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/powerpc/boot/util.S | 67 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) create mode 100644 arch/powerpc/boot/util.S (limited to 'arch/powerpc/boot/util.S') diff --git a/arch/powerpc/boot/util.S b/arch/powerpc/boot/util.S new file mode 100644 index 000000000..6a92376da --- /dev/null +++ b/arch/powerpc/boot/util.S @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copied from + * + * This file contains miscellaneous low-level functions. + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Largely rewritten by Cort Dougan (cort@cs.nmt.edu) + * and Paul Mackerras. + * + * kexec bits: + * Copyright (C) 2002-2003 Eric Biederman + * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz + */ +#include "ppc_asm.h" + +#define SPRN_PVR 0x11F /* Processor Version Register */ + + .text + +/* udelay needs to know the period of the + * timebase in nanoseconds. This used to be hardcoded to be 60ns + * (period of 66MHz/4). Now a variable is used that is initialized to + * 60 for backward compatibility, but it can be overridden as necessary + * with code something like this: + * extern unsigned long timebase_period_ns; + * timebase_period_ns = 1000000000 / bd->bi_tbfreq; + */ + .data + .globl timebase_period_ns +timebase_period_ns: + .long 60 + + .text +/* + * Delay for a number of microseconds + */ + .globl udelay +udelay: + mulli r4,r3,1000 /* nanoseconds */ + /* Change r4 to be the number of ticks using: + * (nanoseconds + (timebase_period_ns - 1 )) / timebase_period_ns + * timebase_period_ns defaults to 60 (16.6MHz) */ + mflr r5 + bcl 20,31,0f +0: mflr r6 + mtlr r5 + addis r5,r6,(timebase_period_ns-0b)@ha + lwz r5,(timebase_period_ns-0b)@l(r5) + add r4,r4,r5 + addi r4,r4,-1 + divw r4,r4,r5 /* BUS ticks */ +1: MFTBU(r5) + MFTBL(r6) + MFTBU(r7) + cmpw 0,r5,r7 + bne 1b /* Get [synced] base time */ + addc r9,r6,r4 /* Compute end time */ + addze r8,r5 +2: MFTBU(r5) + cmpw 0,r5,r8 + blt 2b + bgt 3f + MFTBL(r6) + cmpw 0,r6,r9 + blt 2b +3: blr -- cgit v1.3.1