===================================================================
@@ -2945,6 +2945,9 @@ static void __dm_internal_suspend(struct
static void __dm_internal_resume(struct mapped_device *md)
{
+ int r;
+ struct dm_table *map;
+
BUG_ON(!md->internal_suspend_count);
if (--md->internal_suspend_count)
@@ -2953,11 +2956,23 @@ static void __dm_internal_resume(struct
if (dm_suspended_md(md))
goto done; /* resume from nested suspend */
- /*
- * NOTE: existing callers don't need to call dm_table_resume_targets
- * (which may fail -- so best to avoid it for now by passing NULL map)
- */
- (void) __dm_resume(md, NULL);
+ map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
+ r = __dm_resume(md, map);
+ if (r) {
+ /*
+ * If a preresume method of some target failed, we are in a
+ * tricky situation. We can't return an error to the caller. We
+ * can't fake success because then the "resume" and
+ * "postsuspend" methods would not be paired correctly, and it
+ * would break various targets, for example it would cause list
+ * corruption in the "origin" target.
+ *
+ * So, we fake normal suspend here, to make sure that the
+ * "resume" and "postsuspend" methods will be paired correctly.
+ */
+ DMERR("Preresume method failed: %d", r);
+ set_bit(DMF_SUSPENDED, &md->flags);
+ }
done:
clear_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
There is this reported crash when experimenting with the lvm2 testsuite. The list corruption is caused by the fact that the postsuspend and resume methods were not paired correctly; there were two consecutive calls to the origin_postsuspend function. The second call attempts to remove the "hash_list" entry from a list, while it was already removed by the first call. This patch fixes __dm_internal_resume, so that it calls the preresume and resume methods of the table's targets. If a preresume method of some target fails, we are in a tricky situation. We can't return an error because dm_internal_resume isn't supposed to return errors. We can't return success, because then the "resume" and "postsuspend" methods would not be paired correctly. So, we set the DMF_SUSPENDED flag and we fake normal suspend - it may confuse userspace tools, but it won't cause a kernel crash. ------------[ cut here ]------------ kernel BUG at lib/list_debug.c:56! invalid opcode: 0000 [#1] PREEMPT SMP CPU: 1 PID: 8343 Comm: dmsetup Not tainted 6.8.0-rc6 #4 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 RIP: 0010:__list_del_entry_valid_or_report+0x77/0xc0 Code: 50 94 81 e8 eb 65 d4 ff 0f 0b 48 89 fe 48 c7 c7 d0 50 94 81 e8 da 65 d4 ff 0f 0b 48 89 fe 48 c7 c7 00 51 94 81 e8 c9 65 d4 ff <0f> 0b 48 89 fe 48 89 ca 48 c7 c7 38 51 94 81 e8 b5 65 d4 ff 0f 0b RSP: 0018:ffff8881b831bcc0 EFLAGS: 00010282 RAX: 000000000000004e RBX: ffff888143b6eb80 RCX: 0000000000000000 RDX: 0000000000000001 RSI: ffffffff819053d0 RDI: 00000000ffffffff RBP: ffff8881b83a3400 R08: 00000000fffeffff R09: 0000000000000058 R10: 0000000000000000 R11: ffffffff81a24080 R12: 0000000000000001 R13: ffff88814538e000 R14: ffff888143bc6dc0 R15: ffffffffa02e4bb0 FS: 00000000f7c0f780(0000) GS:ffff8893f0a40000(0000) knlGS:0000000000000000 CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 CR2: 0000000057fb5000 CR3: 0000000143474000 CR4: 00000000000006b0 Call Trace: <TASK> ? die+0x2d/0x80 ? do_trap+0xeb/0xf0 ? __list_del_entry_valid_or_report+0x77/0xc0 ? do_error_trap+0x60/0x80 ? __list_del_entry_valid_or_report+0x77/0xc0 ? exc_invalid_op+0x49/0x60 ? __list_del_entry_valid_or_report+0x77/0xc0 ? asm_exc_invalid_op+0x16/0x20 ? table_deps+0x1b0/0x1b0 [dm_mod] ? __list_del_entry_valid_or_report+0x77/0xc0 origin_postsuspend+0x1a/0x50 [dm_snapshot] dm_table_postsuspend_targets+0x34/0x50 [dm_mod] dm_suspend+0xd8/0xf0 [dm_mod] dev_suspend+0x1f2/0x2f0 [dm_mod] ? table_deps+0x1b0/0x1b0 [dm_mod] ctl_ioctl+0x300/0x5f0 [dm_mod] dm_compat_ctl_ioctl+0x7/0x10 [dm_mod] __x64_compat_sys_ioctl+0x104/0x170 do_syscall_64+0x184/0x1b0 entry_SYSCALL_64_after_hwframe+0x46/0x4e RIP: 0033:0xf7e6aead Code: 04 25 18 00 00 00 89 44 24 1c 31 c0 8d 44 24 60 c7 04 24 10 00 00 00 89 44 24 08 8d 44 24 20 89 44 24 0c b8 02 02 00 40 0f 05 <3d> 00 f0 ff ff 77 1c 8b 54 24 1c 64 2b 14 25 18 00 00 00 75 29 83 RSP: 002b:00000000ffcfbbf0 EFLAGS: 00000246 ORIG_RAX: 0000000040000202 RAX: ffffffffffffffda RBX: 0000000057fb2370 RCX: 00000000f7e6aead RDX: 0000000057fb24f0 RSI: 00000000c138fd06 RDI: 0000000000000003 RBP: 0000000000000019 R08: 000000000000ffff R09: 0000000000000000 R10: 00000000f7e1b390 R11: 0000000000000246 R12: 0000000057fb2520 R13: 0000000057fb25a0 R14: 0000000000000000 R15: 0000000057fb24f0 </TASK> Modules linked in: dm_snapshot brd dm_thin_pool dm_persistent_data dm_bio_prison dm_bufio dm_mod uvesafb cfbfillrect cfbimgblt fb_io_fops cn cfbcopyarea fb font fbdev autofs4 tun binfmt_misc af_packet ipv6 configfs mousedev virtio_net net_failover virtio_rng failover rng_core virtio_balloon pcspkr qemu_fw_cfg button raid10 raid456 libcrc32c async_raid6_recov async_memcpy async_pq raid6_pq async_xor xor async_tx raid1 raid0 md_mod sd_mod t10_pi crc64_rocksoft crc64 crc_t10dif virtio_scsi scsi_mod evdev psmouse bsg scsi_common ---[ end trace 0000000000000000 ]--- Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> --- drivers/md/dm.c | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-)