dma-direct: merge swiotlb_dma_ops into the dma_direct code

While the dma-direct code is (relatively) clean and simple we actually
have to use the swiotlb ops for the mapping on many architectures due
to devices with addressing limits.  Instead of keeping two
implementations around this commit allows the dma-direct
implementation to call the swiotlb bounce buffering functions and
thus share the guts of the mapping implementation.  This also
simplified the dma-mapping setup on a few architectures where we
don't have to differenciate which implementation to use.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Tony Luck <tony.luck@intel.com>

2 files changed, 94 insertions, 251 deletions

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index d45306473c90..85d8286a0ba2 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -13,6 +13,7 @@
 #include <linux/dma-noncoherent.h>
 #include <linux/pfn.h>
 #include <linux/set_memory.h>
+#include <linux/swiotlb.h>
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but
@@ -209,69 +210,110 @@ void dma_direct_free(struct device *dev, size_t size,
 		dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
 }
 
-static void dma_direct_sync_single_for_device(struct device *dev,
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_single_for_device(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
-	if (dev_is_dma_coherent(dev))
-		return;
-	arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir);
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
+
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_device(dev, paddr, size, dir);
 }
 
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE)
-static void dma_direct_sync_sg_for_device(struct device *dev,
+void dma_direct_sync_sg_for_device(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev))
-		return;
+	for_each_sg(sgl, sg, nents, i) {
+		if (unlikely(is_swiotlb_buffer(sg_phys(sg))))
+			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length,
+					dir, SYNC_FOR_DEVICE);
 
-	for_each_sg(sgl, sg, nents, i)
-		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+		if (!dev_is_dma_coherent(dev))
+			arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
+					dir);
+	}
 }
 #endif
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
-static void dma_direct_sync_single_for_cpu(struct device *dev,
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_single_for_cpu(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
-	if (dev_is_dma_coherent(dev))
-		return;
-	arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
-	arch_sync_dma_for_cpu_all(dev);
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (!dev_is_dma_coherent(dev)) {
+		arch_sync_dma_for_cpu(dev, paddr, size, dir);
+		arch_sync_dma_for_cpu_all(dev);
+	}
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
 }
 
-static void dma_direct_sync_sg_for_cpu(struct device *dev,
+void dma_direct_sync_sg_for_cpu(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev))
-		return;
+	for_each_sg(sgl, sg, nents, i) {
+		if (!dev_is_dma_coherent(dev))
+			arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+	
+		if (unlikely(is_swiotlb_buffer(sg_phys(sg))))
+			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, dir,
+					SYNC_FOR_CPU);
+	}
 
-	for_each_sg(sgl, sg, nents, i)
-		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
-	arch_sync_dma_for_cpu_all(dev);
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_cpu_all(dev);
 }
 
-static void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
+	phys_addr_t phys = dma_to_phys(dev, addr);
+
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+
+	if (unlikely(is_swiotlb_buffer(phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
 }
 
-static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir,
+			     attrs);
+}
+#else
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir);
 }
 #endif
 
+static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr,
+		size_t size)
+{
+	return swiotlb_force != SWIOTLB_FORCE &&
+		(!dev || dma_capable(dev, dma_addr, size));
+}
+
 dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir,
 		unsigned long attrs)
@@ -279,13 +321,14 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 	phys_addr_t phys = page_to_phys(page) + offset;
 	dma_addr_t dma_addr = phys_to_dma(dev, phys);
 
-	if (unlikely(dev && !dma_capable(dev, dma_addr, size))) {
+	if (unlikely(!dma_direct_possible(dev, dma_addr, size)) &&
+	    !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) {
 		report_addr(dev, dma_addr, size);
 		return DMA_MAPPING_ERROR;
 	}
 
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_single_for_device(dev, dma_addr, size, dir);
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(dev, phys, size, dir);
 	return dma_addr;
 }
 
@@ -299,11 +342,15 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
 				sg->offset, sg->length, dir, attrs);
 		if (sg->dma_address == DMA_MAPPING_ERROR)
-			return 0;
+			goto out_unmap;
 		sg_dma_len(sg) = sg->length;
 	}
 
 	return nents;
+
+out_unmap:
+	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
+	return 0;
 }
 
 /*
@@ -331,12 +378,14 @@ const struct dma_map_ops dma_direct_ops = {
 	.free			= dma_direct_free,
 	.map_page		= dma_direct_map_page,
 	.map_sg			= dma_direct_map_sg,
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE)
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
 	.sync_single_for_device	= dma_direct_sync_single_for_device,
 	.sync_sg_for_device	= dma_direct_sync_sg_for_device,
 #endif
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
 	.sync_single_for_cpu	= dma_direct_sync_single_for_cpu,
 	.sync_sg_for_cpu	= dma_direct_sync_sg_for_cpu,
 	.unmap_page		= dma_direct_unmap_page,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 2e126bac5d7d..d6361776dc5c 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -21,7 +21,6 @@
 
 #include <linux/cache.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
@@ -65,7 +64,7 @@ enum swiotlb_force swiotlb_force;
  * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
  * API.
  */
-static phys_addr_t io_tlb_start, io_tlb_end;
+phys_addr_t io_tlb_start, io_tlb_end;
 
 /*
  * The number of IO TLB blocks (in groups of 64) between io_tlb_start and
@@ -383,11 +382,6 @@ void __init swiotlb_exit(void)
 	max_segment = 0;
 }
 
-static int is_swiotlb_buffer(phys_addr_t paddr)
-{
-	return paddr >= io_tlb_start && paddr < io_tlb_end;
-}
-
 /*
  * Bounce: copy the swiotlb buffer back to the original dma location
  */
@@ -623,221 +617,36 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 	}
 }
 
-static dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys,
+/*
+ * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing
+ * to the device copy the data into it as well.
+ */
+bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	dma_addr_t dma_addr;
+	trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force);
 
 	if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) {
 		dev_warn_ratelimited(dev,
 			"Cannot do DMA to address %pa\n", phys);
-		return DMA_MAPPING_ERROR;
+		return false;
 	}
 
 	/* Oh well, have to allocate and map a bounce buffer. */
 	*phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
 			*phys, size, dir, attrs);
 	if (*phys == DMA_MAPPING_ERROR)
-		return DMA_MAPPING_ERROR;
+		return false;
 
 	/* Ensure that the address returned is DMA'ble */
-	dma_addr = __phys_to_dma(dev, *phys);
-	if (unlikely(!dma_capable(dev, dma_addr, size))) {
+	*dma_addr = __phys_to_dma(dev, *phys);
+	if (unlikely(!dma_capable(dev, *dma_addr, size))) {
 		swiotlb_tbl_unmap_single(dev, *phys, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
-		return DMA_MAPPING_ERROR;
-	}
-
-	return dma_addr;
-}
-
-/*
- * Map a single buffer of the indicated size for DMA in streaming mode.  The
- * physical address to use is returned.
- *
- * Once the device is given the dma address, the device owns this memory until
- * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
- */
-dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
-			    unsigned long offset, size_t size,
-			    enum dma_data_direction dir,
-			    unsigned long attrs)
-{
-	phys_addr_t phys = page_to_phys(page) + offset;
-	dma_addr_t dev_addr = phys_to_dma(dev, phys);
-
-	BUG_ON(dir == DMA_NONE);
-	/*
-	 * If the address happens to be in the device's DMA window,
-	 * we can safely return the device addr and not worry about bounce
-	 * buffering it.
-	 */
-	if (!dma_capable(dev, dev_addr, size) ||
-	    swiotlb_force == SWIOTLB_FORCE) {
-		trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
-		dev_addr = swiotlb_bounce_page(dev, &phys, size, dir, attrs);
+		return false;
 	}
 
-	if (!dev_is_dma_coherent(dev) &&
-	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0 &&
-	    dev_addr != DMA_MAPPING_ERROR)
-		arch_sync_dma_for_device(dev, phys, size, dir);
-
-	return dev_addr;
-}
-
-/*
- * Unmap a single streaming mode DMA translation.  The dma_addr and size must
- * match what was provided for in a previous swiotlb_map_page call.  All
- * other usages are undefined.
- *
- * After this call, reads by the cpu to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
-			size_t size, enum dma_data_direction dir,
-			unsigned long attrs)
-{
-	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
-
-	BUG_ON(dir == DMA_NONE);
-
-	if (!dev_is_dma_coherent(hwdev) &&
-	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		arch_sync_dma_for_cpu(hwdev, paddr, size, dir);
-
-	if (is_swiotlb_buffer(paddr))
-		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
-}
-
-/*
- * Make physical memory consistent for a single streaming mode DMA translation
- * after a transfer.
- *
- * If you perform a swiotlb_map_page() but wish to interrogate the buffer
- * using the cpu, yet do not wish to teardown the dma mapping, you must
- * call this function before doing so.  At the next point you give the dma
- * address back to the card, you must first perform a
- * swiotlb_dma_sync_for_device, and then the device again owns the buffer
- */
-static void
-swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
-		    size_t size, enum dma_data_direction dir,
-		    enum dma_sync_target target)
-{
-	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
-
-	BUG_ON(dir == DMA_NONE);
-
-	if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_CPU)
-		arch_sync_dma_for_cpu(hwdev, paddr, size, dir);
-
-	if (is_swiotlb_buffer(paddr))
-		swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
-
-	if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_DEVICE)
-		arch_sync_dma_for_device(hwdev, paddr, size, dir);
-}
-
-void
-swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
-			    size_t size, enum dma_data_direction dir)
-{
-	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
-}
-
-void
-swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
-			       size_t size, enum dma_data_direction dir)
-{
-	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
-}
-
-/*
- * Map a set of buffers described by scatterlist in streaming mode for DMA.
- * This is the scatter-gather version of the above swiotlb_map_page
- * interface.  Here the scatter gather list elements are each tagged with the
- * appropriate dma address and length.  They are obtained via
- * sg_dma_{address,length}(SG).
- *
- * Device ownership issues as mentioned above for swiotlb_map_page are the
- * same here.
- */
-int
-swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems,
-		     enum dma_data_direction dir, unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nelems, i) {
-		sg->dma_address = swiotlb_map_page(dev, sg_page(sg), sg->offset,
-				sg->length, dir, attrs);
-		if (sg->dma_address == DMA_MAPPING_ERROR)
-			goto out_error;
-		sg_dma_len(sg) = sg->length;
-	}
-
-	return nelems;
-
-out_error:
-	swiotlb_unmap_sg_attrs(dev, sgl, i, dir,
-			attrs | DMA_ATTR_SKIP_CPU_SYNC);
-	sg_dma_len(sgl) = 0;
-	return 0;
-}
-
-/*
- * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_page() above.
- */
-void
-swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
-		       int nelems, enum dma_data_direction dir,
-		       unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	BUG_ON(dir == DMA_NONE);
-
-	for_each_sg(sgl, sg, nelems, i)
-		swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg), dir,
-			     attrs);
-}
-
-/*
- * Make physical memory consistent for a set of streaming mode DMA translations
- * after a transfer.
- *
- * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
- * and usage.
- */
-static void
-swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
-		int nelems, enum dma_data_direction dir,
-		enum dma_sync_target target)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nelems, i)
-		swiotlb_sync_single(hwdev, sg->dma_address,
-				    sg_dma_len(sg), dir, target);
-}
-
-void
-swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-			int nelems, enum dma_data_direction dir)
-{
-	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
-}
-
-void
-swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
-			   int nelems, enum dma_data_direction dir)
-{
-	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
+	return true;
 }
 
 /*
@@ -851,18 +660,3 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
 	return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
 }
-
-const struct dma_map_ops swiotlb_dma_ops = {
-	.alloc			= dma_direct_alloc,
-	.free			= dma_direct_free,
-	.sync_single_for_cpu	= swiotlb_sync_single_for_cpu,
-	.sync_single_for_device	= swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu	= swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device	= swiotlb_sync_sg_for_device,
-	.map_sg			= swiotlb_map_sg_attrs,
-	.unmap_sg		= swiotlb_unmap_sg_attrs,
-	.map_page		= swiotlb_map_page,
-	.unmap_page		= swiotlb_unmap_page,
-	.dma_supported		= dma_direct_supported,
-};
-EXPORT_SYMBOL(swiotlb_dma_ops);