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, 131 insertions, 0 deletions

diff --git a/arch/mips/bcm63xx/dev-flash.c b/arch/mips/bcm63xx/dev-flash.c
new file mode 100644
index 000000000..f9cc015d3
--- /dev/null
+++ b/arch/mips/bcm63xx/dev-flash.c
@@ -0,0 +1,131 @@
+/*
+ * Broadcom BCM63xx flash registration
+ *
+ * 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.
+ *
+ * Copyright (C) 2008 Maxime Bizon <mbizon@freebox.fr>
+ * Copyright (C) 2008 Florian Fainelli <florian@openwrt.org>
+ * Copyright (C) 2012 Jonas Gorski <jonas.gorski@gmail.com>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/physmap.h>
+
+#include <bcm63xx_cpu.h>
+#include <bcm63xx_dev_flash.h>
+#include <bcm63xx_regs.h>
+#include <bcm63xx_io.h>
+
+static struct mtd_partition mtd_partitions[] = {
+	{
+		.name		= "cfe",
+		.offset		= 0x0,
+		.size		= 0x40000,
+	}
+};
+
+static const char *bcm63xx_part_types[] = { "bcm63xxpart", NULL };
+
+static struct physmap_flash_data flash_data = {
+	.width			= 2,
+	.parts			= mtd_partitions,
+	.part_probe_types	= bcm63xx_part_types,
+};
+
+static struct resource mtd_resources[] = {
+	{
+		.start		= 0,	/* filled at runtime */
+		.end		= 0,	/* filled at runtime */
+		.flags		= IORESOURCE_MEM,
+	}
+};
+
+static struct platform_device mtd_dev = {
+	.name			= "physmap-flash",
+	.resource		= mtd_resources,
+	.num_resources		= ARRAY_SIZE(mtd_resources),
+	.dev			= {
+		.platform_data	= &flash_data,
+	},
+};
+
+static int __init bcm63xx_detect_flash_type(void)
+{
+	u32 val;
+
+	switch (bcm63xx_get_cpu_id()) {
+	case BCM6328_CPU_ID:
+		val = bcm_misc_readl(MISC_STRAPBUS_6328_REG);
+		if (val & STRAPBUS_6328_BOOT_SEL_SERIAL)
+			return BCM63XX_FLASH_TYPE_SERIAL;
+		else
+			return BCM63XX_FLASH_TYPE_NAND;
+	case BCM6338_CPU_ID:
+	case BCM6345_CPU_ID:
+	case BCM6348_CPU_ID:
+		/* no way to auto detect so assume parallel */
+		return BCM63XX_FLASH_TYPE_PARALLEL;
+	case BCM3368_CPU_ID:
+	case BCM6358_CPU_ID:
+		val = bcm_gpio_readl(GPIO_STRAPBUS_REG);
+		if (val & STRAPBUS_6358_BOOT_SEL_PARALLEL)
+			return BCM63XX_FLASH_TYPE_PARALLEL;
+		else
+			return BCM63XX_FLASH_TYPE_SERIAL;
+	case BCM6362_CPU_ID:
+		val = bcm_misc_readl(MISC_STRAPBUS_6362_REG);
+		if (val & STRAPBUS_6362_BOOT_SEL_SERIAL)
+			return BCM63XX_FLASH_TYPE_SERIAL;
+		else
+			return BCM63XX_FLASH_TYPE_NAND;
+	case BCM6368_CPU_ID:
+		val = bcm_gpio_readl(GPIO_STRAPBUS_REG);
+		switch (val & STRAPBUS_6368_BOOT_SEL_MASK) {
+		case STRAPBUS_6368_BOOT_SEL_NAND:
+			return BCM63XX_FLASH_TYPE_NAND;
+		case STRAPBUS_6368_BOOT_SEL_SERIAL:
+			return BCM63XX_FLASH_TYPE_SERIAL;
+		case STRAPBUS_6368_BOOT_SEL_PARALLEL:
+			return BCM63XX_FLASH_TYPE_PARALLEL;
+		}
+		fallthrough;
+	default:
+		return -EINVAL;
+	}
+}
+
+int __init bcm63xx_flash_register(void)
+{
+	int flash_type;
+	u32 val;
+
+	flash_type = bcm63xx_detect_flash_type();
+
+	switch (flash_type) {
+	case BCM63XX_FLASH_TYPE_PARALLEL:
+		/* read base address of boot chip select (0) */
+		val = bcm_mpi_readl(MPI_CSBASE_REG(0));
+		val &= MPI_CSBASE_BASE_MASK;
+
+		mtd_resources[0].start = val;
+		mtd_resources[0].end = 0x1FFFFFFF;
+
+		return platform_device_register(&mtd_dev);
+	case BCM63XX_FLASH_TYPE_SERIAL:
+		pr_warn("unsupported serial flash detected\n");
+		return -ENODEV;
+	case BCM63XX_FLASH_TYPE_NAND:
+		pr_warn("unsupported NAND flash detected\n");
+		return -ENODEV;
+	default:
+		pr_err("flash detection failed for BCM%x: %d\n",
+		       bcm63xx_get_cpu_id(), flash_type);
+		return -ENODEV;
+	}
+}