Add __GFP_MOVABLE for callers to flag allocations from high memory that may be migrated

It is often known at allocation time whether a page may be migrated or not.
This patch adds a flag called __GFP_MOVABLE and a new mask called
GFP_HIGH_MOVABLE.  Allocations using the __GFP_MOVABLE can be either migrated
using the page migration mechanism or reclaimed by syncing with backing
storage and discarding.

An API function very similar to alloc_zeroed_user_highpage() is added for
__GFP_MOVABLE allocations called alloc_zeroed_user_highpage_movable().  The
flags used by alloc_zeroed_user_highpage() are not changed because it would
change the semantics of an existing API.  After this patch is applied there
are no in-kernel users of alloc_zeroed_user_highpage() so it probably should
be marked deprecated if this patch is merged.

Note that this patch includes a minor cleanup to the use of __GFP_ZERO in
shmem.c to keep all flag modifications to inode->mapping in the
shmem_dir_alloc() helper function.  This clean-up suggestion is courtesy of
Hugh Dickens.

Additional credit goes to Christoph Lameter and Linus Torvalds for shaping the
concept.  Credit to Hugh Dickens for catching issues with shmem swap vector
and ramfs allocations.

[akpm@linux-foundation.org: build fix]
[hugh@veritas.com: __GFP_ZERO cleanup]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

19 files changed, 114 insertions, 30 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 424165b569f8..94344b2e0b46 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -982,7 +982,7 @@ grow_dev_page(struct block_device *bdev, sector_t block,
         struct buffer_head *bh;
 
         page = find_or_create_page(inode->i_mapping, index,
-                mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
+                (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE);
         if (!page)
                 return NULL;
 
diff --git a/fs/inode.c b/fs/inode.c
index 9a012cc5b6cd..47b87b071de3 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -145,7 +145,7 @@ static struct inode *alloc_inode(struct super_block *sb)
                 mapping->a_ops = &empty_aops;
                 mapping->host = inode;
                 mapping->flags = 0;
-                mapping_set_gfp_mask(mapping, GFP_HIGHUSER);
+                mapping_set_gfp_mask(mapping, GFP_HIGHUSER_PAGECACHE);
                 mapping->assoc_mapping = NULL;
                 mapping->backing_dev_info = &default_backing_dev_info;
 
@@ -519,7 +519,13 @@ repeat:
  *      new_inode       - obtain an inode
  *      @sb: superblock
  *
- *      Allocates a new inode for given superblock.
+ *      Allocates a new inode for given superblock. The default gfp_mask
+ *      for allocations related to inode->i_mapping is GFP_HIGHUSER_PAGECACHE.
+ *      If HIGHMEM pages are unsuitable or it is known that pages allocated
+ *      for the page cache are not reclaimable or migratable,
+ *      mapping_set_gfp_mask() must be called with suitable flags on the
+ *      newly created inode's mapping
+ *
  */
 struct inode *new_inode(struct super_block *sb)
 {
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index d40d22b347b7..ef2b46d099ff 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -60,6 +60,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev)
                 inode->i_blocks = 0;
                 inode->i_mapping->a_ops = &ramfs_aops;
                 inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
+                mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
                 inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
                 switch (mode & S_IFMT) {
                 default:
diff --git a/include/asm-alpha/page.h b/include/asm-alpha/page.h
index d2bed3cb33ff..bae7f05716d4 100644
--- a/include/asm-alpha/page.h
+++ b/include/asm-alpha/page.h
@@ -17,7 +17,8 @@
 extern void clear_page(void *page);
 #define clear_user_page(page, vaddr, pg)        clear_page(page)
 
-#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vmaddr)
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+        alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vmaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
 extern void copy_page(void * _to, void * _from);
diff --git a/include/asm-cris/page.h b/include/asm-cris/page.h
index 9f13c32552bf..0648e3153f81 100644
--- a/include/asm-cris/page.h
+++ b/include/asm-cris/page.h
@@ -20,7 +20,8 @@
 #define clear_user_page(page, vaddr, pg)    clear_page(page)
 #define copy_user_page(to, from, vaddr, pg) copy_page(to, from)
 
-#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr)
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+        alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
 /*
diff --git a/include/asm-h8300/page.h b/include/asm-h8300/page.h
index 3b4f2903f91d..c8cc81a3aca5 100644
--- a/include/asm-h8300/page.h
+++ b/include/asm-h8300/page.h
@@ -22,7 +22,8 @@
 #define clear_user_page(page, vaddr, pg)        clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)     copy_page(to, from)
 
-#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr)
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+        alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
 /*
diff --git a/include/asm-i386/page.h b/include/asm-i386/page.h
index 818ac8bf01e2..99cf5d3692a9 100644
--- a/include/asm-i386/page.h
+++ b/include/asm-i386/page.h
@@ -34,7 +34,8 @@
 #define clear_user_page(page, vaddr, pg)        clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)     copy_page(to, from)
 
-#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr)
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+        alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
 /*
diff --git a/include/asm-ia64/page.h b/include/asm-ia64/page.h
index 485759ba9e36..d6345464a2b3 100644
--- a/include/asm-ia64/page.h
+++ b/include/asm-ia64/page.h
@@ -87,12 +87,13 @@ do {						\
 } while (0)
 
 
-#define alloc_zeroed_user_highpage(vma, vaddr) \
-({                                              \
-        struct page *page = alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr); \
-        if (page)                               \
-                flush_dcache_page(page);        \
-        page;                                   \
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr)          \
+({                                                                      \
+        struct page *page = alloc_page_vma(                             \
+                GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr);  \
+        if (page)                                                       \
+                flush_dcache_page(page);                                \
+        page;                                                           \
 })
 
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
diff --git a/include/asm-m32r/page.h b/include/asm-m32r/page.h
index 6f6ecf7d14a3..04fd183a2c58 100644
--- a/include/asm-m32r/page.h
+++ b/include/asm-m32r/page.h
@@ -15,7 +15,8 @@ extern void copy_page(void *to, void *from);
 #define clear_user_page(page, vaddr, pg)        clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)     copy_page(to, from)
 
-#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr)
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+        alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
 /*
diff --git a/include/asm-m68knommu/page.h b/include/asm-m68knommu/page.h
index 2a1b8bdcb29c..9efa0a9851b1 100644
--- a/include/asm-m68knommu/page.h
+++ b/include/asm-m68knommu/page.h
@@ -22,7 +22,8 @@
 #define clear_user_page(page, vaddr, pg)        clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)     copy_page(to, from)
 
-#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr)
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+        alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
 /*
diff --git a/include/asm-s390/page.h b/include/asm-s390/page.h
index 05ea6f172786..f326451ed6ec 100644
--- a/include/asm-s390/page.h
+++ b/include/asm-s390/page.h
@@ -64,7 +64,8 @@ static inline void copy_page(void *to, void *from)
 #define clear_user_page(page, vaddr, pg)        clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)     copy_page(to, from)
 
-#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr)
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+        alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
 /*
diff --git a/include/asm-x86_64/page.h b/include/asm-x86_64/page.h
index e327c830da0c..88adf1afb0a2 100644
--- a/include/asm-x86_64/page.h
+++ b/include/asm-x86_64/page.h
@@ -48,7 +48,8 @@ void copy_page(void *, void *);
 #define clear_user_page(page, vaddr, pg)        clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)     copy_page(to, from)
 
-#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr)
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+        alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 /*
  * These are used to make use of C type-checking..
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 0d2ef0b082a6..e5882fe49f83 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -30,6 +30,9 @@ struct vm_area_struct;
  * cannot handle allocation failures.
  *
  * __GFP_NORETRY: The VM implementation must not retry indefinitely.
+ *
+ * __GFP_MOVABLE: Flag that this page will be movable by the page migration
+ * mechanism or reclaimed
  */
 #define __GFP_WAIT      ((__force gfp_t)0x10u)  /* Can wait and reschedule? */
 #define __GFP_HIGH      ((__force gfp_t)0x20u)  /* Should access emergency pools? */
@@ -45,6 +48,7 @@ struct vm_area_struct;
 #define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */
 #define __GFP_HARDWALL   ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */
 #define __GFP_THISNODE  ((__force gfp_t)0x40000u)/* No fallback, no policies */
+#define __GFP_MOVABLE   ((__force gfp_t)0x80000u) /* Page is movable */
 
 #define __GFP_BITS_SHIFT 20     /* Room for 20 __GFP_FOO bits */
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
@@ -53,7 +57,8 @@ struct vm_area_struct;
 #define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \
                         __GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \
                         __GFP_NOFAIL|__GFP_NORETRY|__GFP_COMP| \
-                        __GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE)
+                        __GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE| \
+                        __GFP_MOVABLE)
 
 /* This equals 0, but use constants in case they ever change */
 #define GFP_NOWAIT      (GFP_ATOMIC & ~__GFP_HIGH)
@@ -65,6 +70,15 @@ struct vm_area_struct;
 #define GFP_USER        (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
 #define GFP_HIGHUSER    (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL | \
                          __GFP_HIGHMEM)
+#define GFP_HIGHUSER_MOVABLE    (__GFP_WAIT | __GFP_IO | __GFP_FS | \
+                                 __GFP_HARDWALL | __GFP_HIGHMEM | \
+                                 __GFP_MOVABLE)
+#define GFP_NOFS_PAGECACHE      (__GFP_WAIT | __GFP_IO | __GFP_MOVABLE)
+#define GFP_USER_PAGECACHE      (__GFP_WAIT | __GFP_IO | __GFP_FS | \
+                                 __GFP_HARDWALL | __GFP_MOVABLE)
+#define GFP_HIGHUSER_PAGECACHE  (__GFP_WAIT | __GFP_IO | __GFP_FS | \
+                                 __GFP_HARDWALL | __GFP_HIGHMEM | \
+                                 __GFP_MOVABLE)
 
 #ifdef CONFIG_NUMA
 #define GFP_THISNODE    (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 98e2cce996a4..12c5e4e3135a 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -73,10 +73,27 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
 }
 
 #ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+/**
+ * __alloc_zeroed_user_highpage - Allocate a zeroed HIGHMEM page for a VMA with caller-specified movable GFP flags
+ * @movableflags: The GFP flags related to the pages future ability to move like __GFP_MOVABLE
+ * @vma: The VMA the page is to be allocated for
+ * @vaddr: The virtual address the page will be inserted into
+ *
+ * This function will allocate a page for a VMA but the caller is expected
+ * to specify via movableflags whether the page will be movable in the
+ * future or not
+ *
+ * An architecture may override this function by defining
+ * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE and providing their own
+ * implementation.
+ */
 static inline struct page *
-alloc_zeroed_user_highpage(struct vm_area_struct *vma, unsigned long vaddr)
+__alloc_zeroed_user_highpage(gfp_t movableflags,
+                        struct vm_area_struct *vma,
+                        unsigned long vaddr)
 {
-        struct page *page = alloc_page_vma(GFP_HIGHUSER, vma, vaddr);
+        struct page *page = alloc_page_vma(GFP_HIGHUSER | movableflags,
+                        vma, vaddr);
 
         if (page)
                 clear_user_highpage(page, vaddr);
@@ -85,6 +102,36 @@ alloc_zeroed_user_highpage(struct vm_area_struct *vma, unsigned long vaddr)
 }
 #endif
 
+/**
+ * alloc_zeroed_user_highpage - Allocate a zeroed HIGHMEM page for a VMA
+ * @vma: The VMA the page is to be allocated for
+ * @vaddr: The virtual address the page will be inserted into
+ *
+ * This function will allocate a page for a VMA that the caller knows will
+ * not be able to move in the future using move_pages() or reclaim. If it
+ * is known that the page can move, use alloc_zeroed_user_highpage_movable
+ */
+static inline struct page *
+alloc_zeroed_user_highpage(struct vm_area_struct *vma, unsigned long vaddr)
+{
+        return __alloc_zeroed_user_highpage(0, vma, vaddr);
+}
+
+/**
+ * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move
+ * @vma: The VMA the page is to be allocated for
+ * @vaddr: The virtual address the page will be inserted into
+ *
+ * This function will allocate a page for a VMA that the caller knows will
+ * be able to migrate in the future using move_pages() or reclaimed
+ */
+static inline struct page *
+alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
+                                        unsigned long vaddr)
+{
+        return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
+}
+
 static inline void clear_highpage(struct page *page)
 {
         void *kaddr = kmap_atomic(page, KM_USER0);
diff --git a/mm/memory.c b/mm/memory.c
index b3d73bb1f680..9c6ff7fffdc8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1715,11 +1715,11 @@ gotten:
         if (unlikely(anon_vma_prepare(vma)))
                 goto oom;
         if (old_page == ZERO_PAGE(address)) {
-                new_page = alloc_zeroed_user_highpage(vma, address);
+                new_page = alloc_zeroed_user_highpage_movable(vma, address);
                 if (!new_page)
                         goto oom;
         } else {
-                new_page = alloc_page_vma(GFP_HIGHUSER, vma, address);
+                new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
                 if (!new_page)
                         goto oom;
                 cow_user_page(new_page, old_page, address, vma);
@@ -2237,7 +2237,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
                 if (unlikely(anon_vma_prepare(vma)))
                         goto oom;
-                page = alloc_zeroed_user_highpage(vma, address);
+                page = alloc_zeroed_user_highpage_movable(vma, address);
                 if (!page)
                         goto oom;
 
@@ -2340,7 +2340,8 @@ retry:
 
                         if (unlikely(anon_vma_prepare(vma)))
                                 goto oom;
-                        page = alloc_page_vma(GFP_HIGHUSER, vma, address);
+                        page = alloc_page_vma(GFP_HIGHUSER_MOVABLE,
+                                                vma, address);
                         if (!page)
                                 goto oom;
                         copy_user_highpage(page, new_page, address, vma);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 188f8d9c4aed..4c0f99996811 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -594,7 +594,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
 
 static struct page *new_node_page(struct page *page, unsigned long node, int **x)
 {
-        return alloc_pages_node(node, GFP_HIGHUSER, 0);
+        return alloc_pages_node(node, GFP_HIGHUSER_MOVABLE, 0);
 }
 
 /*
@@ -710,7 +710,8 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int *
 {
         struct vm_area_struct *vma = (struct vm_area_struct *)private;
 
-        return alloc_page_vma(GFP_HIGHUSER, vma, page_address_in_vma(page, vma));
+        return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
+                                        page_address_in_vma(page, vma));
 }
 #else
 
diff --git a/mm/migrate.c b/mm/migrate.c
index a91ca00abebe..34d8ada053e4 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -761,7 +761,8 @@ static struct page *new_page_node(struct page *p, unsigned long private,
 
         *result = &pm->status;
 
-        return alloc_pages_node(pm->node, GFP_HIGHUSER | GFP_THISNODE, 0);
+        return alloc_pages_node(pm->node,
+                                GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
 }
 
 /*
diff --git a/mm/shmem.c b/mm/shmem.c
index 0493e4d0bcaa..e49181d9d893 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -93,8 +93,11 @@ static inline struct page *shmem_dir_alloc(gfp_t gfp_mask)
          * The above definition of ENTRIES_PER_PAGE, and the use of
          * BLOCKS_PER_PAGE on indirect pages, assume PAGE_CACHE_SIZE:
          * might be reconsidered if it ever diverges from PAGE_SIZE.
+         *
+         * __GFP_MOVABLE is masked out as swap vectors cannot move
          */
-        return alloc_pages(gfp_mask, PAGE_CACHE_SHIFT-PAGE_SHIFT);
+        return alloc_pages((gfp_mask & ~__GFP_MOVABLE) | __GFP_ZERO,
+                                PAGE_CACHE_SHIFT-PAGE_SHIFT);
 }
 
 static inline void shmem_dir_free(struct page *page)
@@ -372,7 +375,7 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long
                 }
 
                 spin_unlock(&info->lock);
-                page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping) | __GFP_ZERO);
+                page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping));
                 if (page)
                         set_page_private(page, 0);
                 spin_lock(&info->lock);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 925d5c50f18d..67daecb6031a 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -334,7 +334,8 @@ struct page *read_swap_cache_async(swp_entry_t entry,
                  * Get a new page to read into from swap.
                  */
                 if (!new_page) {
-                        new_page = alloc_page_vma(GFP_HIGHUSER, vma, addr);
+                        new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE,
+                                                                vma, addr);
                         if (!new_page)
                                 break;          /* Out of memory */
                 }