xe_sriov_vfi...op_copy_size(9)

📦 version 7.3.1, in nixpkgs unstable

💅 xe_sriov_vfio_stop_copy_size — Kernel API Manual, bestie ✨

Okay so picture this: you're deep in the xe driver, you're doing VF device migration, and you need to know how much stuff you're about to move. That's literally this function. The manual name is the Kernel API Manual and yes it's giving official 🎀

🌸 NAME 🌸

xe_sriov_vfio_stop_copy_size — get a size estimate of VF device migration data 💖 (that's the whole vibe: an estimate of the size, in bytes, of the data involved in VF device migration, no cap)

✨ SYNOPSIS ✨

ssize_t xe_sriov_vfio_stop_copy_size (struct xe_device *xe , unsigned
       int vfid );

That's it, that's the call. Copy it exactly, character for character, bestie — I'm not about to let you mistype a parameter name 🫶

🦋 ARGUMENTS 🦋

  • xe — the PF xe_device, and listen, you gotta get this one by calling xe_sriov_vfio_get_pf. No sneaky shortcuts. 👑
  • vfid — the VF identifier. And here's the thing, the way that it can't be 0. That's not a suggestion, that's the rule. 💀

🌈 RETURN 🌈

It hands you the migration data size in bytes 🎀 — or, if things go sideways, a negative error code on failure. So if you see a negative number, don't celebrate, that's your signal that it did not slay 😭

👑 SEE ALSO 👑

Like, the whole friend group, fr fr — every single one of those (9) references is in the list and we are not leaving anyone out 🧚

Quick vibe check: vfid can't be 0. Not "probably shouldn't." Can't. 💅

Sign-off time, bestie 🍓 — this lil page came out of ./include/drm/intel, dated October 2026, and it answers to the name xe_sriov_vfi...op_copy_size(9). Iconic, honestly. Periodt. 🔥

📦 where this page comes from