summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/ehca/ehca_irq.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/hw/ehca/ehca_irq.c')
-rw-r--r--drivers/infiniband/hw/ehca/ehca_irq.c250
1 files changed, 150 insertions, 100 deletions
diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/infiniband/hw/ehca/ehca_irq.c
index 100329ba3343..a925ea52443f 100644
--- a/drivers/infiniband/hw/ehca/ehca_irq.c
+++ b/drivers/infiniband/hw/ehca/ehca_irq.c
@@ -5,6 +5,8 @@
*
* Authors: Heiko J Schick <schickhj@de.ibm.com>
* Khadija Souissi <souissi@de.ibm.com>
+ * Hoang-Nam Nguyen <hnguyen@de.ibm.com>
+ * Joachim Fenkes <fenkes@de.ibm.com>
*
* Copyright (c) 2005 IBM Corporation
*
@@ -47,25 +49,26 @@
#include "hipz_fns.h"
#include "ipz_pt_fn.h"
-#define EQE_COMPLETION_EVENT EHCA_BMASK_IBM(1,1)
-#define EQE_CQ_QP_NUMBER EHCA_BMASK_IBM(8,31)
-#define EQE_EE_IDENTIFIER EHCA_BMASK_IBM(2,7)
-#define EQE_CQ_NUMBER EHCA_BMASK_IBM(8,31)
-#define EQE_QP_NUMBER EHCA_BMASK_IBM(8,31)
-#define EQE_QP_TOKEN EHCA_BMASK_IBM(32,63)
-#define EQE_CQ_TOKEN EHCA_BMASK_IBM(32,63)
+#define EQE_COMPLETION_EVENT EHCA_BMASK_IBM( 1, 1)
+#define EQE_CQ_QP_NUMBER EHCA_BMASK_IBM( 8, 31)
+#define EQE_EE_IDENTIFIER EHCA_BMASK_IBM( 2, 7)
+#define EQE_CQ_NUMBER EHCA_BMASK_IBM( 8, 31)
+#define EQE_QP_NUMBER EHCA_BMASK_IBM( 8, 31)
+#define EQE_QP_TOKEN EHCA_BMASK_IBM(32, 63)
+#define EQE_CQ_TOKEN EHCA_BMASK_IBM(32, 63)
-#define NEQE_COMPLETION_EVENT EHCA_BMASK_IBM(1,1)
-#define NEQE_EVENT_CODE EHCA_BMASK_IBM(2,7)
-#define NEQE_PORT_NUMBER EHCA_BMASK_IBM(8,15)
-#define NEQE_PORT_AVAILABILITY EHCA_BMASK_IBM(16,16)
+#define NEQE_COMPLETION_EVENT EHCA_BMASK_IBM( 1, 1)
+#define NEQE_EVENT_CODE EHCA_BMASK_IBM( 2, 7)
+#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 ERROR_DATA_LENGTH EHCA_BMASK_IBM(52,63)
-#define ERROR_DATA_TYPE EHCA_BMASK_IBM(0,7)
+#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;
+static struct ehca_comp_pool *pool;
#ifdef CONFIG_HOTPLUG_CPU
static struct notifier_block comp_pool_callback_nb;
#endif
@@ -82,8 +85,8 @@ static inline void comp_event_callback(struct ehca_cq *cq)
return;
}
-static void print_error_data(struct ehca_shca * shca, void* data,
- u64* rblock, int length)
+static void print_error_data(struct ehca_shca *shca, void *data,
+ u64 *rblock, int length)
{
u64 type = EHCA_BMASK_GET(ERROR_DATA_TYPE, rblock[2]);
u64 resource = rblock[1];
@@ -91,7 +94,7 @@ static void print_error_data(struct ehca_shca * shca, void* data,
switch (type) {
case 0x1: /* Queue Pair */
{
- struct ehca_qp *qp = (struct ehca_qp*)data;
+ struct ehca_qp *qp = (struct ehca_qp *)data;
/* only print error data if AER is set */
if (rblock[6] == 0)
@@ -104,7 +107,7 @@ static void print_error_data(struct ehca_shca * shca, void* data,
}
case 0x4: /* Completion Queue */
{
- struct ehca_cq *cq = (struct ehca_cq*)data;
+ struct ehca_cq *cq = (struct ehca_cq *)data;
ehca_err(&shca->ib_device,
"CQ 0x%x (resource=%lx) has errors.",
@@ -113,7 +116,7 @@ static void print_error_data(struct ehca_shca * shca, void* data,
}
default:
ehca_err(&shca->ib_device,
- "Unknown errror type: %lx on %s.",
+ "Unknown error type: %lx on %s.",
type, shca->ib_device.name);
break;
}
@@ -172,33 +175,55 @@ error_data1:
}
-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;
- unsigned long flags;
u32 token = EHCA_BMASK_GET(EQE_QP_TOKEN, eqe);
- spin_lock_irqsave(&ehca_qp_idr_lock, flags);
+ read_lock(&ehca_qp_idr_lock);
qp = idr_find(&ehca_qp_idr, token);
- spin_unlock_irqrestore(&ehca_qp_idr_lock, flags);
-
+ 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;
+ dispatch_qp_event(shca, qp, fatal && qp->ext_type == EQPT_SRQ ?
+ IB_EVENT_SRQ_ERR : event_type);
- event.device = &shca->ib_device;
- event.event = event_type;
- event.element.qp = &qp->ib_qp;
-
- 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);
return;
}
@@ -207,18 +232,22 @@ static void cq_event_callback(struct ehca_shca *shca,
u64 eqe)
{
struct ehca_cq *cq;
- unsigned long flags;
u32 token = EHCA_BMASK_GET(EQE_CQ_TOKEN, eqe);
- spin_lock_irqsave(&ehca_cq_idr_lock, flags);
+ read_lock(&ehca_cq_idr_lock);
cq = idr_find(&ehca_cq_idr, token);
- spin_unlock_irqrestore(&ehca_cq_idr_lock, flags);
+ if (cq)
+ atomic_inc(&cq->nr_events);
+ read_unlock(&ehca_cq_idr_lock);
if (!cq)
return;
ehca_error_data(shca, cq, cq->ipz_cq_handle.handle);
+ if (atomic_dec_and_test(&cq->nr_events))
+ wake_up(&cq->wait_completion);
+
return;
}
@@ -228,17 +257,17 @@ static void parse_identifier(struct ehca_shca *shca, u64 eqe)
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 */
@@ -272,6 +301,11 @@ static void parse_identifier(struct ehca_shca *shca, u64 eqe)
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);
@@ -281,30 +315,61 @@ static void parse_identifier(struct ehca_shca *shca, u64 eqe)
return;
}
-static void parse_ec(struct ehca_shca *shca, u64 eqe)
+static void dispatch_port_event(struct ehca_shca *shca, int port_num,
+ enum ib_event_type type, const char *msg)
{
struct ib_event event;
+
+ ehca_info(&shca->ib_device, "port %d %s.", port_num, msg);
+ event.device = &shca->ib_device;
+ event.event = type;
+ event.element.port_num = port_num;
+ ib_dispatch_event(&event);
+}
+
+static void notify_port_conf_change(struct ehca_shca *shca, int port_num)
+{
+ struct ehca_sma_attr new_attr;
+ struct ehca_sma_attr *old_attr = &shca->sport[port_num - 1].saved_attr;
+
+ ehca_query_sma_attr(shca, port_num, &new_attr);
+
+ if (new_attr.sm_sl != old_attr->sm_sl ||
+ new_attr.sm_lid != old_attr->sm_lid)
+ dispatch_port_event(shca, port_num, IB_EVENT_SM_CHANGE,
+ "SM changed");
+
+ if (new_attr.lid != old_attr->lid ||
+ new_attr.lmc != old_attr->lmc)
+ dispatch_port_event(shca, port_num, IB_EVENT_LID_CHANGE,
+ "LID changed");
+
+ if (new_attr.pkey_tbl_len != old_attr->pkey_tbl_len ||
+ memcmp(new_attr.pkeys, old_attr->pkeys,
+ sizeof(u16) * new_attr.pkey_tbl_len))
+ dispatch_port_event(shca, port_num, IB_EVENT_PKEY_CHANGE,
+ "P_Key changed");
+
+ *old_attr = new_attr;
+}
+
+static void parse_ec(struct ehca_shca *shca, u64 eqe)
+{
u8 ec = EHCA_BMASK_GET(NEQE_EVENT_CODE, eqe);
u8 port = EHCA_BMASK_GET(NEQE_PORT_NUMBER, eqe);
switch (ec) {
case 0x30: /* port availability change */
if (EHCA_BMASK_GET(NEQE_PORT_AVAILABILITY, eqe)) {
- ehca_info(&shca->ib_device,
- "port %x is active.", port);
- event.device = &shca->ib_device;
- event.event = IB_EVENT_PORT_ACTIVE;
- event.element.port_num = port;
shca->sport[port - 1].port_state = IB_PORT_ACTIVE;
- ib_dispatch_event(&event);
+ dispatch_port_event(shca, port, IB_EVENT_PORT_ACTIVE,
+ "is active");
+ ehca_query_sma_attr(shca, port,
+ &shca->sport[port - 1].saved_attr);
} else {
- ehca_info(&shca->ib_device,
- "port %x is inactive.", port);
- event.device = &shca->ib_device;
- event.event = IB_EVENT_PORT_ERR;
- event.element.port_num = port;
shca->sport[port - 1].port_state = IB_PORT_DOWN;
- ib_dispatch_event(&event);
+ dispatch_port_event(shca, port, IB_EVENT_PORT_ERR,
+ "is inactive");
}
break;
case 0x31:
@@ -312,24 +377,19 @@ static void parse_ec(struct ehca_shca *shca, u64 eqe)
* disruptive change is caused by
* LID, PKEY or SM change
*/
- ehca_warn(&shca->ib_device,
- "disruptive port %x configuration change", port);
-
- ehca_info(&shca->ib_device,
- "port %x is inactive.", port);
- event.device = &shca->ib_device;
- event.event = IB_EVENT_PORT_ERR;
- event.element.port_num = port;
- shca->sport[port - 1].port_state = IB_PORT_DOWN;
- ib_dispatch_event(&event);
-
- ehca_info(&shca->ib_device,
- "port %x is active.", port);
- event.device = &shca->ib_device;
- event.event = IB_EVENT_PORT_ACTIVE;
- event.element.port_num = port;
- shca->sport[port - 1].port_state = IB_PORT_ACTIVE;
- ib_dispatch_event(&event);
+ if (EHCA_BMASK_GET(NEQE_DISRUPTIVE, eqe)) {
+ ehca_warn(&shca->ib_device, "disruptive port "
+ "%d configuration change", port);
+
+ shca->sport[port - 1].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;
+ dispatch_port_event(shca, port, IB_EVENT_PORT_ACTIVE,
+ "is active");
+ } else
+ notify_port_conf_change(shca, port);
break;
case 0x32: /* adapter malfunction */
ehca_err(&shca->ib_device, "Adapter malfunction.");
@@ -404,7 +464,6 @@ static inline void process_eqe(struct ehca_shca *shca, struct ehca_eqe *eqe)
{
u64 eqe_value;
u32 token;
- unsigned long flags;
struct ehca_cq *cq;
eqe_value = eqe->entry;
@@ -412,27 +471,24 @@ static inline void process_eqe(struct ehca_shca *shca, struct ehca_eqe *eqe)
if (EHCA_BMASK_GET(EQE_COMPLETION_EVENT, eqe_value)) {
ehca_dbg(&shca->ib_device, "Got completion event");
token = EHCA_BMASK_GET(EQE_CQ_TOKEN, eqe_value);
- spin_lock_irqsave(&ehca_cq_idr_lock, flags);
+ read_lock(&ehca_cq_idr_lock);
cq = idr_find(&ehca_cq_idr, token);
+ if (cq)
+ atomic_inc(&cq->nr_events);
+ read_unlock(&ehca_cq_idr_lock);
if (cq == NULL) {
- spin_unlock_irqrestore(&ehca_cq_idr_lock, flags);
ehca_err(&shca->ib_device,
"Invalid eqe for non-existing cq token=%x",
token);
return;
}
reset_eq_pending(cq);
- cq->nr_events++;
- spin_unlock_irqrestore(&ehca_cq_idr_lock, flags);
if (ehca_scaling_code)
queue_comp_task(cq);
else {
comp_event_callback(cq);
- spin_lock_irqsave(&ehca_cq_idr_lock, flags);
- cq->nr_events--;
- if (!cq->nr_events)
+ if (atomic_dec_and_test(&cq->nr_events))
wake_up(&cq->wait_completion);
- spin_unlock_irqrestore(&ehca_cq_idr_lock, flags);
}
} else {
ehca_dbg(&shca->ib_device, "Got non completion event");
@@ -476,17 +532,17 @@ void ehca_process_eq(struct ehca_shca *shca, int is_irq)
eqe_value = eqe_cache[eqe_cnt].eqe->entry;
if (EHCA_BMASK_GET(EQE_COMPLETION_EVENT, eqe_value)) {
token = EHCA_BMASK_GET(EQE_CQ_TOKEN, eqe_value);
- spin_lock(&ehca_cq_idr_lock);
+ read_lock(&ehca_cq_idr_lock);
eqe_cache[eqe_cnt].cq = idr_find(&ehca_cq_idr, token);
+ if (eqe_cache[eqe_cnt].cq)
+ atomic_inc(&eqe_cache[eqe_cnt].cq->nr_events);
+ read_unlock(&ehca_cq_idr_lock);
if (!eqe_cache[eqe_cnt].cq) {
- spin_unlock(&ehca_cq_idr_lock);
ehca_err(&shca->ib_device,
"Invalid eqe for non-existing cq "
"token=%x", token);
continue;
}
- eqe_cache[eqe_cnt].cq->nr_events++;
- spin_unlock(&ehca_cq_idr_lock);
} else
eqe_cache[eqe_cnt].cq = NULL;
eqe_cnt++;
@@ -517,11 +573,8 @@ void ehca_process_eq(struct ehca_shca *shca, int is_irq)
else {
struct ehca_cq *cq = eq->eqe_cache[i].cq;
comp_event_callback(cq);
- spin_lock(&ehca_cq_idr_lock);
- cq->nr_events--;
- if (!cq->nr_events)
+ if (atomic_dec_and_test(&cq->nr_events))
wake_up(&cq->wait_completion);
- spin_unlock(&ehca_cq_idr_lock);
}
} else {
ehca_dbg(&shca->ib_device, "Got non completion event");
@@ -547,7 +600,7 @@ void ehca_tasklet_eq(unsigned long data)
ehca_process_eq((struct ehca_shca*)data, 1);
}
-static inline int find_next_online_cpu(struct ehca_comp_pool* pool)
+static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
{
int cpu;
unsigned long flags;
@@ -611,7 +664,7 @@ static void queue_comp_task(struct ehca_cq *__cq)
__queue_comp_task(__cq, cct);
}
-static void run_comp_task(struct ehca_cpu_comp_task* cct)
+static void run_comp_task(struct ehca_cpu_comp_task *cct)
{
struct ehca_cq *cq;
unsigned long flags;
@@ -621,13 +674,10 @@ static void run_comp_task(struct ehca_cpu_comp_task* cct)
while (!list_empty(&cct->cq_list)) {
cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
spin_unlock_irqrestore(&cct->task_lock, flags);
- comp_event_callback(cq);
- spin_lock_irqsave(&ehca_cq_idr_lock, flags);
- cq->nr_events--;
- if (!cq->nr_events)
+ comp_event_callback(cq);
+ if (atomic_dec_and_test(&cq->nr_events))
wake_up(&cq->wait_completion);
- spin_unlock_irqrestore(&ehca_cq_idr_lock, flags);
spin_lock_irqsave(&cct->task_lock, flags);
spin_lock(&cq->task_lock);
@@ -644,12 +694,12 @@ static void run_comp_task(struct ehca_cpu_comp_task* cct)
static int comp_task(void *__cct)
{
- struct ehca_cpu_comp_task* cct = __cct;
+ struct ehca_cpu_comp_task *cct = __cct;
int cql_empty;
DECLARE_WAITQUEUE(wait, current);
set_current_state(TASK_INTERRUPTIBLE);
- while(!kthread_should_stop()) {
+ while (!kthread_should_stop()) {
add_wait_queue(&cct->wait_queue, &wait);
spin_lock_irq(&cct->task_lock);
@@ -723,7 +773,7 @@ static void take_over_work(struct ehca_comp_pool *pool,
list_splice_init(&cct->cq_list, &list);
- while(!list_empty(&list)) {
+ while (!list_empty(&list)) {
cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
list_del(&cq->entry);
@@ -746,7 +796,7 @@ static int comp_pool_callback(struct notifier_block *nfb,
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
ehca_gen_dbg("CPU: %x (CPU_PREPARE)", cpu);
- if(!create_comp_task(pool, cpu)) {
+ if (!create_comp_task(pool, cpu)) {
ehca_gen_err("Can't create comp_task for cpu: %x", cpu);
return NOTIFY_BAD;
}
@@ -816,7 +866,7 @@ 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;
+ comp_pool_callback_nb.priority = 0;
register_cpu_notifier(&comp_pool_callback_nb);
#endif
generated by cgit v1.2.3 (git 2.0.4) at 2024-05-23 15:28:42 +0000