From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug alb_break_llc() decides whether to break LLC preference during active load balance. It does so by testing that every runnable fair task on the source rq prefers its LLC: env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable But the two counters cover different sets. nr_pref_llc_running is updated in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued, so it follows queued tasks. h_nr_runnable is updated in set_delayed()/ clear_delayed() and drops delay-dequeued tasks. So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks, alb_break_llc() returns false, and active balance is free to pull a task off its preferred LLC. Active balance only moves runnable tasks, and this is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB skips the per-task test in can_migrate_task(). The runnable set is the one we want. Fix it on the counter side. A task should be counted in nr_pref_llc_running exactly while it is both queued on its preferred LLC (pref_llc_queued) and runnable (!sched_delayed). Define that membership once in task_pref_llc_runnable(), and adjust the counter only through pref_llc_running_inc()/pref_llc_running_dec() from the four sites that change either input: account_llc_enqueue(), account_llc_dequeue(), set_delayed() and clear_delayed(). Gating every update on the same predicate keeps the delay, wake and dequeue paths from double-counting or underflowing; see the comments at those sites for the ordering. nr_llc_running and sd->llc_counts are not touched and stay on queued semantics. Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC") Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/ Reported-by: Zhan Xusheng Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- scripts/syscalltbl.sh | 92 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 92 insertions(+) create mode 100755 scripts/syscalltbl.sh (limited to 'scripts/syscalltbl.sh') diff --git a/scripts/syscalltbl.sh b/scripts/syscalltbl.sh new file mode 100755 index 000000000..6a903b87a --- /dev/null +++ b/scripts/syscalltbl.sh @@ -0,0 +1,92 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-only +# +# Generate a syscall table header. +# +# Each line of the syscall table should have the following format: +# +# NR ABI NAME [NATIVE] [COMPAT] +# +# NR syscall number +# ABI ABI name +# NAME syscall name +# NATIVE native entry point (optional) +# COMPAT compat entry point (optional) + +set -e + +usage() { + echo >&2 "usage: $0 [--abis ABIS] INFILE OUTFILE" >&2 + echo >&2 + echo >&2 " INFILE input syscall table" + echo >&2 " OUTFILE output header file" + echo >&2 + echo >&2 "options:" + echo >&2 " --abis ABIS ABI(s) to handle (By default, all lines are handled)" + exit 1 +} + +# default unless specified by options +abis= + +while [ $# -gt 0 ] +do + case $1 in + --abis) + abis=$(echo "($2)" | tr ',' '|') + shift 2;; + -*) + echo "$1: unknown option" >&2 + usage;; + *) + break;; + esac +done + +if [ $# -ne 2 ]; then + usage +fi + +infile="$1" +outfile="$2" + +nxt=0 + +grep -E "^[0-9]+[[:space:]]+$abis" "$infile" | { + + while read nr abi name native compat noreturn; do + + if [ $nxt -gt $nr ]; then + echo "error: $infile: syscall table is not sorted or duplicates the same syscall number" >&2 + exit 1 + fi + + while [ $nxt -lt $nr ]; do + echo "__SYSCALL($nxt, sys_ni_syscall)" + nxt=$((nxt + 1)) + done + + if [ "$compat" = "-" ]; then + unset compat + fi + + if [ -n "$noreturn" ]; then + if [ "$noreturn" != "noreturn" ]; then + echo "error: $infile: invalid string \"$noreturn\" in 'noreturn' column" + exit 1 + fi + if [ -n "$compat" ]; then + echo "__SYSCALL_COMPAT_NORETURN($nr, $native, $compat)" + else + echo "__SYSCALL_NORETURN($nr, $native)" + fi + elif [ -n "$compat" ]; then + echo "__SYSCALL_WITH_COMPAT($nr, $native, $compat)" + elif [ -n "$native" ]; then + echo "__SYSCALL($nr, $native)" + else + echo "__SYSCALL($nr, sys_ni_syscall)" + fi + nxt=$((nr + 1)) + done +} > "$outfile" -- cgit v1.3.1