Merging upstream version 6.7.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 95 insertions, 30 deletions

diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index f488997b0..d62f5957f 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -135,6 +135,8 @@ config DMA_COHERENT_POOL
 
 config DMA_GLOBAL_POOL
 	select DMA_DECLARE_COHERENT
+	depends on !ARCH_HAS_DMA_SET_UNCACHED
+	depends on !DMA_DIRECT_REMAP
 	bool
 
 config DMA_DIRECT_REMAP
@@ -142,6 +144,15 @@ config DMA_DIRECT_REMAP
 	select DMA_COHERENT_POOL
 	select DMA_NONCOHERENT_MMAP
 
+#
+# Fallback to arch code for DMA allocations.  This should eventually go away.
+#
+config ARCH_HAS_DMA_ALLOC
+	depends on !ARCH_HAS_DMA_SET_UNCACHED
+	depends on !DMA_DIRECT_REMAP
+	depends on !DMA_GLOBAL_POOL
+	bool
+
 config DMA_CMA
 	bool "DMA Contiguous Memory Allocator"
 	depends on HAVE_DMA_CONTIGUOUS && CMA
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 06366acd2..3de494375 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -139,7 +139,7 @@ static const char *const maperr2str[] = {
 
 static const char *type2name[] = {
 	[dma_debug_single] = "single",
-	[dma_debug_sg] = "scather-gather",
+	[dma_debug_sg] = "scatter-gather",
 	[dma_debug_coherent] = "coherent",
 	[dma_debug_resource] = "resource",
 };
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 9596ae1aa..73c958157 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -220,13 +220,7 @@ 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);
@@ -240,27 +234,24 @@ 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 */
@@ -330,9 +321,7 @@ 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);
@@ -598,6 +587,46 @@ int dma_direct_supported(struct device *dev, u64 mask)
 	return mask >= phys_to_dma_unencrypted(dev, min_mask);
 }
 
+/*
+ * 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;
+	const struct bus_dma_region *bdr = NULL;
+	const struct bus_dma_region *m;
+	struct device *dev = data;
+
+	while (start_pfn < end_pfn) {
+		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)) {
+				bdr = m;
+				break;
+			}
+		}
+		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 */
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index 97ec892ea..18d346118 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -20,6 +20,7 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs);
+bool dma_direct_all_ram_mapped(struct device *dev);
 size_t dma_direct_max_mapping_size(struct device *dev);
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index e323ca48f..58db8fd70 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -793,6 +793,28 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_set_coherent_mask);
 
+/**
+ * dma_addressing_limited - return if the device is addressing limited
+ * @dev:	device to check
+ *
+ * Return %true if the devices DMA mask is too small to address all memory in
+ * the system, else %false.  Lack of addressing bits is the prime reason for
+ * bounce buffering, but might not be the only one.
+ */
+bool dma_addressing_limited(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
+			 dma_get_required_mask(dev))
+		return true;
+
+	if (unlikely(ops))
+		return false;
+	return !dma_direct_all_ram_mapped(dev);
+}
+EXPORT_SYMBOL_GPL(dma_addressing_limited);
+
 size_t dma_max_mapping_size(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 2048194a0..33d942615 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1309,11 +1309,13 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		pool->slots[index + i].orig_addr = slot_addr(orig_addr, i);
 	tlb_addr = slot_addr(pool->start, index) + offset;
 	/*
-	 * When dir == DMA_FROM_DEVICE we could omit the copy from the orig
-	 * to the tlb buffer, if we knew for sure the device will
-	 * overwrite the entire current content. But we don't. Thus
-	 * unconditional bounce may prevent leaking swiotlb content (i.e.
-	 * kernel memory) to user-space.
+	 * When the device is writing memory, i.e. dir == DMA_FROM_DEVICE, copy
+	 * the original buffer to the TLB buffer before initiating DMA in order
+	 * to preserve the original's data if the device does a partial write,
+	 * i.e. if the device doesn't overwrite the entire buffer.  Preserving
+	 * the original data, even if it's garbage, is necessary to match
+	 * hardware behavior.  Use of swiotlb is supposed to be transparent,
+	 * i.e. swiotlb must not corrupt memory by clobbering unwritten bytes.
 	 */
 	swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE);
 	return tlb_addr;