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, 59 insertions, 0 deletions

diff --git a/drivers/soc/apple/rtkit-internal.h b/drivers/soc/apple/rtkit-internal.h
new file mode 100644
index 000000000..b8d524467
--- /dev/null
+++ b/drivers/soc/apple/rtkit-internal.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
+/*
+ * Apple RTKit IPC library
+ * Copyright (C) The Asahi Linux Contributors
+ */
+
+#ifndef _APPLE_RTKIT_INTERAL_H
+#define _APPLE_RTKIT_INTERAL_H
+
+#include <linux/bitfield.h>
+#include <linux/bitmap.h>
+#include <linux/completion.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/soc/apple/rtkit.h>
+#include <linux/workqueue.h>
+#include "mailbox.h"
+
+#define APPLE_RTKIT_APP_ENDPOINT_START 0x20
+#define APPLE_RTKIT_MAX_ENDPOINTS 0x100
+
+struct apple_rtkit {
+	void *cookie;
+	const struct apple_rtkit_ops *ops;
+	struct device *dev;
+
+	struct apple_mbox *mbox;
+
+	struct completion epmap_completion;
+	struct completion iop_pwr_ack_completion;
+	struct completion ap_pwr_ack_completion;
+
+	int boot_result;
+	int version;
+
+	unsigned int iop_power_state;
+	unsigned int ap_power_state;
+	bool crashed;
+
+	DECLARE_BITMAP(endpoints, APPLE_RTKIT_MAX_ENDPOINTS);
+
+	struct apple_rtkit_shmem ioreport_buffer;
+	struct apple_rtkit_shmem crashlog_buffer;
+	struct apple_rtkit_shmem oslog_buffer;
+
+	struct apple_rtkit_shmem syslog_buffer;
+	char *syslog_msg_buffer;
+	size_t syslog_n_entries;
+	size_t syslog_msg_size;
+
+	struct workqueue_struct *wq;
+};
+
+void apple_rtkit_crashlog_dump(struct apple_rtkit *rtk, u8 *bfr, size_t size);
+
+#endif