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/lib/crypto/mpi/mpi-cmp.c b/lib/crypto/mpi/mpi-cmp.c
new file mode 100644
index 000000000..b42929296
--- /dev/null
+++ b/lib/crypto/mpi/mpi-cmp.c
@@ -0,0 +1,74 @@
+/* mpi-cmp.c  -  MPI functions
+ * Copyright (C) 1998, 1999 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ */
+
+#include <linux/export.h>
+
+#include "mpi-internal.h"
+
+int mpi_cmp_ui(MPI u, unsigned long v)
+{
+	mpi_limb_t limb = v;
+
+	mpi_normalize(u);
+	if (u->nlimbs == 0) {
+		if (v == 0)
+			return 0;
+		else
+			return -1;
+	}
+	if (u->sign)
+		return -1;
+	if (u->nlimbs > 1)
+		return 1;
+
+	if (u->d[0] == limb)
+		return 0;
+	else if (u->d[0] > limb)
+		return 1;
+	else
+		return -1;
+}
+EXPORT_SYMBOL_GPL(mpi_cmp_ui);
+
+int mpi_cmp(MPI u, MPI v)
+{
+	mpi_size_t usize, vsize;
+	int cmp;
+
+	mpi_normalize(u);
+	mpi_normalize(v);
+	usize = u->nlimbs;
+	vsize = v->nlimbs;
+	if (!u->sign && v->sign)
+		return 1;
+	if (u->sign && !v->sign)
+		return -1;
+	if (usize != vsize && !u->sign && !v->sign)
+		return usize - vsize;
+	if (usize != vsize && u->sign && v->sign)
+		return vsize - usize;
+	if (!usize)
+		return 0;
+	cmp = mpihelp_cmp(u->d, v->d, usize);
+	if (u->sign)
+		return -cmp;
+	return cmp;
+}
+EXPORT_SYMBOL_GPL(mpi_cmp);