sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted

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 <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com

1 files changed, 64 insertions, 0 deletions

diff --git a/tools/perf/bench/futex.c b/tools/perf/bench/futex.c
new file mode 100644
index 000000000..1968c9d00
--- /dev/null
+++ b/tools/perf/bench/futex.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <err.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/prctl.h>
+
+#include "futex.h"
+
+#ifndef PR_FUTEX_HASH
+#define PR_FUTEX_HASH                   78
+# define PR_FUTEX_HASH_SET_SLOTS        1
+# define PR_FUTEX_HASH_GET_SLOTS        2
+#endif // PR_FUTEX_HASH
+
+void futex_set_nbuckets_param(struct bench_futex_parameters *params)
+{
+	int ret;
+
+	if (params->nbuckets < 0)
+		return;
+
+	ret = prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_SET_SLOTS, params->nbuckets, 0);
+	if (ret) {
+		printf("Requesting %d hash buckets failed: %d/%m\n",
+		       params->nbuckets, ret);
+		err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)");
+	}
+}
+
+void futex_print_nbuckets(struct bench_futex_parameters *params)
+{
+	char *futex_hash_mode;
+	int ret;
+
+	ret = prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_GET_SLOTS);
+	if (params->nbuckets >= 0) {
+		if (ret != params->nbuckets) {
+			if (ret < 0) {
+				printf("Can't query number of buckets: %m\n");
+				err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)");
+			}
+			printf("Requested number of hash buckets does not currently used.\n");
+			printf("Requested: %d in usage: %d\n", params->nbuckets, ret);
+			err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)");
+		}
+		if (params->nbuckets == 0)
+			ret = asprintf(&futex_hash_mode, "Futex hashing: global hash");
+		else
+			ret = asprintf(&futex_hash_mode, "Futex hashing: %d hash buckets",
+				       params->nbuckets);
+	} else {
+		if (ret <= 0) {
+			ret = asprintf(&futex_hash_mode, "Futex hashing: global hash");
+		} else {
+			ret = asprintf(&futex_hash_mode, "Futex hashing: auto resized to %d buckets",
+				       ret);
+		}
+	}
+	if (ret < 0)
+		err(EXIT_FAILURE, "ENOMEM, futex_hash_mode");
+	printf("%s\n", futex_hash_mode);
+	free(futex_hash_mode);
+}