[RFC 5/6] drm/amdgpu: Drop hive->in_reset

Andrey Grodzovsky andrey.grodzovsky at amd.com
Fri Dec 17 22:27:44 UTC 2021


Since we serialize all resets no need to protect from concurrent
resets.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 19 +------------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c   |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h   |  1 -
 3 files changed, 1 insertion(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 55cd67b9ede2..d2701e4d0622 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5013,25 +5013,9 @@ int amdgpu_device_gpu_recover_imp(struct amdgpu_device *adev,
 	dev_info(adev->dev, "GPU %s begin!\n",
 		need_emergency_restart ? "jobs stop":"reset");
 
-	/*
-	 * Here we trylock to avoid chain of resets executing from
-	 * either trigger by jobs on different adevs in XGMI hive or jobs on
-	 * different schedulers for same device while this TO handler is running.
-	 * We always reset all schedulers for device and all devices for XGMI
-	 * hive so that should take care of them too.
-	 */
 	hive = amdgpu_get_xgmi_hive(adev);
-	if (hive) {
-		if (atomic_cmpxchg(&hive->in_reset, 0, 1) != 0) {
-			DRM_INFO("Bailing on TDR for s_job:%llx, hive: %llx as another already in progress",
-				job ? job->base.id : -1, hive->hive_id);
-			amdgpu_put_xgmi_hive(hive);
-			if (job && job->vm)
-				drm_sched_increase_karma(&job->base);
-			return 0;
-		}
+	if (hive)
 		mutex_lock(&hive->hive_lock);
-	}
 
 	reset_context.method = AMD_RESET_METHOD_NONE;
 	reset_context.reset_req_dev = adev;
@@ -5226,7 +5210,6 @@ int amdgpu_device_gpu_recover_imp(struct amdgpu_device *adev,
 
 skip_recovery:
 	if (hive) {
-		atomic_set(&hive->in_reset, 0);
 		mutex_unlock(&hive->hive_lock);
 		amdgpu_put_xgmi_hive(hive);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 8b116f398101..0d54bef5c494 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -403,7 +403,6 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
 	INIT_LIST_HEAD(&hive->device_list);
 	INIT_LIST_HEAD(&hive->node);
 	mutex_init(&hive->hive_lock);
-	atomic_set(&hive->in_reset, 0);
 	atomic_set(&hive->number_devices, 0);
 	task_barrier_init(&hive->tb);
 	hive->pstate = AMDGPU_XGMI_PSTATE_UNKNOWN;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index 6121aaa292cb..2f2ce53645a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -33,7 +33,6 @@ struct amdgpu_hive_info {
 	struct list_head node;
 	atomic_t number_devices;
 	struct mutex hive_lock;
-	atomic_t in_reset;
 	int hi_req_count;
 	struct amdgpu_device *hi_req_gpu;
 	struct task_barrier tb;
-- 
2.25.1



More information about the amd-gfx mailing list