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/input/misc/ad714x.h | 53 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) create mode 100644 drivers/input/misc/ad714x.h (limited to 'drivers/input/misc/ad714x.h') diff --git a/drivers/input/misc/ad714x.h b/drivers/input/misc/ad714x.h new file mode 100644 index 000000000..dafa12325 --- /dev/null +++ b/drivers/input/misc/ad714x.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * AD714X CapTouch Programmable Controller driver (bus interfaces) + * + * Copyright 2009-2011 Analog Devices Inc. + */ + +#ifndef _AD714X_H_ +#define _AD714X_H_ + +#include +#include + +#define STAGE_NUM 12 + +struct device; +struct ad714x_platform_data; +struct ad714x_driver_data; +struct ad714x_chip; + +typedef int (*ad714x_read_t)(struct ad714x_chip *, unsigned short, unsigned short *, size_t); +typedef int (*ad714x_write_t)(struct ad714x_chip *, unsigned short, unsigned short); + +struct ad714x_chip { + unsigned short l_state; + unsigned short h_state; + unsigned short c_state; + unsigned short adc_reg[STAGE_NUM]; + unsigned short amb_reg[STAGE_NUM]; + unsigned short sensor_val[STAGE_NUM]; + + struct ad714x_platform_data *hw; + struct ad714x_driver_data *sw; + + int irq; + struct device *dev; + ad714x_read_t read; + ad714x_write_t write; + + struct mutex mutex; + + unsigned product; + unsigned version; + + __be16 xfer_buf[16] ____cacheline_aligned; + +}; + +extern const struct dev_pm_ops ad714x_pm; +struct ad714x_chip *ad714x_probe(struct device *dev, u16 bus_type, int irq, + ad714x_read_t read, ad714x_write_t write); + +#endif -- cgit v1.3.1