summaryrefslogtreecommitdiffstats
path: root/net/ipv6/ip6_output.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-10-02 13:38:27 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-10-02 13:38:27 -0700
commitaecdc33e111b2c447b622e287c6003726daa1426 (patch)
tree3e7657eae4b785e1a1fb5dfb225dbae0b2f0cfc6 /net/ipv6/ip6_output.c
parenta20acf99f75e49271381d65db097c9763060a1e8 (diff)
parenta3a6cab5ea10cca64d036851fe0d932448f2fe4f (diff)
downloadop-kernel-dev-aecdc33e111b2c447b622e287c6003726daa1426.zip
op-kernel-dev-aecdc33e111b2c447b622e287c6003726daa1426.tar.gz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking changes from David Miller: 1) GRE now works over ipv6, from Dmitry Kozlov. 2) Make SCTP more network namespace aware, from Eric Biederman. 3) TEAM driver now works with non-ethernet devices, from Jiri Pirko. 4) Make openvswitch network namespace aware, from Pravin B Shelar. 5) IPV6 NAT implementation, from Patrick McHardy. 6) Server side support for TCP Fast Open, from Jerry Chu and others. 7) Packet BPF filter supports MOD and XOR, from Eric Dumazet and Daniel Borkmann. 8) Increate the loopback default MTU to 64K, from Eric Dumazet. 9) Use a per-task rather than per-socket page fragment allocator for outgoing networking traffic. This benefits processes that have very many mostly idle sockets, which is quite common. From Eric Dumazet. 10) Use up to 32K for page fragment allocations, with fallbacks to smaller sizes when higher order page allocations fail. Benefits are a) less segments for driver to process b) less calls to page allocator c) less waste of space. From Eric Dumazet. 11) Allow GRO to be used on GRE tunnels, from Eric Dumazet. 12) VXLAN device driver, one way to handle VLAN issues such as the limitation of 4096 VLAN IDs yet still have some level of isolation. From Stephen Hemminger. 13) As usual there is a large boatload of driver changes, with the scale perhaps tilted towards the wireless side this time around. Fix up various fairly trivial conflicts, mostly caused by the user namespace changes. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1012 commits) hyperv: Add buffer for extended info after the RNDIS response message. hyperv: Report actual status in receive completion packet hyperv: Remove extra allocated space for recv_pkt_list elements hyperv: Fix page buffer handling in rndis_filter_send_request() hyperv: Fix the missing return value in rndis_filter_set_packet_filter() hyperv: Fix the max_xfer_size in RNDIS initialization vxlan: put UDP socket in correct namespace vxlan: Depend on CONFIG_INET sfc: Fix the reported priorities of different filter types sfc: Remove EFX_FILTER_FLAG_RX_OVERRIDE_IP sfc: Fix loopback self-test with separate_tx_channels=1 sfc: Fix MCDI structure field lookup sfc: Add parentheses around use of bitfield macro arguments sfc: Fix null function pointer in efx_sriov_channel_type vxlan: virtual extensible lan igmp: export symbol ip_mc_leave_group netlink: add attributes to fdb interface tg3: unconditionally select HWMON support when tg3 is enabled. Revert "net: ti cpsw ethernet: allow reading phy interface mode from DT" gre: fix sparse warning ...
Diffstat (limited to 'net/ipv6/ip6_output.c')
-rw-r--r--net/ipv6/ip6_output.c85
1 files changed, 32 insertions, 53 deletions
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5b2d63e..aece3e7 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -123,16 +123,11 @@ static int ip6_finish_output2(struct sk_buff *skb)
skb->len);
}
- rcu_read_lock();
rt = (struct rt6_info *) dst;
neigh = rt->n;
- if (neigh) {
- int res = dst_neigh_output(dst, neigh, skb);
+ if (neigh)
+ return dst_neigh_output(dst, neigh, skb);
- rcu_read_unlock();
- return res;
- }
- rcu_read_unlock();
IP6_INC_STATS_BH(dev_net(dst->dev),
ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
@@ -493,7 +488,8 @@ int ip6_forward(struct sk_buff *skb)
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
- if (skb->len > mtu && !skb_is_gso(skb)) {
+ if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
+ (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -636,7 +632,9 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
/* We must not fragment if the socket is set to force MTU discovery
* or if the skb it not generated by a local socket.
*/
- if (unlikely(!skb->local_df && skb->len > mtu)) {
+ if (unlikely(!skb->local_df && skb->len > mtu) ||
+ (IP6CB(skb)->frag_max_size &&
+ IP6CB(skb)->frag_max_size > mtu)) {
if (skb->sk && dst_allfrag(skb_dst(skb)))
sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
@@ -980,7 +978,6 @@ static int ip6_dst_lookup_tail(struct sock *sk,
* dst entry and replace it instead with the
* dst entry of the nexthop router
*/
- rcu_read_lock();
rt = (struct rt6_info *) *dst;
n = rt->n;
if (n && !(n->nud_state & NUD_VALID)) {
@@ -988,7 +985,6 @@ static int ip6_dst_lookup_tail(struct sock *sk,
struct flowi6 fl_gw6;
int redirect;
- rcu_read_unlock();
ifp = ipv6_get_ifaddr(net, &fl6->saddr,
(*dst)->dev, 1);
@@ -1008,8 +1004,6 @@ static int ip6_dst_lookup_tail(struct sock *sk,
if ((err = (*dst)->error))
goto out_err_release;
}
- } else {
- rcu_read_unlock();
}
#endif
@@ -1285,8 +1279,6 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
if (dst_allfrag(rt->dst.path))
cork->flags |= IPCORK_ALLFRAG;
cork->length = 0;
- sk->sk_sndmsg_page = NULL;
- sk->sk_sndmsg_off = 0;
exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len;
length += exthdrlen;
transhdrlen += exthdrlen;
@@ -1510,48 +1502,31 @@ alloc_new_skb:
}
} else {
int i = skb_shinfo(skb)->nr_frags;
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
- struct page *page = sk->sk_sndmsg_page;
- int off = sk->sk_sndmsg_off;
- unsigned int left;
-
- if (page && (left = PAGE_SIZE - off) > 0) {
- if (copy >= left)
- copy = left;
- if (page != skb_frag_page(frag)) {
- if (i == MAX_SKB_FRAGS) {
- err = -EMSGSIZE;
- goto error;
- }
- skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
- skb_frag_ref(skb, i);
- frag = &skb_shinfo(skb)->frags[i];
- }
- } else if(i < MAX_SKB_FRAGS) {
- if (copy > PAGE_SIZE)
- copy = PAGE_SIZE;
- page = alloc_pages(sk->sk_allocation, 0);
- if (page == NULL) {
- err = -ENOMEM;
- goto error;
- }
- sk->sk_sndmsg_page = page;
- sk->sk_sndmsg_off = 0;
+ struct page_frag *pfrag = sk_page_frag(sk);
- skb_fill_page_desc(skb, i, page, 0, 0);
- frag = &skb_shinfo(skb)->frags[i];
- } else {
- err = -EMSGSIZE;
+ err = -ENOMEM;
+ if (!sk_page_frag_refill(sk, pfrag))
goto error;
+
+ if (!skb_can_coalesce(skb, i, pfrag->page,
+ pfrag->offset)) {
+ err = -EMSGSIZE;
+ if (i == MAX_SKB_FRAGS)
+ goto error;
+
+ __skb_fill_page_desc(skb, i, pfrag->page,
+ pfrag->offset, 0);
+ skb_shinfo(skb)->nr_frags = ++i;
+ get_page(pfrag->page);
}
+ copy = min_t(int, copy, pfrag->size - pfrag->offset);
if (getfrag(from,
- skb_frag_address(frag) + skb_frag_size(frag),
- offset, copy, skb->len, skb) < 0) {
- err = -EFAULT;
- goto error;
- }
- sk->sk_sndmsg_off += copy;
- skb_frag_size_add(frag, copy);
+ page_address(pfrag->page) + pfrag->offset,
+ offset, copy, skb->len, skb) < 0)
+ goto error_efault;
+
+ pfrag->offset += copy;
+ skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
@@ -1560,7 +1535,11 @@ alloc_new_skb:
offset += copy;
length -= copy;
}
+
return 0;
+
+error_efault:
+ err = -EFAULT;
error:
cork->length -= length;
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
OpenPOWER on IntegriCloud