f2fs: handle errors of f2fs_get_meta_page_nofail

First problem is we hit BUG_ON() in f2fs_get_sum_page given EIO on
f2fs_get_meta_page_nofail().

Quick fix was not to give any error with infinite loop, but syzbot caught
a case where it goes to that loop from fuzzed image. In turned out we abused
f2fs_get_meta_page_nofail() like in the below call stack.

- f2fs_fill_super
 - f2fs_build_segment_manager
  - build_sit_entries
   - get_current_sit_page

INFO: task syz-executor178:6870 can't die for more than 143 seconds.
task:syz-executor178 state:R
 stack:26960 pid: 6870 ppid:  6869 flags:0x00004006
Call Trace:

Showing all locks held in the system:
1 lock held by khungtaskd/1179:
 #0: ffffffff8a554da0 (rcu_read_lock){....}-{1:2}, at: debug_show_all_locks+0x53/0x260 kernel/locking/lockdep.c:6242
1 lock held by systemd-journal/3920:
1 lock held by in:imklog/6769:
 #0: ffff88809eebc130 (&f->f_pos_lock){+.+.}-{3:3}, at: __fdget_pos+0xe9/0x100 fs/file.c:930
1 lock held by syz-executor178/6870:
 #0: ffff8880925120e0 (&type->s_umount_key#47/1){+.+.}-{3:3}, at: alloc_super+0x201/0xaf0 fs/super.c:229

Actually, we didn't have to use _nofail in this case, since we could return
error to mount(2) already with the error handler.

As a result, this patch tries to 1) remove _nofail callers as much as possible,
2) deal with error case in last remaining caller, f2fs_get_sum_page().

Reported-by: syzbot+ee250ac8137be41d7b13@syzkaller.appspotmail.com
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index f18386d30f031ebeddfa009850ad373843bec98e..023462e80e58d5150f3a8e33d015689469205b11 100644 (file)
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -107,7 +107,7 @@ struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
        return __get_meta_page(sbi, index, true);
 }
 
-struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index)
+struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index)
 {
        struct page *page;
        int count = 0;

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index ae46d44bd5211873978ae460b098d159e1ced767..adda53d20a39984488c1000df5140f43a9ab0bea 100644 (file)
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3422,7 +3422,7 @@ unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
 void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
 struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
 struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
-struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index);
 struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
 bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
                                        block_t blkaddr, int type);

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 93fb34d636eb579073a8dd47c3e17450d48d4415..d5d8ce077f2959a7eb99c695983d9aa3e4972b06 100644 (file)
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -109,7 +109,7 @@ static void clear_node_page_dirty(struct page *page)
 
 static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
 {
-       return f2fs_get_meta_page_nofail(sbi, current_nat_addr(sbi, nid));
+       return f2fs_get_meta_page(sbi, current_nat_addr(sbi, nid));
 }
 
 static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 13ecd2c2c361bd92d981d03d37f66cd5a4e115de..05ab5ae2b5f7f06e303c3040bda11e4d6ac19d00 100644 (file)
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -2379,7 +2379,9 @@ int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
  */
 struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
 {
-       return f2fs_get_meta_page_nofail(sbi, GET_SUM_BLOCK(sbi, segno));
+       if (unlikely(f2fs_cp_error(sbi)))
+               return ERR_PTR(-EIO);
+       return f2fs_get_meta_page_retry(sbi, GET_SUM_BLOCK(sbi, segno));
 }
 
 void f2fs_update_meta_page(struct f2fs_sb_info *sbi,
@@ -2669,7 +2671,11 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type, bool flush)
        __next_free_blkoff(sbi, curseg, 0);
 
        sum_page = f2fs_get_sum_page(sbi, new_segno);
-       f2fs_bug_on(sbi, IS_ERR(sum_page));
+       if (IS_ERR(sum_page)) {
+               /* GC won't be able to use stale summary pages by cp_error */
+               memset(curseg->sum_blk, 0, SUM_ENTRY_SIZE);
+               return;
+       }
        sum_node = (struct f2fs_summary_block *)page_address(sum_page);
        memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
        f2fs_put_page(sum_page, 1);
@@ -3964,7 +3970,7 @@ int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
 static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
                                        unsigned int segno)
 {
-       return f2fs_get_meta_page_nofail(sbi, current_sit_addr(sbi, segno));
+       return f2fs_get_meta_page(sbi, current_sit_addr(sbi, segno));
 }
 
 static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,