Merge tag 'amd-drm-next-6.2-2022-11-18' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.2-2022-11-18:

amdgpu:
- SR-IOV fixes
- Clean up DC checks
- DCN 3.2.x fixes
- DCN 3.1.x fixes
- Don't enable degamma on asics which don't support it
- IP discovery fixes
- BACO fixes
- Fix vbios allocation handling when vkms is enabled
- Drop buggy tdr advanced mode GPU reset handling
- Fix the build when DCN is not set in kconfig
- MST DSC fixes
- Userptr fixes
- FRU and RAS EEPROM fixes
- VCN 4.x RAS support
- Aldrebaran CU occupancy reporting fix
- PSP ring cleanup

amdkfd:
- Memory limit fix
- Enable cooperative launch on gfx 10.3

amd-drm-next-6.2-2022-11-11:

amdgpu:
- SMU 13.x updates
- GPUVM TLB race fix
- DCN 3.1.4 updates
- DCN 3.2.x updates
- PSR fixes
- Kerneldoc fix
- Vega10 fan fix
- GPUVM locking fixes in error pathes
- BACO fix for Beige Goby
- EEPROM I2C address cleanup
- GFXOFF fix
- Fix DC memory leak in error pathes
- Flexible array updates
- Mtype fix for GPUVM PTEs
- Move Kconfig into amdgpu directory
- SR-IOV updates
- Fix possible memory leak in CS IOCTL error path

amdkfd:
- Fix possible memory overrun
- CRIU fixes

radeon:
- ACPI ref count fix
- HDA audio notifier support
- Move Kconfig into radeon directory

UAPI:
- Add new GEM_CREATE flags to help to transition more KFD functionality to the DRM UAPI.
  These are used internally in the driver to align location based memory coherency
  requirements from memory allocated in the KFD with how we manage GPUVM PTEs.  They
  are currently blocked in the GEM_CREATE IOCTL as we don't have a user right now.
  They are just used internally in the kernel driver for now for existing KFD memory
  allocations. So a change to the UAPI header, but no functional change in the UAPI.

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221118170807.6505-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 9 insertions, 49 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 6ce04c2e90c0..31f3a1267be4 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -417,27 +417,6 @@ static void drm_sched_job_timedout(struct work_struct *work)
 	}
 }
 
- /**
-  * drm_sched_increase_karma - Update sched_entity guilty flag
-  *
-  * @bad: The job guilty of time out
-  *
-  * Increment on every hang caused by the 'bad' job. If this exceeds the hang
-  * limit of the scheduler then the respective sched entity is marked guilty and
-  * jobs from it will not be scheduled further
-  */
-void drm_sched_increase_karma(struct drm_sched_job *bad)
-{
-	drm_sched_increase_karma_ext(bad, 1);
-}
-EXPORT_SYMBOL(drm_sched_increase_karma);
-
-void drm_sched_reset_karma(struct drm_sched_job *bad)
-{
-	drm_sched_increase_karma_ext(bad, 0);
-}
-EXPORT_SYMBOL(drm_sched_reset_karma);
-
 /**
  * drm_sched_stop - stop the scheduler
  *
@@ -579,31 +558,14 @@ EXPORT_SYMBOL(drm_sched_start);
  */
 void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 {
-	drm_sched_resubmit_jobs_ext(sched, INT_MAX);
-}
-EXPORT_SYMBOL(drm_sched_resubmit_jobs);
-
-/**
- * drm_sched_resubmit_jobs_ext - helper to relunch certain number of jobs from mirror ring list
- *
- * @sched: scheduler instance
- * @max: job numbers to relaunch
- *
- */
-void drm_sched_resubmit_jobs_ext(struct drm_gpu_scheduler *sched, int max)
-{
 	struct drm_sched_job *s_job, *tmp;
 	uint64_t guilty_context;
 	bool found_guilty = false;
 	struct dma_fence *fence;
-	int i = 0;
 
 	list_for_each_entry_safe(s_job, tmp, &sched->pending_list, list) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
 
-		if (i >= max)
-			break;
-
 		if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) {
 			found_guilty = true;
 			guilty_context = s_job->s_fence->scheduled.context;
@@ -613,7 +575,6 @@ void drm_sched_resubmit_jobs_ext(struct drm_gpu_scheduler *sched, int max)
 			dma_fence_set_error(&s_fence->finished, -ECANCELED);
 
 		fence = sched->ops->run_job(s_job);
-		i++;
 
 		if (IS_ERR_OR_NULL(fence)) {
 			if (IS_ERR(fence))
@@ -629,7 +590,7 @@ void drm_sched_resubmit_jobs_ext(struct drm_gpu_scheduler *sched, int max)
 		}
 	}
 }
-EXPORT_SYMBOL(drm_sched_resubmit_jobs_ext);
+EXPORT_SYMBOL(drm_sched_resubmit_jobs);
 
 /**
  * drm_sched_job_init - init a scheduler job
@@ -1165,13 +1126,15 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 EXPORT_SYMBOL(drm_sched_fini);
 
 /**
- * drm_sched_increase_karma_ext - Update sched_entity guilty flag
+ * drm_sched_increase_karma - Update sched_entity guilty flag
  *
  * @bad: The job guilty of time out
- * @type: type for increase/reset karma
  *
+ * Increment on every hang caused by the 'bad' job. If this exceeds the hang
+ * limit of the scheduler then the respective sched entity is marked guilty and
+ * jobs from it will not be scheduled further
  */
-void drm_sched_increase_karma_ext(struct drm_sched_job *bad, int type)
+void drm_sched_increase_karma(struct drm_sched_job *bad)
 {
 	int i;
 	struct drm_sched_entity *tmp;
@@ -1183,10 +1146,7 @@ void drm_sched_increase_karma_ext(struct drm_sched_job *bad, int type)
 	 * corrupt but keep in mind that kernel jobs always considered good.
 	 */
 	if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
-		if (type == 0)
-			atomic_set(&bad->karma, 0);
-		else if (type == 1)
-			atomic_inc(&bad->karma);
+		atomic_inc(&bad->karma);
 
 		for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL;
 		     i++) {
@@ -1197,7 +1157,7 @@ void drm_sched_increase_karma_ext(struct drm_sched_job *bad, int type)
 				if (bad->s_fence->scheduled.context ==
 				    entity->fence_context) {
 					if (entity->guilty)
-						atomic_set(entity->guilty, type);
+						atomic_set(entity->guilty, 1);
 					break;
 				}
 			}
@@ -1207,4 +1167,4 @@ void drm_sched_increase_karma_ext(struct drm_sched_job *bad, int type)
 		}
 	}
 }
-EXPORT_SYMBOL(drm_sched_increase_karma_ext);
+EXPORT_SYMBOL(drm_sched_increase_karma);