#define NEQE_PORT_NUMBER EHCA_BMASK_IBM( 8, 15)
#define NEQE_PORT_AVAILABILITY EHCA_BMASK_IBM(16, 16)
#define NEQE_DISRUPTIVE EHCA_BMASK_IBM(16, 16)
+#define NEQE_SPECIFIC_EVENT EHCA_BMASK_IBM(16, 23)
#define ERROR_DATA_LENGTH EHCA_BMASK_IBM(52, 63)
#define ERROR_DATA_TYPE EHCA_BMASK_IBM( 0, 7)
static void queue_comp_task(struct ehca_cq *__cq);
static struct ehca_comp_pool *pool;
-#ifdef CONFIG_HOTPLUG_CPU
-static struct notifier_block comp_pool_callback_nb;
-#endif
static inline void comp_event_callback(struct ehca_cq *cq)
{
}
default:
ehca_err(&shca->ib_device,
- "Unknown errror type: %lx on %s.",
+ "Unknown error type: %lx on %s.",
type, shca->ib_device.name);
break;
}
}
-static void qp_event_callback(struct ehca_shca *shca,
- u64 eqe,
+static void dispatch_qp_event(struct ehca_shca *shca, struct ehca_qp *qp,
enum ib_event_type event_type)
{
struct ib_event event;
+
+ event.device = &shca->ib_device;
+ event.event = event_type;
+
+ if (qp->ext_type == EQPT_SRQ) {
+ if (!qp->ib_srq.event_handler)
+ return;
+
+ event.element.srq = &qp->ib_srq;
+ qp->ib_srq.event_handler(&event, qp->ib_srq.srq_context);
+ } else {
+ if (!qp->ib_qp.event_handler)
+ return;
+
+ event.element.qp = &qp->ib_qp;
+ qp->ib_qp.event_handler(&event, qp->ib_qp.qp_context);
+ }
+}
+
+static void qp_event_callback(struct ehca_shca *shca, u64 eqe,
+ enum ib_event_type event_type, int fatal)
+{
struct ehca_qp *qp;
u32 token = EHCA_BMASK_GET(EQE_QP_TOKEN, eqe);
read_lock(&ehca_qp_idr_lock);
qp = idr_find(&ehca_qp_idr, token);
+ if (qp)
+ atomic_inc(&qp->nr_events);
read_unlock(&ehca_qp_idr_lock);
-
if (!qp)
return;
- ehca_error_data(shca, qp, qp->ipz_qp_handle.handle);
+ if (fatal)
+ ehca_error_data(shca, qp, qp->ipz_qp_handle.handle);
- if (!qp->ib_qp.event_handler)
- return;
-
- event.device = &shca->ib_device;
- event.event = event_type;
- event.element.qp = &qp->ib_qp;
+ dispatch_qp_event(shca, qp, fatal && qp->ext_type == EQPT_SRQ ?
+ IB_EVENT_SRQ_ERR : event_type);
- qp->ib_qp.event_handler(&event, qp->ib_qp.qp_context);
+ /*
+ * eHCA only processes one WQE at a time for SRQ base QPs,
+ * so the last WQE has been processed as soon as the QP enters
+ * error state.
+ */
+ if (fatal && qp->ext_type == EQPT_SRQBASE)
+ dispatch_qp_event(shca, qp, IB_EVENT_QP_LAST_WQE_REACHED);
+ if (atomic_dec_and_test(&qp->nr_events))
+ wake_up(&qp->wait_completion);
return;
}
switch (identifier) {
case 0x02: /* path migrated */
- qp_event_callback(shca, eqe, IB_EVENT_PATH_MIG);
+ qp_event_callback(shca, eqe, IB_EVENT_PATH_MIG, 0);
break;
case 0x03: /* communication established */
- qp_event_callback(shca, eqe, IB_EVENT_COMM_EST);
+ qp_event_callback(shca, eqe, IB_EVENT_COMM_EST, 0);
break;
case 0x04: /* send queue drained */
- qp_event_callback(shca, eqe, IB_EVENT_SQ_DRAINED);
+ qp_event_callback(shca, eqe, IB_EVENT_SQ_DRAINED, 0);
break;
case 0x05: /* QP error */
case 0x06: /* QP error */
- qp_event_callback(shca, eqe, IB_EVENT_QP_FATAL);
+ qp_event_callback(shca, eqe, IB_EVENT_QP_FATAL, 1);
break;
case 0x07: /* CQ error */
case 0x08: /* CQ error */
case 0x11: /* unaffiliated access error */
ehca_err(&shca->ib_device, "Unaffiliated access error.");
break;
- case 0x12: /* path migrating error */
- ehca_err(&shca->ib_device, "Path migration error.");
+ case 0x12: /* path migrating */
+ ehca_err(&shca->ib_device, "Path migrating.");
break;
case 0x13: /* interface trace stopped */
ehca_err(&shca->ib_device, "Interface trace stopped.");
break;
case 0x14: /* first error capture info available */
+ ehca_info(&shca->ib_device, "First error capture available");
+ break;
+ case 0x15: /* SRQ limit reached */
+ qp_event_callback(shca, eqe, IB_EVENT_SRQ_LIMIT_REACHED, 0);
+ break;
default:
ehca_err(&shca->ib_device, "Unknown identifier: %x on %s.",
identifier, shca->ib_device.name);
{
u8 ec = EHCA_BMASK_GET(NEQE_EVENT_CODE, eqe);
u8 port = EHCA_BMASK_GET(NEQE_PORT_NUMBER, eqe);
+ u8 spec_event;
+ struct ehca_sport *sport = &shca->sport[port - 1];
+ unsigned long flags;
switch (ec) {
case 0x30: /* port availability change */
if (EHCA_BMASK_GET(NEQE_PORT_AVAILABILITY, eqe)) {
- shca->sport[port - 1].port_state = IB_PORT_ACTIVE;
+ int suppress_event;
+ /* replay modify_qp for sqps */
+ spin_lock_irqsave(&sport->mod_sqp_lock, flags);
+ suppress_event = !sport->ibqp_sqp[IB_QPT_GSI];
+ if (sport->ibqp_sqp[IB_QPT_SMI])
+ ehca_recover_sqp(sport->ibqp_sqp[IB_QPT_SMI]);
+ if (!suppress_event)
+ ehca_recover_sqp(sport->ibqp_sqp[IB_QPT_GSI]);
+ spin_unlock_irqrestore(&sport->mod_sqp_lock, flags);
+
+ /* AQP1 was destroyed, ignore this event */
+ if (suppress_event)
+ break;
+
+ sport->port_state = IB_PORT_ACTIVE;
dispatch_port_event(shca, port, IB_EVENT_PORT_ACTIVE,
"is active");
ehca_query_sma_attr(shca, port,
- &shca->sport[port - 1].saved_attr);
+ &sport->saved_attr);
} else {
- shca->sport[port - 1].port_state = IB_PORT_DOWN;
+ sport->port_state = IB_PORT_DOWN;
dispatch_port_event(shca, port, IB_EVENT_PORT_ERR,
"is inactive");
}
ehca_warn(&shca->ib_device, "disruptive port "
"%d configuration change", port);
- shca->sport[port - 1].port_state = IB_PORT_DOWN;
+ sport->port_state = IB_PORT_DOWN;
dispatch_port_event(shca, port, IB_EVENT_PORT_ERR,
"is inactive");
- shca->sport[port - 1].port_state = IB_PORT_ACTIVE;
+ sport->port_state = IB_PORT_ACTIVE;
dispatch_port_event(shca, port, IB_EVENT_PORT_ACTIVE,
"is active");
+ ehca_query_sma_attr(shca, port,
+ &sport->saved_attr);
} else
notify_port_conf_change(shca, port);
break;
case 0x33: /* trace stopped */
ehca_err(&shca->ib_device, "Traced stopped.");
break;
+ case 0x34: /* util async event */
+ spec_event = EHCA_BMASK_GET(NEQE_SPECIFIC_EVENT, eqe);
+ if (spec_event == 0x80) /* client reregister required */
+ dispatch_port_event(shca, port,
+ IB_EVENT_CLIENT_REREGISTER,
+ "client reregister req.");
+ else
+ ehca_warn(&shca->ib_device, "Unknown util async "
+ "event %x on port %x", spec_event, port);
+ break;
default:
ehca_err(&shca->ib_device, "Unknown event code: %x on %s.",
ec, shca->ib_device.name);
{
struct ehca_eq *eq = &shca->eq;
struct ehca_eqe_cache_entry *eqe_cache = eq->eqe_cache;
- u64 eqe_value;
+ u64 eqe_value, ret;
unsigned long flags;
int eqe_cnt, i;
int eq_empty = 0;
ehca_dbg(&shca->ib_device,
"No eqe found for irq event");
goto unlock_irq_spinlock;
- } else if (!is_irq)
+ } else if (!is_irq) {
+ ret = hipz_h_eoi(eq->ist);
+ if (ret != H_SUCCESS)
+ ehca_err(&shca->ib_device,
+ "bad return code EOI -rc = %ld\n", ret);
ehca_dbg(&shca->ib_device, "deadman found %x eqe", eqe_cnt);
+ }
if (unlikely(eqe_cnt == EHCA_EQE_CACHE_SIZE))
ehca_dbg(&shca->ib_device, "too many eqes for one irq event");
/* enable irq for new packets */
unsigned long flags;
WARN_ON_ONCE(!in_interrupt());
- if (ehca_debug_level)
+ if (ehca_debug_level >= 3)
ehca_dmp(&cpu_online_map, sizeof(cpumask_t), "");
spin_lock_irqsave(&pool->last_cpu_lock, flags);
- cpu = next_cpu(pool->last_cpu, cpu_online_map);
- if (cpu == NR_CPUS)
+ cpu = next_cpu_nr(pool->last_cpu, cpu_online_map);
+ if (cpu >= nr_cpu_ids)
cpu = first_cpu(cpu_online_map);
pool->last_cpu = cpu;
spin_unlock_irqrestore(&pool->last_cpu_lock, flags);
kthread_stop(task);
}
-#ifdef CONFIG_HOTPLUG_CPU
-static void take_over_work(struct ehca_comp_pool *pool,
- int cpu)
+static void __cpuinit take_over_work(struct ehca_comp_pool *pool, int cpu)
{
struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
LIST_HEAD(list);
}
-static int comp_pool_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
+static int __cpuinit comp_pool_callback(struct notifier_block *nfb,
+ unsigned long action,
+ void *hcpu)
{
unsigned int cpu = (unsigned long)hcpu;
struct ehca_cpu_comp_task *cct;
return NOTIFY_OK;
}
-#endif
+
+static struct notifier_block comp_pool_callback_nb __cpuinitdata = {
+ .notifier_call = comp_pool_callback,
+ .priority = 0,
+};
int ehca_create_comp_pool(void)
{
}
}
-#ifdef CONFIG_HOTPLUG_CPU
- comp_pool_callback_nb.notifier_call = comp_pool_callback;
- comp_pool_callback_nb.priority = 0;
- register_cpu_notifier(&comp_pool_callback_nb);
-#endif
+ register_hotcpu_notifier(&comp_pool_callback_nb);
printk(KERN_INFO "eHCA scaling code enabled\n");
if (!ehca_scaling_code)
return;
-#ifdef CONFIG_HOTPLUG_CPU
- unregister_cpu_notifier(&comp_pool_callback_nb);
-#endif
+ unregister_hotcpu_notifier(&comp_pool_callback_nb);
for (i = 0; i < NR_CPUS; i++) {
if (cpu_online(i))