sock: add MSG_ZEROCOPY

The kernel supports zerocopy sendmsg in virtio and tap. Expand the
infrastructure to support other socket types. Introduce a completion
notification channel over the socket error queue. Notifications are
returned with ee_origin SO_EE_ORIGIN_ZEROCOPY. ee_errno is 0 to avoid
blocking the send/recv path on receiving notifications.

Add reference counting, to support the skb split, merge, resize and
clone operations possible with SOCK_STREAM and other socket types.

The patch does not yet modify any datapaths.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 66 insertions, 0 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2f64e2bbb592..59cff7aa494e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -429,6 +429,7 @@ enum {
 	SKBTX_SCHED_TSTAMP = 1 << 6,
 };
 
+#define SKBTX_ZEROCOPY_FRAG	(SKBTX_DEV_ZEROCOPY | SKBTX_SHARED_FRAG)
 #define SKBTX_ANY_SW_TSTAMP	(SKBTX_SW_TSTAMP    | \
 				 SKBTX_SCHED_TSTAMP)
 #define SKBTX_ANY_TSTAMP	(SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP)
@@ -445,8 +446,28 @@ struct ubuf_info {
 	void (*callback)(struct ubuf_info *, bool zerocopy_success);
 	void *ctx;
 	unsigned long desc;
+	u16 zerocopy:1;
+	atomic_t refcnt;
 };
 
+#define skb_uarg(SKB)	((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg))
+
+struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size);
+
+static inline void sock_zerocopy_get(struct ubuf_info *uarg)
+{
+	atomic_inc(&uarg->refcnt);
+}
+
+void sock_zerocopy_put(struct ubuf_info *uarg);
+void sock_zerocopy_put_abort(struct ubuf_info *uarg);
+
+void sock_zerocopy_callback(struct ubuf_info *uarg, bool success);
+
+int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
+			     struct msghdr *msg, int len,
+			     struct ubuf_info *uarg);
+
 /* This data is invariant across clones and lives at
  * the end of the header data, ie. at skb->end.
  */
@@ -1214,6 +1235,45 @@ static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb)
 	return &skb_shinfo(skb)->hwtstamps;
 }
 
+static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb)
+{
+	bool is_zcopy = skb && skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY;
+
+	return is_zcopy ? skb_uarg(skb) : NULL;
+}
+
+static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg)
+{
+	if (skb && uarg && !skb_zcopy(skb)) {
+		sock_zerocopy_get(uarg);
+		skb_shinfo(skb)->destructor_arg = uarg;
+		skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG;
+	}
+}
+
+/* Release a reference on a zerocopy structure */
+static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy)
+{
+	struct ubuf_info *uarg = skb_zcopy(skb);
+
+	if (uarg) {
+		uarg->zerocopy = uarg->zerocopy && zerocopy;
+		sock_zerocopy_put(uarg);
+		skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG;
+	}
+}
+
+/* Abort a zerocopy operation and revert zckey on error in send syscall */
+static inline void skb_zcopy_abort(struct sk_buff *skb)
+{
+	struct ubuf_info *uarg = skb_zcopy(skb);
+
+	if (uarg) {
+		sock_zerocopy_put_abort(uarg);
+		skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG;
+	}
+}
+
 /**
  *	skb_queue_empty - check if a queue is empty
  *	@list: queue head
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 8b13db5163cc..8ad963cdc88c 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -287,6 +287,7 @@ struct ucred {
 #define MSG_BATCH	0x40000 /* sendmmsg(): more messages coming */
 #define MSG_EOF         MSG_FIN
 
+#define MSG_ZEROCOPY	0x4000000	/* Use user data in kernel path */
 #define MSG_FASTOPEN	0x20000000	/* Send data in TCP SYN */
 #define MSG_CMSG_CLOEXEC 0x40000000	/* Set close_on_exec for file
 					   descriptor received through
diff --git a/include/net/sock.h b/include/net/sock.h
index 0f778d3c4300..fe1a0bc25cd3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -294,6 +294,7 @@ struct sock_common {
   *	@sk_stamp: time stamp of last packet received
   *	@sk_tsflags: SO_TIMESTAMPING socket options
   *	@sk_tskey: counter to disambiguate concurrent tstamp requests
+  *	@sk_zckey: counter to order MSG_ZEROCOPY notifications
   *	@sk_socket: Identd and reporting IO signals
   *	@sk_user_data: RPC layer private data
   *	@sk_frag: cached page frag
@@ -462,6 +463,7 @@ struct sock {
 	u16			sk_tsflags;
 	u8			sk_shutdown;
 	u32			sk_tskey;
+	atomic_t		sk_zckey;
 	struct socket		*sk_socket;
 	void			*sk_user_data;
 #ifdef CONFIG_SECURITY
diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h
index 07bdce1f444a..78fdf52d6b2f 100644
--- a/include/uapi/linux/errqueue.h
+++ b/include/uapi/linux/errqueue.h
@@ -18,10 +18,13 @@ struct sock_extended_err {
 #define SO_EE_ORIGIN_ICMP	2
 #define SO_EE_ORIGIN_ICMP6	3
 #define SO_EE_ORIGIN_TXSTATUS	4
+#define SO_EE_ORIGIN_ZEROCOPY	5
 #define SO_EE_ORIGIN_TIMESTAMPING SO_EE_ORIGIN_TXSTATUS
 
 #define SO_EE_OFFENDER(ee)	((struct sockaddr*)((ee)+1))
 
+#define SO_EE_CODE_ZEROCOPY_COPIED	1
+
 /**
  *	struct scm_timestamping - timestamps exposed through cmsg
  *