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

2 files changed, 73 insertions, 0 deletions

diff --git a/drivers/soc/gemini/Makefile b/drivers/soc/gemini/Makefile
new file mode 100644
index 000000000..8cbd1e45d
--- /dev/null
+++ b/drivers/soc/gemini/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y	+= soc-gemini.o
diff --git a/drivers/soc/gemini/soc-gemini.c b/drivers/soc/gemini/soc-gemini.c
new file mode 100644
index 000000000..642b96c91
--- /dev/null
+++ b/drivers/soc/gemini/soc-gemini.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Linaro Ltd.
+ *
+ * Author: Linus Walleij <linus.walleij@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2, as
+ * published by the Free Software Foundation.
+ *
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/of.h>
+
+#define GLOBAL_WORD_ID				0x00
+#define GEMINI_GLOBAL_ARB1_CTRL			0x2c
+#define GEMINI_ARB1_BURST_MASK			GENMASK(21, 16)
+#define GEMINI_ARB1_BURST_SHIFT			16
+/* These all define the priority on the BUS2 backplane */
+#define GEMINI_ARB1_PRIO_MASK			GENMASK(9, 0)
+#define GEMINI_ARB1_DMAC_HIGH_PRIO		BIT(0)
+#define GEMINI_ARB1_IDE_HIGH_PRIO		BIT(1)
+#define GEMINI_ARB1_RAID_HIGH_PRIO		BIT(2)
+#define GEMINI_ARB1_SECURITY_HIGH_PRIO		BIT(3)
+#define GEMINI_ARB1_GMAC0_HIGH_PRIO		BIT(4)
+#define GEMINI_ARB1_GMAC1_HIGH_PRIO		BIT(5)
+#define GEMINI_ARB1_USB0_HIGH_PRIO		BIT(6)
+#define GEMINI_ARB1_USB1_HIGH_PRIO		BIT(7)
+#define GEMINI_ARB1_PCI_HIGH_PRIO		BIT(8)
+#define GEMINI_ARB1_TVE_HIGH_PRIO		BIT(9)
+
+#define GEMINI_DEFAULT_BURST_SIZE		0x20
+#define GEMINI_DEFAULT_PRIO			(GEMINI_ARB1_GMAC0_HIGH_PRIO | \
+						 GEMINI_ARB1_GMAC1_HIGH_PRIO)
+
+static int __init gemini_soc_init(void)
+{
+	struct regmap *map;
+	u32 rev;
+	u32 val;
+	int ret;
+
+	/* Multiplatform guard, only proceed on Gemini */
+	if (!of_machine_is_compatible("cortina,gemini"))
+		return 0;
+
+	map = syscon_regmap_lookup_by_compatible("cortina,gemini-syscon");
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+	ret = regmap_read(map, GLOBAL_WORD_ID, &rev);
+	if (ret)
+		return ret;
+
+	val = (GEMINI_DEFAULT_BURST_SIZE << GEMINI_ARB1_BURST_SHIFT) |
+		GEMINI_DEFAULT_PRIO;
+
+	/* Set up system arbitration */
+	regmap_update_bits(map,
+			   GEMINI_GLOBAL_ARB1_CTRL,
+			   GEMINI_ARB1_BURST_MASK | GEMINI_ARB1_PRIO_MASK,
+			   val);
+
+	pr_info("Gemini SoC %04x revision %02x, set arbitration %08x\n",
+		rev >> 8, rev & 0xff, val);
+
+	return 0;
+}
+subsys_initcall(gemini_soc_init);