mbcache: add functions to delete entry if unused

[ Upstream commit 3dc96bba65 ]

Add function mb_cache_entry_delete_or_get() to delete mbcache entry if
it is unused and also add a function to wait for entry to become unused
- mb_cache_entry_wait_unused(). We do not share code between the two
deleting function as one of them will go away soon.

CC: stable@vger.kernel.org
Fixes: 82939d7999 ("ext4: convert to mbcache2")
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20220712105436.32204-2-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Stable-dep-of: a44e84a9b7 ("ext4: fix deadlock due to mbcache entry corruption")
Signed-off-by: Sasha Levin <sashal@kernel.org>

fs/mbcache.c

@@ -11,7 +11,7 @@
 /*
  * Mbcache is a simple key-value store. Keys need not be unique, however
  * key-value pairs are expected to be unique (we use this fact in
- * mb_cache_entry_delete()).
+ * mb_cache_entry_delete_or_get()).
  *
  * Ext2 and ext4 use this cache for deduplication of extended attribute blocks.
  * Ext4 also uses it for deduplication of xattr values stored in inodes.
@@ -125,6 +125,19 @@ void __mb_cache_entry_free(struct mb_cache_entry *entry)
 }
 EXPORT_SYMBOL(__mb_cache_entry_free);
 
+/*
+ * mb_cache_entry_wait_unused - wait to be the last user of the entry
+ *
+ * @entry - entry to work on
+ *
+ * Wait to be the last user of the entry.
+ */
+void mb_cache_entry_wait_unused(struct mb_cache_entry *entry)
+{
+	wait_var_event(&entry->e_refcnt, atomic_read(&entry->e_refcnt) <= 3);
+}
+EXPORT_SYMBOL(mb_cache_entry_wait_unused);
+
 static struct mb_cache_entry *__entry_find(struct mb_cache *cache,
 					   struct mb_cache_entry *entry,
 					   u32 key)
@@ -217,7 +230,7 @@ out:
 }
 EXPORT_SYMBOL(mb_cache_entry_get);
 
-/* mb_cache_entry_delete - remove a cache entry
+/* mb_cache_entry_delete - try to remove a cache entry
  * @cache - cache we work with
  * @key - key
  * @value - value
@@ -254,6 +267,55 @@ void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value)
 }
 EXPORT_SYMBOL(mb_cache_entry_delete);
 
+/* mb_cache_entry_delete_or_get - remove a cache entry if it has no users
+ * @cache - cache we work with
+ * @key - key
+ * @value - value
+ *
+ * Remove entry from cache @cache with key @key and value @value. The removal
+ * happens only if the entry is unused. The function returns NULL in case the
+ * entry was successfully removed or there's no entry in cache. Otherwise the
+ * function grabs reference of the entry that we failed to delete because it
+ * still has users and return it.
+ */
+struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache,
+						    u32 key, u64 value)
+{
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+	struct mb_cache_entry *entry;
+
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
+		if (entry->e_key == key && entry->e_value == value) {
+			if (atomic_read(&entry->e_refcnt) > 2) {
+				atomic_inc(&entry->e_refcnt);
+				hlist_bl_unlock(head);
+				return entry;
+			}
+			/* We keep hash list reference to keep entry alive */
+			hlist_bl_del_init(&entry->e_hash_list);
+			hlist_bl_unlock(head);
+			spin_lock(&cache->c_list_lock);
+			if (!list_empty(&entry->e_list)) {
+				list_del_init(&entry->e_list);
+				if (!WARN_ONCE(cache->c_entry_count == 0,
+		"mbcache: attempt to decrement c_entry_count past zero"))
+					cache->c_entry_count--;
+				atomic_dec(&entry->e_refcnt);
+			}
+			spin_unlock(&cache->c_list_lock);
+			mb_cache_entry_put(cache, entry);
+			return NULL;
+		}
+	}
+	hlist_bl_unlock(head);
+
+	return NULL;
+}
+EXPORT_SYMBOL(mb_cache_entry_delete_or_get);
+
 /* mb_cache_entry_touch - cache entry got used
  * @cache - cache the entry belongs to
  * @entry - entry that got used

include/linux/mbcache.h

@@ -30,15 +30,23 @@ void mb_cache_destroy(struct mb_cache *cache);
 int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key,
 			  u64 value, bool reusable);
 void __mb_cache_entry_free(struct mb_cache_entry *entry);
+void mb_cache_entry_wait_unused(struct mb_cache_entry *entry);
 static inline int mb_cache_entry_put(struct mb_cache *cache,
 				     struct mb_cache_entry *entry)
 {
-	if (!atomic_dec_and_test(&entry->e_refcnt))
+	unsigned int cnt = atomic_dec_return(&entry->e_refcnt);
+
+	if (cnt > 0) {
+		if (cnt <= 3)
+			wake_up_var(&entry->e_refcnt);
 		return 0;
+	}
 	__mb_cache_entry_free(entry);
 	return 1;
 }
 
+struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache,
+						    u32 key, u64 value);
 void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value);
 struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key,
 					  u64 value);