io_uring: cache struct io_notif

kmalloc'ing struct io_notif is too expensive when done frequently, cache
them as many other resources in io_uring. Keep two list, the first one
is from where we're getting notifiers, it's protected by ->uring_lock.
The second is protected by ->completion_lock, to which we queue released
notifiers. Then we splice one list into another when needed.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/9dec18f7fcbab9f4bd40b96e5ae158b119945230.1657643355.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 50 insertions, 7 deletions

diff --git a/io_uring/notif.c b/io_uring/notif.c
index 6ee948af6a49..b257db2120b4 100644
--- a/io_uring/notif.c
+++ b/io_uring/notif.c
@@ -15,10 +15,12 @@ static void __io_notif_complete_tw(struct callback_head *cb)
 
 	io_cq_lock(ctx);
 	io_fill_cqe_aux(ctx, notif->tag, 0, notif->seq, true);
+
+	list_add(&notif->cache_node, &ctx->notif_list_locked);
+	ctx->notif_locked_nr++;
 	io_cq_unlock_post(ctx);
 
 	percpu_ref_put(&ctx->refs);
-	kfree(notif);
 }
 
 static inline void io_notif_complete(struct io_notif *notif)
@@ -45,21 +47,62 @@ static void io_uring_tx_zerocopy_callback(struct sk_buff *skb,
 	queue_work(system_unbound_wq, &notif->commit_work);
 }
 
+static void io_notif_splice_cached(struct io_ring_ctx *ctx)
+	__must_hold(&ctx->uring_lock)
+{
+	spin_lock(&ctx->completion_lock);
+	list_splice_init(&ctx->notif_list_locked, &ctx->notif_list);
+	ctx->notif_locked_nr = 0;
+	spin_unlock(&ctx->completion_lock);
+}
+
+void io_notif_cache_purge(struct io_ring_ctx *ctx)
+	__must_hold(&ctx->uring_lock)
+{
+	io_notif_splice_cached(ctx);
+
+	while (!list_empty(&ctx->notif_list)) {
+		struct io_notif *notif = list_first_entry(&ctx->notif_list,
+						struct io_notif, cache_node);
+
+		list_del(&notif->cache_node);
+		kfree(notif);
+	}
+}
+
+static inline bool io_notif_has_cached(struct io_ring_ctx *ctx)
+	__must_hold(&ctx->uring_lock)
+{
+	if (likely(!list_empty(&ctx->notif_list)))
+		return true;
+	if (data_race(READ_ONCE(ctx->notif_locked_nr) <= IO_NOTIF_SPLICE_BATCH))
+		return false;
+	io_notif_splice_cached(ctx);
+	return !list_empty(&ctx->notif_list);
+}
+
 struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx,
 				struct io_notif_slot *slot)
 	__must_hold(&ctx->uring_lock)
 {
 	struct io_notif *notif;
 
-	notif = kzalloc(sizeof(*notif), GFP_ATOMIC | __GFP_ACCOUNT);
-	if (!notif)
-		return NULL;
+	if (likely(io_notif_has_cached(ctx))) {
+		notif = list_first_entry(&ctx->notif_list,
+					 struct io_notif, cache_node);
+		list_del(&notif->cache_node);
+	} else {
+		notif = kzalloc(sizeof(*notif), GFP_ATOMIC | __GFP_ACCOUNT);
+		if (!notif)
+			return NULL;
+		/* pre-initialise some fields */
+		notif->ctx = ctx;
+		notif->uarg.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN;
+		notif->uarg.callback = io_uring_tx_zerocopy_callback;
+	}
 
 	notif->seq = slot->seq++;
 	notif->tag = slot->tag;
-	notif->ctx = ctx;
-	notif->uarg.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN;
-	notif->uarg.callback = io_uring_tx_zerocopy_callback;
 	/* master ref owned by io_notif_slot, will be dropped on flush */
 	refcount_set(&notif->uarg.refcnt, 1);
 	percpu_ref_get(&ctx->refs);