<div dir="ltr"><div class="gmail_default" style="font-size:small">Yes, I did. It crashed the kernel as follows<br></div><div class="gmail_default" style="font-size:small"><br></div><div class="gmail_default" style="font-size:small">Sep 14 09:12:34 kernel: [ 506.676925][ 4] [ T1045] Hardware name: WEIBU F20A8/F20A8, BIOS 0.1.3 2021-07-06_20:59:09<br>Sep 14 09:12:34 kernel: [ 506.685091][ 4] [ T1045] pstate: 80000005 (Nzcv daif -PAN -UAO)<br>Sep 14 09:12:34 kernel: [ 506.691001][ 4] [ T1045] pc : 0x0<br>Sep 14 09:12:34 kernel: [ 506.694341][ 4] [ T1045] lr : drm_gem_map_dma_buf+0xc0/0x118 [drm]<br>Sep 14 09:12:34 kernel: [ 506.700509][ 4] [ T1045] sp : ffffffa0f4993b10<br>Sep 14 09:12:34 kernel: [ 506.704941][ 4] [ T1045] x29: ffffffa0f4993b10 x28: ffffffa0f4993cd8 <br>Sep 14 09:12:34 kernel: [ 506.711370][ 4] [ T1045] x27: 000000000000000c x26: ffffffa0f33e5200 <br>Sep 14 09:12:34 kernel: [ 506.717800][ 4] [ T1045] x25: ffffffa0e7452630 x24: ffffffa0f5a9f000 <br>Sep 14 09:12:34 kernel: [ 506.724229][ 4] [ T1045] x23: ffffffa0f33e5328 x22: ffffffa0e820f180 <br>Sep 14 09:12:34 kernel: [ 506.730658][ 4] [ T1045] x21: ffffffa0e820f180 x20: 0000000000000000 <br>Sep 14 09:12:34 kernel: [ 506.737087][ 4] [ T1045] x19: ffffffa0e820f180 x18: 0000000000000000 <br>Sep 14 09:12:34 kernel: [ 506.743516][ 4] [ T1045] x17: 0000000000000000 x16: 0000000000000000 <br>Sep 14 09:12:34 kernel: [ 506.749945][ 4] [ T1045] x15: 0000000000000000 x14: 0000000000000000 <br>Sep 14 09:12:34 kernel: [ 506.756373][ 4] [ T1045] x13: 0000000000000000 x12: 0000000000000000 <br>Sep 14 09:12:34 kernel: [ 506.762802][ 4] [ T1045] x11: 0000000000000000 x10: ffffffa0f43d1938 <br>Sep 14 09:12:34 kernel: [ 506.769231][ 4] [ T1045] x9 : 0000000000000000 x8 : ffffffa0e820f200 <br>Sep 14 09:12:34 kernel: [ 506.775659][ 4] [ T1045] x7 : 0000000000000000 x6 : 000000000000003f <br>Sep 14 09:12:34 kernel: [ 506.782088][ 4] [ T1045] x5 : 0000000000000040 x4 : 0000000000000000 <br>Sep 14 09:12:34 kernel: [ 506.788517][ 4] [ T1045] x3 : 0000000000000000 x2 : ffffffc008d553b0 <br>Sep 14 09:12:34 kernel: [ 506.794945][ 4] [ T1045] x1 : 0000000000000000 x0 : ffffffa0f311b000 <br>Sep 14 09:12:34 kernel: [ 506.801375][ 4] [ T1045] Call trace:<br>Sep 14 09:12:34 kernel: [ 506.804938][ 4] [ T1045] 0x0<br>Sep 14 09:12:34 kernel: [ 506.807899][ 4] [ T1045] dma_buf_map_attachment+0x60/0xb0<br>Sep 14 09:12:34 kernel: [ 506.813398][ 4] [ T1045] drm_gem_prime_import_dev+0x7c/0x138 [drm]<br>Sep 14 09:12:34 kernel: [ 506.819675][ 4] [ T1045] drm_gem_prime_fd_to_handle+0x1b4/0x1d8 [drm]<br>Sep 14 09:12:34 kernel: [ 506.826213][ 4] [ T1045] drm_prime_fd_to_handle_ioctl+0x24/0x38 [drm]<br>Sep 14 09:12:34 kernel: [ 506.832750][ 4] [ T1045] drm_ioctl_kernel+0x84/0xd8 [drm]<br>Sep 14 09:12:34 kernel: [ 506.838245][ 4] [ T1045] drm_ioctl+0x218/0x408 [drm]<br>Sep 14 09:12:34 kernel: [ 506.843326][ 4] [ T1045] radeon_drm_ioctl+0x50/0x88 [radeon]<br>Sep 14 09:12:34 kernel: [ 506.849063][ 4] [ T1045] do_vfs_ioctl+0x394/0x7e8<br>Sep 14 09:12:34 kernel: [ 506.853843][ 4] [ T1045] ksys_ioctl+0x78/0xa8<br>Sep 14 09:12:34 kernel: [ 506.858276][ 4] [ T1045] __arm64_sys_ioctl+0x1c/0x28<br>Sep 14 09:12:34 kernel: [ 506.863318][ 4] [ T1045] el0_svc_common.constprop.0+0x68/0x168<br>Sep 14 09:12:34 kernel: [ 506.869226][ 4] [ T1045] el0_svc_handler+0x8c/0x98<br>Sep 14 09:12:34 kernel: [ 506.874093][ 4] [ T1045] el0_svc+0x8/0xc<br>Sep 14 09:12:34 kernel: [ 506.878093][ 4] [ T1045] Code: bad PC value<br>Sep 14 09:12:34 kernel: [ 506.882265][ 4] [ T1045] ---[ end trace 3888e65eac0454cc ]---<br></div><div class="gmail_default" style="font-size:small"><br></div><div class="gmail_default" style="font-size:small">I'm not familiar with the kernel, but I suspect it may be a kmd problem. It seems like something is missing.</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, 13 Sept 2021 at 20:57, Michel Dänzer <<a href="mailto:michel@daenzer.net">michel@daenzer.net</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">On 2021-09-13 14:40, Luc Ma wrote:<br> > Hello,<br> > <br> > I recently tried multi-GPU support on the mesa gallium drivers(glx=dri). When I exported the env `DRI_PRIME=1`, I found that it didn't work with two different drivers loaded at the same time.<br> > because there are different driver names in my case. display_gpu driver name is "r600" while render_gpu driver name is "nouveau". It failed to create display gpu screen<br> > <br> > if (strcmp(driverName, driverNameDisplayGPU) == 0) {<br> > psc->driScreenDisplayGPU =<br> > psc->image_driver->createNewScreen2(screen, psc->fd_display_gpu,<br> > pdp->loader_extensions,<br> > extensions,<br> > &driver_configs, psc);<br> > }<br> > <br> > so I am wondering<br> > <br> > - is it possible to use two GPUs from different vendors on a system with gallium? one is for display, another for rendering<br> > - is it possible to use two GPUs driven by a shared driver(say both "r600") on a system?<br> <br> Both should work.<br> <br> <br> Did you hit a problem other than psc->driScreenDisplayGPU related code being skipped (as is expected ATM with different drivers)?<br> <br> <br> -- <br> Earthling Michel Dänzer | <a href="https://redhat.com" rel="noreferrer" target="_blank">https://redhat.com</a><br> Libre software enthusiast | Mesa and X developer<br> </blockquote></div>