Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-17 Thread Christian König
13日16:40 *To:* Koenig, Christian ; Nicolai Hähnle ; amd-gfx@lists.freedesktop.org *Subject:* RE: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 I doubt it would always work fine… First, we have FENCE_TRACE reference s_fence->finished after “fence_signal(&fence->finished)” Second, we hav

Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-17 Thread Nicolai Hähnle
mailto:nhaeh...@gmail.com>>; amd-gfx@lists.freedesktop.org <mailto:amd-gfx@lists.freedesktop.org> *Subject:* Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 Yeah, that change is actually incorrect and should be reverted. What we really need to do is remove dropping sc

RE: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Liu, Monk
Because you didn't try GPU reset feature -Original Message- From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf Of Tom St Denis Sent: 2017年10月13日 19:11 To: amd-gfx@lists.freedesktop.org Subject: Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 At the

Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Tom St Denis
*To:* Liu, Monk ; Nicolai Hähnle ; amd-gfx@lists.freedesktop.org *Subject:* Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 Good point as well. How about the attached version? This time we keep an extra reference in amd_sched_process_job() until we are sure that we don't n

RE: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Liu, Monk
Yeah, this one looks good You can put my reviewed-by on it From: Koenig, Christian Sent: 2017年10月13日 18:14 To: Liu, Monk ; Nicolai Hähnle ; amd-gfx@lists.freedesktop.org Subject: Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 Good point as well. How about the attached version

Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Christian König
*From:* Koenig, Christian *Sent:* Friday, October 13, 2017 5:00:27 PM *To:* Liu, Monk; Nicolai Hähnle; amd-gfx@lists.freedesktop.org *Subject:* Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 There is chance that free_job() called before that “trace_amd_sched_process

Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Liu, Monk
_ From: Koenig, Christian Sent: Friday, October 13, 2017 5:00:27 PM To: Liu, Monk; Nicolai Hähnle; amd-gfx@lists.freedesktop.org Subject: Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 There is chance that free_job() called before that “trace_amd_sched_process_j

Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Christian König
; Nicolai Hähnle ; amd-gfx@lists.freedesktop.org *Subject:* RE: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 No that’s not true The free_job() is called in sched_job_finish() which is queued on a WORK and scheduled from that “amd_sched_fence_finished()” So the finishing timing of

RE: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Liu, Monk
”, correct? And if so the s_fence referred by it maybe a wild pointer BR Monk From: Liu, Monk Sent: 2017年10月13日 16:49 To: Koenig, Christian ; Nicolai Hähnle ; amd-gfx@lists.freedesktop.org Subject: RE: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 No that’s not true The free_job() is called

RE: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Liu, Monk
” ? From: Koenig, Christian Sent: 2017年10月13日 16:43 To: Liu, Monk ; Nicolai Hähnle ; amd-gfx@lists.freedesktop.org Subject: Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 The free_job() callback is called only way after the job has finished. That is one change actually made by you to

RE: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Liu, Monk
Nicolai met with and submitted this patch BR Monk From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf Of Liu, Monk Sent: 2017年10月13日 16:40 To: Koenig, Christian ; Nicolai Hähnle ; amd-gfx@lists.freedesktop.org Subject: RE: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Christian König
om:*Koenig, Christian *Sent:* 2017年10月13日16:17 *To:* Liu, Monk ; Nicolai Hähnle ; amd-gfx@lists.freedesktop.org *Subject:* Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 Yeah, that change is actually incorrect and should be reverted. What we really need to do is remove dropping sched_jo

RE: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Liu, Monk
job_finish() get very soon executed you’ll have odds to hit wild pointer on above two cases BR Monk From: Koenig, Christian Sent: 2017年10月13日 16:17 To: Liu, Monk ; Nicolai Hähnle ; amd-gfx@lists.freedesktop.org Subject: Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2 Yeah, that

Re: regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Christian König
Yeah, that change is actually incorrect and should be reverted. What we really need to do is remove dropping sched_job->s_fence from amd_sched_process_job() into amd_sched_job_finish() directly before the call to free_job(). Regards, Christian. Am 13.10.2017 um 09:24 schrieb Liu, Monk: comm

regression with d6c650c0a8f6f671e49553725e1db541376d95f2

2017-10-13 Thread Liu, Monk
commit d6c650c0a8f6f671e49553725e1db541376d95f2 Author: Nicolai Hähnle @@ -611,6 +611,10 @@ static int amd_sched_main(void *param) fence = sched->ops->run_job(sched_job); amd_sched_fence_scheduled(s_fence); + + /* amd_sched_process_job drops the job's