From 6c5d911249290f41f7b50b43344a7520605b1acb Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 21 Feb 2020 23:31:11 -0500 Subject: jbd2: fix data races at struct journal_head journal_head::b_transaction and journal_head::b_next_transaction could be accessed concurrently as noticed by KCSAN, LTP: starting fsync04 /dev/zero: Can't open blockdev EXT4-fs (loop0): mounting ext3 file system using the ext4 subsystem EXT4-fs (loop0): mounted filesystem with ordered data mode. Opts: (null) ================================================================== BUG: KCSAN: data-race in __jbd2_journal_refile_buffer [jbd2] / jbd2_write_access_granted [jbd2] write to 0xffff99f9b1bd0e30 of 8 bytes by task 25721 on cpu 70: __jbd2_journal_refile_buffer+0xdd/0x210 [jbd2] __jbd2_journal_refile_buffer at fs/jbd2/transaction.c:2569 jbd2_journal_commit_transaction+0x2d15/0x3f20 [jbd2] (inlined by) jbd2_journal_commit_transaction at fs/jbd2/commit.c:1034 kjournald2+0x13b/0x450 [jbd2] kthread+0x1cd/0x1f0 ret_from_fork+0x27/0x50 read to 0xffff99f9b1bd0e30 of 8 bytes by task 25724 on cpu 68: jbd2_write_access_granted+0x1b2/0x250 [jbd2] jbd2_write_access_granted at fs/jbd2/transaction.c:1155 jbd2_journal_get_write_access+0x2c/0x60 [jbd2] __ext4_journal_get_write_access+0x50/0x90 [ext4] ext4_mb_mark_diskspace_used+0x158/0x620 [ext4] ext4_mb_new_blocks+0x54f/0xca0 [ext4] ext4_ind_map_blocks+0xc79/0x1b40 [ext4] ext4_map_blocks+0x3b4/0x950 [ext4] _ext4_get_block+0xfc/0x270 [ext4] ext4_get_block+0x3b/0x50 [ext4] __block_write_begin_int+0x22e/0xae0 __block_write_begin+0x39/0x50 ext4_write_begin+0x388/0xb50 [ext4] generic_perform_write+0x15d/0x290 ext4_buffered_write_iter+0x11f/0x210 [ext4] ext4_file_write_iter+0xce/0x9e0 [ext4] new_sync_write+0x29c/0x3b0 __vfs_write+0x92/0xa0 vfs_write+0x103/0x260 ksys_write+0x9d/0x130 __x64_sys_write+0x4c/0x60 do_syscall_64+0x91/0xb05 entry_SYSCALL_64_after_hwframe+0x49/0xbe 5 locks held by fsync04/25724: #0: ffff99f9911093f8 (sb_writers#13){.+.+}, at: vfs_write+0x21c/0x260 #1: ffff99f9db4c0348 (&sb->s_type->i_mutex_key#15){+.+.}, at: ext4_buffered_write_iter+0x65/0x210 [ext4] #2: ffff99f5e7dfcf58 (jbd2_handle){++++}, at: start_this_handle+0x1c1/0x9d0 [jbd2] #3: ffff99f9db4c0168 (&ei->i_data_sem){++++}, at: ext4_map_blocks+0x176/0x950 [ext4] #4: ffffffff99086b40 (rcu_read_lock){....}, at: jbd2_write_access_granted+0x4e/0x250 [jbd2] irq event stamp: 1407125 hardirqs last enabled at (1407125): [] __find_get_block+0x107/0x790 hardirqs last disabled at (1407124): [] __find_get_block+0x49/0x790 softirqs last enabled at (1405528): [] __do_softirq+0x34c/0x57c softirqs last disabled at (1405521): [] irq_exit+0xa2/0xc0 Reported by Kernel Concurrency Sanitizer on: CPU: 68 PID: 25724 Comm: fsync04 Tainted: G L 5.6.0-rc2-next-20200221+ #7 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019 The plain reads are outside of jh->b_state_lock critical section which result in data races. Fix them by adding pairs of READ|WRITE_ONCE(). Reviewed-by: Jan Kara Signed-off-by: Qian Cai Link: https://lore.kernel.org/r/20200222043111.2227-1-cai@lca.pw Signed-off-by: Theodore Ts'o --- fs/jbd2/transaction.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index d181948c0390..3dccc23cf010 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1150,8 +1150,8 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, /* For undo access buffer must have data copied */ if (undo && !jh->b_committed_data) goto out; - if (jh->b_transaction != handle->h_transaction && - jh->b_next_transaction != handle->h_transaction) + if (READ_ONCE(jh->b_transaction) != handle->h_transaction && + READ_ONCE(jh->b_next_transaction) != handle->h_transaction) goto out; /* * There are two reasons for the barrier here: @@ -2569,8 +2569,8 @@ bool __jbd2_journal_refile_buffer(struct journal_head *jh) * our jh reference and thus __jbd2_journal_file_buffer() must not * take a new one. */ - jh->b_transaction = jh->b_next_transaction; - jh->b_next_transaction = NULL; + WRITE_ONCE(jh->b_transaction, jh->b_next_transaction); + WRITE_ONCE(jh->b_next_transaction, NULL); if (buffer_freed(bh)) jlist = BJ_Forget; else if (jh->b_modified) -- cgit v1.2.3