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 --- include/asm-generic/bitops.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/asm-generic/bitops.h (limited to 'include/asm-generic/bitops.h') diff --git a/include/asm-generic/bitops.h b/include/asm-generic/bitops.h new file mode 100644 index 000000000..a47b8a71d --- /dev/null +++ b/include/asm-generic/bitops.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_GENERIC_BITOPS_H +#define __ASM_GENERIC_BITOPS_H + +/* + * For the benefit of those who are trying to port Linux to another + * architecture, here are some C-language equivalents. They should + * generate reasonable code, so take a look at what your compiler spits + * out before rolling your own buggy implementation in assembly language. + * + * C language equivalents written by Theodore Ts'o, 9/26/92 + */ + +#include +#include +#include + +#include +#include +#include +#include +#include + +#ifndef _LINUX_BITOPS_H +#error only can be included directly +#endif + +#include +#include +#include +#include + +#include +#include +#include +#include + +#endif /* __ASM_GENERIC_BITOPS_H */ -- cgit v1.3.1