On Mon, Jul 28, 2025 at 5:01 AM YuanShang Mao (River) <yuanshang....@amd.com> wrote: > > [AMD Official Use Only - AMD Internal Distribution Only] > > Hi Alexander > > Since Christian is on vacation. Could you help review the below patch? > If set job->vm to null in amdgpu_job_prepare_job, the job which > should be skipped in amdgpu_job_run will be submitted unexpectedly.
I think we can just remove the amdgpu_vm_generation() check in amdgpu_job_run(). I didn't think we actually resubmitting jobs anymore. How are we ending up trying to resubmit in the first place? Alex > > Thanks > River > > > -----Original Message----- > From: YuanShang Mao (River) <yuanshang....@amd.com> > Sent: Wednesday, July 23, 2025 5:06 PM > To: amd-gfx@lists.freedesktop.org > Cc: Koenig, Christian <christian.koe...@amd.com>; YuanShang Mao (River) > <yuanshang....@amd.com> > Subject: [PATCH] drm/amdgpu: keep job->vm in amdgpu_job_prepare_job > > job->vm is used in function amdgpu_job_run to get the page > table re-generation counter and decide whether the job should be skipped. > > Signed-off-by: YuanShang <yuanshang....@amd.com> > --- > drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 7 ------- > 1 file changed, 7 deletions(-) > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c > b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c > index 45febdc2f349..18998343815e 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c > @@ -360,13 +360,6 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job, > dev_err(ring->adev->dev, "Error getting VM ID > (%d)\n", r); > goto error; > } > - /* > - * The VM structure might be released after the VMID is > - * assigned, we had multiple problems with people trying to > use > - * the VM pointer so better set it to NULL. > - */ > - if (!fence) > - job->vm = NULL; > return fence; > } > > -- > 2.25.1 >
