xtensa: reimplement DMA API using common helpers

- keep existing functionality: don't handle attributes, don't support
  high memory;
- implement scatterlist primitives (map/unmap/sync);
- enable DMA API debug.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>

arch/xtensa/Kconfig

@@ -14,6 +14,8 @@ config XTENSA
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
+	select HAVE_DMA_API_DEBUG
+	select HAVE_DMA_ATTRS
 	select HAVE_FUNCTION_TRACER
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_OPROFILE

arch/xtensa/include/asm/Kbuild

@@ -2,7 +2,6 @@ generic-y += bitsperlong.h
 generic-y += bug.h
 generic-y += clkdev.h
 generic-y += cputime.h
-generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += errno.h

arch/xtensa/include/asm/device.h

+/*
+ * Arch specific extensions to struct device
+ *
+ * This file is released under the GPLv2
+ */
+#ifndef _ASM_XTENSA_DEVICE_H
+#define _ASM_XTENSA_DEVICE_H
+
+struct dma_map_ops;
+
+struct dev_archdata {
+	/* DMA operations on that device */
+	struct dma_map_ops *dma_ops;
+};
+
+struct pdev_archdata {
+};
+
+#endif /* _ASM_XTENSA_DEVICE_H */

arch/xtensa/include/asm/dma-mapping.h

 /*
- * include/asm-xtensa/dma-mapping.h
- *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
  * Copyright (C) 2003 - 2005 Tensilica Inc.
+ * Copyright (C) 2015 Cadence Design Systems Inc.
  */
 
 #ifndef _XTENSA_DMA_MAPPING_H
@@ -13,142 +12,67 @@
 
 #include <asm/cache.h>
 #include <asm/io.h>
+
+#include <asm-generic/dma-coherent.h>
+
 #include <linux/mm.h>
 #include <linux/scatterlist.h>
 
 #define DMA_ERROR_CODE		(~(dma_addr_t)0x0)
 
-/*
- * DMA-consistent mapping functions.
- */
-
-extern void *consistent_alloc(int, size_t, dma_addr_t, unsigned long);
-extern void consistent_free(void*, size_t, dma_addr_t);
-extern void consistent_sync(void*, size_t, int);
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flag);
+extern struct dma_map_ops xtensa_dma_map_ops;
 
-void dma_free_coherent(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle);
-
-static inline dma_addr_t
-dma_map_single(struct device *dev, void *ptr, size_t size,
-	       enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-	consistent_sync(ptr, size, direction);
-	return virt_to_phys(ptr);
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction direction)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	BUG_ON(direction == DMA_NONE);
+	if (dev && dev->archdata.dma_ops)
+		return dev->archdata.dma_ops;
+	else
+		return &xtensa_dma_map_ops;
 }
 
-static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
-	   enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	BUG_ON(direction == DMA_NONE);
-
-	for_each_sg(sglist, sg, nents, i) {
-		BUG_ON(!sg_page(sg));
+#include <asm-generic/dma-mapping-common.h>
 
-		sg->dma_address = sg_phys(sg);
-		consistent_sync(sg_virt(sg), sg->length, direction);
-	}
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
+#define dma_free_noncoherent(d, s, v, h) dma_free_attrs(d, s, v, h, NULL)
+#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
+#define dma_free_coherent(d, s, c, h) dma_free_attrs(d, s, c, h, NULL)
 
-	return nents;
-}
-
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-	     size_t size, enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-	return (dma_addr_t)(page_to_pfn(page)) * PAGE_SIZE + offset;
-}
-
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-	       enum dma_data_direction direction)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t gfp,
+				    struct dma_attrs *attrs)
 {
-	BUG_ON(direction == DMA_NONE);
-}
+	void *ret;
+	struct dma_map_ops *ops = get_dma_ops(dev);
 
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &ret))
+		return ret;
 
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-	     enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-}
-
-static inline void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	consistent_sync((void *)bus_to_virt(dma_handle), size, direction);
-}
+	ret = ops->alloc(dev, size, dma_handle, gfp, attrs);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, ret);
 
-static inline void
-dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
-		           size_t size, enum dma_data_direction direction)
-{
-	consistent_sync((void *)bus_to_virt(dma_handle), size, direction);
+	return ret;
 }
 
-static inline void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-		      unsigned long offset, size_t size,
-		      enum dma_data_direction direction)
-{
-
-	consistent_sync((void *)bus_to_virt(dma_handle)+offset,size,direction);
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-		      unsigned long offset, size_t size,
-		      enum dma_data_direction direction)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *vaddr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
+	struct dma_map_ops *ops = get_dma_ops(dev);
 
-	consistent_sync((void *)bus_to_virt(dma_handle)+offset,size,direction);
-}
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems,
-		 enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
+	if (dma_release_from_coherent(dev, get_order(size), vaddr))
+		return;
 
-	for_each_sg(sglist, sg, nelems, i)
-		consistent_sync(sg_virt(sg), sg->length, dir);
+	ops->free(dev, size, vaddr, dma_handle, attrs);
+	debug_dma_free_coherent(dev, size, vaddr, dma_handle);
 }
 
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
-		       int nelems, enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nelems, i)
-		consistent_sync(sg_virt(sg), sg->length, dir);
-}
 static inline int
 dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-	return 0;
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	debug_dma_mapping_error(dev, dma_addr);
+	return ops->mapping_error(dev, dma_addr);
 }
 
 static inline int
@@ -168,39 +92,7 @@ dma_set_mask(struct device *dev, u64 mask)
 	return 0;
 }
 
-static inline void
-dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	       enum dma_data_direction direction)
-{
-	consistent_sync(vaddr, size, direction);
-}
-
-/* Not supported for now */
-static inline int dma_mmap_coherent(struct device *dev,
-				    struct vm_area_struct *vma, void *cpu_addr,
-				    dma_addr_t dma_addr, size_t size)
-{
-	return -EINVAL;
-}
-
-static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size)
-{
-	return -EINVAL;
-}
-
-static inline void *dma_alloc_attrs(struct device *dev, size_t size,
-				    dma_addr_t *dma_handle, gfp_t flag,
-				    struct dma_attrs *attrs)
-{
-	return NULL;
-}
-
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				  void *vaddr, dma_addr_t dma_handle,
-				  struct dma_attrs *attrs)
-{
-}
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		    enum dma_data_direction direction);
 
 #endif	/* _XTENSA_DMA_MAPPING_H */

arch/xtensa/kernel/pci-dma.c

 /*
- * arch/xtensa/kernel/pci-dma.c
- *
  * DMA coherent memory allocation.
  *
  * This program is free software; you can redistribute  it and/or modify it
@@ -9,6 +7,7 @@
  * option) any later version.
  *
  * Copyright (C) 2002 - 2005 Tensilica Inc.
+ * Copyright (C) 2015 Cadence Design Systems Inc.
  *
  * Based on version for i386.
  *
@@ -25,13 +24,107 @@
 #include <asm/io.h>
 #include <asm/cacheflush.h>
 
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		    enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+		__flush_invalidate_dcache_range((unsigned long)vaddr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		__invalidate_dcache_range((unsigned long)vaddr, size);
+		break;
+
+	case DMA_TO_DEVICE:
+		__flush_dcache_range((unsigned long)vaddr, size);
+		break;
+
+	case DMA_NONE:
+		BUG();
+		break;
+	}
+}
+EXPORT_SYMBOL(dma_cache_sync);
+
+static void xtensa_sync_single_for_cpu(struct device *dev,
+				       dma_addr_t dma_handle, size_t size,
+				       enum dma_data_direction dir)
+{
+	void *vaddr;
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+	case DMA_FROM_DEVICE:
+		vaddr = bus_to_virt(dma_handle);
+		__invalidate_dcache_range((unsigned long)vaddr, size);
+		break;
+
+	case DMA_NONE:
+		BUG();
+		break;
+
+	default:
+		break;
+	}
+}
+
+static void xtensa_sync_single_for_device(struct device *dev,
+					  dma_addr_t dma_handle, size_t size,
+					  enum dma_data_direction dir)
+{
+	void *vaddr;
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+	case DMA_TO_DEVICE:
+		vaddr = bus_to_virt(dma_handle);
+		__flush_dcache_range((unsigned long)vaddr, size);
+		break;
+
+	case DMA_NONE:
+		BUG();
+		break;
+
+	default:
+		break;
+	}
+}
+
+static void xtensa_sync_sg_for_cpu(struct device *dev,
+				   struct scatterlist *sg, int nents,
+				   enum dma_data_direction dir)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		xtensa_sync_single_for_cpu(dev, sg_dma_address(s),
+					   sg_dma_len(s), dir);
+	}
+}
+
+static void xtensa_sync_sg_for_device(struct device *dev,
+				      struct scatterlist *sg, int nents,
+				      enum dma_data_direction dir)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		xtensa_sync_single_for_device(dev, sg_dma_address(s),
+					      sg_dma_len(s), dir);
+	}
+}
+
 /*
  * Note: We assume that the full memory space is always mapped to 'kseg'
  *	 Otherwise we have to use page attributes (not implemented).
  */
 
-void *
-dma_alloc_coherent(struct device *dev,size_t size,dma_addr_t *handle,gfp_t flag)
+static void *xtensa_dma_alloc(struct device *dev, size_t size,
+			      dma_addr_t *handle, gfp_t flag,
+			      struct dma_attrs *attrs)
 {
 	unsigned long ret;
 	unsigned long uncached = 0;
@@ -52,20 +145,15 @@ dma_alloc_coherent(struct device *dev,size_t size,dma_addr_t *handle,gfp_t flag)
 	BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR ||
 	       ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
 
+	uncached = ret + XCHAL_KSEG_BYPASS_VADDR - XCHAL_KSEG_CACHED_VADDR;
+	*handle = virt_to_bus((void *)ret);
+	__invalidate_dcache_range(ret, size);
 
-	if (ret != 0) {
-		memset((void*) ret, 0, size);
-		uncached = ret+XCHAL_KSEG_BYPASS_VADDR-XCHAL_KSEG_CACHED_VADDR;
-		*handle = virt_to_bus((void*)ret);
-		__flush_invalidate_dcache_range(ret, size);
-	}
-
-	return (void*)uncached;
+	return (void *)uncached;
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
-void dma_free_coherent(struct device *hwdev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle)
+static void xtensa_dma_free(struct device *hwdev, size_t size, void *vaddr,
+			    dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	unsigned long addr = (unsigned long)vaddr +
 		XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
@@ -75,24 +163,79 @@ void dma_free_coherent(struct device *hwdev, size_t size,
 
 	free_pages(addr, get_order(size));
 }
-EXPORT_SYMBOL(dma_free_coherent);
 
+static dma_addr_t xtensa_map_page(struct device *dev, struct page *page,
+				  unsigned long offset, size_t size,
+				  enum dma_data_direction dir,
+				  struct dma_attrs *attrs)
+{
+	dma_addr_t dma_handle = page_to_phys(page) + offset;
+
+	BUG_ON(PageHighMem(page));
+	xtensa_sync_single_for_device(dev, dma_handle, size, dir);
+	return dma_handle;
+}
 
-void consistent_sync(void *vaddr, size_t size, int direction)
+static void xtensa_unmap_page(struct device *dev, dma_addr_t dma_handle,
+			      size_t size, enum dma_data_direction dir,
+			      struct dma_attrs *attrs)
 {
-	switch (direction) {
-	case PCI_DMA_NONE:
-		BUG();
-	case PCI_DMA_FROMDEVICE:        /* invalidate only */
-		__invalidate_dcache_range((unsigned long)vaddr,
-				          (unsigned long)size);
-		break;
+	xtensa_sync_single_for_cpu(dev, dma_handle, size, dir);
+}
 
-	case PCI_DMA_TODEVICE:          /* writeback only */
-	case PCI_DMA_BIDIRECTIONAL:     /* writeback and invalidate */
-		__flush_invalidate_dcache_range((unsigned long)vaddr,
-				    		(unsigned long)size);
-		break;
+static int xtensa_map_sg(struct device *dev, struct scatterlist *sg,
+			 int nents, enum dma_data_direction dir,
+			 struct dma_attrs *attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		s->dma_address = xtensa_map_page(dev, sg_page(s), s->offset,
+						 s->length, dir, attrs);
+	}
+	return nents;
+}
+
+static void xtensa_unmap_sg(struct device *dev,
+			    struct scatterlist *sg, int nents,
+			    enum dma_data_direction dir,
+			    struct dma_attrs *attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		xtensa_unmap_page(dev, sg_dma_address(s),
+				  sg_dma_len(s), dir, attrs);
 	}
 }
-EXPORT_SYMBOL(consistent_sync);
+
+int xtensa_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return 0;
+}
+
+struct dma_map_ops xtensa_dma_map_ops = {
+	.alloc = xtensa_dma_alloc,
+	.free = xtensa_dma_free,
+	.map_page = xtensa_map_page,
+	.unmap_page = xtensa_unmap_page,
+	.map_sg = xtensa_map_sg,
+	.unmap_sg = xtensa_unmap_sg,
+	.sync_single_for_cpu = xtensa_sync_single_for_cpu,
+	.sync_single_for_device = xtensa_sync_single_for_device,
+	.sync_sg_for_cpu = xtensa_sync_sg_for_cpu,
+	.sync_sg_for_device = xtensa_sync_sg_for_device,
+	.mapping_error = xtensa_dma_mapping_error,
+};
+EXPORT_SYMBOL(xtensa_dma_map_ops);
+
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
+
+static int __init xtensa_dma_init(void)
+{
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+	return 0;
+}
+fs_initcall(xtensa_dma_init);