diff options
| author | Tim Chen <tim.c.chen@linux.intel.com> | 2026-09-21 17:37:22 -0700 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2026-09-22 10:49:53 +0200 |
| commit | 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 (patch) | |
| tree | 176dc2d685debcfb082c151ee94f2425ac96b364 /drivers/soc/Makefile | |
| download | linux-stable-0d6526f82c3cdefcca47f73f5fc08dc6f335eac6.tar.gz linux-stable-0d6526f82c3cdefcca47f73f5fc08dc6f335eac6.zip | |
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
Diffstat (limited to 'drivers/soc/Makefile')
| -rw-r--r-- | drivers/soc/Makefile | 39 |
1 files changed, 39 insertions, 0 deletions
diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile new file mode 100644 index 000000000..c9e689080 --- /dev/null +++ b/drivers/soc/Makefile @@ -0,0 +1,39 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the Linux Kernel SOC specific device drivers. +# + +obj-y += apple/ +obj-y += aspeed/ +obj-$(CONFIG_ARCH_AT91) += atmel/ +obj-y += bcm/ +obj-$(CONFIG_ARCH_CANAAN) += canaan/ +obj-$(CONFIG_EP93XX_SOC) += cirrus/ +obj-$(CONFIG_ARCH_DOVE) += dove/ +obj-$(CONFIG_MACH_DOVE) += dove/ +obj-y += fsl/ +obj-y += fujitsu/ +obj-$(CONFIG_ARCH_GEMINI) += gemini/ +obj-y += hisilicon/ +obj-y += imx/ +obj-y += ixp4xx/ +obj-$(CONFIG_SOC_XWAY) += lantiq/ +obj-$(CONFIG_LITEX_SOC_CONTROLLER) += litex/ +obj-y += loongson/ +obj-y += mediatek/ +obj-y += microchip/ +obj-y += nuvoton/ +obj-y += pxa/ +obj-y += amlogic/ +obj-y += qcom/ +obj-y += renesas/ +obj-y += rockchip/ +obj-$(CONFIG_SOC_SAMSUNG) += samsung/ +obj-y += sophgo/ +obj-y += sunxi/ +obj-$(CONFIG_ARCH_TEGRA) += tegra/ +obj-y += ti/ +obj-$(CONFIG_ARCH_U8500) += ux500/ +obj-y += versatile/ +obj-y += vt8500/ +obj-y += xilinx/ |