zte's code,first commit
Change-Id: I9a04da59e459a9bc0d67f101f700d9d7dc8d681b
diff --git a/ap/os/linux/linux-3.4.x/net/ipv4/ip_output.c b/ap/os/linux/linux-3.4.x/net/ipv4/ip_output.c
new file mode 100755
index 0000000..166bc0c
--- /dev/null
+++ b/ap/os/linux/linux-3.4.x/net/ipv4/ip_output.c
@@ -0,0 +1,1584 @@
+/*
+ * 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 readibility.
+ * 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 <asm/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 <linux/igmp.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_bridge.h>
+#include <linux/mroute.h>
+#include <linux/netlink.h>
+#include <linux/tcp.h>
+
+#include <net/SI/fast_common.h>
+
+
+int sysctl_ip_default_ttl __read_mostly = IPDEFTTL;
+EXPORT_SYMBOL(sysctl_ip_default_ttl);
+
+/* Generate a checksum for an outgoing IP datagram. */
+__inline__ 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 sk_buff *skb)
+{
+ struct iphdr *iph = ip_hdr(skb);
+
+ iph->tot_len = htons(skb->len);
+ ip_send_check(iph);
+ return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL,
+ skb_dst(skb)->dev, dst_output);
+}
+
+int ip_local_out(struct sk_buff *skb)
+{
+ int err;
+
+ err = __ip_local_out(skb);
+ if (likely(err == 1))
+ err = dst_output(skb);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(ip_local_out);
+
+/* dev_loopback_xmit for use with netfilter. */
+static int ip_dev_loopback_xmit(struct sk_buff *newskb)
+{
+ skb_reset_mac_header(newskb);
+ __skb_pull(newskb, skb_network_offset(newskb));
+ newskb->pkt_type = PACKET_LOOPBACK;
+ newskb->ip_summed = CHECKSUM_UNNECESSARY;
+ WARN_ON(!skb_dst(newskb));
+ skb_dst_force(newskb);
+ netif_rx_ni(newskb);
+ return 0;
+}
+
+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, struct sock *sk,
+ __be32 saddr, __be32 daddr, struct ip_options_rcu *opt)
+{
+ struct inet_sock *inet = inet_sk(sk);
+ struct rtable *rt = skb_rtable(skb);
+ 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 = inet->tos;
+ if (ip_dont_fragment(sk, &rt->dst))
+ iph->frag_off = htons(IP_DF);
+ else
+ iph->frag_off = 0;
+ 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;
+ ip_select_ident(skb, sk);
+
+ 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;
+ skb->mark = sk->sk_mark;
+
+ /* Send it out. */
+ return ip_local_out(skb);
+}
+EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
+
+static inline int ip_finish_output2(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;
+
+ if (rt->rt_type == RTN_MULTICAST) {
+ IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTMCAST, skb->len);
+ } else if (rt->rt_type == RTN_BROADCAST)
+ IP_UPD_PO_STATS(dev_net(dev), 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 == NULL) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+ if (skb->sk)
+ skb_set_owner_w(skb2, skb->sk);
+ kfree_skb(skb);
+ skb = skb2;
+ }
+
+ rcu_read_lock();
+ neigh = dst_get_neighbour_noref(dst);
+ if (neigh) {
+ int res = neigh_output(neigh, skb);
+
+ rcu_read_unlock();
+ return res;
+ }
+ rcu_read_unlock();
+
+ if (net_ratelimit())
+ printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n");
+ kfree_skb(skb);
+ return -EINVAL;
+}
+
+static inline int ip_skb_dst_mtu(struct sk_buff *skb)
+{
+ struct inet_sock *inet = skb->sk ? inet_sk(skb->sk) : NULL;
+
+ return (inet && inet->pmtudisc == IP_PMTUDISC_PROBE) ?
+ skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
+}
+
+static int ip_finish_output(struct sk_buff *skb)
+{
+#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
+ /* Policy lookup after SNAT yielded a new policy */
+ if (skb_dst(skb)->xfrm != NULL) {
+ IPCB(skb)->flags |= IPSKB_REROUTED;
+ return dst_output(skb);
+ }
+#endif
+ if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb))
+ return ip_fragment(skb, ip_finish_output2);
+ else
+ return ip_finish_output2(skb);
+}
+
+int ip_mc_output(struct sk_buff *skb)
+{
+ struct sock *sk = skb->sk;
+ 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(dev_net(dev), 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,
+ newskb, NULL, newskb->dev,
+ ip_dev_loopback_xmit);
+ }
+
+ /* 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, newskb,
+ NULL, newskb->dev, ip_dev_loopback_xmit);
+ }
+
+ return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL,
+ skb->dev, ip_finish_output,
+ !(IPCB(skb)->flags & IPSKB_REROUTED));
+}
+
+int ip_output(struct sk_buff *skb)
+{
+ struct net_device *dev = skb_dst(skb)->dev;
+
+ IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len);
+
+ skb->dev = dev;
+ skb->protocol = htons(ETH_P_IP);
+
+ return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL, dev,
+ ip_finish_output,
+ !(IPCB(skb)->flags & IPSKB_REROUTED));
+}
+
+/*
+ * 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));
+}
+
+extern int fast_local4_output_num;
+
+int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
+{
+ struct sock *sk = skb->sk;
+ struct inet_sock *inet = inet_sk(sk);
+ struct ip_options_rcu *inet_opt;
+ struct flowi4 *fl4;
+ struct rtable *rt;
+ struct iphdr *iph;
+ int res;
+ int fast_flag = 0;
+ struct nf_conn *ct;
+
+ /* 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 != NULL)
+ goto packet_routed;
+
+ /* Make sure we can route this packet. */
+ rt = (struct rtable *)__sk_dst_check(sk, 0);
+ if (rt == NULL) {
+ __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(sock_net(sk), fl4, sk,
+ daddr, inet->inet_saddr,
+ inet->inet_dport,
+ inet->inet_sport,
+ sk->sk_protocol,
+ RT_CONN_FLAGS(sk),
+ 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 && fl4->daddr != rt->rt_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) | (inet->tos & 0xff));
+ if (ip_dont_fragment(sk, &rt->dst) && !skb->local_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(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
+
+ skb->priority = sk->sk_priority;
+ skb->mark = sk->sk_mark;
+
+ //Èç¹ûÒѾ·¢Ëͳ¬¹ýãÐÖµÁË£¬Ö±½Ó¿ìËÙÌí¼ÓMACÍ·£¬Ìø¹ýËùÓеÄIP²ãHOOK¹³×Óº¯Êý
+ if (fast_local4_output_proc && fast_local4_output_proc(skb))
+ {
+ fast_local4_output_num++;
+ res = ip_finish_output(skb);
+ }
+ else
+ {
+ sk->sk_send_sum++;
+ res = ip_local_out(skb);
+ }
+
+ rcu_read_unlock();
+ return res;
+
+no_route:
+ rcu_read_unlock();
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+ kfree_skb(skb);
+ return -EHOSTUNREACH;
+}
+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;
+ skb_dst_drop(to);
+ skb_dst_copy(to, from);
+ to->dev = from->dev;
+ to->mark = from->mark;
+
+ /* Copy the flags to each fragment. */
+ IPCB(to)->flags = IPCB(from)->flags;
+
+#ifdef CONFIG_NET_SCHED
+ to->tc_index = from->tc_index;
+#endif
+ nf_copy(to, from);
+#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
+ defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+ to->nf_trace = from->nf_trace;
+#endif
+#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
+ to->ipvs_property = from->ipvs_property;
+#endif
+ skb_copy_secmark(to, from);
+}
+
+/*
+ * 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_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
+{
+ struct iphdr *iph;
+ int ptr;
+ struct net_device *dev;
+ struct sk_buff *skb2;
+ unsigned int mtu, hlen, left, len, ll_rs;
+ int offset;
+ __be16 not_last_frag;
+ struct rtable *rt = skb_rtable(skb);
+ int err = 0;
+
+ dev = rt->dst.dev;
+
+ /*
+ * Point into the IP datagram header.
+ */
+
+ iph = ip_hdr(skb);
+
+ if (unlikely((iph->frag_off & htons(IP_DF)) && !skb->local_df)) {
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(ip_skb_dst_mtu(skb)));
+ kfree_skb(skb);
+ return -EMSGSIZE;
+ }
+
+ /*
+ * Setup starting values.
+ */
+
+ hlen = iph->ihl * 4;
+ mtu = dst_mtu(&rt->dst) - hlen; /* Size of data space */
+#ifdef CONFIG_BRIDGE_NETFILTER
+ if (skb->nf_bridge)
+ mtu -= nf_bridge_mtu_reduction(skb);
+#endif
+ IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE;
+
+ /* 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;
+ int first_len = skb_pagelen(skb);
+
+ if (first_len - hlen > mtu ||
+ ((first_len - hlen) & 7) ||
+ ip_is_fragment(iph) ||
+ skb_cloned(skb))
+ goto slow_path;
+
+ skb_walk_frags(skb, frag) {
+ /* Correct geometry. */
+ if (frag->len > mtu ||
+ ((frag->len & 7) && frag->next) ||
+ skb_headroom(frag) < hlen)
+ 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! */
+
+ err = 0;
+ offset = 0;
+ frag = skb_shinfo(skb)->frag_list;
+ skb_frag_list_init(skb);
+ 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);
+
+ for (;;) {
+ /* Prepare header of the next frame,
+ * before previous one went down. */
+ if (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);
+ iph = ip_hdr(frag);
+ iph->tot_len = htons(frag->len);
+ ip_copy_metadata(frag, skb);
+ if (offset == 0)
+ ip_options_fragment(frag);
+ offset += skb->len - hlen;
+ iph->frag_off = htons(offset>>3);
+ if (frag->next != NULL)
+ iph->frag_off |= htons(IP_MF);
+ /* Ready, complete checksum */
+ ip_send_check(iph);
+ }
+ net_run_track(PRT_FRAGMENT, "ip_fragment!\n");
+ err = output(skb);
+
+ if (!err)
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES);
+ if (err || !frag)
+ break;
+
+ skb = frag;
+ frag = skb->next;
+ skb->next = NULL;
+ }
+
+ if (err == 0) {
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS);
+ return 0;
+ }
+
+ while (frag) {
+ skb = frag->next;
+ kfree_skb(frag);
+ frag = skb;
+ }
+ IP_INC_STATS(dev_net(dev), 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:
+ left = skb->len - hlen; /* Space per frame */
+ ptr = hlen; /* Where to start from */
+
+ /* for bridged IP traffic encapsulated inside f.e. a vlan header,
+ * we need to make room for the encapsulating header
+ */
+ ll_rs = LL_RESERVED_SPACE_EXTRA(rt->dst.dev, nf_bridge_pad(skb));
+
+ /*
+ * Fragment the datagram.
+ */
+
+ offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
+ not_last_frag = iph->frag_off & htons(IP_MF);
+
+ /*
+ * Keep copying data until we run out.
+ */
+
+ while (left > 0) {
+ len = left;
+ /* IF: it doesn't fit, use 'mtu' - the data space left */
+ if (len > mtu)
+ len = 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 < left) {
+ len &= ~7;
+ }
+ /*
+ * Allocate buffer.
+ */
+
+ if ((skb2 = alloc_skb(len+hlen+ll_rs, GFP_ATOMIC)) == NULL) {
+ NETDEBUG(KERN_INFO "IP: frag: no memory for new fragment!\n");
+ err = -ENOMEM;
+ goto fail;
+ }
+
+ /*
+ * Set up data on packet
+ */
+
+ ip_copy_metadata(skb2, skb);
+ skb_reserve(skb2, ll_rs);
+ skb_put(skb2, len + hlen);
+ skb_reset_network_header(skb2);
+ skb2->transport_header = skb2->network_header + 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), hlen);
+
+ /*
+ * Copy a block of the IP datagram.
+ */
+ if (skb_copy_bits(skb, ptr, skb_transport_header(skb2), len))
+ BUG();
+ left -= len;
+
+ /*
+ * Fill in the new header fields.
+ */
+ iph = ip_hdr(skb2);
+ iph->frag_off = htons((offset >> 3));
+
+ /* 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 (offset == 0)
+ ip_options_fragment(skb);
+
+ /*
+ * Added AC : If we are fragmenting a fragment that's not the
+ * last fragment then keep MF on each bit
+ */
+ if (left > 0 || not_last_frag)
+ iph->frag_off |= htons(IP_MF);
+ ptr += len;
+ offset += len;
+
+ /*
+ * Put this fragment into the sending queue.
+ */
+ iph->tot_len = htons(len + hlen);
+
+ ip_send_check(iph);
+
+ net_run_track(PRT_FRAGMENT, "ip_fragment slow path!\n");
+ err = output(skb2);
+ if (err)
+ goto fail;
+
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES);
+ }
+ kfree_skb(skb);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS);
+ return err;
+
+fail:
+ kfree_skb(skb);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+ return err;
+}
+EXPORT_SYMBOL(ip_fragment);
+
+int
+ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
+{
+ struct iovec *iov = from;
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ if (memcpy_fromiovecend(to, iov, offset, len) < 0)
+ return -EFAULT;
+ } else {
+ __wsum csum = 0;
+ if (csum_partial_copy_fromiovecend(to, iov, offset, len, &csum) < 0)
+ 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 inline int ip_ufo_append_data(struct sock *sk,
+ struct sk_buff_head *queue,
+ int getfrag(void *from, char *to, int offset, int len,
+ int odd, struct sk_buff *skb),
+ void *from, int length, int hh_len, int fragheaderlen,
+ int transhdrlen, int maxfraglen, unsigned int flags)
+{
+ struct sk_buff *skb;
+ int err;
+
+ /* There is support for UDP fragmentation offload by network
+ * device, so create one single skb packet containing complete
+ * udp datagram
+ */
+ if ((skb = skb_peek_tail(queue)) == NULL) {
+ skb = sock_alloc_send_skb(sk,
+ hh_len + fragheaderlen + transhdrlen + 20,
+ (flags & MSG_DONTWAIT), &err);
+
+ if (skb == NULL)
+ return err;
+
+ /* reserve space for Hardware header */
+ skb_reserve(skb, hh_len);
+
+ /* create space for UDP/IP header */
+ skb_put(skb, fragheaderlen + transhdrlen);
+
+ /* initialize network header pointer */
+ skb_reset_network_header(skb);
+
+ /* initialize protocol header pointer */
+ skb->transport_header = skb->network_header + fragheaderlen;
+
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ skb->csum = 0;
+
+ /* specify the length of each IP datagram fragment */
+ skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+ __skb_queue_tail(queue, skb);
+ }
+
+ return skb_append_datato_frags(sk, skb, getfrag, from,
+ (length - transhdrlen));
+}
+
+static int __ip_append_data(struct sock *sk,
+ struct flowi4 *fl4,
+ struct sk_buff_head *queue,
+ struct inet_cork *cork,
+ 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 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;
+ int csummode = CHECKSUM_NONE;
+ struct rtable *rt = (struct rtable *)cork->dst;
+
+ skb = skb_peek_tail(queue);
+
+ exthdrlen = !skb ? rt->dst.header_len : 0;
+ mtu = cork->fragsize;
+
+ hh_len = LL_RESERVED_SPACE(rt->dst.dev);
+
+ fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
+ maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
+
+ if (cork->length + length > 0xFFFF - fragheaderlen) {
+ ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
+ mtu-exthdrlen);
+ 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_V4_CSUM &&
+ !exthdrlen)
+ csummode = CHECKSUM_PARTIAL;
+
+ cork->length += length;
+/*
+ if (((length > mtu) || (skb && skb_has_frags(skb))) &&
+ (sk->sk_protocol == IPPROTO_UDP) &&
+ (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) {
+*/
+ if ((skb && skb_is_gso(skb)) ||//CVE-2017-1000112
+ (((length > mtu) || (skb && skb_has_frags(skb))) &&
+ (sk->sk_protocol == IPPROTO_UDP) &&
+ (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len)) {
+ err = ip_ufo_append_data(sk, queue, getfrag, from, length,
+ hh_len, fragheaderlen, transhdrlen,
+ maxfraglen, flags);
+ if (err)
+ goto error;
+ return 0;
+ }
+
+ /* 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;
+ 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;
+
+ if ((flags & MSG_MORE) &&
+ !(rt->dst.dev->features&NETIF_F_SG))
+ alloclen = mtu;
+ else
+ alloclen = fraglen;
+
+ alloclen += 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)
+ alloclen += rt->dst.trailer_len;
+
+ if (transhdrlen) {
+ skb = sock_alloc_send_skb(sk,
+ alloclen + hh_len + 15,
+ (flags & MSG_DONTWAIT), &err);
+ } else {
+ skb = NULL;
+ if (atomic_read(&sk->sk_wmem_alloc) <=
+ 2 * sk->sk_sndbuf)
+ skb = sock_wmalloc(sk,
+ alloclen + hh_len + 15, 1,
+ sk->sk_allocation);
+ if (unlikely(skb == NULL))
+ err = -ENOBUFS;
+ else
+ /* only the initial fragment is
+ time stamped */
+ cork->tx_flags = 0;
+ }
+ if (skb == NULL)
+ goto error;
+
+ /*
+ * Fill in the control structures
+ */
+ skb->ip_summed = csummode;
+ skb->csum = 0;
+ skb_reserve(skb, hh_len);
+ skb_shinfo(skb)->tx_flags = cork->tx_flags;
+
+ /*
+ * Find where to start putting bytes.
+ */
+ data = skb_put(skb, fraglen + exthdrlen);
+ 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, 0);
+ skb_prev->csum = csum_sub(skb_prev->csum,
+ skb->csum);
+ data += fraggap;
+ pskb_trim_unique(skb_prev, maxfraglen);
+ }
+
+ copy = datalen - transhdrlen - fraggap;
+ if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
+ err = -EFAULT;
+ kfree_skb(skb);
+ goto error;
+ }
+
+ offset += copy;
+ length -= datalen - fraggap;
+ transhdrlen = 0;
+ exthdrlen = 0;
+ csummode = CHECKSUM_NONE;
+
+ /*
+ * Put the packet on the pending queue.
+ */
+ __skb_queue_tail(queue, skb);
+ continue;
+ }
+
+ if (copy > length)
+ copy = length;
+
+ if (!(rt->dst.dev->features&NETIF_F_SG)) {
+ 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 {
+ int i = skb_shinfo(skb)->nr_frags;
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
+ struct page *page = cork->page;
+ int off = cork->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, 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;
+ }
+ netslab_inc(IP_OUTPUT_ALLOC_PAGES);
+ cork->page = page;
+ cork->off = 0;
+
+ skb_fill_page_desc(skb, i, page, 0, 0);
+ frag = &skb_shinfo(skb)->frags[i];
+ } else {
+ err = -EMSGSIZE;
+ goto error;
+ }
+ if (getfrag(from, skb_frag_address(frag)+skb_frag_size(frag),
+ offset, copy, skb->len, skb) < 0) {
+ err = -EFAULT;
+ goto error;
+ }
+ cork->off += copy;
+ skb_frag_size_add(frag, copy);
+ skb->len += copy;
+ skb->data_len += copy;
+ skb->truesize += copy;
+ atomic_add(copy, &sk->sk_wmem_alloc);
+ }
+ offset += copy;
+ length -= copy;
+ }
+
+ return 0;
+
+error:
+ cork->length -= length;
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
+ return err;
+}
+
+static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
+ struct ipcm_cookie *ipc, struct rtable **rtp)
+{
+ struct inet_sock *inet = inet_sk(sk);
+ struct ip_options_rcu *opt;
+ struct rtable *rt;
+
+ /*
+ * setup for corking.
+ */
+ opt = ipc->opt;
+ if (opt) {
+ if (cork->opt == NULL) {
+ cork->opt = kmalloc(sizeof(struct ip_options) + 40,
+ sk->sk_allocation);
+ if (unlikely(cork->opt == NULL))
+ return -ENOBUFS;
+ }
+ memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen);
+ cork->flags |= IPCORK_OPT;
+ cork->addr = ipc->addr;
+ }
+ rt = *rtp;
+ if (unlikely(!rt))
+ return -EFAULT;
+ /*
+ * We steal reference to this route, caller should not release it
+ */
+ *rtp = NULL;
+ cork->fragsize = inet->pmtudisc == IP_PMTUDISC_PROBE ?
+ rt->dst.dev->mtu : dst_mtu(&rt->dst);
+ cork->dst = &rt->dst;
+ cork->length = 0;
+ cork->tx_flags = ipc->tx_flags;
+ cork->page = NULL;
+ cork->off = 0;
+
+ 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, 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;
+
+ 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->fragsize;
+
+ fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
+ maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
+
+ if (cork->length + size > 0xFFFF - fragheaderlen) {
+ ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu);
+ return -EMSGSIZE;
+ }
+
+ if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
+ return -EINVAL;
+
+ cork->length += size;
+ if ((size + skb->len > mtu) &&
+ (skb_queue_len(&sk->sk_write_queue) == 1) &&//CVE-2017-1000112
+ (sk->sk_protocol == IPPROTO_UDP) &&
+ (rt->dst.dev->features & NETIF_F_UFO)) {
+ skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+ }
+
+
+ while (size > 0) {
+ int i;
+
+ if (skb_is_gso(skb))
+ len = size;
+ else {
+
+ /* 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, 0);
+ 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;
+ }
+
+ i = skb_shinfo(skb)->nr_frags;
+ if (len > size)
+ len = size;
+ if (skb_can_coalesce(skb, i, page, offset)) {
+ skb_frag_size_add(&skb_shinfo(skb)->frags[i-1], len);
+ } else if (i < MAX_SKB_FRAGS) {
+ get_page(page);
+ skb_fill_page_desc(skb, i, page, offset, len);
+ } else {
+ 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;
+ atomic_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;
+
+ if ((skb = __skb_dequeue(queue)) == NULL)
+ 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.
+ */
+ if (inet->pmtudisc < IP_PMTUDISC_DO)
+ skb->local_df = 1;
+
+ /* DF bit is set when we want to see DF on outgoing frames.
+ * If local_df is set too, we still allow to fragment this frame
+ * locally. */
+ if (inet->pmtudisc >= IP_PMTUDISC_DO ||
+ (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 (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 = inet->tos;
+ iph->frag_off = df;
+ iph->ttl = ttl;
+ iph->protocol = sk->sk_protocol;
+ ip_copy_addrs(iph, fl4);
+ ip_select_ident(skb, sk);
+
+ if (opt) {
+ iph->ihl += opt->optlen>>2;
+ ip_options_build(skb, opt, cork->addr, rt, 0);
+ }
+
+ skb->priority = sk->sk_priority;
+ skb->mark = sk->sk_mark;
+ /*
+ * 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 sk_buff *skb)
+{
+ struct net *net = sock_net(skb->sk);
+ int err;
+
+ if (fast_local4_output_proc && fast_local4_output_proc(skb))
+ {
+ fast_local4_output_num++;
+ err = ip_finish_output(skb);
+ }
+ else
+ {
+ skb->sk->sk_send_sum++;
+ err = ip_local_out(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(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,
+ unsigned int flags)
+{
+ struct inet_cork cork;
+ 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, 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, 0);
+ 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 TCP resets so far. ICMP should use this function too.
+ *
+ * Should run single threaded per socket because it uses the sock
+ * structure to pass arguments.
+ */
+void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
+ const struct ip_reply_arg *arg, unsigned int len)
+{
+ struct inet_sock *inet = inet_sk(sk);
+ struct ip_options_data replyopts;
+ struct ipcm_cookie ipc;
+ struct flowi4 fl4;
+ struct rtable *rt = skb_rtable(skb);
+
+ if (ip_options_echo(&replyopts.opt.opt, skb))
+ return;
+
+ ipc.addr = daddr;
+ ipc.opt = NULL;
+ ipc.tx_flags = 0;
+
+ if (replyopts.opt.opt.optlen) {
+ ipc.opt = &replyopts.opt;
+
+ if (replyopts.opt.opt.srr)
+ daddr = replyopts.opt.opt.faddr;
+ }
+
+ flowi4_init_output(&fl4, arg->bound_dev_if, 0,
+ RT_TOS(arg->tos),
+ RT_SCOPE_UNIVERSE, sk->sk_protocol,
+ ip_reply_arg_flowi_flags(arg),
+ daddr, rt->rt_spec_dst,
+ tcp_hdr(skb)->source, tcp_hdr(skb)->dest);
+ security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+ rt = ip_route_output_key(sock_net(sk), &fl4);
+ if (IS_ERR(rt))
+ return;
+
+ /* And let IP do all the hard work.
+
+ This chunk is not reenterable, hence spinlock.
+ Note that it uses the fact, that this function is called
+ with locally disabled BH and that sk cannot be already spinlocked.
+ */
+ bh_lock_sock(sk);
+ inet->tos = arg->tos;
+ sk->sk_priority = skb->priority;
+ sk->sk_protocol = ip_hdr(skb)->protocol;
+ sk->sk_bound_dev_if = arg->bound_dev_if;
+ ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0,
+ &ipc, &rt, MSG_DONTWAIT);
+ if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) {
+ if (arg->csumoffset >= 0)
+ *((__sum16 *)skb_transport_header(skb) +
+ arg->csumoffset) = csum_fold(csum_add(skb->csum,
+ arg->csum));
+ skb->ip_summed = CHECKSUM_NONE;
+ ip_push_pending_frames(sk, &fl4);
+ }
+
+ bh_unlock_sock(sk);
+
+ ip_rt_put(rt);
+}
+
+void __init ip_init(void)
+{
+ ip_rt_init();
+ inet_initpeers();
+
+#if defined(CONFIG_IP_MULTICAST) && defined(CONFIG_PROC_FS)
+ igmp_mc_proc_init();
+#endif
+}