f2fs: fix the panic in do_checkpoint()

There could be a scenario where f2fs_sync_meta_pages() will not
ensure that all F2FS_DIRTY_META pages are submitted for IO. Thus,
resulting in the below panic in do_checkpoint() -

f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
				!f2fs_cp_error(sbi));

This can happen in a low-memory condition, where shrinker could
also be doing the writepage operation (stack shown below)
at the same time when checkpoint is running on another core.

schedule
down_write
f2fs_submit_page_write -> by this time, this page in page cache is tagged
			as PAGECACHE_TAG_WRITEBACK and PAGECACHE_TAG_DIRTY
			is cleared, due to which f2fs_sync_meta_pages()
			cannot sync this page in do_checkpoint() path.
f2fs_do_write_meta_page
__f2fs_write_meta_page
f2fs_write_meta_page
shrink_page_list
shrink_inactive_list
shrink_node_memcg
shrink_node
kswapd

Signed-off-by: Sahitya Tummala <stummala@codeaurora.org>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This commit is contained in:
Sahitya Tummala 2020-02-18 09:19:07 +05:30 committed by Jaegeuk Kim
parent dc5a941223
commit bf22c3cc8c
3 changed files with 9 additions and 11 deletions

View File

@ -1250,20 +1250,20 @@ static void unblock_operations(struct f2fs_sb_info *sbi)
f2fs_unlock_all(sbi);
}
void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type)
{
DEFINE_WAIT(wait);
for (;;) {
prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
if (!get_pages(sbi, F2FS_WB_CP_DATA))
if (!get_pages(sbi, type))
break;
if (unlikely(f2fs_cp_error(sbi)))
break;
io_schedule_timeout(5*HZ);
io_schedule_timeout(HZ/50);
}
finish_wait(&sbi->cp_wait, &wait);
}
@ -1384,8 +1384,6 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* Flush all the NAT/SIT pages */
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
!f2fs_cp_error(sbi));
/*
* modify checkpoint
@ -1493,11 +1491,11 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* Here, we have one bio having CP pack except cp pack 2 page */
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
!f2fs_cp_error(sbi));
/* Wait for all dirty meta pages to be submitted for IO */
f2fs_wait_on_all_pages(sbi, F2FS_DIRTY_META);
/* wait for previous submitted meta pages writeback */
f2fs_wait_on_all_pages_writeback(sbi);
f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
/* flush all device cache */
err = f2fs_flush_device_cache(sbi);
@ -1506,7 +1504,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* barrier and flush checkpoint cp pack 2 page if it can */
commit_checkpoint(sbi, ckpt, start_blk);
f2fs_wait_on_all_pages_writeback(sbi);
f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
/*
* invalidate intermediate page cache borrowed from meta inode which are

View File

@ -3308,7 +3308,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi);
void f2fs_update_dirty_page(struct inode *inode, struct page *page);
void f2fs_remove_dirty_inode(struct inode *inode);
int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi);
void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type);
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_checkpoint_caches(void);

View File

@ -1172,7 +1172,7 @@ static void f2fs_put_super(struct super_block *sb)
/* our cp_error case, we can wait for any writeback page */
f2fs_flush_merged_writes(sbi);
f2fs_wait_on_all_pages_writeback(sbi);
f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
f2fs_bug_on(sbi, sbi->fsync_node_num);