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, 142 insertions, 0 deletions

diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
new file mode 100644
index 000000000..8cf71bea2
--- /dev/null
+++ b/tools/perf/util/target.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Helper functions for handling target threads/cpus
+ *
+ * Copyright (C) 2012, LG Electronics, Namhyung Kim <namhyung.kim@lge.com>
+ */
+
+#include "target.h"
+
+#include <pwd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+
+enum target_errno target__validate(struct target *target)
+{
+	enum target_errno ret = TARGET_ERRNO__SUCCESS;
+
+	if (target->pid)
+		target->tid = target->pid;
+
+	/* CPU and PID are mutually exclusive */
+	if (target->tid && target->cpu_list) {
+		target->cpu_list = NULL;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__PID_OVERRIDE_CPU;
+	}
+
+	/* PID and SYSTEM are mutually exclusive */
+	if (target->tid && target->system_wide) {
+		target->system_wide = false;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__PID_OVERRIDE_SYSTEM;
+	}
+
+	/* BPF and CPU are mutually exclusive */
+	if (target->bpf_str && target->cpu_list) {
+		target->cpu_list = NULL;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__BPF_OVERRIDE_CPU;
+	}
+
+	/* BPF and PID/TID are mutually exclusive */
+	if (target->bpf_str && target->tid) {
+		target->tid = NULL;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__BPF_OVERRIDE_PID;
+	}
+
+	/* BPF and THREADS are mutually exclusive */
+	if (target->bpf_str && target->per_thread) {
+		target->per_thread = false;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__BPF_OVERRIDE_THREAD;
+	}
+
+	/* THREAD and SYSTEM/CPU are mutually exclusive */
+	if (target->per_thread && (target->system_wide || target->cpu_list)) {
+		target->per_thread = false;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD;
+	}
+
+	return ret;
+}
+
+uid_t parse_uid(const char *str)
+{
+	struct passwd pwd, *result;
+	char buf[1024];
+
+	if (str == NULL)
+		return UINT_MAX;
+
+	/* Try user name first */
+	getpwnam_r(str, &pwd, buf, sizeof(buf), &result);
+
+	if (result == NULL) {
+		/*
+		 * The user name not found. Maybe it's a UID number.
+		 */
+		char *endptr;
+		int uid = strtol(str, &endptr, 10);
+
+		if (*endptr != '\0')
+			return UINT_MAX;
+
+		getpwuid_r(uid, &pwd, buf, sizeof(buf), &result);
+
+		if (result == NULL)
+			return UINT_MAX;
+	}
+
+	return result->pw_uid;
+}
+
+/*
+ * This must have a same ordering as the enum target_errno.
+ */
+static const char *target__error_str[] = {
+	"PID/TID switch overriding CPU",
+	"PID/TID switch overriding SYSTEM",
+	"SYSTEM/CPU switch overriding PER-THREAD",
+	"BPF switch overriding CPU",
+	"BPF switch overriding PID/TID",
+	"BPF switch overriding THREAD",
+};
+
+int target__strerror(struct target *target __maybe_unused, int errnum,
+			  char *buf, size_t buflen)
+{
+	int idx;
+	const char *msg;
+
+	BUG_ON(buflen == 0);
+
+	if (errnum >= 0) {
+		str_error_r(errnum, buf, buflen);
+		return 0;
+	}
+
+	if (errnum <  __TARGET_ERRNO__START || errnum >= __TARGET_ERRNO__END)
+		return -1;
+
+	idx = errnum - __TARGET_ERRNO__START;
+	msg = target__error_str[idx];
+
+	switch (errnum) {
+	case TARGET_ERRNO__PID_OVERRIDE_CPU ...
+	     TARGET_ERRNO__BPF_OVERRIDE_THREAD:
+		snprintf(buf, buflen, "%s", msg);
+		break;
+
+	default:
+		/* cannot reach here */
+		break;
+	}
+
+	return 0;
+}