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, 72 insertions, 0 deletions

diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
new file mode 100644
index 000000000..3b249195c
--- /dev/null
+++ b/drivers/thermal/Makefile
@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for sensor chip drivers.
+#
+CFLAGS_thermal_core.o		:= -I$(src)
+obj-$(CONFIG_THERMAL)		+= thermal_sys.o
+thermal_sys-y			+= thermal_core.o thermal_sysfs.o
+thermal_sys-y			+= thermal_trip.o thermal_helpers.o
+thermal_sys-y			+= thermal_thresholds.o
+
+# netlink interface to manage the thermal framework
+thermal_sys-$(CONFIG_THERMAL_NETLINK)		+= thermal_netlink.o
+
+thermal_sys-$(CONFIG_THERMAL_DEBUGFS)	+= thermal_debugfs.o
+
+# interface to/from other layers providing sensors
+thermal_sys-$(CONFIG_THERMAL_HWMON)		+= thermal_hwmon.o
+thermal_sys-$(CONFIG_THERMAL_OF)		+= thermal_of.o
+
+# governors
+CFLAGS_gov_power_allocator.o			:= -I$(src)
+thermal_sys-$(CONFIG_THERMAL_GOV_FAIR_SHARE)	+= gov_fair_share.o
+thermal_sys-$(CONFIG_THERMAL_GOV_BANG_BANG)	+= gov_bang_bang.o
+thermal_sys-$(CONFIG_THERMAL_GOV_STEP_WISE)	+= gov_step_wise.o
+thermal_sys-$(CONFIG_THERMAL_GOV_USER_SPACE)	+= gov_user_space.o
+thermal_sys-$(CONFIG_THERMAL_GOV_POWER_ALLOCATOR)	+= gov_power_allocator.o
+
+# cpufreq cooling
+thermal_sys-$(CONFIG_CPU_FREQ_THERMAL)	+= cpufreq_cooling.o
+thermal_sys-$(CONFIG_CPU_IDLE_THERMAL)	+= cpuidle_cooling.o
+
+# devfreq cooling
+thermal_sys-$(CONFIG_DEVFREQ_THERMAL) += devfreq_cooling.o
+
+thermal_sys-$(CONFIG_PCIE_THERMAL) += pcie_cooling.o
+
+obj-$(CONFIG_K3_THERMAL)	+= k3_bandgap.o k3_j72xx_bandgap.o
+# platform thermal drivers
+obj-y				+= broadcom/
+obj-$(CONFIG_THERMAL_MMIO)		+= thermal_mmio.o
+obj-$(CONFIG_AIROHA_THERMAL)	+= airoha_thermal.o
+obj-$(CONFIG_SPEAR_THERMAL)	+= spear_thermal.o
+obj-$(CONFIG_SUN8I_THERMAL)     += sun8i_thermal.o
+obj-$(CONFIG_ROCKCHIP_THERMAL)	+= rockchip_thermal.o
+obj-y				+= renesas/
+obj-$(CONFIG_KIRKWOOD_THERMAL)  += kirkwood_thermal.o
+obj-y				+= samsung/
+obj-$(CONFIG_DOVE_THERMAL)	+= dove_thermal.o
+obj-$(CONFIG_DB8500_THERMAL)	+= db8500_thermal.o
+obj-$(CONFIG_ARMADA_THERMAL)	+= armada_thermal.o
+obj-$(CONFIG_IMX_THERMAL)	+= imx_thermal.o
+obj-$(CONFIG_IMX_SC_THERMAL)	+= imx_sc_thermal.o
+obj-$(CONFIG_IMX8MM_THERMAL)	+= imx8mm_thermal.o
+obj-$(CONFIG_IMX91_THERMAL)	+= imx91_thermal.o
+obj-$(CONFIG_MAX77620_THERMAL)	+= max77620_thermal.o
+obj-$(CONFIG_QORIQ_THERMAL)	+= qoriq_thermal.o
+obj-$(CONFIG_DA9062_THERMAL)	+= da9062-thermal.o
+obj-y				+= intel/
+obj-$(CONFIG_TI_SOC_THERMAL)	+= ti-soc-thermal/
+obj-y				+= st/
+obj-y				+= qcom/
+obj-y				+= tegra/
+obj-$(CONFIG_HISI_THERMAL)     += hisi_thermal.o
+obj-y				+= mediatek/
+obj-$(CONFIG_GENERIC_ADC_THERMAL)	+= thermal-generic-adc.o
+obj-$(CONFIG_UNIPHIER_THERMAL)	+= uniphier_thermal.o
+obj-$(CONFIG_AMLOGIC_THERMAL)     += amlogic_thermal.o
+obj-y				+= spacemit/
+obj-$(CONFIG_SPRD_THERMAL)	+= sprd_thermal.o
+obj-$(CONFIG_KHADAS_MCU_FAN_THERMAL)	+= khadas_mcu_fan.o
+obj-$(CONFIG_LOONGSON2_THERMAL)	+= loongson2_thermal.o
+obj-$(CONFIG_THERMAL_CORE_TESTING)	+= testing/