diff options
author | Dan Williams <dan.j.williams@intel.com> | 2012-01-10 15:14:09 -0800 |
---|---|---|
committer | James Bottomley <JBottomley@Parallels.com> | 2012-02-29 15:22:25 -0600 |
commit | 8abda4d28a55ecb91e39ceb5e3ee264c5a3cd1af (patch) | |
tree | 6ccf0a1a6e545e05cefe68c5c37c18a5bd88c49f | |
parent | 7d05919aad080074453de880822fe5805875645f (diff) | |
download | linux-8abda4d28a55ecb91e39ceb5e3ee264c5a3cd1af.tar.bz2 |
[SCSI] libsas: close scsi_remove_target() vs libata-eh race
ata_port lifetime in libata follows the host. In libsas it follows the
scsi_target. Once scsi_remove_device() has caused all commands to be
completed it allows scsi_remove_target() to immediately proceed to
freeing the ata_port causing bug reports like:
[ 848.393333] BUG: spinlock bad magic on CPU#4, kworker/u:2/5107
[ 848.400262] general protection fault: 0000 [#1] SMP
[ 848.406244] CPU 4
[ 848.408310] Modules linked in: nls_utf8 ipv6 uinput i2c_i801 i2c_core iTCO_wdt iTCO_vendor_support ioatdma dca sg sd_mod sr_mod cdrom ahci libahci isci libsas libata scsi_transport_sas [last unloaded: scsi_wait_scan]
[ 848.432060]
[ 848.434137] Pid: 5107, comm: kworker/u:2 Not tainted 3.2.0-isci+ #8 Intel Corporation S2600CP/S2600CP
[ 848.445310] RIP: 0010:[<ffffffff8126a68c>] [<ffffffff8126a68c>] spin_dump+0x5e/0x8c
[ 848.454787] RSP: 0018:ffff8807f868dca0 EFLAGS: 00010002
[ 848.461137] RAX: 0000000000000048 RBX: ffff8807fe86a630 RCX: ffffffff817d0be0
[ 848.469520] RDX: 0000000000000000 RSI: ffffffff814af1cf RDI: 0000000000000002
[ 848.477959] RBP: ffff8807f868dcb0 R08: 00000000ffffffff R09: 000000006b6b6b6b
[ 848.486327] R10: 000000000003fb8c R11: ffffffff81a19448 R12: 6b6b6b6b6b6b6b6b
[ 848.494699] R13: ffff8808027dc520 R14: 0000000000000000 R15: 000000000000001e
[ 848.503067] FS: 0000000000000000(0000) GS:ffff88083fd00000(0000) knlGS:0000000000000000
[ 848.512899] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[ 848.519710] CR2: 00007ff77d001000 CR3: 00000007f7a5d000 CR4: 00000000000406e0
[ 848.528072] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 848.536446] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[ 848.544831] Process kworker/u:2 (pid: 5107, threadinfo ffff8807f868c000, task ffff8807ff348000)
[ 848.555327] Stack:
[ 848.557959] ffff8807fe86a630 ffff8807fe86a630 ffff8807f868dcd0 ffffffff8126a6e0
[ 848.567072] ffffffff817c142f ffff8807fe86a630 ffff8807f868dcf0 ffffffff8126a703
[ 848.576190] ffff8808027dc520 0000000000000286 ffff8807f868dd10 ffffffff814af1bb
[ 848.585281] Call Trace:
[ 848.588409] [<ffffffff8126a6e0>] spin_bug+0x26/0x28
[ 848.594357] [<ffffffff8126a703>] do_raw_spin_unlock+0x21/0x88
[ 848.601283] [<ffffffff814af1bb>] _raw_spin_unlock_irqrestore+0x2c/0x65
[ 848.609089] [<ffffffffa001c103>] ata_scsi_port_error_handler+0x548/0x557 [libata]
[ 848.618331] [<ffffffff81061813>] ? async_schedule+0x17/0x17
[ 848.625060] [<ffffffffa004f30f>] async_sas_ata_eh+0x45/0x69 [libsas]
[ 848.632655] [<ffffffff810618aa>] async_run_entry_fn+0x97/0x125
[ 848.639670] [<ffffffff81057439>] process_one_work+0x207/0x38d
[ 848.646577] [<ffffffff8105738c>] ? process_one_work+0x15a/0x38d
[ 848.653681] [<ffffffff810576f7>] worker_thread+0x138/0x21c
[ 848.660305] [<ffffffff810575bf>] ? process_one_work+0x38d/0x38d
[ 848.667493] [<ffffffff8105b098>] kthread+0x9d/0xa5
[ 848.673382] [<ffffffff8106e1bd>] ? trace_hardirqs_on_caller+0x12f/0x166
[ 848.681304] [<ffffffff814b7704>] kernel_thread_helper+0x4/0x10
[ 848.688324] [<ffffffff814af534>] ? retint_restore_args+0x13/0x13
[ 848.695530] [<ffffffff8105affb>] ? __init_kthread_worker+0x5b/0x5b
[ 848.702929] [<ffffffff814b7700>] ? gs_change+0x13/0x13
[ 848.709155] Code: 00 00 48 8d 88 38 04 00 00 44 8b 80 84 02 00 00 31 c0 e8 cf 1b 24 00 41 83 c8 ff 44 8b 4b 08 48 c7 c1 e0 0b 7d 81 4d 85 e4 74 10 <45> 8b 84 24 84 02 00 00 49 8d 8c 24 38 04 00 00 8b 53 04 48 89
[ 848.732467] RIP [<ffffffff8126a68c>] spin_dump+0x5e/0x8c
[ 848.738905] RSP <ffff8807f868dca0>
[ 848.743743] ---[ end trace 143161646eee8caa ]---
...so arrange for the ata_port to have the same end of life as the domain
device.
Reported-by: Marcin Tomczak <marcin.tomczak@intel.com>
Acked-by: Jeff Garzik <jgarzik@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
-rw-r--r-- | drivers/scsi/libsas/sas_ata.c | 5 | ||||
-rw-r--r-- | drivers/scsi/libsas/sas_discover.c | 5 | ||||
-rw-r--r-- | drivers/scsi/libsas/sas_scsi_host.c | 3 |
3 files changed, 10 insertions, 3 deletions
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 37a9e73870d4..26a943eb153a 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -661,8 +661,13 @@ static void async_sas_ata_eh(void *data, async_cookie_t cookie) struct ata_port *ap = dev->sata_dev.ap; struct sas_ha_struct *ha = dev->port->ha; + /* hold a reference over eh since we may be racing with final + * remove once all commands are completed + */ + kref_get(&dev->kref); ata_port_printk(ap, KERN_DEBUG, "sas eh calling libata port error handler"); ata_scsi_port_error_handler(ha->core.shost, ap); + sas_put_device(dev); } void sas_ata_strategy_handler(struct Scsi_Host *shost) diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index b91866a8233b..4be5ddad7be7 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -242,6 +242,11 @@ void sas_free_device(struct kref *kref) if (dev->dev_type == EDGE_DEV || dev->dev_type == FANOUT_DEV) kfree(dev->ex_dev.ex_phy); + if (dev_is_sata(dev) && dev->sata_dev.ap) { + ata_sas_port_destroy(dev->sata_dev.ap); + dev->sata_dev.ap = NULL; + } + kfree(dev); } diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c index 731c89250639..b563ff27626b 100644 --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -1028,9 +1028,6 @@ void sas_target_destroy(struct scsi_target *starget) if (!found_dev) return; - if (dev_is_sata(found_dev)) - ata_sas_port_destroy(found_dev->sata_dev.ap); - starget->hostdata = NULL; sas_put_device(found_dev); } |