[PATCH 2/5] drm/amdgpu: Add kfd init_complete flag to check from amdgpu side

[shaoyunl]

amdgpu driver may be in reset state during init which will not initialize the kfd,
driver need to initialize the KFD after reset by check the flag

Signed-off-by: shaoyunl <shaoyun.liu at amd.com>
Acked-by: Alex Deucher <alexander.deucher at amd.com>
Change-Id: Ic1684b55b27e0afd42bee8b9b431c4fb0afcec15
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 9 ++++++++-
 3 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index c5343a5eecbe..a876dc3af017 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -165,7 +165,8 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 					adev->doorbell_index.last_non_cp;
 		}
 
-		kgd2kfd_device_init(adev->kfd.dev, adev_to_drm(adev), &gpu_resources);
+		adev->kfd.init_complete = kgd2kfd_device_init(adev->kfd.dev,
+						adev_to_drm(adev), &gpu_resources);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 4687ff2961e1..3182dd97840e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -80,6 +80,7 @@ struct amdgpu_amdkfd_fence {
 struct amdgpu_kfd_dev {
 	struct kfd_dev *dev;
 	uint64_t vram_used;
+	bool init_complete;
 };
 
 enum kgd_engine_type {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a11760ec3924..62d7ce621457 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4788,9 +4788,16 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 skip_sched_resume:
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
-		/*unlock kfd: SRIOV would do it separately */
+		/* unlock kfd: SRIOV would do it separately */
 		if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev))
 	                amdgpu_amdkfd_post_reset(tmp_adev);
+
+		/* kfd_post_reset will do nothing if kfd device is not initialized,
+		 * need to bring up kfd here if it's not be initialized before
+		 */
+		if (!adev->kfd.init_complete)
+			amdgpu_amdkfd_device_init(adev);
+
 		if (audio_suspended)
 			amdgpu_device_resume_display_audio(tmp_adev);
 		amdgpu_device_unlock_adev(tmp_adev);
-- 
2.17.1