From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug 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 Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- drivers/thermal/Makefile | 72 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) create mode 100644 drivers/thermal/Makefile (limited to 'drivers/thermal/Makefile') 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/ -- cgit v1.3.1