19 files changed, 322 insertions, 223 deletions

diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index da6e97d8dc3b..6bb8917b99a1 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -1208,9 +1208,15 @@ static void fc_rport_prli_resp(struct fc_seq *sp, struct fc_frame *fp,
 		rjt = fc_frame_payload_get(fp, sizeof(*rjt));
 		if (!rjt)
 			FC_RPORT_DBG(rdata, "PRLI bad response\n");
-		else
+		else {
 			FC_RPORT_DBG(rdata, "PRLI ELS rejected, reason %x expl %x\n",
 				     rjt->er_reason, rjt->er_explan);
+			if (rjt->er_reason == ELS_RJT_UNAB &&
+			    rjt->er_explan == ELS_EXPL_PLOGI_REQD) {
+				fc_rport_enter_plogi(rdata);
+				goto out;
+			}
+		}
 		fc_rport_error_retry(rdata, FC_EX_ELS_RJT);
 	}
 
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 04d73e2be373..828873d5b3e8 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -482,7 +482,7 @@ struct lpfc_vport {
 	struct dentry *debug_nvmestat;
 	struct dentry *debug_scsistat;
 	struct dentry *debug_nvmektime;
-	struct dentry *debug_cpucheck;
+	struct dentry *debug_hdwqstat;
 	struct dentry *vport_debugfs_root;
 	struct lpfc_debugfs_trc *disc_trc;
 	atomic_t disc_trc_cnt;
@@ -749,6 +749,7 @@ struct lpfc_hba {
 					 * capability
 					 */
 #define HBA_FLOGI_ISSUED	0x100000 /* FLOGI was issued */
+#define HBA_DEFER_FLOGI		0x800000 /* Defer FLOGI till read_sparm cmpl */
 
 	uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/
 	struct lpfc_dmabuf slim2p;
@@ -1175,12 +1176,11 @@ struct lpfc_hba {
 	uint16_t sfp_warning;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	uint16_t cpucheck_on;
+	uint16_t hdwqstat_on;
 #define LPFC_CHECK_OFF		0
 #define LPFC_CHECK_NVME_IO	1
-#define LPFC_CHECK_NVMET_RCV	2
-#define LPFC_CHECK_NVMET_IO	4
-#define LPFC_CHECK_SCSI_IO	8
+#define LPFC_CHECK_NVMET_IO	2
+#define LPFC_CHECK_SCSI_IO	4
 	uint16_t ktime_on;
 	uint64_t ktime_data_samples;
 	uint64_t ktime_status_samples;
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 819335b16c2e..1b8be1006cbe 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -1603,42 +1603,50 @@ out:
 }
 
 /**
- * lpfc_debugfs_cpucheck_data - Dump target node list to a buffer
+ * lpfc_debugfs_hdwqstat_data - Dump I/O stats to a buffer
  * @vport: The vport to gather target node info from.
  * @buf: The buffer to dump log into.
  * @size: The maximum amount of data to process.
  *
  * Description:
- * This routine dumps the NVME statistics associated with @vport
+ * This routine dumps the NVME + SCSI statistics associated with @vport
  *
  * Return Value:
  * This routine returns the amount of bytes that were dumped into @buf and will
  * not exceed @size.
  **/
 static int
-lpfc_debugfs_cpucheck_data(struct lpfc_vport *vport, char *buf, int size)
+lpfc_debugfs_hdwqstat_data(struct lpfc_vport *vport, char *buf, int size)
 {
 	struct lpfc_hba   *phba = vport->phba;
 	struct lpfc_sli4_hdw_queue *qp;
-	int i, j, max_cnt;
-	int len = 0;
+	struct lpfc_hdwq_stat *c_stat;
+	int i, j, len;
 	uint32_t tot_xmt;
 	uint32_t tot_rcv;
 	uint32_t tot_cmpl;
+	char tmp[LPFC_MAX_SCSI_INFO_TMP_LEN] = {0};
 
-	len += scnprintf(buf + len, PAGE_SIZE - len,
-			"CPUcheck %s ",
-			(phba->cpucheck_on & LPFC_CHECK_NVME_IO ?
-				"Enabled" : "Disabled"));
-	if (phba->nvmet_support) {
-		len += scnprintf(buf + len, PAGE_SIZE - len,
-				"%s\n",
-				(phba->cpucheck_on & LPFC_CHECK_NVMET_RCV ?
-					"Rcv Enabled\n" : "Rcv Disabled\n"));
-	} else {
-		len += scnprintf(buf + len, PAGE_SIZE - len, "\n");
-	}
-	max_cnt = size - LPFC_DEBUG_OUT_LINE_SZ;
+	scnprintf(tmp, sizeof(tmp), "HDWQ Stats:\n\n");
+	if (strlcat(buf, tmp, size) >= size)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp), "(NVME Accounting: %s) ",
+		  (phba->hdwqstat_on &
+		  (LPFC_CHECK_NVME_IO | LPFC_CHECK_NVMET_IO) ?
+		  "Enabled" : "Disabled"));
+	if (strlcat(buf, tmp, size) >= size)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp), "(SCSI Accounting: %s) ",
+		  (phba->hdwqstat_on & LPFC_CHECK_SCSI_IO ?
+		  "Enabled" : "Disabled"));
+	if (strlcat(buf, tmp, size) >= size)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp), "\n\n");
+	if (strlcat(buf, tmp, size) >= size)
+		goto buffer_done;
 
 	for (i = 0; i < phba->cfg_hdw_queue; i++) {
 		qp = &phba->sli4_hba.hdwq[i];
@@ -1646,46 +1654,76 @@ lpfc_debugfs_cpucheck_data(struct lpfc_vport *vport, char *buf, int size)
 		tot_rcv = 0;
 		tot_xmt = 0;
 		tot_cmpl = 0;
-		for (j = 0; j < LPFC_CHECK_CPU_CNT; j++) {
-			tot_xmt += qp->cpucheck_xmt_io[j];
-			tot_cmpl += qp->cpucheck_cmpl_io[j];
-			if (phba->nvmet_support)
-				tot_rcv += qp->cpucheck_rcv_io[j];
-		}
 
-		/* Only display Hardware Qs with something */
-		if (!tot_xmt && !tot_cmpl && !tot_rcv)
-			continue;
+		for_each_present_cpu(j) {
+			c_stat = per_cpu_ptr(phba->sli4_hba.c_stat, j);
+
+			/* Only display for this HDWQ */
+			if (i != c_stat->hdwq_no)
+				continue;
 
-		len += scnprintf(buf + len, PAGE_SIZE - len,
-				"HDWQ %03d: ", i);
-		for (j = 0; j < LPFC_CHECK_CPU_CNT; j++) {
 			/* Only display non-zero counters */
-			if (!qp->cpucheck_xmt_io[j] &&
-			    !qp->cpucheck_cmpl_io[j] &&
-			    !qp->cpucheck_rcv_io[j])
+			if (!c_stat->xmt_io && !c_stat->cmpl_io &&
+			    !c_stat->rcv_io)
 				continue;
+
+			if (!tot_xmt && !tot_cmpl && !tot_rcv) {
+				/* Print HDWQ string only the first time */
+				scnprintf(tmp, sizeof(tmp), "[HDWQ %d]:\t", i);
+				if (strlcat(buf, tmp, size) >= size)
+					goto buffer_done;
+			}
+
+			tot_xmt += c_stat->xmt_io;
+			tot_cmpl += c_stat->cmpl_io;
+			if (phba->nvmet_support)
+				tot_rcv += c_stat->rcv_io;
+
+			scnprintf(tmp, sizeof(tmp), "| [CPU %d]: ", j);
+			if (strlcat(buf, tmp, size) >= size)
+				goto buffer_done;
+
 			if (phba->nvmet_support) {
-				len += scnprintf(buf + len, PAGE_SIZE - len,
-						"CPU %03d: %x/%x/%x ", j,
-						qp->cpucheck_rcv_io[j],
-						qp->cpucheck_xmt_io[j],
-						qp->cpucheck_cmpl_io[j]);
+				scnprintf(tmp, sizeof(tmp),
+					  "XMT 0x%x CMPL 0x%x RCV 0x%x |",
+					  c_stat->xmt_io, c_stat->cmpl_io,
+					  c_stat->rcv_io);
+				if (strlcat(buf, tmp, size) >= size)
+					goto buffer_done;
 			} else {
-				len += scnprintf(buf + len, PAGE_SIZE - len,
-						"CPU %03d: %x/%x ", j,
-						qp->cpucheck_xmt_io[j],
-						qp->cpucheck_cmpl_io[j]);
+				scnprintf(tmp, sizeof(tmp),
+					  "XMT 0x%x CMPL 0x%x |",
+					  c_stat->xmt_io, c_stat->cmpl_io);
+				if (strlcat(buf, tmp, size) >= size)
+					goto buffer_done;
 			}
 		}
-		len += scnprintf(buf + len, PAGE_SIZE - len,
-				"Total: %x\n", tot_xmt);
-		if (len >= max_cnt) {
-			len += scnprintf(buf + len, PAGE_SIZE - len,
-					"Truncated ...\n");
-			return len;
+
+		/* Check if nothing to display */
+		if (!tot_xmt && !tot_cmpl && !tot_rcv)
+			continue;
+
+		scnprintf(tmp, sizeof(tmp), "\t->\t[HDWQ Total: ");
+		if (strlcat(buf, tmp, size) >= size)
+			goto buffer_done;
+
+		if (phba->nvmet_support) {
+			scnprintf(tmp, sizeof(tmp),
+				  "XMT 0x%x CMPL 0x%x RCV 0x%x]\n\n",
+				  tot_xmt, tot_cmpl, tot_rcv);
+			if (strlcat(buf, tmp, size) >= size)
+				goto buffer_done;
+		} else {
+			scnprintf(tmp, sizeof(tmp),
+				  "XMT 0x%x CMPL 0x%x]\n\n",
+				  tot_xmt, tot_cmpl);
+			if (strlcat(buf, tmp, size) >= size)
+				goto buffer_done;
 		}
 	}
+
+buffer_done:
+	len = strnlen(buf, size);
 	return len;
 }
 
@@ -2921,7 +2959,7 @@ lpfc_debugfs_nvmeio_trc_write(struct file *file, const char __user *buf,
 }
 
 static int
-lpfc_debugfs_cpucheck_open(struct inode *inode, struct file *file)
+lpfc_debugfs_hdwqstat_open(struct inode *inode, struct file *file)
 {
 	struct lpfc_vport *vport = inode->i_private;
 	struct lpfc_debug *debug;
@@ -2932,14 +2970,14 @@ lpfc_debugfs_cpucheck_open(struct inode *inode, struct file *file)
 		goto out;
 
 	 /* Round to page boundary */
-	debug->buffer = kmalloc(LPFC_CPUCHECK_SIZE, GFP_KERNEL);
+	debug->buffer = kcalloc(1, LPFC_SCSISTAT_SIZE, GFP_KERNEL);
 	if (!debug->buffer) {
 		kfree(debug);
 		goto out;
 	}
 
-	debug->len = lpfc_debugfs_cpucheck_data(vport, debug->buffer,
-		LPFC_CPUCHECK_SIZE);
+	debug->len = lpfc_debugfs_hdwqstat_data(vport, debug->buffer,
+						LPFC_SCSISTAT_SIZE);
 
 	debug->i_private = inode->i_private;
 	file->private_data = debug;
@@ -2950,16 +2988,16 @@ out:
 }
 
 static ssize_t
-lpfc_debugfs_cpucheck_write(struct file *file, const char __user *buf,
+lpfc_debugfs_hdwqstat_write(struct file *file, const char __user *buf,
 			    size_t nbytes, loff_t *ppos)
 {
 	struct lpfc_debug *debug = file->private_data;
 	struct lpfc_vport *vport = (struct lpfc_vport *)debug->i_private;
 	struct lpfc_hba   *phba = vport->phba;
-	struct lpfc_sli4_hdw_queue *qp;
+	struct lpfc_hdwq_stat *c_stat;
 	char mybuf[64];
 	char *pbuf;
-	int i, j;
+	int i;
 
 	if (nbytes > 64)
 		nbytes = 64;
@@ -2972,41 +3010,39 @@ lpfc_debugfs_cpucheck_write(struct file *file, const char __user *buf,
 
 	if ((strncmp(pbuf, "on", sizeof("on") - 1) == 0)) {
 		if (phba->nvmet_support)
-			phba->cpucheck_on |= LPFC_CHECK_NVMET_IO;
+			phba->hdwqstat_on |= LPFC_CHECK_NVMET_IO;
 		else
-			phba->cpucheck_on |= (LPFC_CHECK_NVME_IO |
+			phba->hdwqstat_on |= (LPFC_CHECK_NVME_IO |
 				LPFC_CHECK_SCSI_IO);
 		return strlen(pbuf);
 	} else if ((strncmp(pbuf, "nvme_on", sizeof("nvme_on") - 1) == 0)) {
 		if (phba->nvmet_support)
-			phba->cpucheck_on |= LPFC_CHECK_NVMET_IO;
+			phba->hdwqstat_on |= LPFC_CHECK_NVMET_IO;
 		else
-			phba->cpucheck_on |= LPFC_CHECK_NVME_IO;
+			phba->hdwqstat_on |= LPFC_CHECK_NVME_IO;
 		return strlen(pbuf);
 	} else if ((strncmp(pbuf, "scsi_on", sizeof("scsi_on") - 1) == 0)) {
-		phba->cpucheck_on |= LPFC_CHECK_SCSI_IO;
+		if (!phba->nvmet_support)
+			phba->hdwqstat_on |= LPFC_CHECK_SCSI_IO;
 		return strlen(pbuf);
-	} else if ((strncmp(pbuf, "rcv",
-		   sizeof("rcv") - 1) == 0)) {
-		if (phba->nvmet_support)
-			phba->cpucheck_on |= LPFC_CHECK_NVMET_RCV;
-		else
-			return -EINVAL;
+	} else if ((strncmp(pbuf, "nvme_off", sizeof("nvme_off") - 1) == 0)) {
+		phba->hdwqstat_on &= ~(LPFC_CHECK_NVME_IO |
+				       LPFC_CHECK_NVMET_IO);
+		return strlen(pbuf);
+	} else if ((strncmp(pbuf, "scsi_off", sizeof("scsi_off") - 1) == 0)) {
+		phba->hdwqstat_on &= ~LPFC_CHECK_SCSI_IO;
 		return strlen(pbuf);
 	} else if ((strncmp(pbuf, "off",
 		   sizeof("off") - 1) == 0)) {
-		phba->cpucheck_on = LPFC_CHECK_OFF;
+		phba->hdwqstat_on = LPFC_CHECK_OFF;
 		return strlen(pbuf);
 	} else if ((strncmp(pbuf, "zero",
 		   sizeof("zero") - 1) == 0)) {
-		for (i = 0; i < phba->cfg_hdw_queue; i++) {
-			qp = &phba->sli4_hba.hdwq[i];
-
-			for (j = 0; j < LPFC_CHECK_CPU_CNT; j++) {
-				qp->cpucheck_rcv_io[j] = 0;
-				qp->cpucheck_xmt_io[j] = 0;
-				qp->cpucheck_cmpl_io[j] = 0;
-			}
+		for_each_present_cpu(i) {
+			c_stat = per_cpu_ptr(phba->sli4_hba.c_stat, i);
+			c_stat->xmt_io = 0;
+			c_stat->cmpl_io = 0;
+			c_stat->rcv_io = 0;
 		}
 		return strlen(pbuf);
 	}
@@ -5451,13 +5487,13 @@ static const struct file_operations lpfc_debugfs_op_nvmeio_trc = {
 	.release =      lpfc_debugfs_release,
 };
 
-#undef lpfc_debugfs_op_cpucheck
-static const struct file_operations lpfc_debugfs_op_cpucheck = {
+#undef lpfc_debugfs_op_hdwqstat
+static const struct file_operations lpfc_debugfs_op_hdwqstat = {
 	.owner =        THIS_MODULE,
-	.open =         lpfc_debugfs_cpucheck_open,
+	.open =         lpfc_debugfs_hdwqstat_open,
 	.llseek =       lpfc_debugfs_lseek,
 	.read =         lpfc_debugfs_read,
-	.write =	lpfc_debugfs_cpucheck_write,
+	.write =	lpfc_debugfs_hdwqstat_write,
 	.release =      lpfc_debugfs_release,
 };
 
@@ -6081,11 +6117,11 @@ nvmeio_off:
 				    vport->vport_debugfs_root,
 				    vport, &lpfc_debugfs_op_nvmektime);
 
-	snprintf(name, sizeof(name), "cpucheck");
-	vport->debug_cpucheck =
+	snprintf(name, sizeof(name), "hdwqstat");
+	vport->debug_hdwqstat =
 		debugfs_create_file(name, 0644,
 				    vport->vport_debugfs_root,
-				    vport, &lpfc_debugfs_op_cpucheck);
+				    vport, &lpfc_debugfs_op_hdwqstat);
 
 	/*
 	 * The following section is for additional directories/files for the
@@ -6219,8 +6255,8 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport)
 	debugfs_remove(vport->debug_nvmektime); /* nvmektime */
 	vport->debug_nvmektime = NULL;
 
-	debugfs_remove(vport->debug_cpucheck); /* cpucheck */
-	vport->debug_cpucheck = NULL;
+	debugfs_remove(vport->debug_hdwqstat); /* hdwqstat */
+	vport->debug_hdwqstat = NULL;
 
 	if (vport->vport_debugfs_root) {
 		debugfs_remove(vport->vport_debugfs_root); /* vportX */
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h
index 20f2537af511..6643b9bfd4f3 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.h
+++ b/drivers/scsi/lpfc/lpfc_debugfs.h
@@ -47,7 +47,6 @@
 /* nvmestat output buffer size */
 #define LPFC_NVMESTAT_SIZE 8192
 #define LPFC_NVMEKTIME_SIZE 8192
-#define LPFC_CPUCHECK_SIZE 8192
 #define LPFC_NVMEIO_TRC_SIZE 8192
 
 /* scsistat output buffer size */
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index dcc8999c6a68..6a2bdae0e52a 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -1163,13 +1163,16 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	}
 
 	/* Start discovery by sending a FLOGI. port_state is identically
-	 * LPFC_FLOGI while waiting for FLOGI cmpl
+	 * LPFC_FLOGI while waiting for FLOGI cmpl. Check if sending
+	 * the FLOGI is being deferred till after MBX_READ_SPARAM completes.
 	 */
-	if (vport->port_state != LPFC_FLOGI)
-		lpfc_initial_flogi(vport);
-	else if (vport->fc_flag & FC_PT2PT)
-		lpfc_disc_start(vport);
-
+	if (vport->port_state != LPFC_FLOGI) {
+		if (!(phba->hba_flag & HBA_DEFER_FLOGI))
+			lpfc_initial_flogi(vport);
+	} else {
+		if (vport->fc_flag & FC_PT2PT)
+			lpfc_disc_start(vport);
+	}
 	return;
 
 out:
@@ -3094,6 +3097,14 @@ lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	lpfc_mbuf_free(phba, mp->virt, mp->phys);
 	kfree(mp);
 	mempool_free(pmb, phba->mbox_mem_pool);
+
+	/* Check if sending the FLOGI is being deferred to after we get
+	 * up to date CSPs from MBX_READ_SPARAM.
+	 */
+	if (phba->hba_flag & HBA_DEFER_FLOGI) {
+		lpfc_initial_flogi(vport);
+		phba->hba_flag &= ~HBA_DEFER_FLOGI;
+	}
 	return;
 
 out:
@@ -3224,6 +3235,23 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
 	}
 
 	lpfc_linkup(phba);
+	sparam_mbox = NULL;
+
+	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
+		cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+		if (!cfglink_mbox)
+			goto out;
+		vport->port_state = LPFC_LOCAL_CFG_LINK;
+		lpfc_config_link(phba, cfglink_mbox);
+		cfglink_mbox->vport = vport;
+		cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link;
+		rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT);
+		if (rc == MBX_NOT_FINISHED) {
+			mempool_free(cfglink_mbox, phba->mbox_mem_pool);
+			goto out;
+		}
+	}
+
 	sparam_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!sparam_mbox)
 		goto out;
@@ -3244,20 +3272,7 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
 		goto out;
 	}
 
-	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
-		cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-		if (!cfglink_mbox)
-			goto out;
-		vport->port_state = LPFC_LOCAL_CFG_LINK;
-		lpfc_config_link(phba, cfglink_mbox);
-		cfglink_mbox->vport = vport;
-		cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link;
-		rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT);
-		if (rc == MBX_NOT_FINISHED) {
-			mempool_free(cfglink_mbox, phba->mbox_mem_pool);
-			goto out;
-		}
-	} else {
+	if (phba->hba_flag & HBA_FCOE_MODE) {
 		vport->port_state = LPFC_VPORT_UNKNOWN;
 		/*
 		 * Add the driver's default FCF record at FCF index 0 now. This
@@ -3314,6 +3329,10 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
 		}
 		/* Reset FCF roundrobin bmask for new discovery */
 		lpfc_sli4_clear_fcf_rr_bmask(phba);
+	} else {
+		if (phba->bbcredit_support && phba->cfg_enable_bbcr &&
+		    !(phba->link_flag & LS_LOOPBACK_MODE))
+			phba->hba_flag |= HBA_DEFER_FLOGI;
 	}
 
 	/* Prepare for LINK up registrations */
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 5a605773dd0a..48fde2b1ebba 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -6935,6 +6935,17 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		rc = -ENOMEM;
 		goto out_free_hba_cpu_map;
 	}
+
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	phba->sli4_hba.c_stat = alloc_percpu(struct lpfc_hdwq_stat);
+	if (!phba->sli4_hba.c_stat) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3332 Failed allocating per cpu hdwq stats\n");
+		rc = -ENOMEM;
+		goto out_free_hba_eq_info;
+	}
+#endif
+
 	/*
 	 * Enable sr-iov virtual functions if supported and configured
 	 * through the module parameter.
@@ -6954,6 +6965,10 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 
 	return 0;
 
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+out_free_hba_eq_info:
+	free_percpu(phba->sli4_hba.eq_info);
+#endif
 out_free_hba_cpu_map:
 	kfree(phba->sli4_hba.cpu_map);
 out_free_hba_eq_hdl:
@@ -6992,6 +7007,9 @@ lpfc_sli4_driver_resource_unset(struct lpfc_hba *phba)
 	struct lpfc_fcf_conn_entry *conn_entry, *next_conn_entry;
 
 	free_percpu(phba->sli4_hba.eq_info);
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	free_percpu(phba->sli4_hba.c_stat);
+#endif
 
 	/* Free memory allocated for msi-x interrupt vector to CPU mapping */
 	kfree(phba->sli4_hba.cpu_map);
@@ -10831,6 +10849,9 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors)
 #ifdef CONFIG_X86
 	struct cpuinfo_x86 *cpuinfo;
 #endif
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	struct lpfc_hdwq_stat *c_stat;
+#endif
 
 	max_phys_id = 0;
 	min_phys_id = LPFC_VECTOR_MAP_EMPTY;
@@ -11082,10 +11103,17 @@ found_any:
 	idx = 0;
 	for_each_possible_cpu(cpu) {
 		cpup = &phba->sli4_hba.cpu_map[cpu];
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+		c_stat = per_cpu_ptr(phba->sli4_hba.c_stat, cpu);
+		c_stat->hdwq_no = cpup->hdwq;
+#endif
 		if (cpup->hdwq != LPFC_VECTOR_MAP_EMPTY)
 			continue;
 
 		cpup->hdwq = idx++ % phba->cfg_hdw_queue;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+		c_stat->hdwq_no = cpup->hdwq;
+#endif
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"3340 Set Affinity: not present "
 				"CPU %d hdwq %d\n",
@@ -11175,11 +11203,9 @@ static void lpfc_cpuhp_add(struct lpfc_hba *phba)
 
 	rcu_read_lock();
 
-	if (!list_empty(&phba->poll_list)) {
-		timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0);
+	if (!list_empty(&phba->poll_list))
 		mod_timer(&phba->cpuhp_poll_timer,
 			  jiffies + msecs_to_jiffies(LPFC_POLL_HB));
-	}
 
 	rcu_read_unlock();
 
@@ -13145,6 +13171,7 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	lpfc_sli4_ras_setup(phba);
 
 	INIT_LIST_HEAD(&phba->poll_list);
+	timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0);
 	cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state, &phba->cpuhp);
 
 	return 0;
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index f6c8963c915d..8403d7ceafe4 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -382,13 +382,15 @@ lpfc_nvme_remoteport_delete(struct nvme_fc_remote_port *remoteport)
 	if (ndlp->upcall_flags & NLP_WAIT_FOR_UNREG) {
 		ndlp->nrport = NULL;
 		ndlp->upcall_flags &= ~NLP_WAIT_FOR_UNREG;
-	}
-	spin_unlock_irq(&vport->phba->hbalock);
+		spin_unlock_irq(&vport->phba->hbalock);
 
-	/* Remove original register reference. The host transport
-	 * won't reference this rport/remoteport any further.
-	 */
-	lpfc_nlp_put(ndlp);
+		/* Remove original register reference. The host transport
+		 * won't reference this rport/remoteport any further.
+		 */
+		lpfc_nlp_put(ndlp);
+	} else {
+		spin_unlock_irq(&vport->phba->hbalock);
+	}
 
  rport_err:
 	return;
@@ -1010,6 +1012,9 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 	uint32_t code, status, idx;
 	uint16_t cid, sqhd, data;
 	uint32_t *ptr;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	int cpu;
+#endif
 
 	/* Sanity check on return of outstanding command */
 	if (!lpfc_ncmd) {
@@ -1182,19 +1187,15 @@ out_err:
 		phba->ktime_last_cmd = lpfc_ncmd->ts_data_nvme;
 		lpfc_nvme_ktime(phba, lpfc_ncmd);
 	}
-	if (unlikely(phba->cpucheck_on & LPFC_CHECK_NVME_IO)) {
-		uint32_t cpu;
-		idx = lpfc_ncmd->cur_iocbq.hba_wqidx;
+	if (unlikely(phba->hdwqstat_on & LPFC_CHECK_NVME_IO)) {
 		cpu = raw_smp_processor_id();
-		if (cpu < LPFC_CHECK_CPU_CNT) {
-			if (lpfc_ncmd->cpu != cpu)
-				lpfc_printf_vlog(vport,
-						 KERN_INFO, LOG_NVME_IOERR,
-						 "6701 CPU Check cmpl: "
-						 "cpu %d expect %d\n",
-						 cpu, lpfc_ncmd->cpu);
-			phba->sli4_hba.hdwq[idx].cpucheck_cmpl_io[cpu]++;
-		}
+		this_cpu_inc(phba->sli4_hba.c_stat->cmpl_io);
+		if (lpfc_ncmd->cpu != cpu)
+			lpfc_printf_vlog(vport,
+					 KERN_INFO, LOG_NVME_IOERR,
+					 "6701 CPU Check cmpl: "
+					 "cpu %d expect %d\n",
+					 cpu, lpfc_ncmd->cpu);
 	}
 #endif
 
@@ -1743,19 +1744,17 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 	if (lpfc_ncmd->ts_cmd_start)
 		lpfc_ncmd->ts_cmd_wqput = ktime_get_ns();
 
-	if (phba->cpucheck_on & LPFC_CHECK_NVME_IO) {
+	if (phba->hdwqstat_on & LPFC_CHECK_NVME_IO) {
 		cpu = raw_smp_processor_id();
-		if (cpu < LPFC_CHECK_CPU_CNT) {
-			lpfc_ncmd->cpu = cpu;
-			if (idx != cpu)
-				lpfc_printf_vlog(vport,
-						 KERN_INFO, LOG_NVME_IOERR,
-						"6702 CPU Check cmd: "
-						"cpu %d wq %d\n",
-						lpfc_ncmd->cpu,
-						lpfc_queue_info->index);
-			phba->sli4_hba.hdwq[idx].cpucheck_xmt_io[cpu]++;
-		}
+		this_cpu_inc(phba->sli4_hba.c_stat->xmt_io);
+		lpfc_ncmd->cpu = cpu;
+		if (idx != cpu)
+			lpfc_printf_vlog(vport,
+					 KERN_INFO, LOG_NVME_IOERR,
+					"6702 CPU Check cmd: "
+					"cpu %d wq %d\n",
+					lpfc_ncmd->cpu,
+					lpfc_queue_info->index);
 	}
 #endif
 	return 0;
@@ -1985,8 +1984,6 @@ out_unlock:
 
 /* Declare and initialization an instance of the FC NVME template. */
 static struct nvme_fc_port_template lpfc_nvme_template = {
-	.module	= THIS_MODULE,
-
 	/* initiator-based functions */
 	.localport_delete  = lpfc_nvme_localport_delete,
 	.remoteport_delete = lpfc_nvme_remoteport_delete,
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 9dc9afe1c255..f3760a4827d8 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -707,7 +707,7 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	struct lpfc_nvmet_rcv_ctx *ctxp;
 	uint32_t status, result, op, start_clean, logerr;
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	uint32_t id;
+	int id;
 #endif
 
 	ctxp = cmdwqe->context2;
@@ -814,16 +814,14 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 		rsp->done(rsp);
 	}
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	if (phba->cpucheck_on & LPFC_CHECK_NVMET_IO) {
+	if (phba->hdwqstat_on & LPFC_CHECK_NVMET_IO) {
 		id = raw_smp_processor_id();
-		if (id < LPFC_CHECK_CPU_CNT) {
-			if (ctxp->cpu != id)
-				lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
-						"6704 CPU Check cmdcmpl: "
-						"cpu %d expect %d\n",
-						id, ctxp->cpu);
-			phba->sli4_hba.hdwq[rsp->hwqid].cpucheck_cmpl_io[id]++;
-		}
+		this_cpu_inc(phba->sli4_hba.c_stat->cmpl_io);
+		if (ctxp->cpu != id)
+			lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
+					"6704 CPU Check cmdcmpl: "
+					"cpu %d expect %d\n",
+					id, ctxp->cpu);
 	}
 #endif
 }
@@ -931,6 +929,9 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 	struct lpfc_sli_ring *pring;
 	unsigned long iflags;
 	int rc;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	int id;
+#endif
 
 	if (phba->pport->load_flag & FC_UNLOADING) {
 		rc = -ENODEV;
@@ -954,16 +955,14 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 	if (!ctxp->hdwq)
 		ctxp->hdwq = &phba->sli4_hba.hdwq[rsp->hwqid];
 
-	if (phba->cpucheck_on & LPFC_CHECK_NVMET_IO) {
-		int id = raw_smp_processor_id();
-		if (id < LPFC_CHECK_CPU_CNT) {
-			if (rsp->hwqid != id)
-				lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
-						"6705 CPU Check OP: "
-						"cpu %d expect %d\n",
-						id, rsp->hwqid);
-			phba->sli4_hba.hdwq[rsp->hwqid].cpucheck_xmt_io[id]++;
-		}
+	if (phba->hdwqstat_on & LPFC_CHECK_NVMET_IO) {
+		id = raw_smp_processor_id();
+		this_cpu_inc(phba->sli4_hba.c_stat->xmt_io);
+		if (rsp->hwqid != id)
+			lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
+					"6705 CPU Check OP: "
+					"cpu %d expect %d\n",
+					id, rsp->hwqid);
 		ctxp->cpu = id; /* Setup cpu for cmpl check */
 	}
 #endif
@@ -2270,15 +2269,13 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 	size = nvmebuf->bytes_recv;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	if (phba->cpucheck_on & LPFC_CHECK_NVMET_RCV) {
-		if (current_cpu < LPFC_CHECK_CPU_CNT) {
-			if (idx != current_cpu)
-				lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
-						"6703 CPU Check rcv: "
-						"cpu %d expect %d\n",
-						current_cpu, idx);
-			phba->sli4_hba.hdwq[idx].cpucheck_rcv_io[current_cpu]++;
-		}
+	if (phba->hdwqstat_on & LPFC_CHECK_NVMET_IO) {
+		this_cpu_inc(phba->sli4_hba.c_stat->rcv_io);
+		if (idx != current_cpu)
+			lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
+					"6703 CPU Check rcv: "
+					"cpu %d expect %d\n",
+					current_cpu, idx);
 	}
 #endif
 
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 2c7e0b22db2f..ed8bcbd043c4 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -671,8 +671,10 @@ lpfc_get_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
 	lpfc_cmd->prot_data_type = 0;
 #endif
 	tmp = lpfc_get_cmd_rsp_buf_per_hdwq(phba, lpfc_cmd);
-	if (!tmp)
+	if (!tmp) {
+		lpfc_release_io_buf(phba, lpfc_cmd, lpfc_cmd->hdwq);
 		return NULL;
+	}
 
 	lpfc_cmd->fcp_cmnd = tmp->fcp_cmnd;
 	lpfc_cmd->fcp_rsp = tmp->fcp_rsp;
@@ -3803,9 +3805,6 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	struct Scsi_Host *shost;
 	int idx;
 	uint32_t logit = LOG_FCP;
-#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	int cpu;
-#endif
 
 	/* Guard against abort handler being called at same time */
 	spin_lock(&lpfc_cmd->buf_lock);
@@ -3824,11 +3823,8 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 		phba->sli4_hba.hdwq[idx].scsi_cstat.io_cmpls++;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	if (unlikely(phba->cpucheck_on & LPFC_CHECK_SCSI_IO)) {
-		cpu = raw_smp_processor_id();
-		if (cpu < LPFC_CHECK_CPU_CNT && phba->sli4_hba.hdwq)
-			phba->sli4_hba.hdwq[idx].cpucheck_cmpl_io[cpu]++;
-	}
+	if (unlikely(phba->hdwqstat_on & LPFC_CHECK_SCSI_IO))
+		this_cpu_inc(phba->sli4_hba.c_stat->cmpl_io);
 #endif
 	shost = cmd->device->host;
 
@@ -4501,9 +4497,6 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	struct lpfc_io_buf *lpfc_cmd;
 	struct fc_rport *rport = starget_to_rport(scsi_target(cmnd->device));
 	int err, idx;
-#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	int cpu;
-#endif
 
 	rdata = lpfc_rport_data_from_scsi_device(cmnd->device);
 
@@ -4624,14 +4617,8 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	lpfc_scsi_prep_cmnd(vport, lpfc_cmd, ndlp);
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	if (unlikely(phba->cpucheck_on & LPFC_CHECK_SCSI_IO)) {
-		cpu = raw_smp_processor_id();
-		if (cpu < LPFC_CHECK_CPU_CNT) {
-			struct lpfc_sli4_hdw_queue *hdwq =
-					&phba->sli4_hba.hdwq[lpfc_cmd->hdwq_no];
-			hdwq->cpucheck_xmt_io[cpu]++;
-		}
-	}
+	if (unlikely(phba->hdwqstat_on & LPFC_CHECK_SCSI_IO))
+		this_cpu_inc(phba->sli4_hba.c_stat->xmt_io);
 #endif
 	err = lpfc_sli_issue_iocb(phba, LPFC_FCP_RING,
 				  &lpfc_cmd->cur_iocbq, SLI_IOCB_RET_IOCB);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 64002b0cb02d..396e24764a1b 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -2511,6 +2511,8 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	    !pmb->u.mb.mbxStatus) {
 		rpi = pmb->u.mb.un.varWords[0];
 		vpi = pmb->u.mb.un.varRegLogin.vpi;
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			vpi -= phba->sli4_hba.max_cfg_param.vpi_base;
 		lpfc_unreg_login(phba, vpi, rpi, pmb);
 		pmb->vport = vport;
 		pmb->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
@@ -4044,6 +4046,11 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba)
 	struct lpfc_iocbq *piocb, *next_iocb;
 
 	spin_lock_irq(&phba->hbalock);
+	if (phba->hba_flag & HBA_IOQ_FLUSH ||
+	    !phba->sli4_hba.hdwq) {
+		spin_unlock_irq(&phba->hbalock);
+		return;
+	}
 	/* Indicate the I/O queues are flushed */
 	phba->hba_flag |= HBA_IOQ_FLUSH;
 	spin_unlock_irq(&phba->hbalock);
@@ -14450,12 +14457,10 @@ static inline void lpfc_sli4_add_to_poll_list(struct lpfc_queue *eq)
 {
 	struct lpfc_hba *phba = eq->phba;
 
-	if (list_empty(&phba->poll_list)) {
-		timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0);
-		/* kickstart slowpath processing for this eq */
+	/* kickstart slowpath processing if needed */
+	if (list_empty(&phba->poll_list))
 		mod_timer(&phba->cpuhp_poll_timer,
 			  jiffies + msecs_to_jiffies(LPFC_POLL_HB));
-	}
 
 	list_add_rcu(&eq->_poll_list, &phba->poll_list);
 	synchronize_rcu();
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index d963ca871383..8da7429e385a 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -697,13 +697,6 @@ struct lpfc_sli4_hdw_queue {
 	struct lpfc_lock_stat lock_conflict;
 #endif
 
-#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-#define LPFC_CHECK_CPU_CNT    128
-	uint32_t cpucheck_rcv_io[LPFC_CHECK_CPU_CNT];
-	uint32_t cpucheck_xmt_io[LPFC_CHECK_CPU_CNT];
-	uint32_t cpucheck_cmpl_io[LPFC_CHECK_CPU_CNT];
-#endif
-
 	/* Per HDWQ pool resources */
 	struct list_head sgl_list;
 	struct list_head cmd_rsp_buf_list;
@@ -740,6 +733,15 @@ struct lpfc_sli4_hdw_queue {
 #define lpfc_qp_spin_lock(lock, qp, lstat) spin_lock(lock)
 #endif
 
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+struct lpfc_hdwq_stat {
+	u32 hdwq_no;
+	u32 rcv_io;
+	u32 xmt_io;
+	u32 cmpl_io;
+};
+#endif
+
 struct lpfc_sli4_hba {
 	void __iomem *conf_regs_memmap_p; /* Kernel memory mapped address for
 					   * config space registers
@@ -921,6 +923,9 @@ struct lpfc_sli4_hba {
 	struct cpumask numa_mask;
 	uint16_t curr_disp_cpu;
 	struct lpfc_eq_intr_info __percpu *eq_info;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	struct lpfc_hdwq_stat __percpu *c_stat;
+#endif
 	uint32_t conf_trunk;
 #define lpfc_conf_trunk_port0_WORD	conf_trunk
 #define lpfc_conf_trunk_port0_SHIFT	0
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index c597d544eb39..a8ec1caf9c77 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -9908,8 +9908,8 @@ static void scsih_remove(struct pci_dev *pdev)
 
 	ioc->remove_host = 1;
 
-	mpt3sas_wait_for_commands_to_complete(ioc);
-	_scsih_flush_running_cmds(ioc);
+	if (!pci_device_is_present(pdev))
+		_scsih_flush_running_cmds(ioc);
 
 	_scsih_fw_event_cleanup_queue(ioc);
 
@@ -9992,8 +9992,8 @@ scsih_shutdown(struct pci_dev *pdev)
 
 	ioc->remove_host = 1;
 
-	mpt3sas_wait_for_commands_to_complete(ioc);
-	_scsih_flush_running_cmds(ioc);
+	if (!pci_device_is_present(pdev))
+		_scsih_flush_running_cmds(ioc);
 
 	_scsih_fw_event_cleanup_queue(ioc);
 
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index bfcd02fdf2b8..941aa53363f5 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -610,7 +610,6 @@ static void qla_nvme_remoteport_delete(struct nvme_fc_remote_port *rport)
 }
 
 static struct nvme_fc_port_template qla_nvme_fc_transport = {
-	.module	= THIS_MODULE,
 	.localport_delete = qla_nvme_localport_delete,
 	.remoteport_delete = qla_nvme_remoteport_delete,
 	.create_queue   = qla_nvme_alloc_queue,
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index dfc726fa34e3..443ace019852 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2012,7 +2012,7 @@ static void __iscsi_unbind_session(struct work_struct *work)
 	if (session->target_id == ISCSI_MAX_TARGET) {
 		spin_unlock_irqrestore(&session->lock, flags);
 		mutex_unlock(&ihost->mutex);
-		return;
+		goto unbind_session_exit;
 	}
 
 	target_id = session->target_id;
@@ -2024,6 +2024,8 @@ static void __iscsi_unbind_session(struct work_struct *work)
 		ida_simple_remove(&iscsi_sess_ida, target_id);
 
 	scsi_remove_target(&session->dev);
+
+unbind_session_exit:
 	iscsi_session_event(session, ISCSI_KEVENT_UNBIND_SESSION);
 	ISCSI_DBG_TRANS_SESSION(session, "Completed target removal\n");
 }
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 4e6af592f018..9c0ee192f0f9 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -793,8 +793,10 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp,
 			"sg_common_write:  scsi opcode=0x%02x, cmd_size=%d\n",
 			(int) cmnd[0], (int) hp->cmd_len));
 
-	if (hp->dxfer_len >= SZ_256M)
+	if (hp->dxfer_len >= SZ_256M) {
+		sg_remove_request(sfp, srp);
 		return -EINVAL;
+	}
 
 	k = sg_start_req(srp, cmnd);
 	if (k) {
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index e4240e4ae8bb..d2fe3fa470f9 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -79,7 +79,6 @@ MODULE_ALIAS_SCSI_DEVICE(TYPE_WORM);
 	 CDC_CD_R|CDC_CD_RW|CDC_DVD|CDC_DVD_R|CDC_DVD_RAM|CDC_GENERIC_PACKET| \
 	 CDC_MRW|CDC_MRW_W|CDC_RAM)
 
-static DEFINE_MUTEX(sr_mutex);
 static int sr_probe(struct device *);
 static int sr_remove(struct device *);
 static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt);
@@ -536,9 +535,9 @@ static int sr_block_open(struct block_device *bdev, fmode_t mode)
 	scsi_autopm_get_device(sdev);
 	check_disk_change(bdev);
 
-	mutex_lock(&sr_mutex);
+	mutex_lock(&cd->lock);
 	ret = cdrom_open(&cd->cdi, bdev, mode);
-	mutex_unlock(&sr_mutex);
+	mutex_unlock(&cd->lock);
 
 	scsi_autopm_put_device(sdev);
 	if (ret)
@@ -551,10 +550,12 @@ out:
 static void sr_block_release(struct gendisk *disk, fmode_t mode)
 {
 	struct scsi_cd *cd = scsi_cd(disk);
-	mutex_lock(&sr_mutex);
+
+	mutex_lock(&cd->lock);
 	cdrom_release(&cd->cdi, mode);
+	mutex_unlock(&cd->lock);
+
 	scsi_cd_put(cd);
-	mutex_unlock(&sr_mutex);
 }
 
 static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
@@ -565,7 +566,7 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	void __user *argp = (void __user *)arg;
 	int ret;
 
-	mutex_lock(&sr_mutex);
+	mutex_lock(&cd->lock);
 
 	ret = scsi_ioctl_block_when_processing_errors(sdev, cmd,
 			(mode & FMODE_NDELAY) != 0);
@@ -595,7 +596,7 @@ put:
 	scsi_autopm_put_device(sdev);
 
 out:
-	mutex_unlock(&sr_mutex);
+	mutex_unlock(&cd->lock);
 	return ret;
 }
 
@@ -608,7 +609,7 @@ static int sr_block_compat_ioctl(struct block_device *bdev, fmode_t mode, unsign
 	void __user *argp = compat_ptr(arg);
 	int ret;
 
-	mutex_lock(&sr_mutex);
+	mutex_lock(&cd->lock);
 
 	ret = scsi_ioctl_block_when_processing_errors(sdev, cmd,
 			(mode & FMODE_NDELAY) != 0);
@@ -638,7 +639,7 @@ put:
 	scsi_autopm_put_device(sdev);
 
 out:
-	mutex_unlock(&sr_mutex);
+	mutex_unlock(&cd->lock);
 	return ret;
 
 }
@@ -745,6 +746,7 @@ static int sr_probe(struct device *dev)
 	disk = alloc_disk(1);
 	if (!disk)
 		goto fail_free;
+	mutex_init(&cd->lock);
 
 	spin_lock(&sr_index_lock);
 	minor = find_first_zero_bit(sr_index_bits, SR_DISKS);
@@ -1055,6 +1057,8 @@ static void sr_kref_release(struct kref *kref)
 
 	put_disk(disk);
 
+	mutex_destroy(&cd->lock);
+
 	kfree(cd);
 }
 
diff --git a/drivers/scsi/sr.h b/drivers/scsi/sr.h
index a2bb7b8bace5..339c624e04d8 100644
--- a/drivers/scsi/sr.h
+++ b/drivers/scsi/sr.h
@@ -20,6 +20,7 @@
 
 #include <linux/genhd.h>
 #include <linux/kref.h>
+#include <linux/mutex.h>
 
 #define MAX_RETRIES	3
 #define SR_TIMEOUT	(30 * HZ)
@@ -51,6 +52,7 @@ typedef struct scsi_cd {
 	bool ignore_get_event:1;	/* GET_EVENT is unreliable, use TUR */
 
 	struct cdrom_device_info cdi;
+	struct mutex lock;
 	/* We hold gendisk and scsi_device references on probe and use
 	 * the refs on this kref to decide when to release them */
 	struct kref kref;
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 2d705694636c..52c379873c56 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -1518,6 +1518,11 @@ start:
 		 */
 		if (ufshcd_can_hibern8_during_gating(hba) &&
 		    ufshcd_is_link_hibern8(hba)) {
+			if (async) {
+				rc = -EAGAIN;
+				hba->clk_gating.active_reqs--;
+				break;
+			}
 			spin_unlock_irqrestore(hba->host->host_lock, flags);
 			flush_work(&hba->clk_gating.ungate_work);
 			spin_lock_irqsave(hba->host->host_lock, flags);
@@ -5486,7 +5491,8 @@ static irqreturn_t ufshcd_update_uic_error(struct ufs_hba *hba)
 static bool ufshcd_is_auto_hibern8_error(struct ufs_hba *hba,
 					 u32 intr_mask)
 {
-	if (!ufshcd_is_auto_hibern8_supported(hba))
+	if (!ufshcd_is_auto_hibern8_supported(hba) ||
+	    !ufshcd_is_auto_hibern8_enabled(hba))
 		return false;
 
 	if (!(intr_mask & UFSHCD_UIC_HIBERN8_MASK))
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 2ae6c7c8528c..81c71a3e3474 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -55,6 +55,7 @@
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/regulator/consumer.h>
+#include <linux/bitfield.h>
 #include "unipro.h"
 
 #include <asm/irq.h>
@@ -773,6 +774,11 @@ static inline bool ufshcd_is_auto_hibern8_supported(struct ufs_hba *hba)
 	return (hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT);
 }
 
+static inline bool ufshcd_is_auto_hibern8_enabled(struct ufs_hba *hba)
+{
+	return FIELD_GET(UFSHCI_AHIBERN8_TIMER_MASK, hba->ahit) ? true : false;
+}
+
 #define ufshcd_writel(hba, val, reg)	\
 	writel((val), (hba)->mmio_base + (reg))
 #define ufshcd_readl(hba, reg)	\