1 files changed, 57 insertions, 67 deletions

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index b8fe0b3d0ffb..583c5922bca2 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -13,6 +13,7 @@
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
 #include <linux/slab.h>
+#include <linux/pci-p2pdma.h>
 #include "direct.h"
 
 /*
@@ -38,7 +39,7 @@ static inline struct page *dma_direct_to_page(struct device *dev,
 
 u64 dma_direct_get_required_mask(struct device *dev)
 {
-	phys_addr_t phys = (phys_addr_t)(max_pfn - 1) << PAGE_SHIFT;
+	phys_addr_t phys = ((phys_addr_t)max_pfn << PAGE_SHIFT) - 1;
 	u64 max_dma = phys_to_dma_direct(dev, phys);
 
 	return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
@@ -119,7 +120,7 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		gfp_t gfp, bool allow_highmem)
 {
 	int node = dev_to_node(dev);
-	struct page *page = NULL;
+	struct page *page;
 	u64 phys_limit;
 
 	WARN_ON_ONCE(!PAGE_ALIGNED(size));
@@ -130,30 +131,25 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit);
 	page = dma_alloc_contiguous(dev, size, gfp);
 	if (page) {
-		if (!dma_coherent_ok(dev, page_to_phys(page), size) ||
-		    (!allow_highmem && PageHighMem(page))) {
-			dma_free_contiguous(dev, page, size);
-			page = NULL;
-		}
+		if (dma_coherent_ok(dev, page_to_phys(page), size) &&
+		    (allow_highmem || !PageHighMem(page)))
+			return page;
+
+		dma_free_contiguous(dev, page, size);
 	}
-again:
-	if (!page)
-		page = alloc_pages_node(node, gfp, get_order(size));
-	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+
+	while ((page = alloc_pages_node(node, gfp, get_order(size)))
+	       && !dma_coherent_ok(dev, page_to_phys(page), size)) {
 		__free_pages(page, get_order(size));
-		page = NULL;
 
 		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
 		    phys_limit < DMA_BIT_MASK(64) &&
-		    !(gfp & (GFP_DMA32 | GFP_DMA))) {
+		    !(gfp & (GFP_DMA32 | GFP_DMA)))
 			gfp |= GFP_DMA32;
-			goto again;
-		}
-
-		if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) {
+		else if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA))
 			gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
-			goto again;
-		}
+		else
+			return NULL;
 	}
 
 	return page;
@@ -410,6 +406,8 @@ void dma_direct_sync_sg_for_device(struct device *dev,
 			arch_sync_dma_for_device(paddr, sg->length,
 					dir);
 	}
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_flush();
 }
 #endif
 
@@ -429,13 +427,12 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 			arch_sync_dma_for_cpu(paddr, sg->length, dir);
 
 		swiotlb_sync_single_for_cpu(dev, paddr, sg->length, dir);
-
-		if (dir == DMA_FROM_DEVICE)
-			arch_dma_mark_clean(paddr, sg->length);
 	}
 
-	if (!dev_is_dma_coherent(dev))
+	if (!dev_is_dma_coherent(dev)) {
+		arch_sync_dma_flush();
 		arch_sync_dma_for_cpu_all();
+	}
 }
 
 /*
@@ -447,14 +444,19 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 {
 	struct scatterlist *sg;
 	int i;
+	bool need_sync = false;
 
 	for_each_sg(sgl,  sg, nents, i) {
-		if (sg_dma_is_bus_address(sg))
+		if (sg_dma_is_bus_address(sg)) {
 			sg_dma_unmark_bus_address(sg);
-		else
-			dma_direct_unmap_page(dev, sg->dma_address,
-					      sg_dma_len(sg), dir, attrs);
+		} else {
+			need_sync = true;
+			dma_direct_unmap_phys(dev, sg->dma_address,
+					      sg_dma_len(sg), dir, attrs, false);
+		}
 	}
+	if (need_sync && !dev_is_dma_coherent(dev))
+		arch_sync_dma_flush();
 }
 #endif
 
@@ -462,39 +464,43 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
 {
 	struct pci_p2pdma_map_state p2pdma_state = {};
-	enum pci_p2pdma_map_type map;
 	struct scatterlist *sg;
 	int i, ret;
+	bool need_sync = false;
 
 	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;
+		switch (pci_p2pdma_state(&p2pdma_state, dev, sg_page(sg))) {
+		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.
+			 */
+			break;
+		case PCI_P2PDMA_MAP_NONE:
+			need_sync = true;
+			sg->dma_address = dma_direct_map_phys(dev, sg_phys(sg),
+					sg->length, dir, attrs, false);
+			if (sg->dma_address == DMA_MAPPING_ERROR) {
+				ret = -EIO;
 				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) {
-			ret = -EIO;
+			break;
+		case PCI_P2PDMA_MAP_BUS_ADDR:
+			sg->dma_address = pci_p2pdma_bus_addr_map(
+				p2pdma_state.mem, sg_phys(sg));
+			sg_dma_len(sg) = sg->length;
+			sg_dma_mark_bus_address(sg);
+			continue;
+		default:
+			ret = -EREMOTEIO;
 			goto out_unmap;
 		}
 		sg_dma_len(sg) = sg->length;
 	}
 
+	if (need_sync && !dev_is_dma_coherent(dev))
+		arch_sync_dma_flush();
 	return nents;
 
 out_unmap:
@@ -502,22 +508,6 @@ out_unmap:
 	return ret;
 }
 
-dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	dma_addr_t dma_addr = paddr;
-
-	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
-		dev_err_once(dev,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		WARN_ON_ONCE(1);
-		return DMA_MAPPING_ERROR;
-	}
-
-	return dma_addr;
-}
-
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs)
@@ -563,7 +553,7 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 
 int dma_direct_supported(struct device *dev, u64 mask)
 {
-	u64 min_mask = (max_pfn - 1) << PAGE_SHIFT;
+	u64 min_mask = ((u64)max_pfn << PAGE_SHIFT) - 1;
 
 	/*
 	 * Because 32-bit DMA masks are so common we expect every architecture
@@ -677,7 +667,7 @@ int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
 	if (!offset)
 		return 0;
 
-	map = kcalloc(2, sizeof(*map), GFP_KERNEL);
+	map = kzalloc_objs(*map, 2);
 	if (!map)
 		return -ENOMEM;
 	map[0].cpu_start = cpu_start;