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/btrfs/extent_io.c | 3 ++- fs/cifs/file.c | 2 +- fs/ext4/readpage.c | 2 +- fs/f2fs/data.c | 3 ++- fs/mpage.c | 4 +++- fs/orangefs/inode.c | 2 +- 6 files changed, 10 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 75533adef998..e91d55837dd2 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4180,7 +4180,8 @@ int extent_readpages(struct extent_io_tree *tree, 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 --git a/fs/cifs/file.c b/fs/cifs/file.c index d4890b6dc22d..579e41b350a2 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3366,7 +3366,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, 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 --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index dc54a4b60eba..c75b66a64982 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -166,7 +166,7 @@ int ext4_mpage_readpages(struct address_space *mapping, 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 --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9a8bbc1fb1fa..c80dda4bdff8 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -996,7 +996,8 @@ static int f2fs_mpage_readpages(struct address_space *mapping, 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 --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; diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 85640e955cde..06a8da75651d 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -80,7 +80,7 @@ static int orangefs_readpages(struct file *file, 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", -- cgit v1.2.3