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, 92 insertions, 0 deletions

diff --git a/drivers/firmware/efi/efibc.c b/drivers/firmware/efi/efibc.c
new file mode 100644
index 000000000..345a10aa7
--- /dev/null
+++ b/drivers/firmware/efi/efibc.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * efibc: control EFI bootloaders which obey LoaderEntryOneShot var
+ * Copyright (c) 2013-2016, Intel Corporation.
+ */
+
+#define pr_fmt(fmt) "efibc: " fmt
+
+#include <linux/efi.h>
+#include <linux/module.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
+#include <linux/ucs2_string.h>
+
+#define MAX_DATA_LEN	512
+
+static int efibc_set_variable(efi_char16_t *name, efi_char16_t *value,
+			      unsigned long len)
+{
+	efi_status_t status;
+
+	status = efi.set_variable(name, &LINUX_EFI_LOADER_ENTRY_GUID,
+				  EFI_VARIABLE_NON_VOLATILE
+				  | EFI_VARIABLE_BOOTSERVICE_ACCESS
+				  | EFI_VARIABLE_RUNTIME_ACCESS,
+				  len * sizeof(efi_char16_t), value);
+
+	if (status != EFI_SUCCESS) {
+		pr_err("failed to set EFI variable: 0x%lx\n", status);
+		return -EIO;
+	}
+	return 0;
+}
+
+static int efibc_reboot_notifier_call(struct notifier_block *notifier,
+				      unsigned long event, void *data)
+{
+	efi_char16_t *reason = event == SYS_RESTART ? L"reboot"
+						    : L"shutdown";
+	const u8 *str = data;
+	efi_char16_t *wdata;
+	unsigned long l;
+	int ret;
+
+	ret = efibc_set_variable(L"LoaderEntryRebootReason", reason,
+				 ucs2_strlen(reason));
+	if (ret || !data)
+		return NOTIFY_DONE;
+
+	wdata = kmalloc_objs(efi_char16_t, MAX_DATA_LEN);
+	if (!wdata)
+		return NOTIFY_DONE;
+
+	for (l = 0; l < MAX_DATA_LEN - 1 && str[l] != '\0'; l++)
+		wdata[l] = str[l];
+	wdata[l] = L'\0';
+
+	efibc_set_variable(L"LoaderEntryOneShot", wdata, l);
+
+	kfree(wdata);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block efibc_reboot_notifier = {
+	.notifier_call = efibc_reboot_notifier_call,
+};
+
+static int __init efibc_init(void)
+{
+	int ret;
+
+	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_SET_VARIABLE))
+		return -ENODEV;
+
+	ret = register_reboot_notifier(&efibc_reboot_notifier);
+	if (ret)
+		pr_err("unable to register reboot notifier\n");
+
+	return ret;
+}
+module_init(efibc_init);
+
+static void __exit efibc_exit(void)
+{
+	unregister_reboot_notifier(&efibc_reboot_notifier);
+}
+module_exit(efibc_exit);
+
+MODULE_AUTHOR("Jeremy Compostella <jeremy.compostella@intel.com>");
+MODULE_AUTHOR("Matt Gumbel <matthew.k.gumbel@intel.com");
+MODULE_DESCRIPTION("EFI Bootloader Control");
+MODULE_LICENSE("GPL v2");