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

1 files changed, 363 insertions, 46 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1851df600438..bab8e3bc4202 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -57,6 +57,7 @@
 #include <linux/ftrace_event.h>
 #include <linux/memcontrol.h>
 #include <linux/prefetch.h>
+#include <linux/migrate.h>
 #include <linux/page-debug-flags.h>
 
 #include <asm/tlbflush.h>
@@ -513,10 +514,10 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
  * free pages of length of (1 << order) and marked with _mapcount -2. Page's
  * order is recorded in page_private(page) field.
  * So when we are allocating or freeing one, we can derive the state of the
- * other.  That is, if we allocate a small block, and both were   
- * free, the remainder of the region must be split into blocks.   
+ * other.  That is, if we allocate a small block, and both were
+ * free, the remainder of the region must be split into blocks.
  * If a block is freed, and its buddy is also free, then this
- * triggers coalescing into a block of larger size.            
+ * triggers coalescing into a block of larger size.
  *
  * -- wli
  */
@@ -749,6 +750,24 @@ void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
 	__free_pages(page, order);
 }
 
+#ifdef CONFIG_CMA
+/* Free whole pageblock and set it's migration type to MIGRATE_CMA. */
+void __init init_cma_reserved_pageblock(struct page *page)
+{
+	unsigned i = pageblock_nr_pages;
+	struct page *p = page;
+
+	do {
+		__ClearPageReserved(p);
+		set_page_count(p, 0);
+	} while (++p, --i);
+
+	set_page_refcounted(page);
+	set_pageblock_migratetype(page, MIGRATE_CMA);
+	__free_pages(page, pageblock_order);
+	totalram_pages += pageblock_nr_pages;
+}
+#endif
 
 /*
  * The order of subdivision here is critical for the IO subsystem.
@@ -874,11 +893,17 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
  * This array describes the order lists are fallen back to when
  * the free lists for the desirable migrate type are depleted
  */
-static int fallbacks[MIGRATE_TYPES][MIGRATE_TYPES-1] = {
-	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,   MIGRATE_RESERVE },
-	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,   MIGRATE_RESERVE },
-	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
-	[MIGRATE_RESERVE]     = { MIGRATE_RESERVE,     MIGRATE_RESERVE,   MIGRATE_RESERVE }, /* Never used */
+static int fallbacks[MIGRATE_TYPES][4] = {
+	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,     MIGRATE_RESERVE },
+	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,     MIGRATE_RESERVE },
+#ifdef CONFIG_CMA
+	[MIGRATE_MOVABLE]     = { MIGRATE_CMA,         MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
+	[MIGRATE_CMA]         = { MIGRATE_RESERVE }, /* Never used */
+#else
+	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE,   MIGRATE_RESERVE },
+#endif
+	[MIGRATE_RESERVE]     = { MIGRATE_RESERVE }, /* Never used */
+	[MIGRATE_ISOLATE]     = { MIGRATE_RESERVE }, /* Never used */
 };
 
 /*
@@ -973,12 +998,12 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 	/* Find the largest possible block of pages in the other list */
 	for (current_order = MAX_ORDER-1; current_order >= order;
 						--current_order) {
-		for (i = 0; i < MIGRATE_TYPES - 1; i++) {
+		for (i = 0;; i++) {
 			migratetype = fallbacks[start_migratetype][i];
 
 			/* MIGRATE_RESERVE handled later if necessary */
 			if (migratetype == MIGRATE_RESERVE)
-				continue;
+				break;
 
 			area = &(zone->free_area[current_order]);
 			if (list_empty(&area->free_list[migratetype]))
@@ -993,11 +1018,18 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 			 * pages to the preferred allocation list. If falling
 			 * back for a reclaimable kernel allocation, be more
 			 * aggressive about taking ownership of free pages
+			 *
+			 * On the other hand, never change migration
+			 * type of MIGRATE_CMA pageblocks nor move CMA
+			 * pages on different free lists. We don't
+			 * want unmovable pages to be allocated from
+			 * MIGRATE_CMA areas.
 			 */
-			if (unlikely(current_order >= (pageblock_order >> 1)) ||
-					start_migratetype == MIGRATE_RECLAIMABLE ||
-					page_group_by_mobility_disabled) {
-				unsigned long pages;
+			if (!is_migrate_cma(migratetype) &&
+			    (unlikely(current_order >= pageblock_order / 2) ||
+			     start_migratetype == MIGRATE_RECLAIMABLE ||
+			     page_group_by_mobility_disabled)) {
+				int pages;
 				pages = move_freepages_block(zone, page,
 								start_migratetype);
 
@@ -1015,11 +1047,14 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 			rmv_page_order(page);
 
 			/* Take ownership for orders >= pageblock_order */
-			if (current_order >= pageblock_order)
+			if (current_order >= pageblock_order &&
+			    !is_migrate_cma(migratetype))
 				change_pageblock_range(page, current_order,
 							start_migratetype);
 
-			expand(zone, page, order, current_order, area, migratetype);
+			expand(zone, page, order, current_order, area,
+			       is_migrate_cma(migratetype)
+			     ? migratetype : start_migratetype);
 
 			trace_mm_page_alloc_extfrag(page, order, current_order,
 				start_migratetype, migratetype);
@@ -1061,17 +1096,17 @@ retry_reserve:
 	return page;
 }
 
-/* 
+/*
  * Obtain a specified number of elements from the buddy allocator, all under
  * a single hold of the lock, for efficiency.  Add them to the supplied list.
  * Returns the number of new pages which were placed at *list.
  */
-static int rmqueue_bulk(struct zone *zone, unsigned int order, 
+static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			unsigned long count, struct list_head *list,
 			int migratetype, int cold)
 {
-	int i;
-	
+	int mt = migratetype, i;
+
 	spin_lock(&zone->lock);
 	for (i = 0; i < count; ++i) {
 		struct page *page = __rmqueue(zone, order, migratetype);
@@ -1091,7 +1126,12 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			list_add(&page->lru, list);
 		else
 			list_add_tail(&page->lru, list);
-		set_page_private(page, migratetype);
+		if (IS_ENABLED(CONFIG_CMA)) {
+			mt = get_pageblock_migratetype(page);
+			if (!is_migrate_cma(mt) && mt != MIGRATE_ISOLATE)
+				mt = migratetype;
+		}
+		set_page_private(page, mt);
 		list = &page->lru;
 	}
 	__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
@@ -1371,8 +1411,12 @@ int split_free_page(struct page *page)
 
 	if (order >= pageblock_order - 1) {
 		struct page *endpage = page + (1 << order) - 1;
-		for (; page < endpage; page += pageblock_nr_pages)
-			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+		for (; page < endpage; page += pageblock_nr_pages) {
+			int mt = get_pageblock_migratetype(page);
+			if (mt != MIGRATE_ISOLATE && !is_migrate_cma(mt))
+				set_pageblock_migratetype(page,
+							  MIGRATE_MOVABLE);
+		}
 	}
 
 	return 1 << order;
@@ -2086,16 +2130,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 }
 #endif /* CONFIG_COMPACTION */
 
-/* The really slow allocator path where we enter direct reclaim */
-static inline struct page *
-__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
-	struct zonelist *zonelist, enum zone_type high_zoneidx,
-	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress)
+/* Perform direct synchronous page reclaim */
+static int
+__perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist,
+		  nodemask_t *nodemask)
 {
-	struct page *page = NULL;
 	struct reclaim_state reclaim_state;
-	bool drained = false;
+	int progress;
 
 	cond_resched();
 
@@ -2106,7 +2147,7 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 	reclaim_state.reclaimed_slab = 0;
 	current->reclaim_state = &reclaim_state;
 
-	*did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);
+	progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);
 
 	current->reclaim_state = NULL;
 	lockdep_clear_current_reclaim_state();
@@ -2114,6 +2155,21 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 
 	cond_resched();
 
+	return progress;
+}
+
+/* The really slow allocator path where we enter direct reclaim */
+static inline struct page *
+__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
+	struct zonelist *zonelist, enum zone_type high_zoneidx,
+	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
+	int migratetype, unsigned long *did_some_progress)
+{
+	struct page *page = NULL;
+	bool drained = false;
+
+	*did_some_progress = __perform_reclaim(gfp_mask, order, zonelist,
+					       nodemask);
 	if (unlikely(!(*did_some_progress)))
 		return NULL;
 
@@ -4301,7 +4357,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	pgdat->kswapd_max_order = 0;
 	pgdat_page_cgroup_init(pgdat);
-	
+
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
 		unsigned long size, realsize, memmap_pages;
@@ -4976,14 +5032,7 @@ static void setup_per_zone_lowmem_reserve(void)
 	calculate_totalreserve_pages();
 }
 
-/**
- * setup_per_zone_wmarks - called when min_free_kbytes changes
- * or when memory is hot-{added|removed}
- *
- * Ensures that the watermark[min,low,high] values for each zone are set
- * correctly with respect to min_free_kbytes.
- */
-void setup_per_zone_wmarks(void)
+static void __setup_per_zone_wmarks(void)
 {
 	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
 	unsigned long lowmem_pages = 0;
@@ -5030,6 +5079,11 @@ void setup_per_zone_wmarks(void)
 
 		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
 		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+
+		zone->watermark[WMARK_MIN] += cma_wmark_pages(zone);
+		zone->watermark[WMARK_LOW] += cma_wmark_pages(zone);
+		zone->watermark[WMARK_HIGH] += cma_wmark_pages(zone);
+
 		setup_zone_migrate_reserve(zone);
 		spin_unlock_irqrestore(&zone->lock, flags);
 	}
@@ -5038,6 +5092,20 @@ void setup_per_zone_wmarks(void)
 	calculate_totalreserve_pages();
 }
 
+/**
+ * setup_per_zone_wmarks - called when min_free_kbytes changes
+ * or when memory is hot-{added|removed}
+ *
+ * Ensures that the watermark[min,low,high] values for each zone are set
+ * correctly with respect to min_free_kbytes.
+ */
+void setup_per_zone_wmarks(void)
+{
+	mutex_lock(&zonelists_mutex);
+	__setup_per_zone_wmarks();
+	mutex_unlock(&zonelists_mutex);
+}
+
 /*
  * The inactive anon list should be small enough that the VM never has to
  * do too much work, but large enough that each inactive page has a chance
@@ -5415,14 +5483,16 @@ static int
 __count_immobile_pages(struct zone *zone, struct page *page, int count)
 {
 	unsigned long pfn, iter, found;
+	int mt;
+
 	/*
 	 * For avoiding noise data, lru_add_drain_all() should be called
 	 * If ZONE_MOVABLE, the zone never contains immobile pages
 	 */
 	if (zone_idx(zone) == ZONE_MOVABLE)
 		return true;
-
-	if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE)
+	mt = get_pageblock_migratetype(page);
+	if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt))
 		return true;
 
 	pfn = page_to_pfn(page);
@@ -5539,7 +5609,7 @@ out:
 	return ret;
 }
 
-void unset_migratetype_isolate(struct page *page)
+void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 {
 	struct zone *zone;
 	unsigned long flags;
@@ -5547,12 +5617,259 @@ void unset_migratetype_isolate(struct page *page)
 	spin_lock_irqsave(&zone->lock, flags);
 	if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
 		goto out;
-	set_pageblock_migratetype(page, MIGRATE_MOVABLE);
-	move_freepages_block(zone, page, MIGRATE_MOVABLE);
+	set_pageblock_migratetype(page, migratetype);
+	move_freepages_block(zone, page, migratetype);
 out:
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
 
+#ifdef CONFIG_CMA
+
+static unsigned long pfn_max_align_down(unsigned long pfn)
+{
+	return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES,
+			     pageblock_nr_pages) - 1);
+}
+
+static unsigned long pfn_max_align_up(unsigned long pfn)
+{
+	return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES,
+				pageblock_nr_pages));
+}
+
+static struct page *
+__alloc_contig_migrate_alloc(struct page *page, unsigned long private,
+			     int **resultp)
+{
+	return alloc_page(GFP_HIGHUSER_MOVABLE);
+}
+
+/* [start, end) must belong to a single zone. */
+static int __alloc_contig_migrate_range(unsigned long start, unsigned long end)
+{
+	/* This function is based on compact_zone() from compaction.c. */
+
+	unsigned long pfn = start;
+	unsigned int tries = 0;
+	int ret = 0;
+
+	struct compact_control cc = {
+		.nr_migratepages = 0,
+		.order = -1,
+		.zone = page_zone(pfn_to_page(start)),
+		.sync = true,
+	};
+	INIT_LIST_HEAD(&cc.migratepages);
+
+	migrate_prep_local();
+
+	while (pfn < end || !list_empty(&cc.migratepages)) {
+		if (fatal_signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+
+		if (list_empty(&cc.migratepages)) {
+			cc.nr_migratepages = 0;
+			pfn = isolate_migratepages_range(cc.zone, &cc,
+							 pfn, end);
+			if (!pfn) {
+				ret = -EINTR;
+				break;
+			}
+			tries = 0;
+		} else if (++tries == 5) {
+			ret = ret < 0 ? ret : -EBUSY;
+			break;
+		}
+
+		ret = migrate_pages(&cc.migratepages,
+				    __alloc_contig_migrate_alloc,
+				    0, false, MIGRATE_SYNC);
+	}
+
+	putback_lru_pages(&cc.migratepages);
+	return ret > 0 ? 0 : ret;
+}
+
+/*
+ * Update zone's cma pages counter used for watermark level calculation.
+ */
+static inline void __update_cma_watermarks(struct zone *zone, int count)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&zone->lock, flags);
+	zone->min_cma_pages += count;
+	spin_unlock_irqrestore(&zone->lock, flags);
+	setup_per_zone_wmarks();
+}
+
+/*
+ * Trigger memory pressure bump to reclaim some pages in order to be able to
+ * allocate 'count' pages in single page units. Does similar work as
+ *__alloc_pages_slowpath() function.
+ */
+static int __reclaim_pages(struct zone *zone, gfp_t gfp_mask, int count)
+{
+	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+	struct zonelist *zonelist = node_zonelist(0, gfp_mask);
+	int did_some_progress = 0;
+	int order = 1;
+
+	/*
+	 * Increase level of watermarks to force kswapd do his job
+	 * to stabilise at new watermark level.
+	 */
+	__update_cma_watermarks(zone, count);
+
+	/* Obey watermarks as if the page was being allocated */
+	while (!zone_watermark_ok(zone, 0, low_wmark_pages(zone), 0, 0)) {
+		wake_all_kswapd(order, zonelist, high_zoneidx, zone_idx(zone));
+
+		did_some_progress = __perform_reclaim(gfp_mask, order, zonelist,
+						      NULL);
+		if (!did_some_progress) {
+			/* Exhausted what can be done so it's blamo time */
+			out_of_memory(zonelist, gfp_mask, order, NULL, false);
+		}
+	}
+
+	/* Restore original watermark levels. */
+	__update_cma_watermarks(zone, -count);
+
+	return count;
+}
+
+/**
+ * alloc_contig_range() -- tries to allocate given range of pages
+ * @start:	start PFN to allocate
+ * @end:	one-past-the-last PFN to allocate
+ * @migratetype:	migratetype of the underlaying pageblocks (either
+ *			#MIGRATE_MOVABLE or #MIGRATE_CMA).  All pageblocks
+ *			in range must have the same migratetype and it must
+ *			be either of the two.
+ *
+ * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
+ * aligned, however it's the caller's responsibility to guarantee that
+ * we are the only thread that changes migrate type of pageblocks the
+ * pages fall in.
+ *
+ * The PFN range must belong to a single zone.
+ *
+ * Returns zero on success or negative error code.  On success all
+ * pages which PFN is in [start, end) are allocated for the caller and
+ * need to be freed with free_contig_range().
+ */
+int alloc_contig_range(unsigned long start, unsigned long end,
+		       unsigned migratetype)
+{
+	struct zone *zone = page_zone(pfn_to_page(start));
+	unsigned long outer_start, outer_end;
+	int ret = 0, order;
+
+	/*
+	 * What we do here is we mark all pageblocks in range as
+	 * MIGRATE_ISOLATE.  Because pageblock and max order pages may
+	 * have different sizes, and due to the way page allocator
+	 * work, we align the range to biggest of the two pages so
+	 * that page allocator won't try to merge buddies from
+	 * different pageblocks and change MIGRATE_ISOLATE to some
+	 * other migration type.
+	 *
+	 * Once the pageblocks are marked as MIGRATE_ISOLATE, we
+	 * migrate the pages from an unaligned range (ie. pages that
+	 * we are interested in).  This will put all the pages in
+	 * range back to page allocator as MIGRATE_ISOLATE.
+	 *
+	 * When this is done, we take the pages in range from page
+	 * allocator removing them from the buddy system.  This way
+	 * page allocator will never consider using them.
+	 *
+	 * This lets us mark the pageblocks back as
+	 * MIGRATE_CMA/MIGRATE_MOVABLE so that free pages in the
+	 * aligned range but not in the unaligned, original range are
+	 * put back to page allocator so that buddy can use them.
+	 */
+
+	ret = start_isolate_page_range(pfn_max_align_down(start),
+				       pfn_max_align_up(end), migratetype);
+	if (ret)
+		goto done;
+
+	ret = __alloc_contig_migrate_range(start, end);
+	if (ret)
+		goto done;
+
+	/*
+	 * Pages from [start, end) are within a MAX_ORDER_NR_PAGES
+	 * aligned blocks that are marked as MIGRATE_ISOLATE.  What's
+	 * more, all pages in [start, end) are free in page allocator.
+	 * What we are going to do is to allocate all pages from
+	 * [start, end) (that is remove them from page allocator).
+	 *
+	 * The only problem is that pages at the beginning and at the
+	 * end of interesting range may be not aligned with pages that
+	 * page allocator holds, ie. they can be part of higher order
+	 * pages.  Because of this, we reserve the bigger range and
+	 * once this is done free the pages we are not interested in.
+	 *
+	 * We don't have to hold zone->lock here because the pages are
+	 * isolated thus they won't get removed from buddy.
+	 */
+
+	lru_add_drain_all();
+	drain_all_pages();
+
+	order = 0;
+	outer_start = start;
+	while (!PageBuddy(pfn_to_page(outer_start))) {
+		if (++order >= MAX_ORDER) {
+			ret = -EBUSY;
+			goto done;
+		}
+		outer_start &= ~0UL << order;
+	}
+
+	/* Make sure the range is really isolated. */
+	if (test_pages_isolated(outer_start, end)) {
+		pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n",
+		       outer_start, end);
+		ret = -EBUSY;
+		goto done;
+	}
+
+	/*
+	 * Reclaim enough pages to make sure that contiguous allocation
+	 * will not starve the system.
+	 */
+	__reclaim_pages(zone, GFP_HIGHUSER_MOVABLE, end-start);
+
+	/* Grab isolated pages from freelists. */
+	outer_end = isolate_freepages_range(outer_start, end);
+	if (!outer_end) {
+		ret = -EBUSY;
+		goto done;
+	}
+
+	/* Free head and tail (if any) */
+	if (start != outer_start)
+		free_contig_range(outer_start, start - outer_start);
+	if (end != outer_end)
+		free_contig_range(end, outer_end - end);
+
+done:
+	undo_isolate_page_range(pfn_max_align_down(start),
+				pfn_max_align_up(end), migratetype);
+	return ret;
+}
+
+void free_contig_range(unsigned long pfn, unsigned nr_pages)
+{
+	for (; nr_pages--; ++pfn)
+		__free_page(pfn_to_page(pfn));
+}
+#endif
+
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /*
  * All pages in the range must be isolated before calling this.