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

arch/arm/mm/init.c

@@ -20,6 +20,7 @@
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
+#include <linux/dma-contiguous.h>
 
 #include <asm/mach-types.h>
 #include <asm/memblock.h>
@@ -226,6 +227,17 @@ static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole,
 }
 #endif
 
+void __init setup_dma_zone(struct machine_desc *mdesc)
+{
+#ifdef CONFIG_ZONE_DMA
+	if (mdesc->dma_zone_size) {
+		arm_dma_zone_size = mdesc->dma_zone_size;
+		arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
+	} else
+		arm_dma_limit = 0xffffffff;
+#endif
+}
+
 static void __init arm_bootmem_free(unsigned long min, unsigned long max_low,
 	unsigned long max_high)
 {
@@ -273,12 +285,9 @@ static void __init arm_bootmem_free(unsigned long min, unsigned long max_low,
 	 * Adjust the sizes according to any special requirements for
 	 * this machine type.
 	 */
-	if (arm_dma_zone_size) {
+	if (arm_dma_zone_size)
 		arm_adjust_dma_zone(zone_size, zhole_size,
 			arm_dma_zone_size >> PAGE_SHIFT);
-		arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
-	} else
-		arm_dma_limit = 0xffffffff;
 #endif
 
 	free_area_init_node(0, zone_size, min, zhole_size);
@@ -364,6 +373,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 	if (mdesc->reserve)
 		mdesc->reserve();
 
+	/*
+	 * reserve memory for DMA contigouos allocations,
+	 * must come from DMA area inside low memory
+	 */
+	dma_contiguous_reserve(min(arm_dma_limit, arm_lowmem_limit));
+
 	arm_memblock_steal_permitted = false;
 	memblock_allow_resize();
 	memblock_dump_all();

arch/arm/mm/mm.h

@@ -67,5 +67,8 @@ extern u32 arm_dma_limit;
 #define arm_dma_limit ((u32)~0)
 #endif
 
+extern phys_addr_t arm_lowmem_limit;
+
 void __init bootmem_init(void);
 void arm_mm_memblock_reserve(void);
+void dma_contiguous_remap(void);

arch/arm/mm/mmu.c

@@ -288,6 +288,11 @@ static struct mem_type mem_types[] = {
 				PMD_SECT_UNCACHED | PMD_SECT_XN,
 		.domain    = DOMAIN_KERNEL,
 	},
+	[MT_MEMORY_DMA_READY] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
+		.prot_l1   = PMD_TYPE_TABLE,
+		.domain    = DOMAIN_KERNEL,
+	},
 };
 
 const struct mem_type *get_mem_type(unsigned int type)
@@ -429,6 +434,7 @@ static void __init build_mem_type_table(void)
 	if (arch_is_coherent() && cpu_is_xsc3()) {
 		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
 		mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+		mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED;
 		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
 		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 	}
@@ -460,6 +466,7 @@ static void __init build_mem_type_table(void)
 			mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
 			mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
 			mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 		}
@@ -512,6 +519,7 @@ static void __init build_mem_type_table(void)
 	mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
 	mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd;
 	mem_types[MT_MEMORY].prot_pte |= kern_pgprot;
+	mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot;
 	mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask;
 	mem_types[MT_ROM].prot_sect |= cp->pmd;
 
@@ -596,7 +604,7 @@ static void __init alloc_init_section(pud_t *pud, unsigned long addr,
 	 * L1 entries, whereas PGDs refer to a group of L1 entries making
 	 * up one logical pointer to an L2 table.
 	 */
-	if (((addr | end | phys) & ~SECTION_MASK) == 0) {
+	if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0) {
 		pmd_t *p = pmd;
 
 #ifndef CONFIG_ARM_LPAE
@@ -814,7 +822,7 @@ static int __init early_vmalloc(char *arg)
 }
 early_param("vmalloc", early_vmalloc);
 
-static phys_addr_t lowmem_limit __initdata = 0;
+phys_addr_t arm_lowmem_limit __initdata = 0;
 
 void __init sanity_check_meminfo(void)
 {
@@ -897,8 +905,8 @@ void __init sanity_check_meminfo(void)
 			bank->size = newsize;
 		}
 #endif
-		if (!bank->highmem && bank->start + bank->size > lowmem_limit)
-			lowmem_limit = bank->start + bank->size;
+		if (!bank->highmem && bank->start + bank->size > arm_lowmem_limit)
+			arm_lowmem_limit = bank->start + bank->size;
 
 		j++;
 	}
@@ -923,8 +931,8 @@ void __init sanity_check_meminfo(void)
 	}
 #endif
 	meminfo.nr_banks = j;
-	high_memory = __va(lowmem_limit - 1) + 1;
-	memblock_set_current_limit(lowmem_limit);
+	high_memory = __va(arm_lowmem_limit - 1) + 1;
+	memblock_set_current_limit(arm_lowmem_limit);
 }
 
 static inline void prepare_page_table(void)
@@ -949,8 +957,8 @@ static inline void prepare_page_table(void)
 	 * Find the end of the first block of lowmem.
 	 */
 	end = memblock.memory.regions[0].base + memblock.memory.regions[0].size;
-	if (end >= lowmem_limit)
-		end = lowmem_limit;
+	if (end >= arm_lowmem_limit)
+		end = arm_lowmem_limit;
 
 	/*
 	 * Clear out all the kernel space mappings, except for the first
@@ -1093,8 +1101,8 @@ static void __init map_lowmem(void)
 		phys_addr_t end = start + reg->size;
 		struct map_desc map;
 
-		if (end > lowmem_limit)
-			end = lowmem_limit;
+		if (end > arm_lowmem_limit)
+			end = arm_lowmem_limit;
 		if (start >= end)
 			break;
 
@@ -1115,11 +1123,12 @@ void __init paging_init(struct machine_desc *mdesc)
 {
 	void *zero_page;
 
-	memblock_set_current_limit(lowmem_limit);
+	memblock_set_current_limit(arm_lowmem_limit);
 
 	build_mem_type_table();
 	prepare_page_table();
 	map_lowmem();
+	dma_contiguous_remap();
 	devicemaps_init(mdesc);
 	kmap_init();
 

arch/arm/mm/vmregion.h

@@ -17,7 +17,7 @@ struct arm_vmregion {
 	struct list_head	vm_list;
 	unsigned long		vm_start;
 	unsigned long		vm_end;
-	struct page		*vm_pages;
+	void			*priv;
 	int			vm_active;
 	const void		*caller;
 };