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, 76 insertions, 0 deletions

diff --git a/mm/failslab.c b/mm/failslab.c
new file mode 100644
index 000000000..c3901b136
--- /dev/null
+++ b/mm/failslab.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fault-inject.h>
+#include <linux/error-injection.h>
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include "slab.h"
+
+static struct {
+	struct fault_attr attr;
+	bool ignore_gfp_reclaim;
+	bool cache_filter;
+} failslab = {
+	.attr = FAULT_ATTR_INITIALIZER,
+	.ignore_gfp_reclaim = true,
+	.cache_filter = false,
+};
+
+int should_failslab(struct kmem_cache *s, gfp_t gfpflags)
+{
+	int flags = 0;
+
+	/* No fault-injection for bootstrap cache */
+	if (unlikely(s == kmem_cache))
+		return 0;
+
+	if (gfpflags & __GFP_NOFAIL)
+		return 0;
+
+	if (failslab.ignore_gfp_reclaim &&
+			(gfpflags & __GFP_DIRECT_RECLAIM))
+		return 0;
+
+	if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB))
+		return 0;
+
+	/*
+	 * In some cases, it expects to specify __GFP_NOWARN
+	 * to avoid printing any information(not just a warning),
+	 * thus avoiding deadlocks. See commit 6b9dbedbe349 for
+	 * details.
+	 */
+	if (gfpflags & __GFP_NOWARN)
+		flags |= FAULT_NOWARN;
+
+	return should_fail_ex(&failslab.attr, s->object_size, flags) ? -ENOMEM : 0;
+}
+ALLOW_ERROR_INJECTION(should_failslab, ERRNO);
+
+static int __init setup_failslab(char *str)
+{
+	return setup_fault_attr(&failslab.attr, str);
+}
+__setup("failslab=", setup_failslab);
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+static int __init failslab_debugfs_init(void)
+{
+	struct dentry *dir;
+	umode_t mode = S_IFREG | 0600;
+
+	dir = fault_create_debugfs_attr("failslab", NULL, &failslab.attr);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	debugfs_create_bool("ignore-gfp-wait", mode, dir,
+			    &failslab.ignore_gfp_reclaim);
+	debugfs_create_bool("cache-filter", mode, dir,
+			    &failslab.cache_filter);
+
+	return 0;
+}
+
+late_initcall(failslab_debugfs_init);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */