scsi: qla2xxx: Fix hang in task management

commit 9ae615c upstream.

Task management command hangs where a side
band chip reset failed to nudge the TMF
from it's current send path.

Add additional error check to block TMF
from entering during chip reset and along
the TMF path to cause it to bail out, skip
over abort of marker.

Cc: [email protected]
Signed-off-by: Quinn Tran <[email protected]>
Signed-off-by: Nilesh Javali <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Reviewed-by: Himanshu Madhani <[email protected]>
Signed-off-by: Martin K. Petersen <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: Quinn Tran

drivers/scsi/qla2xxx/qla_def.h

@@ -5499,4 +5499,8 @@ struct ql_vnd_tgt_stats_resp {
 	_fp->disc_state, _fp->scan_state, _fp->loop_id, _fp->deleted, \
 	_fp->flags
 
+#define TMF_NOT_READY(_fcport) \
+	(!_fcport || IS_SESSION_DELETED(_fcport) || atomic_read(&_fcport->state) != FCS_ONLINE || \
+	!_fcport->vha->hw->flags.fw_started)
+
 #endif

drivers/scsi/qla2xxx/qla_init.c

@@ -1997,6 +1997,11 @@ qla2x00_tmf_iocb_timeout(void *data)
 	int rc, h;
 	unsigned long flags;
 
+	if (sp->type == SRB_MARKER) {
+		complete(&tmf->u.tmf.comp);
+		return;
+	}
+
 	rc = qla24xx_async_abort_cmd(sp, false);
 	if (rc) {
 		spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
@@ -2024,6 +2029,7 @@ static void qla_marker_sp_done(srb_t *sp, int res)
 		    sp->handle, sp->fcport->d_id.b24, sp->u.iocb_cmd.u.tmf.flags,
 		    sp->u.iocb_cmd.u.tmf.lun, sp->qpair->id);
 
+	sp->u.iocb_cmd.u.tmf.data = res;
 	complete(&tmf->u.tmf.comp);
 }
 
@@ -2040,6 +2046,11 @@ static void qla_marker_sp_done(srb_t *sp, int res)
 	} while (cnt); \
 }
 
+/**
+ * qla26xx_marker: send marker IOCB and wait for the completion of it.
+ * @arg: pointer to argument list.
+ *    It is assume caller will provide an fcport pointer and modifier
+ */
 static int
 qla26xx_marker(struct tmf_arg *arg)
 {
@@ -2049,6 +2060,14 @@ qla26xx_marker(struct tmf_arg *arg)
 	int rval = QLA_FUNCTION_FAILED;
 	fc_port_t *fcport = arg->fcport;
 
+	if (TMF_NOT_READY(arg->fcport)) {
+		ql_dbg(ql_dbg_taskm, vha, 0x8039,
+		    "FC port not ready for marker loop-id=%x portid=%06x modifier=%x lun=%lld qp=%d.\n",
+		    fcport->loop_id, fcport->d_id.b24,
+		    arg->modifier, arg->lun, arg->qpair->id);
+		return QLA_SUSPENDED;
+	}
+
 	/* ref: INIT */
 	sp = qla2xxx_get_qpair_sp(vha, arg->qpair, fcport, GFP_KERNEL);
 	if (!sp)
@@ -2075,11 +2094,19 @@ qla26xx_marker(struct tmf_arg *arg)
 
 	if (rval != QLA_SUCCESS) {
 		ql_log(ql_log_warn, vha, 0x8031,
-		    "Marker IOCB failed (%x).\n", rval);
+		    "Marker IOCB send failure (%x).\n", rval);
 		goto done_free_sp;
 	}
 
 	wait_for_completion(&tm_iocb->u.tmf.comp);
+	rval = tm_iocb->u.tmf.data;
+
+	if (rval != QLA_SUCCESS) {
+		ql_log(ql_log_warn, vha, 0x8019,
+		    "Marker failed hdl=%x loop-id=%x portid=%06x modifier=%x lun=%lld qp=%d rval %d.\n",
+		    sp->handle, fcport->loop_id, fcport->d_id.b24,
+		    arg->modifier, arg->lun, sp->qpair->id, rval);
+	}
 
 done_free_sp:
 	/* ref: INIT */
@@ -2092,6 +2119,8 @@ static void qla2x00_tmf_sp_done(srb_t *sp, int res)
 {
 	struct srb_iocb *tmf = &sp->u.iocb_cmd;
 
+	if (res)
+		tmf->u.tmf.data = res;
 	complete(&tmf->u.tmf.comp);
 }
 
@@ -2105,6 +2134,14 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg)
 
 	fc_port_t *fcport = arg->fcport;
 
+	if (TMF_NOT_READY(arg->fcport)) {
+		ql_dbg(ql_dbg_taskm, vha, 0x8032,
+		    "FC port not ready for TM command loop-id=%x portid=%06x modifier=%x lun=%lld qp=%d.\n",
+		    fcport->loop_id, fcport->d_id.b24,
+		    arg->modifier, arg->lun, arg->qpair->id);
+		return QLA_SUSPENDED;
+	}
+
 	/* ref: INIT */
 	sp = qla2xxx_get_qpair_sp(vha, arg->qpair, fcport, GFP_KERNEL);
 	if (!sp)
@@ -2179,7 +2216,9 @@ int qla_get_tmf(fc_port_t *fcport)
 		msleep(1);
 
 		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-		if (fcport->deleted) {
+		if (TMF_NOT_READY(fcport)) {
+			ql_log(ql_log_warn, vha, 0x802c,
+			    "Unable to acquire TM resource due to disruption.\n");
 			rc = EIO;
 			break;
 		}
@@ -2205,7 +2244,10 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun,
 	struct scsi_qla_host *vha = fcport->vha;
 	struct qla_qpair *qpair;
 	struct tmf_arg a;
-	int i, rval;
+	int i, rval = QLA_SUCCESS;
+
+	if (TMF_NOT_READY(fcport))
+		return QLA_SUSPENDED;
 
 	a.vha = fcport->vha;
 	a.fcport = fcport;
@@ -2224,6 +2266,14 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun,
 			qpair = vha->hw->queue_pair_map[i];
 			if (!qpair)
 				continue;
+
+			if (TMF_NOT_READY(fcport)) {
+				ql_log(ql_log_warn, vha, 0x8026,
+				    "Unable to send TM due to disruption.\n");
+				rval = QLA_SUSPENDED;
+				break;
+			}
+
 			a.qpair = qpair;
 			a.flags = flags|TCF_NOTMCMD_TO_TARGET;
 			rval = __qla2x00_async_tm_cmd(&a);
@@ -2232,10 +2282,14 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun,
 		}
 	}
 
+	if (rval)
+		goto bailout;
+
 	a.qpair = vha->hw->base_qpair;
 	a.flags = flags;
 	rval = __qla2x00_async_tm_cmd(&a);
 
+bailout:
 	if (a.modifier == MK_SYNC_ID_LUN)
 		qla_put_tmf(fcport);