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, 104 insertions, 0 deletions

diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
new file mode 100644
index 000000000..25c4a3c24
--- /dev/null
+++ b/drivers/net/phy/Makefile
@@ -0,0 +1,104 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for Linux PHY drivers
+
+libphy-y			:= phy.o phy-c45.o phy-core.o phy_device.o \
+				   linkmode.o phy_link_topology.o \
+				   phy_caps.o mdio_bus_provider.o phy_port.o \
+				   mdio_device.o
+
+ifdef CONFIG_PHYLIB
+# built-in whenever PHYLIB is built-in or module
+obj-y				+= stubs.o
+endif
+
+libphy-$(CONFIG_SWPHY)		+= swphy.o
+libphy-$(CONFIG_LED_TRIGGER_PHY)	+= phy_led_triggers.o
+libphy-$(CONFIG_OPEN_ALLIANCE_HELPERS) += open_alliance_helpers.o
+
+obj-$(CONFIG_PHYLIB)		+= mdio_bus.o
+obj-$(CONFIG_PHYLINK)		+= phylink.o
+obj-$(CONFIG_PHYLIB)		+= libphy.o
+obj-$(CONFIG_PHYLIB)		+= mdio_devres.o
+obj-$(CONFIG_PHY_PACKAGE)	+= phy_package.o
+
+obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += mii_timestamper.o
+
+obj-$(CONFIG_SFP)		+= sfp.o
+sfp-obj-$(CONFIG_SFP)		+= sfp-bus.o
+obj-y				+= $(sfp-obj-y) $(sfp-obj-m)
+
+obj-$(CONFIG_ADIN_PHY)		+= adin.o
+obj-$(CONFIG_ADIN1100_PHY)	+= adin1100.o
+obj-$(CONFIG_ADIN1140_PHY)	+= adin1140-phy.o
+obj-$(CONFIG_AIR_AN8801_PHY)	+= air_an8801.o
+obj-$(CONFIG_AIR_EN8811H_PHY)   += air_en8811h.o
+obj-$(CONFIG_AIR_NET_PHYLIB)	+= air_phy_lib.o
+obj-$(CONFIG_AMD_PHY)		+= amd.o
+obj-$(CONFIG_AMCC_QT2025_PHY)	+= qt2025.o
+obj-$(CONFIG_AQUANTIA_PHY)	+= aquantia/
+obj-$(CONFIG_AS21XXX_PHY)	+= as21xxx.o
+ifdef CONFIG_AX88796B_RUST_PHY
+  obj-$(CONFIG_AX88796B_PHY)	+= ax88796b_rust.o
+else
+  obj-$(CONFIG_AX88796B_PHY)	+= ax88796b.o
+endif
+obj-$(CONFIG_BCM54140_PHY)	+= bcm54140.o
+obj-$(CONFIG_BCM63XX_PHY)	+= bcm63xx.o
+obj-$(CONFIG_BCM7XXX_PHY)	+= bcm7xxx.o
+obj-$(CONFIG_BCM84881_PHY)	+= bcm84881.o
+obj-$(CONFIG_BCM87XX_PHY)	+= bcm87xx.o
+obj-$(CONFIG_BCM_CYGNUS_PHY)	+= bcm-cygnus.o
+obj-$(CONFIG_BCM_NET_PHYLIB)	+= bcm-phy-lib.o
+obj-$(CONFIG_BCM_NET_PHYPTP)	+= bcm-phy-ptp.o
+obj-$(CONFIG_BROADCOM_PHY)	+= broadcom.o
+obj-$(CONFIG_CICADA_PHY)	+= cicada.o
+obj-$(CONFIG_CORTINA_PHY)	+= cortina.o
+obj-$(CONFIG_DAP8211R_PHY)	+= dap8211r.o
+obj-$(CONFIG_DAVICOM_PHY)	+= davicom.o
+obj-$(CONFIG_DP83640_PHY)	+= dp83640.o
+obj-$(CONFIG_DP83822_PHY)	+= dp83822.o
+obj-$(CONFIG_DP83848_PHY)	+= dp83848.o
+obj-$(CONFIG_DP83867_PHY)	+= dp83867.o
+obj-$(CONFIG_DP83869_PHY)	+= dp83869.o
+obj-$(CONFIG_DP83TC811_PHY)	+= dp83tc811.o
+obj-$(CONFIG_DP83TD510_PHY)	+= dp83td510.o
+obj-$(CONFIG_DP83TG720_PHY)	+= dp83tg720.o
+obj-$(CONFIG_FIXED_PHY)		+= fixed_phy.o
+obj-$(CONFIG_ICPLUS_PHY)	+= icplus.o
+obj-$(CONFIG_INTEL_XWAY_PHY)	+= intel-xway.o
+obj-$(CONFIG_LSI_ET1011C_PHY)	+= et1011c.o
+obj-$(CONFIG_LXT_PHY)		+= lxt.o
+obj-$(CONFIG_MARVELL_10G_PHY)	+= marvell10g.o
+obj-$(CONFIG_MARVELL_PHY)	+= marvell.o
+obj-$(CONFIG_MARVELL_88Q2XXX_PHY)	+= marvell-88q2xxx.o
+obj-$(CONFIG_MARVELL_88X2222_PHY)	+= marvell-88x2222.o
+obj-$(CONFIG_MAXLINEAR_GPHY)	+= mxl-gpy.o
+obj-$(CONFIG_MAXLINEAR_86110_PHY)	+= mxl-86110.o
+obj-y				+= mediatek/
+obj-$(CONFIG_MESON_GXL_PHY)	+= meson-gxl.o
+obj-$(CONFIG_MICREL_PHY)	+= micrel.o
+obj-$(CONFIG_MICROCHIP_PHY)	+= microchip.o
+obj-$(CONFIG_MICROCHIP_PHY_RDS_PTP)	+= microchip_rds_ptp.o
+obj-$(CONFIG_MICROCHIP_T1_PHY)	+= microchip_t1.o
+obj-$(CONFIG_MICROCHIP_T1S_PHY) += microchip_t1s.o
+obj-$(CONFIG_MICROSEMI_PHY)	+= mscc/
+obj-$(CONFIG_MOTORCOMM_PHY)	+= motorcomm.o
+obj-$(CONFIG_NATIONAL_PHY)	+= national.o
+obj-$(CONFIG_NCN26000_PHY)	+= ncn26000.o
+nxp-c45-tja-objs		+= nxp-c45-tja11xx.o
+ifdef CONFIG_MACSEC
+nxp-c45-tja-objs		+= nxp-c45-tja11xx-macsec.o
+endif
+obj-$(CONFIG_NXP_C45_TJA11XX_PHY)	+= nxp-c45-tja.o
+obj-$(CONFIG_NXP_CBTX_PHY)	+= nxp-cbtx.o
+obj-$(CONFIG_NXP_TJA11XX_PHY)	+= nxp-tja11xx.o
+obj-y				+= qcom/
+obj-$(CONFIG_QSEMI_PHY)		+= qsemi.o
+obj-$(CONFIG_REALTEK_PHY)	+= realtek/
+obj-$(CONFIG_RENESAS_PHY)	+= uPD60620.o
+obj-$(CONFIG_ROCKCHIP_PHY)	+= rockchip.o
+obj-$(CONFIG_SMSC_PHY)		+= smsc.o
+obj-$(CONFIG_STE10XP)		+= ste10Xp.o
+obj-$(CONFIG_TERANETICS_PHY)	+= teranetics.o
+obj-$(CONFIG_VITESSE_PHY)	+= vitesse.o
+obj-$(CONFIG_XILINX_GMII2RGMII) += xilinx_gmii2rgmii.o