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, 174 insertions, 0 deletions

diff --git a/drivers/md/dm-cache-policy.c b/drivers/md/dm-cache-policy.c
new file mode 100644
index 000000000..9330d5748
--- /dev/null
+++ b/drivers/md/dm-cache-policy.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Red Hat. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-cache-policy-internal.h"
+#include "dm.h"
+
+#include <linux/module.h>
+#include <linux/slab.h>
+
+/*----------------------------------------------------------------*/
+
+#define DM_MSG_PREFIX "cache-policy"
+
+static DEFINE_SPINLOCK(register_lock);
+static LIST_HEAD(register_list);
+
+static struct dm_cache_policy_type *__find_policy(const char *name)
+{
+	struct dm_cache_policy_type *t;
+
+	list_for_each_entry(t, &register_list, list)
+		if (!strcmp(t->name, name))
+			return t;
+
+	return NULL;
+}
+
+static struct dm_cache_policy_type *__get_policy_once(const char *name)
+{
+	struct dm_cache_policy_type *t = __find_policy(name);
+
+	if (t && !try_module_get(t->owner)) {
+		DMWARN("couldn't get module %s", name);
+		t = ERR_PTR(-EINVAL);
+	}
+
+	return t;
+}
+
+static struct dm_cache_policy_type *get_policy_once(const char *name)
+{
+	struct dm_cache_policy_type *t;
+
+	spin_lock(&register_lock);
+	t = __get_policy_once(name);
+	spin_unlock(&register_lock);
+
+	return t;
+}
+
+static struct dm_cache_policy_type *get_policy(const char *name)
+{
+	struct dm_cache_policy_type *t;
+
+	t = get_policy_once(name);
+	if (IS_ERR(t))
+		return NULL;
+
+	if (t)
+		return t;
+
+	request_module("dm-cache-%s", name);
+
+	t = get_policy_once(name);
+	if (IS_ERR(t))
+		return NULL;
+
+	return t;
+}
+
+static void put_policy(struct dm_cache_policy_type *t)
+{
+	module_put(t->owner);
+}
+
+int dm_cache_policy_register(struct dm_cache_policy_type *type)
+{
+	int r;
+
+	/* One size fits all for now */
+	if (type->hint_size != 0 && type->hint_size != 4) {
+		DMWARN("hint size must be 0 or 4 but %llu supplied.", (unsigned long long) type->hint_size);
+		return -EINVAL;
+	}
+
+	spin_lock(&register_lock);
+	if (__find_policy(type->name)) {
+		DMWARN("attempt to register policy under duplicate name %s", type->name);
+		r = -EINVAL;
+	} else {
+		list_add(&type->list, &register_list);
+		r = 0;
+	}
+	spin_unlock(&register_lock);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_register);
+
+void dm_cache_policy_unregister(struct dm_cache_policy_type *type)
+{
+	spin_lock(&register_lock);
+	list_del_init(&type->list);
+	spin_unlock(&register_lock);
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_unregister);
+
+struct dm_cache_policy *dm_cache_policy_create(const char *name,
+					       dm_cblock_t cache_size,
+					       sector_t origin_size,
+					       sector_t cache_block_size)
+{
+	struct dm_cache_policy *p = NULL;
+	struct dm_cache_policy_type *type;
+
+	type = get_policy(name);
+	if (!type) {
+		DMWARN("unknown policy type");
+		return ERR_PTR(-EINVAL);
+	}
+
+	p = type->create(cache_size, origin_size, cache_block_size);
+	if (!p) {
+		put_policy(type);
+		return ERR_PTR(-ENOMEM);
+	}
+	p->private = type;
+
+	return p;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_create);
+
+void dm_cache_policy_destroy(struct dm_cache_policy *p)
+{
+	struct dm_cache_policy_type *t = p->private;
+
+	p->destroy(p);
+	put_policy(t);
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_destroy);
+
+const char *dm_cache_policy_get_name(struct dm_cache_policy *p)
+{
+	struct dm_cache_policy_type *t = p->private;
+
+	/* if t->real is set then an alias was used (e.g. "default") */
+	if (t->real)
+		return t->real->name;
+
+	return t->name;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_get_name);
+
+const unsigned int *dm_cache_policy_get_version(struct dm_cache_policy *p)
+{
+	struct dm_cache_policy_type *t = p->private;
+
+	return t->version;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_get_version);
+
+size_t dm_cache_policy_get_hint_size(struct dm_cache_policy *p)
+{
+	struct dm_cache_policy_type *t = p->private;
+
+	return t->hint_size;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_get_hint_size);
+
+/*----------------------------------------------------------------*/