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, 75 insertions, 0 deletions

diff --git a/net/mctp/test/utils.h b/net/mctp/test/utils.h
new file mode 100644
index 000000000..47603732e
--- /dev/null
+++ b/net/mctp/test/utils.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __NET_MCTP_TEST_UTILS_H
+#define __NET_MCTP_TEST_UTILS_H
+
+#include <uapi/linux/netdevice.h>
+
+#include <net/mctp.h>
+#include <net/mctpdevice.h>
+
+#include <kunit/test.h>
+
+#define MCTP_DEV_TEST_MTU	68
+
+struct mctp_test_dev {
+	struct net_device *ndev;
+	struct mctp_dev *mdev;
+
+	unsigned short lladdr_len;
+	unsigned char lladdr[MAX_ADDR_LEN];
+
+	struct sk_buff_head pkts;
+};
+
+struct mctp_test_dev;
+
+struct mctp_test_route {
+	struct mctp_route	rt;
+};
+
+struct mctp_test_bind_setup {
+	mctp_eid_t bind_addr;
+	int bind_net;
+	u8 bind_type;
+
+	bool have_peer;
+	mctp_eid_t peer_addr;
+	int peer_net;
+
+	/* optional name. Used for comparison in "lookup" tests */
+	const char *name;
+};
+
+struct mctp_test_dev *mctp_test_create_dev(void);
+struct mctp_test_dev *mctp_test_create_dev_with_addr(mctp_eid_t eid);
+struct mctp_test_dev *mctp_test_create_dev_lladdr(unsigned short lladdr_len,
+						  const unsigned char *lladdr);
+void mctp_test_destroy_dev(struct mctp_test_dev *dev);
+
+struct mctp_test_route *mctp_test_create_route_direct(struct net *net,
+						      struct mctp_dev *dev,
+						      mctp_eid_t eid,
+						      unsigned int mtu);
+struct mctp_test_route *mctp_test_create_route_gw(struct net *net,
+						  unsigned int netid,
+						  mctp_eid_t eid,
+						  mctp_eid_t gw,
+						  unsigned int mtu);
+void mctp_test_dst_setup(struct kunit *test, struct mctp_dst *dst,
+			 struct mctp_test_dev *dev, unsigned int mtu);
+void mctp_test_route_destroy(struct kunit *test, struct mctp_test_route *rt);
+void mctp_test_skb_set_dev(struct sk_buff *skb, struct mctp_test_dev *dev);
+struct sk_buff *mctp_test_create_skb(const struct mctp_hdr *hdr,
+				     unsigned int data_len);
+struct sk_buff *__mctp_test_create_skb_data(const struct mctp_hdr *hdr,
+					    const void *data, size_t data_len);
+
+#define mctp_test_create_skb_data(h, d) \
+	__mctp_test_create_skb_data(h, d, sizeof(*d))
+
+void mctp_test_bind_run(struct kunit *test,
+			const struct mctp_test_bind_setup *setup,
+			int *ret_bind_errno, struct socket **sock);
+
+#endif /* __NET_MCTP_TEST_UTILS_H */