feat(stack,runtime): pool-recycle DONTNEED above the retained entry end (RFC 019 §6)

- stack::retain_range: pure checked span fn (retain page-up = zap less;
  None when retain covers the reserve, so the 64 KiB default config never
  pays a syscall) + 6 adversarial units mirroring shrink_range's.
- Stack::recycle_zap: advisory MADV_DONTNEED of [usable_base, top-RETAIN);
  stack is unowned at the call site, synchronous eager zap races nothing.
- recycle_stack: zap OFF-LOCK before pool admission (acquire_stack's
  no-syscall-under-the-pool-lock invariant); rare cap-overflow pays a
  wasted zap ahead of munmap, accepted over a second lock round-trip.
- pub const RECYCLE_RETAIN = 64 KiB beside the shrink knobs, ratified-as-
  constant rationale in doc.
- tests/stack_recycle.rs: mincore-based exact-zero-resident assert over
  the zap span. smaps was tried first and over-counts: a neighboring rw
  anon VMA can merge flush against the stack top (observed once under the
  full-suite run); the PROT_NONE guard pins the usable base exactly.

FLAGGED (Claude-solo calls):
- RFC §6 'above the bottom RETAIN' is direction-ambiguous in address
  terms; implemented as retain the ENTRY end (highest addresses, the
  pages the next actor faults first), zap the cold deep span below.
- Const named RECYCLE_RETAIN (RFC says RETAIN) to sit beside SHRINK_*.
This commit is contained in:
Claude (sandbox)
2026-08-08 16:13:53 +00:00
parent 8225716b11
commit 7d8b9e0310
3 changed files with 226 additions and 1 deletions
+123
View File
@@ -0,0 +1,123 @@
//! RFC 019 commit 5 — pool recycle zaps a dead stack down to its retained
//! entry end, observed from the outside.
//!
//! A default-shaped stack that spiked deep and then died must not carry its
//! spike into the pool as resident RSS: `recycle_stack` DONTNEEDs everything
//! below the top `RECYCLE_RETAIN` bytes before pushing. The zap is
//! synchronous on the death path, so the drop is immediate — but the death
//! path itself races the observer's `join` return, hence the brief poll.
//!
//! Residency is measured with `mincore`, not smaps: a neighboring rw anon
//! mapping can land flush against the stack top and the kernel merges the
//! VMAs (observed under the full test run), so per-mapping smaps fields
//! over-count. The PROT_NONE guard below can never merge, so the usable
//! base is exactly the anchor VMA's start, and `mincore` counts pages
//! within [usable_base, usable_base + reserve) regardless of merging.
use smarm::runtime::{Config, RECYCLE_RETAIN};
use smarm::{channel, spawn, yield_now};
const RESERVE: usize = 4 * 1024 * 1024;
/// Burn ~`frames` × 4 KiB of stack, dirtying every frame.
#[inline(never)]
fn burn_stack(frames: usize) -> u64 {
let mut local = [0u8; 4096];
local[0] = frames as u8;
let below = if frames == 0 { 0 } else { burn_stack(frames - 1) };
std::hint::black_box(&mut local);
below.wrapping_add(local[0] as u64)
}
/// Resident-page count over [lo, lo + len) via mincore (len page-aligned).
fn resident_pages(lo: usize, len: usize) -> usize {
let page = 4096;
let mut vec = vec![0u8; len / page];
let ret = unsafe {
libc::mincore(lo as *mut libc::c_void, len, vec.as_mut_ptr())
};
assert_eq!(ret, 0, "mincore failed: {}", std::io::Error::last_os_error());
vec.iter().filter(|&&b| b & 1 != 0).count()
}
/// The [start, end) of the VMA containing `addr`.
fn vma_containing(addr: usize) -> (usize, usize) {
let maps = std::fs::read_to_string("/proc/self/maps").unwrap();
for line in maps.lines() {
if let Some((range, _)) = line.split_once(' ') {
if let Some((a, b)) = range.split_once('-') {
if let (Ok(start), Ok(end)) =
(usize::from_str_radix(a, 16), usize::from_str_radix(b, 16))
{
if start <= addr && addr < end {
return (start, end);
}
}
}
}
}
panic!("no VMA contains {addr:#x}");
}
fn vma_exists(addr: usize) -> bool {
let maps = std::fs::read_to_string("/proc/self/maps").unwrap();
for line in maps.lines() {
if let Some((range, _)) = line.split_once(' ') {
if let Some((a, b)) = range.split_once('-') {
if let (Ok(start), Ok(end)) =
(usize::from_str_radix(a, 16), usize::from_str_radix(b, 16))
{
if start <= addr && addr < end {
return true;
}
}
}
}
}
false
}
#[test]
fn recycle_zaps_dead_stack_down_to_retain() {
// Default reserve raised so the pool holds big stacks (default-shaped ⇒
// pooled) and the zap has something to bite; single scheduler.
let rt = smarm::runtime::init(Config::exact(1).stack_reserve(RESERVE));
rt.run(|| {
let (tx, rx) = channel::<usize>();
let h = spawn(move || {
let probe = 0u8;
let anchor = &probe as *const u8 as usize;
// The guard below is PROT_NONE and can never merge with the
// usable region, so the anchor VMA's start IS the usable base.
let (vlo, _) = vma_containing(anchor);
// Dirty ~3 MiB of the 4 MiB reserve, then die.
std::hint::black_box(burn_stack(768));
tx.send(vlo).unwrap();
});
let usable_base = rx.recv().unwrap();
h.join().unwrap();
// The zap span is everything below the retained entry end. DONTNEED
// on private anon discards synchronously and unconditionally, so
// this must go to exactly zero resident pages; the poll only covers
// the death path racing join's return.
let zap_len = RESERVE - RECYCLE_RETAIN;
let mut resident = usize::MAX;
for _ in 0..10_000 {
resident = resident_pages(usable_base, zap_len);
if resident == 0 {
break;
}
yield_now();
}
assert_eq!(
resident, 0,
"recycled stack's zap span still resident: {resident} pages in \
[{usable_base:#x}, +{zap_len:#x})"
);
// Pooled, not munmapped: the mapping must still be there.
assert!(vma_exists(usable_base), "default-shaped stack was unmapped instead of pooled");
});
}