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, 67 insertions, 0 deletions

diff --git a/drivers/thermal/qcom/Kconfig b/drivers/thermal/qcom/Kconfig
new file mode 100644
index 000000000..a8cf7e258
--- /dev/null
+++ b/drivers/thermal/qcom/Kconfig
@@ -0,0 +1,67 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config QCOM_TSENS
+	tristate "Qualcomm TSENS Temperature Alarm"
+	depends on NVMEM_QCOM_QFPROM
+	depends on ARCH_QCOM || COMPILE_TEST
+	help
+	  This enables the thermal sysfs driver for the TSENS device. It shows
+	  up in Sysfs as a thermal zone with multiple trip points. Disabling the
+	  thermal zone device via the mode file results in disabling the sensor.
+	  Also able to set threshold temperature for both hot and cold and update
+	  when a threshold is reached.
+
+config QCOM_SPMI_ADC_TM5
+	tristate "Qualcomm SPMI PMIC Thermal Monitor ADC5"
+	depends on OF && SPMI && IIO
+	select REGMAP_SPMI
+	select QCOM_VADC_COMMON
+	help
+	  This enables the thermal driver for the ADC thermal monitoring
+	  device. It shows up as a thermal zone with multiple trip points.
+	  Thermal client sets threshold temperature for both warm and cool and
+	  gets updated when a threshold is reached.
+
+config QCOM_SPMI_MBG_TM
+	tristate "Qualcomm SPMI PMIC MBG Temperature monitor"
+	depends on QCOM_SPMI_ADC5_GEN3
+	select REGMAP_SPMI
+	help
+	  This enables Qualcomm PMIC MBG (Master Bandgap) thermal monitor.
+
+	  The MBG block monitors PMIC die temperature in hardware and raises an
+	  interrupt when the programmed threshold is crossed.
+
+	  Temperature is read from the associated ADC channel, and threshold
+	  interrupts are forwarded to the thermal framework as trip-violation
+	  events. Current support handles a single LVL1 upper (hot) trip.
+
+config QCOM_SPMI_ADC_TM5_GEN3
+	tristate "Qualcomm SPMI PMIC Thermal Monitor ADC5 Gen3"
+	depends on QCOM_SPMI_ADC5_GEN3
+	help
+	  This enables the auxiliary thermal driver for the ADC5 Gen3 thermal
+	  monitoring device. It shows up as a thermal zone with multiple trip points.
+	  Thermal client sets threshold temperature for both warm and cool and
+	  gets updated when a threshold is reached.
+
+config QCOM_SPMI_TEMP_ALARM
+	tristate "Qualcomm SPMI PMIC Temperature Alarm"
+	depends on OF && SPMI && IIO
+	select REGMAP_SPMI
+	help
+	  This enables a thermal sysfs driver for Qualcomm plug-and-play (QPNP)
+	  PMIC devices. It shows up in sysfs as a thermal sensor with multiple
+	  trip points. The temperature reported by the thermal sensor reflects the
+	  real time die temperature if an ADC is present or an estimate of the
+	  temperature based upon the over temperature stage value.
+
+config QCOM_LMH
+	tristate "Qualcomm Limits Management Hardware"
+	depends on ARCH_QCOM || COMPILE_TEST
+	select QCOM_SCM
+	help
+	  This enables initialization of Qualcomm limits management
+	  hardware(LMh). LMh allows for hardware-enforced mitigation for cpus based on
+	  input from temperature and current sensors.  On many newer Qualcomm SoCs
+	  LMh is configured in the firmware and this feature need not be enabled.
+	  However, on certain SoCs like sdm845 LMh has to be configured from kernel.