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, 45 insertions, 0 deletions

diff --git a/mm/gup_test.h b/mm/gup_test.h
new file mode 100644
index 000000000..5b37b54e8
--- /dev/null
+++ b/mm/gup_test.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef __GUP_TEST_H
+#define __GUP_TEST_H
+
+#include <linux/types.h>
+
+#define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_test)
+#define PIN_FAST_BENCHMARK	_IOWR('g', 2, struct gup_test)
+#define PIN_LONGTERM_BENCHMARK	_IOWR('g', 3, struct gup_test)
+#define GUP_BASIC_TEST		_IOWR('g', 4, struct gup_test)
+#define PIN_BASIC_TEST		_IOWR('g', 5, struct gup_test)
+#define DUMP_USER_PAGES_TEST	_IOWR('g', 6, struct gup_test)
+#define PIN_LONGTERM_TEST_START	_IOW('g', 7, struct pin_longterm_test)
+#define PIN_LONGTERM_TEST_STOP	_IO('g', 8)
+#define PIN_LONGTERM_TEST_READ	_IOW('g', 9, __u64)
+
+#define GUP_TEST_MAX_PAGES_TO_DUMP		8
+
+#define GUP_TEST_FLAG_DUMP_PAGES_USE_PIN	0x1
+
+struct gup_test {
+	__u64 get_delta_usec;
+	__u64 put_delta_usec;
+	__u64 addr;
+	__u64 size;
+	__u32 nr_pages_per_call;
+	__u32 gup_flags;
+	__u32 test_flags;
+	/*
+	 * Each non-zero entry is the number of the page (1-based: first page is
+	 * page 1, so that zero entries mean "do nothing") from the .addr base.
+	 */
+	__u32 which_pages[GUP_TEST_MAX_PAGES_TO_DUMP];
+};
+
+#define PIN_LONGTERM_TEST_FLAG_USE_WRITE	1
+#define PIN_LONGTERM_TEST_FLAG_USE_FAST		2
+
+struct pin_longterm_test {
+	__u64 addr;
+	__u64 size;
+	__u32 flags;
+};
+
+#endif	/* __GUP_TEST_H */