scx_discard..._ecaps_syncs(9)

💅 scx_discard_stale_ecaps_syncs(9) 💅

okay bestie, welcome to the Kernel API Manual ✨ this one's a tiny little function with a big job and honestly? she's giving cleanup crew main character energy 🧹💖

---

🌸 NAME 🌸

scx_discard_stale_ecaps_syncs — literally just throws away ecaps syncs that got left behind by schedulers from before 🗑️✨ no cap.

---

🦋 SYNOPSIS 🦋

void scx_discard_stale_ecaps_syncs (void );

that's it. that's the whole vibe. 🎀

---

🍓 ARGUMENTS 🍓

• void — no arguments, babe. nothing. zero. she takes nothing and she gives you a clean slate 🫶

---

🔥 DESCRIPTION 🔥

so here's the tea ☕ — you call this bad girl during root enable, before the scheduler goes live. like, right before the party starts 🎉

the situation is this: an earlier root's sub-sched might not have made it through its RCU free path yet (for example, a still-open link fd defers it 😭), and that can leave queued ecaps syncs just… sitting there. abandoned. orphaned. lowkey haunting the place 👻

and yes, technically you could process them — but that would mean decoding the dead sched's pshards using the current cid layout, which is a whole mess and not the vibe at all 💀 so no. we don't do that. we discard them instead. bye bestie 👋

the good news? the backing scx_sched_pcpu's are still allocated, because the free path removes ecaps_to_sync_node before freeing. so nothing's dangling, we're safe, we're slaying, periodt 💅✨

ngl this is one of those "do it in the right place at the right time or everything gets weird" functions — the ordering genuinely matters, don't improvise 🙈

---

🌈 SEE ALSO 🌈

okay so if you wanna go down the rabbit hole, the kernel file lives at ./kernel/sched/ext/sub.c and here's the whole friend group 👑💜

• scx_skip_subtree_pre(9)
• scx_next_descendant_pre(9)
• scx_rescue_charge(9)
• scx_rescue_end(9)
• scx_rescue_keep(9)
• scx_rescue_accrue(9)
• scx_rescue_admit(9)
• scx_rescue_try_admit(9)
• scx_rescue_check_overload(9)
• scx_rescue_timerfn(9)
• scx_resolve_local_dsq(9)
• queue_sync_ecaps(9)
• scx_process_sync_ecaps(9)
• scx_unbypass_replay_ecaps(9)
• scx_rehome_task(9)
• scx_punt_task(9)
• scx_cgroup_claim_subtree(9)
• scx_cgroup_return_subtree(9)
• scx_cgroup_task_migrating(9)
• scx_cgroup_task_migrated(9)
• scx_cgroup_task_migrate_canceled(9)
• scx_bpf_sub_dispatch(9)
• scx_bpf_sub_grant(9)
• scx_bpf_sub_revoke(9)
• scx_bpf_sub_caps(9)
• scx_bpf_sub_kill_bstr(9)

---

and that's the whole page, bestie!! 🫶✨ this lil icon comes from ./kernel/sched/ext, dated October 2026, and yeah — the manpage name is still scx_discard..._ecaps_syncs(9) if you need to cite her in a paper or whatever 📚💖 mwah, go read some kernel source, ily 💜🎀