bybrooklyn/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-04-18 14:53:58 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: rework context priority handling

Browse Source 
To get a hardware queue priority for a context, we are currently
mapping AMDGPU_CTX_PRIORITY_* to DRM_SCHED_PRIORITY_* and then
to hardware queue priority, which is not the right way to do that
as DRM_SCHED_PRIORITY_* is software scheduler's priority and it is
independent from a hardware queue priority.

Use userspace provided context priority, AMDGPU_CTX_PRIORITY_* to
map a context to proper hardware queue priority.

Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Nirmoy Das
2021-08-24 20:39:18 +02:00
committed by Alex Deucher
parent 391ac13539
commit 84d588c3de
3 changed files with 106 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
View File

@@ -47,8 +47,8 @@ struct amdgpu_ctx {
spinlock_t ring_lock;
struct amdgpu_ctx_entity *entities[AMDGPU_HW_IP_NUM][AMDGPU_MAX_ENTITY_NUM];
bool preamble_presented;
enum drm_sched_priority init_priority;
enum drm_sched_priority override_priority;
int32_t init_priority;
int32_t override_priority;
struct mutex lock;
atomic_t guilty;
unsigned long ras_counter_ce;
@@ -75,8 +75,8 @@ void amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx,
struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,
struct drm_sched_entity *entity,
uint64_t seq);
void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx,
enum drm_sched_priority priority);
bool amdgpu_ctx_priority_is_valid(int32_t ctx_prio);
void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx, int32_t ctx_prio);
int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
struct drm_file *filp);