From 8fdcf86af61bfba744f5868ec04dad71637ac33a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 16 May 2007 14:01:48 -0700 Subject: [SCSI] aic94xx: asd_clear_nexus should fail if the cleared task does not complete Every so often, the driver will call asd_clear_nexus to clean out a task. It is supposed to be the case that the CLEAR NEXUS does not go on the done list until after the task itself has been put on the done list, but for some reason this doesn't always happen. Thus, the wait_for_completion_timeout call times out, and we return success. This makes libsas free the task even though the task hasn't completed, leading to a BUG_ON message from aic94xx_hwi.c around line 341. We should return failure from asd_clear_nexus so that libsas tries again; at a bare minimum it shouldn't be freeing active tasks. I _think_ this will fix one of the SCB timeout crash problems (though I've not been able to reproduce it lately...) Signed-off-by: Darrick J. Wong Signed-off-by: James Bottomley --- drivers/scsi/aic94xx/aic94xx_tmf.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'drivers/scsi/aic94xx') diff --git a/drivers/scsi/aic94xx/aic94xx_tmf.c b/drivers/scsi/aic94xx/aic94xx_tmf.c index 9a14a6d97275..c0d0b7d7a8ce 100644 --- a/drivers/scsi/aic94xx/aic94xx_tmf.c +++ b/drivers/scsi/aic94xx/aic94xx_tmf.c @@ -290,6 +290,7 @@ static void asd_tmf_tasklet_complete(struct asd_ascb *ascb, static inline int asd_clear_nexus(struct sas_task *task) { int res = TMF_RESP_FUNC_FAILED; + int leftover; struct asd_ascb *tascb = task->lldd_task; unsigned long flags; @@ -298,10 +299,12 @@ static inline int asd_clear_nexus(struct sas_task *task) res = asd_clear_nexus_tag(task); else res = asd_clear_nexus_index(task); - wait_for_completion_timeout(&tascb->completion, - AIC94XX_SCB_TIMEOUT); + leftover = wait_for_completion_timeout(&tascb->completion, + AIC94XX_SCB_TIMEOUT); ASD_DPRINTK("came back from clear nexus\n"); spin_lock_irqsave(&task->task_state_lock, flags); + if (leftover < 1) + res = TMF_RESP_FUNC_FAILED; if (task->task_state_flags & SAS_TASK_STATE_DONE) res = TMF_RESP_FUNC_COMPLETE; spin_unlock_irqrestore(&task->task_state_lock, flags); @@ -350,6 +353,7 @@ int asd_abort_task(struct sas_task *task) unsigned long flags; struct asd_ascb *ascb = NULL; struct scb *scb; + int leftover; spin_lock_irqsave(&task->task_state_lock, flags); if (task->task_state_flags & SAS_TASK_STATE_DONE) { @@ -455,9 +459,11 @@ int asd_abort_task(struct sas_task *task) break; case TF_TMF_TASK_DONE + 0xFF00: /* done but not reported yet */ res = TMF_RESP_FUNC_FAILED; - wait_for_completion_timeout(&tascb->completion, - AIC94XX_SCB_TIMEOUT); + leftover = wait_for_completion_timeout(&tascb->completion, + AIC94XX_SCB_TIMEOUT); spin_lock_irqsave(&task->task_state_lock, flags); + if (leftover < 1) + res = TMF_RESP_FUNC_FAILED; if (task->task_state_flags & SAS_TASK_STATE_DONE) res = TMF_RESP_FUNC_COMPLETE; spin_unlock_irqrestore(&task->task_state_lock, flags); -- cgit v1.2.3