/* * 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 <wensong@linuxvirtualserver.org> *              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. * * 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_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){	__u16 ports[2];	if (skb_copy_bits(skb, proto_off, ports, sizeof(ports)) < 0)		return NULL;	if (likely(!inverse)) {		return ip_vs_conn_in_get(iph->protocol,					 iph->saddr, ports[0],					 iph->daddr, ports[1]);	} else {		return ip_vs_conn_in_get(iph->protocol,					 iph->daddr, ports[1],					 iph->saddr, ports[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){	__u16 ports[2];	if (skb_copy_bits(skb, proto_off, ports, sizeof(ports)) < 0)		return NULL;	if (likely(!inverse)) {		return ip_vs_conn_out_get(iph->protocol,					  iph->saddr, ports[0],					  iph->daddr, ports[1]);	} else {		return ip_vs_conn_out_get(iph->protocol,					  iph->daddr, ports[1],					  iph->saddr, ports[0]);	}}static inttcp_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;	if (skb_copy_bits(skb, skb->nh.iph->ihl*4, &tcph, sizeof(tcph)) < 0) {		*verdict = NF_DROP;		return 0;	}	if (tcph.syn &&	    (svc = ip_vs_service_get(skb->nfmark, skb->nh.iph->protocol,				     skb->nh.iph->daddr, tcph.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 voidtcp_fast_csum_update(struct tcphdr *tcph, u32 oldip, u32 newip,		     u16 oldport, u16 newport){	tcph->check =		ip_vs_check_diff(~oldip, newip,				 ip_vs_check_diff(oldport ^ 0xFFFF,						  newport, tcph->check));}static inttcp_snat_handler(struct sk_buff **pskb,		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp){	struct tcphdr *tcph;	unsigned int tcphoff = (*pskb)->nh.iph->ihl * 4;	/* csum_check requires unshared skb */	if (!ip_vs_make_skb_writable(pskb, tcphoff+sizeof(*tcph)))		return 0;	if (unlikely(cp->app != NULL)) {		/* Some checks before mangling */		if (pp->csum_check && !pp->csum_check(*pskb, pp))			return 0;		/* Call application helper if needed */		if (!ip_vs_app_pkt_out(cp, pskb))			return 0;	}	tcph = (void *)(*pskb)->nh.iph + 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 ((*pskb)->ip_summed == CHECKSUM_HW)			(*pskb)->ip_summed = CHECKSUM_NONE;	} else {		/* full checksum calculation */		tcph->check = 0;		(*pskb)->csum = skb_checksum(*pskb, tcphoff,					     (*pskb)->len - tcphoff, 0);		tcph->check = csum_tcpudp_magic(cp->vaddr, cp->caddr,						(*pskb)->len - tcphoff,						cp->protocol,						(*pskb)->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 inttcp_dnat_handler(struct sk_buff **pskb,		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp){	struct tcphdr *tcph;	unsigned int tcphoff = (*pskb)->nh.iph->ihl * 4;	/* csum_check requires unshared skb */	if (!ip_vs_make_skb_writable(pskb, tcphoff+sizeof(*tcph)))		return 0;	if (unlikely(cp->app != NULL)) {		/* Some checks before mangling */		if (pp->csum_check && !pp->csum_check(*pskb, 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, pskb))			return 0;	}	tcph = (void *)(*pskb)->nh.iph + 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 ((*pskb)->ip_summed == CHECKSUM_HW)			(*pskb)->ip_summed = CHECKSUM_NONE;	} else {		/* full checksum calculation */		tcph->check = 0;		(*pskb)->csum = skb_checksum(*pskb, tcphoff,					     (*pskb)->len - tcphoff, 0);		tcph->check = csum_tcpudp_magic(cp->caddr, cp->daddr,						(*pskb)->len - tcphoff,						cp->protocol,						(*pskb)->csum);		(*pskb)->ip_summed = CHECKSUM_UNNECESSARY;	}	return 1;}static inttcp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp){	unsigned int tcphoff = skb->nh.iph->ihl*4;	switch (skb->ip_summed) {	case CHECKSUM_NONE:		skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0);	case CHECKSUM_HW:		if (csum_tcpudp_magic(skb->nh.iph->saddr, skb->nh.iph->daddr,				      skb->len - tcphoff,				      skb->nh.iph->protocol, skb->csum)) {			IP_VS_DBG_RL_PKT(0, pp, skb, 0,					 "Failed checksum for");			return 0;		}		break;	default:		/* CHECKSUM_UNNECESSARY */		break;	}	return 1;}#define TCP_DIR_INPUT		0#define TCP_DIR_OUTPUT		4#define TCP_DIR_INPUT_ONLY	8static 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,};#if 0/* FIXME: This is going to die */static int tcp_timeouts_dos[IP_VS_TCP_S_LAST+1] = {	[IP_VS_TCP_S_NONE]		=	2*HZ,	[IP_VS_TCP_S_ESTABLISHED]	=	8*60*HZ,	[IP_VS_TCP_S_SYN_SENT]		=	60*HZ,	[IP_VS_TCP_S_SYN_RECV]		=	10*HZ,	[IP_VS_TCP_S_FIN_WAIT]		=	60*HZ,	[IP_VS_TCP_S_TIME_WAIT]		=	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]		=	100*HZ,	[IP_VS_TCP_S_LAST]		=	2*HZ,};#endifstatic 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