Merge branch 'for-uring-ubufops' into HEAD

Pavel Begunkov says:

====================
implement io_uring notification (ubuf_info) stacking (net part)

To have per request buffer notifications each zerocopy io_uring send
request allocates a new ubuf_info. However, as an skb can carry only
one uarg, it may force the stack to create many small skbs hurting
performance in many ways.

The patchset implements notification, i.e. an io_uring's ubuf_info
extension, stacking. It attempts to link ubuf_info's into a list,
allowing to have multiple of them per skb.

liburing/examples/send-zerocopy shows up 6 times performance improvement
for TCP with 4KB bytes per send, and levels it with MSG_ZEROCOPY. Without
the patchset it requires much larger sends to utilise all potential.

bytes  | before | after (Kqps)
1200   | 195    | 1023
4000   | 193    | 1386
8000   | 154    | 1058
====================

Link: https://lore.kernel.org/all/cover.1713369317.git.asml.silence@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 13 insertions, 8 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4072a7ee3859..f76825e5b92a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -527,6 +527,13 @@ enum {
 #define SKBFL_ALL_ZEROCOPY	(SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \
 				 SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS)
 
+struct ubuf_info_ops {
+	void (*complete)(struct sk_buff *, struct ubuf_info *,
+			 bool zerocopy_success);
+	/* has to be compatible with skb_zcopy_set() */
+	int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg);
+};
+
 /*
  * The callback notifies userspace to release buffers when skb DMA is done in
  * lower device, the skb last reference should be 0 when calling this.
@@ -536,8 +543,7 @@ enum {
  * The desc field is used to track userspace buffer index.
  */
 struct ubuf_info {
-	void (*callback)(struct sk_buff *, struct ubuf_info *,
-			 bool zerocopy_success);
+	const struct ubuf_info_ops *ops;
 	refcount_t refcnt;
 	u8 flags;
 };
@@ -1671,14 +1677,13 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
 }
 #endif
 
+extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops;
+
 struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
 				       struct ubuf_info *uarg);
 
 void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
 
-void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg,
-			   bool success);
-
 int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 			    struct sk_buff *skb, struct iov_iter *from,
 			    size_t length);
@@ -1766,13 +1771,13 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb)
 static inline void net_zcopy_put(struct ubuf_info *uarg)
 {
 	if (uarg)
-		uarg->callback(NULL, uarg, true);
+		uarg->ops->complete(NULL, uarg, true);
 }
 
 static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref)
 {
 	if (uarg) {
-		if (uarg->callback == msg_zerocopy_callback)
+		if (uarg->ops == &msg_zerocopy_ubuf_ops)
 			msg_zerocopy_put_abort(uarg, have_uref);
 		else if (have_uref)
 			net_zcopy_put(uarg);
@@ -1786,7 +1791,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success)
 
 	if (uarg) {
 		if (!skb_zcopy_is_nouarg(skb))
-			uarg->callback(skb, uarg, zerocopy_success);
+			uarg->ops->complete(skb, uarg, zerocopy_success);
 
 		skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY;
 	}