From 8a5c743e308dd2b90ad10d1faaa7a1b09173a132 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 26 Jul 2016 15:24:53 -0700 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. [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 Cc: Vladimir Davydov Cc: Chris Mason Cc: Steve French Cc: Theodore Ts'o Cc: Jan Kara Cc: Mike Marshall Cc: Jaegeuk Kim Cc: Changman Lee Cc: Chao Yu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/mpage.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'fs/mpage.c') diff --git a/fs/mpage.c b/fs/mpage.c index eedc644b78d7..c8a05901a37b 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -71,6 +71,8 @@ mpage_alloc(struct block_device *bdev, { struct bio *bio; + /* Restrict the given (page cache) mask for slab allocations */ + gfp_flags &= GFP_KERNEL; bio = bio_alloc(gfp_flags, nr_vecs); if (bio == NULL && (current->flags & PF_MEMALLOC)) { @@ -362,7 +364,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, 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; -- cgit v1.2.3-55-g7522