
-		 * dma_alloc_contiguous could return highmem pages.
-		 * Without remapping there is no way to return them here, so
-		 * log an error and fail.
-		 */
-		if (!IS_ENABLED(CONFIG_DMA_REMAP)) {
-			dev_info(dev, "Rejecting highmem page from CMA.\n");
-			goto out_free_pages;
-		}
 		remap = true;
 		set_uncached = false;
 	}
 
 	if (remap) {
+		pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
+
+		if (force_dma_unencrypted(dev))
+			prot = pgprot_decrypted(prot);
+
 		/* remove any dirty cache lines on the kernel alias */
 		arch_dma_prep_coherent(page, size);
 
 		/* create a coherent mapping */
-		ret = dma_common_contiguous_remap(page, size,
-				dma_pgprot(dev, PAGE_KERNEL, attrs),
+		ret = dma_common_contiguous_remap(page, size, prot,
 				__builtin_return_address(0));
 		if (!ret)
 			goto out_free_pages;
@@ -349,12 +352,12 @@ void dma_direct_free(struct device *dev, size_t size,
 	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
 		return;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+	if (is_vmalloc_addr(cpu_addr)) {
 		vunmap(cpu_addr);
 	} else {
 		if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
 			arch_dma_clear_uncached(cpu_addr, size);
-		if (dma_set_encrypted(dev, cpu_addr, 1 << page_order))
+		if (dma_set_encrypted(dev, cpu_addr, size))
 			return;
 	}
 
@@ -370,19 +373,9 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
 	if (force_dma_unencrypted(dev) && dma_direct_use_pool(dev, gfp))
 		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
 
-	page = __dma_direct_alloc_pages(dev, size, gfp);
+	page = __dma_direct_alloc_pages(dev, size, gfp, false);
 	if (!page)
 		return NULL;
-	if (PageHighMem(page)) {
-		/*
-		 * Depending on the cma= arguments and per-arch setup
-		 * dma_alloc_contiguous could return highmem pages.
-		 * Without remapping there is no way to return them here,
-		 * so log an error and fail.
-		 */
-		dev_info(dev, "Rejecting highmem page from CMA.\n");
-		goto out_free_pages;
-	}
 
 	ret = page_address(page);
 	if (dma_set_decrypted(dev, ret, size))
@@ -399,7 +392,6 @@ void dma_direct_free_pages(struct device *dev, size_t size,
 		struct page *page, dma_addr_t dma_addr,
 		enum dma_data_direction dir)
 {
-	unsigned int page_order = get_order(size);
 	void *vaddr = page_address(page);
 
 	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
@@ -407,7 +399,7 @@ void dma_direct_free_pages(struct device *dev, size_t size,
 	    dma_free_from_pool(dev, vaddr, size))
 		return;
 
-	if (dma_set_encrypted(dev, vaddr, 1 << page_order))
+	if (dma_set_encrypted(dev, vaddr, size))
 		return;
 	__dma_direct_free_pages(dev, page, size);
 }
@@ -461,29 +453,60 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 		arch_sync_dma_for_cpu_all();
 }
 
+/*
+ * Unmaps segments, except for ones marked as pci_p2pdma which do not
+ * require any further action as they contain a bus address.
+ */
 void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct scatterlist *sg;
 	int i;
 
-	for_each_sg(sgl, sg, nents, i)
-		dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir,
-			     attrs);
+	for_each_sg(sgl,  sg, nents, i) {
+		if (sg_is_dma_bus_address(sg))
+			sg_dma_unmark_bus_address(sg);
+		else
+			dma_direct_unmap_page(dev, sg->dma_address,
+					      sg_dma_len(sg), dir, attrs);
+	}
 }
 #endif
 
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
 {
-	int i;
+	struct pci_p2pdma_map_state p2pdma_state = {};
+	enum pci_p2pdma_map_type map;
 	struct scatterlist *sg;
+	int i, ret;
 
 	for_each_sg(sgl, sg, nents, i) {
+		if (is_pci_p2pdma_page(sg_page(sg))) {
+			map = pci_p2pdma_map_segment(&p2pdma_state, dev, sg);
+			switch (map) {
+			case PCI_P2PDMA_MAP_BUS_ADDR:
+				continue;
+			case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+				/*
+				 * Any P2P mapping that traverses the PCI
+				 * host bridge must be mapped with CPU physical
+				 * address and not PCI bus addresses. This is
+				 * done with dma_direct_map_page() below.
+				 */
+				break;
+			default:
+				ret = -EREMOTEIO;
+				goto out_unmap;
+			}
+		}
+
 		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
 				sg->offset, sg->length, dir, attrs);
-		if (sg->dma_address == DMA_MAPPING_ERROR)
+		if (sg->dma_address == DMA_MAPPING_ERROR) {
+			ret = -EIO;
 			goto out_unmap;
+		}
 		sg_dma_len(sg) = sg->length;
 	}
 
@@ -491,7 +514,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 
 out_unmap:
 	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
-	return -EIO;
+	return ret;
 }
 
 dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
@@ -539,6 +562,8 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 	int ret = -ENXIO;
 
 	vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
+	if (force_dma_unencrypted(dev))
+		vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
 
 	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;