sh: declared coherent memory support V2

This patch adds declared coherent memory support to the sh architecture. All
functions are based on the x86 implementation. Header files are adjusted to
use the new functions instead of the former consistent_alloc() code.

This version includes the few changes what were included in the fix patch
together with modifications based on feedback from Paul.

Signed-off-by: Magnus Damm <damm@igel.co.jp>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>

2 files changed, 148 insertions, 82 deletions

diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index 65ad300..7b2131c 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -3,6 +3,8 @@
  *
  * Copyright (C) 2004 - 2007  Paul Mundt
  *
+ * Declared coherent memory functions based on arch/x86/kernel/pci-dma_32.c
+ *
  * 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.
@@ -13,66 +15,146 @@
 #include <asm/addrspace.h>
 #include <asm/io.h>
 
-void *consistent_alloc(gfp_t gfp, size_t size, dma_addr_t *handle)
-{
-	struct page *page, *end, *free;
-	void *ret, *vp;
-	int order;
-
-	size = PAGE_ALIGN(size);
-	order = get_order(size);
+struct dma_coherent_mem {
+	void		*virt_base;
+	u32		device_base;
+	int		size;
+	int		flags;
+	unsigned long	*bitmap;
+};
 
-	page = alloc_pages(gfp, order);
-	if (!page)
-		return NULL;
-	split_page(page, order);
+void *dma_alloc_coherent(struct device *dev, size_t size,
+			   dma_addr_t *dma_handle, gfp_t gfp)
+{
+	void *ret;
+	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+	int order = get_order(size);
+
+	if (mem) {
+		int page = bitmap_find_free_region(mem->bitmap, mem->size,
+						     order);
+		if (page >= 0) {
+			*dma_handle = mem->device_base + (page << PAGE_SHIFT);
+			ret = mem->virt_base + (page << PAGE_SHIFT);
+			memset(ret, 0, size);
+			return ret;
+		}
+		if (mem->flags & DMA_MEMORY_EXCLUSIVE)
+			return NULL;
+	}
 
-	ret = page_address(page);
-	*handle = virt_to_phys(ret);
+	ret = (void *)__get_free_pages(gfp, order);
 
-	vp = ioremap_nocache(*handle, size);
-	if (!vp) {
-		free_pages((unsigned long)ret, order);
-		return NULL;
+	if (ret != NULL) {
+		memset(ret, 0, size);
+		/*
+		 * Pages from the page allocator may have data present in
+		 * cache. So flush the cache before using uncached memory.
+		 */
+		dma_cache_sync(NULL, ret, size, DMA_BIDIRECTIONAL);
+		*dma_handle = virt_to_phys(ret);
 	}
+	return ret;
+}
+EXPORT_SYMBOL(dma_alloc_coherent);
 
-	memset(vp, 0, size);
-
-	/*
-	 * We must flush the cache before we pass it on to the device
-	 */
-	dma_cache_sync(NULL, ret, size, DMA_BIDIRECTIONAL);
+void dma_free_coherent(struct device *dev, size_t size,
+			 void *vaddr, dma_addr_t dma_handle)
+{
+	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+	int order = get_order(size);
 
-	page = virt_to_page(ret);
-	free = page + (size >> PAGE_SHIFT);
-	end  = page + (1 << order);
+	if (mem && vaddr >= mem->virt_base && vaddr < (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
 
-	while (++page < end) {
-		/* Free any unused pages */
-		if (page >= free) {
-			__free_page(page);
-		}
+		bitmap_release_region(mem->bitmap, page, order);
+	} else {
+		WARN_ON(irqs_disabled());	/* for portability */
+		BUG_ON(mem && mem->flags & DMA_MEMORY_EXCLUSIVE);
+		free_pages((unsigned long)vaddr, order);
 	}
-
-	return vp;
 }
-EXPORT_SYMBOL(consistent_alloc);
+EXPORT_SYMBOL(dma_free_coherent);
 
-void consistent_free(void *vaddr, size_t size, dma_addr_t dma_handle)
+int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+				dma_addr_t device_addr, size_t size, int flags)
 {
-	struct page *page;
-	unsigned long addr;
-
-	addr = (unsigned long)phys_to_virt((unsigned long)dma_handle);
-	page = virt_to_page(addr);
+	void __iomem *mem_base = NULL;
+	int pages = size >> PAGE_SHIFT;
+	int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
+
+	if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
+		goto out;
+	if (!size)
+		goto out;
+	if (dev->dma_mem)
+		goto out;
+
+	/* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
+
+	mem_base = ioremap_nocache(bus_addr, size);
+	if (!mem_base)
+		goto out;
+
+	dev->dma_mem = kmalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+	if (!dev->dma_mem)
+		goto out;
+	dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!dev->dma_mem->bitmap)
+		goto free1_out;
+
+	dev->dma_mem->virt_base = mem_base;
+	dev->dma_mem->device_base = device_addr;
+	dev->dma_mem->size = pages;
+	dev->dma_mem->flags = flags;
+
+	if (flags & DMA_MEMORY_MAP)
+		return DMA_MEMORY_MAP;
+
+	return DMA_MEMORY_IO;
+
+ free1_out:
+	kfree(dev->dma_mem);
+ out:
+	if (mem_base)
+		iounmap(mem_base);
+	return 0;
+}
+EXPORT_SYMBOL(dma_declare_coherent_memory);
 
-	free_pages(addr, get_order(size));
+void dma_release_declared_memory(struct device *dev)
+{
+	struct dma_coherent_mem *mem = dev->dma_mem;
+
+	if (!mem)
+		return;
+	dev->dma_mem = NULL;
+	iounmap(mem->virt_base);
+	kfree(mem->bitmap);
+	kfree(mem);
+}
+EXPORT_SYMBOL(dma_release_declared_memory);
 
-	iounmap(vaddr);
+void *dma_mark_declared_memory_occupied(struct device *dev,
+					dma_addr_t device_addr, size_t size)
+{
+	struct dma_coherent_mem *mem = dev->dma_mem;
+	int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	int pos, err;
+
+	if (!mem)
+		return ERR_PTR(-EINVAL);
+
+	pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
+	err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages));
+	if (err != 0)
+		return ERR_PTR(err);
+	return mem->virt_base + (pos << PAGE_SHIFT);
 }
-EXPORT_SYMBOL(consistent_free);
+EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
 
-void consistent_sync(void *vaddr, size_t size, int direction)
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		    enum dma_data_direction direction)
 {
 #ifdef CONFIG_CPU_SH5
 	void *p1addr = vaddr;
@@ -94,4 +176,4 @@ void consistent_sync(void *vaddr, size_t size, int direction)
 		BUG();
 	}
 }
-EXPORT_SYMBOL(consistent_sync);
+EXPORT_SYMBOL(dma_cache_sync);
diff --git a/include/asm-sh/dma-mapping.h b/include/asm-sh/dma-mapping.h
index 20ae762..22cc419 100644
--- a/include/asm-sh/dma-mapping.h
+++ b/include/asm-sh/dma-mapping.h
@@ -8,11 +8,6 @@
 
 extern struct bus_type pci_bus_type;
 
-/* arch/sh/mm/consistent.c */
-extern void *consistent_alloc(gfp_t gfp, size_t size, dma_addr_t *handle);
-extern void consistent_free(void *vaddr, size_t size, dma_addr_t handle);
-extern void consistent_sync(void *vaddr, size_t size, int direction);
-
 #define dma_supported(dev, mask)	(1)
 
 static inline int dma_set_mask(struct device *dev, u64 mask)
@@ -25,44 +20,19 @@ static inline int dma_set_mask(struct device *dev, u64 mask)
 	return 0;
 }
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *dma_handle, gfp_t flag)
-{
-	if (sh_mv.mv_consistent_alloc) {
-		void *ret;
+void *dma_alloc_coherent(struct device *dev, size_t size,
+			 dma_addr_t *dma_handle, gfp_t flag);
 
-		ret = sh_mv.mv_consistent_alloc(dev, size, dma_handle, flag);
-		if (ret != NULL)
-			return ret;
-	}
-
-	return consistent_alloc(flag, size, dma_handle);
-}
-
-static inline void dma_free_coherent(struct device *dev, size_t size,
-		       void *vaddr, dma_addr_t dma_handle)
-{
-	if (sh_mv.mv_consistent_free) {
-		int ret;
-
-		ret = sh_mv.mv_consistent_free(dev, size, vaddr, dma_handle);
-		if (ret == 0)
-			return;
-	}
+void dma_free_coherent(struct device *dev, size_t size,
+		       void *vaddr, dma_addr_t dma_handle);
 
-	consistent_free(vaddr, size, dma_handle);
-}
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		    enum dma_data_direction dir);
 
 #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)
 #define dma_is_consistent(d, h) (1)
 
-static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-				  enum dma_data_direction dir)
-{
-	consistent_sync(vaddr, size, (int)dir);
-}
-
 static inline dma_addr_t dma_map_single(struct device *dev,
 					void *ptr, size_t size,
 					enum dma_data_direction dir)
@@ -205,4 +175,18 @@ static inline int dma_mapping_error(dma_addr_t dma_addr)
 {
 	return dma_addr == 0;
 }
+
+#define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
+
+extern int
+dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+			    dma_addr_t device_addr, size_t size, int flags);
+
+extern void
+dma_release_declared_memory(struct device *dev);
+
+extern void *
+dma_mark_declared_memory_occupied(struct device *dev,
+				  dma_addr_t device_addr, size_t size);
+
 #endif /* __ASM_SH_DMA_MAPPING_H */