diff options
Diffstat (limited to 'drivers/scsi/lpfc')
-rw-r--r-- | drivers/scsi/lpfc/lpfc.h | 10 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_bsg.c | 15 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_crtn.h | 8 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_ct.c | 88 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_els.c | 41 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_hbadisc.c | 74 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_init.c | 205 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_nportdisc.c | 8 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_nvme.c | 14 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_nvmet.c | 2 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_scsi.c | 16 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_sli.c | 191 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_sli.h | 3 | ||||
-rw-r--r-- | drivers/scsi/lpfc/lpfc_sli4.h | 21 |
14 files changed, 590 insertions, 106 deletions
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index 4604e1bc334c..273426dfdd9a 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -740,6 +740,7 @@ struct lpfc_hba { */ #define HBA_NVME_IOQ_FLUSH 0x80000 /* NVME IO queues flushed. */ #define HBA_FLOGI_ISSUED 0x100000 /* FLOGI was issued */ +#define HBA_DEFER_FLOGI 0x800000 /* Defer FLOGI till read_sparm cmpl */ uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/ struct lpfc_dmabuf slim2p; @@ -1204,6 +1205,15 @@ 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 * diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index b0202bc0aa62..ef7f62b68413 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -4492,12 +4492,6 @@ 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 +4528,13 @@ 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 +4583,8 @@ 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); diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index e0b14d791b8c..4aa91d0b6291 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -179,7 +179,7 @@ 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 *); @@ -214,6 +214,12 @@ 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 *); diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index 4812bbbf43cc..6bc53d01d49e 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -1439,33 +1439,35 @@ 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 @@ -1938,14 +1940,16 @@ 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 +1962,41 @@ 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); @@ -2551,8 +2579,8 @@ 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_els.c b/drivers/scsi/lpfc/lpfc_els.c index 5ac4f8d76b91..c958e550911f 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -2200,6 +2200,7 @@ 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; @@ -2237,8 +2238,17 @@ 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, @@ -4279,7 +4289,7 @@ 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); @@ -6298,7 +6308,7 @@ 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; @@ -6387,6 +6397,13 @@ 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; @@ -7812,20 +7829,22 @@ 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; } @@ -7842,20 +7861,20 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) } if (phba->sli_rev == LPFC_SLI_REV4) spin_unlock(&pring->ring_lock); - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); /* Abort each iocb on the 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); @@ -7881,7 +7900,7 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) } 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 */ lpfc_sli_cancel_iocbs(phba, &abort_list, @@ -8162,6 +8181,8 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, spin_lock_irq(shost->host_lock); if (ndlp->nlp_flag & NLP_IN_DEV_LOSS) { spin_unlock_irq(shost->host_lock); + if (newnode) + lpfc_nlp_put(ndlp); goto dropit; } spin_unlock_irq(shost->host_lock); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index c43852f97f25..120d2844f3cb 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> @@ -1131,7 +1132,6 @@ 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; @@ -1156,18 +1156,15 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) } /* Start discovery by sending a FLOGI. port_state is identically - * LPFC_FLOGI while waiting for FLOGI cmpl + * LPFC_FLOGI while waiting for FLOGI cmpl. Check if sending + * the FLOGI is being deferred till after MBX_READ_SPARAM completes. */ if (vport->port_state != LPFC_FLOGI) { - 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); - } - lpfc_initial_flogi(vport); - } else if (vport->fc_flag & FC_PT2PT) { - lpfc_disc_start(vport); + if (!(phba->hba_flag & HBA_DEFER_FLOGI)) + lpfc_initial_flogi(vport); + } else { + if (vport->fc_flag & FC_PT2PT) + lpfc_disc_start(vport); } return; @@ -3093,6 +3090,14 @@ lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) lpfc_mbuf_free(phba, mp->virt, mp->phys); kfree(mp); mempool_free(pmb, phba->mbox_mem_pool); + + /* Check if sending the FLOGI is being deferred to after we get + * up to date CSPs from MBX_READ_SPARAM. + */ + if (phba->hba_flag & HBA_DEFER_FLOGI) { + lpfc_initial_flogi(vport); + phba->hba_flag &= ~HBA_DEFER_FLOGI; + } return; out: @@ -3222,6 +3227,23 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) } lpfc_linkup(phba); + sparam_mbox = NULL; + + if (!(phba->hba_flag & HBA_FCOE_MODE)) { + cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); + if (!cfglink_mbox) + goto out; + vport->port_state = LPFC_LOCAL_CFG_LINK; + lpfc_config_link(phba, cfglink_mbox); + cfglink_mbox->vport = vport; + cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link; + rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT); + if (rc == MBX_NOT_FINISHED) { + mempool_free(cfglink_mbox, phba->mbox_mem_pool); + goto out; + } + } + sparam_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); if (!sparam_mbox) goto out; @@ -3242,20 +3264,7 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) goto out; } - if (!(phba->hba_flag & HBA_FCOE_MODE)) { - cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); - if (!cfglink_mbox) - goto out; - vport->port_state = LPFC_LOCAL_CFG_LINK; - lpfc_config_link(phba, cfglink_mbox); - cfglink_mbox->vport = vport; - cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link; - rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT); - if (rc == MBX_NOT_FINISHED) { - mempool_free(cfglink_mbox, phba->mbox_mem_pool); - goto out; - } - } else { + if (phba->hba_flag & HBA_FCOE_MODE) { vport->port_state = LPFC_VPORT_UNKNOWN; /* * Add the driver's default FCF record at FCF index 0 now. This @@ -3312,8 +3321,16 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) } /* Reset FCF roundrobin bmask for new discovery */ lpfc_sli4_clear_fcf_rr_bmask(phba); + } else { + if (phba->bbcredit_support && phba->cfg_enable_bbcr && + !(phba->link_flag & LS_LOOPBACK_MODE)) + phba->hba_flag |= HBA_DEFER_FLOGI; } + /* Prepare for LINK up registrations */ + 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); @@ -5333,9 +5350,14 @@ 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); diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 2fd8f15f9997..546cdc345e6d 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -39,6 +39,7 @@ #include <linux/msi.h> #include <linux/irq.h> #include <linux/bitops.h> +#include <linux/cpuhotplug.h> #include <scsi/scsi.h> #include <scsi/scsi_device.h> @@ -71,9 +72,13 @@ 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 */ 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 *); @@ -1376,7 +1381,7 @@ 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); @@ -3401,6 +3406,8 @@ 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; } @@ -3559,6 +3566,7 @@ 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); @@ -9172,6 +9180,8 @@ 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); @@ -10726,6 +10736,170 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors) } /** + * 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) +{ + struct lpfc_vector_map_info *map; + const struct cpumask *maskp; + struct lpfc_queue *eq; + unsigned int i; + 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 + */ + for_each_possible_cpu(i) { + map = &phba->sli4_hba.cpu_map[i]; + if (!(map->irq == pci_irq_vector(phba->pcidev, idx))) + continue; + eq = phba->sli4_hba.hdwq[map->hdwq].hba_eq; + list_add(&eq->_poll_list, eqlist); + /* 1 is good enough. others will be a copy of this */ + break; + } + } +} + +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; +} + +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_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; + + 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. * @@ -11155,6 +11329,10 @@ 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 */ + if (phba->pport) + lpfc_cpuhp_remove(phba); + /* Disable PCI subsystem interrupt */ lpfc_sli4_disable_intr(phba); @@ -12380,6 +12558,9 @@ 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: @@ -13206,11 +13387,24 @@ 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; } @@ -13227,6 +13421,7 @@ 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) { diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index 59252bfca14e..b3d968303145 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -484,8 +484,10 @@ 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); } @@ -845,9 +847,9 @@ 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); diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 9d99cb915390..532d44d3055e 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -342,13 +342,15 @@ lpfc_nvme_remoteport_delete(struct nvme_fc_remote_port *remoteport) if (ndlp->upcall_flags & NLP_WAIT_FOR_UNREG) { ndlp->nrport = NULL; ndlp->upcall_flags &= ~NLP_WAIT_FOR_UNREG; - } - spin_unlock_irq(&vport->phba->hbalock); + spin_unlock_irq(&vport->phba->hbalock); - /* Remove original register reference. The host transport - * won't reference this rport/remoteport any further. - */ - lpfc_nlp_put(ndlp); + /* Remove original register reference. The host transport + * won't reference this rport/remoteport any further. + */ + lpfc_nlp_put(ndlp); + } else { + spin_unlock_irq(&vport->phba->hbalock); + } rport_err: return; diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index d74bfd264495..8a93dfa79297 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -1723,7 +1723,7 @@ lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba) } tgtp->tport_unreg_cmp = &tport_unreg_cmp; nvmet_fc_unregister_targetport(phba->targetport); - if (!wait_for_completion_timeout(tgtp->tport_unreg_cmp, + if (!wait_for_completion_timeout(&tport_unreg_cmp, msecs_to_jiffies(LPFC_NVMET_WAIT_TMO))) lpfc_printf_log(phba, KERN_ERR, LOG_NVME, "6179 Unreg targetport %p timeout " diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index ba996fbde89b..31989b8863a1 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -583,7 +583,7 @@ lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *phba, if (psb->cur_iocbq.sli4_xritag == xri) { list_del(&psb->list); qp->abts_scsi_io_bufs--; - psb->exch_busy = 0; + psb->flags &= ~LPFC_SBUF_XBUSY; psb->status = IOSTAT_SUCCESS; spin_unlock( &qp->abts_scsi_buf_list_lock); @@ -615,7 +615,7 @@ lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *phba, 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); @@ -834,7 +834,7 @@ 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) { + if (psb->flags & LPFC_SBUF_XBUSY) { spin_lock_irqsave(&qp->abts_scsi_buf_list_lock, iflag); psb->pCmd = NULL; list_add_tail(&psb->list, &qp->lpfc_abts_scsi_buf_list); @@ -3679,7 +3679,10 @@ 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) { @@ -4682,20 +4685,21 @@ 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, diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index d1512e4f9791..6e97d85c698d 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -485,7 +485,8 @@ lpfc_sli4_eq_flush(struct lpfc_hba *phba, struct lpfc_queue *eq) } 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 +520,8 @@ 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; } @@ -2463,6 +2464,8 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) !pmb->u.mb.mbxStatus) { rpi = pmb->u.mb.un.varWords[0]; vpi = pmb->u.mb.un.varRegLogin.vpi; + if (phba->sli_rev == LPFC_SLI_REV4) + vpi -= phba->sli4_hba.max_cfg_param.vpi_base; lpfc_unreg_login(phba, vpi, rpi, pmb); pmb->vport = vport; pmb->mbox_cmpl = lpfc_sli_def_mbox_cmpl; @@ -3991,6 +3994,11 @@ lpfc_sli_flush_fcp_rings(struct lpfc_hba *phba) struct lpfc_iocbq *piocb, *next_iocb; spin_lock_irq(&phba->hbalock); + if (phba->hba_flag & HBA_FCP_IOQ_FLUSH || + !phba->sli4_hba.hdwq) { + spin_unlock_irq(&phba->hbalock); + return; + } /* Indicate the I/O queues are flushed */ phba->hba_flag |= HBA_FCP_IOQ_FLUSH; spin_unlock_irq(&phba->hbalock); @@ -7915,7 +7923,7 @@ 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); @@ -10068,10 +10076,13 @@ 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; @@ -10079,6 +10090,8 @@ 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); @@ -11758,7 +11771,10 @@ 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; @@ -13180,13 +13196,19 @@ 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; } /** @@ -14262,7 +14284,7 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id) 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++; @@ -14322,6 +14344,147 @@ 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. @@ -14396,6 +14559,7 @@ 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); @@ -18193,6 +18357,13 @@ 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--; @@ -19691,6 +19862,8 @@ 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; } @@ -19711,6 +19884,8 @@ 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; } @@ -19739,6 +19914,8 @@ 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; diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h index 467b8270f7fd..9449236c231d 100644 --- a/drivers/scsi/lpfc/lpfc_sli.h +++ b/drivers/scsi/lpfc/lpfc_sli.h @@ -375,14 +375,13 @@ 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 986594ec40e2..9c3100246375 100644 --- a/drivers/scsi/lpfc/lpfc_sli4.h +++ b/drivers/scsi/lpfc/lpfc_sli4.h @@ -137,6 +137,23 @@ 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; @@ -241,10 +258,8 @@ 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 */ }; |