On Fri, 2022-06-17 at 08:46 +0200, Javier Martinez Canillas wrote: > Hello Zack, > > On 6/17/22 03:35, Zack Rusin wrote: > > On Fri, 2022-06-17 at 01:21 +0200, Javier Martinez Canillas wrote: > > > On 6/17/22 00:18, Javier Martinez Canillas wrote: > > > > On 6/16/22 23:03, Zack Rusin wrote: > > > > > > [snip] > > > > > > > > > > > I'll look at this tomorrow but in the meantime, could you please look if the following > > > > commits on top of drm-misc-next help ? > > > > > > > > d258d00fb9c7 fbdev: efifb: Cleanup fb_info in .fb_destroy rather than .remove > > > > 1b5853dfab7f fbdev: efifb: Fix a use-after-free due early fb_info cleanup > > > > > > > > > > Scratch that. I see in your config now that you are not using efifb but instead > > > simpledrm: CONFIG_DRM_SIMPLEDRM=y, CONFIG_SYSFB_SIMPLEFB=y and CONFIG_DRM_VMWGFX. > > > > > > Since you mentioned efifb I misunderstood that you are using it. Anyways, as > > > said I'll investigate this tomorrow. > > > > Sounds good. Let me know if you'd like me to try it without SIMPLEFB. > > > > Yes, please do. Either with CONFIG_SYSFB_SIMPLEFB disabled and CONFIG_FB_EFI > enabled (so that "efi-framebuffer" is registered and efifb probed) or with > CONFIG_SYSFB_SIMPLEFB but CONFIG_FB_SIMPLE enabled (so "simple-framebuffer > is used too but with simplefb instead of simpledrm). > > I'm not able to reproduce, it would be useful to have another data point. Also happening for me with CONFIG_SYSFB_SIMPLEFB, on a Intel Core i7- 1065G7 (with iGPU). Reverting this commit on top of 5.19-rc5 "fixes" the issue.