Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

1 files changed, 48 insertions, 121 deletions

diff --git a/net/socket.c b/net/socket.c
index 1dbff3e60437..5b0126234606 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -610,59 +610,27 @@ void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags)
 }
 EXPORT_SYMBOL(__sock_tx_timestamp);
 
-static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock,
-				       struct msghdr *msg, size_t size)
+static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg)
 {
-	return sock->ops->sendmsg(iocb, sock, msg, size);
-}
-
-static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock,
-				 struct msghdr *msg, size_t size)
-{
-	int err = security_socket_sendmsg(sock, msg, size);
-
-	return err ?: __sock_sendmsg_nosec(iocb, sock, msg, size);
-}
-
-static int do_sock_sendmsg(struct socket *sock, struct msghdr *msg,
-			   size_t size, bool nosec)
-{
-	struct kiocb iocb;
-	int ret;
-
-	init_sync_kiocb(&iocb, NULL);
-	ret = nosec ? __sock_sendmsg_nosec(&iocb, sock, msg, size) :
-		      __sock_sendmsg(&iocb, sock, msg, size);
+	int ret = sock->ops->sendmsg(sock, msg, msg_data_left(msg));
 	BUG_ON(ret == -EIOCBQUEUED);
 	return ret;
 }
 
-int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
+int sock_sendmsg(struct socket *sock, struct msghdr *msg)
 {
-	return do_sock_sendmsg(sock, msg, size, false);
-}
-EXPORT_SYMBOL(sock_sendmsg);
+	int err = security_socket_sendmsg(sock, msg,
+					  msg_data_left(msg));
 
-static int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg, size_t size)
-{
-	return do_sock_sendmsg(sock, msg, size, true);
+	return err ?: sock_sendmsg_nosec(sock, msg);
 }
+EXPORT_SYMBOL(sock_sendmsg);
 
 int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
 		   struct kvec *vec, size_t num, size_t size)
 {
-	mm_segment_t oldfs = get_fs();
-	int result;
-
-	set_fs(KERNEL_DS);
-	/*
-	 * the following is safe, since for compiler definitions of kvec and
-	 * iovec are identical, yielding the same in-core layout and alignment
-	 */
-	iov_iter_init(&msg->msg_iter, WRITE, (struct iovec *)vec, num, size);
-	result = sock_sendmsg(sock, msg, size);
-	set_fs(oldfs);
-	return result;
+	iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size);
+	return sock_sendmsg(sock, msg);
 }
 EXPORT_SYMBOL(kernel_sendmsg);
 
@@ -730,9 +698,9 @@ EXPORT_SYMBOL_GPL(__sock_recv_wifi_status);
 static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk,
 				   struct sk_buff *skb)
 {
-	if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount)
+	if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && SOCK_SKB_CB(skb)->dropcount)
 		put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL,
-			sizeof(__u32), &skb->dropcount);
+			sizeof(__u32), &SOCK_SKB_CB(skb)->dropcount);
 }
 
 void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
@@ -743,45 +711,21 @@ void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
 
-static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
-				       struct msghdr *msg, size_t size, int flags)
+static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
+				     size_t size, int flags)
 {
-	return sock->ops->recvmsg(iocb, sock, msg, size, flags);
+	return sock->ops->recvmsg(sock, msg, size, flags);
 }
 
-static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock,
-				 struct msghdr *msg, size_t size, int flags)
+int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		 int flags)
 {
 	int err = security_socket_recvmsg(sock, msg, size, flags);
 
-	return err ?: __sock_recvmsg_nosec(iocb, sock, msg, size, flags);
-}
-
-int sock_recvmsg(struct socket *sock, struct msghdr *msg,
-		 size_t size, int flags)
-{
-	struct kiocb iocb;
-	int ret;
-
-	init_sync_kiocb(&iocb, NULL);
-	ret = __sock_recvmsg(&iocb, sock, msg, size, flags);
-	BUG_ON(ret == -EIOCBQUEUED);
-	return ret;
+	return err ?: sock_recvmsg_nosec(sock, msg, size, flags);
 }
 EXPORT_SYMBOL(sock_recvmsg);
 
-static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
-			      size_t size, int flags)
-{
-	struct kiocb iocb;
-	int ret;
-
-	init_sync_kiocb(&iocb, NULL);
-	ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags);
-	BUG_ON(ret == -EIOCBQUEUED);
-	return ret;
-}
-
 /**
  * kernel_recvmsg - Receive a message from a socket (kernel space)
  * @sock:       The socket to receive the message from
@@ -803,12 +747,8 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
 	mm_segment_t oldfs = get_fs();
 	int result;
 
+	iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, vec, num, size);
 	set_fs(KERNEL_DS);
-	/*
-	 * the following is safe, since for compiler definitions of kvec and
-	 * iovec are identical, yielding the same in-core layout and alignment
-	 */
-	iov_iter_init(&msg->msg_iter, READ, (struct iovec *)vec, num, size);
 	result = sock_recvmsg(sock, msg, size, flags);
 	set_fs(oldfs);
 	return result;
@@ -846,7 +786,8 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
 	struct socket *sock = file->private_data;
-	struct msghdr msg = {.msg_iter = *to};
+	struct msghdr msg = {.msg_iter = *to,
+			     .msg_iocb = iocb};
 	ssize_t res;
 
 	if (file->f_flags & O_NONBLOCK)
@@ -858,8 +799,7 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	if (!iov_iter_count(to))	/* Match SYS5 behaviour */
 		return 0;
 
-	res = __sock_recvmsg(iocb, sock, &msg,
-			     iov_iter_count(to), msg.msg_flags);
+	res = sock_recvmsg(sock, &msg, iov_iter_count(to), msg.msg_flags);
 	*to = msg.msg_iter;
 	return res;
 }
@@ -868,7 +808,8 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct socket *sock = file->private_data;
-	struct msghdr msg = {.msg_iter = *from};
+	struct msghdr msg = {.msg_iter = *from,
+			     .msg_iocb = iocb};
 	ssize_t res;
 
 	if (iocb->ki_pos != 0)
@@ -880,7 +821,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (sock->type == SOCK_SEQPACKET)
 		msg.msg_flags |= MSG_EOR;
 
-	res = __sock_sendmsg(iocb, sock, &msg, iov_iter_count(from));
+	res = sock_sendmsg(sock, &msg);
 	*from = msg.msg_iter;
 	return res;
 }
@@ -1697,18 +1638,14 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
 	struct iovec iov;
 	int fput_needed;
 
-	if (len > INT_MAX)
-		len = INT_MAX;
-	if (unlikely(!access_ok(VERIFY_READ, buff, len)))
-		return -EFAULT;
+	err = import_single_range(WRITE, buff, len, &iov, &msg.msg_iter);
+	if (unlikely(err))
+		return err;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
 		goto out;
 
-	iov.iov_base = buff;
-	iov.iov_len = len;
 	msg.msg_name = NULL;
-	iov_iter_init(&msg.msg_iter, WRITE, &iov, 1, len);
 	msg.msg_control = NULL;
 	msg.msg_controllen = 0;
 	msg.msg_namelen = 0;
@@ -1722,7 +1659,7 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	msg.msg_flags = flags;
-	err = sock_sendmsg(sock, &msg, len);
+	err = sock_sendmsg(sock, &msg);
 
 out_put:
 	fput_light(sock->file, fput_needed);
@@ -1757,26 +1694,22 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
 	int err, err2;
 	int fput_needed;
 
-	if (size > INT_MAX)
-		size = INT_MAX;
-	if (unlikely(!access_ok(VERIFY_WRITE, ubuf, size)))
-		return -EFAULT;
+	err = import_single_range(READ, ubuf, size, &iov, &msg.msg_iter);
+	if (unlikely(err))
+		return err;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
 		goto out;
 
 	msg.msg_control = NULL;
 	msg.msg_controllen = 0;
-	iov.iov_len = size;
-	iov.iov_base = ubuf;
-	iov_iter_init(&msg.msg_iter, READ, &iov, 1, size);
 	/* Save some cycles and don't copy the address if not needed */
 	msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
 	/* We assume all kernel code knows the size of sockaddr_storage */
 	msg.msg_namelen = 0;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
-	err = sock_recvmsg(sock, &msg, size, flags);
+	err = sock_recvmsg(sock, &msg, iov_iter_count(&msg.msg_iter), flags);
 
 	if (err >= 0 && addr != NULL) {
 		err2 = move_addr_to_user(&address,
@@ -1896,10 +1829,10 @@ struct used_address {
 	unsigned int name_len;
 };
 
-static ssize_t copy_msghdr_from_user(struct msghdr *kmsg,
-				     struct user_msghdr __user *umsg,
-				     struct sockaddr __user **save_addr,
-				     struct iovec **iov)
+static int copy_msghdr_from_user(struct msghdr *kmsg,
+				 struct user_msghdr __user *umsg,
+				 struct sockaddr __user **save_addr,
+				 struct iovec **iov)
 {
 	struct sockaddr __user *uaddr;
 	struct iovec __user *uiov;
@@ -1943,13 +1876,10 @@ static ssize_t copy_msghdr_from_user(struct msghdr *kmsg,
 	if (nr_segs > UIO_MAXIOV)
 		return -EMSGSIZE;
 
-	err = rw_copy_check_uvector(save_addr ? READ : WRITE,
-				    uiov, nr_segs,
-				    UIO_FASTIOV, *iov, iov);
-	if (err >= 0)
-		iov_iter_init(&kmsg->msg_iter, save_addr ? READ : WRITE,
-			      *iov, nr_segs, err);
-	return err;
+	kmsg->msg_iocb = NULL;
+
+	return import_iovec(save_addr ? READ : WRITE, uiov, nr_segs,
+			    UIO_FASTIOV, iov, &kmsg->msg_iter);
 }
 
 static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
@@ -1964,7 +1894,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 	    __attribute__ ((aligned(sizeof(__kernel_size_t))));
 	/* 20 is size of ipv6_pktinfo */
 	unsigned char *ctl_buf = ctl;
-	int ctl_len, total_len;
+	int ctl_len;
 	ssize_t err;
 
 	msg_sys->msg_name = &address;
@@ -1974,8 +1904,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 	else
 		err = copy_msghdr_from_user(msg_sys, msg, NULL, &iov);
 	if (err < 0)
-		goto out_freeiov;
-	total_len = err;
+		return err;
 
 	err = -ENOBUFS;
 
@@ -2022,10 +1951,10 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 	    used_address->name_len == msg_sys->msg_namelen &&
 	    !memcmp(&used_address->name, msg_sys->msg_name,
 		    used_address->name_len)) {
-		err = sock_sendmsg_nosec(sock, msg_sys, total_len);
+		err = sock_sendmsg_nosec(sock, msg_sys);
 		goto out_freectl;
 	}
-	err = sock_sendmsg(sock, msg_sys, total_len);
+	err = sock_sendmsg(sock, msg_sys);
 	/*
 	 * If this is sendmmsg() and sending to current destination address was
 	 * successful, remember it.
@@ -2041,8 +1970,7 @@ out_freectl:
 	if (ctl_buf != ctl)
 		sock_kfree_s(sock->sk, ctl_buf, ctl_len);
 out_freeiov:
-	if (iov != iovstack)
-		kfree(iov);
+	kfree(iov);
 	return err;
 }
 
@@ -2167,8 +2095,8 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
 	else
 		err = copy_msghdr_from_user(msg_sys, msg, &uaddr, &iov);
 	if (err < 0)
-		goto out_freeiov;
-	total_len = err;
+		return err;
+	total_len = iov_iter_count(&msg_sys->msg_iter);
 
 	cmsg_ptr = (unsigned long)msg_sys->msg_control;
 	msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
@@ -2206,8 +2134,7 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
 	err = len;
 
 out_freeiov:
-	if (iov != iovstack)
-		kfree(iov);
+	kfree(iov);
 	return err;
 }