Merge git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending

Pull SCSI target fixes from Nicholas Bellinger:
 "This includes the long awaited series to address a set of bugs around
  active I/O remote-port LUN_RESET, as well as properly handling this
  same case with concurrent fabric driver session disconnect ->
  reconnect.

  Note this set of LUN_RESET bug-fixes has been surviving extended
  testing on both v4.5-rc1 and v3.14.y code over the last weeks, and is
  CC'ed for stable as it's something folks using multiple ESX connected
  hosts with slow backends can certainly trigger.

  The highlights also include:

   - Fix WRITE_SAME/DISCARD emulation 4k sector conversion in
     target/iblock (Mike Christie)

   - Fix TMR abort interaction and AIO type TMR response in qla2xxx
     target (Quinn Tran + Swapnil Nagle)

   - Fix >= v3.17 stale descriptor pointer regression in qla2xxx target
     (Quinn Tran)

   - Fix >= v4.5-rc1 return regression with unmap_zeros_data_store new
     configfs store handler (nab)

   - Add CPU affinity flag + convert qla2xxx to use bit (Quinn + HCH +
     Bart)"

* git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending:
  qla2xxx: use TARGET_SCF_USE_CPUID flag to indiate CPU Affinity
  target/transport: add flag to indicate CPU Affinity is observed
  target: Fix incorrect unmap_zeroes_data_store return
  qla2xxx: Use ATIO type to send correct tmr response
  qla2xxx: Fix stale pointer access.
  target/user: Fix cast from pointer to phys_addr_t
  target: Drop legacy se_cmd->task_stop_comp + REQUEST_STOP usage
  target: Fix race with SCF_SEND_DELAYED_TAS handling
  target: Fix remote-port TMR ABORT + se_cmd fabric stop
  target: Fix TAS handling for multi-session se_node_acls
  target: Fix LUN_RESET active TMR descriptor handling
  target: Fix LUN_RESET active I/O handling for ACK_KREF
  qla2xxx: Fix TMR ABORT interaction issue between qla2xxx and TCM
  qla2xxx: Fix warning reported by static checker
  target: Fix WRITE_SAME/DISCARD conversion to linux 512b sectors

8 files changed, 183 insertions, 60 deletions

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 52a87657c7dd..692a7570b5e1 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -2204,7 +2204,7 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
 	/* Clear outstanding commands array. */
 	for (que = 0; que < ha->max_req_queues; que++) {
 		req = ha->req_q_map[que];
-		if (!req)
+		if (!req || !test_bit(que, ha->req_qid_map))
 			continue;
 		req->out_ptr = (void *)(req->ring + req->length);
 		*req->out_ptr = 0;
@@ -2221,7 +2221,7 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
 
 	for (que = 0; que < ha->max_rsp_queues; que++) {
 		rsp = ha->rsp_q_map[que];
-		if (!rsp)
+		if (!rsp || !test_bit(que, ha->rsp_qid_map))
 			continue;
 		rsp->in_ptr = (void *)(rsp->ring + rsp->length);
 		*rsp->in_ptr = 0;
@@ -4981,7 +4981,7 @@ qla25xx_init_queues(struct qla_hw_data *ha)
 
 	for (i = 1; i < ha->max_rsp_queues; i++) {
 		rsp = ha->rsp_q_map[i];
-		if (rsp) {
+		if (rsp && test_bit(i, ha->rsp_qid_map)) {
 			rsp->options &= ~BIT_0;
 			ret = qla25xx_init_rsp_que(base_vha, rsp);
 			if (ret != QLA_SUCCESS)
@@ -4996,8 +4996,8 @@ qla25xx_init_queues(struct qla_hw_data *ha)
 	}
 	for (i = 1; i < ha->max_req_queues; i++) {
 		req = ha->req_q_map[i];
-		if (req) {
-		/* Clear outstanding commands array. */
+		if (req && test_bit(i, ha->req_qid_map)) {
+			/* Clear outstanding commands array. */
 			req->options &= ~BIT_0;
 			ret = qla25xx_init_req_que(base_vha, req);
 			if (ret != QLA_SUCCESS)
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index d4d65eb0e9b4..4af95479a9db 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -3063,9 +3063,9 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 		    "MSI-X: Failed to enable support "
 		    "-- %d/%d\n Retry with %d vectors.\n",
 		    ha->msix_count, ret, ret);
+		ha->msix_count = ret;
+		ha->max_rsp_queues = ha->msix_count - 1;
 	}
-	ha->msix_count = ret;
-	ha->max_rsp_queues = ha->msix_count - 1;
 	ha->msix_entries = kzalloc(sizeof(struct qla_msix_entry) *
 				ha->msix_count, GFP_KERNEL);
 	if (!ha->msix_entries) {
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index c5dd594f6c31..cf7ba52bae66 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -600,7 +600,7 @@ qla25xx_delete_queues(struct scsi_qla_host *vha)
 	/* Delete request queues */
 	for (cnt = 1; cnt < ha->max_req_queues; cnt++) {
 		req = ha->req_q_map[cnt];
-		if (req) {
+		if (req && test_bit(cnt, ha->req_qid_map)) {
 			ret = qla25xx_delete_req_que(vha, req);
 			if (ret != QLA_SUCCESS) {
 				ql_log(ql_log_warn, vha, 0x00ea,
@@ -614,7 +614,7 @@ qla25xx_delete_queues(struct scsi_qla_host *vha)
 	/* Delete response queues */
 	for (cnt = 1; cnt < ha->max_rsp_queues; cnt++) {
 		rsp = ha->rsp_q_map[cnt];
-		if (rsp) {
+		if (rsp && test_bit(cnt, ha->rsp_qid_map)) {
 			ret = qla25xx_delete_rsp_que(vha, rsp);
 			if (ret != QLA_SUCCESS) {
 				ql_log(ql_log_warn, vha, 0x00eb,
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index f1788db43195..f6c7ce35b542 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -409,6 +409,9 @@ static void qla2x00_free_queues(struct qla_hw_data *ha)
 	int cnt;
 
 	for (cnt = 0; cnt < ha->max_req_queues; cnt++) {
+		if (!test_bit(cnt, ha->req_qid_map))
+			continue;
+
 		req = ha->req_q_map[cnt];
 		qla2x00_free_req_que(ha, req);
 	}
@@ -416,6 +419,9 @@ static void qla2x00_free_queues(struct qla_hw_data *ha)
 	ha->req_q_map = NULL;
 
 	for (cnt = 0; cnt < ha->max_rsp_queues; cnt++) {
+		if (!test_bit(cnt, ha->rsp_qid_map))
+			continue;
+
 		rsp = ha->rsp_q_map[cnt];
 		qla2x00_free_rsp_que(ha, rsp);
 	}
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 8075a4cdb45c..ee967becd257 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -105,7 +105,7 @@ static void qlt_response_pkt(struct scsi_qla_host *ha, response_t *pkt);
 static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun,
 	int fn, void *iocb, int flags);
 static void qlt_send_term_exchange(struct scsi_qla_host *ha, struct qla_tgt_cmd
-	*cmd, struct atio_from_isp *atio, int ha_locked);
+	*cmd, struct atio_from_isp *atio, int ha_locked, int ul_abort);
 static void qlt_reject_free_srr_imm(struct scsi_qla_host *ha,
 	struct qla_tgt_srr_imm *imm, int ha_lock);
 static void qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha,
@@ -1756,7 +1756,7 @@ void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *mcmd)
 		qlt_send_notify_ack(vha, &mcmd->orig_iocb.imm_ntfy,
 		    0, 0, 0, 0, 0, 0);
 	else {
-		if (mcmd->se_cmd.se_tmr_req->function == TMR_ABORT_TASK)
+		if (mcmd->orig_iocb.atio.u.raw.entry_type == ABTS_RECV_24XX)
 			qlt_24xx_send_abts_resp(vha, &mcmd->orig_iocb.abts,
 			    mcmd->fc_tm_rsp, false);
 		else
@@ -2665,7 +2665,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 			/* no need to terminate. FW already freed exchange. */
 			qlt_abort_cmd_on_host_reset(cmd->vha, cmd);
 		else
-			qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+			qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		return 0;
 	}
@@ -3173,7 +3173,8 @@ static int __qlt_send_term_exchange(struct scsi_qla_host *vha,
 }
 
 static void qlt_send_term_exchange(struct scsi_qla_host *vha,
-	struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked)
+	struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked,
+	int ul_abort)
 {
 	unsigned long flags = 0;
 	int rc;
@@ -3193,8 +3194,7 @@ static void qlt_send_term_exchange(struct scsi_qla_host *vha,
 		qlt_alloc_qfull_cmd(vha, atio, 0, 0);
 
 done:
-	if (cmd && (!cmd->aborted ||
-	    !cmd->cmd_sent_to_fw)) {
+	if (cmd && !ul_abort && !cmd->aborted) {
 		if (cmd->sg_mapped)
 			qlt_unmap_sg(vha, cmd);
 		vha->hw->tgt.tgt_ops->free_cmd(cmd);
@@ -3253,21 +3253,38 @@ static void qlt_chk_exch_leak_thresh_hold(struct scsi_qla_host *vha)
 
 }
 
-void qlt_abort_cmd(struct qla_tgt_cmd *cmd)
+int qlt_abort_cmd(struct qla_tgt_cmd *cmd)
 {
 	struct qla_tgt *tgt = cmd->tgt;
 	struct scsi_qla_host *vha = tgt->vha;
 	struct se_cmd *se_cmd = &cmd->se_cmd;
+	unsigned long flags;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014,
 	    "qla_target(%d): terminating exchange for aborted cmd=%p "
 	    "(se_cmd=%p, tag=%llu)", vha->vp_idx, cmd, &cmd->se_cmd,
 	    se_cmd->tag);
 
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	if (cmd->aborted) {
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+		/*
+		 * It's normal to see 2 calls in this path:
+		 *  1) XFER Rdy completion + CMD_T_ABORT
+		 *  2) TCM TMR - drain_state_list
+		 */
+	        ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+			"multiple abort. %p transport_state %x, t_state %x,"
+			" se_cmd_flags %x \n", cmd, cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,cmd->se_cmd.se_cmd_flags);
+		return EIO;
+	}
 	cmd->aborted = 1;
 	cmd->cmd_flags |= BIT_6;
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
 
-	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0);
+	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0, 1);
+	return 0;
 }
 EXPORT_SYMBOL(qlt_abort_cmd);
 
@@ -3282,6 +3299,9 @@ void qlt_free_cmd(struct qla_tgt_cmd *cmd)
 
 	BUG_ON(cmd->cmd_in_wq);
 
+	if (cmd->sg_mapped)
+		qlt_unmap_sg(cmd->vha, cmd);
+
 	if (!cmd->q_full)
 		qlt_decr_num_pend_cmds(cmd->vha);
 
@@ -3399,7 +3419,7 @@ static int qlt_term_ctio_exchange(struct scsi_qla_host *vha, void *ctio,
 		term = 1;
 
 	if (term)
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 
 	return term;
 }
@@ -3580,12 +3600,13 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 		case CTIO_PORT_LOGGED_OUT:
 		case CTIO_PORT_UNAVAILABLE:
 		{
-			int logged_out = (status & 0xFFFF);
+			int logged_out =
+				(status & 0xFFFF) == CTIO_PORT_LOGGED_OUT;
+
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf059,
 			    "qla_target(%d): CTIO with %s status %x "
 			    "received (state %x, se_cmd %p)\n", vha->vp_idx,
-			    (logged_out == CTIO_PORT_LOGGED_OUT) ?
-			    "PORT LOGGED OUT" : "PORT UNAVAILABLE",
+			    logged_out ? "PORT LOGGED OUT" : "PORT UNAVAILABLE",
 			    status, cmd->state, se_cmd);
 
 			if (logged_out && cmd->sess) {
@@ -3754,6 +3775,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd)
 		goto out_term;
 	}
 
+	spin_lock_init(&cmd->cmd_lock);
 	cdb = &atio->u.isp24.fcp_cmnd.cdb[0];
 	cmd->se_cmd.tag = atio->u.isp24.exchange_addr;
 	cmd->unpacked_lun = scsilun_to_int(
@@ -3796,7 +3818,7 @@ out_term:
 	 */
 	cmd->cmd_flags |= BIT_2;
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	qlt_send_term_exchange(vha, NULL, &cmd->atio, 1);
+	qlt_send_term_exchange(vha, NULL, &cmd->atio, 1, 0);
 
 	qlt_decr_num_pend_cmds(vha);
 	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
@@ -3918,7 +3940,7 @@ static void qlt_create_sess_from_atio(struct work_struct *work)
 
 out_term:
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	qlt_send_term_exchange(vha, NULL, &op->atio, 1);
+	qlt_send_term_exchange(vha, NULL, &op->atio, 1, 0);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	kfree(op);
 
@@ -3982,7 +4004,8 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 
 	cmd->cmd_in_wq = 1;
 	cmd->cmd_flags |= BIT_0;
-	cmd->se_cmd.cpuid = -1;
+	cmd->se_cmd.cpuid = ha->msix_count ?
+		ha->tgt.rspq_vector_cpuid : WORK_CPU_UNBOUND;
 
 	spin_lock(&vha->cmd_list_lock);
 	list_add_tail(&cmd->cmd_list, &vha->qla_cmd_list);
@@ -3990,7 +4013,6 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 
 	INIT_WORK(&cmd->work, qlt_do_work);
 	if (ha->msix_count) {
-		cmd->se_cmd.cpuid = ha->tgt.rspq_vector_cpuid;
 		if (cmd->atio.u.isp24.fcp_cmnd.rddata)
 			queue_work_on(smp_processor_id(), qla_tgt_wq,
 			    &cmd->work);
@@ -4771,7 +4793,7 @@ out_reject:
 		dump_stack();
 	} else {
 		cmd->cmd_flags |= BIT_9;
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 	}
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
@@ -4950,7 +4972,7 @@ static void qlt_prepare_srr_imm(struct scsi_qla_host *vha,
 				    sctio, sctio->srr_id);
 				list_del(&sctio->srr_list_entry);
 				qlt_send_term_exchange(vha, sctio->cmd,
-				    &sctio->cmd->atio, 1);
+				    &sctio->cmd->atio, 1, 0);
 				kfree(sctio);
 			}
 		}
@@ -5123,7 +5145,7 @@ static int __qlt_send_busy(struct scsi_qla_host *vha,
 	    atio->u.isp24.fcp_hdr.s_id);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 	if (!sess) {
-		qlt_send_term_exchange(vha, NULL, atio, 1);
+		qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 		return 0;
 	}
 	/* Sending marker isn't necessary, since we called from ISR */
@@ -5406,7 +5428,7 @@ static void qlt_24xx_atio_pkt(struct scsi_qla_host *vha,
 #if 1 /* With TERM EXCHANGE some FC cards refuse to boot */
 				qlt_send_busy(vha, atio, SAM_STAT_BUSY);
 #else
-				qlt_send_term_exchange(vha, NULL, atio, 1);
+				qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 #endif
 
 				if (!ha_locked)
@@ -5523,7 +5545,7 @@ static void qlt_response_pkt(struct scsi_qla_host *vha, response_t *pkt)
 #if 1 /* With TERM EXCHANGE some FC cards refuse to boot */
 				qlt_send_busy(vha, atio, 0);
 #else
-				qlt_send_term_exchange(vha, NULL, atio, 1);
+				qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 #endif
 			} else {
 				if (tgt->tgt_stop) {
@@ -5532,7 +5554,7 @@ static void qlt_response_pkt(struct scsi_qla_host *vha, response_t *pkt)
 					    "command to target, sending TERM "
 					    "EXCHANGE for rsp\n");
 					qlt_send_term_exchange(vha, NULL,
-					    atio, 1);
+					    atio, 1, 0);
 				} else {
 					ql_dbg(ql_dbg_tgt, vha, 0xe060,
 					    "qla_target(%d): Unable to send "
@@ -5960,7 +5982,7 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 	return;
 
 out_term:
-	qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 0);
+	qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 1, 0);
 	if (sess)
 		ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 71b2865ba3c8..22a6a767fe07 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -943,6 +943,36 @@ struct qla_tgt_sess {
 	qlt_plogi_ack_t *plogi_link[QLT_PLOGI_LINK_MAX];
 };
 
+typedef enum {
+	/*
+	 * BIT_0 - Atio Arrival / schedule to work
+	 * BIT_1 - qlt_do_work
+	 * BIT_2 - qlt_do work failed
+	 * BIT_3 - xfer rdy/tcm_qla2xxx_write_pending
+	 * BIT_4 - read respond/tcm_qla2xx_queue_data_in
+	 * BIT_5 - status respond / tcm_qla2xx_queue_status
+	 * BIT_6 - tcm request to abort/Term exchange.
+	 *	pre_xmit_response->qlt_send_term_exchange
+	 * BIT_7 - SRR received (qlt_handle_srr->qlt_xmit_response)
+	 * BIT_8 - SRR received (qlt_handle_srr->qlt_rdy_to_xfer)
+	 * BIT_9 - SRR received (qla_handle_srr->qlt_send_term_exchange)
+	 * BIT_10 - Data in - hanlde_data->tcm_qla2xxx_handle_data
+
+	 * BIT_12 - good completion - qlt_ctio_do_completion -->free_cmd
+	 * BIT_13 - Bad completion -
+	 *	qlt_ctio_do_completion --> qlt_term_ctio_exchange
+	 * BIT_14 - Back end data received/sent.
+	 * BIT_15 - SRR prepare ctio
+	 * BIT_16 - complete free
+	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
+	 * BIT_18 - completion w/abort status
+	 * BIT_19 - completion w/unknown status
+	 * BIT_20 - tcm_qla2xxx_free_cmd
+	 */
+	CMD_FLAG_DATA_WORK = BIT_11,
+	CMD_FLAG_DATA_WORK_FREE = BIT_21,
+} cmd_flags_t;
+
 struct qla_tgt_cmd {
 	struct se_cmd se_cmd;
 	struct qla_tgt_sess *sess;
@@ -952,6 +982,7 @@ struct qla_tgt_cmd {
 	/* Sense buffer that will be mapped into outgoing status */
 	unsigned char sense_buffer[TRANSPORT_SENSE_BUFFER];
 
+	spinlock_t cmd_lock;
 	/* to save extra sess dereferences */
 	unsigned int conf_compl_supported:1;
 	unsigned int sg_mapped:1;
@@ -986,30 +1017,8 @@ struct qla_tgt_cmd {
 
 	uint64_t jiffies_at_alloc;
 	uint64_t jiffies_at_free;
-	/* BIT_0 - Atio Arrival / schedule to work
-	 * BIT_1 - qlt_do_work
-	 * BIT_2 - qlt_do work failed
-	 * BIT_3 - xfer rdy/tcm_qla2xxx_write_pending
-	 * BIT_4 - read respond/tcm_qla2xx_queue_data_in
-	 * BIT_5 - status respond / tcm_qla2xx_queue_status
-	 * BIT_6 - tcm request to abort/Term exchange.
-	 *	pre_xmit_response->qlt_send_term_exchange
-	 * BIT_7 - SRR received (qlt_handle_srr->qlt_xmit_response)
-	 * BIT_8 - SRR received (qlt_handle_srr->qlt_rdy_to_xfer)
-	 * BIT_9 - SRR received (qla_handle_srr->qlt_send_term_exchange)
-	 * BIT_10 - Data in - hanlde_data->tcm_qla2xxx_handle_data
-	 * BIT_11 - Data actually going to TCM : tcm_qla2xx_handle_data_work
-	 * BIT_12 - good completion - qlt_ctio_do_completion -->free_cmd
-	 * BIT_13 - Bad completion -
-	 *	qlt_ctio_do_completion --> qlt_term_ctio_exchange
-	 * BIT_14 - Back end data received/sent.
-	 * BIT_15 - SRR prepare ctio
-	 * BIT_16 - complete free
-	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
-	 * BIT_18 - completion w/abort status
-	 * BIT_19 - completion w/unknown status
-	 */
-	uint32_t cmd_flags;
+
+	cmd_flags_t cmd_flags;
 };
 
 struct qla_tgt_sess_work_param {
@@ -1148,7 +1157,7 @@ static inline void sid_to_portid(const uint8_t *s_id, port_id_t *p)
 extern void qlt_response_pkt_all_vps(struct scsi_qla_host *, response_t *);
 extern int qlt_rdy_to_xfer(struct qla_tgt_cmd *);
 extern int qlt_xmit_response(struct qla_tgt_cmd *, int, uint8_t);
-extern void qlt_abort_cmd(struct qla_tgt_cmd *);
+extern int qlt_abort_cmd(struct qla_tgt_cmd *);
 extern void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_cmd(struct qla_tgt_cmd *cmd);
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index ddbe2e7ac14d..c3e622524604 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -395,6 +395,10 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha,
 	if (ent->t263.queue_type == T263_QUEUE_TYPE_REQ) {
 		for (i = 0; i < vha->hw->max_req_queues; i++) {
 			struct req_que *req = vha->hw->req_q_map[i];
+
+			if (!test_bit(i, vha->hw->req_qid_map))
+				continue;
+
 			if (req || !buf) {
 				length = req ?
 				    req->length : REQUEST_ENTRY_CNT_24XX;
@@ -408,6 +412,10 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha,
 	} else if (ent->t263.queue_type == T263_QUEUE_TYPE_RSP) {
 		for (i = 0; i < vha->hw->max_rsp_queues; i++) {
 			struct rsp_que *rsp = vha->hw->rsp_q_map[i];
+
+			if (!test_bit(i, vha->hw->rsp_qid_map))
+				continue;
+
 			if (rsp || !buf) {
 				length = rsp ?
 				    rsp->length : RESPONSE_ENTRY_CNT_MQ;
@@ -634,6 +642,10 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha,
 	if (ent->t274.queue_type == T274_QUEUE_TYPE_REQ_SHAD) {
 		for (i = 0; i < vha->hw->max_req_queues; i++) {
 			struct req_que *req = vha->hw->req_q_map[i];
+
+			if (!test_bit(i, vha->hw->req_qid_map))
+				continue;
+
 			if (req || !buf) {
 				qla27xx_insert16(i, buf, len);
 				qla27xx_insert16(1, buf, len);
@@ -645,6 +657,10 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha,
 	} else if (ent->t274.queue_type == T274_QUEUE_TYPE_RSP_SHAD) {
 		for (i = 0; i < vha->hw->max_rsp_queues; i++) {
 			struct rsp_que *rsp = vha->hw->rsp_q_map[i];
+
+			if (!test_bit(i, vha->hw->rsp_qid_map))
+				continue;
+
 			if (rsp || !buf) {
 				qla27xx_insert16(i, buf, len);
 				qla27xx_insert16(1, buf, len);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index faf0a126627f..1808a01cfb7e 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -298,6 +298,10 @@ static void tcm_qla2xxx_free_cmd(struct qla_tgt_cmd *cmd)
 {
 	cmd->vha->tgt_counters.core_qla_free_cmd++;
 	cmd->cmd_in_wq = 1;
+
+	BUG_ON(cmd->cmd_flags & BIT_20);
+	cmd->cmd_flags |= BIT_20;
+
 	INIT_WORK(&cmd->work, tcm_qla2xxx_complete_free);
 	queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work);
 }
@@ -374,6 +378,20 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
+
+	if (cmd->aborted) {
+		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
+		 * can get ahead of this cmd. tcm_qla2xxx_aborted_task
+		 * already kick start the free.
+		 */
+		pr_debug("write_pending aborted cmd[%p] refcount %d "
+			"transport_state %x, t_state %x, se_cmd_flags %x\n",
+			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,
+			cmd->se_cmd.se_cmd_flags);
+		return 0;
+	}
 	cmd->cmd_flags |= BIT_3;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
@@ -405,7 +423,7 @@ static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd)
 	    se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) {
 		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
 		wait_for_completion_timeout(&se_cmd->t_transport_stop_comp,
-					    3 * HZ);
+						50);
 		return 0;
 	}
 	spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
@@ -444,6 +462,9 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
 	if (bidi)
 		flags |= TARGET_SCF_BIDI_OP;
 
+	if (se_cmd->cpuid != WORK_CPU_UNBOUND)
+		flags |= TARGET_SCF_USE_CPUID;
+
 	sess = cmd->sess;
 	if (!sess) {
 		pr_err("Unable to locate struct qla_tgt_sess from qla_tgt_cmd\n");
@@ -465,13 +486,25 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
 static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
 {
 	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
+	unsigned long flags;
 
 	/*
 	 * Ensure that the complete FCP WRITE payload has been received.
 	 * Otherwise return an exception via CHECK_CONDITION status.
 	 */
 	cmd->cmd_in_wq = 0;
-	cmd->cmd_flags |= BIT_11;
+
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	cmd->cmd_flags |= CMD_FLAG_DATA_WORK;
+	if (cmd->aborted) {
+		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+
+		tcm_qla2xxx_free_cmd(cmd);
+		return;
+	}
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+
 	cmd->vha->tgt_counters.qla_core_ret_ctio++;
 	if (!cmd->write_data_transferred) {
 		/*
@@ -546,6 +579,20 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
 
+	if (cmd->aborted) {
+		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
+		 * can get ahead of this cmd. tcm_qla2xxx_aborted_task
+		 * already kick start the free.
+		 */
+		pr_debug("queue_data_in aborted cmd[%p] refcount %d "
+			"transport_state %x, t_state %x, se_cmd_flags %x\n",
+			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,
+			cmd->se_cmd.se_cmd_flags);
+		return 0;
+	}
+
 	cmd->cmd_flags |= BIT_4;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
@@ -637,11 +684,34 @@ static void tcm_qla2xxx_queue_tm_rsp(struct se_cmd *se_cmd)
 	qlt_xmit_tm_rsp(mcmd);
 }
 
+
+#define DATA_WORK_NOT_FREE(_flags) \
+	(( _flags & (CMD_FLAG_DATA_WORK|CMD_FLAG_DATA_WORK_FREE)) == \
+	 CMD_FLAG_DATA_WORK)
 static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	qlt_abort_cmd(cmd);
+	unsigned long flags;
+
+	if (qlt_abort_cmd(cmd))
+		return;
+
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	if ((cmd->state == QLA_TGT_STATE_NEW)||
+		((cmd->state == QLA_TGT_STATE_DATA_IN) &&
+		 DATA_WORK_NOT_FREE(cmd->cmd_flags)) ) {
+
+		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+		/* Cmd have not reached firmware.
+		 * Use this trigger to free it. */
+		tcm_qla2xxx_free_cmd(cmd);
+		return;
+	}
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+	return;
+
 }
 
 static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *,