drivers: add Contiguous Memory Allocator

The Contiguous Memory Allocator is a set of helper functions for DMA
mapping framework that improves allocations of contiguous memory chunks.

CMA grabs memory on system boot, marks it with MIGRATE_CMA migrate type
and gives back to the system. Kernel is allowed to allocate only movable
pages within CMA's managed memory so that it can be used for example for
page cache when DMA mapping do not use it. On
dma_alloc_from_contiguous() request such pages are migrated out of CMA
area to free required contiguous block and fulfill the request. This
allows to allocate large contiguous chunks of memory at any time
assuming that there is enough free memory available in the system.

This code is heavily based on earlier works by Michal Nazarewicz.

Signed-off-by: Marek Szyprowski <[e-mail]>
Signed-off-by: Kyungmin Park <[e-mail]>
Signed-off-by: Michal Nazarewicz <[e-mail]>
Acked-by: Arnd Bergmann <[e-mail]>
Tested-by: Rob Clark <[e-mail]>
Tested-by: Ohad Ben-Cohen <[e-mail]>
Tested-by: Benjamin Gaignard <[e-mail]>
Tested-by: Robert Nelson <[e-mail]>
Tested-by: Barry Song <[e-mail]>

Documentation/kernel-parameters.txt

···
 			Also note the kernel might malfunction if you disable
 			some critical bits.
 
+	cma=nn[MG]	[ARM,KNL]
+			Sets the size of kernel global memory area for contiguous
+			memory allocations. For more information, see
+			include/linux/dma-contiguous.h
+
 	cmo_free_hint=	[PPC] Format: { yes | no }
 			Specify whether pages are marked as being inactive
 			when they are freed.  This is used in CMO environments

arch/Kconfig

···
 config HAVE_DMA_ATTRS
 	bool
 
+config HAVE_DMA_CONTIGUOUS
+	bool
+
 config USE_GENERIC_SMP_HELPERS
 	bool
 

drivers/base/Kconfig

···
 	  APIs extension; the file's descriptor can then be passed on to other
 	  driver.
 
+config CMA
+	bool "Contiguous Memory Allocator (EXPERIMENTAL)"
+	depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK && EXPERIMENTAL
+	select MIGRATION
+	help
+	  This enables the Contiguous Memory Allocator which allows drivers
+	  to allocate big physically-contiguous blocks of memory for use with
+	  hardware components that do not support I/O map nor scatter-gather.
+
+	  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.
+
+comment "Default contiguous memory area size:"
+
+config CMA_SIZE_MBYTES
+	int "Size in Mega Bytes"
+	depends on !CMA_SIZE_SEL_PERCENTAGE
+	default 16
+	help
+	  Defines the size (in MiB) of the default memory area for Contiguous
+	  Memory Allocator.
+
+config CMA_SIZE_PERCENTAGE
+	int "Percentage of total memory"
+	depends on !CMA_SIZE_SEL_MBYTES
+	default 10
+	help
+	  Defines the size of the default memory area for Contiguous Memory
+	  Allocator as a percentage of the total memory in the system.
+
+choice
+	prompt "Selected region size"
+	default CMA_SIZE_SEL_ABSOLUTE
+
+config CMA_SIZE_SEL_MBYTES
+	bool "Use mega bytes value only"
+
+config CMA_SIZE_SEL_PERCENTAGE
+	bool "Use percentage value only"
+
+config CMA_SIZE_SEL_MIN
+	bool "Use lower value (minimum)"
+
+config CMA_SIZE_SEL_MAX
+	bool "Use higher value (maximum)"
+
+endchoice
+
+config CMA_ALIGNMENT
+	int "Maximum PAGE_SIZE order of alignment for contiguous buffers"
+	range 4 9
+	default 8
+	help
+	  DMA mapping framework by default aligns all buffers to the smallest
+	  PAGE_SIZE order which is greater than or equal to the requested buffer
+	  size. This works well for buffers up to a few hundreds kilobytes, but
+	  for larger buffers it just a memory waste. With this parameter you can
+	  specify the maximum PAGE_SIZE order for contiguous buffers. Larger
+	  buffers will be aligned only to this specified order. The order is
+	  expressed as a power of two multiplied by the PAGE_SIZE.
+
+	  For example, if your system defaults to 4KiB pages, the order value
+	  of 8 means that the buffers will be aligned up to 1MiB only.
+
+	  If unsure, leave the default value "8".
+
+config CMA_AREAS
+	int "Maximum count of the CMA device-private areas"
+	default 7
+	help
+	  CMA allows to create CMA areas for particular devices. This parameter
+	  sets the maximum number of such device private CMA areas in the
+	  system.
+
+	  If unsure, leave the default value "7".
+
+endif
+
 endmenu

drivers/base/Makefile

···
 			   attribute_container.o transport_class.o \
 			   topology.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
+obj-$(CONFIG_CMA) += dma-contiguous.o
 obj-y			+= power/
 obj-$(CONFIG_HAS_DMA)	+= dma-mapping.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o

drivers/base/dma-contiguous.c

···
+/*
+ * Contiguous Memory Allocator for DMA mapping framework
+ * Copyright (c) 2010-2011 by Samsung Electronics.
+ * Written by:
+ *	Marek Szyprowski <[e-mail]>
+ *	Michal Nazarewicz <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ */
+
+#define pr_fmt(fmt) "cma: " fmt
+
+#ifdef CONFIG_CMA_DEBUG
+#ifndef DEBUG
+#  define DEBUG
+#endif
+#endif
+
+#include <asm/page.h>
+#include <asm/dma-contiguous.h>
+
+#include <linux/memblock.h>
+#include <linux/err.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/page-isolation.h>
+#include <linux/slab.h>
+#include <linux/swap.h>
+#include <linux/mm_types.h>
+#include <linux/dma-contiguous.h>
+
+#ifndef SZ_1M
+#define SZ_1M (1 << 20)
+#endif
+
+struct cma {
+	unsigned long	base_pfn;
+	unsigned long	count;
+	unsigned long	*bitmap;
+};
+
+struct cma *dma_contiguous_default_area;
+
+#ifdef CONFIG_CMA_SIZE_MBYTES
+#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
+#else
+#define CMA_SIZE_MBYTES 0
+#endif
+
+/*
+ * Default global CMA area size can be defined in kernel's .config.
+ * This is usefull mainly for distro maintainers to create a kernel
+ * that works correctly for most supported systems.
+ * The size can be set in bytes or as a percentage of the total memory
+ * in the system.
+ *
+ * Users, who want to set the size of global CMA area for their system
+ * should use cma= kernel parameter.
+ */
+static const unsigned long size_bytes = CMA_SIZE_MBYTES * SZ_1M;
+static long size_cmdline = -1;
+
+static int __init early_cma(char *p)
+{
+	pr_debug("%s(%s)\n", __func__, p);
+	size_cmdline = memparse(p, &p);
+	return 0;
+}
+early_param("cma", early_cma);
+
+#ifdef CONFIG_CMA_SIZE_PERCENTAGE
+
+static unsigned long __init __maybe_unused cma_early_percent_memory(void)
+{
+	struct memblock_region *reg;
+	unsigned long total_pages = 0;
+
+	/*
+	 * We cannot use memblock_phys_mem_size() here, because
+	 * memblock_analyze() has not been called yet.
+	 */
+	for_each_memblock(memory, reg)
+		total_pages += memblock_region_memory_end_pfn(reg) -
+			       memblock_region_memory_base_pfn(reg);
+
+	return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT;
+}
+
+#else
+
+static inline __maybe_unused unsigned long cma_early_percent_memory(void)
+{
+	return 0;
+}
+
+#endif
+
+/**
+ * dma_contiguous_reserve() - reserve area 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
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory.
+ */
+void __init dma_contiguous_reserve(phys_addr_t limit)
+{
+	unsigned long selected_size = 0;
+
+	pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
+
+	if (size_cmdline != -1) {
+		selected_size = size_cmdline;
+	} else {
+#ifdef CONFIG_CMA_SIZE_SEL_MBYTES
+		selected_size = size_bytes;
+#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE)
+		selected_size = cma_early_percent_memory();
+#elif defined(CONFIG_CMA_SIZE_SEL_MIN)
+		selected_size = min(size_bytes, cma_early_percent_memory());
+#elif defined(CONFIG_CMA_SIZE_SEL_MAX)
+		selected_size = max(size_bytes, cma_early_percent_memory());
+#endif
+	}
+
+	if (selected_size) {
+		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
+			 selected_size / SZ_1M);
+
+		dma_declare_contiguous(NULL, selected_size, 0, limit);
+	}
+};
+
+static DEFINE_MUTEX(cma_mutex);
+
+static __init int cma_activate_area(unsigned long base_pfn, unsigned long count)
+{
+	unsigned long pfn = base_pfn;
+	unsigned i = count >> pageblock_order;
+	struct zone *zone;
+
+	WARN_ON_ONCE(!pfn_valid(pfn));
+	zone = page_zone(pfn_to_page(pfn));
+
+	do {
+		unsigned j;
+		base_pfn = pfn;
+		for (j = pageblock_nr_pages; j; --j, pfn++) {
+			WARN_ON_ONCE(!pfn_valid(pfn));
+			if (page_zone(pfn_to_page(pfn)) != zone)
+				return -EINVAL;
+		}
+		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);
+}
+
+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 int __init cma_init_reserved_areas(void)
+{
+	struct cma_reserved *r = cma_reserved;
+	unsigned i = cma_reserved_count;
+
+	pr_debug("%s()\n", __func__);
+
+	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);
+	}
+	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).
+ * @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.
+ */
+int __init dma_declare_contiguous(struct device *dev, unsigned long size,
+				  phys_addr_t base, phys_addr_t limit)
+{
+	struct cma_reserved *r = &cma_reserved[cma_reserved_count];
+	unsigned long alignment;
+
+	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)) {
+		pr_err("Not enough slots for CMA reserved regions!\n");
+		return -ENOSPC;
+	}
+
+	if (!size)
+		return -EINVAL;
+
+	/* Sanitise input arguments */
+	alignment = PAGE_SIZE << max(MAX_ORDER, pageblock_order);
+	base = ALIGN(base, alignment);
+	size = ALIGN(size, alignment);
+	limit &= ~(alignment - 1);
+
+	/* Reserve memory */
+	if (base) {
+		if (memblock_is_region_reserved(base, size) ||
+		    memblock_reserve(base, size) < 0) {
+			base = -EBUSY;
+			goto err;
+		}
+	} else {
+		/*
+		 * Use __memblock_alloc_base() since
+		 * memblock_alloc_base() panic()s.
+		 */
+		phys_addr_t addr = __memblock_alloc_base(size, alignment, limit);
+		if (!addr) {
+			base = -ENOMEM;
+			goto err;
+		} else if (addr + size > ~(unsigned long)0) {
+			memblock_free(addr, size);
+			base = -EINVAL;
+			goto err;
+		} else {
+			base = addr;
+		}
+	}
+
+	/*
+	 * 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++;
+	pr_info("CMA: reserved %ld MiB at %08lx\n", size / SZ_1M,
+		(unsigned long)base);
+
+	/* Architecture specific contiguous memory fixup. */
+	dma_contiguous_early_fixup(base, size);
+	return 0;
+err:
+	pr_err("CMA: failed to reserve %ld MiB\n", size / SZ_1M);
+	return base;
+}
+
+/**
+ * dma_alloc_from_contiguous() - allocate pages from contiguous area
+ * @dev:   Pointer to device for which the allocation is performed.
+ * @count: Requested number of pages.
+ * @align: Requested alignment of pages (in PAGE_SIZE order).
+ *
+ * This function allocates memory buffer for specified device. It uses
+ * device specific contiguous memory area if available or the default
+ * global one. Requires architecture specific get_dev_cma_area() helper
+ * function.
+ */
+struct page *dma_alloc_from_contiguous(struct device *dev, int count,
+				       unsigned int align)
+{
+	unsigned long mask, pfn, pageno, start = 0;
+	struct cma *cma = dev_get_cma_area(dev);
+	int ret;
+
+	if (!cma || !cma->count)
+		return NULL;
+
+	if (align > CONFIG_CMA_ALIGNMENT)
+		align = CONFIG_CMA_ALIGNMENT;
+
+	pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma,
+		 count, align);
+
+	if (!count)
+		return NULL;
+
+	mask = (1 << align) - 1;
+
+	mutex_lock(&cma_mutex);
+
+	for (;;) {
+		pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count,
+						    start, count, mask);
+		if (pageno >= cma->count) {
+			ret = -ENOMEM;
+			goto error;
+		}
+
+		pfn = cma->base_pfn + pageno;
+		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
+		if (ret == 0) {
+			bitmap_set(cma->bitmap, pageno, count);
+			break;
+		} else if (ret != -EBUSY) {
+			goto error;
+		}
+		pr_debug("%s(): memory range at %p is busy, retrying\n",
+			 __func__, pfn_to_page(pfn));
+		/* try again with a bit different memory target */
+		start = pageno + mask + 1;
+	}
+
+	mutex_unlock(&cma_mutex);
+
+	pr_debug("%s(): returned %p\n", __func__, pfn_to_page(pfn));
+	return pfn_to_page(pfn);
+error:
+	mutex_unlock(&cma_mutex);
+	return NULL;
+}
+
+/**
+ * dma_release_from_contiguous() - release allocated pages
+ * @dev:   Pointer to device for which the pages were allocated.
+ * @pages: Allocated pages.
+ * @count: Number of allocated pages.
+ *
+ * This function releases memory allocated by dma_alloc_from_contiguous().
+ * It returns false when provided pages do not belong to contiguous area and
+ * true otherwise.
+ */
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count)
+{
+	struct cma *cma = dev_get_cma_area(dev);
+	unsigned long pfn;
+
+	if (!cma || !pages)
+		return false;
+
+	pr_debug("%s(page %p)\n", __func__, (void *)pages);
+
+	pfn = page_to_pfn(pages);
+
+	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
+		return false;
+
+	VM_BUG_ON(pfn + count > cma->base_pfn + cma->count);
+
+	mutex_lock(&cma_mutex);
+	bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count);
+	free_contig_range(pfn, count);
+	mutex_unlock(&cma_mutex);
+
+	return true;
+}

include/asm-generic/dma-contiguous.h

···
+#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

include/linux/device.h

···
 
 	struct dma_coherent_mem	*dma_mem; /* internal for coherent mem
 					     override */
+#ifdef CONFIG_CMA
+	struct cma *cma_area;		/* contiguous memory area for dma
+					   allocations */
+#endif
 	/* arch specific additions */
 	struct dev_archdata	archdata;
 

include/linux/dma-contiguous.h

···
+#ifndef __LINUX_CMA_H
+#define __LINUX_CMA_H
+
+/*
+ * Contiguous Memory Allocator for DMA mapping framework
+ * Copyright (c) 2010-2011 by Samsung Electronics.
+ * Written by:
+ *	Marek Szyprowski <[e-mail]>
+ *	Michal Nazarewicz <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ */
+
+/*
+ * Contiguous Memory Allocator
+ *
+ *   The Contiguous Memory Allocator (CMA) makes it possible to
+ *   allocate big contiguous chunks of memory after the system has
+ *   booted.
+ *
+ * Why is it needed?
+ *
+ *   Various devices on embedded systems have no scatter-getter and/or
+ *   IO map support and require contiguous blocks of memory to
+ *   operate.  They include devices such as cameras, hardware video
+ *   coders, etc.
+ *
+ *   Such devices often require big memory buffers (a full HD frame
+ *   is, for instance, more then 2 mega pixels large, i.e. more than 6
+ *   MB of memory), which makes mechanisms such as kmalloc() or
+ *   alloc_page() ineffective.
+ *
+ *   At the same time, a solution where a big memory region is
+ *   reserved for a device is suboptimal since often more memory is
+ *   reserved then strictly required and, moreover, the memory is
+ *   inaccessible to page system even if device drivers don't use it.
+ *
+ *   CMA tries to solve this issue by operating on memory regions
+ *   where only movable pages can be allocated from.  This way, kernel
+ *   can use the memory for pagecache and when device driver requests
+ *   it, allocated pages can be migrated.
+ *
+ * Driver usage
+ *
+ *   CMA should not be used by the device drivers directly. It is
+ *   only a helper framework for dma-mapping subsystem.
+ *
+ *   For more information, see kernel-docs in drivers/base/dma-contiguous.c
+ */
+
+#ifdef __KERNEL__
+
+struct cma;
+struct page;
+struct device;
+
+#ifdef CONFIG_CMA
+
+/*
+ * There is always at least global CMA area and a few optional device
+ * private areas configured in kernel .config.
+ */
+#define MAX_CMA_AREAS	(1 + CONFIG_CMA_AREAS)
+
+extern struct cma *dma_contiguous_default_area;
+
+void dma_contiguous_reserve(phys_addr_t addr_limit);
+int dma_declare_contiguous(struct device *dev, unsigned long size,
+			   phys_addr_t base, phys_addr_t limit);
+
+struct page *dma_alloc_from_contiguous(struct device *dev, int count,
+				       unsigned int order);
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count);
+
+#else
+
+#define MAX_CMA_AREAS	(0)
+
+static inline void dma_contiguous_reserve(phys_addr_t limit) { }
+
+static inline
+int dma_declare_contiguous(struct device *dev, unsigned long size,
+			   phys_addr_t base, phys_addr_t limit)
+{
+	return -ENOSYS;
+}
+
+static inline
+struct page *dma_alloc_from_contiguous(struct device *dev, int count,
+				       unsigned int order)
+{
+	return NULL;
+}
+
+static inline
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count)
+{
+	return false;
+}
+
+#endif
+
+#endif
+
+#endif