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 --- arch/mips/lib/delay.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+) create mode 100644 arch/mips/lib/delay.c (limited to 'arch/mips/lib/delay.c') diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c new file mode 100644 index 000000000..ccdb1fc1e --- /dev/null +++ b/arch/mips/lib/delay.c @@ -0,0 +1,68 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1994 by Waldorf Electronics + * Copyright (C) 1995 - 2000, 01, 03 by Ralf Baechle + * Copyright (C) 1999, 2000 Silicon Graphics, Inc. + * Copyright (C) 2007, 2014 Maciej W. Rozycki + */ +#include +#include +#include +#include +#include + +#include +#include + +#ifndef CONFIG_CPU_DADDI_WORKAROUNDS +#define GCC_DADDI_IMM_ASM() "I" +#else +#define GCC_DADDI_IMM_ASM() "r" +#endif + +#ifndef CONFIG_HAVE_PLAT_DELAY + +void __delay(unsigned long loops) +{ + __asm__ __volatile__ ( + " .set noreorder \n" + " .align 3 \n" + "1: bnez %0, 1b \n" + " " __stringify(LONG_SUBU) " %0, %1 \n" + " .set reorder \n" + : "=r" (loops) + : GCC_DADDI_IMM_ASM() (1), "0" (loops)); +} +EXPORT_SYMBOL(__delay); + +/* + * Division by multiplication: you don't have to worry about + * loss of precision. + * + * Use only for very small delays ( < 1 msec). Should probably use a + * lookup table, really, as the multiplications take much too long with + * short delays. This is a "reasonable" implementation, though (and the + * first constant multiplications gets optimized away if the delay is + * a constant) + */ + +void __udelay(unsigned long us) +{ + unsigned int lpj = raw_current_cpu_data.udelay_val; + + __delay((us * 0x000010c7ull * HZ * lpj) >> 32); +} +EXPORT_SYMBOL(__udelay); + +void __ndelay(unsigned long ns) +{ + unsigned int lpj = raw_current_cpu_data.udelay_val; + + __delay((ns * 0x00000005ull * HZ * lpj) >> 32); +} +EXPORT_SYMBOL(__ndelay); + +#endif -- cgit v1.3.1