Merge commit v5.4.132 into fslc-5.15-2.2.x-imx

Revert the following commits before merging, the sources have been
heavely modified by NXP.

5a86ca588b3f9 Revert "perf/imx_ddr: don't enable counter0 if none of 4 counters are used"
56ad67babb7fb Revert "usb: phy: mxs: fix getting wrong state with mxs_phy_is_otg_host()"
50b3a42d82f07 Revert "USB: core: Unite old scheme and new scheme descriptor reads"
cdcf46014f5ca Revert "USB: core: Change usb_get_device_descriptor() API"
2f2af6028f201 Revert "USB: core: Fix race by not overwriting udev->descriptor in hub_port_init()"
9e168d3268f89 Revert "USB: core: Fix oversight in SuperSpeed initialization"
7e95107f9b664 Revert "PCI: dwc: Add start_link/stop_link inlines"
d0bec10a7f796 Revert "PCI: layerscape: Add the endpoint linkup notifier support"
aaf9dc6089bc3 Revert "PCI: layerscape: Add workaround for lost link capabilities during reset"

Conflicts:
	arch/arm/boot/dts/imx6qdl.dtsi
	arch/arm/boot/dts/imx6sx.dtsi
		Keep stable node name changes
	drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
		Keep stable code change
	drivers/media/i2c/ov5640.c
		Keep stable code change

Signed-off-by: Max Krummenacher <max.krummenacher@toradex.com>

13 files changed, 269 insertions, 118 deletions

diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 4a5df867057b..fe0e8b23a805 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -3084,8 +3084,6 @@ qla24xx_vport_create(struct fc_vport *fc_vport, bool disable)
 			vha->flags.difdix_supported = 1;
 			ql_dbg(ql_dbg_user, vha, 0x7082,
 			    "Registered for DIF/DIX type 1 and 3 protection.\n");
-			if (ql2xenabledif == 1)
-				prot = SHOST_DIX_TYPE0_PROTECTION;
 			scsi_host_set_prot(vha->host,
 			    prot | SHOST_DIF_TYPE1_PROTECTION
 			    | SHOST_DIF_TYPE2_PROTECTION
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 7cf1f78cbaee..8e9ffbec6643 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -18,7 +18,7 @@
  * | Queue Command and IO tracing |       0x3074       | 0x300b         |
  * |                              |                    | 0x3027-0x3028  |
  * |                              |                    | 0x303d-0x3041  |
- * |                              |                    | 0x302d,0x3033  |
+ * |                              |                    | 0x302e,0x3033  |
  * |                              |                    | 0x3036,0x3038  |
  * |                              |                    | 0x303a		|
  * | DPC Thread                   |       0x4023       | 0x4002,0x4013  |
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 83228ce822af..d70c2f4ba718 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -453,6 +453,7 @@ static inline be_id_t port_id_to_be_id(port_id_t port_id)
 }
 
 struct tmf_arg {
+	struct list_head tmf_elem;
 	struct qla_qpair *qpair;
 	struct fc_port *fcport;
 	struct scsi_qla_host *vha;
@@ -2523,7 +2524,6 @@ enum rscn_addr_format {
 typedef struct fc_port {
 	struct list_head list;
 	struct scsi_qla_host *vha;
-	struct list_head tmf_pending;
 
 	unsigned int conf_compl_supported:1;
 	unsigned int deleted:2;
@@ -2544,9 +2544,6 @@ typedef struct fc_port {
 	unsigned int do_prli_nvme:1;
 
 	uint8_t nvme_flag;
-	uint8_t active_tmf;
-#define MAX_ACTIVE_TMF 8
-
 	uint8_t node_name[WWN_SIZE];
 	uint8_t port_name[WWN_SIZE];
 	port_id_t d_id;
@@ -3729,6 +3726,16 @@ struct qla_fw_resources {
 	u16 pad;
 };
 
+struct qla_fw_res {
+	u16      iocb_total;
+	u16      iocb_limit;
+	atomic_t iocb_used;
+
+	u16      exch_total;
+	u16      exch_limit;
+	atomic_t exch_used;
+};
+
 #define QLA_IOCB_PCT_LIMIT 95
 
 /*Queue pair data structure */
@@ -4356,7 +4363,6 @@ struct qla_hw_data {
 	uint8_t		aen_mbx_count;
 	atomic_t	num_pend_mbx_stage1;
 	atomic_t	num_pend_mbx_stage2;
-	atomic_t	num_pend_mbx_stage3;
 	uint16_t	frame_payload_size;
 
 	uint32_t	login_retry_count;
@@ -4626,6 +4632,8 @@ struct qla_hw_data {
 		uint32_t	flt_region_aux_img_status_sec;
 	};
 	uint8_t         active_image;
+	uint8_t active_tmf;
+#define MAX_ACTIVE_TMF 8
 
 	/* Needed for BEACON */
 	uint16_t        beacon_blink_led;
@@ -4640,6 +4648,8 @@ struct qla_hw_data {
 
 	struct qla_msix_entry *msix_entries;
 
+	struct list_head tmf_pending;
+	struct list_head tmf_active;
 	struct list_head        vp_list;        /* list of VP */
 	unsigned long   vp_idx_map[(MAX_MULTI_ID_FABRIC / 8) /
 			sizeof(unsigned long)];
@@ -4768,6 +4778,7 @@ struct qla_hw_data {
 	spinlock_t sadb_lock;	/* protects list */
 	struct els_reject elsrej;
 	u8 edif_post_stop_cnt_down;
+	struct qla_fw_res fwres ____cacheline_aligned;
 };
 
 #define RX_ELS_SIZE (roundup(sizeof(struct enode) + ELS_MAX_PAYLOAD, SMP_CACHE_BYTES))
diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c
index 8f6f56c9584c..aa9d69e5274d 100644
--- a/drivers/scsi/qla2xxx/qla_dfs.c
+++ b/drivers/scsi/qla2xxx/qla_dfs.c
@@ -276,6 +276,16 @@ qla_dfs_fw_resource_cnt_show(struct seq_file *s, void *unused)
 
 		seq_printf(s, "estimate exchange used[%d] high water limit [%d] n",
 			   exch_used, ha->base_qpair->fwres.exch_limit);
+
+		if (ql2xenforce_iocb_limit == 2) {
+			iocbs_used = atomic_read(&ha->fwres.iocb_used);
+			exch_used  = atomic_read(&ha->fwres.exch_used);
+			seq_printf(s, "        estimate iocb2 used [%d] high water limit [%d]\n",
+					iocbs_used, ha->fwres.iocb_limit);
+
+			seq_printf(s, "        estimate exchange2 used[%d] high water limit [%d] \n",
+					exch_used, ha->fwres.exch_limit);
+		}
 	}
 
 	return 0;
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index 9e467262c0f1..3861e41a8d2c 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -143,6 +143,7 @@ void qla_edif_sess_down(struct scsi_qla_host *vha, struct fc_port *sess);
 void qla_edif_clear_appdata(struct scsi_qla_host *vha,
 			    struct fc_port *fcport);
 const char *sc_to_str(uint16_t cmd);
+void qla_adjust_iocb_limit(scsi_qla_host_t *vha);
 
 /*
  * Global Data in qla_os.c source file.
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index a97872b6350c..1a2ceef92bf0 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -503,6 +503,7 @@ static
 void qla24xx_handle_adisc_event(scsi_qla_host_t *vha, struct event_arg *ea)
 {
 	struct fc_port *fcport = ea->fcport;
+	unsigned long flags;
 
 	ql_dbg(ql_dbg_disc, vha, 0x20d2,
 	    "%s %8phC DS %d LS %d rc %d login %d|%d rscn %d|%d lid %d\n",
@@ -517,9 +518,15 @@ void qla24xx_handle_adisc_event(scsi_qla_host_t *vha, struct event_arg *ea)
 		ql_dbg(ql_dbg_disc, vha, 0x2066,
 		    "%s %8phC: adisc fail: post delete\n",
 		    __func__, ea->fcport->port_name);
+
+		spin_lock_irqsave(&vha->work_lock, flags);
 		/* deleted = 0 & logout_on_delete = force fw cleanup */
-		fcport->deleted = 0;
+		if (fcport->deleted == QLA_SESS_DELETED)
+			fcport->deleted = 0;
+
 		fcport->logout_on_delete = 1;
+		spin_unlock_irqrestore(&vha->work_lock, flags);
+
 		qlt_schedule_sess_for_deletion(ea->fcport);
 		return;
 	}
@@ -1129,7 +1136,7 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)
 	u16 *mb;
 
 	if (!vha->flags.online || (fcport->flags & FCF_ASYNC_SENT))
-		return rval;
+		goto done;
 
 	ql_dbg(ql_dbg_disc, vha, 0x20d9,
 	    "Async-gnlist WWPN %8phC \n", fcport->port_name);
@@ -1183,8 +1190,9 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)
 done_free_sp:
 	/* ref: INIT */
 	kref_put(&sp->cmd_kref, qla2x00_sp_release);
+	fcport->flags &= ~(FCF_ASYNC_SENT);
 done:
-	fcport->flags &= ~(FCF_ASYNC_ACTIVE | FCF_ASYNC_SENT);
+	fcport->flags &= ~(FCF_ASYNC_ACTIVE);
 	return rval;
 }
 
@@ -1441,7 +1449,6 @@ void __qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)
 
 	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
 	ea->fcport->login_gen++;
-	ea->fcport->deleted = 0;
 	ea->fcport->logout_on_delete = 1;
 
 	if (!ea->fcport->login_succ && !IS_SW_RESV_ADDR(ea->fcport->d_id)) {
@@ -1998,12 +2005,11 @@ 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++) {
@@ -2034,10 +2040,14 @@ static void qla_marker_sp_done(srb_t *sp, int res)
 	complete(&tmf->u.tmf.comp);
 }
 
-#define  START_SP_W_RETRIES(_sp, _rval) \
+#define  START_SP_W_RETRIES(_sp, _rval, _chip_gen, _login_gen) \
 {\
 	int cnt = 5; \
 	do { \
+		if (_chip_gen != sp->vha->hw->chip_reset || _login_gen != sp->fcport->login_gen) {\
+			_rval = EINVAL; \
+			break; \
+		} \
 		_rval = qla2x00_start_sp(_sp); \
 		if (_rval == EAGAIN) \
 			msleep(1); \
@@ -2060,6 +2070,7 @@ qla26xx_marker(struct tmf_arg *arg)
 	srb_t *sp;
 	int rval = QLA_FUNCTION_FAILED;
 	fc_port_t *fcport = arg->fcport;
+	u32 chip_gen, login_gen;
 
 	if (TMF_NOT_READY(arg->fcport)) {
 		ql_dbg(ql_dbg_taskm, vha, 0x8039,
@@ -2069,6 +2080,9 @@ qla26xx_marker(struct tmf_arg *arg)
 		return QLA_SUSPENDED;
 	}
 
+	chip_gen = vha->hw->chip_reset;
+	login_gen = fcport->login_gen;
+
 	/* ref: INIT */
 	sp = qla2xxx_get_qpair_sp(vha, arg->qpair, fcport, GFP_KERNEL);
 	if (!sp)
@@ -2086,7 +2100,7 @@ qla26xx_marker(struct tmf_arg *arg)
 	tm_iocb->u.tmf.loop_id = fcport->loop_id;
 	tm_iocb->u.tmf.vp_index = vha->vp_idx;
 
-	START_SP_W_RETRIES(sp, rval);
+	START_SP_W_RETRIES(sp, rval, chip_gen, login_gen);
 
 	ql_dbg(ql_dbg_taskm, vha, 0x8006,
 	    "Async-marker hdl=%x loop-id=%x portid=%06x modifier=%x lun=%lld qp=%d rval %d.\n",
@@ -2125,6 +2139,17 @@ 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)
 {
@@ -2132,8 +2157,9 @@ __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,
@@ -2143,6 +2169,9 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg)
 		return QLA_SUSPENDED;
 	}
 
+	chip_gen = vha->hw->chip_reset;
+	login_gen = fcport->login_gen;
+
 	/* ref: INIT */
 	sp = qla2xxx_get_qpair_sp(vha, arg->qpair, fcport, GFP_KERNEL);
 	if (!sp)
@@ -2160,7 +2189,7 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg)
 	tm_iocb->u.tmf.flags = arg->flags;
 	tm_iocb->u.tmf.lun = arg->lun;
 
-	START_SP_W_RETRIES(sp, rval);
+	START_SP_W_RETRIES(sp, rval, chip_gen, login_gen);
 
 	ql_dbg(ql_dbg_taskm, vha, 0x802f,
 	    "Async-tmf hdl=%x loop-id=%x portid=%06x ctrl=%x lun=%lld qp=%d rval=%x.\n",
@@ -2178,8 +2207,26 @@ __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)) {
+		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;
+		}
+	}
+	if (tm_iocb->u.tmf.data)
+		rval = tm_iocb->u.tmf.data;
 
 done_free_sp:
 	/* ref: INIT */
@@ -2188,30 +2235,42 @@ done:
 	return rval;
 }
 
-static void qla_put_tmf(fc_port_t *fcport)
+static void qla_put_tmf(struct tmf_arg *arg)
 {
-	struct scsi_qla_host *vha = fcport->vha;
+	struct scsi_qla_host *vha = arg->vha;
 	struct qla_hw_data *ha = vha->hw;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	fcport->active_tmf--;
+	ha->active_tmf--;
+	list_del(&arg->tmf_elem);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 }
 
 static
-int qla_get_tmf(fc_port_t *fcport)
+int qla_get_tmf(struct tmf_arg *arg)
 {
-	struct scsi_qla_host *vha = fcport->vha;
+	struct scsi_qla_host *vha = arg->vha;
 	struct qla_hw_data *ha = vha->hw;
 	unsigned long flags;
+	fc_port_t *fcport = arg->fcport;
 	int rc = 0;
-	LIST_HEAD(tmf_elem);
+	struct tmf_arg *t;
 
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	list_add_tail(&tmf_elem, &fcport->tmf_pending);
+	list_for_each_entry(t, &ha->tmf_active, tmf_elem) {
+		if (t->fcport == arg->fcport && t->lun == arg->lun) {
+			/* reject duplicate TMF */
+			ql_log(ql_log_warn, vha, 0x802c,
+			       "found duplicate TMF.  Nexus=%ld:%06x:%llu.\n",
+			       vha->host_no, fcport->d_id.b24, arg->lun);
+			spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+			return -EINVAL;
+		}
+	}
 
-	while (fcport->active_tmf >= MAX_ACTIVE_TMF) {
+	list_add_tail(&arg->tmf_elem, &ha->tmf_pending);
+	while (ha->active_tmf >= MAX_ACTIVE_TMF) {
 		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 
 		msleep(1);
@@ -2223,15 +2282,17 @@ int qla_get_tmf(fc_port_t *fcport)
 			rc = EIO;
 			break;
 		}
-		if (fcport->active_tmf < MAX_ACTIVE_TMF &&
-		    list_is_first(&tmf_elem, &fcport->tmf_pending))
+		if (ha->active_tmf < MAX_ACTIVE_TMF &&
+		    list_is_first(&arg->tmf_elem, &ha->tmf_pending))
 			break;
 	}
 
-	list_del(&tmf_elem);
+	list_del(&arg->tmf_elem);
 
-	if (!rc)
-		fcport->active_tmf++;
+	if (!rc) {
+		ha->active_tmf++;
+		list_add_tail(&arg->tmf_elem, &ha->tmf_active);
+	}
 
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 
@@ -2243,9 +2304,8 @@ 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;
@@ -2253,47 +2313,22 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun,
 	a.vha = fcport->vha;
 	a.fcport = fcport;
 	a.lun = lun;
+	a.flags = flags;
+	INIT_LIST_HEAD(&a.tmf_elem);
+
 	if (flags & (TCF_LUN_RESET|TCF_ABORT_TASK_SET|TCF_CLEAR_TASK_SET|TCF_CLEAR_ACA)) {
 		a.modifier = MK_SYNC_ID_LUN;
-
-		if (qla_get_tmf(fcport))
-			return QLA_FUNCTION_FAILED;
 	} else {
 		a.modifier = MK_SYNC_ID;
 	}
 
-	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;
+	if (qla_get_tmf(&a))
+		return QLA_FUNCTION_FAILED;
 
 	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);
-
+	qla_put_tmf(&a);
 	return rval;
 }
 
@@ -4149,39 +4184,61 @@ out:
 	return ha->flags.lr_detected;
 }
 
-void qla_init_iocb_limit(scsi_qla_host_t *vha)
+static void __qla_adjust_iocb_limit(struct qla_qpair *qpair)
 {
-	u16 i, num_qps;
-	u32 limit;
-	struct qla_hw_data *ha = vha->hw;
+	u8 num_qps;
+	u16 limit;
+	struct qla_hw_data *ha = qpair->vha->hw;
 
 	num_qps = ha->num_qpairs + 1;
 	limit = (ha->orig_fw_iocb_count * QLA_IOCB_PCT_LIMIT) / 100;
 
-	ha->base_qpair->fwres.iocbs_total = ha->orig_fw_iocb_count;
-	ha->base_qpair->fwres.iocbs_limit = limit;
-	ha->base_qpair->fwres.iocbs_qp_limit = limit / num_qps;
-	ha->base_qpair->fwres.iocbs_used = 0;
+	qpair->fwres.iocbs_total = ha->orig_fw_iocb_count;
+	qpair->fwres.iocbs_limit = limit;
+	qpair->fwres.iocbs_qp_limit = limit / num_qps;
+
+	qpair->fwres.exch_total = ha->orig_fw_xcb_count;
+	qpair->fwres.exch_limit = (ha->orig_fw_xcb_count *
+				   QLA_IOCB_PCT_LIMIT) / 100;
+}
+
+void qla_init_iocb_limit(scsi_qla_host_t *vha)
+{
+	u8 i;
+	struct qla_hw_data *ha = vha->hw;
 
-	ha->base_qpair->fwres.exch_total = ha->orig_fw_xcb_count;
-	ha->base_qpair->fwres.exch_limit = (ha->orig_fw_xcb_count *
-					    QLA_IOCB_PCT_LIMIT) / 100;
+	__qla_adjust_iocb_limit(ha->base_qpair);
+	ha->base_qpair->fwres.iocbs_used = 0;
 	ha->base_qpair->fwres.exch_used  = 0;
 
 	for (i = 0; i < ha->max_qpairs; i++) {
 		if (ha->queue_pair_map[i])  {
-			ha->queue_pair_map[i]->fwres.iocbs_total =
-				ha->orig_fw_iocb_count;
-			ha->queue_pair_map[i]->fwres.iocbs_limit = limit;
-			ha->queue_pair_map[i]->fwres.iocbs_qp_limit =
-				limit / num_qps;
+			__qla_adjust_iocb_limit(ha->queue_pair_map[i]);
 			ha->queue_pair_map[i]->fwres.iocbs_used = 0;
-			ha->queue_pair_map[i]->fwres.exch_total = ha->orig_fw_xcb_count;
-			ha->queue_pair_map[i]->fwres.exch_limit =
-				(ha->orig_fw_xcb_count * QLA_IOCB_PCT_LIMIT) / 100;
 			ha->queue_pair_map[i]->fwres.exch_used = 0;
 		}
 	}
+
+	ha->fwres.iocb_total = ha->orig_fw_iocb_count;
+	ha->fwres.iocb_limit = (ha->orig_fw_iocb_count * QLA_IOCB_PCT_LIMIT) / 100;
+	ha->fwres.exch_total = ha->orig_fw_xcb_count;
+	ha->fwres.exch_limit = (ha->orig_fw_xcb_count * QLA_IOCB_PCT_LIMIT) / 100;
+
+	atomic_set(&ha->fwres.iocb_used, 0);
+	atomic_set(&ha->fwres.exch_used, 0);
+}
+
+void qla_adjust_iocb_limit(scsi_qla_host_t *vha)
+{
+	u8 i;
+	struct qla_hw_data *ha = vha->hw;
+
+	__qla_adjust_iocb_limit(ha->base_qpair);
+
+	for (i = 0; i < ha->max_qpairs; i++) {
+		if (ha->queue_pair_map[i])
+			__qla_adjust_iocb_limit(ha->queue_pair_map[i]);
+	}
 }
 
 /**
@@ -4779,15 +4836,16 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
 	if (ha->flags.edif_enabled)
 		mid_init_cb->init_cb.frame_payload_size = cpu_to_le16(ELS_MAX_PAYLOAD);
 
+	QLA_FW_STARTED(ha);
 	rval = qla2x00_init_firmware(vha, ha->init_cb_size);
 next_check:
 	if (rval) {
+		QLA_FW_STOPPED(ha);
 		ql_log(ql_log_fatal, vha, 0x00d2,
 		    "Init Firmware **** FAILED ****.\n");
 	} else {
 		ql_dbg(ql_dbg_init, vha, 0x00d3,
 		    "Init Firmware -- success.\n");
-		QLA_FW_STARTED(ha);
 		vha->u_ql2xexchoffld = vha->u_ql2xiniexchg = 0;
 	}
 
@@ -5529,7 +5587,6 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags)
 	INIT_WORK(&fcport->reg_work, qla_register_fcport_fn);
 	INIT_LIST_HEAD(&fcport->gnl_entry);
 	INIT_LIST_HEAD(&fcport->list);
-	INIT_LIST_HEAD(&fcport->tmf_pending);
 
 	INIT_LIST_HEAD(&fcport->sess_cmd_list);
 	spin_lock_init(&fcport->sess_cmd_lock);
@@ -5575,7 +5632,7 @@ static void qla_get_login_template(scsi_qla_host_t *vha)
 	__be32 *q;
 
 	memset(ha->init_cb, 0, ha->init_cb_size);
-	sz = min_t(int, sizeof(struct fc_els_csp), ha->init_cb_size);
+	sz = min_t(int, sizeof(struct fc_els_flogi), ha->init_cb_size);
 	rval = qla24xx_get_port_login_templ(vha, ha->init_cb_dma,
 					    ha->init_cb, sz);
 	if (rval != QLA_SUCCESS) {
@@ -6120,6 +6177,8 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport)
 void
 qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 {
+	unsigned long flags;
+
 	if (IS_SW_RESV_ADDR(fcport->d_id))
 		return;
 
@@ -6129,7 +6188,11 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 	qla2x00_set_fcport_disc_state(fcport, DSC_UPD_FCPORT);
 	fcport->login_retry = vha->hw->login_retry_count;
 	fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
+
+	spin_lock_irqsave(&vha->work_lock, flags);
 	fcport->deleted = 0;
+	spin_unlock_irqrestore(&vha->work_lock, flags);
+
 	if (vha->hw->current_topology == ISP_CFG_NL)
 		fcport->logout_on_delete = 0;
 	else
@@ -7419,14 +7482,15 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 	}
 
 	/* purge MBox commands */
-	if (atomic_read(&ha->num_pend_mbx_stage3)) {
+	spin_lock_irqsave(&ha->hardware_lock, flags);
+	if (test_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags)) {
 		clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
 		complete(&ha->mbx_intr_comp);
 	}
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	i = 0;
-	while (atomic_read(&ha->num_pend_mbx_stage3) ||
-	    atomic_read(&ha->num_pend_mbx_stage2) ||
+	while (atomic_read(&ha->num_pend_mbx_stage2) ||
 	    atomic_read(&ha->num_pend_mbx_stage1)) {
 		msleep(20);
 		i++;
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index a034699e58ae..a7b5d1114682 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -386,6 +386,7 @@ enum {
 	RESOURCE_IOCB = BIT_0,
 	RESOURCE_EXCH = BIT_1,  /* exchange */
 	RESOURCE_FORCE = BIT_2,
+	RESOURCE_HA = BIT_3,
 };
 
 static inline int
@@ -393,7 +394,7 @@ qla_get_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores)
 {
 	u16 iocbs_used, i;
 	u16 exch_used;
-	struct qla_hw_data *ha = qp->vha->hw;
+	struct qla_hw_data *ha = qp->hw;
 
 	if (!ql2xenforce_iocb_limit) {
 		iores->res_type = RESOURCE_NONE;
@@ -428,15 +429,69 @@ qla_get_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores)
 			return -ENOSPC;
 		}
 	}
+
+	if (ql2xenforce_iocb_limit == 2) {
+		if ((iores->iocb_cnt + atomic_read(&ha->fwres.iocb_used)) >=
+		    ha->fwres.iocb_limit) {
+			iores->res_type = RESOURCE_NONE;
+			return -ENOSPC;
+		}
+
+		if (iores->res_type & RESOURCE_EXCH) {
+			if ((iores->exch_cnt + atomic_read(&ha->fwres.exch_used)) >=
+			    ha->fwres.exch_limit) {
+				iores->res_type = RESOURCE_NONE;
+				return -ENOSPC;
+			}
+		}
+	}
+
 force:
 	qp->fwres.iocbs_used += iores->iocb_cnt;
 	qp->fwres.exch_used += iores->exch_cnt;
+	if (ql2xenforce_iocb_limit == 2) {
+		atomic_add(iores->iocb_cnt, &ha->fwres.iocb_used);
+		atomic_add(iores->exch_cnt, &ha->fwres.exch_used);
+		iores->res_type |= RESOURCE_HA;
+	}
 	return 0;
 }
 
+/*
+ * decrement to zero.  This routine will not decrement below zero
+ * @v:  pointer of type atomic_t
+ * @amount: amount to decrement from v
+ */
+static void qla_atomic_dtz(atomic_t *v, int amount)
+{
+	int c, old, dec;
+
+	c = atomic_read(v);
+	for (;;) {
+		dec = c - amount;
+		if (unlikely(dec < 0))
+			dec = 0;
+
+		old = atomic_cmpxchg((v), c, dec);
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+}
+
 static inline void
 qla_put_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores)
 {
+	struct qla_hw_data *ha = qp->hw;
+
+	if (iores->res_type & RESOURCE_HA) {
+		if (iores->res_type & RESOURCE_IOCB)
+			qla_atomic_dtz(&ha->fwres.iocb_used, iores->iocb_cnt);
+
+		if (iores->res_type & RESOURCE_EXCH)
+			qla_atomic_dtz(&ha->fwres.exch_used, iores->exch_cnt);
+	}
+
 	if (iores->res_type & RESOURCE_IOCB) {
 		if (qp->fwres.iocbs_used >= iores->iocb_cnt) {
 			qp->fwres.iocbs_used -= iores->iocb_cnt;
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index c9a686f06d29..9e524d52dc86 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -3887,6 +3887,7 @@ 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_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 08d43f43995e..80c2dcf567b0 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1121,8 +1121,12 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
 	unsigned long	flags;
 	fc_port_t	*fcport = NULL;
 
-	if (!vha->hw->flags.fw_started)
+	if (!vha->hw->flags.fw_started) {
+		ql_log(ql_log_warn, vha, 0x50ff,
+		    "Dropping AEN - %04x %04x %04x %04x.\n",
+		    mb[0], mb[1], mb[2], mb[3]);
 		return;
+	}
 
 	/* Setup to process RIO completion. */
 	handle_cnt = 0;
@@ -2513,7 +2517,6 @@ qla24xx_tm_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, void *tsk)
 	case CS_PORT_BUSY:
 	case CS_INCOMPLETE:
 	case CS_PORT_UNAVAILABLE:
-	case CS_TIMEOUT:
 	case CS_RESET:
 		if (atomic_read(&fcport->state) == FCS_ONLINE) {
 			ql_dbg(ql_dbg_disc, fcport->vha, 0x3021,
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 5bcb8da4360f..511f31611aed 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -273,7 +273,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 		wait_time = jiffies;
-		atomic_inc(&ha->num_pend_mbx_stage3);
 		if (!wait_for_completion_timeout(&ha->mbx_intr_comp,
 		    mcp->tov * HZ)) {
 			ql_dbg(ql_dbg_mbx, vha, 0x117a,
@@ -290,7 +289,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 				spin_unlock_irqrestore(&ha->hardware_lock,
 				    flags);
 				atomic_dec(&ha->num_pend_mbx_stage2);
-				atomic_dec(&ha->num_pend_mbx_stage3);
 				rval = QLA_ABORTED;
 				goto premature_exit;
 			}
@@ -302,11 +300,9 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 			ha->flags.mbox_busy = 0;
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
 			atomic_dec(&ha->num_pend_mbx_stage2);
-			atomic_dec(&ha->num_pend_mbx_stage3);
 			rval = QLA_ABORTED;
 			goto premature_exit;
 		}
-		atomic_dec(&ha->num_pend_mbx_stage3);
 
 		if (time_after(jiffies, wait_time + 5 * HZ))
 			ql_log(ql_log_warn, vha, 0x1015, "cmd=0x%x, waited %d msecs\n",
@@ -2207,6 +2203,9 @@ qla2x00_get_firmware_state(scsi_qla_host_t *vha, uint16_t *states)
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1054,
 	    "Entered %s.\n", __func__);
 
+	if (!ha->flags.fw_started)
+		return QLA_FUNCTION_FAILED;
+
 	mcp->mb[0] = MBC_GET_FIRMWARE_STATE;
 	mcp->out_mb = MBX_0;
 	if (IS_FWI2_CAPABLE(vha->hw))
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 53a54e8a4d97..f535f478e37c 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -127,6 +127,7 @@ static int qla_nvme_alloc_queue(struct nvme_fc_local_port *lport,
 			       "Failed to allocate qpair\n");
 			return -EINVAL;
 		}
+		qla_adjust_iocb_limit(vha);
 	}
 	*handle = qpair;
 
@@ -652,7 +653,7 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport,
 
 	rval = qla2x00_start_nvme_mq(sp);
 	if (rval != QLA_SUCCESS) {
-		ql_log(ql_log_warn, vha, 0x212d,
+		ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x212d,
 		    "qla2x00_start_nvme_mq failed = %d\n", rval);
 		sp->priv = NULL;
 		priv->sp = NULL;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 30325fd4c120..a40af9b832ab 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -40,10 +40,11 @@ module_param(ql2xfulldump_on_mpifail, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(ql2xfulldump_on_mpifail,
 		 "Set this to take full dump on MPI hang.");
 
-int ql2xenforce_iocb_limit = 1;
+int ql2xenforce_iocb_limit = 2;
 module_param(ql2xenforce_iocb_limit, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(ql2xenforce_iocb_limit,
-		 "Enforce IOCB throttling, to avoid FW congestion. (default: 1)");
+		 "Enforce IOCB throttling, to avoid FW congestion. (default: 2) "
+		 "1: track usage per queue, 2: track usage per adapter");
 
 /*
  * CT6 CTX allocation cache
@@ -1470,8 +1471,9 @@ 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;
@@ -1537,8 +1539,8 @@ 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;
@@ -2970,9 +2972,10 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	ha->max_exchg = FW_MAX_EXCHANGES_CNT;
 	atomic_set(&ha->num_pend_mbx_stage1, 0);
 	atomic_set(&ha->num_pend_mbx_stage2, 0);
-	atomic_set(&ha->num_pend_mbx_stage3, 0);
 	atomic_set(&ha->zio_threshold, DEFAULT_ZIO_THRESHOLD);
 	ha->last_zio_threshold = DEFAULT_ZIO_THRESHOLD;
+	INIT_LIST_HEAD(&ha->tmf_pending);
+	INIT_LIST_HEAD(&ha->tmf_active);
 
 	/* Assign ISP specific operations. */
 	if (IS_QLA2100(ha)) {
@@ -3249,6 +3252,13 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	host->max_id = ha->max_fibre_devices;
 	host->cmd_per_lun = 3;
 	host->unique_id = host->host_no;
+
+	if (ql2xenabledif && ql2xenabledif != 2) {
+		ql_log(ql_log_warn, base_vha, 0x302d,
+		       "Invalid value for ql2xenabledif, resetting it to default (2)\n");
+		ql2xenabledif = 2;
+	}
+
 	if (IS_T10_PI_CAPABLE(ha) && ql2xenabledif)
 		host->max_cmd_len = 32;
 	else
@@ -3482,8 +3492,6 @@ skip_dpc:
 			base_vha->flags.difdix_supported = 1;
 			ql_dbg(ql_dbg_init, base_vha, 0x00f1,
 			    "Registering for DIF/DIX type 1 and 3 protection.\n");
-			if (ql2xenabledif == 1)
-				prot = SHOST_DIX_TYPE0_PROTECTION;
 			if (ql2xprotmask)
 				scsi_host_set_prot(host, ql2xprotmask);
 			else
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 4b4ca2a9524d..2ce041fdec75 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1089,10 +1089,6 @@ void qlt_free_session_done(struct work_struct *work)
 			(struct imm_ntfy_from_isp *)sess->iocb, SRB_NACK_LOGO);
 	}
 
-	spin_lock_irqsave(&vha->work_lock, flags);
-	sess->flags &= ~FCF_ASYNC_SENT;
-	spin_unlock_irqrestore(&vha->work_lock, flags);
-
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
 	if (sess->se_sess) {
 		sess->se_sess = NULL;
@@ -1102,7 +1098,6 @@ void qlt_free_session_done(struct work_struct *work)
 
 	qla2x00_set_fcport_disc_state(sess, DSC_DELETED);
 	sess->fw_login_state = DSC_LS_PORT_UNAVAIL;
-	sess->deleted = QLA_SESS_DELETED;
 
 	if (sess->login_succ && !IS_SW_RESV_ADDR(sess->d_id)) {
 		vha->fcport_count--;
@@ -1154,10 +1149,15 @@ void qlt_free_session_done(struct work_struct *work)
 
 	sess->explicit_logout = 0;
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
-	sess->free_pending = 0;
 
 	qla2x00_dfs_remove_rport(vha, sess);
 
+	spin_lock_irqsave(&vha->work_lock, flags);
+	sess->flags &= ~FCF_ASYNC_SENT;
+	sess->deleted = QLA_SESS_DELETED;
+	sess->free_pending = 0;
+	spin_unlock_irqrestore(&vha->work_lock, flags);
+
 	ql_dbg(ql_dbg_disc, vha, 0xf001,
 	    "Unregistration of sess %p %8phC finished fcp_cnt %d\n",
 		sess, sess->port_name, vha->fcport_count);
@@ -1206,12 +1206,12 @@ void qlt_unreg_sess(struct fc_port *sess)
 	 * management from being sent.
 	 */
 	sess->flags |= FCF_ASYNC_SENT;
+	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 	spin_unlock_irqrestore(&sess->vha->work_lock, flags);
 
 	if (sess->se_sess)
 		vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess);
 
-	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 	qla2x00_set_fcport_disc_state(sess, DSC_DELETE_PEND);
 	sess->last_rscn_gen = sess->rscn_gen;
 	sess->last_login_gen = sess->login_gen;