[PATCH AUTOSEL 5.4 232/330] drm/amdgpu/sriov add amdgpu_amdkfd_pre_reset in gpu reset

From: Sasha Levin
Date: Thu Sep 17 2020 - 22:59:07 EST


From: Jack Zhang <Jack.Zhang1@xxxxxxx>

[ Upstream commit 04bef61e5da18c2b301c629a209ccdba4d4c6fbb ]

kfd_pre_reset will free mem_objs allocated by kfd_gtt_sa_allocate

Without this change, sriov tdr code path will never free those allocated
memories and get memory leak.

v2:add a bugfix for kiq ring test fail

Signed-off-by: Jack Zhang <Jack.Zhang1@xxxxxxx>
Reviewed-by: Monk Liu <monk.liu@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c | 3 +++
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 3 +++
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 ++
3 files changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index d10f483f5e273..ce30d4e8bf25f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -644,6 +644,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
uint32_t temp;
struct v10_compute_mqd *m = get_mqd(mqd);

+ if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset)
+ return 0;
+
#if 0
unsigned long flags;
int retry;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index e262f2ac07a35..92754cfb98086 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -540,6 +540,9 @@ int kgd_gfx_v9_hqd_destroy(struct kgd_dev *kgd, void *mqd,
uint32_t temp;
struct v9_mqd *m = get_mqd(mqd);

+ if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset)
+ return 0;
+
if (adev->in_gpu_reset)
return -EIO;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5e1dce4241547..4105fbf571674 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3466,6 +3466,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
if (r)
return r;

+ amdgpu_amdkfd_pre_reset(adev);
+
/* Resume IP prior to SMC */
r = amdgpu_device_ip_reinit_early_sriov(adev);
if (r)
--
2.25.1