drm/amdgpu: Introduce reset domain

Defined a reset_domain struct such that
all the entities that go through reset
together will be serialized one against
another. Do it for both single device and
XGMI hive cases.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Suggested-by: Christian König <ckoenig.leichtzumerken@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://www.spinics.net/lists/amd-gfx/msg74111.html

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -813,6 +813,10 @@ struct amd_powerplay {
 #define AMDGPU_RESET_MAGIC_NUM 64
 #define AMDGPU_MAX_DF_PERFMONS 4
 #define AMDGPU_PRODUCT_NAME_LEN 64
+struct amdgpu_reset_domain {
+	struct workqueue_struct *wq;
+};
+
 struct amdgpu_device {
 	struct device			*dev;
 	struct pci_dev			*pdev;
@@ -1100,6 +1104,7 @@ struct amdgpu_device {
 	uint32_t                        ip_versions[MAX_HWIP][HWIP_MAX_INSTANCE];
 
 	bool				ram_is_direct_mapped;
+	struct amdgpu_reset_domain	reset_domain;
 };
 
 static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -2398,9 +2398,27 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (r)
 		goto init_failed;
 
-	if (adev->gmc.xgmi.num_physical_nodes > 1)
+	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+		struct amdgpu_hive_info *hive;
+
 		amdgpu_xgmi_add_device(adev);
 
+		hive = amdgpu_get_xgmi_hive(adev);
+		if (!hive || !hive->reset_domain.wq) {
+			DRM_ERROR("Failed to obtain reset domain info for XGMI hive:%llx", hive->hive_id);
+			r = -EINVAL;
+			goto init_failed;
+		}
+
+		adev->reset_domain.wq = hive->reset_domain.wq;
+	} else {
+		adev->reset_domain.wq = alloc_ordered_workqueue("amdgpu-reset-dev", 0);
+		if (!adev->reset_domain.wq) {
+			r = -ENOMEM;
+			goto init_failed;
+		}
+	}
+
 	/* Don't init kfd if whole hive need to be reset during init */
 	if (!adev->gmc.xgmi.pending_reset)
 		amdgpu_amdkfd_device_init(adev);

drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c

@@ -398,6 +398,14 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
 		goto pro_end;
 	}
 
+	hive->reset_domain.wq = alloc_ordered_workqueue("amdgpu-reset-hive", 0);
+	if (!hive->reset_domain.wq) {
+		dev_err(adev->dev, "XGMI: failed allocating wq for reset domain!\n");
+		kfree(hive);
+		hive = NULL;
+		goto pro_end;
+	}
+
 	hive->hive_id = adev->gmc.xgmi.hive_id;
 	INIT_LIST_HEAD(&hive->device_list);
 	INIT_LIST_HEAD(&hive->node);
@@ -407,6 +415,7 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
 	task_barrier_init(&hive->tb);
 	hive->pstate = AMDGPU_XGMI_PSTATE_UNKNOWN;
 	hive->hi_req_gpu = NULL;
+
 	/*
 	 * hive pstate on boot is high in vega20 so we have to go to low
 	 * pstate on after boot.

drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h

@@ -42,6 +42,8 @@ struct amdgpu_hive_info {
 		AMDGPU_XGMI_PSTATE_MAX_VEGA20,
 		AMDGPU_XGMI_PSTATE_UNKNOWN
 	} pstate;
+
+	struct amdgpu_reset_domain reset_domain;
 };
 
 struct amdgpu_pcs_ras_field {