Merge remote-tracking branch 'lsk/v3.10/topic/arm64-cma' into lsk-v3.10-arm64-dma

14 files changed, 200 insertions, 132 deletions

diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h
index 3ed37b4d93da..4f8e9e5514b1 100644
--- a/arch/arm/include/asm/dma-contiguous.h
+++ b/arch/arm/include/asm/dma-contiguous.h
@@ -2,10 +2,9 @@
 #define ASMARM_DMA_CONTIGUOUS_H
 
 #ifdef __KERNEL__
-#ifdef CONFIG_CMA
+#ifdef CONFIG_DMA_CMA
 
 #include <linux/types.h>
-#include <asm-generic/dma-contiguous.h>
 
 void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ef3e0f3aac96..1fb40dc37ec2 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -358,7 +358,7 @@ static int __init atomic_pool_init(void)
 	if (!pages)
 		goto no_pages;
 
-	if (IS_ENABLED(CONFIG_CMA))
+	if (IS_ENABLED(CONFIG_DMA_CMA))
 		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
 					      atomic_pool_init);
 	else
@@ -670,7 +670,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
 	else if (!(gfp & __GFP_WAIT))
 		addr = __alloc_from_pool(size, &page);
-	else if (!IS_ENABLED(CONFIG_CMA))
+	else if (!IS_ENABLED(CONFIG_DMA_CMA))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
 	else
 		addr = __alloc_from_contiguous(dev, size, prot, &page, caller);
@@ -759,7 +759,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		__dma_free_buffer(page, size);
 	} else if (__free_from_pool(cpu_addr, size)) {
 		return;
-	} else if (!IS_ENABLED(CONFIG_CMA)) {
+	} else if (!IS_ENABLED(CONFIG_DMA_CMA)) {
 		__dma_free_remap(cpu_addr, size);
 		__dma_free_buffer(page, size);
 	} else {
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 56b3f6d447ae..1c650048a4e3 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -21,6 +21,7 @@ config ARM64
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
+	select HAVE_DMA_CONTIGUOUS
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
diff --git a/arch/arm64/include/asm/dma-contiguous.h b/arch/arm64/include/asm/dma-contiguous.h
new file mode 100644
index 000000000000..14c4c0ca7f2a
--- /dev/null
+++ b/arch/arm64/include/asm/dma-contiguous.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (c) 2013, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _ASM_DMA_CONTIGUOUS_H
+#define _ASM_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+#ifdef CONFIG_DMA_CMA
+
+#include <linux/types.h>
+
+static inline void
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
+
+#endif
+#endif
+
+#endif
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index ba0ff75666ee..550873ace597 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -21,6 +21,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-contiguous.h>
 #include <linux/vmalloc.h>
 #include <linux/swiotlb.h>
 
@@ -36,14 +37,40 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 	if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
 		flags |= GFP_DMA32;
-	return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+	if (IS_ENABLED(CONFIG_DMA_CMA)) {
+		struct page *page;
+
+		size = PAGE_ALIGN(size);
+		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
+							get_order(size));
+		if (!page)
+			return NULL;
+
+		*dma_handle = phys_to_dma(dev, page_to_phys(page));
+		return page_address(page);
+	} else {
+		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+	}
 }
 
 static void __dma_free_coherent(struct device *dev, size_t size,
 				void *vaddr, dma_addr_t dma_handle,
 				struct dma_attrs *attrs)
 {
-	swiotlb_free_coherent(dev, size, vaddr, dma_handle);
+	if (dev == NULL) {
+		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
+		return;
+	}
+
+	if (IS_ENABLED(CONFIG_DMA_CMA)) {
+		phys_addr_t paddr = dma_to_phys(dev, dma_handle);
+
+		dma_release_from_contiguous(dev,
+					phys_to_page(paddr),
+					size >> PAGE_SHIFT);
+	} else {
+		swiotlb_free_coherent(dev, size, vaddr, dma_handle);
+	}
 }
 
 static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f497ca77925a..851d3c137e03 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -30,6 +30,7 @@
 #include <linux/memblock.h>
 #include <linux/sort.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-contiguous.h>
 
 #include <asm/prom.h>
 #include <asm/sections.h>
@@ -173,6 +174,8 @@ void __init arm64_memblock_init(void)
 		memblock_reserve(base, size);
 	}
 
+	dma_contiguous_reserve(0);
+
 	memblock_allow_resize();
 	memblock_dump_all();
 }
diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
index c09241659971..b4b38bacb404 100644
--- a/arch/x86/include/asm/dma-contiguous.h
+++ b/arch/x86/include/asm/dma-contiguous.h
@@ -4,7 +4,6 @@
 #ifdef __KERNEL__
 
 #include <linux/types.h>
-#include <asm-generic/dma-contiguous.h>
 
 static inline void
 dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 07abd9d76f7f..10cd80af2aec 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -202,11 +202,9 @@ config DMA_SHARED_BUFFER
 	  APIs extension; the file's descriptor can then be passed on to other
 	  driver.
 
-config CMA
-	bool "Contiguous Memory Allocator"
-	depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK
-	select MIGRATION
-	select MEMORY_ISOLATION
+config DMA_CMA
+	bool "DMA Contiguous Memory Allocator"
+	depends on HAVE_DMA_CONTIGUOUS && CMA
 	help
 	  This enables the Contiguous Memory Allocator which allows drivers
 	  to allocate big physically-contiguous blocks of memory for use with
@@ -215,17 +213,7 @@ config CMA
 	  For more information see <include/linux/dma-contiguous.h>.
 	  If unsure, say "n".
 
-if CMA
-
-config CMA_DEBUG
-	bool "CMA debug messages (DEVELOPMENT)"
-	depends on DEBUG_KERNEL
-	help
-	  Turns on debug messages in CMA.  This produces KERN_DEBUG
-	  messages for every CMA call as well as various messages while
-	  processing calls such as dma_alloc_from_contiguous().
-	  This option does not affect warning and error messages.
-
+if  DMA_CMA
 comment "Default contiguous memory area size:"
 
 config CMA_SIZE_MBYTES
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 4e22ce3ed73d..5d93bb519753 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -6,7 +6,7 @@ obj-y			:= core.o bus.o dd.o syscore.o \
 			   attribute_container.o transport_class.o \
 			   topology.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
-obj-$(CONFIG_CMA) += dma-contiguous.o
+obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
 obj-y			+= power/
 obj-$(CONFIG_HAS_DMA)	+= dma-mapping.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 0ca54421ce97..99802d6f3c60 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -96,7 +96,7 @@ static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
 #endif
 
 /**
- * dma_contiguous_reserve() - reserve area for contiguous memory handling
+ * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
  * @limit: End address of the reserved memory (optional, 0 for any).
  *
  * This function reserves memory from early allocator. It should be
@@ -124,22 +124,29 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 #endif
 	}
 
-	if (selected_size) {
+	if (selected_size && !dma_contiguous_default_area) {
 		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
 			 (unsigned long)selected_size / SZ_1M);
 
-		dma_declare_contiguous(NULL, selected_size, 0, limit);
+		dma_contiguous_reserve_area(selected_size, 0, limit,
+					    &dma_contiguous_default_area);
 	}
 };
 
 static DEFINE_MUTEX(cma_mutex);
 
-static __init int cma_activate_area(unsigned long base_pfn, unsigned long count)
+static int __init cma_activate_area(struct cma *cma)
 {
-	unsigned long pfn = base_pfn;
-	unsigned i = count >> pageblock_order;
+	int bitmap_size = BITS_TO_LONGS(cma->count) * sizeof(long);
+	unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
+	unsigned i = cma->count >> pageblock_order;
 	struct zone *zone;
 
+	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+
+	if (!cma->bitmap)
+		return -ENOMEM;
+
 	WARN_ON_ONCE(!pfn_valid(pfn));
 	zone = page_zone(pfn_to_page(pfn));
 
@@ -153,92 +160,53 @@ static __init int cma_activate_area(unsigned long base_pfn, unsigned long count)
 		}
 		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
 	} while (--i);
-	return 0;
-}
-
-static __init struct cma *cma_create_area(unsigned long base_pfn,
-				     unsigned long count)
-{
-	int bitmap_size = BITS_TO_LONGS(count) * sizeof(long);
-	struct cma *cma;
-	int ret = -ENOMEM;
-
-	pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count);
-
-	cma = kmalloc(sizeof *cma, GFP_KERNEL);
-	if (!cma)
-		return ERR_PTR(-ENOMEM);
-
-	cma->base_pfn = base_pfn;
-	cma->count = count;
-	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
 
-	if (!cma->bitmap)
-		goto no_mem;
-
-	ret = cma_activate_area(base_pfn, count);
-	if (ret)
-		goto error;
-
-	pr_debug("%s: returned %p\n", __func__, (void *)cma);
-	return cma;
-
-error:
-	kfree(cma->bitmap);
-no_mem:
-	kfree(cma);
-	return ERR_PTR(ret);
+	return 0;
 }
 
-static struct cma_reserved {
-	phys_addr_t start;
-	unsigned long size;
-	struct device *dev;
-} cma_reserved[MAX_CMA_AREAS] __initdata;
-static unsigned cma_reserved_count __initdata;
+static struct cma cma_areas[MAX_CMA_AREAS];
+static unsigned cma_area_count;
 
 static int __init cma_init_reserved_areas(void)
 {
-	struct cma_reserved *r = cma_reserved;
-	unsigned i = cma_reserved_count;
-
-	pr_debug("%s()\n", __func__);
+	int i;
 
-	for (; i; --i, ++r) {
-		struct cma *cma;
-		cma = cma_create_area(PFN_DOWN(r->start),
-				      r->size >> PAGE_SHIFT);
-		if (!IS_ERR(cma))
-			dev_set_cma_area(r->dev, cma);
+	for (i = 0; i < cma_area_count; i++) {
+		int ret = cma_activate_area(&cma_areas[i]);
+		if (ret)
+			return ret;
 	}
+
 	return 0;
 }
 core_initcall(cma_init_reserved_areas);
 
 /**
- * dma_declare_contiguous() - reserve area for contiguous memory handling
- *			      for particular device
- * @dev:   Pointer to device structure.
- * @size:  Size of the reserved memory.
- * @base:  Start address of the reserved memory (optional, 0 for any).
+ * dma_contiguous_reserve_area() - reserve custom contiguous area
+ * @size: Size of the reserved area (in bytes),
+ * @base: Base address of the reserved area optional, use 0 for any
  * @limit: End address of the reserved memory (optional, 0 for any).
+ * @res_cma: Pointer to store the created cma region.
  *
- * This function reserves memory for specified device. It should be
- * called by board specific code when early allocator (memblock or bootmem)
- * is still activate.
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory. This function allows to create custom reserved areas for specific
+ * devices.
  */
-int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
-				  phys_addr_t base, phys_addr_t limit)
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+				       phys_addr_t limit, struct cma **res_cma)
 {
-	struct cma_reserved *r = &cma_reserved[cma_reserved_count];
+	struct cma *cma = &cma_areas[cma_area_count];
 	phys_addr_t alignment;
+	int ret = 0;
 
 	pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__,
 		 (unsigned long)size, (unsigned long)base,
 		 (unsigned long)limit);
 
 	/* Sanity checks */
-	if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) {
+	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
 		pr_err("Not enough slots for CMA reserved regions!\n");
 		return -ENOSPC;
 	}
@@ -256,7 +224,7 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 	if (base) {
 		if (memblock_is_region_reserved(base, size) ||
 		    memblock_reserve(base, size) < 0) {
-			base = -EBUSY;
+			ret = -EBUSY;
 			goto err;
 		}
 	} else {
@@ -266,7 +234,7 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 		 */
 		phys_addr_t addr = __memblock_alloc_base(size, alignment, limit);
 		if (!addr) {
-			base = -ENOMEM;
+			ret = -ENOMEM;
 			goto err;
 		} else {
 			base = addr;
@@ -277,10 +245,11 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 	 * Each reserved area must be initialised later, when more kernel
 	 * subsystems (like slab allocator) are available.
 	 */
-	r->start = base;
-	r->size = size;
-	r->dev = dev;
-	cma_reserved_count++;
+	cma->base_pfn = PFN_DOWN(base);
+	cma->count = size >> PAGE_SHIFT;
+	*res_cma = cma;
+	cma_area_count++;
+
 	pr_info("CMA: reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
 		(unsigned long)base);
 
@@ -289,7 +258,7 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 	return 0;
 err:
 	pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
-	return base;
+	return ret;
 }
 
 /**
diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h
deleted file mode 100644
index 294b1e755ab2..000000000000
--- a/include/asm-generic/dma-contiguous.h
+++ /dev/null
@@ -1,28 +0,0 @@
-#ifndef ASM_DMA_CONTIGUOUS_H
-#define ASM_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-#ifdef CONFIG_CMA
-
-#include <linux/device.h>
-#include <linux/dma-contiguous.h>
-
-static inline struct cma *dev_get_cma_area(struct device *dev)
-{
-	if (dev && dev->cma_area)
-		return dev->cma_area;
-	return dma_contiguous_default_area;
-}
-
-static inline void dev_set_cma_area(struct device *dev, struct cma *cma)
-{
-	if (dev)
-		dev->cma_area = cma;
-	if (!dev && !dma_contiguous_default_area)
-		dma_contiguous_default_area = cma;
-}
-
-#endif
-#endif
-
-#endif
diff --git a/include/linux/device.h b/include/linux/device.h
index c0a126125325..d98ec771de42 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -698,7 +698,7 @@ struct device {
 
 	struct dma_coherent_mem	*dma_mem; /* internal for coherent mem
 					     override */
-#ifdef CONFIG_CMA
+#ifdef CONFIG_DMA_CMA
 	struct cma *cma_area;		/* contiguous memory area for dma
 					   allocations */
 #endif
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index 01b5c84be828..3b28f937d959 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -57,7 +57,7 @@ struct cma;
 struct page;
 struct device;
 
-#ifdef CONFIG_CMA
+#ifdef CONFIG_DMA_CMA
 
 /*
  * There is always at least global CMA area and a few optional device
@@ -67,9 +67,53 @@ struct device;
 
 extern struct cma *dma_contiguous_default_area;
 
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	if (dev && dev->cma_area)
+		return dev->cma_area;
+	return dma_contiguous_default_area;
+}
+
+static inline void dev_set_cma_area(struct device *dev, struct cma *cma)
+{
+	if (dev)
+		dev->cma_area = cma;
+}
+
+static inline void dma_contiguous_set_default(struct cma *cma)
+{
+	dma_contiguous_default_area = cma;
+}
+
 void dma_contiguous_reserve(phys_addr_t addr_limit);
-int dma_declare_contiguous(struct device *dev, phys_addr_t size,
-			   phys_addr_t base, phys_addr_t limit);
+
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+				       phys_addr_t limit, struct cma **res_cma);
+
+/**
+ * dma_declare_contiguous() - reserve area for contiguous memory handling
+ *			      for particular device
+ * @dev:   Pointer to device structure.
+ * @size:  Size of the reserved memory.
+ * @base:  Start address of the reserved memory (optional, 0 for any).
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory for specified device. It should be
+ * called by board specific code when early allocator (memblock or bootmem)
+ * is still activate.
+ */
+
+static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size,
+					 phys_addr_t base, phys_addr_t limit)
+{
+	struct cma *cma;
+	int ret;
+	ret = dma_contiguous_reserve_area(size, base, limit, &cma);
+	if (ret == 0)
+		dev_set_cma_area(dev, cma);
+
+	return ret;
+}
 
 struct page *dma_alloc_from_contiguous(struct device *dev, int count,
 				       unsigned int order);
@@ -80,8 +124,22 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 
 #define MAX_CMA_AREAS	(0)
 
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	return NULL;
+}
+
+static inline void dev_set_cma_area(struct device *dev, struct cma *cma) { }
+
+static inline void dma_contiguous_set_default(struct cma *cma) { }
+
 static inline void dma_contiguous_reserve(phys_addr_t limit) { }
 
+static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+				       phys_addr_t limit, struct cma **res_cma) {
+	return -ENOSYS;
+}
+
 static inline
 int dma_declare_contiguous(struct device *dev, phys_addr_t size,
 			   phys_addr_t base, phys_addr_t limit)
diff --git a/mm/Kconfig b/mm/Kconfig
index e742d06285b7..26a5f815cfc3 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -477,3 +477,27 @@ config FRONTSWAP
 	  and swap data is stored as normal on the matching swap device.
 
 	  If unsure, say Y to enable frontswap.
+
+config CMA
+	bool "Contiguous Memory Allocator"
+	depends on HAVE_MEMBLOCK
+	select MIGRATION
+	select MEMORY_ISOLATION
+	help
+	  This enables the Contiguous Memory Allocator which allows other
+	  subsystems to allocate big physically-contiguous blocks of memory.
+	  CMA reserves a region of memory and allows only movable pages to
+	  be allocated from it. This way, the kernel can use the memory for
+	  pagecache and when a subsystem requests for contiguous area, the
+	  allocated pages are migrated away to serve the contiguous request.
+
+	  If unsure, say "n".
+
+config CMA_DEBUG
+	bool "CMA debug messages (DEVELOPMENT)"
+	depends on DEBUG_KERNEL && CMA
+	help
+	  Turns on debug messages in CMA.  This produces KERN_DEBUG
+	  messages for every CMA call as well as various messages while
+	  processing calls such as dma_alloc_from_contiguous().
+	  This option does not affect warning and error messages.