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, 207 insertions, 0 deletions

diff --git a/drivers/reset/reset-simple.c b/drivers/reset/reset-simple.c
new file mode 100644
index 000000000..79e94ecfe
--- /dev/null
+++ b/drivers/reset/reset-simple.c
@@ -0,0 +1,207 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Simple Reset Controller Driver
+ *
+ * Copyright (C) 2017 Pengutronix, Philipp Zabel <kernel@pengutronix.de>
+ *
+ * Based on Allwinner SoCs Reset Controller driver
+ *
+ * Copyright 2013 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset-controller.h>
+#include <linux/reset/reset-simple.h>
+#include <linux/spinlock.h>
+
+static inline struct reset_simple_data *
+to_reset_simple_data(struct reset_controller_dev *rcdev)
+{
+	return container_of(rcdev, struct reset_simple_data, rcdev);
+}
+
+static int reset_simple_update(struct reset_controller_dev *rcdev,
+			       unsigned long id, bool assert)
+{
+	struct reset_simple_data *data = to_reset_simple_data(rcdev);
+	int reg_width = sizeof(u32);
+	int bank = id / (reg_width * BITS_PER_BYTE);
+	int offset = id % (reg_width * BITS_PER_BYTE);
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(&data->lock, flags);
+
+	reg = readl(data->membase + (bank * reg_width));
+	if (assert ^ data->active_low)
+		reg |= BIT(offset);
+	else
+		reg &= ~BIT(offset);
+	writel(reg, data->membase + (bank * reg_width));
+
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	return 0;
+}
+
+static int reset_simple_assert(struct reset_controller_dev *rcdev,
+			       unsigned long id)
+{
+	return reset_simple_update(rcdev, id, true);
+}
+
+static int reset_simple_deassert(struct reset_controller_dev *rcdev,
+				 unsigned long id)
+{
+	return reset_simple_update(rcdev, id, false);
+}
+
+static int reset_simple_reset(struct reset_controller_dev *rcdev,
+			      unsigned long id)
+{
+	struct reset_simple_data *data = to_reset_simple_data(rcdev);
+	int ret;
+
+	if (!data->reset_us)
+		return -ENOTSUPP;
+
+	ret = reset_simple_assert(rcdev, id);
+	if (ret)
+		return ret;
+
+	usleep_range(data->reset_us, data->reset_us * 2);
+
+	return reset_simple_deassert(rcdev, id);
+}
+
+static int reset_simple_status(struct reset_controller_dev *rcdev,
+			       unsigned long id)
+{
+	struct reset_simple_data *data = to_reset_simple_data(rcdev);
+	int reg_width = sizeof(u32);
+	int bank = id / (reg_width * BITS_PER_BYTE);
+	int offset = id % (reg_width * BITS_PER_BYTE);
+	u32 reg;
+
+	reg = readl(data->membase + (bank * reg_width));
+
+	return !(reg & BIT(offset)) ^ !data->status_active_low;
+}
+
+const struct reset_control_ops reset_simple_ops = {
+	.assert		= reset_simple_assert,
+	.deassert	= reset_simple_deassert,
+	.reset		= reset_simple_reset,
+	.status		= reset_simple_status,
+};
+EXPORT_SYMBOL_GPL(reset_simple_ops);
+
+/**
+ * struct reset_simple_devdata - simple reset controller properties
+ * @reg_offset: offset between base address and first reset register.
+ * @nr_resets: number of resets. If not set, default to resource size in bits.
+ * @active_low: if true, bits are cleared to assert the reset. Otherwise, bits
+ *              are set to assert the reset.
+ * @status_active_low: if true, bits read back as cleared while the reset is
+ *                     asserted. Otherwise, bits read back as set while the
+ *                     reset is asserted.
+ */
+struct reset_simple_devdata {
+	u32 reg_offset;
+	u32 nr_resets;
+	bool active_low;
+	bool status_active_low;
+};
+
+#define SOCFPGA_NR_BANKS	8
+
+static const struct reset_simple_devdata reset_simple_socfpga = {
+	.reg_offset = 0x20,
+	.nr_resets = SOCFPGA_NR_BANKS * 32,
+	.status_active_low = true,
+};
+
+static const struct reset_simple_devdata reset_simple_active_low = {
+	.active_low = true,
+	.status_active_low = true,
+};
+
+static const struct of_device_id reset_simple_dt_ids[] = {
+	{ .compatible = "altr,stratix10-rst-mgr",
+		.data = &reset_simple_socfpga },
+	{ .compatible = "st,stm32-rcc", },
+	{ .compatible = "allwinner,sun6i-a31-clock-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "zte,zx296718-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "aspeed,ast2400-lpc-reset" },
+	{ .compatible = "aspeed,ast2500-lpc-reset" },
+	{ .compatible = "aspeed,ast2600-lpc-reset" },
+	{ .compatible = "bitmain,bm1880-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "brcm,bcm4908-misc-pcie-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "snps,dw-high-reset" },
+	{ .compatible = "snps,dw-low-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "sophgo,cv1800b-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "sophgo,sg2042-reset",
+		.data = &reset_simple_active_low },
+	{ /* sentinel */ },
+};
+
+static int reset_simple_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct reset_simple_devdata *devdata;
+	struct reset_simple_data *data;
+	void __iomem *membase;
+	struct resource *res;
+	u32 reg_offset = 0;
+
+	devdata = of_device_get_match_data(dev);
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	membase = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(membase))
+		return PTR_ERR(membase);
+
+	spin_lock_init(&data->lock);
+	data->membase = membase;
+	data->rcdev.owner = THIS_MODULE;
+	data->rcdev.nr_resets = resource_size(res) * BITS_PER_BYTE;
+	data->rcdev.ops = &reset_simple_ops;
+	data->rcdev.of_node = dev->of_node;
+
+	if (devdata) {
+		reg_offset = devdata->reg_offset;
+		if (devdata->nr_resets)
+			data->rcdev.nr_resets = devdata->nr_resets;
+		data->active_low = devdata->active_low;
+		data->status_active_low = devdata->status_active_low;
+	}
+
+	data->membase += reg_offset;
+
+	return devm_reset_controller_register(dev, &data->rcdev);
+}
+
+static struct platform_driver reset_simple_driver = {
+	.probe	= reset_simple_probe,
+	.driver = {
+		.name		= "simple-reset",
+		.of_match_table	= reset_simple_dt_ids,
+	},
+};
+builtin_platform_driver(reset_simple_driver);