aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/scsi/lpfc
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/scsi/lpfc')
-rw-r--r--drivers/scsi/lpfc/lpfc.h40
-rw-r--r--drivers/scsi/lpfc/lpfc_attr.c298
-rw-r--r--drivers/scsi/lpfc/lpfc_bsg.c18
-rw-r--r--drivers/scsi/lpfc/lpfc_crtn.h7
-rw-r--r--drivers/scsi/lpfc/lpfc_ct.c28
-rw-r--r--drivers/scsi/lpfc/lpfc_debugfs.c118
-rw-r--r--drivers/scsi/lpfc/lpfc_els.c57
-rw-r--r--drivers/scsi/lpfc/lpfc_hbadisc.c200
-rw-r--r--drivers/scsi/lpfc/lpfc_hw4.h31
-rw-r--r--drivers/scsi/lpfc/lpfc_init.c956
-rw-r--r--drivers/scsi/lpfc/lpfc_logmsg.h17
-rw-r--r--drivers/scsi/lpfc/lpfc_mbox.c1
-rw-r--r--drivers/scsi/lpfc/lpfc_mem.c3
-rw-r--r--drivers/scsi/lpfc/lpfc_nportdisc.c149
-rw-r--r--drivers/scsi/lpfc/lpfc_nvme.c85
-rw-r--r--drivers/scsi/lpfc/lpfc_nvmet.c103
-rw-r--r--drivers/scsi/lpfc/lpfc_nvmet.h2
-rw-r--r--drivers/scsi/lpfc/lpfc_scsi.c43
-rw-r--r--drivers/scsi/lpfc/lpfc_sli.c391
-rw-r--r--drivers/scsi/lpfc/lpfc_sli.h3
-rw-r--r--drivers/scsi/lpfc/lpfc_sli4.h42
-rw-r--r--drivers/scsi/lpfc/lpfc_version.h2
22 files changed, 1999 insertions, 595 deletions
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 691acbdcc46d..935f98804198 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -605,6 +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 */
@@ -621,7 +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 {
@@ -725,6 +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 */
@@ -830,6 +837,7 @@ struct lpfc_hba {
uint32_t cfg_fcp_mq_threshold;
uint32_t cfg_hdw_queue;
uint32_t cfg_irq_chann;
+ uint32_t cfg_irq_numa;
uint32_t cfg_suppress_rsp;
uint32_t cfg_nvme_oas;
uint32_t cfg_nvme_embed_cmd;
@@ -872,7 +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;
@@ -990,7 +997,6 @@ 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;
@@ -1055,6 +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;
@@ -1209,6 +1216,13 @@ 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 */
};
static inline struct Scsi_Host *
@@ -1299,6 +1313,26 @@ 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 25aa7a53d255..4ff82b36a37a 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);
@@ -1475,8 +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) &&
@@ -1486,8 +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))
@@ -1642,7 +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,
@@ -3533,6 +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)
@@ -3580,9 +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.
@@ -4096,7 +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 ||
+ /*
+ * The 'topology' is not a configurable parameter if :
+ * - persistent topology enabled
+ * - G7 adapters
+ * - 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,
@@ -5298,7 +5331,7 @@ 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,
@@ -5311,10 +5344,10 @@ 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));
@@ -5329,7 +5362,7 @@ 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,
@@ -5340,7 +5373,7 @@ 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++;
@@ -5711,7 +5744,7 @@ LPFC_ATTR_RW(nvme_embed_cmd, 1, 0, 2,
* the driver will advertise it supports to the SCSI layer.
*
* 0 = Set nr_hw_queues by the number of CPUs or HW queues.
- * 1,128 = Manually specify the maximum nr_hw_queue value to be set,
+ * 1,256 = Manually specify nr_hw_queue value to be advertised,
*
* Value range is [0,256]. Default value is 8.
*/
@@ -5729,30 +5762,130 @@ LPFC_ATTR_R(fcp_mq_threshold, LPFC_FCP_MQ_THRESHOLD_DEF,
* 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.
@@ -5933,7 +6066,53 @@ LPFC_ATTR_RW(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
@@ -6071,8 +6250,9 @@ 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,
@@ -7085,11 +7265,22 @@ struct fc_function_template lpfc_vport_transport_functions = {
static void
lpfc_get_hba_function_mode(struct lpfc_hba *phba)
{
- /* If it's a SkyHawk FCoE adapter */
- if (phba->pcidev->device == PCI_DEVICE_ID_SKYHAWK)
+ /* 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;
- else
+ break;
+ default:
+ /* for others, clear the flag */
phba->hba_flag &= ~HBA_FCOE_MODE;
+ }
}
/**
@@ -7099,6 +7290,7 @@ lpfc_get_hba_function_mode(struct lpfc_hba *phba)
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);
@@ -7205,12 +7397,10 @@ 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;
@@ -7256,11 +7446,11 @@ 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 39a736b887b1..d4e1b120cc9e 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -5435,10 +5435,12 @@ 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;
@@ -5495,10 +5497,13 @@ 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);
@@ -5509,8 +5514,10 @@ 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,
@@ -5626,10 +5633,13 @@ 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) +
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index b2ad8c750486..ee353c84a097 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -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 *);
@@ -586,6 +592,7 @@ void lpfc_release_io_buf(struct lpfc_hba *phba, struct lpfc_io_buf *ncmd,
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 25e86706e207..99c9bb249758 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -763,9 +763,11 @@ lpfc_cmpl_ct_cmd_gid_ft(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
cpu_to_be16(SLI_CT_RESPONSE_FS_ACC)) {
lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
"0208 NameServer Rsp Data: x%x x%x "
- "sz x%x\n",
+ "x%x x%x sz x%x\n",
vport->fc_flag,
CTreq->un.gid.Fc4Type,
+ vport->num_disc_nodes,
+ vport->gidft_inp,
irsp->un.genreq64.bdl.bdeSize);
lpfc_ns_rsp(vport,
@@ -961,9 +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,
@@ -1025,6 +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)) {
@@ -1159,6 +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.
@@ -1868,6 +1884,12 @@ 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:
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 8d34be60d379..2e6a68d9ea4f 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>
@@ -2078,6 +2079,96 @@ 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;
+
+ 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) {
+ memcpy(buffer + copied, dmabuf->virt, LPFC_RAS_MAX_ENTRY_SIZE);
+ copied += LPFC_RAS_MAX_ENTRY_SIZE;
+ if (size > copied)
+ break;
+ }
+ 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_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.
+ *
+ * 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_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;
+
+ 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_ras_log_data(phba, debug->buffer, size);
+ if (debug->len < 0) {
+ rc = -EINVAL;
+ goto free_buffer;
+ }
+ file->private_data = debug;
+
+ return 0;
+
+free_buffer:
+ vfree(debug->buffer);
+free_debug:
+ kfree(debug);
+out:
+ return rc;
+}
+
/**
* lpfc_debugfs_dumpHBASlim_open - Open the Dump HBA SLIM debugfs buffer
* @inode: The inode pointer that contains a vport pointer.
@@ -5286,6 +5377,16 @@ 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,
+};
+#endif
+
#undef lpfc_debugfs_op_dumpHBASlim
static const struct file_operations lpfc_debugfs_op_dumpHBASlim = {
.owner = THIS_MODULE,
@@ -5457,7 +5558,6 @@ static const struct file_operations lpfc_idiag_op_extAcc = {
.release = lpfc_idiag_cmd_release,
};
-#endif
/* lpfc_idiag_mbxacc_dump_bsg_mbox - idiag debugfs dump bsg mailbox command
* @phba: Pointer to HBA context object.
@@ -5707,6 +5807,19 @@ 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 =
@@ -6117,6 +6230,9 @@ 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;
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index d5303994bfd6..42a2bf38eaea 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -2236,6 +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;
@@ -2273,8 +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,
@@ -4291,6 +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;
@@ -4430,7 +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);
@@ -5260,6 +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);
}
@@ -6455,7 +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;
@@ -6561,6 +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;
@@ -6663,9 +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;
@@ -7986,20 +8014,22 @@ 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;
}
@@ -8014,6 +8044,9 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
if (piocb->vport != vport)
continue;
+ if (piocb->iocb_flag & LPFC_DRIVER_ABORTED)
+ continue;
+
/* On the ELS ring we can have ELS_REQUESTs or
* GEN_REQUESTs waiting for a response.
*/
@@ -8037,21 +8070,21 @@ 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 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);
@@ -8091,7 +8124,7 @@ 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);
/* Cancel all the IOCBs from the completions list */
lpfc_sli_cancel_iocbs(phba, &abort_list,
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 749286acdc17..85ada3deb47d 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -700,7 +700,10 @@ 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,
@@ -1135,7 +1138,6 @@ 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;
@@ -1162,17 +1164,11 @@ 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:
@@ -3456,8 +3452,8 @@ 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),
@@ -4046,7 +4042,7 @@ 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,
+ 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),
@@ -4575,8 +4571,10 @@ 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;
}
@@ -4835,12 +4833,51 @@ lpfc_nlp_logo_unreg(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
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
@@ -4860,7 +4897,8 @@ 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",
@@ -4871,7 +4909,8 @@ 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: x%px\n",
@@ -4890,39 +4929,19 @@ 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:x%px\n",
@@ -5057,6 +5076,7 @@ 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,
@@ -5138,8 +5158,20 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
lpfc_cleanup_vports_rrqs(vport, ndlp);
if (phba->sli_rev == LPFC_SLI_REV4)
ndlp->nlp_flag |= NLP_RELEASE_RPI;
- lpfc_unreg_rpi(vport, ndlp);
-
+ 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;
}
@@ -5165,8 +5197,10 @@ 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 x%px\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);
@@ -5203,8 +5237,9 @@ lpfc_nlp_remove(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
*/
lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE,
"0940 removed node x%px DID x%x "
- " rport not null x%px\n",
- ndlp, ndlp->nlp_DID, ndlp->rport);
+ "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;
@@ -5362,6 +5397,13 @@ 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);
@@ -5375,6 +5417,12 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
"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);
@@ -5394,6 +5442,12 @@ 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
@@ -5405,15 +5459,32 @@ 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.
@@ -5565,10 +5636,10 @@ 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);
@@ -5996,7 +6067,7 @@ 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,
+ 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),
@@ -6185,12 +6256,12 @@ 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 x%px\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,
@@ -6419,7 +6490,8 @@ 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_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index bd533475c86a..25cdcbc2b02f 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
@@ -2320,6 +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;
@@ -2809,6 +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
@@ -3479,6 +3488,9 @@ 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
@@ -3518,6 +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;
@@ -3532,6 +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
@@ -4261,6 +4283,8 @@ 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
};
/*
@@ -4659,6 +4683,7 @@ 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
@@ -4807,8 +4832,8 @@ 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 e8813d26e594..6298b1729098 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -40,6 +40,8 @@
#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>
@@ -66,9 +68,13 @@
#include "lpfc_version.h"
#include "lpfc_ids.h"
+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 *);
@@ -1235,10 +1241,9 @@ 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;
- bool update = false;
if (!phba->cfg_auto_imax || phba->pport->load_flag & FC_UNLOADING)
return;
@@ -1247,44 +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;
- if (phba->cfg_irq_chann > 1) {
- /* 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)
- continue;
- if (eq->q_mode) {
- update = true;
- break;
- }
- if (eqcnt[eq->last_cpu] < 2)
- eqcnt[eq->last_cpu]++;
+ 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)
+ 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;
}
- } else
- update = true;
+ }
for_each_present_cpu(i) {
eqi = per_cpu_ptr(phba->sli4_hba.eq_info, i);
- if (!update && eqcnt[i] < 2) {
- eqi->icnt = 0;
- continue;
+ 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;
}
- usdelay = (eqi->icnt / LPFC_IMAX_THRESHOLD) *
- LPFC_EQ_DELAY_STEP;
- if (usdelay > LPFC_MAX_AUTO_EQ_DELAY)
- usdelay = LPFC_MAX_AUTO_EQ_DELAY;
-
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);
@@ -1296,7 +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,
@@ -3053,11 +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 x%px\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);
@@ -3387,6 +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;
}
@@ -3453,10 +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);
@@ -3472,16 +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%px 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);
}
@@ -3545,6 +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);
@@ -5283,10 +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)
@@ -5433,11 +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;
}
@@ -5976,6 +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.
*
@@ -6416,8 +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);
@@ -6953,6 +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);
@@ -7126,7 +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;
}
@@ -7545,18 +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);
@@ -8235,6 +8273,94 @@ 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:
+ if (tf || (pt == LINK_FLAGS_LOOP)) {
+ /* Invalid values from FW - use driver params */
+ phba->hba_flag &= ~HBA_PERSISTENT_TOPO;
+ } else {
+ /* Prism only supports PT2PT topology */
+ phba->cfg_topology = FLAGS_TOPOLOGY_MODE_PT_PT;
+ }
+ break;
+ 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.
@@ -8346,6 +8472,7 @@ 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), "
@@ -8619,8 +8746,8 @@ 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;
}
@@ -9160,6 +9287,8 @@ 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);
@@ -10581,7 +10710,6 @@ 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;
@@ -10619,6 +10747,75 @@ 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.
@@ -10637,22 +10834,10 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors)
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;
@@ -10688,65 +10873,6 @@ 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);
-
- /* 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++;
-
- lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
- "3336 Set Affinity: CPU %d "
- "irq %d eq %d flag x%x\n",
- cpu, cpup->irq, cpup->eq, cpup->flag);
- }
- }
-
/* 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
@@ -10772,7 +10898,7 @@ 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(
@@ -10785,7 +10911,6 @@ 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
@@ -10797,9 +10922,10 @@ 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);
}
}
@@ -10823,7 +10949,7 @@ 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);
@@ -10833,13 +10959,12 @@ 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
@@ -10851,8 +10976,8 @@ 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);
}
}
@@ -10873,11 +10998,11 @@ found_any:
idx++;
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
"3333 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);
+ cpup->hdwq, cpup->eq, cpup->flag);
}
- /* Finally we need to associate a hdwq with each cpu_map entry
+ /* 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.
@@ -10951,9 +11076,26 @@ found_any:
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);
+ 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
@@ -10963,11 +11105,280 @@ found_any:
}
/**
+ * 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
@@ -10978,13 +11389,31 @@ 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);
@@ -10994,23 +11423,61 @@ 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) {
@@ -11020,17 +11487,18 @@ 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);
@@ -11057,6 +11525,8 @@ static int
lpfc_sli4_enable_msi(struct lpfc_hba *phba)
{
int rc, index;
+ unsigned int cpu;
+ struct lpfc_hba_eq_hdl *eqhdl;
rc = pci_alloc_irq_vectors(phba->pcidev, 1, 1,
PCI_IRQ_MSI | PCI_IRQ_AFFINITY);
@@ -11078,9 +11548,15 @@ lpfc_sli4_enable_msi(struct lpfc_hba *phba)
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;
@@ -11138,15 +11614,21 @@ 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;
}
}
}
@@ -11168,14 +11650,14 @@ 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);
@@ -11367,6 +11849,9 @@ 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);
@@ -11538,6 +12023,7 @@ 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);
@@ -11589,13 +12075,10 @@ fcponly:
}
/* 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.
+ * accommodate 512K and 1M IOs in a single nvme buf.
*/
- if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+ if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)
phba->cfg_sg_seg_cnt = LPFC_MAX_NVME_SEG_CNT;
- phba->cfg_iocb_cnt = 5;
- }
/* 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) !=
@@ -12312,35 +12795,57 @@ 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,
- "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);
+ "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. 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
@@ -12409,8 +12914,12 @@ 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;
}
}
@@ -12430,9 +12939,12 @@ 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);
}
/**
@@ -12551,6 +13063,12 @@ 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) {
@@ -12632,6 +13150,9 @@ 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:
@@ -13344,8 +13865,7 @@ 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;
}
@@ -13450,11 +13970,24 @@ 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;
}
@@ -13471,6 +14004,7 @@ 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);
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 ae09bb863497..7082279e4c01 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -230,9 +230,6 @@ lpfc_mem_free(struct lpfc_hba *phba)
dma_pool_destroy(phba->lpfc_hrb_pool);
phba->lpfc_hrb_pool = NULL;
- dma_pool_destroy(phba->txrdy_payload_pool);
- phba->txrdy_payload_pool = NULL;
-
dma_pool_destroy(phba->lpfc_hbq_pool);
phba->lpfc_hbq_pool = NULL;
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index fc6e4546d738..ae4359013846 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -279,6 +279,55 @@ 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);
+ lpfc_sli_release_iocbq(phba, 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);
+ lpfc_sli_release_iocbq(phba, save_iocb);
+}
+
static int
lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
struct lpfc_iocbq *cmdiocb)
@@ -291,10 +340,12 @@ 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;
+ int rc, defer_acc;
memset(&stat, 0, sizeof (struct ls_rjt));
pcmd = (struct lpfc_dmabuf *) cmdiocb->context2;
@@ -343,6 +394,7 @@ 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 +406,6 @@ 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 +447,10 @@ 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 +478,22 @@ 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 = lpfc_sli_get_iocbq(phba);
+ 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);
@@ -448,8 +508,8 @@ 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 */
@@ -457,21 +517,19 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
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 +542,10 @@ 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);
}
@@ -504,16 +564,47 @@ 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:
+ * Issue CONFIG_LINK mbox
+ * CONFIG_LINK 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 pt2pt discovery failure: %p %p %p\n",
+ save_iocb, link_mbox, login_mbox);
+ if (save_iocb)
+ lpfc_sli_release_iocbq(phba, 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);
@@ -2030,7 +2121,9 @@ 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))
+ 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;
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index a227e36cbdc2..db4a04a207ec 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.
@@ -1791,7 +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;
@@ -1912,37 +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(*abts_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;
@@ -2084,7 +2093,7 @@ 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",
@@ -2139,12 +2148,10 @@ 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;
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 9884228800a5..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;
@@ -1958,12 +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;
@@ -1971,6 +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);
@@ -2326,7 +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;
@@ -2401,6 +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;
@@ -2429,6 +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;
@@ -2595,7 +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;
@@ -2757,23 +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;
@@ -2808,17 +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;
@@ -3239,9 +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;
@@ -3280,8 +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. */
@@ -3327,40 +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(*abts_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;
@@ -3495,7 +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 6822cd9ff8f1..b138d9fee675 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -134,21 +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;
@@ -526,7 +526,7 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba,
&qp->lpfc_abts_io_buf_list, list) {
if (psb->cur_iocbq.sli4_xritag == xri) {
list_del_init(&psb->list);
- psb->exch_busy = 0;
+ psb->flags &= ~LPFC_SBUF_XBUSY;
psb->status = IOSTAT_SUCCESS;
if (psb->cur_iocbq.iocb_flag == LPFC_IO_NVME) {
qp->abts_nvme_io_bufs--;
@@ -566,7 +566,7 @@ lpfc_sli4_io_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);
@@ -786,7 +786,7 @@ 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_io_buf_list_lock, iflag);
psb->pCmd = NULL;
list_add_tail(&psb->list, &qp->lpfc_abts_io_buf_list);
@@ -3812,7 +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);
@@ -3824,7 +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]++;
@@ -3835,7 +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) {
@@ -3869,7 +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;
@@ -4002,7 +4005,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
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))) {
@@ -4610,17 +4613,18 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
err = lpfc_scsi_prep_dma_buf(phba, lpfc_cmd);
}
- if (err == 2) {
- cmnd->result = DID_ERROR << 16;
- goto out_fail_command_release_buf;
- } else 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 =
@@ -4843,20 +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,
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 614f78dddafe..c82b5792da98 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;
}
@@ -2526,6 +2557,8 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
} else {
__lpfc_sli_rpi_release(vport, ndlp);
}
+ if (vport->load_flag & FC_UNLOADING)
+ lpfc_nlp_put(ndlp);
pmb->ctx_ndlp = NULL;
}
}
@@ -2672,7 +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),
@@ -2693,7 +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),
@@ -2701,7 +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);
@@ -6167,6 +6203,14 @@ 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;
@@ -6184,11 +6228,16 @@ 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);
}
/**
@@ -6224,7 +6273,9 @@ 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);
}
/**
@@ -6326,7 +6377,9 @@ 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;
@@ -6358,6 +6411,10 @@ 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);
@@ -6417,6 +6474,9 @@ 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;
@@ -7148,7 +7208,7 @@ 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;
@@ -7399,6 +7459,23 @@ 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.
@@ -7523,9 +7600,11 @@ 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);
@@ -7547,14 +7626,17 @@ 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,
@@ -7892,7 +7974,7 @@ 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);
@@ -8964,7 +9046,8 @@ 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.
**/
@@ -8972,7 +9055,10 @@ 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);
}
@@ -9863,7 +9949,7 @@ 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.
**/
@@ -10053,10 +10139,13 @@ 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;
@@ -10064,6 +10153,8 @@ 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);
@@ -10678,14 +10769,14 @@ 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)
@@ -11050,9 +11141,6 @@ lpfc_sli_abort_els_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
irsp->ulpStatus, irsp->un.ulpWord[4]);
spin_unlock_irq(&phba->hbalock);
- if (irsp->ulpStatus == IOSTAT_LOCAL_REJECT &&
- irsp->un.ulpWord[4] == IOERR_SLI_ABORTED)
- lpfc_sli_release_iocbq(phba, abort_iocb);
}
release_iocb:
lpfc_sli_release_iocbq(phba, cmdiocb);
@@ -11736,7 +11824,10 @@ 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;
@@ -13158,13 +13249,19 @@ 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;
}
/**
@@ -13217,7 +13314,6 @@ 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))) {
@@ -13239,9 +13335,8 @@ 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;
}
@@ -13592,6 +13687,7 @@ __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)
@@ -14220,7 +14316,7 @@ 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;
}
@@ -14230,14 +14326,14 @@ 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++;
@@ -14297,6 +14393,147 @@ 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.
@@ -14371,6 +14608,7 @@ 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);
@@ -18124,8 +18362,9 @@ 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);
/*
@@ -18181,11 +18420,19 @@ 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_SLI,
+ lpfc_printf_log(phba, KERN_INFO,
+ LOG_NODE | LOG_DISCOVERY,
"2016 rpi %x not inuse\n",
rpi);
}
@@ -19683,6 +19930,8 @@ 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;
}
@@ -19703,6 +19952,8 @@ 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;
}
@@ -19731,6 +19982,8 @@ 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;
@@ -20093,6 +20346,13 @@ 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 */
@@ -20157,13 +20417,6 @@ void lpfc_release_io_buf(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_ncmd,
spin_unlock_irqrestore(&qp->io_buf_list_put_lock,
iflag);
}
-
- 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);
}
/**
@@ -20399,8 +20652,9 @@ lpfc_get_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
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_irq(&hdwq->hdwq_lock);
+ spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
if (likely(!list_empty(buf_list))) {
/* break off 1 chunk from the sgl_list */
@@ -20412,9 +20666,9 @@ lpfc_get_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
}
} else {
/* allocate more */
- spin_unlock_irq(&hdwq->hdwq_lock);
+ spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
tmp = kmalloc_node(sizeof(*tmp), GFP_ATOMIC,
- cpu_to_node(smp_processor_id()));
+ cpu_to_node(hdwq->io_wq->chann));
if (!tmp) {
lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
"8353 error kmalloc memory for HDWQ "
@@ -20434,7 +20688,7 @@ lpfc_get_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
return NULL;
}
- spin_lock_irq(&hdwq->hdwq_lock);
+ spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
list_add_tail(&tmp->list_node, &lpfc_buf->dma_sgl_xtra_list);
}
@@ -20442,7 +20696,7 @@ lpfc_get_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
struct sli4_hybrid_sgl,
list_node);
- spin_unlock_irq(&hdwq->hdwq_lock);
+ spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
return allocated_sgl;
}
@@ -20466,8 +20720,9 @@ lpfc_put_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
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_irq(&hdwq->hdwq_lock);
+ 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,
@@ -20480,7 +20735,7 @@ lpfc_put_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
rc = -EINVAL;
}
- spin_unlock_irq(&hdwq->hdwq_lock);
+ spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
return rc;
}
@@ -20501,8 +20756,9 @@ lpfc_free_sgl_per_hdwq(struct lpfc_hba *phba,
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_irq(&hdwq->hdwq_lock);
+ spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
/* Free sgl pool */
list_for_each_entry_safe(list_entry, tmp,
@@ -20514,7 +20770,7 @@ lpfc_free_sgl_per_hdwq(struct lpfc_hba *phba,
kfree(list_entry);
}
- spin_unlock_irq(&hdwq->hdwq_lock);
+ spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
}
/**
@@ -20538,8 +20794,9 @@ lpfc_get_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
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_irq(&hdwq->hdwq_lock);
+ spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
if (likely(!list_empty(buf_list))) {
/* break off 1 chunk from the list */
@@ -20552,9 +20809,9 @@ lpfc_get_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
}
} else {
/* allocate more */
- spin_unlock_irq(&hdwq->hdwq_lock);
+ spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
tmp = kmalloc_node(sizeof(*tmp), GFP_ATOMIC,
- cpu_to_node(smp_processor_id()));
+ cpu_to_node(hdwq->io_wq->chann));
if (!tmp) {
lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
"8355 error kmalloc memory for HDWQ "
@@ -20579,7 +20836,7 @@ lpfc_get_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
tmp->fcp_rsp = (struct fcp_rsp *)((uint8_t *)tmp->fcp_cmnd +
sizeof(struct fcp_cmnd));
- spin_lock_irq(&hdwq->hdwq_lock);
+ spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
list_add_tail(&tmp->list_node, &lpfc_buf->dma_cmd_rsp_list);
}
@@ -20587,7 +20844,7 @@ lpfc_get_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
struct fcp_cmd_rsp_buf,
list_node);
- spin_unlock_irq(&hdwq->hdwq_lock);
+ spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
return allocated_buf;
}
@@ -20612,8 +20869,9 @@ lpfc_put_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
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_irq(&hdwq->hdwq_lock);
+ 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,
@@ -20626,7 +20884,7 @@ lpfc_put_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
rc = -EINVAL;
}
- spin_unlock_irq(&hdwq->hdwq_lock);
+ spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
return rc;
}
@@ -20647,8 +20905,9 @@ lpfc_free_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
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_irq(&hdwq->hdwq_lock);
+ spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
/* Free cmd_rsp buf pool */
list_for_each_entry_safe(list_entry, tmp,
@@ -20661,5 +20920,5 @@ lpfc_free_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
kfree(list_entry);
}
- spin_unlock_irq(&hdwq->hdwq_lock);
+ spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
}
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 37fbcb46387e..7bcf922a8be2 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -384,14 +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 0d4882a9e634..d963ca871383 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -41,8 +41,13 @@
/* 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
+
+/* 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
@@ -133,6 +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;
@@ -199,6 +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;
@@ -239,10 +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 */
};
@@ -451,11 +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;
@@ -513,6 +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;
@@ -544,11 +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;
@@ -891,6 +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;
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index b8aae31ffda3..9e5ff58edaca 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 "12.4.0.0"
+#define LPFC_DRIVER_VERSION "12.6.0.2"
#define LPFC_DRIVER_NAME "lpfc"
/* Used for SLI 2/3 */
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.