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, 136 insertions, 0 deletions

diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
new file mode 100644
index 000000000..d1b0affb8
--- /dev/null
+++ b/drivers/acpi/Makefile
@@ -0,0 +1,136 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the Linux ACPI interpreter
+#
+
+ccflags-$(CONFIG_ACPI_DEBUG)	+= -DACPI_DEBUG_OUTPUT
+
+ifdef CONFIG_TRACE_BRANCH_PROFILING
+CFLAGS_processor_idle.o += -DDISABLE_BRANCH_PROFILING
+endif
+
+#
+# ACPI Boot-Time Table Parsing
+#
+ifeq ($(CONFIG_ACPI_CUSTOM_DSDT),y)
+tables.o: $(src)/../../include/$(CONFIG_ACPI_CUSTOM_DSDT_FILE) ;
+
+endif
+
+obj-$(CONFIG_ACPI)		+= tables.o
+
+#
+# ACPI Core Subsystem (Interpreter)
+#
+obj-$(CONFIG_ACPI)		+= acpi.o \
+					acpica/
+
+# All the builtin files are in the "acpi." module_param namespace.
+acpi-y				+= osi.o osl.o utils.o reboot.o
+acpi-y				+= nvs.o
+
+# Power management related files
+acpi-y				+= wakeup.o
+acpi-$(CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT) += sleep.o
+acpi-y				+= device_sysfs.o device_pm.o
+acpi-$(CONFIG_ACPI_SLEEP)	+= proc.o
+
+
+#
+# ACPI Bus and Device Drivers
+#
+acpi-y				+= bus.o glue.o
+acpi-y				+= scan.o mipi-disco-img.o
+acpi-y				+= resource.o
+acpi-y				+= acpi_processor.o
+acpi-y				+= processor_core.o
+acpi-$(CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC) += processor_pdc.o
+acpi-$(CONFIG_ACPI_EC)		+= ec.o
+acpi-$(CONFIG_ACPI_DOCK)	+= dock.o
+acpi-$(CONFIG_PCI)		+= pci_root.o pci_link.o pci_irq.o
+obj-$(CONFIG_ACPI_MCFG)		+= pci_mcfg.o
+acpi-y				+= acpi_apd.o
+acpi-y				+= acpi_platform.o
+acpi-y				+= acpi_pnp.o
+acpi-y				+= power.o
+acpi-y				+= event.o
+acpi-y				+= evged.o
+acpi-y				+= sysfs.o
+acpi-y				+= property.o
+acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
+acpi-y				+= acpi_lpat.o
+acpi-$(CONFIG_ACPI_FPDT)	+= acpi_fpdt.o
+acpi-$(CONFIG_ACPI_LPIT)	+= acpi_lpit.o
+acpi-$(CONFIG_ACPI_GENERIC_GSI) += irq.o
+acpi-$(CONFIG_ACPI_WATCHDOG)	+= acpi_watchdog.o
+acpi-$(CONFIG_ACPI_PRMT)	+= prmt.o
+acpi-$(CONFIG_ACPI_PCC)		+= acpi_pcc.o
+acpi-$(CONFIG_ACPI_FFH)		+= acpi_ffh.o
+acpi-$(CONFIG_ACPI_MRRM)	+= acpi_mrrm.o
+
+# Address translation
+acpi-$(CONFIG_ACPI_ADXL)	+= acpi_adxl.o
+
+# These are (potentially) separate modules
+
+# IPMI may be used by other drivers, so it has to initialise before them
+obj-$(CONFIG_ACPI_IPMI)		+= acpi_ipmi.o
+
+obj-$(CONFIG_ACPI_AC) 		+= ac.o
+obj-$(CONFIG_ACPI_BUTTON)	+= button.o
+obj-$(CONFIG_ACPI_TINY_POWER_BUTTON)	+= tiny-power-button.o
+obj-$(CONFIG_ACPI_FAN)		+= fan.o
+fan-objs			:= fan_core.o
+fan-objs			+= fan_attr.o
+fan-$(CONFIG_HWMON)		+= fan_hwmon.o
+
+obj-$(CONFIG_ACPI_VIDEO)	+= video.o
+obj-$(CONFIG_ACPI_TAD)		+= acpi_tad.o
+obj-$(CONFIG_ACPI_PCI_SLOT)	+= pci_slot.o
+obj-$(CONFIG_ACPI_PROCESSOR)	+= processor.o
+obj-$(CONFIG_ACPI)		+= container.o
+obj-$(CONFIG_ACPI_THERMAL_LIB)	+= thermal_lib.o
+obj-$(CONFIG_ACPI_THERMAL)	+= thermal.o
+obj-$(CONFIG_ACPI_PLATFORM_PROFILE) 	+= platform_profile.o
+obj-$(CONFIG_ACPI_NFIT)		+= nfit/
+obj-$(CONFIG_ACPI_NHLT)		+= nhlt.o
+obj-$(CONFIG_ACPI_NUMA)		+= numa/
+obj-$(CONFIG_ACPI)		+= acpi_memhotplug.o
+obj-$(CONFIG_ACPI_HOTPLUG_IOAPIC) += ioapic.o
+obj-$(CONFIG_ACPI_BATTERY)	+= battery.o
+obj-$(CONFIG_ACPI_SBS)		+= sbshc.o
+obj-$(CONFIG_ACPI_SBS)		+= sbs.o
+obj-$(CONFIG_ACPI_HED)		+= hed.o
+obj-$(CONFIG_ACPI_EC_DEBUGFS)	+= ec_sys.o
+obj-$(CONFIG_ACPI_BGRT)		+= bgrt.o
+obj-$(CONFIG_ACPI_CPPC_LIB)	+= cppc_acpi.o
+obj-$(CONFIG_ACPI_SPCR_TABLE)	+= spcr.o
+obj-$(CONFIG_ACPI_DEBUGGER_USER) += acpi_dbg.o
+obj-$(CONFIG_ACPI_PPTT) 	+= pptt.o
+obj-$(CONFIG_ACPI_PFRUT)	+= pfr_update.o pfr_telemetry.o
+
+# processor has its own "processor." module_param namespace
+processor-y			:= processor_driver.o processor_thermal.o
+processor-$(CONFIG_ACPI_PROCESSOR_IDLE) += processor_idle.o
+processor-$(CONFIG_ACPI_CPU_FREQ_PSS)	+= processor_throttling.o
+processor-$(CONFIG_CPU_FREQ)	+= processor_perflib.o
+
+obj-$(CONFIG_ACPI_PROCESSOR_AGGREGATOR) += acpi_pad.o
+
+obj-$(CONFIG_ACPI_APEI)		+= apei/
+
+obj-$(CONFIG_ACPI_EXTLOG)	+= acpi_extlog.o
+
+obj-$(CONFIG_ACPI_CONFIGFS)	+= acpi_configfs.o
+
+obj-y				+= pmic/
+
+video-objs			+= acpi_video.o video_detect.o
+obj-y				+= dptf/
+
+obj-$(CONFIG_ARM64)		+= arm64/
+
+obj-$(CONFIG_ACPI_VIOT)		+= viot.o
+
+obj-$(CONFIG_RISCV)		+= riscv/
+obj-$(CONFIG_X86)		+= x86/