Adjust latencies and timeouts for dequeueing with HWS and consolidate them in one place. Make them longer to allow long running waves to complete without causing a timeout. The timeout is twice as long as the latency plus some buffer to make sure we don't detect a timeout prematurely. Change timeouts for dequeueing HQDs without HWS. KFD_UNMAP_LATENCY is more consistent with what the HWS does for user queues. Signed-off-by: Yong Zhao <yong.zhao at amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com> Reviewed-by: Oded Gabbay <oded.gabbay at gmail.com> --- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h | 4 +++- drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 3 --- 5 files changed, 6 insertions(+), 7 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 87961fe..dd60c6e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -323,7 +323,7 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm, retval = mqd->destroy_mqd(mqd, q->mqd, KFD_PREEMPT_TYPE_WAVEFRONT_RESET, - QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS, + KFD_UNMAP_LATENCY_MS, q->pipe, q->queue); if (retval) 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 faf820a..99e2305 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -29,7 +29,9 @@ #include "kfd_priv.h" #include "kfd_mqd_manager.h" -#define QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS (500) +#define KFD_UNMAP_LATENCY_MS (4000) +#define QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS (2 * KFD_UNMAP_LATENCY_MS + 1000) + #define CIK_VMID_NUM (8) #define KFD_VMID_START_OFFSET (8) #define VMID_PER_DEVICE CIK_VMID_NUM diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c index 0649dd4..04379a6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c @@ -185,7 +185,7 @@ static void uninitialize(struct kernel_queue *kq) kq->mqd->destroy_mqd(kq->mqd, kq->queue->mqd, false, - QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS, + KFD_UNMAP_LATENCY_MS, kq->queue->pipe, kq->queue->queue); else if (kq->queue->properties.type == KFD_QUEUE_TYPE_DIQ) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c index 1d31260..9eda884 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c @@ -376,7 +376,7 @@ int pm_send_set_resources(struct packet_manager *pm, packet->bitfields2.queue_type = queue_type__mes_set_resources__hsa_interface_queue_hiq; packet->bitfields2.vmid_mask = res->vmid_mask; - packet->bitfields2.unmap_latency = KFD_UNMAP_LATENCY; + packet->bitfields2.unmap_latency = KFD_UNMAP_LATENCY_MS / 100; packet->bitfields7.oac_mask = res->oac_mask; packet->bitfields8.gds_heap_base = res->gds_heap_base; packet->bitfields8.gds_heap_size = res->gds_heap_size; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 1c341b3..7adb890 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -673,11 +673,8 @@ int amdkfd_fence_wait_timeout(unsigned int *fence_addr, /* Packet Manager */ -#define KFD_HIQ_TIMEOUT (500) - #define KFD_FENCE_COMPLETED (100) #define KFD_FENCE_INIT (10) -#define KFD_UNMAP_LATENCY (150) struct packet_manager { struct device_queue_manager *dqm; -- 2.7.4