drm/amdgpu: Add gpu_recovery parameter

Add new parameter to control GPU recovery procedure.

v2:
Add auto logic where reset is disabled for bare metal and enabled
for SR-IOV.
Allow forced reset from debugfs.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -126,6 +126,7 @@ extern int amdgpu_param_buf_per_se;
 extern int amdgpu_job_hang_limit;
 extern int amdgpu_lbpw;
 extern int amdgpu_compute_multipipe;
+extern int amdgpu_gpu_recovery;
 
 #ifdef CONFIG_DRM_AMDGPU_SI
 extern int amdgpu_si_support;
@@ -1910,7 +1911,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_psp_check_fw_loading_status(adev, i) (adev)->firmware.funcs->check_fw_loading_status((adev), (i))
 
 /* Common functions */
-int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job* job);
+int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job* job, bool force);
 bool amdgpu_need_backup(struct amdgpu_device *adev);
 void amdgpu_pci_config_reset(struct amdgpu_device *adev);
 bool amdgpu_need_post(struct amdgpu_device *adev);

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

@@ -3009,11 +3009,12 @@ static int amdgpu_reset_sriov(struct amdgpu_device *adev, uint64_t *reset_flags,
  *
  * @adev: amdgpu device pointer
  * @job: which job trigger hang
+ * @force forces reset regardless of amdgpu_gpu_recovery
  *
  * Attempt to reset the GPU if it has hung (all asics).
  * Returns 0 for success or an error on failure.
  */
-int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job)
+int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job, bool force)
 {
 	struct drm_atomic_state *state = NULL;
 	uint64_t reset_flags = 0;
@@ -3024,6 +3025,12 @@ int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job)
 		return 0;
 	}
 
+	if (!force && (amdgpu_gpu_recovery == 0 ||
+			(amdgpu_gpu_recovery == -1  && !amdgpu_sriov_vf(adev)))) {
+		DRM_INFO("GPU recovery disabled.\n");
+		return 0;
+	}
+
 	dev_info(adev->dev, "GPU reset begin!\n");
 
 	mutex_lock(&adev->lock_reset);

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

@@ -128,6 +128,7 @@ int amdgpu_param_buf_per_se = 0;
 int amdgpu_job_hang_limit = 0;
 int amdgpu_lbpw = -1;
 int amdgpu_compute_multipipe = -1;
+int amdgpu_gpu_recovery = -1; /* auto */
 
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -280,6 +281,9 @@ module_param_named(lbpw, amdgpu_lbpw, int, 0444);
 MODULE_PARM_DESC(compute_multipipe, "Force compute queues to be spread across pipes (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444);
 
+MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (1 = enable, 0 = disable, -1 = auto");
+module_param_named(gpu_recovery, amdgpu_gpu_recovery, int, 0444);
+
 #ifdef CONFIG_DRM_AMDGPU_SI
 
 #if defined(CONFIG_DRM_RADEON) || defined(CONFIG_DRM_RADEON_MODULE)

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

@@ -705,7 +705,7 @@ static int amdgpu_debugfs_gpu_recover(struct seq_file *m, void *data)
 	struct amdgpu_device *adev = dev->dev_private;
 
 	seq_printf(m, "gpu recover\n");
-	amdgpu_gpu_recover(adev, NULL);
+	amdgpu_gpu_recover(adev, NULL, true);
 
 	return 0;
 }

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

@@ -88,7 +88,7 @@ static void amdgpu_irq_reset_work_func(struct work_struct *work)
 						  reset_work);
 
 	if (!amdgpu_sriov_vf(adev))
-		amdgpu_gpu_recover(adev, NULL);
+		amdgpu_gpu_recover(adev, NULL, false);
 }
 
 /* Disable *all* interrupts */

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

@@ -37,7 +37,7 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 		  atomic_read(&job->ring->fence_drv.last_seq),
 		  job->ring->fence_drv.sync_seq);
 
-	amdgpu_gpu_recover(job->adev, job);
+	amdgpu_gpu_recover(job->adev, job, false);
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,

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

@@ -253,7 +253,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	}
 
 	/* Trigger recovery due to world switch failure */
-	amdgpu_gpu_recover(adev, NULL);
+	amdgpu_gpu_recover(adev, NULL, false);
 }
 
 static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev,

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

@@ -521,7 +521,7 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work)
 	}
 
 	/* Trigger recovery due to world switch failure */
-	amdgpu_gpu_recover(adev, NULL);
+	amdgpu_gpu_recover(adev, NULL, false);
 }
 
 static int xgpu_vi_set_mailbox_rcv_irq(struct amdgpu_device *adev,