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

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 15e8fde3ac2d022652855cc30ac547c5c44ffc1a..7e92f2432087f8fec68ff06e938184b6df8a9b64 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -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);
        }

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index d406897346d67ad37698d4bbdffd0d51177440b6..89b682afe821715d8fdb038ff9cfece945bbd944 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -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;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index 6121aaa292cbf931386f20c15435d48a566321d8..2f2ce53645a50443722091be7f69dfb69d54bcb0 100644 (file)
--- 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;