<html><head> <meta http-equiv="Content-Type" content="text/html; charset=Windows-1252"> </head> <body text="#000000" bgcolor="#FFFFFF"> <div class="moz-cite-prefix">Am 03.03.20 um 15:34 schrieb He, Jacob: </div> <blockquote type="cite" cite="mid:MN2PR12MB3376C82E9294503F14F928A79BE40@MN2PR12MB3376.namprd12.prod.outlook.com"> <meta name="Generator" content="Microsoft Word 15 (filtered medium)"> <style></style> [AMD Official Use Only - Internal Distribution Only] <div> <div class="WordSection1"> It would be better if we could do that asynchronously with a register write on the ring. Sorry, I don’t get your point. Could you please elaborate more? </div> </div> </blockquote> You pass the ring from amdgpu_vm_flush() to the *_update_spm_vmid() functions. And then instead of using WREG32() you call amdgpu_ring_emit_wreg() to make the write asynchronously on the ring buffer using a CP command. This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it. Regards, Christian. <blockquote type="cite" cite="mid:MN2PR12MB3376C82E9294503F14F928A79BE40@MN2PR12MB3376.namprd12.prod.outlook.com"> <div> <div class="WordSection1"> <o:p> </o:p> Thanks<o:p></o:p> Jacob<o:p></o:p> <o:p> </o:p> <div style="mso-element:para-border-div;border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0in 0in 0in"> From: <a href="mailto:ckoenig.leichtzumerken@gmail.com" moz-do-not-send="true">Christian König</a> Sent: Tuesday, March 3, 2020 10:16 PM To: <a href="mailto:Jacob.He@amd.com" moz-do-not-send="true">He, Jacob</a>; <a href="mailto:amd-gfx@lists.freedesktop.org" moz-do-not-send="true"> amd-gfx@lists.freedesktop.org</a> Subject: Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid </div> <o:p> </o:p> Am 02.03.20 um 06:35 schrieb Jacob He: > SPM access the video memory according to SPM_VMID. It should be updated > with the job's vmid right before the job is scheduled. SPM_VMID is a > global resource > > Change-Id: Id3881908960398f87e7c95026a54ff83ff826700 > Signed-off-by: Jacob He <a class="moz-txt-link-rfc2396E" href="mailto:jacob.he@amd.com"><jacob.he@amd.com></a> > --- > drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++++ > 1 file changed, 4 insertions(+) > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c > index c00696f3017e..c761d3a0b6e8 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c > @@ -1080,8 +1080,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, > struct dma_fence *fence = NULL; > bool pasid_mapping_needed = false; > unsigned patch_offset = 0; > + bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] != NULL)); > int r; > > + if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid) > + adev->gfx.rlc.funcs->update_spm_vmid(adev, job->vmid); > + It would be better if we could do that asynchronously with a register write on the ring. The alternative is that we block for the VM to be idle in amdgpu_vm_ioctl() before unreserving the VMID. In other words lock the reservation object of the root PD and call amdgpu_vm_wait_idle() before calling amdgpu_vmid_free_reserved(). Regards, Christian. > if (amdgpu_vmid_had_gpu_reset(adev, id)) { > gds_switch_needed = true; > vm_flush_needed = true;<o:p></o:p> <o:p> </o:p> </div> </div> </blockquote> </body> </html>