From e5d25003d059649e18a249635ed5ca7a7b1de5ad Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 19 Feb 2020 10:30:47 -0800 Subject: [PATCH] ext4: fix race between writepages and enabling EXT4_EXTENTS_FL commit cb85f4d23f794e24127f3e562cb3b54b0803f456 upstream. If EXT4_EXTENTS_FL is set on an inode while ext4_writepages() is running on it, the following warning in ext4_add_complete_io() can be hit: WARNING: CPU: 1 PID: 0 at fs/ext4/page-io.c:234 ext4_put_io_end_defer+0xf0/0x120 Here's a minimal reproducer (not 100% reliable) (root isn't required): while true; do sync done & while true; do rm -f file touch file chattr -e file echo X >> file chattr +e file done The problem is that in ext4_writepages(), ext4_should_dioread_nolock() (which only returns true on extent-based files) is checked once to set the number of reserved journal credits, and also again later to select the flags for ext4_map_blocks() and copy the reserved journal handle to ext4_io_end::handle. But if EXT4_EXTENTS_FL is being concurrently set, the first check can see dioread_nolock disabled while the later one can see it enabled, causing the reserved handle to unexpectedly be NULL. Since changing EXT4_EXTENTS_FL is uncommon, and there may be other races related to doing so as well, fix this by synchronizing changing EXT4_EXTENTS_FL with ext4_writepages() via the existing s_writepages_rwsem (previously called s_journal_flag_rwsem). This was originally reported by syzbot without a reproducer at https://syzkaller.appspot.com/bug?extid=2202a584a00fffd19fbf, but now that dioread_nolock is the default I also started seeing this when running syzkaller locally. Link: https://lore.kernel.org/r/20200219183047.47417-3-ebiggers@kernel.org Reported-by: syzbot+2202a584a00fffd19fbf@syzkaller.appspotmail.com Fixes: 6b523df4fb5a ("ext4: use transaction reservation for extent conversion in ext4_end_io") Signed-off-by: Eric Biggers Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/ext4.h | 5 ++++- fs/ext4/migrate.c | 27 +++++++++++++++++++-------- 2 files changed, 23 insertions(+), 9 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c97e7ae53d10..d576addfdd03 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1548,7 +1548,10 @@ struct ext4_sb_info { struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; - /* Barrier between changing inodes' journal flags and writepages ops. */ + /* + * Barrier between writepages ops and changing any inode's JOURNAL_DATA + * or EXTENTS flag. + */ struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; }; diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index b1e4d359f73b..be4ee3dcc5cf 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -427,6 +427,7 @@ static int free_ext_block(handle_t *handle, struct inode *inode) int ext4_ext_migrate(struct inode *inode) { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; int retval = 0, i; __le32 *i_data; @@ -451,6 +452,8 @@ int ext4_ext_migrate(struct inode *inode) */ return retval; + percpu_down_write(&sbi->s_writepages_rwsem); + /* * Worst case we can touch the allocation bitmaps, a bgd * block, and a block to link in the orphan list. We do need @@ -461,7 +464,7 @@ int ext4_ext_migrate(struct inode *inode) if (IS_ERR(handle)) { retval = PTR_ERR(handle); - return retval; + goto out_unlock; } goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) * EXT4_INODES_PER_GROUP(inode->i_sb)) + 1; @@ -472,7 +475,7 @@ int ext4_ext_migrate(struct inode *inode) if (IS_ERR(tmp_inode)) { retval = PTR_ERR(tmp_inode); ext4_journal_stop(handle); - return retval; + goto out_unlock; } i_size_write(tmp_inode, i_size_read(inode)); /* @@ -514,7 +517,7 @@ int ext4_ext_migrate(struct inode *inode) */ ext4_orphan_del(NULL, tmp_inode); retval = PTR_ERR(handle); - goto out; + goto out_tmp_inode; } ei = EXT4_I(inode); @@ -595,10 +598,11 @@ err_out: /* Reset the extent details */ ext4_ext_tree_init(handle, tmp_inode); ext4_journal_stop(handle); -out: +out_tmp_inode: unlock_new_inode(tmp_inode); iput(tmp_inode); - +out_unlock: + percpu_up_write(&sbi->s_writepages_rwsem); return retval; } @@ -608,7 +612,8 @@ out: int ext4_ind_migrate(struct inode *inode) { struct ext4_extent_header *eh; - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_super_block *es = sbi->s_es; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_extent *ex; unsigned int i, len; @@ -632,9 +637,13 @@ int ext4_ind_migrate(struct inode *inode) if (test_opt(inode->i_sb, DELALLOC)) ext4_alloc_da_blocks(inode); + percpu_down_write(&sbi->s_writepages_rwsem); + handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out_unlock; + } down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_check_inode(inode); @@ -669,5 +678,7 @@ int ext4_ind_migrate(struct inode *inode) errout: ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); +out_unlock: + percpu_up_write(&sbi->s_writepages_rwsem); return ret; }