From: David Yat Sin david.yatsin@amd.com
stable inclusion from stable-v5.10.114 commit 18068e0527d4eb92291ddfed183c921bc92f3869 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5IY1V
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
[ Upstream commit 7c6b6e18c890f30965b0589b0a57645e1dbccfde ]
dqm->gws_queue_count and pdd->qpd.mapped_gws_queue need to be updated each time the queue gets evicted.
Fixes: b8020b0304c8 ("drm/amdkfd: Enable over-subscription with >1 GWS queue") Signed-off-by: David Yat Sin david.yatsin@amd.com Reviewed-by: Felix Kuehling Felix.Kuehling@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- .../drm/amd/amdkfd/kfd_device_queue_manager.c | 83 +++++++++---------- 1 file changed, 37 insertions(+), 46 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 2645ebc63a14..195b7e02dc4b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -138,19 +138,33 @@ void program_sh_mem_settings(struct device_queue_manager *dqm, }
static void increment_queue_count(struct device_queue_manager *dqm, - enum kfd_queue_type type) + struct qcm_process_device *qpd, + struct queue *q) { dqm->active_queue_count++; - if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ) + if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || + q->properties.type == KFD_QUEUE_TYPE_DIQ) dqm->active_cp_queue_count++; + + if (q->properties.is_gws) { + dqm->gws_queue_count++; + qpd->mapped_gws_queue = true; + } }
static void decrement_queue_count(struct device_queue_manager *dqm, - enum kfd_queue_type type) + struct qcm_process_device *qpd, + struct queue *q) { dqm->active_queue_count--; - if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ) + if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || + q->properties.type == KFD_QUEUE_TYPE_DIQ) dqm->active_cp_queue_count--; + + if (q->properties.is_gws) { + dqm->gws_queue_count--; + qpd->mapped_gws_queue = false; + } }
static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q) @@ -377,7 +391,7 @@ 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) - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, qpd, q);
/* * Unconditionally increment this counter, regardless of the queue's @@ -502,13 +516,8 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm, deallocate_vmid(dqm, qpd, q); } qpd->queue_count--; - if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } - } + if (q->properties.is_active) + decrement_queue_count(dqm, qpd, q);
return retval; } @@ -598,12 +607,11 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q) * dqm->active_queue_count to determine whether a new runlist must be * uploaded. */ - if (q->properties.is_active && !prev_active) - increment_queue_count(dqm, q->properties.type); - else if (!q->properties.is_active && prev_active) - decrement_queue_count(dqm, q->properties.type); - - if (q->gws && !q->properties.is_gws) { + if (q->properties.is_active && !prev_active) { + increment_queue_count(dqm, &pdd->qpd, q); + } else if (!q->properties.is_active && prev_active) { + decrement_queue_count(dqm, &pdd->qpd, q); + } else if (q->gws && !q->properties.is_gws) { if (q->properties.is_active) { dqm->gws_queue_count++; pdd->qpd.mapped_gws_queue = true; @@ -665,11 +673,7 @@ 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; - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } + decrement_queue_count(dqm, qpd, q);
if (WARN_ONCE(!dqm->sched_running, "Evict when stopped\n")) continue; @@ -713,7 +717,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, continue;
q->properties.is_active = false; - decrement_queue_count(dqm, q->properties.type); + decrement_queue_count(dqm, qpd, q); } pdd->last_evict_timestamp = get_jiffies_64(); retval = execute_queues_cpsch(dqm, @@ -784,11 +788,7 @@ 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; - increment_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count++; - qpd->mapped_gws_queue = true; - } + increment_queue_count(dqm, qpd, q);
if (WARN_ONCE(!dqm->sched_running, "Restore when stopped\n")) continue; @@ -846,7 +846,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, continue;
q->properties.is_active = true; - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, &pdd->qpd, q); } retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); @@ -1247,7 +1247,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm, dqm->total_queue_count);
list_add(&kq->list, &qpd->priv_queue_list); - increment_queue_count(dqm, kq->queue->properties.type); + increment_queue_count(dqm, qpd, kq->queue); qpd->is_debug = true; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); dqm_unlock(dqm); @@ -1261,7 +1261,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm, { dqm_lock(dqm); list_del(&kq->list); - decrement_queue_count(dqm, kq->queue->properties.type); + decrement_queue_count(dqm, qpd, kq->queue); qpd->is_debug = false; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0); /* @@ -1328,7 +1328,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, qpd->queue_count++;
if (q->properties.is_active) { - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, qpd, q);
execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); @@ -1513,15 +1513,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, list_del(&q->list); qpd->queue_count--; if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); + decrement_queue_count(dqm, qpd, q); retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); if (retval == -ETIME) qpd->reset_wavefronts = true; - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } }
/* @@ -1732,7 +1728,7 @@ 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); - decrement_queue_count(dqm, kq->queue->properties.type); + decrement_queue_count(dqm, qpd, kq->queue); qpd->is_debug = false; dqm->total_queue_count--; filter = KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES; @@ -1745,13 +1741,8 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) deallocate_sdma_queue(dqm, q);
- if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } - } + if (q->properties.is_active) + decrement_queue_count(dqm, qpd, q);
dqm->total_queue_count--; }