cregit-Linux how code gets into the kernel

Release 4.11 net/ipv4/ip_output.c

Directory: net/ipv4
/*
 * 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 <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/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);
}

Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)34100.00%1100.00%


Total34100.00%1100.00%




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);
}


Contributors
PersonTokensPropCommitsCommitProp
Herbert Xu4746.53%19.09%


David Ahern2120.79%19.09%


David S. Miller109.90%19.09%


Eli Cooper98.91%19.09%


Eric W. Biedermann98.91%436.36%


Eric Dumazet32.97%19.09%


Jan Engelhardt10.99%19.09%


Patrick McHardy10.99%19.09%


Total101100.00%11100.00%






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;
}

Contributors
PersonTokensPropCommitsCommitProp
Herbert Xu3663.16%111.11%


Eric W. Biedermann1424.56%777.78%


Eric Dumazet712.28%111.11%


Total57100.00%9100.00%




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;
}


Contributors
PersonTokensPropCommitsCommitProp
David S. Miller3997.50%266.67%


Arnaldo Carvalho de Melo12.50%133.33%


Total40100.00%3100.00%



/*
 *              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)
{
	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      = inet->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;
	skb->mark = sk->sk_mark;

	/* Send it out. */
	return ip_local_out(net, skb->sk, skb);
}

Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)14149.65%1035.71%


Eric Dumazet5519.37%310.71%


David S. Miller3512.32%310.71%


Arnaldo Carvalho de Melo175.99%414.29%


Eric W. Biedermann175.99%310.71%


Tóth László Attila82.82%13.57%


Alexey Kuznetsov72.46%13.57%


Al Viro20.70%13.57%


Herbert Xu10.35%13.57%


Hannes Frederic Sowa10.35%13.57%


Total284100.00%28100.00%




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;
	u32 nexthop;

	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();
	nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
	neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
	if (unlikely(!neigh))
		neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
	if (!IS_ERR(neigh)) {
		int res;

		sock_confirm_neigh(skb, neigh);
		res = neigh_output(neigh, skb);

		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;
}


Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov8927.38%27.14%


David S. Miller6219.08%621.43%


Linus Torvalds (pre-git)3711.38%310.71%


Mitsuru Chinen3510.77%13.57%


Roopa Prabhu329.85%13.57%


Julian Anastasov206.15%310.71%


Eric Dumazet164.92%310.71%


Neil Horman144.31%13.57%


Eric W. Biedermann72.15%27.14%


Vasiliy Kulikov41.23%13.57%


Joe Perches41.23%13.57%


Pavel Emelyanov20.62%13.57%


Chuck Lever10.31%13.57%


Ian Morris10.31%13.57%


Stephen Hemminger10.31%13.57%


Total325100.00%28100.00%






static int ip_finish_output_gso(struct net *net, struct sock *sk,
				struct sk_buff *skb, unsigned int mtu)
{
	netdev_features_t features;
	struct sk_buff *segs;
	int ret = 0;

	/* common case: seglen is <= mtu
         */
	if (skb_gso_validate_mtu(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
         *    insufficent MTU.
         */
	features = netif_skb_features(skb);
	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_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);

	do {
		struct sk_buff *nskb = segs->next;
		int err;

		segs->next = NULL;
		err = ip_fragment(net, sk, segs, mtu, ip_finish_output2);

		if (err && ret == 0)
			ret = err;
		segs = nskb;
	} while (segs);

	return ret;
}


Contributors
PersonTokensPropCommitsCommitProp
Florian Westphal13878.86%333.33%


Konstantin Khlebnikov148.00%111.11%


David S. Miller95.14%111.11%


Eric W. Biedermann95.14%111.11%


Marcelo Ricardo Leitner31.71%111.11%


Lance Richardson21.14%222.22%


Total175100.00%9100.00%






static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	unsigned int mtu;
	int ret;

	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
	if (ret) {
		kfree_skb(skb);
		return ret;
	}

#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)->flags & IPSKB_FRAG_PMTU))
		return ip_fragment(net, sk, skb, mtu, ip_finish_output2);

	return ip_finish_output2(net, sk, skb);
}


Contributors
PersonTokensPropCommitsCommitProp
Patrick McHardy4828.92%317.65%


Florian Westphal4024.10%317.65%


Daniel Mack2615.66%15.88%


Linus Torvalds (pre-git)1911.45%211.76%


Eric W. Biedermann148.43%423.53%


David S. Miller137.83%15.88%


Eric Dumazet31.81%15.88%


Shmulik Ladkani21.20%15.88%


Adrian Bunk10.60%15.88%


Total166100.00%17100.00%






static int ip_mc_finish_output(struct net *net, struct sock *sk,
			       struct sk_buff *skb)
{
	int ret;

	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
	if (ret) {
		kfree_skb(skb);
		return ret;
	}

	return dev_loopback_xmit(net, sk, skb);
}


Contributors
PersonTokensPropCommitsCommitProp
Daniel Mack57100.00%1100.00%


Total57100.00%1100.00%






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));
}


Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)17267.19%931.03%


Patrick McHardy249.38%310.34%


Eric W. Biedermann155.86%310.34%


Eric Dumazet83.12%26.90%


David S. Miller83.12%26.90%


Linus Torvalds83.12%13.45%


Neil Horman51.95%13.45%


Alexey Kuznetsov41.56%13.45%


Arnaldo Carvalho de Melo31.17%13.45%


Jan Engelhardt31.17%13.45%


Daniel Mack20.78%13.45%


Pavel Emelyanov10.39%13.45%


Herbert Xu10.39%13.45%


Octavian Purdila10.39%13.45%


Hideaki Yoshifuji / 吉藤英明10.39%13.45%


Total256100.00%29100.00%






int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct net_device *dev = skb_dst(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, NULL, dev,
			    ip_finish_output,
			    !(IPCB(skb)->flags & IPSKB_REROUTED));
}


Contributors
PersonTokensPropCommitsCommitProp
Patrick McHardy3842.22%316.67%


Linus Torvalds (pre-git)1516.67%316.67%


Eric W. Biedermann1011.11%316.67%


Eric Dumazet88.89%211.11%


Alexey Kuznetsov77.78%15.56%


Neil Horman55.56%15.56%


David S. Miller22.22%15.56%


Ananda Raju22.22%15.56%


Herbert Xu11.11%15.56%


Pavel Emelyanov11.11%15.56%


Jan Engelhardt11.11%15.56%


Total90100.00%18100.00%



/*
 * 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));
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Dumazet76100.00%1100.00%


Total76100.00%1100.00%



/* 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)
{
	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(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 && 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) | (inet->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;
}

Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov21243.80%35.45%


Eric Dumazet7315.08%814.55%


Linus Torvalds (pre-git)7114.67%59.09%


David S. Miller6112.60%1018.18%


Eric W. Biedermann183.72%47.27%


Arnaldo Carvalho de Melo163.31%59.09%


Tóth László Attila81.65%11.82%


Herbert Xu40.83%23.64%


Hideaki Yoshifuji / 吉藤英明30.62%23.64%


Shan Wei20.41%11.82%


Denis V. Lunev20.41%23.64%


Sridhar Samudrala20.41%11.82%


Venkat Yekkirala20.41%11.82%


Al Viro20.41%23.64%


Ian Morris10.21%11.82%


Américo Wang10.21%11.82%


Ansis Atteka10.21%11.82%


Linus Torvalds10.21%11.82%


Atis Elsts10.21%11.82%


Hannes Frederic Sowa10.21%11.82%


Pavel Emelyanov10.21%11.82%


Julian Anastasov10.21%11.82%


Total484100.00%55100.00%




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 IS_ENABLED(CONFIG_IP_VS)
	to->ipvs_property = from->ipvs_property;
#endif
	skb_copy_secmark(to, from);
}


Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov8265.08%19.09%


Julian Anastasov1411.11%19.09%


Thomas Graf86.35%19.09%


James Morris75.56%19.09%


Eric Dumazet53.97%218.18%


Patrick McHardy43.17%19.09%


Jozsef Kadlecsik32.38%218.18%


Yasuyuki Kozakai21.59%19.09%


Javier Martinez Canillas10.79%19.09%


Total126100.00%11100.00%






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);
}


Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov6743.79%214.29%


Florian Westphal2113.73%214.29%


Patrick McHardy1811.76%17.14%


Eric W. Biedermann149.15%214.29%


Andy Zhou138.50%17.14%


David S. Miller95.88%17.14%


Wei Dong53.27%17.14%


Eric Dumazet21.31%17.14%


Hannes Frederic Sowa21.31%17.14%


Pavel Emelyanov10.65%17.14%


Américo Wang10.65%17.14%


Total153100.00%14100.00%



/*
 *      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;
	int ptr;
	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;

	/* 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;

	/* 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))
			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)
					iph->frag_off |= htons(IP_MF);
				/* Ready, complete checksum */
				ip_send_check(iph);
			}

			err = output(net, sk, skb);

			if (!err)
				IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
			if (err || !frag)
				break;

			skb = frag;
			frag = skb->next;
			skb->next = NULL;
		}

		if (err == 0) {
			IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS);
			return 0;
		}

		while (frag) {
			skb = frag->next;
			kfree_skb(frag);
			frag = skb;
		}
		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:
	iph = ip_hdr(skb);

	left = skb->len - hlen;		/* Space per frame */
	ptr = hlen;		/* Where to start from */

	ll_rs = LL_RESERVED_SPACE(rt->dst.dev);

	/*
         *      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 */
		skb2 = alloc_skb(len + hlen + ll_rs, GFP_ATOMIC);
		if (!skb2) {
			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));

		if (IPCB(skb)->flags & IPSKB_FRAG_PMTU)
			iph->frag_off |= htons(IP_DF);

		/* 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);

		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;
}

Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov64463.39%12.70%


Andy Zhou908.86%12.70%


Florian Westphal484.72%25.41%


Herbert Xu484.72%410.81%


Eric Dumazet474.63%25.41%


Arnaldo Carvalho de Melo313.05%821.62%


Hannes Frederic Sowa222.17%25.41%


Eric W. Biedermann191.87%25.41%


Wei Dong151.48%12.70%


Bart De Schuymer111.08%12.70%


David S. Miller100.98%38.11%


Pravin B Shelar70.69%12.70%


Pavel Emelyanov60.59%12.70%


Joe Perches60.59%12.70%


Hideaki Yoshifuji / 吉藤英明40.39%12.70%


Paul Gortmaker20.20%12.70%


Shmulik Ladkani20.20%12.70%


Alexey Dobriyan10.10%12.70%


Stephen Hemminger10.10%12.70%


Patrick McHardy10.10%12.70%


Lucas De Marchi10.10%12.70%


Total1016100.00%37100.00%




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;
}

Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov9282.88%225.00%


Al Viro1816.22%562.50%


Patrick McHardy10.90%112.50%


Total111100.00%8100.00%




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;
}


Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov4075.47%111.11%


Linus Torvalds (pre-git)1120.75%777.78%


Al Viro23.77%111.11%


Total53100.00%9100.00%






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
         */
	skb = skb_peek_tail(queue);
	if (!skb) {
		skb = sock_alloc_send_skb(sk,
			hh_len + fragheaderlen + transhdrlen + 20,
			(flags & MSG_DONTWAIT), &err);

		if (!skb)
			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->csum = 0;

		if (flags & MSG_CONFIRM)
			skb_set_dst_pending_confirm(skb, 1);

		__skb_queue_tail(queue, skb);
	} else if (skb_is_gso(skb)) {
		goto append;
	}

	skb->ip_summed = CHECKSUM_PARTIAL;
	/* specify the length of each IP datagram fragment */
	skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
	skb_shinfo(skb)->gso_type = SKB_GSO_UDP;

append:
	return skb_append_datato_frags(sk, skb, getfrag, from,
				       (length - transhdrlen));
}


Contributors
PersonTokensPropCommitsCommitProp
Ananda Raju15764.88%18.33%


Jiri Pirko2711.16%18.33%


Herbert Xu166.61%325.00%


Kostya Belezko156.20%18.33%


Julian Anastasov135.37%18.33%


Ian Morris62.48%18.33%


Arnaldo Carvalho de Melo52.07%216.67%


Bill Sommerfeld20.83%18.33%


Adrian Bunk10.41%18.33%


Total242100.00%12100.00%






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 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;
	u32 tskey = 0;

	skb = skb_peek_tail(queue);

	exthdrlen = !skb ? rt->dst.header_len : 0;
	mtu = cork->fragsize;
	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) ? 0xFFFF : 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) &&
	    !exthdrlen)
		csummode = CHECKSUM_PARTIAL;

	cork->length += length;
	if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) &&
	    (sk->sk_protocol == IPPROTO_UDP) &&
	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
		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))
					err = -ENOBUFS;
			}
			if (!skb)
				goto error;

			/*
                         *      Fill in the control structures
                         */
			skb->ip_summed = csummode;
			skb->csum = 0;
			skb_reserve(skb, hh_len);

			/* 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;

			/*
                         *      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;

			if ((flags & MSG_CONFIRM) && !skb_prev)
				skb_set_dst_pending_confirm(skb, 1);

			/*
                         * 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;

			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;
			atomic_add(copy, &sk->sk_wmem_alloc);
		}
		offset += copy;
		length -= copy;
	}

	return 0;

error_efault:
	err = -EFAULT;
error:
	cork->length -= length;
	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
	return err;
}


Contributors
PersonTokensPropCommitsCommitProp
Herbert Xu51640.95%610.17%


Alexey Kuznetsov28522.62%46.78%


Linus Torvalds (pre-git)1159.13%1118.64%


Eric Dumazet967.62%46.78%


Willem de Bruijn463.65%23.39%


David S. Miller302.38%46.78%


Hannes Frederic Sowa292.30%46.78%


Hideaki Yoshifuji / 吉藤英明262.06%23.39%


Steffen Klassert221.75%35.08%


Julian Anastasov181.43%11.69%


Michal Kubeček131.03%23.39%


Ananda Raju131.03%11.69%


Krishna Kumar100.79%11.69%


John Heffner80.63%11.69%


Patrick McHardy70.56%23.39%


Tom Herbert50.40%11.69%


Alexey Kodanev40.32%11.69%


Julien Tinnes40.32%11.69%


Zheng Li40.32%11.69%


Ian Campbell20.16%11.69%


Ian Morris20.16%11.69%


Arnaldo Carvalho de Melo10.08%11.69%


Bill Sommerfeld10.08%11.69%


Américo Wang10.08%11.69%


Kostya Belezko10.08%11.69%


Linus Torvalds10.08%11.69%


Total1260100.00%59100.00%






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;

	/*
         * 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;
	}
	rt = *rtp;
	if (unlikely(!rt))
		return -EFAULT;
	/*
         * We steal reference to this route, caller should not release it
         */
	*rtp = NULL;
	cork->fragsize = ip_sk_use_pmtu(sk) ?
			 dst_mtu(&rt->dst) : rt->dst.dev->mtu;
	cork->dst = &rt->dst;
	cork->length = 0;
	cork->ttl = ipc->ttl;
	cork->tos = ipc->tos;
	cork->priority = ipc->priority;
	cork->tx_flags = ipc->tx_flags;

	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Herbert Xu18380.26%116.67%


Francesco Fusco2410.53%116.67%


Hannes Frederic Sowa125.26%116.67%


Eric Dumazet62.63%116.67%


Ian Morris20.88%116.67%


Steffen Klassert10.44%116.67%


Total228100.00%6100.00%



/*
 *      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);
}


Contributors
PersonTokensPropCommitsCommitProp
Herbert Xu13480.24%215.38%


David S. Miller116.59%215.38%


Linus Torvalds (pre-git)105.99%646.15%


Alexey Kuznetsov63.59%17.69%


Eric Dumazet52.99%17.69%


Pavel Emelyanov10.60%17.69%


Total167100.00%13100.00%






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->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;

	if ((size + skb->len > mtu) &&
	    (sk->sk_protocol == IPPROTO_UDP) &&
	    (rt->dst.dev->features & NETIF_F_UFO)) {
		if (skb->ip_summed != CHECKSUM_PARTIAL)
			return -EOPNOTSUPP;

		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
	}
	cork->length += size;

	while (size > 0) {
		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;
		}

		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;
		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;
}


Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov25835.59%23.85%


Linus Torvalds (pre-git)14520.00%1426.92%


David S. Miller10514.48%611.54%


Herbert Xu466.34%713.46%


Ananda Raju456.21%11.92%


Hannes Frederic Sowa446.07%59.62%


Hideaki Yoshifuji / 吉藤英明283.86%35.77%


Arnaldo Carvalho de Melo223.03%611.54%


Patrick McHardy162.21%11.92%


Pavel Emelyanov50.69%11.92%


Ian Morris50.69%11.92%


Eric Dumazet30.41%23.85%


Al Viro10.14%11.92%


Linus Torvalds10.14%11.92%


Américo Wang10.14%11.92%


Total725100.00%52100.00%






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;
}


Contributors
PersonTokensPropCommitsCommitProp
Pavel Emelyanov3477.27%133.33%


Herbert Xu715.91%133.33%


Hideaki Yoshifuji / 吉藤英明36.82%133.33%


Total44100.00%3100.00%



/*
 *      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 = 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;
}


Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov17533.59%36.98%


Linus Torvalds (pre-git)8015.36%716.28%


David S. Miller6412.28%49.30%


Francesco Fusco417.87%12.33%


Herbert Xu407.68%36.98%


David L Stevens254.80%12.33%


Eric Dumazet203.84%49.30%


Linus Torvalds142.69%49.30%


Hannes Frederic Sowa122.30%36.98%


Arnaldo Carvalho de Melo122.30%511.63%


Pavel Emelyanov122.30%12.33%


Tóth László Attila71.34%12.33%


Hideaki Yoshifuji / 吉藤英明61.15%12.33%


Ian Morris50.96%12.33%


Ansis Atteka40.77%24.65%


Américo Wang30.58%12.33%


Alexey Dobriyan10.19%12.33%


Total521100.00%43100.00%






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;
}


Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov2132.81%110.00%


Herbert Xu1726.56%220.00%


Linus Torvalds (pre-git)1218.75%220.00%


Eric W. Biedermann69.38%220.00%


Eric Dumazet57.81%110.00%


Pavel Emelyanov23.12%110.00%


Hideaki Yoshifuji / 吉藤英明11.56%110.00%


Total64100.00%10100.00%






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);
}


Contributors
PersonTokensPropCommitsCommitProp
Herbert Xu3775.51%250.00%


David S. Miller714.29%125.00%


Eric Dumazet510.20%125.00%


Total49100.00%4100.00%



/*
 *      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);
}


Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov2551.02%120.00%


Herbert Xu1734.69%120.00%


Linus Torvalds (pre-git)612.24%240.00%


Pavel Emelyanov12.04%120.00%


Total49100.00%5100.00%






void ip_flush_pending_frames(struct sock *sk)
{
	__ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
}


Contributors
PersonTokensPropCommitsCommitProp
Herbert Xu2170.00%120.00%


Alexey Kuznetsov310.00%120.00%


Pavel Emelyanov310.00%120.00%


David S. Miller26.67%120.00%


Linus Torvalds (pre-git)13.33%120.00%


Total30100.00%5100.00%






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,
			       &current->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);
}


Contributors
PersonTokensPropCommitsCommitProp
Herbert Xu17184.24%116.67%


David S. Miller2713.30%466.67%


Eric Dumazet52.46%116.67%


Total203100.00%6100.00%



/*
 *      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;
}


Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)4570.31%125.00%


Alexey Kuznetsov1828.12%250.00%


Al Viro11.56%125.00%


Total64100.00%4100.00%



/*
 *      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)
{
	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(&replyopts.opt.opt, skb, sopt))
		return;

	ipc.addr = daddr;
	ipc.opt = NULL;
	ipc.tx_flags = 0;
	ipc.ttl = 0;
	ipc.tos = -1;

	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),
			   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(&fl4));
	rt = ip_route_output_key(net, &fl4);
	if (IS_ERR(rt))
		return;

	inet_sk(sk)->tos = arg->tos;

	sk->sk_priority = skb->priority;
	sk->sk_protocol = ip_hdr(skb)->protocol;
	sk->sk_bound_dev_if = arg->bound_dev_if;
	sk->sk_sndbuf = sysctl_wmem_default;
	sk->sk_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);
}


Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)13729.91%817.39%


Eric Dumazet6714.63%715.22%


David S. Miller6313.76%919.57%


Alexey Kuznetsov6213.54%24.35%


David Ahern306.55%36.52%


Vasily Averin245.24%12.17%


Arnaldo Carvalho de Melo143.06%48.70%


Francesco Fusco132.84%12.17%


Lorenzo Colitti122.62%24.35%


Patrick McHardy81.75%12.17%


Pau Espin Pedrol81.75%12.17%


Venkat Yekkirala71.53%12.17%


Patrick Ohly51.09%12.17%


Changli Gao20.44%12.17%


Denis V. Lunev20.44%12.17%


KOVACS Krisztian20.44%12.17%


Al Viro10.22%12.17%


Oliver Hartkopp10.22%12.17%


Total458100.00%46100.00%






void __init ip_init(void)
{
	ip_rt_init();
	inet_initpeers();

#if defined(CONFIG_IP_MULTICAST)
	igmp_mc_init();
#endif
}

Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)1664.00%555.56%


Stephen Hemminger520.00%111.11%


David L Stevens28.00%111.11%


Américo Wang14.00%111.11%


Hideaki Yoshifuji / 吉藤英明14.00%111.11%


Total25100.00%9100.00%




Overall Contributors
PersonTokensPropCommitsCommitProp
Alexey Kuznetsov209926.49%72.30%


Herbert Xu134817.01%196.23%


Linus Torvalds (pre-git)115214.54%3310.82%


David S. Miller5677.15%3812.46%


Eric Dumazet5336.73%268.52%


Florian Westphal2513.17%51.64%


Ananda Raju2172.74%10.33%


Patrick McHardy1732.18%134.26%


Eric W. Biedermann1622.04%175.57%


Andy Zhou1351.70%10.33%


Arnaldo Carvalho de Melo1331.68%206.56%


Hannes Frederic Sowa1231.55%103.28%


Daniel Mack881.11%10.33%


Francesco Fusco780.98%10.33%


Hideaki Yoshifuji / 吉藤英明740.93%82.62%


Pavel Emelyanov700.88%30.98%


Julian Anastasov660.83%51.64%


David Ahern510.64%41.31%


Willem de Bruijn460.58%20.66%


Roopa Prabhu350.44%10.33%


Mitsuru Chinen350.44%10.33%


Al Viro300.38%113.61%


Jiri Pirko270.34%10.33%


David L Stevens270.34%20.66%


Linus Torvalds260.33%61.97%


Neil Horman240.30%10.33%


Vasily Averin240.30%10.33%


Steffen Klassert230.29%30.98%


Tóth László Attila230.29%10.33%


Ian Morris220.28%10.33%


Wei Dong200.25%20.66%


Kostya Belezko160.20%10.33%


Bart De Schuymer140.18%10.33%


Konstantin Khlebnikov140.18%10.33%


Michal Kubeček130.16%20.66%


Lorenzo Colitti120.15%20.66%


Krishna Kumar100.13%10.33%


Joe Perches100.13%20.66%


Venkat Yekkirala90.11%10.33%


Eli Cooper90.11%10.33%


Américo Wang80.10%20.66%


Thomas Graf80.10%10.33%


Pau Espin Pedrol80.10%10.33%


John Heffner80.10%10.33%


Stephen Hemminger70.09%30.98%


Pravin B Shelar70.09%10.33%


James Morris70.09%10.33%


Patrick Ohly50.06%10.33%


Ansis Atteka50.06%20.66%


Jan Engelhardt50.06%10.33%


Tom Herbert50.06%10.33%


Denis V. Lunev40.05%30.98%


Shmulik Ladkani40.05%10.33%


Julien Tinnes40.05%10.33%


Vasiliy Kulikov40.05%10.33%


Alexey Kodanev40.05%10.33%


Zheng Li40.05%10.33%


Bill Sommerfeld30.04%10.33%


Tejun Heo30.04%10.33%


Jozsef Kadlecsik30.04%20.66%


Marcelo Ricardo Leitner30.04%10.33%


Adrian Bunk30.04%30.98%


Alexey Dobriyan20.03%20.66%


Lance Richardson20.03%20.66%


KOVACS Krisztian20.03%10.33%


Shan Wei20.03%10.33%


Ian Campbell20.03%10.33%


Changli Gao20.03%10.33%


Paul Gortmaker20.03%10.33%


Yasuyuki Kozakai20.03%10.33%


Sridhar Samudrala20.03%10.33%


Octavian Purdila10.01%10.33%


Atis Elsts10.01%10.33%


Lucas De Marchi10.01%10.33%


Oliver Hartkopp10.01%10.33%


Javier Martinez Canillas10.01%10.33%


Chuck Lever10.01%10.33%


Total7925100.00%305100.00%


Directory: net/ipv4



Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.