1 files changed, 119 insertions, 107 deletions

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 63859a101ed8..50c3fe2a1d55 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"
 
 /*
@@ -20,7 +21,7 @@
  * it for entirely different regions. In that case the arch code needs to
  * override the variable below for dma-direct to work properly.
  */
-unsigned int zone_dma_bits __ro_after_init = 24;
+u64 zone_dma_limit __ro_after_init = DMA_BIT_MASK(24);
 
 static inline dma_addr_t phys_to_dma_direct(struct device *dev,
 		phys_addr_t phys)
@@ -44,10 +45,11 @@ u64 dma_direct_get_required_mask(struct device *dev)
 	return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
 }
 
-static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
-				  u64 *phys_limit)
+static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 *phys_limit)
 {
-	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
+	u64 dma_limit = min_not_zero(
+		dev->coherent_dma_mask,
+		dev->bus_dma_limit);
 
 	/*
 	 * Optimistically try the zone that the physical address mask falls
@@ -58,14 +60,14 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	 * zones.
 	 */
 	*phys_limit = dma_to_phys(dev, dma_limit);
-	if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits))
+	if (*phys_limit <= zone_dma_limit)
 		return GFP_DMA;
 	if (*phys_limit <= DMA_BIT_MASK(32))
 		return GFP_DMA32;
 	return 0;
 }
 
-static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
 	dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);
 
@@ -118,7 +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));
@@ -126,34 +128,28 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	if (is_swiotlb_for_alloc(dev))
 		return dma_direct_alloc_swiotlb(dev, size);
 
-	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
-					   &phys_limit);
+	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;
-		}
-	}
-again:
-	if (!page)
-		page = alloc_pages_node(node, gfp, get_order(size));
-	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+		if (dma_coherent_ok(dev, page_to_phys(page), size) &&
+		    (allow_highmem || !PageHighMem(page)))
+			return page;
+
 		dma_free_contiguous(dev, page, size);
-		page = NULL;
+	}
+
+	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));
 
 		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;
@@ -172,14 +168,13 @@ static void *dma_direct_alloc_from_pool(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
 	struct page *page;
-	u64 phys_mask;
+	u64 phys_limit;
 	void *ret;
 
 	if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_DMA_COHERENT_POOL)))
 		return NULL;
 
-	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
-					   &phys_mask);
+	gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit);
 	page = dma_alloc_from_pool(dev, size, &ret, gfp, dma_coherent_ok);
 	if (!page)
 		return NULL;
@@ -221,13 +216,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 		return dma_direct_alloc_no_mapping(dev, size, dma_handle, gfp);
 
 	if (!dev_is_dma_coherent(dev)) {
-		/*
-		 * Fallback to the arch handler if it exists.  This should
-		 * eventually go away.
-		 */
-		if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-		    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-		    !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
+		if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_ALLOC) &&
 		    !is_swiotlb_for_alloc(dev))
 			return arch_dma_alloc(dev, size, dma_handle, gfp,
 					      attrs);
@@ -241,27 +230,24 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 					dma_handle);
 
 		/*
-		 * Otherwise remap if the architecture is asking for it.  But
-		 * given that remapping memory is a blocking operation we'll
-		 * instead have to dip into the atomic pools.
+		 * Otherwise we require the architecture to either be able to
+		 * mark arbitrary parts of the kernel direct mapping uncached,
+		 * or remapped it uncached.
 		 */
+		set_uncached = IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED);
 		remap = IS_ENABLED(CONFIG_DMA_DIRECT_REMAP);
-		if (remap) {
-			if (dma_direct_use_pool(dev, gfp))
-				return dma_direct_alloc_from_pool(dev, size,
-						dma_handle, gfp);
-		} else {
-			if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED))
-				return NULL;
-			set_uncached = true;
+		if (!set_uncached && !remap) {
+			pr_warn_once("coherent DMA allocations not supported on this platform.\n");
+			return NULL;
 		}
 	}
 
 	/*
-	 * Decrypting memory may block, so allocate the memory from the atomic
-	 * pools if we can't block.
+	 * Remapping or decrypting memory may block, allocate the memory from
+	 * the atomic pools instead if we aren't allowed block.
 	 */
-	if (force_dma_unencrypted(dev) && dma_direct_use_pool(dev, gfp))
+	if ((remap || force_dma_unencrypted(dev)) &&
+	    dma_direct_use_pool(dev, gfp))
 		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
 
 	/* we always manually zero the memory once we are done */
@@ -296,7 +282,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 	} else {
 		ret = page_address(page);
 		if (dma_set_decrypted(dev, ret, size))
-			goto out_free_pages;
+			goto out_leak_pages;
 	}
 
 	memset(ret, 0, size);
@@ -317,6 +303,8 @@ out_encrypt_pages:
 out_free_pages:
 	__dma_direct_free_pages(dev, page, size);
 	return NULL;
+out_leak_pages:
+	return NULL;
 }
 
 void dma_direct_free(struct device *dev, size_t size,
@@ -331,9 +319,7 @@ void dma_direct_free(struct device *dev, size_t size,
 		return;
 	}
 
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
+	if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_ALLOC) &&
 	    !dev_is_dma_coherent(dev) &&
 	    !is_swiotlb_for_alloc(dev)) {
 		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
@@ -379,12 +365,11 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
 
 	ret = page_address(page);
 	if (dma_set_decrypted(dev, ret, size))
-		goto out_free_pages;
+		goto out_leak_pages;
 	memset(ret, 0, size);
 	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
 	return page;
-out_free_pages:
-	__dma_direct_free_pages(dev, page, size);
+out_leak_pages:
 	return NULL;
 }
 
@@ -415,9 +400,7 @@ void dma_direct_sync_sg_for_device(struct device *dev,
 	for_each_sg(sgl, sg, nents, i) {
 		phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg));
 
-		if (unlikely(is_swiotlb_buffer(dev, paddr)))
-			swiotlb_sync_single_for_device(dev, paddr, sg->length,
-						       dir);
+		swiotlb_sync_single_for_device(dev, paddr, sg->length, dir);
 
 		if (!dev_is_dma_coherent(dev))
 			arch_sync_dma_for_device(paddr, sg->length,
@@ -441,9 +424,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 		if (!dev_is_dma_coherent(dev))
 			arch_sync_dma_for_cpu(paddr, sg->length, dir);
 
-		if (unlikely(is_swiotlb_buffer(dev, paddr)))
-			swiotlb_sync_single_for_cpu(dev, 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);
@@ -464,10 +445,10 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 	int i;
 
 	for_each_sg(sgl,  sg, nents, i) {
-		if (sg_is_dma_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,
+			dma_direct_unmap_phys(dev, sg->dma_address,
 					      sg_dma_len(sg), dir, attrs);
 	}
 }
@@ -477,34 +458,34 @@ 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;
 
 	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:
+			sg->dma_address = dma_direct_map_phys(dev, sg_phys(sg),
+					sg->length, dir, attrs);
+			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;
@@ -517,22 +498,6 @@ 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)
@@ -595,10 +560,58 @@ int dma_direct_supported(struct device *dev, u64 mask)
 	 * part of the check.
 	 */
 	if (IS_ENABLED(CONFIG_ZONE_DMA))
-		min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits));
+		min_mask = min_t(u64, min_mask, zone_dma_limit);
 	return mask >= phys_to_dma_unencrypted(dev, min_mask);
 }
 
+static const struct bus_dma_region *dma_find_range(struct device *dev,
+						   unsigned long start_pfn)
+{
+	const struct bus_dma_region *m;
+
+	for (m = dev->dma_range_map; PFN_DOWN(m->size); m++) {
+		unsigned long cpu_start_pfn = PFN_DOWN(m->cpu_start);
+
+		if (start_pfn >= cpu_start_pfn &&
+		    start_pfn - cpu_start_pfn < PFN_DOWN(m->size))
+			return m;
+	}
+
+	return NULL;
+}
+
+/*
+ * To check whether all ram resource ranges are covered by dma range map
+ * Returns 0 when further check is needed
+ * Returns 1 if there is some RAM range can't be covered by dma_range_map
+ */
+static int check_ram_in_range_map(unsigned long start_pfn,
+				  unsigned long nr_pages, void *data)
+{
+	unsigned long end_pfn = start_pfn + nr_pages;
+	struct device *dev = data;
+
+	while (start_pfn < end_pfn) {
+		const struct bus_dma_region *bdr;
+
+		bdr = dma_find_range(dev, start_pfn);
+		if (!bdr)
+			return 1;
+
+		start_pfn = PFN_DOWN(bdr->cpu_start) + PFN_DOWN(bdr->size);
+	}
+
+	return 0;
+}
+
+bool dma_direct_all_ram_mapped(struct device *dev)
+{
+	if (!dev->dma_range_map)
+		return true;
+	return !walk_system_ram_range(0, PFN_DOWN(ULONG_MAX) + 1, dev,
+				      check_ram_in_range_map);
+}
+
 size_t dma_direct_max_mapping_size(struct device *dev)
 {
 	/* If SWIOTLB is active, use its maximum mapping size */
@@ -611,7 +624,7 @@ size_t dma_direct_max_mapping_size(struct device *dev)
 bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	return !dev_is_dma_coherent(dev) ||
-	       is_swiotlb_buffer(dev, dma_to_phys(dev, dma_addr));
+	       swiotlb_find_pool(dev, dma_to_phys(dev, dma_addr));
 }
 
 /**
@@ -649,7 +662,6 @@ int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
 		return -ENOMEM;
 	map[0].cpu_start = cpu_start;
 	map[0].dma_start = dma_start;
-	map[0].offset = offset;
 	map[0].size = size;
 	dev->dma_range_map = map;
 	return 0;