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

arch/arm/Kconfig

@@ -8,6 +8,7 @@ config ARM
 	select ARCH_HAS_CPU_FINALIZE_INIT if MMU
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL if MMU
+	select ARCH_HAS_DMA_ALLOC if MMU
 	select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE

arch/m68k/Kconfig

@@ -6,15 +6,15 @@ config M68K
 	select ARCH_HAS_BINFMT_FLAT
 	select ARCH_HAS_CPU_FINALIZE_INIT if MMU
 	select ARCH_HAS_CURRENT_STACK_POINTER
-	select ARCH_HAS_DMA_PREP_COHERENT if HAS_DMA && MMU && !COLDFIRE
-	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA
+	select ARCH_HAS_DMA_PREP_COHERENT if M68K_NONCOHERENT_DMA && !COLDFIRE
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if M68K_NONCOHERENT_DMA
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS
 	select ARCH_MIGHT_HAVE_PC_PARPORT if ISA
 	select ARCH_NO_PREEMPT if !COLDFIRE
 	select ARCH_USE_MEMTEST if MMU_MOTOROLA
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BINFMT_FLAT_ARGVP_ENVP_ON_STACK
-	select DMA_DIRECT_REMAP if HAS_DMA && MMU && !COLDFIRE
+	select DMA_DIRECT_REMAP if M68K_NONCOHERENT_DMA && !COLDFIRE
 	select GENERIC_ATOMIC64
 	select GENERIC_CPU_DEVICES
 	select GENERIC_IOMAP

arch/m68k/Kconfig.cpu

@@ -535,3 +535,15 @@ config CACHE_COPYBACK
 	  The ColdFire CPU cache is set into Copy-back mode.
 endchoice
 endif # HAVE_CACHE_CB
+
+# Coldfire cores that do not have a data cache configured can do coherent DMA.
+config COLDFIRE_COHERENT_DMA
+	bool
+	default y
+	depends on COLDFIRE
+	depends on !HAVE_CACHE_CB && !CACHE_D && !CACHE_BOTH
+
+config M68K_NONCOHERENT_DMA
+	bool
+	default y
+	depends on HAS_DMA && !COLDFIRE_COHERENT_DMA

arch/m68k/kernel/Makefile

@@ -23,7 +23,7 @@ obj-$(CONFIG_MMU_MOTOROLA) += ints.o vectors.o
 obj-$(CONFIG_MMU_SUN3) += ints.o vectors.o
 obj-$(CONFIG_PCI) += pcibios.o
 
-obj-$(CONFIG_HAS_DMA)	+= dma.o
+obj-$(CONFIG_M68K_NONCOHERENT_DMA) += dma.o
 
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_BOOTINFO_PROC)	+= bootinfo_proc.o

arch/m68k/kernel/dma.c

@@ -4,20 +4,11 @@
  * for more details.
  */
 
-#undef DEBUG
-
 #include <linux/dma-map-ops.h>
-#include <linux/device.h>
 #include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/scatterlist.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-#include <linux/export.h>
-
 #include <asm/cacheflush.h>
 
-#if defined(CONFIG_MMU) && !defined(CONFIG_COLDFIRE)
+#ifndef CONFIG_COLDFIRE
 void arch_dma_prep_coherent(struct page *page, size_t size)
 {
 	cache_push(page_to_phys(page), size);
@@ -33,29 +24,6 @@ pgprot_t pgprot_dmacoherent(pgprot_t prot)
 	}
 	return prot;
 }
-#else
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp, unsigned long attrs)
-{
-	void *ret;
-
-	if (dev == NULL || (*dev->dma_mask < 0xffffffff))
-		gfp |= GFP_DMA;
-	ret = (void *)__get_free_pages(gfp, get_order(size));
-
-	if (ret != NULL) {
-		memset(ret, 0, size);
-		*dma_handle = virt_to_phys(ret);
-	}
-	return ret;
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-}
-
 #endif /* CONFIG_MMU && !CONFIG_COLDFIRE */
 
 void arch_sync_dma_for_device(phys_addr_t handle, size_t size,

arch/parisc/Kconfig

@@ -8,6 +8,7 @@ config PARISC
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_SYSCALL_TRACEPOINTS
 	select ARCH_WANT_FRAME_POINTERS
+	select ARCH_HAS_DMA_ALLOC if PA11
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX

drivers/net/ethernet/freescale/fec_main.c

@@ -363,6 +363,70 @@ static void fec_dump(struct net_device *ndev)
 	} while (bdp != txq->bd.base);
 }
 
+/*
+ * Coldfire does not support DMA coherent allocations, and has historically used
+ * a band-aid with a manual flush in fec_enet_rx_queue.
+ */
+#if defined(CONFIG_COLDFIRE) && !defined(CONFIG_COLDFIRE_COHERENT_DMA)
+static void *fec_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		gfp_t gfp)
+{
+	return dma_alloc_noncoherent(dev, size, handle, DMA_BIDIRECTIONAL, gfp);
+}
+
+static void fec_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t handle)
+{
+	dma_free_noncoherent(dev, size, cpu_addr, handle, DMA_BIDIRECTIONAL);
+}
+#else /* !CONFIG_COLDFIRE || CONFIG_COLDFIRE_COHERENT_DMA */
+static void *fec_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		gfp_t gfp)
+{
+	return dma_alloc_coherent(dev, size, handle, gfp);
+}
+
+static void fec_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t handle)
+{
+	dma_free_coherent(dev, size, cpu_addr, handle);
+}
+#endif /* !CONFIG_COLDFIRE || CONFIG_COLDFIRE_COHERENT_DMA */
+
+struct fec_dma_devres {
+	size_t		size;
+	void		*vaddr;
+	dma_addr_t	dma_handle;
+};
+
+static void fec_dmam_release(struct device *dev, void *res)
+{
+	struct fec_dma_devres *this = res;
+
+	fec_dma_free(dev, this->size, this->vaddr, this->dma_handle);
+}
+
+static void *fec_dmam_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		gfp_t gfp)
+{
+	struct fec_dma_devres *dr;
+	void *vaddr;
+
+	dr = devres_alloc(fec_dmam_release, sizeof(*dr), gfp);
+	if (!dr)
+		return NULL;
+	vaddr = fec_dma_alloc(dev, size, handle, gfp);
+	if (!vaddr) {
+		devres_free(dr);
+		return NULL;
+	}
+	dr->vaddr = vaddr;
+	dr->dma_handle = *handle;
+	dr->size = size;
+	devres_add(dev, dr);
+	return vaddr;
+}
+
 static inline bool is_ipv4_pkt(struct sk_buff *skb)
 {
 	return skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->version == 4;
@@ -1617,7 +1681,11 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 	}
 #endif
 
-#ifdef CONFIG_M532x
+#if defined(CONFIG_COLDFIRE) && !defined(CONFIG_COLDFIRE_COHERENT_DMA)
+	/*
+	 * Hacky flush of all caches instead of using the DMA API for the TSO
+	 * headers.
+	 */
 	flush_cache_all();
 #endif
 	rxq = fep->rx_queue[queue_id];
@@ -3243,10 +3311,9 @@ static void fec_enet_free_queue(struct net_device *ndev)
 	for (i = 0; i < fep->num_tx_queues; i++)
 		if (fep->tx_queue[i] && fep->tx_queue[i]->tso_hdrs) {
 			txq = fep->tx_queue[i];
-			dma_free_coherent(&fep->pdev->dev,
-					  txq->bd.ring_size * TSO_HEADER_SIZE,
-					  txq->tso_hdrs,
-					  txq->tso_hdrs_dma);
+			fec_dma_free(&fep->pdev->dev,
+				     txq->bd.ring_size * TSO_HEADER_SIZE,
+				     txq->tso_hdrs, txq->tso_hdrs_dma);
 		}
 
 	for (i = 0; i < fep->num_rx_queues; i++)
@@ -3276,10 +3343,9 @@ static int fec_enet_alloc_queue(struct net_device *ndev)
 		txq->tx_stop_threshold = FEC_MAX_SKB_DESCS;
 		txq->tx_wake_threshold = FEC_MAX_SKB_DESCS + 2 * MAX_SKB_FRAGS;
 
-		txq->tso_hdrs = dma_alloc_coherent(&fep->pdev->dev,
+		txq->tso_hdrs = fec_dma_alloc(&fep->pdev->dev,
 					txq->bd.ring_size * TSO_HEADER_SIZE,
-					&txq->tso_hdrs_dma,
-					GFP_KERNEL);
+					&txq->tso_hdrs_dma, GFP_KERNEL);
 		if (!txq->tso_hdrs) {
 			ret = -ENOMEM;
 			goto alloc_failed;
@@ -3998,8 +4064,8 @@ static int fec_enet_init(struct net_device *ndev)
 	bd_size = (fep->total_tx_ring_size + fep->total_rx_ring_size) * dsize;
 
 	/* Allocate memory for buffer descriptors. */
-	cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma,
-				       GFP_KERNEL);
+	cbd_base = fec_dmam_alloc(&fep->pdev->dev, bd_size, &bd_dma,
+				  GFP_KERNEL);
 	if (!cbd_base) {
 		ret = -ENOMEM;
 		goto free_queue_mem;

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

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",
 };

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);

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;