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, 120 insertions, 0 deletions

diff --git a/drivers/net/phy/amd.c b/drivers/net/phy/amd.c
new file mode 100644
index 000000000..75b5fe655
--- /dev/null
+++ b/drivers/net/phy/amd.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Driver for AMD am79c PHYs
+ *
+ * Author: Heiko Schocher <hs@denx.de>
+ *
+ * Copyright (c) 2011 DENX Software Engineering GmbH
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mii.h>
+#include <linux/phy.h>
+
+#define PHY_ID_AC101L		0x00225520
+#define PHY_ID_AM79C874		0x0022561b
+
+#define MII_AM79C_IR		17	/* Interrupt Status/Control Register */
+#define MII_AM79C_IR_EN_LINK	0x0400	/* IR enable Linkstate */
+#define MII_AM79C_IR_EN_ANEG	0x0100	/* IR enable Aneg Complete */
+#define MII_AM79C_IR_IMASK_INIT	(MII_AM79C_IR_EN_LINK | MII_AM79C_IR_EN_ANEG)
+
+#define MII_AM79C_IR_LINK_DOWN	BIT(2)
+#define MII_AM79C_IR_ANEG_DONE	BIT(0)
+#define MII_AM79C_IR_IMASK_STAT	(MII_AM79C_IR_LINK_DOWN | MII_AM79C_IR_ANEG_DONE)
+
+MODULE_DESCRIPTION("AMD PHY driver");
+MODULE_AUTHOR("Heiko Schocher <hs@denx.de>");
+MODULE_LICENSE("GPL");
+
+static int am79c_ack_interrupt(struct phy_device *phydev)
+{
+	int err;
+
+	err = phy_read(phydev, MII_BMSR);
+	if (err < 0)
+		return err;
+
+	err = phy_read(phydev, MII_AM79C_IR);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int am79c_config_init(struct phy_device *phydev)
+{
+	return 0;
+}
+
+static int am79c_config_intr(struct phy_device *phydev)
+{
+	int err;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+		err = am79c_ack_interrupt(phydev);
+		if (err)
+			return err;
+
+		err = phy_write(phydev, MII_AM79C_IR, MII_AM79C_IR_IMASK_INIT);
+	} else {
+		err = phy_write(phydev, MII_AM79C_IR, 0);
+		if (err)
+			return err;
+
+		err = am79c_ack_interrupt(phydev);
+	}
+
+	return err;
+}
+
+static irqreturn_t am79c_handle_interrupt(struct phy_device *phydev)
+{
+	int irq_status;
+
+	irq_status = phy_read(phydev, MII_AM79C_IR);
+	if (irq_status < 0) {
+		phy_error(phydev);
+		return IRQ_NONE;
+	}
+
+	if (!(irq_status & MII_AM79C_IR_IMASK_STAT))
+		return IRQ_NONE;
+
+	phy_trigger_machine(phydev);
+
+	return IRQ_HANDLED;
+}
+
+static struct phy_driver am79c_drivers[] = {
+	{
+		.phy_id		= PHY_ID_AM79C874,
+		.name		= "AM79C874",
+		.phy_id_mask	= 0xfffffff0,
+		/* PHY_BASIC_FEATURES */
+		.config_init	= am79c_config_init,
+		.config_intr	= am79c_config_intr,
+		.handle_interrupt = am79c_handle_interrupt,
+	},
+	{
+		.phy_id		= PHY_ID_AC101L,
+		.name		= "AC101L",
+		.phy_id_mask	= 0xfffffff0,
+		/* PHY_BASIC_FEATURES */
+		.config_init	= am79c_config_init,
+		.config_intr	= am79c_config_intr,
+		.handle_interrupt = am79c_handle_interrupt,
+	},
+};
+
+module_phy_driver(am79c_drivers);
+
+static const struct mdio_device_id __maybe_unused amd_tbl[] = {
+	{ PHY_ID_AC101L, 0xfffffff0 },
+	{ PHY_ID_AM79C874, 0xfffffff0 },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, amd_tbl);