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/net/dsa/netlink.c b/net/dsa/netlink.c
new file mode 100644
index 000000000..1332e5634
--- /dev/null
+++ b/net/dsa/netlink.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2022 NXP
+ */
+#include <linux/netdevice.h>
+#include <net/rtnetlink.h>
+
+#include "netlink.h"
+#include "user.h"
+
+static const struct nla_policy dsa_policy[IFLA_DSA_MAX + 1] = {
+	[IFLA_DSA_CONDUIT]	= { .type = NLA_U32 },
+};
+
+static int dsa_changelink(struct net_device *dev, struct nlattr *tb[],
+			  struct nlattr *data[],
+			  struct netlink_ext_ack *extack)
+{
+	int err;
+
+	if (!data)
+		return 0;
+
+	if (data[IFLA_DSA_CONDUIT]) {
+		u32 ifindex = nla_get_u32(data[IFLA_DSA_CONDUIT]);
+		struct net_device *conduit;
+
+		conduit = __dev_get_by_index(dev_net(dev), ifindex);
+		if (!conduit)
+			return -EINVAL;
+
+		err = dsa_user_change_conduit(dev, conduit, extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static size_t dsa_get_size(const struct net_device *dev)
+{
+	return nla_total_size(sizeof(u32)) +	/* IFLA_DSA_CONDUIT  */
+	       0;
+}
+
+static int dsa_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct net_device *conduit = dsa_user_to_conduit(dev);
+
+	if (nla_put_u32(skb, IFLA_DSA_CONDUIT, conduit->ifindex))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+struct rtnl_link_ops dsa_link_ops __read_mostly = {
+	.kind			= "dsa",
+	.priv_size		= sizeof(struct dsa_port),
+	.maxtype		= IFLA_DSA_MAX,
+	.policy			= dsa_policy,
+	.changelink		= dsa_changelink,
+	.get_size		= dsa_get_size,
+	.fill_info		= dsa_fill_info,
+	.netns_refund		= true,
+};