synchronize_rcu_tasks(9)

✨ synchronize_rcu_tasks(9) ✨

okay bestie, this is synchronize_rcu_tasks(9) from the Kernel API Manual — and it's lowkey iconic. fr fr, let's get into it.

💖 NAME 💖

synchronize_rcu_tasks — wait until an rcu-tasks grace period has elapsed. That's it. That's the whole mission. 👑

🌸 SYNOPSIS 🌸

void synchronize_rcu_tasks (void );

🎀 ARGUMENTS 🎀

• void — no arguments. literally none. zero. the voidest void. 🫶

🦋 DESCRIPTION 🦋

So here's the tea, bestie: control will return to the caller some time after a full rcu-tasks grace period has elapsed. In other words? After all currently executing rcu-tasks read-side critical sections have elapsed. periodt. 💅

These read-side critical sections are delimited by calls to schedule, cond_resched_tasks_rcu_qs, idle execution, userspace execution, calls to synchronize_rcu_tasks, and — (in theory, anyway) — cond_resched. yes, cond_resched is in the group chat too, but the page says "in theory, anyway," so we're keeping that energy. 🙈

This is a very specialized primitive. Like, niche niche. It is intended only for a few uses in tracing and other situations requiring manipulation of function preambles and profiling hooks. So don't just sprinkle it on everything like glitter. ✨

The synchronize_rcu_tasks function is not (yet) intended for heavy use from multiple CPUs. Not yet. The "yet" is doing a lot of work there. 😭

For more detailed information on memory ordering guarantees, see the description of synchronize_rcu. That's where the receipts live. 🔥

🌈 SEE ALSO 🌈

• Kernel file ./kernel/rcu/tasks.h — also struct rcu_tasks_percpu(9), struct rcu_tasks(9), call_rcu_tasks(9), rcu_barrier_tasks(9), synchronize_rcu_tasks_rude(9).

cute sign-off: shoutout to source/version ./kernel/rcu and the October 2026 date stamp. mwah 💋