ip_vs_proto_tcp.c

linux 内核源代码

/*
 * ip_vs_proto_tcp.c:	TCP load balancing support for IPVS
 *
 * Version:     $Id: ip_vs_proto_tcp.c,v 1.3 2002/11/30 01:50:35 wensong Exp $
 *
 * Authors:     Wensong Zhang <[e-mail]>
 *              Julian Anastasov <[e-mail]>
 *
 *              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.
 *
 * Changes:
 *
 */

#include <linux/kernel.h>
#include <linux/ip.h>
#include <linux/tcp.h>                  /* for tcphdr */
#include <net/ip.h>
#include <net/tcp.h>                    /* for csum_tcpudp_magic */
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>

#include <net/ip_vs.h>


static struct ip_vs_conn *
tcp_conn_in_get(const struct sk_buff *skb, struct ip_vs_protocol *pp,
		const struct iphdr *iph, unsigned int proto_off, int inverse)
{
	__be16 _ports[2], *pptr;

	pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
	if (pptr == NULL)
		return NULL;

	if (likely(!inverse)) {
		return ip_vs_conn_in_get(iph->protocol,
					 iph->saddr, pptr[0],
					 iph->daddr, pptr[1]);
	} else {
		return ip_vs_conn_in_get(iph->protocol,
					 iph->daddr, pptr[1],
					 iph->saddr, pptr[0]);
	}
}

static struct ip_vs_conn *
tcp_conn_out_get(const struct sk_buff *skb, struct ip_vs_protocol *pp,
		 const struct iphdr *iph, unsigned int proto_off, int inverse)
{
	__be16 _ports[2], *pptr;

	pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
	if (pptr == NULL)
		return NULL;

	if (likely(!inverse)) {
		return ip_vs_conn_out_get(iph->protocol,
					  iph->saddr, pptr[0],
					  iph->daddr, pptr[1]);
	} else {
		return ip_vs_conn_out_get(iph->protocol,
					  iph->daddr, pptr[1],
					  iph->saddr, pptr[0]);
	}
}


static int
tcp_conn_schedule(struct sk_buff *skb,
		  struct ip_vs_protocol *pp,
		  int *verdict, struct ip_vs_conn **cpp)
{
	struct ip_vs_service *svc;
	struct tcphdr _tcph, *th;

	th = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph);
	if (th == NULL) {
		*verdict = NF_DROP;
		return 0;
	}

	if (th->syn &&
	    (svc = ip_vs_service_get(skb->mark, ip_hdr(skb)->protocol,
				     ip_hdr(skb)->daddr, th->dest))) {
		if (ip_vs_todrop()) {
			/*
			 * It seems that we are very loaded.
			 * We have to drop this packet :(
			 */
			ip_vs_service_put(svc);
			*verdict = NF_DROP;
			return 0;
		}

		/*
		 * Let the virtual server select a real server for the
		 * incoming connection, and create a connection entry.
		 */
		*cpp = ip_vs_schedule(svc, skb);
		if (!*cpp) {
			*verdict = ip_vs_leave(svc, skb, pp);
			return 0;
		}
		ip_vs_service_put(svc);
	}
	return 1;
}


static inline void
tcp_fast_csum_update(struct tcphdr *tcph, __be32 oldip, __be32 newip,
		     __be16 oldport, __be16 newport)
{
	tcph->check =
		csum_fold(ip_vs_check_diff4(oldip, newip,
				 ip_vs_check_diff2(oldport, newport,
						~csum_unfold(tcph->check))));
}


static int
tcp_snat_handler(struct sk_buff *skb,
		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
{
	struct tcphdr *tcph;
	const unsigned int tcphoff = ip_hdrlen(skb);

	/* csum_check requires unshared skb */
	if (!skb_make_writable(skb, tcphoff+sizeof(*tcph)))
		return 0;

	if (unlikely(cp->app != NULL)) {
		/* Some checks before mangling */
		if (pp->csum_check && !pp->csum_check(skb, pp))
			return 0;

		/* Call application helper if needed */
		if (!ip_vs_app_pkt_out(cp, skb))
			return 0;
	}

	tcph = (void *)ip_hdr(skb) + tcphoff;
	tcph->source = cp->vport;

	/* Adjust TCP checksums */
	if (!cp->app) {
		/* Only port and addr are changed, do fast csum update */
		tcp_fast_csum_update(tcph, cp->daddr, cp->vaddr,
				     cp->dport, cp->vport);
		if (skb->ip_summed == CHECKSUM_COMPLETE)
			skb->ip_summed = CHECKSUM_NONE;
	} else {
		/* full checksum calculation */
		tcph->check = 0;
		skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0);
		tcph->check = csum_tcpudp_magic(cp->vaddr, cp->caddr,
						skb->len - tcphoff,
						cp->protocol, skb->csum);
		IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n",
			  pp->name, tcph->check,
			  (char*)&(tcph->check) - (char*)tcph);
	}
	return 1;
}


static int
tcp_dnat_handler(struct sk_buff *skb,
		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
{
	struct tcphdr *tcph;
	const unsigned int tcphoff = ip_hdrlen(skb);

	/* csum_check requires unshared skb */
	if (!skb_make_writable(skb, tcphoff+sizeof(*tcph)))
		return 0;

	if (unlikely(cp->app != NULL)) {
		/* Some checks before mangling */
		if (pp->csum_check && !pp->csum_check(skb, pp))
			return 0;

		/*
		 *	Attempt ip_vs_app call.
		 *	It will fix ip_vs_conn and iph ack_seq stuff
		 */
		if (!ip_vs_app_pkt_in(cp, skb))
			return 0;
	}

	tcph = (void *)ip_hdr(skb) + tcphoff;
	tcph->dest = cp->dport;

	/*
	 *	Adjust TCP checksums
	 */
	if (!cp->app) {
		/* Only port and addr are changed, do fast csum update */
		tcp_fast_csum_update(tcph, cp->vaddr, cp->daddr,
				     cp->vport, cp->dport);
		if (skb->ip_summed == CHECKSUM_COMPLETE)
			skb->ip_summed = CHECKSUM_NONE;
	} else {
		/* full checksum calculation */
		tcph->check = 0;
		skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0);
		tcph->check = csum_tcpudp_magic(cp->caddr, cp->daddr,
						skb->len - tcphoff,
						cp->protocol, skb->csum);
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	}
	return 1;
}


static int
tcp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp)
{
	const unsigned int tcphoff = ip_hdrlen(skb);

	switch (skb->ip_summed) {
	case CHECKSUM_NONE:
		skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0);
	case CHECKSUM_COMPLETE:
		if (csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
				      skb->len - tcphoff,
				      ip_hdr(skb)->protocol, skb->csum)) {
			IP_VS_DBG_RL_PKT(0, pp, skb, 0,
					 "Failed checksum for");
			return 0;
		}
		break;
	default:
		/* No need to checksum. */
		break;
	}

	return 1;
}


#define TCP_DIR_INPUT		0
#define TCP_DIR_OUTPUT		4
#define TCP_DIR_INPUT_ONLY	8

static const int tcp_state_off[IP_VS_DIR_LAST] = {
	[IP_VS_DIR_INPUT]		=	TCP_DIR_INPUT,
	[IP_VS_DIR_OUTPUT]		=	TCP_DIR_OUTPUT,
	[IP_VS_DIR_INPUT_ONLY]		=	TCP_DIR_INPUT_ONLY,
};

/*
 *	Timeout table[state]
 */
static int tcp_timeouts[IP_VS_TCP_S_LAST+1] = {
	[IP_VS_TCP_S_NONE]		=	2*HZ,
	[IP_VS_TCP_S_ESTABLISHED]	=	15*60*HZ,
	[IP_VS_TCP_S_SYN_SENT]		=	2*60*HZ,
	[IP_VS_TCP_S_SYN_RECV]		=	1*60*HZ,
	[IP_VS_TCP_S_FIN_WAIT]		=	2*60*HZ,
	[IP_VS_TCP_S_TIME_WAIT]		=	2*60*HZ,
	[IP_VS_TCP_S_CLOSE]		=	10*HZ,
	[IP_VS_TCP_S_CLOSE_WAIT]	=	60*HZ,
	[IP_VS_TCP_S_LAST_ACK]		=	30*HZ,
	[IP_VS_TCP_S_LISTEN]		=	2*60*HZ,
	[IP_VS_TCP_S_SYNACK]		=	120*HZ,
	[IP_VS_TCP_S_LAST]		=	2*HZ,
};

static char * tcp_state_name_table[IP_VS_TCP_S_LAST+1] = {
	[IP_VS_TCP_S_NONE]		=	"NONE",
	[IP_VS_TCP_S_ESTABLISHED]	=	"ESTABLISHED",
	[IP_VS_TCP_S_SYN_SENT]		=	"SYN_SENT",
	[IP_VS_TCP_S_SYN_RECV]		=	"SYN_RECV",
	[IP_VS_TCP_S_FIN_WAIT]		=	"FIN_WAIT",
	[IP_VS_TCP_S_TIME_WAIT]		=	"TIME_WAIT",
	[IP_VS_TCP_S_CLOSE]		=	"CLOSE",
	[IP_VS_TCP_S_CLOSE_WAIT]	=	"CLOSE_WAIT",
	[IP_VS_TCP_S_LAST_ACK]		=	"LAST_ACK",
	[IP_VS_TCP_S_LISTEN]		=	"LISTEN",
	[IP_VS_TCP_S_SYNACK]		=	"SYNACK",
	[IP_VS_TCP_S_LAST]		=	"BUG!",
};

#define sNO IP_VS_TCP_S_NONE
#define sES IP_VS_TCP_S_ESTABLISHED
#define sSS IP_VS_TCP_S_SYN_SENT
#define sSR IP_VS_TCP_S_SYN_RECV
#define sFW IP_VS_TCP_S_FIN_WAIT
#define sTW IP_VS_TCP_S_TIME_WAIT
#define sCL IP_VS_TCP_S_CLOSE
#define sCW IP_VS_TCP_S_CLOSE_WAIT
#define sLA IP_VS_TCP_S_LAST_ACK
#define sLI IP_VS_TCP_S_LISTEN
#define sSA IP_VS_TCP_S_SYNACK

struct tcp_states_t {
	int next_state[IP_VS_TCP_S_LAST];
};

static const char * tcp_state_name(int state)
{
	if (state >= IP_VS_TCP_S_LAST)
		return "ERR!";