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 --- net/wireless/tests/util.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 net/wireless/tests/util.c (limited to 'net/wireless/tests/util.c') diff --git a/net/wireless/tests/util.c b/net/wireless/tests/util.c new file mode 100644 index 000000000..118f7fb42 --- /dev/null +++ b/net/wireless/tests/util.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KUnit fixture to have a (configurable) wiphy + * + * Copyright (C) 2023 Intel Corporation + */ +#include +#include +#include +#include +#include "util.h" + +int t_wiphy_init(struct kunit_resource *resource, void *ctx) +{ + struct kunit *test = kunit_get_current_test(); + struct cfg80211_ops *ops; + struct wiphy *wiphy; + struct t_wiphy_priv *priv; + + ops = kzalloc_obj(*ops); + KUNIT_ASSERT_NOT_NULL(test, ops); + + wiphy = wiphy_new_nm(ops, sizeof(*priv), "kunit"); + KUNIT_ASSERT_NOT_NULL(test, wiphy); + + priv = wiphy_priv(wiphy); + priv->ctx = ctx; + priv->ops = ops; + + /* Initialize channels, feel free to add more here channels/bands */ + memcpy(priv->channels_2ghz, channels_2ghz, sizeof(channels_2ghz)); + wiphy->bands[NL80211_BAND_2GHZ] = &priv->band_2ghz; + priv->band_2ghz.channels = priv->channels_2ghz; + priv->band_2ghz.n_channels = ARRAY_SIZE(channels_2ghz); + + resource->data = wiphy; + resource->name = "wiphy"; + + return 0; +} + +void t_wiphy_exit(struct kunit_resource *resource) +{ + struct t_wiphy_priv *priv; + struct cfg80211_ops *ops; + + priv = wiphy_priv(resource->data); + ops = priv->ops; + + /* Should we ensure anything about the state here? + * e.g. full destruction or no calls to any ops on destruction? + */ + + wiphy_free(resource->data); + kfree(ops); +} -- cgit v1.3.1