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, 74 insertions, 0 deletions

diff --git a/arch/m68k/lib/memset.c b/arch/m68k/lib/memset.c
new file mode 100644
index 000000000..8a7639f0a
--- /dev/null
+++ b/arch/m68k/lib/memset.c
@@ -0,0 +1,74 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+
+void *memset(void *s, int c, size_t count)
+{
+	void *xs = s;
+	size_t temp;
+
+	if (!count)
+		return xs;
+	c &= 0xff;
+	c |= c << 8;
+	c |= c << 16;
+	if ((long)s & 1) {
+		char *cs = s;
+		*cs++ = c;
+		s = cs;
+		count--;
+	}
+	if (count > 2 && (long)s & 2) {
+		short *ss = s;
+		*ss++ = c;
+		s = ss;
+		count -= 2;
+	}
+	temp = count >> 2;
+	if (temp) {
+		long *ls = s;
+#if defined(CONFIG_M68000) || defined(CONFIG_COLDFIRE)
+		for (; temp; temp--)
+			*ls++ = c;
+#else
+		size_t temp1;
+		asm volatile (
+			"	movel %1,%2\n"
+			"	andw  #7,%2\n"
+			"	lsrl  #3,%1\n"
+			"	negw  %2\n"
+			"	jmp   %%pc@(2f,%2:w:2)\n"
+			"1:	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"2:	dbra  %1,1b\n"
+			"	clrw  %1\n"
+			"	subql #1,%1\n"
+			"	jpl   1b"
+			: "=a" (ls), "=d" (temp), "=&d" (temp1)
+			: "d" (c), "0" (ls), "1" (temp));
+#endif
+		s = ls;
+	}
+	if (count & 2) {
+		short *ss = s;
+		*ss++ = c;
+		s = ss;
+	}
+	if (count & 1) {
+		char *cs = s;
+		*cs = c;
+	}
+	return xs;
+}
+EXPORT_SYMBOL(memset);