Release 4.8 net/netfilter/ipvs/ip_vs_core.c

/*
 * IPVS         An implementation of the IP virtual server support for the
 *              LINUX operating system.  IPVS is now implemented as a module
 *              over the Netfilter framework. IPVS can be used to build a
 *              high-performance and highly available server based on a
 *              cluster of servers.
 *
 * Authors:     Wensong Zhang <wensong@linuxvirtualserver.org>
 *              Peter Kese <peter.kese@ijs.si>
 *              Julian Anastasov <ja@ssi.bg>
 *
 *              This program is free software; you can redistribute it and/or
 *              modify it under the terms of the GNU General Public License
 *              as published by the Free Software Foundation; either version
 *              2 of the License, or (at your option) any later version.
 *
 * The IPVS code for kernel 2.2 was done by Wensong Zhang and Peter Kese,
 * with changes/fixes from Julian Anastasov, Lars Marowsky-Bree, Horms
 * and others.
 *
 * Changes:
 *      Paul `Rusty' Russell            properly handle non-linear skbs
 *      Harald Welte                    don't use nfcache
 *
 */


#define KMSG_COMPONENT "IPVS"

#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/sctp.h>
#include <linux/icmp.h>
#include <linux/slab.h>

#include <net/ip.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/icmp.h>                   /* for icmp_send */
#include <net/route.h>
#include <net/ip6_checksum.h>
#include <net/netns/generic.h>		/* net_generic() */

#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>

#ifdef CONFIG_IP_VS_IPV6
#include <net/ipv6.h>
#include <linux/netfilter_ipv6.h>
#include <net/ip6_route.h>
#endif

#include <net/ip_vs.h>



EXPORT_SYMBOL(register_ip_vs_scheduler);

EXPORT_SYMBOL(unregister_ip_vs_scheduler);

EXPORT_SYMBOL(ip_vs_proto_name);

EXPORT_SYMBOL(ip_vs_conn_new);

EXPORT_SYMBOL(ip_vs_conn_in_get);

EXPORT_SYMBOL(ip_vs_conn_out_get);
#ifdef CONFIG_IP_VS_PROTO_TCP

EXPORT_SYMBOL(ip_vs_tcp_conn_listen);
#endif

EXPORT_SYMBOL(ip_vs_conn_put);
#ifdef CONFIG_IP_VS_DEBUG

EXPORT_SYMBOL(ip_vs_get_debug_level);
#endif

EXPORT_SYMBOL(ip_vs_new_conn_out);


static int ip_vs_net_id __read_mostly;
/* netns cnt used for uniqueness */

static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0);

/* ID used in ICMP lookups */

#define icmp_id(icmph)          (((icmph)->un).echo.id)

#define icmpv6_id(icmph)        (icmph->icmp6_dataun.u_echo.identifier)



const char *ip_vs_proto_name(unsigned int proto)
{
	static char buf[20];

	switch (proto) {
	case IPPROTO_IP:
		return "IP";
	case IPPROTO_UDP:
		return "UDP";
	case IPPROTO_TCP:
		return "TCP";
	case IPPROTO_SCTP:
		return "SCTP";
	case IPPROTO_ICMP:
		return "ICMP";
#ifdef CONFIG_IP_VS_IPV6
	case IPPROTO_ICMPV6:
		return "ICMPv6";
#endif
	default:
		sprintf(buf, "IP_%u", proto);
		return buf;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
59
75.64%
1
20.00%
julius volz
julius volz
11
14.10%
1
20.00%
venkata mohan reddy
venkata mohan reddy
6
7.69%
1
20.00%
masanari iida
masanari iida
1
1.28%
1
20.00%
eric dumazet
eric dumazet
1
1.28%
1
20.00%
Total
78
100.00%
5
100.00%



void ip_vs_init_hash_table(struct list_head *table, int rows)
{
	while (--rows >= 0)
		INIT_LIST_HEAD(&table[rows]);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
29
100.00%
1
100.00%
Total
29
100.00%
1
100.00%


static inline void

ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
{
	struct ip_vs_dest *dest = cp->dest;
	struct netns_ipvs *ipvs = cp->ipvs;

	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
		struct ip_vs_cpu_stats *s;
		struct ip_vs_service *svc;

		s = this_cpu_ptr(dest->stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.inpkts++;
		s->cnt.inbytes += skb->len;
		u64_stats_update_end(&s->syncp);

		rcu_read_lock();
		svc = rcu_dereference(dest->svc);
		s = this_cpu_ptr(svc->stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.inpkts++;
		s->cnt.inbytes += skb->len;
		u64_stats_update_end(&s->syncp);
		rcu_read_unlock();

		s = this_cpu_ptr(ipvs->tot_stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.inpkts++;
		s->cnt.inbytes += skb->len;
		u64_stats_update_end(&s->syncp);
	}
}


Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
94
45.63%
1
14.29%
hans schillstrom
hans schillstrom
60
29.13%
1
14.29%
julian anastasov
julian anastasov
46
22.33%
3
42.86%
sven wegener
sven wegener
3
1.46%
1
14.29%
eric w. biederman
eric w. biederman
3
1.46%
1
14.29%
Total
206
100.00%
7
100.00%


static inline void

ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
{
	struct ip_vs_dest *dest = cp->dest;
	struct netns_ipvs *ipvs = cp->ipvs;

	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
		struct ip_vs_cpu_stats *s;
		struct ip_vs_service *svc;

		s = this_cpu_ptr(dest->stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.outpkts++;
		s->cnt.outbytes += skb->len;
		u64_stats_update_end(&s->syncp);

		rcu_read_lock();
		svc = rcu_dereference(dest->svc);
		s = this_cpu_ptr(svc->stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.outpkts++;
		s->cnt.outbytes += skb->len;
		u64_stats_update_end(&s->syncp);
		rcu_read_unlock();

		s = this_cpu_ptr(ipvs->tot_stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.outpkts++;
		s->cnt.outbytes += skb->len;
		u64_stats_update_end(&s->syncp);
	}
}


Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
94
45.63%
1
14.29%
hans schillstrom
hans schillstrom
60
29.13%
1
14.29%
julian anastasov
julian anastasov
46
22.33%
3
42.86%
sven wegener
sven wegener
3
1.46%
1
14.29%
eric w. biederman
eric w. biederman
3
1.46%
1
14.29%
Total
206
100.00%
7
100.00%


static inline void

ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
{
	struct netns_ipvs *ipvs = svc->ipvs;
	struct ip_vs_cpu_stats *s;

	s = this_cpu_ptr(cp->dest->stats.cpustats);
	u64_stats_update_begin(&s->syncp);
	s->cnt.conns++;
	u64_stats_update_end(&s->syncp);

	s = this_cpu_ptr(svc->stats.cpustats);
	u64_stats_update_begin(&s->syncp);
	s->cnt.conns++;
	u64_stats_update_end(&s->syncp);

	s = this_cpu_ptr(ipvs->tot_stats.cpustats);
	u64_stats_update_begin(&s->syncp);
	s->cnt.conns++;
	u64_stats_update_end(&s->syncp);
}


Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
49
36.30%
1
16.67%
julian anastasov
julian anastasov
49
36.30%
2
33.33%
hans schillstrom
hans schillstrom
33
24.44%
1
16.67%
sven wegener
sven wegener
3
2.22%
1
16.67%
eric w. biederman
eric w. biederman
1
0.74%
1
16.67%
Total
135
100.00%
6
100.00%


static inline void

ip_vs_set_state(struct ip_vs_conn *cp, int direction,
		const struct sk_buff *skb,
		struct ip_vs_proto_data *pd)
{
	if (likely(pd->pp->state_transition))
		pd->pp->state_transition(cp, direction, skb, pd);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
38
73.08%
1
25.00%
hans schillstrom
hans schillstrom
7
13.46%
1
25.00%
julian anastasov
julian anastasov
4
7.69%
1
25.00%
simon horman
simon horman
3
5.77%
1
25.00%
Total
52
100.00%
4
100.00%


static inline int

ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
			      struct sk_buff *skb, int protocol,
			      const union nf_inet_addr *caddr, __be16 cport,
			      const union nf_inet_addr *vaddr, __be16 vport,
			      struct ip_vs_conn_param *p)
{
	ip_vs_conn_fill_param(svc->ipvs, svc->af, protocol, caddr, cport, vaddr,
			      vport, p);
	p->pe = rcu_dereference(svc->pe);
	if (p->pe && p->pe->fill_param)
		return p->pe->fill_param(p, skb);

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
simon horman
simon horman
92
87.62%
1
20.00%
hans schillstrom
hans schillstrom
9
8.57%
2
40.00%
julian anastasov
julian anastasov
3
2.86%
1
20.00%
eric w. biederman
eric w. biederman
1
0.95%
1
20.00%
Total
105
100.00%
5
100.00%

/*
 *  IPVS persistent scheduling function
 *  It creates a connection entry according to its template if exists,
 *  or selects a server and creates a connection entry plus a template.
 *  Locking: we are svc user (svc->refcnt), so we hold all dests too
 *  Protocols supported: TCP, UDP
 */

static struct ip_vs_conn *

ip_vs_sched_persist(struct ip_vs_service *svc,
		    struct sk_buff *skb, __be16 src_port, __be16 dst_port,
		    int *ignored, struct ip_vs_iphdr *iph)
{
	struct ip_vs_conn *cp = NULL;
	struct ip_vs_dest *dest;
	struct ip_vs_conn *ct;
	__be16 dport = 0;		/* destination port to forward */
	unsigned int flags;
	struct ip_vs_conn_param param;
	const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) };
	union nf_inet_addr snet;	/* source network of the client,
                                           after masking */
	const union nf_inet_addr *src_addr, *dst_addr;

	if (likely(!ip_vs_iph_inverse(iph))) {
		src_addr = &iph->saddr;
		dst_addr = &iph->daddr;
	} else {
		src_addr = &iph->daddr;
		dst_addr = &iph->saddr;
	}


	/* Mask saddr with the netmask to adjust template granularity */
#ifdef CONFIG_IP_VS_IPV6
	if (svc->af == AF_INET6)
		ipv6_addr_prefix(&snet.in6, &src_addr->in6,
				 (__force __u32) svc->netmask);
	else
#endif
		snet.ip = src_addr->ip & svc->netmask;

	IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u "
		      "mnet %s\n",
		      IP_VS_DBG_ADDR(svc->af, src_addr), ntohs(src_port),
		      IP_VS_DBG_ADDR(svc->af, dst_addr), ntohs(dst_port),
		      IP_VS_DBG_ADDR(svc->af, &snet));

	/*
         * As far as we know, FTP is a very complicated network protocol, and
         * it uses control connection and data connections. For active FTP,
         * FTP server initialize data connection to the client, its source port
         * is often 20. For passive FTP, FTP server tells the clients the port
         * that it passively listens to,  and the client issues the data
         * connection. In the tunneling or direct routing mode, the load
         * balancer is on the client-to-server half of connection, the port
         * number is unknown to the load balancer. So, a conn template like
         * <caddr, 0, vaddr, 0, daddr, 0> is created for persistent FTP
         * service, and a template like <caddr, 0, vaddr, vport, daddr, dport>
         * is created for other persistent services.
         */
	{
		int protocol = iph->protocol;
		const union nf_inet_addr *vaddr = dst_addr;
		__be16 vport = 0;

		if (dst_port == svc->port) {
			/* non-FTP template:
                         * <protocol, caddr, 0, vaddr, vport, daddr, dport>
                         * FTP template:
                         * <protocol, caddr, 0, vaddr, 0, daddr, 0>
                         */
			if (svc->port != FTPPORT)
				vport = dst_port;
		} else {
			/* Note: persistent fwmark-based services and
                         * persistent port zero service are handled here.
                         * fwmark template:
                         * <IPPROTO_IP,caddr,0,fwmark,0,daddr,0>
                         * port zero template:
                         * <protocol,caddr,0,vaddr,0,daddr,0>
                         */
			if (svc->fwmark) {
				protocol = IPPROTO_IP;
				vaddr = &fwmark;
			}
		}
		/* return *ignored = -1 so NF_DROP can be used */
		if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0,
						  vaddr, vport, &param) < 0) {
			*ignored = -1;
			return NULL;
		}
	}

	/* Check if a template already exists */
	ct = ip_vs_ct_in_get(&param);
	if (!ct || !ip_vs_check_template(ct, NULL)) {
		struct ip_vs_scheduler *sched;

		/*
                 * No template found or the dest of the connection
                 * template is not available.
                 * return *ignored=0 i.e. ICMP and NF_DROP
                 */
		sched = rcu_dereference(svc->scheduler);
		if (sched) {
			/* read svc->sched_data after svc->scheduler */
			smp_rmb();
			dest = sched->schedule(svc, skb, iph);
		} else {
			dest = NULL;
		}
		if (!dest) {
			IP_VS_DBG(1, "p-schedule: no dest found.\n");
			kfree(param.pe_data);
			*ignored = 0;
			return NULL;
		}

		if (dst_port == svc->port && svc->port != FTPPORT)
			dport = dest->port;

		/* Create a template
                 * This adds param.pe_data to the template,
                 * and thus param.pe_data will be destroyed
                 * when the template expires */
		ct = ip_vs_conn_new(&param, dest->af, &dest->addr, dport,
				    IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
		if (ct == NULL) {
			kfree(param.pe_data);
			*ignored = -1;
			return NULL;
		}

		ct->timeout = svc->timeout;
	} else {
		/* set destination with the found template */
		dest = ct->dest;
		kfree(param.pe_data);
	}

	dport = dst_port;
	if (dport == svc->port && dest->port)
		dport = dest->port;

	flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
		 && iph->protocol == IPPROTO_UDP) ?
		IP_VS_CONN_F_ONE_PACKET : 0;

	/*
         *    Create a new connection according to the template
         */
	ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, src_addr,
			      src_port, dst_addr, dst_port, &param);

	cp = ip_vs_conn_new(&param, dest->af, &dest->addr, dport, flags, dest,
			    skb->mark);
	if (cp == NULL) {
		ip_vs_conn_put(ct);
		*ignored = -1;
		return NULL;
	}

	/*
         *    Add its control
         */
	ip_vs_control_add(cp, ct);
	ip_vs_conn_put(ct);

	ip_vs_conn_stats(cp, svc);
	return cp;
}


Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
256
38.15%
1
3.85%
simon horman
simon horman
135
20.12%
5
19.23%
julius volz
julius volz
69
10.28%
2
7.69%
alex gartrell
alex gartrell
68
10.13%
2
7.69%
hans schillstrom
hans schillstrom
61
9.09%
4
15.38%
julian anastasov
julian anastasov
45
6.71%
7
26.92%
nick chalk
nick chalk
22
3.28%
1
3.85%
jesper dangaard brouer
jesper dangaard brouer
10
1.49%
1
3.85%
al viro
al viro
2
0.30%
1
3.85%
marco angaroni
marco angaroni
2
0.30%
1
3.85%
eric w. biederman
eric w. biederman
1
0.15%
1
3.85%
Total
671
100.00%
26
100.00%

/*
 *  IPVS main scheduling function
 *  It selects a server according to the virtual service, and
 *  creates a connection entry.
 *  Protocols supported: TCP, UDP
 *
 *  Usage of *ignored
 *
 * 1 :   protocol tried to schedule (eg. on SYN), found svc but the
 *       svc/scheduler decides that this packet should be accepted with
 *       NF_ACCEPT because it must not be scheduled.
 *
 * 0 :   scheduler can not find destination, so try bypass or
 *       return ICMP and then NF_DROP (ip_vs_leave).
 *
 * -1 :  scheduler tried to schedule but fatal error occurred, eg.
 *       ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param
 *       failure such as missing Call-ID, ENOMEM on skb_linearize
 *       or pe_data. In this case we should return NF_DROP without
 *       any attempts to send ICMP with ip_vs_leave.
 */

struct ip_vs_conn *

ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
	       struct ip_vs_proto_data *pd, int *ignored,
	       struct ip_vs_iphdr *iph)
{
	struct ip_vs_protocol *pp = pd->pp;
	struct ip_vs_conn *cp = NULL;
	struct ip_vs_scheduler *sched;
	struct ip_vs_dest *dest;
	__be16 _ports[2], *pptr, cport, vport;
	const void *caddr, *vaddr;
	unsigned int flags;

	*ignored = 1;
	/*
         * IPv6 frags, only the first hit here.
         */
	pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
	if (pptr == NULL)
		return NULL;

	if (likely(!ip_vs_iph_inverse(iph))) {
		cport = pptr[0];
		caddr = &iph->saddr;
		vport = pptr[1];
		vaddr = &iph->daddr;
	} else {
		cport = pptr[1];
		caddr = &iph->daddr;
		vport = pptr[0];
		vaddr = &iph->saddr;
	}

	/*
         * FTPDATA needs this check when using local real server.
         * Never schedule Active FTPDATA connections from real server.
         * For LVS-NAT they must be already created. For other methods
         * with persistence the connection is created on SYN+ACK.
         */
	if (cport == FTPDATA) {
		IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off,
			      "Not scheduling FTPDATA");
		return NULL;
	}

	/*
         *    Do not schedule replies from local real server.
         */
	if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK)) {
		iph->hdr_flags ^= IP_VS_HDR_INVERSE;
		cp = pp->conn_in_get(svc->ipvs, svc->af, skb, iph);
		iph->hdr_flags ^= IP_VS_HDR_INVERSE;

		if (cp) {
			IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off,
				      "Not scheduling reply for existing"
				      " connection");
			__ip_vs_conn_put(cp);
			return NULL;
		}
	}

	/*
         *    Persistent service
         */
	if (svc->flags & IP_VS_SVC_F_PERSISTENT)
		return ip_vs_sched_persist(svc, skb, cport, vport, ignored,
					   iph);

	*ignored = 0;

	/*
         *    Non-persistent service
         */
	if (!svc->fwmark && vport != svc->port) {
		if (!svc->port)
			pr_err("Schedule: port zero only supported "
			       "in persistent services, "
			       "check your ipvs configuration\n");
		return NULL;
	}

	sched = rcu_dereference(svc->scheduler);
	if (sched) {
		/* read svc->sched_data after svc->scheduler */
		smp_rmb();
		dest = sched->schedule(svc, skb, iph);
	} else {
		dest = NULL;
	}
	if (dest == NULL) {
		IP_VS_DBG(1, "Schedule: no dest found.\n");
		return NULL;
	}

	flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
		 && iph->protocol == IPPROTO_UDP) ?
		IP_VS_CONN_F_ONE_PACKET : 0;

	/*
         *    Create a connection entry.
         */
	{
		struct ip_vs_conn_param p;

		ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol,
				      caddr, cport, vaddr, vport, &p);
		cp = ip_vs_conn_new(&p, dest->af, &dest->addr,
				    dest->port ? dest->port : vport,
				    flags, dest, skb->mark);
		if (!cp) {
			*ignored = -1;
			return NULL;
		}
	}

	IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u "
		      "d:%s:%u conn->flags:%X conn->refcnt:%d\n",
		      ip_vs_fwd_tag(cp),
		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
		      cp->flags, atomic_read(&cp->refcnt));

	ip_vs_conn_stats(cp, svc);
	return cp;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
208
33.49%
1
3.45%
julian anastasov
julian anastasov
158
25.44%
8
27.59%
alex gartrell
alex gartrell
121
19.48%
4
13.79%
hans schillstrom
hans schillstrom
35
5.64%
5
17.24%
julius volz
julius volz
23
3.70%
2
6.90%
nick chalk
nick chalk
21
3.38%
1
3.45%
simon horman
simon horman
19
3.06%
1
3.45%
david s. miller
david s. miller
15
2.42%
1
3.45%
jesper dangaard brouer
jesper dangaard brouer
14
2.25%
2
6.90%
eric w. biederman
eric w. biederman
5
0.81%
2
6.90%
hannes eder
hannes eder
1
0.16%
1
3.45%
al viro
al viro
1
0.16%
1
3.45%
Total
621
100.00%
29
100.00%



static inline int ip_vs_addr_is_unicast(struct net *net, int af,
					union nf_inet_addr *addr)
{
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		return ipv6_addr_type(&addr->in6) & IPV6_ADDR_UNICAST;
#endif
	return (inet_addr_type(net, addr->ip) == RTN_UNICAST);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
alex gartrell
alex gartrell
56
100.00%
1
100.00%
Total
56
100.00%
1
100.00%

/*
 *  Pass or drop the packet.
 *  Called by ip_vs_in, when the virtual service is available but
 *  no destination is available for a new connection.
 */


int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
		struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph)
{
	__be16 _ports[2], *pptr, dport;
	struct netns_ipvs *ipvs = svc->ipvs;
	struct net *net = ipvs->net;

	pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
	if (!pptr)
		return NF_DROP;
	dport = likely(!ip_vs_iph_inverse(iph)) ? pptr[1] : pptr[0];

	/* if it is fwmark-based service, the cache_bypass sysctl is up
           and the destination is a non-local unicast, then create
           a cache_bypass connection entry */
	if (sysctl_cache_bypass(ipvs) && svc->fwmark &&
	    !(iph->hdr_flags & (IP_VS_HDR_INVERSE | IP_VS_HDR_ICMP)) &&
	    ip_vs_addr_is_unicast(net, svc->af, &iph->daddr)) {
		int ret;
		struct ip_vs_conn *cp;
		unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
				      iph->protocol == IPPROTO_UDP) ?
				      IP_VS_CONN_F_ONE_PACKET : 0;
		union nf_inet_addr daddr =  { .all = { 0, 0, 0, 0 } };

		/* create a new connection entry */
		IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
		{
			struct ip_vs_conn_param p;
			ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol,
					      &iph->saddr, pptr[0],
					      &iph->daddr, pptr[1], &p);
			cp = ip_vs_conn_new(&p, svc->af, &daddr, 0,
					    IP_VS_CONN_F_BYPASS | flags,
					    NULL, skb->mark);
			if (!cp)
				return NF_DROP;
		}

		/* statistics */
		ip_vs_in_stats(cp, skb);

		/* set state */
		ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);

		/* transmit the first SYN packet */
		ret = cp->packet_xmit(skb, cp, pd->pp, iph);
		/* do not touch skb anymore */

		if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control)
			atomic_inc(&cp->control->in_pkts);
		else
			atomic_inc(&cp->in_pkts);
		ip_vs_conn_put(cp);
		return ret;
	}

	/*
         * When the virtual ftp service is presented, packets destined
         * for other services on the VIP may get here (except services
         * listed in the ipvs table), pass the packets, because it is
         * not ipvs job to decide to drop the packets.
         */
	if (svc->port == FTPPORT && dport != FTPPORT)
		return NF_ACCEPT;

	if (unlikely(ip_vs_iph_icmp(iph)))
		return NF_DROP;

	/*
         * Notify the client that the destination is unreachable, and
         * release the socket buffer.
         * Since it is in IP layer, the TCP socket is not actually
         * created, the TCP RST packet cannot be sent, instead that
         * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ
         */
#ifdef CONFIG_IP_VS_IPV6
	if (svc->af == AF_INET6) {
		if (!skb->dev)
			skb->dev = net->loopback_dev;
		icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
	} else
#endif
		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);

	return NF_DROP;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
145
32.37%
1
3.70%
alex gartrell
alex gartrell
62
13.84%
2
7.41%
simon horman
simon horman
47
10.49%
3
11.11%
julius volz
julius volz
44
9.82%
2
7.41%
julian anastasov
julian anastasov
39
8.71%
4
14.81%
marco angaroni
marco angaroni
25
5.58%
1
3.70%
nick chalk
nick chalk
21
4.69%
1
3.70%
eric w. biederman
eric w. biederman
16
3.57%
3
11.11%
david s. miller
david s. miller
15
3.35%
1
3.70%
hans schillstrom
hans schillstrom
15
3.35%
5
18.52%
jesper dangaard brouer
jesper dangaard brouer
15
3.35%
2
7.41%
hannes eder
hannes eder
3
0.67%
1
3.70%
al viro
al viro
1
0.22%
1
3.70%
Total
448
100.00%
27
100.00%

#ifdef CONFIG_SYSCTL



static int sysctl_snat_reroute(struct netns_ipvs *ipvs)
{
	return ipvs->sysctl_snat_reroute;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
simon horman
simon horman
14
87.50%
1
50.00%
eric w. biederman
eric w. biederman
2
12.50%
1
50.00%
Total
16
100.00%
2
100.00%



static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs)
{
	return ipvs->sysctl_nat_icmp_send;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
simon horman
simon horman
14
87.50%
1
50.00%
eric w. biederman
eric w. biederman
2
12.50%
1
50.00%
Total
16
100.00%
2
100.00%



static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs)
{
	return ipvs->sysctl_expire_nodest_conn;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
simon horman
simon horman
16
100.00%
1
100.00%
Total
16
100.00%
1
100.00%

#else



static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return 0; }
Contributors
Person
Tokens
Prop
Commits
CommitProp
simon horman
simon horman
12
85.71%
1
50.00%
eric w. biederman
eric w. biederman
2
14.29%
1
50.00%
Total
14
100.00%
2
100.00%



static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; }
Contributors
Person
Tokens
Prop
Commits
CommitProp
simon horman
simon horman
12
85.71%
1
50.00%
eric w. biederman
eric w. biederman
2
14.29%
1
50.00%
Total
14
100.00%
2
100.00%



static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) { return 0; }

Contributors
Person
Tokens
Prop
Commits
CommitProp
simon horman
simon horman
14
100.00%
1
100.00%
Total
14
100.00%
1
100.00%

#endif



__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
{
	return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
21
65.62%
1
33.33%
wensong zhang
wensong zhang
10
31.25%
1
33.33%
al viro
al viro
1
3.12%
1
33.33%
Total
32
100.00%
3
100.00%



static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum)
{
	if (NF_INET_LOCAL_IN == hooknum)
		return IP_DEFRAG_VS_IN;
	if (NF_INET_FORWARD == hooknum)
		return IP_DEFRAG_VS_FWD;
	return IP_DEFRAG_VS_OUT;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
33
100.00%
1
100.00%
Total
33
100.00%
1
100.00%



static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs,
				     struct sk_buff *skb, u_int32_t user)
{
	int err;

	local_bh_disable();
	err = ip_defrag(ipvs->net, skb, user);
	local_bh_enable();
	if (!err)
		ip_send_check(ip_hdr(skb));

	return err;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
18
31.03%
2
25.00%
wensong zhang
wensong zhang
17
29.31%
1
12.50%
eric w. biederman
eric w. biederman
9
15.52%
2
25.00%
herbert xu
herbert xu
6
10.34%
1
12.50%
patrick mchardy
patrick mchardy
5
8.62%
1
12.50%
arnaldo carvalho de melo
arnaldo carvalho de melo
3
5.17%
1
12.50%
Total
58
100.00%
8
100.00%



static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af,
				 struct sk_buff *skb, unsigned int hooknum)
{
	if (!sysctl_snat_reroute(ipvs))
		return 0;
	/* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */
	if (NF_INET_LOCAL_IN == hooknum)
		return 0;
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6) {
		struct dst_entry *dst = skb_dst(skb);

		if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
		    ip6_route_me_harder(ipvs->net, skb) != 0)
			return 1;
	} else
#endif
		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
		    ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0)
			return 1;

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
simon horman
simon horman
70
53.03%
2
33.33%
julian anastasov
julian anastasov
48
36.36%
1
16.67%
eric w. biederman
eric w. biederman
14
10.61%
3
50.00%
Total
132
100.00%
6
100.00%

/*
 * Packet has been made sufficiently writable in caller
 * - inout: 1=in->out, 0=out->in
 */


void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
		    struct ip_vs_conn *cp, int inout)
{
	struct iphdr *iph	 = ip_hdr(skb);
	unsigned int icmp_offset = iph->ihl*4;
	struct icmphdr *icmph	 = (struct icmphdr *)(skb_network_header(skb) +
						      icmp_offset);
	struct iphdr *ciph	 = (struct iphdr *)(icmph + 1);

	if (inout) {
		iph->saddr = cp->vaddr.ip;
		ip_send_check(iph);
		ciph->daddr = cp->vaddr.ip;
		ip_send_check(ciph);
	} else {
		iph->daddr = cp->daddr.ip;
		ip_send_check(iph);
		ciph->saddr = cp->daddr.ip;
		ip_send_check(ciph);
	}

	/* the TCP/UDP/SCTP port */
	if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol ||
	    IPPROTO_SCTP == ciph->protocol) {
		__be16 *ports = (void *)ciph + ciph->ihl*4;

		if (inout)
			ports[1] = cp->vport;
		else
			ports[0] = cp->dport;
	}

	/* And finally the ICMP checksum */
	icmph->checksum = 0;
	icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset);
	skb->ip_summed = CHECKSUM_UNNECESSARY;

	if (inout)
		IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph,
			"Forwarding altered outgoing ICMP");
	else
		IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph,
			"Forwarding altered incoming ICMP");
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
245
85.07%
2
25.00%
wensong zhang
wensong zhang
21
7.29%
1
12.50%
julius volz
julius volz
8
2.78%
1
12.50%
venkata mohan reddy
venkata mohan reddy
7
2.43%
1
12.50%
arnaldo carvalho de melo
arnaldo carvalho de melo
6
2.08%
2
25.00%
al viro
al viro
1
0.35%
1
12.50%
Total
288
100.00%
8
100.00%

#ifdef CONFIG_IP_VS_IPV6


void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
		    struct ip_vs_conn *cp, int inout)
{
	struct ipv6hdr *iph	 = ipv6_hdr(skb);
	unsigned int icmp_offset = 0;
	unsigned int offs	 = 0; /* header offset*/
	int protocol;
	struct icmp6hdr *icmph;
	struct ipv6hdr *ciph;
	unsigned short fragoffs;

	ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL);
	icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset);
	offs = icmp_offset + sizeof(struct icmp6hdr);
	ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs);

	protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL);

	if (inout) {
		iph->saddr = cp->vaddr.in6;
		ciph->daddr = cp->vaddr.in6;
	} else {
		iph->daddr = cp->daddr.in6;
		ciph->saddr = cp->daddr.in6;
	}

	/* the TCP/UDP/SCTP port */
	if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol ||
			  IPPROTO_SCTP == protocol)) {
		__be16 *ports = (void *)(skb_network_header(skb) + offs);

		IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__,
			      ntohs(inout ? ports[1] : ports[0]),
			      ntohs(inout ? cp->vport : cp->dport));
		if (inout)
			ports[1] = cp->vport;
		else
			ports[0] = cp->dport;
	}

	/* And finally the ICMP checksum */
	icmph->icmp6_cksum = ~csum_ipv6_magic(&iph->saddr, &iph->daddr,
					      skb->len - icmp_offset,
					      IPPROTO_ICMPV6, 0);
	skb->csum_start = skb_network_header(skb) - skb->head + icmp_offset;
	skb->csum_offset = offsetof(struct icmp6hdr, icmp6_cksum);
	skb->ip_summed = CHECKSUM_PARTIAL;

	if (inout)
		IP_VS_DBG_PKT(11, AF_INET6, pp, skb,
			      (void *)ciph - (void *)iph,
			      "Forwarding altered outgoing ICMPv6");
	else
		IP_VS_DBG_PKT(11, AF_INET6, pp, skb,
			      (void *)ciph - (void *)iph,
			      "Forwarding altered incoming ICMPv6");
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
julius volz
julius volz
225
55.83%
1
20.00%
jesper dangaard brouer
jesper dangaard brouer
125
31.02%
1
20.00%
simon horman
simon horman
45
11.17%
1
20.00%
julian anastasov
julian anastasov
4
0.99%
1
20.00%
venkata mohan reddy
venkata mohan reddy
4
0.99%
1
20.00%
Total
403
100.00%
5
100.00%

#endif

/* Handle relevant response ICMP messages - forward to the right
 * destination host.
 */


static int handle_response_icmp(int af, struct sk_buff *skb,
				union nf_inet_addr *snet,
				__u8 protocol, struct ip_vs_conn *cp,
				struct ip_vs_protocol *pp,
				unsigned int offset, unsigned int ihl,
				unsigned int hooknum)
{
	unsigned int verdict = NF_DROP;

	if (IP_VS_FWD_METHOD(cp) != 0) {
		pr_err("shouldn't reach here, because the box is on the "
		       "half connection in the tun/dr module.\n");
	}

	/* Ensure the checksum is correct */
	if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
		/* Failed checksum! */
		IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n",
			      IP_VS_DBG_ADDR(af, snet));
		goto out;
	}

	if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol ||
	    IPPROTO_SCTP == protocol)
		offset += 2 * sizeof(__u16);
	if (!skb_make_writable(skb, offset))
		goto out;

#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		ip_vs_nat_icmp_v6(skb, pp, cp, 1);
	else
#endif
		ip_vs_nat_icmp(skb, pp, cp, 1);

	if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum))
		goto out;

	/* do the statistics and put it back */
	ip_vs_out_stats(cp, skb);

	skb->ipvs_property = 1;
	if (!(cp->flags & IP_VS_CONN_F_NFCT))
		ip_vs_notrack(skb);
	else
		ip_vs_update_conntrack(skb, cp, 0);
	verdict = NF_ACCEPT;

out:
	__ip_vs_conn_put(cp);

	return verdict;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
malcolm turnbull
malcolm turnbull
151
61.63%
1
10.00%
julian anastasov
julian anastasov
45
18.37%
4
40.00%
simon horman
simon horman
40
16.33%
2
20.00%
eric w. biederman
eric w. biederman
4
1.63%
1
10.00%
venkata mohan reddy
venkata mohan reddy
4
1.63%
1
10.00%
hannes eder
hannes eder
1
0.41%
1
10.00%
Total
245
100.00%
10
100.00%

/*
 *      Handle ICMP messages in the inside-to-outside direction (outgoing).
 *      Find any that might be relevant, check against existing connections.
 *      Currently handles error types - unreachable, quench, ttl exceeded.
 */


static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
			  int *related, unsigned int hooknum)
{
	struct iphdr *iph;
	struct icmphdr	_icmph, *ic;
	struct iphdr	_ciph, *cih;	/* The ip header contained within the ICMP */
	struct ip_vs_iphdr ciph;
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp;
	unsigned int offset, ihl;
	union nf_inet_addr snet;

	*related = 1;

	/* reassemble IP fragments */
	if (ip_is_fragment(ip_hdr(skb))) {
		if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum)))
			return NF_STOLEN;
	}

	iph = ip_hdr(skb);
	offset = ihl = iph->ihl * 4;
	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
	if (ic == NULL)
		return NF_DROP;

	IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %pI4->%pI4\n",
		  ic->type, ntohs(icmp_id(ic)),
		  &iph->saddr, &iph->daddr);

	/*
         * Work through seeing if this is for us.
         * These checks are supposed to be in an order that means easy
         * things are checked first to speed up processing.... however
         * this means that some packets will manage to get a long way
         * down this stack and then be rejected, but that's life.
         */
	if ((ic->type != ICMP_DEST_UNREACH) &&
	    (ic->type != ICMP_SOURCE_QUENCH) &&
	    (ic->type != ICMP_TIME_EXCEEDED)) {
		*related = 0;
		return NF_ACCEPT;
	}

	/* Now find the contained IP header */
	offset += sizeof(_icmph);
	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
	if (cih == NULL)
		return NF_ACCEPT; /* The packet looks wrong, ignore */

	pp = ip_vs_proto_get(cih->protocol);
	if (!pp)
		return NF_ACCEPT;

	/* Is the embedded protocol header present? */
	if (unlikely(cih->frag_off & htons(IP_OFFSET) &&
		     pp->dont_defrag))
		return NF_ACCEPT;

	IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
		      "Checking outgoing ICMP for");

	ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph);

	/* The embedded headers contain source and dest in reverse order */
	cp = pp->conn_out_get(ipvs, AF_INET, skb, &ciph);
	if (!cp)
		return NF_ACCEPT;

	snet.ip = iph->saddr;
	return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp,
				    pp, ciph.len, ihl, hooknum);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
139
37.07%
1
4.55%
julian anastasov
julian anastasov
111
29.60%
4
18.18%
david s. miller
david s. miller
48
12.80%
1
4.55%
simon horman
simon horman
18
4.80%
1
4.55%
julius volz
julius volz
14
3.73%
1
4.55%
malcolm turnbull
malcolm turnbull
9
2.40%
1
4.55%
eric w. biederman
eric w. biederman
9
2.40%
3
13.64%
alex gartrell
alex gartrell
8
2.13%
2
9.09%
arnaldo carvalho de melo
arnaldo carvalho de melo
6
1.60%
1
4.55%
jesper dangaard brouer
jesper dangaard brouer
3
0.80%
1
4.55%
harvey harrison
harvey harrison
3
0.80%
1
4.55%
herbert xu
herbert xu
3
0.80%
2
9.09%
paul gortmaker
paul gortmaker
2
0.53%
1
4.55%
patrick mchardy
patrick mchardy
1
0.27%
1
4.55%
hideaki yoshifuji
hideaki yoshifuji
1
0.27%
1
4.55%
Total
375
100.00%
22
100.00%

#ifdef CONFIG_IP_VS_IPV6


static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
			     int *related,  unsigned int hooknum,
			     struct ip_vs_iphdr *ipvsh)
{
	struct icmp6hdr	_icmph, *ic;
	struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp;
	union nf_inet_addr snet;
	unsigned int offset;

	*related = 1;
	ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph, ipvsh);
	if (ic == NULL)
		return NF_DROP;

	/*
         * Work through seeing if this is for us.
         * These checks are supposed to be in an order that means easy
         * things are checked first to speed up processing.... however
         * this means that some packets will manage to get a long way
         * down this stack and then be rejected, but that's life.
         */
	if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) {
		*related = 0;
		return NF_ACCEPT;
	}
	/* Fragment header that is before ICMP header tells us that:
         * it's not an error message since they can't be fragmented.
         */
	if (ipvsh->flags & IP6_FH_F_FRAG)
		return NF_DROP;

	IP_VS_DBG(8, "Outgoing ICMPv6 (%d,%d) %pI6c->%pI6c\n",
		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
		  &ipvsh->saddr, &ipvsh->daddr);

	if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, ipvsh->len + sizeof(_icmph),
				     true, &ciph))
		return NF_ACCEPT; /* The packet looks wrong, ignore */

	pp = ip_vs_proto_get(ciph.protocol);
	if (!pp)
		return NF_ACCEPT;

	/* The embedded headers contain source and dest in reverse order */
	cp = pp->conn_out_get(ipvs, AF_INET6, skb, &ciph);
	if (!cp)
		return NF_ACCEPT;

	snet.in6 = ciph.saddr.in6;
	offset = ciph.len;
	return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
				    pp, offset, sizeof(struct ipv6hdr),
				    hooknum);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
jesper dangaard brouer
jesper dangaard brouer
98
34.88%
3
16.67%
julius volz
julius volz
80
28.47%
2
11.11%
wensong zhang
wensong zhang
28
9.96%
1
5.56%
julian anastasov
julian anastasov
22
7.83%
3
16.67%
simon horman
simon horman
17
6.05%
1
5.56%
alex gartrell
alex gartrell
15
5.34%
2
11.11%
david s. miller
david s. miller
11
3.91%
2
11.11%
eric w. biederman
eric w. biederman
7
2.49%
2
11.11%
harvey harrison
harvey harrison
2
0.71%
1
5.56%
alexey dobriyan
alexey dobriyan
1
0.36%
1
5.56%
Total
281
100.00%
18
100.00%

#endif

/*
 * Check if sctp chunc is ABORT chunk
 */


static inline int is_sctp_abort(const struct sk_buff *skb, int nh_len)
{
	sctp_chunkhdr_t *sch, schunk;
	sch = skb_header_pointer(skb, nh_len + sizeof(sctp_sctphdr_t),
			sizeof(schunk), &schunk);
	if (sch == NULL)
		return 0;
	if (sch->type == SCTP_CID_ABORT)
		return 1;
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
venkata mohan reddy
venkata mohan reddy
67
100.00%
1
100.00%
Total
67
100.00%
1
100.00%



static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len)
{
	struct tcphdr _tcph, *th;

	th = skb_header_pointer(skb, nh_len, sizeof(_tcph), &_tcph);
	if (th == NULL)
		return 0;
	return th->rst;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julius volz
julius volz
24
44.44%
1
25.00%
malcolm turnbull
malcolm turnbull
22
40.74%
1
25.00%
david s. miller
david s. miller
4
7.41%
1
25.00%
julian anastasov
julian anastasov
4
7.41%
1
25.00%
Total
54
100.00%
4
100.00%



static inline bool is_new_conn(const struct sk_buff *skb,
			       struct ip_vs_iphdr *iph)
{
	switch (iph->protocol) {
	case IPPROTO_TCP: {
		struct tcphdr _tcph, *th;

		th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
		if (th == NULL)
			return false;
		return th->syn;
	}
	case IPPROTO_SCTP: {
		sctp_chunkhdr_t *sch, schunk;

		sch = skb_header_pointer(skb, iph->len + sizeof(sctp_sctphdr_t),
					 sizeof(schunk), &schunk);
		if (sch == NULL)
			return false;
		return sch->type == SCTP_CID_INIT;
	}
	default:
		return false;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
grzegorz lyczba
grzegorz lyczba
126
100.00%
1
100.00%
Total
126
100.00%
1
100.00%



static inline bool is_new_conn_expected(const struct ip_vs_conn *cp,
					int conn_reuse_mode)
{
	/* Controlled (FTP DATA or persistence)? */
	if (cp->control)
		return false;

	switch (cp->protocol) {
	case IPPROTO_TCP:
		return (cp->state == IP_VS_TCP_S_TIME_WAIT) ||
		       (cp->state == IP_VS_TCP_S_CLOSE) ||
			((conn_reuse_mode & 2) &&
			 (cp->state == IP_VS_TCP_S_FIN_WAIT) &&
			 (cp->flags & IP_VS_CONN_F_NOOUTPUT));
	case IPPROTO_SCTP:
		return cp->state == IP_VS_SCTP_S_CLOSED;
	default:
		return false;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
marcelo ricardo leitner
marcelo ricardo leitner
84
91.30%
1
50.00%
julian anastasov
julian anastasov
8
8.70%
1
50.00%
Total
92
100.00%
2
100.00%

/* Generic function to create new connections for outgoing RS packets
 *
 * Pre-requisites for successful connection creation:
 * 1) Virtual Service is NOT fwmark based:
 *    In fwmark-VS actual vaddr and vport are unknown to IPVS
 * 2) Real Server and Virtual Service were NOT configured without port:
 *    This is to allow match of different VS to the same RS ip-addr
 */


struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc,
				      struct ip_vs_dest *dest,
				      struct sk_buff *skb,
				      const struct ip_vs_iphdr *iph,
				      __be16 dport,
				      __be16 cport)
{
	struct ip_vs_conn_param param;
	struct ip_vs_conn *ct = NULL, *cp = NULL;
	const union nf_inet_addr *vaddr, *daddr, *caddr;
	union nf_inet_addr snet;
	__be16 vport;
	unsigned int flags;

	EnterFunction(12);
	vaddr = &svc->addr;
	vport = svc->port;
	daddr = &iph->saddr;
	caddr = &iph->daddr;

	/* check pre-requisites are satisfied */
	if (svc->fwmark)
		return NULL;
	if (!vport || !dport)
		return NULL;

	/* for persistent service first create connection template */
	if (svc->flags & IP_VS_SVC_F_PERSISTENT) {
		/* apply netmask the same way ingress-side does */
#ifdef CONFIG_IP_VS_IPV6
		if (svc->af == AF_INET6)
			ipv6_addr_prefix(&snet.in6, &caddr->in6,
					 (__force __u32)svc->netmask);
		else
#endif
			snet.ip = caddr->ip & svc->netmask;
		/* fill params and create template if not existent */
		if (ip_vs_conn_fill_param_persist(svc, skb, iph->protocol,
						  &snet, 0, vaddr,
						  vport, &param) < 0)
			return NULL;
		ct = ip_vs_ct_in_get(&param);
		/* check if template exists and points to the same dest */
		if (!ct || !ip_vs_check_template(ct, dest)) {
			ct = ip_vs_conn_new(&param, dest->af, daddr, dport,
					    IP_VS_CONN_F_TEMPLATE, dest, 0);
			if (!ct) {
				kfree(param.pe_data);
				return NULL;
			}
			ct->timeout = svc->timeout;
		} else {
			kfree(param.pe_data);
		}
	}

	/* connection flags */
	flags = ((svc->flags & IP_VS_SVC_F_ONEPACKET) &&
		 iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0;
	/* create connection */
	ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol,
			      caddr, cport, vaddr, vport, &param);
	cp = ip_vs_conn_new(&param, dest->af, daddr, dport, flags, dest, 0);
	if (!cp) {
		if (ct)
			ip_vs_conn_put(ct);
		return NULL;
	}
	if (ct) {
		ip_vs_control_add(cp, ct);
		ip_vs_conn_put(ct);
	}
	ip_vs_conn_stats(cp, svc);

	/* return connection (will be used to handle outgoing packet) */
	IP_VS_DBG_BUF(6, "New connection RS-initiated:%c c:%s:%u v:%s:%u "
		      "d:%s:%u conn->flags:%X conn->refcnt:%d\n",
		      ip_vs_fwd_tag(cp),
		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
		      IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),
		      cp->flags, atomic_read(&cp->refcnt));
	LeaveFunction(12);
	return cp;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
marco angaroni
marco angaroni
440
87.30%
2
22.22%
malcolm turnbull
malcolm turnbull
49
9.72%
1
11.11%
jesper dangaard brouer
jesper dangaard brouer
5
0.99%
1
11.11%
hans schillstrom
hans schillstrom
4
0.79%
1
11.11%
julian anastasov
julian anastasov
3
0.60%
2
22.22%
alex gartrell
alex gartrell
2
0.40%
1
11.11%
simon horman
simon horman
1
0.20%
1
11.11%
Total
504
100.00%
9
100.00%

/* Handle outgoing packets which are considered requests initiated by
 * real servers, so that subsequent responses from external client can be
 * routed to the right real server.
 * Used also for outgoing responses in OPS mode.
 *
 * Connection management is handled by persistent-engine specific callback.
 */


static struct ip_vs_conn *__ip_vs_rs_conn_out(unsigned int hooknum,
					      struct netns_ipvs *ipvs,
					      int af, struct sk_buff *skb,
					      const struct ip_vs_iphdr *iph)
{
	struct ip_vs_dest *dest;
	struct ip_vs_conn *cp = NULL;
	__be16 _ports[2], *pptr;

	if (hooknum == NF_INET_LOCAL_IN)
		return NULL;

	pptr = frag_safe_skb_hp(skb, iph->len,
				sizeof(_ports), _ports, iph);
	if (!pptr)
		return NULL;

	rcu_read_lock();
	dest = ip_vs_find_real_service(ipvs, af, iph->protocol,
				       &iph->saddr, pptr[0]);
	if (dest) {
		struct ip_vs_service *svc;
		struct ip_vs_pe *pe;

		svc = rcu_dereference(dest->svc);
		if (svc) {
			pe = rcu_dereference(svc->pe);
			if (pe && pe->conn_out)
				cp = pe->conn_out(svc, dest, skb, iph,
						  pptr[0], pptr[1]);
		}
	}
	rcu_read_unlock();

	return cp;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
marco angaroni
marco angaroni
194
100.00%
1
100.00%
Total
194
100.00%
1
100.00%

/* Handle response packets: rewrite addresses and send away...
 */

static unsigned int

handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
		struct ip_vs_conn *cp, struct ip_vs_iphdr *iph,
		unsigned int hooknum)
{
	struct ip_vs_protocol *pp = pd->pp;

	IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet");

	if (!skb_make_writable(skb, iph->len))
		goto drop;

	/* mangle the packet */
	if (pp->snat_handler && !pp->snat_handler(skb, pp, cp, iph))
		goto drop;

#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		ipv6_hdr(skb)->saddr = cp->vaddr.in6;
	else
#endif
	{
		ip_hdr(skb)->saddr = cp->vaddr.ip;
		ip_send_check(ip_hdr(skb));
	}

	/*
         * nf_iterate does not expect change in the skb->dst->dev.
         * It looks like it is not fatal to enable this code for hooks
         * where our handlers are at the end of the chain list and
         * when all next handlers use skb->dst->dev and not outdev.
         * It will definitely route properly the inout NAT traffic
         * when multiple paths are used.
         */

	/* For policy routing, packets originating from this
         * machine itself may be routed differently to packets
         * passing through.  We want this packet to be routed as
         * if it came from this machine itself.  So re-compute
         * the routing information.
         */
	if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum))
		goto drop;

	IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT");

	ip_vs_out_stats(cp, skb);
	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd);
	skb->ipvs_property = 1;
	if (!(cp->flags & IP_VS_CONN_F_NFCT))
		ip_vs_notrack(skb);
	else
		ip_vs_update_conntrack(skb, cp, 0);
	ip_vs_conn_put(cp);

	LeaveFunction(11);
	return NF_ACCEPT;

drop:
	ip_vs_conn_put(cp);
	kfree_skb(skb);
	LeaveFunction(11);
	return NF_STOLEN;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
marco angaroni
marco angaroni
178
66.67%
1
12.50%
malcolm turnbull
malcolm turnbull
43
16.10%
1
12.50%
julian anastasov
julian anastasov
37
13.86%
3
37.50%
julius volz
julius volz
7
2.62%
1
12.50%
alex gartrell
alex gartrell
1
0.37%
1
12.50%
hans schillstrom
hans schillstrom
1
0.37%
1
12.50%
Total
267
100.00%
8
100.00%

/*
 *      Check if outgoing packet belongs to the established ip_vs_conn.
 */

static unsigned int

ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af)
{
	struct ip_vs_iphdr iph;
	struct ip_vs_protocol *pp;
	struct ip_vs_proto_data *pd;
	struct ip_vs_conn *cp;
	struct sock *sk;

	EnterFunction(11);

	/* Already marked as IPVS request or reply? */
	if (skb->ipvs_property)
		return NF_ACCEPT;

	sk = skb_to_full_sk(skb);
	/* Bad... Do not break raw sockets */
	if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT &&
		     af == AF_INET)) {

		if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag)
			return NF_ACCEPT;
	}

	if (unlikely(!skb_dst(skb)))
		return NF_ACCEPT;

	if (!ipvs->enable)
		return NF_ACCEPT;

	ip_vs_fill_iph_skb(af, skb, false, &iph);
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6) {
		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
			int related;
			int verdict = ip_vs_out_icmp_v6(ipvs, skb, &related,
							hooknum, &iph);

			if (related)
				return verdict;
		}
	} else
#endif
		if (unlikely(iph.protocol == IPPROTO_ICMP)) {
			int related;
			int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum);

			if (related)
				return verdict;
		}

	pd = ip_vs_proto_data_get(ipvs, iph.protocol);
	if (unlikely(!pd))
		return NF_ACCEPT;
	pp = pd->pp;

	/* reassemble IP fragments */
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET)
#endif
		if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) {
			if (ip_vs_gather_frags(ipvs, skb,
					       ip_vs_defrag_user(hooknum)))
				return NF_STOLEN;

			ip_vs_fill_iph_skb(AF_INET, skb, false, &iph);
		}

	/*
         * Check if the packet belongs to an existing entry
         */
	cp = pp->conn_out_get(ipvs, af, skb, &iph);

	if (likely(cp))
		return handle_response(af, skb, pd, cp, &iph, hooknum);

	/* Check for real-server-started requests */
	if (atomic_read(&ipvs->conn_out_counter)) {
		/* Currently only for UDP:
                 * connection oriented protocols typically use
                 * ephemeral ports for outgoing connections, so
                 * related incoming responses would not match any VS
                 */
		if (pp->protocol == IPPROTO_UDP) {
			cp = __ip_vs_rs_conn_out(hooknum, ipvs, af, skb, &iph);
			if (likely(cp))
				return handle_response(af, skb, pd, cp, &iph,
						       hooknum);
		}
	}

	if (sysctl_nat_icmp_send(ipvs) &&
	    (pp->protocol == IPPROTO_TCP ||
	     pp->protocol == IPPROTO_UDP ||
	     pp->protocol == IPPROTO_SCTP)) {
		__be16 _ports[2], *pptr;

		pptr = frag_safe_skb_hp(skb, iph.len,
					 sizeof(_ports), _ports, &iph);
		if (pptr == NULL)
			return NF_ACCEPT;	/* Not for me */
		if (ip_vs_has_real_service(ipvs, af, iph.protocol, &iph.saddr,
					   pptr[0])) {
			/*
                         * Notify the real server: there is no
                         * existing entry if it is not RST
                         * packet or not TCP packet.
                         */
			if ((iph.protocol != IPPROTO_TCP &&
			     iph.protocol != IPPROTO_SCTP)
			     || ((iph.protocol == IPPROTO_TCP
				  && !is_tcp_reset(skb, iph.len))
				 || (iph.protocol == IPPROTO_SCTP
					&& !is_sctp_abort(skb,
						iph.len)))) {
#ifdef CONFIG_IP_VS_IPV6
				if (af == AF_INET6) {
					if (!skb->dev)
						skb->dev = ipvs->net->loopback_dev;
					icmpv6_send(skb,
						    ICMPV6_DEST_UNREACH,
						    ICMPV6_PORT_UNREACH,
						    0);
				} else
#endif
					icmp_send(skb,
						  ICMP_DEST_UNREACH,
						  ICMP_PORT_UNREACH, 0);
				return NF_DROP;
			}
		}
	}
	IP_VS_DBG_PKT(12, af, pp, skb, iph.off,
		      "ip_vs_out: packet continues traversal as normal");
	return NF_ACCEPT;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julius volz
julius volz
286
43.60%
2
6.45%
julian anastasov
julian anastasov
97
14.79%
6
19.35%
malcolm turnbull
malcolm turnbull
81
12.35%
1
3.23%
marco angaroni
marco angaroni
64
9.76%
1
3.23%
venkata mohan reddy
venkata mohan reddy
42
6.40%
1
3.23%
hans schillstrom
hans schillstrom
24
3.66%
4
12.90%
eric w. biederman
eric w. biederman
20
3.05%
7
22.58%
eric dumazet
eric dumazet
16
2.44%
1
3.23%
alex gartrell
alex gartrell
10
1.52%
2
6.45%
jesper dangaard brouer
jesper dangaard brouer
10
1.52%
3
9.68%
david ahern
david ahern
2
0.30%
1
3.23%
paul gortmaker
paul gortmaker
2
0.30%
1
3.23%
simon horman
simon horman
2
0.30%
1
3.23%
Total
656
100.00%
31
100.00%

/*
 *      It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain,
 *      used only for VS/NAT.
 *      Check if packet is reply for established ip_vs_conn.
 */

static unsigned int

ip_vs_reply4(void *priv, struct sk_buff *skb,
	     const struct nf_hook_state *state)
{
	return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
26
63.41%
1
16.67%
eric w. biederman
eric w. biederman
11
26.83%
3
50.00%
patrick mchardy
patrick mchardy
2
4.88%
1
16.67%
david s. miller
david s. miller
2
4.88%
1
16.67%
Total
41
100.00%
6
100.00%

/*
 *      It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT.
 *      Check if packet is reply for established ip_vs_conn.
 */

static unsigned int

ip_vs_local_reply4(void *priv, struct sk_buff *skb,
		   const struct nf_hook_state *state)
{
	return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
26
63.41%
2
28.57%
eric w. biederman
eric w. biederman
11
26.83%
3
42.86%
david s. miller
david s. miller
2
4.88%
1
14.29%
patrick mchardy
patrick mchardy
2
4.88%
1
14.29%
Total
41
100.00%
7
100.00%

#ifdef CONFIG_IP_VS_IPV6

/*
 *      It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain,
 *      used only for VS/NAT.
 *      Check if packet is reply for established ip_vs_conn.
 */

static unsigned int

ip_vs_reply6(void *priv, struct sk_buff *skb,
	     const struct nf_hook_state *state)
{
	return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
26
63.41%
1
16.67%
eric w. biederman
eric w. biederman
11
26.83%
3
50.00%
patrick mchardy
patrick mchardy
2
4.88%
1
16.67%
david s. miller
david s. miller
2
4.88%
1
16.67%
Total
41
100.00%
6
100.00%

/*
 *      It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT.
 *      Check if packet is reply for established ip_vs_conn.
 */

static unsigned int

ip_vs_local_reply6(void *priv, struct sk_buff *skb,
		   const struct nf_hook_state *state)
{
	return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
26
63.41%
2
28.57%
eric w. biederman
eric w. biederman
11
26.83%
3
42.86%
patrick mchardy
patrick mchardy
2
4.88%
1
14.29%
david s. miller
david s. miller
2
4.88%
1
14.29%
Total
41
100.00%
7
100.00%

#endif


static unsigned int

ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
		      struct ip_vs_proto_data *pd,
		      int *verdict, struct ip_vs_conn **cpp,
		      struct ip_vs_iphdr *iph)
{
	struct ip_vs_protocol *pp = pd->pp;

	if (!iph->fragoffs) {
		/* No (second) fragments need to enter here, as nf_defrag_ipv6
                 * replayed fragment zero will already have created the cp
                 */

		/* Schedule and create new connection entry into cpp */
		if (!pp->conn_schedule(ipvs, af, skb, pd, verdict, cpp, iph))
			return 0;
	}

	if (unlikely(!*cpp)) {
		/* sorry, all this trouble for a no-hit :) */
		IP_VS_DBG_PKT(12, af, pp, skb, iph->off,
			      "ip_vs_in: packet continues traversal as normal");
		if (iph->fragoffs) {
			/* Fragment that couldn't be mapped to a conn entry
                         * is missing module nf_defrag_ipv6
                         */
			IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n");
			IP_VS_DBG_PKT(7, af, pp, skb, iph->off,
				      "unhandled fragment");
		}
		*verdict = NF_ACCEPT;
		return 0;
	}

	return 1;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
alex gartrell
alex gartrell
149
95.51%
1
50.00%
eric w. biederman
eric w. biederman
7
4.49%
1
50.00%
Total
156
100.00%
2
100.00%

/*
 *      Handle ICMP messages in the outside-to-inside direction (incoming).
 *      Find any that might be relevant, check against existing connections,
 *      forward to the right destination host if relevant.
 *      Currently handles error types - unreachable, quench, ttl exceeded.
 */

static int

ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
	      unsigned int hooknum)
{
	struct iphdr *iph;
	struct icmphdr	_icmph, *ic;
	struct iphdr	_ciph, *cih;	/* The ip header contained within the ICMP */
	struct ip_vs_iphdr ciph;
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp;
	struct ip_vs_proto_data *pd;
	unsigned int offset, offset2, ihl, verdict;
	bool ipip, new_cp = false;

	*related = 1;

	/* reassemble IP fragments */
	if (ip_is_fragment(ip_hdr(skb))) {
		if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum)))
			return NF_STOLEN;
	}

	iph = ip_hdr(skb);
	offset = ihl = iph->ihl * 4;
	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
	if (ic == NULL)
		return NF_DROP;

	IP_VS_DBG(12, "Incoming ICMP (%d,%d) %pI4->%pI4\n",
		  ic->type, ntohs(icmp_id(ic)),
		  &iph->saddr, &iph->daddr);

	/*
         * Work through seeing if this is for us.
         * These checks are supposed to be in an order that means easy
         * things are checked first to speed up processing.... however
         * this means that some packets will manage to get a long way
         * down this stack and then be rejected, but that's life.
         */
	if ((ic->type != ICMP_DEST_UNREACH) &&
	    (ic->type != ICMP_SOURCE_QUENCH) &&
	    (ic->type != ICMP_TIME_EXCEEDED)) {
		*related = 0;
		return NF_ACCEPT;
	}

	/* Now find the contained IP header */
	offset += sizeof(_icmph);
	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
	if (cih == NULL)
		return NF_ACCEPT; /* The packet looks wrong, ignore */

	/* Special case for errors for IPIP packets */
	ipip = false;
	if (cih->protocol == IPPROTO_IPIP) {
		if (unlikely(cih->frag_off & htons(IP_OFFSET)))
			return NF_ACCEPT;
		/* Error for our IPIP must arrive at LOCAL_IN */
		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
			return NF_ACCEPT;
		offset += cih->ihl * 4;
		cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
		if (cih == NULL)
			return NF_ACCEPT; /* The packet looks wrong, ignore */
		ipip = true;
	}

	pd = ip_vs_proto_data_get(ipvs, cih->protocol);
	if (!pd)
		return NF_ACCEPT;
	pp = pd->pp;

	/* Is the embedded protocol header present? */
	if (unlikely(cih->frag_off & htons(IP_OFFSET) &&
		     pp->dont_defrag))
		return NF_ACCEPT;

	IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
		      "Checking incoming ICMP for");

	offset2 = offset;
	ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !ipip, &ciph);
	offset = ciph.len;

	/* The embedded headers contain source and dest in reverse order.
         * For IPIP this is error for request, not for reply.
         */
	cp = pp->conn_in_get(ipvs, AF_INET, skb, &ciph);

	if (!cp) {
		int v;

		if (!sysctl_schedule_icmp(ipvs))
			return NF_ACCEPT;

		if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph))
			return v;
		new_cp = true;
	}

	verdict = NF_DROP;

	/* Ensure the checksum is correct */
	if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
		/* Failed checksum! */
		IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n",
			  &iph->saddr);
		goto out;
	}

	if (ipip) {
		__be32 info = ic->un.gateway;
		__u8 type = ic->type;
		__u8 code = ic->code;

		/* Update the MTU */
		if (ic->type == ICMP_DEST_UNREACH &&
		    ic->code == ICMP_FRAG_NEEDED) {
			struct ip_vs_dest *dest = cp->dest;
			u32 mtu = ntohs(ic->un.frag.mtu);
			__be16 frag_off = cih->frag_off;

			/* Strip outer IP and ICMP, go to IPIP header */
			if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL)
				goto ignore_ipip;
			offset2 -= ihl + sizeof(_icmph);
			skb_reset_network_header(skb);
			IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
				&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu);
			ipv4_update_pmtu(skb, ipvs->net,
					 mtu, 0, 0, 0, 0);
			/* Client uses PMTUD? */
			if (!(frag_off & htons(IP_DF)))
				goto ignore_ipip;
			/* Prefer the resulting PMTU */
			if (dest) {
				struct ip_vs_dest_dst *dest_dst;

				rcu_read_lock();
				dest_dst = rcu_dereference(dest->dest_dst);
				if (dest_dst)
					mtu = dst_mtu(dest_dst->dst_cache);
				rcu_read_unlock();
			}
			if (mtu > 68 + sizeof(struct iphdr))
				mtu -= sizeof(struct iphdr);
			info = htonl(mtu);
		}
		/* Strip outer IP, ICMP and IPIP, go to IP header of
                 * original request.
                 */
		if (pskb_pull(skb, offset2) == NULL)
			goto ignore_ipip;
		skb_reset_network_header(skb);
		IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
			&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
			type, code, ntohl(info));
		icmp_send(skb, type, code, info);
		/* ICMP can be shorter but anyways, account it */
		ip_vs_out_stats(cp, skb);

ignore_ipip:
		consume_skb(skb);
		verdict = NF_STOLEN;
		goto out;
	}

	/* do the statistics and put it back */
	ip_vs_in_stats(cp, skb);
	if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol ||
	    IPPROTO_SCTP == cih->protocol)
		offset += 2 * sizeof(__u16);
	verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph);

out:
	if (likely(!new_cp))
		__ip_vs_conn_put(cp);
	else
		ip_vs_conn_put(cp);

	return verdict;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
419
44.48%
9
30.00%
julius volz
julius volz
312
33.12%
1
3.33%
alex gartrell
alex gartrell
67
7.11%
3
10.00%
wensong zhang
wensong zhang
43
4.56%
1
3.33%
peter christensen
peter christensen
39
4.14%
1
3.33%
hans schillstrom
hans schillstrom
17
1.80%
1
3.33%
eric w. biederman
eric w. biederman
15
1.59%
6
20.00%
jesper dangaard brouer
jesper dangaard brouer
9
0.96%
2
6.67%
david s. miller
david s. miller
6
0.64%
1
3.33%
harvey harrison
harvey harrison
5
0.53%
1
3.33%
simon horman
simon horman
4
0.42%
1
3.33%
arnaldo carvalho de melo
arnaldo carvalho de melo
2
0.21%
1
3.33%
herbert xu
herbert xu
2
0.21%
1
3.33%
paul gortmaker
paul gortmaker
2
0.21%
1
3.33%
Total
942
100.00%
30
100.00%

#ifdef CONFIG_IP_VS_IPV6


static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
			    int *related, unsigned int hooknum,
			    struct ip_vs_iphdr *iph)
{
	struct icmp6hdr	_icmph, *ic;
	struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp;
	struct ip_vs_proto_data *pd;
	unsigned int offset, verdict;
	bool new_cp = false;

	*related = 1;

	ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph, iph);
	if (ic == NULL)
		return NF_DROP;

	/*
         * Work through seeing if this is for us.
         * These checks are supposed to be in an order that means easy
         * things are checked first to speed up processing.... however
         * this means that some packets will manage to get a long way
         * down this stack and then be rejected, but that's life.
         */
	if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) {
		*related = 0;
		return NF_ACCEPT;
	}
	/* Fragment header that is before ICMP header tells us that:
         * it's not an error message since they can't be fragmented.
         */
	if (iph->flags & IP6_FH_F_FRAG)
		return NF_DROP;

	IP_VS_DBG(8, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n",
		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
		  &iph->saddr, &iph->daddr);

	offset = iph->len + sizeof(_icmph);
	if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, offset, true, &ciph))
		return NF_ACCEPT;

	pd = ip_vs_proto_data_get(ipvs, ciph.protocol);
	if (!pd)
		return NF_ACCEPT;
	pp = pd->pp;

	/* Cannot handle fragmented embedded protocol */
	if (ciph.fragoffs)
		return NF_ACCEPT;

	IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset,
		      "Checking incoming ICMPv6 for");

	/* The embedded headers contain source and dest in reverse order
         * if not from localhost
         */
	cp = pp->conn_in_get(ipvs, AF_INET6, skb, &ciph);

	if (!cp) {
		int v;

		if (!sysctl_schedule_icmp(ipvs))
			return NF_ACCEPT;

		if (!ip_vs_try_to_schedule(ipvs, AF_INET6, skb, pd, &v, &cp, &ciph))
			return v;

		new_cp = true;
	}

	/* VS/TUN, VS/DR and LOCALNODE just let it go */
	if ((hooknum == NF_INET_LOCAL_OUT) &&
	    (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) {
		verdict = NF_ACCEPT;
		goto out;
	}

	/* do the statistics and put it back */
	ip_vs_in_stats(cp, skb);

	/* Need to mangle contained IPv6 header in ICMPv6 packet */
	offset = ciph.len;
	if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol ||
	    IPPROTO_SCTP == ciph.protocol)
		offset += 2 * sizeof(__u16); /* Also mangle ports */

	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph);

out:
	if (likely(!new_cp))
		__ip_vs_conn_put(cp);
	else
		ip_vs_conn_put(cp);

	return verdict;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
jesper dangaard brouer
jesper dangaard brouer
123
28.15%
4
15.38%
wensong zhang
wensong zhang
119
27.23%
1
3.85%
alex gartrell
alex gartrell
80
18.31%
3
11.54%
julian anastasov
julian anastasov
41
9.38%
4
15.38%
david s. miller
david s. miller
23
5.26%
2
7.69%
hans schillstrom
hans schillstrom
16
3.66%
1
3.85%
julius volz
julius volz
14
3.20%
2
7.69%
eric w. biederman
eric w. biederman
11
2.52%
5
19.23%
patrick mchardy
patrick mchardy
4
0.92%
1
3.85%
venkata mohan reddy
venkata mohan reddy
3
0.69%
1
3.85%
harvey harrison
harvey harrison
2
0.46%
1
3.85%
herbert xu
herbert xu
1
0.23%
1
3.85%
Total
437
100.00%
26
100.00%

#endif


/*
 *      Check if it's for virtual services, look it up,
 *      and send it on its way...
 */

static unsigned int

ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af)
{
	struct ip_vs_iphdr iph;
	struct ip_vs_protocol *pp;
	struct ip_vs_proto_data *pd;
	struct ip_vs_conn *cp;
	int ret, pkts;
	int conn_reuse_mode;
	struct sock *sk;

	/* Already marked as IPVS request or reply? */
	if (skb->ipvs_property)
		return NF_ACCEPT;

	/*
         *      Big tappo:
         *      - remote client: only PACKET_HOST
         *      - route: used for struct net when skb->dev is unset
         */
	if (unlikely((skb->pkt_type != PACKET_HOST &&
		      hooknum != NF_INET_LOCAL_OUT) ||
		     !skb_dst(skb))) {
		ip_vs_fill_iph_skb(af, skb, false, &iph);
		IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s"
			      " ignored in hook %u\n",
			      skb->pkt_type, iph.protocol,
			      IP_VS_DBG_ADDR(af, &iph.daddr), hooknum);
		return NF_ACCEPT;
	}
	/* ipvs enabled in this netns ? */
	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
		return NF_ACCEPT;

	ip_vs_fill_iph_skb(af, skb, false, &iph);

	/* Bad... Do not break raw sockets */
	sk = skb_to_full_sk(skb);
	if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT &&
		     af == AF_INET)) {

		if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag)
			return NF_ACCEPT;
	}

#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6) {
		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
			int related;
			int verdict = ip_vs_in_icmp_v6(ipvs, skb, &related,
						       hooknum, &iph);

			if (related)
				return verdict;
		}
	} else
#endif
		if (unlikely(iph.protocol == IPPROTO_ICMP)) {
			int related;
			int verdict = ip_vs_in_icmp(ipvs, skb, &related,
						    hooknum);

			if (related)
				return verdict;
		}

	/* Protocol supported? */
	pd = ip_vs_proto_data_get(ipvs, iph.protocol);
	if (unlikely(!pd)) {
		/* The only way we'll see this packet again is if it's
                 * encapsulated, so mark it with ipvs_property=1 so we
                 * skip it if we're ignoring tunneled packets
                 */
		if (sysctl_ignore_tunneled(ipvs))
			skb->ipvs_property = 1;

		return NF_ACCEPT;
	}
	pp = pd->pp;
	/*
         * Check if the packet belongs to an existing connection entry
         */
	cp = pp->conn_in_get(ipvs, af, skb, &iph);

	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
		bool uses_ct = false, resched = false;

		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
		    unlikely(!atomic_read(&cp->dest->weight))) {
			resched = true;
			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
			if (!atomic_read(&cp->n_control)) {
				resched = true;
			} else {
				/* Do not reschedule controlling connection
                                 * that uses conntrack while it is still
                                 * referenced by controlled connection(s).
                                 */
				resched = !uses_ct;
			}
		}

		if (resched) {
			if (!atomic_read(&cp->n_control))
				ip_vs_conn_expire_now(cp);
			__ip_vs_conn_put(cp);
			if (uses_ct)
				return NF_DROP;
			cp = NULL;
		}
	}

	if (unlikely(!cp)) {
		int v;

		if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph))
			return v;
	}

	IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet");

	/* Check the server status */
	if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
		/* the destination server is not available */

		if (sysctl_expire_nodest_conn(ipvs)) {
			/* try to expire the connection immediately */
			ip_vs_conn_expire_now(cp);
		}
		/* don't restart its timer, and silently
                   drop the packet. */
		__ip_vs_conn_put(cp);
		return NF_DROP;
	}

	ip_vs_in_stats(cp, skb);
	ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
	if (cp->packet_xmit)
		ret = cp->packet_xmit(skb, cp, pp, &iph);
		/* do not touch skb anymore */
	else {
		IP_VS_DBG_RL("warning: packet_xmit is null");
		ret = NF_ACCEPT;
	}

	/* Increase its packet counter and check if it is needed
         * to be synchronized
         *
         * Sync connection if it is about to close to
         * encorage the standby servers to update the connections timeout
         *
         * For ONE_PKT let ip_vs_sync_conn() do the filter work.
         */

	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
		pkts = sysctl_sync_threshold(ipvs);
	else
		pkts = atomic_add_return(1, &cp->in_pkts);

	if (ipvs->sync_state & IP_VS_STATE_MASTER)
		ip_vs_sync_conn(ipvs, cp, pkts);
	else if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control)
		/* increment is done inside ip_vs_sync_conn too */
		atomic_inc(&cp->control->in_pkts);

	ip_vs_conn_put(cp);
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
238
31.19%
2
4.35%
julian anastasov
julian anastasov
191
25.03%
10
21.74%
julius volz
julius volz
77
10.09%
3
6.52%
grzegorz lyczba
grzegorz lyczba
48
6.29%
1
2.17%
hans schillstrom
hans schillstrom
44
5.77%
5
10.87%
marcelo ricardo leitner
marcelo ricardo leitner
41
5.37%
1
2.17%
marco angaroni
marco angaroni
26
3.41%
1
2.17%
alex gartrell
alex gartrell
24
3.15%
4
8.70%
eric dumazet
eric dumazet
16
2.10%
1
2.17%
eric w. biederman
eric w. biederman
15
1.97%
6
13.04%
simon horman
simon horman
13
1.70%
4
8.70%
jesper dangaard brouer
jesper dangaard brouer
12
1.57%
3
6.52%
malcolm turnbull
malcolm turnbull
9
1.18%
1
2.17%
venkata mohan reddy
venkata mohan reddy
4
0.52%
1
2.17%
herbert xu
herbert xu
2
0.26%
1
2.17%
patrick mchardy
patrick mchardy
2
0.26%
1
2.17%
arnaldo carvalho de melo
arnaldo carvalho de melo
1
0.13%
1
2.17%
Total
763
100.00%
46
100.00%

/*
 *      AF_INET handler in NF_INET_LOCAL_IN chain
 *      Schedule and forward packets from remote clients
 */

static unsigned int

ip_vs_remote_request4(void *priv, struct sk_buff *skb,
		      const struct nf_hook_state *state)
{
	return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
26
63.41%
1
16.67%
eric w. biederman
eric w. biederman
11
26.83%
3
50.00%
patrick mchardy
patrick mchardy
2
4.88%
1
16.67%
david s. miller
david s. miller
2
4.88%
1
16.67%
Total
41
100.00%
6
100.00%

/*
 *      AF_INET handler in NF_INET_LOCAL_OUT chain
 *      Schedule and forward packets from local clients
 */

static unsigned int

ip_vs_local_request4(void *priv, struct sk_buff *skb,
		     const struct nf_hook_state *state)
{
	return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
26
63.41%
2
28.57%
eric w. biederman
eric w. biederman
11
26.83%
3
42.86%
patrick mchardy
patrick mchardy
2
4.88%
1
14.29%
david s. miller
david s. miller
2
4.88%
1
14.29%
Total
41
100.00%
7
100.00%

#ifdef CONFIG_IP_VS_IPV6

/*
 *      AF_INET6 handler in NF_INET_LOCAL_IN chain
 *      Schedule and forward packets from remote clients
 */

static unsigned int

ip_vs_remote_request6(void *priv, struct sk_buff *skb,
		      const struct nf_hook_state *state)
{
	return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
26
63.41%
1
16.67%
eric w. biederman
eric w. biederman
11
26.83%
3
50.00%
david s. miller
david s. miller
2
4.88%
1
16.67%
patrick mchardy
patrick mchardy
2
4.88%
1
16.67%
Total
41
100.00%
6
100.00%

/*
 *      AF_INET6 handler in NF_INET_LOCAL_OUT chain
 *      Schedule and forward packets from local clients
 */

static unsigned int

ip_vs_local_request6(void *priv, struct sk_buff *skb,
		     const struct nf_hook_state *state)
{
	return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
26
63.41%
2
28.57%
eric w. biederman
eric w. biederman
11
26.83%
3
42.86%
patrick mchardy
patrick mchardy
2
4.88%
1
14.29%
david s. miller
david s. miller
2
4.88%
1
14.29%
Total
41
100.00%
7
100.00%

#endif


/*
 *      It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP
 *      related packets destined for 0.0.0.0/0.
 *      When fwmark-based virtual service is used, such as transparent
 *      cache cluster, TCP packets can be marked and routed to ip_vs_in,
 *      but ICMP destined for 0.0.0.0/0 cannot not be easily marked and
 *      sent to ip_vs_in_icmp. So, catch them at the NF_INET_FORWARD chain
 *      and send them to ip_vs_in_icmp.
 */

static unsigned int

ip_vs_forward_icmp(void *priv, struct sk_buff *skb,
		   const struct nf_hook_state *state)
{
	int r;
	struct netns_ipvs *ipvs = net_ipvs(state->net);

	if (ip_hdr(skb)->protocol != IPPROTO_ICMP)
		return NF_ACCEPT;

	/* ipvs enabled in this netns ? */
	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
		return NF_ACCEPT;

	return ip_vs_in_icmp(ipvs, skb, &r, state->hook);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
37
43.53%
1
10.00%
julian anastasov
julian anastasov
16
18.82%
1
10.00%
eric w. biederman
eric w. biederman
13
15.29%
2
20.00%
hans schillstrom
hans schillstrom
8
9.41%
1
10.00%
patrick mchardy
patrick mchardy
3
3.53%
2
20.00%
herbert xu
herbert xu
3
3.53%
1
10.00%
arnaldo carvalho de melo
arnaldo carvalho de melo
3
3.53%
1
10.00%
david s. miller
david s. miller
2
2.35%
1
10.00%
Total
85
100.00%
10
100.00%

#ifdef CONFIG_IP_VS_IPV6

static unsigned int

ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb,
		      const struct nf_hook_state *state)
{
	int r;
	struct netns_ipvs *ipvs = net_ipvs(state->net);
	struct ip_vs_iphdr iphdr;

	ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr);
	if (iphdr.protocol != IPPROTO_ICMPV6)
		return NF_ACCEPT;

	/* ipvs enabled in this netns ? */
	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
		return NF_ACCEPT;

	return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
julius volz
julius volz
39
38.61%
1
10.00%
jesper dangaard brouer
jesper dangaard brouer
18
17.82%
2
20.00%
julian anastasov
julian anastasov
17
16.83%
1
10.00%
eric w. biederman
eric w. biederman
13
12.87%
2
20.00%
hans schillstrom
hans schillstrom
8
7.92%
1
10.00%
david s. miller
david s. miller
2
1.98%
1
10.00%
alex gartrell
alex gartrell
2
1.98%
1
10.00%
patrick mchardy
patrick mchardy
2
1.98%
1
10.00%
Total
101
100.00%
10
100.00%

#endif



static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
	/* After packet filtering, change source only for VS/NAT */
	{
		.hook		= ip_vs_reply4,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP_PRI_NAT_SRC - 2,
        },
	/* After packet filtering, forward packet through VS/DR, VS/TUN,
         * or VS/NAT(change destination), so that filtering rules can be
         * applied to IPVS. */
	{
		.hook		= ip_vs_remote_request4,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP_PRI_NAT_SRC - 1,
        },
	/* Before ip_vs_in, change source only for VS/NAT */
	{
		.hook		= ip_vs_local_reply4,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP_PRI_NAT_DST + 1,
        },
	/* After mangle, schedule and forward local requests */
	{
		.hook		= ip_vs_local_request4,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP_PRI_NAT_DST + 2,
        },
	/* After packet filtering (but before ip_vs_out_icmp), catch icmp
         * destined for 0.0.0.0/0, which is for incoming IPVS connections */
	{
		.hook		= ip_vs_forward_icmp,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_FORWARD,
		.priority	= 99,
        },
	/* After packet filtering, change source only for VS/NAT */
	{
		.hook		= ip_vs_reply4,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_FORWARD,
		.priority	= 100,
        },
#ifdef CONFIG_IP_VS_IPV6
	/* After packet filtering, change source only for VS/NAT */
	{
		.hook		= ip_vs_reply6,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP6_PRI_NAT_SRC - 2,
        },
	/* After packet filtering, forward packet through VS/DR, VS/TUN,
         * or VS/NAT(change destination), so that filtering rules can be
         * applied to IPVS. */
	{
		.hook		= ip_vs_remote_request6,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP6_PRI_NAT_SRC - 1,
        },
	/* Before ip_vs_in, change source only for VS/NAT */
	{
		.hook		= ip_vs_local_reply6,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP6_PRI_NAT_DST + 1,
        },
	/* After mangle, schedule and forward local requests */
	{
		.hook		= ip_vs_local_request6,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP6_PRI_NAT_DST + 2,
        },
	/* After packet filtering (but before ip_vs_out_icmp), catch icmp
         * destined for 0.0.0.0/0, which is for incoming IPVS connections */
	{
		.hook		= ip_vs_forward_icmp_v6,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_FORWARD,
		.priority	= 99,
        },
	/* After packet filtering, change source only for VS/NAT */
	{
		.hook		= ip_vs_reply6,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_FORWARD,
		.priority	= 100,
        },
#endif
};
/*
 *      Initialize IP Virtual Server netns mem.
 */


static int __net_init __ip_vs_init(struct net *net)
{
	struct netns_ipvs *ipvs;

	ipvs = net_generic(net, ip_vs_net_id);
	if (ipvs == NULL)
		return -ENOMEM;

	/* Hold the beast until a service is registerd */
	ipvs->enable = 0;
	ipvs->net = net;
	/* Counters used for creating unique names */
	ipvs->gen = atomic_read(&ipvs_netns_cnt);
	atomic_inc(&ipvs_netns_cnt);
	net->ipvs = ipvs;

	if (ip_vs_estimator_net_init(ipvs) < 0)
		goto estimator_fail;

	if (ip_vs_control_net_init(ipvs) < 0)
		goto control_fail;

	if (ip_vs_protocol_net_init(ipvs) < 0)
		goto protocol_fail;

	if (ip_vs_app_net_init(ipvs) < 0)
		goto app_fail;

	if (ip_vs_conn_net_init(ipvs) < 0)
		goto conn_fail;

	if (ip_vs_sync_net_init(ipvs) < 0)
		goto sync_fail;

	printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n",
			 sizeof(struct netns_ipvs), ipvs->gen);
	return 0;
/*
 * Error handling
 */

sync_fail:
	ip_vs_conn_net_cleanup(ipvs);
conn_fail:
	ip_vs_app_net_cleanup(ipvs);
app_fail:
	ip_vs_protocol_net_cleanup(ipvs);
protocol_fail:
	ip_vs_control_net_cleanup(ipvs);
control_fail:
	ip_vs_estimator_net_cleanup(ipvs);
estimator_fail:
	net->ipvs = NULL;
	return -ENOMEM;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
hans schillstrom
hans schillstrom
193
91.47%
4
33.33%
eric w. biederman
eric w. biederman
11
5.21%
6
50.00%
julian anastasov
julian anastasov
6
2.84%
1
8.33%
simon horman
simon horman
1
0.47%
1
8.33%
Total
211
100.00%
12
100.00%



static void __net_exit __ip_vs_cleanup(struct net *net)
{
	struct netns_ipvs *ipvs = net_ipvs(net);

	ip_vs_service_net_cleanup(ipvs);	/* ip_vs_flush() with locks */
	ip_vs_conn_net_cleanup(ipvs);
	ip_vs_app_net_cleanup(ipvs);
	ip_vs_protocol_net_cleanup(ipvs);
	ip_vs_control_net_cleanup(ipvs);
	ip_vs_estimator_net_cleanup(ipvs);
	IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen);
	net->ipvs = NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
hans schillstrom
hans schillstrom
47
67.14%
4
36.36%
eric w. biederman
eric w. biederman
17
24.29%
6
54.55%
julian anastasov
julian anastasov
6
8.57%
1
9.09%
Total
70
100.00%
11
100.00%



static void __net_exit __ip_vs_dev_cleanup(struct net *net)
{
	struct netns_ipvs *ipvs = net_ipvs(net);
	EnterFunction(2);
	ipvs->enable = 0;	/* Disable packet reception */
	smp_wmb();
	ip_vs_sync_net_cleanup(ipvs);
	LeaveFunction(2);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
hans schillstrom
hans schillstrom
35
74.47%
3
75.00%
eric w. biederman
eric w. biederman
12
25.53%
1
25.00%
Total
47
100.00%
4
100.00%


static struct pernet_operations ipvs_core_ops = {
	.init = __ip_vs_init,
	.exit = __ip_vs_cleanup,
	.id   = &ip_vs_net_id,
	.size = sizeof(struct netns_ipvs),
};


static struct pernet_operations ipvs_core_dev_ops = {
	.exit = __ip_vs_dev_cleanup,
};

/*
 *      Initialize IP Virtual Server
 */


static int __init ip_vs_init(void)
{
	int ret;

	ret = ip_vs_control_init();
	if (ret < 0) {
		pr_err("can't setup control.\n");
		goto exit;
	}

	ip_vs_protocol_init();

	ret = ip_vs_conn_init();
	if (ret < 0) {
		pr_err("can't setup connection table.\n");
		goto cleanup_protocol;
	}

	ret = register_pernet_subsys(&ipvs_core_ops);	/* Alloc ip_vs struct */
	if (ret < 0)
		goto cleanup_conn;

	ret = register_pernet_device(&ipvs_core_dev_ops);
	if (ret < 0)
		goto cleanup_sub;

	ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
	if (ret < 0) {
		pr_err("can't register hooks.\n");
		goto cleanup_dev;
	}

	ret = ip_vs_register_nl_ioctl();
	if (ret < 0) {
		pr_err("can't register netlink/ioctl.\n");
		goto cleanup_hooks;
	}

	pr_info("ipvs loaded.\n");

	return ret;

cleanup_hooks:
	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
cleanup_dev:
	unregister_pernet_device(&ipvs_core_dev_ops);
cleanup_sub:
	unregister_pernet_subsys(&ipvs_core_ops);
cleanup_conn:
	ip_vs_conn_cleanup();
cleanup_protocol:
	ip_vs_protocol_cleanup();
	ip_vs_control_cleanup();
exit:
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
93
47.69%
1
14.29%
hans schillstrom
hans schillstrom
92
47.18%
4
57.14%
patrick mchardy
patrick mchardy
6
3.08%
1
14.29%
hannes eder
hannes eder
4
2.05%
1
14.29%
Total
195
100.00%
7
100.00%



static void __exit ip_vs_cleanup(void)
{
	ip_vs_unregister_nl_ioctl();
	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
	unregister_pernet_device(&ipvs_core_dev_ops);
	unregister_pernet_subsys(&ipvs_core_ops);	/* free ip_vs struct */
	ip_vs_conn_cleanup();
	ip_vs_protocol_cleanup();
	ip_vs_control_cleanup();
	pr_info("ipvs unloaded.\n");
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
wensong zhang
wensong zhang
27
55.10%
1
20.00%
hans schillstrom
hans schillstrom
16
32.65%
2
40.00%
patrick mchardy
patrick mchardy
5
10.20%
1
20.00%
hannes eder
hannes eder
1
2.04%
1
20.00%
Total
49
100.00%
5
100.00%


module_init(ip_vs_init);

module_exit(ip_vs_cleanup);
MODULE_LICENSE("GPL");
Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
julian anastasov
julian anastasov
2177
20.76%
39
22.81%
wensong zhang
wensong zhang
1915
18.27%
2
1.17%
julius volz
julius volz
1338
12.76%
8
4.68%
marco angaroni
marco angaroni
937
8.94%
3
1.75%
hans schillstrom
hans schillstrom
849
8.10%
19
11.11%
alex gartrell
alex gartrell
665
6.34%
9
5.26%
simon horman
simon horman
596
5.68%
19
11.11%
jesper dangaard brouer
jesper dangaard brouer
442
4.22%
4
2.34%
malcolm turnbull
malcolm turnbull
365
3.48%
1
0.58%
eric w. biederman
eric w. biederman
303
2.89%
31
18.13%
grzegorz lyczba
grzegorz lyczba
174
1.66%
1
0.58%
david s. miller
david s. miller
142
1.35%
3
1.75%
venkata mohan reddy
venkata mohan reddy
141
1.34%
1
0.58%
marcelo ricardo leitner
marcelo ricardo leitner
125
1.19%
1
0.58%
nick chalk
nick chalk
64
0.61%
1
0.58%
patrick mchardy
patrick mchardy
59
0.56%
5
2.92%
peter christensen
peter christensen
39
0.37%
1
0.58%
eric dumazet
eric dumazet
33
0.31%
2
1.17%
arnaldo carvalho de melo
arnaldo carvalho de melo
21
0.20%
2
1.17%
hannes eder
hannes eder
21
0.20%
2
1.17%
herbert xu
herbert xu
17
0.16%
2
1.17%
harvey harrison
harvey harrison
12
0.11%
2
1.17%
alban crequy
alban crequy
11
0.10%
1
0.58%
sven wegener
sven wegener
9
0.09%
1
0.58%
paul gortmaker
paul gortmaker
6
0.06%
1
0.58%
hideaki yoshifuji
hideaki yoshifuji
6
0.06%
2
1.17%
al viro
al viro
6
0.06%
2
1.17%
stephen rothwell
stephen rothwell
3
0.03%
1
0.58%
tejun heo
tejun heo
3
0.03%
1
0.58%
david ahern
david ahern
2
0.02%
1
0.58%
alexey dobriyan
alexey dobriyan
1
0.01%
1
0.58%
adrian bunk
adrian bunk
1
0.01%
1
0.58%
masanari iida
masanari iida
1
0.01%
1
0.58%
Total
10484
100.00%
171
100.00%
  
Directory: net/netfilter/ipvs

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