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.

[akpm@linux-foundation.org: coding-style fixes]
[mhocko@suse.com: restrict gfp mask in mpage_alloc]
  Link: http://lkml.kernel.org/r/20160610074223.GC32285@dhcp22.suse.cz
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>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 6 insertions, 7 deletions

diff --git a/mm/readahead.c b/mm/readahead.c
index 40be3ae..65ec288 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -89,7 +89,7 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
 		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_space *mapping, struct list_head *pages,
 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 int nr_pages, gfp_t gfp)
 {
 	struct blk_plug plug;
 	unsigned page_idx;
@@ -126,10 +126,8 @@ static int read_pages(struct address_space *mapping, struct file *filp,
 	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))
 			mapping->a_ops->readpage(filp, page);
-		}
 		put_page(page);
 	}
 	ret = 0;
@@ -159,6 +157,7 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 	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 +179,7 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 		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 +195,7 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 	 * 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;