The previous code of calculating active CP queues is problematic if
some SDMA queues are inactive. Fix that by counting CP queues directly.
Change-Id: I5ffaa75a95cbebc984558199ba2f3db6909c52a9
Signed-off-by: Yong Zhao <Yong.Zhao@xxxxxxx>
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 45 +++++++++++++------
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 1 +
.../gpu/drm/amd/amdkfd/kfd_packet_manager.c | 3 +-
3 files changed, 33 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 973581c2b401..064108cf493b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -132,6 +132,22 @@ void program_sh_mem_settings(struct device_queue_manager *dqm,
qpd->sh_mem_bases);
}
+void increment_queue_count(struct device_queue_manager *dqm,
+ enum kfd_queue_type type)
+{
+ dqm->active_queue_count++;
+ if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ)
+ dqm->active_cp_queue_count++;
+}
+
+void decrement_queue_count(struct device_queue_manager *dqm,
+ enum kfd_queue_type type)
+{
+ dqm->active_queue_count--;
+ if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ)
+ dqm->active_cp_queue_count--;
+}
+
static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
{
struct kfd_dev *dev = qpd->dqm->dev;
@@ -359,7 +375,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
list_add(&q->list, &qpd->queues_list);
qpd->queue_count++;
if (q->properties.is_active)
- dqm->active_queue_count++;
+ increment_queue_count(dqm, q->properties.type);
if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
dqm->sdma_queue_count++;
@@ -494,7 +510,7 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
}
qpd->queue_count--;
if (q->properties.is_active)
- dqm->active_queue_count--;
+ decrement_queue_count(dqm, q->properties.type);
return retval;
}
@@ -567,9 +583,9 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
* uploaded.
*/
if (q->properties.is_active && !prev_active)
- dqm->active_queue_count++;
+ increment_queue_count(dqm, q->properties.type);
else if (!q->properties.is_active && prev_active)
- dqm->active_queue_count--;
+ decrement_queue_count(dqm, q->properties.type);
if (dqm->sched_policy != KFD_SCHED_POLICY_NO_HWS)
retval = map_queues_cpsch(dqm);
@@ -618,7 +634,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type(
q->properties.type)];
q->properties.is_active = false;
- dqm->active_queue_count--;
+ decrement_queue_count(dqm, q->properties.type);
if (WARN_ONCE(!dqm->sched_running, "Evict when stopped\n"))
continue;
@@ -662,7 +678,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
continue;
q->properties.is_active = false;
- dqm->active_queue_count--;
+ decrement_queue_count(dqm, q->properties.type);
}
retval = execute_queues_cpsch(dqm,
qpd->is_debug ?
@@ -731,7 +747,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type(
q->properties.type)];
q->properties.is_active = true;
- dqm->active_queue_count++;
+ increment_queue_count(dqm, q->properties.type);
if (WARN_ONCE(!dqm->sched_running, "Restore when stopped\n"))
continue;
@@ -786,7 +802,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
continue;
q->properties.is_active = true;
- dqm->active_queue_count++;
+ increment_queue_count(dqm, q->properties.type);
}
retval = execute_queues_cpsch(dqm,
KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
@@ -1158,7 +1174,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
dqm->total_queue_count);
list_add(&kq->list, &qpd->priv_queue_list);
- dqm->active_queue_count++;
+ increment_queue_count(dqm, kq->queue->properties.type);
qpd->is_debug = true;
execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
dqm_unlock(dqm);
@@ -1172,7 +1188,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
{
dqm_lock(dqm);
list_del(&kq->list);
- dqm->active_queue_count--;
+ decrement_queue_count(dqm, kq->queue->properties.type);
qpd->is_debug = false;
execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
/*
@@ -1244,7 +1260,8 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
dqm->xgmi_sdma_queue_count++;
if (q->properties.is_active) {
- dqm->active_queue_count++;
+ increment_queue_count(dqm, q->properties.type);
+
retval = execute_queues_cpsch(dqm,
KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
}
@@ -1438,7 +1455,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
list_del(&q->list);
qpd->queue_count--;
if (q->properties.is_active) {
- dqm->active_queue_count--;
+ decrement_queue_count(dqm, q->properties.type);
retval = execute_queues_cpsch(dqm,
KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
if (retval == -ETIME)
@@ -1648,7 +1665,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
/* Clean all kernel queues */
list_for_each_entry_safe(kq, kq_next, &qpd->priv_queue_list, list) {
list_del(&kq->list);
- dqm->active_queue_count--;
+ decrement_queue_count(dqm, kq->queue->properties.type);
qpd->is_debug = false;
dqm->total_queue_count--;
filter = KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES;
@@ -1665,7 +1682,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
}
if (q->properties.is_active)
- dqm->active_queue_count--;
+ decrement_queue_count(dqm, q->properties.type);
dqm->total_queue_count--;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 3f0fb0d28c01..05e0afc04cd9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -181,6 +181,7 @@ struct device_queue_manager {
unsigned int saved_flags;
unsigned int processes_count;
unsigned int active_queue_count;
+ unsigned int active_cp_queue_count;
unsigned int sdma_queue_count;
unsigned int xgmi_sdma_queue_count;
unsigned int total_queue_count;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 377bde0e781c..efdb75e7677b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -48,8 +48,7 @@ static void pm_calc_rlib_size(struct packet_manager *pm,
process_count = pm->dqm->processes_count;
queue_count = pm->dqm->active_queue_count;
- compute_queue_count = queue_count - pm->dqm->sdma_queue_count -
- pm->dqm->xgmi_sdma_queue_count;
+ compute_queue_count = pm->dqm->active_cp_queue_count;
/* check if there is over subscription
* Note: the arbitration between the number of VMIDs and
--
2.17.1
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
