net: Allow custom iter handler in msghdr

Add support for custom iov_iter handling to msghdr. The idea is that
in-kernel subsystems want control over how an SG is split.
Signed-off-by: David Ahern <dsahern@kernel.org>
[pavel: move callback into msghdr]
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/skbuff.h

@@ -1776,13 +1776,14 @@ 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 sock *sk, struct sk_buff *skb,
-			    struct iov_iter *from, size_t length);
+int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
+			    struct sk_buff *skb, struct iov_iter *from,
+			    size_t length);
 
 static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb,
 					  struct msghdr *msg, int len)
 {
-	return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len);
+	return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len);
 }
 
 int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,

include/linux/socket.h

@@ -14,6 +14,8 @@ struct file;
 struct pid;
 struct cred;
 struct socket;
+struct sock;
+struct sk_buff;
 
 #define __sockaddr_check_size(size)	\
 	BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
@@ -70,6 +72,8 @@ struct msghdr {
 	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
 	struct kiocb	*msg_iocb;	/* ptr to iocb for async requests */
 	struct ubuf_info *msg_ubuf;
+	int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb,
+			    struct iov_iter *from, size_t length);
 };
 
 struct user_msghdr {

net/core/datagram.c

@@ -613,10 +613,16 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 }
 EXPORT_SYMBOL(skb_copy_datagram_from_iter);
 
-int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
-			    struct iov_iter *from, size_t length)
+int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
+			    struct sk_buff *skb, struct iov_iter *from,
+			    size_t length)
 {
-	int frag = skb_shinfo(skb)->nr_frags;
+	int frag;
+
+	if (msg && msg->sg_from_iter)
+		return msg->sg_from_iter(sk, skb, from, length);
+
+	frag = skb_shinfo(skb)->nr_frags;
 
 	while (length && iov_iter_count(from)) {
 		struct page *pages[MAX_SKB_FRAGS];
@@ -702,7 +708,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 	if (skb_copy_datagram_from_iter(skb, 0, from, copy))
 		return -EFAULT;
 
-	return __zerocopy_sg_from_iter(NULL, skb, from, ~0U);
+	return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U);
 }
 EXPORT_SYMBOL(zerocopy_sg_from_iter);
 

net/core/skbuff.c

@@ -1358,7 +1358,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 	if (orig_uarg && uarg != orig_uarg)
 		return -EEXIST;
 
-	err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len);
+	err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len);
 	if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) {
 		struct sock *save_sk = skb->sk;