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, 118 insertions, 0 deletions

diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
new file mode 100644
index 000000000..1dd73ed6b
--- /dev/null
+++ b/tools/perf/builtin-data.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <stdio.h>
+#include <string.h>
+#include "builtin.h"
+#include "debug.h"
+#include <subcmd/parse-options.h>
+#include "data-convert.h"
+#include "util/util.h"
+
+typedef int (*data_cmd_fn_t)(int argc, const char **argv);
+
+struct data_cmd {
+	const char	*name;
+	const char	*summary;
+	data_cmd_fn_t	fn;
+};
+
+static struct data_cmd data_cmds[];
+
+#define for_each_cmd(cmd) \
+	for (cmd = data_cmds; cmd && cmd->name; cmd++)
+
+static const char * const data_subcommands[] = { "convert", NULL };
+
+static const char *data_usage[] = {
+	"perf data convert [<options>]",
+	NULL
+};
+
+static const char *to_json;
+static const char *to_ctf;
+static struct perf_data_convert_opts opts = {
+	.force = false,
+	.all = false,
+	.time_str = NULL,
+};
+
+static const struct option data_options[] = {
+		OPT_INCR('v', "verbose", &verbose, "be more verbose"),
+		OPT_STRING('i', "input", &input_name, "file", "input file name"),
+		OPT_STRING(0, "to-json", &to_json, NULL, "Convert to JSON format"),
+		OPT_STRING(0, "to-ctf", &to_ctf, NULL, "Convert to CTF format"),
+		OPT_BOOLEAN(0, "tod", &opts.tod, "Convert time to wall clock time"),
+		OPT_BOOLEAN('f', "force", &opts.force, "don't complain, do it"),
+		OPT_BOOLEAN(0, "all", &opts.all, "Convert all events"),
+		OPT_STRING(0, "time", &opts.time_str, "str",
+			   "Time span of interest (start,stop)"),
+		OPT_END()
+	};
+
+static int cmd_data_convert(int argc, const char **argv)
+{
+
+	argc = parse_options(argc, argv, data_options,
+			     data_usage, 0);
+	if (argc) {
+		usage_with_options(data_usage, data_options);
+		return -1;
+	}
+
+	if (to_json && to_ctf) {
+		pr_err("You cannot specify both --to-ctf and --to-json.\n");
+		return -1;
+	}
+	if (!to_json && !to_ctf) {
+		pr_err("You must specify one of --to-ctf or --to-json.\n");
+		return -1;
+	}
+
+	if (to_json)
+		return bt_convert__perf2json(input_name, to_json, &opts);
+
+	if (to_ctf) {
+#if defined(HAVE_BABELTRACE2_CTF_WRITER_SUPPORT) && defined(HAVE_LIBTRACEEVENT)
+		return bt_convert__perf2ctf(input_name, to_ctf, &opts);
+#else
+		pr_err("The babeltrace2 ctf support is not compiled in. Ensure you have both\n"
+			"libbabeltrace2-dev[el] and libtraceevent-dev[el] installed or set\n"
+			"PKG_CONFIG_PATH to find a local installation of those libraries.\n");
+		return -1;
+#endif
+	}
+
+	return 0;
+}
+
+static struct data_cmd data_cmds[] = {
+	{ "convert", "converts data file between formats", cmd_data_convert },
+	{ .name = NULL, },
+};
+
+int cmd_data(int argc, const char **argv)
+{
+	struct data_cmd *cmd;
+	const char *cmdstr;
+
+	argc = parse_options_subcommand(argc, argv, data_options, data_subcommands, data_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	if (!argc) {
+		usage_with_options(data_usage, data_options);
+		return -1;
+	}
+
+	cmdstr = argv[0];
+
+	for_each_cmd(cmd) {
+		if (strcmp(cmd->name, cmdstr))
+			continue;
+
+		return cmd->fn(argc, argv);
+	}
+
+	pr_err("Unknown command: %s\n", cmdstr);
+	usage_with_options(data_usage, data_options);
+	return -1;
+}