scsi: qla2xxx: Multi-que support for TMF

Add queue flush for task management command, before
placing it on the wire.
Do IO flush for all Request Q's.

Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/oe-kbuild-all/202304271702.GpIL391S-lkp@intel.com/
Cc: stable@vger.kernel.org
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230428075339.32551-2-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com <mailto:himanshu.madhani@oracle.com>>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

Author: Quinn Tran

drivers/scsi/qla2xxx/qla_def.h

@@ -465,6 +465,14 @@ static inline be_id_t port_id_to_be_id(port_id_t port_id)
 	return res;
 }
 
+struct tmf_arg {
+	struct qla_qpair *qpair;
+	struct fc_port *fcport;
+	struct scsi_qla_host *vha;
+	u64 lun;
+	u32 flags;
+};
+
 struct els_logo_payload {
 	uint8_t opcode;
 	uint8_t rsvd[3];

drivers/scsi/qla2xxx/qla_gbl.h

@@ -69,7 +69,7 @@ extern int qla2x00_async_logout(struct scsi_qla_host *, fc_port_t *);
 extern int qla2x00_async_prlo(struct scsi_qla_host *, fc_port_t *);
 extern int qla2x00_async_adisc(struct scsi_qla_host *, fc_port_t *,
     uint16_t *);
-extern int qla2x00_async_tm_cmd(fc_port_t *, uint32_t, uint32_t, uint32_t);
+extern int qla2x00_async_tm_cmd(fc_port_t *, uint32_t, uint64_t, uint32_t);
 struct qla_work_evt *qla2x00_alloc_work(struct scsi_qla_host *,
     enum qla_work_type);
 extern int qla24xx_async_gnl(struct scsi_qla_host *, fc_port_t *);

drivers/scsi/qla2xxx/qla_init.c

@@ -2020,17 +2020,19 @@ static void qla2x00_tmf_sp_done(srb_t *sp, int res)
 	complete(&tmf->u.tmf.comp);
 }
 
-int
-qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun,
-	uint32_t tag)
+static int
+__qla2x00_async_tm_cmd(struct tmf_arg *arg)
 {
-	struct scsi_qla_host *vha = fcport->vha;
+	struct scsi_qla_host *vha = arg->vha;
 	struct srb_iocb *tm_iocb;
 	srb_t *sp;
+	unsigned long flags;
 	int rval = QLA_FUNCTION_FAILED;
 
+	fc_port_t *fcport = arg->fcport;
+
 	/* ref: INIT */
-	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
+	sp = qla2xxx_get_qpair_sp(vha, arg->qpair, fcport, GFP_KERNEL);
 	if (!sp)
 		goto done;
 
@@ -2043,15 +2045,15 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun,
 
 	tm_iocb = &sp->u.iocb_cmd;
 	init_completion(&tm_iocb->u.tmf.comp);
-	tm_iocb->u.tmf.flags = flags;
-	tm_iocb->u.tmf.lun = lun;
+	tm_iocb->u.tmf.flags = arg->flags;
+	tm_iocb->u.tmf.lun = arg->lun;
 
+	rval = qla2x00_start_sp(sp);
 	ql_dbg(ql_dbg_taskm, vha, 0x802f,
-	    "Async-tmf hdl=%x loop-id=%x portid=%02x%02x%02x.\n",
+	    "Async-tmf hdl=%x loop-id=%x portid=%02x%02x%02x ctrl=%x.\n",
 	    sp->handle, fcport->loop_id, fcport->d_id.b.domain,
-	    fcport->d_id.b.area, fcport->d_id.b.al_pa);
+	    fcport->d_id.b.area, fcport->d_id.b.al_pa, arg->flags);
 
-	rval = qla2x00_start_sp(sp);
 	if (rval != QLA_SUCCESS)
 		goto done_free_sp;
 	wait_for_completion(&tm_iocb->u.tmf.comp);
@@ -2065,12 +2067,14 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun,
 
 	if (!test_bit(UNLOADING, &vha->dpc_flags) && !IS_QLAFX00(vha->hw)) {
 		flags = tm_iocb->u.tmf.flags;
-		lun = (uint16_t)tm_iocb->u.tmf.lun;
+		if (flags & (TCF_LUN_RESET|TCF_ABORT_TASK_SET|
+			TCF_CLEAR_TASK_SET|TCF_CLEAR_ACA))
+			flags = MK_SYNC_ID_LUN;
+		else
+			flags = MK_SYNC_ID;
 
-		/* Issue Marker IOCB */
-		qla2x00_marker(vha, vha->hw->base_qpair,
-		    fcport->loop_id, lun,
-		    flags == TCF_LUN_RESET ? MK_SYNC_ID_LUN : MK_SYNC_ID);
+		qla2x00_marker(vha, sp->qpair,
+		    sp->fcport->loop_id, arg->lun, flags);
 	}
 
 done_free_sp:
@@ -2080,6 +2084,41 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun,
 	return rval;
 }
 
+int
+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;
+	struct completion comp;
+	int i, rval;
+
+	init_completion(&comp);
+	a.vha = fcport->vha;
+	a.fcport = fcport;
+	a.lun = lun;
+
+	if (vha->hw->mqenable) {
+		for (i = 0; i < vha->hw->num_qpairs; i++) {
+			qpair = vha->hw->queue_pair_map[i];
+			if (!qpair)
+				continue;
+			a.qpair = qpair;
+			a.flags = flags|TCF_NOTMCMD_TO_TARGET;
+			rval = __qla2x00_async_tm_cmd(&a);
+			if (rval)
+				break;
+		}
+	}
+
+	a.qpair = vha->hw->base_qpair;
+	a.flags = flags;
+	rval = __qla2x00_async_tm_cmd(&a);
+
+	return rval;
+}
+
 int
 qla24xx_async_abort_command(srb_t *sp)
 {

drivers/scsi/qla2xxx/qla_iocb.c

@@ -2541,7 +2541,7 @@ qla24xx_tm_iocb(srb_t *sp, struct tsk_mgmt_entry *tsk)
 	scsi_qla_host_t *vha = fcport->vha;
 	struct qla_hw_data *ha = vha->hw;
 	struct srb_iocb *iocb = &sp->u.iocb_cmd;
-	struct req_que *req = vha->req;
+	struct req_que *req = sp->qpair->req;
 
 	flags = iocb->u.tmf.flags;
 	lun = iocb->u.tmf.lun;
@@ -2557,7 +2557,8 @@ qla24xx_tm_iocb(srb_t *sp, struct tsk_mgmt_entry *tsk)
 	tsk->port_id[2] = fcport->d_id.b.domain;
 	tsk->vp_index = fcport->vha->vp_idx;
 
-	if (flags == TCF_LUN_RESET) {
+	if (flags & (TCF_LUN_RESET | TCF_ABORT_TASK_SET|
+	    TCF_CLEAR_TASK_SET|TCF_CLEAR_ACA)) {
 		int_to_scsilun(lun, &tsk->lun);
 		host_to_fcp_swap((uint8_t *)&tsk->lun,
 			sizeof(tsk->lun));