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, 32 insertions, 0 deletions

diff --git a/scripts/makelst b/scripts/makelst
new file mode 100755
index 000000000..e432af073
--- /dev/null
+++ b/scripts/makelst
@@ -0,0 +1,32 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# A script to dump mixed source code & assembly
+# with correct relocations from System.map
+# Requires the following lines in makefile:
+#%.lst: %.c
+#	$(CC) $(c_flags) -g -c -o $*.o $< &&
+#	$(srctree)/scripts/makelst $*.o System.map $(OBJDUMP) > $@
+#
+# Copyright (C) 2000 IBM Corporation
+# Author(s): DJ Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
+#            William Stearns <wstearns@pobox.com>
+#
+
+# awk style field access
+field() {
+  shift $1 ; echo $1
+}
+
+t1=`$3 --syms $1 | grep .text | grep -m1 " F "`
+if [ -n "$t1" ]; then
+  t2=`field 6 $t1`
+  if [ ! -r $2 ]; then
+    echo "No System.map" >&2
+  else
+    t3=`grep $t2 $2`
+    t4=`field 1 $t3`
+    t5=`field 1 $t1`
+    t6=`printf "%lu" $((0x$t4 - 0x$t5))`
+  fi
+fi
+$3 -r --source --adjust-vma=${t6:-0} $1