drm/amdgpu: Fix crash on device remove/driver unload

Crash:
BUG: unable to handle page fault for address: 00000000000010e1
RIP: 0010:vega10_power_gate_vce+0x26/0x50 [amdgpu]
Call Trace:
pp_set_powergating_by_smu+0x16a/0x2b0 [amdgpu]
amdgpu_dpm_set_powergating_by_smu+0x92/0xf0 [amdgpu]
amdgpu_dpm_enable_vce+0x2e/0xc0 [amdgpu]
vce_v4_0_hw_fini+0x95/0xa0 [amdgpu]
amdgpu_device_fini_hw+0x232/0x30d [amdgpu]
amdgpu_driver_unload_kms+0x5c/0x80 [amdgpu]
amdgpu_pci_remove+0x27/0x40 [amdgpu]
pci_device_remove+0x3e/0xb0
device_release_driver_internal+0x103/0x1d0
device_release_driver+0x12/0x20
pci_stop_bus_device+0x79/0xa0
pci_stop_and_remove_bus_device_locked+0x1b/0x30
remove_store+0x7b/0x90
dev_attr_store+0x17/0x30
sysfs_kf_write+0x4b/0x60
kernfs_fop_write_iter+0x151/0x1e0

Why:
VCE/UVD had dependency on SMC block for their suspend but
SMC block is the first to do HW fini due to some constraints

How:
Since the original patch was dealing with suspend issues
move the SMC block dependency back into suspend hooks as
was done in V1 of the original patches.
Keep flushing idle work both in suspend and HW fini seuqnces
since it's essential in both cases.

Fixes: 859e4659273f1d ("drm/amdgpu: add missing cleanups for more ASICs on UVD/VCE suspend")
Fixes: bf756fb833cbe8 ("drm/amdgpu: add missing cleanups for Polaris12 UVD/VCE on suspend")
Signed-off-by: Andrey Grodzovsky <[e-mail]>
Signed-off-by: Alex Deucher <[e-mail]>

drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c

···
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (RREG32(mmUVD_STATUS) != 0)
+		uvd_v3_1_stop(adev);
+
+	return 0;
+}
+
+static int uvd_v3_1_suspend(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
 	/*
 	 * Proper cleanups before halting the HW engine:
 	 *   - cancel the delayed idle work
···
 		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
 						       AMD_CG_STATE_GATE);
 	}
-
-	if (RREG32(mmUVD_STATUS) != 0)
-		uvd_v3_1_stop(adev);
-
-	return 0;
-}
-
-static int uvd_v3_1_suspend(void *handle)
-{
-	int r;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	r = uvd_v3_1_hw_fini(adev);
 	if (r)

drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c

···
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (RREG32(mmUVD_STATUS) != 0)
+		uvd_v4_2_stop(adev);
+
+	return 0;
+}
+
+static int uvd_v4_2_suspend(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
 	/*
 	 * Proper cleanups before halting the HW engine:
 	 *   - cancel the delayed idle work
···
 		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
 						       AMD_CG_STATE_GATE);
 	}
-
-	if (RREG32(mmUVD_STATUS) != 0)
-		uvd_v4_2_stop(adev);
-
-	return 0;
-}
-
-static int uvd_v4_2_suspend(void *handle)
-{
-	int r;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	r = uvd_v4_2_hw_fini(adev);
 	if (r)

drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c

···
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (RREG32(mmUVD_STATUS) != 0)
+		uvd_v5_0_stop(adev);
+
+	return 0;
+}
+
+static int uvd_v5_0_suspend(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
 	/*
 	 * Proper cleanups before halting the HW engine:
 	 *   - cancel the delayed idle work
···
 		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
 						       AMD_CG_STATE_GATE);
 	}
-
-	if (RREG32(mmUVD_STATUS) != 0)
-		uvd_v5_0_stop(adev);
-
-	return 0;
-}
-
-static int uvd_v5_0_suspend(void *handle)
-{
-	int r;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	r = uvd_v5_0_hw_fini(adev);
 	if (r)

drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c

···
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (!amdgpu_sriov_vf(adev))
+		uvd_v7_0_stop(adev);
+	else {
+		/* full access mode, so don't touch any UVD register */
+		DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
+	}
+
+	return 0;
+}
+
+static int uvd_v7_0_suspend(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
 	/*
 	 * Proper cleanups before halting the HW engine:
 	 *   - cancel the delayed idle work
···
 		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
 						       AMD_CG_STATE_GATE);
 	}
-
-	if (!amdgpu_sriov_vf(adev))
-		uvd_v7_0_stop(adev);
-	else {
-		/* full access mode, so don't touch any UVD register */
-		DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
-	}
-
-	return 0;
-}
-
-static int uvd_v7_0_suspend(void *handle)
-{
-	int r;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	r = uvd_v7_0_hw_fini(adev);
 	if (r)

drivers/gpu/drm/amd/amdgpu/vce_v2_0.c

···
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	cancel_delayed_work_sync(&adev->vce.idle_work);
+
+	return 0;
+}
+
+static int vce_v2_0_suspend(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+
 	/*
 	 * Proper cleanups before halting the HW engine:
 	 *   - cancel the delayed idle work
···
 		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
 						       AMD_CG_STATE_GATE);
 	}
-
-	return 0;
-}
-
-static int vce_v2_0_suspend(void *handle)
-{
-	int r;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	r = vce_v2_0_hw_fini(adev);
 	if (r)

drivers/gpu/drm/amd/amdgpu/vce_v3_0.c

···
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	cancel_delayed_work_sync(&adev->vce.idle_work);
+
+	r = vce_v3_0_wait_for_idle(handle);
+	if (r)
+		return r;
+
+	vce_v3_0_stop(adev);
+	return vce_v3_0_set_clockgating_state(adev, AMD_CG_STATE_GATE);
+}
+
+static int vce_v3_0_suspend(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
 	/*
 	 * Proper cleanups before halting the HW engine:
 	 *   - cancel the delayed idle work
···
 		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
 						       AMD_CG_STATE_GATE);
 	}
-
-	r = vce_v3_0_wait_for_idle(handle);
-	if (r)
-		return r;
-
-	vce_v3_0_stop(adev);
-	return vce_v3_0_set_clockgating_state(adev, AMD_CG_STATE_GATE);
-}
-
-static int vce_v3_0_suspend(void *handle)
-{
-	int r;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	r = vce_v3_0_hw_fini(adev);
 	if (r)

drivers/gpu/drm/amd/amdgpu/vce_v4_0.c

···
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	/*
-	 * Proper cleanups before halting the HW engine:
-	 *   - cancel the delayed idle work
-	 *   - enable powergating
-	 *   - enable clockgating
-	 *   - disable dpm
-	 *
-	 * TODO: to align with the VCN implementation, move the
-	 * jobs for clockgating/powergating/dpm setting to
-	 * ->set_powergating_state().
-	 */
 	cancel_delayed_work_sync(&adev->vce.idle_work);
-
-	if (adev->pm.dpm_enabled) {
-		amdgpu_dpm_enable_vce(adev, false);
-	} else {
-		amdgpu_asic_set_vce_clocks(adev, 0, 0);
-		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
-						       AMD_PG_STATE_GATE);
-		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
-						       AMD_CG_STATE_GATE);
-	}
 
 	if (!amdgpu_sriov_vf(adev)) {
 		/* vce_v4_0_wait_for_idle(handle); */
···
 			memcpy_fromio(adev->vce.saved_bo, ptr, size);
 		}
 		drm_dev_exit(idx);
+	}
+
+	/*
+	 * Proper cleanups before halting the HW engine:
+	 *   - cancel the delayed idle work
+	 *   - enable powergating
+	 *   - enable clockgating
+	 *   - disable dpm
+	 *
+	 * TODO: to align with the VCN implementation, move the
+	 * jobs for clockgating/powergating/dpm setting to
+	 * ->set_powergating_state().
+	 */
+	cancel_delayed_work_sync(&adev->vce.idle_work);
+
+	if (adev->pm.dpm_enabled) {
+		amdgpu_dpm_enable_vce(adev, false);
+	} else {
+		amdgpu_asic_set_vce_clocks(adev, 0, 0);
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+						       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+						       AMD_CG_STATE_GATE);
 	}
 
 	r = vce_v4_0_hw_fini(adev);