io_uring: Move from hlist to io_wq_work_node

Having cache entries linked using the hlist format brings no benefit, and
also requires an unnecessary extra pointer address per cache entry.

Use the internal io_wq_work_node single-linked list for the internal
alloc caches (async_msghdr and async_poll)

This is required to be able to use KASAN on cache entries, since we do
not need to touch unused (and poisoned) cache entries when adding more
entries to the list.
Suggested-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20230223164353.2839177-2-leitao@debian.orgSigned-off-by: Jens Axboe <axboe@kernel.dk>

include/linux/io_uring_types.h

@@ -188,7 +188,7 @@ struct io_ev_fd {
 };
 
 struct io_alloc_cache {
-	struct hlist_head	list;
+	struct io_wq_work_node	list;
 	unsigned int		nr_cached;
 };
 

io_uring/alloc_cache.h

@@ -7,7 +7,7 @@
 #define IO_ALLOC_CACHE_MAX	512
 
 struct io_cache_entry {
-	struct hlist_node	node;
+	struct io_wq_work_node node;
 };
 
 static inline bool io_alloc_cache_put(struct io_alloc_cache *cache,
@@ -15,7 +15,7 @@ static inline bool io_alloc_cache_put(struct io_alloc_cache *cache,
 {
 	if (cache->nr_cached < IO_ALLOC_CACHE_MAX) {
 		cache->nr_cached++;
-		hlist_add_head(&entry->node, &cache->list);
+		wq_stack_add_head(&entry->node, &cache->list);
 		return true;
 	}
 	return false;
@@ -23,12 +23,13 @@ static inline bool io_alloc_cache_put(struct io_alloc_cache *cache,
 
 static inline struct io_cache_entry *io_alloc_cache_get(struct io_alloc_cache *cache)
 {
-	if (!hlist_empty(&cache->list)) {
-		struct hlist_node *node = cache->list.first;
+	if (cache->list.next) {
+		struct io_cache_entry *entry;
 
-		hlist_del(node);
+		entry = container_of(cache->list.next, struct io_cache_entry, node);
+		cache->list.next = cache->list.next->next;
 		cache->nr_cached--;
-		return container_of(node, struct io_cache_entry, node);
+		return entry;
 	}
 
 	return NULL;
@@ -36,18 +37,19 @@ static inline struct io_cache_entry *io_alloc_cache_get(struct io_alloc_cache *c
 
 static inline void io_alloc_cache_init(struct io_alloc_cache *cache)
 {
-	INIT_HLIST_HEAD(&cache->list);
+	cache->list.next = NULL;
 	cache->nr_cached = 0;
 }
 
 static inline void io_alloc_cache_free(struct io_alloc_cache *cache,
 					void (*free)(struct io_cache_entry *))
 {
-	while (!hlist_empty(&cache->list)) {
-		struct hlist_node *node = cache->list.first;
+	while (1) {
+		struct io_cache_entry *entry = io_alloc_cache_get(cache);
 
-		hlist_del(node);
-		free(container_of(node, struct io_cache_entry, node));
+		if (!entry)
+			break;
+		free(entry);
 	}
 	cache->nr_cached = 0;
 }