scsi: qla2xxx: Fix command flush during TMF

For each TMF request, driver iterates through each qpair and flushes
commands associated to the TMF. At the end of the qpair flush, a Marker is
used to complete the flush transaction. This process was repeated for each
qpair. The multiple flush and marker for this TMF request seems to cause
confusion for FW.

Instead, 1 flush is sent to FW. Driver would wait for FW to go through all
the I/Os on each qpair to be read then return. Driver then closes out the
transaction with a Marker.

Cc: stable@vger.kernel.org
Fixes: d90171dd0da5 ("scsi: qla2xxx: Multi-que support for TMF")
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230714070104.40052-5-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

3 files changed, 45 insertions, 39 deletions

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 404b32ceeaa2..f6f172fa1e18 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -2002,12 +2002,11 @@ qla2x00_tmf_iocb_timeout(void *data)
 	int rc, h;
 	unsigned long flags;
 
-	if (sp->type == SRB_MARKER) {
-		complete(&tmf->u.tmf.comp);
-		return;
-	}
+	if (sp->type == SRB_MARKER)
+		rc = QLA_FUNCTION_FAILED;
+	else
+		rc = qla24xx_async_abort_cmd(sp, false);
 
-	rc = qla24xx_async_abort_cmd(sp, false);
 	if (rc) {
 		spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
 		for (h = 1; h < sp->qpair->req->num_outstanding_cmds; h++) {
@@ -2129,6 +2128,17 @@ static void qla2x00_tmf_sp_done(srb_t *sp, int res)
 	complete(&tmf->u.tmf.comp);
 }
 
+static int qla_tmf_wait(struct tmf_arg *arg)
+{
+	/* there are only 2 types of error handling that reaches here, lun or target reset */
+	if (arg->flags & (TCF_LUN_RESET | TCF_ABORT_TASK_SET | TCF_CLEAR_TASK_SET))
+		return qla2x00_eh_wait_for_pending_commands(arg->vha,
+		    arg->fcport->d_id.b24, arg->lun, WAIT_LUN);
+	else
+		return qla2x00_eh_wait_for_pending_commands(arg->vha,
+		    arg->fcport->d_id.b24, arg->lun, WAIT_TARGET);
+}
+
 static int
 __qla2x00_async_tm_cmd(struct tmf_arg *arg)
 {
@@ -2136,8 +2146,9 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg)
 	struct srb_iocb *tm_iocb;
 	srb_t *sp;
 	int rval = QLA_FUNCTION_FAILED;
-
 	fc_port_t *fcport = arg->fcport;
+	u32 chip_gen, login_gen;
+	u64 jif;
 
 	if (TMF_NOT_READY(arg->fcport)) {
 		ql_dbg(ql_dbg_taskm, vha, 0x8032,
@@ -2182,8 +2193,27 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg)
 		    "TM IOCB failed (%x).\n", rval);
 	}
 
-	if (!test_bit(UNLOADING, &vha->dpc_flags) && !IS_QLAFX00(vha->hw))
-		rval = qla26xx_marker(arg);
+	if (!test_bit(UNLOADING, &vha->dpc_flags) && !IS_QLAFX00(vha->hw)) {
+		chip_gen = vha->hw->chip_reset;
+		login_gen = fcport->login_gen;
+
+		jif = jiffies;
+		if (qla_tmf_wait(arg)) {
+			ql_log(ql_log_info, vha, 0x803e,
+			       "Waited %u ms Nexus=%ld:%06x:%llu.\n",
+			       jiffies_to_msecs(jiffies - jif), vha->host_no,
+			       fcport->d_id.b24, arg->lun);
+		}
+
+		if (chip_gen == vha->hw->chip_reset && login_gen == fcport->login_gen) {
+			rval = qla26xx_marker(arg);
+		} else {
+			ql_log(ql_log_info, vha, 0x803e,
+			       "Skip Marker due to disruption. Nexus=%ld:%06x:%llu.\n",
+			       vha->host_no, fcport->d_id.b24, arg->lun);
+			rval = QLA_FUNCTION_FAILED;
+		}
+	}
 
 done_free_sp:
 	/* ref: INIT */
@@ -2261,9 +2291,8 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun,
 		     uint32_t tag)
 {
 	struct scsi_qla_host *vha = fcport->vha;
-	struct qla_qpair *qpair;
 	struct tmf_arg a;
-	int i, rval = QLA_SUCCESS;
+	int rval = QLA_SUCCESS;
 
 	if (TMF_NOT_READY(fcport))
 		return QLA_SUSPENDED;
@@ -2283,34 +2312,9 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun,
 	if (qla_get_tmf(&a))
 		return QLA_FUNCTION_FAILED;
 
-	if (vha->hw->mqenable) {
-		for (i = 0; i < vha->hw->num_qpairs; i++) {
-			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);
-			if (rval)
-				break;
-		}
-	}
-
-	if (rval)
-		goto bailout;
-
 	a.qpair = vha->hw->base_qpair;
 	rval = __qla2x00_async_tm_cmd(&a);
 
-bailout:
 	qla_put_tmf(&a);
 	return rval;
 }
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index a1675f056a5c..1c6e300ed3ab 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -3881,6 +3881,7 @@ qla_marker_iocb(srb_t *sp, struct mrk_entry_24xx *mrk)
 {
 	mrk->entry_type = MARKER_TYPE;
 	mrk->modifier = sp->u.iocb_cmd.u.tmf.modifier;
+	mrk->handle = make_handle(sp->qpair->req->id, sp->handle);
 	if (sp->u.iocb_cmd.u.tmf.modifier != MK_SYNC_ALL) {
 		mrk->nport_handle = cpu_to_le16(sp->u.iocb_cmd.u.tmf.loop_id);
 		int_to_scsilun(sp->u.iocb_cmd.u.tmf.lun, (struct scsi_lun *)&mrk->lun);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 47bbc8b321f8..03bc3a0b45b6 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1488,8 +1488,9 @@ qla2xxx_eh_device_reset(struct scsi_cmnd *cmd)
 		goto eh_reset_failed;
 	}
 	err = 3;
-	if (qla2x00_eh_wait_for_pending_commands(vha, sdev->id,
-	    sdev->lun, WAIT_LUN) != QLA_SUCCESS) {
+	if (qla2x00_eh_wait_for_pending_commands(vha, fcport->d_id.b24,
+						 cmd->device->lun,
+						 WAIT_LUN) != QLA_SUCCESS) {
 		ql_log(ql_log_warn, vha, 0x800d,
 		    "wait for pending cmds failed for cmd=%p.\n", cmd);
 		goto eh_reset_failed;
@@ -1555,8 +1556,8 @@ qla2xxx_eh_target_reset(struct scsi_cmnd *cmd)
 		goto eh_reset_failed;
 	}
 	err = 3;
-	if (qla2x00_eh_wait_for_pending_commands(vha, sdev->id,
-	    0, WAIT_TARGET) != QLA_SUCCESS) {
+	if (qla2x00_eh_wait_for_pending_commands(vha, fcport->d_id.b24, 0,
+						 WAIT_TARGET) != QLA_SUCCESS) {
 		ql_log(ql_log_warn, vha, 0x800d,
 		    "wait for pending cmds failed for cmd=%p.\n", cmd);
 		goto eh_reset_failed;