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, 51 insertions, 0 deletions

diff --git a/mm/debug_page_alloc.c b/mm/debug_page_alloc.c
new file mode 100644
index 000000000..fd2664c3c
--- /dev/null
+++ b/mm/debug_page_alloc.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/mm.h>
+#include <linux/page-isolation.h>
+
+unsigned int _debug_guardpage_minorder;
+
+bool _debug_pagealloc_enabled_early __read_mostly
+			= IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT);
+EXPORT_SYMBOL(_debug_pagealloc_enabled_early);
+DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
+EXPORT_SYMBOL(_debug_pagealloc_enabled);
+
+DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled);
+
+static int __init early_debug_pagealloc(char *buf)
+{
+	return kstrtobool(buf, &_debug_pagealloc_enabled_early);
+}
+early_param("debug_pagealloc", early_debug_pagealloc);
+
+static int __init debug_guardpage_minorder_setup(char *buf)
+{
+	unsigned int res;
+
+	if (!buf || kstrtouint(buf, 10, &res) < 0 || res > MAX_PAGE_ORDER / 2) {
+		pr_err("Bad debug_guardpage_minorder value: %s\n", buf ?: "(missing)");
+		return 0;
+	}
+	_debug_guardpage_minorder = res;
+	pr_info("Setting debug_guardpage_minorder to %u\n", res);
+	return 0;
+}
+early_param("debug_guardpage_minorder", debug_guardpage_minorder_setup);
+
+bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order)
+{
+	if (order >= debug_guardpage_minorder())
+		return false;
+
+	__SetPageGuard(page);
+	INIT_LIST_HEAD(&page->buddy_list);
+	set_page_private(page, order);
+
+	return true;
+}
+
+void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order)
+{
+	__ClearPageGuard(page);
+	set_page_private(page, 0);
+}