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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 44 insertions, 7 deletions

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index b0d07b35909d..55d8ba92291d 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -251,20 +251,23 @@ bool tipc_msg_validate(struct sk_buff **_skb)
  * @pktmax: Max packet size that can be used
  * @list: Buffer or chain of buffers to be returned to caller
  *
+ * Note that the recursive call we are making here is safe, since it can
+ * logically go only one further level down.
+ *
  * Returns message data size or errno: -ENOMEM, -EFAULT
  */
-int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m,
-		   int offset, int dsz, int pktmax, struct sk_buff_head *list)
+int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset,
+		   int dsz, int pktmax, struct sk_buff_head *list)
 {
 	int mhsz = msg_hdr_sz(mhdr);
+	struct tipc_msg pkthdr;
 	int msz = mhsz + dsz;
-	int pktno = 1;
-	int pktsz;
 	int pktrem = pktmax;
-	int drem = dsz;
-	struct tipc_msg pkthdr;
 	struct sk_buff *skb;
+	int drem = dsz;
+	int pktno = 1;
 	char *pktpos;
+	int pktsz;
 	int rc;
 
 	msg_set_size(mhdr, msz);
@@ -272,8 +275,18 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m,
 	/* No fragmentation needed? */
 	if (likely(msz <= pktmax)) {
 		skb = tipc_buf_acquire(msz, GFP_KERNEL);
-		if (unlikely(!skb))
+
+		/* Fall back to smaller MTU if node local message */
+		if (unlikely(!skb)) {
+			if (pktmax != MAX_MSG_SIZE)
+				return -ENOMEM;
+			rc = tipc_msg_build(mhdr, m, offset, dsz, FB_MTU, list);
+			if (rc != dsz)
+				return rc;
+			if (tipc_msg_assemble(list))
+				return dsz;
 			return -ENOMEM;
+		}
 		skb_orphan(skb);
 		__skb_queue_tail(list, skb);
 		skb_copy_to_linear_data(skb, mhdr, mhsz);
@@ -589,6 +602,30 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err)
 	return true;
 }
 
+/* tipc_msg_assemble() - assemble chain of fragments into one message
+ */
+bool tipc_msg_assemble(struct sk_buff_head *list)
+{
+	struct sk_buff *skb, *tmp = NULL;
+
+	if (skb_queue_len(list) == 1)
+		return true;
+
+	while ((skb = __skb_dequeue(list))) {
+		skb->next = NULL;
+		if (tipc_buf_append(&tmp, &skb)) {
+			__skb_queue_tail(list, skb);
+			return true;
+		}
+		if (!tmp)
+			break;
+	}
+	__skb_queue_purge(list);
+	__skb_queue_head_init(list);
+	pr_warn("Failed do assemble buffer\n");
+	return false;
+}
+
 /* tipc_msg_reassemble() - clone a buffer chain of fragments and
  *                         reassemble the clones into one message
  */