smp_mb__afte..._read_unlock(9)

📦 version 7.3.1, in nixpkgs unstable

💅 smp_mb__after_srcu_read_unlock(9) — NAME 💅

okay so bestie, this is the page for smp_mb__after_srcu_read_unlock — and yes, it lives in the Kernel API Manual (the header up top literally gets cut off to smp_mb__afte..._read_unlock(9) because the terminal ran out of room 😭 icon behaviour honestly).

What does it do? It ensures full ordering after srcu_read_unlock. That's the whole vibe check. 🎀

✨ SYNOPSIS ✨

void smp_mb__after_srcu_read_unlock (void );

🫶 ARGUMENTS 🫶

  • void — no arguments. none. zero. it takes nothing. it just shows up, does the barrier, and leaves 👑

🌸 DESCRIPTION 🌸

So here's the tea ☕: this function converts the preceding srcu_read_unlock into a two-way memory barrier. That's it. That's the whole function. Lowkey iconic.

Call this after srcu_read_unlock, and it guarantees that all memory operations that occur after smp_mb__after_srcu_read_unlock will appear to happen after the preceding srcu_read_unlock. Like, the CPU is not gonna reorder your stuff behind your back, periodt 💀✨

ordering flirting: the unlock comes first, the barrier makes sure nobody sneaks past it — the memory ordering is literally not beating the allegations 🦋

💜 SEE ALSO 💜

Kernel file ./include/linux/srcu.h — home of all this goodness:

that's the whole friend group right there, go say hi 🧚💖

✨ bye bestie ✨ — this page came from the ./include/linux corner of the source tree, dated October 2026, and the footer still spells the name smp_mb__afte..._read_unlock(9) because truncation is forever 🙈💅 go forth and be memory-ordered 🎀

📦 where this page comes from