+ mm-memcg-use-consistent-gfp-flags-during-readahead.patch added to -mm tree

[akpm@linux-foundation.org]

The patch titled
     Subject: mm, memcg: use consistent gfp flags during readahead
has been added to the -mm tree.  Its filename is
     mm-memcg-use-consistent-gfp-flags-during-readahead.patch

This patch should soon appear at
    http://ozlabs.org/~akpm/mmots/broken-out/mm-memcg-use-consistent-gfp-flags-during-readahead.patch
and later at
    http://ozlabs.org/~akpm/mmotm/broken-out/mm-memcg-use-consistent-gfp-flags-during-readahead.patch

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/SubmitChecklist when testing your code ***

The -mm tree is included into linux-next and is updated
there every 3-4 working days

------------------------------------------------------
From: Michal Hocko <mhocko@suse.com>
Subject: mm, memcg: use consistent gfp flags during readahead

Vladimir has noticed that we might declare memcg oom even during readahead
because read_pages only uses GFP_KERNEL (with mapping_gfp restriction)
while __do_page_cache_readahead uses page_cache_alloc_readahead which adds
__GFP_NORETRY to prevent from OOMs.  This gfp mask discrepancy is really
unfortunate and easily fixable.  Drop page_cache_alloc_readahead() which
only has one user and outsource the gfp_mask logic into readahead_gfp_mask
and propagate this mask from __do_page_cache_readahead down to read_pages.

This alone would have only very limited impact as most filesystems are
implementing ->readpages and the common implementation mpage_readpages
does GFP_KERNEL (with mapping_gfp restriction) again.  We can tell it to
use readahead_gfp_mask instead as this function is called only during
readahead as well.  The same applies to read_cache_pages.

ext4 has its own ext4_mpage_readpages but the path which has pages != NULL
can use the same gfp mask.  Btrfs, cifs, f2fs and orangefs are doing a
very similar pattern to mpage_readpages so the same can be applied to them
as well.

Link: http://lkml.kernel.org/r/1465301556-26431-1-git-send-email-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Chris Mason <clm@fb.com>
Cc: Steve French <sfrench@samba.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Jan Kara <jack@suse.cz>
Cc: Mike Marshall <hubcap@omnibond.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Changman Lee <cm224.lee@samsung.com>
Cc: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 fs/btrfs/extent_io.c    |    3 ++-
 fs/cifs/file.c          |    2 +-
 fs/ext4/readpage.c      |    2 +-
 fs/f2fs/data.c          |    3 ++-
 fs/mpage.c              |    2 +-
 fs/orangefs/inode.c     |    2 +-
 include/linux/pagemap.h |    6 +++---
 mm/readahead.c          |   12 ++++++------
 8 files changed, 17 insertions(+), 15 deletions(-)

diff -puN fs/btrfs/extent_io.c~mm-memcg-use-consistent-gfp-flags-during-readahead fs/btrfs/extent_io.c
--- a/fs/btrfs/extent_io.c~mm-memcg-use-consistent-gfp-flags-during-readahead
+++ a/fs/btrfs/extent_io.c
@@ -4180,7 +4180,8 @@ int extent_readpages(struct extent_io_tr
 		prefetchw(&page->flags);
 		list_del(&page->lru);
 		if (add_to_page_cache_lru(page, mapping,
-					page->index, GFP_NOFS)) {
+					page->index,
+					readahead_gfp_mask(mapping))) {
 			put_page(page);
 			continue;
 		}
diff -puN fs/cifs/file.c~mm-memcg-use-consistent-gfp-flags-during-readahead fs/cifs/file.c
--- a/fs/cifs/file.c~mm-memcg-use-consistent-gfp-flags-during-readahead
+++ a/fs/cifs/file.c
@@ -3358,7 +3358,7 @@ readpages_get_pages(struct address_space
 	struct page *page, *tpage;
 	unsigned int expected_index;
 	int rc;
-	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
+	gfp_t gfp = readahead_gfp_mask(mapping);
 
 	INIT_LIST_HEAD(tmplist);
 
diff -puN fs/ext4/readpage.c~mm-memcg-use-consistent-gfp-flags-during-readahead fs/ext4/readpage.c
--- a/fs/ext4/readpage.c~mm-memcg-use-consistent-gfp-flags-during-readahead
+++ a/fs/ext4/readpage.c
@@ -166,7 +166,7 @@ int ext4_mpage_readpages(struct address_
 			page = list_entry(pages->prev, struct page, lru);
 			list_del(&page->lru);
 			if (add_to_page_cache_lru(page, mapping, page->index,
-				  mapping_gfp_constraint(mapping, GFP_KERNEL)))
+				  readahead_gfp_mask(mapping)))
 				goto next_page;
 		}
 
diff -puN fs/f2fs/data.c~mm-memcg-use-consistent-gfp-flags-during-readahead fs/f2fs/data.c
--- a/fs/f2fs/data.c~mm-memcg-use-consistent-gfp-flags-during-readahead
+++ a/fs/f2fs/data.c
@@ -996,7 +996,8 @@ static int f2fs_mpage_readpages(struct a
 			page = list_entry(pages->prev, struct page, lru);
 			list_del(&page->lru);
 			if (add_to_page_cache_lru(page, mapping,
-						  page->index, GFP_KERNEL))
+						  page->index,
+						  readahead_gfp_mask(mapping)))
 				goto next_page;
 		}
 
diff -puN fs/mpage.c~mm-memcg-use-consistent-gfp-flags-during-readahead fs/mpage.c
--- a/fs/mpage.c~mm-memcg-use-consistent-gfp-flags-during-readahead
+++ a/fs/mpage.c
@@ -362,7 +362,7 @@ mpage_readpages(struct address_space *ma
 	sector_t last_block_in_bio = 0;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
-	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
+	gfp_t gfp = readahead_gfp_mask(mapping);
 
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;
diff -puN fs/orangefs/inode.c~mm-memcg-use-consistent-gfp-flags-during-readahead fs/orangefs/inode.c
--- a/fs/orangefs/inode.c~mm-memcg-use-consistent-gfp-flags-during-readahead
+++ a/fs/orangefs/inode.c
@@ -80,7 +80,7 @@ static int orangefs_readpages(struct fil
 		if (!add_to_page_cache(page,
 				       mapping,
 				       page->index,
-				       GFP_KERNEL)) {
+				       readahead_gfp_mask(mapping))) {
 			ret = read_one_page(page);
 			gossip_debug(GOSSIP_INODE_DEBUG,
 				"failure adding page to cache, read_one_page returned: %d\n",
diff -puN include/linux/pagemap.h~mm-memcg-use-consistent-gfp-flags-during-readahead include/linux/pagemap.h
--- a/include/linux/pagemap.h~mm-memcg-use-consistent-gfp-flags-during-readahead
+++ a/include/linux/pagemap.h
@@ -209,10 +209,10 @@ static inline struct page *page_cache_al
 	return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD);
 }
 
-static inline struct page *page_cache_alloc_readahead(struct address_space *x)
+static inline gfp_t readahead_gfp_mask(struct address_space *x)
 {
-	return __page_cache_alloc(mapping_gfp_mask(x) |
-				  __GFP_COLD | __GFP_NORETRY | __GFP_NOWARN);
+	return mapping_gfp_mask(x) |
+				  __GFP_COLD | __GFP_NORETRY | __GFP_NOWARN;
 }
 
 typedef int filler_t(void *, struct page *);
diff -puN mm/readahead.c~mm-memcg-use-consistent-gfp-flags-during-readahead mm/readahead.c
--- a/mm/readahead.c~mm-memcg-use-consistent-gfp-flags-during-readahead
+++ a/mm/readahead.c
@@ -89,7 +89,7 @@ int read_cache_pages(struct address_spac
 		page = lru_to_page(pages);
 		list_del(&page->lru);
 		if (add_to_page_cache_lru(page, mapping, page->index,
-				mapping_gfp_constraint(mapping, GFP_KERNEL))) {
+				readahead_gfp_mask(mapping))) {
 			read_cache_pages_invalidate_page(mapping, page);
 			continue;
 		}
@@ -108,7 +108,7 @@ int read_cache_pages(struct address_spac
 EXPORT_SYMBOL(read_cache_pages);
 
 static int read_pages(struct address_space *mapping, struct file *filp,
-		struct list_head *pages, unsigned nr_pages)
+		struct list_head *pages, unsigned nr_pages, gfp_t gfp_mask)
 {
 	struct blk_plug plug;
 	unsigned page_idx;
@@ -126,8 +126,7 @@ static int read_pages(struct address_spa
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		struct page *page = lru_to_page(pages);
 		list_del(&page->lru);
-		if (!add_to_page_cache_lru(page, mapping, page->index,
-				mapping_gfp_constraint(mapping, GFP_KERNEL))) {
+		if (!add_to_page_cache_lru(page, mapping, page->index, gfp_mask)) {
 			mapping->a_ops->readpage(filp, page);
 		}
 		put_page(page);
@@ -159,6 +158,7 @@ int __do_page_cache_readahead(struct add
 	int page_idx;
 	int ret = 0;
 	loff_t isize = i_size_read(inode);
+	gfp_t gfp_mask = readahead_gfp_mask(mapping);
 
 	if (isize == 0)
 		goto out;
@@ -180,7 +180,7 @@ int __do_page_cache_readahead(struct add
 		if (page && !radix_tree_exceptional_entry(page))
 			continue;
 
-		page = page_cache_alloc_readahead(mapping);
+		page = __page_cache_alloc(gfp_mask);
 		if (!page)
 			break;
 		page->index = page_offset;
@@ -196,7 +196,7 @@ int __do_page_cache_readahead(struct add
 	 * will then handle the error.
 	 */
 	if (ret)
-		read_pages(mapping, filp, &page_pool, ret);
+		read_pages(mapping, filp, &page_pool, ret, gfp_mask);
 	BUG_ON(!list_empty(&page_pool));
 out:
 	return ret;
_

Patches currently in -mm which might be from mhocko@suse.com are

tree-wide-get-rid-of-__gfp_repeat-for-order-0-allocations-part-i.patch
x86-get-rid-of-superfluous-__gfp_repeat.patch
x86-efi-get-rid-of-superfluous-__gfp_repeat.patch
arm-get-rid-of-superfluous-__gfp_repeat.patch
arm64-get-rid-of-superfluous-__gfp_repeat.patch
arc-get-rid-of-superfluous-__gfp_repeat.patch
mips-get-rid-of-superfluous-__gfp_repeat.patch
nios2-get-rid-of-superfluous-__gfp_repeat.patch
parisc-get-rid-of-superfluous-__gfp_repeat.patch
score-get-rid-of-superfluous-__gfp_repeat.patch
powerpc-get-rid-of-superfluous-__gfp_repeat.patch
sparc-get-rid-of-superfluous-__gfp_repeat.patch
s390-get-rid-of-superfluous-__gfp_repeat.patch
sh-get-rid-of-superfluous-__gfp_repeat.patch
tile-get-rid-of-superfluous-__gfp_repeat.patch
unicore32-get-rid-of-superfluous-__gfp_repeat.patch
jbd2-get-rid-of-superfluous-__gfp_repeat.patch
mm-oom_reaper-make-sure-that-mmput_async-is-called-only-when-memory-was-reaped.patch
mm-memcg-use-consistent-gfp-flags-during-readahead.patch