Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi

Pull SCSI updates from James Bottomley:
 :This series consists of the usual driver updates (qla2xxx, ufs, zfcp,
  target, scsi_debug, lpfc, qedi, qedf, hisi_sas, mpt3sas) plus a host
  of other minor updates.

  There are no major core changes in this series apart from a
  refactoring in scsi_lib.c"

* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (207 commits)
  scsi: ufs: ti-j721e-ufs: Fix unwinding of pm_runtime changes
  scsi: cxgb3i: Fix some leaks in init_act_open()
  scsi: ibmvscsi: Make some functions static
  scsi: iscsi: Fix deadlock on recovery path during GFP_IO reclaim
  scsi: ufs: Fix WriteBooster flush during runtime suspend
  scsi: ufs: Fix index of attributes query for WriteBooster feature
  scsi: ufs: Allow WriteBooster on UFS 2.2 devices
  scsi: ufs: Remove unnecessary memset for dev_info
  scsi: ufs-qcom: Fix scheduling while atomic issue
  scsi: mpt3sas: Fix reply queue count in non RDPQ mode
  scsi: lpfc: Fix lpfc_nodelist leak when processing unsolicited event
  scsi: target: tcmu: Fix a use after free in tcmu_check_expired_queue_cmd()
  scsi: vhost: Notify TCM about the maximum sg entries supported per command
  scsi: qla2xxx: Remove return value from qla_nvme_ls()
  scsi: qla2xxx: Remove an unused function
  scsi: iscsi: Register sysfs for iscsi workqueue
  scsi: scsi_debug: Parser tables and code interaction
  scsi: core: Refactor scsi_mq_setup_tags function
  scsi: core: Fix incorrect usage of shost_for_each_device
  scsi: qla2xxx: Fix endianness annotations in source files
  ...

14 files changed, 172 insertions, 164 deletions

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 62e96d4fdcc6..c3ceb6e5b061 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -627,6 +627,19 @@ struct lpfc_ras_fwlog {
 	enum ras_state state;    /* RAS logging running state */
 };
 
+enum lpfc_irq_chann_mode {
+	/* Assign IRQs to all possible cpus that have hardware queues */
+	NORMAL_MODE,
+
+	/* Assign IRQs only to cpus on the same numa node as HBA */
+	NUMA_MODE,
+
+	/* Assign IRQs only on non-hyperthreaded CPUs. This is the
+	 * same as normal_mode, but assign IRQS only on physical CPUs.
+	 */
+	NHT_MODE,
+};
+
 struct lpfc_hba {
 	/* SCSI interface function jump table entries */
 	struct lpfc_io_buf * (*lpfc_get_scsi_buf)
@@ -835,7 +848,6 @@ struct lpfc_hba {
 	uint32_t cfg_fcp_mq_threshold;
 	uint32_t cfg_hdw_queue;
 	uint32_t cfg_irq_chann;
-	uint32_t cfg_irq_numa;
 	uint32_t cfg_suppress_rsp;
 	uint32_t cfg_nvme_oas;
 	uint32_t cfg_nvme_embed_cmd;
@@ -1003,6 +1015,7 @@ struct lpfc_hba {
 	mempool_t *active_rrq_pool;
 
 	struct fc_host_statistics link_stats;
+	enum lpfc_irq_chann_mode irq_chann_mode;
 	enum intr_type_t intr_type;
 	uint32_t intr_mode;
 #define LPFC_INTR_ERROR	0xFFFFFFFF
@@ -1314,19 +1327,19 @@ lpfc_phba_elsring(struct lpfc_hba *phba)
 }
 
 /**
- * lpfc_next_online_numa_cpu - Finds next online CPU on NUMA node
- * @numa_mask: Pointer to phba's numa_mask member.
+ * lpfc_next_online_cpu - Finds next online CPU on cpumask
+ * @mask: Pointer to phba's cpumask member.
  * @start: starting cpu index
  *
  * Note: If no valid cpu found, then nr_cpu_ids is returned.
  *
  **/
 static inline unsigned int
-lpfc_next_online_numa_cpu(const struct cpumask *numa_mask, unsigned int start)
+lpfc_next_online_cpu(const struct cpumask *mask, unsigned int start)
 {
 	unsigned int cpu_it;
 
-	for_each_cpu_wrap(cpu_it, numa_mask, start) {
+	for_each_cpu_wrap(cpu_it, mask, start) {
 		if (cpu_online(cpu_it))
 			break;
 	}
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index f089867674cb..a62c60ca6477 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -4874,7 +4874,7 @@ lpfc_request_firmware_upgrade_store(struct device *dev,
 	struct Scsi_Host *shost = class_to_shost(dev);
 	struct lpfc_vport *vport = (struct lpfc_vport *)shost->hostdata;
 	struct lpfc_hba *phba = vport->phba;
-	int val = 0, rc = -EINVAL;
+	int val = 0, rc;
 
 	/* Sanity check on user data */
 	if (!isdigit(buf[0]))
@@ -5701,17 +5701,69 @@ LPFC_ATTR_R(hdw_queue,
 	    LPFC_HBA_HDWQ_MIN, LPFC_HBA_HDWQ_MAX,
 	    "Set the number of I/O Hardware Queues");
 
-static inline void
-lpfc_assign_default_irq_numa(struct lpfc_hba *phba)
+#if IS_ENABLED(CONFIG_X86)
+/**
+ * lpfc_cpumask_irq_mode_init - initalizes cpumask of phba based on
+ *				irq_chann_mode
+ * @phba: Pointer to HBA context object.
+ **/
+static void
+lpfc_cpumask_irq_mode_init(struct lpfc_hba *phba)
+{
+	unsigned int cpu, first_cpu, numa_node = NUMA_NO_NODE;
+	const struct cpumask *sibling_mask;
+	struct cpumask *aff_mask = &phba->sli4_hba.irq_aff_mask;
+
+	cpumask_clear(aff_mask);
+
+	if (phba->irq_chann_mode == NUMA_MODE) {
+		/* Check if we're a NUMA architecture */
+		numa_node = dev_to_node(&phba->pcidev->dev);
+		if (numa_node == NUMA_NO_NODE) {
+			phba->irq_chann_mode = NORMAL_MODE;
+			return;
+		}
+	}
+
+	for_each_possible_cpu(cpu) {
+		switch (phba->irq_chann_mode) {
+		case NUMA_MODE:
+			if (cpu_to_node(cpu) == numa_node)
+				cpumask_set_cpu(cpu, aff_mask);
+			break;
+		case NHT_MODE:
+			sibling_mask = topology_sibling_cpumask(cpu);
+			first_cpu = cpumask_first(sibling_mask);
+			if (first_cpu < nr_cpu_ids)
+				cpumask_set_cpu(first_cpu, aff_mask);
+			break;
+		default:
+			break;
+		}
+	}
+}
+#endif
+
+static void
+lpfc_assign_default_irq_chann(struct lpfc_hba *phba)
 {
 #if IS_ENABLED(CONFIG_X86)
-	/* If AMD architecture, then default is LPFC_IRQ_CHANN_NUMA */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
-		phba->cfg_irq_numa = 1;
-	else
-		phba->cfg_irq_numa = 0;
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_AMD:
+		/* If AMD architecture, then default is NUMA_MODE */
+		phba->irq_chann_mode = NUMA_MODE;
+		break;
+	case X86_VENDOR_INTEL:
+		/* If Intel architecture, then default is no hyperthread mode */
+		phba->irq_chann_mode = NHT_MODE;
+		break;
+	default:
+		phba->irq_chann_mode = NORMAL_MODE;
+		break;
+	}
+	lpfc_cpumask_irq_mode_init(phba);
 #else
-	phba->cfg_irq_numa = 0;
+	phba->irq_chann_mode = NORMAL_MODE;
 #endif
 }
 
@@ -5723,6 +5775,7 @@ lpfc_assign_default_irq_numa(struct lpfc_hba *phba)
  *
  *	0		= Configure number of IRQ Channels to:
  *			  if AMD architecture, number of CPUs on HBA's NUMA node
+ *			  if Intel architecture, number of physical CPUs.
  *			  otherwise, number of active CPUs.
  *	[1,256]		= Manually specify how many IRQ Channels to use.
  *
@@ -5748,35 +5801,44 @@ MODULE_PARM_DESC(lpfc_irq_chann, "Set number of interrupt vectors to allocate");
 static int
 lpfc_irq_chann_init(struct lpfc_hba *phba, uint32_t val)
 {
-	const struct cpumask *numa_mask;
+	const struct cpumask *aff_mask;
 
 	if (phba->cfg_use_msi != 2) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"8532 use_msi = %u ignoring cfg_irq_numa\n",
 				phba->cfg_use_msi);
-		phba->cfg_irq_numa = 0;
-		phba->cfg_irq_chann = LPFC_IRQ_CHANN_MIN;
+		phba->irq_chann_mode = NORMAL_MODE;
+		phba->cfg_irq_chann = LPFC_IRQ_CHANN_DEF;
 		return 0;
 	}
 
 	/* Check if default setting was passed */
 	if (val == LPFC_IRQ_CHANN_DEF)
-		lpfc_assign_default_irq_numa(phba);
+		lpfc_assign_default_irq_chann(phba);
 
-	if (phba->cfg_irq_numa) {
-		numa_mask = &phba->sli4_hba.numa_mask;
+	if (phba->irq_chann_mode != NORMAL_MODE) {
+		aff_mask = &phba->sli4_hba.irq_aff_mask;
 
-		if (cpumask_empty(numa_mask)) {
+		if (cpumask_empty(aff_mask)) {
 			lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-					"8533 Could not identify NUMA node, "
-					"ignoring cfg_irq_numa\n");
-			phba->cfg_irq_numa = 0;
-			phba->cfg_irq_chann = LPFC_IRQ_CHANN_MIN;
+					"8533 Could not identify CPUS for "
+					"mode %d, ignoring\n",
+					phba->irq_chann_mode);
+			phba->irq_chann_mode = NORMAL_MODE;
+			phba->cfg_irq_chann = LPFC_IRQ_CHANN_DEF;
 		} else {
-			phba->cfg_irq_chann = cpumask_weight(numa_mask);
+			phba->cfg_irq_chann = cpumask_weight(aff_mask);
+
+			/* If no hyperthread mode, then set hdwq count to
+			 * aff_mask weight as well
+			 */
+			if (phba->irq_chann_mode == NHT_MODE)
+				phba->cfg_hdw_queue = phba->cfg_irq_chann;
+
 			lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 					"8543 lpfc_irq_chann set to %u "
-					"(numa)\n", phba->cfg_irq_chann);
+					"(mode: %d)\n", phba->cfg_irq_chann,
+					phba->irq_chann_mode);
 		}
 	} else {
 		if (val > LPFC_IRQ_CHANN_MAX) {
@@ -5787,7 +5849,7 @@ lpfc_irq_chann_init(struct lpfc_hba *phba, uint32_t val)
 					val,
 					LPFC_IRQ_CHANN_MIN,
 					LPFC_IRQ_CHANN_MAX);
-			phba->cfg_irq_chann = LPFC_IRQ_CHANN_MIN;
+			phba->cfg_irq_chann = LPFC_IRQ_CHANN_DEF;
 			return -EINVAL;
 		}
 		phba->cfg_irq_chann = val;
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 196f6ae9952e..69d4710d95a0 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -461,7 +461,6 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 	struct lpfc_nodelist *ndlp;
 
 	if ((vport->port_type != LPFC_NPIV_PORT) ||
-	    (fc4_type == FC_TYPE_FCP) ||
 	    !(vport->ct_flags & FC_CT_RFF_ID) || !vport->cfg_restrict_login) {
 
 		ndlp = lpfc_setup_disc_node(vport, Did);
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 4daae90e0c99..ae0a8252128c 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -2429,7 +2429,8 @@ lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf,
 		return 0;
 
 	if (dent == phba->debug_InjErrLBA) {
-		if ((buf[0] == 'o') && (buf[1] == 'f') && (buf[2] == 'f'))
+		if ((dstbuf[0] == 'o') && (dstbuf[1] == 'f') &&
+		    (dstbuf[2] == 'f'))
 			tmp = (uint64_t)(-1);
 	}
 
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 80d1e661b0d4..3d670568a276 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -7936,19 +7936,13 @@ lpfc_els_timeout_handler(struct lpfc_vport *vport)
 	if (unlikely(!pring))
 		return;
 
-	if ((phba->pport->load_flag & FC_UNLOADING))
+	if (phba->pport->load_flag & FC_UNLOADING)
 		return;
+
 	spin_lock_irq(&phba->hbalock);
 	if (phba->sli_rev == LPFC_SLI_REV4)
 		spin_lock(&pring->ring_lock);
 
-	if ((phba->pport->load_flag & FC_UNLOADING)) {
-		if (phba->sli_rev == LPFC_SLI_REV4)
-			spin_unlock(&pring->ring_lock);
-		spin_unlock_irq(&phba->hbalock);
-		return;
-	}
-
 	list_for_each_entry_safe(piocb, tmp_iocb, &pring->txcmplq, list) {
 		cmd = &piocb->iocb;
 
@@ -8514,6 +8508,8 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	spin_lock_irq(shost->host_lock);
 	if (ndlp->nlp_flag & NLP_IN_DEV_LOSS) {
 		spin_unlock_irq(shost->host_lock);
+		if (newnode)
+			lpfc_nlp_put(ndlp);
 		goto dropit;
 	}
 	spin_unlock_irq(shost->host_lock);
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index f5952f8cd4b5..4084f7f2b821 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -1360,14 +1360,14 @@ lpfc_vlan_id_match(uint16_t curr_vlan_id, uint16_t new_vlan_id)
 }
 
 /**
- * lpfc_update_fcf_record - Update driver fcf record
  * __lpfc_update_fcf_record_pri - update the lpfc_fcf_pri record.
  * @phba: pointer to lpfc hba data structure.
  * @fcf_index: Index for the lpfc_fcf_record.
  * @new_fcf_record: pointer to hba fcf record.
  *
  * This routine updates the driver FCF priority record from the new HBA FCF
- * record. This routine is called with the host lock held.
+ * record. The hbalock is asserted held in the code path calling this
+ * routine.
  **/
 static void
 __lpfc_update_fcf_record_pri(struct lpfc_hba *phba, uint16_t fcf_index,
@@ -1376,8 +1376,6 @@ __lpfc_update_fcf_record_pri(struct lpfc_hba *phba, uint16_t fcf_index,
 {
 	struct lpfc_fcf_pri *fcf_pri;
 
-	lockdep_assert_held(&phba->hbalock);
-
 	fcf_pri = &phba->fcf.fcf_pri[fcf_index];
 	fcf_pri->fcf_rec.fcf_index = fcf_index;
 	/* FCF record priority */
@@ -1455,7 +1453,7 @@ lpfc_copy_fcf_record(struct lpfc_fcf_rec *fcf_rec,
  *
  * This routine updates the driver FCF record from the new HBA FCF record
  * together with the address mode, vlan_id, and other informations. This
- * routine is called with the host lock held.
+ * routine is called with the hbalock held.
  **/
 static void
 __lpfc_update_fcf_record(struct lpfc_hba *phba, struct lpfc_fcf_rec *fcf_rec,
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 10c5d1c3122e..6dfff0376547 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -3541,7 +3541,7 @@ struct lpfc_mbx_set_feature {
 #define lpfc_mbx_set_feature_UER_SHIFT  0
 #define lpfc_mbx_set_feature_UER_MASK   0x00000001
 #define lpfc_mbx_set_feature_UER_WORD   word6
-#define lpfc_mbx_set_feature_mds_SHIFT  0
+#define lpfc_mbx_set_feature_mds_SHIFT  2
 #define lpfc_mbx_set_feature_mds_MASK   0x00000001
 #define lpfc_mbx_set_feature_mds_WORD   word6
 #define lpfc_mbx_set_feature_mds_deep_loopbk_SHIFT  1
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index ea99483345f2..69a5249e007a 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -6020,29 +6020,6 @@ static void lpfc_log_intr_mode(struct lpfc_hba *phba, uint32_t intr_mode)
 }
 
 /**
- * lpfc_cpumask_of_node_init - initalizes cpumask of phba's NUMA node
- * @phba: Pointer to HBA context object.
- *
- **/
-static void
-lpfc_cpumask_of_node_init(struct lpfc_hba *phba)
-{
-	unsigned int cpu, numa_node;
-	struct cpumask *numa_mask = &phba->sli4_hba.numa_mask;
-
-	cpumask_clear(numa_mask);
-
-	/* Check if we're a NUMA architecture */
-	numa_node = dev_to_node(&phba->pcidev->dev);
-	if (numa_node == NUMA_NO_NODE)
-		return;
-
-	for_each_possible_cpu(cpu)
-		if (cpu_to_node(cpu) == numa_node)
-			cpumask_set_cpu(cpu, numa_mask);
-}
-
-/**
  * lpfc_enable_pci_dev - Enable a generic PCI device.
  * @phba: pointer to lpfc hba data structure.
  *
@@ -6480,7 +6457,6 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	phba->sli4_hba.num_present_cpu = lpfc_present_cpu;
 	phba->sli4_hba.num_possible_cpu = cpumask_last(cpu_possible_mask) + 1;
 	phba->sli4_hba.curr_disp_cpu = 0;
-	lpfc_cpumask_of_node_init(phba);
 
 	/* Get all the module params for configuring this host */
 	lpfc_get_cfgparam(phba);
@@ -6688,6 +6664,13 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 #endif
 				/* Not supported for NVMET */
 				phba->cfg_xri_rebalancing = 0;
+				if (phba->irq_chann_mode == NHT_MODE) {
+					phba->cfg_irq_chann =
+						phba->sli4_hba.num_present_cpu;
+					phba->cfg_hdw_queue =
+						phba->sli4_hba.num_present_cpu;
+					phba->irq_chann_mode = NORMAL_MODE;
+				}
 				break;
 			}
 		}
@@ -7029,7 +7012,7 @@ lpfc_sli4_driver_resource_unset(struct lpfc_hba *phba)
 	phba->sli4_hba.num_possible_cpu = 0;
 	phba->sli4_hba.num_present_cpu = 0;
 	phba->sli4_hba.curr_disp_cpu = 0;
-	cpumask_clear(&phba->sli4_hba.numa_mask);
+	cpumask_clear(&phba->sli4_hba.irq_aff_mask);
 
 	/* Free memory allocated for fast-path work queue handles */
 	kfree(phba->sli4_hba.hba_eq_hdl);
@@ -11284,11 +11267,12 @@ lpfc_irq_clear_aff(struct lpfc_hba_eq_hdl *eqhdl)
  * @offline: true, cpu is going offline. false, cpu is coming online.
  *
  * If cpu is going offline, we'll try our best effort to find the next
- * online cpu on the phba's NUMA node and migrate all offlining IRQ affinities.
+ * online cpu on the phba's original_mask and migrate all offlining IRQ
+ * affinities.
  *
- * If cpu is coming online, reaffinitize the IRQ back to the onlineng cpu.
+ * If cpu is coming online, reaffinitize the IRQ back to the onlining cpu.
  *
- * Note: Call only if cfg_irq_numa is enabled, otherwise rely on
+ * Note: Call only if NUMA or NHT mode is enabled, otherwise rely on
  *	 PCI_IRQ_AFFINITY to auto-manage IRQ affinity.
  *
  **/
@@ -11298,14 +11282,14 @@ lpfc_irq_rebalance(struct lpfc_hba *phba, unsigned int cpu, bool offline)
 	struct lpfc_vector_map_info *cpup;
 	struct cpumask *aff_mask;
 	unsigned int cpu_select, cpu_next, idx;
-	const struct cpumask *numa_mask;
+	const struct cpumask *orig_mask;
 
-	if (!phba->cfg_irq_numa)
+	if (phba->irq_chann_mode == NORMAL_MODE)
 		return;
 
-	numa_mask = &phba->sli4_hba.numa_mask;
+	orig_mask = &phba->sli4_hba.irq_aff_mask;
 
-	if (!cpumask_test_cpu(cpu, numa_mask))
+	if (!cpumask_test_cpu(cpu, orig_mask))
 		return;
 
 	cpup = &phba->sli4_hba.cpu_map[cpu];
@@ -11314,9 +11298,9 @@ lpfc_irq_rebalance(struct lpfc_hba *phba, unsigned int cpu, bool offline)
 		return;
 
 	if (offline) {
-		/* Find next online CPU on NUMA node */
-		cpu_next = cpumask_next_wrap(cpu, numa_mask, cpu, true);
-		cpu_select = lpfc_next_online_numa_cpu(numa_mask, cpu_next);
+		/* Find next online CPU on original mask */
+		cpu_next = cpumask_next_wrap(cpu, orig_mask, cpu, true);
+		cpu_select = lpfc_next_online_cpu(orig_mask, cpu_next);
 
 		/* Found a valid CPU */
 		if ((cpu_select < nr_cpu_ids) && (cpu_select != cpu)) {
@@ -11431,7 +11415,7 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 {
 	int vectors, rc, index;
 	char *name;
-	const struct cpumask *numa_mask = NULL;
+	const struct cpumask *aff_mask = NULL;
 	unsigned int cpu = 0, cpu_cnt = 0, cpu_select = nr_cpu_ids;
 	struct lpfc_hba_eq_hdl *eqhdl;
 	const struct cpumask *maskp;
@@ -11441,16 +11425,18 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 	/* Set up MSI-X multi-message vectors */
 	vectors = phba->cfg_irq_chann;
 
-	if (phba->cfg_irq_numa) {
-		numa_mask = &phba->sli4_hba.numa_mask;
-		cpu_cnt = cpumask_weight(numa_mask);
+	if (phba->irq_chann_mode != NORMAL_MODE)
+		aff_mask = &phba->sli4_hba.irq_aff_mask;
+
+	if (aff_mask) {
+		cpu_cnt = cpumask_weight(aff_mask);
 		vectors = min(phba->cfg_irq_chann, cpu_cnt);
 
-		/* cpu: iterates over numa_mask including offline or online
-		 * cpu_select: iterates over online numa_mask to set affinity
+		/* cpu: iterates over aff_mask including offline or online
+		 * cpu_select: iterates over online aff_mask to set affinity
 		 */
-		cpu = cpumask_first(numa_mask);
-		cpu_select = lpfc_next_online_numa_cpu(numa_mask, cpu);
+		cpu = cpumask_first(aff_mask);
+		cpu_select = lpfc_next_online_cpu(aff_mask, cpu);
 	} else {
 		flags |= PCI_IRQ_AFFINITY;
 	}
@@ -11484,7 +11470,7 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 
 		eqhdl->irq = pci_irq_vector(phba->pcidev, index);
 
-		if (phba->cfg_irq_numa) {
+		if (aff_mask) {
 			/* If found a neighboring online cpu, set affinity */
 			if (cpu_select < nr_cpu_ids)
 				lpfc_irq_set_aff(eqhdl, cpu_select);
@@ -11494,11 +11480,11 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 						LPFC_CPU_FIRST_IRQ,
 						cpu);
 
-			/* Iterate to next offline or online cpu in numa_mask */
-			cpu = cpumask_next(cpu, numa_mask);
+			/* Iterate to next offline or online cpu in aff_mask */
+			cpu = cpumask_next(cpu, aff_mask);
 
-			/* Find next online cpu in numa_mask to set affinity */
-			cpu_select = lpfc_next_online_numa_cpu(numa_mask, cpu);
+			/* Find next online cpu in aff_mask to set affinity */
+			cpu_select = lpfc_next_online_cpu(aff_mask, cpu);
 		} else if (vectors == 1) {
 			cpu = cpumask_first(cpu_present_mask);
 			lpfc_assign_eq_map_info(phba, index, LPFC_CPU_FIRST_IRQ,
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index e35b52b66d6c..e34e0f11bfdd 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -1378,7 +1378,8 @@ lpfc_config_port(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	 */
 
 	if (phba->cfg_hostmem_hgp && phba->sli_rev != 3) {
-		phba->host_gp = &phba->mbox->us.s2.host[0];
+		phba->host_gp = (struct lpfc_hgp __iomem *)
+				 &phba->mbox->us.s2.host[0];
 		phba->hbq_put = NULL;
 		offset = (uint8_t *)&phba->mbox->us.s2.host -
 			(uint8_t *)phba->slim2p.virt;
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index b46ba70f78da..b16c087ba272 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -1654,11 +1654,6 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 
 	phba = vport->phba;
 
-	if (vport->load_flag & FC_UNLOADING) {
-		ret = -ENODEV;
-		goto out_fail;
-	}
-
 	if (unlikely(vport->load_flag & FC_UNLOADING)) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR,
 				 "6124 Fail IO, Driver unload\n");
@@ -2491,38 +2486,6 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		spin_unlock_irq(&vport->phba->hbalock);
 		rport = remote_port->private;
 		if (oldrport) {
-			/* New remoteport record does not guarantee valid
-			 * host private memory area.
-			 */
-			if (oldrport == remote_port->private) {
-				/* Same remoteport - ndlp should match.
-				 * Just reuse.
-				 */
-				lpfc_printf_vlog(ndlp->vport, KERN_INFO,
-						 LOG_NVME_DISC,
-						 "6014 Rebind lport to current "
-						 "remoteport x%px wwpn 0x%llx, "
-						 "Data: x%x x%x x%px x%px x%x "
-						 " x%06x\n",
-						 remote_port,
-						 remote_port->port_name,
-						 remote_port->port_id,
-						 remote_port->port_role,
-						 oldrport->ndlp,
-						 ndlp,
-						 ndlp->nlp_type,
-						 ndlp->nlp_DID);
-
-				/* It's a complete rebind only if the driver
-				 * is registering with the same ndlp. Otherwise
-				 * the driver likely executed a node swap
-				 * prior to this registration and the ndlp to
-				 * remoteport binding needs to be redone.
-				 */
-				if (prev_ndlp == ndlp)
-					return 0;
-
-			}
 
 			/* Sever the ndlp<->rport association
 			 * before dropping the ndlp ref from
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 32eb5e873e9b..88760416a8cb 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -1030,11 +1030,6 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 		goto aerr;
 	}
 
-	if (phba->pport->load_flag & FC_UNLOADING) {
-		rc = -ENODEV;
-		goto aerr;
-	}
-
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	if (ctxp->ts_cmd_nvme) {
 		if (rsp->op == NVMET_FCOP_RSP)
@@ -1157,9 +1152,6 @@ lpfc_nvmet_xmt_fcp_abort(struct nvmet_fc_target_port *tgtport,
 	if (phba->pport->load_flag & FC_UNLOADING)
 		return;
 
-	if (phba->pport->load_flag & FC_UNLOADING)
-		return;
-
 	if (!ctxp->hdwq)
 		ctxp->hdwq = &phba->sli4_hba.hdwq[0];
 
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 9e21c4f3b009..25653baba367 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -535,7 +535,7 @@ lpfc_sli4_process_eq(struct lpfc_hba *phba, struct lpfc_queue *eq,
 	if (count > eq->EQ_max_eqe)
 		eq->EQ_max_eqe = count;
 
-	eq->queue_claimed = 0;
+	xchg(&eq->queue_claimed, 0);
 
 rearm_and_exit:
 	/* Always clear the EQ. */
@@ -1245,8 +1245,8 @@ lpfc_sli_get_iocbq(struct lpfc_hba *phba)
  * @phba: Pointer to HBA context object.
  * @iocbq: Pointer to driver iocb object.
  *
- * This function is called with hbalock held to release driver
- * iocb object to the iocb pool. The iotag in the iocb object
+ * This function is called to release the driver iocb object
+ * to the iocb pool. The iotag in the iocb object
  * does not change for each use of the iocb object. This function
  * clears all other fields of the iocb object when it is freed.
  * The sqlq structure that holds the xritag and phys and virtual
@@ -1256,7 +1256,8 @@ lpfc_sli_get_iocbq(struct lpfc_hba *phba)
  * this IO was aborted then the sglq entry it put on the
  * lpfc_abts_els_sgl_list until the CQ_ABORTED_XRI is received. If the
  * IO has good status or fails for any other reason then the sglq
- * entry is added to the free list (lpfc_els_sgl_list).
+ * entry is added to the free list (lpfc_els_sgl_list). The hbalock is
+ *  asserted held in the code path calling this routine.
  **/
 static void
 __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
@@ -1266,8 +1267,6 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 	unsigned long iflag = 0;
 	struct lpfc_sli_ring *pring;
 
-	lockdep_assert_held(&phba->hbalock);
-
 	if (iocbq->sli4_xritag == NO_XRI)
 		sglq = NULL;
 	else
@@ -1330,18 +1329,17 @@ out:
  * @phba: Pointer to HBA context object.
  * @iocbq: Pointer to driver iocb object.
  *
- * This function is called with hbalock held to release driver
- * iocb object to the iocb pool. The iotag in the iocb object
- * does not change for each use of the iocb object. This function
- * clears all other fields of the iocb object when it is freed.
+ * This function is called to release the driver iocb object to the
+ * iocb pool. The iotag in the iocb object does not change for each
+ * use of the iocb object. This function clears all other fields of
+ * the iocb object when it is freed. The hbalock is asserted held in
+ * the code path calling this routine.
  **/
 static void
 __lpfc_sli_release_iocbq_s3(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 {
 	size_t start_clean = offsetof(struct lpfc_iocbq, iocb);
 
-	lockdep_assert_held(&phba->hbalock);
-
 	/*
 	 * Clean all volatile data fields, preserve iotag and node struct.
 	 */
@@ -1786,17 +1784,17 @@ lpfc_sli_next_iotag(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
  * @nextiocb: Pointer to driver iocb object which need to be
  *            posted to firmware.
  *
- * This function is called with hbalock held to post a new iocb to
- * the firmware. This function copies the new iocb to ring iocb slot and
- * updates the ring pointers. It adds the new iocb to txcmplq if there is
+ * This function is called to post a new iocb to the firmware. This
+ * function copies the new iocb to ring iocb slot and updates the
+ * ring pointers. It adds the new iocb to txcmplq if there is
  * a completion call back for this iocb else the function will free the
- * iocb object.
+ * iocb object.  The hbalock is asserted held in the code path calling
+ * this routine.
  **/
 static void
 lpfc_sli_submit_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		IOCB_t *iocb, struct lpfc_iocbq *nextiocb)
 {
-	lockdep_assert_held(&phba->hbalock);
 	/*
 	 * Set up an iotag
 	 */
@@ -11284,6 +11282,7 @@ lpfc_ignore_els_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
  * request, this function issues abort out unconditionally. This function is
  * called with hbalock held. The function returns 0 when it fails due to
  * memory allocation failure or when the command iocb is an abort request.
+ * The hbalock is asserted held in the code path calling this routine.
  **/
 static int
 lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
@@ -11297,8 +11296,6 @@ lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	unsigned long iflags;
 	struct lpfc_nodelist *ndlp;
 
-	lockdep_assert_held(&phba->hbalock);
-
 	/*
 	 * There are certain command types we don't want to abort.  And we
 	 * don't want to abort commands that are already in the process of
@@ -13808,7 +13805,7 @@ __lpfc_sli4_process_cq(struct lpfc_hba *phba, struct lpfc_queue *cq,
 				"0369 No entry from completion queue "
 				"qid=%d\n", cq->queue_id);
 
-	cq->queue_claimed = 0;
+	xchg(&cq->queue_claimed, 0);
 
 rearm_and_exit:
 	phba->sli4_hba.sli4_write_cq_db(phba, cq, consumed,
@@ -14389,7 +14386,6 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 	int ecount = 0;
 	int hba_eqidx;
 	struct lpfc_eq_intr_info *eqi;
-	uint32_t icnt;
 
 	/* Get the driver's phba structure from the dev_id */
 	hba_eq_hdl = (struct lpfc_hba_eq_hdl *)dev_id;
@@ -14417,11 +14413,12 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 		return IRQ_NONE;
 	}
 
-	eqi = phba->sli4_hba.eq_info;
-	icnt = this_cpu_inc_return(eqi->icnt);
+	eqi = this_cpu_ptr(phba->sli4_hba.eq_info);
+	eqi->icnt++;
+
 	fpeq->last_cpu = raw_smp_processor_id();
 
-	if (icnt > LPFC_EQD_ISR_TRIGGER &&
+	if (eqi->icnt > LPFC_EQD_ISR_TRIGGER &&
 	    fpeq->q_flag & HBA_EQ_DELAY_CHK &&
 	    phba->cfg_auto_imax &&
 	    fpeq->q_mode != LPFC_MAX_AUTO_EQ_DELAY &&
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 8da7429e385a..4decb53d81c3 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -920,7 +920,7 @@ struct lpfc_sli4_hba {
 	struct lpfc_vector_map_info *cpu_map;
 	uint16_t num_possible_cpu;
 	uint16_t num_present_cpu;
-	struct cpumask numa_mask;
+	struct cpumask irq_aff_mask;
 	uint16_t curr_disp_cpu;
 	struct lpfc_eq_intr_info __percpu *eq_info;
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index ca40c47cfbe0..ab0bc26c098d 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "12.8.0.0"
+#define LPFC_DRIVER_VERSION "12.8.0.1"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */