[PATCH 2/2] dma-buf: try to replace a signaled fence in reservation_object_add_shared_inplace

Christian König ckoenig.leichtzumerken at gmail.com
Tue Nov 14 14:24:44 UTC 2017


Am 06.11.2017 um 17:22 schrieb Chris Wilson:
> Quoting Christian König (2017-10-30 14:59:04)
>> From: Christian König <christian.koenig at amd.com>
>>
>> The amdgpu issue to also need signaled fences in the reservation objects should
>> be fixed by now.
>>
>> Optimize the handling by replacing a signaled fence when adding a new
>> shared one.
>>
>> Signed-off-by: Christian König <christian.koenig at amd.com>
>> ---
>>   drivers/dma-buf/reservation.c | 18 +++++++++++++++---
>>   1 file changed, 15 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
>> index 6fc794576997..a3928ce9f311 100644
>> --- a/drivers/dma-buf/reservation.c
>> +++ b/drivers/dma-buf/reservation.c
>> @@ -104,7 +104,8 @@ reservation_object_add_shared_inplace(struct reservation_object *obj,
>>                                        struct reservation_object_list *fobj,
>>                                        struct dma_fence *fence)
>>   {
>> -       u32 i;
>> +       struct dma_fence *signaled = NULL;
>> +       u32 i, signaled_idx;
>>   
>>          dma_fence_get(fence);
>>   
>> @@ -126,17 +127,28 @@ reservation_object_add_shared_inplace(struct reservation_object *obj,
>>                          dma_fence_put(old_fence);
>>                          return;
>>                  }
>> +
>> +               if (!signaled && dma_fence_is_signaled(old_fence)) {
>> +                       signaled = old_fence;
>> +                       signaled_idx = i;
>> +               }
> How much do we care about only keeping one fence per-ctx here? You could
> rearrange this to break on old_fence->context == fence->context ||
> dma_fence_is_signaled(old_fence) then everyone can use the final block.

Yeah, that is what David Zhou suggested as well.

I've rejected this approach for now cause I think we still have cases 
where we rely on one fence per ctx (but I'm not 100% sure).

I changed patch #1 in this series as you suggest and going to send that 
out once more in a minute.

Can we get this upstream as is for now? I won't have much more time 
working on this.

Regards,
Christian.

> -Chris




More information about the amd-gfx mailing list