In amdgpu_fence_process it shouldn't put the signaled hw fence and set
RCU pointer to NULL, instead the more reasonable sequence is just leave
the RCU be there untouched, and:
1) Either driver_fini() should put this RCU fence or
2) New hw fence emitting should take the RCU slot and put the old hw fence.
mapping between get & put on hw fence is:
Get Put
fence_emit:fence_init ---> free_job:put job->fence
---> run_job:put job->fence //GPU RESET case
fence_emit:rcu_assign_pointer ---> fence_driver_fini:put
ring->fence_drv.fences[j]
---> fence_emit:put(old) //after fence_wait(old)
run_job:job->fence=fence_get() --> sched_main:put(fence)
--> job_recovery:put(fence) //for GPU RESET case
sched_main:parent=fence_get() --> sched_fence_free:put(fence->parent)
sched_job_recovery:parent=fence_get() -->
sched_hw_job_reset:put(s_job->s_fence->parent) // for GPU RESET case
Change-Id: I623167c1e3143233f4e1be7a400a9b698b4a1355
Signed-off-by: Monk Liu <[email protected]>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index f43319c..d7374cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -161,6 +161,8 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct
dma_fence **f)
dma_fence_wait(old, false);
}
+ dma_fence_put(old);
+
rcu_assign_pointer(*ptr, dma_fence_get(&fence->base));
*f = &fence->base;
@@ -246,7 +248,6 @@ void amdgpu_fence_process(struct amdgpu_ring *ring)
/* There is always exactly one thread signaling this fence slot
*/
fence = rcu_dereference_protected(*ptr, 1);
- RCU_INIT_POINTER(*ptr, NULL);
if (!fence)
continue;
@@ -257,7 +258,6 @@ void amdgpu_fence_process(struct amdgpu_ring *ring)
else
BUG();
- dma_fence_put(fence);
} while (last_seq != seq);
}
--
2.7.4
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
