From a77e28c7e1dc1a6a035c7627d4a88ecf3ea09aea Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Fri, 4 Sep 2009 20:40:16 +0100 Subject: [PATCH] dm multipath: fix oops when request based io fails when no paths The patch posted at http://marc.info/?l=dm-devel&m=124539787228784&w=2 which was merged into cec47e3d4a861e1d942b3a580d0bbef2700d2bb2 ("dm: prepare for request based option") introduced a regression in request-based dm. If map_request() calls dm_kill_unmapped_request() to complete a cloned bio without dispatching it, clone->bio is still set when dm_end_request() is called and the BUG_ON(clone->bio) is incorrect. The patch fixes this bug by freeing bio in dm_end_request() if the clone has bio. I've redone my tests to cover all I/O paths and confirmed there's no other regression. Here is the oops I hit in request-based dm when I do I/O to a multipath device which doesn't have any active path nor queue_if_no_path setting: ------------[ cut here ]------------ kernel BUG at /root/2.6.31-rc4.rqdm/drivers/md/dm.c:828! invalid opcode: 0000 [#1] SMP last sysfs file: /sys/devices/system/cpu/cpu3/cache/index2/shared_cpu_map CPU 1 Modules linked in: autofs4 sunrpc cpufreq_ondemand acpi_cpufreq dm_mirror dm_region_hash dm_log dm_service_time dm_multipath scsi_dh dm_mod video output sbs sbshc battery ac sg sr_mod e1000e button cdrom serio_raw rtc_cmos rtc_core rtc_lib piix lpfc scsi_transport_fc ata_piix libata megaraid_sas sd_mod scsi_mod crc_t10dif ext3 jbd uhci_hcd ohci_hcd ehci_hcd [last unloaded: microcode] Pid: 7, comm: ksoftirqd/1 Not tainted 2.6.31-rc4.rqdm #1 Express5800/120Lj [N8100-1417] RIP: 0010:[] [] dm_softirq_done+0xbd/0x100 [dm_mod] RSP: 0018:ffff8800280a1f08 EFLAGS: 00010282 RAX: ffffffffa02544e0 RBX: ffff8802aa1111d0 RCX: ffff8802aa1111e0 RDX: ffff8802ab913e70 RSI: 0000000000000000 RDI: ffff8802ab913e70 RBP: ffff8800280a1f28 R08: ffffc90005457040 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: 00000000fffffffb R13: ffff8802ab913e88 R14: ffff8802ab9c1438 R15: 0000000000000100 FS: 0000000000000000(0000) GS:ffff88002809e000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 0000003d54a98640 CR3: 000000029f0a1000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process ksoftirqd/1 (pid: 7, threadinfo ffff8802ae50e000, task ffff8802ae4f8040) Stack: ffff8800280a1f38 0000000000000020 ffffffff814f30a0 0000000000000004 <0> ffff8800280a1f58 ffffffff8116b245 ffff8800280a1f38 ffff8800280a1f38 <0> ffff8800280a1f58 0000000000000001 ffff8800280a1fa8 ffffffff810477bc Call Trace: [] blk_done_softirq+0x75/0x90 [] __do_softirq+0xcc/0x210 [] ? ksoftirqd+0x0/0x110 [] call_softirq+0x1c/0x50 [] do_softirq+0x65/0xa0 [] ? ksoftirqd+0x0/0x110 [] ksoftirqd+0x70/0x110 [] kthread+0x99/0xb0 [] child_rip+0xa/0x20 [] ? restore_args+0x0/0x30 [] ? kthread+0x0/0xb0 [] ? child_rip+0x0/0x20 Code: 44 89 e6 48 89 df e8 23 fb f2 e0 be 01 00 00 00 4c 89 f7 e8 f6 fd ff ff 5b 41 5c 41 5d 41 5e c9 c3 4c 89 ef e8 85 fe ff ff eb ed <0f> 0b eb fe 41 8b 85 dc 00 00 00 48 83 bb 10 01 00 00 00 89 83 RIP [] dm_softirq_done+0xbd/0x100 [dm_mod] RSP ---[ end trace 16af0a1d8542da55 ]--- Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Alasdair G Kergon --- drivers/md/dm.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 8a311ea0d441..b4845b14740d 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -738,16 +738,22 @@ static void rq_completed(struct mapped_device *md, int run_queue) dm_put(md); } +static void free_rq_clone(struct request *clone) +{ + struct dm_rq_target_io *tio = clone->end_io_data; + + blk_rq_unprep_clone(clone); + free_rq_tio(tio); +} + static void dm_unprep_request(struct request *rq) { struct request *clone = rq->special; - struct dm_rq_target_io *tio = clone->end_io_data; rq->special = NULL; rq->cmd_flags &= ~REQ_DONTPREP; - blk_rq_unprep_clone(clone); - free_rq_tio(tio); + free_rq_clone(clone); } /* @@ -825,8 +831,7 @@ static void dm_end_request(struct request *clone, int error) rq->sense_len = clone->sense_len; } - BUG_ON(clone->bio); - free_rq_tio(tio); + free_rq_clone(clone); blk_end_request_all(rq, error);