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, 119 insertions, 0 deletions

diff --git a/tools/perf/util/clockid.c b/tools/perf/util/clockid.c
new file mode 100644
index 000000000..74365a5d9
--- /dev/null
+++ b/tools/perf/util/clockid.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <subcmd/parse-options.h>
+#include <stdio.h>
+#include <time.h>
+#include <strings.h>
+#include <linux/time64.h>
+#include "debug.h"
+#include "clockid.h"
+#include "record.h"
+
+struct clockid_map {
+	const char *name;
+	int clockid;
+};
+
+#define CLOCKID_MAP(n, c)	\
+	{ .name = n, .clockid = (c), }
+
+#define CLOCKID_END	{ .name = NULL, }
+
+
+/*
+ * Add the missing ones, we need to build on many distros...
+ */
+#ifndef CLOCK_MONOTONIC_RAW
+#define CLOCK_MONOTONIC_RAW 4
+#endif
+#ifndef CLOCK_BOOTTIME
+#define CLOCK_BOOTTIME 7
+#endif
+#ifndef CLOCK_TAI
+#define CLOCK_TAI 11
+#endif
+
+static const struct clockid_map clockids[] = {
+	/* available for all events, NMI safe */
+	CLOCKID_MAP("monotonic", CLOCK_MONOTONIC),
+	CLOCKID_MAP("monotonic_raw", CLOCK_MONOTONIC_RAW),
+
+	/* available for some events */
+	CLOCKID_MAP("realtime", CLOCK_REALTIME),
+	CLOCKID_MAP("boottime", CLOCK_BOOTTIME),
+	CLOCKID_MAP("tai", CLOCK_TAI),
+
+	/* available for the lazy */
+	CLOCKID_MAP("mono", CLOCK_MONOTONIC),
+	CLOCKID_MAP("raw", CLOCK_MONOTONIC_RAW),
+	CLOCKID_MAP("real", CLOCK_REALTIME),
+	CLOCKID_MAP("boot", CLOCK_BOOTTIME),
+
+	CLOCKID_END,
+};
+
+static int get_clockid_res(clockid_t clk_id, u64 *res_ns)
+{
+	struct timespec res;
+
+	*res_ns = 0;
+	if (!clock_getres(clk_id, &res))
+		*res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC;
+	else
+		pr_warning("WARNING: Failed to determine specified clock resolution.\n");
+
+	return 0;
+}
+
+int parse_clockid(const struct option *opt, const char *str, int unset)
+{
+	struct record_opts *opts = (struct record_opts *)opt->value;
+	const struct clockid_map *cm;
+	const char *ostr = str;
+
+	if (unset) {
+		opts->use_clockid = 0;
+		return 0;
+	}
+
+	/* no arg passed */
+	if (!str)
+		return 0;
+
+	/* no setting it twice */
+	if (opts->use_clockid)
+		return -1;
+
+	opts->use_clockid = true;
+
+	/* if its a number, we're done */
+	if (sscanf(str, "%d", &opts->clockid) == 1)
+		return get_clockid_res(opts->clockid, &opts->clockid_res_ns);
+
+	/* allow a "CLOCK_" prefix to the name */
+	if (!strncasecmp(str, "CLOCK_", 6))
+		str += 6;
+
+	for (cm = clockids; cm->name; cm++) {
+		if (!strcasecmp(str, cm->name)) {
+			opts->clockid = cm->clockid;
+			return get_clockid_res(opts->clockid,
+					       &opts->clockid_res_ns);
+		}
+	}
+
+	opts->use_clockid = false;
+	ui__warning("unknown clockid %s, check man page\n", ostr);
+	return -1;
+}
+
+const char *clockid_name(clockid_t clk_id)
+{
+	const struct clockid_map *cm;
+
+	for (cm = clockids; cm->name; cm++) {
+		if (cm->clockid == clk_id)
+			return cm->name;
+	}
+	return "(not found)";
+}