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, 69 insertions, 0 deletions

diff --git a/mm/fail_page_alloc.c b/mm/fail_page_alloc.c
new file mode 100644
index 000000000..764709617
--- /dev/null
+++ b/mm/fail_page_alloc.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fault-inject.h>
+#include <linux/debugfs.h>
+#include <linux/error-injection.h>
+#include <linux/mm.h>
+
+static struct {
+	struct fault_attr attr;
+
+	bool ignore_gfp_highmem;
+	bool ignore_gfp_reclaim;
+	u32 min_order;
+} fail_page_alloc = {
+	.attr = FAULT_ATTR_INITIALIZER,
+	.ignore_gfp_reclaim = true,
+	.ignore_gfp_highmem = true,
+	.min_order = 1,
+};
+
+static int __init setup_fail_page_alloc(char *str)
+{
+	return setup_fault_attr(&fail_page_alloc.attr, str);
+}
+__setup("fail_page_alloc=", setup_fail_page_alloc);
+
+bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+{
+	int flags = 0;
+
+	if (order < fail_page_alloc.min_order)
+		return false;
+	if (gfp_mask & __GFP_NOFAIL)
+		return false;
+	if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
+		return false;
+	if (fail_page_alloc.ignore_gfp_reclaim &&
+			(gfp_mask & __GFP_DIRECT_RECLAIM))
+		return false;
+
+	/* See comment in __should_failslab() */
+	if (gfp_mask & __GFP_NOWARN)
+		flags |= FAULT_NOWARN;
+
+	return should_fail_ex(&fail_page_alloc.attr, 1 << order, flags);
+}
+ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+static int __init fail_page_alloc_debugfs(void)
+{
+	umode_t mode = S_IFREG | 0600;
+	struct dentry *dir;
+
+	dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
+					&fail_page_alloc.attr);
+
+	debugfs_create_bool("ignore-gfp-wait", mode, dir,
+			    &fail_page_alloc.ignore_gfp_reclaim);
+	debugfs_create_bool("ignore-gfp-highmem", mode, dir,
+			    &fail_page_alloc.ignore_gfp_highmem);
+	debugfs_create_u32("min-order", mode, dir, &fail_page_alloc.min_order);
+
+	return 0;
+}
+
+late_initcall(fail_page_alloc_debugfs);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */