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, 20 insertions, 0 deletions

diff --git a/Documentation/admin-guide/media/raspberrypi-pisp-be.dot b/Documentation/admin-guide/media/raspberrypi-pisp-be.dot
new file mode 100644
index 000000000..55671dc1d
--- /dev/null
+++ b/Documentation/admin-guide/media/raspberrypi-pisp-be.dot
@@ -0,0 +1,20 @@
+digraph board {
+	rankdir=TB
+	n00000001 [label="{{<port0> 0 | <port1> 1 | <port2> 2 | <port7> 7} | pispbe\n | {<port3> 3 | <port4> 4 | <port5> 5 | <port6> 6}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000001:port3 -> n0000001c [style=bold]
+	n00000001:port4 -> n00000022 [style=bold]
+	n00000001:port5 -> n00000028 [style=bold]
+	n00000001:port6 -> n0000002e [style=bold]
+	n0000000a [label="pispbe-input\n/dev/video0", shape=box, style=filled, fillcolor=yellow]
+	n0000000a -> n00000001:port0 [style=bold]
+	n00000010 [label="pispbe-tdn_input\n/dev/video1", shape=box, style=filled, fillcolor=yellow]
+	n00000010 -> n00000001:port1 [style=bold]
+	n00000016 [label="pispbe-stitch_input\n/dev/video2", shape=box, style=filled, fillcolor=yellow]
+	n00000016 -> n00000001:port2 [style=bold]
+	n0000001c [label="pispbe-output0\n/dev/video3", shape=box, style=filled, fillcolor=yellow]
+	n00000022 [label="pispbe-output1\n/dev/video4", shape=box, style=filled, fillcolor=yellow]
+	n00000028 [label="pispbe-tdn_output\n/dev/video5", shape=box, style=filled, fillcolor=yellow]
+	n0000002e [label="pispbe-stitch_output\n/dev/video6", shape=box, style=filled, fillcolor=yellow]
+	n00000034 [label="pispbe-config\n/dev/video7", shape=box, style=filled, fillcolor=yellow]
+	n00000034 -> n00000001:port7 [style=bold]
+}