gfs2: wait for recovery log bios in sync recovery
PATCH 1/1 gfs2: wait for recovery log bios in sync recovery
[BUG]
Mounting a fuzzed image can recover journal 0 and queue clean_journal()'s log-header bio, then fail recovering journal 1 on corrupted metadata. The mount unwind frees struct gfs2_sbd, and the delayed bio completion later reports:
BUG: KASAN: slab-use-after-free in instrument_atomic_read_write include/linux/instrumented.h:96 [inline] BUG: KASAN: slab-use-after-free in atomic_dec_and_test include/linux/atomic/atomic-instrumented.h:1383 [inline] BUG: KASAN: slab-use-after-free in gfs2_end_log_write+0xe3/0x7c0 fs/gfs2/lops.c:230 Write of size 4 at addr ffff888012810e78 by task ublk.fsfuzz/334 __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0xbe/0x130 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xd1/0x650 mm/kasan/report.c:482 kasan_report+0xfb/0x140 mm/kasan/report.c:595 check_region_inline mm/kasan/generic.c:186 [inline] kasan_check_range+0x11c/0x200 mm/kasan/generic.c:200 __kasan_check_write+0x14/0x30 mm/kasan/shadow.c:37 instrument_atomic_read_write include/linux/instrumented.h:96 [inline] atomic_dec_and_test include/linux/atomic/atomic-instrumented.h:1383 [inline] gfs2_end_log_write+0xe3/0x7c0 fs/gfs2/lops.c:230 bio_endio+0x5e0/0x700 block/bio.c:1678 blk_update_request+0x7e5/0x14e0 block/blk-mq.c:998 blk_mq_end_request+0x61/0x3e0 block/blk-mq.c:1160 blk_flush_complete_seq+0x8f6/0xea0 block/blk-flush.c:191 mq_flush_data_end_io+0x2b1/0x550 block/blk-flush.c:362 __blk_mq_end_request+0x123/0x380 block/blk-mq.c:1150 __ublk_complete_rq drivers/block/ublk_drv.c:1202 [inline] ublk_ch_uring_cmd_local+0x1a5f/0x2180 drivers/block/ublk_drv.c:2478 ublk_ch_uring_cmd+0x42/0x640 drivers/block/ublk_drv.c:2562 io_uring_cmd+0x26f/0x570 io_uring/uring_cmd.c:263 __io_issue_sqe+0xc2/0x760 io_uring/io_uring.c:1826 io_issue_sqe+0xdd/0x11e0 io_uring/io_uring.c:1849 io_queue_sqe io_uring/io_uring.c:2076 [inline] io_submit_sqe io_uring/io_uring.c:2336 [inline] io_submit_sqes+0x806/0x2390 io_uring/io_uring.c:2449 __do_sys_io_uring_enter+0x5c0/0x13a0 io_uring/io_uring.c:3516 __se_sys_io_uring_enter io_uring/io_uring.c:3455 [inline] __x64_sys_io_uring_enter+0xe5/0x1c0 io_uring/io_uring.c:3455 x64_sys_call+0x2419/0x26a0 arch/x86/include/generated/asm/syscalls_64.h:427 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x93/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e ... Allocated by task 314: kasan_save_stack+0x39/0x70 mm/kasan/common.c:56 kasan_save_track+0x14/0x40 mm/kasan/common.c:77 kasan_save_alloc_info+0x37/0x60 mm/kasan/generic.c:573 poison_kmalloc_redzone mm/kasan/common.c:400 [inline] __kasan_kmalloc+0xc3/0xd0 mm/kasan/common.c:417 kasan_kmalloc include/linux/kasan.h:262 [inline] __kmalloc_cache_noprof+0x25f/0x800 mm/slub.c:5771 kmalloc_noprof include/linux/slab.h:957 [inline] kzalloc_noprof include/linux/slab.h:1094 [inline] init_sbd fs/gfs2/ops_fstype.c:78 [inline] gfs2_fill_super+0x19e/0x2a80 fs/gfs2/ops_fstype.c:1128 get_tree_bdev_flags+0x38b/0x640 fs/super.c:1698 get_tree_bdev+0x24/0x40 fs/super.c:1721 gfs2_get_tree+0x56/0x280 fs/gfs2/ops_fstype.c:1337 vfs_get_tree+0x9a/0x370 fs/super.c:1758 fc_mount fs/namespace.c:1199 [inline] do_new_mount_fc fs/namespace.c:3642 [inline] do_new_mount fs/namespace.c:3718 [inline] path_mount+0x5b8/0x1ea0 fs/namespace.c:4028 do_mount fs/namespace.c:4041 [inline] __do_sys_mount fs/namespace.c:4229 [inline] __se_sys_mount fs/namespace.c:4206 [inline] __x64_sys_mount+0x282/0x320 fs/namespace.c:4206 x64_sys_call+0x1a7d/0x26a0 arch/x86/include/generated/asm/syscalls_64.h:166 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x93/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 314: kasan_save_stack+0x39/0x70 mm/kasan/common.c:56 kasan_save_track+0x14/0x40 mm/kasan/common.c:77 __kasan_save_free_info+0x3b/0x60 mm/kasan/generic.c:587 kasan_save_free_info mm/kasan/kasan.h:406 [inline] poison_slab_object mm/kasan/common.c:252 [inline] __kasan_slab_free+0x6f/0xa0 mm/kasan/common.c:284 kasan_slab_free include/linux/kasan.h:234 [inline] slab_free_hook mm/slub.c:2543 [inline] slab_free mm/slub.c:6642 [inline] kfree+0x2bf/0x6b0 mm/slub.c:6849 free_sbd fs/gfs2/ops_fstype.c:71 [inline] gfs2_fill_super+0x14cd/0x2a80 fs/gfs2/ops_fstype.c:1321 get_tree_bdev_flags+0x38b/0x640 fs/super.c:1698 get_tree_bdev+0x24/0x40 fs/super.c:1721 gfs2_get_tree+0x56/0x280 fs/gfs2/ops_fstype.c:1337 vfs_get_tree+0x9a/0x370 fs/super.c:1758 fc_mount fs/namespace.c:1199 [inline] do_new_mount_fc fs/namespace.c:3642 [inline] do_new_mount fs/namespace.c:3718 [inline] path_mount+0x5b8/0x1ea0 fs/namespace.c:4028 do_mount fs/namespace.c:4041 [inline] __do_sys_mount fs/namespace.c:4229 [inline] __se_sys_mount fs/namespace.c:4206 [inline] __x64_sys_mount+0x282/0x320 fs/namespace.c:4206 x64_sys_call+0x1a7d/0x26a0 arch/x86/include/generated/asm/syscalls_64.h:166 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x93/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e
[CAUSE]gfs2_recover_journal(jd, true) only waits for the recovery worker to clear JDF_RECOVERY. After the clean_journal() wait was removed, clean_journal() can still have an in-flight bio holding bi_private = sdp when the synchronous caller returns. If a later recovery step fails, mount teardown can free sdp before gfs2_end_log_write() decrements sd_log_in_flight.
[FIX]
When wait=true, also wait for sd_log_in_flight to drain before returning from gfs2_recover_journal(). This restores the synchronous recovery completion contract on the cold mount path without changing the wait=false recovery callers.
--- fs/gfs2/recovery.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
fs/gfs2/recovery.c +5 -1
@@ -566,6 +566,7 @@ void gfs2_recover_func(struct work_struct *work)int gfs2_recover_journal (struct gfs2_jdesc *jd,bool wait) { +struct gfs2_sbd *sdp =GFS2_SB (jd->jd_inode);int rv;if (test_and_set_bit (JDF_RECOVERY , &jd->jd_flags))
@@ -575,9 +576,12 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait) rv =queue_work (gfs2_recovery_wq, &jd->jd_work);BUG_ON (!rv); -if (wait) +if (wait) {wait_on_bit (&jd->jd_flags,JDF_RECOVERY ,TASK_UNINTERRUPTIBLE ); +/* Synchronous recovery must not return while its log bio is live. */ +log_flush_wait (sdp); + }return wait ? jd->jd_recover_error :0 ; }
Signature · 1 line
2.49.0