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, 107 insertions, 0 deletions

diff --git a/include/drm/task_barrier.h b/include/drm/task_barrier.h
new file mode 100644
index 000000000..f6e6ed529
--- /dev/null
+++ b/include/drm/task_barrier.h
@@ -0,0 +1,107 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include <linux/semaphore.h>
+#include <linux/atomic.h>
+
+/*
+ * Reusable 2 PHASE task barrier (rendez-vous point) implementation for N tasks.
+ * Based on the Little book of semaphores - https://greenteapress.com/wp/semaphores/
+ */
+
+
+
+#ifndef DRM_TASK_BARRIER_H_
+#define DRM_TASK_BARRIER_H_
+
+/*
+ * Represents an instance of a task barrier.
+ */
+struct task_barrier {
+	unsigned int n;
+	atomic_t count;
+	struct semaphore enter_turnstile;
+	struct semaphore exit_turnstile;
+};
+
+static inline void task_barrier_signal_turnstile(struct semaphore *turnstile,
+						 unsigned int n)
+{
+	int i;
+
+	for (i = 0 ; i < n; i++)
+		up(turnstile);
+}
+
+static inline void task_barrier_init(struct task_barrier *tb)
+{
+	tb->n = 0;
+	atomic_set(&tb->count, 0);
+	sema_init(&tb->enter_turnstile, 0);
+	sema_init(&tb->exit_turnstile, 0);
+}
+
+static inline void task_barrier_add_task(struct task_barrier *tb)
+{
+	tb->n++;
+}
+
+static inline void task_barrier_rem_task(struct task_barrier *tb)
+{
+	tb->n--;
+}
+
+/*
+ * Lines up all the threads BEFORE the critical point.
+ *
+ * When all thread passed this code the entry barrier is back to locked state.
+ */
+static inline void task_barrier_enter(struct task_barrier *tb)
+{
+	if (atomic_inc_return(&tb->count) == tb->n)
+		task_barrier_signal_turnstile(&tb->enter_turnstile, tb->n);
+
+	down(&tb->enter_turnstile);
+}
+
+/*
+ * Lines up all the threads AFTER the critical point.
+ *
+ * This function is used to avoid any one thread running ahead if the barrier is
+ *  used repeatedly .
+ */
+static inline void task_barrier_exit(struct task_barrier *tb)
+{
+	if (atomic_dec_return(&tb->count) == 0)
+		task_barrier_signal_turnstile(&tb->exit_turnstile, tb->n);
+
+	down(&tb->exit_turnstile);
+}
+
+/* Convinieince function when nothing to be done in between entry and exit */
+static inline void task_barrier_full(struct task_barrier *tb)
+{
+	task_barrier_enter(tb);
+	task_barrier_exit(tb);
+}
+
+#endif