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, 140 insertions, 0 deletions

diff --git a/drivers/rtc/rtc-macsmc.c b/drivers/rtc/rtc-macsmc.c
new file mode 100644
index 000000000..8fe883066
--- /dev/null
+++ b/drivers/rtc/rtc-macsmc.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Apple SMC RTC driver
+ * Copyright The Asahi Linux Contributors
+ */
+
+#include <linux/bitops.h>
+#include <linux/mfd/macsmc.h>
+#include <linux/module.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+#include <linux/slab.h>
+
+/* 48-bit RTC */
+#define RTC_BYTES 6
+#define RTC_BITS (8 * RTC_BYTES)
+
+/* 32768 Hz clock */
+#define RTC_SEC_SHIFT 15
+
+struct macsmc_rtc {
+	struct device *dev;
+	struct apple_smc *smc;
+	struct rtc_device *rtc_dev;
+	struct nvmem_cell *rtc_offset;
+};
+
+static int macsmc_rtc_get_time(struct device *dev, struct rtc_time *tm)
+{
+	struct macsmc_rtc *rtc = dev_get_drvdata(dev);
+	u64 ctr = 0, off = 0;
+	time64_t now;
+	void *p_off;
+	size_t len;
+	int ret;
+
+	ret = apple_smc_read(rtc->smc, SMC_KEY(CLKM), &ctr, RTC_BYTES);
+	if (ret < 0)
+		return ret;
+	if (ret != RTC_BYTES)
+		return -EIO;
+
+	p_off = nvmem_cell_read(rtc->rtc_offset, &len);
+	if (IS_ERR(p_off))
+		return PTR_ERR(p_off);
+	if (len < RTC_BYTES) {
+		kfree(p_off);
+		return -EIO;
+	}
+
+	memcpy(&off, p_off, RTC_BYTES);
+	kfree(p_off);
+
+	/* Sign extend from 48 to 64 bits, then arithmetic shift right 15 bits to get seconds */
+	now = sign_extend64(ctr + off, RTC_BITS - 1) >> RTC_SEC_SHIFT;
+	rtc_time64_to_tm(now, tm);
+
+	return ret;
+}
+
+static int macsmc_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct macsmc_rtc *rtc = dev_get_drvdata(dev);
+	u64 ctr = 0, off = 0;
+	int ret;
+
+	ret = apple_smc_read(rtc->smc, SMC_KEY(CLKM), &ctr, RTC_BYTES);
+	if (ret < 0)
+		return ret;
+	if (ret != RTC_BYTES)
+		return -EIO;
+
+	/* This sets the offset such that the set second begins now */
+	off = (rtc_tm_to_time64(tm) << RTC_SEC_SHIFT) - ctr;
+	return nvmem_cell_write(rtc->rtc_offset, &off, RTC_BYTES);
+}
+
+static const struct rtc_class_ops macsmc_rtc_ops = {
+	.read_time = macsmc_rtc_get_time,
+	.set_time = macsmc_rtc_set_time,
+};
+
+static int macsmc_rtc_probe(struct platform_device *pdev)
+{
+	struct apple_smc *smc = dev_get_drvdata(pdev->dev.parent);
+	struct macsmc_rtc *rtc;
+
+	/*
+	 * MFD will probe this device even without a node in the device tree,
+	 * thus bail out early if the SMC on the current machines does not
+	 * support RTC and has no node in the device tree.
+	 */
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
+	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
+	if (!rtc)
+		return -ENOMEM;
+
+	rtc->dev = &pdev->dev;
+	rtc->smc = smc;
+
+	rtc->rtc_offset = devm_nvmem_cell_get(&pdev->dev, "rtc_offset");
+	if (IS_ERR(rtc->rtc_offset))
+		return dev_err_probe(&pdev->dev, PTR_ERR(rtc->rtc_offset),
+				     "Failed to get rtc_offset NVMEM cell\n");
+
+	rtc->rtc_dev = devm_rtc_allocate_device(&pdev->dev);
+	if (IS_ERR(rtc->rtc_dev))
+		return PTR_ERR(rtc->rtc_dev);
+
+	rtc->rtc_dev->ops = &macsmc_rtc_ops;
+	rtc->rtc_dev->range_min = S64_MIN >> (RTC_SEC_SHIFT + (64 - RTC_BITS));
+	rtc->rtc_dev->range_max = S64_MAX >> (RTC_SEC_SHIFT + (64 - RTC_BITS));
+
+	platform_set_drvdata(pdev, rtc);
+
+	return devm_rtc_register_device(rtc->rtc_dev);
+}
+
+static const struct of_device_id macsmc_rtc_of_table[] = {
+	{ .compatible = "apple,smc-rtc", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, macsmc_rtc_of_table);
+
+static struct platform_driver macsmc_rtc_driver = {
+	.driver = {
+		.name = "macsmc-rtc",
+		.of_match_table = macsmc_rtc_of_table,
+	},
+	.probe = macsmc_rtc_probe,
+};
+module_platform_driver(macsmc_rtc_driver);
+
+MODULE_LICENSE("Dual MIT/GPL");
+MODULE_DESCRIPTION("Apple SMC RTC driver");
+MODULE_AUTHOR("Hector Martin <marcan@marcan.st>");