drm/amdgpu: cleanup GPU recovery check a bit (v2)

Check if we should call the function instead of providing the forced
flag.

v2: rebase on KFD changes (Alex)

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

8 files changed, 38 insertions, 22 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 19ef7711d944..340e40d03d54 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1158,8 +1158,9 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define amdgpu_asic_need_full_reset(adev) (adev)->asic_funcs->need_full_reset((adev))
 
 /* Common functions */
+bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev);
 int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
-			      struct amdgpu_job* job, bool force);
+			      struct amdgpu_job* job);
 void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
 bool amdgpu_device_need_post(struct amdgpu_device *adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index f8bbbb3a9504..3dbe675b6fe1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -267,7 +267,8 @@ void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 
-	amdgpu_device_gpu_recover(adev, NULL, false);
+	if (amdgpu_device_should_recover_gpu(adev))
+		amdgpu_device_gpu_recover(adev, NULL);
 }
 
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c961e781430d..8f431740c424 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3244,31 +3244,43 @@ error:
 }
 
 /**
+ * amdgpu_device_should_recover_gpu - check if we should try GPU recovery
+ *
+ * @adev: amdgpu device pointer
+ *
+ * Check amdgpu_gpu_recovery and SRIOV status to see if we should try to recover
+ * a hung GPU.
+ */
+bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
+{
+	if (!amdgpu_device_ip_check_soft_reset(adev)) {
+		DRM_INFO("Timeout, but no hardware hang detected.\n");
+		return false;
+	}
+
+	if (amdgpu_gpu_recovery == 0 || (amdgpu_gpu_recovery == -1  &&
+					 !amdgpu_sriov_vf(adev))) {
+		DRM_INFO("GPU recovery disabled.\n");
+		return false;
+	}
+
+	return true;
+}
+
+/**
  * amdgpu_device_gpu_recover - reset the asic and recover scheduler
  *
  * @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_device_gpu_recover(struct amdgpu_device *adev,
-			      struct amdgpu_job *job, bool force)
+			      struct amdgpu_job *job)
 {
 	int i, r, resched;
 
-	if (!force && !amdgpu_device_ip_check_soft_reset(adev)) {
-		DRM_INFO("No hardware hang detected. Did some blocks stall?\n");
-		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);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 7056925eb386..da36731460b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -701,7 +701,7 @@ 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_device_gpu_recover(adev, NULL, true);
+	amdgpu_device_gpu_recover(adev, NULL);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 1abf5b5bac9e..b927e8798534 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -105,8 +105,8 @@ static void amdgpu_irq_reset_work_func(struct work_struct *work)
 	struct amdgpu_device *adev = container_of(work, struct amdgpu_device,
 						  reset_work);
 
-	if (!amdgpu_sriov_vf(adev))
-		amdgpu_device_gpu_recover(adev, NULL, false);
+	if (!amdgpu_sriov_vf(adev) && amdgpu_device_should_recover_gpu(adev))
+		amdgpu_device_gpu_recover(adev, NULL);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 391e2f7c03aa..265ff90f4e01 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -37,7 +37,8 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 		  job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
 		  ring->fence_drv.sync_seq);
 
-	amdgpu_device_gpu_recover(ring->adev, job, false);
+	if (amdgpu_device_should_recover_gpu(ring->adev))
+		amdgpu_device_gpu_recover(ring->adev, job);
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 078f70faedcb..8cbb4655896a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -266,8 +266,8 @@ flr_done:
 	}
 
 	/* Trigger recovery for world switch failure if no TDR */
-	if (amdgpu_lockup_timeout == 0)
-		amdgpu_device_gpu_recover(adev, NULL, true);
+	if (amdgpu_device_should_recover_gpu(adev))
+		amdgpu_device_gpu_recover(adev, NULL);
 }
 
 static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
index 9fc1c37344ce..842567b53df5 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
@@ -521,7 +521,8 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work)
 	}
 
 	/* Trigger recovery due to world switch failure */
-	amdgpu_device_gpu_recover(adev, NULL, false);
+	if (amdgpu_device_should_recover_gpu(adev))
+		amdgpu_device_gpu_recover(adev, NULL);
 }
 
 static int xgpu_vi_set_mailbox_rcv_irq(struct amdgpu_device *adev,