1 files changed, 129 insertions, 93 deletions

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 375c77e8d52f..355d16acee6d 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -13,6 +13,7 @@
 #include <linux/dma-noncoherent.h>
 #include <linux/pfn.h>
 #include <linux/set_memory.h>
+#include <linux/swiotlb.h>
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but
@@ -30,27 +31,16 @@ static inline bool force_dma_unencrypted(void)
 	return sev_active();
 }
 
-static bool
-check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
-		const char *caller)
+static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
 {
-	if (unlikely(dev && !dma_capable(dev, dma_addr, size))) {
-		if (!dev->dma_mask) {
-			dev_err(dev,
-				"%s: call on device without dma_mask\n",
-				caller);
-			return false;
-		}
-
-		if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) {
-			dev_err(dev,
-				"%s: overflow %pad+%zu of device mask %llx bus mask %llx\n",
-				caller, &dma_addr, size,
-				*dev->dma_mask, dev->bus_dma_mask);
-		}
-		return false;
+	if (!dev->dma_mask) {
+		dev_err_once(dev, "DMA map on device without dma_mask\n");
+	} else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) {
+		dev_err_once(dev,
+			"overflow %pad+%zu of DMA mask %llx bus mask %llx\n",
+			&dma_addr, size, *dev->dma_mask, dev->bus_dma_mask);
 	}
-	return true;
+	WARN_ON_ONCE(1);
 }
 
 static inline dma_addr_t phys_to_dma_direct(struct device *dev,
@@ -103,14 +93,13 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_mask);
 }
 
-void *dma_direct_alloc_pages(struct device *dev, size_t size,
+struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	int page_order = get_order(size);
 	struct page *page = NULL;
 	u64 phys_mask;
-	void *ret;
 
 	if (attrs & DMA_ATTR_NO_WARN)
 		gfp |= __GFP_NOWARN;
@@ -150,11 +139,34 @@ again:
 		}
 	}
 
+	return page;
+}
+
+void *dma_direct_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+	struct page *page;
+	void *ret;
+
+	page = __dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
 	if (!page)
 		return NULL;
+
+	if (PageHighMem(page)) {
+		/*
+		 * Depending on the cma= arguments and per-arch setup
+		 * dma_alloc_from_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");
+		__dma_direct_free_pages(dev, size, page);
+		return NULL;
+	}
+
 	ret = page_address(page);
 	if (force_dma_unencrypted()) {
-		set_memory_decrypted((unsigned long)ret, 1 << page_order);
+		set_memory_decrypted((unsigned long)ret, 1 << get_order(size));
 		*dma_handle = __phys_to_dma(dev, page_to_phys(page));
 	} else {
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
@@ -163,20 +175,22 @@ again:
 	return ret;
 }
 
-/*
- * NOTE: this function must never look at the dma_addr argument, because we want
- * to be able to use it as a helper for iommu implementations as well.
- */
+void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page)
+{
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	if (!dma_release_from_contiguous(dev, page, count))
+		__free_pages(page, get_order(size));
+}
+
 void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs)
 {
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned int page_order = get_order(size);
 
 	if (force_dma_unencrypted())
 		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
-	if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count))
-		free_pages((unsigned long)cpu_addr, page_order);
+	__dma_direct_free_pages(dev, size, virt_to_page(cpu_addr));
 }
 
 void *dma_direct_alloc(struct device *dev, size_t size,
@@ -196,67 +210,111 @@ void dma_direct_free(struct device *dev, size_t size,
 		dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
 }
 
-static void dma_direct_sync_single_for_device(struct device *dev,
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_single_for_device(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
-	if (dev_is_dma_coherent(dev))
-		return;
-	arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir);
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
+
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_device(dev, paddr, size, dir);
 }
+EXPORT_SYMBOL(dma_direct_sync_single_for_device);
 
-static void dma_direct_sync_sg_for_device(struct device *dev,
+void dma_direct_sync_sg_for_device(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev))
-		return;
+	for_each_sg(sgl, sg, nents, i) {
+		if (unlikely(is_swiotlb_buffer(sg_phys(sg))))
+			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length,
+					dir, SYNC_FOR_DEVICE);
 
-	for_each_sg(sgl, sg, nents, i)
-		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+		if (!dev_is_dma_coherent(dev))
+			arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
+					dir);
+	}
 }
+EXPORT_SYMBOL(dma_direct_sync_sg_for_device);
+#endif
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
-static void dma_direct_sync_single_for_cpu(struct device *dev,
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_single_for_cpu(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
-	if (dev_is_dma_coherent(dev))
-		return;
-	arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
-	arch_sync_dma_for_cpu_all(dev);
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (!dev_is_dma_coherent(dev)) {
+		arch_sync_dma_for_cpu(dev, paddr, size, dir);
+		arch_sync_dma_for_cpu_all(dev);
+	}
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
 }
+EXPORT_SYMBOL(dma_direct_sync_single_for_cpu);
 
-static void dma_direct_sync_sg_for_cpu(struct device *dev,
+void dma_direct_sync_sg_for_cpu(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev))
-		return;
+	for_each_sg(sgl, sg, nents, i) {
+		if (!dev_is_dma_coherent(dev))
+			arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+	
+		if (unlikely(is_swiotlb_buffer(sg_phys(sg))))
+			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, dir,
+					SYNC_FOR_CPU);
+	}
 
-	for_each_sg(sgl, sg, nents, i)
-		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
-	arch_sync_dma_for_cpu_all(dev);
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_cpu_all(dev);
 }
+EXPORT_SYMBOL(dma_direct_sync_sg_for_cpu);
 
-static void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
+	phys_addr_t phys = dma_to_phys(dev, addr);
+
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+
+	if (unlikely(is_swiotlb_buffer(phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
 }
+EXPORT_SYMBOL(dma_direct_unmap_page);
 
-static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir);
+	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);
 }
+EXPORT_SYMBOL(dma_direct_unmap_sg);
 #endif
 
+static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr,
+		size_t size)
+{
+	return swiotlb_force != SWIOTLB_FORCE &&
+		(!dev || dma_capable(dev, dma_addr, size));
+}
+
 dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir,
 		unsigned long attrs)
@@ -264,13 +322,17 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 	phys_addr_t phys = page_to_phys(page) + offset;
 	dma_addr_t dma_addr = phys_to_dma(dev, phys);
 
-	if (!check_addr(dev, dma_addr, size, __func__))
-		return DIRECT_MAPPING_ERROR;
+	if (unlikely(!dma_direct_possible(dev, dma_addr, size)) &&
+	    !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) {
+		report_addr(dev, dma_addr, size);
+		return DMA_MAPPING_ERROR;
+	}
 
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_single_for_device(dev, dma_addr, size, dir);
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(dev, phys, size, dir);
 	return dma_addr;
 }
+EXPORT_SYMBOL(dma_direct_map_page);
 
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
@@ -279,18 +341,20 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 	struct scatterlist *sg;
 
 	for_each_sg(sgl, sg, nents, i) {
-		BUG_ON(!sg_page(sg));
-
-		sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg));
-		if (!check_addr(dev, sg_dma_address(sg), sg->length, __func__))
-			return 0;
+		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
+				sg->offset, sg->length, dir, attrs);
+		if (sg->dma_address == DMA_MAPPING_ERROR)
+			goto out_unmap;
 		sg_dma_len(sg) = sg->length;
 	}
 
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_sg_for_device(dev, sgl, nents, dir);
 	return nents;
+
+out_unmap:
+	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
+	return 0;
 }
+EXPORT_SYMBOL(dma_direct_map_sg);
 
 /*
  * Because 32-bit DMA masks are so common we expect every architecture to be
@@ -316,31 +380,3 @@ int dma_direct_supported(struct device *dev, u64 mask)
 	 */
 	return mask >= __phys_to_dma(dev, min_mask);
 }
-
-int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == DIRECT_MAPPING_ERROR;
-}
-
-const struct dma_map_ops dma_direct_ops = {
-	.alloc			= dma_direct_alloc,
-	.free			= dma_direct_free,
-	.map_page		= dma_direct_map_page,
-	.map_sg			= dma_direct_map_sg,
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE)
-	.sync_single_for_device	= dma_direct_sync_single_for_device,
-	.sync_sg_for_device	= dma_direct_sync_sg_for_device,
-#endif
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
-	.sync_single_for_cpu	= dma_direct_sync_single_for_cpu,
-	.sync_sg_for_cpu	= dma_direct_sync_sg_for_cpu,
-	.unmap_page		= dma_direct_unmap_page,
-	.unmap_sg		= dma_direct_unmap_sg,
-#endif
-	.get_required_mask	= dma_direct_get_required_mask,
-	.dma_supported		= dma_direct_supported,
-	.mapping_error		= dma_direct_mapping_error,
-	.cache_sync		= arch_dma_cache_sync,
-};
-EXPORT_SYMBOL(dma_direct_ops);