Merge branch 'master' into for-next

Conflicts:
	include/linux/mmzone.h

Synced with Linus' tree so that trivial patch can be applied
on top of up-to-date code properly.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>

30 files changed, 1137 insertions, 984 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 39220026c79..b2176374b98 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -349,6 +349,16 @@ choice
 	  benefit.
 endchoice
 
+config CROSS_MEMORY_ATTACH
+	bool "Cross Memory Support"
+	depends on MMU
+	default y
+	help
+	  Enabling this option adds the system calls process_vm_readv and
+	  process_vm_writev which allow a process with the correct privileges
+	  to directly read from or write to to another process's address space.
+	  See the man page for more details.
+
 #
 # UP and nommu archs use km based percpu allocator
 #
diff --git a/mm/Makefile b/mm/Makefile
index 8aada89efbb..a156285ce88 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -5,8 +5,11 @@
 mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
-			   vmalloc.o pagewalk.o pgtable-generic.o \
-			   process_vm_access.o
+			   vmalloc.o pagewalk.o pgtable-generic.o
+
+ifdef CONFIG_CROSS_MEMORY_ATTACH
+mmu-$(CONFIG_MMU)	+= process_vm_access.o
+endif
 
 obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \
@@ -25,7 +28,7 @@ endif
 obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
 
 obj-$(CONFIG_BOUNCE)	+= bounce.o
-obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o
+obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
 obj-$(CONFIG_NUMA) 	+= mempolicy.o
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 0131170c9d5..ec4fcb7a56c 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -77,16 +77,16 @@ unsigned long __init bootmem_bootmap_pages(unsigned long pages)
  */
 static void __init link_bootmem(bootmem_data_t *bdata)
 {
-	struct list_head *iter;
+	bootmem_data_t *ent;
 
-	list_for_each(iter, &bdata_list) {
-		bootmem_data_t *ent;
-
-		ent = list_entry(iter, bootmem_data_t, list);
-		if (bdata->node_min_pfn < ent->node_min_pfn)
-			break;
+	list_for_each_entry(ent, &bdata_list, list) {
+		if (bdata->node_min_pfn < ent->node_min_pfn) {
+			list_add_tail(&bdata->list, &ent->list);
+			return;
+		}
 	}
-	list_add_tail(&bdata->list, iter);
+
+	list_add_tail(&bdata->list, &bdata_list);
 }
 
 /*
@@ -203,7 +203,8 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 		} else {
 			unsigned long off = 0;
 
-			while (vec && off < BITS_PER_LONG) {
+			vec >>= start & (BITS_PER_LONG - 1);
+			while (vec) {
 				if (vec & 1) {
 					page = pfn_to_page(start + off);
 					__free_pages_bootmem(page, 0);
@@ -467,7 +468,7 @@ static unsigned long __init align_off(struct bootmem_data *bdata,
 	return ALIGN(base + off, align) - base;
 }
 
-static void * __init alloc_bootmem_core(struct bootmem_data *bdata,
+static void * __init alloc_bootmem_bdata(struct bootmem_data *bdata,
 					unsigned long size, unsigned long align,
 					unsigned long goal, unsigned long limit)
 {
@@ -588,14 +589,14 @@ static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata,
 		p_bdata = bootmem_arch_preferred_node(bdata, size, align,
 							goal, limit);
 		if (p_bdata)
-			return alloc_bootmem_core(p_bdata, size, align,
+			return alloc_bootmem_bdata(p_bdata, size, align,
 							goal, limit);
 	}
 #endif
 	return NULL;
 }
 
-static void * __init ___alloc_bootmem_nopanic(unsigned long size,
+static void * __init alloc_bootmem_core(unsigned long size,
 					unsigned long align,
 					unsigned long goal,
 					unsigned long limit)
@@ -603,7 +604,6 @@ static void * __init ___alloc_bootmem_nopanic(unsigned long size,
 	bootmem_data_t *bdata;
 	void *region;
 
-restart:
 	region = alloc_arch_preferred_bootmem(NULL, size, align, goal, limit);
 	if (region)
 		return region;
@@ -614,11 +614,25 @@ restart:
 		if (limit && bdata->node_min_pfn >= PFN_DOWN(limit))
 			break;
 
-		region = alloc_bootmem_core(bdata, size, align, goal, limit);
+		region = alloc_bootmem_bdata(bdata, size, align, goal, limit);
 		if (region)
 			return region;
 	}
 
+	return NULL;
+}
+
+static void * __init ___alloc_bootmem_nopanic(unsigned long size,
+					      unsigned long align,
+					      unsigned long goal,
+					      unsigned long limit)
+{
+	void *ptr;
+
+restart:
+	ptr = alloc_bootmem_core(size, align, goal, limit);
+	if (ptr)
+		return ptr;
 	if (goal) {
 		goal = 0;
 		goto restart;
@@ -684,21 +698,56 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 	return ___alloc_bootmem(size, align, goal, limit);
 }
 
-static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata,
+static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 				unsigned long size, unsigned long align,
 				unsigned long goal, unsigned long limit)
 {
 	void *ptr;
 
-	ptr = alloc_arch_preferred_bootmem(bdata, size, align, goal, limit);
+again:
+	ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size,
+					   align, goal, limit);
 	if (ptr)
 		return ptr;
 
-	ptr = alloc_bootmem_core(bdata, size, align, goal, limit);
+	ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit);
 	if (ptr)
 		return ptr;
 
-	return ___alloc_bootmem(size, align, goal, limit);
+	ptr = alloc_bootmem_core(size, align, goal, limit);
+	if (ptr)
+		return ptr;
+
+	if (goal) {
+		goal = 0;
+		goto again;
+	}
+
+	return NULL;
+}
+
+void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
+}
+
+void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
+				    unsigned long align, unsigned long goal,
+				    unsigned long limit)
+{
+	void *ptr;
+
+	ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
+	if (ptr)
+		return ptr;
+
+	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
+	panic("Out of memory");
+	return NULL;
 }
 
 /**
@@ -722,7 +771,7 @@ void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-	return  ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0);
+	return  ___alloc_bootmem_node(pgdat, size, align, goal, 0);
 }
 
 void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
@@ -743,7 +792,7 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 		unsigned long new_goal;
 
 		new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
-		ptr = alloc_bootmem_core(pgdat->bdata, size, align,
+		ptr = alloc_bootmem_bdata(pgdat->bdata, size, align,
 						 new_goal, 0);
 		if (ptr)
 			return ptr;
@@ -754,47 +803,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 
 }
 
-#ifdef CONFIG_SPARSEMEM
-/**
- * alloc_bootmem_section - allocate boot memory from a specific section
- * @size: size of the request in bytes
- * @section_nr: sparse map section to allocate from
- *
- * Return NULL on failure.
- */
-void * __init alloc_bootmem_section(unsigned long size,
-				    unsigned long section_nr)
-{
-	bootmem_data_t *bdata;
-	unsigned long pfn, goal;
-
-	pfn = section_nr_to_pfn(section_nr);
-	goal = pfn << PAGE_SHIFT;
-	bdata = &bootmem_node_data[early_pfn_to_nid(pfn)];
-
-	return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, 0);
-}
-#endif
-
-void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
-				   unsigned long align, unsigned long goal)
-{
-	void *ptr;
-
-	if (WARN_ON_ONCE(slab_is_available()))
-		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
-
-	ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size, align, goal, 0);
-	if (ptr)
-		return ptr;
-
-	ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
-	if (ptr)
-		return ptr;
-
-	return __alloc_bootmem_nopanic(size, align, goal);
-}
-
 #ifndef ARCH_LOW_ADDRESS_LIMIT
 #define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
 #endif
@@ -839,6 +847,6 @@ void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-	return ___alloc_bootmem_node(pgdat->bdata, size, align,
-				goal, ARCH_LOW_ADDRESS_LIMIT);
+	return ___alloc_bootmem_node(pgdat, size, align,
+				     goal, ARCH_LOW_ADDRESS_LIMIT);
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index da7d35ea510..840ee288e29 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -235,7 +235,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	 */
 	while (unlikely(too_many_isolated(zone))) {
 		/* async migration should just abort */
-		if (!cc->sync)
+		if (cc->mode != COMPACT_SYNC)
 			return 0;
 
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -303,7 +303,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		 * satisfies the allocation
 		 */
 		pageblock_nr = low_pfn >> pageblock_order;
-		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
+		if (cc->mode != COMPACT_SYNC &&
+		    last_pageblock_nr != pageblock_nr &&
 		    !migrate_async_suitable(get_pageblock_migratetype(page))) {
 			low_pfn += pageblock_nr_pages;
 			low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1;
@@ -324,7 +325,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 		}
 
-		if (!cc->sync)
+		if (cc->mode != COMPACT_SYNC)
 			mode |= ISOLATE_ASYNC_MIGRATE;
 
 		/* Try isolate the page */
@@ -357,27 +358,90 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 
 #endif /* CONFIG_COMPACTION || CONFIG_CMA */
 #ifdef CONFIG_COMPACTION
+/*
+ * Returns true if MIGRATE_UNMOVABLE pageblock was successfully
+ * converted to MIGRATE_MOVABLE type, false otherwise.
+ */
+static bool rescue_unmovable_pageblock(struct page *page)
+{
+	unsigned long pfn, start_pfn, end_pfn;
+	struct page *start_page, *end_page;
+
+	pfn = page_to_pfn(page);
+	start_pfn = pfn & ~(pageblock_nr_pages - 1);
+	end_pfn = start_pfn + pageblock_nr_pages;
+
+	start_page = pfn_to_page(start_pfn);
+	end_page = pfn_to_page(end_pfn);
+
+	/* Do not deal with pageblocks that overlap zones */
+	if (page_zone(start_page) != page_zone(end_page))
+		return false;
+
+	for (page = start_page, pfn = start_pfn; page < end_page; pfn++,
+								  page++) {
+		if (!pfn_valid_within(pfn))
+			continue;
+
+		if (PageBuddy(page)) {
+			int order = page_order(page);
+
+			pfn += (1 << order) - 1;
+			page += (1 << order) - 1;
+
+			continue;
+		} else if (page_count(page) == 0 || PageLRU(page))
+			continue;
+
+		return false;
+	}
+
+	set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+	move_freepages_block(page_zone(page), page, MIGRATE_MOVABLE);
+	return true;
+}
 
-/* Returns true if the page is within a block suitable for migration to */
-static bool suitable_migration_target(struct page *page)
+enum smt_result {
+	GOOD_AS_MIGRATION_TARGET,
+	FAIL_UNMOVABLE_TARGET,
+	FAIL_BAD_TARGET,
+};
+
+/*
+ * Returns GOOD_AS_MIGRATION_TARGET if the page is within a block
+ * suitable for migration to, FAIL_UNMOVABLE_TARGET if the page
+ * is within a MIGRATE_UNMOVABLE block, FAIL_BAD_TARGET otherwise.
+ */
+static enum smt_result suitable_migration_target(struct page *page,
+				      struct compact_control *cc)
 {
 
 	int migratetype = get_pageblock_migratetype(page);
 
 	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
 	if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE)
-		return false;
+		return FAIL_BAD_TARGET;
 
 	/* If the page is a large free page, then allow migration */
 	if (PageBuddy(page) && page_order(page) >= pageblock_order)
-		return true;
+		return GOOD_AS_MIGRATION_TARGET;
 
 	/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
-	if (migrate_async_suitable(migratetype))
-		return true;
+	if (cc->mode != COMPACT_ASYNC_UNMOVABLE &&
+	    migrate_async_suitable(migratetype))
+		return GOOD_AS_MIGRATION_TARGET;
+
+	if (cc->mode == COMPACT_ASYNC_MOVABLE &&
+	    migratetype == MIGRATE_UNMOVABLE)
+		return FAIL_UNMOVABLE_TARGET;
+
+	if (cc->mode != COMPACT_ASYNC_MOVABLE &&
+	    migratetype == MIGRATE_UNMOVABLE &&
+	    rescue_unmovable_pageblock(page))
+		return GOOD_AS_MIGRATION_TARGET;
 
 	/* Otherwise skip the block */
-	return false;
+	return FAIL_BAD_TARGET;
 }
 
 /*
@@ -411,6 +475,13 @@ static void isolate_freepages(struct zone *zone,
 	zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
 
 	/*
+	 * isolate_freepages() may be called more than once during
+	 * compact_zone_order() run and we want only the most recent
+	 * count.
+	 */
+	cc->nr_pageblocks_skipped = 0;
+
+	/*
 	 * Isolate free pages until enough are available to migrate the
 	 * pages on cc->migratepages. We stop searching if the migrate
 	 * and free page scanners meet or enough free pages are isolated.
@@ -418,6 +489,7 @@ static void isolate_freepages(struct zone *zone,
 	for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
 					pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
+		enum smt_result ret;
 
 		if (!pfn_valid(pfn))
 			continue;
@@ -434,9 +506,12 @@ static void isolate_freepages(struct zone *zone,
 			continue;
 
 		/* Check the block is suitable for migration */
-		if (!suitable_migration_target(page))
+		ret = suitable_migration_target(page, cc);
+		if (ret != GOOD_AS_MIGRATION_TARGET) {
+			if (ret == FAIL_UNMOVABLE_TARGET)
+				cc->nr_pageblocks_skipped++;
 			continue;
-
+		}
 		/*
 		 * Found a block suitable for isolating free pages from. Now
 		 * we disabled interrupts, double check things are ok and
@@ -445,12 +520,14 @@ static void isolate_freepages(struct zone *zone,
 		 */
 		isolated = 0;
 		spin_lock_irqsave(&zone->lock, flags);
-		if (suitable_migration_target(page)) {
+		ret = suitable_migration_target(page, cc);
+		if (ret == GOOD_AS_MIGRATION_TARGET) {
 			end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn);
 			isolated = isolate_freepages_block(pfn, end_pfn,
 							   freelist, false);
 			nr_freepages += isolated;
-		}
+		} else if (ret == FAIL_UNMOVABLE_TARGET)
+			cc->nr_pageblocks_skipped++;
 		spin_unlock_irqrestore(&zone->lock, flags);
 
 		/*
@@ -682,8 +759,9 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
 		nr_migrate = cc->nr_migratepages;
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
-				(unsigned long)cc, false,
-				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC);
+			(unsigned long)&cc->freepages, false,
+			(cc->mode == COMPACT_SYNC) ? MIGRATE_SYNC_LIGHT
+						      : MIGRATE_ASYNC);
 		update_nr_listpages(cc);
 		nr_remaining = cc->nr_migratepages;
 
@@ -712,7 +790,8 @@ out:
 
 static unsigned long compact_zone_order(struct zone *zone,
 				 int order, gfp_t gfp_mask,
-				 bool sync)
+				 enum compact_mode mode,
+				 unsigned long *nr_pageblocks_skipped)
 {
 	struct compact_control cc = {
 		.nr_freepages = 0,
@@ -720,12 +799,17 @@ static unsigned long compact_zone_order(struct zone *zone,
 		.order = order,
 		.migratetype = allocflags_to_migratetype(gfp_mask),
 		.zone = zone,
-		.sync = sync,
+		.mode = mode,
 	};
+	unsigned long rc;
+
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
 
-	return compact_zone(zone, &cc);
+	rc = compact_zone(zone, &cc);
+	*nr_pageblocks_skipped = cc.nr_pageblocks_skipped;
+
+	return rc;
 }
 
 int sysctl_extfrag_threshold = 500;
@@ -750,6 +834,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	int rc = COMPACT_SKIPPED;
+	unsigned long nr_pageblocks_skipped;
+	enum compact_mode mode;
 
 	/*
 	 * Check whether it is worth even starting compaction. The order check is
@@ -766,12 +852,22 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 								nodemask) {
 		int status;
 
-		status = compact_zone_order(zone, order, gfp_mask, sync);
+		mode = sync ? COMPACT_SYNC : COMPACT_ASYNC_MOVABLE;
+retry:
+		status = compact_zone_order(zone, order, gfp_mask, mode,
+						&nr_pageblocks_skipped);
 		rc = max(status, rc);
 
 		/* If a normal allocation would succeed, stop compacting */
 		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
 			break;
+
+		if (rc == COMPACT_COMPLETE && mode == COMPACT_ASYNC_MOVABLE) {
+			if (nr_pageblocks_skipped) {
+				mode = COMPACT_ASYNC_UNMOVABLE;
+				goto retry;
+			}
+		}
 	}
 
 	return rc;
@@ -805,7 +901,7 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 			if (ok && cc->order > zone->compact_order_failed)
 				zone->compact_order_failed = cc->order + 1;
 			/* Currently async compaction is never deferred. */
-			else if (!ok && cc->sync)
+			else if (!ok && cc->mode == COMPACT_SYNC)
 				defer_compaction(zone, cc->order);
 		}
 
@@ -820,7 +916,7 @@ int compact_pgdat(pg_data_t *pgdat, int order)
 {
 	struct compact_control cc = {
 		.order = order,
-		.sync = false,
+		.mode = COMPACT_ASYNC_MOVABLE,
 	};
 
 	return __compact_pgdat(pgdat, &cc);
@@ -830,7 +926,7 @@ static int compact_node(int nid)
 {
 	struct compact_control cc = {
 		.order = -1,
-		.sync = true,
+		.mode = COMPACT_SYNC,
 	};
 
 	return __compact_pgdat(NODE_DATA(nid), &cc);
diff --git a/mm/filemap.c b/mm/filemap.c
index 79c4b2b0b14..64b48f934b8 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -29,7 +29,6 @@
 #include <linux/pagevec.h>
 #include <linux/blkdev.h>
 #include <linux/security.h>
-#include <linux/syscalls.h>
 #include <linux/cpuset.h>
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
 #include <linux/memcontrol.h>
@@ -1478,44 +1477,6 @@ out:
 }
 EXPORT_SYMBOL(generic_file_aio_read);
 
-static ssize_t
-do_readahead(struct address_space *mapping, struct file *filp,
-	     pgoff_t index, unsigned long nr)
-{
-	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
-		return -EINVAL;
-
-	force_page_cache_readahead(mapping, filp, index, nr);
-	return 0;
-}
-
-SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count)
-{
-	ssize_t ret;
-	struct file *file;
-
-	ret = -EBADF;
-	file = fget(fd);
-	if (file) {
-		if (file->f_mode & FMODE_READ) {
-			struct address_space *mapping = file->f_mapping;
-			pgoff_t start = offset >> PAGE_CACHE_SHIFT;
-			pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
-			unsigned long len = end - start + 1;
-			ret = do_readahead(mapping, file, start, len);
-		}
-		fput(file);
-	}
-	return ret;
-}
-#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
-asmlinkage long SyS_readahead(long fd, loff_t offset, long count)
-{
-	return SYSC_readahead((int) fd, offset, (size_t) count);
-}
-SYSCALL_ALIAS(sys_readahead, SyS_readahead);
-#endif
-
 #ifdef CONFIG_MMU
 /**
  * page_cache_read - adds requested page to the page cache if not already there
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f0e5306eeb5..d0def42c121 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -636,16 +636,12 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 					unsigned long haddr, pmd_t *pmd,
 					struct page *page)
 {
-	int ret = 0;
 	pgtable_t pgtable;
 
 	VM_BUG_ON(!PageCompound(page));
 	pgtable = pte_alloc_one(mm, haddr);
-	if (unlikely(!pgtable)) {
-		mem_cgroup_uncharge_page(page);
-		put_page(page);
+	if (unlikely(!pgtable))
 		return VM_FAULT_OOM;
-	}
 
 	clear_huge_page(page, haddr, HPAGE_PMD_NR);
 	__SetPageUptodate(page);
@@ -675,7 +671,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		spin_unlock(&mm->page_table_lock);
 	}
 
-	return ret;
+	return 0;
 }
 
 static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp)
@@ -724,8 +720,14 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			put_page(page);
 			goto out;
 		}
+		if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd,
+							  page))) {
+			mem_cgroup_uncharge_page(page);
+			put_page(page);
+			goto out;
+		}
 
-		return __do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page);
+		return 0;
 	}
 out:
 	/*
@@ -950,6 +952,8 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		count_vm_event(THP_FAULT_FALLBACK);
 		ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 						   pmd, orig_pmd, page, haddr);
+		if (ret & VM_FAULT_OOM)
+			split_huge_page(page);
 		put_page(page);
 		goto out;
 	}
@@ -957,6 +961,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
 		put_page(new_page);
+		split_huge_page(page);
 		put_page(page);
 		ret |= VM_FAULT_OOM;
 		goto out;
@@ -968,8 +973,10 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	spin_lock(&mm->page_table_lock);
 	put_page(page);
 	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
+		spin_unlock(&mm->page_table_lock);
 		mem_cgroup_uncharge_page(new_page);
 		put_page(new_page);
+		goto out;
 	} else {
 		pmd_t entry;
 		VM_BUG_ON(!PageHead(page));
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4e28416c47f..285a81e87ec 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -273,8 +273,8 @@ static long region_count(struct list_head *head, long f, long t)
 
 	/* Locate each segment we overlap with, and count that overlap. */
 	list_for_each_entry(rg, head, link) {
-		int seg_from;
-		int seg_to;
+		long seg_from;
+		long seg_to;
 
 		if (rg->to <= f)
 			continue;
@@ -2157,6 +2157,15 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 		kref_get(&reservations->refs);
 }
 
+static void resv_map_put(struct vm_area_struct *vma)
+{
+	struct resv_map *reservations = vma_resv_map(vma);
+
+	if (!reservations)
+		return;
+	kref_put(&reservations->refs, resv_map_release);
+}
+
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
 	struct hstate *h = hstate_vma(vma);
@@ -2173,7 +2182,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 		reserve = (end - start) -
 			region_count(&reservations->regions, start, end);
 
-		kref_put(&reservations->refs, resv_map_release);
+		resv_map_put(vma);
 
 		if (reserve) {
 			hugetlb_acct_memory(h, -reserve);
@@ -2991,12 +3000,16 @@ int hugetlb_reserve_pages(struct inode *inode,
 		set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
 	}
 
-	if (chg < 0)
-		return chg;
+	if (chg < 0) {
+		ret = chg;
+		goto out_err;
+	}
 
 	/* There must be enough pages in the subpool for the mapping */
-	if (hugepage_subpool_get_pages(spool, chg))
-		return -ENOSPC;
+	if (hugepage_subpool_get_pages(spool, chg)) {
+		ret = -ENOSPC;
+		goto out_err;
+	}
 
 	/*
 	 * Check enough hugepages are available for the reservation.
@@ -3005,7 +3018,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
 		hugepage_subpool_put_pages(spool, chg);
-		return ret;
+		goto out_err;
 	}
 
 	/*
@@ -3022,6 +3035,9 @@ int hugetlb_reserve_pages(struct inode *inode,
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
 		region_add(&inode->i_mapping->private_list, from, to);
 	return 0;
+out_err:
+	resv_map_put(vma);
+	return ret;
 }
 
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
diff --git a/mm/internal.h b/mm/internal.h
index aee4761cf9a..4194ab9dc19 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -94,6 +94,9 @@ extern void putback_lru_page(struct page *page);
 /*
  * in mm/page_alloc.c
  */
+extern void set_pageblock_migratetype(struct page *page, int migratetype);
+extern int move_freepages_block(struct zone *zone, struct page *page,
+				int migratetype);
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
 extern void prep_compound_page(struct page *page, unsigned long order);
 #ifdef CONFIG_MEMORY_FAILURE
@@ -101,6 +104,7 @@ extern bool is_free_buddy_page(struct page *page);
 #endif
 
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
+#include <linux/compaction.h>
 
 /*
  * in mm/compaction.c
@@ -119,11 +123,14 @@ struct compact_control {
 	unsigned long nr_migratepages;	/* Number of pages to migrate */
 	unsigned long free_pfn;		/* isolate_freepages search base */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
-	bool sync;			/* Synchronous migration */
+	enum compact_mode mode;		/* Compaction mode */
 
 	int order;			/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
+
+	/* Number of UNMOVABLE destination pageblocks skipped during scan */
+	unsigned long nr_pageblocks_skipped;
 };
 
 unsigned long
@@ -164,7 +171,8 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
  * to determine if it's being mapped into a LOCKED vma.
  * If so, mark page as mlocked.
  */
-static inline int is_mlocked_vma(struct vm_area_struct *vma, struct page *page)
+static inline int mlocked_vma_newpage(struct vm_area_struct *vma,
+				    struct page *page)
 {
 	VM_BUG_ON(PageLRU(page));
 
@@ -222,7 +230,7 @@ extern unsigned long vma_address(struct page *page,
 				 struct vm_area_struct *vma);
 #endif
 #else /* !CONFIG_MMU */
-static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
+static inline int mlocked_vma_newpage(struct vm_area_struct *v, struct page *p)
 {
 	return 0;
 }
diff --git a/mm/madvise.c b/mm/madvise.c
index 1ccbba5b667..deff1b64a08 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -11,8 +11,10 @@
 #include <linux/mempolicy.h>
 #include <linux/page-isolation.h>
 #include <linux/hugetlb.h>
+#include <linux/falloc.h>
 #include <linux/sched.h>
 #include <linux/ksm.h>
+#include <linux/fs.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -200,8 +202,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 				struct vm_area_struct **prev,
 				unsigned long start, unsigned long end)
 {
-	struct address_space *mapping;
-	loff_t offset, endoff;
+	loff_t offset;
 	int error;
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
@@ -217,16 +218,14 @@ static long madvise_remove(struct vm_area_struct *vma,
 	if ((vma->vm_flags & (VM_SHARED|VM_WRITE)) != (VM_SHARED|VM_WRITE))
 		return -EACCES;
 
-	mapping = vma->vm_file->f_mapping;
-
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgo