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, 78 insertions, 0 deletions

diff --git a/drivers/firmware/efi/reboot.c b/drivers/firmware/efi/reboot.c
new file mode 100644
index 000000000..ceae84c19
--- /dev/null
+++ b/drivers/firmware/efi/reboot.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2014 Intel Corporation; author Matt Fleming
+ * Copyright (c) 2014 Red Hat, Inc., Mark Salter <msalter@redhat.com>
+ */
+#include <linux/efi.h>
+#include <linux/reboot.h>
+
+static struct sys_off_handler *efi_sys_off_handler;
+
+int efi_reboot_quirk_mode = -1;
+
+void efi_reboot(enum reboot_mode reboot_mode, const char *__unused)
+{
+	const char *str[] = { "cold", "warm", "shutdown", "platform" };
+	int efi_mode, cap_reset_mode;
+
+	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_RESET_SYSTEM))
+		return;
+
+	switch (reboot_mode) {
+	case REBOOT_WARM:
+	case REBOOT_SOFT:
+		efi_mode = EFI_RESET_WARM;
+		break;
+	default:
+		efi_mode = EFI_RESET_COLD;
+		break;
+	}
+
+	/*
+	 * If a quirk forced an EFI reset mode, always use that.
+	 */
+	if (efi_reboot_quirk_mode != -1)
+		efi_mode = efi_reboot_quirk_mode;
+
+	if (efi_capsule_pending(&cap_reset_mode)) {
+		if (efi_mode != cap_reset_mode)
+			printk(KERN_CRIT "efi: %s reset requested but pending "
+			       "capsule update requires %s reset... Performing "
+			       "%s reset.\n", str[efi_mode], str[cap_reset_mode],
+			       str[cap_reset_mode]);
+		efi_mode = cap_reset_mode;
+	}
+
+	efi.reset_system(efi_mode, EFI_SUCCESS, 0, NULL);
+}
+
+bool __weak efi_poweroff_required(void)
+{
+	return false;
+}
+
+static int efi_power_off(struct sys_off_data *data)
+{
+	efi.reset_system(EFI_RESET_SHUTDOWN, EFI_SUCCESS, 0, NULL);
+
+	return NOTIFY_DONE;
+}
+
+static int __init efi_shutdown_init(void)
+{
+	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_RESET_SYSTEM))
+		return -ENODEV;
+
+	if (efi_poweroff_required()) {
+		/* SYS_OFF_PRIO_FIRMWARE + 1 so that it runs before acpi_power_off */
+		efi_sys_off_handler =
+			register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
+						 SYS_OFF_PRIO_FIRMWARE + 1,
+						 efi_power_off, NULL);
+		if (IS_ERR(efi_sys_off_handler))
+			return PTR_ERR(efi_sys_off_handler);
+	}
+
+	return 0;
+}
+late_initcall(efi_shutdown_init);