Messages in this thread Patch in this message | | | From | Jaegeuk Kim <> | Subject | [PATCH 2/3] f2fs: fix deadlock to grab 0'th data page | Date | Thu, 13 Nov 2014 16:59:33 -0800 |
| |
The scenario is like this.
One trhead triggers: f2fs_write_data_pages lock_page f2fs_write_data_page f2fs_lock_op <- wait
The other thread triggers: f2fs_truncate truncate_blocks f2fs_lock_op truncate_partial_data_page lock_page <- wait for locking the page
This patch resolves this bug by relocating truncate_partial_data_page. This function is just to truncate user data page and not related to FS consistency as well. And, we don't need to call truncate_inline_data. Rather than that, f2fs_write_data_page will finally update inline_data later.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> --- fs/f2fs/file.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 54722a0..edc3ce8 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -477,8 +477,6 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) } if (f2fs_has_inline_data(inode)) { - truncate_inline_data(ipage, from); - update_inode(inode, ipage); f2fs_put_page(ipage, 1); goto out; } @@ -504,13 +502,13 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) f2fs_put_dnode(&dn); free_next: err = truncate_inode_blocks(inode, free_from); +out: + if (lock) + f2fs_unlock_op(sbi); /* lastly zero out the first data page */ if (!err) err = truncate_partial_data_page(inode, from); -out: - if (lock) - f2fs_unlock_op(sbi); trace_f2fs_truncate_blocks_exit(inode, err); return err; -- 2.1.1
| |