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, 170 insertions, 0 deletions

diff --git a/drivers/mfd/altera-a10sr.c b/drivers/mfd/altera-a10sr.c
new file mode 100644
index 000000000..9c0262228
--- /dev/null
+++ b/drivers/mfd/altera-a10sr.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Altera Arria10 DevKit System Resource MFD Driver
+ *
+ * Author: Thor Thayer <tthayer@opensource.altera.com>
+ *
+ * Copyright Intel Corporation (C) 2014-2016. All Rights Reserved
+ *
+ * SPI access for Altera Arria10 MAX5 System Resource Chip
+ *
+ * Adapted from DA9052
+ */
+
+#include <linux/mfd/altera-a10sr.h>
+#include <linux/mfd/core.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/spi/spi.h>
+
+static const struct mfd_cell altr_a10sr_subdev_info[] = {
+	{
+		.name = "altr_a10sr_gpio",
+		.of_compatible = "altr,a10sr-gpio",
+	},
+	{
+		.name = "altr_a10sr_reset",
+		.of_compatible = "altr,a10sr-reset",
+	},
+};
+
+static bool altr_a10sr_reg_readable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ALTR_A10SR_VERSION_READ:
+	case ALTR_A10SR_LED_REG:
+	case ALTR_A10SR_PBDSW_REG:
+	case ALTR_A10SR_PBDSW_IRQ_REG:
+	case ALTR_A10SR_PWR_GOOD1_REG:
+	case ALTR_A10SR_PWR_GOOD2_REG:
+	case ALTR_A10SR_PWR_GOOD3_REG:
+	case ALTR_A10SR_FMCAB_REG:
+	case ALTR_A10SR_HPS_RST_REG:
+	case ALTR_A10SR_USB_QSPI_REG:
+	case ALTR_A10SR_SFPA_REG:
+	case ALTR_A10SR_SFPB_REG:
+	case ALTR_A10SR_I2C_M_REG:
+	case ALTR_A10SR_WARM_RST_REG:
+	case ALTR_A10SR_WR_KEY_REG:
+	case ALTR_A10SR_PMBUS_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool altr_a10sr_reg_writeable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ALTR_A10SR_LED_REG:
+	case ALTR_A10SR_PBDSW_IRQ_REG:
+	case ALTR_A10SR_FMCAB_REG:
+	case ALTR_A10SR_HPS_RST_REG:
+	case ALTR_A10SR_USB_QSPI_REG:
+	case ALTR_A10SR_SFPA_REG:
+	case ALTR_A10SR_SFPB_REG:
+	case ALTR_A10SR_WARM_RST_REG:
+	case ALTR_A10SR_WR_KEY_REG:
+	case ALTR_A10SR_PMBUS_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool altr_a10sr_reg_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ALTR_A10SR_PBDSW_REG:
+	case ALTR_A10SR_PBDSW_IRQ_REG:
+	case ALTR_A10SR_PWR_GOOD1_REG:
+	case ALTR_A10SR_PWR_GOOD2_REG:
+	case ALTR_A10SR_PWR_GOOD3_REG:
+	case ALTR_A10SR_HPS_RST_REG:
+	case ALTR_A10SR_I2C_M_REG:
+	case ALTR_A10SR_WARM_RST_REG:
+	case ALTR_A10SR_WR_KEY_REG:
+	case ALTR_A10SR_PMBUS_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const struct regmap_config altr_a10sr_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.cache_type = REGCACHE_NONE,
+
+	.use_single_read = true,
+	.use_single_write = true,
+	.read_flag_mask = 1,
+	.write_flag_mask = 0,
+
+	.max_register = ALTR_A10SR_WR_KEY_REG,
+	.readable_reg = altr_a10sr_reg_readable,
+	.writeable_reg = altr_a10sr_reg_writeable,
+	.volatile_reg = altr_a10sr_reg_volatile,
+
+};
+
+static int altr_a10sr_spi_probe(struct spi_device *spi)
+{
+	int ret;
+	struct altr_a10sr *a10sr;
+
+	a10sr = devm_kzalloc(&spi->dev, sizeof(*a10sr),
+			     GFP_KERNEL);
+	if (!a10sr)
+		return -ENOMEM;
+
+	spi->mode = SPI_MODE_3;
+	spi->bits_per_word = 8;
+	spi_setup(spi);
+
+	a10sr->dev = &spi->dev;
+
+	spi_set_drvdata(spi, a10sr);
+
+	a10sr->regmap = devm_regmap_init_spi(spi, &altr_a10sr_regmap_config);
+	if (IS_ERR(a10sr->regmap)) {
+		ret = PTR_ERR(a10sr->regmap);
+		dev_err(&spi->dev, "Failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = devm_mfd_add_devices(a10sr->dev, PLATFORM_DEVID_AUTO,
+				   altr_a10sr_subdev_info,
+				   ARRAY_SIZE(altr_a10sr_subdev_info),
+				   NULL, 0, NULL);
+	if (ret)
+		dev_err(a10sr->dev, "Failed to register sub-devices: %d\n",
+			ret);
+
+	return ret;
+}
+
+static const struct of_device_id altr_a10sr_spi_of_match[] = {
+	{ .compatible = "altr,a10sr" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, altr_a10sr_spi_of_match);
+
+static const struct spi_device_id altr_a10sr_spi_ids[] = {
+	{ .name = "a10sr" },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, altr_a10sr_spi_ids);
+
+static struct spi_driver altr_a10sr_spi_driver = {
+	.probe = altr_a10sr_spi_probe,
+	.driver = {
+		.name = "altr_a10sr",
+		.of_match_table = altr_a10sr_spi_of_match,
+	},
+	.id_table = altr_a10sr_spi_ids,
+};
+builtin_driver(altr_a10sr_spi_driver, spi_register_driver)