i915_perf_r...config_ioctl(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

πŸ’… i915_perf_remove_config_ioctl(9) β€” a Kernel API Manual moment

okay so this is a page from the Kernel API Manual bestie, and the title up top is literally rendered as i915_perf_r...config_ioctl(9) because the whole name is too iconic to fit (it's the classic man-page truncation vibe, not a typo fr fr).


✨ NAME ✨

i915_perf_remove_config_ioctl β€” the DRM ioctl() that lets userspace yeet an OA config out of existence πŸ—‘οΈβœ¨

🌸 SYNOPSIS 🌸

int i915_perf_remove_config_ioctl (struct drm_device *dev , void *data ,
       struct drm_file *file );

πŸŽ€ ARGUMENTS πŸŽ€

  • dev β€” the drm device, the main character of this whole operation πŸ’–
  • data β€” the ioctl data (a pointer to a u64 integer) copied from userspace 🫢
  • file β€” the drm file πŸ¦‹

πŸ‘‘ DESCRIPTION πŸ‘‘

okay so here's the tea β˜•: configs can totally be removed while they're being used. Like, no drama, it's fine.

The way that works is β€” the config stops appearing in sysfs (gone, ghosted, bye πŸ‘‹), and its content gets freed later, when the stream that's using that config is closed. So it's giving "we'll deal with the cleanup when the stream wraps up" energy πŸ’…

⭐ RETURN ⭐

0 on success, or a negative error code on failure. slay when it's 0, sad girl hours when it's negative 😭

πŸ¦‹ SEE ALSO πŸ¦‹

like, that's the whole friend group right there 🫢 no cap, they all ate πŸ’…


ngl bestie, if you're poking at OA configs from userspace, read the whole squad above before you touch anything β€” the perf overview and the tail pointer race pages are especially the ones you don't wanna skip πŸ™ˆ

and that's the page!! source lives at ./drivers/gpu/drm/i915, it's dated October 2026, and the footer keeps the same truncated i915_perf_r...config_ioctl(9) title. periodt πŸ’–βœ¨πŸŽ€

πŸ“¦ where this page comes from