Merge tag 'dma-mapping-6.7-2023-10-30' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - get rid of the fake support for coherent DMA allocation on coldfire
   with caches (Christoph Hellwig)

 - add a few Kconfig dependencies so that Kconfig catches the use of
   invalid configurations (Christoph Hellwig)

 - fix a type in dma-debug output (Chuck Lever)

 - rewrite a comment in swiotlb (Sean Christopherson)

* tag 'dma-mapping-6.7-2023-10-30' of git://git.infradead.org/users/hch/dma-mapping:
  dma-debug: Fix a typo in a debugging eye-catcher
  swiotlb: rewrite comment explaining why the source is preserved on DMA_FROM_DEVICE
  m68k: remove unused includes from dma.c
  m68k: don't provide arch_dma_alloc for nommu/coldfire
  net: fec: use dma_alloc_noncoherent for data cache enabled coldfire
  m68k: use the coherent DMA code for coldfire without data cache
  dma-direct: warn when coherent allocations aren't supported
  dma-direct: simplify the use atomic pool logic in dma_direct_alloc
  dma-direct: add a CONFIG_ARCH_HAS_DMA_ALLOC symbol
  dma-direct: add dependencies to CONFIG_DMA_GLOBAL_POOL

4 files changed, 32 insertions, 30 deletions

diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index f488997b0717..d62f5957f36b 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 06366acd27b0..3de494375b7b 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 9596ae1aa0da..ed3056eb20b8 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);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index dff067bd56b1..26202274784f 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1301,11 +1301,13 @@ 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;