[PATCH 3/4] drm/amdgpu: Add kfd init_complete flag to check from amdgpu side

Liu, Shaoyun Shaoyun.Liu at amd.com
Mon Feb 22 16:14:51 UTC 2021


[AMD Official Use Only - Internal Distribution Only]



-----Original Message-----
From: Liu, Shaoyun <shaoyun.liu at amd.com> 
Sent: Thursday, February 18, 2021 8:20 PM
To: amd-gfx at lists.freedesktop.org
Cc: Liu, Shaoyun <Shaoyun.Liu at amd.com>
Subject: [PATCH 3/4] drm/amdgpu: Add kfd init_complete flag to check from amdgpu side

amdgpu driver may in reset state duirng 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>
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 | 7 +++++++
 3 files changed, 10 insertions(+), 1 deletion(-)

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 9f574fd151bc..e898fce96f75 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4841,6 +4841,13 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		/*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


More information about the amd-gfx mailing list