diff options
Diffstat (limited to 'drivers/scsi/lpfc')
26 files changed, 4110 insertions, 2060 deletions
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index 2c3bb8a966e5..04d73e2be373 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -51,6 +51,8 @@ struct lpfc_sli2_slim; cmnd for menlo needs nearly twice as for firmware downloads using bsg */ +#define LPFC_DEFAULT_XPSGL_SIZE 256 +#define LPFC_MAX_SG_TABLESIZE 0xffff #define LPFC_MIN_SG_SLI4_BUF_SZ 0x800 /* based on LPFC_DEFAULT_SG_SEG_CNT */ #define LPFC_MAX_BG_SLI4_SEG_CNT_DIF 128 /* sg element count for BlockGuard */ #define LPFC_MAX_SG_SEG_CNT_DIF 512 /* sg element count per scsi cmnd */ @@ -603,6 +605,12 @@ struct lpfc_epd_pool { spinlock_t lock; /* lock for expedite pool */ }; +enum ras_state { + INACTIVE, + REG_INPROGRESS, + ACTIVE +}; + struct lpfc_ras_fwlog { uint8_t *fwlog_buff; uint32_t fw_buffcount; /* Buffer size posted to FW */ @@ -619,7 +627,7 @@ struct lpfc_ras_fwlog { bool ras_enabled; /* Ras Enabled for the function */ #define LPFC_RAS_DISABLE_LOGGING 0x00 #define LPFC_RAS_ENABLE_LOGGING 0x01 - bool ras_active; /* RAS logging running state */ + enum ras_state state; /* RAS logging running state */ }; struct lpfc_hba { @@ -723,6 +731,7 @@ struct lpfc_hba { #define HBA_FCOE_MODE 0x4 /* HBA function in FCoE Mode */ #define HBA_SP_QUEUE_EVT 0x8 /* Slow-path qevt posted to worker thread*/ #define HBA_POST_RECEIVE_BUFFER 0x10 /* Rcv buffers need to be posted */ +#define HBA_PERSISTENT_TOPO 0x20 /* Persistent topology support in hba */ #define ELS_XRI_ABORT_EVENT 0x40 #define ASYNC_EVENT 0x80 #define LINK_DISABLED 0x100 /* Link disabled by user */ @@ -732,14 +741,13 @@ struct lpfc_hba { #define HBA_AER_ENABLED 0x1000 /* AER enabled with HBA */ #define HBA_DEVLOSS_TMO 0x2000 /* HBA in devloss timeout */ #define HBA_RRQ_ACTIVE 0x4000 /* process the rrq active list */ -#define HBA_FCP_IOQ_FLUSH 0x8000 /* FCP I/O queues being flushed */ +#define HBA_IOQ_FLUSH 0x8000 /* FCP/NVME I/O queues being flushed */ #define HBA_FW_DUMP_OP 0x10000 /* Skips fn reset before FW dump */ #define HBA_RECOVERABLE_UE 0x20000 /* Firmware supports recoverable UE */ #define HBA_FORCED_LINK_SPEED 0x40000 /* * Firmware supports Forced Link Speed * capability */ -#define HBA_NVME_IOQ_FLUSH 0x80000 /* NVME IO queues flushed. */ #define HBA_FLOGI_ISSUED 0x100000 /* FLOGI was issued */ uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/ @@ -795,10 +803,12 @@ struct lpfc_hba { uint8_t mds_diags_support; uint8_t bbcredit_support; uint8_t enab_exp_wqcq_pages; + u8 nsler; /* Firmware supports FC-NVMe-2 SLER */ /* HBA Config Parameters */ uint32_t cfg_ack0; uint32_t cfg_xri_rebalancing; + uint32_t cfg_xpsgl; uint32_t cfg_enable_npiv; uint32_t cfg_enable_rrq; uint32_t cfg_topology; @@ -824,8 +834,10 @@ struct lpfc_hba { uint32_t cfg_cq_poll_threshold; uint32_t cfg_cq_max_proc_limit; uint32_t cfg_fcp_cpu_map; + 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; @@ -868,7 +880,6 @@ struct lpfc_hba { uint32_t cfg_aer_support; uint32_t cfg_sriov_nr_virtfn; uint32_t cfg_request_firmware_upgrade; - uint32_t cfg_iocb_cnt; uint32_t cfg_suppress_link_up; uint32_t cfg_rrq_xri_bitmap_sz; uint32_t cfg_delay_discovery; @@ -904,6 +915,7 @@ struct lpfc_hba { wait_queue_head_t work_waitq; struct task_struct *worker_thread; unsigned long data_flags; + uint32_t border_sge_num; uint32_t hbq_in_use; /* HBQs in use flag */ uint32_t hbq_count; /* Count of configured HBQs */ @@ -985,7 +997,7 @@ struct lpfc_hba { struct dma_pool *lpfc_drb_pool; /* data receive buffer pool */ struct dma_pool *lpfc_nvmet_drb_pool; /* data receive buffer pool */ struct dma_pool *lpfc_hbq_pool; /* SLI3 hbq buffer pool */ - struct dma_pool *txrdy_payload_pool; + struct dma_pool *lpfc_cmd_rsp_buf_pool; struct lpfc_dma_pool lpfc_mbuf_safety_pool; mempool_t *mbox_mem_pool; @@ -1033,8 +1045,6 @@ struct lpfc_hba { struct dentry *debug_hbqinfo; struct dentry *debug_dumpHostSlim; struct dentry *debug_dumpHBASlim; - struct dentry *debug_dumpData; /* BlockGuard BPL */ - struct dentry *debug_dumpDif; /* BlockGuard BPL */ struct dentry *debug_InjErrLBA; /* LBA to inject errors at */ struct dentry *debug_InjErrNPortID; /* NPortID to inject errors at */ struct dentry *debug_InjErrWWPN; /* WWPN to inject errors at */ @@ -1051,6 +1061,7 @@ struct lpfc_hba { #ifdef LPFC_HDWQ_LOCK_STAT struct dentry *debug_lockstat; #endif + struct dentry *debug_ras_log; atomic_t nvmeio_trc_cnt; uint32_t nvmeio_trc_size; uint32_t nvmeio_trc_output_idx; @@ -1205,6 +1216,15 @@ struct lpfc_hba { uint64_t ktime_seg10_min; uint64_t ktime_seg10_max; #endif + + struct hlist_node cpuhp; /* used for cpuhp per hba callback */ + struct timer_list cpuhp_poll_timer; + struct list_head poll_list; /* slowpath eq polling list */ +#define LPFC_POLL_HB 1 /* slowpath heartbeat */ +#define LPFC_POLL_FASTPATH 0 /* called from fastpath */ +#define LPFC_POLL_SLOWPATH 1 /* called from slowpath */ + + char os_host_name[MAXHOSTNAMELEN]; }; static inline struct Scsi_Host * @@ -1295,6 +1315,26 @@ 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. + * @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) +{ + unsigned int cpu_it; + + for_each_cpu_wrap(cpu_it, numa_mask, start) { + if (cpu_online(cpu_it)) + break; + } + + return cpu_it; +} +/** * lpfc_sli4_mod_hba_eq_delay - update EQ delay * @phba: Pointer to HBA context object. * @q: The Event Queue to update. diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index ea62322ffe2b..46f56f30f77e 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -176,7 +176,6 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, int i; int len = 0; char tmp[LPFC_MAX_NVME_INFO_TMP_LEN] = {0}; - unsigned long iflags = 0; if (!(vport->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) { len = scnprintf(buf, PAGE_SIZE, "NVME Disabled\n"); @@ -347,7 +346,6 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, if (strlcat(buf, "\nNVME Initiator Enabled\n", PAGE_SIZE) >= PAGE_SIZE) goto buffer_done; - rcu_read_lock(); scnprintf(tmp, sizeof(tmp), "XRI Dist lpfc%d Total %d IO %d ELS %d\n", phba->brd_no, @@ -355,7 +353,7 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, phba->sli4_hba.io_xri_max, lpfc_sli4_get_els_iocb_cnt(phba)); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto buffer_done; /* Port state is only one of two values for now. */ if (localport->port_id) @@ -371,15 +369,17 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, wwn_to_u64(vport->fc_nodename.u.wwn), localport->port_id, statep); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto buffer_done; + + spin_lock_irq(shost->host_lock); list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) { nrport = NULL; - spin_lock_irqsave(&vport->phba->hbalock, iflags); + spin_lock(&vport->phba->hbalock); rport = lpfc_ndlp_get_nrport(ndlp); if (rport) nrport = rport->remoteport; - spin_unlock_irqrestore(&vport->phba->hbalock, iflags); + spin_unlock(&vport->phba->hbalock); if (!nrport) continue; @@ -398,39 +398,39 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, /* Tab in to show lport ownership. */ if (strlcat(buf, "NVME RPORT ", PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; if (phba->brd_no >= 10) { if (strlcat(buf, " ", PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } scnprintf(tmp, sizeof(tmp), "WWPN x%llx ", nrport->port_name); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; scnprintf(tmp, sizeof(tmp), "WWNN x%llx ", nrport->node_name); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; scnprintf(tmp, sizeof(tmp), "DID x%06x ", nrport->port_id); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; /* An NVME rport can have multiple roles. */ if (nrport->port_role & FC_PORT_ROLE_NVME_INITIATOR) { if (strlcat(buf, "INITIATOR ", PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } if (nrport->port_role & FC_PORT_ROLE_NVME_TARGET) { if (strlcat(buf, "TARGET ", PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } if (nrport->port_role & FC_PORT_ROLE_NVME_DISCOVERY) { if (strlcat(buf, "DISCSRVC ", PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } if (nrport->port_role & ~(FC_PORT_ROLE_NVME_INITIATOR | FC_PORT_ROLE_NVME_TARGET | @@ -438,14 +438,14 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, scnprintf(tmp, sizeof(tmp), "UNKNOWN ROLE x%x", nrport->port_role); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } scnprintf(tmp, sizeof(tmp), "%s\n", statep); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } - rcu_read_unlock(); + spin_unlock_irq(shost->host_lock); if (!lport) goto buffer_done; @@ -505,11 +505,11 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, atomic_read(&lport->cmpl_fcp_err)); strlcat(buf, tmp, PAGE_SIZE); - /* RCU is already unlocked. */ + /* host_lock is already unlocked. */ goto buffer_done; - rcu_unlock_buf_done: - rcu_read_unlock(); + unlock_buf_done: + spin_unlock_irq(shost->host_lock); buffer_done: len = strnlen(buf, PAGE_SIZE); @@ -841,7 +841,8 @@ lpfc_hdw_show(struct device *dev, struct device_attribute *attr, char *buf) lpfc_vpd_t *vp = &phba->vpd; lpfc_jedec_to_ascii(vp->rev.biuRev, hdw); - return scnprintf(buf, PAGE_SIZE, "%s\n", hdw); + return scnprintf(buf, PAGE_SIZE, "%s %08x %08x\n", hdw, + vp->rev.smRev, vp->rev.smFwRev); } /** @@ -1474,8 +1475,9 @@ lpfc_sli4_pdev_status_reg_wait(struct lpfc_hba *phba) int i; msleep(100); - lpfc_readl(phba->sli4_hba.u.if_type2.STATUSregaddr, - &portstat_reg.word0); + if (lpfc_readl(phba->sli4_hba.u.if_type2.STATUSregaddr, + &portstat_reg.word0)) + return -EIO; /* verify if privileged for the request operation */ if (!bf_get(lpfc_sliport_status_rn, &portstat_reg) && @@ -1485,8 +1487,9 @@ lpfc_sli4_pdev_status_reg_wait(struct lpfc_hba *phba) /* wait for the SLI port firmware ready after firmware reset */ for (i = 0; i < LPFC_FW_RESET_MAXIMUM_WAIT_10MS_CNT; i++) { msleep(10); - lpfc_readl(phba->sli4_hba.u.if_type2.STATUSregaddr, - &portstat_reg.word0); + if (lpfc_readl(phba->sli4_hba.u.if_type2.STATUSregaddr, + &portstat_reg.word0)) + continue; if (!bf_get(lpfc_sliport_status_err, &portstat_reg)) continue; if (!bf_get(lpfc_sliport_status_rn, &portstat_reg)) @@ -1641,7 +1644,7 @@ lpfc_set_trunking(struct lpfc_hba *phba, char *buff_out) { LPFC_MBOXQ_t *mbox = NULL; unsigned long val = 0; - char *pval = 0; + char *pval = NULL; int rc = 0; if (!strncmp("enable", buff_out, @@ -3532,6 +3535,31 @@ LPFC_ATTR_R(enable_rrq, 2, 0, 2, LPFC_ATTR_R(suppress_link_up, LPFC_INITIALIZE_LINK, LPFC_INITIALIZE_LINK, LPFC_DELAY_INIT_LINK_INDEFINITELY, "Suppress Link Up at initialization"); + +static ssize_t +lpfc_pls_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(dev); + struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; + + return scnprintf(buf, PAGE_SIZE, "%d\n", + phba->sli4_hba.pc_sli4_params.pls); +} +static DEVICE_ATTR(pls, 0444, + lpfc_pls_show, NULL); + +static ssize_t +lpfc_pt_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(dev); + struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; + + return scnprintf(buf, PAGE_SIZE, "%d\n", + (phba->hba_flag & HBA_PERSISTENT_TOPO) ? 1 : 0); +} +static DEVICE_ATTR(pt, 0444, + lpfc_pt_show, NULL); + /* # lpfc_cnt: Number of IOCBs allocated for ELS, CT, and ABTS # 1 - (1024) @@ -3579,9 +3607,6 @@ lpfc_txcmplq_hw_show(struct device *dev, struct device_attribute *attr, static DEVICE_ATTR(txcmplq_hw, S_IRUGO, lpfc_txcmplq_hw_show, NULL); -LPFC_ATTR_R(iocb_cnt, 2, 1, 5, - "Number of IOCBs alloc for ELS, CT, and ABTS: 1k to 5k IOCBs"); - /* # lpfc_nodev_tmo: If set, it will hold all I/O errors on devices that disappear # until the timer expires. Value range is [0,255]. Default value is 30. @@ -3682,8 +3707,8 @@ lpfc_update_rport_devloss_tmo(struct lpfc_vport *vport) if (rport) remoteport = rport->remoteport; spin_unlock(&vport->phba->hbalock); - if (remoteport) - nvme_fc_set_remoteport_devloss(rport->remoteport, + if (rport && remoteport) + nvme_fc_set_remoteport_devloss(remoteport, vport->cfg_devloss_tmo); #endif } @@ -4095,8 +4120,16 @@ lpfc_topology_store(struct device *dev, struct device_attribute *attr, val); return -EINVAL; } - if ((phba->pcidev->device == PCI_DEVICE_ID_LANCER_G6_FC || - phba->pcidev->device == PCI_DEVICE_ID_LANCER_G7_FC) && + /* + * The 'topology' is not a configurable parameter if : + * - persistent topology enabled + * - G7/G6 with no private loop support + */ + + if ((phba->hba_flag & HBA_PERSISTENT_TOPO || + (!phba->sli4_hba.pc_sli4_params.pls && + (phba->pcidev->device == PCI_DEVICE_ID_LANCER_G6_FC || + phba->pcidev->device == PCI_DEVICE_ID_LANCER_G7_FC))) && val == 4) { lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT, "3114 Loop mode not supported\n"); @@ -5297,7 +5330,7 @@ lpfc_fcp_cpu_map_show(struct device *dev, struct device_attribute *attr, len += scnprintf(buf + len, PAGE_SIZE - len, "CPU %02d not present\n", phba->sli4_hba.curr_disp_cpu); - else if (cpup->irq == LPFC_VECTOR_MAP_EMPTY) { + else if (cpup->eq == LPFC_VECTOR_MAP_EMPTY) { if (cpup->hdwq == LPFC_VECTOR_MAP_EMPTY) len += scnprintf( buf + len, PAGE_SIZE - len, @@ -5310,10 +5343,10 @@ lpfc_fcp_cpu_map_show(struct device *dev, struct device_attribute *attr, else len += scnprintf( buf + len, PAGE_SIZE - len, - "CPU %02d EQ %04d hdwq %04d " + "CPU %02d EQ None hdwq %04d " "physid %d coreid %d ht %d ua %d\n", phba->sli4_hba.curr_disp_cpu, - cpup->eq, cpup->hdwq, cpup->phys_id, + cpup->hdwq, cpup->phys_id, cpup->core_id, (cpup->flag & LPFC_CPU_MAP_HYPER), (cpup->flag & LPFC_CPU_MAP_UNASSIGN)); @@ -5328,7 +5361,7 @@ lpfc_fcp_cpu_map_show(struct device *dev, struct device_attribute *attr, cpup->core_id, (cpup->flag & LPFC_CPU_MAP_HYPER), (cpup->flag & LPFC_CPU_MAP_UNASSIGN), - cpup->irq); + lpfc_get_irq(cpup->eq)); else len += scnprintf( buf + len, PAGE_SIZE - len, @@ -5339,7 +5372,7 @@ lpfc_fcp_cpu_map_show(struct device *dev, struct device_attribute *attr, cpup->core_id, (cpup->flag & LPFC_CPU_MAP_HYPER), (cpup->flag & LPFC_CPU_MAP_UNASSIGN), - cpup->irq); + lpfc_get_irq(cpup->eq)); } phba->sli4_hba.curr_disp_cpu++; @@ -5467,15 +5500,12 @@ LPFC_ATTR_RW(nvmet_fb_size, 0, 0, 65536, * lpfc_nvme_enable_fb: Enable NVME first burst on I and T functions. * For the Initiator (I), enabling this parameter means that an NVMET * PRLI response with FBA enabled and an FB_SIZE set to a nonzero value will be - * processed by the initiator for subsequent NVME FCP IO. For the target - * function (T), enabling this parameter qualifies the lpfc_nvmet_fb_size - * driver parameter as the target function's first burst size returned to the - * initiator in the target's NVME PRLI response. Parameter supported on physical - * port only - no NPIV support. + * processed by the initiator for subsequent NVME FCP IO. + * Currently, this feature is not supported on the NVME target * Value range is [0,1]. Default value is 0 (disabled). */ LPFC_ATTR_RW(nvme_enable_fb, 0, 0, 1, - "Enable First Burst feature on I and T functions."); + "Enable First Burst feature for NVME Initiator."); /* # lpfc_max_scsicmpl_time: Use scsi command completion time to control I/O queue @@ -5709,6 +5739,19 @@ LPFC_ATTR_RW(nvme_embed_cmd, 1, 0, 2, "Embed NVME Command in WQE"); /* + * lpfc_fcp_mq_threshold: Set the maximum number of Hardware Queues + * the driver will advertise it supports to the SCSI layer. + * + * 0 = Set nr_hw_queues by the number of CPUs or HW queues. + * 1,256 = Manually specify nr_hw_queue value to be advertised, + * + * Value range is [0,256]. Default value is 8. + */ +LPFC_ATTR_R(fcp_mq_threshold, LPFC_FCP_MQ_THRESHOLD_DEF, + LPFC_FCP_MQ_THRESHOLD_MIN, LPFC_FCP_MQ_THRESHOLD_MAX, + "Set the number of SCSI Queues advertised"); + +/* * lpfc_hdw_queue: Set the number of Hardware Queues the driver * will advertise it supports to the NVME and SCSI layers. This also * will map to the number of CQ/WQ pairs the driver will create. @@ -5718,30 +5761,130 @@ LPFC_ATTR_RW(nvme_embed_cmd, 1, 0, 2, * A hardware IO queue maps (qidx) to a specific driver CQ/WQ. * * 0 = Configure the number of hdw queues to the number of active CPUs. - * 1,128 = Manually specify how many hdw queues to use. + * 1,256 = Manually specify how many hdw queues to use. * - * Value range is [0,128]. Default value is 0. + * Value range is [0,256]. Default value is 0. */ LPFC_ATTR_R(hdw_queue, LPFC_HBA_HDWQ_DEF, 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) + /* 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; +#else + phba->cfg_irq_numa = 0; +#endif +} + /* * lpfc_irq_chann: Set the number of IRQ vectors that are available * for Hardware Queues to utilize. This also will map to the number * of EQ / MSI-X vectors the driver will create. This should never be * more than the number of Hardware Queues * - * 0 = Configure number of IRQ Channels to the number of active CPUs. - * 1,128 = Manually specify how many IRQ Channels to use. + * 0 = Configure number of IRQ Channels to: + * if AMD architecture, number of CPUs on HBA's NUMA node + * otherwise, number of active CPUs. + * [1,256] = Manually specify how many IRQ Channels to use. * - * Value range is [0,128]. Default value is 0. + * Value range is [0,256]. Default value is [0]. */ -LPFC_ATTR_R(irq_chann, - LPFC_HBA_HDWQ_DEF, - LPFC_HBA_HDWQ_MIN, LPFC_HBA_HDWQ_MAX, - "Set the number of I/O IRQ Channels"); +static uint lpfc_irq_chann = LPFC_IRQ_CHANN_DEF; +module_param(lpfc_irq_chann, uint, 0444); +MODULE_PARM_DESC(lpfc_irq_chann, "Set number of interrupt vectors to allocate"); + +/* lpfc_irq_chann_init - Set the hba irq_chann initial value + * @phba: lpfc_hba pointer. + * @val: contains the initial value + * + * Description: + * Validates the initial value is within range and assigns it to the + * adapter. If not in range, an error message is posted and the + * default value is assigned. + * + * Returns: + * zero if value is in range and is set + * -EINVAL if value was out of range + **/ +static int +lpfc_irq_chann_init(struct lpfc_hba *phba, uint32_t val) +{ + const struct cpumask *numa_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; + return 0; + } + + /* Check if default setting was passed */ + if (val == LPFC_IRQ_CHANN_DEF) + lpfc_assign_default_irq_numa(phba); + + if (phba->cfg_irq_numa) { + numa_mask = &phba->sli4_hba.numa_mask; + + if (cpumask_empty(numa_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; + } else { + phba->cfg_irq_chann = cpumask_weight(numa_mask); + lpfc_printf_log(phba, KERN_INFO, LOG_INIT, + "8543 lpfc_irq_chann set to %u " + "(numa)\n", phba->cfg_irq_chann); + } + } else { + if (val > LPFC_IRQ_CHANN_MAX) { + lpfc_printf_log(phba, KERN_INFO, LOG_INIT, + "8545 lpfc_irq_chann attribute cannot " + "be set to %u, allowed range is " + "[%u,%u]\n", + val, + LPFC_IRQ_CHANN_MIN, + LPFC_IRQ_CHANN_MAX); + phba->cfg_irq_chann = LPFC_IRQ_CHANN_MIN; + return -EINVAL; + } + phba->cfg_irq_chann = val; + } + + return 0; +} + +/** + * lpfc_irq_chann_show - Display value of irq_chann + * @dev: class converted to a Scsi_host structure. + * @attr: device attribute, not used. + * @buf: on return contains a string with the list sizes + * + * Returns: size of formatted string. + **/ +static ssize_t +lpfc_irq_chann_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct Scsi_Host *shost = class_to_shost(dev); + struct lpfc_vport *vport = (struct lpfc_vport *)shost->hostdata; + struct lpfc_hba *phba = vport->phba; + + return scnprintf(buf, PAGE_SIZE, "%u\n", phba->cfg_irq_chann); +} + +static DEVICE_ATTR_RO(lpfc_irq_chann); /* # lpfc_enable_hba_reset: Allow or prevent HBA resets to the hardware. @@ -5914,7 +6057,7 @@ lpfc_sg_seg_cnt_init(struct lpfc_hba *phba, int val) * 1 = MDS Diagnostics enabled * Value range is [0,1]. Default value is 0. */ -LPFC_ATTR_R(enable_mds_diags, 0, 0, 1, "Enable MDS Diagnostics"); +LPFC_ATTR_RW(enable_mds_diags, 0, 0, 1, "Enable MDS Diagnostics"); /* * lpfc_ras_fwlog_buffsize: Firmware logging host buffer size @@ -5922,7 +6065,53 @@ LPFC_ATTR_R(enable_mds_diags, 0, 0, 1, "Enable MDS Diagnostics"); * [1-4] = Multiple of 1/4th Mb of host memory for FW logging * Value range [0..4]. Default value is 0 */ -LPFC_ATTR_RW(ras_fwlog_buffsize, 0, 0, 4, "Host memory for FW logging"); +LPFC_ATTR(ras_fwlog_buffsize, 0, 0, 4, "Host memory for FW logging"); +lpfc_param_show(ras_fwlog_buffsize); + +static ssize_t +lpfc_ras_fwlog_buffsize_set(struct lpfc_hba *phba, uint val) +{ + int ret = 0; + enum ras_state state; + + if (!lpfc_rangecheck(val, 0, 4)) + return -EINVAL; + + if (phba->cfg_ras_fwlog_buffsize == val) + return 0; + + if (phba->cfg_ras_fwlog_func != PCI_FUNC(phba->pcidev->devfn)) + return -EINVAL; + + spin_lock_irq(&phba->hbalock); + state = phba->ras_fwlog.state; + spin_unlock_irq(&phba->hbalock); + + if (state == REG_INPROGRESS) { + lpfc_printf_log(phba, KERN_ERR, LOG_SLI, "6147 RAS Logging " + "registration is in progress\n"); + return -EBUSY; + } + + /* For disable logging: stop the logs and free the DMA. + * For ras_fwlog_buffsize size change we still need to free and + * reallocate the DMA in lpfc_sli4_ras_fwlog_init. + */ + phba->cfg_ras_fwlog_buffsize = val; + if (state == ACTIVE) { + lpfc_ras_stop_fwlog(phba); + lpfc_sli4_ras_dma_free(phba); + } + + lpfc_sli4_ras_init(phba); + if (phba->ras_fwlog.ras_enabled) + ret = lpfc_sli4_ras_fwlog_init(phba, phba->cfg_ras_fwlog_level, + LPFC_RAS_ENABLE_LOGGING); + return ret; +} + +lpfc_param_store(ras_fwlog_buffsize); +static DEVICE_ATTR_RW(lpfc_ras_fwlog_buffsize); /* * lpfc_ras_fwlog_level: Firmware logging verbosity level @@ -6030,6 +6219,7 @@ struct device_attribute *lpfc_hba_attrs[] = { &dev_attr_lpfc_cq_poll_threshold, &dev_attr_lpfc_cq_max_proc_limit, &dev_attr_lpfc_fcp_cpu_map, + &dev_attr_lpfc_fcp_mq_threshold, &dev_attr_lpfc_hdw_queue, &dev_attr_lpfc_irq_chann, &dev_attr_lpfc_suppress_rsp, @@ -6059,8 +6249,9 @@ struct device_attribute *lpfc_hba_attrs[] = { &dev_attr_lpfc_sriov_nr_virtfn, &dev_attr_lpfc_req_fw_upgrade, &dev_attr_lpfc_suppress_link_up, - &dev_attr_lpfc_iocb_cnt, &dev_attr_iocb_hw, + &dev_attr_pls, + &dev_attr_pt, &dev_attr_txq_hw, &dev_attr_txcmplq_hw, &dev_attr_lpfc_fips_level, @@ -6845,10 +7036,31 @@ lpfc_get_starget_port_name(struct scsi_target *starget) static void lpfc_set_rport_loss_tmo(struct fc_rport *rport, uint32_t timeout) { + struct lpfc_rport_data *rdata = rport->dd_data; + struct lpfc_nodelist *ndlp = rdata->pnode; +#if (IS_ENABLED(CONFIG_NVME_FC)) + struct lpfc_nvme_rport *nrport = NULL; +#endif + if (timeout) rport->dev_loss_tmo = timeout; else rport->dev_loss_tmo = 1; + + if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) { + dev_info(&rport->dev, "Cannot find remote node to " + "set rport dev loss tmo, port_id x%x\n", + rport->port_id); + return; + } + +#if (IS_ENABLED(CONFIG_NVME_FC)) + nrport = lpfc_ndlp_get_nrport(ndlp); + + if (nrport && nrport->remoteport) + nvme_fc_set_remoteport_devloss(nrport->remoteport, + rport->dev_loss_tmo); +#endif } /** @@ -7045,12 +7257,39 @@ struct fc_function_template lpfc_vport_transport_functions = { }; /** + * lpfc_get_hba_function_mode - Used to determine the HBA function in FCoE + * Mode + * @phba: lpfc_hba pointer. + **/ +static void +lpfc_get_hba_function_mode(struct lpfc_hba *phba) +{ + /* If the adapter supports FCoE mode */ + switch (phba->pcidev->device) { + case PCI_DEVICE_ID_SKYHAWK: + case PCI_DEVICE_ID_SKYHAWK_VF: + case PCI_DEVICE_ID_LANCER_FCOE: + case PCI_DEVICE_ID_LANCER_FCOE_VF: + case PCI_DEVICE_ID_ZEPHYR_DCSP: + case PCI_DEVICE_ID_HORNET: + case PCI_DEVICE_ID_TIGERSHARK: + case PCI_DEVICE_ID_TOMCAT: + phba->hba_flag |= HBA_FCOE_MODE; + break; + default: + /* for others, clear the flag */ + phba->hba_flag &= ~HBA_FCOE_MODE; + } +} + +/** * lpfc_get_cfgparam - Used during probe_one to init the adapter structure * @phba: lpfc_hba pointer. **/ void lpfc_get_cfgparam(struct lpfc_hba *phba) { + lpfc_hba_log_verbose_init(phba, lpfc_log_verbose); lpfc_fcp_io_sched_init(phba, lpfc_fcp_io_sched); lpfc_ns_query_init(phba, lpfc_ns_query); lpfc_fcp2_no_tgt_reset_init(phba, lpfc_fcp2_no_tgt_reset); @@ -7100,8 +7339,18 @@ lpfc_get_cfgparam(struct lpfc_hba *phba) else phba->cfg_poll = lpfc_poll; - if (phba->cfg_enable_bg) + /* Get the function mode */ + lpfc_get_hba_function_mode(phba); + + /* BlockGuard allowed for FC only. */ + if (phba->cfg_enable_bg && phba->hba_flag & HBA_FCOE_MODE) { + lpfc_printf_log(phba, KERN_INFO, LOG_INIT, + "0581 BlockGuard feature not supported\n"); + /* If set, clear the BlockGuard support param */ + phba->cfg_enable_bg = 0; + } else if (phba->cfg_enable_bg) { phba->sli3_options |= LPFC_SLI3_BG_ENABLED; + } lpfc_suppress_rsp_init(phba, lpfc_suppress_rsp); @@ -7112,6 +7361,7 @@ lpfc_get_cfgparam(struct lpfc_hba *phba) /* Initialize first burst. Target vs Initiator are different. */ lpfc_nvme_enable_fb_init(phba, lpfc_nvme_enable_fb); lpfc_nvmet_fb_size_init(phba, lpfc_nvmet_fb_size); + lpfc_fcp_mq_threshold_init(phba, lpfc_fcp_mq_threshold); lpfc_hdw_queue_init(phba, lpfc_hdw_queue); lpfc_irq_chann_init(phba, lpfc_irq_chann); lpfc_enable_bbcr_init(phba, lpfc_enable_bbcr); @@ -7146,12 +7396,10 @@ lpfc_get_cfgparam(struct lpfc_hba *phba) phba->cfg_soft_wwpn = 0L; lpfc_sg_seg_cnt_init(phba, lpfc_sg_seg_cnt); lpfc_hba_queue_depth_init(phba, lpfc_hba_queue_depth); - lpfc_hba_log_verbose_init(phba, lpfc_log_verbose); lpfc_aer_support_init(phba, lpfc_aer_support); lpfc_sriov_nr_virtfn_init(phba, lpfc_sriov_nr_virtfn); lpfc_request_firmware_upgrade_init(phba, lpfc_req_fw_upgrade); lpfc_suppress_link_up_init(phba, lpfc_suppress_link_up); - lpfc_iocb_cnt_init(phba, lpfc_iocb_cnt); lpfc_delay_discovery_init(phba, lpfc_delay_discovery); lpfc_sli_mode_init(phba, lpfc_sli_mode); phba->cfg_enable_dss = 1; @@ -7160,16 +7408,6 @@ lpfc_get_cfgparam(struct lpfc_hba *phba) lpfc_ras_fwlog_level_init(phba, lpfc_ras_fwlog_level); lpfc_ras_fwlog_func_init(phba, lpfc_ras_fwlog_func); - - /* If the NVME FC4 type is enabled, scale the sg_seg_cnt to - * accommodate 512K and 1M IOs in a single nvme buf and supply - * enough NVME LS iocb buffers for larger connectivity counts. - */ - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - phba->cfg_sg_seg_cnt = LPFC_MAX_NVME_SEG_CNT; - phba->cfg_iocb_cnt = 5; - } - return; } @@ -7207,11 +7445,11 @@ lpfc_nvme_mod_param_dep(struct lpfc_hba *phba) } if (!phba->cfg_nvmet_mrq) - phba->cfg_nvmet_mrq = phba->cfg_irq_chann; + phba->cfg_nvmet_mrq = phba->cfg_hdw_queue; /* Adjust lpfc_nvmet_mrq to avoid running out of WQE slots */ - if (phba->cfg_nvmet_mrq > phba->cfg_irq_chann) { - phba->cfg_nvmet_mrq = phba->cfg_irq_chann; + if (phba->cfg_nvmet_mrq > phba->cfg_hdw_queue) { + phba->cfg_nvmet_mrq = phba->cfg_hdw_queue; lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC, "6018 Adjust lpfc_nvmet_mrq to %d\n", phba->cfg_nvmet_mrq); diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index b7216d694bff..0ea03ae93d91 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -1040,7 +1040,7 @@ lpfc_bsg_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, if (!dmabuf) { lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC, "2616 No dmabuf " - "found for iocbq 0x%p\n", + "found for iocbq x%px\n", iocbq); kfree(evt_dat->data); kfree(evt_dat); @@ -1276,9 +1276,7 @@ lpfc_bsg_hba_set_event(struct bsg_job *job) return 0; /* call job done later */ job_error: - if (dd_data != NULL) - kfree(dd_data); - + kfree(dd_data); job->dd_data = NULL; return rc; } @@ -1571,7 +1569,6 @@ lpfc_issue_ct_rsp(struct lpfc_hba *phba, struct bsg_job *job, uint32_t tag, "2722 Xmit CT response on exchange x%x Data: x%x x%x x%x\n", icmd->ulpContext, icmd->ulpIoTag, tag, phba->link_state); - ctiocb->iocb_cmpl = NULL; ctiocb->iocb_flag |= LPFC_IO_LIBDFC; ctiocb->vport = phba->pport; ctiocb->context1 = dd_data; @@ -4492,12 +4489,6 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job, phba->mbox_ext_buf_ctx.seqNum++; nemb_tp = phba->mbox_ext_buf_ctx.nembType; - dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL); - if (!dd_data) { - rc = -ENOMEM; - goto job_error; - } - pbuf = (uint8_t *)dmabuf->virt; size = job->request_payload.payload_len; sg_copy_to_buffer(job->request_payload.sg_list, @@ -4534,6 +4525,13 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job, "2968 SLI_CONFIG ext-buffer wr all %d " "ebuffers received\n", phba->mbox_ext_buf_ctx.numBuf); + + dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL); + if (!dd_data) { + rc = -ENOMEM; + goto job_error; + } + /* mailbox command structure for base driver */ pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); if (!pmboxq) { @@ -4582,6 +4580,8 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job, return SLI_CONFIG_HANDLED; job_error: + if (pmboxq) + mempool_free(pmboxq, phba->mbox_mem_pool); lpfc_bsg_dma_page_free(phba, dmabuf); kfree(dd_data); @@ -5438,10 +5438,12 @@ lpfc_bsg_get_ras_config(struct bsg_job *job) bsg_reply->reply_data.vendor_reply.vendor_rsp; /* Current logging state */ - if (ras_fwlog->ras_active == true) + spin_lock_irq(&phba->hbalock); + if (ras_fwlog->state == ACTIVE) ras_reply->state = LPFC_RASLOG_STATE_RUNNING; else ras_reply->state = LPFC_RASLOG_STATE_STOPPED; + spin_unlock_irq(&phba->hbalock); ras_reply->log_level = phba->ras_fwlog.fw_loglevel; ras_reply->log_buff_sz = phba->cfg_ras_fwlog_buffsize; @@ -5451,7 +5453,9 @@ ras_job_error: bsg_reply->result = rc; /* complete the job back to userspace */ - bsg_job_done(job, bsg_reply->result, bsg_reply->reply_payload_rcv_len); + if (!rc) + bsg_job_done(job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); return rc; } @@ -5496,10 +5500,13 @@ lpfc_bsg_set_ras_config(struct bsg_job *job) if (action == LPFC_RASACTION_STOP_LOGGING) { /* Check if already disabled */ - if (ras_fwlog->ras_active == false) { + spin_lock_irq(&phba->hbalock); + if (ras_fwlog->state != ACTIVE) { + spin_unlock_irq(&phba->hbalock); rc = -ESRCH; goto ras_job_error; } + spin_unlock_irq(&phba->hbalock); /* Disable logging */ lpfc_ras_stop_fwlog(phba); @@ -5510,8 +5517,10 @@ lpfc_bsg_set_ras_config(struct bsg_job *job) * FW-logging with new log-level. Return status * "Logging already Running" to caller. **/ - if (ras_fwlog->ras_active) + spin_lock_irq(&phba->hbalock); + if (ras_fwlog->state != INACTIVE) action_status = -EINPROGRESS; + spin_unlock_irq(&phba->hbalock); /* Enable logging */ rc = lpfc_sli4_ras_fwlog_init(phba, log_level, @@ -5530,8 +5539,9 @@ ras_job_error: bsg_reply->result = rc; /* complete the job back to userspace */ - bsg_job_done(job, bsg_reply->result, - bsg_reply->reply_payload_rcv_len); + if (!rc) + bsg_job_done(job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); return rc; } @@ -5591,7 +5601,9 @@ ras_job_error: bsg_reply->result = rc; /* complete the job back to userspace */ - bsg_job_done(job, bsg_reply->result, bsg_reply->reply_payload_rcv_len); + if (!rc) + bsg_job_done(job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); return rc; } @@ -5624,10 +5636,13 @@ lpfc_bsg_get_ras_fwlog(struct bsg_job *job) goto ras_job_error; /* Logging to be stopped before reading */ - if (ras_fwlog->ras_active == true) { + spin_lock_irq(&phba->hbalock); + if (ras_fwlog->state == ACTIVE) { + spin_unlock_irq(&phba->hbalock); rc = -EINPROGRESS; goto ras_job_error; } + spin_unlock_irq(&phba->hbalock); if (job->request_len < sizeof(struct fc_bsg_request) + @@ -5673,7 +5688,9 @@ lpfc_bsg_get_ras_fwlog(struct bsg_job *job) ras_job_error: bsg_reply->result = rc; - bsg_job_done(job, bsg_reply->result, bsg_reply->reply_payload_rcv_len); + if (!rc) + bsg_job_done(job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); return rc; } @@ -5744,8 +5761,9 @@ lpfc_get_trunk_info(struct bsg_job *job) phba->sli4_hba.link_state.logical_speed / 1000; job_error: bsg_reply->result = rc; - bsg_job_done(job, bsg_reply->result, - bsg_reply->reply_payload_rcv_len); + if (!rc) + bsg_job_done(job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); return rc; } diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index 68e9f96242d3..25d3dd39bc05 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -180,7 +180,7 @@ int lpfc_issue_gidft(struct lpfc_vport *vport); int lpfc_get_gidft_type(struct lpfc_vport *vport, struct lpfc_iocbq *iocbq); int lpfc_ns_cmd(struct lpfc_vport *, int, uint8_t, uint32_t); int lpfc_fdmi_cmd(struct lpfc_vport *, struct lpfc_nodelist *, int, uint32_t); -void lpfc_fdmi_num_disc_check(struct lpfc_vport *); +void lpfc_fdmi_change_check(struct lpfc_vport *vport); void lpfc_delayed_disc_tmo(struct timer_list *); void lpfc_delayed_disc_timeout_handler(struct lpfc_vport *); @@ -215,6 +215,12 @@ irqreturn_t lpfc_sli_fp_intr_handler(int, void *); irqreturn_t lpfc_sli4_intr_handler(int, void *); irqreturn_t lpfc_sli4_hba_intr_handler(int, void *); +void lpfc_sli4_cleanup_poll_list(struct lpfc_hba *phba); +int lpfc_sli4_poll_eq(struct lpfc_queue *q, uint8_t path); +void lpfc_sli4_poll_hbtimer(struct timer_list *t); +void lpfc_sli4_start_polling(struct lpfc_queue *q); +void lpfc_sli4_stop_polling(struct lpfc_queue *q); + void lpfc_read_rev(struct lpfc_hba *, LPFC_MBOXQ_t *); void lpfc_sli4_swap_str(struct lpfc_hba *, LPFC_MBOXQ_t *); void lpfc_config_ring(struct lpfc_hba *, int, LPFC_MBOXQ_t *); @@ -326,7 +332,7 @@ void lpfc_sli_bemem_bcopy(void *, void *, uint32_t); void lpfc_sli_abort_iocb_ring(struct lpfc_hba *, struct lpfc_sli_ring *); void lpfc_sli_abort_fcp_rings(struct lpfc_hba *phba); void lpfc_sli_hba_iocb_abort(struct lpfc_hba *); -void lpfc_sli_flush_fcp_rings(struct lpfc_hba *); +void lpfc_sli_flush_io_rings(struct lpfc_hba *phba); int lpfc_sli_ringpostbuf_put(struct lpfc_hba *, struct lpfc_sli_ring *, struct lpfc_dmabuf *); struct lpfc_dmabuf *lpfc_sli_ringpostbuf_get(struct lpfc_hba *, @@ -433,16 +439,6 @@ int lpfc_sli4_get_allocated_extnts(struct lpfc_hba *, uint16_t, int lpfc_sli4_get_avail_extnt_rsrc(struct lpfc_hba *, uint16_t, uint16_t *, uint16_t *); -/* externs BlockGuard */ -extern char *_dump_buf_data; -extern unsigned long _dump_buf_data_order; -extern char *_dump_buf_dif; -extern unsigned long _dump_buf_dif_order; -extern spinlock_t _dump_buf_lock; -extern int _dump_buf_done; -extern spinlock_t pgcnt_lock; -extern unsigned int pgcnt; - /* Interface exported by fabric iocb scheduler */ void lpfc_fabric_abort_nport(struct lpfc_nodelist *); void lpfc_fabric_abort_hba(struct lpfc_hba *); @@ -595,6 +591,8 @@ void lpfc_release_io_buf(struct lpfc_hba *phba, struct lpfc_io_buf *ncmd, struct lpfc_sli4_hdw_queue *qp); void lpfc_nvme_cmd_template(void); void lpfc_nvmet_cmd_template(void); +void lpfc_nvme_cancel_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn); +void lpfc_nvme_prep_abort_wqe(struct lpfc_iocbq *pwqeq, u16 xritag, u8 opt); extern int lpfc_enable_nvmet_cnt; extern unsigned long long lpfc_enable_nvmet[]; extern int lpfc_no_hba_reset_cnt; diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index ec72c39997d2..58b35a1442c1 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -462,6 +462,7 @@ 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); @@ -480,10 +481,20 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type) lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, "0238 Process x%06x NameServer Rsp " - "Data: x%x x%x x%x x%x\n", Did, + "Data: x%x x%x x%x x%x x%x\n", Did, ndlp->nlp_flag, ndlp->nlp_fc4_type, - vport->fc_flag, + ndlp->nlp_state, vport->fc_flag, vport->fc_rscn_id_cnt); + + /* if ndlp needs to be discovered and prior + * state of ndlp hit devloss, change state to + * allow rediscovery. + */ + if (ndlp->nlp_flag & NLP_NPR_2B_DISC && + ndlp->nlp_state == NLP_STE_UNUSED_NODE) { + lpfc_nlp_set_state(vport, ndlp, + NLP_STE_NPR_NODE); + } } else { lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_CT, "Skip1 GID_FTrsp: did:x%x flg:x%x cnt:%d", @@ -491,9 +502,9 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type) lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, "0239 Skip x%06x NameServer Rsp " - "Data: x%x x%x\n", Did, - vport->fc_flag, - vport->fc_rscn_id_cnt); + "Data: x%x x%x %p\n", + Did, vport->fc_flag, + vport->fc_rscn_id_cnt, ndlp); } } else { if (!(vport->fc_flag & FC_RSCN_MODE) || @@ -751,9 +762,13 @@ lpfc_cmpl_ct_cmd_gid_ft(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, if (CTrsp->CommandResponse.bits.CmdRsp == cpu_to_be16(SLI_CT_RESPONSE_FS_ACC)) { lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, - "0208 NameServer Rsp Data: x%x x%x\n", + "0208 NameServer Rsp Data: x%x x%x " + "x%x x%x sz x%x\n", vport->fc_flag, - CTreq->un.gid.Fc4Type); + CTreq->un.gid.Fc4Type, + vport->num_disc_nodes, + vport->gidft_inp, + irsp->un.genreq64.bdl.bdeSize); lpfc_ns_rsp(vport, outp, @@ -814,6 +829,11 @@ lpfc_cmpl_ct_cmd_gid_ft(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } vport->gidft_inp--; } + + lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, + "4216 GID_FT cmpl inp %d disc %d\n", + vport->gidft_inp, vport->num_disc_nodes); + /* Link up / RSCN discovery */ if ((vport->num_disc_nodes == 0) && (vport->gidft_inp == 0)) { @@ -943,9 +963,13 @@ lpfc_cmpl_ct_cmd_gid_pt(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, if (CTrsp->CommandResponse.bits.CmdRsp == cpu_to_be16(SLI_CT_RESPONSE_FS_ACC)) { lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, - "4105 NameServer Rsp Data: x%x x%x\n", + "4105 NameServer Rsp Data: x%x x%x " + "x%x x%x sz x%x\n", vport->fc_flag, - CTreq->un.gid.Fc4Type); + CTreq->un.gid.Fc4Type, + vport->num_disc_nodes, + vport->gidft_inp, + irsp->un.genreq64.bdl.bdeSize); lpfc_ns_rsp(vport, outp, @@ -1007,6 +1031,11 @@ lpfc_cmpl_ct_cmd_gid_pt(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } vport->gidft_inp--; } + + lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, + "6450 GID_PT cmpl inp %d disc %d\n", + vport->gidft_inp, vport->num_disc_nodes); + /* Link up / RSCN discovery */ if ((vport->num_disc_nodes == 0) && (vport->gidft_inp == 0)) { @@ -1141,6 +1170,11 @@ out: /* Link up / RSCN discovery */ if (vport->num_disc_nodes) vport->num_disc_nodes--; + + lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, + "6451 GFF_ID cmpl inp %d disc %d\n", + vport->gidft_inp, vport->num_disc_nodes); + if (vport->num_disc_nodes == 0) { /* * The driver has cycled through all Nports in the RSCN payload. @@ -1209,14 +1243,34 @@ lpfc_cmpl_ct_cmd_gft_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, if (fc4_data_1 & LPFC_FC4_TYPE_BITMASK) ndlp->nlp_fc4_type |= NLP_FC4_NVME; lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, - "3064 Setting ndlp %p, DID x%06x with " - "FC4 x%08x, Data: x%08x x%08x\n", + "3064 Setting ndlp x%px, DID x%06x " + "with FC4 x%08x, Data: x%08x x%08x " + "%d\n", ndlp, did, ndlp->nlp_fc4_type, - FC_TYPE_FCP, FC_TYPE_NVME); - ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE; - - lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE); - lpfc_issue_els_prli(vport, ndlp, 0); + FC_TYPE_FCP, FC_TYPE_NVME, + ndlp->nlp_state); + + if (ndlp->nlp_state == NLP_STE_REG_LOGIN_ISSUE && + ndlp->nlp_fc4_type) { + ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE; + + lpfc_nlp_set_state(vport, ndlp, + NLP_STE_PRLI_ISSUE); + lpfc_issue_els_prli(vport, ndlp, 0); + } else if (!ndlp->nlp_fc4_type) { + /* If fc4 type is still unknown, then LOGO */ + lpfc_printf_vlog(vport, KERN_INFO, + LOG_DISCOVERY, + "6443 Sending LOGO ndlp x%px," + "DID x%06x with fc4_type: " + "x%08x, state: %d\n", + ndlp, did, ndlp->nlp_fc4_type, + ndlp->nlp_state); + lpfc_issue_els_logo(vport, ndlp, 0); + ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE; + lpfc_nlp_set_state(vport, ndlp, + NLP_STE_NPR_NODE); + } } } else lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY, @@ -1439,33 +1493,35 @@ int lpfc_vport_symbolic_node_name(struct lpfc_vport *vport, char *symbol, size_t size) { - char fwrev[FW_REV_STR_SIZE]; - int n; + char fwrev[FW_REV_STR_SIZE] = {0}; + char tmp[MAXHOSTNAMELEN] = {0}; - lpfc_decode_firmware_rev(vport->phba, fwrev, 0); + memset(symbol, 0, size); - n = scnprintf(symbol, size, "Emulex %s", vport->phba->ModelName); - if (size < n) - return n; + scnprintf(tmp, sizeof(tmp), "Emulex %s", vport->phba->ModelName); + if (strlcat(symbol, tmp, size) >= size) + goto buffer_done; - n += scnprintf(symbol + n, size - n, " FV%s", fwrev); - if (size < n) - return n; + lpfc_decode_firmware_rev(vport->phba, fwrev, 0); + scnprintf(tmp, sizeof(tmp), " FV%s", fwrev); + if (strlcat(symbol, tmp, size) >= size) + goto buffer_done; - n += scnprintf(symbol + n, size - n, " DV%s.", - lpfc_release_version); - if (size < n) - return n; + scnprintf(tmp, sizeof(tmp), " DV%s", lpfc_release_version); + if (strlcat(symbol, tmp, size) >= size) + goto buffer_done; - n += scnprintf(symbol + n, size - n, " HN:%s.", - init_utsname()->nodename); - if (size < n) - return n; + scnprintf(tmp, sizeof(tmp), " HN:%s", vport->phba->os_host_name); + if (strlcat(symbol, tmp, size) >= size) + goto buffer_done; /* Note :- OS name is "Linux" */ - n += scnprintf(symbol + n, size - n, " OS:%s", - init_utsname()->sysname); - return n; + scnprintf(tmp, sizeof(tmp), " OS:%s", init_utsname()->sysname); + strlcat(symbol, tmp, size); + +buffer_done: + return strnlen(symbol, size); + } static uint32_t @@ -1830,6 +1886,12 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, if (irsp->ulpStatus == IOSTAT_LOCAL_REJECT) { switch ((irsp->un.ulpWord[4] & IOERR_PARAM_MASK)) { case IOERR_SLI_ABORTED: + case IOERR_SLI_DOWN: + /* Driver aborted this IO. No retry as error + * is likely Offline->Online or some adapter + * error. Recovery will try again. + */ + break; case IOERR_ABORT_IN_PROGRESS: case IOERR_SEQUENCE_TIMEOUT: case IOERR_ILLEGAL_FRAME: @@ -1938,14 +2000,16 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, /** - * lpfc_fdmi_num_disc_check - Check how many mapped NPorts we are connected to + * lpfc_fdmi_change_check - Check for changed FDMI parameters * @vport: pointer to a host virtual N_Port data structure. * - * Called from hbeat timeout routine to check if the number of discovered - * ports has changed. If so, re-register thar port Attribute. + * Check how many mapped NPorts we are connected to + * Check if our hostname changed + * Called from hbeat timeout routine to check if any FDMI parameters + * changed. If so, re-register those Attributes. */ void -lpfc_fdmi_num_disc_check(struct lpfc_vport *vport) +lpfc_fdmi_change_check(struct lpfc_vport *vport) { struct lpfc_hba *phba = vport->phba; struct lpfc_nodelist *ndlp; @@ -1958,17 +2022,41 @@ lpfc_fdmi_num_disc_check(struct lpfc_vport *vport) if (!(vport->fc_flag & FC_FABRIC)) return; + ndlp = lpfc_findnode_did(vport, FDMI_DID); + if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) + return; + + /* Check if system hostname changed */ + if (strcmp(phba->os_host_name, init_utsname()->nodename)) { + memset(phba->os_host_name, 0, sizeof(phba->os_host_name)); + scnprintf(phba->os_host_name, sizeof(phba->os_host_name), "%s", + init_utsname()->nodename); + lpfc_ns_cmd(vport, SLI_CTNS_RSNN_NN, 0, 0); + + /* Since this effects multiple HBA and PORT attributes, we need + * de-register and go thru the whole FDMI registration cycle. + * DHBA -> DPRT -> RHBA -> RPA (physical port) + * DPRT -> RPRT (vports) + */ + if (vport->port_type == LPFC_PHYSICAL_PORT) + lpfc_fdmi_cmd(vport, ndlp, SLI_MGMT_DHBA, 0); + else + lpfc_fdmi_cmd(vport, ndlp, SLI_MGMT_DPRT, 0); + + /* Since this code path registers all the port attributes + * we can just return without further checking. + */ + return; + } + if (!(vport->fdmi_port_mask & LPFC_FDMI_PORT_ATTR_num_disc)) return; + /* Check if the number of mapped NPorts changed */ cnt = lpfc_find_map_node(vport); if (cnt == vport->fdmi_num_disc) return; - ndlp = lpfc_findnode_did(vport, FDMI_DID); - if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) - return; - if (vport->port_type == LPFC_PHYSICAL_PORT) { lpfc_fdmi_cmd(vport, ndlp, SLI_MGMT_RPA, LPFC_FDMI_PORT_ATTR_num_disc); @@ -2515,7 +2603,7 @@ lpfc_fdmi_port_attr_max_frame(struct lpfc_vport *vport, ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; hsp = (struct serv_parm *)&vport->fc_sparam; - ae->un.AttrInt = (((uint32_t) hsp->cmn.bbRcvSizeMsb) << 8) | + ae->un.AttrInt = (((uint32_t) hsp->cmn.bbRcvSizeMsb & 0x0F) << 8) | (uint32_t) hsp->cmn.bbRcvSizeLsb; ae->un.AttrInt = cpu_to_be32(ae->un.AttrInt); size = FOURBYTES + sizeof(uint32_t); @@ -2556,8 +2644,8 @@ lpfc_fdmi_port_attr_host_name(struct lpfc_vport *vport, ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; memset(ae, 0, 256); - snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s", - init_utsname()->nodename); + scnprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s", + vport->phba->os_host_name); len = strnlen(ae->un.AttrString, sizeof(ae->un.AttrString)); len += (len & 3) ? (4 - (len & 3)) : 4; diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 1ee857d9d165..819335b16c2e 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -31,6 +31,7 @@ #include <linux/pci.h> #include <linux/spinlock.h> #include <linux/ctype.h> +#include <linux/vmalloc.h> #include <scsi/scsi.h> #include <scsi/scsi_device.h> @@ -361,7 +362,7 @@ lpfc_debugfs_hbqinfo_data(struct lpfc_hba *phba, char *buf, int size) phys = ((uint64_t)hbq_buf->dbuf.phys & 0xffffffff); if (phys == le32_to_cpu(hbqe->bde.addrLow)) { len += scnprintf(buf+len, size-len, - "Buf%d: %p %06x\n", i, + "Buf%d: x%px %06x\n", i, hbq_buf->dbuf.virt, hbq_buf->tag); found = 1; break; @@ -416,8 +417,7 @@ lpfc_debugfs_commonxripools_data(struct lpfc_hba *phba, char *buf, int size) qp = &phba->sli4_hba.hdwq[lpfc_debugfs_last_xripool]; len += scnprintf(buf + len, size - len, "HdwQ %d Info ", i); - spin_lock_irqsave(&qp->abts_scsi_buf_list_lock, iflag); - spin_lock(&qp->abts_nvme_buf_list_lock); + spin_lock_irqsave(&qp->abts_io_buf_list_lock, iflag); spin_lock(&qp->io_buf_list_get_lock); spin_lock(&qp->io_buf_list_put_lock); out = qp->total_io_bufs - (qp->get_io_bufs + qp->put_io_bufs + @@ -430,8 +430,7 @@ lpfc_debugfs_commonxripools_data(struct lpfc_hba *phba, char *buf, int size) qp->abts_nvme_io_bufs, out); spin_unlock(&qp->io_buf_list_put_lock); spin_unlock(&qp->io_buf_list_get_lock); - spin_unlock(&qp->abts_nvme_buf_list_lock); - spin_unlock_irqrestore(&qp->abts_scsi_buf_list_lock, iflag); + spin_unlock_irqrestore(&qp->abts_io_buf_list_lock, iflag); lpfc_debugfs_last_xripool++; if (lpfc_debugfs_last_xripool >= phba->cfg_hdw_queue) @@ -533,9 +532,7 @@ lpfc_debugfs_multixripools_data(struct lpfc_hba *phba, char *buf, int size) continue; pbl_pool = &multixri_pool->pbl_pool; pvt_pool = &multixri_pool->pvt_pool; - txcmplq_cnt = qp->fcp_wq->pring->txcmplq_cnt; - if (qp->nvme_wq) - txcmplq_cnt += qp->nvme_wq->pring->txcmplq_cnt; + txcmplq_cnt = qp->io_wq->pring->txcmplq_cnt; scnprintf(tmp, sizeof(tmp), "%03d: %4d %4d %4d %4d | %10d %10d ", @@ -2082,8 +2079,49 @@ lpfc_debugfs_lockstat_write(struct file *file, const char __user *buf, } #endif +static int lpfc_debugfs_ras_log_data(struct lpfc_hba *phba, + char *buffer, int size) +{ + int copied = 0; + struct lpfc_dmabuf *dmabuf, *next; + + memset(buffer, 0, size); + + spin_lock_irq(&phba->hbalock); + if (phba->ras_fwlog.state != ACTIVE) { + spin_unlock_irq(&phba->hbalock); + return -EINVAL; + } + spin_unlock_irq(&phba->hbalock); + + list_for_each_entry_safe(dmabuf, next, + &phba->ras_fwlog.fwlog_buff_list, list) { + /* Check if copying will go over size and a '\0' char */ + if ((copied + LPFC_RAS_MAX_ENTRY_SIZE) >= (size - 1)) { + memcpy(buffer + copied, dmabuf->virt, + size - copied - 1); + copied += size - copied - 1; + break; + } + memcpy(buffer + copied, dmabuf->virt, LPFC_RAS_MAX_ENTRY_SIZE); + copied += LPFC_RAS_MAX_ENTRY_SIZE; + } + return copied; +} + +static int +lpfc_debugfs_ras_log_release(struct inode *inode, struct file *file) +{ + struct lpfc_debug *debug = file->private_data; + + vfree(debug->buffer); + kfree(debug); + + return 0; +} + /** - * lpfc_debugfs_dumpHBASlim_open - Open the Dump HBA SLIM debugfs buffer + * lpfc_debugfs_ras_log_open - Open the RAS log debugfs buffer * @inode: The inode pointer that contains a vport pointer. * @file: The file pointer to attach the log output. * @@ -2098,34 +2136,48 @@ lpfc_debugfs_lockstat_write(struct file *file, const char __user *buf, * error value. **/ static int -lpfc_debugfs_dumpHBASlim_open(struct inode *inode, struct file *file) +lpfc_debugfs_ras_log_open(struct inode *inode, struct file *file) { struct lpfc_hba *phba = inode->i_private; struct lpfc_debug *debug; + int size; int rc = -ENOMEM; + spin_lock_irq(&phba->hbalock); + if (phba->ras_fwlog.state != ACTIVE) { + spin_unlock_irq(&phba->hbalock); + rc = -EINVAL; + goto out; + } + spin_unlock_irq(&phba->hbalock); debug = kmalloc(sizeof(*debug), GFP_KERNEL); if (!debug) goto out; - /* Round to page boundary */ - debug->buffer = kmalloc(LPFC_DUMPHBASLIM_SIZE, GFP_KERNEL); - if (!debug->buffer) { - kfree(debug); - goto out; - } + size = LPFC_RAS_MIN_BUFF_POST_SIZE * phba->cfg_ras_fwlog_buffsize; + debug->buffer = vmalloc(size); + if (!debug->buffer) + goto free_debug; - debug->len = lpfc_debugfs_dumpHBASlim_data(phba, debug->buffer, - LPFC_DUMPHBASLIM_SIZE); + debug->len = lpfc_debugfs_ras_log_data(phba, debug->buffer, size); + if (debug->len < 0) { + rc = -EINVAL; + goto free_buffer; + } file->private_data = debug; - rc = 0; + return 0; + +free_buffer: + vfree(debug->buffer); +free_debug: + kfree(debug); out: return rc; } /** - * lpfc_debugfs_dumpHostSlim_open - Open the Dump Host SLIM debugfs buffer + * lpfc_debugfs_dumpHBASlim_open - Open the Dump HBA SLIM debugfs buffer * @inode: The inode pointer that contains a vport pointer. * @file: The file pointer to attach the log output. * @@ -2140,7 +2192,7 @@ out: * error value. **/ static int -lpfc_debugfs_dumpHostSlim_open(struct inode *inode, struct file *file) +lpfc_debugfs_dumpHBASlim_open(struct inode *inode, struct file *file) { struct lpfc_hba *phba = inode->i_private; struct lpfc_debug *debug; @@ -2151,44 +2203,14 @@ lpfc_debugfs_dumpHostSlim_open(struct inode *inode, struct file *file) goto out; /* Round to page boundary */ - debug->buffer = kmalloc(LPFC_DUMPHOSTSLIM_SIZE, GFP_KERNEL); - if (!debug->buffer) { - kfree(debug); - goto out; - } - - debug->len = lpfc_debugfs_dumpHostSlim_data(phba, debug->buffer, - LPFC_DUMPHOSTSLIM_SIZE); - file->private_data = debug; - - rc = 0; -out: - return rc; -} - -static int -lpfc_debugfs_dumpData_open(struct inode *inode, struct file *file) -{ - struct lpfc_debug *debug; - int rc = -ENOMEM; - - if (!_dump_buf_data) - return -EBUSY; - - debug = kmalloc(sizeof(*debug), GFP_KERNEL); - if (!debug) - goto out; - - /* Round to page boundary */ - pr_err("9059 BLKGRD: %s: _dump_buf_data=0x%p\n", - __func__, _dump_buf_data); - debug->buffer = _dump_buf_data; + debug->buffer = kmalloc(LPFC_DUMPHBASLIM_SIZE, GFP_KERNEL); if (!debug->buffer) { kfree(debug); goto out; } - debug->len = (1 << _dump_buf_data_order) << PAGE_SHIFT; + debug->len = lpfc_debugfs_dumpHBASlim_data(phba, debug->buffer, + LPFC_DUMPHBASLIM_SIZE); file->private_data = debug; rc = 0; @@ -2196,29 +2218,41 @@ out: return rc; } +/** + * lpfc_debugfs_dumpHostSlim_open - Open the Dump Host SLIM debugfs buffer + * @inode: The inode pointer that contains a vport pointer. + * @file: The file pointer to attach the log output. + * + * Description: + * This routine is the entry point for the debugfs open file operation. It gets + * the vport from the i_private field in @inode, allocates the necessary buffer + * for the log, fills the buffer from the in-memory log for this vport, and then + * returns a pointer to that log in the private_data field in @file. + * + * Returns: + * This function returns zero if successful. On error it will return a negative + * error value. + **/ static int -lpfc_debugfs_dumpDif_open(struct inode *inode, struct file *file) +lpfc_debugfs_dumpHostSlim_open(struct inode *inode, struct file *file) { + struct lpfc_hba *phba = inode->i_private; struct lpfc_debug *debug; int rc = -ENOMEM; - if (!_dump_buf_dif) - return -EBUSY; - debug = kmalloc(sizeof(*debug), GFP_KERNEL); if (!debug) goto out; /* Round to page boundary */ - pr_err("9060 BLKGRD: %s: _dump_buf_dif=0x%p file=%pD\n", - __func__, _dump_buf_dif, file); - debug->buffer = _dump_buf_dif; + debug->buffer = kmalloc(LPFC_DUMPHOSTSLIM_SIZE, GFP_KERNEL); if (!debug->buffer) { kfree(debug); goto out; } - debug->len = (1 << _dump_buf_dif_order) << PAGE_SHIFT; + debug->len = lpfc_debugfs_dumpHostSlim_data(phba, debug->buffer, + LPFC_DUMPHOSTSLIM_SIZE); file->private_data = debug; rc = 0; @@ -2227,29 +2261,6 @@ out: } static ssize_t -lpfc_debugfs_dumpDataDif_write(struct file *file, const char __user *buf, - size_t nbytes, loff_t *ppos) -{ - /* - * The Data/DIF buffers only save one failing IO - * The write op is used as a reset mechanism after an IO has - * already been saved to the next one can be saved - */ - spin_lock(&_dump_buf_lock); - - memset((void *)_dump_buf_data, 0, - ((1 << PAGE_SHIFT) << _dump_buf_data_order)); - memset((void *)_dump_buf_dif, 0, - ((1 << PAGE_SHIFT) << _dump_buf_dif_order)); - - _dump_buf_done = 0; - - spin_unlock(&_dump_buf_lock); - - return nbytes; -} - -static ssize_t lpfc_debugfs_dif_err_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { @@ -2461,17 +2472,6 @@ lpfc_debugfs_release(struct inode *inode, struct file *file) return 0; } -static int -lpfc_debugfs_dumpDataDif_release(struct inode *inode, struct file *file) -{ - struct lpfc_debug *debug = file->private_data; - - debug->buffer = NULL; - kfree(debug); - - return 0; -} - /** * lpfc_debugfs_multixripools_write - Clear multi-XRI pools statistics * @file: The file pointer to read from. @@ -3786,23 +3786,13 @@ lpfc_idiag_wqs_for_cq(struct lpfc_hba *phba, char *wqtype, char *pbuffer, int qidx; for (qidx = 0; qidx < phba->cfg_hdw_queue; qidx++) { - qp = phba->sli4_hba.hdwq[qidx].fcp_wq; + qp = phba->sli4_hba.hdwq[qidx].io_wq; if (qp->assoc_qid != cq_id) continue; *len = __lpfc_idiag_print_wq(qp, wqtype, pbuffer, *len); if (*len >= max_cnt) return 1; } - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - for (qidx = 0; qidx < phba->cfg_hdw_queue; qidx++) { - qp = phba->sli4_hba.hdwq[qidx].nvme_wq; - if (qp->assoc_qid != cq_id) - continue; - *len = __lpfc_idiag_print_wq(qp, wqtype, pbuffer, *len); - if (*len >= max_cnt) - return 1; - } - } return 0; } @@ -3868,9 +3858,9 @@ lpfc_idiag_cqs_for_eq(struct lpfc_hba *phba, char *pbuffer, struct lpfc_queue *qp; int rc; - qp = phba->sli4_hba.hdwq[eqidx].fcp_cq; + qp = phba->sli4_hba.hdwq[eqidx].io_cq; - *len = __lpfc_idiag_print_cq(qp, "FCP", pbuffer, *len); + *len = __lpfc_idiag_print_cq(qp, "IO", pbuffer, *len); /* Reset max counter */ qp->CQ_max_cqe = 0; @@ -3878,28 +3868,11 @@ lpfc_idiag_cqs_for_eq(struct lpfc_hba *phba, char *pbuffer, if (*len >= max_cnt) return 1; - rc = lpfc_idiag_wqs_for_cq(phba, "FCP", pbuffer, len, + rc = lpfc_idiag_wqs_for_cq(phba, "IO", pbuffer, len, max_cnt, qp->queue_id); if (rc) return 1; - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - qp = phba->sli4_hba.hdwq[eqidx].nvme_cq; - - *len = __lpfc_idiag_print_cq(qp, "NVME", pbuffer, *len); - - /* Reset max counter */ - qp->CQ_max_cqe = 0; - - if (*len >= max_cnt) - return 1; - - rc = lpfc_idiag_wqs_for_cq(phba, "NVME", pbuffer, len, - max_cnt, qp->queue_id); - if (rc) - return 1; - } - if ((eqidx < phba->cfg_nvmet_mrq) && phba->nvmet_support) { /* NVMET CQset */ qp = phba->sli4_hba.nvmet_cqset[eqidx]; @@ -4348,7 +4321,7 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf, if (phba->sli4_hba.hdwq) { for (qidx = 0; qidx < phba->cfg_hdw_queue; qidx++) { - qp = phba->sli4_hba.hdwq[qidx].fcp_cq; + qp = phba->sli4_hba.hdwq[qidx].io_cq; if (qp && qp->queue_id == queid) { /* Sanity check */ rc = lpfc_idiag_que_param_check( @@ -4360,22 +4333,6 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf, } } } - /* NVME complete queue */ - if (phba->sli4_hba.hdwq) { - qidx = 0; - do { - qp = phba->sli4_hba.hdwq[qidx].nvme_cq; - if (qp && qp->queue_id == queid) { - /* Sanity check */ - rc = lpfc_idiag_que_param_check( - qp, index, count); - if (rc) - goto error_out; - idiag.ptr_private = qp; - goto pass_check; - } - } while (++qidx < phba->cfg_hdw_queue); - } goto error_out; break; case LPFC_IDIAG_MQ: @@ -4419,20 +4376,7 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf, if (phba->sli4_hba.hdwq) { /* FCP/SCSI work queue */ for (qidx = 0; qidx < phba->cfg_hdw_queue; qidx++) { - qp = phba->sli4_hba.hdwq[qidx].fcp_wq; - if (qp && qp->queue_id == queid) { - /* Sanity check */ - rc = lpfc_idiag_que_param_check( - qp, index, count); - if (rc) - goto error_out; - idiag.ptr_private = qp; - goto pass_check; - } - } - /* NVME work queue */ - for (qidx = 0; qidx < phba->cfg_hdw_queue; qidx++) { - qp = phba->sli4_hba.hdwq[qidx].nvme_wq; + qp = phba->sli4_hba.hdwq[qidx].io_wq; if (qp && qp->queue_id == queid) { /* Sanity check */ rc = lpfc_idiag_que_param_check( @@ -5440,6 +5384,15 @@ static const struct file_operations lpfc_debugfs_op_lockstat = { }; #endif +#undef lpfc_debugfs_ras_log +static const struct file_operations lpfc_debugfs_ras_log = { + .owner = THIS_MODULE, + .open = lpfc_debugfs_ras_log_open, + .llseek = lpfc_debugfs_lseek, + .read = lpfc_debugfs_read, + .release = lpfc_debugfs_ras_log_release, +}; + #undef lpfc_debugfs_op_dumpHBASlim static const struct file_operations lpfc_debugfs_op_dumpHBASlim = { .owner = THIS_MODULE, @@ -5508,26 +5461,6 @@ static const struct file_operations lpfc_debugfs_op_cpucheck = { .release = lpfc_debugfs_release, }; -#undef lpfc_debugfs_op_dumpData -static const struct file_operations lpfc_debugfs_op_dumpData = { - .owner = THIS_MODULE, - .open = lpfc_debugfs_dumpData_open, - .llseek = lpfc_debugfs_lseek, - .read = lpfc_debugfs_read, - .write = lpfc_debugfs_dumpDataDif_write, - .release = lpfc_debugfs_dumpDataDif_release, -}; - -#undef lpfc_debugfs_op_dumpDif -static const struct file_operations lpfc_debugfs_op_dumpDif = { - .owner = THIS_MODULE, - .open = lpfc_debugfs_dumpDif_open, - .llseek = lpfc_debugfs_lseek, - .read = lpfc_debugfs_read, - .write = lpfc_debugfs_dumpDataDif_write, - .release = lpfc_debugfs_dumpDataDif_release, -}; - #undef lpfc_debugfs_op_dif_err static const struct file_operations lpfc_debugfs_op_dif_err = { .owner = THIS_MODULE, @@ -5630,7 +5563,6 @@ static const struct file_operations lpfc_idiag_op_extAcc = { .write = lpfc_idiag_extacc_write, .release = lpfc_idiag_cmd_release, }; - #endif /* lpfc_idiag_mbxacc_dump_bsg_mbox - idiag debugfs dump bsg mailbox command @@ -5881,6 +5813,19 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport) goto debug_failed; } + /* RAS log */ + snprintf(name, sizeof(name), "ras_log"); + phba->debug_ras_log = + debugfs_create_file(name, 0644, + phba->hba_debugfs_root, + phba, &lpfc_debugfs_ras_log); + if (!phba->debug_ras_log) { + lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT, + "6148 Cannot create debugfs" + " ras_log\n"); + goto debug_failed; + } + /* Setup hbqinfo */ snprintf(name, sizeof(name), "hbqinfo"); phba->debug_hbqinfo = @@ -5924,20 +5869,6 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport) } else phba->debug_dumpHostSlim = NULL; - /* Setup dumpData */ - snprintf(name, sizeof(name), "dumpData"); - phba->debug_dumpData = - debugfs_create_file(name, S_IFREG|S_IRUGO|S_IWUSR, - phba->hba_debugfs_root, - phba, &lpfc_debugfs_op_dumpData); - - /* Setup dumpDif */ - snprintf(name, sizeof(name), "dumpDif"); - phba->debug_dumpDif = - debugfs_create_file(name, S_IFREG|S_IRUGO|S_IWUSR, - phba->hba_debugfs_root, - phba, &lpfc_debugfs_op_dumpDif); - /* Setup DIF Error Injections */ snprintf(name, sizeof(name), "InjErrLBA"); phba->debug_InjErrLBA = @@ -6305,6 +6236,9 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport) debugfs_remove(phba->debug_hbqinfo); /* hbqinfo */ phba->debug_hbqinfo = NULL; + debugfs_remove(phba->debug_ras_log); + phba->debug_ras_log = NULL; + #ifdef LPFC_HDWQ_LOCK_STAT debugfs_remove(phba->debug_lockstat); /* lockstat */ phba->debug_lockstat = NULL; @@ -6315,12 +6249,6 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport) debugfs_remove(phba->debug_dumpHostSlim); /* HostSlim */ phba->debug_dumpHostSlim = NULL; - debugfs_remove(phba->debug_dumpData); /* dumpData */ - phba->debug_dumpData = NULL; - - debugfs_remove(phba->debug_dumpDif); /* dumpDif */ - phba->debug_dumpDif = NULL; - debugfs_remove(phba->debug_InjErrLBA); /* InjErrLBA */ phba->debug_InjErrLBA = NULL; @@ -6442,12 +6370,7 @@ lpfc_debug_dump_all_queues(struct lpfc_hba *phba) lpfc_debug_dump_wq(phba, DUMP_NVMELS, 0); for (idx = 0; idx < phba->cfg_hdw_queue; idx++) - lpfc_debug_dump_wq(phba, DUMP_FCP, idx); - - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - for (idx = 0; idx < phba->cfg_hdw_queue; idx++) - lpfc_debug_dump_wq(phba, DUMP_NVME, idx); - } + lpfc_debug_dump_wq(phba, DUMP_IO, idx); lpfc_debug_dump_hdr_rq(phba); lpfc_debug_dump_dat_rq(phba); @@ -6459,12 +6382,7 @@ lpfc_debug_dump_all_queues(struct lpfc_hba *phba) lpfc_debug_dump_cq(phba, DUMP_NVMELS, 0); for (idx = 0; idx < phba->cfg_hdw_queue; idx++) - lpfc_debug_dump_cq(phba, DUMP_FCP, idx); - - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - for (idx = 0; idx < phba->cfg_hdw_queue; idx++) - lpfc_debug_dump_cq(phba, DUMP_NVME, idx); - } + lpfc_debug_dump_cq(phba, DUMP_IO, idx); /* * Dump Event Queues (EQs) diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h index 34070874616d..20f2537af511 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.h +++ b/drivers/scsi/lpfc/lpfc_debugfs.h @@ -291,8 +291,7 @@ struct lpfc_idiag { #define LPFC_DUMP_MULTIXRIPOOL_SIZE 8192 enum { - DUMP_FCP, - DUMP_NVME, + DUMP_IO, DUMP_MBX, DUMP_ELS, DUMP_NVMELS, @@ -415,12 +414,9 @@ lpfc_debug_dump_wq(struct lpfc_hba *phba, int qtype, int wqidx) struct lpfc_queue *wq; char *qtypestr; - if (qtype == DUMP_FCP) { - wq = phba->sli4_hba.hdwq[wqidx].fcp_wq; - qtypestr = "FCP"; - } else if (qtype == DUMP_NVME) { - wq = phba->sli4_hba.hdwq[wqidx].nvme_wq; - qtypestr = "NVME"; + if (qtype == DUMP_IO) { + wq = phba->sli4_hba.hdwq[wqidx].io_wq; + qtypestr = "IO"; } else if (qtype == DUMP_MBX) { wq = phba->sli4_hba.mbx_wq; qtypestr = "MBX"; @@ -433,7 +429,7 @@ lpfc_debug_dump_wq(struct lpfc_hba *phba, int qtype, int wqidx) } else return; - if (qtype == DUMP_FCP || qtype == DUMP_NVME) + if (qtype == DUMP_IO) pr_err("%s WQ: WQ[Idx:%d|Qid:%d]\n", qtypestr, wqidx, wq->queue_id); else @@ -459,17 +455,13 @@ lpfc_debug_dump_cq(struct lpfc_hba *phba, int qtype, int wqidx) char *qtypestr; int eqidx; - /* fcp/nvme wq and cq are 1:1, thus same indexes */ + /* io wq and cq are 1:1, thus same indexes */ eq = NULL; - if (qtype == DUMP_FCP) { - wq = phba->sli4_hba.hdwq[wqidx].fcp_wq; - cq = phba->sli4_hba.hdwq[wqidx].fcp_cq; - qtypestr = "FCP"; - } else if (qtype == DUMP_NVME) { - wq = phba->sli4_hba.hdwq[wqidx].nvme_wq; - cq = phba->sli4_hba.hdwq[wqidx].nvme_cq; - qtypestr = "NVME"; + if (qtype == DUMP_IO) { + wq = phba->sli4_hba.hdwq[wqidx].io_wq; + cq = phba->sli4_hba.hdwq[wqidx].io_cq; + qtypestr = "IO"; } else if (qtype == DUMP_MBX) { wq = phba->sli4_hba.mbx_wq; cq = phba->sli4_hba.mbx_cq; @@ -496,7 +488,7 @@ lpfc_debug_dump_cq(struct lpfc_hba *phba, int qtype, int wqidx) eq = phba->sli4_hba.hdwq[0].hba_eq; } - if (qtype == DUMP_FCP || qtype == DUMP_NVME) + if (qtype == DUMP_IO) pr_err("%s CQ: WQ[Idx:%d|Qid%d]->CQ[Idx%d|Qid%d]" "->EQ[Idx:%d|Qid:%d]:\n", qtypestr, wqidx, wq->queue_id, wqidx, cq->queue_id, @@ -572,20 +564,11 @@ lpfc_debug_dump_wq_by_id(struct lpfc_hba *phba, int qid) int wq_idx; for (wq_idx = 0; wq_idx < phba->cfg_hdw_queue; wq_idx++) - if (phba->sli4_hba.hdwq[wq_idx].fcp_wq->queue_id == qid) + if (phba->sli4_hba.hdwq[wq_idx].io_wq->queue_id == qid) break; if (wq_idx < phba->cfg_hdw_queue) { - pr_err("FCP WQ[Idx:%d|Qid:%d]\n", wq_idx, qid); - lpfc_debug_dump_q(phba->sli4_hba.hdwq[wq_idx].fcp_wq); - return; - } - - for (wq_idx = 0; wq_idx < phba->cfg_hdw_queue; wq_idx++) - if (phba->sli4_hba.hdwq[wq_idx].nvme_wq->queue_id == qid) - break; - if (wq_idx < phba->cfg_hdw_queue) { - pr_err("NVME WQ[Idx:%d|Qid:%d]\n", wq_idx, qid); - lpfc_debug_dump_q(phba->sli4_hba.hdwq[wq_idx].nvme_wq); + pr_err("IO WQ[Idx:%d|Qid:%d]\n", wq_idx, qid); + lpfc_debug_dump_q(phba->sli4_hba.hdwq[wq_idx].io_wq); return; } @@ -654,22 +637,12 @@ lpfc_debug_dump_cq_by_id(struct lpfc_hba *phba, int qid) int cq_idx; for (cq_idx = 0; cq_idx < phba->cfg_hdw_queue; cq_idx++) - if (phba->sli4_hba.hdwq[cq_idx].fcp_cq->queue_id == qid) - break; - - if (cq_idx < phba->cfg_hdw_queue) { - pr_err("FCP CQ[Idx:%d|Qid:%d]\n", cq_idx, qid); - lpfc_debug_dump_q(phba->sli4_hba.hdwq[cq_idx].fcp_cq); - return; - } - - for (cq_idx = 0; cq_idx < phba->cfg_hdw_queue; cq_idx++) - if (phba->sli4_hba.hdwq[cq_idx].nvme_cq->queue_id == qid) + if (phba->sli4_hba.hdwq[cq_idx].io_cq->queue_id == qid) break; if (cq_idx < phba->cfg_hdw_queue) { - pr_err("NVME CQ[Idx:%d|Qid:%d]\n", cq_idx, qid); - lpfc_debug_dump_q(phba->sli4_hba.hdwq[cq_idx].nvme_cq); + pr_err("IO CQ[Idx:%d|Qid:%d]\n", cq_idx, qid); + lpfc_debug_dump_q(phba->sli4_hba.hdwq[cq_idx].io_cq); return; } diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h index 1c89c9f314fa..482e4a888dae 100644 --- a/drivers/scsi/lpfc/lpfc_disc.h +++ b/drivers/scsi/lpfc/lpfc_disc.h @@ -112,6 +112,8 @@ struct lpfc_nodelist { uint8_t nlp_retry; /* used for ELS retries */ uint8_t nlp_fcp_info; /* class info, bits 0-3 */ #define NLP_FCP_2_DEVICE 0x10 /* FCP-2 device */ + u8 nlp_nvme_info; /* NVME NSLER Support */ +#define NLP_NVME_NSLER 0x1 /* NVME NSLER device */ uint16_t nlp_usg_map; /* ndlp management usage bitmap */ #define NLP_USG_NODE_ACT_BIT 0x1 /* Indicate ndlp is actively used */ @@ -157,6 +159,7 @@ struct lpfc_node_rrq { /* Defines for nlp_flag (uint32) */ #define NLP_IGNR_REG_CMPL 0x00000001 /* Rcvd rscn before we cmpl reg login */ #define NLP_REG_LOGIN_SEND 0x00000002 /* sent reglogin to adapter */ +#define NLP_RELEASE_RPI 0x00000004 /* Release RPI to free pool */ #define NLP_SUPPRESS_RSP 0x00000010 /* Remote NPort supports suppress rsp */ #define NLP_PLOGI_SND 0x00000020 /* sent PLOGI request for this entry */ #define NLP_PRLI_SND 0x00000040 /* sent PRLI request for this entry */ diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index f12780f4cfbb..42a2bf38eaea 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -1052,17 +1052,18 @@ stop_rr_fcf_flogi: if (lpfc_els_retry(phba, cmdiocb, rspiocb)) goto out; + lpfc_printf_vlog(vport, KERN_WARNING, LOG_ELS, + "0150 FLOGI failure Status:x%x/x%x " + "xri x%x TMO:x%x\n", + irsp->ulpStatus, irsp->un.ulpWord[4], + cmdiocb->sli4_xritag, irsp->ulpTimeout); + /* If this is not a loop open failure, bail out */ if (!(irsp->ulpStatus == IOSTAT_LOCAL_REJECT && ((irsp->un.ulpWord[4] & IOERR_PARAM_MASK) == IOERR_LOOP_OPEN_FAILURE))) goto flogifail; - lpfc_printf_vlog(vport, KERN_WARNING, LOG_ELS, - "0150 FLOGI failure Status:x%x/x%x xri x%x TMO:x%x\n", - irsp->ulpStatus, irsp->un.ulpWord[4], - cmdiocb->sli4_xritag, irsp->ulpTimeout); - /* FLOGI failed, so there is no fabric */ spin_lock_irq(shost->host_lock); vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP); @@ -1207,6 +1208,39 @@ out: } /** + * lpfc_cmpl_els_link_down - Completion callback function for ELS command + * aborted during a link down + * @phba: pointer to lpfc hba data structure. + * @cmdiocb: pointer to lpfc command iocb data structure. + * @rspiocb: pointer to lpfc response iocb data structure. + * + */ +static void +lpfc_cmpl_els_link_down(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, + struct lpfc_iocbq *rspiocb) +{ + IOCB_t *irsp; + uint32_t *pcmd; + uint32_t cmd; + + pcmd = (uint32_t *)(((struct lpfc_dmabuf *)cmdiocb->context2)->virt); + cmd = *pcmd; + irsp = &rspiocb->iocb; + + lpfc_printf_log(phba, KERN_INFO, LOG_ELS, + "6445 ELS completes after LINK_DOWN: " + " Status %x/%x cmd x%x flg x%x\n", + irsp->ulpStatus, irsp->un.ulpWord[4], cmd, + cmdiocb->iocb_flag); + + if (cmdiocb->iocb_flag & LPFC_IO_FABRIC) { + cmdiocb->iocb_flag &= ~LPFC_IO_FABRIC; + atomic_dec(&phba->fabric_iocb_count); + } + lpfc_els_free_iocb(phba, cmdiocb); +} + +/** * lpfc_issue_els_flogi - Issue an flogi iocb command for a vport * @vport: pointer to a host virtual N_Port data structure. * @ndlp: pointer to a node-list data structure. @@ -2107,7 +2141,7 @@ lpfc_issue_els_plogi(struct lpfc_vport *vport, uint32_t did, uint8_t retry) !(vport->fc_flag & FC_OFFLINE_MODE)) { lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, "4110 Issue PLOGI x%x deferred " - "on NPort x%x rpi x%x Data: %p\n", + "on NPort x%x rpi x%x Data: x%px\n", ndlp->nlp_defer_did, ndlp->nlp_DID, ndlp->nlp_rpi, ndlp); @@ -2202,6 +2236,7 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, struct Scsi_Host *shost = lpfc_shost_from_vport(vport); IOCB_t *irsp; struct lpfc_nodelist *ndlp; + char *mode; /* we pass cmdiocb to state machine which needs rspiocb as well */ cmdiocb->context_un.rsp_iocb = rspiocb; @@ -2239,8 +2274,17 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, goto out; } + /* If we don't send GFT_ID to Fabric, a PRLI error + * could be expected. + */ + if ((vport->fc_flag & FC_FABRIC) || + (vport->cfg_enable_fc4_type != LPFC_ENABLE_BOTH)) + mode = KERN_ERR; + else + mode = KERN_INFO; + /* PRLI failed */ - lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS, + lpfc_printf_vlog(vport, mode, LOG_ELS, "2754 PRLI failure DID:%06X Status:x%x/x%x, " "data: x%x\n", ndlp->nlp_DID, irsp->ulpStatus, @@ -2401,6 +2445,10 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, npr_nvme = (struct lpfc_nvme_prli *)pcmd; bf_set(prli_type_code, npr_nvme, PRLI_NVME_TYPE); bf_set(prli_estabImagePair, npr_nvme, 0); /* Should be 0 */ + if (phba->nsler) { + bf_set(prli_nsler, npr_nvme, 1); + bf_set(prli_conf, npr_nvme, 1); + } /* Only initiators request first burst. */ if ((phba->cfg_nvme_enable_fb) && @@ -4203,7 +4251,7 @@ lpfc_mbx_cmpl_dflt_rpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) mempool_free(pmb, phba->mbox_mem_pool); if (ndlp) { lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, - "0006 rpi%x DID:%x flg:%x %d map:%x %p\n", + "0006 rpi%x DID:%x flg:%x %d map:%x x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); @@ -4253,6 +4301,11 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, irsp = &rspiocb->iocb; + if (!vport) { + lpfc_printf_log(phba, KERN_ERR, LOG_ELS, + "3177 ELS response failed\n"); + goto out; + } if (cmdiocb->context_un.mbox) mbox = cmdiocb->context_un.mbox; @@ -4392,7 +4445,7 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, mempool_free(mbox, phba->mbox_mem_pool); } out: - if (ndlp && NLP_CHK_NODE_ACT(ndlp)) { + if (ndlp && NLP_CHK_NODE_ACT(ndlp) && shost) { spin_lock_irq(shost->host_lock); ndlp->nlp_flag &= ~(NLP_ACC_REGLOGIN | NLP_RM_DFLT_RPI); spin_unlock_irq(shost->host_lock); @@ -5222,6 +5275,11 @@ lpfc_els_disc_plogi(struct lpfc_vport *vport) } } } + + lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, + "6452 Discover PLOGI %d flag x%x\n", + sentplogi, vport->fc_flag); + if (sentplogi) { lpfc_set_disctmo(vport); } @@ -5634,16 +5692,16 @@ lpfc_rdp_res_attach_port_names(struct fc_rdp_port_name_desc *desc, desc->tag = cpu_to_be32(RDP_PORT_NAMES_DESC_TAG); if (vport->fc_flag & FC_FABRIC) { memcpy(desc->port_names.wwnn, &vport->fabric_nodename, - sizeof(desc->port_names.wwnn)); + sizeof(desc->port_names.wwnn)); memcpy(desc->port_names.wwpn, &vport->fabric_portname, - sizeof(desc->port_names.wwpn)); + sizeof(desc->port_names.wwpn)); } else { /* Point to Point */ memcpy(desc->port_names.wwnn, &ndlp->nlp_nodename, - sizeof(desc->port_names.wwnn)); + sizeof(desc->port_names.wwnn)); - memcpy(desc->port_names.wwnn, &ndlp->nlp_portname, - sizeof(desc->port_names.wwpn)); + memcpy(desc->port_names.wwpn, &ndlp->nlp_portname, + sizeof(desc->port_names.wwpn)); } desc->length = cpu_to_be32(sizeof(desc->port_names)); @@ -6327,7 +6385,11 @@ lpfc_rscn_recovery_check(struct lpfc_vport *vport) continue; } - if (ndlp->nlp_fc4_type & NLP_FC4_NVME) + /* Check to see if we need to NVME rescan this target + * remoteport. + */ + if (ndlp->nlp_fc4_type & NLP_FC4_NVME && + ndlp->nlp_type & (NLP_NVME_TARGET | NLP_NVME_DISCOVERY)) lpfc_nvme_rescan_port(vport, ndlp); lpfc_disc_state_machine(vport, ndlp, NULL, @@ -6413,7 +6475,7 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb, uint32_t payload_len, length, nportid, *cmd; int rscn_cnt; int rscn_id = 0, hba_id = 0; - int i; + int i, tmo; pcmd = (struct lpfc_dmabuf *) cmdiocb->context2; lp = (uint32_t *) pcmd->virt; @@ -6441,7 +6503,11 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb, *lp, vport->fc_flag, payload_len); lpfc_els_rsp_acc(vport, ELS_CMD_ACC, cmdiocb, ndlp, NULL); - if (ndlp->nlp_fc4_type & NLP_FC4_NVME) + /* Check to see if we need to NVME rescan this target + * remoteport. + */ + if (ndlp->nlp_fc4_type & NLP_FC4_NVME && + ndlp->nlp_type & (NLP_NVME_TARGET | NLP_NVME_DISCOVERY)) lpfc_nvme_rescan_port(vport, ndlp); return 0; } @@ -6515,6 +6581,13 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb, spin_lock_irq(shost->host_lock); vport->fc_flag |= FC_RSCN_DEFERRED; + + /* Restart disctmo if its already running */ + if (vport->fc_flag & FC_DISC_TMO) { + tmo = ((phba->fc_ratov * 3) + 3); + mod_timer(&vport->fc_disctmo, + jiffies + msecs_to_jiffies(1000 * tmo)); + } if ((rscn_cnt < FC_MAX_HOLD_RSCN) && !(vport->fc_flag & FC_RSCN_DISCOVERY)) { vport->fc_flag |= FC_RSCN_MODE; @@ -6617,9 +6690,10 @@ lpfc_els_handle_rscn(struct lpfc_vport *vport) /* RSCN processed */ lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, - "0215 RSCN processed Data: x%x x%x x%x x%x\n", + "0215 RSCN processed Data: x%x x%x x%x x%x x%x x%x\n", vport->fc_flag, 0, vport->fc_rscn_id_cnt, - vport->port_state); + vport->port_state, vport->num_disc_nodes, + vport->gidft_inp); /* To process RSCN, first compare RSCN data with NameServer */ vport->fc_ns_retry = 0; @@ -7940,53 +8014,83 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) struct lpfc_sli_ring *pring; struct lpfc_iocbq *tmp_iocb, *piocb; IOCB_t *cmd = NULL; + unsigned long iflags = 0; lpfc_fabric_abort_vport(vport); + /* * For SLI3, only the hbalock is required. But SLI4 needs to coordinate * with the ring insert operation. Because lpfc_sli_issue_abort_iotag * ultimately grabs the ring_lock, the driver must splice the list into * a working list and release the locks before calling the abort. */ - spin_lock_irq(&phba->hbalock); + spin_lock_irqsave(&phba->hbalock, iflags); pring = lpfc_phba_elsring(phba); /* Bail out if we've no ELS wq, like in PCI error recovery case. */ if (unlikely(!pring)) { - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); return; } if (phba->sli_rev == LPFC_SLI_REV4) spin_lock(&pring->ring_lock); + /* First we need to issue aborts to outstanding cmds on txcmpl */ list_for_each_entry_safe(piocb, tmp_iocb, &pring->txcmplq, list) { if (piocb->iocb_flag & LPFC_IO_LIBDFC) continue; if (piocb->vport != vport) continue; - list_add_tail(&piocb->dlist, &abort_list); + + if (piocb->iocb_flag & LPFC_DRIVER_ABORTED) + continue; + + /* On the ELS ring we can have ELS_REQUESTs or + * GEN_REQUESTs waiting for a response. + */ + cmd = &piocb->iocb; + if (cmd->ulpCommand == CMD_ELS_REQUEST64_CR) { + list_add_tail(&piocb->dlist, &abort_list); + + /* If the link is down when flushing ELS commands + * the firmware will not complete them till after + * the link comes back up. This may confuse + * discovery for the new link up, so we need to + * change the compl routine to just clean up the iocb + * and avoid any retry logic. + */ + if (phba->link_state == LPFC_LINK_DOWN) + piocb->iocb_cmpl = lpfc_cmpl_els_link_down; + } + if (cmd->ulpCommand == CMD_GEN_REQUEST64_CR) + list_add_tail(&piocb->dlist, &abort_list); } + if (phba->sli_rev == LPFC_SLI_REV4) spin_unlock(&pring->ring_lock); - spin_unlock_irq(&phba->hbalock); - /* Abort each iocb on the aborted list and remove the dlist links. */ + spin_unlock_irqrestore(&phba->hbalock, iflags); + + /* Abort each txcmpl iocb on aborted list and remove the dlist links. */ list_for_each_entry_safe(piocb, tmp_iocb, &abort_list, dlist) { - spin_lock_irq(&phba->hbalock); + spin_lock_irqsave(&phba->hbalock, iflags); list_del_init(&piocb->dlist); lpfc_sli_issue_abort_iotag(phba, pring, piocb); - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); } if (!list_empty(&abort_list)) lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS, "3387 abort list for txq not empty\n"); INIT_LIST_HEAD(&abort_list); - spin_lock_irq(&phba->hbalock); + spin_lock_irqsave(&phba->hbalock, iflags); if (phba->sli_rev == LPFC_SLI_REV4) spin_lock(&pring->ring_lock); + /* No need to abort the txq list, + * just queue them up for lpfc_sli_cancel_iocbs + */ list_for_each_entry_safe(piocb, tmp_iocb, &pring->txq, list) { cmd = &piocb->iocb; @@ -8007,11 +8111,22 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) list_del_init(&piocb->list); list_add_tail(&piocb->list, &abort_list); } + + /* The same holds true for any FLOGI/FDISC on the fabric_iocb_list */ + if (vport == phba->pport) { + list_for_each_entry_safe(piocb, tmp_iocb, + &phba->fabric_iocb_list, list) { + cmd = &piocb->iocb; + list_del_init(&piocb->list); + list_add_tail(&piocb->list, &abort_list); + } + } + if (phba->sli_rev == LPFC_SLI_REV4) spin_unlock(&pring->ring_lock); - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); - /* Cancell all the IOCBs from the completions list */ + /* Cancel all the IOCBs from the completions list */ lpfc_sli_cancel_iocbs(phba, &abort_list, IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 28ecaa7fc715..dcc8999c6a68 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -28,6 +28,7 @@ #include <linux/kthread.h> #include <linux/interrupt.h> #include <linux/lockdep.h> +#include <linux/utsname.h> #include <scsi/scsi.h> #include <scsi/scsi_device.h> @@ -118,6 +119,7 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) struct lpfc_work_evt *evtp; int put_node; int put_rport; + unsigned long iflags; rdata = rport->dd_data; ndlp = rdata->pnode; @@ -132,7 +134,7 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->nlp_sid, ndlp->nlp_DID, ndlp->nlp_flag); lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, - "3181 dev_loss_callbk x%06x, rport %p flg x%x\n", + "3181 dev_loss_callbk x%06x, rport x%px flg x%x\n", ndlp->nlp_DID, ndlp->rport, ndlp->nlp_flag); /* Don't defer this if we are in the process of deleting the vport @@ -170,22 +172,22 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) } shost = lpfc_shost_from_vport(vport); - spin_lock_irq(shost->host_lock); + spin_lock_irqsave(shost->host_lock, iflags); ndlp->nlp_flag |= NLP_IN_DEV_LOSS; - spin_unlock_irq(shost->host_lock); + spin_unlock_irqrestore(shost->host_lock, iflags); /* We need to hold the node by incrementing the reference * count until this queued work is done */ evtp->evt_arg1 = lpfc_nlp_get(ndlp); - spin_lock_irq(&phba->hbalock); + spin_lock_irqsave(&phba->hbalock, iflags); if (evtp->evt_arg1) { evtp->evt = LPFC_EVT_DEV_LOSS; list_add_tail(&evtp->evt_listp, &phba->work_list); lpfc_worker_wake_up(phba); } - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); return; } @@ -212,14 +214,15 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) int put_node; int warn_on = 0; int fcf_inuse = 0; + unsigned long iflags; rport = ndlp->rport; vport = ndlp->vport; shost = lpfc_shost_from_vport(vport); - spin_lock_irq(shost->host_lock); + spin_lock_irqsave(shost->host_lock, iflags); ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; - spin_unlock_irq(shost->host_lock); + spin_unlock_irqrestore(shost->host_lock, iflags); if (!rport) return fcf_inuse; @@ -235,7 +238,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) ndlp->nlp_DID, ndlp->nlp_type, rport->scsi_target_id); lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, - "3182 dev_loss_tmo_handler x%06x, rport %p flg x%x\n", + "3182 dev_loss_tmo_handler x%06x, rport x%px flg x%x\n", ndlp->nlp_DID, ndlp->rport, ndlp->nlp_flag); /* @@ -698,7 +701,10 @@ lpfc_work_done(struct lpfc_hba *phba) if (!(phba->hba_flag & HBA_SP_QUEUE_EVT)) set_bit(LPFC_DATA_READY, &phba->data_flags); } else { - if (phba->link_state >= LPFC_LINK_UP || + /* Driver could have abort request completed in queue + * when link goes down. Allow for this transition. + */ + if (phba->link_state >= LPFC_LINK_DOWN || phba->link_flag & LS_MDS_LOOPBACK) { pring->flag &= ~LPFC_DEFERRED_RING_EVENT; lpfc_sli_handle_slow_ring_event(phba, pring, @@ -903,6 +909,8 @@ lpfc_linkdown(struct lpfc_hba *phba) phba->trunk_link.link1.state = 0; phba->trunk_link.link2.state = 0; phba->trunk_link.link3.state = 0; + phba->sli4_hba.link_state.logical_speed = + LPFC_LINK_SPEED_UNKNOWN; } spin_lock_irq(shost->host_lock); phba->pport->fc_flag &= ~FC_LBIT; @@ -1131,7 +1139,6 @@ void lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) { struct lpfc_vport *vport = pmb->vport; - uint8_t bbscn = 0; if (pmb->u.mb.mbxStatus) goto out; @@ -1158,17 +1165,11 @@ 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 */ - if (vport->port_state != LPFC_FLOGI) { - if (phba->bbcredit_support && phba->cfg_enable_bbcr) { - bbscn = bf_get(lpfc_bbscn_def, - &phba->sli4_hba.bbscn_params); - vport->fc_sparam.cmn.bbRcvSizeMsb &= 0xf; - vport->fc_sparam.cmn.bbRcvSizeMsb |= (bbscn << 4); - } + if (vport->port_state != LPFC_FLOGI) lpfc_initial_flogi(vport); - } else if (vport->fc_flag & FC_PT2PT) { + else if (vport->fc_flag & FC_PT2PT) lpfc_disc_start(vport); - } + return; out: @@ -3115,8 +3116,9 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) int rc; struct fcf_record *fcf_record; uint32_t fc_flags = 0; + unsigned long iflags; - spin_lock_irq(&phba->hbalock); + spin_lock_irqsave(&phba->hbalock, iflags); phba->fc_linkspeed = bf_get(lpfc_mbx_read_top_link_spd, la); if (!(phba->hba_flag & HBA_FCOE_MODE)) { @@ -3213,12 +3215,12 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) vport->fc_myDID = phba->fc_pref_DID; fc_flags |= FC_LBIT; } - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); if (fc_flags) { - spin_lock_irq(shost->host_lock); + spin_lock_irqsave(shost->host_lock, iflags); vport->fc_flag |= fc_flags; - spin_unlock_irq(shost->host_lock); + spin_unlock_irqrestore(shost->host_lock, iflags); } lpfc_linkup(phba); @@ -3292,33 +3294,37 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) * The driver is expected to do FIP/FCF. Call the port * and get the FCF Table. */ - spin_lock_irq(&phba->hbalock); + spin_lock_irqsave(&phba->hbalock, iflags); if (phba->hba_flag & FCF_TS_INPROG) { - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); return; } /* This is the initial FCF discovery scan */ phba->fcf.fcf_flag |= FCF_INIT_DISC; - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); lpfc_printf_log(phba, KERN_INFO, LOG_FIP | LOG_DISCOVERY, "2778 Start FCF table scan at linkup\n"); rc = lpfc_sli4_fcf_scan_read_fcf_rec(phba, LPFC_FCOE_FCF_GET_FIRST); if (rc) { - spin_lock_irq(&phba->hbalock); + spin_lock_irqsave(&phba->hbalock, iflags); phba->fcf.fcf_flag &= ~FCF_INIT_DISC; - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); goto out; } /* Reset FCF roundrobin bmask for new discovery */ lpfc_sli4_clear_fcf_rr_bmask(phba); } + /* Prepare for LINK up registrations */ + memset(phba->os_host_name, 0, sizeof(phba->os_host_name)); + scnprintf(phba->os_host_name, sizeof(phba->os_host_name), "%s", + init_utsname()->nodename); return; out: lpfc_vport_set_state(vport, FC_VPORT_FAILED); lpfc_printf_vlog(vport, KERN_ERR, LOG_MBOX, - "0263 Discovery Mailbox error: state: 0x%x : %p %p\n", + "0263 Discovery Mailbox error: state: 0x%x : x%px x%px\n", vport->port_state, sparam_mbox, cfglink_mbox); lpfc_issue_clear_la(phba, vport); return; @@ -3366,6 +3372,7 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) MAILBOX_t *mb = &pmb->u.mb; struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *)(pmb->ctx_buf); uint8_t attn_type; + unsigned long iflags; /* Unblock ELS traffic */ pring = lpfc_phba_elsring(phba); @@ -3387,12 +3394,12 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) memcpy(&phba->alpa_map[0], mp->virt, 128); - spin_lock_irq(shost->host_lock); + spin_lock_irqsave(shost->host_lock, iflags); if (bf_get(lpfc_mbx_read_top_pb, la)) vport->fc_flag |= FC_BYPASSED_MODE; else vport->fc_flag &= ~FC_BYPASSED_MODE; - spin_unlock_irq(shost->host_lock); + spin_unlock_irqrestore(shost->host_lock, iflags); if (phba->fc_eventTag <= la->eventTag) { phba->fc_stat.LinkMultiEvent++; @@ -3403,12 +3410,12 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) phba->fc_eventTag = la->eventTag; if (phba->sli_rev < LPFC_SLI_REV4) { - spin_lock_irq(&phba->hbalock); + spin_lock_irqsave(&phba->hbalock, iflags); if (bf_get(lpfc_mbx_read_top_mm, la)) phba->sli.sli_flag |= LPFC_MENLO_MAINT; else phba->sli.sli_flag &= ~LPFC_MENLO_MAINT; - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); } phba->link_events++; @@ -3450,8 +3457,8 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) phba->pport->port_state, vport->fc_flag); else if (attn_type == LPFC_ATT_UNEXP_WWPN) lpfc_printf_log(phba, KERN_ERR, LOG_LINK_EVENT, - "1313 Link Down UNEXP WWPN Event x%x received " - "Data: x%x x%x x%x x%x x%x\n", + "1313 Link Down Unexpected FA WWPN Event x%x " + "received Data: x%x x%x x%x x%x x%x\n", la->eventTag, phba->fc_eventTag, phba->pport->port_state, vport->fc_flag, bf_get(lpfc_mbx_read_top_mm, la), @@ -3529,7 +3536,7 @@ lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) pmb->ctx_ndlp = NULL; lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, - "0002 rpi:%x DID:%x flg:%x %d map:%x %p\n", + "0002 rpi:%x DID:%x flg:%x %d map:%x x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); @@ -4040,8 +4047,8 @@ out: ndlp->nlp_flag |= NLP_RPI_REGISTERED; ndlp->nlp_type |= NLP_FABRIC; lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE); - lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, - "0003 rpi:%x DID:%x flg:%x %d map%x %p\n", + lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY, + "0003 rpi:%x DID:%x flg:%x %d map%x x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); @@ -4160,7 +4167,7 @@ lpfc_register_remote_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) fc_remote_port_rolechg(rport, rport_ids.roles); lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, - "3183 rport register x%06x, rport %p role x%x\n", + "3183 rport register x%06x, rport x%px role x%x\n", ndlp->nlp_DID, rport, rport_ids.roles); if ((rport->scsi_target_id != -1) && @@ -4184,7 +4191,7 @@ lpfc_unregister_remote_port(struct lpfc_nodelist *ndlp) ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_type); lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, - "3184 rport unregister x%06x, rport %p\n", + "3184 rport unregister x%06x, rport x%px\n", ndlp->nlp_DID, rport); fc_remote_port_delete(rport); @@ -4196,8 +4203,9 @@ static void lpfc_nlp_counters(struct lpfc_vport *vport, int state, int count) { struct Scsi_Host *shost = lpfc_shost_from_vport(vport); + unsigned long iflags; - spin_lock_irq(shost->host_lock); + spin_lock_irqsave(shost->host_lock, iflags); switch (state) { case NLP_STE_UNUSED_NODE: vport->fc_unused_cnt += count; @@ -4227,7 +4235,7 @@ lpfc_nlp_counters(struct lpfc_vport *vport, int state, int count) vport->fc_npr_cnt += count; break; } - spin_unlock_irq(shost->host_lock); + spin_unlock_irqrestore(shost->host_lock, iflags); } static void @@ -4480,9 +4488,21 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, return NULL; if (phba->sli_rev == LPFC_SLI_REV4) { - rpi = lpfc_sli4_alloc_rpi(vport->phba); - if (rpi == LPFC_RPI_ALLOC_ERROR) + if (ndlp->nlp_rpi == LPFC_RPI_ALLOC_ERROR) + rpi = lpfc_sli4_alloc_rpi(vport->phba); + else + rpi = ndlp->nlp_rpi; + + if (rpi == LPFC_RPI_ALLOC_ERROR) { + lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE, + "0359 %s: ndlp:x%px " + "usgmap:x%x refcnt:%d FAILED RPI " + " ALLOC\n", + __func__, + (void *)ndlp, ndlp->nlp_usg_map, + kref_read(&ndlp->kref)); return NULL; + } } spin_lock_irqsave(&phba->ndlp_lock, flags); @@ -4490,9 +4510,9 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if (NLP_CHK_FREE_REQ(ndlp)) { spin_unlock_irqrestore(&phba->ndlp_lock, flags); lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE, - "0277 lpfc_enable_node: ndlp:x%p " + "0277 %s: ndlp:x%px " "usgmap:x%x refcnt:%d\n", - (void *)ndlp, ndlp->nlp_usg_map, + __func__, (void *)ndlp, ndlp->nlp_usg_map, kref_read(&ndlp->kref)); goto free_rpi; } @@ -4500,9 +4520,9 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if (NLP_CHK_NODE_ACT(ndlp)) { spin_unlock_irqrestore(&phba->ndlp_lock, flags); lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE, - "0278 lpfc_enable_node: ndlp:x%p " + "0278 %s: ndlp:x%px " "usgmap:x%x refcnt:%d\n", - (void *)ndlp, ndlp->nlp_usg_map, + __func__, (void *)ndlp, ndlp->nlp_usg_map, kref_read(&ndlp->kref)); goto free_rpi; } @@ -4532,7 +4552,7 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_rpi = rpi; lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, "0008 rpi:%x DID:%x flg:%x refcnt:%d " - "map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID, + "map:%x x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); @@ -4541,6 +4561,14 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if (state != NLP_STE_UNUSED_NODE) lpfc_nlp_set_state(vport, ndlp, state); + else + lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, + "0013 rpi:%x DID:%x flg:%x refcnt:%d " + "map:%x x%px STATE=UNUSED\n", + ndlp->nlp_rpi, ndlp->nlp_DID, + ndlp->nlp_flag, + kref_read(&ndlp->kref), + ndlp->nlp_usg_map, ndlp); lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_NODE, "node enable: did:x%x", @@ -4548,8 +4576,10 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, return ndlp; free_rpi: - if (phba->sli_rev == LPFC_SLI_REV4) + if (phba->sli_rev == LPFC_SLI_REV4) { lpfc_sli4_free_rpi(vport->phba, rpi); + ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR; + } return NULL; } @@ -4797,7 +4827,7 @@ lpfc_nlp_logo_unreg(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) (ndlp->nlp_defer_did != NLP_EVT_NOTHING_PENDING)) { lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, "1434 UNREG cmpl deferred logo x%x " - "on NPort x%x Data: x%x %p\n", + "on NPort x%x Data: x%x x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_defer_did, ndlp); @@ -4805,11 +4835,54 @@ lpfc_nlp_logo_unreg(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) ndlp->nlp_defer_did = NLP_EVT_NOTHING_PENDING; lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0); } else { + if (ndlp->nlp_flag & NLP_RELEASE_RPI) { + lpfc_sli4_free_rpi(vport->phba, ndlp->nlp_rpi); + ndlp->nlp_flag &= ~NLP_RELEASE_RPI; + ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR; + } ndlp->nlp_flag &= ~NLP_UNREG_INP; } } /* + * Sets the mailbox completion handler to be used for the + * unreg_rpi command. The handler varies based on the state of + * the port and what will be happening to the rpi next. + */ +static void +lpfc_set_unreg_login_mbx_cmpl(struct lpfc_hba *phba, struct lpfc_vport *vport, + struct lpfc_nodelist *ndlp, LPFC_MBOXQ_t *mbox) +{ + unsigned long iflags; + + if (ndlp->nlp_flag & NLP_ISSUE_LOGO) { + mbox->ctx_ndlp = ndlp; + mbox->mbox_cmpl = lpfc_nlp_logo_unreg; + + } else if (phba->sli_rev == LPFC_SLI_REV4 && + (!(vport->load_flag & FC_UNLOADING)) && + (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) >= + LPFC_SLI_INTF_IF_TYPE_2) && + (kref_read(&ndlp->kref) > 0)) { + mbox->ctx_ndlp = lpfc_nlp_get(ndlp); + mbox->mbox_cmpl = lpfc_sli4_unreg_rpi_cmpl_clr; + } else { + if (vport->load_flag & FC_UNLOADING) { + if (phba->sli_rev == LPFC_SLI_REV4) { + spin_lock_irqsave(&vport->phba->ndlp_lock, + iflags); + ndlp->nlp_flag |= NLP_RELEASE_RPI; + spin_unlock_irqrestore(&vport->phba->ndlp_lock, + iflags); + } + lpfc_nlp_get(ndlp); + } + mbox->ctx_ndlp = ndlp; + mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl; + } +} + +/* * Free rpi associated with LPFC_NODELIST entry. * This routine is called from lpfc_freenode(), when we are removing * a LPFC_NODELIST entry. It is also called if the driver initiates a @@ -4829,7 +4902,8 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) if (ndlp->nlp_flag & NLP_RPI_REGISTERED || ndlp->nlp_flag & NLP_REG_LOGIN_SEND) { if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND) - lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, + lpfc_printf_vlog(vport, KERN_INFO, + LOG_NODE | LOG_DISCOVERY, "3366 RPI x%x needs to be " "unregistered nlp_flag x%x " "did x%x\n", @@ -4840,10 +4914,11 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) * no need to queue up another one. */ if (ndlp->nlp_flag & NLP_UNREG_INP) { - lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, + lpfc_printf_vlog(vport, KERN_INFO, + LOG_NODE | LOG_DISCOVERY, "1436 unreg_rpi SKIP UNREG x%x on " "NPort x%x deferred x%x flg x%x " - "Data: %p\n", + "Data: x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_defer_did, ndlp->nlp_flag, ndlp); @@ -4859,41 +4934,22 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) lpfc_unreg_login(phba, vport->vpi, rpi, mbox); mbox->vport = vport; - if (ndlp->nlp_flag & NLP_ISSUE_LOGO) { - mbox->ctx_ndlp = ndlp; - mbox->mbox_cmpl = lpfc_nlp_logo_unreg; - } else { - if (phba->sli_rev == LPFC_SLI_REV4 && - (!(vport->load_flag & FC_UNLOADING)) && - (bf_get(lpfc_sli_intf_if_type, - &phba->sli4_hba.sli_intf) >= - LPFC_SLI_INTF_IF_TYPE_2) && - (kref_read(&ndlp->kref) > 0)) { - mbox->ctx_ndlp = lpfc_nlp_get(ndlp); - mbox->mbox_cmpl = - lpfc_sli4_unreg_rpi_cmpl_clr; - /* - * accept PLOGIs after unreg_rpi_cmpl - */ - acc_plogi = 0; - } else if (vport->load_flag & FC_UNLOADING) { - mbox->ctx_ndlp = NULL; - mbox->mbox_cmpl = - lpfc_sli_def_mbox_cmpl; - } else { - mbox->ctx_ndlp = ndlp; - mbox->mbox_cmpl = - lpfc_sli_def_mbox_cmpl; - } - } + lpfc_set_unreg_login_mbx_cmpl(phba, vport, ndlp, mbox); + if (mbox->mbox_cmpl == lpfc_sli4_unreg_rpi_cmpl_clr) + /* + * accept PLOGIs after unreg_rpi_cmpl + */ + acc_plogi = 0; if (((ndlp->nlp_DID & Fabric_DID_MASK) != Fabric_DID_MASK) && (!(vport->fc_flag & FC_OFFLINE_MODE))) ndlp->nlp_flag |= NLP_UNREG_INP; - lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, + lpfc_printf_vlog(vport, KERN_INFO, + LOG_NODE | LOG_DISCOVERY, "1433 unreg_rpi UNREG x%x on " - "NPort x%x deferred flg x%x Data:%p\n", + "NPort x%x deferred flg x%x " + "Data:x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, ndlp); @@ -5025,6 +5081,7 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) struct lpfc_hba *phba = vport->phba; LPFC_MBOXQ_t *mb, *nextmb; struct lpfc_dmabuf *mp; + unsigned long iflags; /* Cleanup node for NPort <nlp_DID> */ lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, @@ -5034,16 +5091,16 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_state, ndlp->nlp_rpi); if (NLP_CHK_FREE_REQ(ndlp)) { lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE, - "0280 lpfc_cleanup_node: ndlp:x%p " + "0280 %s: ndlp:x%px " "usgmap:x%x refcnt:%d\n", - (void *)ndlp, ndlp->nlp_usg_map, + __func__, (void *)ndlp, ndlp->nlp_usg_map, kref_read(&ndlp->kref)); lpfc_dequeue_node(vport, ndlp); } else { lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE, - "0281 lpfc_cleanup_node: ndlp:x%p " + "0281 %s: ndlp:x%px " "usgmap:x%x refcnt:%d\n", - (void *)ndlp, ndlp->nlp_usg_map, + __func__, (void *)ndlp, ndlp->nlp_usg_map, kref_read(&ndlp->kref)); lpfc_disable_node(vport, ndlp); } @@ -5104,8 +5161,22 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) list_del_init(&ndlp->els_retry_evt.evt_listp); list_del_init(&ndlp->dev_loss_evt.evt_listp); lpfc_cleanup_vports_rrqs(vport, ndlp); - lpfc_unreg_rpi(vport, ndlp); - + if (phba->sli_rev == LPFC_SLI_REV4) + ndlp->nlp_flag |= NLP_RELEASE_RPI; + if (!lpfc_unreg_rpi(vport, ndlp)) { + /* Clean up unregistered and non freed rpis */ + if ((ndlp->nlp_flag & NLP_RELEASE_RPI) && + !(ndlp->nlp_rpi == LPFC_RPI_ALLOC_ERROR)) { + lpfc_sli4_free_rpi(vport->phba, + ndlp->nlp_rpi); + spin_lock_irqsave(&vport->phba->ndlp_lock, + iflags); + ndlp->nlp_flag &= ~NLP_RELEASE_RPI; + ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR; + spin_unlock_irqrestore(&vport->phba->ndlp_lock, + iflags); + } + } return 0; } @@ -5131,8 +5202,10 @@ lpfc_nlp_remove(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) /* For this case we need to cleanup the default rpi * allocated by the firmware. */ - lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, - "0005 rpi:%x DID:%x flg:%x %d map:%x %p\n", + lpfc_printf_vlog(vport, KERN_INFO, + LOG_NODE | LOG_DISCOVERY, + "0005 Cleanup Default rpi:x%x DID:x%x flg:x%x " + "ref %d map:x%x ndlp x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); @@ -5168,9 +5241,10 @@ lpfc_nlp_remove(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) * for registered rport so need to cleanup rport */ lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE, - "0940 removed node x%p DID x%x " - " rport not null %p\n", - ndlp, ndlp->nlp_DID, ndlp->rport); + "0940 removed node x%px DID x%x " + "rpi %d rport not null x%px\n", + ndlp, ndlp->nlp_DID, ndlp->nlp_rpi, + ndlp->rport); rport = ndlp->rport; rdata = rport->dd_data; rdata->pnode = NULL; @@ -5243,15 +5317,15 @@ __lpfc_findnode_did(struct lpfc_vport *vport, uint32_t did) list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) { if (lpfc_matchdid(vport, ndlp, did)) { - data1 = (((uint32_t) ndlp->nlp_state << 24) | - ((uint32_t) ndlp->nlp_xri << 16) | - ((uint32_t) ndlp->nlp_type << 8) | - ((uint32_t) ndlp->nlp_rpi & 0xff)); + data1 = (((uint32_t)ndlp->nlp_state << 24) | + ((uint32_t)ndlp->nlp_xri << 16) | + ((uint32_t)ndlp->nlp_type << 8) | + ((uint32_t)ndlp->nlp_usg_map & 0xff)); lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, "0929 FIND node DID " - "Data: x%p x%x x%x x%x %p\n", + "Data: x%px x%x x%x x%x x%x x%px\n", ndlp, ndlp->nlp_DID, - ndlp->nlp_flag, data1, + ndlp->nlp_flag, data1, ndlp->nlp_rpi, ndlp->active_rrqs_xri_bitmap); return ndlp; } @@ -5296,7 +5370,7 @@ lpfc_findnode_mapped(struct lpfc_vport *vport) spin_unlock_irqrestore(shost->host_lock, iflags); lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, "2025 FIND node DID " - "Data: x%p x%x x%x x%x %p\n", + "Data: x%px x%x x%x x%x x%px\n", ndlp, ndlp->nlp_DID, ndlp->nlp_flag, data1, ndlp->active_rrqs_xri_bitmap); @@ -5328,6 +5402,13 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did) if (!ndlp) return NULL; lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE); + + lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, + "6453 Setup New Node 2B_DISC x%x " + "Data:x%x x%x x%x\n", + ndlp->nlp_DID, ndlp->nlp_flag, + ndlp->nlp_state, vport->fc_flag); + spin_lock_irq(shost->host_lock); ndlp->nlp_flag |= NLP_NPR_2B_DISC; spin_unlock_irq(shost->host_lock); @@ -5336,8 +5417,17 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did) if (vport->phba->nvmet_support) return NULL; ndlp = lpfc_enable_node(vport, ndlp, NLP_STE_NPR_NODE); - if (!ndlp) + if (!ndlp) { + lpfc_printf_vlog(vport, KERN_WARNING, LOG_SLI, + "0014 Could not enable ndlp\n"); return NULL; + } + lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, + "6454 Setup Enabled Node 2B_DISC x%x " + "Data:x%x x%x x%x\n", + ndlp->nlp_DID, ndlp->nlp_flag, + ndlp->nlp_state, vport->fc_flag); + spin_lock_irq(shost->host_lock); ndlp->nlp_flag |= NLP_NPR_2B_DISC; spin_unlock_irq(shost->host_lock); @@ -5357,6 +5447,12 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did) */ lpfc_cancel_retry_delay_tmo(vport, ndlp); + lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, + "6455 Setup RSCN Node 2B_DISC x%x " + "Data:x%x x%x x%x\n", + ndlp->nlp_DID, ndlp->nlp_flag, + ndlp->nlp_state, vport->fc_flag); + /* NVME Target mode waits until rport is known to be * impacted by the RSCN before it transitions. No * active management - just go to NPR provided the @@ -5368,15 +5464,32 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did) /* If we've already received a PLOGI from this NPort * we don't need to try to discover it again. */ - if (ndlp->nlp_flag & NLP_RCV_PLOGI) + if (ndlp->nlp_flag & NLP_RCV_PLOGI && + !(ndlp->nlp_type & + (NLP_FCP_TARGET | NLP_NVME_TARGET))) return NULL; + ndlp->nlp_prev_state = ndlp->nlp_state; + lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE); + spin_lock_irq(shost->host_lock); ndlp->nlp_flag |= NLP_NPR_2B_DISC; spin_unlock_irq(shost->host_lock); - } else + } else { + lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, + "6456 Skip Setup RSCN Node x%x " + "Data:x%x x%x x%x\n", + ndlp->nlp_DID, ndlp->nlp_flag, + ndlp->nlp_state, vport->fc_flag); ndlp = NULL; + } } else { + lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, + "6457 Setup Active Node 2B_DISC x%x " + "Data:x%x x%x x%x\n", + ndlp->nlp_DID, ndlp->nlp_flag, + ndlp->nlp_state, vport->fc_flag); + /* If the initiator received a PLOGI from this NPort or if the * initiator is already in the process of discovery on it, * there's no need to try to discover it again. @@ -5528,10 +5641,10 @@ lpfc_disc_start(struct lpfc_vport *vport) /* Start Discovery state <hba_state> */ lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, - "0202 Start Discovery hba state x%x " - "Data: x%x x%x x%x\n", + "0202 Start Discovery port state x%x " + "flg x%x Data: x%x x%x x%x\n", vport->port_state, vport->fc_flag, vport->fc_plogi_cnt, - vport->fc_adisc_cnt); + vport->fc_adisc_cnt, vport->fc_npr_cnt); /* First do ADISCs - if any */ num_sent = lpfc_els_disc_adisc(vport); @@ -5959,8 +6072,8 @@ lpfc_mbx_cmpl_fdmi_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) ndlp->nlp_flag |= NLP_RPI_REGISTERED; ndlp->nlp_type |= NLP_FABRIC; lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE); - lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, - "0004 rpi:%x DID:%x flg:%x %d map:%x %p\n", + lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY, + "0004 rpi:%x DID:%x flg:%x %d map:%x x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); @@ -6014,8 +6127,8 @@ __lpfc_find_node(struct lpfc_vport *vport, node_filter filter, void *param) list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) { if (filter(ndlp, param)) { lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, - "3185 FIND node filter %p DID " - "ndlp %p did x%x flg x%x st x%x " + "3185 FIND node filter %ps DID " + "ndlp x%px did x%x flg x%x st x%x " "xri x%x type x%x rpi x%x\n", filter, ndlp, ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state, @@ -6025,7 +6138,7 @@ __lpfc_find_node(struct lpfc_vport *vport, node_filter filter, void *param) } } lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, - "3186 FIND node filter %p NOT FOUND.\n", filter); + "3186 FIND node filter %ps NOT FOUND.\n", filter); return NULL; } @@ -6065,10 +6178,11 @@ lpfc_findnode_rpi(struct lpfc_vport *vport, uint16_t rpi) { struct Scsi_Host *shost = lpfc_shost_from_vport(vport); struct lpfc_nodelist *ndlp; + unsigned long flags; - spin_lock_irq(shost->host_lock); + spin_lock_irqsave(shost->host_lock, flags); ndlp = __lpfc_findnode_rpi(vport, rpi); - spin_unlock_irq(shost->host_lock); + spin_unlock_irqrestore(shost->host_lock, flags); return ndlp; } @@ -6147,12 +6261,12 @@ lpfc_nlp_init(struct lpfc_vport *vport, uint32_t did) INIT_LIST_HEAD(&ndlp->nlp_listp); if (vport->phba->sli_rev == LPFC_SLI_REV4) { ndlp->nlp_rpi = rpi; - lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, - "0007 rpi:%x DID:%x flg:%x refcnt:%d " - "map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID, - ndlp->nlp_flag, - kref_read(&ndlp->kref), - ndlp->nlp_usg_map, ndlp); + lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY, + "0007 Init New ndlp x%px, rpi:x%x DID:%x " + "flg:x%x refcnt:%d map:x%x\n", + ndlp, ndlp->nlp_rpi, ndlp->nlp_DID, + ndlp->nlp_flag, kref_read(&ndlp->kref), + ndlp->nlp_usg_map); ndlp->active_rrqs_xri_bitmap = mempool_alloc(vport->phba->active_rrq_pool, @@ -6187,8 +6301,9 @@ lpfc_nlp_release(struct kref *kref) ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_type); lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, - "0279 lpfc_nlp_release: ndlp:x%p did %x " + "0279 %s: ndlp:x%px did %x " "usgmap:x%x refcnt:%d rpi:%x\n", + __func__, (void *)ndlp, ndlp->nlp_DID, ndlp->nlp_usg_map, kref_read(&ndlp->kref), ndlp->nlp_rpi); @@ -6200,8 +6315,6 @@ lpfc_nlp_release(struct kref *kref) spin_lock_irqsave(&phba->ndlp_lock, flags); NLP_CLR_NODE_ACT(ndlp); spin_unlock_irqrestore(&phba->ndlp_lock, flags); - if (phba->sli_rev == LPFC_SLI_REV4) - lpfc_sli4_free_rpi(phba, ndlp->nlp_rpi); /* free ndlp memory for final ndlp release */ if (NLP_CHK_FREE_REQ(ndlp)) { @@ -6237,9 +6350,9 @@ lpfc_nlp_get(struct lpfc_nodelist *ndlp) if (!NLP_CHK_NODE_ACT(ndlp) || NLP_CHK_FREE_ACK(ndlp)) { spin_unlock_irqrestore(&phba->ndlp_lock, flags); lpfc_printf_vlog(ndlp->vport, KERN_WARNING, LOG_NODE, - "0276 lpfc_nlp_get: ndlp:x%p " + "0276 %s: ndlp:x%px " "usgmap:x%x refcnt:%d\n", - (void *)ndlp, ndlp->nlp_usg_map, + __func__, (void *)ndlp, ndlp->nlp_usg_map, kref_read(&ndlp->kref)); return NULL; } else @@ -6265,9 +6378,9 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp) return 1; lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE, - "node put: did:x%x flg:x%x refcnt:x%x", - ndlp->nlp_DID, ndlp->nlp_flag, - kref_read(&ndlp->kref)); + "node put: did:x%x flg:x%x refcnt:x%x", + ndlp->nlp_DID, ndlp->nlp_flag, + kref_read(&ndlp->kref)); phba = ndlp->phba; spin_lock_irqsave(&phba->ndlp_lock, flags); /* Check the ndlp memory free acknowledge flag to avoid the @@ -6277,9 +6390,9 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp) if (NLP_CHK_FREE_ACK(ndlp)) { spin_unlock_irqrestore(&phba->ndlp_lock, flags); lpfc_printf_vlog(ndlp->vport, KERN_WARNING, LOG_NODE, - "0274 lpfc_nlp_put: ndlp:x%p " + "0274 %s: ndlp:x%px " "usgmap:x%x refcnt:%d\n", - (void *)ndlp, ndlp->nlp_usg_map, + __func__, (void *)ndlp, ndlp->nlp_usg_map, kref_read(&ndlp->kref)); return 1; } @@ -6290,9 +6403,9 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp) if (NLP_CHK_IACT_REQ(ndlp)) { spin_unlock_irqrestore(&phba->ndlp_lock, flags); lpfc_printf_vlog(ndlp->vport, KERN_WARNING, LOG_NODE, - "0275 lpfc_nlp_put: ndlp:x%p " + "0275 %s: ndlp:x%px " "usgmap:x%x refcnt:%d\n", - (void *)ndlp, ndlp->nlp_usg_map, + __func__, (void *)ndlp, ndlp->nlp_usg_map, kref_read(&ndlp->kref)); return 1; } @@ -6382,7 +6495,8 @@ lpfc_fcf_inuse(struct lpfc_hba *phba) goto out; } else if (ndlp->nlp_flag & NLP_RPI_REGISTERED) { ret = 1; - lpfc_printf_log(phba, KERN_INFO, LOG_ELS, + lpfc_printf_log(phba, KERN_INFO, + LOG_NODE | LOG_DISCOVERY, "2624 RPI %x DID %x flag %x " "still logged in\n", ndlp->nlp_rpi, ndlp->nlp_DID, diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h index 5b439a6dcde1..436cdc8c5ef4 100644 --- a/drivers/scsi/lpfc/lpfc_hw.h +++ b/drivers/scsi/lpfc/lpfc_hw.h @@ -843,7 +843,7 @@ typedef struct _ADISC { /* Structure is in Big Endian format */ struct lpfc_name portName; struct lpfc_name nodeName; uint32_t DID; -} ADISC; +} __packed ADISC; typedef struct _FARP { /* Structure is in Big Endian format */ uint32_t Mflags:8; @@ -873,7 +873,7 @@ typedef struct _FAN { /* Structure is in Big Endian format */ uint32_t Fdid; struct lpfc_name FportName; struct lpfc_name FnodeName; -} FAN; +} __packed FAN; typedef struct _SCR { /* Structure is in Big Endian format */ uint8_t resvd1; @@ -917,7 +917,7 @@ typedef struct _RNID { /* Structure is in Big Endian format */ union { RNID_TOP_DISC topologyDisc; /* topology disc (0xdf) */ } un; -} RNID; +} __packed RNID; typedef struct _RPS { /* Structure is in Big Endian format */ union { diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h index 77f9a55a3f54..9a064b96e570 100644 --- a/drivers/scsi/lpfc/lpfc_hw4.h +++ b/drivers/scsi/lpfc/lpfc_hw4.h @@ -210,7 +210,6 @@ struct lpfc_sli_intf { #define LPFC_MAX_IMAX 5000000 #define LPFC_DEF_IMAX 0 -#define LPFC_IMAX_THRESHOLD 1000 #define LPFC_MAX_AUTO_EQ_DELAY 120 #define LPFC_EQ_DELAY_STEP 15 #define LPFC_EQD_ISR_TRIGGER 20000 @@ -2050,6 +2049,23 @@ struct sli4_sge { /* SLI-4 */ uint32_t sge_len; }; +struct sli4_hybrid_sgl { + struct list_head list_node; + struct sli4_sge *dma_sgl; + dma_addr_t dma_phys_sgl; +}; + +struct fcp_cmd_rsp_buf { + struct list_head list_node; + + /* for storing cmd/rsp dma alloc'ed virt_addr */ + struct fcp_cmnd *fcp_cmnd; + struct fcp_rsp *fcp_rsp; + + /* for storing this cmd/rsp's dma mapped phys addr from per CPU pool */ + dma_addr_t fcp_cmd_rsp_dma_handle; +}; + struct sli4_sge_diseed { /* SLI-4 */ uint32_t ref_tag; uint32_t ref_tag_tran; @@ -2303,6 +2319,7 @@ struct lpfc_mbx_redisc_fcf_tbl { #define ADD_STATUS_OPERATION_ALREADY_ACTIVE 0x67 #define ADD_STATUS_FW_NOT_SUPPORTED 0xEB #define ADD_STATUS_INVALID_REQUEST 0x4B +#define ADD_STATUS_FW_DOWNLOAD_HW_DISABLED 0x58 struct lpfc_mbx_sli4_config { struct mbox_header header; @@ -2792,6 +2809,15 @@ struct lpfc_mbx_read_config { #define lpfc_mbx_rd_conf_trunk_SHIFT 12 #define lpfc_mbx_rd_conf_trunk_MASK 0x0000000F #define lpfc_mbx_rd_conf_trunk_WORD word2 +#define lpfc_mbx_rd_conf_pt_SHIFT 20 +#define lpfc_mbx_rd_conf_pt_MASK 0x00000003 +#define lpfc_mbx_rd_conf_pt_WORD word2 +#define lpfc_mbx_rd_conf_tf_SHIFT 22 +#define lpfc_mbx_rd_conf_tf_MASK 0x00000001 +#define lpfc_mbx_rd_conf_tf_WORD word2 +#define lpfc_mbx_rd_conf_ptv_SHIFT 23 +#define lpfc_mbx_rd_conf_ptv_MASK 0x00000001 +#define lpfc_mbx_rd_conf_ptv_WORD word2 #define lpfc_mbx_rd_conf_topology_SHIFT 24 #define lpfc_mbx_rd_conf_topology_MASK 0x000000FF #define lpfc_mbx_rd_conf_topology_WORD word2 @@ -3449,6 +3475,9 @@ struct lpfc_sli4_parameters { #define cfg_xib_SHIFT 4 #define cfg_xib_MASK 0x00000001 #define cfg_xib_WORD word19 +#define cfg_xpsgl_SHIFT 6 +#define cfg_xpsgl_MASK 0x00000001 +#define cfg_xpsgl_WORD word19 #define cfg_eqdr_SHIFT 8 #define cfg_eqdr_MASK 0x00000001 #define cfg_eqdr_WORD word19 @@ -3459,6 +3488,13 @@ struct lpfc_sli4_parameters { #define cfg_bv1s_SHIFT 10 #define cfg_bv1s_MASK 0x00000001 #define cfg_bv1s_WORD word19 +#define cfg_pvl_SHIFT 13 +#define cfg_pvl_MASK 0x00000001 +#define cfg_pvl_WORD word19 + +#define cfg_nsler_SHIFT 12 +#define cfg_nsler_MASK 0x00000001 +#define cfg_nsler_WORD word19 uint32_t word20; #define cfg_max_tow_xri_SHIFT 0 @@ -3494,6 +3530,7 @@ struct lpfc_sli4_parameters { #define LPFC_SET_UE_RECOVERY 0x10 #define LPFC_SET_MDS_DIAGS 0x11 +#define LPFC_SET_DUAL_DUMP 0x1e struct lpfc_mbx_set_feature { struct mbox_header header; uint32_t feature; @@ -3508,6 +3545,15 @@ struct lpfc_mbx_set_feature { #define lpfc_mbx_set_feature_mds_deep_loopbk_SHIFT 1 #define lpfc_mbx_set_feature_mds_deep_loopbk_MASK 0x00000001 #define lpfc_mbx_set_feature_mds_deep_loopbk_WORD word6 +#define lpfc_mbx_set_feature_dd_SHIFT 0 +#define lpfc_mbx_set_feature_dd_MASK 0x00000001 +#define lpfc_mbx_set_feature_dd_WORD word6 +#define lpfc_mbx_set_feature_ddquery_SHIFT 1 +#define lpfc_mbx_set_feature_ddquery_MASK 0x00000001 +#define lpfc_mbx_set_feature_ddquery_WORD word6 +#define LPFC_DISABLE_DUAL_DUMP 0 +#define LPFC_ENABLE_DUAL_DUMP 1 +#define LPFC_QUERY_OP_DUAL_DUMP 2 uint32_t word7; #define lpfc_mbx_set_feature_UERP_SHIFT 0 #define lpfc_mbx_set_feature_UERP_MASK 0x0000ffff @@ -3879,6 +3925,9 @@ struct lpfc_mbx_wr_object { #define LPFC_CHANGE_STATUS_FW_RESET 0x02 #define LPFC_CHANGE_STATUS_PORT_MIGRATION 0x04 #define LPFC_CHANGE_STATUS_PCI_RESET 0x05 +#define lpfc_wr_object_csf_SHIFT 8 +#define lpfc_wr_object_csf_MASK 0x00000001 +#define lpfc_wr_object_csf_WORD word5 } response; } u; }; @@ -4237,6 +4286,8 @@ struct lpfc_acqe_sli { #define LPFC_SLI_EVENT_TYPE_DIAG_DUMP 0x5 #define LPFC_SLI_EVENT_TYPE_MISCONFIGURED 0x9 #define LPFC_SLI_EVENT_TYPE_REMOTE_DPORT 0xA +#define LPFC_SLI_EVENT_TYPE_MISCONF_FAWWN 0xF +#define LPFC_SLI_EVENT_TYPE_EEPROM_FAILURE 0x10 }; /* @@ -4314,6 +4365,12 @@ struct wqe_common { #define wqe_rcvoxid_SHIFT 16 #define wqe_rcvoxid_MASK 0x0000FFFF #define wqe_rcvoxid_WORD word9 +#define wqe_sof_SHIFT 24 +#define wqe_sof_MASK 0x000000FF +#define wqe_sof_WORD word9 +#define wqe_eof_SHIFT 16 +#define wqe_eof_MASK 0x000000FF +#define wqe_eof_WORD word9 uint32_t word10; #define wqe_ebde_cnt_SHIFT 0 #define wqe_ebde_cnt_MASK 0x0000000f @@ -4595,6 +4652,7 @@ struct lpfc_nvme_prli { #define prli_type_code_WORD word1 uint32_t word_rsvd2; uint32_t word_rsvd3; + uint32_t word4; #define prli_fba_SHIFT 0 #define prli_fba_MASK 0x00000001 @@ -4611,6 +4669,9 @@ struct lpfc_nvme_prli { #define prli_conf_SHIFT 7 #define prli_conf_MASK 0x00000001 #define prli_conf_WORD word4 +#define prli_nsler_SHIFT 8 +#define prli_nsler_MASK 0x00000001 +#define prli_nsler_WORD word4 uint32_t word5; #define prli_fb_sz_SHIFT 0 #define prli_fb_sz_MASK 0x0000ffff @@ -4625,6 +4686,7 @@ struct create_xri_wqe { uint32_t rsvd_12_15[4]; /* word 12-15 */ }; +#define INHIBIT_ABORT 1 #define T_REQUEST_TAG 3 #define T_XRI_TAG 1 @@ -4773,8 +4835,8 @@ union lpfc_wqe128 { struct send_frame_wqe send_frame; }; -#define MAGIC_NUMER_G6 0xFEAA0003 -#define MAGIC_NUMER_G7 0xFEAA0005 +#define MAGIC_NUMBER_G6 0xFEAA0003 +#define MAGIC_NUMBER_G7 0xFEAA0005 struct lpfc_grp_hdr { uint32_t size; diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index a7549ae32542..5a605773dd0a 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -39,6 +39,9 @@ #include <linux/msi.h> #include <linux/irq.h> #include <linux/bitops.h> +#include <linux/crash_dump.h> +#include <linux/cpu.h> +#include <linux/cpuhotplug.h> #include <scsi/scsi.h> #include <scsi/scsi_device.h> @@ -65,15 +68,13 @@ #include "lpfc_version.h" #include "lpfc_ids.h" -char *_dump_buf_data; -unsigned long _dump_buf_data_order; -char *_dump_buf_dif; -unsigned long _dump_buf_dif_order; -spinlock_t _dump_buf_lock; - +static enum cpuhp_state lpfc_cpuhp_state; /* Used when mapping IRQ vectors in a driver centric manner */ static uint32_t lpfc_present_cpu; +static void __lpfc_cpuhp_remove(struct lpfc_hba *phba); +static void lpfc_cpuhp_remove(struct lpfc_hba *phba); +static void lpfc_cpuhp_add(struct lpfc_hba *phba); static void lpfc_get_hba_model_desc(struct lpfc_hba *, uint8_t *, uint8_t *); static int lpfc_post_rcv_buf(struct lpfc_hba *); static int lpfc_sli4_queue_verify(struct lpfc_hba *); @@ -1081,8 +1082,8 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba) for (idx = 0; idx < phba->cfg_hdw_queue; idx++) { qp = &phba->sli4_hba.hdwq[idx]; - spin_lock(&qp->abts_scsi_buf_list_lock); - list_splice_init(&qp->lpfc_abts_scsi_buf_list, + spin_lock(&qp->abts_io_buf_list_lock); + list_splice_init(&qp->lpfc_abts_io_buf_list, &aborts); list_for_each_entry_safe(psb, psb_next, &aborts, list) { @@ -1093,29 +1094,11 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba) spin_lock(&qp->io_buf_list_put_lock); list_splice_init(&aborts, &qp->lpfc_io_buf_list_put); qp->put_io_bufs += qp->abts_scsi_io_bufs; + qp->put_io_bufs += qp->abts_nvme_io_bufs; qp->abts_scsi_io_bufs = 0; + qp->abts_nvme_io_bufs = 0; spin_unlock(&qp->io_buf_list_put_lock); - spin_unlock(&qp->abts_scsi_buf_list_lock); - - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - spin_lock(&qp->abts_nvme_buf_list_lock); - list_splice_init(&qp->lpfc_abts_nvme_buf_list, - &nvme_aborts); - list_for_each_entry_safe(psb, psb_next, &nvme_aborts, - list) { - psb->pCmd = NULL; - psb->status = IOSTAT_SUCCESS; - cnt++; - } - spin_lock(&qp->io_buf_list_put_lock); - qp->put_io_bufs += qp->abts_nvme_io_bufs; - qp->abts_nvme_io_bufs = 0; - list_splice_init(&nvme_aborts, - &qp->lpfc_io_buf_list_put); - spin_unlock(&qp->io_buf_list_put_lock); - spin_unlock(&qp->abts_nvme_buf_list_lock); - - } + spin_unlock(&qp->abts_io_buf_list_lock); } spin_unlock_irq(&phba->hbalock); @@ -1258,7 +1241,7 @@ lpfc_hb_eq_delay_work(struct work_struct *work) struct lpfc_hba, eq_delay_work); struct lpfc_eq_intr_info *eqi, *eqi_new; struct lpfc_queue *eq, *eq_next; - unsigned char *eqcnt = NULL; + unsigned char *ena_delay = NULL; uint32_t usdelay; int i; @@ -1269,35 +1252,36 @@ lpfc_hb_eq_delay_work(struct work_struct *work) phba->pport->fc_flag & FC_OFFLINE_MODE) goto requeue; - eqcnt = kcalloc(num_possible_cpus(), sizeof(unsigned char), - GFP_KERNEL); - if (!eqcnt) + ena_delay = kcalloc(phba->sli4_hba.num_possible_cpu, sizeof(*ena_delay), + GFP_KERNEL); + if (!ena_delay) goto requeue; - /* Loop thru all IRQ vectors */ for (i = 0; i < phba->cfg_irq_chann; i++) { /* Get the EQ corresponding to the IRQ vector */ eq = phba->sli4_hba.hba_eq_hdl[i].eq; - if (eq && eqcnt[eq->last_cpu] < 2) - eqcnt[eq->last_cpu]++; - continue; + if (!eq) + continue; + if (eq->q_mode || eq->q_flag & HBA_EQ_DELAY_CHK) { + eq->q_flag &= ~HBA_EQ_DELAY_CHK; + ena_delay[eq->last_cpu] = 1; + } } for_each_present_cpu(i) { - if (phba->cfg_irq_chann > 1 && eqcnt[i] < 2) - continue; - eqi = per_cpu_ptr(phba->sli4_hba.eq_info, i); - - usdelay = (eqi->icnt / LPFC_IMAX_THRESHOLD) * - LPFC_EQ_DELAY_STEP; - if (usdelay > LPFC_MAX_AUTO_EQ_DELAY) - usdelay = LPFC_MAX_AUTO_EQ_DELAY; + if (ena_delay[i]) { + usdelay = (eqi->icnt >> 10) * LPFC_EQ_DELAY_STEP; + if (usdelay > LPFC_MAX_AUTO_EQ_DELAY) + usdelay = LPFC_MAX_AUTO_EQ_DELAY; + } else { + usdelay = 0; + } eqi->icnt = 0; list_for_each_entry_safe(eq, eq_next, &eqi->list, cpu_list) { - if (eq->last_cpu != i) { + if (unlikely(eq->last_cpu != i)) { eqi_new = per_cpu_ptr(phba->sli4_hba.eq_info, eq->last_cpu); list_move_tail(&eq->cpu_list, &eqi_new->list); @@ -1309,7 +1293,7 @@ lpfc_hb_eq_delay_work(struct work_struct *work) } } - kfree(eqcnt); + kfree(ena_delay); requeue: queue_delayed_work(phba->wq, &phba->eq_delay_work, @@ -1378,7 +1362,7 @@ lpfc_hb_timeout_handler(struct lpfc_hba *phba) if (vports != NULL) for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) { lpfc_rcv_seq_check_edtov(vports[i]); - lpfc_fdmi_num_disc_check(vports[i]); + lpfc_fdmi_change_check(vports[i]); } lpfc_destroy_vport_work_array(phba, vports); @@ -1535,6 +1519,7 @@ lpfc_sli4_offline_eratt(struct lpfc_hba *phba) spin_unlock_irq(&phba->hbalock); lpfc_offline_prep(phba, LPFC_MBX_NO_WAIT); + lpfc_sli_flush_io_rings(phba); lpfc_offline(phba); lpfc_hba_down_post(phba); lpfc_unblock_mgmt_io(phba); @@ -1796,6 +1781,7 @@ lpfc_sli4_port_sta_fn_reset(struct lpfc_hba *phba, int mbx_action, "2887 Reset Needed: Attempting Port " "Recovery...\n"); lpfc_offline_prep(phba, mbx_action); + lpfc_sli_flush_io_rings(phba); lpfc_offline(phba); /* release interrupt for possible resource change */ lpfc_sli4_disable_intr(phba); @@ -1915,7 +1901,7 @@ lpfc_handle_eratt_s4(struct lpfc_hba *phba) lpfc_printf_log(phba, KERN_ERR, LOG_INIT, "7624 Firmware not ready: Failing UE recovery," " waited %dSec", i); - lpfc_sli4_offline_eratt(phba); + phba->link_state = LPFC_HBA_ERROR; break; case LPFC_SLI_INTF_IF_TYPE_2: @@ -1989,9 +1975,8 @@ lpfc_handle_eratt_s4(struct lpfc_hba *phba) } /* fall through for not able to recover */ lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "3152 Unrecoverable error, bring the port " - "offline\n"); - lpfc_sli4_offline_eratt(phba); + "3152 Unrecoverable error\n"); + phba->link_state = LPFC_HBA_ERROR; break; case LPFC_SLI_INTF_IF_TYPE_1: default: @@ -2863,7 +2848,7 @@ lpfc_cleanup(struct lpfc_vport *vport) &vport->fc_nodes, nlp_listp) { lpfc_printf_vlog(ndlp->vport, KERN_ERR, LOG_NODE, - "0282 did:x%x ndlp:x%p " + "0282 did:x%x ndlp:x%px " "usgmap:x%x refcnt:%d\n", ndlp->nlp_DID, (void *)ndlp, ndlp->nlp_usg_map, @@ -3065,11 +3050,12 @@ lpfc_sli4_node_prep(struct lpfc_hba *phba) continue; } ndlp->nlp_rpi = rpi; - lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, - "0009 rpi:%x DID:%x " - "flg:%x map:%x %p\n", ndlp->nlp_rpi, - ndlp->nlp_DID, ndlp->nlp_flag, - ndlp->nlp_usg_map, ndlp); + lpfc_printf_vlog(ndlp->vport, KERN_INFO, + LOG_NODE | LOG_DISCOVERY, + "0009 Assign RPI x%x to ndlp x%px " + "DID:x%06x flg:x%x map:x%x\n", + ndlp->nlp_rpi, ndlp, ndlp->nlp_DID, + ndlp->nlp_flag, ndlp->nlp_usg_map); } } lpfc_destroy_vport_work_array(phba, vports); @@ -3252,12 +3238,8 @@ static void lpfc_destroy_multixri_pools(struct lpfc_hba *phba) if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) lpfc_destroy_expedite_pool(phba); - if (!(phba->pport->load_flag & FC_UNLOADING)) { - lpfc_sli_flush_fcp_rings(phba); - - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) - lpfc_sli_flush_nvme_rings(phba); - } + if (!(phba->pport->load_flag & FC_UNLOADING)) + lpfc_sli_flush_io_rings(phba); hwq_count = phba->cfg_hdw_queue; @@ -3403,6 +3385,8 @@ lpfc_online(struct lpfc_hba *phba) if (phba->cfg_xri_rebalancing) lpfc_create_multixri_pools(phba); + lpfc_cpuhp_add(phba); + lpfc_unblock_mgmt_io(phba); return 0; } @@ -3469,10 +3453,15 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) list_for_each_entry_safe(ndlp, next_ndlp, &vports[i]->fc_nodes, nlp_listp) { - if (!NLP_CHK_NODE_ACT(ndlp)) - continue; - if (ndlp->nlp_state == NLP_STE_UNUSED_NODE) + if ((!NLP_CHK_NODE_ACT(ndlp)) || + ndlp->nlp_state == NLP_STE_UNUSED_NODE) { + /* Driver must assume RPI is invalid for + * any unused or inactive node. + */ + ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR; continue; + } + if (ndlp->nlp_type & NLP_FABRIC) { lpfc_disc_state_machine(vports[i], ndlp, NULL, NLP_EVT_DEVICE_RECOVERY); @@ -3488,16 +3477,16 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) * comes back online. */ if (phba->sli_rev == LPFC_SLI_REV4) { - lpfc_printf_vlog(ndlp->vport, - KERN_INFO, LOG_NODE, - "0011 lpfc_offline: " - "ndlp:x%p did %x " - "usgmap:x%x rpi:%x\n", - ndlp, ndlp->nlp_DID, - ndlp->nlp_usg_map, - ndlp->nlp_rpi); - + lpfc_printf_vlog(ndlp->vport, KERN_INFO, + LOG_NODE | LOG_DISCOVERY, + "0011 Free RPI x%x on " + "ndlp:x%px did x%x " + "usgmap:x%x\n", + ndlp->nlp_rpi, ndlp, + ndlp->nlp_DID, + ndlp->nlp_usg_map); lpfc_sli4_free_rpi(phba, ndlp->nlp_rpi); + ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR; } lpfc_unreg_rpi(vports[i], ndlp); } @@ -3561,6 +3550,7 @@ lpfc_offline(struct lpfc_hba *phba) spin_unlock_irq(shost->host_lock); } lpfc_destroy_vport_work_array(phba, vports); + __lpfc_cpuhp_remove(phba); if (phba->cfg_xri_rebalancing) lpfc_destroy_multixri_pools(phba); @@ -3636,6 +3626,9 @@ lpfc_io_free(struct lpfc_hba *phba) qp->put_io_bufs--; dma_pool_free(phba->lpfc_sg_dma_buf_pool, lpfc_ncmd->data, lpfc_ncmd->dma_handle); + if (phba->cfg_xpsgl && !phba->nvmet_support) + lpfc_put_sgl_per_hdwq(phba, lpfc_ncmd); + lpfc_put_cmd_rsp_buf_per_hdwq(phba, lpfc_ncmd); kfree(lpfc_ncmd); qp->total_io_bufs--; } @@ -3649,6 +3642,9 @@ lpfc_io_free(struct lpfc_hba *phba) qp->get_io_bufs--; dma_pool_free(phba->lpfc_sg_dma_buf_pool, lpfc_ncmd->data, lpfc_ncmd->dma_handle); + if (phba->cfg_xpsgl && !phba->nvmet_support) + lpfc_put_sgl_per_hdwq(phba, lpfc_ncmd); + lpfc_put_cmd_rsp_buf_per_hdwq(phba, lpfc_ncmd); kfree(lpfc_ncmd); qp->total_io_bufs--; } @@ -4097,18 +4093,9 @@ lpfc_new_io_buf(struct lpfc_hba *phba, int num_to_alloc) LIST_HEAD(post_nblist); LIST_HEAD(nvme_nblist); - /* Sanity check to ensure our sizing is right for both SCSI and NVME */ - if (sizeof(struct lpfc_io_buf) > LPFC_COMMON_IO_BUF_SZ) { - lpfc_printf_log(phba, KERN_ERR, LOG_FCP, - "6426 Common buffer size %zd exceeds %d\n", - sizeof(struct lpfc_io_buf), - LPFC_COMMON_IO_BUF_SZ); - return 0; - } - phba->sli4_hba.io_xri_cnt = 0; for (bcnt = 0; bcnt < num_to_alloc; bcnt++) { - lpfc_ncmd = kzalloc(LPFC_COMMON_IO_BUF_SZ, GFP_KERNEL); + lpfc_ncmd = kzalloc(sizeof(*lpfc_ncmd), GFP_KERNEL); if (!lpfc_ncmd) break; /* @@ -4124,22 +4111,30 @@ lpfc_new_io_buf(struct lpfc_hba *phba, int num_to_alloc) break; } - /* - * 4K Page alignment is CRITICAL to BlockGuard, double check - * to be sure. - */ - if ((phba->sli3_options & LPFC_SLI3_BG_ENABLED) && - (((unsigned long)(lpfc_ncmd->data) & - (unsigned long)(SLI4_PAGE_SIZE - 1)) != 0)) { - lpfc_printf_log(phba, KERN_ERR, LOG_FCP, - "3369 Memory alignment err: addr=%lx\n", - (unsigned long)lpfc_ncmd->data); - dma_pool_free(phba->lpfc_sg_dma_buf_pool, - lpfc_ncmd->data, lpfc_ncmd->dma_handle); - kfree(lpfc_ncmd); - break; + if (phba->cfg_xpsgl && !phba->nvmet_support) { + INIT_LIST_HEAD(&lpfc_ncmd->dma_sgl_xtra_list); + } else { + /* + * 4K Page alignment is CRITICAL to BlockGuard, double + * check to be sure. + */ + if ((phba->sli3_options & LPFC_SLI3_BG_ENABLED) && + (((unsigned long)(lpfc_ncmd->data) & + (unsigned long)(SLI4_PAGE_SIZE - 1)) != 0)) { + lpfc_printf_log(phba, KERN_ERR, LOG_FCP, + "3369 Memory alignment err: " + "addr=%lx\n", + (unsigned long)lpfc_ncmd->data); + dma_pool_free(phba->lpfc_sg_dma_buf_pool, + lpfc_ncmd->data, + lpfc_ncmd->dma_handle); + kfree(lpfc_ncmd); + break; + } } + INIT_LIST_HEAD(&lpfc_ncmd->dma_cmd_rsp_list); + lxri = lpfc_sli4_next_xritag(phba); if (lxri == NO_XRI) { dma_pool_free(phba->lpfc_sg_dma_buf_pool, @@ -4309,14 +4304,20 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev) shost->max_cmd_len = 16; if (phba->sli_rev == LPFC_SLI_REV4) { - if (phba->cfg_fcp_io_sched == LPFC_FCP_SCHED_BY_HDWQ) - shost->nr_hw_queues = phba->cfg_hdw_queue; - else - shost->nr_hw_queues = phba->sli4_hba.num_present_cpu; + if (!phba->cfg_fcp_mq_threshold || + phba->cfg_fcp_mq_threshold > phba->cfg_hdw_queue) + phba->cfg_fcp_mq_threshold = phba->cfg_hdw_queue; + + shost->nr_hw_queues = min_t(int, 2 * num_possible_nodes(), + phba->cfg_fcp_mq_threshold); shost->dma_boundary = phba->sli4_hba.pc_sli4_params.sge_supp_len-1; - shost->sg_tablesize = phba->cfg_scsi_seg_cnt; + + if (phba->cfg_xpsgl && !phba->nvmet_support) + shost->sg_tablesize = LPFC_MAX_SG_TABLESIZE; + else + shost->sg_tablesize = phba->cfg_scsi_seg_cnt; } else /* SLI-3 has a limited number of hardware queues (3), * thus there is only one for FCP processing. @@ -5288,10 +5289,10 @@ lpfc_sli4_async_sli_evt(struct lpfc_hba *phba, struct lpfc_acqe_sli *acqe_sli) evt_type = bf_get(lpfc_trailer_type, acqe_sli); lpfc_printf_log(phba, KERN_INFO, LOG_SLI, - "2901 Async SLI event - Event Data1:x%08x Event Data2:" - "x%08x SLI Event Type:%d\n", + "2901 Async SLI event - Type:%d, Event Data: x%08x " + "x%08x x%08x x%08x\n", evt_type, acqe_sli->event_data1, acqe_sli->event_data2, - evt_type); + acqe_sli->reserved, acqe_sli->trailer); port_name = phba->Port[0]; if (port_name == 0x00) @@ -5438,11 +5439,26 @@ lpfc_sli4_async_sli_evt(struct lpfc_hba *phba, struct lpfc_acqe_sli *acqe_sli) "Event Data1:x%08x Event Data2: x%08x\n", acqe_sli->event_data1, acqe_sli->event_data2); break; + case LPFC_SLI_EVENT_TYPE_MISCONF_FAWWN: + /* Misconfigured WWN. Reports that the SLI Port is configured + * to use FA-WWN, but the attached device doesn’t support it. + * No driver action is required. + * Event Data1 - N.A, Event Data2 - N.A + */ + lpfc_log_msg(phba, KERN_WARNING, LOG_SLI, + "2699 Misconfigured FA-WWN - Attached device does " + "not support FA-WWN\n"); + break; + case LPFC_SLI_EVENT_TYPE_EEPROM_FAILURE: + /* EEPROM failure. No driver action is required */ + lpfc_printf_log(phba, KERN_WARNING, LOG_SLI, + "2518 EEPROM failure - " + "Event Data1: x%08x Event Data2: x%08x\n", + acqe_sli->event_data1, acqe_sli->event_data2); + break; default: lpfc_printf_log(phba, KERN_INFO, LOG_SLI, - "3193 Async SLI event - Event Data1:x%08x Event Data2:" - "x%08x SLI Event Type:%d\n", - acqe_sli->event_data1, acqe_sli->event_data2, + "3193 Unrecognized SLI event, type: 0x%x", evt_type); break; } @@ -5867,7 +5883,7 @@ void lpfc_sli4_async_event_proc(struct lpfc_hba *phba) break; default: lpfc_printf_log(phba, KERN_ERR, LOG_SLI, - "1804 Invalid asynchrous event code: " + "1804 Invalid asynchronous event code: " "x%x\n", bf_get(lpfc_trailer_code, &cq_event->cqe.mcqe_cmpl)); break; @@ -5981,6 +5997,29 @@ 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. * @@ -6334,6 +6373,24 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba) if (lpfc_mem_alloc(phba, BPL_ALIGN_SZ)) return -ENOMEM; + phba->lpfc_sg_dma_buf_pool = + dma_pool_create("lpfc_sg_dma_buf_pool", + &phba->pcidev->dev, phba->cfg_sg_dma_buf_size, + BPL_ALIGN_SZ, 0); + + if (!phba->lpfc_sg_dma_buf_pool) + goto fail_free_mem; + + phba->lpfc_cmd_rsp_buf_pool = + dma_pool_create("lpfc_cmd_rsp_buf_pool", + &phba->pcidev->dev, + sizeof(struct fcp_cmnd) + + sizeof(struct fcp_rsp), + BPL_ALIGN_SZ, 0); + + if (!phba->lpfc_cmd_rsp_buf_pool) + goto fail_free_dma_buf_pool; + /* * Enable sr-iov virtual functions if supported and configured * through the module parameter. @@ -6352,6 +6409,13 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba) } return 0; + +fail_free_dma_buf_pool: + dma_pool_destroy(phba->lpfc_sg_dma_buf_pool); + phba->lpfc_sg_dma_buf_pool = NULL; +fail_free_mem: + lpfc_mem_free(phba); + return -ENOMEM; } /** @@ -6396,8 +6460,9 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) u32 if_fam; phba->sli4_hba.num_present_cpu = lpfc_present_cpu; - phba->sli4_hba.num_possible_cpu = num_possible_cpus(); + 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); @@ -6412,6 +6477,11 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) if (rc) return -ENODEV; + /* Allocate all driver workqueues here */ + + /* The lpfc_wq workqueue for deferred irq use */ + phba->wq = alloc_workqueue("lpfc_wq", WQ_MEM_RECLAIM, 0); + /* * Initialize timers used by driver */ @@ -6446,102 +6516,6 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) * The WQ create will allocate the ring. */ - /* - * 1 for cmd, 1 for rsp, NVME adds an extra one - * for boundary conditions in its max_sgl_segment template. - */ - extra = 2; - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) - extra++; - - /* - * It doesn't matter what family our adapter is in, we are - * limited to 2 Pages, 512 SGEs, for our SGL. - * There are going to be 2 reserved SGEs: 1 FCP cmnd + 1 FCP rsp - */ - max_buf_size = (2 * SLI4_PAGE_SIZE); - - /* - * Since lpfc_sg_seg_cnt is module param, the sg_dma_buf_size - * used to create the sg_dma_buf_pool must be calculated. - */ - if (phba->sli3_options & LPFC_SLI3_BG_ENABLED) { - /* - * The scsi_buf for a T10-DIF I/O holds the FCP cmnd, - * the FCP rsp, and a SGE. Sice we have no control - * over how many protection segments the SCSI Layer - * will hand us (ie: there could be one for every block - * in the IO), just allocate enough SGEs to accomidate - * our max amount and we need to limit lpfc_sg_seg_cnt - * to minimize the risk of running out. - */ - phba->cfg_sg_dma_buf_size = sizeof(struct fcp_cmnd) + - sizeof(struct fcp_rsp) + max_buf_size; - - /* Total SGEs for scsi_sg_list and scsi_sg_prot_list */ - phba->cfg_total_seg_cnt = LPFC_MAX_SGL_SEG_CNT; - - /* - * If supporting DIF, reduce the seg count for scsi to - * allow room for the DIF sges. - */ - if (phba->cfg_enable_bg && - phba->cfg_sg_seg_cnt > LPFC_MAX_BG_SLI4_SEG_CNT_DIF) - phba->cfg_scsi_seg_cnt = LPFC_MAX_BG_SLI4_SEG_CNT_DIF; - else - phba->cfg_scsi_seg_cnt = phba->cfg_sg_seg_cnt; - - } else { - /* - * The scsi_buf for a regular I/O holds the FCP cmnd, - * the FCP rsp, a SGE for each, and a SGE for up to - * cfg_sg_seg_cnt data segments. - */ - phba->cfg_sg_dma_buf_size = sizeof(struct fcp_cmnd) + - sizeof(struct fcp_rsp) + - ((phba->cfg_sg_seg_cnt + extra) * - sizeof(struct sli4_sge)); - - /* Total SGEs for scsi_sg_list */ - phba->cfg_total_seg_cnt = phba->cfg_sg_seg_cnt + extra; - phba->cfg_scsi_seg_cnt = phba->cfg_sg_seg_cnt; - - /* - * NOTE: if (phba->cfg_sg_seg_cnt + extra) <= 256 we only - * need to post 1 page for the SGL. - */ - } - - /* Limit to LPFC_MAX_NVME_SEG_CNT for NVME. */ - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - if (phba->cfg_sg_seg_cnt > LPFC_MAX_NVME_SEG_CNT) { - lpfc_printf_log(phba, KERN_INFO, LOG_NVME | LOG_INIT, - "6300 Reducing NVME sg segment " - "cnt to %d\n", - LPFC_MAX_NVME_SEG_CNT); - phba->cfg_nvme_seg_cnt = LPFC_MAX_NVME_SEG_CNT; - } else - phba->cfg_nvme_seg_cnt = phba->cfg_sg_seg_cnt; - } - - /* Initialize the host templates with the updated values. */ - lpfc_vport_template.sg_tablesize = phba->cfg_scsi_seg_cnt; - lpfc_template.sg_tablesize = phba->cfg_scsi_seg_cnt; - lpfc_template_no_hr.sg_tablesize = phba->cfg_scsi_seg_cnt; - - if (phba->cfg_sg_dma_buf_size <= LPFC_MIN_SG_SLI4_BUF_SZ) - phba->cfg_sg_dma_buf_size = LPFC_MIN_SG_SLI4_BUF_SZ; - else - phba->cfg_sg_dma_buf_size = - SLI4_PAGE_ALIGN(phba->cfg_sg_dma_buf_size); - - lpfc_printf_log(phba, KERN_INFO, LOG_INIT | LOG_FCP, - "9087 sg_seg_cnt:%d dmabuf_size:%d " - "total:%d scsi:%d nvme:%d\n", - phba->cfg_sg_seg_cnt, phba->cfg_sg_dma_buf_size, - phba->cfg_total_seg_cnt, phba->cfg_scsi_seg_cnt, - phba->cfg_nvme_seg_cnt); - /* Initialize buffer queue management fields */ INIT_LIST_HEAD(&phba->hbqs[LPFC_ELS_HBQ].hbq_buffer_list); phba->hbqs[LPFC_ELS_HBQ].hbq_alloc_buffer = lpfc_sli4_rb_alloc; @@ -6550,11 +6524,9 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) /* * Initialize the SLI Layer to run with lpfc SLI4 HBAs. */ - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) { - /* Initialize the Abort scsi buffer list used by driver */ - spin_lock_init(&phba->sli4_hba.abts_scsi_buf_list_lock); - INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_scsi_buf_list); - } + /* Initialize the Abort buffer list used by driver */ + spin_lock_init(&phba->sli4_hba.abts_io_buf_list_lock); + INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_io_buf_list); if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { /* Initialize the Abort nvme buffer list used by driver */ @@ -6762,6 +6734,131 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) } } + /* + * 1 for cmd, 1 for rsp, NVME adds an extra one + * for boundary conditions in its max_sgl_segment template. + */ + extra = 2; + if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) + extra++; + + /* + * It doesn't matter what family our adapter is in, we are + * limited to 2 Pages, 512 SGEs, for our SGL. + * There are going to be 2 reserved SGEs: 1 FCP cmnd + 1 FCP rsp + */ + max_buf_size = (2 * SLI4_PAGE_SIZE); + + /* + * Since lpfc_sg_seg_cnt is module param, the sg_dma_buf_size + * used to create the sg_dma_buf_pool must be calculated. + */ + if (phba->sli3_options & LPFC_SLI3_BG_ENABLED) { + /* Both cfg_enable_bg and cfg_external_dif code paths */ + + /* + * The scsi_buf for a T10-DIF I/O holds the FCP cmnd, + * the FCP rsp, and a SGE. Sice we have no control + * over how many protection segments the SCSI Layer + * will hand us (ie: there could be one for every block + * in the IO), just allocate enough SGEs to accomidate + * our max amount and we need to limit lpfc_sg_seg_cnt + * to minimize the risk of running out. + */ + phba->cfg_sg_dma_buf_size = sizeof(struct fcp_cmnd) + + sizeof(struct fcp_rsp) + max_buf_size; + + /* Total SGEs for scsi_sg_list and scsi_sg_prot_list */ + phba->cfg_total_seg_cnt = LPFC_MAX_SGL_SEG_CNT; + + /* + * If supporting DIF, reduce the seg count for scsi to + * allow room for the DIF sges. + */ + if (phba->cfg_enable_bg && + phba->cfg_sg_seg_cnt > LPFC_MAX_BG_SLI4_SEG_CNT_DIF) + phba->cfg_scsi_seg_cnt = LPFC_MAX_BG_SLI4_SEG_CNT_DIF; + else + phba->cfg_scsi_seg_cnt = phba->cfg_sg_seg_cnt; + + } else { + /* + * The scsi_buf for a regular I/O holds the FCP cmnd, + * the FCP rsp, a SGE for each, and a SGE for up to + * cfg_sg_seg_cnt data segments. + */ + phba->cfg_sg_dma_buf_size = sizeof(struct fcp_cmnd) + + sizeof(struct fcp_rsp) + + ((phba->cfg_sg_seg_cnt + extra) * + sizeof(struct sli4_sge)); + + /* Total SGEs for scsi_sg_list */ + phba->cfg_total_seg_cnt = phba->cfg_sg_seg_cnt + extra; + phba->cfg_scsi_seg_cnt = phba->cfg_sg_seg_cnt; + + /* + * NOTE: if (phba->cfg_sg_seg_cnt + extra) <= 256 we only + * need to post 1 page for the SGL. + */ + } + + if (phba->cfg_xpsgl && !phba->nvmet_support) + phba->cfg_sg_dma_buf_size = LPFC_DEFAULT_XPSGL_SIZE; + else if (phba->cfg_sg_dma_buf_size <= LPFC_MIN_SG_SLI4_BUF_SZ) + phba->cfg_sg_dma_buf_size = LPFC_MIN_SG_SLI4_BUF_SZ; + else + phba->cfg_sg_dma_buf_size = + SLI4_PAGE_ALIGN(phba->cfg_sg_dma_buf_size); + + phba->border_sge_num = phba->cfg_sg_dma_buf_size / + sizeof(struct sli4_sge); + + /* Limit to LPFC_MAX_NVME_SEG_CNT for NVME. */ + if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { + if (phba->cfg_sg_seg_cnt > LPFC_MAX_NVME_SEG_CNT) { + lpfc_printf_log(phba, KERN_INFO, LOG_NVME | LOG_INIT, + "6300 Reducing NVME sg segment " + "cnt to %d\n", + LPFC_MAX_NVME_SEG_CNT); + phba->cfg_nvme_seg_cnt = LPFC_MAX_NVME_SEG_CNT; + } else + phba->cfg_nvme_seg_cnt = phba->cfg_sg_seg_cnt; + } + + /* Initialize the host templates with the updated values. */ + lpfc_vport_template.sg_tablesize = phba->cfg_scsi_seg_cnt; + lpfc_template.sg_tablesize = phba->cfg_scsi_seg_cnt; + lpfc_template_no_hr.sg_tablesize = phba->cfg_scsi_seg_cnt; + + lpfc_printf_log(phba, KERN_INFO, LOG_INIT | LOG_FCP, + "9087 sg_seg_cnt:%d dmabuf_size:%d " + "total:%d scsi:%d nvme:%d\n", + phba->cfg_sg_seg_cnt, phba->cfg_sg_dma_buf_size, + phba->cfg_total_seg_cnt, phba->cfg_scsi_seg_cnt, + phba->cfg_nvme_seg_cnt); + + if (phba->cfg_sg_dma_buf_size < SLI4_PAGE_SIZE) + i = phba->cfg_sg_dma_buf_size; + else + i = SLI4_PAGE_SIZE; + + phba->lpfc_sg_dma_buf_pool = + dma_pool_create("lpfc_sg_dma_buf_pool", + &phba->pcidev->dev, + phba->cfg_sg_dma_buf_size, + i, 0); + if (!phba->lpfc_sg_dma_buf_pool) + goto out_free_bsmbx; + + phba->lpfc_cmd_rsp_buf_pool = + dma_pool_create("lpfc_cmd_rsp_buf_pool", + &phba->pcidev->dev, + sizeof(struct fcp_cmnd) + + sizeof(struct fcp_rsp), + i, 0); + if (!phba->lpfc_cmd_rsp_buf_pool) + goto out_free_sg_dma_buf; + mempool_free(mboxq, phba->mbox_mem_pool); /* Verify OAS is supported */ @@ -6773,12 +6870,12 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) /* Verify all the SLI4 queues */ rc = lpfc_sli4_queue_verify(phba); if (rc) - goto out_free_bsmbx; + goto out_free_cmd_rsp_buf; /* Create driver internal CQE event pool */ rc = lpfc_sli4_cq_event_pool_create(phba); if (rc) - goto out_free_bsmbx; + goto out_free_cmd_rsp_buf; /* Initialize sgl lists per host */ lpfc_init_sgl_list(phba); @@ -6869,6 +6966,12 @@ out_free_active_sgl: lpfc_free_active_sgl(phba); out_destroy_cq_event_pool: lpfc_sli4_cq_event_pool_destroy(phba); +out_free_cmd_rsp_buf: + dma_pool_destroy(phba->lpfc_cmd_rsp_buf_pool); + phba->lpfc_cmd_rsp_buf_pool = NULL; +out_free_sg_dma_buf: + dma_pool_destroy(phba->lpfc_sg_dma_buf_pool); + phba->lpfc_sg_dma_buf_pool = NULL; out_free_bsmbx: lpfc_destroy_bootstrap_mbox(phba); out_free_mem: @@ -6895,6 +6998,7 @@ 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); /* Free memory allocated for fast-path work queue handles */ kfree(phba->sli4_hba.hba_eq_hdl); @@ -6995,12 +7099,6 @@ lpfc_setup_driver_resource_phase2(struct lpfc_hba *phba) return error; } - /* The lpfc_wq workqueue for deferred irq use, is only used for SLI4 */ - if (phba->sli_rev == LPFC_SLI_REV4) - phba->wq = alloc_workqueue("lpfc_wq", WQ_MEM_RECLAIM, 0); - else - phba->wq = NULL; - return 0; } @@ -7074,7 +7172,7 @@ lpfc_init_iocb_list(struct lpfc_hba *phba, int iocb_count) if (iocbq_entry == NULL) { printk(KERN_ERR "%s: only allocated %d iocbs of " "expected %d count. Unloading driver.\n", - __func__, i, LPFC_IOCB_LIST_CNT); + __func__, i, iocb_count); goto out_free_iocbq; } @@ -7493,18 +7591,10 @@ lpfc_create_shost(struct lpfc_hba *phba) if (phba->nvmet_support) { /* Only 1 vport (pport) will support NVME target */ - if (phba->txrdy_payload_pool == NULL) { - phba->txrdy_payload_pool = dma_pool_create( - "txrdy_pool", &phba->pcidev->dev, - TXRDY_PAYLOAD_LEN, 16, 0); - if (phba->txrdy_payload_pool) { - phba->targetport = NULL; - phba->cfg_enable_fc4_type = LPFC_ENABLE_NVME; - lpfc_printf_log(phba, KERN_INFO, - LOG_INIT | LOG_NVME_DISC, - "6076 NVME Target Found\n"); - } - } + phba->targetport = NULL; + phba->cfg_enable_fc4_type = LPFC_ENABLE_NVME; + lpfc_printf_log(phba, KERN_INFO, LOG_INIT | LOG_NVME_DISC, + "6076 NVME Target Found\n"); } lpfc_debugfs_initialize(vport); @@ -7561,7 +7651,6 @@ lpfc_setup_bg(struct lpfc_hba *phba, struct Scsi_Host *shost) uint32_t old_mask; uint32_t old_guard; - int pagecnt = 10; if (phba->cfg_prot_mask && phba->cfg_prot_guard) { lpfc_printf_log(phba, KERN_INFO, LOG_INIT, "1478 Registering BlockGuard with the " @@ -7598,56 +7687,6 @@ lpfc_setup_bg(struct lpfc_hba *phba, struct Scsi_Host *shost) "layer, Bad protection parameters: %d %d\n", old_mask, old_guard); } - - if (!_dump_buf_data) { - while (pagecnt) { - spin_lock_init(&_dump_buf_lock); - _dump_buf_data = - (char *) __get_free_pages(GFP_KERNEL, pagecnt); - if (_dump_buf_data) { - lpfc_printf_log(phba, KERN_ERR, LOG_BG, - "9043 BLKGRD: allocated %d pages for " - "_dump_buf_data at 0x%p\n", - (1 << pagecnt), _dump_buf_data); - _dump_buf_data_order = pagecnt; - memset(_dump_buf_data, 0, - ((1 << PAGE_SHIFT) << pagecnt)); - break; - } else - --pagecnt; - } - if (!_dump_buf_data_order) - lpfc_printf_log(phba, KERN_ERR, LOG_BG, - "9044 BLKGRD: ERROR unable to allocate " - "memory for hexdump\n"); - } else - lpfc_printf_log(phba, KERN_ERR, LOG_BG, - "9045 BLKGRD: already allocated _dump_buf_data=0x%p" - "\n", _dump_buf_data); - if (!_dump_buf_dif) { - while (pagecnt) { - _dump_buf_dif = - (char *) __get_free_pages(GFP_KERNEL, pagecnt); - if (_dump_buf_dif) { - lpfc_printf_log(phba, KERN_ERR, LOG_BG, - "9046 BLKGRD: allocated %d pages for " - "_dump_buf_dif at 0x%p\n", - (1 << pagecnt), _dump_buf_dif); - _dump_buf_dif_order = pagecnt; - memset(_dump_buf_dif, 0, - ((1 << PAGE_SHIFT) << pagecnt)); - break; - } else - --pagecnt; - } - if (!_dump_buf_dif_order) - lpfc_printf_log(phba, KERN_ERR, LOG_BG, - "9047 BLKGRD: ERROR unable to allocate " - "memory for hexdump\n"); - } else - lpfc_printf_log(phba, KERN_ERR, LOG_BG, - "9048 BLKGRD: already allocated _dump_buf_dif=0x%p\n", - _dump_buf_dif); } /** @@ -8234,6 +8273,86 @@ lpfc_destroy_bootstrap_mbox(struct lpfc_hba *phba) memset(&phba->sli4_hba.bmbx, 0, sizeof(struct lpfc_bmbx)); } +static const char * const lpfc_topo_to_str[] = { + "Loop then P2P", + "Loopback", + "P2P Only", + "Unsupported", + "Loop Only", + "Unsupported", + "P2P then Loop", +}; + +/** + * lpfc_map_topology - Map the topology read from READ_CONFIG + * @phba: pointer to lpfc hba data structure. + * @rdconf: pointer to read config data + * + * This routine is invoked to map the topology values as read + * from the read config mailbox command. If the persistent + * topology feature is supported, the firmware will provide the + * saved topology information to be used in INIT_LINK + * + **/ +#define LINK_FLAGS_DEF 0x0 +#define LINK_FLAGS_P2P 0x1 +#define LINK_FLAGS_LOOP 0x2 +static void +lpfc_map_topology(struct lpfc_hba *phba, struct lpfc_mbx_read_config *rd_config) +{ + u8 ptv, tf, pt; + + ptv = bf_get(lpfc_mbx_rd_conf_ptv, rd_config); + tf = bf_get(lpfc_mbx_rd_conf_tf, rd_config); + pt = bf_get(lpfc_mbx_rd_conf_pt, rd_config); + + lpfc_printf_log(phba, KERN_INFO, LOG_SLI, + "2027 Read Config Data : ptv:0x%x, tf:0x%x pt:0x%x", + ptv, tf, pt); + if (!ptv) { + lpfc_printf_log(phba, KERN_WARNING, LOG_SLI, + "2019 FW does not support persistent topology " + "Using driver parameter defined value [%s]", + lpfc_topo_to_str[phba->cfg_topology]); + return; + } + /* FW supports persistent topology - override module parameter value */ + phba->hba_flag |= HBA_PERSISTENT_TOPO; + switch (phba->pcidev->device) { + case PCI_DEVICE_ID_LANCER_G7_FC: + case PCI_DEVICE_ID_LANCER_G6_FC: + if (!tf) { + phba->cfg_topology = ((pt == LINK_FLAGS_LOOP) + ? FLAGS_TOPOLOGY_MODE_LOOP + : FLAGS_TOPOLOGY_MODE_PT_PT); + } else { + phba->hba_flag &= ~HBA_PERSISTENT_TOPO; + } + break; + default: /* G5 */ + if (tf) { + /* If topology failover set - pt is '0' or '1' */ + phba->cfg_topology = (pt ? FLAGS_TOPOLOGY_MODE_PT_LOOP : + FLAGS_TOPOLOGY_MODE_LOOP_PT); + } else { + phba->cfg_topology = ((pt == LINK_FLAGS_P2P) + ? FLAGS_TOPOLOGY_MODE_PT_PT + : FLAGS_TOPOLOGY_MODE_LOOP); + } + break; + } + if (phba->hba_flag & HBA_PERSISTENT_TOPO) { + lpfc_printf_log(phba, KERN_INFO, LOG_SLI, + "2020 Using persistent topology value [%s]", + lpfc_topo_to_str[phba->cfg_topology]); + } else { + lpfc_printf_log(phba, KERN_WARNING, LOG_SLI, + "2021 Invalid topology values from FW " + "Using driver parameter defined value [%s]", + lpfc_topo_to_str[phba->cfg_topology]); + } +} + /** * lpfc_sli4_read_config - Get the config parameters. * @phba: pointer to lpfc hba data structure. @@ -8307,6 +8426,10 @@ lpfc_sli4_read_config(struct lpfc_hba *phba) bf_get(lpfc_mbx_rd_conf_extnts_inuse, rd_config); phba->sli4_hba.max_cfg_param.max_xri = bf_get(lpfc_mbx_rd_conf_xri_count, rd_config); + /* Reduce resource usage in kdump environment */ + if (is_kdump_kernel() && + phba->sli4_hba.max_cfg_param.max_xri > 512) + phba->sli4_hba.max_cfg_param.max_xri = 512; phba->sli4_hba.max_cfg_param.xri_base = bf_get(lpfc_mbx_rd_conf_xri_base, rd_config); phba->sli4_hba.max_cfg_param.max_vpi = @@ -8341,6 +8464,7 @@ lpfc_sli4_read_config(struct lpfc_hba *phba) phba->max_vpi = (phba->sli4_hba.max_cfg_param.max_vpi > 0) ? (phba->sli4_hba.max_cfg_param.max_vpi - 1) : 0; phba->max_vports = phba->max_vpi; + lpfc_map_topology(phba, rd_config); lpfc_printf_log(phba, KERN_INFO, LOG_SLI, "2003 cfg params Extents? %d " "XRI(B:%d M:%d), " @@ -8380,11 +8504,6 @@ lpfc_sli4_read_config(struct lpfc_hba *phba) */ qmin -= 4; - /* If NVME is configured, double the number of CQ/WQs needed */ - if ((phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) && - !phba->nvmet_support) - qmin /= 2; - /* Check to see if there is enough for NVME */ if ((phba->cfg_irq_chann > qmin) || (phba->cfg_hdw_queue > qmin)) { @@ -8619,8 +8738,8 @@ lpfc_sli4_queue_verify(struct lpfc_hba *phba) */ if (phba->nvmet_support) { - if (phba->cfg_irq_chann < phba->cfg_nvmet_mrq) - phba->cfg_nvmet_mrq = phba->cfg_irq_chann; + if (phba->cfg_hdw_queue < phba->cfg_nvmet_mrq) + phba->cfg_nvmet_mrq = phba->cfg_hdw_queue; if (phba->cfg_nvmet_mrq > LPFC_NVMET_MRQ_MAX) phba->cfg_nvmet_mrq = LPFC_NVMET_MRQ_MAX; } @@ -8641,51 +8760,14 @@ lpfc_sli4_queue_verify(struct lpfc_hba *phba) } static int -lpfc_alloc_nvme_wq_cq(struct lpfc_hba *phba, int wqidx) +lpfc_alloc_io_wq_cq(struct lpfc_hba *phba, int idx) { struct lpfc_queue *qdesc; + u32 wqesize; int cpu; - cpu = lpfc_find_cpu_handle(phba, wqidx, LPFC_FIND_BY_HDWQ); - qdesc = lpfc_sli4_queue_alloc(phba, LPFC_EXPANDED_PAGE_SIZE, - phba->sli4_hba.cq_esize, - LPFC_CQE_EXP_COUNT, cpu); - if (!qdesc) { - lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "0508 Failed allocate fast-path NVME CQ (%d)\n", - wqidx); - return 1; - } - qdesc->qe_valid = 1; - qdesc->hdwq = wqidx; - qdesc->chann = cpu; - phba->sli4_hba.hdwq[wqidx].nvme_cq = qdesc; - - qdesc = lpfc_sli4_queue_alloc(phba, LPFC_EXPANDED_PAGE_SIZE, - LPFC_WQE128_SIZE, LPFC_WQE_EXP_COUNT, - cpu); - if (!qdesc) { - lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "0509 Failed allocate fast-path NVME WQ (%d)\n", - wqidx); - return 1; - } - qdesc->hdwq = wqidx; - qdesc->chann = wqidx; - phba->sli4_hba.hdwq[wqidx].nvme_wq = qdesc; - list_add_tail(&qdesc->wq_list, &phba->sli4_hba.lpfc_wq_list); - return 0; -} - -static int -lpfc_alloc_fcp_wq_cq(struct lpfc_hba *phba, int wqidx) -{ - struct lpfc_queue *qdesc; - uint32_t wqesize; - int cpu; - - cpu = lpfc_find_cpu_handle(phba, wqidx, LPFC_FIND_BY_HDWQ); - /* Create Fast Path FCP CQs */ + cpu = lpfc_find_cpu_handle(phba, idx, LPFC_FIND_BY_HDWQ); + /* Create Fast Path IO CQs */ if (phba->enab_exp_wqcq_pages) /* Increase the CQ size when WQEs contain an embedded cdb */ qdesc = lpfc_sli4_queue_alloc(phba, LPFC_EXPANDED_PAGE_SIZE, @@ -8698,15 +8780,15 @@ lpfc_alloc_fcp_wq_cq(struct lpfc_hba *phba, int wqidx) phba->sli4_hba.cq_ecount, cpu); if (!qdesc) { lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "0499 Failed allocate fast-path FCP CQ (%d)\n", wqidx); + "0499 Failed allocate fast-path IO CQ (%d)\n", idx); return 1; } qdesc->qe_valid = 1; - qdesc->hdwq = wqidx; + qdesc->hdwq = idx; qdesc->chann = cpu; - phba->sli4_hba.hdwq[wqidx].fcp_cq = qdesc; + phba->sli4_hba.hdwq[idx].io_cq = qdesc; - /* Create Fast Path FCP WQs */ + /* Create Fast Path IO WQs */ if (phba->enab_exp_wqcq_pages) { /* Increase the WQ size when WQEs contain an embedded cdb */ wqesize = (phba->fcp_embed_io) ? @@ -8721,13 +8803,13 @@ lpfc_alloc_fcp_wq_cq(struct lpfc_hba *phba, int wqidx) if (!qdesc) { lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "0503 Failed allocate fast-path FCP WQ (%d)\n", - wqidx); + "0503 Failed allocate fast-path IO WQ (%d)\n", + idx); return 1; } - qdesc->hdwq = wqidx; - qdesc->chann = wqidx; - phba->sli4_hba.hdwq[wqidx].fcp_wq = qdesc; + qdesc->hdwq = idx; + qdesc->chann = cpu; + phba->sli4_hba.hdwq[idx].io_wq = qdesc; list_add_tail(&qdesc->wq_list, &phba->sli4_hba.lpfc_wq_list); return 0; } @@ -8791,12 +8873,13 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) qp->get_io_bufs = 0; qp->put_io_bufs = 0; qp->total_io_bufs = 0; - spin_lock_init(&qp->abts_scsi_buf_list_lock); - INIT_LIST_HEAD(&qp->lpfc_abts_scsi_buf_list); + spin_lock_init(&qp->abts_io_buf_list_lock); + INIT_LIST_HEAD(&qp->lpfc_abts_io_buf_list); qp->abts_scsi_io_bufs = 0; - spin_lock_init(&qp->abts_nvme_buf_list_lock); - INIT_LIST_HEAD(&qp->lpfc_abts_nvme_buf_list); qp->abts_nvme_io_bufs = 0; + INIT_LIST_HEAD(&qp->sgl_list); + INIT_LIST_HEAD(&qp->cmd_rsp_buf_list); + spin_lock_init(&qp->hdwq_lock); } } @@ -8862,7 +8945,7 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) } qdesc->qe_valid = 1; qdesc->hdwq = cpup->hdwq; - qdesc->chann = cpu; /* First CPU this EQ is affinitised to */ + qdesc->chann = cpu; /* First CPU this EQ is affinitized to */ qdesc->last_cpu = qdesc->chann; /* Save the allocated EQ in the Hardware Queue */ @@ -8893,41 +8976,31 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) qp->hba_eq = phba->sli4_hba.hdwq[eqcpup->hdwq].hba_eq; } - /* Allocate SCSI SLI4 CQ/WQs */ + /* Allocate IO Path SLI4 CQ/WQs */ for (idx = 0; idx < phba->cfg_hdw_queue; idx++) { - if (lpfc_alloc_fcp_wq_cq(phba, idx)) + if (lpfc_alloc_io_wq_cq(phba, idx)) goto out_error; } - /* Allocate NVME SLI4 CQ/WQs */ - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - for (idx = 0; idx < phba->cfg_hdw_queue; idx++) { - if (lpfc_alloc_nvme_wq_cq(phba, idx)) - goto out_error; - } - - if (phba->nvmet_support) { - for (idx = 0; idx < phba->cfg_nvmet_mrq; idx++) { - cpu = lpfc_find_cpu_handle(phba, idx, - LPFC_FIND_BY_HDWQ); - qdesc = lpfc_sli4_queue_alloc( - phba, + if (phba->nvmet_support) { + for (idx = 0; idx < phba->cfg_nvmet_mrq; idx++) { + cpu = lpfc_find_cpu_handle(phba, idx, + LPFC_FIND_BY_HDWQ); + qdesc = lpfc_sli4_queue_alloc(phba, LPFC_DEFAULT_PAGE_SIZE, phba->sli4_hba.cq_esize, phba->sli4_hba.cq_ecount, cpu); - if (!qdesc) { - lpfc_printf_log( - phba, KERN_ERR, LOG_INIT, + if (!qdesc) { + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, "3142 Failed allocate NVME " "CQ Set (%d)\n", idx); - goto out_error; - } - qdesc->qe_valid = 1; - qdesc->hdwq = idx; - qdesc->chann = cpu; - phba->sli4_hba.nvmet_cqset[idx] = qdesc; + goto out_error; } + qdesc->qe_valid = 1; + qdesc->hdwq = idx; + qdesc->chann = cpu; + phba->sli4_hba.nvmet_cqset[idx] = qdesc; } } @@ -8958,7 +9031,7 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) goto out_error; } qdesc->qe_valid = 1; - qdesc->chann = 0; + qdesc->chann = cpu; phba->sli4_hba.els_cq = qdesc; @@ -8976,7 +9049,7 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) "0505 Failed allocate slow-path MQ\n"); goto out_error; } - qdesc->chann = 0; + qdesc->chann = cpu; phba->sli4_hba.mbx_wq = qdesc; /* @@ -8992,7 +9065,7 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) "0504 Failed allocate slow-path ELS WQ\n"); goto out_error; } - qdesc->chann = 0; + qdesc->chann = cpu; phba->sli4_hba.els_wq = qdesc; list_add_tail(&qdesc->wq_list, &phba->sli4_hba.lpfc_wq_list); @@ -9006,7 +9079,7 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) "6079 Failed allocate NVME LS CQ\n"); goto out_error; } - qdesc->chann = 0; + qdesc->chann = cpu; qdesc->qe_valid = 1; phba->sli4_hba.nvmels_cq = qdesc; @@ -9019,7 +9092,7 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) "6080 Failed allocate NVME LS WQ\n"); goto out_error; } - qdesc->chann = 0; + qdesc->chann = cpu; phba->sli4_hba.nvmels_wq = qdesc; list_add_tail(&qdesc->wq_list, &phba->sli4_hba.lpfc_wq_list); } @@ -9101,7 +9174,6 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) } } -#if defined(BUILD_NVME) /* Clear NVME stats */ if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { for (idx = 0; idx < phba->cfg_hdw_queue; idx++) { @@ -9109,7 +9181,6 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) sizeof(phba->sli4_hba.hdwq[idx].nvme_cstat)); } } -#endif /* Clear SCSI stats */ if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) { @@ -9162,15 +9233,13 @@ lpfc_sli4_release_hdwq(struct lpfc_hba *phba) /* Loop thru all Hardware Queues */ for (idx = 0; idx < phba->cfg_hdw_queue; idx++) { /* Free the CQ/WQ corresponding to the Hardware Queue */ - lpfc_sli4_queue_free(hdwq[idx].fcp_cq); - lpfc_sli4_queue_free(hdwq[idx].nvme_cq); - lpfc_sli4_queue_free(hdwq[idx].fcp_wq); - lpfc_sli4_queue_free(hdwq[idx].nvme_wq); - hdwq[idx].hba_eq = NULL; - hdwq[idx].fcp_cq = NULL; - hdwq[idx].nvme_cq = NULL; - hdwq[idx].fcp_wq = NULL; - hdwq[idx].nvme_wq = NULL; + lpfc_sli4_queue_free(hdwq[idx].io_cq); + lpfc_sli4_queue_free(hdwq[idx].io_wq); + hdwq[idx].io_cq = NULL; + hdwq[idx].io_wq = NULL; + if (phba->cfg_xpsgl && !phba->nvmet_support) + lpfc_free_sgl_per_hdwq(phba, &hdwq[idx]); + lpfc_free_cmd_rsp_buf_per_hdwq(phba, &hdwq[idx]); } /* Loop thru all IRQ vectors */ for (idx = 0; idx < phba->cfg_irq_chann; idx++) { @@ -9210,6 +9279,8 @@ lpfc_sli4_queue_destroy(struct lpfc_hba *phba) } spin_unlock_irq(&phba->hbalock); + lpfc_sli4_cleanup_poll_list(phba); + /* Release HBA eqs */ if (phba->sli4_hba.hdwq) lpfc_sli4_release_hdwq(phba); @@ -9370,8 +9441,7 @@ lpfc_setup_cq_lookup(struct lpfc_hba *phba) list_for_each_entry(childq, &eq->child_list, list) { if (childq->queue_id > phba->sli4_hba.cq_max) continue; - if ((childq->subtype == LPFC_FCP) || - (childq->subtype == LPFC_NVME)) + if (childq->subtype == LPFC_IO) phba->sli4_hba.cq_lookup[childq->queue_id] = childq; } @@ -9497,31 +9567,6 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba) } /* Loop thru all Hardware Queues */ - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - for (qidx = 0; qidx < phba->cfg_hdw_queue; qidx++) { - cpu = lpfc_find_cpu_handle(phba, qidx, - LPFC_FIND_BY_HDWQ); - cpup = &phba->sli4_hba.cpu_map[cpu]; - - /* Create the CQ/WQ corresponding to the - * Hardware Queue - */ - rc = lpfc_create_wq_cq(phba, - phba->sli4_hba.hdwq[cpup->hdwq].hba_eq, - qp[qidx].nvme_cq, - qp[qidx].nvme_wq, - &phba->sli4_hba.hdwq[qidx].nvme_cq_map, - qidx, LPFC_NVME); - if (rc) { - lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "6123 Failed to setup fastpath " - "NVME WQ/CQ (%d), rc = 0x%x\n", - qidx, (uint32_t)rc); - goto out_destroy; - } - } - } - for (qidx = 0; qidx < phba->cfg_hdw_queue; qidx++) { cpu = lpfc_find_cpu_handle(phba, qidx, LPFC_FIND_BY_HDWQ); cpup = &phba->sli4_hba.cpu_map[cpu]; @@ -9529,14 +9574,15 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba) /* Create the CQ/WQ corresponding to the Hardware Queue */ rc = lpfc_create_wq_cq(phba, phba->sli4_hba.hdwq[cpup->hdwq].hba_eq, - qp[qidx].fcp_cq, - qp[qidx].fcp_wq, - &phba->sli4_hba.hdwq[qidx].fcp_cq_map, - qidx, LPFC_FCP); + qp[qidx].io_cq, + qp[qidx].io_wq, + &phba->sli4_hba.hdwq[qidx].io_cq_map, + qidx, + LPFC_IO); if (rc) { lpfc_printf_log(phba, KERN_ERR, LOG_INIT, "0535 Failed to setup fastpath " - "FCP WQ/CQ (%d), rc = 0x%x\n", + "IO WQ/CQ (%d), rc = 0x%x\n", qidx, (uint32_t)rc); goto out_destroy; } @@ -9836,10 +9882,8 @@ lpfc_sli4_queue_unset(struct lpfc_hba *phba) for (qidx = 0; qidx < phba->cfg_hdw_queue; qidx++) { /* Destroy the CQ/WQ corresponding to Hardware Queue */ qp = &phba->sli4_hba.hdwq[qidx]; - lpfc_wq_destroy(phba, qp->fcp_wq); - lpfc_wq_destroy(phba, qp->nvme_wq); - lpfc_cq_destroy(phba, qp->fcp_cq); - lpfc_cq_destroy(phba, qp->nvme_cq); + lpfc_wq_destroy(phba, qp->io_wq); + lpfc_cq_destroy(phba, qp->io_cq); } /* Loop thru all IRQ vectors */ for (qidx = 0; qidx < phba->cfg_irq_chann; qidx++) { @@ -10397,6 +10441,8 @@ lpfc_sli4_pci_mem_unset(struct lpfc_hba *phba) case LPFC_SLI_INTF_IF_TYPE_6: iounmap(phba->sli4_hba.drbl_regs_memmap_p); iounmap(phba->sli4_hba.conf_regs_memmap_p); + if (phba->sli4_hba.dpp_regs_memmap_p) + iounmap(phba->sli4_hba.dpp_regs_memmap_p); break; case LPFC_SLI_INTF_IF_TYPE_1: default: @@ -10658,7 +10704,6 @@ lpfc_find_cpu_handle(struct lpfc_hba *phba, uint16_t id, int match) */ if ((match == LPFC_FIND_BY_EQ) && (cpup->flag & LPFC_CPU_FIRST_IRQ) && - (cpup->irq != LPFC_VECTOR_MAP_EMPTY) && (cpup->eq == id)) return cpu; @@ -10696,6 +10741,75 @@ lpfc_find_hyper(struct lpfc_hba *phba, int cpu, } #endif +/* + * lpfc_assign_eq_map_info - Assigns eq for vector_map structure + * @phba: pointer to lpfc hba data structure. + * @eqidx: index for eq and irq vector + * @flag: flags to set for vector_map structure + * @cpu: cpu used to index vector_map structure + * + * The routine assigns eq info into vector_map structure + */ +static inline void +lpfc_assign_eq_map_info(struct lpfc_hba *phba, uint16_t eqidx, uint16_t flag, + unsigned int cpu) +{ + struct lpfc_vector_map_info *cpup = &phba->sli4_hba.cpu_map[cpu]; + struct lpfc_hba_eq_hdl *eqhdl = lpfc_get_eq_hdl(eqidx); + + cpup->eq = eqidx; + cpup->flag |= flag; + + lpfc_printf_log(phba, KERN_INFO, LOG_INIT, + "3336 Set Affinity: CPU %d irq %d eq %d flag x%x\n", + cpu, eqhdl->irq, cpup->eq, cpup->flag); +} + +/** + * lpfc_cpu_map_array_init - Initialize cpu_map structure + * @phba: pointer to lpfc hba data structure. + * + * The routine initializes the cpu_map array structure + */ +static void +lpfc_cpu_map_array_init(struct lpfc_hba *phba) +{ + struct lpfc_vector_map_info *cpup; + struct lpfc_eq_intr_info *eqi; + int cpu; + + for_each_possible_cpu(cpu) { + cpup = &phba->sli4_hba.cpu_map[cpu]; + cpup->phys_id = LPFC_VECTOR_MAP_EMPTY; + cpup->core_id = LPFC_VECTOR_MAP_EMPTY; + cpup->hdwq = LPFC_VECTOR_MAP_EMPTY; + cpup->eq = LPFC_VECTOR_MAP_EMPTY; + cpup->flag = 0; + eqi = per_cpu_ptr(phba->sli4_hba.eq_info, cpu); + INIT_LIST_HEAD(&eqi->list); + eqi->icnt = 0; + } +} + +/** + * lpfc_hba_eq_hdl_array_init - Initialize hba_eq_hdl structure + * @phba: pointer to lpfc hba data structure. + * + * The routine initializes the hba_eq_hdl array structure + */ +static void +lpfc_hba_eq_hdl_array_init(struct lpfc_hba *phba) +{ + struct lpfc_hba_eq_hdl *eqhdl; + int i; + + for (i = 0; i < phba->cfg_irq_chann; i++) { + eqhdl = lpfc_get_eq_hdl(i); + eqhdl->irq = LPFC_VECTOR_MAP_EMPTY; + eqhdl->phba = phba; + } +} + /** * lpfc_cpu_affinity_check - Check vector CPU affinity mappings * @phba: pointer to lpfc hba data structure. @@ -10709,27 +10823,15 @@ lpfc_find_hyper(struct lpfc_hba *phba, int cpu, static void lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors) { - int i, cpu, idx, new_cpu, start_cpu, first_cpu; + int i, cpu, idx, next_idx, new_cpu, start_cpu, first_cpu; int max_phys_id, min_phys_id; int max_core_id, min_core_id; struct lpfc_vector_map_info *cpup; struct lpfc_vector_map_info *new_cpup; - const struct cpumask *maskp; #ifdef CONFIG_X86 struct cpuinfo_x86 *cpuinfo; #endif - /* Init cpu_map array */ - for_each_possible_cpu(cpu) { - cpup = &phba->sli4_hba.cpu_map[cpu]; - cpup->phys_id = LPFC_VECTOR_MAP_EMPTY; - cpup->core_id = LPFC_VECTOR_MAP_EMPTY; - cpup->hdwq = LPFC_VECTOR_MAP_EMPTY; - cpup->eq = LPFC_VECTOR_MAP_EMPTY; - cpup->irq = LPFC_VECTOR_MAP_EMPTY; - cpup->flag = 0; - } - max_phys_id = 0; min_phys_id = LPFC_VECTOR_MAP_EMPTY; max_core_id = 0; @@ -10751,8 +10853,8 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors) #endif lpfc_printf_log(phba, KERN_INFO, LOG_INIT, - "3328 CPU physid %d coreid %d\n", - cpup->phys_id, cpup->core_id); + "3328 CPU %d physid %d coreid %d flag x%x\n", + cpu, cpup->phys_id, cpup->core_id, cpup->flag); if (cpup->phys_id > max_phys_id) max_phys_id = cpup->phys_id; @@ -10765,65 +10867,6 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors) min_core_id = cpup->core_id; } - for_each_possible_cpu(i) { - struct lpfc_eq_intr_info *eqi = - per_cpu_ptr(phba->sli4_hba.eq_info, i); - - INIT_LIST_HEAD(&eqi->list); - eqi->icnt = 0; - } - - /* This loop sets up all CPUs that are affinitized with a - * irq vector assigned to the driver. All affinitized CPUs - * will get a link to that vectors IRQ and EQ. - * - * NULL affinity mask handling: - * If irq count is greater than one, log an error message. - * If the null mask is received for the first irq, find the - * first present cpu, and assign the eq index to ensure at - * least one EQ is assigned. - */ - for (idx = 0; idx < phba->cfg_irq_chann; idx++) { - /* Get a CPU mask for all CPUs affinitized to this vector */ - maskp = pci_irq_get_affinity(phba->pcidev, idx); - if (!maskp) { - if (phba->cfg_irq_chann > 1) - lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "3329 No affinity mask found " - "for vector %d (%d)\n", - idx, phba->cfg_irq_chann); - if (!idx) { - cpu = cpumask_first(cpu_present_mask); - cpup = &phba->sli4_hba.cpu_map[cpu]; - cpup->eq = idx; - cpup->irq = pci_irq_vector(phba->pcidev, idx); - cpup->flag |= LPFC_CPU_FIRST_IRQ; - } - break; - } - - i = 0; - /* Loop through all CPUs associated with vector idx */ - for_each_cpu_and(cpu, maskp, cpu_present_mask) { - /* Set the EQ index and IRQ for that vector */ - cpup = &phba->sli4_hba.cpu_map[cpu]; - cpup->eq = idx; - cpup->irq = pci_irq_vector(phba->pcidev, idx); - - lpfc_printf_log(phba, KERN_INFO, LOG_INIT, - "3336 Set Affinity: CPU %d " - "irq %d eq %d\n", - cpu, cpup->irq, cpup->eq); - - /* If this is the first CPU thats assigned to this - * vector, set LPFC_CPU_FIRST_IRQ. - */ - if (!i) - cpup->flag |= LPFC_CPU_FIRST_IRQ; - i++; - } - } - /* After looking at each irq vector assigned to this pcidev, its * possible to see that not ALL CPUs have been accounted for. * Next we will set any unassigned (unaffinitized) cpu map @@ -10849,7 +10892,7 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors) for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) { new_cpup = &phba->sli4_hba.cpu_map[new_cpu]; if (!(new_cpup->flag & LPFC_CPU_MAP_UNASSIGN) && - (new_cpup->irq != LPFC_VECTOR_MAP_EMPTY) && + (new_cpup->eq != LPFC_VECTOR_MAP_EMPTY) && (new_cpup->phys_id == cpup->phys_id)) goto found_same; new_cpu = cpumask_next( @@ -10862,7 +10905,6 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors) found_same: /* We found a matching phys_id, so copy the IRQ info */ cpup->eq = new_cpup->eq; - cpup->irq = new_cpup->irq; /* Bump start_cpu to the next slot to minmize the * chance of having multiple unassigned CPU entries @@ -10874,9 +10916,10 @@ found_same: lpfc_printf_log(phba, KERN_INFO, LOG_INIT, "3337 Set Affinity: CPU %d " - "irq %d from id %d same " + "eq %d from peer cpu %d same " "phys_id (%d)\n", - cpu, cpup->irq, new_cpu, cpup->phys_id); + cpu, cpup->eq, new_cpu, + cpup->phys_id); } } @@ -10900,7 +10943,7 @@ found_same: for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) { new_cpup = &phba->sli4_hba.cpu_map[new_cpu]; if (!(new_cpup->flag & LPFC_CPU_MAP_UNASSIGN) && - (new_cpup->irq != LPFC_VECTOR_MAP_EMPTY)) + (new_cpup->eq != LPFC_VECTOR_MAP_EMPTY)) goto found_any; new_cpu = cpumask_next( new_cpu, cpu_present_mask); @@ -10910,13 +10953,12 @@ found_same: /* We should never leave an entry unassigned */ lpfc_printf_log(phba, KERN_ERR, LOG_INIT, "3339 Set Affinity: CPU %d " - "irq %d UNASSIGNED\n", - cpup->hdwq, cpup->irq); + "eq %d UNASSIGNED\n", + cpup->hdwq, cpup->eq); continue; found_any: /* We found an available entry, copy the IRQ info */ cpup->eq = new_cpup->eq; - cpup->irq = new_cpup->irq; /* Bump start_cpu to the next slot to minmize the * chance of having multiple unassigned CPU entries @@ -10928,75 +10970,126 @@ found_any: lpfc_printf_log(phba, KERN_INFO, LOG_INIT, "3338 Set Affinity: CPU %d " - "irq %d from id %d (%d/%d)\n", - cpu, cpup->irq, new_cpu, + "eq %d from peer cpu %d (%d/%d)\n", + cpu, cpup->eq, new_cpu, new_cpup->phys_id, new_cpup->core_id); } } - /* Finally we need to associate a hdwq with each cpu_map entry + /* Assign hdwq indices that are unique across all cpus in the map + * that are also FIRST_CPUs. + */ + idx = 0; + for_each_present_cpu(cpu) { + cpup = &phba->sli4_hba.cpu_map[cpu]; + + /* Only FIRST IRQs get a hdwq index assignment. */ + if (!(cpup->flag & LPFC_CPU_FIRST_IRQ)) + continue; + + /* 1 to 1, the first LPFC_CPU_FIRST_IRQ cpus to a unique hdwq */ + cpup->hdwq = idx; + idx++; + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "3333 Set Affinity: CPU %d (phys %d core %d): " + "hdwq %d eq %d flg x%x\n", + cpu, cpup->phys_id, cpup->core_id, + cpup->hdwq, cpup->eq, cpup->flag); + } + /* Associate a hdwq with each cpu_map entry * This will be 1 to 1 - hdwq to cpu, unless there are less * hardware queues then CPUs. For that case we will just round-robin * the available hardware queues as they get assigned to CPUs. + * The next_idx is the idx from the FIRST_CPU loop above to account + * for irq_chann < hdwq. The idx is used for round-robin assignments + * and needs to start at 0. */ - idx = 0; + next_idx = idx; start_cpu = 0; + idx = 0; for_each_present_cpu(cpu) { cpup = &phba->sli4_hba.cpu_map[cpu]; - if (idx >= phba->cfg_hdw_queue) { - /* We need to reuse a Hardware Queue for another CPU, - * so be smart about it and pick one that has its - * IRQ/EQ mapped to the same phys_id (CPU package). - * and core_id. - */ - new_cpu = start_cpu; - for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) { - new_cpup = &phba->sli4_hba.cpu_map[new_cpu]; - if ((new_cpup->hdwq != LPFC_VECTOR_MAP_EMPTY) && - (new_cpup->phys_id == cpup->phys_id) && - (new_cpup->core_id == cpup->core_id)) - goto found_hdwq; - new_cpu = cpumask_next( - new_cpu, cpu_present_mask); - if (new_cpu == nr_cpumask_bits) - new_cpu = first_cpu; - } - /* If we can't match both phys_id and core_id, - * settle for just a phys_id match. - */ - new_cpu = start_cpu; - for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) { - new_cpup = &phba->sli4_hba.cpu_map[new_cpu]; - if ((new_cpup->hdwq != LPFC_VECTOR_MAP_EMPTY) && - (new_cpup->phys_id == cpup->phys_id)) - goto found_hdwq; - new_cpu = cpumask_next( - new_cpu, cpu_present_mask); - if (new_cpu == nr_cpumask_bits) - new_cpu = first_cpu; + /* FIRST cpus are already mapped. */ + if (cpup->flag & LPFC_CPU_FIRST_IRQ) + continue; + + /* If the cfg_irq_chann < cfg_hdw_queue, set the hdwq + * of the unassigned cpus to the next idx so that all + * hdw queues are fully utilized. + */ + if (next_idx < phba->cfg_hdw_queue) { + cpup->hdwq = next_idx; + next_idx++; + continue; + } + + /* Not a First CPU and all hdw_queues are used. Reuse a + * Hardware Queue for another CPU, so be smart about it + * and pick one that has its IRQ/EQ mapped to the same phys_id + * (CPU package) and core_id. + */ + new_cpu = start_cpu; + for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) { + new_cpup = &phba->sli4_hba.cpu_map[new_cpu]; + if (new_cpup->hdwq != LPFC_VECTOR_MAP_EMPTY && + new_cpup->phys_id == cpup->phys_id && + new_cpup->core_id == cpup->core_id) { + goto found_hdwq; } + new_cpu = cpumask_next(new_cpu, cpu_present_mask); + if (new_cpu == nr_cpumask_bits) + new_cpu = first_cpu; + } - /* Otherwise just round robin on cfg_hdw_queue */ - cpup->hdwq = idx % phba->cfg_hdw_queue; - goto logit; -found_hdwq: - /* We found an available entry, copy the IRQ info */ - start_cpu = cpumask_next(new_cpu, cpu_present_mask); - if (start_cpu == nr_cpumask_bits) - start_cpu = first_cpu; - cpup->hdwq = new_cpup->hdwq; - } else { - /* 1 to 1, CPU to hdwq */ - cpup->hdwq = idx; + /* If we can't match both phys_id and core_id, + * settle for just a phys_id match. + */ + new_cpu = start_cpu; + for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) { + new_cpup = &phba->sli4_hba.cpu_map[new_cpu]; + if (new_cpup->hdwq != LPFC_VECTOR_MAP_EMPTY && + new_cpup->phys_id == cpup->phys_id) + goto found_hdwq; + + new_cpu = cpumask_next(new_cpu, cpu_present_mask); + if (new_cpu == nr_cpumask_bits) + new_cpu = first_cpu; } -logit: + + /* Otherwise just round robin on cfg_hdw_queue */ + cpup->hdwq = idx % phba->cfg_hdw_queue; + idx++; + goto logit; + found_hdwq: + /* We found an available entry, copy the IRQ info */ + start_cpu = cpumask_next(new_cpu, cpu_present_mask); + if (start_cpu == nr_cpumask_bits) + start_cpu = first_cpu; + cpup->hdwq = new_cpup->hdwq; + logit: lpfc_printf_log(phba, KERN_ERR, LOG_INIT, "3335 Set Affinity: CPU %d (phys %d core %d): " - "hdwq %d eq %d irq %d flg x%x\n", + "hdwq %d eq %d flg x%x\n", cpu, cpup->phys_id, cpup->core_id, - cpup->hdwq, cpup->eq, cpup->irq, cpup->flag); - idx++; + cpup->hdwq, cpup->eq, cpup->flag); + } + + /* + * Initialize the cpu_map slots for not-present cpus in case + * a cpu is hot-added. Perform a simple hdwq round robin assignment. + */ + idx = 0; + for_each_possible_cpu(cpu) { + cpup = &phba->sli4_hba.cpu_map[cpu]; + if (cpup->hdwq != LPFC_VECTOR_MAP_EMPTY) + continue; + + cpup->hdwq = idx++ % phba->cfg_hdw_queue; + lpfc_printf_log(phba, KERN_INFO, LOG_INIT, + "3340 Set Affinity: not present " + "CPU %d hdwq %d\n", + cpu, cpup->hdwq); } /* The cpu_map array will be used later during initialization @@ -11006,11 +11099,280 @@ logit: } /** + * lpfc_cpuhp_get_eq + * + * @phba: pointer to lpfc hba data structure. + * @cpu: cpu going offline + * @eqlist: + */ +static void +lpfc_cpuhp_get_eq(struct lpfc_hba *phba, unsigned int cpu, + struct list_head *eqlist) +{ + const struct cpumask *maskp; + struct lpfc_queue *eq; + cpumask_t tmp; + u16 idx; + + for (idx = 0; idx < phba->cfg_irq_chann; idx++) { + maskp = pci_irq_get_affinity(phba->pcidev, idx); + if (!maskp) + continue; + /* + * if irq is not affinitized to the cpu going + * then we don't need to poll the eq attached + * to it. + */ + if (!cpumask_and(&tmp, maskp, cpumask_of(cpu))) + continue; + /* get the cpus that are online and are affini- + * tized to this irq vector. If the count is + * more than 1 then cpuhp is not going to shut- + * down this vector. Since this cpu has not + * gone offline yet, we need >1. + */ + cpumask_and(&tmp, maskp, cpu_online_mask); + if (cpumask_weight(&tmp) > 1) + continue; + + /* Now that we have an irq to shutdown, get the eq + * mapped to this irq. Note: multiple hdwq's in + * the software can share an eq, but eventually + * only eq will be mapped to this vector + */ + eq = phba->sli4_hba.hba_eq_hdl[idx].eq; + list_add(&eq->_poll_list, eqlist); + } +} + +static void __lpfc_cpuhp_remove(struct lpfc_hba *phba) +{ + if (phba->sli_rev != LPFC_SLI_REV4) + return; + + cpuhp_state_remove_instance_nocalls(lpfc_cpuhp_state, + &phba->cpuhp); + /* + * unregistering the instance doesn't stop the polling + * timer. Wait for the poll timer to retire. + */ + synchronize_rcu(); + del_timer_sync(&phba->cpuhp_poll_timer); +} + +static void lpfc_cpuhp_remove(struct lpfc_hba *phba) +{ + if (phba->pport->fc_flag & FC_OFFLINE_MODE) + return; + + __lpfc_cpuhp_remove(phba); +} + +static void lpfc_cpuhp_add(struct lpfc_hba *phba) +{ + if (phba->sli_rev != LPFC_SLI_REV4) + return; + + rcu_read_lock(); + + if (!list_empty(&phba->poll_list)) { + timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0); + mod_timer(&phba->cpuhp_poll_timer, + jiffies + msecs_to_jiffies(LPFC_POLL_HB)); + } + + rcu_read_unlock(); + + cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state, + &phba->cpuhp); +} + +static int __lpfc_cpuhp_checks(struct lpfc_hba *phba, int *retval) +{ + if (phba->pport->load_flag & FC_UNLOADING) { + *retval = -EAGAIN; + return true; + } + + if (phba->sli_rev != LPFC_SLI_REV4) { + *retval = 0; + return true; + } + + /* proceed with the hotplug */ + return false; +} + +/** + * lpfc_irq_set_aff - set IRQ affinity + * @eqhdl: EQ handle + * @cpu: cpu to set affinity + * + **/ +static inline void +lpfc_irq_set_aff(struct lpfc_hba_eq_hdl *eqhdl, unsigned int cpu) +{ + cpumask_clear(&eqhdl->aff_mask); + cpumask_set_cpu(cpu, &eqhdl->aff_mask); + irq_set_status_flags(eqhdl->irq, IRQ_NO_BALANCING); + irq_set_affinity_hint(eqhdl->irq, &eqhdl->aff_mask); +} + +/** + * lpfc_irq_clear_aff - clear IRQ affinity + * @eqhdl: EQ handle + * + **/ +static inline void +lpfc_irq_clear_aff(struct lpfc_hba_eq_hdl *eqhdl) +{ + cpumask_clear(&eqhdl->aff_mask); + irq_clear_status_flags(eqhdl->irq, IRQ_NO_BALANCING); + irq_set_affinity_hint(eqhdl->irq, &eqhdl->aff_mask); +} + +/** + * lpfc_irq_rebalance - rebalances IRQ affinity according to cpuhp event + * @phba: pointer to HBA context object. + * @cpu: cpu going offline/online + * @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. + * + * If cpu is coming online, reaffinitize the IRQ back to the onlineng cpu. + * + * Note: Call only if cfg_irq_numa is enabled, otherwise rely on + * PCI_IRQ_AFFINITY to auto-manage IRQ affinity. + * + **/ +static void +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; + + if (!phba->cfg_irq_numa) + return; + + numa_mask = &phba->sli4_hba.numa_mask; + + if (!cpumask_test_cpu(cpu, numa_mask)) + return; + + cpup = &phba->sli4_hba.cpu_map[cpu]; + + if (!(cpup->flag & LPFC_CPU_FIRST_IRQ)) + 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); + + /* Found a valid CPU */ + if ((cpu_select < nr_cpu_ids) && (cpu_select != cpu)) { + /* Go through each eqhdl and ensure offlining + * cpu aff_mask is migrated + */ + for (idx = 0; idx < phba->cfg_irq_chann; idx++) { + aff_mask = lpfc_get_aff_mask(idx); + + /* Migrate affinity */ + if (cpumask_test_cpu(cpu, aff_mask)) + lpfc_irq_set_aff(lpfc_get_eq_hdl(idx), + cpu_select); + } + } else { + /* Rely on irqbalance if no online CPUs left on NUMA */ + for (idx = 0; idx < phba->cfg_irq_chann; idx++) + lpfc_irq_clear_aff(lpfc_get_eq_hdl(idx)); + } + } else { + /* Migrate affinity back to this CPU */ + lpfc_irq_set_aff(lpfc_get_eq_hdl(cpup->eq), cpu); + } +} + +static int lpfc_cpu_offline(unsigned int cpu, struct hlist_node *node) +{ + struct lpfc_hba *phba = hlist_entry_safe(node, struct lpfc_hba, cpuhp); + struct lpfc_queue *eq, *next; + LIST_HEAD(eqlist); + int retval; + + if (!phba) { + WARN_ONCE(!phba, "cpu: %u. phba:NULL", raw_smp_processor_id()); + return 0; + } + + if (__lpfc_cpuhp_checks(phba, &retval)) + return retval; + + lpfc_irq_rebalance(phba, cpu, true); + + lpfc_cpuhp_get_eq(phba, cpu, &eqlist); + + /* start polling on these eq's */ + list_for_each_entry_safe(eq, next, &eqlist, _poll_list) { + list_del_init(&eq->_poll_list); + lpfc_sli4_start_polling(eq); + } + + return 0; +} + +static int lpfc_cpu_online(unsigned int cpu, struct hlist_node *node) +{ + struct lpfc_hba *phba = hlist_entry_safe(node, struct lpfc_hba, cpuhp); + struct lpfc_queue *eq, *next; + unsigned int n; + int retval; + + if (!phba) { + WARN_ONCE(!phba, "cpu: %u. phba:NULL", raw_smp_processor_id()); + return 0; + } + + if (__lpfc_cpuhp_checks(phba, &retval)) + return retval; + + lpfc_irq_rebalance(phba, cpu, false); + + list_for_each_entry_safe(eq, next, &phba->poll_list, _poll_list) { + n = lpfc_find_cpu_handle(phba, eq->hdwq, LPFC_FIND_BY_HDWQ); + if (n == cpu) + lpfc_sli4_stop_polling(eq); + } + + return 0; +} + +/** * lpfc_sli4_enable_msix - Enable MSI-X interrupt mode to SLI-4 device * @phba: pointer to lpfc hba data structure. * * This routine is invoked to enable the MSI-X interrupt vectors to device - * with SLI-4 interface spec. + * with SLI-4 interface spec. It also allocates MSI-X vectors and maps them + * to cpus on the system. + * + * When cfg_irq_numa is enabled, the adapter will only allocate vectors for + * the number of cpus on the same numa node as this adapter. The vectors are + * allocated without requesting OS affinity mapping. A vector will be + * allocated and assigned to each online and offline cpu. If the cpu is + * online, then affinity will be set to that cpu. If the cpu is offline, then + * affinity will be set to the nearest peer cpu within the numa node that is + * online. If there are no online cpus within the numa node, affinity is not + * assigned and the OS may do as it pleases. Note: cpu vector affinity mapping + * is consistent with the way cpu online/offline is handled when cfg_irq_numa is + * configured. + * + * If numa mode is not enabled and there is more than 1 vector allocated, then + * the driver relies on the managed irq interface where the OS assigns vector to + * cpu affinity. The driver will then use that affinity mapping to setup its + * cpu mapping table. * * Return codes * 0 - successful @@ -11021,13 +11383,31 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba) { int vectors, rc, index; char *name; + const struct cpumask *numa_mask = NULL; + unsigned int cpu = 0, cpu_cnt = 0, cpu_select = nr_cpu_ids; + struct lpfc_hba_eq_hdl *eqhdl; + const struct cpumask *maskp; + bool first; + unsigned int flags = PCI_IRQ_MSIX; /* Set up MSI-X multi-message vectors */ vectors = phba->cfg_irq_chann; - rc = pci_alloc_irq_vectors(phba->pcidev, - 1, - vectors, PCI_IRQ_MSIX | PCI_IRQ_AFFINITY); + if (phba->cfg_irq_numa) { + numa_mask = &phba->sli4_hba.numa_mask; + cpu_cnt = cpumask_weight(numa_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 = cpumask_first(numa_mask); + cpu_select = lpfc_next_online_numa_cpu(numa_mask, cpu); + } else { + flags |= PCI_IRQ_AFFINITY; + } + + rc = pci_alloc_irq_vectors(phba->pcidev, 1, vectors, flags); if (rc < 0) { lpfc_printf_log(phba, KERN_INFO, LOG_INIT, "0484 PCI enable MSI-X failed (%d)\n", rc); @@ -11037,23 +11417,61 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba) /* Assign MSI-X vectors to interrupt handlers */ for (index = 0; index < vectors; index++) { - name = phba->sli4_hba.hba_eq_hdl[index].handler_name; + eqhdl = lpfc_get_eq_hdl(index); + name = eqhdl->handler_name; memset(name, 0, LPFC_SLI4_HANDLER_NAME_SZ); snprintf(name, LPFC_SLI4_HANDLER_NAME_SZ, LPFC_DRIVER_HANDLER_NAME"%d", index); - phba->sli4_hba.hba_eq_hdl[index].idx = index; - phba->sli4_hba.hba_eq_hdl[index].phba = phba; + eqhdl->idx = index; rc = request_irq(pci_irq_vector(phba->pcidev, index), &lpfc_sli4_hba_intr_handler, 0, - name, - &phba->sli4_hba.hba_eq_hdl[index]); + name, eqhdl); if (rc) { lpfc_printf_log(phba, KERN_WARNING, LOG_INIT, "0486 MSI-X fast-path (%d) " "request_irq failed (%d)\n", index, rc); goto cfg_fail_out; } + + eqhdl->irq = pci_irq_vector(phba->pcidev, index); + + if (phba->cfg_irq_numa) { + /* If found a neighboring online cpu, set affinity */ + if (cpu_select < nr_cpu_ids) + lpfc_irq_set_aff(eqhdl, cpu_select); + + /* Assign EQ to cpu_map */ + lpfc_assign_eq_map_info(phba, index, + LPFC_CPU_FIRST_IRQ, + cpu); + + /* Iterate to next offline or online cpu in numa_mask */ + cpu = cpumask_next(cpu, numa_mask); + + /* Find next online cpu in numa_mask to set affinity */ + cpu_select = lpfc_next_online_numa_cpu(numa_mask, cpu); + } else if (vectors == 1) { + cpu = cpumask_first(cpu_present_mask); + lpfc_assign_eq_map_info(phba, index, LPFC_CPU_FIRST_IRQ, + cpu); + } else { + maskp = pci_irq_get_affinity(phba->pcidev, index); + + first = true; + /* Loop through all CPUs associated with vector index */ + for_each_cpu_and(cpu, maskp, cpu_present_mask) { + /* If this is the first CPU thats assigned to + * this vector, set LPFC_CPU_FIRST_IRQ. + */ + lpfc_assign_eq_map_info(phba, index, + first ? + LPFC_CPU_FIRST_IRQ : 0, + cpu); + if (first) + first = false; + } + } } if (vectors != phba->cfg_irq_chann) { @@ -11063,17 +11481,18 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba) phba->cfg_irq_chann, vectors); if (phba->cfg_irq_chann > vectors) phba->cfg_irq_chann = vectors; - if (phba->nvmet_support && (phba->cfg_nvmet_mrq > vectors)) - phba->cfg_nvmet_mrq = vectors; } return rc; cfg_fail_out: /* free the irq already requested */ - for (--index; index >= 0; index--) - free_irq(pci_irq_vector(phba->pcidev, index), - &phba->sli4_hba.hba_eq_hdl[index]); + for (--index; index >= 0; index--) { + eqhdl = lpfc_get_eq_hdl(index); + lpfc_irq_clear_aff(eqhdl); + irq_set_affinity_hint(eqhdl->irq, NULL); + free_irq(eqhdl->irq, eqhdl); + } /* Unconfigure MSI-X capability structure */ pci_free_irq_vectors(phba->pcidev); @@ -11087,10 +11506,10 @@ vec_fail_out: * @phba: pointer to lpfc hba data structure. * * This routine is invoked to enable the MSI interrupt mode to device with - * SLI-4 interface spec. The kernel function pci_enable_msi() is called - * to enable the MSI vector. The device driver is responsible for calling - * the request_irq() to register MSI vector with a interrupt the handler, - * which is done in this function. + * SLI-4 interface spec. The kernel function pci_alloc_irq_vectors() is + * called to enable the MSI vector. The device driver is responsible for + * calling the request_irq() to register MSI vector with a interrupt the + * handler, which is done in this function. * * Return codes * 0 - successful @@ -11100,29 +11519,38 @@ static int lpfc_sli4_enable_msi(struct lpfc_hba *phba) { int rc, index; + unsigned int cpu; + struct lpfc_hba_eq_hdl *eqhdl; - rc = pci_enable_msi(phba->pcidev); - if (!rc) + rc = pci_alloc_irq_vectors(phba->pcidev, 1, 1, + PCI_IRQ_MSI | PCI_IRQ_AFFINITY); + if (rc > 0) lpfc_printf_log(phba, KERN_INFO, LOG_INIT, "0487 PCI enable MSI mode success.\n"); else { lpfc_printf_log(phba, KERN_INFO, LOG_INIT, "0488 PCI enable MSI mode failed (%d)\n", rc); - return rc; + return rc ? rc : -1; } rc = request_irq(phba->pcidev->irq, lpfc_sli4_intr_handler, 0, LPFC_DRIVER_NAME, phba); if (rc) { - pci_disable_msi(phba->pcidev); + pci_free_irq_vectors(phba->pcidev); lpfc_printf_log(phba, KERN_WARNING, LOG_INIT, "0490 MSI request_irq failed (%d)\n", rc); return rc; } + eqhdl = lpfc_get_eq_hdl(0); + eqhdl->irq = pci_irq_vector(phba->pcidev, 0); + + cpu = cpumask_first(cpu_present_mask); + lpfc_assign_eq_map_info(phba, 0, LPFC_CPU_FIRST_IRQ, cpu); + for (index = 0; index < phba->cfg_irq_chann; index++) { - phba->sli4_hba.hba_eq_hdl[index].idx = index; - phba->sli4_hba.hba_eq_hdl[index].phba = phba; + eqhdl = lpfc_get_eq_hdl(index); + eqhdl->idx = index; } return 0; @@ -11180,15 +11608,21 @@ lpfc_sli4_enable_intr(struct lpfc_hba *phba, uint32_t cfg_mode) IRQF_SHARED, LPFC_DRIVER_NAME, phba); if (!retval) { struct lpfc_hba_eq_hdl *eqhdl; + unsigned int cpu; /* Indicate initialization to INTx mode */ phba->intr_type = INTx; intr_mode = 0; + eqhdl = lpfc_get_eq_hdl(0); + eqhdl->irq = pci_irq_vector(phba->pcidev, 0); + + cpu = cpumask_first(cpu_present_mask); + lpfc_assign_eq_map_info(phba, 0, LPFC_CPU_FIRST_IRQ, + cpu); for (idx = 0; idx < phba->cfg_irq_chann; idx++) { - eqhdl = &phba->sli4_hba.hba_eq_hdl[idx]; + eqhdl = lpfc_get_eq_hdl(idx); eqhdl->idx = idx; - eqhdl->phba = phba; } } } @@ -11210,14 +11644,14 @@ lpfc_sli4_disable_intr(struct lpfc_hba *phba) /* Disable the currently initialized interrupt mode */ if (phba->intr_type == MSIX) { int index; + struct lpfc_hba_eq_hdl *eqhdl; /* Free up MSI-X multi-message vectors */ for (index = 0; index < phba->cfg_irq_chann; index++) { - irq_set_affinity_hint( - pci_irq_vector(phba->pcidev, index), - NULL); - free_irq(pci_irq_vector(phba->pcidev, index), - &phba->sli4_hba.hba_eq_hdl[index]); + eqhdl = lpfc_get_eq_hdl(index); + lpfc_irq_clear_aff(eqhdl); + irq_set_affinity_hint(eqhdl->irq, NULL); + free_irq(eqhdl->irq, eqhdl); } } else { free_irq(phba->pcidev->irq, phba); @@ -11280,11 +11714,10 @@ static void lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba) { struct lpfc_sli4_hdw_queue *qp; - int idx, ccnt, fcnt; + int idx, ccnt; int wait_time = 0; int io_xri_cmpl = 1; int nvmet_xri_cmpl = 1; - int fcp_xri_cmpl = 1; int els_xri_cmpl = list_empty(&phba->sli4_hba.lpfc_abts_els_sgl_list); /* Driver just aborted IOs during the hba_unset process. Pause @@ -11298,32 +11731,21 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba) lpfc_nvme_wait_for_io_drain(phba); ccnt = 0; - fcnt = 0; for (idx = 0; idx < phba->cfg_hdw_queue; idx++) { qp = &phba->sli4_hba.hdwq[idx]; - fcp_xri_cmpl = list_empty( - &qp->lpfc_abts_scsi_buf_list); - if (!fcp_xri_cmpl) /* if list is NOT empty */ - fcnt++; - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - io_xri_cmpl = list_empty( - &qp->lpfc_abts_nvme_buf_list); - if (!io_xri_cmpl) /* if list is NOT empty */ - ccnt++; - } + io_xri_cmpl = list_empty(&qp->lpfc_abts_io_buf_list); + if (!io_xri_cmpl) /* if list is NOT empty */ + ccnt++; } if (ccnt) io_xri_cmpl = 0; - if (fcnt) - fcp_xri_cmpl = 0; if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { nvmet_xri_cmpl = list_empty(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list); } - while (!fcp_xri_cmpl || !els_xri_cmpl || !io_xri_cmpl || - !nvmet_xri_cmpl) { + while (!els_xri_cmpl || !io_xri_cmpl || !nvmet_xri_cmpl) { if (wait_time > LPFC_XRI_EXCH_BUSY_WAIT_TMO) { if (!nvmet_xri_cmpl) lpfc_printf_log(phba, KERN_ERR, LOG_INIT, @@ -11332,12 +11754,7 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba) wait_time/1000); if (!io_xri_cmpl) lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "6100 NVME XRI exchange busy " - "wait time: %d seconds.\n", - wait_time/1000); - if (!fcp_xri_cmpl) - lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "2877 FCP XRI exchange busy " + "6100 IO XRI exchange busy " "wait time: %d seconds.\n", wait_time/1000); if (!els_xri_cmpl) @@ -11353,24 +11770,15 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba) } ccnt = 0; - fcnt = 0; for (idx = 0; idx < phba->cfg_hdw_queue; idx++) { qp = &phba->sli4_hba.hdwq[idx]; - fcp_xri_cmpl = list_empty( - &qp->lpfc_abts_scsi_buf_list); - if (!fcp_xri_cmpl) /* if list is NOT empty */ - fcnt++; - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - io_xri_cmpl = list_empty( - &qp->lpfc_abts_nvme_buf_list); - if (!io_xri_cmpl) /* if list is NOT empty */ - ccnt++; - } + io_xri_cmpl = list_empty( + &qp->lpfc_abts_io_buf_list); + if (!io_xri_cmpl) /* if list is NOT empty */ + ccnt++; } if (ccnt) io_xri_cmpl = 0; - if (fcnt) - fcp_xri_cmpl = 0; if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { nvmet_xri_cmpl = list_empty( @@ -11435,6 +11843,9 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) /* Wait for completion of device XRI exchange busy */ lpfc_sli4_xri_exchange_busy_wait(phba); + /* per-phba callback de-registration for hotplug event */ + lpfc_cpuhp_remove(phba); + /* Disable PCI subsystem interrupt */ lpfc_sli4_disable_intr(phba); @@ -11606,6 +12017,7 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq) sli4_params->cqav = bf_get(cfg_cqav, mbx_sli4_parameters); sli4_params->wqsize = bf_get(cfg_wqsize, mbx_sli4_parameters); sli4_params->bv1s = bf_get(cfg_bv1s, mbx_sli4_parameters); + sli4_params->pls = bf_get(cfg_pvl, mbx_sli4_parameters); sli4_params->sgl_pages_max = bf_get(cfg_sgl_page_cnt, mbx_sli4_parameters); sli4_params->wqpcnt = bf_get(cfg_wqpcnt, mbx_sli4_parameters); @@ -11614,6 +12026,9 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq) phba->sli4_hba.extents_in_use = bf_get(cfg_ext, mbx_sli4_parameters); phba->sli4_hba.rpi_hdrs_in_use = bf_get(cfg_hdrr, mbx_sli4_parameters); + /* Check for Extended Pre-Registered SGL support */ + phba->cfg_xpsgl = bf_get(cfg_xpsgl, mbx_sli4_parameters); + /* Check for firmware nvme support */ rc = (bf_get(cfg_nvme, mbx_sli4_parameters) && bf_get(cfg_xib, mbx_sli4_parameters)); @@ -11644,6 +12059,7 @@ fcponly: phba->nvme_support = 0; phba->nvmet_support = 0; phba->cfg_nvmet_mrq = 0; + phba->cfg_nvme_seg_cnt = 0; /* If no FC4 type support, move to just SCSI support */ if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP)) @@ -11652,6 +12068,12 @@ fcponly: } } + /* If the NVME FC4 type is enabled, scale the sg_seg_cnt to + * accommodate 512K and 1M IOs in a single nvme buf. + */ + if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) + phba->cfg_sg_seg_cnt = LPFC_MAX_NVME_SEG_CNT; + /* Only embed PBDE for if_type 6, PBDE support requires xib be set */ if ((bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) != LPFC_SLI_INTF_IF_TYPE_6) || (!bf_get(cfg_xib, mbx_sli4_parameters))) @@ -11716,6 +12138,14 @@ fcponly: else phba->mds_diags_support = 0; + /* + * Check if the SLI port supports NSLER + */ + if (bf_get(cfg_nsler, mbx_sli4_parameters)) + phba->nsler = 1; + else + phba->nsler = 0; + return 0; } @@ -12144,7 +12574,7 @@ lpfc_sli_prep_dev_for_reset(struct lpfc_hba *phba) lpfc_scsi_dev_block(phba); /* Flush all driver's outstanding SCSI I/Os as we are to reset */ - lpfc_sli_flush_fcp_rings(phba); + lpfc_sli_flush_io_rings(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); @@ -12174,7 +12604,7 @@ lpfc_sli_prep_dev_for_perm_failure(struct lpfc_hba *phba) lpfc_stop_hba_timers(phba); /* Clean up all driver's outstanding SCSI I/Os */ - lpfc_sli_flush_fcp_rings(phba); + lpfc_sli_flush_io_rings(phba); } /** @@ -12359,35 +12789,57 @@ lpfc_sli4_get_iocb_cnt(struct lpfc_hba *phba) } -static void +static int lpfc_log_write_firmware_error(struct lpfc_hba *phba, uint32_t offset, uint32_t magic_number, uint32_t ftype, uint32_t fid, uint32_t fsize, const struct firmware *fw) { - if ((offset == ADD_STATUS_FW_NOT_SUPPORTED) || + int rc; + + /* Three cases: (1) FW was not supported on the detected adapter. + * (2) FW update has been locked out administratively. + * (3) Some other error during FW update. + * In each case, an unmaskable message is written to the console + * for admin diagnosis. + */ + if (offset == ADD_STATUS_FW_NOT_SUPPORTED || (phba->pcidev->device == PCI_DEVICE_ID_LANCER_G6_FC && - magic_number != MAGIC_NUMER_G6) || + magic_number != MAGIC_NUMBER_G6) || (phba->pcidev->device == PCI_DEVICE_ID_LANCER_G7_FC && - magic_number != MAGIC_NUMER_G7)) + magic_number != MAGIC_NUMBER_G7)) { lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "3030 This firmware version is not supported on " - "this HBA model. Device:%x Magic:%x Type:%x " - "ID:%x Size %d %zd\n", - phba->pcidev->device, magic_number, ftype, fid, - fsize, fw->size); - else + "3030 This firmware version is not supported on" + " this HBA model. Device:%x Magic:%x Type:%x " + "ID:%x Size %d %zd\n", + phba->pcidev->device, magic_number, ftype, fid, + fsize, fw->size); + rc = -EINVAL; + } else if (offset == ADD_STATUS_FW_DOWNLOAD_HW_DISABLED) { + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "3021 Firmware downloads have been prohibited " + "by a system configuration setting on " + "Device:%x Magic:%x Type:%x ID:%x Size %d " + "%zd\n", + phba->pcidev->device, magic_number, ftype, fid, + fsize, fw->size); + rc = -EACCES; + } else { lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "3022 FW Download failed. Device:%x Magic:%x Type:%x " - "ID:%x Size %d %zd\n", - phba->pcidev->device, magic_number, ftype, fid, - fsize, fw->size); + "3022 FW Download failed. Add Status x%x " + "Device:%x Magic:%x Type:%x ID:%x Size %d " + "%zd\n", + offset, phba->pcidev->device, magic_number, + ftype, fid, fsize, fw->size); + rc = -EIO; + } + return rc; } - /** * lpfc_write_firmware - attempt to write a firmware image to the port * @fw: pointer to firmware image returned from request_firmware. - * @phba: pointer to lpfc hba data structure. + * @context: pointer to firmware image returned from request_firmware. + * @ret: return value this routine provides to the caller. * **/ static void @@ -12456,8 +12908,12 @@ lpfc_write_firmware(const struct firmware *fw, void *context) rc = lpfc_wr_object(phba, &dma_buffer_list, (fw->size - offset), &offset); if (rc) { - lpfc_log_write_firmware_error(phba, offset, - magic_number, ftype, fid, fsize, fw); + rc = lpfc_log_write_firmware_error(phba, offset, + magic_number, + ftype, + fid, + fsize, + fw); goto release_out; } } @@ -12477,9 +12933,12 @@ release_out: } release_firmware(fw); out: - lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "3024 Firmware update done: %d.\n", rc); - return; + if (rc < 0) + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "3062 Firmware update error, status %d.\n", rc); + else + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "3024 Firmware update success: size %d.\n", rc); } /** @@ -12598,6 +13057,12 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid) phba->pport = NULL; lpfc_stop_port(phba); + /* Init cpu_map array */ + lpfc_cpu_map_array_init(phba); + + /* Init hba_eq_hdl array */ + lpfc_hba_eq_hdl_array_init(phba); + /* Configure and enable interrupt */ intr_mode = lpfc_sli4_enable_intr(phba, cfg_mode); if (intr_mode == LPFC_INTR_ERROR) { @@ -12679,6 +13144,9 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid) /* Enable RAS FW log support */ lpfc_sli4_ras_setup(phba); + INIT_LIST_HEAD(&phba->poll_list); + cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state, &phba->cpuhp); + return 0; out_free_sysfs_attr: @@ -12946,12 +13414,8 @@ lpfc_sli4_prep_dev_for_reset(struct lpfc_hba *phba) /* Block all SCSI devices' I/Os on the host */ lpfc_scsi_dev_block(phba); - /* Flush all driver's outstanding SCSI I/Os as we are to reset */ - lpfc_sli_flush_fcp_rings(phba); - - /* Flush the outstanding NVME IOs if fc4 type enabled. */ - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) - lpfc_sli_flush_nvme_rings(phba); + /* Flush all driver's outstanding I/Os as we are to reset */ + lpfc_sli_flush_io_rings(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); @@ -12982,12 +13446,8 @@ lpfc_sli4_prep_dev_for_perm_failure(struct lpfc_hba *phba) /* stop all timers */ lpfc_stop_hba_timers(phba); - /* Clean up all driver's outstanding SCSI I/Os */ - lpfc_sli_flush_fcp_rings(phba); - - /* Flush the outstanding NVME IOs if fc4 type enabled. */ - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) - lpfc_sli_flush_nvme_rings(phba); + /* Clean up all driver's outstanding I/Os */ + lpfc_sli_flush_io_rings(phba); } /** @@ -13399,8 +13859,7 @@ lpfc_sli4_oas_verify(struct lpfc_hba *phba) phba->cfg_fof = 1; } else { phba->cfg_fof = 0; - if (phba->device_data_mem_pool) - mempool_destroy(phba->device_data_mem_pool); + mempool_destroy(phba->device_data_mem_pool); phba->device_data_mem_pool = NULL; } @@ -13505,11 +13964,24 @@ lpfc_init(void) /* Initialize in case vector mapping is needed */ lpfc_present_cpu = num_present_cpus(); + error = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, + "lpfc/sli4:online", + lpfc_cpu_online, lpfc_cpu_offline); + if (error < 0) + goto cpuhp_failure; + lpfc_cpuhp_state = error; + error = pci_register_driver(&lpfc_driver); - if (error) { - fc_release_transport(lpfc_transport_template); - fc_release_transport(lpfc_vport_transport_template); - } + if (error) + goto unwind; + + return error; + +unwind: + cpuhp_remove_multi_state(lpfc_cpuhp_state); +cpuhp_failure: + fc_release_transport(lpfc_transport_template); + fc_release_transport(lpfc_vport_transport_template); return error; } @@ -13526,21 +13998,9 @@ lpfc_exit(void) { misc_deregister(&lpfc_mgmt_dev); pci_unregister_driver(&lpfc_driver); + cpuhp_remove_multi_state(lpfc_cpuhp_state); fc_release_transport(lpfc_transport_template); fc_release_transport(lpfc_vport_transport_template); - if (_dump_buf_data) { - printk(KERN_ERR "9062 BLKGRD: freeing %lu pages for " - "_dump_buf_data at 0x%p\n", - (1L << _dump_buf_data_order), _dump_buf_data); - free_pages((unsigned long)_dump_buf_data, _dump_buf_data_order); - } - - if (_dump_buf_dif) { - printk(KERN_ERR "9049 BLKGRD: freeing %lu pages for " - "_dump_buf_dif at 0x%p\n", - (1L << _dump_buf_dif_order), _dump_buf_dif); - free_pages((unsigned long)_dump_buf_dif, _dump_buf_dif_order); - } idr_destroy(&lpfc_hba_index); } diff --git a/drivers/scsi/lpfc/lpfc_logmsg.h b/drivers/scsi/lpfc/lpfc_logmsg.h index ea10f03437f5..148d02a27b58 100644 --- a/drivers/scsi/lpfc/lpfc_logmsg.h +++ b/drivers/scsi/lpfc/lpfc_logmsg.h @@ -46,6 +46,23 @@ #define LOG_NVME_IOERR 0x00800000 /* NVME IO Error events. */ #define LOG_ALL_MSG 0xffffffff /* LOG all messages */ +/* generate message by verbose log setting or severity */ +#define lpfc_vlog_msg(vport, level, mask, fmt, arg...) \ +{ if (((mask) & (vport)->cfg_log_verbose) || (level[1] <= '4')) \ + dev_printk(level, &((vport)->phba->pcidev)->dev, "%d:(%d):" \ + fmt, (vport)->phba->brd_no, vport->vpi, ##arg); } + +#define lpfc_log_msg(phba, level, mask, fmt, arg...) \ +do { \ + { uint32_t log_verbose = (phba)->pport ? \ + (phba)->pport->cfg_log_verbose : \ + (phba)->cfg_log_verbose; \ + if (((mask) & log_verbose) || (level[1] <= '4')) \ + dev_printk(level, &((phba)->pcidev)->dev, "%d:" \ + fmt, phba->brd_no, ##arg); \ + } \ +} while (0) + #define lpfc_printf_vlog(vport, level, mask, fmt, arg...) \ do { \ { if (((mask) & (vport)->cfg_log_verbose) || (level[1] <= '3')) \ diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c index 8abe933bad09..d1773c01d2b3 100644 --- a/drivers/scsi/lpfc/lpfc_mbox.c +++ b/drivers/scsi/lpfc/lpfc_mbox.c @@ -515,6 +515,7 @@ lpfc_init_link(struct lpfc_hba * phba, if ((phba->pcidev->device == PCI_DEVICE_ID_LANCER_G6_FC || phba->pcidev->device == PCI_DEVICE_ID_LANCER_G7_FC) && + !(phba->sli4_hba.pc_sli4_params.pls) && mb->un.varInitLnk.link_flags & FLAGS_TOPOLOGY_MODE_LOOP) { mb->un.varInitLnk.link_flags = FLAGS_TOPOLOGY_MODE_PT_PT; phba->cfg_topology = FLAGS_TOPOLOGY_MODE_PT_PT; diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c index 66191fa35f63..7082279e4c01 100644 --- a/drivers/scsi/lpfc/lpfc_mem.c +++ b/drivers/scsi/lpfc/lpfc_mem.c @@ -72,8 +72,8 @@ lpfc_mem_alloc_active_rrq_pool_s4(struct lpfc_hba *phba) { * lpfc_mem_alloc - create and allocate all PCI and memory pools * @phba: HBA to allocate pools for * - * Description: Creates and allocates PCI pools lpfc_sg_dma_buf_pool, - * lpfc_mbuf_pool, lpfc_hrb_pool. Creates and allocates kmalloc-backed mempools + * Description: Creates and allocates PCI pools lpfc_mbuf_pool, + * lpfc_hrb_pool. Creates and allocates kmalloc-backed mempools * for LPFC_MBOXQ_t and lpfc_nodelist. Also allocates the VPI bitmask. * * Notes: Not interrupt-safe. Must be called with no locks held. If any @@ -89,36 +89,12 @@ lpfc_mem_alloc(struct lpfc_hba *phba, int align) struct lpfc_dma_pool *pool = &phba->lpfc_mbuf_safety_pool; int i; - if (phba->sli_rev == LPFC_SLI_REV4) { - /* Calculate alignment */ - if (phba->cfg_sg_dma_buf_size < SLI4_PAGE_SIZE) - i = phba->cfg_sg_dma_buf_size; - else - i = SLI4_PAGE_SIZE; - - phba->lpfc_sg_dma_buf_pool = - dma_pool_create("lpfc_sg_dma_buf_pool", - &phba->pcidev->dev, - phba->cfg_sg_dma_buf_size, - i, 0); - if (!phba->lpfc_sg_dma_buf_pool) - goto fail; - - } else { - phba->lpfc_sg_dma_buf_pool = - dma_pool_create("lpfc_sg_dma_buf_pool", - &phba->pcidev->dev, phba->cfg_sg_dma_buf_size, - align, 0); - - if (!phba->lpfc_sg_dma_buf_pool) - goto fail; - } phba->lpfc_mbuf_pool = dma_pool_create("lpfc_mbuf_pool", &phba->pcidev->dev, LPFC_BPL_SIZE, align, 0); if (!phba->lpfc_mbuf_pool) - goto fail_free_dma_buf_pool; + goto fail; pool->elements = kmalloc_array(LPFC_MBUF_POOL_SIZE, sizeof(struct lpfc_dmabuf), @@ -208,9 +184,6 @@ fail_free_drb_pool: fail_free_lpfc_mbuf_pool: dma_pool_destroy(phba->lpfc_mbuf_pool); phba->lpfc_mbuf_pool = NULL; - fail_free_dma_buf_pool: - dma_pool_destroy(phba->lpfc_sg_dma_buf_pool); - phba->lpfc_sg_dma_buf_pool = NULL; fail: return -ENOMEM; } @@ -248,25 +221,19 @@ lpfc_mem_free(struct lpfc_hba *phba) /* Free HBQ pools */ lpfc_sli_hbqbuf_free_all(phba); - if (phba->lpfc_nvmet_drb_pool) - dma_pool_destroy(phba->lpfc_nvmet_drb_pool); + dma_pool_destroy(phba->lpfc_nvmet_drb_pool); phba->lpfc_nvmet_drb_pool = NULL; - if (phba->lpfc_drb_pool) - dma_pool_destroy(phba->lpfc_drb_pool); + + dma_pool_destroy(phba->lpfc_drb_pool); phba->lpfc_drb_pool = NULL; - if (phba->lpfc_hrb_pool) - dma_pool_destroy(phba->lpfc_hrb_pool); + + dma_pool_destroy(phba->lpfc_hrb_pool); phba->lpfc_hrb_pool = NULL; - if (phba->txrdy_payload_pool) - dma_pool_destroy(phba->txrdy_payload_pool); - phba->txrdy_payload_pool = NULL; - if (phba->lpfc_hbq_pool) - dma_pool_destroy(phba->lpfc_hbq_pool); + dma_pool_destroy(phba->lpfc_hbq_pool); phba->lpfc_hbq_pool = NULL; - if (phba->rrq_pool) - mempool_destroy(phba->rrq_pool); + mempool_destroy(phba->rrq_pool); phba->rrq_pool = NULL; /* Free NLP memory pool */ @@ -290,10 +257,6 @@ lpfc_mem_free(struct lpfc_hba *phba) dma_pool_destroy(phba->lpfc_mbuf_pool); phba->lpfc_mbuf_pool = NULL; - /* Free DMA buffer memory pool */ - dma_pool_destroy(phba->lpfc_sg_dma_buf_pool); - phba->lpfc_sg_dma_buf_pool = NULL; - /* Free Device Data memory pool */ if (phba->device_data_mem_pool) { /* Ensure all objects have been returned to the pool */ @@ -366,6 +329,13 @@ lpfc_mem_free_all(struct lpfc_hba *phba) /* Free and destroy all the allocated memory pools */ lpfc_mem_free(phba); + /* Free DMA buffer memory pool */ + dma_pool_destroy(phba->lpfc_sg_dma_buf_pool); + phba->lpfc_sg_dma_buf_pool = NULL; + + dma_pool_destroy(phba->lpfc_cmd_rsp_buf_pool); + phba->lpfc_cmd_rsp_buf_pool = NULL; + /* Free the iocb lookup array */ kfree(psli->iocbq_lookup); psli->iocbq_lookup = NULL; diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index 59252bfca14e..a024e5a3918f 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -279,6 +279,109 @@ lpfc_els_abort(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp) lpfc_cancel_retry_delay_tmo(phba->pport, ndlp); } +/* lpfc_defer_pt2pt_acc - Complete SLI3 pt2pt processing on link up + * @phba: pointer to lpfc hba data structure. + * @link_mbox: pointer to CONFIG_LINK mailbox object + * + * This routine is only called if we are SLI3, direct connect pt2pt + * mode and the remote NPort issues the PLOGI after link up. + */ +static void +lpfc_defer_pt2pt_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *link_mbox) +{ + LPFC_MBOXQ_t *login_mbox; + MAILBOX_t *mb = &link_mbox->u.mb; + struct lpfc_iocbq *save_iocb; + struct lpfc_nodelist *ndlp; + int rc; + + ndlp = link_mbox->ctx_ndlp; + login_mbox = link_mbox->context3; + save_iocb = login_mbox->context3; + link_mbox->context3 = NULL; + login_mbox->context3 = NULL; + + /* Check for CONFIG_LINK error */ + if (mb->mbxStatus) { + lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY, + "4575 CONFIG_LINK fails pt2pt discovery: %x\n", + mb->mbxStatus); + mempool_free(login_mbox, phba->mbox_mem_pool); + mempool_free(link_mbox, phba->mbox_mem_pool); + kfree(save_iocb); + return; + } + + /* Now that CONFIG_LINK completed, and our SID is configured, + * we can now proceed with sending the PLOGI ACC. + */ + rc = lpfc_els_rsp_acc(link_mbox->vport, ELS_CMD_PLOGI, + save_iocb, ndlp, login_mbox); + if (rc) { + lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY, + "4576 PLOGI ACC fails pt2pt discovery: %x\n", + rc); + mempool_free(login_mbox, phba->mbox_mem_pool); + } + + mempool_free(link_mbox, phba->mbox_mem_pool); + kfree(save_iocb); +} + +/** + * lpfc_defer_tgt_acc - Progress SLI4 target rcv PLOGI handler + * @phba: Pointer to HBA context object. + * @pmb: Pointer to mailbox object. + * + * This function provides the unreg rpi mailbox completion handler for a tgt. + * The routine frees the memory resources associated with the completed + * mailbox command and transmits the ELS ACC. + * + * This routine is only called if we are SLI4, acting in target + * mode and the remote NPort issues the PLOGI after link up. + **/ +static void +lpfc_defer_acc_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) +{ + struct lpfc_vport *vport = pmb->vport; + struct lpfc_nodelist *ndlp = pmb->ctx_ndlp; + LPFC_MBOXQ_t *mbox = pmb->context3; + struct lpfc_iocbq *piocb = NULL; + int rc; + + if (mbox) { + pmb->context3 = NULL; + piocb = mbox->context3; + mbox->context3 = NULL; + } + + /* + * Complete the unreg rpi mbx request, and update flags. + * This will also restart any deferred events. + */ + lpfc_nlp_get(ndlp); + lpfc_sli4_unreg_rpi_cmpl_clr(phba, pmb); + + if (!piocb) { + lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY | LOG_ELS, + "4578 PLOGI ACC fail\n"); + if (mbox) + mempool_free(mbox, phba->mbox_mem_pool); + goto out; + } + + rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, piocb, ndlp, mbox); + if (rc) { + lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY | LOG_ELS, + "4579 PLOGI ACC fail %x\n", rc); + if (mbox) + mempool_free(mbox, phba->mbox_mem_pool); + } + kfree(piocb); +out: + lpfc_nlp_put(ndlp); +} + static int lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, struct lpfc_iocbq *cmdiocb) @@ -291,10 +394,13 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, IOCB_t *icmd; struct serv_parm *sp; uint32_t ed_tov; - LPFC_MBOXQ_t *mbox; + LPFC_MBOXQ_t *link_mbox; + LPFC_MBOXQ_t *login_mbox; + struct lpfc_iocbq *save_iocb; struct ls_rjt stat; uint32_t vid, flag; - int rc; + u16 rpi; + int rc, defer_acc; memset(&stat, 0, sizeof (struct ls_rjt)); pcmd = (struct lpfc_dmabuf *) cmdiocb->context2; @@ -343,6 +449,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, else ndlp->nlp_fcp_info |= CLASS3; + defer_acc = 0; ndlp->nlp_class_sup = 0; if (sp->cls1.classValid) ndlp->nlp_class_sup |= FC_COS_CLASS1; @@ -354,7 +461,6 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_class_sup |= FC_COS_CLASS4; ndlp->nlp_maxframe = ((sp->cmn.bbRcvSizeMsb & 0x0F) << 8) | sp->cmn.bbRcvSizeLsb; - /* if already logged in, do implicit logout */ switch (ndlp->nlp_state) { case NLP_STE_NPR_NODE: @@ -396,6 +502,10 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE; ndlp->nlp_flag &= ~NLP_FIRSTBURST; + login_mbox = NULL; + link_mbox = NULL; + save_iocb = NULL; + /* Check for Nport to NPort pt2pt protocol */ if ((vport->fc_flag & FC_PT2PT) && !(vport->fc_flag & FC_PT2PT_PLOGI)) { @@ -423,17 +533,22 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if (phba->sli_rev == LPFC_SLI_REV4) lpfc_issue_reg_vfi(vport); else { - mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); - if (mbox == NULL) + defer_acc = 1; + link_mbox = mempool_alloc(phba->mbox_mem_pool, + GFP_KERNEL); + if (!link_mbox) goto out; - lpfc_config_link(phba, mbox); - mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl; - mbox->vport = vport; - rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT); - if (rc == MBX_NOT_FINISHED) { - mempool_free(mbox, phba->mbox_mem_pool); + lpfc_config_link(phba, link_mbox); + link_mbox->mbox_cmpl = lpfc_defer_pt2pt_acc; + link_mbox->vport = vport; + link_mbox->ctx_ndlp = ndlp; + + save_iocb = kzalloc(sizeof(*save_iocb), GFP_KERNEL); + if (!save_iocb) goto out; - } + /* Save info from cmd IOCB used in rsp */ + memcpy((uint8_t *)save_iocb, (uint8_t *)cmdiocb, + sizeof(struct lpfc_iocbq)); } lpfc_can_disctmo(vport); @@ -448,30 +563,57 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_flag |= NLP_SUPPRESS_RSP; } - mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); - if (!mbox) + login_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); + if (!login_mbox) goto out; /* Registering an existing RPI behaves differently for SLI3 vs SLI4 */ - if (phba->sli_rev == LPFC_SLI_REV4) + if (phba->nvmet_support && !defer_acc) { + link_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); + if (!link_mbox) + goto out; + + /* As unique identifiers such as iotag would be overwritten + * with those from the cmdiocb, allocate separate temporary + * storage for the copy. + */ + save_iocb = kzalloc(sizeof(*save_iocb), GFP_KERNEL); + if (!save_iocb) + goto out; + + /* Unreg RPI is required for SLI4. */ + rpi = phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]; + lpfc_unreg_login(phba, vport->vpi, rpi, link_mbox); + link_mbox->vport = vport; + link_mbox->ctx_ndlp = ndlp; + link_mbox->mbox_cmpl = lpfc_defer_acc_rsp; + + if (((ndlp->nlp_DID & Fabric_DID_MASK) != Fabric_DID_MASK) && + (!(vport->fc_flag & FC_OFFLINE_MODE))) + ndlp->nlp_flag |= NLP_UNREG_INP; + + /* Save info from cmd IOCB used in rsp */ + memcpy(save_iocb, cmdiocb, sizeof(*save_iocb)); + + /* Delay sending ACC till unreg RPI completes. */ + defer_acc = 1; + } else if (phba->sli_rev == LPFC_SLI_REV4) lpfc_unreg_rpi(vport, ndlp); rc = lpfc_reg_rpi(phba, vport->vpi, icmd->un.rcvels.remoteID, - (uint8_t *) sp, mbox, ndlp->nlp_rpi); - if (rc) { - mempool_free(mbox, phba->mbox_mem_pool); + (uint8_t *)sp, login_mbox, ndlp->nlp_rpi); + if (rc) goto out; - } /* ACC PLOGI rsp command needs to execute first, - * queue this mbox command to be processed later. + * queue this login_mbox command to be processed later. */ - mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login; + login_mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login; /* - * mbox->ctx_ndlp = lpfc_nlp_get(ndlp) deferred until mailbox + * login_mbox->ctx_ndlp = lpfc_nlp_get(ndlp) deferred until mailbox * command issued in lpfc_cmpl_els_acc(). */ - mbox->vport = vport; + login_mbox->vport = vport; spin_lock_irq(shost->host_lock); ndlp->nlp_flag |= (NLP_ACC_REGLOGIN | NLP_RCV_PLOGI); spin_unlock_irq(shost->host_lock); @@ -484,8 +626,10 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, * single discovery thread, this will cause a huge delay in * discovery. Also this will cause multiple state machines * running in parallel for this node. + * This only applies to a fabric environment. */ - if (ndlp->nlp_state == NLP_STE_PLOGI_ISSUE) { + if ((ndlp->nlp_state == NLP_STE_PLOGI_ISSUE) && + (vport->fc_flag & FC_FABRIC)) { /* software abort outstanding PLOGI */ lpfc_els_abort(phba, ndlp); } @@ -493,6 +637,9 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if ((vport->port_type == LPFC_NPIV_PORT && vport->cfg_restrict_login)) { + /* no deferred ACC */ + kfree(save_iocb); + /* In order to preserve RPIs, we want to cleanup * the default RPI the firmware created to rcv * this ELS request. The only way to do this is @@ -504,16 +651,50 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, stat.un.b.lsRjtRsnCode = LSRJT_INVALID_CMD; stat.un.b.lsRjtRsnCodeExp = LSEXP_NOTHING_MORE; rc = lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb, - ndlp, mbox); + ndlp, login_mbox); if (rc) - mempool_free(mbox, phba->mbox_mem_pool); + mempool_free(login_mbox, phba->mbox_mem_pool); + return 1; + } + if (defer_acc) { + /* So the order here should be: + * SLI3 pt2pt + * Issue CONFIG_LINK mbox + * CONFIG_LINK cmpl + * SLI4 tgt + * Issue UNREG RPI mbx + * UNREG RPI cmpl + * Issue PLOGI ACC + * PLOGI ACC cmpl + * Issue REG_LOGIN mbox + */ + + /* Save the REG_LOGIN mbox for and rcv IOCB copy later */ + link_mbox->context3 = login_mbox; + login_mbox->context3 = save_iocb; + + /* Start the ball rolling by issuing CONFIG_LINK here */ + rc = lpfc_sli_issue_mbox(phba, link_mbox, MBX_NOWAIT); + if (rc == MBX_NOT_FINISHED) + goto out; return 1; } - rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, mbox); + + rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, login_mbox); if (rc) - mempool_free(mbox, phba->mbox_mem_pool); + mempool_free(login_mbox, phba->mbox_mem_pool); return 1; out: + if (defer_acc) + lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY, + "4577 discovery failure: %p %p %p\n", + save_iocb, link_mbox, login_mbox); + kfree(save_iocb); + if (link_mbox) + mempool_free(link_mbox, phba->mbox_mem_pool); + if (login_mbox) + mempool_free(login_mbox, phba->mbox_mem_pool); + stat.un.b.lsRjtRsnCode = LSRJT_UNABLE_TPC; stat.un.b.lsRjtRsnCodeExp = LSEXP_OUT_OF_RESOURCE; lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb, ndlp, NULL); @@ -614,7 +795,7 @@ lpfc_rcv_padisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, } out: /* If we are authenticated, move to the proper state */ - if (ndlp->nlp_type & NLP_FCP_TARGET) + if (ndlp->nlp_type & (NLP_FCP_TARGET | NLP_NVME_TARGET)) lpfc_nlp_set_state(vport, ndlp, NLP_STE_MAPPED_NODE); else lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE); @@ -799,9 +980,15 @@ lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if (npr->writeXferRdyDis) ndlp->nlp_flag |= NLP_FIRSTBURST; } - if (npr->Retry) + if (npr->Retry && ndlp->nlp_type & + (NLP_FCP_INITIATOR | NLP_FCP_TARGET)) ndlp->nlp_fcp_info |= NLP_FCP_2_DEVICE; + if (npr->Retry && phba->nsler && + ndlp->nlp_type & (NLP_NVME_INITIATOR | NLP_NVME_TARGET)) + ndlp->nlp_nvme_info |= NLP_NVME_NSLER; + + /* If this driver is in nvme target mode, set the ndlp's fc4 * type to NVME provided the PRLI response claims NVME FC4 * type. Target mode does not issue gft_id so doesn't get @@ -845,9 +1032,9 @@ lpfc_disc_set_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) if (!(vport->fc_flag & FC_PT2PT)) { /* Check config parameter use-adisc or FCP-2 */ - if ((vport->cfg_use_adisc && (vport->fc_flag & FC_RSCN_MODE)) || + if (vport->cfg_use_adisc && ((vport->fc_flag & FC_RSCN_MODE) || ((ndlp->nlp_fcp_info & NLP_FCP_2_DEVICE) && - (ndlp->nlp_type & NLP_FCP_TARGET))) { + (ndlp->nlp_type & NLP_FCP_TARGET)))) { spin_lock_irq(shost->host_lock); ndlp->nlp_flag |= NLP_NPR_ADISC; spin_unlock_irq(shost->host_lock); @@ -885,7 +1072,7 @@ lpfc_release_rpi(struct lpfc_hba *phba, struct lpfc_vport *vport, lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, "1435 release_rpi SKIP UNREG x%x on " "NPort x%x deferred x%x flg x%x " - "Data: %p\n", + "Data: x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_defer_did, ndlp->nlp_flag, ndlp); @@ -1661,6 +1848,7 @@ lpfc_rcv_logo_reglogin_issue(struct lpfc_vport *vport, LPFC_MBOXQ_t *mb; LPFC_MBOXQ_t *nextmb; struct lpfc_dmabuf *mp; + struct lpfc_nodelist *ns_ndlp; cmdiocb = (struct lpfc_iocbq *) arg; @@ -1693,6 +1881,13 @@ lpfc_rcv_logo_reglogin_issue(struct lpfc_vport *vport, } spin_unlock_irq(&phba->hbalock); + /* software abort if any GID_FT is outstanding */ + if (vport->cfg_enable_fc4_type != LPFC_ENABLE_FCP) { + ns_ndlp = lpfc_findnode_did(vport, NameServer_DID); + if (ns_ndlp && NLP_CHK_NODE_ACT(ns_ndlp)) + lpfc_els_abort(phba, ns_ndlp); + } + lpfc_rcv_logo(vport, ndlp, cmdiocb, ELS_CMD_LOGO); return ndlp->nlp_state; } @@ -1814,7 +2009,11 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport, ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE; lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE); - lpfc_issue_els_prli(vport, ndlp, 0); + if (lpfc_issue_els_prli(vport, ndlp, 0)) { + lpfc_issue_els_logo(vport, ndlp, 0); + ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE; + lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE); + } } else { if ((vport->fc_flag & FC_PT2PT) && phba->nvmet_support) phba->targetport->port_id = vport->fc_myDID; @@ -2012,6 +2211,13 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if (bf_get_be32(prli_init, nvpr)) ndlp->nlp_type |= NLP_NVME_INITIATOR; + if (phba->nsler && bf_get_be32(prli_nsler, nvpr) && + bf_get_be32(prli_conf, nvpr)) + + ndlp->nlp_nvme_info |= NLP_NVME_NSLER; + else + ndlp->nlp_nvme_info &= ~NLP_NVME_NSLER; + /* Target driver cannot solicit NVME FB. */ if (bf_get_be32(prli_tgt, nvpr)) { /* Complete the nvme target roles. The transport @@ -2891,18 +3097,21 @@ lpfc_disc_state_machine(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, uint32_t(*func) (struct lpfc_vport *, struct lpfc_nodelist *, void *, uint32_t); uint32_t got_ndlp = 0; + uint32_t data1; if (lpfc_nlp_get(ndlp)) got_ndlp = 1; cur_state = ndlp->nlp_state; + data1 = (((uint32_t)ndlp->nlp_fc4_type << 16) | + ((uint32_t)ndlp->nlp_type)); /* DSM in event <evt> on NPort <nlp_DID> in state <cur_state> */ lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, "0211 DSM in event x%x on NPort x%x in " "state %d rpi x%x Data: x%x x%x\n", evt, ndlp->nlp_DID, cur_state, ndlp->nlp_rpi, - ndlp->nlp_flag, ndlp->nlp_fc4_type); + ndlp->nlp_flag, data1); lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_DSM, "DSM in: evt:%d ste:%d did:x%x", @@ -2913,10 +3122,13 @@ lpfc_disc_state_machine(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, /* DSM out state <rc> on NPort <nlp_DID> */ if (got_ndlp) { + data1 = (((uint32_t)ndlp->nlp_fc4_type << 16) | + ((uint32_t)ndlp->nlp_type)); lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, "0212 DSM out state %d on NPort x%x " - "rpi x%x Data: x%x\n", - rc, ndlp->nlp_DID, ndlp->nlp_rpi, ndlp->nlp_flag); + "rpi x%x Data: x%x x%x\n", + rc, ndlp->nlp_DID, ndlp->nlp_rpi, ndlp->nlp_flag, + data1); lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_DSM, "DSM out: ste:%d did:x%x flg:x%x", diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 946642cee3df..f6c8963c915d 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -196,6 +196,46 @@ lpfc_nvme_cmd_template(void) } /** + * lpfc_nvme_prep_abort_wqe - set up 'abort' work queue entry. + * @pwqeq: Pointer to command iocb. + * @xritag: Tag that uniqely identifies the local exchange resource. + * @opt: Option bits - + * bit 0 = inhibit sending abts on the link + * + * This function is called with hbalock held. + **/ +void +lpfc_nvme_prep_abort_wqe(struct lpfc_iocbq *pwqeq, u16 xritag, u8 opt) +{ + union lpfc_wqe128 *wqe = &pwqeq->wqe; + + /* WQEs are reused. Clear stale data and set key fields to + * zero like ia, iaab, iaar, xri_tag, and ctxt_tag. + */ + memset(wqe, 0, sizeof(*wqe)); + + if (opt & INHIBIT_ABORT) + bf_set(abort_cmd_ia, &wqe->abort_cmd, 1); + /* Abort specified xri tag, with the mask deliberately zeroed */ + bf_set(abort_cmd_criteria, &wqe->abort_cmd, T_XRI_TAG); + + bf_set(wqe_cmnd, &wqe->abort_cmd.wqe_com, CMD_ABORT_XRI_CX); + + /* Abort the IO associated with this outstanding exchange ID. */ + wqe->abort_cmd.wqe_com.abort_tag = xritag; + + /* iotag for the wqe completion. */ + bf_set(wqe_reqtag, &wqe->abort_cmd.wqe_com, pwqeq->iotag); + + bf_set(wqe_qosd, &wqe->abort_cmd.wqe_com, 1); + bf_set(wqe_lenloc, &wqe->abort_cmd.wqe_com, LPFC_WQE_LENLOC_NONE); + + bf_set(wqe_cmd_type, &wqe->abort_cmd.wqe_com, OTHER_COMMAND); + bf_set(wqe_wqec, &wqe->abort_cmd.wqe_com, 1); + bf_set(wqe_cqid, &wqe->abort_cmd.wqe_com, LPFC_WQE_CQ_ID_DEFAULT); +} + +/** * lpfc_nvme_create_queue - * @lpfc_pnvme: Pointer to the driver's nvme instance data * @qidx: An cpu index used to affinitize IO queues and MSIX vectors. @@ -247,7 +287,7 @@ lpfc_nvme_create_queue(struct nvme_fc_local_port *pnvme_lport, lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME, "6073 Binding %s HdwQueue %d (cpu %d) to " - "hdw_queue %d qhandle %p\n", str, + "hdw_queue %d qhandle x%px\n", str, qidx, qhandle->cpu_id, qhandle->index, qhandle); *handle = (void *)qhandle; return 0; @@ -282,7 +322,7 @@ lpfc_nvme_delete_queue(struct nvme_fc_local_port *pnvme_lport, vport = lport->vport; lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME, - "6001 ENTER. lpfc_pnvme %p, qidx x%x qhandle %p\n", + "6001 ENTER. lpfc_pnvme x%px, qidx x%x qhandle x%px\n", lport, qidx, handle); kfree(handle); } @@ -293,7 +333,7 @@ lpfc_nvme_localport_delete(struct nvme_fc_local_port *localport) struct lpfc_nvme_lport *lport = localport->private; lpfc_printf_vlog(lport->vport, KERN_INFO, LOG_NVME, - "6173 localport %p delete complete\n", + "6173 localport x%px delete complete\n", lport); /* release any threads waiting for the unreg to complete */ @@ -332,7 +372,7 @@ lpfc_nvme_remoteport_delete(struct nvme_fc_remote_port *remoteport) * calling state machine to remove the node. */ lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC, - "6146 remoteport delete of remoteport %p\n", + "6146 remoteport delete of remoteport x%px\n", remoteport); spin_lock_irq(&vport->phba->hbalock); @@ -383,8 +423,8 @@ lpfc_nvme_cmpl_gen_req(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe, ndlp = (struct lpfc_nodelist *)cmdwqe->context1; lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC, "6047 nvme cmpl Enter " - "Data %p DID %x Xri: %x status %x reason x%x cmd:%p " - "lsreg:%p bmp:%p ndlp:%p\n", + "Data %px DID %x Xri: %x status %x reason x%x " + "cmd:x%px lsreg:x%px bmp:x%px ndlp:x%px\n", pnvme_lsreq, ndlp ? ndlp->nlp_DID : 0, cmdwqe->sli4_xritag, status, (wcqe->parameter & 0xffff), @@ -404,7 +444,7 @@ lpfc_nvme_cmpl_gen_req(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe, else lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC, "6046 nvme cmpl without done call back? " - "Data %p DID %x Xri: %x status %x\n", + "Data %px DID %x Xri: %x status %x\n", pnvme_lsreq, ndlp ? ndlp->nlp_DID : 0, cmdwqe->sli4_xritag, status); if (ndlp) { @@ -436,6 +476,7 @@ lpfc_nvme_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp, return 1; wqe = &genwqe->wqe; + /* Initialize only 64 bytes */ memset(wqe, 0, sizeof(union lpfc_wqe)); genwqe->context3 = (uint8_t *)bmp; @@ -516,7 +557,8 @@ lpfc_nvme_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp, /* Issue GEN REQ WQE for NPORT <did> */ lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS, "6050 Issue GEN REQ WQE to NPORT x%x " - "Data: x%x x%x wq:%p lsreq:%p bmp:%p xmit:%d 1st:%d\n", + "Data: x%x x%x wq:x%px lsreq:x%px bmp:x%px " + "xmit:%d 1st:%d\n", ndlp->nlp_DID, genwqe->iotag, vport->port_state, genwqe, pnvme_lsreq, bmp, xmit_len, first_len); @@ -594,7 +636,7 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport, ndlp = rport->ndlp; if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) { lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR, - "6051 Remoteport %p, rport has invalid ndlp. " + "6051 Remoteport x%px, rport has invalid ndlp. " "Failing LS Req\n", pnvme_rport); return -ENODEV; } @@ -646,10 +688,10 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport, /* Expand print to include key fields. */ lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC, - "6149 Issue LS Req to DID 0x%06x lport %p, rport %p " - "lsreq%p rqstlen:%d rsplen:%d %pad %pad\n", - ndlp->nlp_DID, - pnvme_lport, pnvme_rport, + "6149 Issue LS Req to DID 0x%06x lport x%px, " + "rport x%px lsreq x%px rqstlen:%d rsplen:%d " + "%pad %pad\n", + ndlp->nlp_DID, pnvme_lport, pnvme_rport, pnvme_lsreq, pnvme_lsreq->rqstlen, pnvme_lsreq->rsplen, &pnvme_lsreq->rqstdma, &pnvme_lsreq->rspdma); @@ -665,8 +707,8 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport, if (ret != WQE_SUCCESS) { atomic_inc(&lport->xmt_ls_err); lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC, - "6052 EXIT. issue ls wqe failed lport %p, " - "rport %p lsreq%p Status %x DID %x\n", + "6052 EXIT. issue ls wqe failed lport x%px, " + "rport x%px lsreq x%px Status %x DID %x\n", pnvme_lport, pnvme_rport, pnvme_lsreq, ret, ndlp->nlp_DID); lpfc_mbuf_free(vport->phba, bmp->virt, bmp->phys); @@ -723,7 +765,7 @@ lpfc_nvme_ls_abort(struct nvme_fc_local_port *pnvme_lport, /* Expand print to include key fields. */ lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_ABTS, - "6040 ENTER. lport %p, rport %p lsreq %p rqstlen:%d " + "6040 ENTER. lport x%px, rport x%px lsreq x%px rqstlen:%d " "rsplen:%d %pad %pad\n", pnvme_lport, pnvme_rport, pnvme_lsreq, pnvme_lsreq->rqstlen, @@ -984,8 +1026,8 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn, if (!lpfc_ncmd->nvmeCmd) { spin_unlock(&lpfc_ncmd->buf_lock); lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR, - "6066 Missing cmpl ptrs: lpfc_ncmd %p, " - "nvmeCmd %p\n", + "6066 Missing cmpl ptrs: lpfc_ncmd x%px, " + "nvmeCmd x%px\n", lpfc_ncmd, lpfc_ncmd->nvmeCmd); /* Release the lpfc_ncmd regardless of the missing elements. */ @@ -998,9 +1040,9 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn, idx = lpfc_ncmd->cur_iocbq.hba_wqidx; phba->sli4_hba.hdwq[idx].nvme_cstat.io_cmpls++; - if (vport->localport) { + if (unlikely(status && vport->localport)) { lport = (struct lpfc_nvme_lport *)vport->localport->private; - if (lport && status) { + if (lport) { if (bf_get(lpfc_wcqe_c_xb, wcqe)) atomic_inc(&lport->cmpl_fcp_xb); atomic_inc(&lport->cmpl_fcp_err); @@ -1100,8 +1142,8 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn, if (lpfc_ncmd->result == IOERR_ABORT_REQUESTED) lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR, - "6032 Delay Aborted cmd %p " - "nvme cmd %p, xri x%x, " + "6032 Delay Aborted cmd x%px " + "nvme cmd x%px, xri x%x, " "xb %d\n", lpfc_ncmd, nCmd, lpfc_ncmd->cur_iocbq.sli4_xritag, @@ -1140,7 +1182,7 @@ out_err: phba->ktime_last_cmd = lpfc_ncmd->ts_data_nvme; lpfc_nvme_ktime(phba, lpfc_ncmd); } - if (phba->cpucheck_on & LPFC_CHECK_NVME_IO) { + if (unlikely(phba->cpucheck_on & LPFC_CHECK_NVME_IO)) { uint32_t cpu; idx = lpfc_ncmd->cur_iocbq.hba_wqidx; cpu = raw_smp_processor_id(); @@ -1253,6 +1295,9 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport, sizeof(uint32_t) * 8); cstat->control_requests++; } + + if (pnode->nlp_nvme_info & NLP_NVME_NSLER) + bf_set(wqe_erp, &wqe->generic.wqe_com, 1); /* * Finish initializing those WQE fields that are independent * of the nvme_cmnd request_buffer @@ -1304,14 +1349,16 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport, struct nvmefc_fcp_req *nCmd = lpfc_ncmd->nvmeCmd; union lpfc_wqe128 *wqe = &lpfc_ncmd->cur_iocbq.wqe; struct sli4_sge *sgl = lpfc_ncmd->dma_sgl; + struct sli4_hybrid_sgl *sgl_xtra = NULL; struct scatterlist *data_sg; struct sli4_sge *first_data_sgl; struct ulp_bde64 *bde; - dma_addr_t physaddr; + dma_addr_t physaddr = 0; uint32_t num_bde = 0; - uint32_t dma_len; + uint32_t dma_len = 0; uint32_t dma_offset = 0; - int nseg, i; + int nseg, i, j; + bool lsp_just_set = false; /* Fix up the command and response DMA stuff. */ lpfc_nvme_adj_fcp_sgls(vport, lpfc_ncmd, nCmd); @@ -1348,6 +1395,9 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport, */ nseg = nCmd->sg_cnt; data_sg = nCmd->first_sgl; + + /* for tracking the segment boundaries */ + j = 2; for (i = 0; i < nseg; i++) { if (data_sg == NULL) { lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR, @@ -1356,23 +1406,76 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport, lpfc_ncmd->seg_cnt = 0; return 1; } - physaddr = data_sg->dma_address; - dma_len = data_sg->length; - sgl->addr_lo = cpu_to_le32(putPaddrLow(physaddr)); - sgl->addr_hi = cpu_to_le32(putPaddrHigh(physaddr)); - sgl->word2 = le32_to_cpu(sgl->word2); - if ((num_bde + 1) == nseg) + + sgl->word2 = 0; + if ((num_bde + 1) == nseg) { bf_set(lpfc_sli4_sge_last, sgl, 1); - else + bf_set(lpfc_sli4_sge_type, sgl, + LPFC_SGE_TYPE_DATA); + } else { bf_set(lpfc_sli4_sge_last, sgl, 0); - bf_set(lpfc_sli4_sge_offset, sgl, dma_offset); - bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_DATA); - sgl->word2 = cpu_to_le32(sgl->word2); - sgl->sge_len = cpu_to_le32(dma_len); - - dma_offset += dma_len; - data_sg = sg_next(data_sg); - sgl++; + + /* expand the segment */ + if (!lsp_just_set && + !((j + 1) % phba->border_sge_num) && + ((nseg - 1) != i)) { + /* set LSP type */ + bf_set(lpfc_sli4_sge_type, sgl, + LPFC_SGE_TYPE_LSP); + + sgl_xtra = lpfc_get_sgl_per_hdwq( + phba, lpfc_ncmd); + + if (unlikely(!sgl_xtra)) { + lpfc_ncmd->seg_cnt = 0; + return 1; + } + sgl->addr_lo = cpu_to_le32(putPaddrLow( + sgl_xtra->dma_phys_sgl)); + sgl->addr_hi = cpu_to_le32(putPaddrHigh( + sgl_xtra->dma_phys_sgl)); + + } else { + bf_set(lpfc_sli4_sge_type, sgl, + LPFC_SGE_TYPE_DATA); + } + } + + if (!(bf_get(lpfc_sli4_sge_type, sgl) & + LPFC_SGE_TYPE_LSP)) { + if ((nseg - 1) == i) + bf_set(lpfc_sli4_sge_last, sgl, 1); + + physaddr = data_sg->dma_address; + dma_len = data_sg->length; + sgl->addr_lo = cpu_to_le32( + putPaddrLow(physaddr)); + sgl->addr_hi = cpu_to_le32( + putPaddrHigh(physaddr)); + + bf_set(lpfc_sli4_sge_offset, sgl, dma_offset); + sgl->word2 = cpu_to_le32(sgl->word2); + sgl->sge_len = cpu_to_le32(dma_len); + + dma_offset += dma_len; + data_sg = sg_next(data_sg); + + sgl++; + + lsp_just_set = false; + } else { + sgl->word2 = cpu_to_le32(sgl->word2); + + sgl->sge_len = cpu_to_le32( + phba->cfg_sg_dma_buf_size); + + sgl = (struct sli4_sge *)sgl_xtra->dma_sgl; + i = i - 1; + + lsp_just_set = true; + } + + j++; } if (phba->cfg_enable_pbde) { /* Use PBDE support for first SGL only, offset == 0 */ @@ -1474,7 +1577,7 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport, goto out_fail; } - if (vport->load_flag & FC_UNLOADING) { + if (unlikely(vport->load_flag & FC_UNLOADING)) { lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR, "6124 Fail IO, Driver unload\n"); atomic_inc(&lport->xmt_fcp_err); @@ -1505,8 +1608,8 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport, ndlp = rport->ndlp; if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) { lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_NVME_IOERR, - "6053 Fail IO, ndlp not ready: rport %p " - "ndlp %p, DID x%06x\n", + "6053 Busy IO, ndlp not ready: rport x%px " + "ndlp x%px, DID x%06x\n", rport, ndlp, pnvme_rport->port_id); atomic_inc(&lport->xmt_fcp_err); ret = -EBUSY; @@ -1728,7 +1831,6 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport, struct lpfc_iocbq *abts_buf; struct lpfc_iocbq *nvmereq_wqe; struct lpfc_nvme_fcpreq_priv *freqpriv; - union lpfc_wqe128 *abts_wqe; unsigned long flags; int ret_val; @@ -1758,7 +1860,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport, /* Announce entry to new IO submit field. */ lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_ABTS, "6002 Abort Request to rport DID x%06x " - "for nvme_fc_req %p\n", + "for nvme_fc_req x%px\n", pnvme_rport->port_id, pnvme_fcreq); @@ -1767,7 +1869,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport, */ spin_lock_irqsave(&phba->hbalock, flags); /* driver queued commands are in process of being flushed */ - if (phba->hba_flag & HBA_NVME_IOQ_FLUSH) { + if (phba->hba_flag & HBA_IOQ_FLUSH) { spin_unlock_irqrestore(&phba->hbalock, flags); lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS, "6139 Driver in reset cleanup - flushing " @@ -1805,8 +1907,8 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport, if (lpfc_nbuf->nvmeCmd != pnvme_fcreq) { lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS, "6143 NVME req mismatch: " - "lpfc_nbuf %p nvmeCmd %p, " - "pnvme_fcreq %p. Skipping Abort xri x%x\n", + "lpfc_nbuf x%px nvmeCmd x%px, " + "pnvme_fcreq x%px. Skipping Abort xri x%x\n", lpfc_nbuf, lpfc_nbuf->nvmeCmd, pnvme_fcreq, nvmereq_wqe->sli4_xritag); goto out_unlock; @@ -1815,7 +1917,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport, /* Don't abort IOs no longer on the pending queue. */ if (!(nvmereq_wqe->iocb_flag & LPFC_IO_ON_TXCMPLQ)) { lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS, - "6142 NVME IO req %p not queued - skipping " + "6142 NVME IO req x%px not queued - skipping " "abort req xri x%x\n", pnvme_fcreq, nvmereq_wqe->sli4_xritag); goto out_unlock; @@ -1830,8 +1932,8 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport, if (nvmereq_wqe->iocb_flag & LPFC_DRIVER_ABORTED) { lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS, "6144 Outstanding NVME I/O Abort Request " - "still pending on nvme_fcreq %p, " - "lpfc_ncmd %p xri x%x\n", + "still pending on nvme_fcreq x%px, " + "lpfc_ncmd %px xri x%x\n", pnvme_fcreq, lpfc_nbuf, nvmereq_wqe->sli4_xritag); goto out_unlock; @@ -1841,7 +1943,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport, if (!abts_buf) { lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS, "6136 No available abort wqes. Skipping " - "Abts req for nvme_fcreq %p xri x%x\n", + "Abts req for nvme_fcreq x%px xri x%x\n", pnvme_fcreq, nvmereq_wqe->sli4_xritag); goto out_unlock; } @@ -1849,37 +1951,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport, /* Ready - mark outstanding as aborted by driver. */ nvmereq_wqe->iocb_flag |= LPFC_DRIVER_ABORTED; - /* Complete prepping the abort wqe and issue to the FW. */ - abts_wqe = &abts_buf->wqe; - - /* WQEs are reused. Clear stale data and set key fields to - * zero like ia, iaab, iaar, xri_tag, and ctxt_tag. - */ - memset(abts_wqe, 0, sizeof(union lpfc_wqe)); - bf_set(abort_cmd_criteria, &abts_wqe->abort_cmd, T_XRI_TAG); - - /* word 7 */ - bf_set(wqe_cmnd, &abts_wqe->abort_cmd.wqe_com, CMD_ABORT_XRI_CX); - bf_set(wqe_class, &abts_wqe->abort_cmd.wqe_com, - nvmereq_wqe->iocb.ulpClass); - - /* word 8 - tell the FW to abort the IO associated with this - * outstanding exchange ID. - */ - abts_wqe->abort_cmd.wqe_com.abort_tag = nvmereq_wqe->sli4_xritag; - - /* word 9 - this is the iotag for the abts_wqe completion. */ - bf_set(wqe_reqtag, &abts_wqe->abort_cmd.wqe_com, - abts_buf->iotag); - - /* word 10 */ - bf_set(wqe_qosd, &abts_wqe->abort_cmd.wqe_com, 1); - bf_set(wqe_lenloc, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_LENLOC_NONE); - - /* word 11 */ - bf_set(wqe_cmd_type, &abts_wqe->abort_cmd.wqe_com, OTHER_COMMAND); - bf_set(wqe_wqec, &abts_wqe->abort_cmd.wqe_com, 1); - bf_set(wqe_cqid, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_CQ_ID_DEFAULT); + lpfc_nvme_prep_abort_wqe(abts_buf, nvmereq_wqe->sli4_xritag, 0); /* ABTS WQE must go to the same WQ as the WQE to be aborted */ abts_buf->iocb_flag |= LPFC_IO_NVME; @@ -1892,7 +1964,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport, if (ret_val) { lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS, "6137 Failed abts issue_wqe with status x%x " - "for nvme_fcreq %p.\n", + "for nvme_fcreq x%px.\n", ret_val, pnvme_fcreq); lpfc_sli_release_iocbq(phba, abts_buf); return; @@ -1913,6 +1985,8 @@ 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, @@ -1982,7 +2056,7 @@ lpfc_get_nvme_buf(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp, sgl->word2 = cpu_to_le32(sgl->word2); /* Fill in word 3 / sgl_len during cmd submission */ - /* Initialize WQE */ + /* Initialize 64 bytes only */ memset(wqe, 0, sizeof(union lpfc_wqe)); if (lpfc_ndlp_check_qdepth(phba, ndlp)) { @@ -2021,18 +2095,18 @@ lpfc_release_nvme_buf(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_ncmd) lpfc_ncmd->flags &= ~LPFC_SBUF_BUMP_QDEPTH; qp = lpfc_ncmd->hdwq; - if (lpfc_ncmd->flags & LPFC_SBUF_XBUSY) { + if (unlikely(lpfc_ncmd->flags & LPFC_SBUF_XBUSY)) { lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS, "6310 XB release deferred for " "ox_id x%x on reqtag x%x\n", lpfc_ncmd->cur_iocbq.sli4_xritag, lpfc_ncmd->cur_iocbq.iotag); - spin_lock_irqsave(&qp->abts_nvme_buf_list_lock, iflag); + spin_lock_irqsave(&qp->abts_io_buf_list_lock, iflag); list_add_tail(&lpfc_ncmd->list, - &qp->lpfc_abts_nvme_buf_list); + &qp->lpfc_abts_io_buf_list); qp->abts_nvme_io_bufs++; - spin_unlock_irqrestore(&qp->abts_nvme_buf_list_lock, iflag); + spin_unlock_irqrestore(&qp->abts_io_buf_list_lock, iflag); } else lpfc_release_io_buf(phba, (struct lpfc_io_buf *)lpfc_ncmd, qp); } @@ -2076,12 +2150,10 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport) */ lpfc_nvme_template.max_sgl_segments = phba->cfg_nvme_seg_cnt + 1; - /* Advertise how many hw queues we support based on fcp_io_sched */ - if (phba->cfg_fcp_io_sched == LPFC_FCP_SCHED_BY_HDWQ) - lpfc_nvme_template.max_hw_queues = phba->cfg_hdw_queue; - else - lpfc_nvme_template.max_hw_queues = - phba->sli4_hba.num_present_cpu; + /* Advertise how many hw queues we support based on cfg_hdw_queue, + * which will not exceed cpu count. + */ + lpfc_nvme_template.max_hw_queues = phba->cfg_hdw_queue; if (!IS_ENABLED(CONFIG_NVME_FC)) return ret; @@ -2095,8 +2167,8 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport) if (!ret) { lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME | LOG_NVME_DISC, "6005 Successfully registered local " - "NVME port num %d, localP %p, private %p, " - "sg_seg %d\n", + "NVME port num %d, localP x%px, private " + "x%px, sg_seg %d\n", localport->port_num, localport, localport->private, lpfc_nvme_template.max_sgl_segments); @@ -2157,14 +2229,14 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, if (unlikely(!ret)) { pending = 0; for (i = 0; i < phba->cfg_hdw_queue; i++) { - pring = phba->sli4_hba.hdwq[i].nvme_wq->pring; + pring = phba->sli4_hba.hdwq[i].io_wq->pring; if (!pring) continue; if (pring->txcmplq_cnt) pending += pring->txcmplq_cnt; } lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_IOERR, - "6176 Lport %p Localport %p wait " + "6176 Lport x%px Localport x%px wait " "timed out. Pending %d. Renewing.\n", lport, vport->localport, pending); continue; @@ -2172,7 +2244,7 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, break; } lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR, - "6177 Lport %p Localport %p Complete Success\n", + "6177 Lport x%px Localport x%px Complete Success\n", lport, vport->localport); } #endif @@ -2203,7 +2275,7 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport) lport = (struct lpfc_nvme_lport *)localport->private; lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME, - "6011 Destroying NVME localport %p\n", + "6011 Destroying NVME localport x%px\n", localport); /* lport's rport list is clear. Unregister @@ -2253,12 +2325,12 @@ lpfc_nvme_update_localport(struct lpfc_vport *vport) lport = (struct lpfc_nvme_lport *)localport->private; if (!lport) { lpfc_printf_vlog(vport, KERN_WARNING, LOG_NVME, - "6171 Update NVME fail. localP %p, No lport\n", + "6171 Update NVME fail. localP x%px, No lport\n", localport); return; } lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME, - "6012 Update NVME lport %p did x%x\n", + "6012 Update NVME lport x%px did x%x\n", localport, vport->fc_myDID); localport->port_id = vport->fc_myDID; @@ -2268,7 +2340,7 @@ lpfc_nvme_update_localport(struct lpfc_vport *vport) localport->port_role = FC_PORT_ROLE_NVME_INITIATOR; lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC, - "6030 bound lport %p to DID x%06x\n", + "6030 bound lport x%px to DID x%06x\n", lport, localport->port_id); #endif } @@ -2317,9 +2389,13 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) spin_lock_irq(&vport->phba->hbalock); oldrport = lpfc_ndlp_get_nrport(ndlp); - spin_unlock_irq(&vport->phba->hbalock); - if (!oldrport) + if (oldrport) { + prev_ndlp = oldrport->ndlp; + spin_unlock_irq(&vport->phba->hbalock); + } else { + spin_unlock_irq(&vport->phba->hbalock); lpfc_nlp_get(ndlp); + } ret = nvme_fc_register_remoteport(localport, &rpinfo, &remote_port); if (!ret) { @@ -2338,25 +2414,34 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) /* New remoteport record does not guarantee valid * host private memory area. */ - prev_ndlp = oldrport->ndlp; if (oldrport == remote_port->private) { /* Same remoteport - ndlp should match. * Just reuse. */ lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NVME_DISC, - "6014 Rebinding lport to " - "remoteport %p wwpn 0x%llx, " - "Data: x%x x%x %p %p x%x x%06x\n", + "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, - prev_ndlp, + oldrport->ndlp, ndlp, ndlp->nlp_type, ndlp->nlp_DID); - return 0; + + /* 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 @@ -2390,10 +2475,10 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) spin_unlock_irq(&vport->phba->hbalock); lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC | LOG_NODE, - "6022 Binding new rport to " - "lport %p Remoteport %p rport %p WWNN 0x%llx, " + "6022 Bind lport x%px to remoteport x%px " + "rport x%px WWNN 0x%llx, " "Rport WWPN 0x%llx DID " - "x%06x Role x%x, ndlp %p prev_ndlp %p\n", + "x%06x Role x%x, ndlp %p prev_ndlp x%px\n", lport, remote_port, rport, rpinfo.node_name, rpinfo.port_name, rpinfo.port_id, rpinfo.port_role, @@ -2423,20 +2508,23 @@ void lpfc_nvme_rescan_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) { #if (IS_ENABLED(CONFIG_NVME_FC)) - struct lpfc_nvme_rport *rport; - struct nvme_fc_remote_port *remoteport; + struct lpfc_nvme_rport *nrport; + struct nvme_fc_remote_port *remoteport = NULL; - rport = ndlp->nrport; + spin_lock_irq(&vport->phba->hbalock); + nrport = lpfc_ndlp_get_nrport(ndlp); + if (nrport) + remoteport = nrport->remoteport; + spin_unlock_irq(&vport->phba->hbalock); lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC, "6170 Rescan NPort DID x%06x type x%x " - "state x%x rport %p\n", - ndlp->nlp_DID, ndlp->nlp_type, ndlp->nlp_state, rport); - if (!rport) - goto input_err; - remoteport = rport->remoteport; - if (!remoteport) - goto input_err; + "state x%x nrport x%px remoteport x%px\n", + ndlp->nlp_DID, ndlp->nlp_type, ndlp->nlp_state, + nrport, remoteport); + + if (!nrport || !remoteport) + goto rescan_exit; /* Only rescan if we are an NVME target in the MAPPED state */ if (remoteport->port_role & FC_PORT_ROLE_NVME_DISCOVERY && @@ -2449,10 +2537,10 @@ lpfc_nvme_rescan_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_DID, remoteport->port_state); } return; -input_err: - lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC, - "6169 State error: lport %p, rport%p FCID x%06x\n", - vport->localport, ndlp->rport, ndlp->nlp_DID); + rescan_exit: + lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC, + "6169 Skip NVME Rport Rescan, NVME remoteport " + "unregistered\n"); #endif } @@ -2499,7 +2587,7 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) goto input_err; lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC, - "6033 Unreg nvme remoteport %p, portname x%llx, " + "6033 Unreg nvme remoteport x%px, portname x%llx, " "port_id x%06x, portstate x%x port type x%x\n", remoteport, remoteport->port_name, remoteport->port_id, remoteport->port_state, @@ -2537,7 +2625,7 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) input_err: #endif lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC, - "6168 State error: lport %p, rport%p FCID x%06x\n", + "6168 State error: lport x%px, rport x%px FCID x%06x\n", vport->localport, ndlp->rport, ndlp->nlp_DID); } @@ -2545,6 +2633,7 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) * lpfc_sli4_nvme_xri_aborted - Fast-path process of NVME xri abort * @phba: pointer to lpfc hba data structure. * @axri: pointer to the fcp xri abort wcqe structure. + * @lpfc_ncmd: The nvme job structure for the request being aborted. * * This routine is invoked by the worker thread to process a SLI4 fast-path * NVME aborted xri. Aborted NVME IO commands are completed to the transport @@ -2552,59 +2641,33 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) **/ void lpfc_sli4_nvme_xri_aborted(struct lpfc_hba *phba, - struct sli4_wcqe_xri_aborted *axri, int idx) + struct sli4_wcqe_xri_aborted *axri, + struct lpfc_io_buf *lpfc_ncmd) { uint16_t xri = bf_get(lpfc_wcqe_xa_xri, axri); - struct lpfc_io_buf *lpfc_ncmd, *next_lpfc_ncmd; struct nvmefc_fcp_req *nvme_cmd = NULL; - struct lpfc_nodelist *ndlp; - struct lpfc_sli4_hdw_queue *qp; - unsigned long iflag = 0; + struct lpfc_nodelist *ndlp = lpfc_ncmd->ndlp; - if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) - return; - qp = &phba->sli4_hba.hdwq[idx]; - spin_lock_irqsave(&phba->hbalock, iflag); - spin_lock(&qp->abts_nvme_buf_list_lock); - list_for_each_entry_safe(lpfc_ncmd, next_lpfc_ncmd, - &qp->lpfc_abts_nvme_buf_list, list) { - if (lpfc_ncmd->cur_iocbq.sli4_xritag == xri) { - list_del_init(&lpfc_ncmd->list); - qp->abts_nvme_io_bufs--; - lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY; - lpfc_ncmd->status = IOSTAT_SUCCESS; - spin_unlock(&qp->abts_nvme_buf_list_lock); - - spin_unlock_irqrestore(&phba->hbalock, iflag); - ndlp = lpfc_ncmd->ndlp; - if (ndlp) - lpfc_sli4_abts_err_handler(phba, ndlp, axri); - - lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS, - "6311 nvme_cmd %p xri x%x tag x%x " - "abort complete and xri released\n", - lpfc_ncmd->nvmeCmd, xri, - lpfc_ncmd->cur_iocbq.iotag); - - /* Aborted NVME commands are required to not complete - * before the abort exchange command fully completes. - * Once completed, it is available via the put list. - */ - if (lpfc_ncmd->nvmeCmd) { - nvme_cmd = lpfc_ncmd->nvmeCmd; - nvme_cmd->done(nvme_cmd); - lpfc_ncmd->nvmeCmd = NULL; - } - lpfc_release_nvme_buf(phba, lpfc_ncmd); - return; - } - } - spin_unlock(&qp->abts_nvme_buf_list_lock); - spin_unlock_irqrestore(&phba->hbalock, iflag); - lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS, - "6312 XRI Aborted xri x%x not found\n", xri); + if (ndlp) + lpfc_sli4_abts_err_handler(phba, ndlp, axri); + lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS, + "6311 nvme_cmd %p xri x%x tag x%x abort complete and " + "xri released\n", + lpfc_ncmd->nvmeCmd, xri, + lpfc_ncmd->cur_iocbq.iotag); + + /* Aborted NVME commands are required to not complete + * before the abort exchange command fully completes. + * Once completed, it is available via the put list. + */ + if (lpfc_ncmd->nvmeCmd) { + nvme_cmd = lpfc_ncmd->nvmeCmd; + nvme_cmd->done(nvme_cmd); + lpfc_ncmd->nvmeCmd = NULL; + } + lpfc_release_nvme_buf(phba, lpfc_ncmd); } /** @@ -2626,13 +2689,13 @@ lpfc_nvme_wait_for_io_drain(struct lpfc_hba *phba) if (phba->sli_rev < LPFC_SLI_REV4 || !phba->sli4_hba.hdwq) return; - /* Cycle through all NVME rings and make sure all outstanding + /* Cycle through all IO rings and make sure all outstanding * WQEs have been removed from the txcmplqs. */ for (i = 0; i < phba->cfg_hdw_queue; i++) { - if (!phba->sli4_hba.hdwq[i].nvme_wq) + if (!phba->sli4_hba.hdwq[i].io_wq) continue; - pring = phba->sli4_hba.hdwq[i].nvme_wq->pring; + pring = phba->sli4_hba.hdwq[i].io_wq->pring; if (!pring) continue; @@ -2653,3 +2716,50 @@ lpfc_nvme_wait_for_io_drain(struct lpfc_hba *phba) } } } + +void +lpfc_nvme_cancel_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn) +{ +#if (IS_ENABLED(CONFIG_NVME_FC)) + struct lpfc_io_buf *lpfc_ncmd; + struct nvmefc_fcp_req *nCmd; + struct lpfc_nvme_fcpreq_priv *freqpriv; + + if (!pwqeIn->context1) { + lpfc_sli_release_iocbq(phba, pwqeIn); + return; + } + /* For abort iocb just return, IO iocb will do a done call */ + if (bf_get(wqe_cmnd, &pwqeIn->wqe.gen_req.wqe_com) == + CMD_ABORT_XRI_CX) { + lpfc_sli_release_iocbq(phba, pwqeIn); + return; + } + lpfc_ncmd = (struct lpfc_io_buf *)pwqeIn->context1; + + spin_lock(&lpfc_ncmd->buf_lock); + if (!lpfc_ncmd->nvmeCmd) { + spin_unlock(&lpfc_ncmd->buf_lock); + lpfc_release_nvme_buf(phba, lpfc_ncmd); + return; + } + + nCmd = lpfc_ncmd->nvmeCmd; + lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR, + "6194 NVME Cancel xri %x\n", + lpfc_ncmd->cur_iocbq.sli4_xritag); + + nCmd->transferred_length = 0; + nCmd->rcv_rsplen = 0; + nCmd->status = NVME_SC_INTERNAL; + freqpriv = nCmd->private; + freqpriv->nvme_buf = NULL; + lpfc_ncmd->nvmeCmd = NULL; + + spin_unlock(&lpfc_ncmd->buf_lock); + nCmd->done(nCmd); + + /* Call release with XB=1 to queue the IO into the abort list. */ + lpfc_release_nvme_buf(phba, lpfc_ncmd); +#endif +} diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index faa596f9e861..9dc9afe1c255 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -378,13 +378,6 @@ lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf) int cpu; unsigned long iflag; - if (ctxp->txrdy) { - dma_pool_free(phba->txrdy_payload_pool, ctxp->txrdy, - ctxp->txrdy_phys); - ctxp->txrdy = NULL; - ctxp->txrdy_phys = 0; - } - if (ctxp->state == LPFC_NVMET_STE_FREE) { lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR, "6411 NVMET free, already free IO x%x: %d %d\n", @@ -430,7 +423,6 @@ lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf) ctxp = (struct lpfc_nvmet_rcv_ctx *)ctx_buf->context; ctxp->wqeq = NULL; - ctxp->txrdy = NULL; ctxp->offset = 0; ctxp->phba = phba; ctxp->size = size; @@ -1026,7 +1018,7 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport, * WQE release CQE */ ctxp->flag |= LPFC_NVMET_DEFER_WQFULL; - wq = ctxp->hdwq->nvme_wq; + wq = ctxp->hdwq->io_wq; pring = wq->pring; spin_lock_irqsave(&pring->ring_lock, iflags); list_add_tail(&nvmewqeq->list, &wq->wqfull_list); @@ -1104,7 +1096,7 @@ lpfc_nvmet_xmt_fcp_abort(struct nvmet_fc_target_port *tgtport, spin_unlock_irqrestore(&ctxp->ctxlock, flags); lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, ctxp->sid, ctxp->oxid); - wq = ctxp->hdwq->nvme_wq; + wq = ctxp->hdwq->io_wq; lpfc_nvmet_wqfull_flush(phba, wq, ctxp); return; } @@ -1437,7 +1429,7 @@ lpfc_nvmet_setup_io_context(struct lpfc_hba *phba) infop = lpfc_get_ctx_list(phba, i, j); lpfc_printf_log(phba, KERN_INFO, LOG_NVME | LOG_INIT, "6408 TOTAL NVMET ctx for CPU %d " - "MRQ %d: cnt %d nextcpu %p\n", + "MRQ %d: cnt %d nextcpu x%px\n", i, j, infop->nvmet_ctx_list_cnt, infop->nvmet_ctx_next_cpu); } @@ -1500,7 +1492,7 @@ lpfc_nvmet_create_targetport(struct lpfc_hba *phba) lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC, "6026 Registered NVME " - "targetport: %p, private %p " + "targetport: x%px, private x%px " "portnm %llx nodenm %llx segs %d qs %d\n", phba->targetport, tgtp, pinfo.port_name, pinfo.node_name, @@ -1555,7 +1547,7 @@ lpfc_nvmet_update_targetport(struct lpfc_hba *phba) return 0; lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME, - "6007 Update NVMET port %p did x%x\n", + "6007 Update NVMET port x%px did x%x\n", phba->targetport, vport->fc_myDID); phba->targetport->port_id = vport->fc_myDID; @@ -1790,12 +1782,8 @@ lpfc_nvmet_rcv_unsol_abort(struct lpfc_vport *vport, lpfc_nvmet_defer_release(phba, ctxp); spin_unlock_irqrestore(&ctxp->ctxlock, iflag); } - if (ctxp->state == LPFC_NVMET_STE_RCV) - lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, ctxp->sid, - ctxp->oxid); - else - lpfc_nvmet_sol_fcp_issue_abort(phba, ctxp, ctxp->sid, - ctxp->oxid); + lpfc_nvmet_sol_fcp_issue_abort(phba, ctxp, ctxp->sid, + ctxp->oxid); lpfc_sli4_seq_abort_rsp(vport, fc_hdr, 1); return 0; @@ -1922,7 +1910,7 @@ lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba) if (phba->targetport) { tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private; for (qidx = 0; qidx < phba->cfg_hdw_queue; qidx++) { - wq = phba->sli4_hba.hdwq[qidx].nvme_wq; + wq = phba->sli4_hba.hdwq[qidx].io_wq; lpfc_nvmet_wqfull_flush(phba, wq, NULL); } tgtp->tport_unreg_cmp = &tport_unreg_cmp; @@ -1930,7 +1918,7 @@ lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba) if (!wait_for_completion_timeout(tgtp->tport_unreg_cmp, msecs_to_jiffies(LPFC_NVMET_WAIT_TMO))) lpfc_printf_log(phba, KERN_ERR, LOG_NVME, - "6179 Unreg targetport %p timeout " + "6179 Unreg targetport x%px timeout " "reached.\n", phba->targetport); lpfc_nvmet_cleanup_io_context(phba); } @@ -1962,12 +1950,10 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, uint32_t *payload; uint32_t size, oxid, sid, rc; - fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt); - oxid = be16_to_cpu(fc_hdr->fh_ox_id); - if (!phba->targetport) { + if (!nvmebuf || !phba->targetport) { lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR, - "6154 LS Drop IO x%x\n", oxid); + "6154 LS Drop IO\n"); oxid = 0; size = 0; sid = 0; @@ -1975,6 +1961,9 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, goto dropit; } + fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt); + oxid = be16_to_cpu(fc_hdr->fh_ox_id); + tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private; payload = (uint32_t *)(nvmebuf->dbuf.virt); size = bf_get(lpfc_rcqe_length, &nvmebuf->cq_event.cqe.rcqe_cmpl); @@ -2330,7 +2319,6 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba, ctxp->state, ctxp->entry_cnt, ctxp->oxid); } ctxp->wqeq = NULL; - ctxp->txrdy = NULL; ctxp->offset = 0; ctxp->phba = phba; ctxp->size = size; @@ -2405,6 +2393,11 @@ lpfc_nvmet_unsol_ls_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, d_buf = piocb->context2; nvmebuf = container_of(d_buf, struct hbq_dmabuf, dbuf); + if (!nvmebuf) { + lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR, + "3015 LS Drop IO\n"); + return; + } if (phba->nvmet_support == 0) { lpfc_in_buf_free(phba, &nvmebuf->dbuf); return; @@ -2433,6 +2426,11 @@ lpfc_nvmet_unsol_fcp_event(struct lpfc_hba *phba, uint64_t isr_timestamp, uint8_t cqflag) { + if (!nvmebuf) { + lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR, + "3167 NVMET FCP Drop IO\n"); + return; + } if (phba->nvmet_support == 0) { lpfc_rq_buf_free(phba, &nvmebuf->hbuf); return; @@ -2599,7 +2597,6 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba, struct scatterlist *sgel; union lpfc_wqe128 *wqe; struct ulp_bde64 *bde; - uint32_t *txrdy; dma_addr_t physaddr; int i, cnt; int do_pbde; @@ -2761,23 +2758,11 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba, &lpfc_treceive_cmd_template.words[3], sizeof(uint32_t) * 9); - /* Words 0 - 2 : The first sg segment */ - txrdy = dma_pool_alloc(phba->txrdy_payload_pool, - GFP_KERNEL, &physaddr); - if (!txrdy) { - lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR, - "6041 Bad txrdy buffer: oxid x%x\n", - ctxp->oxid); - return NULL; - } - ctxp->txrdy = txrdy; - ctxp->txrdy_phys = physaddr; - wqe->fcp_treceive.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64; - wqe->fcp_treceive.bde.tus.f.bdeSize = TXRDY_PAYLOAD_LEN; - wqe->fcp_treceive.bde.addrLow = - cpu_to_le32(putPaddrLow(physaddr)); - wqe->fcp_treceive.bde.addrHigh = - cpu_to_le32(putPaddrHigh(physaddr)); + /* Words 0 - 2 : First SGE is skipped, set invalid BDE type */ + wqe->fcp_treceive.bde.tus.f.bdeFlags = LPFC_SGE_TYPE_SKIP; + wqe->fcp_treceive.bde.tus.f.bdeSize = 0; + wqe->fcp_treceive.bde.addrLow = 0; + wqe->fcp_treceive.bde.addrHigh = 0; /* Word 4 */ wqe->fcp_treceive.relative_offset = ctxp->offset; @@ -2812,17 +2797,13 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba, /* Word 12 */ wqe->fcp_tsend.fcp_data_len = rsp->transfer_length; - /* Setup 1 TXRDY and 1 SKIP SGE */ - txrdy[0] = 0; - txrdy[1] = cpu_to_be32(rsp->transfer_length); - txrdy[2] = 0; - - sgl->addr_hi = putPaddrHigh(physaddr); - sgl->addr_lo = putPaddrLow(physaddr); + /* Setup 2 SKIP SGEs */ + sgl->addr_hi = 0; + sgl->addr_lo = 0; sgl->word2 = 0; - bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_DATA); + bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_SKIP); sgl->word2 = cpu_to_le32(sgl->word2); - sgl->sge_len = cpu_to_le32(TXRDY_PAYLOAD_LEN); + sgl->sge_len = 0; sgl++; sgl->addr_hi = 0; sgl->addr_lo = 0; @@ -3113,7 +3094,7 @@ lpfc_nvmet_xmt_ls_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe, atomic_inc(&tgtp->xmt_ls_abort_cmpl); lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS, - "6083 Abort cmpl: ctx %p WCQE:%08x %08x %08x %08x\n", + "6083 Abort cmpl: ctx x%px WCQE:%08x %08x %08x %08x\n", ctxp, wcqe->word0, wcqe->total_data_placed, result, wcqe->word3); @@ -3243,9 +3224,9 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba, { struct lpfc_nvmet_tgtport *tgtp; struct lpfc_iocbq *abts_wqeq; - union lpfc_wqe128 *abts_wqe; struct lpfc_nodelist *ndlp; unsigned long flags; + u8 opt; int rc; tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private; @@ -3284,8 +3265,8 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba, return 0; } abts_wqeq = ctxp->abort_wqeq; - abts_wqe = &abts_wqeq->wqe; ctxp->state = LPFC_NVMET_STE_ABORT; + opt = (ctxp->flag & LPFC_NVMET_ABTS_RCV) ? INHIBIT_ABORT : 0; spin_unlock_irqrestore(&ctxp->ctxlock, flags); /* Announce entry to new IO submit field. */ @@ -3299,7 +3280,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba, */ spin_lock_irqsave(&phba->hbalock, flags); /* driver queued commands are in process of being flushed */ - if (phba->hba_flag & HBA_NVME_IOQ_FLUSH) { + if (phba->hba_flag & HBA_IOQ_FLUSH) { spin_unlock_irqrestore(&phba->hbalock, flags); atomic_inc(&tgtp->xmt_abort_rsp_error); lpfc_printf_log(phba, KERN_ERR, LOG_NVME, @@ -3331,40 +3312,12 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba, /* Ready - mark outstanding as aborted by driver. */ abts_wqeq->iocb_flag |= LPFC_DRIVER_ABORTED; - /* WQEs are reused. Clear stale data and set key fields to - * zero like ia, iaab, iaar, xri_tag, and ctxt_tag. - */ - memset(abts_wqe, 0, sizeof(union lpfc_wqe)); - - /* word 3 */ - bf_set(abort_cmd_criteria, &abts_wqe->abort_cmd, T_XRI_TAG); - - /* word 7 */ - bf_set(wqe_ct, &abts_wqe->abort_cmd.wqe_com, 0); - bf_set(wqe_cmnd, &abts_wqe->abort_cmd.wqe_com, CMD_ABORT_XRI_CX); - - /* word 8 - tell the FW to abort the IO associated with this - * outstanding exchange ID. - */ - abts_wqe->abort_cmd.wqe_com.abort_tag = ctxp->wqeq->sli4_xritag; - - /* word 9 - this is the iotag for the abts_wqe completion. */ - bf_set(wqe_reqtag, &abts_wqe->abort_cmd.wqe_com, - abts_wqeq->iotag); - - /* word 10 */ - bf_set(wqe_qosd, &abts_wqe->abort_cmd.wqe_com, 1); - bf_set(wqe_lenloc, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_LENLOC_NONE); - - /* word 11 */ - bf_set(wqe_cmd_type, &abts_wqe->abort_cmd.wqe_com, OTHER_COMMAND); - bf_set(wqe_wqec, &abts_wqe->abort_cmd.wqe_com, 1); - bf_set(wqe_cqid, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_CQ_ID_DEFAULT); + lpfc_nvme_prep_abort_wqe(abts_wqeq, ctxp->wqeq->sli4_xritag, opt); /* ABTS WQE must go to the same WQ as the WQE to be aborted */ abts_wqeq->hba_wqidx = ctxp->wqeq->hba_wqidx; abts_wqeq->wqe_cmpl = lpfc_nvmet_sol_fcp_abort_cmp; - abts_wqeq->iocb_cmpl = 0; + abts_wqeq->iocb_cmpl = NULL; abts_wqeq->iocb_flag |= LPFC_IO_NVME; abts_wqeq->context2 = ctxp; abts_wqeq->vport = phba->pport; @@ -3499,7 +3452,7 @@ lpfc_nvmet_unsol_ls_issue_abort(struct lpfc_hba *phba, spin_lock_irqsave(&phba->hbalock, flags); abts_wqeq->wqe_cmpl = lpfc_nvmet_xmt_ls_abort_cmp; - abts_wqeq->iocb_cmpl = 0; + abts_wqeq->iocb_cmpl = NULL; abts_wqeq->iocb_flag |= LPFC_IO_NVME_LS; rc = lpfc_sli4_issue_wqe(phba, ctxp->hdwq, abts_wqeq); spin_unlock_irqrestore(&phba->hbalock, flags); diff --git a/drivers/scsi/lpfc/lpfc_nvmet.h b/drivers/scsi/lpfc/lpfc_nvmet.h index 8ff67deac10a..b80b1639b9a7 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.h +++ b/drivers/scsi/lpfc/lpfc_nvmet.h @@ -112,9 +112,7 @@ struct lpfc_nvmet_rcv_ctx { struct lpfc_hba *phba; struct lpfc_iocbq *wqeq; struct lpfc_iocbq *abort_wqeq; - dma_addr_t txrdy_phys; spinlock_t ctxlock; /* protect flag access */ - uint32_t *txrdy; uint32_t sid; uint32_t offset; uint16_t oxid; diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index f9df800e7067..2c7e0b22db2f 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -53,8 +53,6 @@ #define LPFC_RESET_WAIT 2 #define LPFC_ABORT_WAIT 2 -int _dump_buf_done = 1; - static char *dif_op_str[] = { "PROT_NORMAL", "PROT_READ_INSERT", @@ -89,63 +87,6 @@ lpfc_release_scsi_buf_s3(struct lpfc_hba *phba, struct lpfc_io_buf *psb); static int lpfc_prot_group_type(struct lpfc_hba *phba, struct scsi_cmnd *sc); -static void -lpfc_debug_save_data(struct lpfc_hba *phba, struct scsi_cmnd *cmnd) -{ - void *src, *dst; - struct scatterlist *sgde = scsi_sglist(cmnd); - - if (!_dump_buf_data) { - lpfc_printf_log(phba, KERN_ERR, LOG_BG, - "9050 BLKGRD: ERROR %s _dump_buf_data is NULL\n", - __func__); - return; - } - - - if (!sgde) { - lpfc_printf_log(phba, KERN_ERR, LOG_BG, - "9051 BLKGRD: ERROR: data scatterlist is null\n"); - return; - } - - dst = (void *) _dump_buf_data; - while (sgde) { - src = sg_virt(sgde); - memcpy(dst, src, sgde->length); - dst += sgde->length; - sgde = sg_next(sgde); - } -} - -static void -lpfc_debug_save_dif(struct lpfc_hba *phba, struct scsi_cmnd *cmnd) -{ - void *src, *dst; - struct scatterlist *sgde = scsi_prot_sglist(cmnd); - - if (!_dump_buf_dif) { - lpfc_printf_log(phba, KERN_ERR, LOG_BG, - "9052 BLKGRD: ERROR %s _dump_buf_data is NULL\n", - __func__); - return; - } - - if (!sgde) { - lpfc_printf_log(phba, KERN_ERR, LOG_BG, - "9053 BLKGRD: ERROR: prot scatterlist is null\n"); - return; - } - - dst = _dump_buf_dif; - while (sgde) { - src = sg_virt(sgde); - memcpy(dst, src, sgde->length); - dst += sgde->length; - sgde = sg_next(sgde); - } -} - static inline unsigned lpfc_cmd_blksize(struct scsi_cmnd *sc) { @@ -193,21 +134,21 @@ lpfc_sli4_set_rsp_sgl_last(struct lpfc_hba *phba, /** * lpfc_update_stats - Update statistical data for the command completion - * @phba: Pointer to HBA object. + * @vport: The virtual port on which this call is executing. * @lpfc_cmd: lpfc scsi command object pointer. * * This function is called when there is a command completion and this * function updates the statistical data for the command completion. **/ static void -lpfc_update_stats(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd) +lpfc_update_stats(struct lpfc_vport *vport, struct lpfc_io_buf *lpfc_cmd) { + struct lpfc_hba *phba = vport->phba; struct lpfc_rport_data *rdata; struct lpfc_nodelist *pnode; struct scsi_cmnd *cmd = lpfc_cmd->pCmd; unsigned long flags; - struct Scsi_Host *shost = cmd->device->host; - struct lpfc_vport *vport = (struct lpfc_vport *) shost->hostdata; + struct Scsi_Host *shost = lpfc_shost_from_vport(vport); unsigned long latency; int i; @@ -537,29 +478,32 @@ lpfc_sli4_vport_delete_fcp_xri_aborted(struct lpfc_vport *vport) for (idx = 0; idx < phba->cfg_hdw_queue; idx++) { qp = &phba->sli4_hba.hdwq[idx]; - spin_lock(&qp->abts_scsi_buf_list_lock); + spin_lock(&qp->abts_io_buf_list_lock); list_for_each_entry_safe(psb, next_psb, - &qp->lpfc_abts_scsi_buf_list, list) { + &qp->lpfc_abts_io_buf_list, list) { + if (psb->cur_iocbq.iocb_flag & LPFC_IO_NVME) + continue; + if (psb->rdata && psb->rdata->pnode && psb->rdata->pnode->vport == vport) psb->rdata = NULL; } - spin_unlock(&qp->abts_scsi_buf_list_lock); + spin_unlock(&qp->abts_io_buf_list_lock); } spin_unlock_irqrestore(&phba->hbalock, iflag); } /** - * lpfc_sli4_fcp_xri_aborted - Fast-path process of fcp xri abort + * lpfc_sli4_io_xri_aborted - Fast-path process of fcp xri abort * @phba: pointer to lpfc hba data structure. * @axri: pointer to the fcp xri abort wcqe structure. * * This routine is invoked by the worker thread to process a SLI4 fast-path - * FCP aborted xri. + * FCP or NVME aborted xri. **/ void -lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *phba, - struct sli4_wcqe_xri_aborted *axri, int idx) +lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba, + struct sli4_wcqe_xri_aborted *axri, int idx) { uint16_t xri = bf_get(lpfc_wcqe_xa_xri, axri); uint16_t rxid = bf_get(lpfc_wcqe_xa_remote_xid, axri); @@ -577,16 +521,23 @@ lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *phba, qp = &phba->sli4_hba.hdwq[idx]; spin_lock_irqsave(&phba->hbalock, iflag); - spin_lock(&qp->abts_scsi_buf_list_lock); + spin_lock(&qp->abts_io_buf_list_lock); list_for_each_entry_safe(psb, next_psb, - &qp->lpfc_abts_scsi_buf_list, list) { + &qp->lpfc_abts_io_buf_list, list) { if (psb->cur_iocbq.sli4_xritag == xri) { - list_del(&psb->list); - qp->abts_scsi_io_bufs--; - psb->exch_busy = 0; + list_del_init(&psb->list); + psb->flags &= ~LPFC_SBUF_XBUSY; psb->status = IOSTAT_SUCCESS; - spin_unlock( - &qp->abts_scsi_buf_list_lock); + if (psb->cur_iocbq.iocb_flag & LPFC_IO_NVME) { + qp->abts_nvme_io_bufs--; + spin_unlock(&qp->abts_io_buf_list_lock); + spin_unlock_irqrestore(&phba->hbalock, iflag); + lpfc_sli4_nvme_xri_aborted(phba, axri, psb); + return; + } + qp->abts_scsi_io_bufs--; + spin_unlock(&qp->abts_io_buf_list_lock); + if (psb->rdata && psb->rdata->pnode) ndlp = psb->rdata->pnode; else @@ -605,17 +556,17 @@ lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *phba, return; } } - spin_unlock(&qp->abts_scsi_buf_list_lock); + spin_unlock(&qp->abts_io_buf_list_lock); for (i = 1; i <= phba->sli.last_iotag; i++) { iocbq = phba->sli.iocbq_lookup[i]; - if (!(iocbq->iocb_flag & LPFC_IO_FCP) || - (iocbq->iocb_flag & LPFC_IO_LIBDFC)) + if (!(iocbq->iocb_flag & LPFC_IO_FCP) || + (iocbq->iocb_flag & LPFC_IO_LIBDFC)) continue; if (iocbq->sli4_xritag != xri) continue; psb = container_of(iocbq, struct lpfc_io_buf, cur_iocbq); - psb->exch_busy = 0; + psb->flags &= ~LPFC_SBUF_XBUSY; spin_unlock_irqrestore(&phba->hbalock, iflag); if (!list_empty(&pring->txq)) lpfc_worker_wake_up(phba); @@ -685,8 +636,9 @@ lpfc_get_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp, IOCB_t *iocb; dma_addr_t pdma_phys_fcp_rsp; dma_addr_t pdma_phys_fcp_cmd; - uint32_t sgl_size, cpu, idx; + uint32_t cpu, idx; int tag; + struct fcp_cmd_rsp_buf *tmp = NULL; cpu = raw_smp_processor_id(); if (cmnd && phba->cfg_fcp_io_sched == LPFC_FCP_SCHED_BY_HDWQ) { @@ -704,9 +656,6 @@ lpfc_get_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp, return NULL; } - sgl_size = phba->cfg_sg_dma_buf_size - - (sizeof(struct fcp_cmnd) + sizeof(struct fcp_rsp)); - /* Setup key fields in buffer that may have been changed * if other protocols used this buffer. */ @@ -721,9 +670,12 @@ lpfc_get_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp, #ifdef CONFIG_SCSI_LPFC_DEBUG_FS lpfc_cmd->prot_data_type = 0; #endif - lpfc_cmd->fcp_cmnd = (lpfc_cmd->data + sgl_size); - lpfc_cmd->fcp_rsp = (struct fcp_rsp *)((uint8_t *)lpfc_cmd->fcp_cmnd + - sizeof(struct fcp_cmnd)); + tmp = lpfc_get_cmd_rsp_buf_per_hdwq(phba, lpfc_cmd); + if (!tmp) + return NULL; + + lpfc_cmd->fcp_cmnd = tmp->fcp_cmnd; + lpfc_cmd->fcp_rsp = tmp->fcp_rsp; /* * The first two SGEs are the FCP_CMD and FCP_RSP. @@ -731,7 +683,7 @@ lpfc_get_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp, * first two and leave the rest for queuecommand. */ sgl = (struct sli4_sge *)lpfc_cmd->dma_sgl; - pdma_phys_fcp_cmd = (lpfc_cmd->dma_handle + sgl_size); + pdma_phys_fcp_cmd = tmp->fcp_cmd_rsp_dma_handle; sgl->addr_hi = cpu_to_le32(putPaddrHigh(pdma_phys_fcp_cmd)); sgl->addr_lo = cpu_to_le32(putPaddrLow(pdma_phys_fcp_cmd)); sgl->word2 = le32_to_cpu(sgl->word2); @@ -834,12 +786,12 @@ lpfc_release_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *psb) psb->prot_seg_cnt = 0; qp = psb->hdwq; - if (psb->exch_busy) { - spin_lock_irqsave(&qp->abts_scsi_buf_list_lock, iflag); + if (psb->flags & LPFC_SBUF_XBUSY) { + spin_lock_irqsave(&qp->abts_io_buf_list_lock, iflag); psb->pCmd = NULL; - list_add_tail(&psb->list, &qp->lpfc_abts_scsi_buf_list); + list_add_tail(&psb->list, &qp->lpfc_abts_io_buf_list); qp->abts_scsi_io_bufs++; - spin_unlock_irqrestore(&qp->abts_scsi_buf_list_lock, iflag); + spin_unlock_irqrestore(&qp->abts_io_buf_list_lock, iflag); } else { lpfc_release_io_buf(phba, (struct lpfc_io_buf *)psb, qp); } @@ -918,9 +870,10 @@ lpfc_scsi_prep_dma_buf_s3(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd) "dma_map_sg. Config %d, seg_cnt %d\n", __func__, phba->cfg_sg_seg_cnt, lpfc_cmd->seg_cnt); + WARN_ON_ONCE(lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt); lpfc_cmd->seg_cnt = 0; scsi_dma_unmap(scsi_cmnd); - return 1; + return 2; } /* @@ -1774,7 +1727,7 @@ lpfc_bg_setup_bpl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, if (!sgpe || !sgde) { lpfc_printf_log(phba, KERN_ERR, LOG_FCP, - "9020 Invalid s/g entry: data=0x%p prot=0x%p\n", + "9020 Invalid s/g entry: data=x%px prot=x%px\n", sgpe, sgde); return 0; } @@ -1989,7 +1942,8 @@ out: **/ static int lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, - struct sli4_sge *sgl, int datasegcnt) + struct sli4_sge *sgl, int datasegcnt, + struct lpfc_io_buf *lpfc_cmd) { struct scatterlist *sgde = NULL; /* s/g data entry */ struct sli4_sge_diseed *diseed = NULL; @@ -2003,6 +1957,9 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, uint32_t checking = 1; uint32_t dma_len; uint32_t dma_offset = 0; + struct sli4_hybrid_sgl *sgl_xtra = NULL; + int j; + bool lsp_just_set = false; status = lpfc_sc_to_bg_opcodes(phba, sc, &txop, &rxop); if (status) @@ -2062,23 +2019,64 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, sgl++; /* assumption: caller has already run dma_map_sg on command data */ - scsi_for_each_sg(sc, sgde, datasegcnt, i) { - physaddr = sg_dma_address(sgde); - dma_len = sg_dma_len(sgde); - sgl->addr_lo = cpu_to_le32(putPaddrLow(physaddr)); - sgl->addr_hi = cpu_to_le32(putPaddrHigh(physaddr)); - if ((i + 1) == datasegcnt) - bf_set(lpfc_sli4_sge_last, sgl, 1); - else - bf_set(lpfc_sli4_sge_last, sgl, 0); - bf_set(lpfc_sli4_sge_offset, sgl, dma_offset); - bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_DATA); + sgde = scsi_sglist(sc); + j = 3; + for (i = 0; i < datasegcnt; i++) { + /* clear it */ + sgl->word2 = 0; - sgl->sge_len = cpu_to_le32(dma_len); - dma_offset += dma_len; + /* do we need to expand the segment */ + if (!lsp_just_set && !((j + 1) % phba->border_sge_num) && + ((datasegcnt - 1) != i)) { + /* set LSP type */ + bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_LSP); + + sgl_xtra = lpfc_get_sgl_per_hdwq(phba, lpfc_cmd); + + if (unlikely(!sgl_xtra)) { + lpfc_cmd->seg_cnt = 0; + return 0; + } + sgl->addr_lo = cpu_to_le32(putPaddrLow( + sgl_xtra->dma_phys_sgl)); + sgl->addr_hi = cpu_to_le32(putPaddrHigh( + sgl_xtra->dma_phys_sgl)); + + } else { + bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_DATA); + } + + if (!(bf_get(lpfc_sli4_sge_type, sgl) & LPFC_SGE_TYPE_LSP)) { + if ((datasegcnt - 1) == i) + bf_set(lpfc_sli4_sge_last, sgl, 1); + physaddr = sg_dma_address(sgde); + dma_len = sg_dma_len(sgde); + sgl->addr_lo = cpu_to_le32(putPaddrLow(physaddr)); + sgl->addr_hi = cpu_to_le32(putPaddrHigh(physaddr)); + + bf_set(lpfc_sli4_sge_offset, sgl, dma_offset); + sgl->word2 = cpu_to_le32(sgl->word2); + sgl->sge_len = cpu_to_le32(dma_len); + + dma_offset += dma_len; + sgde = sg_next(sgde); + + sgl++; + num_sge++; + lsp_just_set = false; + + } else { + sgl->word2 = cpu_to_le32(sgl->word2); + sgl->sge_len = cpu_to_le32(phba->cfg_sg_dma_buf_size); + + sgl = (struct sli4_sge *)sgl_xtra->dma_sgl; + i = i - 1; + + lsp_just_set = true; + } + + j++; - sgl++; - num_sge++; } out: @@ -2124,7 +2122,8 @@ out: **/ static int lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, - struct sli4_sge *sgl, int datacnt, int protcnt) + struct sli4_sge *sgl, int datacnt, int protcnt, + struct lpfc_io_buf *lpfc_cmd) { struct scatterlist *sgde = NULL; /* s/g data entry */ struct scatterlist *sgpe = NULL; /* s/g prot entry */ @@ -2146,14 +2145,15 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, #endif uint32_t checking = 1; uint32_t dma_offset = 0; - int num_sge = 0; + int num_sge = 0, j = 2; + struct sli4_hybrid_sgl *sgl_xtra = NULL; sgpe = scsi_prot_sglist(sc); sgde = scsi_sglist(sc); if (!sgpe || !sgde) { lpfc_printf_log(phba, KERN_ERR, LOG_FCP, - "9082 Invalid s/g entry: data=0x%p prot=0x%p\n", + "9082 Invalid s/g entry: data=x%px prot=x%px\n", sgpe, sgde); return 0; } @@ -2179,9 +2179,37 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, split_offset = 0; do { /* Check to see if we ran out of space */ - if (num_sge >= (phba->cfg_total_seg_cnt - 2)) + if ((num_sge >= (phba->cfg_total_seg_cnt - 2)) && + !(phba->cfg_xpsgl)) return num_sge + 3; + /* DISEED and DIF have to be together */ + if (!((j + 1) % phba->border_sge_num) || + !((j + 2) % phba->border_sge_num) || + !((j + 3) % phba->border_sge_num)) { + sgl->word2 = 0; + + /* set LSP type */ + bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_LSP); + + sgl_xtra = lpfc_get_sgl_per_hdwq(phba, lpfc_cmd); + + if (unlikely(!sgl_xtra)) { + goto out; + } else { + sgl->addr_lo = cpu_to_le32(putPaddrLow( + sgl_xtra->dma_phys_sgl)); + sgl->addr_hi = cpu_to_le32(putPaddrHigh( + sgl_xtra->dma_phys_sgl)); + } + + sgl->word2 = cpu_to_le32(sgl->word2); + sgl->sge_len = cpu_to_le32(phba->cfg_sg_dma_buf_size); + + sgl = (struct sli4_sge *)sgl_xtra->dma_sgl; + j = 0; + } + /* setup DISEED with what we have */ diseed = (struct sli4_sge_diseed *) sgl; memset(diseed, 0, sizeof(struct sli4_sge_diseed)); @@ -2228,7 +2256,9 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, /* advance sgl and increment bde count */ num_sge++; + sgl++; + j++; /* setup the first BDE that points to protection buffer */ protphysaddr = sg_dma_address(sgpe) + protgroup_offset; @@ -2243,6 +2273,7 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, sgl->addr_hi = le32_to_cpu(putPaddrHigh(protphysaddr)); sgl->addr_lo = le32_to_cpu(putPaddrLow(protphysaddr)); sgl->word2 = cpu_to_le32(sgl->word2); + sgl->sge_len = 0; protgrp_blks = protgroup_len / 8; protgrp_bytes = protgrp_blks * blksize; @@ -2263,9 +2294,14 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, /* setup SGE's for data blocks associated with DIF data */ pgdone = 0; subtotal = 0; /* total bytes processed for current prot grp */ + + sgl++; + j++; + while (!pgdone) { /* Check to see if we ran out of space */ - if (num_sge >= phba->cfg_total_seg_cnt) + if ((num_sge >= phba->cfg_total_seg_cnt) && + !phba->cfg_xpsgl) return num_sge + 1; if (!sgde) { @@ -2274,60 +2310,101 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, __func__); return 0; } - sgl++; - dataphysaddr = sg_dma_address(sgde) + split_offset; - remainder = sg_dma_len(sgde) - split_offset; + if (!((j + 1) % phba->border_sge_num)) { + sgl->word2 = 0; - if ((subtotal + remainder) <= protgrp_bytes) { - /* we can use this whole buffer */ - dma_len = remainder; - split_offset = 0; + /* set LSP type */ + bf_set(lpfc_sli4_sge_type, sgl, + LPFC_SGE_TYPE_LSP); - if ((subtotal + remainder) == protgrp_bytes) - pgdone = 1; + sgl_xtra = lpfc_get_sgl_per_hdwq(phba, + lpfc_cmd); + + if (unlikely(!sgl_xtra)) { + goto out; + } else { + sgl->addr_lo = cpu_to_le32( + putPaddrLow(sgl_xtra->dma_phys_sgl)); + sgl->addr_hi = cpu_to_le32( + putPaddrHigh(sgl_xtra->dma_phys_sgl)); + } + + sgl->word2 = cpu_to_le32(sgl->word2); + sgl->sge_len = cpu_to_le32( + phba->cfg_sg_dma_buf_size); + + sgl = (struct sli4_sge *)sgl_xtra->dma_sgl; } else { - /* must split this buffer with next prot grp */ - dma_len = protgrp_bytes - subtotal; - split_offset += dma_len; - } + dataphysaddr = sg_dma_address(sgde) + + split_offset; - subtotal += dma_len; + remainder = sg_dma_len(sgde) - split_offset; - sgl->addr_lo = cpu_to_le32(putPaddrLow(dataphysaddr)); - sgl->addr_hi = cpu_to_le32(putPaddrHigh(dataphysaddr)); - bf_set(lpfc_sli4_sge_last, sgl, 0); - bf_set(lpfc_sli4_sge_offset, sgl, dma_offset); - bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_DATA); + if ((subtotal + remainder) <= protgrp_bytes) { + /* we can use this whole buffer */ + dma_len = remainder; + split_offset = 0; - sgl->sge_len = cpu_to_le32(dma_len); - dma_offset += dma_len; + if ((subtotal + remainder) == + protgrp_bytes) + pgdone = 1; + } else { + /* must split this buffer with next + * prot grp + */ + dma_len = protgrp_bytes - subtotal; + split_offset += dma_len; + } - num_sge++; - curr_data++; + subtotal += dma_len; - if (split_offset) - break; + sgl->word2 = 0; + sgl->addr_lo = cpu_to_le32(putPaddrLow( + dataphysaddr)); + sgl->addr_hi = cpu_to_le32(putPaddrHigh( + dataphysaddr)); + bf_set(lpfc_sli4_sge_last, sgl, 0); + bf_set(lpfc_sli4_sge_offset, sgl, dma_offset); + bf_set(lpfc_sli4_sge_type, sgl, + LPFC_SGE_TYPE_DATA); - /* Move to the next s/g segment if possible */ - sgde = sg_next(sgde); + sgl->sge_len = cpu_to_le32(dma_len); + dma_offset += dma_len; + + num_sge++; + curr_data++; + + if (split_offset) { + sgl++; + j++; + break; + } + + /* Move to the next s/g segment if possible */ + sgde = sg_next(sgde); + + sgl++; + } + + j++; } if (protgroup_offset) { /* update the reference tag */ reftag += protgrp_blks; - sgl++; continue; } /* are we done ? */ if (curr_prot == protcnt) { + /* mark the last SGL */ + sgl--; bf_set(lpfc_sli4_sge_last, sgl, 1); alldone = 1; } else if (curr_prot < protcnt) { /* advance to next prot buffer */ sgpe = sg_next(sgpe); - sgl++; /* update the reference tag */ reftag += protgrp_blks; @@ -2430,7 +2507,10 @@ lpfc_bg_scsi_adjust_dl(struct lpfc_hba *phba, * * This is the protection/DIF aware version of * lpfc_scsi_prep_dma_buf(). It may be a good idea to combine the - * two functions eventually, but for now, it's here + * two functions eventually, but for now, it's here. + * RETURNS 0 - SUCCESS, + * 1 - Failed DMA map, retry. + * 2 - Invalid scsi cmd or prot-type. Do not rety. **/ static int lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc_hba *phba, @@ -2444,6 +2524,7 @@ lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc_hba *phba, int datasegcnt, protsegcnt, datadir = scsi_cmnd->sc_data_direction; int prot_group_type = 0; int fcpdl; + int ret = 1; struct lpfc_vport *vport = phba->pport; /* @@ -2467,8 +2548,11 @@ lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc_hba *phba, lpfc_cmd->seg_cnt = datasegcnt; /* First check if data segment count from SCSI Layer is good */ - if (lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt) + if (lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt) { + WARN_ON_ONCE(lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt); + ret = 2; goto err; + } prot_group_type = lpfc_prot_group_type(phba, scsi_cmnd); @@ -2476,14 +2560,18 @@ lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc_hba *phba, case LPFC_PG_TYPE_NO_DIF: /* Here we need to add a PDE5 and PDE6 to the count */ - if ((lpfc_cmd->seg_cnt + 2) > phba->cfg_total_seg_cnt) + if ((lpfc_cmd->seg_cnt + 2) > phba->cfg_total_seg_cnt) { + ret = 2; goto err; + } num_bde = lpfc_bg_setup_bpl(phba, scsi_cmnd, bpl, datasegcnt); /* we should have 2 or more entries in buffer list */ - if (num_bde < 2) + if (num_bde < 2) { + ret = 2; goto err; + } break; case LPFC_PG_TYPE_DIF_BUF: @@ -2507,15 +2595,19 @@ lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc_hba *phba, * protection data segment. */ if ((lpfc_cmd->prot_seg_cnt * 4) > - (phba->cfg_total_seg_cnt - 2)) + (phba->cfg_total_seg_cnt - 2)) { + ret = 2; goto err; + } num_bde = lpfc_bg_setup_bpl_prot(phba, scsi_cmnd, bpl, datasegcnt, protsegcnt); /* we should have 3 or more entries in buffer list */ if ((num_bde < 3) || - (num_bde > phba->cfg_total_seg_cnt)) + (num_bde > phba->cfg_total_seg_cnt)) { + ret = 2; goto err; + } break; case LPFC_PG_TYPE_INVALID: @@ -2526,7 +2618,7 @@ lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc_hba *phba, lpfc_printf_log(phba, KERN_ERR, LOG_FCP, "9022 Unexpected protection group %i\n", prot_group_type); - return 1; + return 2; } } @@ -2576,7 +2668,7 @@ err: lpfc_cmd->seg_cnt = 0; lpfc_cmd->prot_seg_cnt = 0; - return 1; + return ret; } /* @@ -2809,26 +2901,6 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd, uint32_t bgstat = bgf->bgstat; uint64_t failing_sector = 0; - spin_lock(&_dump_buf_lock); - if (!_dump_buf_done) { - lpfc_printf_log(phba, KERN_ERR, LOG_BG, "9070 BLKGRD: Saving" - " Data for %u blocks to debugfs\n", - (cmd->cmnd[7] << 8 | cmd->cmnd[8])); - lpfc_debug_save_data(phba, cmd); - - /* If we have a prot sgl, save the DIF buffer */ - if (lpfc_prot_group_type(phba, cmd) == - LPFC_PG_TYPE_DIF_BUF) { - lpfc_printf_log(phba, KERN_ERR, LOG_BG, "9071 BLKGRD: " - "Saving DIF for %u blocks to debugfs\n", - (cmd->cmnd[7] << 8 | cmd->cmnd[8])); - lpfc_debug_save_dif(phba, cmd); - } - - _dump_buf_done = 1; - } - spin_unlock(&_dump_buf_lock); - if (lpfc_bgs_get_invalid_prof(bgstat)) { cmd->result = DID_ERROR << 16; lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG, @@ -2962,7 +3034,8 @@ out: * field of @lpfc_cmd for device with SLI-4 interface spec. * * Return codes: - * 1 - Error + * 2 - Error - Do not retry + * 1 - Error - Retry * 0 - Success **/ static int @@ -2978,8 +3051,10 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd) uint32_t num_bde = 0; uint32_t dma_len; uint32_t dma_offset = 0; - int nseg; + int nseg, i, j; struct ulp_bde64 *bde; + bool lsp_just_set = false; + struct sli4_hybrid_sgl *sgl_xtra = NULL; /* * There are three possibilities here - use scatter-gather segment, use @@ -3006,15 +3081,17 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd) sgl += 1; first_data_sgl = sgl; lpfc_cmd->seg_cnt = nseg; - if (lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt) { + if (!phba->cfg_xpsgl && + lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt) { lpfc_printf_log(phba, KERN_ERR, LOG_BG, "9074 BLKGRD:" " %s: Too many sg segments from " "dma_map_sg. Config %d, seg_cnt %d\n", __func__, phba->cfg_sg_seg_cnt, lpfc_cmd->seg_cnt); + WARN_ON_ONCE(lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt); lpfc_cmd->seg_cnt = 0; scsi_dma_unmap(scsi_cmnd); - return 1; + return 2; } /* @@ -3026,22 +3103,80 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd) * the IOCB. If it can't then the BDEs get added to a BPL as it * does for SLI-2 mode. */ - scsi_for_each_sg(scsi_cmnd, sgel, nseg, num_bde) { - physaddr = sg_dma_address(sgel); - dma_len = sg_dma_len(sgel); - sgl->addr_lo = cpu_to_le32(putPaddrLow(physaddr)); - sgl->addr_hi = cpu_to_le32(putPaddrHigh(physaddr)); - sgl->word2 = le32_to_cpu(sgl->word2); - if ((num_bde + 1) == nseg) + + /* for tracking segment boundaries */ + sgel = scsi_sglist(scsi_cmnd); + j = 2; + for (i = 0; i < nseg; i++) { + sgl->word2 = 0; + if ((num_bde + 1) == nseg) { bf_set(lpfc_sli4_sge_last, sgl, 1); - else + bf_set(lpfc_sli4_sge_type, sgl, + LPFC_SGE_TYPE_DATA); + } else { bf_set(lpfc_sli4_sge_last, sgl, 0); - bf_set(lpfc_sli4_sge_offset, sgl, dma_offset); - bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_DATA); - sgl->word2 = cpu_to_le32(sgl->word2); - sgl->sge_len = cpu_to_le32(dma_len); - dma_offset += dma_len; - sgl++; + + /* do we need to expand the segment */ + if (!lsp_just_set && + !((j + 1) % phba->border_sge_num) && + ((nseg - 1) != i)) { + /* set LSP type */ + bf_set(lpfc_sli4_sge_type, sgl, + LPFC_SGE_TYPE_LSP); + + sgl_xtra = lpfc_get_sgl_per_hdwq( + phba, lpfc_cmd); + + if (unlikely(!sgl_xtra)) { + lpfc_cmd->seg_cnt = 0; + scsi_dma_unmap(scsi_cmnd); + return 1; + } + sgl->addr_lo = cpu_to_le32(putPaddrLow( + sgl_xtra->dma_phys_sgl)); + sgl->addr_hi = cpu_to_le32(putPaddrHigh( + sgl_xtra->dma_phys_sgl)); + + } else { + bf_set(lpfc_sli4_sge_type, sgl, + LPFC_SGE_TYPE_DATA); + } + } + + if (!(bf_get(lpfc_sli4_sge_type, sgl) & + LPFC_SGE_TYPE_LSP)) { + if ((nseg - 1) == i) + bf_set(lpfc_sli4_sge_last, sgl, 1); + + physaddr = sg_dma_address(sgel); + dma_len = sg_dma_len(sgel); + sgl->addr_lo = cpu_to_le32(putPaddrLow( + physaddr)); + sgl->addr_hi = cpu_to_le32(putPaddrHigh( + physaddr)); + + bf_set(lpfc_sli4_sge_offset, sgl, dma_offset); + sgl->word2 = cpu_to_le32(sgl->word2); + sgl->sge_len = cpu_to_le32(dma_len); + + dma_offset += dma_len; + sgel = sg_next(sgel); + + sgl++; + lsp_just_set = false; + + } else { + sgl->word2 = cpu_to_le32(sgl->word2); + sgl->sge_len = cpu_to_le32( + phba->cfg_sg_dma_buf_size); + + sgl = (struct sli4_sge *)sgl_xtra->dma_sgl; + i = i - 1; + + lsp_just_set = true; + } + + j++; } /* * Setup the first Payload BDE. For FCoE we just key off @@ -3110,6 +3245,10 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd) * This is the protection/DIF aware version of * lpfc_scsi_prep_dma_buf(). It may be a good idea to combine the * two functions eventually, but for now, it's here + * Return codes: + * 2 - Error - Do not retry + * 1 - Error - Retry + * 0 - Success **/ static int lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, @@ -3123,6 +3262,7 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, int datasegcnt, protsegcnt, datadir = scsi_cmnd->sc_data_direction; int prot_group_type = 0; int fcpdl; + int ret = 1; struct lpfc_vport *vport = phba->pport; /* @@ -3152,23 +3292,33 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, lpfc_cmd->seg_cnt = datasegcnt; /* First check if data segment count from SCSI Layer is good */ - if (lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt) + if (lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt && + !phba->cfg_xpsgl) { + WARN_ON_ONCE(lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt); + ret = 2; goto err; + } prot_group_type = lpfc_prot_group_type(phba, scsi_cmnd); switch (prot_group_type) { case LPFC_PG_TYPE_NO_DIF: /* Here we need to add a DISEED to the count */ - if ((lpfc_cmd->seg_cnt + 1) > phba->cfg_total_seg_cnt) + if (((lpfc_cmd->seg_cnt + 1) > + phba->cfg_total_seg_cnt) && + !phba->cfg_xpsgl) { + ret = 2; goto err; + } num_sge = lpfc_bg_setup_sgl(phba, scsi_cmnd, sgl, - datasegcnt); + datasegcnt, lpfc_cmd); /* we should have 2 or more entries in buffer list */ - if (num_sge < 2) + if (num_sge < 2) { + ret = 2; goto err; + } break; case LPFC_PG_TYPE_DIF_BUF: @@ -3190,17 +3340,23 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, * There is a minimun of 3 SGEs used for every * protection data segment. */ - if ((lpfc_cmd->prot_seg_cnt * 3) > - (phba->cfg_total_seg_cnt - 2)) + if (((lpfc_cmd->prot_seg_cnt * 3) > + (phba->cfg_total_seg_cnt - 2)) && + !phba->cfg_xpsgl) { + ret = 2; goto err; + } num_sge = lpfc_bg_setup_sgl_prot(phba, scsi_cmnd, sgl, - datasegcnt, protsegcnt); + datasegcnt, protsegcnt, lpfc_cmd); /* we should have 3 or more entries in buffer list */ - if ((num_sge < 3) || - (num_sge > phba->cfg_total_seg_cnt)) + if (num_sge < 3 || + (num_sge > phba->cfg_total_seg_cnt && + !phba->cfg_xpsgl)) { + ret = 2; goto err; + } break; case LPFC_PG_TYPE_INVALID: @@ -3211,7 +3367,7 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, lpfc_printf_log(phba, KERN_ERR, LOG_FCP, "9083 Unexpected protection group %i\n", prot_group_type); - return 1; + return 2; } } @@ -3273,7 +3429,7 @@ err: lpfc_cmd->seg_cnt = 0; lpfc_cmd->prot_seg_cnt = 0; - return 1; + return ret; } /** @@ -3656,7 +3812,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, /* Sanity check on return of outstanding command */ cmd = lpfc_cmd->pCmd; - if (!cmd) { + if (!cmd || !phba) { lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT, "2621 IO completion: Not an active IO\n"); spin_unlock(&lpfc_cmd->buf_lock); @@ -3668,7 +3824,7 @@ 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 (phba->cpucheck_on & LPFC_CHECK_SCSI_IO) { + 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]++; @@ -3679,7 +3835,10 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, lpfc_cmd->result = (pIocbOut->iocb.un.ulpWord[4] & IOERR_PARAM_MASK); lpfc_cmd->status = pIocbOut->iocb.ulpStatus; /* pick up SLI4 exhange busy status from HBA */ - lpfc_cmd->exch_busy = pIocbOut->iocb_flag & LPFC_EXCHANGE_BUSY; + if (pIocbOut->iocb_flag & LPFC_EXCHANGE_BUSY) + lpfc_cmd->flags |= LPFC_SBUF_XBUSY; + else + lpfc_cmd->flags &= ~LPFC_SBUF_XBUSY; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS if (lpfc_cmd->prot_data_type) { @@ -3713,7 +3872,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, } #endif - if (lpfc_cmd->status) { + if (unlikely(lpfc_cmd->status)) { if (lpfc_cmd->status == IOSTAT_LOCAL_REJECT && (lpfc_cmd->result & IOERR_DRVR_MASK)) lpfc_cmd->status = IOSTAT_DRIVER_REJECT; @@ -3839,14 +3998,14 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, uint32_t *lp = (uint32_t *)cmd->sense_buffer; lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP, - "0710 Iodone <%d/%llu> cmd %p, error " + "0710 Iodone <%d/%llu> cmd x%px, error " "x%x SNS x%x x%x Data: x%x x%x\n", cmd->device->id, cmd->device->lun, cmd, cmd->result, *lp, *(lp + 3), cmd->retries, scsi_get_resid(cmd)); } - lpfc_update_stats(phba, lpfc_cmd); + lpfc_update_stats(vport, lpfc_cmd); if (vport->cfg_max_scsicmpl_time && time_after(jiffies, lpfc_cmd->start_time + msecs_to_jiffies(vport->cfg_max_scsicmpl_time))) { @@ -4454,13 +4613,18 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd) err = lpfc_scsi_prep_dma_buf(phba, lpfc_cmd); } - if (err) + if (unlikely(err)) { + if (err == 2) { + cmnd->result = DID_ERROR << 16; + goto out_fail_command_release_buf; + } goto out_host_busy_free_buf; + } lpfc_scsi_prep_cmnd(vport, lpfc_cmd, ndlp); #ifdef CONFIG_SCSI_LPFC_DEBUG_FS - if (phba->cpucheck_on & LPFC_CHECK_SCSI_IO) { + 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 = @@ -4526,6 +4690,9 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd) out_tgt_busy: return SCSI_MLQUEUE_TARGET_BUSY; + out_fail_command_release_buf: + lpfc_release_scsi_buf(phba, lpfc_cmd); + out_fail_command: cmnd->scsi_done(cmnd); return 0; @@ -4568,7 +4735,7 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd) spin_lock_irqsave(&phba->hbalock, flags); /* driver queued commands are in process of being flushed */ - if (phba->hba_flag & HBA_FCP_IOQ_FLUSH) { + if (phba->hba_flag & HBA_IOQ_FLUSH) { lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP, "3168 SCSI Layer abort requested I/O has been " "flushed by LLD.\n"); @@ -4589,7 +4756,7 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd) iocb = &lpfc_cmd->cur_iocbq; if (phba->sli_rev == LPFC_SLI_REV4) { - pring_s4 = phba->sli4_hba.hdwq[iocb->hba_wqidx].fcp_wq->pring; + pring_s4 = phba->sli4_hba.hdwq[iocb->hba_wqidx].io_wq->pring; if (!pring_s4) { ret = FAILED; goto out_unlock_buf; @@ -4680,20 +4847,21 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd) ret_val = __lpfc_sli_issue_iocb(phba, LPFC_FCP_RING, abtsiocb, 0); } - /* no longer need the lock after this point */ - spin_unlock_irqrestore(&phba->hbalock, flags); if (ret_val == IOCB_ERROR) { /* Indicate the IO is not being aborted by the driver. */ iocb->iocb_flag &= ~LPFC_DRIVER_ABORTED; lpfc_cmd->waitq = NULL; spin_unlock(&lpfc_cmd->buf_lock); + spin_unlock_irqrestore(&phba->hbalock, flags); lpfc_sli_release_iocbq(phba, abtsiocb); ret = FAILED; goto out; } + /* no longer need the lock after this point */ spin_unlock(&lpfc_cmd->buf_lock); + spin_unlock_irqrestore(&phba->hbalock, flags); if (phba->cfg_poll & DISABLE_FCP_RING_INT) lpfc_sli_handle_fast_ring_event(phba, @@ -4956,7 +5124,7 @@ lpfc_chk_tgt_mapped(struct lpfc_vport *vport, struct scsi_cmnd *cmnd) rdata = lpfc_rport_data_from_scsi_device(cmnd->device); if (!rdata) { lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP, - "0797 Tgt Map rport failure: rdata x%p\n", rdata); + "0797 Tgt Map rport failure: rdata x%px\n", rdata); return FAILED; } pnode = rdata->pnode; @@ -5054,7 +5222,7 @@ lpfc_device_reset_handler(struct scsi_cmnd *cmnd) rdata = lpfc_rport_data_from_scsi_device(cmnd->device); if (!rdata || !rdata->pnode) { lpfc_printf_vlog(vport, KERN_ERR, LOG_FCP, - "0798 Device Reset rdata failure: rdata x%p\n", + "0798 Device Reset rdata failure: rdata x%px\n", rdata); return FAILED; } @@ -5066,7 +5234,7 @@ lpfc_device_reset_handler(struct scsi_cmnd *cmnd) status = lpfc_chk_tgt_mapped(vport, cmnd); if (status == FAILED) { lpfc_printf_vlog(vport, KERN_ERR, LOG_FCP, - "0721 Device Reset rport failure: rdata x%p\n", rdata); + "0721 Device Reset rport failure: rdata x%px\n", rdata); return FAILED; } @@ -5125,7 +5293,7 @@ lpfc_target_reset_handler(struct scsi_cmnd *cmnd) rdata = lpfc_rport_data_from_scsi_device(cmnd->device); if (!rdata || !rdata->pnode) { lpfc_printf_vlog(vport, KERN_ERR, LOG_FCP, - "0799 Target Reset rdata failure: rdata x%p\n", + "0799 Target Reset rdata failure: rdata x%px\n", rdata); return FAILED; } @@ -5137,7 +5305,7 @@ lpfc_target_reset_handler(struct scsi_cmnd *cmnd) status = lpfc_chk_tgt_mapped(vport, cmnd); if (status == FAILED) { lpfc_printf_vlog(vport, KERN_ERR, LOG_FCP, - "0722 Target Reset rport failure: rdata x%p\n", rdata); + "0722 Target Reset rport failure: rdata x%px\n", rdata); if (pnode) { spin_lock_irq(shost->host_lock); pnode->nlp_flag &= ~NLP_NPR_ADISC; @@ -5295,18 +5463,20 @@ lpfc_host_reset_handler(struct scsi_cmnd *cmnd) lpfc_offline(phba); rc = lpfc_sli_brdrestart(phba); if (rc) - ret = FAILED; + goto error; + rc = lpfc_online(phba); if (rc) - ret = FAILED; + goto error; + lpfc_unblock_mgmt_io(phba); - if (ret == FAILED) { - lpfc_printf_vlog(vport, KERN_ERR, LOG_FCP, - "3323 Failed host reset, bring it offline\n"); - lpfc_sli4_offline_eratt(phba); - } return ret; +error: + lpfc_printf_vlog(vport, KERN_ERR, LOG_FCP, + "3323 Failed host reset\n"); + lpfc_unblock_mgmt_io(phba); + return FAILED; } /** @@ -5870,7 +6040,7 @@ struct scsi_host_template lpfc_template_no_hr = { .sg_tablesize = LPFC_DEFAULT_SG_SEG_CNT, .cmd_per_lun = LPFC_CMD_PER_LUN, .shost_attrs = lpfc_hba_attrs, - .max_sectors = 0xFFFF, + .max_sectors = 0xFFFFFFFF, .vendor_id = LPFC_NL_VENDOR_ID, .change_queue_depth = scsi_change_queue_depth, .track_queue_depth = 1, diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index f9e6a135d656..64002b0cb02d 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -87,6 +87,10 @@ static void lpfc_sli4_hba_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe); static bool lpfc_sli4_mbox_completions_pending(struct lpfc_hba *phba); static bool lpfc_sli4_process_missed_mbox_completions(struct lpfc_hba *phba); +static struct lpfc_cqe *lpfc_sli4_cq_get(struct lpfc_queue *q); +static void __lpfc_sli4_consume_cqe(struct lpfc_hba *phba, + struct lpfc_queue *cq, + struct lpfc_cqe *cqe); static IOCB_t * lpfc_get_iocb_from_iocbq(struct lpfc_iocbq *iocbq) @@ -467,25 +471,52 @@ __lpfc_sli4_consume_eqe(struct lpfc_hba *phba, struct lpfc_queue *eq, } static void -lpfc_sli4_eq_flush(struct lpfc_hba *phba, struct lpfc_queue *eq) +lpfc_sli4_eqcq_flush(struct lpfc_hba *phba, struct lpfc_queue *eq) { - struct lpfc_eqe *eqe; - uint32_t count = 0; + struct lpfc_eqe *eqe = NULL; + u32 eq_count = 0, cq_count = 0; + struct lpfc_cqe *cqe = NULL; + struct lpfc_queue *cq = NULL, *childq = NULL; + int cqid = 0; /* walk all the EQ entries and drop on the floor */ eqe = lpfc_sli4_eq_get(eq); while (eqe) { + /* Get the reference to the corresponding CQ */ + cqid = bf_get_le32(lpfc_eqe_resource_id, eqe); + cq = NULL; + + list_for_each_entry(childq, &eq->child_list, list) { + if (childq->queue_id == cqid) { + cq = childq; + break; + } + } + /* If CQ is valid, iterate through it and drop all the CQEs */ + if (cq) { + cqe = lpfc_sli4_cq_get(cq); + while (cqe) { + __lpfc_sli4_consume_cqe(phba, cq, cqe); + cq_count++; + cqe = lpfc_sli4_cq_get(cq); + } + /* Clear and re-arm the CQ */ + phba->sli4_hba.sli4_write_cq_db(phba, cq, cq_count, + LPFC_QUEUE_REARM); + cq_count = 0; + } __lpfc_sli4_consume_eqe(phba, eq, eqe); - count++; + eq_count++; eqe = lpfc_sli4_eq_get(eq); } /* Clear and re-arm the EQ */ - phba->sli4_hba.sli4_write_eq_db(phba, eq, count, LPFC_QUEUE_REARM); + phba->sli4_hba.sli4_write_eq_db(phba, eq, eq_count, LPFC_QUEUE_REARM); } static int -lpfc_sli4_process_eq(struct lpfc_hba *phba, struct lpfc_queue *eq) +lpfc_sli4_process_eq(struct lpfc_hba *phba, struct lpfc_queue *eq, + uint8_t rearm) { struct lpfc_eqe *eqe; int count = 0, consumed = 0; @@ -519,8 +550,8 @@ lpfc_sli4_process_eq(struct lpfc_hba *phba, struct lpfc_queue *eq) eq->queue_claimed = 0; rearm_and_exit: - /* Always clear and re-arm the EQ */ - phba->sli4_hba.sli4_write_eq_db(phba, eq, consumed, LPFC_QUEUE_REARM); + /* Always clear the EQ. */ + phba->sli4_hba.sli4_write_eq_db(phba, eq, consumed, rearm); return count; } @@ -1391,9 +1422,12 @@ lpfc_sli_cancel_iocbs(struct lpfc_hba *phba, struct list_head *iocblist, while (!list_empty(iocblist)) { list_remove_head(iocblist, piocb, struct lpfc_iocbq, list); - if (!piocb->iocb_cmpl) - lpfc_sli_release_iocbq(phba, piocb); - else { + if (!piocb->iocb_cmpl) { + if (piocb->iocb_flag & LPFC_IO_NVME) + lpfc_nvme_cancel_iocb(phba, piocb); + else + lpfc_sli_release_iocbq(phba, piocb); + } else { piocb->iocb.ulpStatus = ulpstatus; piocb->iocb.un.ulpWord[4] = ulpWord4; (piocb->iocb_cmpl) (phba, piocb, piocb); @@ -2426,6 +2460,20 @@ lpfc_sli_wake_mbox_wait(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq) return; } +static void +__lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) +{ + unsigned long iflags; + + if (ndlp->nlp_flag & NLP_RELEASE_RPI) { + lpfc_sli4_free_rpi(vport->phba, ndlp->nlp_rpi); + spin_lock_irqsave(&vport->phba->ndlp_lock, iflags); + ndlp->nlp_flag &= ~NLP_RELEASE_RPI; + ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR; + spin_unlock_irqrestore(&vport->phba->ndlp_lock, iflags); + } + ndlp->nlp_flag &= ~NLP_UNREG_INP; +} /** * lpfc_sli_def_mbox_cmpl - Default mailbox completion handler @@ -2497,7 +2545,7 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) vport, KERN_INFO, LOG_MBOX | LOG_DISCOVERY, "1438 UNREG cmpl deferred mbox x%x " - "on NPort x%x Data: x%x x%x %p\n", + "on NPort x%x Data: x%x x%x %px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_defer_did, ndlp); @@ -2507,8 +2555,10 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) ndlp->nlp_defer_did = NLP_EVT_NOTHING_PENDING; lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0); } else { - ndlp->nlp_flag &= ~NLP_UNREG_INP; + __lpfc_sli_rpi_release(vport, ndlp); } + if (vport->load_flag & FC_UNLOADING) + lpfc_nlp_put(ndlp); pmb->ctx_ndlp = NULL; } } @@ -2555,7 +2605,7 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) vport, KERN_INFO, LOG_MBOX | LOG_SLI, "0010 UNREG_LOGIN vpi:%x " "rpi:%x DID:%x defer x%x flg x%x " - "map:%x %p\n", + "map:%x %px\n", vport->vpi, ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_defer_did, ndlp->nlp_flag, @@ -2573,7 +2623,7 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) vport, KERN_INFO, LOG_DISCOVERY, "4111 UNREG cmpl deferred " "clr x%x on " - "NPort x%x Data: x%x %p\n", + "NPort x%x Data: x%x x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_defer_did, ndlp); ndlp->nlp_flag &= ~NLP_UNREG_INP; @@ -2582,7 +2632,7 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) lpfc_issue_els_plogi( vport, ndlp->nlp_DID, 0); } else { - ndlp->nlp_flag &= ~NLP_UNREG_INP; + __lpfc_sli_rpi_release(vport, ndlp); } } } @@ -2655,7 +2705,8 @@ lpfc_sli_handle_mb_event(struct lpfc_hba *phba) lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI, "(%d):0323 Unknown Mailbox command " "x%x (x%x/x%x) Cmpl\n", - pmb->vport ? pmb->vport->vpi : 0, + pmb->vport ? pmb->vport->vpi : + LPFC_VPORT_UNKNOWN, pmbox->mbxCommand, lpfc_sli_config_mbox_subsys_get(phba, pmb), @@ -2676,7 +2727,8 @@ lpfc_sli_handle_mb_event(struct lpfc_hba *phba) "(%d):0305 Mbox cmd cmpl " "error - RETRYing Data: x%x " "(x%x/x%x) x%x x%x x%x\n", - pmb->vport ? pmb->vport->vpi : 0, + pmb->vport ? pmb->vport->vpi : + LPFC_VPORT_UNKNOWN, pmbox->mbxCommand, lpfc_sli_config_mbox_subsys_get(phba, pmb), @@ -2684,7 +2736,8 @@ lpfc_sli_handle_mb_event(struct lpfc_hba *phba) pmb), pmbox->mbxStatus, pmbox->un.varWords[0], - pmb->vport->port_state); + pmb->vport ? pmb->vport->port_state : + LPFC_VPORT_UNKNOWN); pmbox->mbxStatus = 0; pmbox->mbxOwner = OWN_HOST; rc = lpfc_sli_issue_mbox(phba, pmb, MBX_NOWAIT); @@ -2695,7 +2748,7 @@ lpfc_sli_handle_mb_event(struct lpfc_hba *phba) /* Mailbox cmd <cmd> Cmpl <cmpl> */ lpfc_printf_log(phba, KERN_INFO, LOG_MBOX | LOG_SLI, - "(%d):0307 Mailbox cmd x%x (x%x/x%x) Cmpl x%p " + "(%d):0307 Mailbox cmd x%x (x%x/x%x) Cmpl %ps " "Data: x%x x%x x%x x%x x%x x%x x%x x%x x%x " "x%x x%x x%x\n", pmb->vport ? pmb->vport->vpi : 0, @@ -3961,7 +4014,7 @@ lpfc_sli_abort_fcp_rings(struct lpfc_hba *phba) /* Look on all the FCP Rings for the iotag */ if (phba->sli_rev >= LPFC_SLI_REV4) { for (i = 0; i < phba->cfg_hdw_queue; i++) { - pring = phba->sli4_hba.hdwq[i].fcp_wq->pring; + pring = phba->sli4_hba.hdwq[i].io_wq->pring; lpfc_sli_abort_iocb_ring(phba, pring); } } else { @@ -3971,17 +4024,17 @@ lpfc_sli_abort_fcp_rings(struct lpfc_hba *phba) } /** - * lpfc_sli_flush_fcp_rings - flush all iocbs in the fcp ring + * lpfc_sli_flush_io_rings - flush all iocbs in the IO ring * @phba: Pointer to HBA context object. * - * This function flushes all iocbs in the fcp ring and frees all the iocb + * This function flushes all iocbs in the IO ring and frees all the iocb * objects in txq and txcmplq. This function will not issue abort iocbs * for all the iocb commands in txcmplq, they will just be returned with * IOERR_SLI_DOWN. This function is invoked with EEH when device's PCI * slot has been permanently disabled. **/ void -lpfc_sli_flush_fcp_rings(struct lpfc_hba *phba) +lpfc_sli_flush_io_rings(struct lpfc_hba *phba) { LIST_HEAD(txq); LIST_HEAD(txcmplq); @@ -3992,13 +4045,13 @@ lpfc_sli_flush_fcp_rings(struct lpfc_hba *phba) spin_lock_irq(&phba->hbalock); /* Indicate the I/O queues are flushed */ - phba->hba_flag |= HBA_FCP_IOQ_FLUSH; + phba->hba_flag |= HBA_IOQ_FLUSH; spin_unlock_irq(&phba->hbalock); /* Look on all the FCP Rings for the iotag */ if (phba->sli_rev >= LPFC_SLI_REV4) { for (i = 0; i < phba->cfg_hdw_queue; i++) { - pring = phba->sli4_hba.hdwq[i].fcp_wq->pring; + pring = phba->sli4_hba.hdwq[i].io_wq->pring; spin_lock_irq(&pring->ring_lock); /* Retrieve everything on txq */ @@ -4046,56 +4099,6 @@ lpfc_sli_flush_fcp_rings(struct lpfc_hba *phba) } /** - * lpfc_sli_flush_nvme_rings - flush all wqes in the nvme rings - * @phba: Pointer to HBA context object. - * - * This function flushes all wqes in the nvme rings and frees all resources - * in the txcmplq. This function does not issue abort wqes for the IO - * commands in txcmplq, they will just be returned with - * IOERR_SLI_DOWN. This function is invoked with EEH when device's PCI - * slot has been permanently disabled. - **/ -void -lpfc_sli_flush_nvme_rings(struct lpfc_hba *phba) -{ - LIST_HEAD(txcmplq); - struct lpfc_sli_ring *pring; - uint32_t i; - struct lpfc_iocbq *piocb, *next_iocb; - - if ((phba->sli_rev < LPFC_SLI_REV4) || - !(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) - return; - - /* Hint to other driver operations that a flush is in progress. */ - spin_lock_irq(&phba->hbalock); - phba->hba_flag |= HBA_NVME_IOQ_FLUSH; - spin_unlock_irq(&phba->hbalock); - - /* Cycle through all NVME rings and complete each IO with - * a local driver reason code. This is a flush so no - * abort exchange to FW. - */ - for (i = 0; i < phba->cfg_hdw_queue; i++) { - pring = phba->sli4_hba.hdwq[i].nvme_wq->pring; - - spin_lock_irq(&pring->ring_lock); - list_for_each_entry_safe(piocb, next_iocb, - &pring->txcmplq, list) - piocb->iocb_flag &= ~LPFC_IO_ON_TXCMPLQ; - /* Retrieve everything on the txcmplq */ - list_splice_init(&pring->txcmplq, &txcmplq); - pring->txcmplq_cnt = 0; - spin_unlock_irq(&pring->ring_lock); - - /* Flush the txcmpq &&&PAE */ - lpfc_sli_cancel_iocbs(phba, &txcmplq, - IOSTAT_LOCAL_REJECT, - IOERR_SLI_DOWN); - } -} - -/** * lpfc_sli_brdready_s3 - Check for sli3 host ready status * @phba: Pointer to HBA context object. * @mask: Bit mask to be checked. @@ -4495,7 +4498,7 @@ lpfc_sli_brdreset(struct lpfc_hba *phba) * checking during resets the device. The caller is not required to hold * any locks. * - * This function returns 0 always. + * This function returns 0 on success else returns negative error code. **/ int lpfc_sli4_brdreset(struct lpfc_hba *phba) @@ -4652,8 +4655,10 @@ lpfc_sli_brdrestart_s4(struct lpfc_hba *phba) hba_aer_enabled = phba->hba_flag & HBA_AER_ENABLED; rc = lpfc_sli4_brdreset(phba); - if (rc) - return rc; + if (rc) { + phba->link_state = LPFC_HBA_ERROR; + goto hba_down_queue; + } spin_lock_irq(&phba->hbalock); phba->pport->stopped = 0; @@ -4668,6 +4673,7 @@ lpfc_sli_brdrestart_s4(struct lpfc_hba *phba) if (hba_aer_enabled) pci_disable_pcie_error_reporting(phba->pcidev); +hba_down_queue: lpfc_hba_down_post(phba); lpfc_sli4_queue_destroy(phba); @@ -4912,8 +4918,17 @@ static int lpfc_sli4_rb_setup(struct lpfc_hba *phba) { phba->hbq_in_use = 1; - phba->hbqs[LPFC_ELS_HBQ].entry_count = - lpfc_hbq_defs[LPFC_ELS_HBQ]->entry_count; + /** + * Specific case when the MDS diagnostics is enabled and supported. + * The receive buffer count is truncated to manage the incoming + * traffic. + **/ + if (phba->cfg_enable_mds_diags && phba->mds_diags_support) + phba->hbqs[LPFC_ELS_HBQ].entry_count = + lpfc_hbq_defs[LPFC_ELS_HBQ]->entry_count >> 1; + else + phba->hbqs[LPFC_ELS_HBQ].entry_count = + lpfc_hbq_defs[LPFC_ELS_HBQ]->entry_count; phba->hbq_count = 1; lpfc_sli_hbqbuf_init_hbqs(phba, LPFC_ELS_HBQ); /* Initially populate or replenish the HBQs */ @@ -5584,10 +5599,8 @@ lpfc_sli4_arm_cqeq_intr(struct lpfc_hba *phba) for (qidx = 0; qidx < phba->cfg_hdw_queue; qidx++) { qp = &sli4_hba->hdwq[qidx]; /* ARM the corresponding CQ */ - sli4_hba->sli4_write_cq_db(phba, qp->fcp_cq, 0, - LPFC_QUEUE_REARM); - sli4_hba->sli4_write_cq_db(phba, qp->nvme_cq, 0, - LPFC_QUEUE_REARM); + sli4_hba->sli4_write_cq_db(phba, qp->io_cq, 0, + LPFC_QUEUE_REARM); } /* Loop thru all IRQ vectors */ @@ -6199,6 +6212,14 @@ lpfc_set_features(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox, mbox->u.mqe.un.set_feature.feature = LPFC_SET_MDS_DIAGS; mbox->u.mqe.un.set_feature.param_len = 8; break; + case LPFC_SET_DUAL_DUMP: + bf_set(lpfc_mbx_set_feature_dd, + &mbox->u.mqe.un.set_feature, LPFC_ENABLE_DUAL_DUMP); + bf_set(lpfc_mbx_set_feature_ddquery, + &mbox->u.mqe.un.set_feature, 0); + mbox->u.mqe.un.set_feature.feature = LPFC_SET_DUAL_DUMP; + mbox->u.mqe.un.set_feature.param_len = 4; + break; } return; @@ -6216,11 +6237,16 @@ lpfc_ras_stop_fwlog(struct lpfc_hba *phba) { struct lpfc_ras_fwlog *ras_fwlog = &phba->ras_fwlog; - ras_fwlog->ras_active = false; + spin_lock_irq(&phba->hbalock); + ras_fwlog->state = INACTIVE; + spin_unlock_irq(&phba->hbalock); /* Disable FW logging to host memory */ writel(LPFC_CTL_PDEV_CTL_DDL_RAS, phba->sli4_hba.conf_regs_memmap_p + LPFC_CTL_PDEV_CTL_OFFSET); + + /* Wait 10ms for firmware to stop using DMA buffer */ + usleep_range(10 * 1000, 20 * 1000); } /** @@ -6256,7 +6282,9 @@ lpfc_sli4_ras_dma_free(struct lpfc_hba *phba) ras_fwlog->lwpd.virt = NULL; } - ras_fwlog->ras_active = false; + spin_lock_irq(&phba->hbalock); + ras_fwlog->state = INACTIVE; + spin_unlock_irq(&phba->hbalock); } /** @@ -6358,7 +6386,9 @@ lpfc_sli4_ras_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) goto disable_ras; } - ras_fwlog->ras_active = true; + spin_lock_irq(&phba->hbalock); + ras_fwlog->state = ACTIVE; + spin_unlock_irq(&phba->hbalock); mempool_free(pmb, phba->mbox_mem_pool); return; @@ -6390,6 +6420,10 @@ lpfc_sli4_ras_fwlog_init(struct lpfc_hba *phba, uint32_t len = 0, fwlog_buffsize, fwlog_entry_count; int rc = 0; + spin_lock_irq(&phba->hbalock); + ras_fwlog->state = INACTIVE; + spin_unlock_irq(&phba->hbalock); + fwlog_buffsize = (LPFC_RAS_MIN_BUFF_POST_SIZE * phba->cfg_ras_fwlog_buffsize); fwlog_entry_count = (fwlog_buffsize/LPFC_RAS_MAX_ENTRY_SIZE); @@ -6449,6 +6483,9 @@ lpfc_sli4_ras_fwlog_init(struct lpfc_hba *phba, mbx_fwlog->u.request.lwpd.addr_lo = putPaddrLow(ras_fwlog->lwpd.phys); mbx_fwlog->u.request.lwpd.addr_hi = putPaddrHigh(ras_fwlog->lwpd.phys); + spin_lock_irq(&phba->hbalock); + ras_fwlog->state = REG_INPROGRESS; + spin_unlock_irq(&phba->hbalock); mbox->vport = phba->pport; mbox->mbox_cmpl = lpfc_sli4_ras_mbox_cmpl; @@ -7180,7 +7217,7 @@ lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hrq, int lpfc_sli4_hba_setup(struct lpfc_hba *phba) { - int rc, i, cnt, len; + int rc, i, cnt, len, dd; LPFC_MBOXQ_t *mboxq; struct lpfc_mqe *mqe; uint8_t *vpd; @@ -7243,7 +7280,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba) else phba->hba_flag &= ~HBA_FIP_SUPPORT; - phba->hba_flag &= ~HBA_FCP_IOQ_FLUSH; + phba->hba_flag &= ~HBA_IOQ_FLUSH; if (phba->sli_rev != LPFC_SLI_REV4) { lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI, @@ -7431,6 +7468,23 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba) phba->sli3_options |= (LPFC_SLI3_NPIV_ENABLED | LPFC_SLI3_HBQ_ENABLED); spin_unlock_irq(&phba->hbalock); + /* Always try to enable dual dump feature if we can */ + lpfc_set_features(phba, mboxq, LPFC_SET_DUAL_DUMP); + rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL); + dd = bf_get(lpfc_mbx_set_feature_dd, &mboxq->u.mqe.un.set_feature); + if ((rc == MBX_SUCCESS) && (dd == LPFC_ENABLE_DUAL_DUMP)) + lpfc_printf_log(phba, KERN_ERR, LOG_SLI | LOG_INIT, + "6448 Dual Dump is enabled\n"); + else + lpfc_printf_log(phba, KERN_INFO, LOG_SLI | LOG_INIT, + "6447 Dual Dump Mailbox x%x (x%x/x%x) failed, " + "rc:x%x dd:x%x\n", + bf_get(lpfc_mqe_command, &mboxq->u.mqe), + lpfc_sli_config_mbox_subsys_get( + phba, mboxq), + lpfc_sli_config_mbox_opcode_get( + phba, mboxq), + rc, dd); /* * Allocate all resources (xri,rpi,vpi,vfi) now. Subsequent * calls depends on these resources to complete port setup. @@ -7555,9 +7609,11 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba) } phba->sli4_hba.nvmet_xri_cnt = rc; - cnt = phba->cfg_iocb_cnt * 1024; - /* We need 1 iocbq for every SGL, for IO processing */ - cnt += phba->sli4_hba.nvmet_xri_cnt; + /* We allocate an iocbq for every receive context SGL. + * The additional allocation is for abort and ls handling. + */ + cnt = phba->sli4_hba.nvmet_xri_cnt + + phba->sli4_hba.max_cfg_param.max_xri; } else { /* update host common xri-sgl sizes and mappings */ rc = lpfc_sli4_io_sgl_update(phba); @@ -7579,14 +7635,17 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba) rc = -ENODEV; goto out_destroy_queue; } - cnt = phba->cfg_iocb_cnt * 1024; + /* Each lpfc_io_buf job structure has an iocbq element. + * This cnt provides for abort, els, ct and ls requests. + */ + cnt = phba->sli4_hba.max_cfg_param.max_xri; } if (!phba->sli.iocbq_lookup) { /* Initialize and populate the iocb list per host */ lpfc_printf_log(phba, KERN_INFO, LOG_INIT, - "2821 initialize iocb list %d total %d\n", - phba->cfg_iocb_cnt, cnt); + "2821 initialize iocb list with %d entries\n", + cnt); rc = lpfc_init_iocb_list(phba, cnt); if (rc) { lpfc_printf_log(phba, KERN_ERR, LOG_INIT, @@ -7898,7 +7957,7 @@ lpfc_sli4_process_missed_mbox_completions(struct lpfc_hba *phba) if (sli4_hba->hdwq) { for (eqidx = 0; eqidx < phba->cfg_irq_chann; eqidx++) { eq = phba->sli4_hba.hba_eq_hdl[eqidx].eq; - if (eq->queue_id == sli4_hba->mbx_cq->assoc_qid) { + if (eq && eq->queue_id == sli4_hba->mbx_cq->assoc_qid) { fpeq = eq; break; } @@ -7924,7 +7983,7 @@ lpfc_sli4_process_missed_mbox_completions(struct lpfc_hba *phba) if (mbox_pending) /* process and rearm the EQ */ - lpfc_sli4_process_eq(phba, fpeq); + lpfc_sli4_process_eq(phba, fpeq, LPFC_QUEUE_REARM); else /* Always clear and re-arm the EQ */ sli4_hba->sli4_write_eq_db(phba, fpeq, 0, LPFC_QUEUE_REARM); @@ -7972,7 +8031,7 @@ lpfc_mbox_timeout_handler(struct lpfc_hba *phba) /* Mbox cmd <mbxCommand> timeout */ lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI, - "0310 Mailbox command x%x timeout Data: x%x x%x x%p\n", + "0310 Mailbox command x%x timeout Data: x%x x%x x%px\n", mb->mbxCommand, phba->pport->port_state, phba->sli.sli_flag, @@ -8505,7 +8564,7 @@ lpfc_sli4_async_mbox_unblock(struct lpfc_hba *phba) psli->sli_flag &= ~LPFC_SLI_ASYNC_MBX_BLK; spin_unlock_irq(&phba->hbalock); - /* wake up worker thread to post asynchronlous mailbox command */ + /* wake up worker thread to post asynchronous mailbox command */ lpfc_worker_wake_up(phba); } @@ -8773,7 +8832,7 @@ lpfc_sli_issue_mbox_s4(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq, return rc; } - /* Now, interrupt mode asynchrous mailbox command */ + /* Now, interrupt mode asynchronous mailbox command */ rc = lpfc_mbox_cmd_check(phba, mboxq); if (rc) { lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI, @@ -8996,7 +9055,8 @@ lpfc_mbox_api_table_setup(struct lpfc_hba *phba, uint8_t dev_grp) * @pring: Pointer to driver SLI ring object. * @piocb: Pointer to address of newly added command iocb. * - * This function is called with hbalock held to add a command + * This function is called with hbalock held for SLI3 ports or + * the ring lock held for SLI4 ports to add a command * iocb to the txq when SLI layer cannot submit the command iocb * to the ring. **/ @@ -9004,7 +9064,10 @@ void __lpfc_sli_ringtx_put(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, struct lpfc_iocbq *piocb) { - lockdep_assert_held(&phba->hbalock); + if (phba->sli_rev == LPFC_SLI_REV4) + lockdep_assert_held(&pring->ring_lock); + else + lockdep_assert_held(&phba->hbalock); /* Insert the caller's iocb in the txq tail for later processing. */ list_add_tail(&piocb->list, &pring->txq); } @@ -9333,11 +9396,9 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq, memset(wqe, 0, sizeof(union lpfc_wqe128)); /* Some of the fields are in the right position already */ memcpy(wqe, &iocbq->iocb, sizeof(union lpfc_wqe)); - if (iocbq->iocb.ulpCommand != CMD_SEND_FRAME) { - /* The ct field has moved so reset */ - wqe->generic.wqe_com.word7 = 0; - wqe->generic.wqe_com.word10 = 0; - } + /* The ct field has moved so reset */ + wqe->generic.wqe_com.word7 = 0; + wqe->generic.wqe_com.word10 = 0; abort_tag = (uint32_t) iocbq->iotag; xritag = iocbq->sli4_xritag; @@ -9796,7 +9857,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq, * we re-construct this WQE here based on information in * iocbq from scratch. */ - memset(wqe, 0, sizeof(union lpfc_wqe)); + memset(wqe, 0, sizeof(*wqe)); /* OX_ID is invariable to who sent ABTS to CT exchange */ bf_set(xmit_bls_rsp64_oxid, &wqe->xmit_bls_rsp, bf_get(lpfc_abts_oxid, &iocbq->iocb.un.bls_rsp)); @@ -9843,6 +9904,15 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq, break; case CMD_SEND_FRAME: + bf_set(wqe_cmnd, &wqe->generic.wqe_com, CMD_SEND_FRAME); + bf_set(wqe_sof, &wqe->generic.wqe_com, 0x2E); /* SOF byte */ + bf_set(wqe_eof, &wqe->generic.wqe_com, 0x41); /* EOF byte */ + bf_set(wqe_lenloc, &wqe->generic.wqe_com, 1); + bf_set(wqe_xbl, &wqe->generic.wqe_com, 1); + bf_set(wqe_dbde, &wqe->generic.wqe_com, 1); + bf_set(wqe_xc, &wqe->generic.wqe_com, 1); + bf_set(wqe_cmd_type, &wqe->generic.wqe_com, 0xA); + bf_set(wqe_cqid, &wqe->generic.wqe_com, LPFC_WQE_CQ_ID_DEFAULT); bf_set(wqe_xri_tag, &wqe->generic.wqe_com, xritag); bf_set(wqe_reqtag, &wqe->generic.wqe_com, iocbq->iotag); return 0; @@ -9888,7 +9958,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq, * __lpfc_sli_issue_iocb_s4 is used by other functions in the driver to issue * an iocb command to an HBA with SLI-4 interface spec. * - * This function is called with hbalock held. The function will return success + * This function is called with ringlock held. The function will return success * after it successfully submit the iocb to firmware or after adding to the * txq. **/ @@ -9904,7 +9974,7 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number, /* Get the WQ */ if ((piocb->iocb_flag & LPFC_IO_FCP) || (piocb->iocb_flag & LPFC_USE_FCPWQIDX)) { - wq = phba->sli4_hba.hdwq[piocb->hba_wqidx].fcp_wq; + wq = phba->sli4_hba.hdwq[piocb->hba_wqidx].io_wq; } else { wq = phba->sli4_hba.els_wq; } @@ -10051,7 +10121,7 @@ lpfc_sli4_calc_ring(struct lpfc_hba *phba, struct lpfc_iocbq *piocb) lpfc_cmd = (struct lpfc_io_buf *)piocb->context1; piocb->hba_wqidx = lpfc_cmd->hdwq_no; } - return phba->sli4_hba.hdwq[piocb->hba_wqidx].fcp_wq->pring; + return phba->sli4_hba.hdwq[piocb->hba_wqidx].io_wq->pring; } else { if (unlikely(!phba->sli4_hba.els_wq)) return NULL; @@ -10078,10 +10148,13 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number, struct lpfc_iocbq *piocb, uint32_t flag) { struct lpfc_sli_ring *pring; + struct lpfc_queue *eq; unsigned long iflags; int rc; if (phba->sli_rev == LPFC_SLI_REV4) { + eq = phba->sli4_hba.hdwq[piocb->hba_wqidx].hba_eq; + pring = lpfc_sli4_calc_ring(phba, piocb); if (unlikely(pring == NULL)) return IOCB_ERROR; @@ -10089,6 +10162,8 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number, spin_lock_irqsave(&pring->ring_lock, iflags); rc = __lpfc_sli_issue_iocb(phba, ring_number, piocb, flag); spin_unlock_irqrestore(&pring->ring_lock, iflags); + + lpfc_sli4_poll_eq(eq, LPFC_POLL_FASTPATH); } else { /* For now, SLI2/3 will still use hbalock */ spin_lock_irqsave(&phba->hbalock, iflags); @@ -10504,7 +10579,7 @@ lpfc_sli4_queue_init(struct lpfc_hba *phba) INIT_LIST_HEAD(&psli->mboxq_cmpl); /* Initialize list headers for txq and txcmplq as double linked lists */ for (i = 0; i < phba->cfg_hdw_queue; i++) { - pring = phba->sli4_hba.hdwq[i].fcp_wq->pring; + pring = phba->sli4_hba.hdwq[i].io_wq->pring; pring->flag = 0; pring->ringno = LPFC_FCP_RING; pring->txcmplq_cnt = 0; @@ -10523,16 +10598,6 @@ lpfc_sli4_queue_init(struct lpfc_hba *phba) spin_lock_init(&pring->ring_lock); if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - for (i = 0; i < phba->cfg_hdw_queue; i++) { - pring = phba->sli4_hba.hdwq[i].nvme_wq->pring; - pring->flag = 0; - pring->ringno = LPFC_FCP_RING; - pring->txcmplq_cnt = 0; - INIT_LIST_HEAD(&pring->txq); - INIT_LIST_HEAD(&pring->txcmplq); - INIT_LIST_HEAD(&pring->iocb_continueq); - spin_lock_init(&pring->ring_lock); - } pring = phba->sli4_hba.nvmels_wq->pring; pring->flag = 0; pring->ringno = LPFC_ELS_RING; @@ -10713,14 +10778,14 @@ lpfc_sli_host_down(struct lpfc_vport *vport) set_bit(LPFC_DATA_READY, &phba->data_flags); } prev_pring_flag = pring->flag; - spin_lock_irq(&pring->ring_lock); + spin_lock(&pring->ring_lock); list_for_each_entry_safe(iocb, next_iocb, &pring->txq, list) { if (iocb->vport != vport) continue; list_move_tail(&iocb->list, &completions); } - spin_unlock_irq(&pring->ring_lock); + spin_unlock(&pring->ring_lock); list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list) { if (iocb->vport != vport) @@ -10796,9 +10861,9 @@ lpfc_sli_hba_down(struct lpfc_hba *phba) pring = qp->pring; if (!pring) continue; - spin_lock_irq(&pring->ring_lock); + spin_lock(&pring->ring_lock); list_splice_init(&pring->txq, &completions); - spin_unlock_irq(&pring->ring_lock); + spin_unlock(&pring->ring_lock); if (pring == phba->sli4_hba.els_wq->pring) { pring->flag |= LPFC_DEFERRED_RING_EVENT; /* Set the lpfc data pending flag */ @@ -10979,7 +11044,7 @@ lpfc_sli_ring_taggedbuf_get(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, spin_unlock_irq(&phba->hbalock); lpfc_printf_log(phba, KERN_ERR, LOG_INIT, "0402 Cannot find virtual addr for buffer tag on " - "ring %d Data x%lx x%p x%p x%x\n", + "ring %d Data x%lx x%px x%px x%x\n", pring->ringno, (unsigned long) tag, slp->next, slp->prev, pring->postbufq_cnt); @@ -11023,7 +11088,7 @@ lpfc_sli_ringpostbuf_get(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, spin_unlock_irq(&phba->hbalock); lpfc_printf_log(phba, KERN_ERR, LOG_INIT, "0410 Cannot find virtual addr for mapped buf on " - "ring %d Data x%llx x%p x%p x%x\n", + "ring %d Data x%llx x%px x%px x%x\n", pring->ringno, (unsigned long long)phys, slp->next, slp->prev, pring->postbufq_cnt); return NULL; @@ -11078,7 +11143,7 @@ lpfc_sli_abort_els_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, abort_iocb = phba->sli.iocbq_lookup[abort_context]; lpfc_printf_log(phba, KERN_WARNING, LOG_ELS | LOG_SLI, - "0327 Cannot abort els iocb %p " + "0327 Cannot abort els iocb x%px " "with tag %x context %x, abort status %x, " "abort code %x\n", abort_iocb, abort_iotag, abort_context, @@ -11493,7 +11558,7 @@ lpfc_sli_abort_iocb(struct lpfc_vport *vport, struct lpfc_sli_ring *pring, int i; /* all I/Os are in process of being flushed */ - if (phba->hba_flag & HBA_FCP_IOQ_FLUSH) + if (phba->hba_flag & HBA_IOQ_FLUSH) return errcnt; for (i = 1; i <= phba->sli.last_iotag; i++) { @@ -11603,7 +11668,7 @@ lpfc_sli_abort_taskmgmt(struct lpfc_vport *vport, struct lpfc_sli_ring *pring, spin_lock_irqsave(&phba->hbalock, iflags); /* all I/Os are in process of being flushed */ - if (phba->hba_flag & HBA_FCP_IOQ_FLUSH) { + if (phba->hba_flag & HBA_IOQ_FLUSH) { spin_unlock_irqrestore(&phba->hbalock, iflags); return 0; } @@ -11627,7 +11692,7 @@ lpfc_sli_abort_taskmgmt(struct lpfc_vport *vport, struct lpfc_sli_ring *pring, if (phba->sli_rev == LPFC_SLI_REV4) { pring_s4 = - phba->sli4_hba.hdwq[iocbq->hba_wqidx].fcp_wq->pring; + phba->sli4_hba.hdwq[iocbq->hba_wqidx].io_wq->pring; if (!pring_s4) { spin_unlock(&lpfc_cmd->buf_lock); continue; @@ -11768,7 +11833,10 @@ lpfc_sli_wake_iocb_wait(struct lpfc_hba *phba, !(cmdiocbq->iocb_flag & LPFC_IO_LIBDFC)) { lpfc_cmd = container_of(cmdiocbq, struct lpfc_io_buf, cur_iocbq); - lpfc_cmd->exch_busy = rspiocbq->iocb_flag & LPFC_EXCHANGE_BUSY; + if (rspiocbq && (rspiocbq->iocb_flag & LPFC_EXCHANGE_BUSY)) + lpfc_cmd->flags |= LPFC_SBUF_XBUSY; + else + lpfc_cmd->flags &= ~LPFC_SBUF_XBUSY; } pdone_q = cmdiocbq->context_un.wait_queue; @@ -13053,11 +13121,11 @@ lpfc_cq_event_setup(struct lpfc_hba *phba, void *entry, int size) } /** - * lpfc_sli4_sp_handle_async_event - Handle an asynchroous event + * lpfc_sli4_sp_handle_async_event - Handle an asynchronous event * @phba: Pointer to HBA context object. * @cqe: Pointer to mailbox completion queue entry. * - * This routine process a mailbox completion queue entry with asynchrous + * This routine process a mailbox completion queue entry with asynchronous * event. * * Return: true if work posted to worker thread, otherwise false. @@ -13190,13 +13258,19 @@ send_current_mbox: phba->sli.sli_flag &= ~LPFC_SLI_MBOX_ACTIVE; /* Setting active mailbox pointer need to be in sync to flag clear */ phba->sli.mbox_active = NULL; + if (bf_get(lpfc_trailer_consumed, mcqe)) + lpfc_sli4_mq_release(phba->sli4_hba.mbx_wq); spin_unlock_irqrestore(&phba->hbalock, iflags); /* Wake up worker thread to post the next pending mailbox command */ lpfc_worker_wake_up(phba); + return workposted; + out_no_mqe_complete: + spin_lock_irqsave(&phba->hbalock, iflags); if (bf_get(lpfc_trailer_consumed, mcqe)) lpfc_sli4_mq_release(phba->sli4_hba.mbx_wq); - return workposted; + spin_unlock_irqrestore(&phba->hbalock, iflags); + return false; } /** @@ -13205,7 +13279,7 @@ out_no_mqe_complete: * @cqe: Pointer to mailbox completion queue entry. * * This routine process a mailbox completion queue entry, it invokes the - * proper mailbox complete handling or asynchrous event handling routine + * proper mailbox complete handling or asynchronous event handling routine * according to the MCQE's async bit. * * Return: true if work posted to worker thread, otherwise false. @@ -13249,7 +13323,6 @@ lpfc_sli4_sp_handle_els_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq, struct lpfc_sli_ring *pring = cq->pring; int txq_cnt = 0; int txcmplq_cnt = 0; - int fcp_txcmplq_cnt = 0; /* Check for response status */ if (unlikely(bf_get(lpfc_wcqe_c_status, wcqe))) { @@ -13271,9 +13344,8 @@ lpfc_sli4_sp_handle_els_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq, txcmplq_cnt++; lpfc_printf_log(phba, KERN_ERR, LOG_SLI, "0387 NO IOCBQ data: txq_cnt=%d iocb_cnt=%d " - "fcp_txcmplq_cnt=%d, els_txcmplq_cnt=%d\n", + "els_txcmplq_cnt=%d\n", txq_cnt, phba->iocb_cnt, - fcp_txcmplq_cnt, txcmplq_cnt); return false; } @@ -13336,8 +13408,13 @@ lpfc_sli4_sp_handle_abort_xri_wcqe(struct lpfc_hba *phba, unsigned long iflags; switch (cq->subtype) { - case LPFC_FCP: - lpfc_sli4_fcp_xri_aborted(phba, wcqe, cq->hdwq); + case LPFC_IO: + lpfc_sli4_io_xri_aborted(phba, wcqe, cq->hdwq); + if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { + /* Notify aborted XRI for NVME work queue */ + if (phba->nvmet_support) + lpfc_sli4_nvmet_xri_aborted(phba, wcqe); + } workposted = false; break; case LPFC_NVME_LS: /* NVME LS uses ELS resources */ @@ -13355,15 +13432,6 @@ lpfc_sli4_sp_handle_abort_xri_wcqe(struct lpfc_hba *phba, spin_unlock_irqrestore(&phba->hbalock, iflags); workposted = true; break; - case LPFC_NVME: - /* Notify aborted XRI for NVME work queue */ - if (phba->nvmet_support) - lpfc_sli4_nvmet_xri_aborted(phba, wcqe); - else - lpfc_sli4_nvme_xri_aborted(phba, wcqe, cq->hdwq); - - workposted = false; - break; default: lpfc_printf_log(phba, KERN_ERR, LOG_SLI, "0603 Invalid CQ subtype %d: " @@ -13628,6 +13696,7 @@ __lpfc_sli4_process_cq(struct lpfc_hba *phba, struct lpfc_queue *cq, phba->sli4_hba.sli4_write_cq_db(phba, cq, consumed, LPFC_QUEUE_NOARM); consumed = 0; + cq->assoc_qp->q_flag |= HBA_EQ_DELAY_CHK; } if (count == LPFC_NVMET_CQ_NOTIFY) @@ -13691,7 +13760,7 @@ __lpfc_sli4_sp_process_cq(struct lpfc_queue *cq) &delay); break; case LPFC_WCQ: - if (cq->subtype == LPFC_FCP || cq->subtype == LPFC_NVME) + if (cq->subtype == LPFC_IO) workposted |= __lpfc_sli4_process_cq(phba, cq, lpfc_sli4_fp_handle_cqe, &delay); @@ -14008,10 +14077,7 @@ lpfc_sli4_fp_handle_cqe(struct lpfc_hba *phba, struct lpfc_queue *cq, cq->CQ_wq++; /* Process the WQ complete event */ phba->last_completion_time = jiffies; - if ((cq->subtype == LPFC_FCP) || (cq->subtype == LPFC_NVME)) - lpfc_sli4_fp_handle_fcp_wcqe(phba, cq, - (struct lpfc_wcqe_complete *)&wcqe); - if (cq->subtype == LPFC_NVME_LS) + if (cq->subtype == LPFC_IO || cq->subtype == LPFC_NVME_LS) lpfc_sli4_fp_handle_fcp_wcqe(phba, cq, (struct lpfc_wcqe_complete *)&wcqe); break; @@ -14259,7 +14325,7 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id) spin_lock_irqsave(&phba->hbalock, iflag); if (phba->link_state < LPFC_LINK_DOWN) /* Flush, clear interrupt, and rearm the EQ */ - lpfc_sli4_eq_flush(phba, fpeq); + lpfc_sli4_eqcq_flush(phba, fpeq); spin_unlock_irqrestore(&phba->hbalock, iflag); return IRQ_NONE; } @@ -14269,14 +14335,14 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id) fpeq->last_cpu = raw_smp_processor_id(); if (icnt > LPFC_EQD_ISR_TRIGGER && - phba->cfg_irq_chann == 1 && + fpeq->q_flag & HBA_EQ_DELAY_CHK && phba->cfg_auto_imax && fpeq->q_mode != LPFC_MAX_AUTO_EQ_DELAY && phba->sli.sli_flag & LPFC_SLI_USE_EQDR) lpfc_sli4_mod_hba_eq_delay(phba, fpeq, LPFC_MAX_AUTO_EQ_DELAY); /* process and rearm the EQ */ - ecount = lpfc_sli4_process_eq(phba, fpeq); + ecount = lpfc_sli4_process_eq(phba, fpeq, LPFC_QUEUE_REARM); if (unlikely(ecount == 0)) { fpeq->EQ_no_entry++; @@ -14336,6 +14402,147 @@ lpfc_sli4_intr_handler(int irq, void *dev_id) return (hba_handled == true) ? IRQ_HANDLED : IRQ_NONE; } /* lpfc_sli4_intr_handler */ +void lpfc_sli4_poll_hbtimer(struct timer_list *t) +{ + struct lpfc_hba *phba = from_timer(phba, t, cpuhp_poll_timer); + struct lpfc_queue *eq; + int i = 0; + + rcu_read_lock(); + + list_for_each_entry_rcu(eq, &phba->poll_list, _poll_list) + i += lpfc_sli4_poll_eq(eq, LPFC_POLL_SLOWPATH); + if (!list_empty(&phba->poll_list)) + mod_timer(&phba->cpuhp_poll_timer, + jiffies + msecs_to_jiffies(LPFC_POLL_HB)); + + rcu_read_unlock(); +} + +inline int lpfc_sli4_poll_eq(struct lpfc_queue *eq, uint8_t path) +{ + struct lpfc_hba *phba = eq->phba; + int i = 0; + + /* + * Unlocking an irq is one of the entry point to check + * for re-schedule, but we are good for io submission + * path as midlayer does a get_cpu to glue us in. Flush + * out the invalidate queue so we can see the updated + * value for flag. + */ + smp_rmb(); + + if (READ_ONCE(eq->mode) == LPFC_EQ_POLL) + /* We will not likely get the completion for the caller + * during this iteration but i guess that's fine. + * Future io's coming on this eq should be able to + * pick it up. As for the case of single io's, they + * will be handled through a sched from polling timer + * function which is currently triggered every 1msec. + */ + i = lpfc_sli4_process_eq(phba, eq, LPFC_QUEUE_NOARM); + + return i; +} + +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 */ + mod_timer(&phba->cpuhp_poll_timer, + jiffies + msecs_to_jiffies(LPFC_POLL_HB)); + } + + list_add_rcu(&eq->_poll_list, &phba->poll_list); + synchronize_rcu(); +} + +static inline void lpfc_sli4_remove_from_poll_list(struct lpfc_queue *eq) +{ + struct lpfc_hba *phba = eq->phba; + + /* Disable slowpath processing for this eq. Kick start the eq + * by RE-ARMING the eq's ASAP + */ + list_del_rcu(&eq->_poll_list); + synchronize_rcu(); + + if (list_empty(&phba->poll_list)) + del_timer_sync(&phba->cpuhp_poll_timer); +} + +void lpfc_sli4_cleanup_poll_list(struct lpfc_hba *phba) +{ + struct lpfc_queue *eq, *next; + + list_for_each_entry_safe(eq, next, &phba->poll_list, _poll_list) + list_del(&eq->_poll_list); + + INIT_LIST_HEAD(&phba->poll_list); + synchronize_rcu(); +} + +static inline void +__lpfc_sli4_switch_eqmode(struct lpfc_queue *eq, uint8_t mode) +{ + if (mode == eq->mode) + return; + /* + * currently this function is only called during a hotplug + * event and the cpu on which this function is executing + * is going offline. By now the hotplug has instructed + * the scheduler to remove this cpu from cpu active mask. + * So we don't need to work about being put aside by the + * scheduler for a high priority process. Yes, the inte- + * rrupts could come but they are known to retire ASAP. + */ + + /* Disable polling in the fastpath */ + WRITE_ONCE(eq->mode, mode); + /* flush out the store buffer */ + smp_wmb(); + + /* + * Add this eq to the polling list and start polling. For + * a grace period both interrupt handler and poller will + * try to process the eq _but_ that's fine. We have a + * synchronization mechanism in place (queue_claimed) to + * deal with it. This is just a draining phase for int- + * errupt handler (not eq's) as we have guranteed through + * barrier that all the CPUs have seen the new CQ_POLLED + * state. which will effectively disable the REARMING of + * the EQ. The whole idea is eq's die off eventually as + * we are not rearming EQ's anymore. + */ + mode ? lpfc_sli4_add_to_poll_list(eq) : + lpfc_sli4_remove_from_poll_list(eq); +} + +void lpfc_sli4_start_polling(struct lpfc_queue *eq) +{ + __lpfc_sli4_switch_eqmode(eq, LPFC_EQ_POLL); +} + +void lpfc_sli4_stop_polling(struct lpfc_queue *eq) +{ + struct lpfc_hba *phba = eq->phba; + + __lpfc_sli4_switch_eqmode(eq, LPFC_EQ_INTERRUPT); + + /* Kick start for the pending io's in h/w. + * Once we switch back to interrupt processing on a eq + * the io path completion will only arm eq's when it + * receives a completion. But since eq's are in disa- + * rmed state it doesn't receive a completion. This + * creates a deadlock scenaro. + */ + phba->sli4_hba.sli4_write_eq_db(phba, eq, 0, LPFC_QUEUE_REARM); +} + /** * lpfc_sli4_queue_free - free a queue structure and associated memory * @queue: The queue structure to free. @@ -14410,6 +14617,7 @@ lpfc_sli4_queue_alloc(struct lpfc_hba *phba, uint32_t page_size, return NULL; INIT_LIST_HEAD(&queue->list); + INIT_LIST_HEAD(&queue->_poll_list); INIT_LIST_HEAD(&queue->wq_list); INIT_LIST_HEAD(&queue->wqfull_list); INIT_LIST_HEAD(&queue->page_list); @@ -16918,6 +17126,8 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr) struct fc_vft_header *fc_vft_hdr; uint32_t *header = (uint32_t *) fc_hdr; +#define FC_RCTL_MDS_DIAGS 0xF4 + switch (fc_hdr->fh_r_ctl) { case FC_RCTL_DD_UNCAT: /* uncategorized information */ case FC_RCTL_DD_SOL_DATA: /* solicited data */ @@ -17445,7 +17655,6 @@ lpfc_sli4_seq_abort_rsp(struct lpfc_vport *vport, icmd->ulpContext = phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]; ctiocb->context1 = lpfc_nlp_get(ndlp); - ctiocb->iocb_cmpl = NULL; ctiocb->vport = phba->pport; ctiocb->iocb_cmpl = lpfc_sli4_seq_abort_rsp_cmpl; ctiocb->sli4_lxritag = NO_XRI; @@ -17928,6 +18137,17 @@ lpfc_sli4_handle_received_buffer(struct lpfc_hba *phba, fcfi = bf_get(lpfc_rcqe_fcf_id, &dmabuf->cq_event.cqe.rcqe_cmpl); + if (fc_hdr->fh_r_ctl == 0xF4 && fc_hdr->fh_type == 0xFF) { + vport = phba->pport; + lpfc_printf_log(phba, KERN_INFO, LOG_SLI, + "2023 MDS Loopback %d bytes\n", + bf_get(lpfc_rcqe_length, + &dmabuf->cq_event.cqe.rcqe_cmpl)); + /* Handle MDS Loopback frames */ + lpfc_sli4_handle_mds_loopback(vport, dmabuf); + return; + } + /* d_id this frame is directed to */ did = sli4_did_from_fc_hdr(fc_hdr); @@ -18151,8 +18371,9 @@ lpfc_sli4_alloc_rpi(struct lpfc_hba *phba) phba->sli4_hba.max_cfg_param.rpi_used++; phba->sli4_hba.rpi_count++; } - lpfc_printf_log(phba, KERN_INFO, LOG_SLI, - "0001 rpi:%x max:%x lim:%x\n", + lpfc_printf_log(phba, KERN_INFO, + LOG_NODE | LOG_DISCOVERY, + "0001 Allocated rpi:x%x max:x%x lim:x%x\n", (int) rpi, max_rpi, rpi_limit); /* @@ -18208,9 +18429,21 @@ lpfc_sli4_alloc_rpi(struct lpfc_hba *phba) static void __lpfc_sli4_free_rpi(struct lpfc_hba *phba, int rpi) { + /* + * if the rpi value indicates a prior unreg has already + * been done, skip the unreg. + */ + if (rpi == LPFC_RPI_ALLOC_ERROR) + return; + if (test_and_clear_bit(rpi, phba->sli4_hba.rpi_bmask)) { phba->sli4_hba.rpi_count--; phba->sli4_hba.max_cfg_param.rpi_used--; + } else { + lpfc_printf_log(phba, KERN_INFO, + LOG_NODE | LOG_DISCOVERY, + "2016 rpi %x not inuse\n", + rpi); } } @@ -19225,7 +19458,7 @@ lpfc_wr_object(struct lpfc_hba *phba, struct list_head *dmabuf_list, struct lpfc_mbx_wr_object *wr_object; LPFC_MBOXQ_t *mbox; int rc = 0, i = 0; - uint32_t shdr_status, shdr_add_status, shdr_change_status; + uint32_t shdr_status, shdr_add_status, shdr_change_status, shdr_csf; uint32_t mbox_tmo; struct lpfc_dmabuf *dmabuf; uint32_t written = 0; @@ -19282,6 +19515,16 @@ lpfc_wr_object(struct lpfc_hba *phba, struct list_head *dmabuf_list, if (check_change_status) { shdr_change_status = bf_get(lpfc_wr_object_change_status, &wr_object->u.response); + + if (shdr_change_status == LPFC_CHANGE_STATUS_FW_RESET || + shdr_change_status == LPFC_CHANGE_STATUS_PORT_MIGRATION) { + shdr_csf = bf_get(lpfc_wr_object_csf, + &wr_object->u.response); + if (shdr_csf) + shdr_change_status = + LPFC_CHANGE_STATUS_PCI_RESET; + } + switch (shdr_change_status) { case (LPFC_CHANGE_STATUS_PHYS_DEV_RESET): lpfc_printf_log(phba, KERN_INFO, LOG_INIT, @@ -19461,7 +19704,7 @@ lpfc_drain_txq(struct lpfc_hba *phba) if (phba->link_flag & LS_MDS_LOOPBACK) { /* MDS WQE are posted only to first WQ*/ - wq = phba->sli4_hba.hdwq[0].fcp_wq; + wq = phba->sli4_hba.hdwq[0].io_wq; if (unlikely(!wq)) return 0; pring = wq->pring; @@ -19706,16 +19949,18 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp, lpfc_sli_ringtxcmpl_put(phba, pring, pwqe); spin_unlock_irqrestore(&pring->ring_lock, iflags); + + lpfc_sli4_poll_eq(qp->hba_eq, LPFC_POLL_FASTPATH); return 0; } /* NVME_FCREQ and NVME_ABTS requests */ if (pwqe->iocb_flag & LPFC_IO_NVME) { /* Get the IO distribution (hba_wqidx) for WQ assignment. */ - wq = qp->nvme_wq; + wq = qp->io_wq; pring = wq->pring; - bf_set(wqe_cqid, &wqe->generic.wqe_com, qp->nvme_cq_map); + bf_set(wqe_cqid, &wqe->generic.wqe_com, qp->io_cq_map); lpfc_qp_spin_lock_irqsave(&pring->ring_lock, iflags, qp, wq_access); @@ -19726,13 +19971,15 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp, } lpfc_sli_ringtxcmpl_put(phba, pring, pwqe); spin_unlock_irqrestore(&pring->ring_lock, iflags); + + lpfc_sli4_poll_eq(qp->hba_eq, LPFC_POLL_FASTPATH); return 0; } /* NVMET requests */ if (pwqe->iocb_flag & LPFC_IO_NVMET) { /* Get the IO distribution (hba_wqidx) for WQ assignment. */ - wq = qp->nvme_wq; + wq = qp->io_wq; pring = wq->pring; ctxp = pwqe->context2; @@ -19743,7 +19990,7 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp, } bf_set(wqe_xri_tag, &pwqe->wqe.xmit_bls_rsp.wqe_com, pwqe->sli4_xritag); - bf_set(wqe_cqid, &wqe->generic.wqe_com, qp->nvme_cq_map); + bf_set(wqe_cqid, &wqe->generic.wqe_com, qp->io_cq_map); lpfc_qp_spin_lock_irqsave(&pring->ring_lock, iflags, qp, wq_access); @@ -19754,6 +20001,8 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp, } lpfc_sli_ringtxcmpl_put(phba, pring, pwqe); spin_unlock_irqrestore(&pring->ring_lock, iflags); + + lpfc_sli4_poll_eq(qp->hba_eq, LPFC_POLL_FASTPATH); return 0; } return WQE_ERROR; @@ -19790,9 +20039,7 @@ void lpfc_snapshot_mxp(struct lpfc_hba *phba, u32 hwqid) if (multixri_pool->stat_snapshot_taken == LPFC_MXP_SNAPSHOT_TAKEN) { pvt_pool = &qp->p_multixri_pool->pvt_pool; pbl_pool = &qp->p_multixri_pool->pbl_pool; - txcmplq_cnt = qp->fcp_wq->pring->txcmplq_cnt; - if (qp->nvme_wq) - txcmplq_cnt += qp->nvme_wq->pring->txcmplq_cnt; + txcmplq_cnt = qp->io_wq->pring->txcmplq_cnt; multixri_pool->stat_pbl_count = pbl_pool->count; multixri_pool->stat_pvt_count = pvt_pool->count; @@ -19862,12 +20109,9 @@ void lpfc_adjust_high_watermark(struct lpfc_hba *phba, u32 hwqid) watermark_max = xri_limit; watermark_min = xri_limit / 2; - txcmplq_cnt = qp->fcp_wq->pring->txcmplq_cnt; + txcmplq_cnt = qp->io_wq->pring->txcmplq_cnt; abts_io_bufs = qp->abts_scsi_io_bufs; - if (qp->nvme_wq) { - txcmplq_cnt += qp->nvme_wq->pring->txcmplq_cnt; - abts_io_bufs += qp->abts_nvme_io_bufs; - } + abts_io_bufs += qp->abts_nvme_io_bufs; new_watermark = txcmplq_cnt + abts_io_bufs; new_watermark = min(watermark_max, new_watermark); @@ -20121,6 +20365,13 @@ void lpfc_release_io_buf(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_ncmd, lpfc_ncmd->cur_iocbq.wqe_cmpl = NULL; lpfc_ncmd->cur_iocbq.iocb_cmpl = NULL; + if (phba->cfg_xpsgl && !phba->nvmet_support && + !list_empty(&lpfc_ncmd->dma_sgl_xtra_list)) + lpfc_put_sgl_per_hdwq(phba, lpfc_ncmd); + + if (!list_empty(&lpfc_ncmd->dma_cmd_rsp_list)) + lpfc_put_cmd_rsp_buf_per_hdwq(phba, lpfc_ncmd); + if (phba->cfg_xri_rebalancing) { if (lpfc_ncmd->expedite) { /* Return to expedite pool */ @@ -20142,12 +20393,9 @@ void lpfc_release_io_buf(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_ncmd, pbl_pool = &qp->p_multixri_pool->pbl_pool; pvt_pool = &qp->p_multixri_pool->pvt_pool; - txcmplq_cnt = qp->fcp_wq->pring->txcmplq_cnt; + txcmplq_cnt = qp->io_wq->pring->txcmplq_cnt; abts_io_bufs = qp->abts_scsi_io_bufs; - if (qp->nvme_wq) { - txcmplq_cnt += qp->nvme_wq->pring->txcmplq_cnt; - abts_io_bufs += qp->abts_nvme_io_bufs; - } + abts_io_bufs += qp->abts_nvme_io_bufs; xri_owned = pvt_pool->count + txcmplq_cnt + abts_io_bufs; xri_limit = qp->p_multixri_pool->xri_limit; @@ -20402,3 +20650,294 @@ struct lpfc_io_buf *lpfc_get_io_buf(struct lpfc_hba *phba, return lpfc_cmd; } + +/** + * lpfc_get_sgl_per_hdwq - Get one SGL chunk from hdwq's pool + * @phba: The HBA for which this call is being executed. + * @lpfc_buf: IO buf structure to append the SGL chunk + * + * This routine gets one SGL chunk buffer from hdwq's SGL chunk pool, + * and will allocate an SGL chunk if the pool is empty. + * + * Return codes: + * NULL - Error + * Pointer to sli4_hybrid_sgl - Success + **/ +struct sli4_hybrid_sgl * +lpfc_get_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf) +{ + struct sli4_hybrid_sgl *list_entry = NULL; + struct sli4_hybrid_sgl *tmp = NULL; + struct sli4_hybrid_sgl *allocated_sgl = NULL; + struct lpfc_sli4_hdw_queue *hdwq = lpfc_buf->hdwq; + struct list_head *buf_list = &hdwq->sgl_list; + unsigned long iflags; + + spin_lock_irqsave(&hdwq->hdwq_lock, iflags); + + if (likely(!list_empty(buf_list))) { + /* break off 1 chunk from the sgl_list */ + list_for_each_entry_safe(list_entry, tmp, + buf_list, list_node) { + list_move_tail(&list_entry->list_node, + &lpfc_buf->dma_sgl_xtra_list); + break; + } + } else { + /* allocate more */ + spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags); + tmp = kmalloc_node(sizeof(*tmp), GFP_ATOMIC, + cpu_to_node(hdwq->io_wq->chann)); + if (!tmp) { + lpfc_printf_log(phba, KERN_INFO, LOG_SLI, + "8353 error kmalloc memory for HDWQ " + "%d %s\n", + lpfc_buf->hdwq_no, __func__); + return NULL; + } + + tmp->dma_sgl = dma_pool_alloc(phba->lpfc_sg_dma_buf_pool, + GFP_ATOMIC, &tmp->dma_phys_sgl); + if (!tmp->dma_sgl) { + lpfc_printf_log(phba, KERN_INFO, LOG_SLI, + "8354 error pool_alloc memory for HDWQ " + "%d %s\n", + lpfc_buf->hdwq_no, __func__); + kfree(tmp); + return NULL; + } + + spin_lock_irqsave(&hdwq->hdwq_lock, iflags); + list_add_tail(&tmp->list_node, &lpfc_buf->dma_sgl_xtra_list); + } + + allocated_sgl = list_last_entry(&lpfc_buf->dma_sgl_xtra_list, + struct sli4_hybrid_sgl, + list_node); + + spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags); + + return allocated_sgl; +} + +/** + * lpfc_put_sgl_per_hdwq - Put one SGL chunk into hdwq pool + * @phba: The HBA for which this call is being executed. + * @lpfc_buf: IO buf structure with the SGL chunk + * + * This routine puts one SGL chunk buffer into hdwq's SGL chunk pool. + * + * Return codes: + * 0 - Success + * -EINVAL - Error + **/ +int +lpfc_put_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf) +{ + int rc = 0; + struct sli4_hybrid_sgl *list_entry = NULL; + struct sli4_hybrid_sgl *tmp = NULL; + struct lpfc_sli4_hdw_queue *hdwq = lpfc_buf->hdwq; + struct list_head *buf_list = &hdwq->sgl_list; + unsigned long iflags; + + spin_lock_irqsave(&hdwq->hdwq_lock, iflags); + + if (likely(!list_empty(&lpfc_buf->dma_sgl_xtra_list))) { + list_for_each_entry_safe(list_entry, tmp, + &lpfc_buf->dma_sgl_xtra_list, + list_node) { + list_move_tail(&list_entry->list_node, + buf_list); + } + } else { + rc = -EINVAL; + } + + spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags); + return rc; +} + +/** + * lpfc_free_sgl_per_hdwq - Free all SGL chunks of hdwq pool + * @phba: phba object + * @hdwq: hdwq to cleanup sgl buff resources on + * + * This routine frees all SGL chunks of hdwq SGL chunk pool. + * + * Return codes: + * None + **/ +void +lpfc_free_sgl_per_hdwq(struct lpfc_hba *phba, + struct lpfc_sli4_hdw_queue *hdwq) +{ + struct list_head *buf_list = &hdwq->sgl_list; + struct sli4_hybrid_sgl *list_entry = NULL; + struct sli4_hybrid_sgl *tmp = NULL; + unsigned long iflags; + + spin_lock_irqsave(&hdwq->hdwq_lock, iflags); + + /* Free sgl pool */ + list_for_each_entry_safe(list_entry, tmp, + buf_list, list_node) { + dma_pool_free(phba->lpfc_sg_dma_buf_pool, + list_entry->dma_sgl, + list_entry->dma_phys_sgl); + list_del(&list_entry->list_node); + kfree(list_entry); + } + + spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags); +} + +/** + * lpfc_get_cmd_rsp_buf_per_hdwq - Get one CMD/RSP buffer from hdwq + * @phba: The HBA for which this call is being executed. + * @lpfc_buf: IO buf structure to attach the CMD/RSP buffer + * + * This routine gets one CMD/RSP buffer from hdwq's CMD/RSP pool, + * and will allocate an CMD/RSP buffer if the pool is empty. + * + * Return codes: + * NULL - Error + * Pointer to fcp_cmd_rsp_buf - Success + **/ +struct fcp_cmd_rsp_buf * +lpfc_get_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba, + struct lpfc_io_buf *lpfc_buf) +{ + struct fcp_cmd_rsp_buf *list_entry = NULL; + struct fcp_cmd_rsp_buf *tmp = NULL; + struct fcp_cmd_rsp_buf *allocated_buf = NULL; + struct lpfc_sli4_hdw_queue *hdwq = lpfc_buf->hdwq; + struct list_head *buf_list = &hdwq->cmd_rsp_buf_list; + unsigned long iflags; + + spin_lock_irqsave(&hdwq->hdwq_lock, iflags); + + if (likely(!list_empty(buf_list))) { + /* break off 1 chunk from the list */ + list_for_each_entry_safe(list_entry, tmp, + buf_list, + list_node) { + list_move_tail(&list_entry->list_node, + &lpfc_buf->dma_cmd_rsp_list); + break; + } + } else { + /* allocate more */ + spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags); + tmp = kmalloc_node(sizeof(*tmp), GFP_ATOMIC, + cpu_to_node(hdwq->io_wq->chann)); + if (!tmp) { + lpfc_printf_log(phba, KERN_INFO, LOG_SLI, + "8355 error kmalloc memory for HDWQ " + "%d %s\n", + lpfc_buf->hdwq_no, __func__); + return NULL; + } + + tmp->fcp_cmnd = dma_pool_alloc(phba->lpfc_cmd_rsp_buf_pool, + GFP_ATOMIC, + &tmp->fcp_cmd_rsp_dma_handle); + + if (!tmp->fcp_cmnd) { + lpfc_printf_log(phba, KERN_INFO, LOG_SLI, + "8356 error pool_alloc memory for HDWQ " + "%d %s\n", + lpfc_buf->hdwq_no, __func__); + kfree(tmp); + return NULL; + } + + tmp->fcp_rsp = (struct fcp_rsp *)((uint8_t *)tmp->fcp_cmnd + + sizeof(struct fcp_cmnd)); + + spin_lock_irqsave(&hdwq->hdwq_lock, iflags); + list_add_tail(&tmp->list_node, &lpfc_buf->dma_cmd_rsp_list); + } + + allocated_buf = list_last_entry(&lpfc_buf->dma_cmd_rsp_list, + struct fcp_cmd_rsp_buf, + list_node); + + spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags); + + return allocated_buf; +} + +/** + * lpfc_put_cmd_rsp_buf_per_hdwq - Put one CMD/RSP buffer into hdwq pool + * @phba: The HBA for which this call is being executed. + * @lpfc_buf: IO buf structure with the CMD/RSP buf + * + * This routine puts one CMD/RSP buffer into executing CPU's CMD/RSP pool. + * + * Return codes: + * 0 - Success + * -EINVAL - Error + **/ +int +lpfc_put_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba, + struct lpfc_io_buf *lpfc_buf) +{ + int rc = 0; + struct fcp_cmd_rsp_buf *list_entry = NULL; + struct fcp_cmd_rsp_buf *tmp = NULL; + struct lpfc_sli4_hdw_queue *hdwq = lpfc_buf->hdwq; + struct list_head *buf_list = &hdwq->cmd_rsp_buf_list; + unsigned long iflags; + + spin_lock_irqsave(&hdwq->hdwq_lock, iflags); + + if (likely(!list_empty(&lpfc_buf->dma_cmd_rsp_list))) { + list_for_each_entry_safe(list_entry, tmp, + &lpfc_buf->dma_cmd_rsp_list, + list_node) { + list_move_tail(&list_entry->list_node, + buf_list); + } + } else { + rc = -EINVAL; + } + + spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags); + return rc; +} + +/** + * lpfc_free_cmd_rsp_buf_per_hdwq - Free all CMD/RSP chunks of hdwq pool + * @phba: phba object + * @hdwq: hdwq to cleanup cmd rsp buff resources on + * + * This routine frees all CMD/RSP buffers of hdwq's CMD/RSP buf pool. + * + * Return codes: + * None + **/ +void +lpfc_free_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba, + struct lpfc_sli4_hdw_queue *hdwq) +{ + struct list_head *buf_list = &hdwq->cmd_rsp_buf_list; + struct fcp_cmd_rsp_buf *list_entry = NULL; + struct fcp_cmd_rsp_buf *tmp = NULL; + unsigned long iflags; + + spin_lock_irqsave(&hdwq->hdwq_lock, iflags); + + /* Free cmd_rsp buf pool */ + list_for_each_entry_safe(list_entry, tmp, + buf_list, + list_node) { + dma_pool_free(phba->lpfc_cmd_rsp_buf_pool, + list_entry->fcp_cmnd, + list_entry->fcp_cmd_rsp_dma_handle); + list_del(&list_entry->list_node); + kfree(list_entry); + } + + spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags); +} diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h index 467b8270f7fd..7bcf922a8be2 100644 --- a/drivers/scsi/lpfc/lpfc_sli.h +++ b/drivers/scsi/lpfc/lpfc_sli.h @@ -365,9 +365,18 @@ struct lpfc_io_buf { /* Common fields */ struct list_head list; void *data; + dma_addr_t dma_handle; dma_addr_t dma_phys_sgl; - struct sli4_sge *dma_sgl; + + struct sli4_sge *dma_sgl; /* initial segment chunk */ + + /* linked list of extra sli4_hybrid_sge */ + struct list_head dma_sgl_xtra_list; + + /* list head for fcp_cmd_rsp buf */ + struct list_head dma_cmd_rsp_list; + struct lpfc_iocbq cur_iocbq; struct lpfc_sli4_hdw_queue *hdwq; uint16_t hdwq_no; @@ -375,14 +384,13 @@ struct lpfc_io_buf { struct lpfc_nodelist *ndlp; uint32_t timeout; - uint16_t flags; /* TBD convert exch_busy to flags */ + uint16_t flags; #define LPFC_SBUF_XBUSY 0x1 /* SLI4 hba reported XB on WCQE cmpl */ #define LPFC_SBUF_BUMP_QDEPTH 0x2 /* bumped queue depth counter */ /* External DIF device IO conversions */ #define LPFC_SBUF_NORMAL_DIF 0x4 /* normal mode to insert/strip */ #define LPFC_SBUF_PASS_DIF 0x8 /* insert/strip mode to passthru */ #define LPFC_SBUF_NOT_POSTED 0x10 /* SGL failed post to FW. */ - uint16_t exch_busy; /* SLI4 hba reported XB on complete WCQE */ uint16_t status; /* From IOCB Word 7- ulpStatus */ uint32_t result; /* From IOCB Word 4. */ diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h index 3aeca387b22a..d963ca871383 100644 --- a/drivers/scsi/lpfc/lpfc_sli4.h +++ b/drivers/scsi/lpfc/lpfc_sli4.h @@ -41,11 +41,18 @@ /* Multi-queue arrangement for FCP EQ/CQ/WQ tuples */ #define LPFC_HBA_HDWQ_MIN 0 -#define LPFC_HBA_HDWQ_MAX 128 -#define LPFC_HBA_HDWQ_DEF 0 +#define LPFC_HBA_HDWQ_MAX 256 +#define LPFC_HBA_HDWQ_DEF LPFC_HBA_HDWQ_MIN -/* Common buffer size to accomidate SCSI and NVME IO buffers */ -#define LPFC_COMMON_IO_BUF_SZ 768 +/* irq_chann range, values */ +#define LPFC_IRQ_CHANN_MIN 0 +#define LPFC_IRQ_CHANN_MAX 256 +#define LPFC_IRQ_CHANN_DEF LPFC_IRQ_CHANN_MIN + +/* FCP MQ queue count limiting */ +#define LPFC_FCP_MQ_THRESHOLD_MIN 0 +#define LPFC_FCP_MQ_THRESHOLD_MAX 256 +#define LPFC_FCP_MQ_THRESHOLD_DEF 8 /* * Provide the default FCF Record attributes used by the driver @@ -109,9 +116,8 @@ enum lpfc_sli4_queue_type { enum lpfc_sli4_queue_subtype { LPFC_NONE, LPFC_MBOX, - LPFC_FCP, + LPFC_IO, LPFC_ELS, - LPFC_NVME, LPFC_NVMET, LPFC_NVME_LS, LPFC_USOL @@ -132,6 +138,23 @@ struct lpfc_rqb { struct lpfc_queue { struct list_head list; struct list_head wq_list; + + /* + * If interrupts are in effect on _all_ the eq's the footprint + * of polling code is zero (except mode). This memory is chec- + * ked for every io to see if the io needs to be polled and + * while completion to check if the eq's needs to be rearmed. + * Keep in same cacheline as the queue ptr to avoid cpu fetch + * stalls. Using 1B memory will leave us with 7B hole. Fill + * it with other frequently used members. + */ + uint16_t last_cpu; /* most recent cpu */ + uint16_t hdwq; + uint8_t qe_valid; + uint8_t mode; /* interrupt or polling */ +#define LPFC_EQ_INTERRUPT 0 +#define LPFC_EQ_POLL 1 + struct list_head wqfull_list; enum lpfc_sli4_queue_type type; enum lpfc_sli4_queue_subtype subtype; @@ -198,6 +221,7 @@ struct lpfc_queue { uint8_t q_flag; #define HBA_NVMET_WQFULL 0x1 /* We hit WQ Full condition for NVMET */ #define HBA_NVMET_CQ_NOTIFY 0x1 /* LPFC_NVMET_CQ_NOTIFY CQEs this EQE */ +#define HBA_EQ_DELAY_CHK 0x2 /* EQ is a candidate for coalescing */ #define LPFC_NVMET_CQ_NOTIFY 4 void __iomem *db_regaddr; uint16_t dpp_enable; @@ -238,10 +262,8 @@ struct lpfc_queue { struct delayed_work sched_spwork; uint64_t isr_timestamp; - uint16_t hdwq; - uint16_t last_cpu; /* most recent cpu */ - uint8_t qe_valid; struct lpfc_queue *assoc_qp; + struct list_head _poll_list; void **q_pgs; /* array to index entries per page */ }; @@ -450,11 +472,17 @@ struct lpfc_hba; #define LPFC_SLI4_HANDLER_NAME_SZ 16 struct lpfc_hba_eq_hdl { uint32_t idx; + uint16_t irq; char handler_name[LPFC_SLI4_HANDLER_NAME_SZ]; struct lpfc_hba *phba; struct lpfc_queue *eq; + struct cpumask aff_mask; }; +#define lpfc_get_eq_hdl(eqidx) (&phba->sli4_hba.hba_eq_hdl[eqidx]) +#define lpfc_get_aff_mask(eqidx) (&phba->sli4_hba.hba_eq_hdl[eqidx].aff_mask) +#define lpfc_get_irq(eqidx) (phba->sli4_hba.hba_eq_hdl[eqidx].irq) + /*BB Credit recovery value*/ struct lpfc_bbscn_params { uint32_t word0; @@ -512,6 +540,7 @@ struct lpfc_pc_sli4_params { uint8_t cqav; uint8_t wqsize; uint8_t bv1s; + uint8_t pls; #define LPFC_WQ_SZ64_SUPPORT 1 #define LPFC_WQ_SZ128_SUPPORT 2 uint8_t wqpcnt; @@ -543,11 +572,10 @@ struct lpfc_sli4_lnk_info { #define LPFC_SLI4_HANDLER_CNT (LPFC_HBA_IO_CHAN_MAX+ \ LPFC_FOF_IO_CHAN_NUM) -/* Used for IRQ vector to CPU mapping */ +/* Used for tracking CPU mapping attributes */ struct lpfc_vector_map_info { uint16_t phys_id; uint16_t core_id; - uint16_t irq; uint16_t eq; uint16_t hdwq; uint16_t flag; @@ -641,22 +669,17 @@ struct lpfc_eq_intr_info { struct lpfc_sli4_hdw_queue { /* Pointers to the constructed SLI4 queues */ struct lpfc_queue *hba_eq; /* Event queues for HBA */ - struct lpfc_queue *fcp_cq; /* Fast-path FCP compl queue */ - struct lpfc_queue *nvme_cq; /* Fast-path NVME compl queue */ - struct lpfc_queue *fcp_wq; /* Fast-path FCP work queue */ - struct lpfc_queue *nvme_wq; /* Fast-path NVME work queue */ - uint16_t fcp_cq_map; - uint16_t nvme_cq_map; + struct lpfc_queue *io_cq; /* Fast-path FCP & NVME compl queue */ + struct lpfc_queue *io_wq; /* Fast-path FCP & NVME work queue */ + uint16_t io_cq_map; /* Keep track of IO buffers for this hardware queue */ spinlock_t io_buf_list_get_lock; /* Common buf alloc list lock */ struct list_head lpfc_io_buf_list_get; spinlock_t io_buf_list_put_lock; /* Common buf free list lock */ struct list_head lpfc_io_buf_list_put; - spinlock_t abts_scsi_buf_list_lock; /* list of aborted SCSI IOs */ - struct list_head lpfc_abts_scsi_buf_list; - spinlock_t abts_nvme_buf_list_lock; /* list of aborted NVME IOs */ - struct list_head lpfc_abts_nvme_buf_list; + spinlock_t abts_io_buf_list_lock; /* list of aborted IOs */ + struct list_head lpfc_abts_io_buf_list; uint32_t total_io_bufs; uint32_t get_io_bufs; uint32_t put_io_bufs; @@ -680,6 +703,13 @@ struct lpfc_sli4_hdw_queue { 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; + + /* Lock for syncing Per HDWQ pool resources */ + spinlock_t hdwq_lock; }; #ifdef LPFC_HDWQ_LOCK_STAT @@ -845,8 +875,8 @@ struct lpfc_sli4_hba { struct lpfc_queue **cq_lookup; struct list_head lpfc_els_sgl_list; struct list_head lpfc_abts_els_sgl_list; - spinlock_t abts_scsi_buf_list_lock; /* list of aborted SCSI IOs */ - struct list_head lpfc_abts_scsi_buf_list; + spinlock_t abts_io_buf_list_lock; /* list of aborted SCSI IOs */ + struct list_head lpfc_abts_io_buf_list; struct list_head lpfc_nvmet_sgl_list; spinlock_t abts_nvmet_buf_list_lock; /* list of aborted NVMET IOs */ struct list_head lpfc_abts_nvmet_ctx_list; @@ -888,6 +918,7 @@ 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; uint16_t curr_disp_cpu; struct lpfc_eq_intr_info __percpu *eq_info; uint32_t conf_trunk; @@ -1051,10 +1082,11 @@ int lpfc_sli4_resume_rpi(struct lpfc_nodelist *, void (*)(struct lpfc_hba *, LPFC_MBOXQ_t *), void *); void lpfc_sli4_fcp_xri_abort_event_proc(struct lpfc_hba *); void lpfc_sli4_els_xri_abort_event_proc(struct lpfc_hba *); -void lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *, - struct sli4_wcqe_xri_aborted *, int); void lpfc_sli4_nvme_xri_aborted(struct lpfc_hba *phba, - struct sli4_wcqe_xri_aborted *axri, int idx); + struct sli4_wcqe_xri_aborted *axri, + struct lpfc_io_buf *lpfc_ncmd); +void lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba, + struct sli4_wcqe_xri_aborted *axri, int idx); void lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba, struct sli4_wcqe_xri_aborted *axri); void lpfc_sli4_els_xri_aborted(struct lpfc_hba *, @@ -1089,6 +1121,17 @@ int lpfc_sli4_post_status_check(struct lpfc_hba *); uint8_t lpfc_sli_config_mbox_subsys_get(struct lpfc_hba *, LPFC_MBOXQ_t *); uint8_t lpfc_sli_config_mbox_opcode_get(struct lpfc_hba *, LPFC_MBOXQ_t *); void lpfc_sli4_ras_dma_free(struct lpfc_hba *phba); +struct sli4_hybrid_sgl *lpfc_get_sgl_per_hdwq(struct lpfc_hba *phba, + struct lpfc_io_buf *buf); +struct fcp_cmd_rsp_buf *lpfc_get_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba, + struct lpfc_io_buf *buf); +int lpfc_put_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *buf); +int lpfc_put_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba, + struct lpfc_io_buf *buf); +void lpfc_free_sgl_per_hdwq(struct lpfc_hba *phba, + struct lpfc_sli4_hdw_queue *hdwq); +void lpfc_free_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba, + struct lpfc_sli4_hdw_queue *hdwq); static inline void *lpfc_sli4_qe(struct lpfc_queue *q, uint16_t idx) { return q->q_pgs[idx / q->entry_cnt_per_pg] + diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index f7e93aaf1e00..9563c49f36ab 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 "12.2.0.3" +#define LPFC_DRIVER_VERSION "12.6.0.3" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c index 343bc71d4615..b76646357980 100644 --- a/drivers/scsi/lpfc/lpfc_vport.c +++ b/drivers/scsi/lpfc/lpfc_vport.c @@ -527,9 +527,11 @@ disable_vport(struct fc_vport *fc_vport) * scsi_host_put() to release the vport. */ lpfc_mbx_unreg_vpi(vport); - spin_lock_irq(shost->host_lock); - vport->fc_flag |= FC_VPORT_NEEDS_INIT_VPI; - spin_unlock_irq(shost->host_lock); + if (phba->sli_rev == LPFC_SLI_REV4) { + spin_lock_irq(shost->host_lock); + vport->fc_flag |= FC_VPORT_NEEDS_INIT_VPI; + spin_unlock_irq(shost->host_lock); + } lpfc_vport_set_state(vport, FC_VPORT_DISABLED); lpfc_printf_vlog(vport, KERN_ERR, LOG_VPORT, |
