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, 224 insertions, 0 deletions

diff --git a/drivers/rtc/rtc-efi.c b/drivers/rtc/rtc-efi.c
new file mode 100644
index 000000000..b4f44999e
--- /dev/null
+++ b/drivers/rtc/rtc-efi.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * rtc-efi: RTC Class Driver for EFI-based systems
+ *
+ * Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+ *
+ * Author: dann frazier <dannf@dannf.org>
+ * Based on efirtc.c by Stephane Eranian
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/stringify.h>
+#include <linux/time.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+#include <linux/efi.h>
+
+#define EFI_ISDST (EFI_TIME_ADJUST_DAYLIGHT|EFI_TIME_IN_DAYLIGHT)
+
+/*
+ * returns day of the year [0-365]
+ */
+static inline int
+compute_yday(efi_time_t *eft)
+{
+	/* efi_time_t.month is in the [1-12] so, we need -1 */
+	return rtc_year_days(eft->day, eft->month - 1, eft->year);
+}
+
+/*
+ * returns day of the week [0-6] 0=Sunday
+ */
+static int
+compute_wday(efi_time_t *eft, int yday)
+{
+	int ndays = eft->year * (365 % 7)
+		    + (eft->year - 1) / 4
+		    - (eft->year - 1) / 100
+		    + (eft->year - 1) / 400
+		    + yday;
+
+	/*
+	 * 1/1/0000 may or may not have been a Sunday (if it ever existed at
+	 * all) but assuming it was makes this calculation work correctly.
+	 */
+	return ndays % 7;
+}
+
+static void
+convert_to_efi_time(struct rtc_time *wtime, efi_time_t *eft)
+{
+	eft->year	= wtime->tm_year + 1900;
+	eft->month	= wtime->tm_mon + 1;
+	eft->day	= wtime->tm_mday;
+	eft->hour	= wtime->tm_hour;
+	eft->minute	= wtime->tm_min;
+	eft->second	= wtime->tm_sec;
+	eft->nanosecond = 0;
+	eft->daylight	= wtime->tm_isdst ? EFI_ISDST : 0;
+	eft->timezone	= EFI_UNSPECIFIED_TIMEZONE;
+}
+
+static bool
+convert_from_efi_time(efi_time_t *eft, struct rtc_time *wtime)
+{
+	memset(wtime, 0, sizeof(*wtime));
+
+	if (eft->second >= 60)
+		return false;
+	wtime->tm_sec  = eft->second;
+
+	if (eft->minute >= 60)
+		return false;
+	wtime->tm_min  = eft->minute;
+
+	if (eft->hour >= 24)
+		return false;
+	wtime->tm_hour = eft->hour;
+
+	if (!eft->day || eft->day > 31)
+		return false;
+	wtime->tm_mday = eft->day;
+
+	if (!eft->month || eft->month > 12)
+		return false;
+	wtime->tm_mon  = eft->month - 1;
+
+	if (eft->year < 1900 || eft->year > 9999)
+		return false;
+	wtime->tm_year = eft->year - 1900;
+
+	/* day in the year [1-365]*/
+	wtime->tm_yday = compute_yday(eft);
+
+	/* day of the week [0-6], Sunday=0 */
+	wtime->tm_wday = compute_wday(eft, wtime->tm_yday);
+
+	switch (eft->daylight & EFI_ISDST) {
+	case EFI_ISDST:
+		wtime->tm_isdst = 1;
+		break;
+	case EFI_TIME_ADJUST_DAYLIGHT:
+		wtime->tm_isdst = 0;
+		break;
+	default:
+		wtime->tm_isdst = -1;
+	}
+
+	return true;
+}
+
+static int efi_read_time(struct device *dev, struct rtc_time *tm)
+{
+	efi_status_t status;
+	efi_time_t eft;
+	efi_time_cap_t cap;
+
+	status = efi.get_time(&eft, &cap);
+
+	if (status != EFI_SUCCESS) {
+		/* should never happen */
+		dev_err_once(dev, "can't read time\n");
+		return -EINVAL;
+	}
+
+	if (!convert_from_efi_time(&eft, tm))
+		return -EIO;
+
+	return 0;
+}
+
+static int efi_set_time(struct device *dev, struct rtc_time *tm)
+{
+	efi_status_t status;
+	efi_time_t eft;
+
+	convert_to_efi_time(tm, &eft);
+
+	status = efi.set_time(&eft);
+
+	return status == EFI_SUCCESS ? 0 : -EINVAL;
+}
+
+static int efi_procfs(struct device *dev, struct seq_file *seq)
+{
+	efi_time_t        eft;
+	efi_time_cap_t    cap;
+
+	memset(&eft, 0, sizeof(eft));
+	memset(&cap, 0, sizeof(cap));
+
+	efi.get_time(&eft, &cap);
+
+	seq_printf(seq,
+		   "Time\t\t: %u:%u:%u.%09u\n"
+		   "Date\t\t: %u-%u-%u\n"
+		   "Daylight\t: %u\n",
+		   eft.hour, eft.minute, eft.second, eft.nanosecond,
+		   eft.year, eft.month, eft.day,
+		   eft.daylight);
+
+	if (eft.timezone == EFI_UNSPECIFIED_TIMEZONE)
+		seq_puts(seq, "Timezone\t: unspecified\n");
+	else
+		/* XXX fixme: convert to string? */
+		seq_printf(seq, "Timezone\t: %u\n", eft.timezone);
+
+	/*
+	 * now prints the capabilities
+	 */
+	seq_printf(seq,
+		   "Resolution\t: %u\n"
+		   "Accuracy\t: %u\n"
+		   "SetstoZero\t: %u\n",
+		   cap.resolution, cap.accuracy, cap.sets_to_zero);
+
+	return 0;
+}
+
+static const struct rtc_class_ops efi_rtc_ops = {
+	.read_time	= efi_read_time,
+	.set_time	= efi_set_time,
+	.proc		= efi_procfs,
+};
+
+static int __init efi_rtc_probe(struct platform_device *dev)
+{
+	struct rtc_device *rtc;
+	efi_time_t eft;
+	efi_time_cap_t cap;
+
+	/* First check if the RTC is usable */
+	if (efi.get_time(&eft, &cap) != EFI_SUCCESS)
+		return -ENODEV;
+
+	rtc = devm_rtc_allocate_device(&dev->dev);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	platform_set_drvdata(dev, rtc);
+
+	rtc->ops = &efi_rtc_ops;
+	clear_bit(RTC_FEATURE_ALARM, rtc->features);
+
+	device_init_wakeup(&dev->dev, true);
+
+	return devm_rtc_register_device(rtc);
+}
+
+static struct platform_driver efi_rtc_driver = {
+	.driver = {
+		.name = "rtc-efi",
+	},
+};
+
+module_platform_driver_probe(efi_rtc_driver, efi_rtc_probe);
+
+MODULE_AUTHOR("dann frazier <dannf@dannf.org>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("EFI RTC driver");
+MODULE_ALIAS("platform:rtc-efi");