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>
diff --git a/mm/memory.c b/mm/memory.c
index b3d73bb..9c6ff7f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1715,11 +1715,11 @@
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 @@
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 @@
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 188f8d9..4c0f999 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -594,7 +594,7 @@
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 @@
{
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 a91ca00..34d8ada 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -761,7 +761,8 @@
*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 0493e4d..e49181d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -93,8 +93,11 @@
* 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 @@
}
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 925d5c5..67daecb 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -334,7 +334,8 @@
* 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 */
}