1 files changed, 69 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index b24f78b74b41..668c20902358 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -45,6 +45,7 @@
 #include "amdgpu_amdkfd.h"
 
 #include "amdgpu_ras.h"
+#include "amdgpu_xgmi.h"
 
 /*
  * KMS wrapper.
@@ -168,8 +169,13 @@ int amdgpu_tmz = -1; /* auto */
 int amdgpu_reset_method = -1; /* auto */
 int amdgpu_num_kcq = -1;
 
+static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
+
 struct amdgpu_mgpu_info mgpu_info = {
 	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
+	.delayed_reset_work = __DELAYED_WORK_INITIALIZER(
+			mgpu_info.delayed_reset_work,
+			amdgpu_drv_delayed_reset_work_handler, 0),
 };
 int amdgpu_ras_enable = -1;
 uint amdgpu_ras_mask = 0xffffffff;
@@ -1321,6 +1327,69 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)
 	adev->mp1_state = PP_MP1_STATE_NONE;
 }
 
+/**
+ * amdgpu_drv_delayed_reset_work_handler - work handler for reset
+ *
+ * @work: work_struct.
+ */
+static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work)
+{
+	struct list_head device_list;
+	struct amdgpu_device *adev;
+	int i, r;
+	bool need_full_reset = true;
+
+	mutex_lock(&mgpu_info.mutex);
+	if (mgpu_info.pending_reset == true) {
+		mutex_unlock(&mgpu_info.mutex);
+		return;
+	}
+	mgpu_info.pending_reset = true;
+	mutex_unlock(&mgpu_info.mutex);
+
+	for (i = 0; i < mgpu_info.num_dgpu; i++) {
+		adev = mgpu_info.gpu_ins[i].adev;
+		r = amdgpu_device_pre_asic_reset(adev, NULL, &need_full_reset);
+		if (r) {
+			dev_err(adev->dev, "GPU pre asic reset failed with err, %d for drm dev, %s ",
+				r, adev_to_drm(adev)->unique);
+		}
+		if (!queue_work(system_unbound_wq, &adev->xgmi_reset_work))
+			r = -EALREADY;
+	}
+	for (i = 0; i < mgpu_info.num_dgpu; i++) {
+		adev = mgpu_info.gpu_ins[i].adev;
+		adev->gmc.xgmi.pending_reset = false;
+		flush_work(&adev->xgmi_reset_work);
+	}
+
+	/* reset function will rebuild the xgmi hive info , clear it now */
+	for (i = 0; i < mgpu_info.num_dgpu; i++)
+		amdgpu_xgmi_remove_device(mgpu_info.gpu_ins[i].adev);
+
+	INIT_LIST_HEAD(&device_list);
+
+	for (i = 0; i < mgpu_info.num_dgpu; i++)
+		list_add_tail(&mgpu_info.gpu_ins[i].adev->reset_list, &device_list);
+
+	/* unregister the GPU first, reset function will add them back */
+	list_for_each_entry(adev, &device_list, reset_list)
+		amdgpu_unregister_gpu_instance(adev);
+
+	r = amdgpu_do_asic_reset(NULL, &device_list, &need_full_reset, true);
+	if (r) {
+		DRM_ERROR("reinit gpus failure");
+		return;
+	}
+	for (i = 0; i < mgpu_info.num_dgpu; i++) {
+		adev = mgpu_info.gpu_ins[i].adev;
+		if (!adev->kfd.init_complete)
+			amdgpu_amdkfd_device_init(adev);
+		amdgpu_ttm_set_buffer_funcs_status(adev, true);
+	}
+	return;
+}
+
 static int amdgpu_pmops_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);