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, 44 insertions, 0 deletions

diff --git a/arch/powerpc/sysdev/dcr-low.S b/arch/powerpc/sysdev/dcr-low.S
new file mode 100644
index 000000000..e8401b205
--- /dev/null
+++ b/arch/powerpc/sysdev/dcr-low.S
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * "Indirect" DCR access
+ *
+ * Copyright (c) 2004 Eugene Surovegin <ebs@ebshome.net>
+ */
+
+#include <linux/export.h>
+#include <asm/ppc_asm.h>
+#include <asm/processor.h>
+#include <asm/bug.h>
+
+#define DCR_ACCESS_PROLOG(table) \
+	cmplwi	cr0,r3,1024;	 \
+	rlwinm  r3,r3,4,18,27;   \
+	lis     r5,table@h;      \
+	ori     r5,r5,table@l;   \
+	add     r3,r3,r5;        \
+	bge-	1f;		 \
+	mtctr   r3;              \
+	bctr;			 \
+1:	trap;			 \
+	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0;	\
+	blr
+
+_GLOBAL(__mfdcr)
+	DCR_ACCESS_PROLOG(__mfdcr_table)
+EXPORT_SYMBOL(__mfdcr)
+
+_GLOBAL(__mtdcr)
+	DCR_ACCESS_PROLOG(__mtdcr_table)
+EXPORT_SYMBOL(__mtdcr)
+
+__mfdcr_table:
+	mfdcr  r3,0; blr
+__mtdcr_table:
+	mtdcr  0,r4; blr
+
+dcr     = 1
+        .rept   1023
+	mfdcr   r3,dcr; blr
+	mtdcr   dcr,r4; blr
+	dcr     = dcr + 1
+	.endr