[SCSI] - fusion - mptfc bug fix's to prevent deadlock situations

mptbase.h

	bump version number to 3.03.09

	remove unneeded flags
	define workq and remove old fc specific locks

mptbase.c

	initialize new lock and don't initialize two removed locks

mptscsih.c

	when firmware reports target is no longer there, return
        DID_REQUEUE for fc hosts so that i/o doesn't get killed until
        the transport has an opportunity to manage the loss via its
        dev loss timer

	when the "eh_abort" routine is called, check to see if the
        driver has the command or not before looking to see if a reset
        is pending.  James Smart and I talked about this and believe
        that the API for this routine is: if driver doesn't have
        command, return SUCCESS.  This change helps prevent a target
        from being taken offline.  SUCCESS is returned because it's
        likely that the command completed after error recovery timed
        it out but before it could be aborted.

	provide a routine to queue work to newly created workq, and
        use it.

	remove "ioc" from mptscsih_abort() it was only used one time.
	the other references were via hd->ioc, so I just moved it....
	net change in references to ioc via hd->ioc is zero

	move hd->resetPending test and hd->timeouts increment to after
	the test for whether the command to be aborted remains known
	to the driver

	Make certain that the workq exists before queuing work to it.

mptfc.c

	no longer need to lock rport data structures as I was able to
	single thread the code!  I fixed up the debug code to
	eliminate compilation messages due to type mismatch in the
	printk.  Got rid of some no longer needed rport flags.
	Initialize and destroy the workq used for the rescan work.

	simplify the logic regarding the increment of
        fc_rescan_work_count.  use post increment and test for zero
        vs. pre increment and test for one; eliminate work_count
        variable: queue_work can be called with the work_lock held as
        it doesn't sleep

Signed-off-by: Michael Reed <mdr@sgi.com>
Signed-off-by: Eric Moore <Eric.Moore@lsil.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>

1 files changed, 26 insertions, 22 deletions

diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index 6a71b066bd21..84fa271eb8f4 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -632,7 +632,11 @@ mptscsih_io_done(MPT_ADAPTER *ioc, MPT_FRAME_HDR *mf, MPT_FRAME_HDR *mr)
 
 		case MPI_IOCSTATUS_SCSI_DEVICE_NOT_THERE:	/* 0x0043 */
 			/* Spoof to SCSI Selection Timeout! */
-			sc->result = DID_NO_CONNECT << 16;
+			if (ioc->bus_type != FC)
+				sc->result = DID_NO_CONNECT << 16;
+			/* else fibre, just stall until rescan event */
+			else
+				sc->result = DID_REQUEUE << 16;
 
 			if (hd->sel_timeout[pScsiReq->TargetID] < 0xFFFF)
 				hd->sel_timeout[pScsiReq->TargetID]++;
@@ -1645,7 +1649,6 @@ int
 mptscsih_abort(struct scsi_cmnd * SCpnt)
 {
 	MPT_SCSI_HOST	*hd;
-	MPT_ADAPTER	*ioc;
 	MPT_FRAME_HDR	*mf;
 	u32		 ctx2abort;
 	int		 scpnt_idx;
@@ -1663,14 +1666,6 @@ mptscsih_abort(struct scsi_cmnd * SCpnt)
 		return FAILED;
 	}
 
-	ioc = hd->ioc;
-	if (hd->resetPending) {
-		return FAILED;
-	}
-
-	if (hd->timeouts < -1)
-		hd->timeouts++;
-
 	/* Find this command
 	 */
 	if ((scpnt_idx = SCPNT_TO_LOOKUP_IDX(SCpnt)) < 0) {
@@ -1684,6 +1679,13 @@ mptscsih_abort(struct scsi_cmnd * SCpnt)
 		return SUCCESS;
 	}
 
+	if (hd->resetPending) {
+		return FAILED;
+	}
+
+	if (hd->timeouts < -1)
+		hd->timeouts++;
+
 	printk(KERN_WARNING MYNAM ": %s: attempting task abort! (sc=%p)\n",
 	       hd->ioc->name, SCpnt);
 	scsi_print_command(SCpnt);
@@ -1703,7 +1705,7 @@ mptscsih_abort(struct scsi_cmnd * SCpnt)
 	vdev = SCpnt->device->hostdata;
 	retval = mptscsih_TMHandler(hd, MPI_SCSITASKMGMT_TASKTYPE_ABORT_TASK,
 		vdev->vtarget->bus_id, vdev->vtarget->target_id, vdev->lun,
-		ctx2abort, mptscsih_get_tm_timeout(ioc));
+		ctx2abort, mptscsih_get_tm_timeout(hd->ioc));
 
 	printk (KERN_WARNING MYNAM ": %s: task abort: %s (sc=%p)\n",
 		hd->ioc->name,
@@ -2521,15 +2523,15 @@ mptscsih_ioc_reset(MPT_ADAPTER *ioc, int reset_phase)
 
 		/* 7. FC: Rescan for blocked rports which might have returned.
 		 */
-		else if (ioc->bus_type == FC) {
-			int work_count;
-			unsigned long flags;
-
+		if (ioc->bus_type == FC) {
 			spin_lock_irqsave(&ioc->fc_rescan_work_lock, flags);
-			work_count = ++ioc->fc_rescan_work_count;
+			if (ioc->fc_rescan_work_q) {
+				if (ioc->fc_rescan_work_count++ == 0) {
+					queue_work(ioc->fc_rescan_work_q,
+						   &ioc->fc_rescan_work);
+				}
+			}
 			spin_unlock_irqrestore(&ioc->fc_rescan_work_lock, flags);
-			if (work_count == 1)
-				schedule_work(&ioc->fc_rescan_work);
 		}
 		dtmprintk((MYIOC_s_WARN_FMT "Post-Reset complete.\n", ioc->name));
 
@@ -2544,7 +2546,6 @@ mptscsih_event_process(MPT_ADAPTER *ioc, EventNotificationReply_t *pEvReply)
 {
 	MPT_SCSI_HOST *hd;
 	u8 event = le32_to_cpu(pEvReply->Event) & 0xFF;
-	int work_count;
 	unsigned long flags;
 
 	devtverboseprintk((MYIOC_s_INFO_FMT "MPT event (=%02Xh) routed to SCSI host driver!\n",
@@ -2569,10 +2570,13 @@ mptscsih_event_process(MPT_ADAPTER *ioc, EventNotificationReply_t *pEvReply)
 
 	case MPI_EVENT_RESCAN:				/* 06 */
 		spin_lock_irqsave(&ioc->fc_rescan_work_lock, flags);
-		work_count = ++ioc->fc_rescan_work_count;
+		if (ioc->fc_rescan_work_q) {
+			if (ioc->fc_rescan_work_count++ == 0) {
+				queue_work(ioc->fc_rescan_work_q,
+					   &ioc->fc_rescan_work);
+			}
+		}
 		spin_unlock_irqrestore(&ioc->fc_rescan_work_lock, flags);
-		if (work_count == 1)
-			schedule_work(&ioc->fc_rescan_work);
 		break;
 
 		/*