ARM: integrate CMA with DMA-mapping subsystem

This patch adds support for CMA to dma-mapping subsystem for ARM
architecture. By default a global CMA area is used, but specific devices
are allowed to have their private memory areas if required (they can be
created with dma_declare_contiguous() function during board
initialisation).

Contiguous memory areas reserved for DMA are remapped with 2-level page
tables on boot. Once a buffer is requested, a low memory kernel mapping
is updated to to match requested memory access type.

GFP_ATOMIC allocations are performed from special pool which is created
early during boot. This way remapping page attributes is not needed on
allocation time.

CMA has been enabled unconditionally for ARMv6+ systems.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
CC: Michal Nazarewicz <mina86@mina86.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Rob Clark <rob.clark@linaro.org>
Tested-by: Ohad Ben-Cohen <ohad@wizery.com>
Tested-by: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Tested-by: Robert Nelson <robertcnelson@gmail.com>
Tested-by: Barry Song <Baohua.Song@csr.com>
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index db23ae4..302f5bf 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -17,7 +17,9 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
+#include <linux/memblock.h>
 #include <linux/slab.h>
 
 #include <asm/memory.h>
@@ -26,6 +28,9 @@
 #include <asm/tlbflush.h>
 #include <asm/sizes.h>
 #include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <asm/system_info.h>
+#include <asm/dma-contiguous.h>
 
 #include "mm.h"
 
@@ -56,6 +61,19 @@
 	return mask;
 }
 
+static void __dma_clear_buffer(struct page *page, size_t size)
+{
+	void *ptr;
+	/*
+	 * Ensure that the allocated pages are zeroed, and that any data
+	 * lurking in the kernel direct-mapped region is invalidated.
+	 */
+	ptr = page_address(page);
+	memset(ptr, 0, size);
+	dmac_flush_range(ptr, ptr + size);
+	outer_flush_range(__pa(ptr), __pa(ptr) + size);
+}
+
 /*
  * Allocate a DMA buffer for 'dev' of size 'size' using the
  * specified gfp mask.  Note that 'size' must be page aligned.
@@ -64,23 +82,6 @@
 {
 	unsigned long order = get_order(size);
 	struct page *page, *p, *e;
-	void *ptr;
-	u64 mask = get_coherent_dma_mask(dev);
-
-#ifdef CONFIG_DMA_API_DEBUG
-	u64 limit = (mask + 1) & ~mask;
-	if (limit && size >= limit) {
-		dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n",
-			size, mask);
-		return NULL;
-	}
-#endif
-
-	if (!mask)
-		return NULL;
-
-	if (mask < 0xffffffffULL)
-		gfp |= GFP_DMA;
 
 	page = alloc_pages(gfp, order);
 	if (!page)
@@ -93,14 +94,7 @@
 	for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++)
 		__free_page(p);
 
-	/*
-	 * Ensure that the allocated pages are zeroed, and that any data
-	 * lurking in the kernel direct-mapped region is invalidated.
-	 */
-	ptr = page_address(page);
-	memset(ptr, 0, size);
-	dmac_flush_range(ptr, ptr + size);
-	outer_flush_range(__pa(ptr), __pa(ptr) + size);
+	__dma_clear_buffer(page, size);
 
 	return page;
 }
@@ -170,6 +164,9 @@
 	unsigned long base = consistent_base;
 	unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT;
 
+	if (cpu_architecture() >= CPU_ARCH_ARMv6)
+		return 0;
+
 	consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
 	if (!consistent_pte) {
 		pr_err("%s: no memory\n", __func__);
@@ -210,9 +207,101 @@
 
 	return ret;
 }
-
 core_initcall(consistent_init);
 
+static void *__alloc_from_contiguous(struct device *dev, size_t size,
+				     pgprot_t prot, struct page **ret_page);
+
+static struct arm_vmregion_head coherent_head = {
+	.vm_lock	= __SPIN_LOCK_UNLOCKED(&coherent_head.vm_lock),
+	.vm_list	= LIST_HEAD_INIT(coherent_head.vm_list),
+};
+
+size_t coherent_pool_size = DEFAULT_CONSISTENT_DMA_SIZE / 8;
+
+static int __init early_coherent_pool(char *p)
+{
+	coherent_pool_size = memparse(p, &p);
+	return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+/*
+ * Initialise the coherent pool for atomic allocations.
+ */
+static int __init coherent_init(void)
+{
+	pgprot_t prot = pgprot_dmacoherent(pgprot_kernel);
+	size_t size = coherent_pool_size;
+	struct page *page;
+	void *ptr;
+
+	if (cpu_architecture() < CPU_ARCH_ARMv6)
+		return 0;
+
+	ptr = __alloc_from_contiguous(NULL, size, prot, &page);
+	if (ptr) {
+		coherent_head.vm_start = (unsigned long) ptr;
+		coherent_head.vm_end = (unsigned long) ptr + size;
+		printk(KERN_INFO "DMA: preallocated %u KiB pool for atomic coherent allocations\n",
+		       (unsigned)size / 1024);
+		return 0;
+	}
+	printk(KERN_ERR "DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
+	       (unsigned)size / 1024);
+	return -ENOMEM;
+}
+/*
+ * CMA is activated by core_initcall, so we must be called after it.
+ */
+postcore_initcall(coherent_init);
+
+struct dma_contig_early_reserve {
+	phys_addr_t base;
+	unsigned long size;
+};
+
+static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS] __initdata;
+
+static int dma_mmu_remap_num __initdata;
+
+void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+	dma_mmu_remap[dma_mmu_remap_num].base = base;
+	dma_mmu_remap[dma_mmu_remap_num].size = size;
+	dma_mmu_remap_num++;
+}
+
+void __init dma_contiguous_remap(void)
+{
+	int i;
+	for (i = 0; i < dma_mmu_remap_num; i++) {
+		phys_addr_t start = dma_mmu_remap[i].base;
+		phys_addr_t end = start + dma_mmu_remap[i].size;
+		struct map_desc map;
+		unsigned long addr;
+
+		if (end > arm_lowmem_limit)
+			end = arm_lowmem_limit;
+		if (start >= end)
+			return;
+
+		map.pfn = __phys_to_pfn(start);
+		map.virtual = __phys_to_virt(start);
+		map.length = end - start;
+		map.type = MT_MEMORY_DMA_READY;
+
+		/*
+		 * Clear previous low-memory mapping
+		 */
+		for (addr = __phys_to_virt(start); addr < __phys_to_virt(end);
+		     addr += PGDIR_SIZE)
+			pmd_clear(pmd_off_k(addr));
+
+		iotable_init(&map, 1);
+	}
+}
+
 static void *
 __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
 	const void *caller)
@@ -319,20 +408,173 @@
 	arm_vmregion_free(&consistent_head, c);
 }
 
+static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr,
+			    void *data)
+{
+	struct page *page = virt_to_page(addr);
+	pgprot_t prot = *(pgprot_t *)data;
+
+	set_pte_ext(pte, mk_pte(page, prot), 0);
+	return 0;
+}
+
+static void __dma_remap(struct page *page, size_t size, pgprot_t prot)
+{
+	unsigned long start = (unsigned long) page_address(page);
+	unsigned end = start + size;
+
+	apply_to_page_range(&init_mm, start, size, __dma_update_pte, &prot);
+	dsb();
+	flush_tlb_kernel_range(start, end);
+}
+
+static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
+				 pgprot_t prot, struct page **ret_page,
+				 const void *caller)
+{
+	struct page *page;
+	void *ptr;
+	page = __dma_alloc_buffer(dev, size, gfp);
+	if (!page)
+		return NULL;
+
+	ptr = __dma_alloc_remap(page, size, gfp, prot, caller);
+	if (!ptr) {
+		__dma_free_buffer(page, size);
+		return NULL;
+	}
+
+	*ret_page = page;
+	return ptr;
+}
+
+static void *__alloc_from_pool(struct device *dev, size_t size,
+			       struct page **ret_page, const void *caller)
+{
+	struct arm_vmregion *c;
+	size_t align;
+
+	if (!coherent_head.vm_start) {
+		printk(KERN_ERR "%s: coherent pool not initialised!\n",
+		       __func__);
+		dump_stack();
+		return NULL;
+	}
+
+	/*
+	 * Align the region allocation - allocations from pool are rather
+	 * small, so align them to their order in pages, minimum is a page
+	 * size. This helps reduce fragmentation of the DMA space.
+	 */
+	align = PAGE_SIZE << get_order(size);
+	c = arm_vmregion_alloc(&coherent_head, align, size, 0, caller);
+	if (c) {
+		void *ptr = (void *)c->vm_start;
+		struct page *page = virt_to_page(ptr);
+		*ret_page = page;
+		return ptr;
+	}
+	return NULL;
+}
+
+static int __free_from_pool(void *cpu_addr, size_t size)
+{
+	unsigned long start = (unsigned long)cpu_addr;
+	unsigned long end = start + size;
+	struct arm_vmregion *c;
+
+	if (start < coherent_head.vm_start || end > coherent_head.vm_end)
+		return 0;
+
+	c = arm_vmregion_find_remove(&coherent_head, (unsigned long)start);
+
+	if ((c->vm_end - c->vm_start) != size) {
+		printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
+		       __func__, c->vm_end - c->vm_start, size);
+		dump_stack();
+		size = c->vm_end - c->vm_start;
+	}
+
+	arm_vmregion_free(&coherent_head, c);
+	return 1;
+}
+
+static void *__alloc_from_contiguous(struct device *dev, size_t size,
+				     pgprot_t prot, struct page **ret_page)
+{
+	unsigned long order = get_order(size);
+	size_t count = size >> PAGE_SHIFT;
+	struct page *page;
+
+	page = dma_alloc_from_contiguous(dev, count, order);
+	if (!page)
+		return NULL;
+
+	__dma_clear_buffer(page, size);
+	__dma_remap(page, size, prot);
+
+	*ret_page = page;
+	return page_address(page);
+}
+
+static void __free_from_contiguous(struct device *dev, struct page *page,
+				   size_t size)
+{
+	__dma_remap(page, size, pgprot_kernel);
+	dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
+}
+
+#define nommu() 0
+
 #else	/* !CONFIG_MMU */
 
-#define __dma_alloc_remap(page, size, gfp, prot, c)	page_address(page)
-#define __dma_free_remap(addr, size)			do { } while (0)
+#define nommu() 1
+
+#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c)	NULL
+#define __alloc_from_pool(dev, size, ret_page, c)		NULL
+#define __alloc_from_contiguous(dev, size, prot, ret)		NULL
+#define __free_from_pool(cpu_addr, size)			0
+#define __free_from_contiguous(dev, page, size)			do { } while (0)
+#define __dma_free_remap(cpu_addr, size)			do { } while (0)
 
 #endif	/* CONFIG_MMU */
 
-static void *
-__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
-	    pgprot_t prot, const void *caller)
+static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
+				   struct page **ret_page)
 {
 	struct page *page;
+	page = __dma_alloc_buffer(dev, size, gfp);
+	if (!page)
+		return NULL;
+
+	*ret_page = page;
+	return page_address(page);
+}
+
+
+
+static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+			 gfp_t gfp, pgprot_t prot, const void *caller)
+{
+	u64 mask = get_coherent_dma_mask(dev);
+	struct page *page;
 	void *addr;
 
+#ifdef CONFIG_DMA_API_DEBUG
+	u64 limit = (mask + 1) & ~mask;
+	if (limit && size >= limit) {
+		dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n",
+			size, mask);
+		return NULL;
+	}
+#endif
+
+	if (!mask)
+		return NULL;
+
+	if (mask < 0xffffffffULL)
+		gfp |= GFP_DMA;
+
 	/*
 	 * Following is a work-around (a.k.a. hack) to prevent pages
 	 * with __GFP_COMP being passed to split_page() which cannot
@@ -345,19 +587,17 @@
 	*handle = ~0;
 	size = PAGE_ALIGN(size);
 
-	page = __dma_alloc_buffer(dev, size, gfp);
-	if (!page)
-		return NULL;
-
-	if (!arch_is_coherent())
-		addr = __dma_alloc_remap(page, size, gfp, prot, caller);
+	if (arch_is_coherent() || nommu())
+		addr = __alloc_simple_buffer(dev, size, gfp, &page);
+	else if (cpu_architecture() < CPU_ARCH_ARMv6)
+		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
+	else if (gfp & GFP_ATOMIC)
+		addr = __alloc_from_pool(dev, size, &page, caller);
 	else
-		addr = page_address(page);
+		addr = __alloc_from_contiguous(dev, size, prot, &page);
 
 	if (addr)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
-	else
-		__dma_free_buffer(page, size);
 
 	return addr;
 }
@@ -366,8 +606,8 @@
  * Allocate DMA-coherent memory space and return both the kernel remapped
  * virtual and bus address for that space.
  */
-void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
+void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle,
+			 gfp_t gfp)
 {
 	void *memory;
 
@@ -398,25 +638,11 @@
 {
 	int ret = -ENXIO;
 #ifdef CONFIG_MMU
-	unsigned long user_size, kern_size;
-	struct arm_vmregion *c;
-
-	user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
-
-	c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr);
-	if (c) {
-		unsigned long off = vma->vm_pgoff;
-
-		kern_size = (c->vm_end - c->vm_start) >> PAGE_SHIFT;
-
-		if (off < kern_size &&
-		    user_size <= (kern_size - off)) {
-			ret = remap_pfn_range(vma, vma->vm_start,
-					      page_to_pfn(c->vm_pages) + off,
-					      user_size << PAGE_SHIFT,
-					      vma->vm_page_prot);
-		}
-	}
+	unsigned long pfn = dma_to_pfn(dev, dma_addr);
+	ret = remap_pfn_range(vma, vma->vm_start,
+			      pfn + vma->vm_pgoff,
+			      vma->vm_end - vma->vm_start,
+			      vma->vm_page_prot);
 #endif	/* CONFIG_MMU */
 
 	return ret;
@@ -438,23 +664,33 @@
 }
 EXPORT_SYMBOL(dma_mmap_writecombine);
 
+
 /*
- * free a page as defined by the above mapping.
- * Must not be called with IRQs disabled.
+ * Free a buffer as defined by the above mapping.
  */
 void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle)
 {
-	WARN_ON(irqs_disabled());
+	struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
 
 	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
 		return;
 
 	size = PAGE_ALIGN(size);
 
-	if (!arch_is_coherent())
+	if (arch_is_coherent() || nommu()) {
+		__dma_free_buffer(page, size);
+	} else if (cpu_architecture() < CPU_ARCH_ARMv6) {
 		__dma_free_remap(cpu_addr, size);
-
-	__dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size);
+		__dma_free_buffer(page, size);
+	} else {
+		if (__free_from_pool(cpu_addr, size))
+			return;
+		/*
+		 * Non-atomic allocations cannot be freed with IRQs disabled
+		 */
+		WARN_ON(irqs_disabled());
+		__free_from_contiguous(dev, page, size);
+	}
 }
 EXPORT_SYMBOL(dma_free_coherent);