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, 96 insertions, 0 deletions

diff --git a/drivers/net/phy/teranetics.c b/drivers/net/phy/teranetics.c
new file mode 100644
index 000000000..46c5ff7d7
--- /dev/null
+++ b/drivers/net/phy/teranetics.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for Teranetics PHY
+ *
+ * Author: Shaohui Xie <Shaohui.Xie@freescale.com>
+ *
+ * Copyright 2015 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mii.h>
+#include <linux/ethtool.h>
+#include <linux/mdio.h>
+#include <linux/phy.h>
+
+MODULE_DESCRIPTION("Teranetics PHY driver");
+MODULE_AUTHOR("Shaohui Xie <Shaohui.Xie@freescale.com>");
+MODULE_LICENSE("GPL v2");
+
+#define PHY_ID_TN2020	0x00a19410
+#define MDIO_PHYXS_LNSTAT_SYNC0	0x0001
+#define MDIO_PHYXS_LNSTAT_SYNC1	0x0002
+#define MDIO_PHYXS_LNSTAT_SYNC2	0x0004
+#define MDIO_PHYXS_LNSTAT_SYNC3	0x0008
+#define MDIO_PHYXS_LNSTAT_ALIGN 0x1000
+
+#define MDIO_PHYXS_LANE_READY	(MDIO_PHYXS_LNSTAT_SYNC0 | \
+				MDIO_PHYXS_LNSTAT_SYNC1 | \
+				MDIO_PHYXS_LNSTAT_SYNC2 | \
+				MDIO_PHYXS_LNSTAT_SYNC3 | \
+				MDIO_PHYXS_LNSTAT_ALIGN)
+
+static int teranetics_aneg_done(struct phy_device *phydev)
+{
+	/* auto negotiation state can only be checked when using copper
+	 * port, if using fiber port, just lie it's done.
+	 */
+	if (!phy_read_mmd(phydev, MDIO_MMD_VEND1, 93))
+		return genphy_c45_aneg_done(phydev);
+
+	return 1;
+}
+
+static int teranetics_read_status(struct phy_device *phydev)
+{
+	int reg;
+
+	phydev->link = 1;
+
+	phydev->speed = SPEED_10000;
+	phydev->duplex = DUPLEX_FULL;
+
+	if (!phy_read_mmd(phydev, MDIO_MMD_VEND1, 93)) {
+		reg = phy_read_mmd(phydev, MDIO_MMD_PHYXS, MDIO_PHYXS_LNSTAT);
+		if (reg < 0 ||
+		    !((reg & MDIO_PHYXS_LANE_READY) == MDIO_PHYXS_LANE_READY)) {
+			phydev->link = 0;
+			return 0;
+		}
+
+		reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1);
+		if (reg < 0 || !(reg & MDIO_STAT1_LSTATUS))
+			phydev->link = 0;
+	}
+
+	return 0;
+}
+
+static int teranetics_match_phy_device(struct phy_device *phydev,
+				       const struct phy_driver *phydrv)
+{
+	return phydev->c45_ids.device_ids[3] == PHY_ID_TN2020;
+}
+
+static struct phy_driver teranetics_driver[] = {
+{
+	.phy_id		= PHY_ID_TN2020,
+	.phy_id_mask	= 0xffffffff,
+	.name		= "Teranetics TN2020",
+	.features       = PHY_10GBIT_FEATURES,
+	.aneg_done	= teranetics_aneg_done,
+	.config_aneg    = gen10g_config_aneg,
+	.read_status	= teranetics_read_status,
+	.match_phy_device = teranetics_match_phy_device,
+},
+};
+
+module_phy_driver(teranetics_driver);
+
+static const struct mdio_device_id __maybe_unused teranetics_tbl[] = {
+	{ PHY_ID_TN2020, 0xffffffff },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, teranetics_tbl);