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

Pull networking changes from David Miller:

 1) Get rid of the error prone NLA_PUT*() macros that used an embedded
    goto.

 2) Kill off the token-ring and MCA networking drivers, from Paul
    Gortmaker.

 3) Reduce high-order allocations made by datagram AF_UNIX sockets, from
    Eric Dumazet.

 4) Add PTP hardware clock support to IGB and IXGBE, from Richard
    Cochran and Jacob Keller.

 5) Allow users to query timestamping capabilities of a card via
    ethtool, from Richard Cochran.

 6) Add loadbalance mode to the teaming driver, from Jiri Pirko.  Part
    of this is that we can now have BPF filters not attached to sockets,
    and the loadbalancing function is calculated using one.

 7) Francois Romieu went through the network drivers removing gratuitous
    uses of netdev->base_addr, perhaps some day we can remove it
    completely but it's used for ISA probing still.

 8) Add a BPF JIT for sparc.  I know, who cares, right? :-)

 9) Move networking sysctl registry away from using the compatability
    mode interfaces in the sysctl code.  From Eric W Biederman.

10) Pavel Emelyanov added a way to save and restore TCP socket state via
    TCP_REPAIR, TCP_REPAIR_QUEUE, and TCP_QUEUE_SEQ socket options as
    well as a way to forcefully bind a socket to a port via the
    sk->sk_reuse value SK_FORCE_REUSE.  There is also a
    TCP_REPAIR_OPTIONS which allows to reinstante the TCP options
    enabled on the connection.

11) Several enhancements from Eric Dumazet that, in particular, can
    enhance splice performance on TCP sockets significantly.

     a) Reset the offset of the per-socket sendmsg page when we know
        we're the only use of the page in linear_to_page().

     b) Add facilities such that skb->data can be backed a page rather
        than SLAB kmalloc'd memory.  In particular devices which were
        receiving into linear RX buffers can now end up providing paged
        data.

    The big result is that code like splice and GRO do not have to copy
    any more.

12) Allow a pure sender to more gracefully handle ACK backlogs in TCP.
    What can happen at high rates is that the sender hasn't grown his
    receive buffer limits at all (he's not receiving data so really
    doesn't need to), but the non-data ACKs consume receive buffer
    space.

    sk_add_backlog() is too aggressive in dropping frames in this case,
    so relax it's requirements by using the receive buffer plus the send
    buffer limit as the backlog limit instead of just the former.

    Also from Eric Dumazet.

13) Add ipv6 support to L2TP, from Benjamin LaHaise, James Chapman, and
    Chris Elston.

14) Implement TCP early retransmit (RFC 5827), from Yuchung Cheng.
    Basically, we can start fast retransmit before hiting the dupack
    threshold under certain conditions.

15) New CODEL active queue management packet scheduler, from Eric
    Dumazet based upon initial work by Dave Taht.

    Basically, the big feature is that packets are dropped (or ECN bits
    are set) based upon how long packets live in the queue, rather than
    the queue length (which is what RED uses).

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1341 commits)
  drivers/net/stmmac: seq_file fix memory leak
  ipv6/exthdrs: strict Pad1 and PadN check
  USB: qmi_wwan: Add ZTE (Vodafone) K3520-Z
  USB: qmi_wwan: Add ZTE (Vodafone) K3765-Z
  USB: qmi_wwan: Make forced int 4 whitelist generic
  net/ipv4: replace simple_strtoul with kstrtoul
  net/ipv4/ipconfig: neaten __setup placement
  net: qmi_wwan: Add Vodafone/Huawei K5005 support
  net: cdc_ether: Add ZTE WWAN matches before generic Ethernet
  ipv6: use skb coalescing in reassembly
  ipv4: use skb coalescing in defragmentation
  net: introduce skb_try_coalesce()
  net:ipv6:fixed space issues relating to operators.
  net:ipv6:fixed a trailing white space issue.
  ipv6: disable GSO on sockets hitting dst_allfrag
  tg3: use netdev_alloc_frag() API
  net: napi_frags_skb() is static
  ppp: avoid false drop_monitor false positives
  ipv6: bool/const conversions phase2
  ipx: Remove spurious NULL checking in ipx_ioctl().
  ...

1 files changed, 30 insertions, 17 deletions

diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 9447bd69873a..4ff9af628e72 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -134,15 +134,16 @@ static unsigned int ip6_hashfn(struct inet_frag_queue *q)
         return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr, ip6_frags.rnd);
 }
 
-int ip6_frag_match(struct inet_frag_queue *q, void *a)
+bool ip6_frag_match(struct inet_frag_queue *q, void *a)
 {
         struct frag_queue *fq;
         struct ip6_create_arg *arg = a;
 
         fq = container_of(q, struct frag_queue, q);
-        return (fq->id == arg->id && fq->user == arg->user &&
-                        ipv6_addr_equal(&fq->saddr, arg->src) &&
-                        ipv6_addr_equal(&fq->daddr, arg->dst));
+        return  fq->id == arg->id &&
+                fq->user == arg->user &&
+                ipv6_addr_equal(&fq->saddr, arg->src) &&
+                ipv6_addr_equal(&fq->daddr, arg->dst);
 }
 EXPORT_SYMBOL(ip6_frag_match);
 
@@ -414,6 +415,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
         struct sk_buff *fp, *head = fq->q.fragments;
         int    payload_len;
         unsigned int nhoff;
+        int sum_truesize;
 
         fq_kill(fq);
 
@@ -433,7 +435,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
                 skb_morph(head, fq->q.fragments);
                 head->next = fq->q.fragments->next;
 
-                kfree_skb(fq->q.fragments);
+                consume_skb(fq->q.fragments);
                 fq->q.fragments = head;
         }
 
@@ -483,20 +485,33 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
         head->mac_header += sizeof(struct frag_hdr);
         head->network_header += sizeof(struct frag_hdr);
 
-        skb_shinfo(head)->frag_list = head->next;
         skb_reset_transport_header(head);
         skb_push(head, head->data - skb_network_header(head));
 
-        for (fp=head->next; fp; fp = fp->next) {
-                head->data_len += fp->len;
-                head->len += fp->len;
+        sum_truesize = head->truesize;
+        for (fp = head->next; fp;) {
+                bool headstolen;
+                int delta;
+                struct sk_buff *next = fp->next;
+
+                sum_truesize += fp->truesize;
                 if (head->ip_summed != fp->ip_summed)
                         head->ip_summed = CHECKSUM_NONE;
                 else if (head->ip_summed == CHECKSUM_COMPLETE)
                         head->csum = csum_add(head->csum, fp->csum);
-                head->truesize += fp->truesize;
+
+                if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
+                        kfree_skb_partial(fp, headstolen);
+                } else {
+                        if (!skb_shinfo(head)->frag_list)
+                                skb_shinfo(head)->frag_list = fp;
+                        head->data_len += fp->len;
+                        head->len += fp->len;
+                        head->truesize += fp->truesize;
+                }
+                fp = next;
         }
-        atomic_sub(head->truesize, &fq->q.net->mem);
+        atomic_sub(sum_truesize, &fq->q.net->mem);
 
         head->next = NULL;
         head->dev = dev;
@@ -518,12 +533,10 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
         return 1;
 
 out_oversize:
-        if (net_ratelimit())
-                printk(KERN_DEBUG "ip6_frag_reasm: payload len = %d\n", payload_len);
+        net_dbg_ratelimited("ip6_frag_reasm: payload len = %d\n", payload_len);
         goto out_fail;
 out_oom:
-        if (net_ratelimit())
-                printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
+        net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n");
 out_fail:
         rcu_read_lock();
         IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
@@ -646,7 +659,7 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
                 table[2].data = &net->ipv6.frags.timeout;
         }
 
-        hdr = register_net_sysctl_table(net, net_ipv6_ctl_path, table);
+        hdr = register_net_sysctl(net, "net/ipv6", table);
         if (hdr == NULL)
                 goto err_reg;
 
@@ -674,7 +687,7 @@ static struct ctl_table_header *ip6_ctl_header;
 
 static int ip6_frags_sysctl_register(void)
 {
-        ip6_ctl_header = register_net_sysctl_rotable(net_ipv6_ctl_path,
+        ip6_ctl_header = register_net_sysctl(&init_net, "net/ipv6",
                         ip6_frags_ctl_table);
         return ip6_ctl_header == NULL ? -ENOMEM : 0;
 }