jbd2: jbd2_log_wait_for_space improve error detetcion

If EIO happens after we have dropped j_state_lock, we won't notice
that the journal has been aborted.  So it is reasonable to move this
check after we have grabbed the j_checkpoint_mutex and re-grabbed the
j_state_lock.  This patch helps to prevent false positive complain
after EIO.

#DMESG:
__jbd2_log_wait_for_space: needed 8448 blocks and only had 8386 space available
__jbd2_log_wait_for_space: no way to get more journal space in ram1-8
------------[ cut here ]------------
WARNING: CPU: 15 PID: 6739 at fs/jbd2/checkpoint.c:168 __jbd2_log_wait_for_space+0x188/0x200()
Modules linked in: brd iTCO_wdt lpc_ich mfd_core igb ptp dm_mirror dm_region_hash dm_log dm_mod
CPU: 15 PID: 6739 Comm: fsstress Tainted: G        W      3.17.0-rc2-00429-g684de57 #139
Hardware name: Intel Corporation W2600CR/W2600CR, BIOS SE5C600.86B.99.99.x028.061320111235 06/13/2011
 00000000000000a8 ffff88077aaab878 ffffffff815c1a8c 00000000000000a8
 0000000000000000 ffff88077aaab8b8 ffffffff8106ce8c ffff88077aaab898
 ffff8807c57e6000 ffff8807c57e6028 0000000000002100 ffff8807c57e62f0
Call Trace:
 [<ffffffff815c1a8c>] dump_stack+0x51/0x6d
 [<ffffffff8106ce8c>] warn_slowpath_common+0x8c/0xc0
 [<ffffffff8106ceda>] warn_slowpath_null+0x1a/0x20
 [<ffffffff812419f8>] __jbd2_log_wait_for_space+0x188/0x200
 [<ffffffff8123be9a>] start_this_handle+0x4da/0x7b0
 [<ffffffff810990e5>] ? local_clock+0x25/0x30
 [<ffffffff810aba87>] ? lockdep_init_map+0xe7/0x180
 [<ffffffff8123c5bc>] jbd2__journal_start+0xdc/0x1d0
 [<ffffffff811f2414>] ? __ext4_new_inode+0x7f4/0x1330
 [<ffffffff81222a38>] __ext4_journal_start_sb+0xf8/0x110
 [<ffffffff811f2414>] __ext4_new_inode+0x7f4/0x1330
 [<ffffffff810ac359>] ? lock_release_holdtime+0x29/0x190
 [<ffffffff812025bb>] ext4_create+0x8b/0x150
 [<ffffffff8117fe3b>] vfs_create+0x7b/0xb0
 [<ffffffff8118097b>] do_last+0x7db/0xcf0
 [<ffffffff8117e31d>] ? inode_permission+0x4d/0x50
 [<ffffffff811845d2>] path_openat+0x242/0x590
 [<ffffffff81191a76>] ? __alloc_fd+0x36/0x140
 [<ffffffff81184a6a>] do_filp_open+0x4a/0xb0
 [<ffffffff81191b61>] ? __alloc_fd+0x121/0x140
 [<ffffffff81172f20>] do_sys_open+0x170/0x220
 [<ffffffff8117300e>] SyS_open+0x1e/0x20
 [<ffffffff811715d6>] SyS_creat+0x16/0x20
 [<ffffffff815c7e12>] system_call_fastpath+0x16/0x1b
---[ end trace cd71c831f82059db ]---

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 9ffb19cf376b47cc57eafd38b67a1d534048827f..1fbf59938cc0f71cefcddebf3e36650bfcf36dd5 100644 (file)
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -115,8 +115,6 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 
        nblocks = jbd2_space_needed(journal);
        while (jbd2_log_space_left(journal) < nblocks) {
-               if (journal->j_flags & JBD2_ABORT)
-                       return;
                write_unlock(&journal->j_state_lock);
                mutex_lock(&journal->j_checkpoint_mutex);
 
@@ -132,6 +130,10 @@ void __jbd2_log_wait_for_space(journal_t *journal)
                 * trace for forensic evidence.
                 */
                write_lock(&journal->j_state_lock);
+               if (journal->j_flags & JBD2_ABORT) {
+                       mutex_unlock(&journal->j_checkpoint_mutex);
+                       return;
+               }
                spin_lock(&journal->j_list_lock);
                nblocks = jbd2_space_needed(journal);
                space_left = jbd2_log_space_left(journal);