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, 163 insertions, 0 deletions

diff --git a/net/sched/em_text.c b/net/sched/em_text.c
new file mode 100644
index 000000000..343f1aebe
--- /dev/null
+++ b/net/sched/em_text.c
@@ -0,0 +1,163 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * net/sched/em_text.c	Textsearch ematch
+ *
+ * Authors:	Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/skbuff.h>
+#include <linux/textsearch.h>
+#include <linux/tc_ematch/tc_em_text.h>
+#include <net/pkt_cls.h>
+
+struct text_match {
+	u16			from_offset;
+	u16			to_offset;
+	u8			from_layer;
+	u8			to_layer;
+	struct ts_config	*config;
+};
+
+#define EM_TEXT_PRIV(m) ((struct text_match *) (m)->data)
+
+static int em_text_match(struct sk_buff *skb, struct tcf_ematch *m,
+			 struct tcf_pkt_info *info)
+{
+	struct text_match *tm = EM_TEXT_PRIV(m);
+	unsigned char *ptr;
+	int from, to;
+
+	ptr = tcf_get_base_ptr(skb, tm->from_layer);
+	if (!ptr)
+		return 0;
+	from = ptr - skb->data;
+	from += tm->from_offset;
+
+	ptr = tcf_get_base_ptr(skb, tm->to_layer);
+	if (!ptr)
+		return 0;
+	to = ptr - skb->data;
+	to += tm->to_offset;
+
+	return skb_find_text(skb, from, to, tm->config) != UINT_MAX;
+}
+
+static int em_text_change(struct net *net, void *data, int len,
+			  struct tcf_ematch *m)
+{
+	struct text_match *tm;
+	struct tcf_em_text *conf = data;
+	struct ts_config *ts_conf;
+	int flags = 0;
+
+	if (len < sizeof(*conf) || len < (sizeof(*conf) + conf->pattern_len))
+		return -EINVAL;
+
+	if (conf->from_layer > conf->to_layer)
+		return -EINVAL;
+
+	if (conf->from_layer == conf->to_layer &&
+	    conf->from_offset > conf->to_offset)
+		return -EINVAL;
+
+retry:
+	ts_conf = textsearch_prepare(conf->algo, (u8 *) conf + sizeof(*conf),
+				     conf->pattern_len, GFP_KERNEL, flags);
+
+	if (flags & TS_AUTOLOAD)
+		rtnl_lock();
+
+	if (IS_ERR(ts_conf)) {
+		if (PTR_ERR(ts_conf) == -ENOENT && !(flags & TS_AUTOLOAD)) {
+			rtnl_unlock();
+			flags |= TS_AUTOLOAD;
+			goto retry;
+		} else
+			return PTR_ERR(ts_conf);
+	} else if (flags & TS_AUTOLOAD) {
+		textsearch_destroy(ts_conf);
+		return -EAGAIN;
+	}
+
+	tm = kmalloc_obj(*tm);
+	if (tm == NULL) {
+		textsearch_destroy(ts_conf);
+		return -ENOBUFS;
+	}
+
+	tm->from_offset = conf->from_offset;
+	tm->to_offset   = conf->to_offset;
+	tm->from_layer  = conf->from_layer;
+	tm->to_layer    = conf->to_layer;
+	tm->config      = ts_conf;
+
+	m->datalen = sizeof(*tm);
+	m->data = (unsigned long) tm;
+
+	return 0;
+}
+
+static void em_text_destroy(struct tcf_ematch *m)
+{
+	if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) {
+		textsearch_destroy(EM_TEXT_PRIV(m)->config);
+		kfree(EM_TEXT_PRIV(m));
+	}
+}
+
+static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m)
+{
+	struct text_match *tm = EM_TEXT_PRIV(m);
+	struct tcf_em_text conf;
+
+	strscpy(conf.algo, tm->config->ops->name);
+	conf.from_offset = tm->from_offset;
+	conf.to_offset = tm->to_offset;
+	conf.from_layer = tm->from_layer;
+	conf.to_layer = tm->to_layer;
+	conf.pattern_len = textsearch_get_pattern_len(tm->config);
+	conf.pad = 0;
+
+	if (nla_put_nohdr(skb, sizeof(conf), &conf) < 0)
+		goto nla_put_failure;
+	if (nla_append(skb, conf.pattern_len,
+		       textsearch_get_pattern(tm->config)) < 0)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct tcf_ematch_ops em_text_ops = {
+	.kind	  = TCF_EM_TEXT,
+	.change	  = em_text_change,
+	.match	  = em_text_match,
+	.destroy  = em_text_destroy,
+	.dump	  = em_text_dump,
+	.owner	  = THIS_MODULE,
+	.link	  = LIST_HEAD_INIT(em_text_ops.link)
+};
+
+static int __init init_em_text(void)
+{
+	return tcf_em_register(&em_text_ops);
+}
+
+static void __exit exit_em_text(void)
+{
+	tcf_em_unregister(&em_text_ops);
+}
+
+MODULE_DESCRIPTION("ematch classifier for embedded text in skbs");
+MODULE_LICENSE("GPL");
+
+module_init(init_em_text);
+module_exit(exit_em_text);
+
+MODULE_ALIAS_TCF_EMATCH(TCF_EM_TEXT);