From 4afcb30383bef8bf972c6aae47995ef314e5f8a1 Mon Sep 17 00:00:00 2001 From: Jammy Zhou Date: Thu, 30 Jul 2015 16:44:05 +0800 Subject: [PATCH] drm/amdgpu: add amdgpu.sched_hw_submission option This option can be used to specify the max number of submissions in the active HW queue. The default value is 2 now. Signed-off-by: Jammy Zhou Reviewed-by: Chunming Zhou --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 ++++ drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 3 ++- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 5 +++-- drivers/gpu/drm/amd/scheduler/gpu_scheduler.h | 5 ++--- 5 files changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 4de114711951..6e1fea473a66 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -81,6 +81,7 @@ extern int amdgpu_vm_size; extern int amdgpu_vm_block_size; extern int amdgpu_enable_scheduler; extern int amdgpu_sched_jobs; +extern int amdgpu_sched_hw_submission; #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS 3000 #define AMDGPU_MAX_USEC_TIMEOUT 100000 /* 100 ms */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 319de441e907..8bb5610c2d25 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -77,6 +77,7 @@ int amdgpu_vm_block_size = -1; int amdgpu_exp_hw_support = 0; int amdgpu_enable_scheduler = 0; int amdgpu_sched_jobs = 16; +int amdgpu_sched_hw_submission = 2; MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes"); module_param_named(vramlimit, amdgpu_vram_limit, int, 0600); @@ -147,6 +148,9 @@ module_param_named(enable_scheduler, amdgpu_enable_scheduler, int, 0444); MODULE_PARM_DESC(sched_jobs, "the max number of jobs supported in the sw queue (default 16)"); module_param_named(sched_jobs, amdgpu_sched_jobs, int, 0444); +MODULE_PARM_DESC(sched_hw_submission, "the max number of HW submissions (default 2)"); +module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444); + static struct pci_device_id pciidlist[] = { #ifdef CONFIG_DRM_AMDGPU_CIK /* Kaveri */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index b0e15b574606..67d9277d6168 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -926,7 +926,8 @@ void amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring) if (amdgpu_enable_scheduler) { ring->scheduler = amd_sched_create((void *)ring->adev, &amdgpu_sched_ops, - ring->idx, 5, 0); + ring->idx, 5, 0, + amdgpu_sched_hw_submission); if (!ring->scheduler) DRM_ERROR("Failed to create scheduler on ring %d.\n", ring->idx); diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index 87993e06ba37..042da7ddf8db 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -468,7 +468,8 @@ struct amd_gpu_scheduler *amd_sched_create(void *device, struct amd_sched_backend_ops *ops, unsigned ring, unsigned granularity, - unsigned preemption) + unsigned preemption, + unsigned hw_submission) { struct amd_gpu_scheduler *sched; char name[20] = "gpu_sched[0]"; @@ -495,7 +496,7 @@ struct amd_gpu_scheduler *amd_sched_create(void *device, init_waitqueue_head(&sched->wait_queue); if(kfifo_alloc(&sched->active_hw_rq, - AMD_MAX_ACTIVE_HW_SUBMISSION * sizeof(void *), + hw_submission * sizeof(void *), GFP_KERNEL)) { kfree(sched); return NULL; diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h index 52577a88b054..7f6bc26d2d29 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h @@ -26,8 +26,6 @@ #include -#define AMD_MAX_ACTIVE_HW_SUBMISSION 2 - #define AMD_KERNEL_CONTEXT_ID 0 #define AMD_KERNEL_PROCESS_ID 0 @@ -127,7 +125,8 @@ struct amd_gpu_scheduler *amd_sched_create(void *device, struct amd_sched_backend_ops *ops, uint32_t ring, uint32_t granularity, - uint32_t preemption); + uint32_t preemption, + uint32_t hw_submission); int amd_sched_destroy(struct amd_gpu_scheduler *sched);