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, 49 insertions, 0 deletions

diff --git a/net/dsa/Makefile b/net/dsa/Makefile
new file mode 100644
index 000000000..d15bcf5c6
--- /dev/null
+++ b/net/dsa/Makefile
@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# the stubs are built-in whenever DSA is built-in or module
+ifdef CONFIG_NET_DSA
+obj-y := stubs.o
+endif
+
+# the core
+obj-$(CONFIG_NET_DSA) += dsa_core.o
+dsa_core-y += \
+	conduit.o \
+	devlink.o \
+	dsa.o \
+	netlink.o \
+	port.o \
+	switch.o \
+	tag.o \
+	tag_8021q.o \
+	trace.o \
+	user.o
+
+# tagging formats
+obj-$(CONFIG_NET_DSA_TAG_AR9331) += tag_ar9331.o
+obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o
+obj-$(CONFIG_NET_DSA_TAG_DSA_COMMON) += tag_dsa.o
+obj-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o
+obj-$(CONFIG_NET_DSA_TAG_HELLCREEK) += tag_hellcreek.o
+obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o
+obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o
+obj-$(CONFIG_NET_DSA_TAG_MT7628) += tag_mt7628.o
+obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o
+obj-$(CONFIG_NET_DSA_TAG_MXL_862XX) += tag_mxl862xx.o
+obj-$(CONFIG_NET_DSA_TAG_MXL_GSW1XX) += tag_mxl-gsw1xx.o
+obj-$(CONFIG_NET_DSA_TAG_NETC) += tag_netc.o
+obj-$(CONFIG_NET_DSA_TAG_NONE) += tag_none.o
+obj-$(CONFIG_NET_DSA_TAG_OCELOT) += tag_ocelot.o
+obj-$(CONFIG_NET_DSA_TAG_OCELOT_8021Q) += tag_ocelot_8021q.o
+obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o
+obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o
+obj-$(CONFIG_NET_DSA_TAG_RTL8_4) += tag_rtl8_4.o
+obj-$(CONFIG_NET_DSA_TAG_RZN1_A5PSW) += tag_rzn1_a5psw.o
+obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o
+obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o
+obj-$(CONFIG_NET_DSA_TAG_VSC73XX_8021Q) += tag_vsc73xx_8021q.o
+obj-$(CONFIG_NET_DSA_TAG_XRS700X) += tag_xrs700x.o
+obj-$(CONFIG_NET_DSA_TAG_YT921X) += tag_yt921x.o
+
+# for tracing framework to find trace.h
+CFLAGS_trace.o := -I$(src)