drm/amdgpu: Drop hive->in_reset

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

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://www.spinics.net/lists/amd-gfx/msg74115.html
This commit is contained in:
Andrey Grodzovsky 2021-12-15 16:55:25 -05:00
parent 02599bc7f7
commit 681260df4d
3 changed files with 1 additions and 20 deletions

View File

@ -5067,26 +5067,10 @@ 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.
*/
if (!amdgpu_sriov_vf(adev))
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;
@ -5282,7 +5266,6 @@ skip_sched_resume:
skip_recovery:
if (hive) {
atomic_set(&hive->in_reset, 0);
mutex_unlock(&hive->hive_lock);
amdgpu_put_xgmi_hive(hive);
}

View File

@ -410,7 +410,6 @@ 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;

View File

@ -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;