Merge branch 'for-linus' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping

Pull CMA and ARM DMA-mapping updates from Marek Szyprowski:
 "These patches contain two major updates for DMA mapping subsystem
  (mainly for ARM architecture).  First one is Contiguous Memory
  Allocator (CMA) which makes it possible for device drivers to allocate
  big contiguous chunks of memory after the system has booted.

  The main difference from the similar frameworks is the fact that CMA
  allows to transparently reuse the memory region reserved for the big
  chunk allocation as a system memory, so no memory is wasted when no
  big chunk is allocated.  Once the alloc request is issued, the
  framework migrates system pages to create space for the required big
  chunk of physically contiguous memory.

  For more information one can refer to nice LWN articles:

   - 'A reworked contiguous memory allocator':
		http://lwn.net/Articles/447405/

   - 'CMA and ARM':
		http://lwn.net/Articles/450286/

   - 'A deep dive into CMA':
		http://lwn.net/Articles/486301/

   - and the following thread with the patches and links to all previous
     versions:
		https://lkml.org/lkml/2012/4/3/204

  The main client for this new framework is ARM DMA-mapping subsystem.

  The second part provides a complete redesign in ARM DMA-mapping
  subsystem.  The core implementation has been changed to use common
  struct dma_map_ops based infrastructure with the recent updates for
  new dma attributes merged in v3.4-rc2.  This allows to use more than
  one implementation of dma-mapping calls and change/select them on the
  struct device basis.  The first client of this new infractructure is
  dmabounce implementation which has been completely cut out of the
  core, common code.

  The last patch of this redesign update introduces a new, experimental
  implementation of dma-mapping calls on top of generic IOMMU framework.
  This lets ARM sub-platform to transparently use IOMMU for DMA-mapping
  calls if one provides required IOMMU hardware.

  For more information please refer to the following thread:
		http://www.spinics.net/lists/arm-kernel/msg175729.html

  The last patch merges changes from both updates and provides a
  resolution for the conflicts which cannot be avoided when patches have
  been applied on the same files (mainly arch/arm/mm/dma-mapping.c)."

Acked by Andrew Morton <akpm@linux-foundation.org>:
 "Yup, this one please.  It's had much work, plenty of review and I
  think even Russell is happy with it."

* 'for-linus' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping: (28 commits)
  ARM: dma-mapping: use PMD size for section unmap
  cma: fix migration mode
  ARM: integrate CMA with DMA-mapping subsystem
  X86: integrate CMA with DMA-mapping subsystem
  drivers: add Contiguous Memory Allocator
  mm: trigger page reclaim in alloc_contig_range() to stabilise watermarks
  mm: extract reclaim code from __alloc_pages_direct_reclaim()
  mm: Serialize access to min_free_kbytes
  mm: page_isolation: MIGRATE_CMA isolation functions added
  mm: mmzone: MIGRATE_CMA migration type added
  mm: page_alloc: change fallbacks array handling
  mm: page_alloc: introduce alloc_contig_range()
  mm: compaction: export some of the functions
  mm: compaction: introduce isolate_freepages_range()
  mm: compaction: introduce map_pages()
  mm: compaction: introduce isolate_migratepages_range()
  mm: page_alloc: remove trailing whitespace
  ARM: dma-mapping: add support for IOMMU mapper
  ARM: dma-mapping: use alloc, mmap, free from dma_ops
  ARM: dma-mapping: remove redundant code and do the cleanup
  ...

Conflicts:
	arch/x86/include/asm/dma-mapping.h

7 files changed, 206 insertions, 17 deletions

diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h
index 85a3ffaa0242..abfb2682de7f 100644
--- a/include/asm-generic/dma-coherent.h
+++ b/include/asm-generic/dma-coherent.h
@@ -3,13 +3,15 @@
 
 #ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
 /*
- * These two functions are only for dma allocator.
+ * These three functions are only for dma allocator.
  * Don't use them in device drivers.
  */
 int dma_alloc_from_coherent(struct device *dev, ssize_t size,
                                        dma_addr_t *dma_handle, void **ret);
 int dma_release_from_coherent(struct device *dev, int order, void *vaddr);
 
+int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
+                            void *cpu_addr, size_t size, int *ret);
 /*
  * Standard interface
  */
diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h
new file mode 100644
index 000000000000..c544356b374b
--- /dev/null
+++ b/include/asm-generic/dma-contiguous.h
@@ -0,0 +1,28 @@
+#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 e04f5776f6d0..161d96241b1b 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -667,6 +667,10 @@ struct device {
 
         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;
 
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
new file mode 100644
index 000000000000..2f303e4b7ed3
--- /dev/null
+++ b/include/linux/dma-contiguous.h
@@ -0,0 +1,110 @@
+#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 <m.szyprowski@samsung.com>
+ *      Michal Nazarewicz <mina86@mina86.com>
+ *
+ * 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
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 581e74b7df95..1e49be49d324 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -391,4 +391,16 @@ static inline bool pm_suspended_storage(void)
 }
 #endif /* CONFIG_PM_SLEEP */
 
+#ifdef CONFIG_CMA
+
+/* The below functions must be run on a range from a single zone. */
+extern int alloc_contig_range(unsigned long start, unsigned long end,
+                              unsigned migratetype);
+extern void free_contig_range(unsigned long pfn, unsigned nr_pages);
+
+/* CMA stuff */
+extern void init_cma_reserved_pageblock(struct page *page);
+
+#endif
+
 #endif /* __LINUX_GFP_H */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 41aa49b74821..4871e31ae277 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -35,13 +35,39 @@
  */
 #define PAGE_ALLOC_COSTLY_ORDER 3
 
-#define MIGRATE_UNMOVABLE     0
-#define MIGRATE_RECLAIMABLE   1
-#define MIGRATE_MOVABLE       2
-#define MIGRATE_PCPTYPES      3 /* the number of types on the pcp lists */
-#define MIGRATE_RESERVE       3
-#define MIGRATE_ISOLATE       4 /* can't allocate from here */
-#define MIGRATE_TYPES         5
+enum {
+        MIGRATE_UNMOVABLE,
+        MIGRATE_RECLAIMABLE,
+        MIGRATE_MOVABLE,
+        MIGRATE_PCPTYPES,       /* the number of types on the pcp lists */
+        MIGRATE_RESERVE = MIGRATE_PCPTYPES,
+#ifdef CONFIG_CMA
+        /*
+         * MIGRATE_CMA migration type is designed to mimic the way
+         * ZONE_MOVABLE works.  Only movable pages can be allocated
+         * from MIGRATE_CMA pageblocks and page allocator never
+         * implicitly change migration type of MIGRATE_CMA pageblock.
+         *
+         * The way to use it is to change migratetype of a range of
+         * pageblocks to MIGRATE_CMA which can be done by
+         * __free_pageblock_cma() function.  What is important though
+         * is that a range of pageblocks must be aligned to
+         * MAX_ORDER_NR_PAGES should biggest page be bigger then
+         * a single pageblock.
+         */
+        MIGRATE_CMA,
+#endif
+        MIGRATE_ISOLATE,        /* can't allocate from here */
+        MIGRATE_TYPES
+};
+
+#ifdef CONFIG_CMA
+#  define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
+#  define cma_wmark_pages(zone) zone->min_cma_pages
+#else
+#  define is_migrate_cma(migratetype) false
+#  define cma_wmark_pages(zone) 0
+#endif
 
 #define for_each_migratetype_order(order, type) \
         for (order = 0; order < MAX_ORDER; order++) \
@@ -347,6 +373,13 @@ struct zone {
         /* see spanned/present_pages for more description */
         seqlock_t               span_seqlock;
 #endif
+#ifdef CONFIG_CMA
+        /*
+         * CMA needs to increase watermark levels during the allocation
+         * process to make sure that the system is not starved.
+         */
+        unsigned long           min_cma_pages;
+#endif
         struct free_area        free_area[MAX_ORDER];
 
 #ifndef CONFIG_SPARSEMEM
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 051c1b1ede4e..3bdcab30ca41 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -3,7 +3,7 @@
 
 /*
  * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE.
- * If specified range includes migrate types other than MOVABLE,
+ * If specified range includes migrate types other than MOVABLE or CMA,
  * this will fail with -EBUSY.
  *
  * For isolating all pages in the range finally, the caller have to
@@ -11,27 +11,27 @@
  * test it.
  */
 extern int
-start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn);
+start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
+                         unsigned migratetype);
 
 /*
  * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE.
  * target range is [start_pfn, end_pfn)
  */
 extern int
-undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn);
+undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
+                        unsigned migratetype);
 
 /*
- * test all pages in [start_pfn, end_pfn)are isolated or not.
+ * Test all pages in [start_pfn, end_pfn) are isolated or not.
  */
-extern int
-test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn);
+int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn);
 
 /*
- * Internal funcs.Changes pageblock's migrate type.
- * Please use make_pagetype_isolated()/make_pagetype_movable().
+ * Internal functions. Changes pageblock's migrate type.
  */
 extern int set_migratetype_isolate(struct page *page);
-extern void unset_migratetype_isolate(struct page *page);
+extern void unset_migratetype_isolate(struct page *page, unsigned migratetype);
 
 
 #endif