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, 70 insertions, 0 deletions

diff --git a/drivers/net/phy/phy-caps.h b/drivers/net/phy/phy-caps.h
new file mode 100644
index 000000000..421088e6f
--- /dev/null
+++ b/drivers/net/phy/phy-caps.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * link caps internal header, for link modes <-> capabilities <-> interfaces
+ * conversions.
+ */
+
+#ifndef __PHY_CAPS_H
+#define __PHY_CAPS_H
+
+#include <linux/ethtool.h>
+#include <linux/phy.h>
+
+enum {
+	LINK_CAPA_10HD = 0,
+	LINK_CAPA_10FD,
+	LINK_CAPA_100HD,
+	LINK_CAPA_100FD,
+	LINK_CAPA_1000HD,
+	LINK_CAPA_1000FD,
+	LINK_CAPA_2500FD,
+	LINK_CAPA_5000FD,
+	LINK_CAPA_10000FD,
+	LINK_CAPA_20000FD,
+	LINK_CAPA_25000FD,
+	LINK_CAPA_40000FD,
+	LINK_CAPA_50000FD,
+	LINK_CAPA_56000FD,
+	LINK_CAPA_80000FD,
+	LINK_CAPA_100000FD,
+	LINK_CAPA_200000FD,
+	LINK_CAPA_400000FD,
+	LINK_CAPA_800000FD,
+	LINK_CAPA_1600000FD,
+
+	__LINK_CAPA_MAX,
+};
+
+#define LINK_CAPA_ALL	GENMASK((__LINK_CAPA_MAX - 1), 0)
+
+struct link_capabilities {
+	int speed;
+	unsigned int duplex;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(linkmodes);
+};
+
+int __init phy_caps_init(void);
+
+size_t phy_caps_speeds(unsigned int *speeds, size_t size,
+		       unsigned long *linkmodes);
+void phy_caps_linkmode_max_speed(u32 max_speed, unsigned long *linkmodes);
+bool phy_caps_valid(int speed, int duplex, const unsigned long *linkmodes);
+void phy_caps_linkmodes(unsigned long caps, unsigned long *linkmodes);
+unsigned long phy_caps_from_interface(phy_interface_t interface);
+
+const struct link_capabilities *
+phy_caps_lookup_by_linkmode(const unsigned long *linkmodes);
+
+const struct link_capabilities *
+phy_caps_lookup_by_linkmode_rev(const unsigned long *linkmodes, bool fdx_only);
+
+const struct link_capabilities *
+phy_caps_lookup(int speed, unsigned int duplex, const unsigned long *supported,
+		bool exact);
+
+void phy_caps_medium_get_supported(unsigned long *supported,
+				   enum ethtool_link_medium medium,
+				   int lanes);
+u32 phy_caps_mediums_from_linkmodes(unsigned long *linkmodes);
+
+#endif /* __PHY_CAPS_H */