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, 137 insertions, 0 deletions

diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c
new file mode 100644
index 000000000..f7eb976b0
--- /dev/null
+++ b/arch/x86/boot/tty.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Very simple screen and serial I/O
+ */
+
+#include "boot.h"
+
+int early_serial_base;
+
+#define XMTRDY          0x20
+
+#define TXR             0       /*  Transmit register (WRITE) */
+#define LSR             5       /*  Line Status               */
+
+/*
+ * These functions are in .inittext so they can be used to signal
+ * error during initialization.
+ */
+
+static void __section(".inittext") serial_putchar(int ch)
+{
+	unsigned timeout = 0xffff;
+
+	while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout)
+		cpu_relax();
+
+	outb(ch, early_serial_base + TXR);
+}
+
+static void __section(".inittext") bios_putchar(int ch)
+{
+	struct biosregs ireg;
+
+	initregs(&ireg);
+	ireg.bx = 0x0007;
+	ireg.cx = 0x0001;
+	ireg.ah = 0x0e;
+	ireg.al = ch;
+	intcall(0x10, &ireg, NULL);
+}
+
+void __section(".inittext") putchar(int ch)
+{
+	if (ch == '\n')
+		putchar('\r');	/* \n -> \r\n */
+
+	bios_putchar(ch);
+
+	if (early_serial_base != 0)
+		serial_putchar(ch);
+}
+
+void __section(".inittext") puts(const char *str)
+{
+	while (*str)
+		putchar(*str++);
+}
+
+/*
+ * Read the CMOS clock through the BIOS, and return the
+ * seconds in BCD.
+ */
+
+static u8 gettime(void)
+{
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	ireg.ah = 0x02;
+	intcall(0x1a, &ireg, &oreg);
+
+	return oreg.dh;
+}
+
+/*
+ * Read from the keyboard
+ */
+int getchar(void)
+{
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	/* ireg.ah = 0x00; */
+	intcall(0x16, &ireg, &oreg);
+
+	return oreg.al;
+}
+
+static int kbd_pending(void)
+{
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	ireg.ah = 0x01;
+	intcall(0x16, &ireg, &oreg);
+
+	return !(oreg.eflags & X86_EFLAGS_ZF);
+}
+
+void kbd_flush(void)
+{
+	for (;;) {
+		if (!kbd_pending())
+			break;
+		getchar();
+	}
+}
+
+int getchar_timeout(void)
+{
+	int cnt = 30;
+	int t0, t1;
+
+	t0 = gettime();
+
+	while (cnt) {
+		if (kbd_pending())
+			return getchar();
+
+		t1 = gettime();
+		if (t0 != t1) {
+			cnt--;
+			t0 = t1;
+		}
+	}
+
+	return 0;		/* Timeout! */
+}
+