[PATCH v3] drm/amdgpu: set start timestamp of fence in the right place

[<jiadong.zhu@xxxxxxx>]

From: Jiadong Zhu <Jiadong.Zhu@xxxxxxx>

The job's embedded fence is dma_fence which shall not be conversed
to amdgpu_fence. The start timestamp shall be saved on job for
hw_fence.

v2: optimize get_fence_start_time.
v3: set start time only when mcbp enabled.

Signed-off-by: Jiadong Zhu <Jiadong.Zhu@xxxxxxx>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 32 ++++++++++++++++++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.h   |  3 +++
 2 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 2f24a6aa13bf..8a2fdf5a310c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -88,6 +88,31 @@ static inline struct amdgpu_fence *to_amdgpu_fence(struct dma_fence *f)
 	return NULL;
 }
 
+static inline void set_fence_start_time(struct dma_fence *f, ktime_t start_timestamp)
+{
+	if (f->ops == &amdgpu_fence_ops) {
+		struct amdgpu_fence *__f = container_of(f, struct amdgpu_fence, base);
+
+		__f->start_timestamp = start_timestamp;
+	} else if (f->ops == &amdgpu_job_fence_ops) {
+		struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+
+		job->start_timestamp = start_timestamp;
+	}
+}
+
+static inline ktime_t get_fence_start_time(struct dma_fence *f)
+{
+	if (unlikely(f->ops == &amdgpu_fence_ops)) {
+		struct amdgpu_fence *__f = container_of(f, struct amdgpu_fence, base);
+
+		return __f->start_timestamp;
+	}
+	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+
+	return job->start_timestamp;
+}
+
 /**
  * amdgpu_fence_write - write a fence value
  *
@@ -197,7 +222,8 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
 		}
 	}
 
-	to_amdgpu_fence(fence)->start_timestamp = ktime_get();
+	if (adev->gfx.mcbp)
+		set_fence_start_time(fence, ktime_get());
 
 	/* This function can't be called concurrently anyway, otherwise
 	 * emitting the fence would mess up the hardware ring buffer.
@@ -428,7 +454,7 @@ u64 amdgpu_fence_last_unsignaled_time_us(struct amdgpu_ring *ring)
 		return 0;
 
 	return ktime_us_delta(ktime_get(),
-		to_amdgpu_fence(fence)->start_timestamp);
+		get_fence_start_time(fence));
 }
 
 /**
@@ -451,7 +477,7 @@ void amdgpu_fence_update_start_timestamp(struct amdgpu_ring *ring, uint32_t seq,
 	if (!fence)
 		return;
 
-	to_amdgpu_fence(fence)->start_timestamp = timestamp;
+	set_fence_start_time(fence, timestamp);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index a963a25ddd62..3a73fe11a1ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -73,6 +73,9 @@ struct amdgpu_job {
 	uint64_t		gds_va;
 	bool			init_shadow;
 
+	/* start timestamp for hw_fence*/
+	ktime_t			start_timestamp;
+
 	/* job_run_counter >= 1 means a resubmit job */
 	uint32_t		job_run_counter;
 
-- 
2.25.1