forked from Minki/linux
6d123b81ac
Dave observed number of machines hitting OOM on the UDP send path. The workload seems to be sending large UDP packets over loopback. Since loopback has MTU of 64k kernel will try to allocate an skb with up to 64k of head space. This has a good chance of failing under memory pressure. What's worse if the message length is <32k the allocation may trigger an OOM killer. This is entirely avoidable, we can use an skb with page frags. af_unix solves a similar problem by limiting the head length to SKB_MAX_ALLOC. This seems like a good and simple approach. It means that UDP messages > 16kB will now use fragments if underlying device supports SG, if extra allocator pressure causes regressions in real workloads we can switch to trying the large allocation first and falling back. v4: pre-calculate all the additions to alloclen so we can be sure it won't go over order-2 Reported-by: Dave Jones <dsj@fb.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
1747 lines
43 KiB
C
1747 lines
43 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* INET An implementation of the TCP/IP protocol suite for the LINUX
|
|
* operating system. INET is implemented using the BSD Socket
|
|
* interface as the means of communication with the user level.
|
|
*
|
|
* The Internet Protocol (IP) output module.
|
|
*
|
|
* Authors: Ross Biro
|
|
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
|
|
* Donald Becker, <becker@super.org>
|
|
* Alan Cox, <Alan.Cox@linux.org>
|
|
* Richard Underwood
|
|
* Stefan Becker, <stefanb@yello.ping.de>
|
|
* Jorge Cwik, <jorge@laser.satlink.net>
|
|
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
|
|
* Hirokazu Takahashi, <taka@valinux.co.jp>
|
|
*
|
|
* See ip_input.c for original log
|
|
*
|
|
* Fixes:
|
|
* Alan Cox : Missing nonblock feature in ip_build_xmit.
|
|
* Mike Kilburn : htons() missing in ip_build_xmit.
|
|
* Bradford Johnson: Fix faulty handling of some frames when
|
|
* no route is found.
|
|
* Alexander Demenshin: Missing sk/skb free in ip_queue_xmit
|
|
* (in case if packet not accepted by
|
|
* output firewall rules)
|
|
* Mike McLagan : Routing by source
|
|
* Alexey Kuznetsov: use new route cache
|
|
* Andi Kleen: Fix broken PMTU recovery and remove
|
|
* some redundant tests.
|
|
* Vitaly E. Lavrov : Transparent proxy revived after year coma.
|
|
* Andi Kleen : Replace ip_reply with ip_send_reply.
|
|
* Andi Kleen : Split fast and slow ip_build_xmit path
|
|
* for decreased register pressure on x86
|
|
* and more readability.
|
|
* Marc Boucher : When call_out_firewall returns FW_QUEUE,
|
|
* silently drop skb instead of failing with -EPERM.
|
|
* Detlev Wengorz : Copy protocol for fragments.
|
|
* Hirokazu Takahashi: HW checksumming for outgoing UDP
|
|
* datagrams.
|
|
* Hirokazu Takahashi: sendfile() on UDP works now.
|
|
*/
|
|
|
|
#include <linux/uaccess.h>
|
|
#include <linux/module.h>
|
|
#include <linux/types.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/string.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/socket.h>
|
|
#include <linux/sockios.h>
|
|
#include <linux/in.h>
|
|
#include <linux/inet.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/etherdevice.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/stat.h>
|
|
#include <linux/init.h>
|
|
|
|
#include <net/snmp.h>
|
|
#include <net/ip.h>
|
|
#include <net/protocol.h>
|
|
#include <net/route.h>
|
|
#include <net/xfrm.h>
|
|
#include <linux/skbuff.h>
|
|
#include <net/sock.h>
|
|
#include <net/arp.h>
|
|
#include <net/icmp.h>
|
|
#include <net/checksum.h>
|
|
#include <net/inetpeer.h>
|
|
#include <net/inet_ecn.h>
|
|
#include <net/lwtunnel.h>
|
|
#include <linux/bpf-cgroup.h>
|
|
#include <linux/igmp.h>
|
|
#include <linux/netfilter_ipv4.h>
|
|
#include <linux/netfilter_bridge.h>
|
|
#include <linux/netlink.h>
|
|
#include <linux/tcp.h>
|
|
|
|
static int
|
|
ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
|
|
unsigned int mtu,
|
|
int (*output)(struct net *, struct sock *, struct sk_buff *));
|
|
|
|
/* Generate a checksum for an outgoing IP datagram. */
|
|
void ip_send_check(struct iphdr *iph)
|
|
{
|
|
iph->check = 0;
|
|
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
|
|
}
|
|
EXPORT_SYMBOL(ip_send_check);
|
|
|
|
int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
struct iphdr *iph = ip_hdr(skb);
|
|
|
|
iph->tot_len = htons(skb->len);
|
|
ip_send_check(iph);
|
|
|
|
/* if egress device is enslaved to an L3 master device pass the
|
|
* skb to its handler for processing
|
|
*/
|
|
skb = l3mdev_ip_out(sk, skb);
|
|
if (unlikely(!skb))
|
|
return 0;
|
|
|
|
skb->protocol = htons(ETH_P_IP);
|
|
|
|
return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
|
|
net, sk, skb, NULL, skb_dst(skb)->dev,
|
|
dst_output);
|
|
}
|
|
|
|
int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
int err;
|
|
|
|
err = __ip_local_out(net, sk, skb);
|
|
if (likely(err == 1))
|
|
err = dst_output(net, sk, skb);
|
|
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(ip_local_out);
|
|
|
|
static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
|
|
{
|
|
int ttl = inet->uc_ttl;
|
|
|
|
if (ttl < 0)
|
|
ttl = ip4_dst_hoplimit(dst);
|
|
return ttl;
|
|
}
|
|
|
|
/*
|
|
* Add an ip header to a skbuff and send it out.
|
|
*
|
|
*/
|
|
int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
|
|
__be32 saddr, __be32 daddr, struct ip_options_rcu *opt,
|
|
u8 tos)
|
|
{
|
|
struct inet_sock *inet = inet_sk(sk);
|
|
struct rtable *rt = skb_rtable(skb);
|
|
struct net *net = sock_net(sk);
|
|
struct iphdr *iph;
|
|
|
|
/* Build the IP header. */
|
|
skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0));
|
|
skb_reset_network_header(skb);
|
|
iph = ip_hdr(skb);
|
|
iph->version = 4;
|
|
iph->ihl = 5;
|
|
iph->tos = tos;
|
|
iph->ttl = ip_select_ttl(inet, &rt->dst);
|
|
iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
|
|
iph->saddr = saddr;
|
|
iph->protocol = sk->sk_protocol;
|
|
if (ip_dont_fragment(sk, &rt->dst)) {
|
|
iph->frag_off = htons(IP_DF);
|
|
iph->id = 0;
|
|
} else {
|
|
iph->frag_off = 0;
|
|
__ip_select_ident(net, iph, 1);
|
|
}
|
|
|
|
if (opt && opt->opt.optlen) {
|
|
iph->ihl += opt->opt.optlen>>2;
|
|
ip_options_build(skb, &opt->opt, daddr, rt, 0);
|
|
}
|
|
|
|
skb->priority = sk->sk_priority;
|
|
if (!skb->mark)
|
|
skb->mark = sk->sk_mark;
|
|
|
|
/* Send it out. */
|
|
return ip_local_out(net, skb->sk, skb);
|
|
}
|
|
EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
|
|
|
|
static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
struct dst_entry *dst = skb_dst(skb);
|
|
struct rtable *rt = (struct rtable *)dst;
|
|
struct net_device *dev = dst->dev;
|
|
unsigned int hh_len = LL_RESERVED_SPACE(dev);
|
|
struct neighbour *neigh;
|
|
bool is_v6gw = false;
|
|
|
|
if (rt->rt_type == RTN_MULTICAST) {
|
|
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len);
|
|
} else if (rt->rt_type == RTN_BROADCAST)
|
|
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len);
|
|
|
|
/* Be paranoid, rather than too clever. */
|
|
if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
|
|
struct sk_buff *skb2;
|
|
|
|
skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev));
|
|
if (!skb2) {
|
|
kfree_skb(skb);
|
|
return -ENOMEM;
|
|
}
|
|
if (skb->sk)
|
|
skb_set_owner_w(skb2, skb->sk);
|
|
consume_skb(skb);
|
|
skb = skb2;
|
|
}
|
|
|
|
if (lwtunnel_xmit_redirect(dst->lwtstate)) {
|
|
int res = lwtunnel_xmit(skb);
|
|
|
|
if (res < 0 || res == LWTUNNEL_XMIT_DONE)
|
|
return res;
|
|
}
|
|
|
|
rcu_read_lock_bh();
|
|
neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
|
|
if (!IS_ERR(neigh)) {
|
|
int res;
|
|
|
|
sock_confirm_neigh(skb, neigh);
|
|
/* if crossing protocols, can not use the cached header */
|
|
res = neigh_output(neigh, skb, is_v6gw);
|
|
rcu_read_unlock_bh();
|
|
return res;
|
|
}
|
|
rcu_read_unlock_bh();
|
|
|
|
net_dbg_ratelimited("%s: No header cache and no neighbour!\n",
|
|
__func__);
|
|
kfree_skb(skb);
|
|
return -EINVAL;
|
|
}
|
|
|
|
static int ip_finish_output_gso(struct net *net, struct sock *sk,
|
|
struct sk_buff *skb, unsigned int mtu)
|
|
{
|
|
struct sk_buff *segs, *nskb;
|
|
netdev_features_t features;
|
|
int ret = 0;
|
|
|
|
/* common case: seglen is <= mtu
|
|
*/
|
|
if (skb_gso_validate_network_len(skb, mtu))
|
|
return ip_finish_output2(net, sk, skb);
|
|
|
|
/* Slowpath - GSO segment length exceeds the egress MTU.
|
|
*
|
|
* This can happen in several cases:
|
|
* - Forwarding of a TCP GRO skb, when DF flag is not set.
|
|
* - Forwarding of an skb that arrived on a virtualization interface
|
|
* (virtio-net/vhost/tap) with TSO/GSO size set by other network
|
|
* stack.
|
|
* - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an
|
|
* interface with a smaller MTU.
|
|
* - Arriving GRO skb (or GSO skb in a virtualized environment) that is
|
|
* bridged to a NETIF_F_TSO tunnel stacked over an interface with an
|
|
* insufficient MTU.
|
|
*/
|
|
features = netif_skb_features(skb);
|
|
BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET);
|
|
segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
|
|
if (IS_ERR_OR_NULL(segs)) {
|
|
kfree_skb(skb);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
consume_skb(skb);
|
|
|
|
skb_list_walk_safe(segs, segs, nskb) {
|
|
int err;
|
|
|
|
skb_mark_not_on_list(segs);
|
|
err = ip_fragment(net, sk, segs, mtu, ip_finish_output2);
|
|
|
|
if (err && ret == 0)
|
|
ret = err;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
unsigned int mtu;
|
|
|
|
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
|
|
/* Policy lookup after SNAT yielded a new policy */
|
|
if (skb_dst(skb)->xfrm) {
|
|
IPCB(skb)->flags |= IPSKB_REROUTED;
|
|
return dst_output(net, sk, skb);
|
|
}
|
|
#endif
|
|
mtu = ip_skb_dst_mtu(sk, skb);
|
|
if (skb_is_gso(skb))
|
|
return ip_finish_output_gso(net, sk, skb, mtu);
|
|
|
|
if (skb->len > mtu || IPCB(skb)->frag_max_size)
|
|
return ip_fragment(net, sk, skb, mtu, ip_finish_output2);
|
|
|
|
return ip_finish_output2(net, sk, skb);
|
|
}
|
|
|
|
static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
int ret;
|
|
|
|
ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
|
|
switch (ret) {
|
|
case NET_XMIT_SUCCESS:
|
|
return __ip_finish_output(net, sk, skb);
|
|
case NET_XMIT_CN:
|
|
return __ip_finish_output(net, sk, skb) ? : ret;
|
|
default:
|
|
kfree_skb(skb);
|
|
return ret;
|
|
}
|
|
}
|
|
|
|
static int ip_mc_finish_output(struct net *net, struct sock *sk,
|
|
struct sk_buff *skb)
|
|
{
|
|
struct rtable *new_rt;
|
|
bool do_cn = false;
|
|
int ret, err;
|
|
|
|
ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
|
|
switch (ret) {
|
|
case NET_XMIT_CN:
|
|
do_cn = true;
|
|
fallthrough;
|
|
case NET_XMIT_SUCCESS:
|
|
break;
|
|
default:
|
|
kfree_skb(skb);
|
|
return ret;
|
|
}
|
|
|
|
/* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting
|
|
* this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten,
|
|
* see ipv4_pktinfo_prepare().
|
|
*/
|
|
new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb));
|
|
if (new_rt) {
|
|
new_rt->rt_iif = 0;
|
|
skb_dst_drop(skb);
|
|
skb_dst_set(skb, &new_rt->dst);
|
|
}
|
|
|
|
err = dev_loopback_xmit(net, sk, skb);
|
|
return (do_cn && err) ? ret : err;
|
|
}
|
|
|
|
int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
struct rtable *rt = skb_rtable(skb);
|
|
struct net_device *dev = rt->dst.dev;
|
|
|
|
/*
|
|
* If the indicated interface is up and running, send the packet.
|
|
*/
|
|
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
|
|
|
|
skb->dev = dev;
|
|
skb->protocol = htons(ETH_P_IP);
|
|
|
|
/*
|
|
* Multicasts are looped back for other local users
|
|
*/
|
|
|
|
if (rt->rt_flags&RTCF_MULTICAST) {
|
|
if (sk_mc_loop(sk)
|
|
#ifdef CONFIG_IP_MROUTE
|
|
/* Small optimization: do not loopback not local frames,
|
|
which returned after forwarding; they will be dropped
|
|
by ip_mr_input in any case.
|
|
Note, that local frames are looped back to be delivered
|
|
to local recipients.
|
|
|
|
This check is duplicated in ip_mr_input at the moment.
|
|
*/
|
|
&&
|
|
((rt->rt_flags & RTCF_LOCAL) ||
|
|
!(IPCB(skb)->flags & IPSKB_FORWARDED))
|
|
#endif
|
|
) {
|
|
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
|
|
if (newskb)
|
|
NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
|
|
net, sk, newskb, NULL, newskb->dev,
|
|
ip_mc_finish_output);
|
|
}
|
|
|
|
/* Multicasts with ttl 0 must not go beyond the host */
|
|
|
|
if (ip_hdr(skb)->ttl == 0) {
|
|
kfree_skb(skb);
|
|
return 0;
|
|
}
|
|
}
|
|
|
|
if (rt->rt_flags&RTCF_BROADCAST) {
|
|
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
|
|
if (newskb)
|
|
NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
|
|
net, sk, newskb, NULL, newskb->dev,
|
|
ip_mc_finish_output);
|
|
}
|
|
|
|
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
|
|
net, sk, skb, NULL, skb->dev,
|
|
ip_finish_output,
|
|
!(IPCB(skb)->flags & IPSKB_REROUTED));
|
|
}
|
|
|
|
int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev;
|
|
|
|
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
|
|
|
|
skb->dev = dev;
|
|
skb->protocol = htons(ETH_P_IP);
|
|
|
|
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
|
|
net, sk, skb, indev, dev,
|
|
ip_finish_output,
|
|
!(IPCB(skb)->flags & IPSKB_REROUTED));
|
|
}
|
|
EXPORT_SYMBOL(ip_output);
|
|
|
|
/*
|
|
* copy saddr and daddr, possibly using 64bit load/stores
|
|
* Equivalent to :
|
|
* iph->saddr = fl4->saddr;
|
|
* iph->daddr = fl4->daddr;
|
|
*/
|
|
static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
|
|
{
|
|
BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) !=
|
|
offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr));
|
|
memcpy(&iph->saddr, &fl4->saddr,
|
|
sizeof(fl4->saddr) + sizeof(fl4->daddr));
|
|
}
|
|
|
|
/* Note: skb->sk can be different from sk, in case of tunnels */
|
|
int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
|
|
__u8 tos)
|
|
{
|
|
struct inet_sock *inet = inet_sk(sk);
|
|
struct net *net = sock_net(sk);
|
|
struct ip_options_rcu *inet_opt;
|
|
struct flowi4 *fl4;
|
|
struct rtable *rt;
|
|
struct iphdr *iph;
|
|
int res;
|
|
|
|
/* Skip all of this if the packet is already routed,
|
|
* f.e. by something like SCTP.
|
|
*/
|
|
rcu_read_lock();
|
|
inet_opt = rcu_dereference(inet->inet_opt);
|
|
fl4 = &fl->u.ip4;
|
|
rt = skb_rtable(skb);
|
|
if (rt)
|
|
goto packet_routed;
|
|
|
|
/* Make sure we can route this packet. */
|
|
rt = (struct rtable *)__sk_dst_check(sk, 0);
|
|
if (!rt) {
|
|
__be32 daddr;
|
|
|
|
/* Use correct destination address if we have options. */
|
|
daddr = inet->inet_daddr;
|
|
if (inet_opt && inet_opt->opt.srr)
|
|
daddr = inet_opt->opt.faddr;
|
|
|
|
/* If this fails, retransmit mechanism of transport layer will
|
|
* keep trying until route appears or the connection times
|
|
* itself out.
|
|
*/
|
|
rt = ip_route_output_ports(net, fl4, sk,
|
|
daddr, inet->inet_saddr,
|
|
inet->inet_dport,
|
|
inet->inet_sport,
|
|
sk->sk_protocol,
|
|
RT_CONN_FLAGS_TOS(sk, tos),
|
|
sk->sk_bound_dev_if);
|
|
if (IS_ERR(rt))
|
|
goto no_route;
|
|
sk_setup_caps(sk, &rt->dst);
|
|
}
|
|
skb_dst_set_noref(skb, &rt->dst);
|
|
|
|
packet_routed:
|
|
if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
|
|
goto no_route;
|
|
|
|
/* OK, we know where to send it, allocate and build IP header. */
|
|
skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0));
|
|
skb_reset_network_header(skb);
|
|
iph = ip_hdr(skb);
|
|
*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff));
|
|
if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df)
|
|
iph->frag_off = htons(IP_DF);
|
|
else
|
|
iph->frag_off = 0;
|
|
iph->ttl = ip_select_ttl(inet, &rt->dst);
|
|
iph->protocol = sk->sk_protocol;
|
|
ip_copy_addrs(iph, fl4);
|
|
|
|
/* Transport layer set skb->h.foo itself. */
|
|
|
|
if (inet_opt && inet_opt->opt.optlen) {
|
|
iph->ihl += inet_opt->opt.optlen >> 2;
|
|
ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
|
|
}
|
|
|
|
ip_select_ident_segs(net, skb, sk,
|
|
skb_shinfo(skb)->gso_segs ?: 1);
|
|
|
|
/* TODO : should we use skb->sk here instead of sk ? */
|
|
skb->priority = sk->sk_priority;
|
|
skb->mark = sk->sk_mark;
|
|
|
|
res = ip_local_out(net, sk, skb);
|
|
rcu_read_unlock();
|
|
return res;
|
|
|
|
no_route:
|
|
rcu_read_unlock();
|
|
IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
|
|
kfree_skb(skb);
|
|
return -EHOSTUNREACH;
|
|
}
|
|
EXPORT_SYMBOL(__ip_queue_xmit);
|
|
|
|
int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
|
|
{
|
|
return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos);
|
|
}
|
|
EXPORT_SYMBOL(ip_queue_xmit);
|
|
|
|
static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
|
|
{
|
|
to->pkt_type = from->pkt_type;
|
|
to->priority = from->priority;
|
|
to->protocol = from->protocol;
|
|
to->skb_iif = from->skb_iif;
|
|
skb_dst_drop(to);
|
|
skb_dst_copy(to, from);
|
|
to->dev = from->dev;
|
|
to->mark = from->mark;
|
|
|
|
skb_copy_hash(to, from);
|
|
|
|
#ifdef CONFIG_NET_SCHED
|
|
to->tc_index = from->tc_index;
|
|
#endif
|
|
nf_copy(to, from);
|
|
skb_ext_copy(to, from);
|
|
#if IS_ENABLED(CONFIG_IP_VS)
|
|
to->ipvs_property = from->ipvs_property;
|
|
#endif
|
|
skb_copy_secmark(to, from);
|
|
}
|
|
|
|
static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
|
|
unsigned int mtu,
|
|
int (*output)(struct net *, struct sock *, struct sk_buff *))
|
|
{
|
|
struct iphdr *iph = ip_hdr(skb);
|
|
|
|
if ((iph->frag_off & htons(IP_DF)) == 0)
|
|
return ip_do_fragment(net, sk, skb, output);
|
|
|
|
if (unlikely(!skb->ignore_df ||
|
|
(IPCB(skb)->frag_max_size &&
|
|
IPCB(skb)->frag_max_size > mtu))) {
|
|
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
|
|
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
|
|
htonl(mtu));
|
|
kfree_skb(skb);
|
|
return -EMSGSIZE;
|
|
}
|
|
|
|
return ip_do_fragment(net, sk, skb, output);
|
|
}
|
|
|
|
void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph,
|
|
unsigned int hlen, struct ip_fraglist_iter *iter)
|
|
{
|
|
unsigned int first_len = skb_pagelen(skb);
|
|
|
|
iter->frag = skb_shinfo(skb)->frag_list;
|
|
skb_frag_list_init(skb);
|
|
|
|
iter->offset = 0;
|
|
iter->iph = iph;
|
|
iter->hlen = hlen;
|
|
|
|
skb->data_len = first_len - skb_headlen(skb);
|
|
skb->len = first_len;
|
|
iph->tot_len = htons(first_len);
|
|
iph->frag_off = htons(IP_MF);
|
|
ip_send_check(iph);
|
|
}
|
|
EXPORT_SYMBOL(ip_fraglist_init);
|
|
|
|
static void ip_fraglist_ipcb_prepare(struct sk_buff *skb,
|
|
struct ip_fraglist_iter *iter)
|
|
{
|
|
struct sk_buff *to = iter->frag;
|
|
|
|
/* Copy the flags to each fragment. */
|
|
IPCB(to)->flags = IPCB(skb)->flags;
|
|
|
|
if (iter->offset == 0)
|
|
ip_options_fragment(to);
|
|
}
|
|
|
|
void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter)
|
|
{
|
|
unsigned int hlen = iter->hlen;
|
|
struct iphdr *iph = iter->iph;
|
|
struct sk_buff *frag;
|
|
|
|
frag = iter->frag;
|
|
frag->ip_summed = CHECKSUM_NONE;
|
|
skb_reset_transport_header(frag);
|
|
__skb_push(frag, hlen);
|
|
skb_reset_network_header(frag);
|
|
memcpy(skb_network_header(frag), iph, hlen);
|
|
iter->iph = ip_hdr(frag);
|
|
iph = iter->iph;
|
|
iph->tot_len = htons(frag->len);
|
|
ip_copy_metadata(frag, skb);
|
|
iter->offset += skb->len - hlen;
|
|
iph->frag_off = htons(iter->offset >> 3);
|
|
if (frag->next)
|
|
iph->frag_off |= htons(IP_MF);
|
|
/* Ready, complete checksum */
|
|
ip_send_check(iph);
|
|
}
|
|
EXPORT_SYMBOL(ip_fraglist_prepare);
|
|
|
|
void ip_frag_init(struct sk_buff *skb, unsigned int hlen,
|
|
unsigned int ll_rs, unsigned int mtu, bool DF,
|
|
struct ip_frag_state *state)
|
|
{
|
|
struct iphdr *iph = ip_hdr(skb);
|
|
|
|
state->DF = DF;
|
|
state->hlen = hlen;
|
|
state->ll_rs = ll_rs;
|
|
state->mtu = mtu;
|
|
|
|
state->left = skb->len - hlen; /* Space per frame */
|
|
state->ptr = hlen; /* Where to start from */
|
|
|
|
state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
|
|
state->not_last_frag = iph->frag_off & htons(IP_MF);
|
|
}
|
|
EXPORT_SYMBOL(ip_frag_init);
|
|
|
|
static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to,
|
|
bool first_frag, struct ip_frag_state *state)
|
|
{
|
|
/* Copy the flags to each fragment. */
|
|
IPCB(to)->flags = IPCB(from)->flags;
|
|
|
|
/* ANK: dirty, but effective trick. Upgrade options only if
|
|
* the segment to be fragmented was THE FIRST (otherwise,
|
|
* options are already fixed) and make it ONCE
|
|
* on the initial skb, so that all the following fragments
|
|
* will inherit fixed options.
|
|
*/
|
|
if (first_frag)
|
|
ip_options_fragment(from);
|
|
}
|
|
|
|
struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state)
|
|
{
|
|
unsigned int len = state->left;
|
|
struct sk_buff *skb2;
|
|
struct iphdr *iph;
|
|
|
|
len = state->left;
|
|
/* IF: it doesn't fit, use 'mtu' - the data space left */
|
|
if (len > state->mtu)
|
|
len = state->mtu;
|
|
/* IF: we are not sending up to and including the packet end
|
|
then align the next start on an eight byte boundary */
|
|
if (len < state->left) {
|
|
len &= ~7;
|
|
}
|
|
|
|
/* Allocate buffer */
|
|
skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC);
|
|
if (!skb2)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
/*
|
|
* Set up data on packet
|
|
*/
|
|
|
|
ip_copy_metadata(skb2, skb);
|
|
skb_reserve(skb2, state->ll_rs);
|
|
skb_put(skb2, len + state->hlen);
|
|
skb_reset_network_header(skb2);
|
|
skb2->transport_header = skb2->network_header + state->hlen;
|
|
|
|
/*
|
|
* Charge the memory for the fragment to any owner
|
|
* it might possess
|
|
*/
|
|
|
|
if (skb->sk)
|
|
skb_set_owner_w(skb2, skb->sk);
|
|
|
|
/*
|
|
* Copy the packet header into the new buffer.
|
|
*/
|
|
|
|
skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen);
|
|
|
|
/*
|
|
* Copy a block of the IP datagram.
|
|
*/
|
|
if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len))
|
|
BUG();
|
|
state->left -= len;
|
|
|
|
/*
|
|
* Fill in the new header fields.
|
|
*/
|
|
iph = ip_hdr(skb2);
|
|
iph->frag_off = htons((state->offset >> 3));
|
|
if (state->DF)
|
|
iph->frag_off |= htons(IP_DF);
|
|
|
|
/*
|
|
* Added AC : If we are fragmenting a fragment that's not the
|
|
* last fragment then keep MF on each bit
|
|
*/
|
|
if (state->left > 0 || state->not_last_frag)
|
|
iph->frag_off |= htons(IP_MF);
|
|
state->ptr += len;
|
|
state->offset += len;
|
|
|
|
iph->tot_len = htons(len + state->hlen);
|
|
|
|
ip_send_check(iph);
|
|
|
|
return skb2;
|
|
}
|
|
EXPORT_SYMBOL(ip_frag_next);
|
|
|
|
/*
|
|
* This IP datagram is too large to be sent in one piece. Break it up into
|
|
* smaller pieces (each of size equal to IP header plus
|
|
* a block of the data of the original IP data part) that will yet fit in a
|
|
* single device frame, and queue such a frame for sending.
|
|
*/
|
|
|
|
int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
|
|
int (*output)(struct net *, struct sock *, struct sk_buff *))
|
|
{
|
|
struct iphdr *iph;
|
|
struct sk_buff *skb2;
|
|
struct rtable *rt = skb_rtable(skb);
|
|
unsigned int mtu, hlen, ll_rs;
|
|
struct ip_fraglist_iter iter;
|
|
ktime_t tstamp = skb->tstamp;
|
|
struct ip_frag_state state;
|
|
int err = 0;
|
|
|
|
/* for offloaded checksums cleanup checksum before fragmentation */
|
|
if (skb->ip_summed == CHECKSUM_PARTIAL &&
|
|
(err = skb_checksum_help(skb)))
|
|
goto fail;
|
|
|
|
/*
|
|
* Point into the IP datagram header.
|
|
*/
|
|
|
|
iph = ip_hdr(skb);
|
|
|
|
mtu = ip_skb_dst_mtu(sk, skb);
|
|
if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu)
|
|
mtu = IPCB(skb)->frag_max_size;
|
|
|
|
/*
|
|
* Setup starting values.
|
|
*/
|
|
|
|
hlen = iph->ihl * 4;
|
|
mtu = mtu - hlen; /* Size of data space */
|
|
IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE;
|
|
ll_rs = LL_RESERVED_SPACE(rt->dst.dev);
|
|
|
|
/* When frag_list is given, use it. First, check its validity:
|
|
* some transformers could create wrong frag_list or break existing
|
|
* one, it is not prohibited. In this case fall back to copying.
|
|
*
|
|
* LATER: this step can be merged to real generation of fragments,
|
|
* we can switch to copy when see the first bad fragment.
|
|
*/
|
|
if (skb_has_frag_list(skb)) {
|
|
struct sk_buff *frag, *frag2;
|
|
unsigned int first_len = skb_pagelen(skb);
|
|
|
|
if (first_len - hlen > mtu ||
|
|
((first_len - hlen) & 7) ||
|
|
ip_is_fragment(iph) ||
|
|
skb_cloned(skb) ||
|
|
skb_headroom(skb) < ll_rs)
|
|
goto slow_path;
|
|
|
|
skb_walk_frags(skb, frag) {
|
|
/* Correct geometry. */
|
|
if (frag->len > mtu ||
|
|
((frag->len & 7) && frag->next) ||
|
|
skb_headroom(frag) < hlen + ll_rs)
|
|
goto slow_path_clean;
|
|
|
|
/* Partially cloned skb? */
|
|
if (skb_shared(frag))
|
|
goto slow_path_clean;
|
|
|
|
BUG_ON(frag->sk);
|
|
if (skb->sk) {
|
|
frag->sk = skb->sk;
|
|
frag->destructor = sock_wfree;
|
|
}
|
|
skb->truesize -= frag->truesize;
|
|
}
|
|
|
|
/* Everything is OK. Generate! */
|
|
ip_fraglist_init(skb, iph, hlen, &iter);
|
|
|
|
for (;;) {
|
|
/* Prepare header of the next frame,
|
|
* before previous one went down. */
|
|
if (iter.frag) {
|
|
ip_fraglist_ipcb_prepare(skb, &iter);
|
|
ip_fraglist_prepare(skb, &iter);
|
|
}
|
|
|
|
skb->tstamp = tstamp;
|
|
err = output(net, sk, skb);
|
|
|
|
if (!err)
|
|
IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
|
|
if (err || !iter.frag)
|
|
break;
|
|
|
|
skb = ip_fraglist_next(&iter);
|
|
}
|
|
|
|
if (err == 0) {
|
|
IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS);
|
|
return 0;
|
|
}
|
|
|
|
kfree_skb_list(iter.frag);
|
|
|
|
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
|
|
return err;
|
|
|
|
slow_path_clean:
|
|
skb_walk_frags(skb, frag2) {
|
|
if (frag2 == frag)
|
|
break;
|
|
frag2->sk = NULL;
|
|
frag2->destructor = NULL;
|
|
skb->truesize += frag2->truesize;
|
|
}
|
|
}
|
|
|
|
slow_path:
|
|
/*
|
|
* Fragment the datagram.
|
|
*/
|
|
|
|
ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU,
|
|
&state);
|
|
|
|
/*
|
|
* Keep copying data until we run out.
|
|
*/
|
|
|
|
while (state.left > 0) {
|
|
bool first_frag = (state.offset == 0);
|
|
|
|
skb2 = ip_frag_next(skb, &state);
|
|
if (IS_ERR(skb2)) {
|
|
err = PTR_ERR(skb2);
|
|
goto fail;
|
|
}
|
|
ip_frag_ipcb(skb, skb2, first_frag, &state);
|
|
|
|
/*
|
|
* Put this fragment into the sending queue.
|
|
*/
|
|
skb2->tstamp = tstamp;
|
|
err = output(net, sk, skb2);
|
|
if (err)
|
|
goto fail;
|
|
|
|
IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
|
|
}
|
|
consume_skb(skb);
|
|
IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS);
|
|
return err;
|
|
|
|
fail:
|
|
kfree_skb(skb);
|
|
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL(ip_do_fragment);
|
|
|
|
int
|
|
ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
|
|
{
|
|
struct msghdr *msg = from;
|
|
|
|
if (skb->ip_summed == CHECKSUM_PARTIAL) {
|
|
if (!copy_from_iter_full(to, len, &msg->msg_iter))
|
|
return -EFAULT;
|
|
} else {
|
|
__wsum csum = 0;
|
|
if (!csum_and_copy_from_iter_full(to, len, &csum, &msg->msg_iter))
|
|
return -EFAULT;
|
|
skb->csum = csum_block_add(skb->csum, csum, odd);
|
|
}
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(ip_generic_getfrag);
|
|
|
|
static inline __wsum
|
|
csum_page(struct page *page, int offset, int copy)
|
|
{
|
|
char *kaddr;
|
|
__wsum csum;
|
|
kaddr = kmap(page);
|
|
csum = csum_partial(kaddr + offset, copy, 0);
|
|
kunmap(page);
|
|
return csum;
|
|
}
|
|
|
|
static int __ip_append_data(struct sock *sk,
|
|
struct flowi4 *fl4,
|
|
struct sk_buff_head *queue,
|
|
struct inet_cork *cork,
|
|
struct page_frag *pfrag,
|
|
int getfrag(void *from, char *to, int offset,
|
|
int len, int odd, struct sk_buff *skb),
|
|
void *from, int length, int transhdrlen,
|
|
unsigned int flags)
|
|
{
|
|
struct inet_sock *inet = inet_sk(sk);
|
|
struct ubuf_info *uarg = NULL;
|
|
struct sk_buff *skb;
|
|
|
|
struct ip_options *opt = cork->opt;
|
|
int hh_len;
|
|
int exthdrlen;
|
|
int mtu;
|
|
int copy;
|
|
int err;
|
|
int offset = 0;
|
|
unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
|
|
int csummode = CHECKSUM_NONE;
|
|
struct rtable *rt = (struct rtable *)cork->dst;
|
|
unsigned int wmem_alloc_delta = 0;
|
|
bool paged, extra_uref = false;
|
|
u32 tskey = 0;
|
|
|
|
skb = skb_peek_tail(queue);
|
|
|
|
exthdrlen = !skb ? rt->dst.header_len : 0;
|
|
mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
|
|
paged = !!cork->gso_size;
|
|
|
|
if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
|
|
sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
|
|
tskey = sk->sk_tskey++;
|
|
|
|
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
|
|
|
|
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
|
|
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
|
|
maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu;
|
|
|
|
if (cork->length + length > maxnonfragsize - fragheaderlen) {
|
|
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
|
|
mtu - (opt ? opt->optlen : 0));
|
|
return -EMSGSIZE;
|
|
}
|
|
|
|
/*
|
|
* transhdrlen > 0 means that this is the first fragment and we wish
|
|
* it won't be fragmented in the future.
|
|
*/
|
|
if (transhdrlen &&
|
|
length + fragheaderlen <= mtu &&
|
|
rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) &&
|
|
(!(flags & MSG_MORE) || cork->gso_size) &&
|
|
(!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM)))
|
|
csummode = CHECKSUM_PARTIAL;
|
|
|
|
if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) {
|
|
uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
|
|
if (!uarg)
|
|
return -ENOBUFS;
|
|
extra_uref = !skb_zcopy(skb); /* only ref on new uarg */
|
|
if (rt->dst.dev->features & NETIF_F_SG &&
|
|
csummode == CHECKSUM_PARTIAL) {
|
|
paged = true;
|
|
} else {
|
|
uarg->zerocopy = 0;
|
|
skb_zcopy_set(skb, uarg, &extra_uref);
|
|
}
|
|
}
|
|
|
|
cork->length += length;
|
|
|
|
/* So, what's going on in the loop below?
|
|
*
|
|
* We use calculated fragment length to generate chained skb,
|
|
* each of segments is IP fragment ready for sending to network after
|
|
* adding appropriate IP header.
|
|
*/
|
|
|
|
if (!skb)
|
|
goto alloc_new_skb;
|
|
|
|
while (length > 0) {
|
|
/* Check if the remaining data fits into current packet. */
|
|
copy = mtu - skb->len;
|
|
if (copy < length)
|
|
copy = maxfraglen - skb->len;
|
|
if (copy <= 0) {
|
|
char *data;
|
|
unsigned int datalen;
|
|
unsigned int fraglen;
|
|
unsigned int fraggap;
|
|
unsigned int alloclen, alloc_extra;
|
|
unsigned int pagedlen;
|
|
struct sk_buff *skb_prev;
|
|
alloc_new_skb:
|
|
skb_prev = skb;
|
|
if (skb_prev)
|
|
fraggap = skb_prev->len - maxfraglen;
|
|
else
|
|
fraggap = 0;
|
|
|
|
/*
|
|
* If remaining data exceeds the mtu,
|
|
* we know we need more fragment(s).
|
|
*/
|
|
datalen = length + fraggap;
|
|
if (datalen > mtu - fragheaderlen)
|
|
datalen = maxfraglen - fragheaderlen;
|
|
fraglen = datalen + fragheaderlen;
|
|
pagedlen = 0;
|
|
|
|
alloc_extra = hh_len + 15;
|
|
alloc_extra += exthdrlen;
|
|
|
|
/* The last fragment gets additional space at tail.
|
|
* Note, with MSG_MORE we overallocate on fragments,
|
|
* because we have no idea what fragment will be
|
|
* the last.
|
|
*/
|
|
if (datalen == length + fraggap)
|
|
alloc_extra += rt->dst.trailer_len;
|
|
|
|
if ((flags & MSG_MORE) &&
|
|
!(rt->dst.dev->features&NETIF_F_SG))
|
|
alloclen = mtu;
|
|
else if (!paged &&
|
|
(fraglen + alloc_extra < SKB_MAX_ALLOC ||
|
|
!(rt->dst.dev->features & NETIF_F_SG)))
|
|
alloclen = fraglen;
|
|
else {
|
|
alloclen = min_t(int, fraglen, MAX_HEADER);
|
|
pagedlen = fraglen - alloclen;
|
|
}
|
|
|
|
alloclen += alloc_extra;
|
|
|
|
if (transhdrlen) {
|
|
skb = sock_alloc_send_skb(sk, alloclen,
|
|
(flags & MSG_DONTWAIT), &err);
|
|
} else {
|
|
skb = NULL;
|
|
if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <=
|
|
2 * sk->sk_sndbuf)
|
|
skb = alloc_skb(alloclen,
|
|
sk->sk_allocation);
|
|
if (unlikely(!skb))
|
|
err = -ENOBUFS;
|
|
}
|
|
if (!skb)
|
|
goto error;
|
|
|
|
/*
|
|
* Fill in the control structures
|
|
*/
|
|
skb->ip_summed = csummode;
|
|
skb->csum = 0;
|
|
skb_reserve(skb, hh_len);
|
|
|
|
/*
|
|
* Find where to start putting bytes.
|
|
*/
|
|
data = skb_put(skb, fraglen + exthdrlen - pagedlen);
|
|
skb_set_network_header(skb, exthdrlen);
|
|
skb->transport_header = (skb->network_header +
|
|
fragheaderlen);
|
|
data += fragheaderlen + exthdrlen;
|
|
|
|
if (fraggap) {
|
|
skb->csum = skb_copy_and_csum_bits(
|
|
skb_prev, maxfraglen,
|
|
data + transhdrlen, fraggap);
|
|
skb_prev->csum = csum_sub(skb_prev->csum,
|
|
skb->csum);
|
|
data += fraggap;
|
|
pskb_trim_unique(skb_prev, maxfraglen);
|
|
}
|
|
|
|
copy = datalen - transhdrlen - fraggap - pagedlen;
|
|
if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
|
|
err = -EFAULT;
|
|
kfree_skb(skb);
|
|
goto error;
|
|
}
|
|
|
|
offset += copy;
|
|
length -= copy + transhdrlen;
|
|
transhdrlen = 0;
|
|
exthdrlen = 0;
|
|
csummode = CHECKSUM_NONE;
|
|
|
|
/* only the initial fragment is time stamped */
|
|
skb_shinfo(skb)->tx_flags = cork->tx_flags;
|
|
cork->tx_flags = 0;
|
|
skb_shinfo(skb)->tskey = tskey;
|
|
tskey = 0;
|
|
skb_zcopy_set(skb, uarg, &extra_uref);
|
|
|
|
if ((flags & MSG_CONFIRM) && !skb_prev)
|
|
skb_set_dst_pending_confirm(skb, 1);
|
|
|
|
/*
|
|
* Put the packet on the pending queue.
|
|
*/
|
|
if (!skb->destructor) {
|
|
skb->destructor = sock_wfree;
|
|
skb->sk = sk;
|
|
wmem_alloc_delta += skb->truesize;
|
|
}
|
|
__skb_queue_tail(queue, skb);
|
|
continue;
|
|
}
|
|
|
|
if (copy > length)
|
|
copy = length;
|
|
|
|
if (!(rt->dst.dev->features&NETIF_F_SG) &&
|
|
skb_tailroom(skb) >= copy) {
|
|
unsigned int off;
|
|
|
|
off = skb->len;
|
|
if (getfrag(from, skb_put(skb, copy),
|
|
offset, copy, off, skb) < 0) {
|
|
__skb_trim(skb, off);
|
|
err = -EFAULT;
|
|
goto error;
|
|
}
|
|
} else if (!uarg || !uarg->zerocopy) {
|
|
int i = skb_shinfo(skb)->nr_frags;
|
|
|
|
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,
|
|
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;
|
|
wmem_alloc_delta += copy;
|
|
} else {
|
|
err = skb_zerocopy_iter_dgram(skb, from, copy);
|
|
if (err < 0)
|
|
goto error;
|
|
}
|
|
offset += copy;
|
|
length -= copy;
|
|
}
|
|
|
|
if (wmem_alloc_delta)
|
|
refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
|
|
return 0;
|
|
|
|
error_efault:
|
|
err = -EFAULT;
|
|
error:
|
|
net_zcopy_put_abort(uarg, extra_uref);
|
|
cork->length -= length;
|
|
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
|
|
refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
|
|
return err;
|
|
}
|
|
|
|
static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
|
|
struct ipcm_cookie *ipc, struct rtable **rtp)
|
|
{
|
|
struct ip_options_rcu *opt;
|
|
struct rtable *rt;
|
|
|
|
rt = *rtp;
|
|
if (unlikely(!rt))
|
|
return -EFAULT;
|
|
|
|
/*
|
|
* setup for corking.
|
|
*/
|
|
opt = ipc->opt;
|
|
if (opt) {
|
|
if (!cork->opt) {
|
|
cork->opt = kmalloc(sizeof(struct ip_options) + 40,
|
|
sk->sk_allocation);
|
|
if (unlikely(!cork->opt))
|
|
return -ENOBUFS;
|
|
}
|
|
memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen);
|
|
cork->flags |= IPCORK_OPT;
|
|
cork->addr = ipc->addr;
|
|
}
|
|
|
|
cork->fragsize = ip_sk_use_pmtu(sk) ?
|
|
dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
|
|
|
|
if (!inetdev_valid_mtu(cork->fragsize))
|
|
return -ENETUNREACH;
|
|
|
|
cork->gso_size = ipc->gso_size;
|
|
|
|
cork->dst = &rt->dst;
|
|
/* We stole this route, caller should not release it. */
|
|
*rtp = NULL;
|
|
|
|
cork->length = 0;
|
|
cork->ttl = ipc->ttl;
|
|
cork->tos = ipc->tos;
|
|
cork->mark = ipc->sockc.mark;
|
|
cork->priority = ipc->priority;
|
|
cork->transmit_time = ipc->sockc.transmit_time;
|
|
cork->tx_flags = 0;
|
|
sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* ip_append_data() and ip_append_page() can make one large IP datagram
|
|
* from many pieces of data. Each pieces will be holded on the socket
|
|
* until ip_push_pending_frames() is called. Each piece can be a page
|
|
* or non-page data.
|
|
*
|
|
* Not only UDP, other transport protocols - e.g. raw sockets - can use
|
|
* this interface potentially.
|
|
*
|
|
* LATER: length must be adjusted by pad at tail, when it is required.
|
|
*/
|
|
int ip_append_data(struct sock *sk, struct flowi4 *fl4,
|
|
int getfrag(void *from, char *to, int offset, int len,
|
|
int odd, struct sk_buff *skb),
|
|
void *from, int length, int transhdrlen,
|
|
struct ipcm_cookie *ipc, struct rtable **rtp,
|
|
unsigned int flags)
|
|
{
|
|
struct inet_sock *inet = inet_sk(sk);
|
|
int err;
|
|
|
|
if (flags&MSG_PROBE)
|
|
return 0;
|
|
|
|
if (skb_queue_empty(&sk->sk_write_queue)) {
|
|
err = ip_setup_cork(sk, &inet->cork.base, ipc, rtp);
|
|
if (err)
|
|
return err;
|
|
} else {
|
|
transhdrlen = 0;
|
|
}
|
|
|
|
return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base,
|
|
sk_page_frag(sk), getfrag,
|
|
from, length, transhdrlen, flags);
|
|
}
|
|
|
|
ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
|
|
int offset, size_t size, int flags)
|
|
{
|
|
struct inet_sock *inet = inet_sk(sk);
|
|
struct sk_buff *skb;
|
|
struct rtable *rt;
|
|
struct ip_options *opt = NULL;
|
|
struct inet_cork *cork;
|
|
int hh_len;
|
|
int mtu;
|
|
int len;
|
|
int err;
|
|
unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize;
|
|
|
|
if (inet->hdrincl)
|
|
return -EPERM;
|
|
|
|
if (flags&MSG_PROBE)
|
|
return 0;
|
|
|
|
if (skb_queue_empty(&sk->sk_write_queue))
|
|
return -EINVAL;
|
|
|
|
cork = &inet->cork.base;
|
|
rt = (struct rtable *)cork->dst;
|
|
if (cork->flags & IPCORK_OPT)
|
|
opt = cork->opt;
|
|
|
|
if (!(rt->dst.dev->features & NETIF_F_SG))
|
|
return -EOPNOTSUPP;
|
|
|
|
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
|
|
mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
|
|
|
|
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
|
|
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
|
|
maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
|
|
|
|
if (cork->length + size > maxnonfragsize - fragheaderlen) {
|
|
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
|
|
mtu - (opt ? opt->optlen : 0));
|
|
return -EMSGSIZE;
|
|
}
|
|
|
|
skb = skb_peek_tail(&sk->sk_write_queue);
|
|
if (!skb)
|
|
return -EINVAL;
|
|
|
|
cork->length += size;
|
|
|
|
while (size > 0) {
|
|
/* Check if the remaining data fits into current packet. */
|
|
len = mtu - skb->len;
|
|
if (len < size)
|
|
len = maxfraglen - skb->len;
|
|
|
|
if (len <= 0) {
|
|
struct sk_buff *skb_prev;
|
|
int alloclen;
|
|
|
|
skb_prev = skb;
|
|
fraggap = skb_prev->len - maxfraglen;
|
|
|
|
alloclen = fragheaderlen + hh_len + fraggap + 15;
|
|
skb = sock_wmalloc(sk, alloclen, 1, sk->sk_allocation);
|
|
if (unlikely(!skb)) {
|
|
err = -ENOBUFS;
|
|
goto error;
|
|
}
|
|
|
|
/*
|
|
* Fill in the control structures
|
|
*/
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
skb->csum = 0;
|
|
skb_reserve(skb, hh_len);
|
|
|
|
/*
|
|
* Find where to start putting bytes.
|
|
*/
|
|
skb_put(skb, fragheaderlen + fraggap);
|
|
skb_reset_network_header(skb);
|
|
skb->transport_header = (skb->network_header +
|
|
fragheaderlen);
|
|
if (fraggap) {
|
|
skb->csum = skb_copy_and_csum_bits(skb_prev,
|
|
maxfraglen,
|
|
skb_transport_header(skb),
|
|
fraggap);
|
|
skb_prev->csum = csum_sub(skb_prev->csum,
|
|
skb->csum);
|
|
pskb_trim_unique(skb_prev, maxfraglen);
|
|
}
|
|
|
|
/*
|
|
* Put the packet on the pending queue.
|
|
*/
|
|
__skb_queue_tail(&sk->sk_write_queue, skb);
|
|
continue;
|
|
}
|
|
|
|
if (len > size)
|
|
len = size;
|
|
|
|
if (skb_append_pagefrags(skb, page, offset, len)) {
|
|
err = -EMSGSIZE;
|
|
goto error;
|
|
}
|
|
|
|
if (skb->ip_summed == CHECKSUM_NONE) {
|
|
__wsum csum;
|
|
csum = csum_page(page, offset, len);
|
|
skb->csum = csum_block_add(skb->csum, csum, skb->len);
|
|
}
|
|
|
|
skb->len += len;
|
|
skb->data_len += len;
|
|
skb->truesize += len;
|
|
refcount_add(len, &sk->sk_wmem_alloc);
|
|
offset += len;
|
|
size -= len;
|
|
}
|
|
return 0;
|
|
|
|
error:
|
|
cork->length -= size;
|
|
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
|
|
return err;
|
|
}
|
|
|
|
static void ip_cork_release(struct inet_cork *cork)
|
|
{
|
|
cork->flags &= ~IPCORK_OPT;
|
|
kfree(cork->opt);
|
|
cork->opt = NULL;
|
|
dst_release(cork->dst);
|
|
cork->dst = NULL;
|
|
}
|
|
|
|
/*
|
|
* Combined all pending IP fragments on the socket as one IP datagram
|
|
* and push them out.
|
|
*/
|
|
struct sk_buff *__ip_make_skb(struct sock *sk,
|
|
struct flowi4 *fl4,
|
|
struct sk_buff_head *queue,
|
|
struct inet_cork *cork)
|
|
{
|
|
struct sk_buff *skb, *tmp_skb;
|
|
struct sk_buff **tail_skb;
|
|
struct inet_sock *inet = inet_sk(sk);
|
|
struct net *net = sock_net(sk);
|
|
struct ip_options *opt = NULL;
|
|
struct rtable *rt = (struct rtable *)cork->dst;
|
|
struct iphdr *iph;
|
|
__be16 df = 0;
|
|
__u8 ttl;
|
|
|
|
skb = __skb_dequeue(queue);
|
|
if (!skb)
|
|
goto out;
|
|
tail_skb = &(skb_shinfo(skb)->frag_list);
|
|
|
|
/* move skb->data to ip header from ext header */
|
|
if (skb->data < skb_network_header(skb))
|
|
__skb_pull(skb, skb_network_offset(skb));
|
|
while ((tmp_skb = __skb_dequeue(queue)) != NULL) {
|
|
__skb_pull(tmp_skb, skb_network_header_len(skb));
|
|
*tail_skb = tmp_skb;
|
|
tail_skb = &(tmp_skb->next);
|
|
skb->len += tmp_skb->len;
|
|
skb->data_len += tmp_skb->len;
|
|
skb->truesize += tmp_skb->truesize;
|
|
tmp_skb->destructor = NULL;
|
|
tmp_skb->sk = NULL;
|
|
}
|
|
|
|
/* Unless user demanded real pmtu discovery (IP_PMTUDISC_DO), we allow
|
|
* to fragment the frame generated here. No matter, what transforms
|
|
* how transforms change size of the packet, it will come out.
|
|
*/
|
|
skb->ignore_df = ip_sk_ignore_df(sk);
|
|
|
|
/* DF bit is set when we want to see DF on outgoing frames.
|
|
* If ignore_df is set too, we still allow to fragment this frame
|
|
* locally. */
|
|
if (inet->pmtudisc == IP_PMTUDISC_DO ||
|
|
inet->pmtudisc == IP_PMTUDISC_PROBE ||
|
|
(skb->len <= dst_mtu(&rt->dst) &&
|
|
ip_dont_fragment(sk, &rt->dst)))
|
|
df = htons(IP_DF);
|
|
|
|
if (cork->flags & IPCORK_OPT)
|
|
opt = cork->opt;
|
|
|
|
if (cork->ttl != 0)
|
|
ttl = cork->ttl;
|
|
else if (rt->rt_type == RTN_MULTICAST)
|
|
ttl = inet->mc_ttl;
|
|
else
|
|
ttl = ip_select_ttl(inet, &rt->dst);
|
|
|
|
iph = ip_hdr(skb);
|
|
iph->version = 4;
|
|
iph->ihl = 5;
|
|
iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;
|
|
iph->frag_off = df;
|
|
iph->ttl = ttl;
|
|
iph->protocol = sk->sk_protocol;
|
|
ip_copy_addrs(iph, fl4);
|
|
ip_select_ident(net, skb, sk);
|
|
|
|
if (opt) {
|
|
iph->ihl += opt->optlen >> 2;
|
|
ip_options_build(skb, opt, cork->addr, rt, 0);
|
|
}
|
|
|
|
skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
|
|
skb->mark = cork->mark;
|
|
skb->tstamp = cork->transmit_time;
|
|
/*
|
|
* Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
|
|
* on dst refcount
|
|
*/
|
|
cork->dst = NULL;
|
|
skb_dst_set(skb, &rt->dst);
|
|
|
|
if (iph->protocol == IPPROTO_ICMP)
|
|
icmp_out_count(net, ((struct icmphdr *)
|
|
skb_transport_header(skb))->type);
|
|
|
|
ip_cork_release(cork);
|
|
out:
|
|
return skb;
|
|
}
|
|
|
|
int ip_send_skb(struct net *net, struct sk_buff *skb)
|
|
{
|
|
int err;
|
|
|
|
err = ip_local_out(net, skb->sk, skb);
|
|
if (err) {
|
|
if (err > 0)
|
|
err = net_xmit_errno(err);
|
|
if (err)
|
|
IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
|
|
}
|
|
|
|
return err;
|
|
}
|
|
|
|
int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4)
|
|
{
|
|
struct sk_buff *skb;
|
|
|
|
skb = ip_finish_skb(sk, fl4);
|
|
if (!skb)
|
|
return 0;
|
|
|
|
/* Netfilter gets whole the not fragmented skb. */
|
|
return ip_send_skb(sock_net(sk), skb);
|
|
}
|
|
|
|
/*
|
|
* Throw away all pending data on the socket.
|
|
*/
|
|
static void __ip_flush_pending_frames(struct sock *sk,
|
|
struct sk_buff_head *queue,
|
|
struct inet_cork *cork)
|
|
{
|
|
struct sk_buff *skb;
|
|
|
|
while ((skb = __skb_dequeue_tail(queue)) != NULL)
|
|
kfree_skb(skb);
|
|
|
|
ip_cork_release(cork);
|
|
}
|
|
|
|
void ip_flush_pending_frames(struct sock *sk)
|
|
{
|
|
__ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
|
|
}
|
|
|
|
struct sk_buff *ip_make_skb(struct sock *sk,
|
|
struct flowi4 *fl4,
|
|
int getfrag(void *from, char *to, int offset,
|
|
int len, int odd, struct sk_buff *skb),
|
|
void *from, int length, int transhdrlen,
|
|
struct ipcm_cookie *ipc, struct rtable **rtp,
|
|
struct inet_cork *cork, unsigned int flags)
|
|
{
|
|
struct sk_buff_head queue;
|
|
int err;
|
|
|
|
if (flags & MSG_PROBE)
|
|
return NULL;
|
|
|
|
__skb_queue_head_init(&queue);
|
|
|
|
cork->flags = 0;
|
|
cork->addr = 0;
|
|
cork->opt = NULL;
|
|
err = ip_setup_cork(sk, cork, ipc, rtp);
|
|
if (err)
|
|
return ERR_PTR(err);
|
|
|
|
err = __ip_append_data(sk, fl4, &queue, cork,
|
|
¤t->task_frag, getfrag,
|
|
from, length, transhdrlen, flags);
|
|
if (err) {
|
|
__ip_flush_pending_frames(sk, &queue, cork);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
return __ip_make_skb(sk, fl4, &queue, cork);
|
|
}
|
|
|
|
/*
|
|
* Fetch data from kernel space and fill in checksum if needed.
|
|
*/
|
|
static int ip_reply_glue_bits(void *dptr, char *to, int offset,
|
|
int len, int odd, struct sk_buff *skb)
|
|
{
|
|
__wsum csum;
|
|
|
|
csum = csum_partial_copy_nocheck(dptr+offset, to, len);
|
|
skb->csum = csum_block_add(skb->csum, csum, odd);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Generic function to send a packet as reply to another packet.
|
|
* Used to send some TCP resets/acks so far.
|
|
*/
|
|
void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
|
|
const struct ip_options *sopt,
|
|
__be32 daddr, __be32 saddr,
|
|
const struct ip_reply_arg *arg,
|
|
unsigned int len, u64 transmit_time)
|
|
{
|
|
struct ip_options_data replyopts;
|
|
struct ipcm_cookie ipc;
|
|
struct flowi4 fl4;
|
|
struct rtable *rt = skb_rtable(skb);
|
|
struct net *net = sock_net(sk);
|
|
struct sk_buff *nskb;
|
|
int err;
|
|
int oif;
|
|
|
|
if (__ip_options_echo(net, &replyopts.opt.opt, skb, sopt))
|
|
return;
|
|
|
|
ipcm_init(&ipc);
|
|
ipc.addr = daddr;
|
|
ipc.sockc.transmit_time = transmit_time;
|
|
|
|
if (replyopts.opt.opt.optlen) {
|
|
ipc.opt = &replyopts.opt;
|
|
|
|
if (replyopts.opt.opt.srr)
|
|
daddr = replyopts.opt.opt.faddr;
|
|
}
|
|
|
|
oif = arg->bound_dev_if;
|
|
if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
|
|
oif = skb->skb_iif;
|
|
|
|
flowi4_init_output(&fl4, oif,
|
|
IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark,
|
|
RT_TOS(arg->tos),
|
|
RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
|
|
ip_reply_arg_flowi_flags(arg),
|
|
daddr, saddr,
|
|
tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
|
|
arg->uid);
|
|
security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
|
|
rt = ip_route_output_key(net, &fl4);
|
|
if (IS_ERR(rt))
|
|
return;
|
|
|
|
inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK;
|
|
|
|
sk->sk_protocol = ip_hdr(skb)->protocol;
|
|
sk->sk_bound_dev_if = arg->bound_dev_if;
|
|
sk->sk_sndbuf = sysctl_wmem_default;
|
|
ipc.sockc.mark = fl4.flowi4_mark;
|
|
err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
|
|
len, 0, &ipc, &rt, MSG_DONTWAIT);
|
|
if (unlikely(err)) {
|
|
ip_flush_pending_frames(sk);
|
|
goto out;
|
|
}
|
|
|
|
nskb = skb_peek(&sk->sk_write_queue);
|
|
if (nskb) {
|
|
if (arg->csumoffset >= 0)
|
|
*((__sum16 *)skb_transport_header(nskb) +
|
|
arg->csumoffset) = csum_fold(csum_add(nskb->csum,
|
|
arg->csum));
|
|
nskb->ip_summed = CHECKSUM_NONE;
|
|
ip_push_pending_frames(sk, &fl4);
|
|
}
|
|
out:
|
|
ip_rt_put(rt);
|
|
}
|
|
|
|
void __init ip_init(void)
|
|
{
|
|
ip_rt_init();
|
|
inet_initpeers();
|
|
|
|
#if defined(CONFIG_IP_MULTICAST)
|
|
igmp_mc_init();
|
|
#endif
|
|
}
|