| From 93fe8003e0cb6c4e15e42750d665326471eb2265 Mon Sep 17 00:00:00 2001 |
| From: Dan Williams <dan.j.williams@intel.com> |
| Date: Thu, 21 Jun 2012 23:25:32 -0700 |
| Subject: [PATCH] fix eh wakeup (scsi_schedule_eh vs scsi_restart_operations) |
| |
| commit 57fc2e335fd3c2f898ee73570dc81426c28dc7b4 upstream. |
| |
| Rapid ata hotplug on a libsas controller results in cases where libsas |
| is waiting indefinitely on eh to perform an ata probe. |
| |
| A race exists between scsi_schedule_eh() and scsi_restart_operations() |
| in the case when scsi_restart_operations() issues i/o to other devices |
| in the sas domain. When this happens the host state transitions from |
| SHOST_RECOVERY (set by scsi_schedule_eh) back to SHOST_RUNNING and |
| ->host_busy is non-zero so we put the eh thread to sleep even though |
| ->host_eh_scheduled is active. |
| |
| Before putting the error handler to sleep we need to check if the |
| host_state needs to return to SHOST_RECOVERY for another trip through |
| eh. Since i/o that is released by scsi_restart_operations has been |
| blocked for at least one eh cycle, this implementation allows those |
| i/o's to run before another eh cycle starts to discourage hung task |
| timeouts. |
| |
| Reported-by: Tom Jackson <thomas.p.jackson@intel.com> |
| Tested-by: Tom Jackson <thomas.p.jackson@intel.com> |
| Signed-off-by: Dan Williams <dan.j.williams@intel.com> |
| Signed-off-by: James Bottomley <JBottomley@Parallels.com> |
| Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> |
| --- |
| drivers/scsi/scsi_error.c | 14 ++++++++++++++ |
| 1 file changed, 14 insertions(+) |
| |
| diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c |
| index 7ad53fa42766..3a56835c3ad3 100644 |
| --- a/drivers/scsi/scsi_error.c |
| +++ b/drivers/scsi/scsi_error.c |
| @@ -1614,6 +1614,20 @@ static void scsi_restart_operations(struct Scsi_Host *shost) |
| * requests are started. |
| */ |
| scsi_run_host_queues(shost); |
| + |
| + /* |
| + * if eh is active and host_eh_scheduled is pending we need to re-run |
| + * recovery. we do this check after scsi_run_host_queues() to allow |
| + * everything pent up since the last eh run a chance to make forward |
| + * progress before we sync again. Either we'll immediately re-run |
| + * recovery or scsi_device_unbusy() will wake us again when these |
| + * pending commands complete. |
| + */ |
| + spin_lock_irqsave(shost->host_lock, flags); |
| + if (shost->host_eh_scheduled) |
| + if (scsi_host_set_state(shost, SHOST_RECOVERY)) |
| + WARN_ON(scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY)); |
| + spin_unlock_irqrestore(shost->host_lock, flags); |
| } |
| |
| /** |
| -- |
| 1.8.5.2 |
| |