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/mm/sc-debugfs.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 61 insertions(+) create mode 100644 arch/mips/mm/sc-debugfs.c (limited to 'arch/mips/mm/sc-debugfs.c') diff --git a/arch/mips/mm/sc-debugfs.c b/arch/mips/mm/sc-debugfs.c new file mode 100644 index 000000000..80ff39471 --- /dev/null +++ b/arch/mips/mm/sc-debugfs.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2015 Imagination Technologies + * Author: Paul Burton + */ + +#include +#include +#include +#include +#include + +static ssize_t sc_prefetch_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + bool enabled = bc_prefetch_is_enabled(); + char buf[3]; + + buf[0] = enabled ? 'Y' : 'N'; + buf[1] = '\n'; + buf[2] = 0; + + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t sc_prefetch_write(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + bool enabled; + int err; + + err = kstrtobool_from_user(user_buf, count, &enabled); + if (err) + return err; + + if (enabled) + bc_prefetch_enable(); + else + bc_prefetch_disable(); + + return count; +} + +static const struct file_operations sc_prefetch_fops = { + .open = simple_open, + .llseek = default_llseek, + .read = sc_prefetch_read, + .write = sc_prefetch_write, +}; + +static int __init sc_debugfs_init(void) +{ + struct dentry *dir; + + dir = debugfs_create_dir("l2cache", mips_debugfs_dir); + debugfs_create_file("prefetch", S_IRUGO | S_IWUSR, dir, NULL, + &sc_prefetch_fops); + return 0; +} +late_initcall(sc_debugfs_init); -- cgit v1.3.1