xe_hw_engine...ting_lr_jobs(9)

💅 NAME

xe_hw_engine_group_resume_faulting_lr_jobs — bestie, this one asynchronously resumes the hw engine group's faulting LR jobs. Like, it doesn't sit around waiting, it just pokes them awake and goes about its day. Iconic behaviour honestly ✨

So yeah — this is a page from the Kernel API Manual (yes the Kernel API Manual, we're in the big leagues now), and it's about kicking those LR jobs that tripped over themselves back into gear. No cap.

✨ SYNOPSIS

void xe_hw_engine_group_resume_faulting_lr_jobs (struct xe_hw_engine_group *group );

Returns void — nothing comes back out, it just does the thing 🫶

🎀 ARGUMENTS

• group — the hw engine group 💖 literally just the group. That's the whole vibe check.

🦋 SEE ALSO

Kernel file ./drivers/gpu/drm/xe/xe_hw_engine_group.c — that's where the actual source lives, go read it, iykyk 📖

And the whole friend group of related functions, all hanging out together:

• xe_hw_engine_setup_groups(9)
• xe_hw_engine_group_add_exec_queue(9)
• xe_hw_engine_group_del_exec_queue(9)
• xe_hw_engine_group_suspend_faulting_lr_jobs(9)
• xe_hw_engine_group_wait_for_dma_fence_jobs(9)
• xe_hw_engine_group_get_mode(9)
• xe_hw_engine_group_put(9)
• xe_hw_engine_group_find_exec_mode(9)

Fr fr go check the sibling pages too — suspend_faulting_lr_jobs is literally the mirror of this one, so if you're confused here, she'll explain the whole dynamic 💀

🌸 Okay that's the whole page, mwah 💋 Source/version is ./drivers/gpu/drm/xe and the date stamp says October 2026, and the page name is, once more with feeling, xe_hw_engine...ting_lr_jobs(9). Slay, bye 👑