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, 68 insertions, 0 deletions

diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c
new file mode 100644
index 000000000..ccdb1fc1e
--- /dev/null
+++ b/arch/mips/lib/delay.c
@@ -0,0 +1,68 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1994 by Waldorf Electronics
+ * Copyright (C) 1995 - 2000, 01, 03 by Ralf Baechle
+ * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
+ * Copyright (C) 2007, 2014 Maciej W. Rozycki
+ */
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/param.h>
+#include <linux/smp.h>
+#include <linux/stringify.h>
+
+#include <asm/asm.h>
+#include <asm/compiler.h>
+
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
+#define GCC_DADDI_IMM_ASM() "I"
+#else
+#define GCC_DADDI_IMM_ASM() "r"
+#endif
+
+#ifndef CONFIG_HAVE_PLAT_DELAY
+
+void __delay(unsigned long loops)
+{
+	__asm__ __volatile__ (
+	"	.set	noreorder				\n"
+	"	.align	3					\n"
+	"1:	bnez	%0, 1b					\n"
+	"	 " __stringify(LONG_SUBU) "	%0, %1		\n"
+	"	.set	reorder					\n"
+	: "=r" (loops)
+	: GCC_DADDI_IMM_ASM() (1), "0" (loops));
+}
+EXPORT_SYMBOL(__delay);
+
+/*
+ * Division by multiplication: you don't have to worry about
+ * loss of precision.
+ *
+ * Use only for very small delays ( < 1 msec).	Should probably use a
+ * lookup table, really, as the multiplications take much too long with
+ * short delays.  This is a "reasonable" implementation, though (and the
+ * first constant multiplications gets optimized away if the delay is
+ * a constant)
+ */
+
+void __udelay(unsigned long us)
+{
+	unsigned int lpj = raw_current_cpu_data.udelay_val;
+
+	__delay((us * 0x000010c7ull * HZ * lpj) >> 32);
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long ns)
+{
+	unsigned int lpj = raw_current_cpu_data.udelay_val;
+
+	__delay((ns * 0x00000005ull * HZ * lpj) >> 32);
+}
+EXPORT_SYMBOL(__ndelay);
+
+#endif