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

Pull networking fixes from David Miller:

 1) Fix double-free in batman-adv, from Sven Eckelmann.

 2) Fix packet stats for fast-RX path, from Joannes Berg.

 3) Netfilter's ip_route_me_harder() doesn't handle request sockets
    properly, fix from Florian Westphal.

 4) Fix sendmsg deadlock in rxrpc, from David Howells.

 5) Add missing RCU locking to transport hashtable scan, from Xin Long.

 6) Fix potential packet loss in mlxsw driver, from Ido Schimmel.

 7) Fix race in NAPI handling between poll handlers and busy polling,
    from Eric Dumazet.

 8) TX path in vxlan and geneve need proper RCU locking, from Jakub
    Kicinski.

 9) SYN processing in DCCP and TCP need to disable BH, from Eric
    Dumazet.

10) Properly handle net_enable_timestamp() being invoked from IRQ
    context, also from Eric Dumazet.

11) Fix crash on device-tree systems in xgene driver, from Alban Bedel.

12) Do not call sk_free() on a locked socket, from Arnaldo Carvalho de
    Melo.

13) Fix use-after-free in netvsc driver, from Dexuan Cui.

14) Fix max MTU setting in bonding driver, from WANG Cong.

15) xen-netback hash table can be allocated from softirq context, so use
    GFP_ATOMIC. From Anoob Soman.

16) Fix MAC address change bug in bgmac driver, from Hari Vyas.

17) strparser needs to destroy strp_wq on module exit, from WANG Cong.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (69 commits)
  strparser: destroy workqueue on module exit
  sfc: fix IPID endianness in TSOv2
  sfc: avoid max() in array size
  rds: remove unnecessary returned value check
  rxrpc: Fix potential NULL-pointer exception
  nfp: correct DMA direction in XDP DMA sync
  nfp: don't tell FW about the reserved buffer space
  net: ethernet: bgmac: mac address change bug
  net: ethernet: bgmac: init sequence bug
  xen-netback: don't vfree() queues under spinlock
  xen-netback: keep a local pointer for vif in backend_disconnect()
  netfilter: nf_tables: don't call nfnetlink_set_err() if nfnetlink_send() fails
  netfilter: nft_set_rbtree: incorrect assumption on lower interval lookups
  netfilter: nf_conntrack_sip: fix wrong memory initialisation
  can: flexcan: fix typo in comment
  can: usb_8dev: Fix memory leak of priv->cmd_msg_buffer
  can: gs_usb: fix coding style
  can: gs_usb: Don't use stack memory for USB transfers
  ixgbe: Limit use of 2K buffers on architectures with 256B or larger cache lines
  ixgbe: update the rss key on h/w, when ethtool ask for it
  ...

1 files changed, 33 insertions, 6 deletions

diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 28274a3c9831..6491ca46a03f 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -489,6 +489,20 @@ try_again:
 
 	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0, 0, 0, 0);
 
+	/* We're going to drop the socket lock, so we need to lock the call
+	 * against interference by sendmsg.
+	 */
+	if (!mutex_trylock(&call->user_mutex)) {
+		ret = -EWOULDBLOCK;
+		if (flags & MSG_DONTWAIT)
+			goto error_requeue_call;
+		ret = -ERESTARTSYS;
+		if (mutex_lock_interruptible(&call->user_mutex) < 0)
+			goto error_requeue_call;
+	}
+
+	release_sock(&rx->sk);
+
 	if (test_bit(RXRPC_CALL_RELEASED, &call->flags))
 		BUG();
 
@@ -504,7 +518,7 @@ try_again:
 				       &call->user_call_ID);
 		}
 		if (ret < 0)
-			goto error;
+			goto error_unlock_call;
 	}
 
 	if (msg->msg_name) {
@@ -535,12 +549,12 @@ try_again:
 	}
 
 	if (ret < 0)
-		goto error;
+		goto error_unlock_call;
 
 	if (call->state == RXRPC_CALL_COMPLETE) {
 		ret = rxrpc_recvmsg_term(call, msg);
 		if (ret < 0)
-			goto error;
+			goto error_unlock_call;
 		if (!(flags & MSG_PEEK))
 			rxrpc_release_call(rx, call);
 		msg->msg_flags |= MSG_EOR;
@@ -553,8 +567,21 @@ try_again:
 		msg->msg_flags &= ~MSG_MORE;
 	ret = copied;
 
-error:
+error_unlock_call:
+	mutex_unlock(&call->user_mutex);
 	rxrpc_put_call(call, rxrpc_call_put);
+	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret);
+	return ret;
+
+error_requeue_call:
+	if (!(flags & MSG_PEEK)) {
+		write_lock_bh(&rx->recvmsg_lock);
+		list_add(&call->recvmsg_link, &rx->recvmsg_q);
+		write_unlock_bh(&rx->recvmsg_lock);
+		trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0, 0, 0, 0);
+	} else {
+		rxrpc_put_call(call, rxrpc_call_put);
+	}
 error_no_call:
 	release_sock(&rx->sk);
 	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret);
@@ -611,7 +638,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 	iov.iov_len = size - *_offset;
 	iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, size - *_offset);
 
-	lock_sock(sock->sk);
+	mutex_lock(&call->user_mutex);
 
 	switch (call->state) {
 	case RXRPC_CALL_CLIENT_RECV_REPLY:
@@ -650,7 +677,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 read_phase_complete:
 	ret = 1;
 out:
-	release_sock(sock->sk);
+	mutex_unlock(&call->user_mutex);
 	_leave(" = %d [%zu,%d]", ret, *_offset, *_abort);
 	return ret;