that way we can know which job cause hang and
can do per sched reset/recovery instead of all
sched.
Change-Id: Ifc98cd74b2d93823c489de6a89087ba188957eff
Signed-off-by: Monk Liu <Monk.Liu at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 +++----
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 2 +-
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 2 +-
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 2 +-
5 files changed, 7 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 4985a7e..0e5f314 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2529,14 +2529,13 @@ static int amdgpu_recover_vram_from_shadow(struct amdgpu_device *adev,
* amdgpu_sriov_gpu_reset - reset the asic
*
* @adev: amdgpu device pointer
- * @voluntary: if this reset is requested by guest.
- * (true means by guest and false means by HYPERVISOR )
+ * @job: which job trigger hang
*
* Attempt the reset the GPU if it has hung (all asics).
* for SRIOV case.
* Returns 0 for success or an error on failure.
*/
-int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, bool voluntary)
+int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job)
{
int i, r = 0;
int resched;
@@ -2566,7 +2565,7 @@ int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, bool voluntary)
amdgpu_fence_driver_force_completion(adev);
/* request to take full control of GPU before re-initialization */
- if (voluntary)
+ if (job)
amdgpu_virt_reset_gpu(adev);
else
amdgpu_virt_request_full_gpu(adev, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index c7718af..3c6fb6e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -38,7 +38,7 @@ static void amdgpu_job_timedout(struct amd_sched_job *s_job)
job->ring->fence_drv.sync_seq);
if (amdgpu_sriov_vf(job->adev))
- amdgpu_sriov_gpu_reset(job->adev, true);
+ amdgpu_sriov_gpu_reset(job->adev, job);
else
amdgpu_gpu_reset(job->adev);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index 6f2b7df..9e1062e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -96,7 +96,7 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v);
int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init);
int amdgpu_virt_release_full_gpu(struct amdgpu_device *adev, bool init);
int amdgpu_virt_reset_gpu(struct amdgpu_device *adev);
-int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, bool voluntary);
+int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job);
int amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev);
void amdgpu_virt_free_mm_table(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 96139ec..69da52d 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -243,7 +243,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
}
/* Trigger recovery due to world switch failure */
- amdgpu_sriov_gpu_reset(adev, false);
+ amdgpu_sriov_gpu_reset(adev, NULL);
}
static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
index f0d64f1..1cdf5cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
@@ -514,7 +514,7 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work)
}
/* Trigger recovery due to world switch failure */
- amdgpu_sriov_gpu_reset(adev, false);
+ amdgpu_sriov_gpu_reset(adev, NULL);
}
static int xgpu_vi_set_mailbox_rcv_irq(struct amdgpu_device *adev,
--
2.7.4
