Merge tag 'amd-drm-next-5.18-2022-02-25' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.18-2022-02-25:

amdgpu:
- Raven2 suspend/resume fix
- SDMA 5.2.6 updates
- VCN 3.1.2 updates
- SMU 13.0.5 updates
- DCN 3.1.5 updates
- Virtual display fixes
- SMU code cleanup
- Harvest fixes
- Expose benchmark tests via debugfs
- Drop no longer relevant gart aperture tests
- More RAS restructuring
- W=1 fixes
- PSR rework
- DP/VGA adapter fixes
- DP MST fixes
- GPUVM eviction fix
- GPU reset debugfs register dumping support
- Misc display fixes
- SR-IOV fix
- Aldebaran mGPU fix
- Add module parameter to disable XGMI for testing

amdkfd:
- IH ring overflow logging fixes
- CRIU fixes
- Misc fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220225183535.5907-1-alexander.deucher@amd.com

1 files changed, 23 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ca8e76771ea1..ca854626a108 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1539,6 +1539,11 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 		amdgpu_sched_hw_submission = roundup_pow_of_two(amdgpu_sched_hw_submission);
 	}
 
+	if (amdgpu_reset_method < -1 || amdgpu_reset_method > 4) {
+		dev_warn(adev->dev, "invalid option for reset method, reverting to default\n");
+		amdgpu_reset_method = -1;
+	}
+
 	amdgpu_device_check_smu_prv_buffer_size(adev);
 
 	amdgpu_device_check_vm_size(adev);
@@ -3609,6 +3614,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->psp.mutex);
 	mutex_init(&adev->notifier_lock);
 	mutex_init(&adev->pm.stable_pstate_ctx_lock);
+	mutex_init(&adev->benchmark_mutex);
 
 	amdgpu_device_init_apu_flags(adev);
 
@@ -3872,19 +3878,6 @@ fence_driver_init:
 	} else
 		adev->ucode_sysfs_en = true;
 
-	if ((amdgpu_testing & 1)) {
-		if (adev->accel_working)
-			amdgpu_test_moves(adev);
-		else
-			DRM_INFO("amdgpu: acceleration disabled, skipping move tests\n");
-	}
-	if (amdgpu_benchmarking) {
-		if (adev->accel_working)
-			amdgpu_benchmark(adev, amdgpu_benchmarking);
-		else
-			DRM_INFO("amdgpu: acceleration disabled, skipping benchmarks\n");
-	}
-
 	/*
 	 * Register gpu instance before amdgpu_device_enable_mgpu_fan_boost.
 	 * Otherwise the mgpu fan boost feature will be skipped due to the
@@ -4723,6 +4716,22 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 	return r;
 }
 
+static int amdgpu_reset_reg_dumps(struct amdgpu_device *adev)
+{
+	uint32_t reg_value;
+	int i;
+
+	lockdep_assert_held(&adev->reset_domain->sem);
+	dump_stack();
+
+	for (i = 0; i < adev->num_regs; i++) {
+		reg_value = RREG32(adev->reset_dump_reg_list[i]);
+		trace_amdgpu_reset_reg_dumps(adev->reset_dump_reg_list[i], reg_value);
+	}
+
+	return 0;
+}
+
 int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 			 struct amdgpu_reset_context *reset_context)
 {
@@ -4733,6 +4742,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 	/* Try reset handler method first */
 	tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
 				    reset_list);
+	amdgpu_reset_reg_dumps(tmp_adev);
 	r = amdgpu_reset_perform_reset(tmp_adev, reset_context);
 	/* If reset handler not implemented, continue; otherwise return */
 	if (r == -ENOSYS)