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

Pull networking updates from David Miller:
 "Here is a pile of bug fixes that accumulated while I was in Europe"

 1) In fixing kernel leaks to userspace during copying of socket
    addresses, we broke a case that used to work, namely the user
    providing a buffer larger than the in-kernel generic socket address
    structure.  This broke Ruby amongst other things.  Fix from Dan
    Carpenter.

 2) Fix regression added by byte queue limit support in 8139cp driver,
    from Yang Yingliang.

 3) The addition of MSG_SENDPAGE_NOTLAST buggered up a few sendpage
    implementations, they should just treat it the same as MSG_MORE.
    Fix from Richard Weinberger and Shawn Landden.

 4) Handle icmpv4 errors received on ipv6 SIT tunnels correctly, from
    Oussama Ghorbel.  In particular we should send an ICMPv6 unreachable
    in such situations.

 5) Fix some regressions in the recent genetlink fixes, in particular
    get the pmcraid driver to use the new safer interfaces correctly.
    From Johannes Berg.

 6) macvtap was converted to use a per-cpu set of statistics, but some
    code was still bumping tx_dropped elsewhere.  From Jason Wang.

 7) Fix build failure of xen-netback due to missing include on some
    architectures, from Andy Whitecroft.

 8) macvtap double counts received packets in statistics, fix from Vlad
    Yasevich.

 9) Fix various cases of using *_STATS_BH() when *_STATS() is more
    appropriate.  From Eric Dumazet and Hannes Frederic Sowa.

10) Pktgen ipsec mode doesn't update the ipv4 header length and checksum
    properly after encapsulation.  Fix from Fan Du.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (61 commits)
  net/mlx4_en: Remove selftest TX queues empty condition
  {pktgen, xfrm} Update IPv4 header total len and checksum after tranformation
  virtio_net: make all RX paths handle erors consistently
  virtio_net: fix error handling for mergeable buffers
  virtio_net: Fixed a trivial typo (fitler --> filter)
  netem: fix gemodel loss generator
  netem: fix loss 4 state model
  netem: missing break in ge loss generator
  net/hsr: Support iproute print_opt ('ip -details ...')
  net/hsr: Very small fix of comment style.
  MAINTAINERS: Added net/hsr/ maintainer
  ipv6: fix possible seqlock deadlock in ip6_finish_output2
  ixgbe: Make ixgbe_identify_qsfp_module_generic static
  ixgbe: turn NETIF_F_HW_L2FW_DOFFLOAD off by default
  ixgbe: ixgbe_fwd_ring_down needs to be static
  e1000: fix possible reset_task running after adapter down
  e1000: fix lockdep warning in e1000_reset_task
  e1000: prevent oops when adapter is being closed and reset simultaneously
  igb: Fixed Wake On LAN support
  inet: fix possible seqlock deadlocks
  ...

1 files changed, 25 insertions, 7 deletions

diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 68f98595819..a6090051c5d 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -21,6 +21,7 @@
 #include <net/netlink.h>
 #include <net/sch_generic.h>
 #include <net/pkt_sched.h>
+#include <net/tcp.h>
 
 
 /*	Simple Token Bucket Filter.
@@ -117,6 +118,22 @@ struct tbf_sched_data {
 };
 
 
+/*
+ * Return length of individual segments of a gso packet,
+ * including all headers (MAC, IP, TCP/UDP)
+ */
+static unsigned int skb_gso_seglen(const struct sk_buff *skb)
+{
+	unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
+	const struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+	if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
+		hdr_len += tcp_hdrlen(skb);
+	else
+		hdr_len += sizeof(struct udphdr);
+	return hdr_len + shinfo->gso_size;
+}
+
 /* GSO packet is too big, segment it so that tbf can transmit
  * each segment in time
  */
@@ -136,12 +153,8 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	while (segs) {
 		nskb = segs->next;
 		segs->next = NULL;
-		if (likely(segs->len <= q->max_size)) {
-			qdisc_skb_cb(segs)->pkt_len = segs->len;
-			ret = qdisc_enqueue(segs, q->qdisc);
-		} else {
-			ret = qdisc_reshape_fail(skb, sch);
-		}
+		qdisc_skb_cb(segs)->pkt_len = segs->len;
+		ret = qdisc_enqueue(segs, q->qdisc);
 		if (ret != NET_XMIT_SUCCESS) {
 			if (net_xmit_drop_count(ret))
 				sch->qstats.drops++;
@@ -163,7 +176,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	int ret;
 
 	if (qdisc_pkt_len(skb) > q->max_size) {
-		if (skb_is_gso(skb))
+		if (skb_is_gso(skb) && skb_gso_seglen(skb) <= q->max_size)
 			return tbf_segment(skb, sch);
 		return qdisc_reshape_fail(skb, sch);
 	}
@@ -319,6 +332,11 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 	if (max_size < 0)
 		goto done;
 
+	if (max_size < psched_mtu(qdisc_dev(sch)))
+		pr_warn_ratelimited("sch_tbf: burst %u is lower than device %s mtu (%u) !\n",
+				    max_size, qdisc_dev(sch)->name,
+				    psched_mtu(qdisc_dev(sch)));
+
 	if (q->qdisc != &noop_qdisc) {
 		err = fifo_set_limit(q->qdisc, qopt->limit);
 		if (err)