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, 67 insertions, 0 deletions

diff --git a/arch/arm/lib/delay-loop.S b/arch/arm/lib/delay-loop.S
new file mode 100644
index 000000000..33b08ca1c
--- /dev/null
+++ b/arch/arm/lib/delay-loop.S
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  linux/arch/arm/lib/delay.S
+ *
+ *  Copyright (C) 1995, 1996 Russell King
+ */
+#include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <asm/assembler.h>
+#include <asm/delay.h>
+
+#ifdef CONFIG_ARCH_RPC
+		.arch	armv4
+#endif
+
+		.text
+
+.LC0:		.word	loops_per_jiffy
+.LC1:		.word	UDELAY_MULT
+
+/*
+ * loops = r0 * HZ * loops_per_jiffy / 1000000
+ *
+ * r0  <= 2000
+ * HZ  <= 1000
+ */
+
+SYM_TYPED_FUNC_START(__loop_udelay)
+		ldr	r2, .LC1
+		mul	r0, r2, r0		@ r0 = delay_us * UDELAY_MULT
+		b	__loop_const_udelay
+SYM_FUNC_END(__loop_udelay)
+
+SYM_TYPED_FUNC_START(__loop_const_udelay)	@ 0 <= r0 <= 0xfffffaf0
+		ldr	r2, .LC0
+		ldr	r2, [r2]
+		umull	r1, r0, r2, r0		@ r0-r1 = r0 * loops_per_jiffy
+		adds	r1, r1, #0xffffffff	@ rounding up ...
+		adcs	r0, r0, r0		@ and right shift by 31
+		reteq	lr
+		b	__loop_delay
+SYM_FUNC_END(__loop_const_udelay)
+
+		.align 3
+
+@ Delay routine
+SYM_TYPED_FUNC_START(__loop_delay)
+		subs	r0, r0, #1
+#if 0
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+#endif
+		bhi	__loop_delay
+		ret	lr
+SYM_FUNC_END(__loop_delay)