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, 38 insertions, 0 deletions

diff --git a/scripts/package/gen-diff-patch b/scripts/package/gen-diff-patch
new file mode 100755
index 000000000..f272f7770
--- /dev/null
+++ b/scripts/package/gen-diff-patch
@@ -0,0 +1,38 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+set -eu
+
+diff_patch=$1
+
+mkdir -p "$(dirname "${diff_patch}")"
+
+git -C "${srctree:-.}" diff HEAD > "${diff_patch}"
+
+if [ ! -s "${diff_patch}" ] ||
+   [ -z "$(git -C "${srctree:-.}" ls-files --other --exclude-standard | head -n1)" ]; then
+	exit
+fi
+
+# The source tarball, which is generated by 'git archive', contains everything
+# you committed in the repository. If you have local diff ('git diff HEAD'),
+# it will go into ${diff_patch}. If untracked files are remaining, the resulting
+# source package may not be correct.
+#
+# Examples:
+#  - You modified a source file to add #include "new-header.h"
+#    but forgot to add new-header.h
+#  - You modified a Makefile to add 'obj-$(CONFIG_FOO) += new-dirver.o'
+#    but you forgot to add new-driver.c
+#
+# You need to commit them, or at least stage them by 'git add'.
+#
+# This script does not take care of untracked files because doing so would
+# introduce additional complexity. Instead, print a warning message here if
+# untracked files are found.
+# If all untracked files are just garbage, you can ignore this warning.
+echo >&2 "============================ WARNING ============================"
+echo >&2 "Your working tree has diff from HEAD, and also untracked file(s)."
+echo >&2 "Please make sure you did 'git add' for all new files you need in"
+echo >&2 "the source package."
+echo >&2 "================================================================="