[PATCH 4/9] drm/amdkfd: Avoid submitting an unnecessary packet to HWS
Oded Gabbay
oded.gabbay at gmail.com
Sun Oct 8 12:13:31 UTC 2017
On Wed, Sep 27, 2017 at 7:09 AM, Felix Kuehling <Felix.Kuehling at amd.com> wrote:
> From: Yong Zhao <yong.zhao at amd.com>
>
> Signed-off-by: Yong Zhao <yong.zhao at amd.com>
> Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com>
> ---
> .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 28 ++++++++++++----------
> 1 file changed, 16 insertions(+), 12 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 dccb493..0f2a756 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
> @@ -44,7 +44,8 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
> struct queue *q,
> struct qcm_process_device *qpd);
>
> -static int execute_queues_cpsch(struct device_queue_manager *dqm);
> +static int execute_queues_cpsch(struct device_queue_manager *dqm,
> + bool static_queues_included);
> static int unmap_queues_cpsch(struct device_queue_manager *dqm,
> enum kfd_unmap_queues_filter filter,
> uint32_t filter_param);
> @@ -729,7 +730,7 @@ static int start_cpsch(struct device_queue_manager *dqm)
> init_interrupts(dqm);
>
> mutex_lock(&dqm->lock);
> - execute_queues_cpsch(dqm);
> + execute_queues_cpsch(dqm, false);
> mutex_unlock(&dqm->lock);
>
> return 0;
> @@ -775,7 +776,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
> list_add(&kq->list, &qpd->priv_queue_list);
> dqm->queue_count++;
> qpd->is_debug = true;
> - execute_queues_cpsch(dqm);
> + execute_queues_cpsch(dqm, false);
> mutex_unlock(&dqm->lock);
>
> return 0;
> @@ -786,12 +787,10 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
> struct qcm_process_device *qpd)
> {
> mutex_lock(&dqm->lock);
> - /* here we actually preempt the DIQ */
> - unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
> list_del(&kq->list);
> dqm->queue_count--;
> qpd->is_debug = false;
> - execute_queues_cpsch(dqm);
> + execute_queues_cpsch(dqm, true);
> /*
> * Unconditionally decrement this counter, regardless of the queue's
> * type.
> @@ -850,7 +849,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
> list_add(&q->list, &qpd->queues_list);
> if (q->properties.is_active) {
> dqm->queue_count++;
> - retval = execute_queues_cpsch(dqm);
> + retval = execute_queues_cpsch(dqm, false);
> }
>
> if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
> @@ -960,14 +959,19 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
> }
>
> /* dqm->lock mutex has to be locked before calling this function */
> -static int execute_queues_cpsch(struct device_queue_manager *dqm)
> +static int execute_queues_cpsch(struct device_queue_manager *dqm,
> + bool static_queues_included)
> {
> int retval;
> + enum kfd_unmap_queues_filter filter;
> +
> + filter = static_queues_included ?
> + KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES :
> + KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES;
>
> - retval = unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES,
> - 0);
> + retval = unmap_queues_cpsch(dqm, filter, 0);
> if (retval) {
> - pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption");
> + pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption\n");
> return retval;
> }
>
> @@ -1013,7 +1017,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
> if (q->properties.is_active)
> dqm->queue_count--;
>
> - execute_queues_cpsch(dqm);
> + execute_queues_cpsch(dqm, false);
>
> mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
>
> --
> 2.7.4
>
The patch is correct, but the API is inconsistent with the new API you
wrote for unmap_queues_cpsch in patch 2, where the filter is passed
explicitly to the function.
I suggest to change the execute_queues_cpsch API to be the same as
unmap_queues_cpsch
Oded
More information about the amd-gfx
mailing list