diff options
Diffstat (limited to 'net/ipv4/ipvs')
-rw-r--r-- | net/ipv4/ipvs/Kconfig | 17 | ||||
-rw-r--r-- | net/ipv4/ipvs/Makefile | 3 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_conn.c | 249 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_core.c | 817 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_ctl.c | 1370 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_dh.c | 5 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_est.c | 58 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_ftp.c | 61 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_lblc.c | 220 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_lblcr.c | 249 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_lc.c | 32 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_nq.c | 39 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_proto.c | 65 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_proto_ah.c | 178 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_proto_ah_esp.c | 235 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_proto_esp.c | 176 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_proto_tcp.c | 254 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_proto_udp.c | 227 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_rr.c | 20 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_sed.c | 39 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_sh.c | 5 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_sync.c | 40 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_wlc.c | 39 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_wrr.c | 15 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_xmit.c | 471 |
25 files changed, 3504 insertions, 1380 deletions
diff --git a/net/ipv4/ipvs/Kconfig b/net/ipv4/ipvs/Kconfig index 09d0c3f..de6004d 100644 --- a/net/ipv4/ipvs/Kconfig +++ b/net/ipv4/ipvs/Kconfig @@ -24,6 +24,14 @@ menuconfig IP_VS if IP_VS +config IP_VS_IPV6 + bool "IPv6 support for IPVS (DANGEROUS)" + depends on EXPERIMENTAL && (IPV6 = y || IP_VS = IPV6) + ---help--- + Add IPv6 support to IPVS. This is incomplete and might be dangerous. + + Say N if unsure. + config IP_VS_DEBUG bool "IP virtual server debugging" ---help--- @@ -33,7 +41,8 @@ config IP_VS_DEBUG config IP_VS_TAB_BITS int "IPVS connection table size (the Nth power of 2)" - default "12" + range 8 20 + default 12 ---help--- The IPVS connection hash table uses the chaining scheme to handle hash collisions. Using a big IPVS connection hash table will greatly @@ -71,14 +80,20 @@ config IP_VS_PROTO_UDP This option enables support for load balancing UDP transport protocol. Say Y if unsure. +config IP_VS_PROTO_AH_ESP + bool + depends on UNDEFINED + config IP_VS_PROTO_ESP bool "ESP load balancing support" + select IP_VS_PROTO_AH_ESP ---help--- This option enables support for load balancing ESP (Encapsulation Security Payload) transport protocol. Say Y if unsure. config IP_VS_PROTO_AH bool "AH load balancing support" + select IP_VS_PROTO_AH_ESP ---help--- This option enables support for load balancing AH (Authentication Header) transport protocol. Say Y if unsure. diff --git a/net/ipv4/ipvs/Makefile b/net/ipv4/ipvs/Makefile index 30e85de..73a46fe 100644 --- a/net/ipv4/ipvs/Makefile +++ b/net/ipv4/ipvs/Makefile @@ -6,8 +6,7 @@ ip_vs_proto-objs-y := ip_vs_proto-objs-$(CONFIG_IP_VS_PROTO_TCP) += ip_vs_proto_tcp.o ip_vs_proto-objs-$(CONFIG_IP_VS_PROTO_UDP) += ip_vs_proto_udp.o -ip_vs_proto-objs-$(CONFIG_IP_VS_PROTO_ESP) += ip_vs_proto_esp.o -ip_vs_proto-objs-$(CONFIG_IP_VS_PROTO_AH) += ip_vs_proto_ah.o +ip_vs_proto-objs-$(CONFIG_IP_VS_PROTO_AH_ESP) += ip_vs_proto_ah_esp.o ip_vs-objs := ip_vs_conn.o ip_vs_core.o ip_vs_ctl.o ip_vs_sched.o \ ip_vs_xmit.o ip_vs_app.o ip_vs_sync.o \ diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c index 44a6872..9a24332 100644 --- a/net/ipv4/ipvs/ip_vs_conn.c +++ b/net/ipv4/ipvs/ip_vs_conn.c @@ -114,9 +114,18 @@ static inline void ct_write_unlock_bh(unsigned key) /* * Returns hash value for IPVS connection entry */ -static unsigned int ip_vs_conn_hashkey(unsigned proto, __be32 addr, __be16 port) +static unsigned int ip_vs_conn_hashkey(int af, unsigned proto, + const union nf_inet_addr *addr, + __be16 port) { - return jhash_3words((__force u32)addr, (__force u32)port, proto, ip_vs_conn_rnd) +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + return jhash_3words(jhash(addr, 16, ip_vs_conn_rnd), + (__force u32)port, proto, ip_vs_conn_rnd) + & IP_VS_CONN_TAB_MASK; +#endif + return jhash_3words((__force u32)addr->ip, (__force u32)port, proto, + ip_vs_conn_rnd) & IP_VS_CONN_TAB_MASK; } @@ -131,7 +140,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) int ret; /* Hash by protocol, client address and port */ - hash = ip_vs_conn_hashkey(cp->protocol, cp->caddr, cp->cport); + hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport); ct_write_lock(hash); @@ -162,7 +171,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) int ret; /* unhash it and decrease its reference counter */ - hash = ip_vs_conn_hashkey(cp->protocol, cp->caddr, cp->cport); + hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport); ct_write_lock(hash); @@ -187,20 +196,23 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) * d_addr, d_port: pkt dest address (load balancer) */ static inline struct ip_vs_conn *__ip_vs_conn_in_get -(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port) +(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, + const union nf_inet_addr *d_addr, __be16 d_port) { unsigned hash; struct ip_vs_conn *cp; - hash = ip_vs_conn_hashkey(protocol, s_addr, s_port); + hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port); ct_read_lock(hash); list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { - if (s_addr==cp->caddr && s_port==cp->cport && - d_port==cp->vport && d_addr==cp->vaddr && + if (cp->af == af && + ip_vs_addr_equal(af, s_addr, &cp->caddr) && + ip_vs_addr_equal(af, d_addr, &cp->vaddr) && + s_port == cp->cport && d_port == cp->vport && ((!s_port) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) && - protocol==cp->protocol) { + protocol == cp->protocol) { /* HIT */ atomic_inc(&cp->refcnt); ct_read_unlock(hash); @@ -214,39 +226,44 @@ static inline struct ip_vs_conn *__ip_vs_conn_in_get } struct ip_vs_conn *ip_vs_conn_in_get -(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port) +(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, + const union nf_inet_addr *d_addr, __be16 d_port) { struct ip_vs_conn *cp; - cp = __ip_vs_conn_in_get(protocol, s_addr, s_port, d_addr, d_port); + cp = __ip_vs_conn_in_get(af, protocol, s_addr, s_port, d_addr, d_port); if (!cp && atomic_read(&ip_vs_conn_no_cport_cnt)) - cp = __ip_vs_conn_in_get(protocol, s_addr, 0, d_addr, d_port); + cp = __ip_vs_conn_in_get(af, protocol, s_addr, 0, d_addr, + d_port); - IP_VS_DBG(9, "lookup/in %s %u.%u.%u.%u:%d->%u.%u.%u.%u:%d %s\n", - ip_vs_proto_name(protocol), - NIPQUAD(s_addr), ntohs(s_port), - NIPQUAD(d_addr), ntohs(d_port), - cp?"hit":"not hit"); + IP_VS_DBG_BUF(9, "lookup/in %s %s:%d->%s:%d %s\n", + ip_vs_proto_name(protocol), + IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port), + IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port), + cp ? "hit" : "not hit"); return cp; } /* Get reference to connection template */ struct ip_vs_conn *ip_vs_ct_in_get -(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port) +(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, + const union nf_inet_addr *d_addr, __be16 d_port) { unsigned hash; struct ip_vs_conn *cp; - hash = ip_vs_conn_hashkey(protocol, s_addr, s_port); + hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port); ct_read_lock(hash); list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { - if (s_addr==cp->caddr && s_port==cp->cport && - d_port==cp->vport && d_addr==cp->vaddr && + if (cp->af == af && + ip_vs_addr_equal(af, s_addr, &cp->caddr) && + ip_vs_addr_equal(af, d_addr, &cp->vaddr) && + s_port == cp->cport && d_port == cp->vport && cp->flags & IP_VS_CONN_F_TEMPLATE && - protocol==cp->protocol) { + protocol == cp->protocol) { /* HIT */ atomic_inc(&cp->refcnt); goto out; @@ -257,11 +274,11 @@ struct ip_vs_conn *ip_vs_ct_in_get out: ct_read_unlock(hash); - IP_VS_DBG(9, "template lookup/in %s %u.%u.%u.%u:%d->%u.%u.%u.%u:%d %s\n", - ip_vs_proto_name(protocol), - NIPQUAD(s_addr), ntohs(s_port), - NIPQUAD(d_addr), ntohs(d_port), - cp?"hit":"not hit"); + IP_VS_DBG_BUF(9, "template lookup/in %s %s:%d->%s:%d %s\n", + ip_vs_proto_name(protocol), + IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port), + IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port), + cp ? "hit" : "not hit"); return cp; } @@ -273,7 +290,8 @@ struct ip_vs_conn *ip_vs_ct_in_get * d_addr, d_port: pkt dest address (foreign host) */ struct ip_vs_conn *ip_vs_conn_out_get -(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port) +(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, + const union nf_inet_addr *d_addr, __be16 d_port) { unsigned hash; struct ip_vs_conn *cp, *ret=NULL; @@ -281,13 +299,15 @@ struct ip_vs_conn *ip_vs_conn_out_get /* * Check for "full" addressed entries */ - hash = ip_vs_conn_hashkey(protocol, d_addr, d_port); + hash = ip_vs_conn_hashkey(af, protocol, d_addr, d_port); ct_read_lock(hash); list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { - if (d_addr == cp->caddr && d_port == cp->cport && - s_port == cp->dport && s_addr == cp->daddr && + if (cp->af == af && + ip_vs_addr_equal(af, d_addr, &cp->caddr) && + ip_vs_addr_equal(af, s_addr, &cp->daddr) && + d_port == cp->cport && s_port == cp->dport && protocol == cp->protocol) { /* HIT */ atomic_inc(&cp->refcnt); @@ -298,11 +318,11 @@ struct ip_vs_conn *ip_vs_conn_out_get ct_read_unlock(hash); - IP_VS_DBG(9, "lookup/out %s %u.%u.%u.%u:%d->%u.%u.%u.%u:%d %s\n", - ip_vs_proto_name(protocol), - NIPQUAD(s_addr), ntohs(s_port), - NIPQUAD(d_addr), ntohs(d_port), - ret?"hit":"not hit"); + IP_VS_DBG_BUF(9, "lookup/out %s %s:%d->%s:%d %s\n", + ip_vs_proto_name(protocol), + IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port), + IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port), + ret ? "hit" : "not hit"); return ret; } @@ -369,6 +389,33 @@ static inline void ip_vs_bind_xmit(struct ip_vs_conn *cp) } } +#ifdef CONFIG_IP_VS_IPV6 +static inline void ip_vs_bind_xmit_v6(struct ip_vs_conn *cp) +{ + switch (IP_VS_FWD_METHOD(cp)) { + case IP_VS_CONN_F_MASQ: + cp->packet_xmit = ip_vs_nat_xmit_v6; + break; + + case IP_VS_CONN_F_TUNNEL: + cp->packet_xmit = ip_vs_tunnel_xmit_v6; + break; + + case IP_VS_CONN_F_DROUTE: + cp->packet_xmit = ip_vs_dr_xmit_v6; + break; + + case IP_VS_CONN_F_LOCALNODE: + cp->packet_xmit = ip_vs_null_xmit; + break; + + case IP_VS_CONN_F_BYPASS: + cp->packet_xmit = ip_vs_bypass_xmit_v6; + break; + } +} +#endif + static inline int ip_vs_dest_totalconns(struct ip_vs_dest *dest) { @@ -402,16 +449,16 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) cp->flags |= atomic_read(&dest->conn_flags); cp->dest = dest; - IP_VS_DBG(7, "Bind-dest %s c:%u.%u.%u.%u:%d v:%u.%u.%u.%u:%d " - "d:%u.%u.%u.%u:%d fwd:%c s:%u conn->flags:%X conn->refcnt:%d " - "dest->refcnt:%d\n", - ip_vs_proto_name(cp->protocol), - NIPQUAD(cp->caddr), ntohs(cp->cport), - NIPQUAD(cp->vaddr), ntohs(cp->vport), - NIPQUAD(cp->daddr), ntohs(cp->dport), - ip_vs_fwd_tag(cp), cp->state, - cp->flags, atomic_read(&cp->refcnt), - atomic_read(&dest->refcnt)); + IP_VS_DBG_BUF(7, "Bind-dest %s c:%s:%d v:%s:%d " + "d:%s:%d fwd:%c s:%u conn->flags:%X conn->refcnt:%d " + "dest->refcnt:%d\n", + ip_vs_proto_name(cp->protocol), + 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), + ip_vs_fwd_tag(cp), cp->state, + cp->flags, atomic_read(&cp->refcnt), + atomic_read(&dest->refcnt)); /* Update the connection counters */ if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) { @@ -444,8 +491,9 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) struct ip_vs_dest *dest; if ((cp) && (!cp->dest)) { - dest = ip_vs_find_dest(cp->daddr, cp->dport, - cp->vaddr, cp->vport, cp->protocol); + dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport, + &cp->vaddr, cp->vport, + cp->protocol); ip_vs_bind_dest(cp, dest); return dest; } else @@ -464,16 +512,16 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) if (!dest) return; - IP_VS_DBG(7, "Unbind-dest %s c:%u.%u.%u.%u:%d v:%u.%u.%u.%u:%d " - "d:%u.%u.%u.%u:%d fwd:%c s:%u conn->flags:%X conn->refcnt:%d " - "dest->refcnt:%d\n", - ip_vs_proto_name(cp->protocol), - NIPQUAD(cp->caddr), ntohs(cp->cport), - NIPQUAD(cp->vaddr), ntohs(cp->vport), - NIPQUAD(cp->daddr), ntohs(cp->dport), - ip_vs_fwd_tag(cp), cp->state, - cp->flags, atomic_read(&cp->refcnt), - atomic_read(&dest->refcnt)); + IP_VS_DBG_BUF(7, "Unbind-dest %s c:%s:%d v:%s:%d " + "d:%s:%d fwd:%c s:%u conn->flags:%X conn->refcnt:%d " + "dest->refcnt:%d\n", + ip_vs_proto_name(cp->protocol), + 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), + ip_vs_fwd_tag(cp), cp->state, + cp->flags, atomic_read(&cp->refcnt), + atomic_read(&dest->refcnt)); /* Update the connection counters */ if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) { @@ -526,13 +574,16 @@ int ip_vs_check_template(struct ip_vs_conn *ct) !(dest->flags & IP_VS_DEST_F_AVAILABLE) || (sysctl_ip_vs_expire_quiescent_template && (atomic_read(&dest->weight) == 0))) { - IP_VS_DBG(9, "check_template: dest not available for " - "protocol %s s:%u.%u.%u.%u:%d v:%u.%u.%u.%u:%d " - "-> d:%u.%u.%u.%u:%d\n", - ip_vs_proto_name(ct->protocol), - NIPQUAD(ct->caddr), ntohs(ct->cport), - NIPQUAD(ct->vaddr), ntohs(ct->vport), - NIPQUAD(ct->daddr), ntohs(ct->dport)); + IP_VS_DBG_BUF(9, "check_template: dest not available for " + "protocol %s s:%s:%d v:%s:%d " + "-> d:%s:%d\n", + ip_vs_proto_name(ct->protocol), + IP_VS_DBG_ADDR(ct->af, &ct->caddr), + ntohs(ct->cport), + IP_VS_DBG_ADDR(ct->af, &ct->vaddr), + ntohs(ct->vport), + IP_VS_DBG_ADDR(ct->af, &ct->daddr), + ntohs(ct->dport)); /* * Invalidate the connection template @@ -625,8 +676,9 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp) * Create a new connection entry and hash it into the ip_vs_conn_tab */ struct ip_vs_conn * -ip_vs_conn_new(int proto, __be32 caddr, __be16 cport, __be32 vaddr, __be16 vport, - __be32 daddr, __be16 dport, unsigned flags, +ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, + const union nf_inet_addr *vaddr, __be16 vport, + const union nf_inet_addr *daddr, __be16 dport, unsigned flags, struct ip_vs_dest *dest) { struct ip_vs_conn *cp; @@ -640,12 +692,13 @@ ip_vs_conn_new(int proto, __be32 caddr, __be16 cport, __be32 vaddr, __be16 vport INIT_LIST_HEAD(&cp->c_list); setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp); + cp->af = af; cp->protocol = proto; - cp->caddr = caddr; + ip_vs_addr_copy(af, &cp->caddr, caddr); cp->cport = cport; - cp->vaddr = vaddr; + ip_vs_addr_copy(af, &cp->vaddr, vaddr); cp->vport = vport; - cp->daddr = daddr; + ip_vs_addr_copy(af, &cp->daddr, daddr); cp->dport = dport; cp->flags = flags; spin_lock_init(&cp->lock); @@ -672,7 +725,12 @@ ip_vs_conn_new(int proto, __be32 caddr, __be16 cport, __be32 vaddr, __be16 vport cp->timeout = 3*HZ; /* Bind its packet transmitter */ - ip_vs_bind_xmit(cp); +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + ip_vs_bind_xmit_v6(cp); + else +#endif + ip_vs_bind_xmit(cp); if (unlikely(pp && atomic_read(&pp->appcnt))) ip_vs_bind_app(cp, pp); @@ -760,12 +818,26 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) else { const struct ip_vs_conn *cp = v; - seq_printf(seq, - "%-3s %08X %04X %08X %04X %08X %04X %-11s %7lu\n", +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + seq_printf(seq, + "%-3s " NIP6_FMT " %04X " NIP6_FMT + " %04X " NIP6_FMT " %04X %-11s %7lu\n", + ip_vs_proto_name(cp->protocol), + NIP6(cp->caddr.in6), ntohs(cp->cport), + NIP6(cp->vaddr.in6), ntohs(cp->vport), + NIP6(cp->daddr.in6), ntohs(cp->dport), + ip_vs_state_name(cp->protocol, cp->state), + (cp->timer.expires-jiffies)/HZ); + else +#endif + seq_printf(seq, + "%-3s %08X %04X %08X %04X" + " %08X %04X %-11s %7lu\n", ip_vs_proto_name(cp->protocol), - ntohl(cp->caddr), ntohs(cp->cport), - ntohl(cp->vaddr), ntohs(cp->vport), - ntohl(cp->daddr), ntohs(cp->dport), + ntohl(cp->caddr.ip), ntohs(cp->cport), + ntohl(cp->vaddr.ip), ntohs(cp->vport), + ntohl(cp->daddr.ip), ntohs(cp->dport), ip_vs_state_name(cp->protocol, cp->state), (cp->timer.expires-jiffies)/HZ); } @@ -809,12 +881,27 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v) else { const struct ip_vs_conn *cp = v; - seq_printf(seq, - "%-3s %08X %04X %08X %04X %08X %04X %-11s %-6s %7lu\n", +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + seq_printf(seq, + "%-3s " NIP6_FMT " %04X " NIP6_FMT + " %04X " NIP6_FMT " %04X %-11s %-6s %7lu\n", + ip_vs_proto_name(cp->protocol), + NIP6(cp->caddr.in6), ntohs(cp->cport), + NIP6(cp->vaddr.in6), ntohs(cp->vport), + NIP6(cp->daddr.in6), ntohs(cp->dport), + ip_vs_state_name(cp->protocol, cp->state), + ip_vs_origin_name(cp->flags), + (cp->timer.expires-jiffies)/HZ); + else +#endif + seq_printf(seq, + "%-3s %08X %04X %08X %04X " + "%08X %04X %-11s %-6s %7lu\n", ip_vs_proto_name(cp->protocol), - ntohl(cp->caddr), ntohs(cp->cport), - ntohl(cp->vaddr), ntohs(cp->vport), - ntohl(cp->daddr), ntohs(cp->dport), + ntohl(cp->caddr.ip), ntohs(cp->cport), + ntohl(cp->vaddr.ip), ntohs(cp->vport), + ntohl(cp->daddr.ip), ntohs(cp->dport), ip_vs_state_name(cp->protocol, cp->state), ip_vs_origin_name(cp->flags), (cp->timer.expires-jiffies)/HZ); diff --git a/net/ipv4/ipvs/ip_vs_core.c b/net/ipv4/ipvs/ip_vs_core.c index a7879ea..958abf3 100644 --- a/net/ipv4/ipvs/ip_vs_core.c +++ b/net/ipv4/ipvs/ip_vs_core.c @@ -39,6 +39,11 @@ #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> +#ifdef CONFIG_IP_VS_IPV6 +#include <net/ipv6.h> +#include <linux/netfilter_ipv6.h> +#endif + #include <net/ip_vs.h> @@ -60,6 +65,7 @@ EXPORT_SYMBOL(ip_vs_get_debug_level); /* 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 proto) { @@ -74,6 +80,10 @@ const char *ip_vs_proto_name(unsigned proto) return "TCP"; case IPPROTO_ICMP: return "ICMP"; +#ifdef CONFIG_IP_VS_IPV6 + case IPPROTO_ICMPV6: + return "ICMPv6"; +#endif default: sprintf(buf, "IP_%d", proto); return buf; @@ -92,18 +102,18 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_dest *dest = cp->dest; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { spin_lock(&dest->stats.lock); - dest->stats.inpkts++; - dest->stats.inbytes += skb->len; + dest->stats.ustats.inpkts++; + dest->stats.ustats.inbytes += skb->len; spin_unlock(&dest->stats.lock); spin_lock(&dest->svc->stats.lock); - dest->svc->stats.inpkts++; - dest->svc->stats.inbytes += skb->len; + dest->svc->stats.ustats.inpkts++; + dest->svc->stats.ustats.inbytes += skb->len; spin_unlock(&dest->svc->stats.lock); spin_lock(&ip_vs_stats.lock); - ip_vs_stats.inpkts++; - ip_vs_stats.inbytes += skb->len; + ip_vs_stats.ustats.inpkts++; + ip_vs_stats.ustats.inbytes += skb->len; spin_unlock(&ip_vs_stats.lock); } } @@ -115,18 +125,18 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_dest *dest = cp->dest; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { spin_lock(&dest->stats.lock); - dest->stats.outpkts++; - dest->stats.outbytes += skb->len; + dest->stats.ustats.outpkts++; + dest->stats.ustats.outbytes += skb->len; spin_unlock(&dest->stats.lock); spin_lock(&dest->svc->stats.lock); - dest->svc->stats.outpkts++; - dest->svc->stats.outbytes += skb->len; + dest->svc->stats.ustats.outpkts++; + dest->svc->stats.ustats.outbytes += skb->len; spin_unlock(&dest->svc->stats.lock); spin_lock(&ip_vs_stats.lock); - ip_vs_stats.outpkts++; - ip_vs_stats.outbytes += skb->len; + ip_vs_stats.ustats.outpkts++; + ip_vs_stats.ustats.outbytes += skb->len; spin_unlock(&ip_vs_stats.lock); } } @@ -136,15 +146,15 @@ static inline void ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) { spin_lock(&cp->dest->stats.lock); - cp->dest->stats.conns++; + cp->dest->stats.ustats.conns++; spin_unlock(&cp->dest->stats.lock); spin_lock(&svc->stats.lock); - svc->stats.conns++; + svc->stats.ustats.conns++; spin_unlock(&svc->stats.lock); spin_lock(&ip_vs_stats.lock); - ip_vs_stats.conns++; + ip_vs_stats.ustats.conns++; spin_unlock(&ip_vs_stats.lock); } @@ -173,20 +183,28 @@ ip_vs_sched_persist(struct ip_vs_service *svc, __be16 ports[2]) { struct ip_vs_conn *cp = NULL; - struct iphdr *iph = ip_hdr(skb); + struct ip_vs_iphdr iph; struct ip_vs_dest *dest; struct ip_vs_conn *ct; - __be16 dport; /* destination port to forward */ - __be32 snet; /* source network of the client, after masking */ + __be16 dport; /* destination port to forward */ + union nf_inet_addr snet; /* source network of the client, + after masking */ + + ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); /* Mask saddr with the netmask to adjust template granularity */ - snet = iph->saddr & svc->netmask; +#ifdef CONFIG_IP_VS_IPV6 + if (svc->af == AF_INET6) + ipv6_addr_prefix(&snet.in6, &iph.saddr.in6, svc->netmask); + else +#endif + snet.ip = iph.saddr.ip & svc->netmask; - IP_VS_DBG(6, "p-schedule: src %u.%u.%u.%u:%u dest %u.%u.%u.%u:%u " - "mnet %u.%u.%u.%u\n", - NIPQUAD(iph->saddr), ntohs(ports[0]), - NIPQUAD(iph->daddr), ntohs(ports[1]), - NIPQUAD(snet)); + IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u " + "mnet %s\n", + IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(ports[0]), + IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(ports[1]), + IP_VS_DBG_ADDR(svc->af, &snet)); /* * As far as we know, FTP is a very complicated network protocol, and @@ -204,11 +222,11 @@ ip_vs_sched_persist(struct ip_vs_service *svc, if (ports[1] == svc->port) { /* Check if a template already exists */ if (svc->port != FTPPORT) - ct = ip_vs_ct_in_get(iph->protocol, snet, 0, - iph->daddr, ports[1]); + ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0, + &iph.daddr, ports[1]); else - ct = ip_vs_ct_in_get(iph->protocol, snet, 0, - iph->daddr, 0); + ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0, + &iph.daddr, 0); if (!ct || !ip_vs_check_template(ct)) { /* @@ -228,18 +246,18 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * for ftp service. */ if (svc->port != FTPPORT) - ct = ip_vs_conn_new(iph->protocol, - snet, 0, - iph->daddr, + ct = ip_vs_conn_new(svc->af, iph.protocol, + &snet, 0, + &iph.daddr, ports[1], - dest->addr, dest->port, + &dest->addr, dest->port, IP_VS_CONN_F_TEMPLATE, dest); else - ct = ip_vs_conn_new(iph->protocol, - snet, 0, - iph->daddr, 0, - dest->addr, 0, + ct = ip_vs_conn_new(svc->af, iph.protocol, + &snet, 0, + &iph.daddr, 0, + &dest->addr, 0, IP_VS_CONN_F_TEMPLATE, dest); if (ct == NULL) @@ -258,12 +276,16 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * fwmark template: <IPPROTO_IP,caddr,0,fwmark,0,daddr,0> * port zero template: <protocol,caddr,0,vaddr,0,daddr,0> */ - if (svc->fwmark) - ct = ip_vs_ct_in_get(IPPROTO_IP, snet, 0, - htonl(svc->fwmark), 0); - else - ct = ip_vs_ct_in_get(iph->protocol, snet, 0, - iph->daddr, 0); + if (svc->fwmark) { + union nf_inet_addr fwmark = { + .all = { 0, 0, 0, htonl(svc->fwmark) } + }; + + ct = ip_vs_ct_in_get(svc->af, IPPROTO_IP, &snet, 0, + &fwmark, 0); + } else + ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0, + &iph.daddr, 0); if (!ct || !ip_vs_check_template(ct)) { /* @@ -282,18 +304,22 @@ ip_vs_sched_persist(struct ip_vs_service *svc, /* * Create a template according to the service */ - if (svc->fwmark) - ct = ip_vs_conn_new(IPPROTO_IP, - snet, 0, - htonl(svc->fwmark), 0, - dest->addr, 0, + if (svc->fwmark) { + union nf_inet_addr fwmark = { + .all = { 0, 0, 0, htonl(svc->fwmark) } + }; + + ct = ip_vs_conn_new(svc->af, IPPROTO_IP, + &snet, 0, + &fwmark, 0, + &dest->addr, 0, IP_VS_CONN_F_TEMPLATE, dest); - else - ct = ip_vs_conn_new(iph->protocol, - snet, 0, - iph->daddr, 0, - dest->addr, 0, + } else + ct = ip_vs_conn_new(svc->af, iph.protocol, + &snet, 0, + &iph.daddr, 0, + &dest->addr, 0, IP_VS_CONN_F_TEMPLATE, dest); if (ct == NULL) @@ -310,10 +336,10 @@ ip_vs_sched_persist(struct ip_vs_service *svc, /* * Create a new connection according to the template */ - cp = ip_vs_conn_new(iph->protocol, - iph->saddr, ports[0], - iph->daddr, ports[1], - dest->addr, dport, + cp = ip_vs_conn_new(svc->af, iph.protocol, + &iph.saddr, ports[0], + &iph.daddr, ports[1], + &dest->addr, dport, 0, dest); if (cp == NULL) { @@ -342,12 +368,12 @@ struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) { struct ip_vs_conn *cp = NULL; - struct iphdr *iph = ip_hdr(skb); + struct ip_vs_iphdr iph; struct ip_vs_dest *dest; __be16 _ports[2], *pptr; - pptr = skb_header_pointer(skb, iph->ihl*4, - sizeof(_ports), _ports); + ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); + pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports); if (pptr == NULL) return NULL; @@ -377,22 +403,22 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) /* * Create a connection entry. */ - cp = ip_vs_conn_new(iph->protocol, - iph->saddr, pptr[0], - iph->daddr, pptr[1], - dest->addr, dest->port?dest->port:pptr[1], + cp = ip_vs_conn_new(svc->af, iph.protocol, + &iph.saddr, pptr[0], + &iph.daddr, pptr[1], + &dest->addr, dest->port ? dest->port : pptr[1], 0, dest); if (cp == NULL) return NULL; - IP_VS_DBG(6, "Schedule fwd:%c c:%u.%u.%u.%u:%u v:%u.%u.%u.%u:%u " - "d:%u.%u.%u.%u:%u conn->flags:%X conn->refcnt:%d\n", - ip_vs_fwd_tag(cp), - NIPQUAD(cp->caddr), ntohs(cp->cport), - NIPQUAD(cp->vaddr), ntohs(cp->vport), - NIPQUAD(cp->daddr), ntohs(cp->dport), - cp->flags, atomic_read(&cp->refcnt)); + 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(svc->af, &cp->caddr), ntohs(cp->cport), + IP_VS_DBG_ADDR(svc->af, &cp->vaddr), ntohs(cp->vport), + IP_VS_DBG_ADDR(svc->af, &cp->daddr), ntohs(cp->dport), + cp->flags, atomic_read(&cp->refcnt)); ip_vs_conn_stats(cp, svc); return cp; @@ -408,31 +434,39 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_protocol *pp) { __be16 _ports[2], *pptr; - struct iphdr *iph = ip_hdr(skb); + struct ip_vs_iphdr iph; + int unicast; + ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); - pptr = skb_header_pointer(skb, iph->ihl*4, - sizeof(_ports), _ports); + pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports); if (pptr == NULL) { ip_vs_service_put(svc); return NF_DROP; } +#ifdef CONFIG_IP_VS_IPV6 + if (svc->af == AF_INET6) + unicast = ipv6_addr_type(&iph.daddr.in6) & IPV6_ADDR_UNICAST; + else +#endif + unicast = (inet_addr_type(&init_net, iph.daddr.ip) == RTN_UNICAST); + /* if it is fwmark-based service, the cache_bypass sysctl is up - and the destination is RTN_UNICAST (and not local), then create + and the destination is a non-local unicast, then create a cache_bypass connection entry */ - if (sysctl_ip_vs_cache_bypass && svc->fwmark - && (inet_addr_type(&init_net, iph->daddr) == RTN_UNICAST)) { + if (sysctl_ip_vs_cache_bypass && svc->fwmark && unicast) { int ret, cs; struct ip_vs_conn *cp; + union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } }; ip_vs_service_put(svc); /* create a new connection entry */ IP_VS_DBG(6, "ip_vs_leave: create a cache_bypass entry\n"); - cp = ip_vs_conn_new(iph->protocol, - iph->saddr, pptr[0], - iph->daddr, pptr[1], - 0, 0, + cp = ip_vs_conn_new(svc->af, iph.protocol, + &iph.saddr, pptr[0], + &iph.daddr, pptr[1], + &daddr, 0, IP_VS_CONN_F_BYPASS, NULL); if (cp == NULL) @@ -473,7 +507,14 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, * created, the TCP RST packet cannot be sent, instead that * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ */ - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); +#ifdef CONFIG_IP_VS_IPV6 + if (svc->af == AF_INET6) + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, + skb->dev); + else +#endif + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + return NF_DROP; } @@ -512,6 +553,14 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user) return err; } +#ifdef CONFIG_IP_VS_IPV6 +static inline int ip_vs_gather_frags_v6(struct sk_buff *skb, u_int32_t user) +{ + /* TODO IPv6: Find out what to do here for IPv6 */ + return 0; +} +#endif + /* * Packet has been made sufficiently writable in caller * - inout: 1=in->out, 0=out->in @@ -526,14 +575,14 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct iphdr *ciph = (struct iphdr *)(icmph + 1); if (inout) { - iph->saddr = cp->vaddr; + iph->saddr = cp->vaddr.ip; ip_send_check(iph); - ciph->daddr = cp->vaddr; + ciph->daddr = cp->vaddr.ip; ip_send_check(ciph); } else { - iph->daddr = cp->daddr; + iph->daddr = cp->daddr.ip; ip_send_check(iph); - ciph->saddr = cp->daddr; + ciph->saddr = cp->daddr.ip; ip_send_check(ciph); } @@ -560,21 +609,112 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, "Forwarding altered incoming ICMP"); } +#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 = sizeof(struct ipv6hdr); + struct icmp6hdr *icmph = (struct icmp6hdr *)(skb_network_header(skb) + + icmp_offset); + struct ipv6hdr *ciph = (struct ipv6hdr *)(icmph + 1); + + 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 port */ + if (IPPROTO_TCP == ciph->nexthdr || IPPROTO_UDP == ciph->nexthdr) { + __be16 *ports = (void *)ciph + sizeof(struct ipv6hdr); + + if (inout) + ports[1] = cp->vport; + else + ports[0] = cp->dport; + } + + /* And finally the ICMP checksum */ + icmph->icmp6_cksum = 0; + /* TODO IPv6: is this correct for ICMPv6? */ + ip_vs_checksum_complete(skb, icmp_offset); + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (inout) + IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph, + "Forwarding altered outgoing ICMPv6"); + else + IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph, + "Forwarding altered incoming ICMPv6"); +} +#endif + +/* Handle relevant response ICMP messages - forward to the right + * destination host. Used for NAT and local client. + */ +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 verdict = NF_DROP; + + if (IP_VS_FWD_METHOD(cp) != 0) { + IP_VS_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) + 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); + + /* do the statistics and put it back */ + ip_vs_out_stats(cp, skb); + + skb->ipvs_property = 1; + verdict = NF_ACCEPT; + +out: + __ip_vs_conn_put(cp); + + return verdict; +} + /* * Handle ICMP messages in the inside-to-outside direction (outgoing). - * Find any that might be relevant, check against existing connections, - * forward to the right destination host if relevant. + * Find any that might be relevant, check against existing connections. * Currently handles error types - unreachable, quench, ttl exceeded. - * (Only used in VS/NAT) */ static int ip_vs_out_icmp(struct sk_buff *skb, int *related) { 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, verdict; + unsigned int offset, ihl; + union nf_inet_addr snet; *related = 1; @@ -627,102 +767,231 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related) offset += cih->ihl * 4; + ip_vs_fill_iphdr(AF_INET, cih, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(skb, pp, cih, offset, 1); + cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1); if (!cp) return NF_ACCEPT; - verdict = NF_DROP; + snet.ip = iph->saddr; + return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, + pp, offset, ihl); +} - if (IP_VS_FWD_METHOD(cp) != 0) { - IP_VS_ERR("shouldn't reach here, because the box is on the " - "half connection in the tun/dr module.\n"); +#ifdef CONFIG_IP_VS_IPV6 +static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related) +{ + struct ipv6hdr *iph; + struct icmp6hdr _icmph, *ic; + struct ipv6hdr _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; + union nf_inet_addr snet; + + *related = 1; + + /* reassemble IP fragments */ + if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) { + if (ip_vs_gather_frags_v6(skb, IP_DEFRAG_VS_OUT)) + return NF_STOLEN; } - /* Ensure the checksum is correct */ - if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { - /* Failed checksum! */ - IP_VS_DBG(1, "Forward ICMP: failed checksum from %d.%d.%d.%d!\n", - NIPQUAD(iph->saddr)); - goto out; + iph = ipv6_hdr(skb); + offset = sizeof(struct ipv6hdr); + ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); + if (ic == NULL) + return NF_DROP; + + IP_VS_DBG(12, "Outgoing ICMPv6 (%d,%d) " NIP6_FMT "->" NIP6_FMT "\n", + ic->icmp6_type, ntohs(icmpv6_id(ic)), + NIP6(iph->saddr), NIP6(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->icmp6_type != ICMPV6_DEST_UNREACH) && + (ic->icmp6_type != ICMPV6_PKT_TOOBIG) && + (ic->icmp6_type != ICMPV6_TIME_EXCEED)) { + *related = 0; + return NF_ACCEPT; } - if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol) - offset += 2 * sizeof(__u16); - if (!skb_make_writable(skb, offset)) - goto out; + /* 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 */ - ip_vs_nat_icmp(skb, pp, cp, 1); + pp = ip_vs_proto_get(cih->nexthdr); + if (!pp) + return NF_ACCEPT; - /* do the statistics and put it back */ - ip_vs_out_stats(cp, skb); + /* Is the embedded protocol header present? */ + /* TODO: we don't support fragmentation at the moment anyways */ + if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag)) + return NF_ACCEPT; - skb->ipvs_property = 1; - verdict = NF_ACCEPT; + IP_VS_DBG_PKT(11, pp, skb, offset, "Checking outgoing ICMPv6 for"); - out: - __ip_vs_conn_put(cp); + offset += sizeof(struct ipv6hdr); - return verdict; + ip_vs_fill_iphdr(AF_INET6, cih, &ciph); + /* The embedded headers contain source and dest in reverse order */ + cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1); + if (!cp) + return NF_ACCEPT; + + ipv6_addr_copy(&snet.in6, &iph->saddr); + return handle_response_icmp(AF_INET6, skb, &snet, cih->nexthdr, cp, + pp, offset, sizeof(struct ipv6hdr)); } +#endif -static inline int is_tcp_reset(const struct sk_buff *skb) +static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len) { struct tcphdr _tcph, *th; - th = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph); + th = skb_header_pointer(skb, nh_len, sizeof(_tcph), &_tcph); if (th == NULL) return 0; return th->rst; } +/* Handle response packets: rewrite addresses and send away... + * Used for NAT and local client. + */ +static unsigned int +handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, + struct ip_vs_conn *cp, int ihl) +{ + IP_VS_DBG_PKT(11, pp, skb, 0, "Outgoing packet"); + + if (!skb_make_writable(skb, ihl)) + goto drop; + + /* mangle the packet */ + if (pp->snat_handler && !pp->snat_handler(skb, pp, cp)) + 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)); + } + + /* 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. + */ +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) { + if (ip6_route_me_harder(skb) != 0) + goto drop; + } else +#endif + if (ip_route_me_harder(skb, RTN_LOCAL) != 0) + goto drop; + + IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT"); + + ip_vs_out_stats(cp, skb); + ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp); + ip_vs_conn_put(cp); + + skb->ipvs_property = 1; + + LeaveFunction(11); + return NF_ACCEPT; + +drop: + ip_vs_conn_put(cp); + kfree_skb(skb); + return NF_STOLEN; +} + /* * It is hooked at the NF_INET_FORWARD chain, used only for VS/NAT. - * Check if outgoing packet belongs to the established ip_vs_conn, - * rewrite addresses of the packet and send it on its way... + * Check if outgoing packet belongs to the established ip_vs_conn. */ static unsigned int ip_vs_out(unsigned int hooknum, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct iphdr *iph; + struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_conn *cp; - int ihl; + int af; EnterFunction(11); + af = (skb->protocol == htons(ETH_P_IP)) ? AF_INET : AF_INET6; + if (skb->ipvs_property) return NF_ACCEPT; - iph = ip_hdr(skb); - if (unlikely(iph->protocol == IPPROTO_ICMP)) { - int related, verdict = ip_vs_out_icmp(skb, &related); + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) { + if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { + int related, verdict = ip_vs_out_icmp_v6(skb, &related); - if (related) - return verdict; - iph = ip_hdr(skb); - } + if (related) + return verdict; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + } + } else +#endif + if (unlikely(iph.protocol == IPPROTO_ICMP)) { + int related, verdict = ip_vs_out_icmp(skb, &related); - pp = ip_vs_proto_get(iph->protocol); + if (related) + return verdict; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + } + + pp = ip_vs_proto_get(iph.protocol); if (unlikely(!pp)) return NF_ACCEPT; /* reassemble IP fragments */ - if (unlikely(iph->frag_off & htons(IP_MF|IP_OFFSET) && - !pp->dont_defrag)) { - if (ip_vs_gather_frags(skb, IP_DEFRAG_VS_OUT)) - return NF_STOLEN; - iph = ip_hdr(skb); - } +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) { + if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { + int related, verdict = ip_vs_out_icmp_v6(skb, &related); + + if (related) + return verdict; - ihl = iph->ihl << 2; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + } + } else +#endif + if (unlikely(ip_hdr(skb)->frag_off & htons(IP_MF|IP_OFFSET) && + !pp->dont_defrag)) { + if (ip_vs_gather_frags(skb, IP_DEFRAG_VS_OUT)) + return NF_STOLEN; + + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + } /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(skb, pp, iph, ihl, 0); + cp = pp->conn_out_get(af, skb, pp, &iph, iph.len, 0); if (unlikely(!cp)) { if (sysctl_ip_vs_nat_icmp_send && @@ -730,21 +999,31 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, pp->protocol == IPPROTO_UDP)) { __be16 _ports[2], *pptr; - pptr = skb_header_pointer(skb, ihl, + pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports); if (pptr == NULL) return NF_ACCEPT; /* Not for me */ - if (ip_vs_lookup_real_service(iph->protocol, - iph->saddr, pptr[0])) { + if (ip_vs_lookup_real_service(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 - || !is_tcp_reset(skb)) { - icmp_send(skb,ICMP_DEST_UNREACH, - ICMP_PORT_UNREACH, 0); + if (iph.protocol != IPPROTO_TCP + || !is_tcp_reset(skb, iph.len)) { +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + icmpv6_send(skb, + ICMPV6_DEST_UNREACH, + ICMPV6_PORT_UNREACH, + 0, skb->dev); + else +#endif + icmp_send(skb, + ICMP_DEST_UNREACH, + ICMP_PORT_UNREACH, 0); return NF_DROP; } } @@ -754,41 +1033,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, return NF_ACCEPT; } - IP_VS_DBG_PKT(11, pp, skb, 0, "Outgoing packet"); - - if (!skb_make_writable(skb, ihl)) - goto drop; - - /* mangle the packet */ - if (pp->snat_handler && !pp->snat_handler(skb, pp, cp)) - goto drop; - ip_hdr(skb)->saddr = cp->vaddr; - ip_send_check(ip_hdr(skb)); - - /* 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_route_me_harder(skb, RTN_LOCAL) != 0) - goto drop; - - IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT"); - - ip_vs_out_stats(cp, skb); - ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp); - ip_vs_conn_put(cp); - - skb->ipvs_property = 1; - - LeaveFunction(11); - return NF_ACCEPT; - - drop: - ip_vs_conn_put(cp); - kfree_skb(skb); - return NF_STOLEN; + return handle_response(af, skb, pp, cp, iph.len); } @@ -804,9 +1049,11 @@ ip_vs_in_icmp(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, verdict; + union nf_inet_addr snet; *related = 1; @@ -860,10 +1107,20 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) offset += cih->ihl * 4; + ip_vs_fill_iphdr(AF_INET, cih, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_in_get(skb, pp, cih, offset, 1); - if (!cp) + cp = pp->conn_in_get(AF_INET, skb, pp, &ciph, offset, 1); + if (!cp) { + /* The packet could also belong to a local client */ + cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1); + if (cp) { + snet.ip = iph->saddr; + return handle_response_icmp(AF_INET, skb, &snet, + cih->protocol, cp, pp, + offset, ihl); + } return NF_ACCEPT; + } verdict = NF_DROP; @@ -888,6 +1145,105 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) return verdict; } +#ifdef CONFIG_IP_VS_IPV6 +static int +ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) +{ + struct ipv6hdr *iph; + struct icmp6hdr _icmph, *ic; + struct ipv6hdr _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, verdict; + union nf_inet_addr snet; + + *related = 1; + + /* reassemble IP fragments */ + if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) { + if (ip_vs_gather_frags_v6(skb, hooknum == NF_INET_LOCAL_IN ? + IP_DEFRAG_VS_IN : + IP_DEFRAG_VS_FWD)) + return NF_STOLEN; + } + + iph = ipv6_hdr(skb); + offset = sizeof(struct ipv6hdr); + ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); + if (ic == NULL) + return NF_DROP; + + IP_VS_DBG(12, "Incoming ICMPv6 (%d,%d) " NIP6_FMT "->" NIP6_FMT "\n", + ic->icmp6_type, ntohs(icmpv6_id(ic)), + NIP6(iph->saddr), NIP6(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->icmp6_type != ICMPV6_DEST_UNREACH) && + (ic->icmp6_type != ICMPV6_PKT_TOOBIG) && + (ic->icmp6_type != ICMPV6_TIME_EXCEED)) { + *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->nexthdr); + if (!pp) + return NF_ACCEPT; + + /* Is the embedded protocol header present? */ + /* TODO: we don't support fragmentation at the moment anyways */ + if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag)) + return NF_ACCEPT; + + IP_VS_DBG_PKT(11, pp, skb, offset, "Checking incoming ICMPv6 for"); + + offset += sizeof(struct ipv6hdr); + + ip_vs_fill_iphdr(AF_INET6, cih, &ciph); + /* The embedded headers contain source and dest in reverse order */ + cp = pp->conn_in_get(AF_INET6, skb, pp, &ciph, offset, 1); + if (!cp) { + /* The packet could also belong to a local client */ + cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1); + if (cp) { + ipv6_addr_copy(&snet.in6, &iph->saddr); + return handle_response_icmp(AF_INET6, skb, &snet, + cih->nexthdr, + cp, pp, offset, + sizeof(struct ipv6hdr)); + } + return NF_ACCEPT; + } + + verdict = NF_DROP; + + /* do the statistics and put it back */ + ip_vs_in_stats(cp, skb); + if (IPPROTO_TCP == cih->nexthdr || IPPROTO_UDP == cih->nexthdr) + offset += 2 * sizeof(__u16); + verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset); + /* do not touch skb anymore */ + + __ip_vs_conn_put(cp); + + return verdict; +} +#endif + + /* * Check if it's for virtual services, look it up, * and send it on its way... @@ -897,50 +1253,54 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct iphdr *iph; + struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_conn *cp; - int ret, restart; - int ihl; + int ret, restart, af; + + af = (skb->protocol == htons(ETH_P_IP)) ? AF_INET : AF_INET6; + + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); /* - * Big tappo: only PACKET_HOST (neither loopback nor mcasts) - * ... don't know why 1st test DOES NOT include 2nd (?) + * Big tappo: only PACKET_HOST, including loopback for local client + * Don't handle local packets on IPv6 for now */ - if (unlikely(skb->pkt_type != PACKET_HOST - || skb->dev->flags & IFF_LOOPBACK || skb->sk)) { - IP_VS_DBG(12, "packet type=%d proto=%d daddr=%d.%d.%d.%d ignored\n", - skb->pkt_type, - ip_hdr(skb)->protocol, - NIPQUAD(ip_hdr(skb)->daddr)); + if (unlikely(skb->pkt_type != PACKET_HOST)) { + IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s ignored\n", + skb->pkt_type, + iph.protocol, + IP_VS_DBG_ADDR(af, &iph.daddr)); return NF_ACCEPT; } - iph = ip_hdr(skb); - if (unlikely(iph->protocol == IPPROTO_ICMP)) { + if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related, verdict = ip_vs_in_icmp(skb, &related, hooknum); if (related) return verdict; - iph = ip_hdr(skb); + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } /* Protocol supported? */ - pp = ip_vs_proto_get(iph->protocol); + pp = ip_vs_proto_get(iph.protocol); if (unlikely(!pp)) return NF_ACCEPT; - ihl = iph->ihl << 2; - /* * Check if the packet belongs to an existing connection entry */ - cp = pp->conn_in_get(skb, pp, iph, ihl, 0); + cp = pp->conn_in_get(af, skb, pp, &iph, iph.len, 0); if (unlikely(!cp)) { int v; - if (!pp->conn_schedule(skb, pp, &v, &cp)) + /* For local client packets, it could be a response */ + cp = pp->conn_out_get(af, skb, pp, &iph, iph.len, 0); + if (cp) + return handle_response(af, skb, pp, cp, iph.len); + + if (!pp->conn_schedule(af, skb, pp, &v, &cp)) return v; } @@ -984,7 +1344,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, * encorage the standby servers to update the connections timeout */ atomic_inc(&cp->in_pkts); - if ((ip_vs_sync_state & IP_VS_STATE_MASTER) && + if (af == AF_INET && + (ip_vs_sync_state & IP_VS_STATE_MASTER) && (((cp->protocol != IPPROTO_TCP || cp->state == IP_VS_TCP_S_ESTABLISHED) && (atomic_read(&cp->in_pkts) % sysctl_ip_vs_sync_threshold[1] @@ -1023,6 +1384,21 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, return ip_vs_in_icmp(skb, &r, hooknum); } +#ifdef CONFIG_IP_VS_IPV6 +static unsigned int +ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + int r; + + if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) + return NF_ACCEPT; + + return ip_vs_in_icmp_v6(skb, &r, hooknum); +} +#endif + static struct nf_hook_ops ip_vs_ops[] __read_mostly = { /* After packet filtering, forward packet through VS/DR, VS/TUN, @@ -1060,6 +1436,43 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC-1, }, +#ifdef CONFIG_IP_VS_IPV6 + /* 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_in, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_INET_LOCAL_IN, + .priority = 100, + }, + /* After packet filtering, change source only for VS/NAT */ + { + .hook = ip_vs_out, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_INET_FORWARD, + .priority = 100, + }, + /* 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, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_INET_FORWARD, + .priority = 99, + }, + /* Before the netfilter connection tracking, exit from POST_ROUTING */ + { + .hook = ip_vs_post_routing, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_NAT_SRC-1, + }, +#endif }; @@ -1070,10 +1483,12 @@ static int __init ip_vs_init(void) { int ret; + ip_vs_estimator_init(); + ret = ip_vs_control_init(); if (ret < 0) { IP_VS_ERR("can't setup control.\n"); - goto cleanup_nothing; + goto cleanup_estimator; } ip_vs_protocol_init(); @@ -1106,7 +1521,8 @@ static int __init ip_vs_init(void) cleanup_protocol: ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); - cleanup_nothing: + cleanup_estimator: + ip_vs_estimator_cleanup(); return ret; } @@ -1117,6 +1533,7 @@ static void __exit ip_vs_cleanup(void) ip_vs_app_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); + ip_vs_estimator_cleanup(); IP_VS_INFO("ipvs unloaded.\n"); } diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c index 6379705..771551d 100644 --- a/net/ipv4/ipvs/ip_vs_ctl.c +++ b/net/ipv4/ipvs/ip_vs_ctl.c @@ -35,8 +35,13 @@ #include <net/net_namespace.h> #include <net/ip.h> +#ifdef CONFIG_IP_VS_IPV6 +#include <net/ipv6.h> +#include <net/ip6_route.h> +#endif #include <net/route.h> #include <net/sock.h> +#include <net/genetlink.h> #include <asm/uaccess.h> @@ -90,6 +95,26 @@ int ip_vs_get_debug_level(void) } #endif +#ifdef CONFIG_IP_VS_IPV6 +/* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ +static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr) +{ + struct rt6_info *rt; + struct flowi fl = { + .oif = 0, + .nl_u = { + .ip6_u = { + .daddr = *addr, + .saddr = { .s6_addr32 = {0, 0, 0, 0} }, } }, + }; + + rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl); + if (rt && rt->rt6i_dev && (rt->rt6i_dev->flags & IFF_LOOPBACK)) + return 1; + + return 0; +} +#endif /* * update_defense_level is called from keventd and from sysctl, * so it needs to protect itself from softirqs @@ -281,11 +306,19 @@ static atomic_t ip_vs_nullsvc_counter = ATOMIC_INIT(0); * Returns hash value for virtual service */ static __inline__ unsigned -ip_vs_svc_hashkey(unsigned proto, __be32 addr, __be16 port) +ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr, + __be16 port) { register unsigned porth = ntohs(port); + __be32 addr_fold = addr->ip; + +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + addr_fold = addr->ip6[0]^addr->ip6[1]^ + addr->ip6[2]^addr->ip6[3]; +#endif - return (proto^ntohl(addr)^(porth>>IP_VS_SVC_TAB_BITS)^porth) + return (proto^ntohl(addr_fold)^(porth>>IP_VS_SVC_TAB_BITS)^porth) & IP_VS_SVC_TAB_MASK; } @@ -316,7 +349,8 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) /* * Hash it by <protocol,addr,port> in ip_vs_svc_table */ - hash = ip_vs_svc_hashkey(svc->protocol, svc->addr, svc->port); + hash = ip_vs_svc_hashkey(svc->af, svc->protocol, &svc->addr, + svc->port); list_add(&svc->s_list, &ip_vs_svc_table[hash]); } else { /* @@ -362,17 +396,19 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc) /* * Get service by {proto,addr,port} in the service table. */ -static __inline__ struct ip_vs_service * -__ip_vs_service_get(__u16 protocol, __be32 vaddr, __be16 vport) +static inline struct ip_vs_service * +__ip_vs_service_get(int af, __u16 protocol, const union nf_inet_addr *vaddr, + __be16 vport) { unsigned hash; struct ip_vs_service *svc; /* Check for "full" addressed entries */ - hash = ip_vs_svc_hashkey(protocol, vaddr, vport); + hash = ip_vs_svc_hashkey(af, protocol, vaddr, vport); list_for_each_entry(svc, &ip_vs_svc_table[hash], s_list){ - if ((svc->addr == vaddr) + if ((svc->af == af) + && ip_vs_addr_equal(af, &svc->addr, vaddr) && (svc->port == vport) && (svc->protocol == protocol)) { /* HIT */ @@ -388,7 +424,8 @@ __ip_vs_service_get(__u16 protocol, __be32 vaddr, __be16 vport) /* * Get service by {fwmark} in the service table. */ -static __inline__ struct ip_vs_service *__ip_vs_svc_fwm_get(__u32 fwmark) +static inline struct ip_vs_service * +__ip_vs_svc_fwm_get(int af, __u32 fwmark) { unsigned hash; struct ip_vs_service *svc; @@ -397,7 +434,7 @@ static __inline__ struct ip_vs_service *__ip_vs_svc_fwm_get(__u32 fwmark) hash = ip_vs_svc_fwm_hashkey(fwmark); list_for_each_entry(svc, &ip_vs_svc_fwm_table[hash], f_list) { - if (svc->fwmark == fwmark) { + if (svc->fwmark == fwmark && svc->af == af) { /* HIT */ atomic_inc(&svc->usecnt); return svc; @@ -408,7 +445,8 @@ static __inline__ struct ip_vs_service *__ip_vs_svc_fwm_get(__u32 fwmark) } struct ip_vs_service * -ip_vs_service_get(__u32 fwmark, __u16 protocol, __be32 vaddr, __be16 vport) +ip_vs_service_get(int af, __u32 fwmark, __u16 protocol, + const union nf_inet_addr *vaddr, __be16 vport) { struct ip_vs_service *svc; @@ -417,14 +455,14 @@ ip_vs_service_get(__u32 fwmark, __u16 protocol, __be32 vaddr, __be16 vport) /* * Check the table hashed by fwmark first */ - if (fwmark && (svc = __ip_vs_svc_fwm_get(fwmark))) + if (fwmark && (svc = __ip_vs_svc_fwm_get(af, fwmark))) goto out; /* * Check the table hashed by <protocol,addr,port> * for "full" addressed entries */ - svc = __ip_vs_service_get(protocol, vaddr, vport); + svc = __ip_vs_service_get(af, protocol, vaddr, vport); if (svc == NULL && protocol == IPPROTO_TCP @@ -434,7 +472,7 @@ ip_vs_service_get(__u32 fwmark, __u16 protocol, __be32 vaddr, __be16 vport) * Check if ftp service entry exists, the packet * might belong to FTP data connections. */ - svc = __ip_vs_service_get(protocol, vaddr, FTPPORT); + svc = __ip_vs_service_get(af, protocol, vaddr, FTPPORT); } if (svc == NULL @@ -442,16 +480,16 @@ ip_vs_service_get(__u32 fwmark, __u16 protocol, __be32 vaddr, __be16 vport) /* * Check if the catch-all port (port zero) exists */ - svc = __ip_vs_service_get(protocol, vaddr, 0); + svc = __ip_vs_service_get(af, protocol, vaddr, 0); } out: read_unlock(&__ip_vs_svc_lock); - IP_VS_DBG(9, "lookup service: fwm %u %s %u.%u.%u.%u:%u %s\n", - fwmark, ip_vs_proto_name(protocol), - NIPQUAD(vaddr), ntohs(vport), - svc?"hit":"not hit"); + IP_VS_DBG_BUF(9, "lookup service: fwm %u %s %s:%u %s\n", + fwmark, ip_vs_proto_name(protocol), + IP_VS_DBG_ADDR(af, vaddr), ntohs(vport), + svc ? "hit" : "not hit"); return svc; } @@ -478,11 +516,20 @@ __ip_vs_unbind_svc(struct ip_vs_dest *dest) /* * Returns hash value for real service */ -static __inline__ unsigned ip_vs_rs_hashkey(__be32 addr, __be16 port) +static inline unsigned ip_vs_rs_hashkey(int af, + const union nf_inet_addr *addr, + __be16 port) { register unsigned porth = ntohs(port); + __be32 addr_fold = addr->ip; + +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + addr_fold = addr->ip6[0]^addr->ip6[1]^ + addr->ip6[2]^addr->ip6[3]; +#endif - return (ntohl(addr)^(porth>>IP_VS_RTAB_BITS)^porth) + return (ntohl(addr_fold)^(porth>>IP_VS_RTAB_BITS)^porth) & IP_VS_RTAB_MASK; } @@ -502,7 +549,8 @@ static int ip_vs_rs_hash(struct ip_vs_dest *dest) * Hash by proto,addr,port, * which are the parameters of the real service. */ - hash = ip_vs_rs_hashkey(dest->addr, dest->port); + hash = ip_vs_rs_hashkey(dest->af, &dest->addr, dest->port); + list_add(&dest->d_list, &ip_vs_rtable[hash]); return 1; @@ -529,7 +577,9 @@ static int ip_vs_rs_unhash(struct ip_vs_dest *dest) * Lookup real service by <proto,addr,port> in the real service table. */ struct ip_vs_dest * -ip_vs_lookup_real_service(__u16 protocol, __be32 daddr, __be16 dport) +ip_vs_lookup_real_service(int af, __u16 protocol, + const union nf_inet_addr *daddr, + __be16 dport) { unsigned hash; struct ip_vs_dest *dest; @@ -538,11 +588,12 @@ ip_vs_lookup_real_service(__u16 protocol, __be32 daddr, __be16 dport) * Check for "full" addressed entries * Return the first found entry */ - hash = ip_vs_rs_hashkey(daddr, dport); + hash = ip_vs_rs_hashkey(af, daddr, dport); read_lock(&__ip_vs_rs_lock); list_for_each_entry(dest, &ip_vs_rtable[hash], d_list) { - if ((dest->addr == daddr) + if ((dest->af == af) + && ip_vs_addr_equal(af, &dest->addr, daddr) && (dest->port == dport) && ((dest->protocol == protocol) || dest->vfwmark)) { @@ -560,7 +611,8 @@ ip_vs_lookup_real_service(__u16 protocol, __be32 daddr, __be16 dport) * Lookup destination by {addr,port} in the given service */ static struct ip_vs_dest * -ip_vs_lookup_dest(struct ip_vs_service *svc, __be32 daddr, __be16 dport) +ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, + __be16 dport) { struct ip_vs_dest *dest; @@ -568,7 +620,9 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, __be32 daddr, __be16 dport) * Find the destination for the given service */ list_for_each_entry(dest, &svc->destinations, n_list) { - if ((dest->addr == daddr) && (dest->port == dport)) { + if ((dest->af == svc->af) + && ip_vs_addr_equal(svc->af, &dest->addr, daddr) + && (dest->port == dport)) { /* HIT */ return dest; } @@ -587,13 +641,15 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, __be32 daddr, __be16 dport) * ip_vs_lookup_real_service() looked promissing, but * seems not working as expected. */ -struct ip_vs_dest *ip_vs_find_dest(__be32 daddr, __be16 dport, - __be32 vaddr, __be16 vport, __u16 protocol) +struct ip_vs_dest *ip_vs_find_dest(int af, const union nf_inet_addr *daddr, + __be16 dport, + const union nf_inet_addr *vaddr, + __be16 vport, __u16 protocol) { struct ip_vs_dest *dest; struct ip_vs_service *svc; - svc = ip_vs_service_get(0, protocol, vaddr, vport); + svc = ip_vs_service_get(af, 0, protocol, vaddr, vport); if (!svc) return NULL; dest = ip_vs_lookup_dest(svc, daddr, dport); @@ -614,7 +670,8 @@ struct ip_vs_dest *ip_vs_find_dest(__be32 daddr, __be16 dport, * scheduling. */ static struct ip_vs_dest * -ip_vs_trash_get_dest(struct ip_vs_service *svc, __be32 daddr, __be16 dport) +ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, + __be16 dport) { struct ip_vs_dest *dest, *nxt; @@ -622,17 +679,19 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, __be32 daddr, __be16 dport) * Find the destination in trash */ list_for_each_entry_safe(dest, nxt, &ip_vs_dest_trash, n_list) { - IP_VS_DBG(3, "Destination %u/%u.%u.%u.%u:%u still in trash, " - "dest->refcnt=%d\n", - dest->vfwmark, - NIPQUAD(dest->addr), ntohs(dest->port), - atomic_read(&dest->refcnt)); - if (dest->addr == daddr && + IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, " + "dest->refcnt=%d\n", + dest->vfwmark, + IP_VS_DBG_ADDR(svc->af, &dest->addr), + ntohs(dest->port), + atomic_read(&dest->refcnt)); + if (dest->af == svc->af && + ip_vs_addr_equal(svc->af, &dest->addr, daddr) && dest->port == dport && dest->vfwmark == svc->fwmark && dest->protocol == svc->protocol && (svc->fwmark || - (dest->vaddr == svc->addr && + (ip_vs_addr_equal(svc->af, &dest->vaddr, &svc->addr) && dest->vport == svc->port))) { /* HIT */ return dest; @@ -642,10 +701,11 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, __be32 daddr, __be16 dport) * Try to purge the destination from trash if not referenced */ if (atomic_read(&dest->refcnt) == 1) { - IP_VS_DBG(3, "Removing destination %u/%u.%u.%u.%u:%u " - "from trash\n", - dest->vfwmark, - NIPQUAD(dest->addr), ntohs(dest->port)); + IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u " + "from trash\n", + dest->vfwmark, + IP_VS_DBG_ADDR(svc->af, &dest->addr), + ntohs(dest->port)); list_del(&dest->n_list); ip_vs_dst_reset(dest); __ip_vs_unbind_svc(dest); @@ -684,18 +744,7 @@ ip_vs_zero_stats(struct ip_vs_stats *stats) { spin_lock_bh(&stats->lock); - stats->conns = 0; - stats->inpkts = 0; - stats->outpkts = 0; - stats->inbytes = 0; - stats->outbytes = 0; - - stats->cps = 0; - stats->inpps = 0; - stats->outpps = 0; - stats->inbps = 0; - stats->outbps = 0; - + memset(&stats->ustats, 0, sizeof(stats->ustats)); ip_vs_zero_estimator(stats); spin_unlock_bh(&stats->lock); @@ -706,7 +755,7 @@ ip_vs_zero_stats(struct ip_vs_stats *stats) */ static void __ip_vs_update_dest(struct ip_vs_service *svc, - struct ip_vs_dest *dest, struct ip_vs_dest_user *udest) + struct ip_vs_dest *dest, struct ip_vs_dest_user_kern *udest) { int conn_flags; @@ -715,10 +764,18 @@ __ip_vs_update_dest(struct ip_vs_service *svc, conn_flags = udest->conn_flags | IP_VS_CONN_F_INACTIVE; /* check if local node and update the flags */ - if (inet_addr_type(&init_net, udest->addr) == RTN_LOCAL) { - conn_flags = (conn_flags & ~IP_VS_CONN_F_FWD_MASK) - | IP_VS_CONN_F_LOCALNODE; - } +#ifdef CONFIG_IP_VS_IPV6 + if (svc->af == AF_INET6) { + if (__ip_vs_addr_is_local_v6(&udest->addr.in6)) { + conn_flags = (conn_flags & ~IP_VS_CONN_F_FWD_MASK) + | IP_VS_CONN_F_LOCALNODE; + } + } else +#endif + if (inet_addr_type(&init_net, udest->addr.ip) == RTN_LOCAL) { + conn_flags = (conn_flags & ~IP_VS_CONN_F_FWD_MASK) + | IP_VS_CONN_F_LOCALNODE; + } /* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */ if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != 0) { @@ -759,7 +816,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, * Create a destination for the given service */ static int -ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest, +ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, struct ip_vs_dest **dest_p) { struct ip_vs_dest *dest; @@ -767,9 +824,20 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest, EnterFunction(2); - atype = inet_addr_type(&init_net, udest->addr); - if (atype != RTN_LOCAL && atype != RTN_UNICAST) - return -EINVAL; +#ifdef CONFIG_IP_VS_IPV6 + if (svc->af == AF_INET6) { + atype = ipv6_addr_type(&udest->addr.in6); + if ((!(atype & IPV6_ADDR_UNICAST) || + atype & IPV6_ADDR_LINKLOCAL) && + !__ip_vs_addr_is_local_v6(&udest->addr.in6)) + return -EINVAL; + } else +#endif + { + atype = inet_addr_type(&init_net, udest->addr.ip); + if (atype != RTN_LOCAL && atype != RTN_UNICAST) + return -EINVAL; + } dest = kzalloc(sizeof(struct ip_vs_dest), GFP_ATOMIC); if (dest == NULL) { @@ -777,11 +845,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest, return -ENOMEM; } + dest->af = svc->af; dest->protocol = svc->protocol; dest->vaddr = svc->addr; dest->vport = svc->port; dest->vfwmark = svc->fwmark; - dest->addr = udest->addr; + ip_vs_addr_copy(svc->af, &dest->addr, &udest->addr); dest->port = udest->port; atomic_set(&dest->activeconns, 0); @@ -806,10 +875,10 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest, * Add a destination into an existing service */ static int -ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest) +ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) { struct ip_vs_dest *dest; - __be32 daddr = udest->addr; + union nf_inet_addr daddr; __be16 dport = udest->port; int ret; @@ -826,10 +895,13 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest) return -ERANGE; } + ip_vs_addr_copy(svc->af, &daddr, &udest->addr); + /* * Check if the dest already exists in the list */ - dest = ip_vs_lookup_dest(svc, daddr, dport); + dest = ip_vs_lookup_dest(svc, &daddr, dport); + if (dest != NULL) { IP_VS_DBG(1, "ip_vs_add_dest(): dest already exists\n"); return -EEXIST; @@ -839,15 +911,17 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest) * Check if the dest already exists in the trash and * is from the same service */ - dest = ip_vs_trash_get_dest(svc, daddr, dport); + dest = ip_vs_trash_get_dest(svc, &daddr, dport); + if (dest != NULL) { - IP_VS_DBG(3, "Get destination %u.%u.%u.%u:%u from trash, " - "dest->refcnt=%d, service %u/%u.%u.%u.%u:%u\n", - NIPQUAD(daddr), ntohs(dport), - atomic_read(&dest->refcnt), - dest->vfwmark, - NIPQUAD(dest->vaddr), - ntohs(dest->vport)); + IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, " + "dest->refcnt=%d, service %u/%s:%u\n", + IP_VS_DBG_ADDR(svc->af, &daddr), ntohs(dport), + atomic_read(&dest->refcnt), + dest->vfwmark, + IP_VS_DBG_ADDR(svc->af, &dest->vaddr), + ntohs(dest->vport)); + __ip_vs_update_dest(svc, dest, udest); /* @@ -868,7 +942,8 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest) svc->num_dests++; /* call the update_service function of its scheduler */ - svc->scheduler->update_service(svc); + if (svc->scheduler->update_service) + svc->scheduler->update_service(svc); write_unlock_bh(&__ip_vs_svc_lock); return 0; @@ -898,7 +973,8 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest) svc->num_dests++; /* call the update_service function of its scheduler */ - svc->scheduler->update_service(svc); + if (svc->scheduler->update_service) + svc->scheduler->update_service(svc); write_unlock_bh(&__ip_vs_svc_lock); @@ -912,10 +988,10 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest) * Edit a destination in the given service */ static int -ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest) +ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) { struct ip_vs_dest *dest; - __be32 daddr = udest->addr; + union nf_inet_addr daddr; __be16 dport = udest->port; EnterFunction(2); @@ -931,10 +1007,13 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest) return -ERANGE; } + ip_vs_addr_copy(svc->af, &daddr, &udest->addr); + /* * Lookup the destination list */ - dest = ip_vs_lookup_dest(svc, daddr, dport); + dest = ip_vs_lookup_dest(svc, &daddr, dport); + if (dest == NULL) { IP_VS_DBG(1, "ip_vs_edit_dest(): dest doesn't exist\n"); return -ENOENT; @@ -948,7 +1027,8 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest) IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1); /* call the update_service, because server weight may be changed */ - svc->scheduler->update_service(svc); + if (svc->scheduler->update_service) + svc->scheduler->update_service(svc); write_unlock_bh(&__ip_vs_svc_lock); @@ -987,10 +1067,11 @@ static void __ip_vs_del_dest(struct ip_vs_dest *dest) atomic_dec(&dest->svc->refcnt); kfree(dest); } else { - IP_VS_DBG(3, "Moving dest %u.%u.%u.%u:%u into trash, " - "dest->refcnt=%d\n", - NIPQUAD(dest->addr), ntohs(dest->port), - atomic_read(&dest->refcnt)); + IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, " + "dest->refcnt=%d\n", + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port), + atomic_read(&dest->refcnt)); list_add(&dest->n_list, &ip_vs_dest_trash); atomic_inc(&dest->refcnt); } @@ -1011,12 +1092,12 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, */ list_del(&dest->n_list); svc->num_dests--; - if (svcupd) { - /* - * Call the update_service function of its scheduler - */ - svc->scheduler->update_service(svc); - } + + /* + * Call the update_service function of its scheduler + */ + if (svcupd && svc->scheduler->update_service) + svc->scheduler->update_service(svc); } @@ -1024,15 +1105,15 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, * Delete a destination server in the given service */ static int -ip_vs_del_dest(struct ip_vs_service *svc,struct ip_vs_dest_user *udest) +ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) { struct ip_vs_dest *dest; - __be32 daddr = udest->addr; __be16 dport = udest->port; EnterFunction(2); - dest = ip_vs_lookup_dest(svc, daddr, dport); + dest = ip_vs_lookup_dest(svc, &udest->addr, dport); + if (dest == NULL) { IP_VS_DBG(1, "ip_vs_del_dest(): destination not found!\n"); return -ENOENT; @@ -1067,7 +1148,8 @@ ip_vs_del_dest(struct ip_vs_service *svc,struct ip_vs_dest_user *udest) * Add a service into the service hash table */ static int -ip_vs_add_service(struct ip_vs_service_user *u, struct ip_vs_service **svc_p) +ip_vs_add_service(struct ip_vs_service_user_kern *u, + struct ip_vs_service **svc_p) { int ret = 0; struct ip_vs_scheduler *sched = NULL; @@ -1085,6 +1167,19 @@ ip_vs_add_service(struct ip_vs_service_user *u, struct ip_vs_service **svc_p) goto out_mod_dec; } +#ifdef CONFIG_IP_VS_IPV6 + if (u->af == AF_INET6) { + if (!sched->supports_ipv6) { + ret = -EAFNOSUPPORT; + goto out_err; + } + if ((u->netmask < 1) || (u->netmask > 128)) { + ret = -EINVAL; + goto out_err; + } + } +#endif + svc = kzalloc(sizeof(struct ip_vs_service), GFP_ATOMIC); if (svc == NULL) { IP_VS_DBG(1, "ip_vs_add_service: kmalloc failed.\n"); @@ -1096,8 +1191,9 @@ ip_vs_add_service(struct ip_vs_service_user *u, struct ip_vs_service **svc_p) atomic_set(&svc->usecnt, 1); atomic_set(&svc->refcnt, 0); + svc->af = u->af; svc->protocol = u->protocol; - svc->addr = u->addr; + ip_vs_addr_copy(svc->af, &svc->addr, &u->addr); svc->port = u->port; svc->fwmark = u->fwmark; svc->flags = u->flags; @@ -1121,7 +1217,10 @@ ip_vs_add_service(struct ip_vs_service_user *u, struct ip_vs_service **svc_p) atomic_inc(&ip_vs_nullsvc_counter); ip_vs_new_estimator(&svc->stats); - ip_vs_num_services++; + + /* Count only IPv4 services for old get/setsockopt interface */ + if (svc->af == AF_INET) + ip_vs_num_services++; /* Hash the service into the service table */ write_lock_bh(&__ip_vs_svc_lock); @@ -1156,7 +1255,7 @@ ip_vs_add_service(struct ip_vs_service_user *u, struct ip_vs_service **svc_p) * Edit a service and bind it with a new scheduler */ static int -ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user *u) +ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) { struct ip_vs_scheduler *sched, *old_sched; int ret = 0; @@ -1172,6 +1271,19 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user *u) } old_sched = sched; +#ifdef CONFIG_IP_VS_IPV6 + if (u->af == AF_INET6) { + if (!sched->supports_ipv6) { + ret = -EAFNOSUPPORT; + goto out; + } + if ((u->netmask < 1) || (u->netmask > 128)) { + ret = -EINVAL; + goto out; + } + } +#endif + write_lock_bh(&__ip_vs_svc_lock); /* @@ -1193,7 +1305,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user *u) */ if ((ret = ip_vs_unbind_scheduler(svc))) { old_sched = sched; - goto out; + goto out_unlock; } /* @@ -1212,12 +1324,13 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user *u) */ ip_vs_bind_scheduler(svc, old_sched); old_sched = sched; - goto out; + goto out_unlock; } } - out: + out_unlock: write_unlock_bh(&__ip_vs_svc_lock); + out: if (old_sched) ip_vs_scheduler_put(old_sched); @@ -1236,7 +1349,10 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) struct ip_vs_dest *dest, *nxt; struct ip_vs_scheduler *old_sched; - ip_vs_num_services--; + /* Count only IPv4 services for old get/setsockopt interface */ + if (svc->af == AF_INET) + ip_vs_num_services--; + ip_vs_kill_estimator(&svc->stats); /* Unbind scheduler */ @@ -1671,6 +1787,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) } static void *ip_vs_info_seq_start(struct seq_file *seq, loff_t *pos) +__acquires(__ip_vs_svc_lock) { read_lock_bh(&__ip_vs_svc_lock); @@ -1724,6 +1841,7 @@ static void *ip_vs_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void ip_vs_info_seq_stop(struct seq_file *seq, void *v) +__releases(__ip_vs_svc_lock) { read_unlock_bh(&__ip_vs_svc_lock); } @@ -1744,15 +1862,25 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) const struct ip_vs_iter *iter = seq->private; const struct ip_vs_dest *dest; - if (iter->table == ip_vs_svc_table) - seq_printf(seq, "%s %08X:%04X %s ", - ip_vs_proto_name(svc->protocol), - ntohl(svc->addr), - ntohs(svc->port), - svc->scheduler->name); - else + if (iter->table == ip_vs_svc_table) { +#ifdef CONFIG_IP_VS_IPV6 + if (svc->af == AF_INET6) + seq_printf(seq, "%s [" NIP6_FMT "]:%04X %s ", + ip_vs_proto_name(svc->protocol), + NIP6(svc->addr.in6), + ntohs(svc->port), + svc->scheduler->name); + else +#endif + seq_printf(seq, "%s %08X:%04X %s ", + ip_vs_proto_name(svc->protocol), + ntohl(svc->addr.ip), + ntohs(svc->port), + svc->scheduler->name); + } else { seq_printf(seq, "FWM %08X %s ", svc->fwmark, svc->scheduler->name); + } if (svc->flags & IP_VS_SVC_F_PERSISTENT) seq_printf(seq, "persistent %d %08X\n", @@ -1762,13 +1890,29 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) seq_putc(seq, '\n'); list_for_each_entry(dest, &svc->destinations, n_list) { - seq_printf(seq, - " -> %08X:%04X %-7s %-6d %-10d %-10d\n", - ntohl(dest->addr), ntohs(dest->port), - ip_vs_fwd_name(atomic_read(&dest->conn_flags)), - atomic_read(&dest->weight), - atomic_read(&dest->activeconns), - atomic_read(&dest->inactconns)); +#ifdef CONFIG_IP_VS_IPV6 + if (dest->af == AF_INET6) + seq_printf(seq, + " -> [" NIP6_FMT "]:%04X" + " %-7s %-6d %-10d %-10d\n", + NIP6(dest->addr.in6), + ntohs(dest->port), + ip_vs_fwd_name(atomic_read(&dest->conn_flags)), + atomic_read(&dest->weight), + atomic_read(&dest->activeconns), + atomic_read(&dest->inactconns)); + else +#endif + seq_printf(seq, + " -> %08X:%04X " + "%-7s %-6d %-10d %-10d\n", + ntohl(dest->addr.ip), + ntohs(dest->port), + ip_vs_fwd_name(atomic_read(&dest->conn_flags)), + atomic_read(&dest->weight), + atomic_read(&dest->activeconns), + atomic_read(&dest->inactconns)); + } } return 0; @@ -1812,20 +1956,20 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v) " Conns Packets Packets Bytes Bytes\n"); spin_lock_bh(&ip_vs_stats.lock); - seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", ip_vs_stats.conns, - ip_vs_stats.inpkts, ip_vs_stats.outpkts, - (unsigned long long) ip_vs_stats.inbytes, - (unsigned long long) ip_vs_stats.outbytes); + seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", ip_vs_stats.ustats.conns, + ip_vs_stats.ustats.inpkts, ip_vs_stats.ustats.outpkts, + (unsigned long long) ip_vs_stats.ustats.inbytes, + (unsigned long long) ip_vs_stats.ustats.outbytes); /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); seq_printf(seq,"%8X %8X %8X %16X %16X\n", - ip_vs_stats.cps, - ip_vs_stats.inpps, - ip_vs_stats.outpps, - ip_vs_stats.inbps, - ip_vs_stats.outbps); + ip_vs_stats.ustats.cps, + ip_vs_stats.ustats.inpps, + ip_vs_stats.ustats.outpps, + ip_vs_stats.ustats.inbps, + ip_vs_stats.ustats.outbps); spin_unlock_bh(&ip_vs_stats.lock); return 0; @@ -1900,14 +2044,44 @@ static const unsigned char set_arglen[SET_CMDID(IP_VS_SO_SET_MAX)+1] = { [SET_CMDID(IP_VS_SO_SET_ZERO)] = SERVICE_ARG_LEN, }; +static void ip_vs_copy_usvc_compat(struct ip_vs_service_user_kern *usvc, + struct ip_vs_service_user *usvc_compat) +{ + usvc->af = AF_INET; + usvc->protocol = usvc_compat->protocol; + usvc->addr.ip = usvc_compat->addr; + usvc->port = usvc_compat->port; + usvc->fwmark = usvc_compat->fwmark; + + /* Deep copy of sched_name is not needed here */ + usvc->sched_name = usvc_compat->sched_name; + + usvc->flags = usvc_compat->flags; + usvc->timeout = usvc_compat->timeout; + usvc->netmask = usvc_compat->netmask; +} + +static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest, + struct ip_vs_dest_user *udest_compat) +{ + udest->addr.ip = udest_compat->addr; + udest->port = udest_compat->port; + udest->conn_flags = udest_compat->conn_flags; + udest->weight = udest_compat->weight; + udest->u_threshold = udest_compat->u_threshold; + udest->l_threshold = udest_compat->l_threshold; +} + static int do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) { int ret; unsigned char arg[MAX_ARG_LEN]; - struct ip_vs_service_user *usvc; + struct ip_vs_service_user *usvc_compat; + struct ip_vs_service_user_kern usvc; struct ip_vs_service *svc; - struct ip_vs_dest_user *udest; + struct ip_vs_dest_user *udest_compat; + struct ip_vs_dest_user_kern udest; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -1947,35 +2121,40 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) goto out_unlock; } - usvc = (struct ip_vs_service_user *)arg; - udest = (struct ip_vs_dest_user *)(usvc + 1); + usvc_compat = (struct ip_vs_service_user *)arg; + udest_compat = (struct ip_vs_dest_user *)(usvc_compat + 1); + + /* We only use the new structs internally, so copy userspace compat + * structs to extended internal versions */ + ip_vs_copy_usvc_compat(&usvc, usvc_compat); + ip_vs_copy_udest_compat(&udest, udest_compat); if (cmd == IP_VS_SO_SET_ZERO) { /* if no service address is set, zero counters in all */ - if (!usvc->fwmark && !usvc->addr && !usvc->port) { + if (!usvc.fwmark && !usvc.addr.ip && !usvc.port) { ret = ip_vs_zero_all(); goto out_unlock; } } /* Check for valid protocol: TCP or UDP, even for fwmark!=0 */ - if (usvc->protocol!=IPPROTO_TCP && usvc->protocol!=IPPROTO_UDP) { + if (usvc.protocol != IPPROTO_TCP && usvc.protocol != IPPROTO_UDP) { IP_VS_ERR("set_ctl: invalid protocol: %d %d.%d.%d.%d:%d %s\n", - usvc->protocol, NIPQUAD(usvc->addr), - ntohs(usvc->port), usvc->sched_name); + usvc.protocol, NIPQUAD(usvc.addr.ip), + ntohs(usvc.port), usvc.sched_name); ret = -EFAULT; goto out_unlock; } /* Lookup the exact service by <protocol, addr, port> or fwmark */ - if (usvc->fwmark == 0) - svc = __ip_vs_service_get(usvc->protocol, - usvc->addr, usvc->port); + if (usvc.fwmark == 0) + svc = __ip_vs_service_get(usvc.af, usvc.protocol, + &usvc.addr, usvc.port); else - svc = __ip_vs_svc_fwm_get(usvc->fwmark); + svc = __ip_vs_svc_fwm_get(usvc.af, usvc.fwmark); if (cmd != IP_VS_SO_SET_ADD - && (svc == NULL || svc->protocol != usvc->protocol)) { + && (svc == NULL || svc->protocol != usvc.protocol)) { ret = -ESRCH; goto out_unlock; } @@ -1985,10 +2164,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (svc != NULL) ret = -EEXIST; else - ret = ip_vs_add_service(usvc, &svc); + ret = ip_vs_add_service(&usvc, &svc); break; case IP_VS_SO_SET_EDIT: - ret = ip_vs_edit_service(svc, usvc); + ret = ip_vs_edit_service(svc, &usvc); break; case IP_VS_SO_SET_DEL: ret = ip_vs_del_service(svc); @@ -1999,13 +2178,13 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) ret = ip_vs_zero_service(svc); break; case IP_VS_SO_SET_ADDDEST: - ret = ip_vs_add_dest(svc, udest); + ret = ip_vs_add_dest(svc, &udest); break; case IP_VS_SO_SET_EDITDEST: - ret = ip_vs_edit_dest(svc, udest); + ret = ip_vs_edit_dest(svc, &udest); break; case IP_VS_SO_SET_DELDEST: - ret = ip_vs_del_dest(svc, udest); + ret = ip_vs_del_dest(svc, &udest); break; default: ret = -EINVAL; @@ -2028,7 +2207,7 @@ static void ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src) { spin_lock_bh(&src->lock); - memcpy(dst, src, (char*)&src->lock - (char*)src); + memcpy(dst, &src->ustats, sizeof(*dst)); spin_unlock_bh(&src->lock); } @@ -2036,7 +2215,7 @@ static void ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) { dst->protocol = src->protocol; - dst->addr = src->addr; + dst->addr = src->addr.ip; dst->port = src->port; dst->fwmark = src->fwmark; strlcpy(dst->sched_name, src->scheduler->name, sizeof(dst->sched_name)); @@ -2058,6 +2237,10 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get, for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { + /* Only expose IPv4 entries to old interface */ + if (svc->af != AF_INET) + continue; + if (count >= get->num_services) goto out; memset(&entry, 0, sizeof(entry)); @@ -2073,6 +2256,10 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get, for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { + /* Only expose IPv4 entries to old interface */ + if (svc->af != AF_INET) + continue; + if (count >= get->num_services) goto out; memset(&entry, 0, sizeof(entry)); @@ -2094,13 +2281,15 @@ __ip_vs_get_dest_entries(const struct ip_vs_get_dests *get, struct ip_vs_get_dests __user *uptr) { struct ip_vs_service *svc; + union nf_inet_addr addr = { .ip = get->addr }; int ret = 0; if (get->fwmark) - svc = __ip_vs_svc_fwm_get(get->fwmark); + svc = __ip_vs_svc_fwm_get(AF_INET, get->fwmark); else - svc = __ip_vs_service_get(get->protocol, - get->addr, get->port); + svc = __ip_vs_service_get(AF_INET, get->protocol, &addr, + get->port); + if (svc) { int count = 0; struct ip_vs_dest *dest; @@ -2110,7 +2299,7 @@ __ip_vs_get_dest_entries(const struct ip_vs_get_dests *get, if (count >= get->num_dests) break; - entry.addr = dest->addr; + entry.addr = dest->addr.ip; entry.port = dest->port; entry.conn_flags = atomic_read(&dest->conn_flags); entry.weight = atomic_read(&dest->weight); @@ -2235,13 +2424,15 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { struct ip_vs_service_entry *entry; struct ip_vs_service *svc; + union nf_inet_addr addr; entry = (struct ip_vs_service_entry *)arg; + addr.ip = entry->addr; if (entry->fwmark) - svc = __ip_vs_svc_fwm_get(entry->fwmark); + svc = __ip_vs_svc_fwm_get(AF_INET, entry->fwmark); else - svc = __ip_vs_service_get(entry->protocol, - entry->addr, entry->port); + svc = __ip_vs_service_get(AF_INET, entry->protocol, + &addr, entry->port); if (svc) { ip_vs_copy_service(entry, svc); if (copy_to_user(user, entry, sizeof(*entry)) != 0) @@ -2320,6 +2511,875 @@ static struct nf_sockopt_ops ip_vs_sockopts = { .owner = THIS_MODULE, }; +/* + * Generic Netlink interface + */ + +/* IPVS genetlink family */ +static struct genl_family ip_vs_genl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = IPVS_GENL_NAME, + .version = IPVS_GENL_VERSION, + .maxattr = IPVS_CMD_MAX, +}; + +/* Policy used for first-level command attributes */ +static const struct nla_policy ip_vs_cmd_policy[IPVS_CMD_ATTR_MAX + 1] = { + [IPVS_CMD_ATTR_SERVICE] = { .type = NLA_NESTED }, + [IPVS_CMD_ATTR_DEST] = { .type = NLA_NESTED }, + [IPVS_CMD_ATTR_DAEMON] = { .type = NLA_NESTED }, + [IPVS_CMD_ATTR_TIMEOUT_TCP] = { .type = NLA_U32 }, + [IPVS_CMD_ATTR_TIMEOUT_TCP_FIN] = { .type = NLA_U32 }, + [IPVS_CMD_ATTR_TIMEOUT_UDP] = { .type = NLA_U32 }, +}; + +/* Policy used for attributes in nested attribute IPVS_CMD_ATTR_DAEMON */ +static const struct nla_policy ip_vs_daemon_policy[IPVS_DAEMON_ATTR_MAX + 1] = { + [IPVS_DAEMON_ATTR_STATE] = { .type = NLA_U32 }, + [IPVS_DAEMON_ATTR_MCAST_IFN] = { .type = NLA_NUL_STRING, + .len = IP_VS_IFNAME_MAXLEN }, + [IPVS_DAEMON_ATTR_SYNC_ID] = { .type = NLA_U32 }, +}; + +/* Policy used for attributes in nested attribute IPVS_CMD_ATTR_SERVICE */ +static const struct nla_policy ip_vs_svc_policy[IPVS_SVC_ATTR_MAX + 1] = { + [IPVS_SVC_ATTR_AF] = { .type = NLA_U16 }, + [IPVS_SVC_ATTR_PROTOCOL] = { .type = NLA_U16 }, + [IPVS_SVC_ATTR_ADDR] = { .type = NLA_BINARY, + .len = sizeof(union nf_inet_addr) }, + [IPVS_SVC_ATTR_PORT] = { .type = NLA_U16 }, + [IPVS_SVC_ATTR_FWMARK] = { .type = NLA_U32 }, + [IPVS_SVC_ATTR_SCHED_NAME] = { .type = NLA_NUL_STRING, + .len = IP_VS_SCHEDNAME_MAXLEN }, + [IPVS_SVC_ATTR_FLAGS] = { .type = NLA_BINARY, + .len = sizeof(struct ip_vs_flags) }, + [IPVS_SVC_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPVS_SVC_ATTR_NETMASK] = { .type = NLA_U32 }, + [IPVS_SVC_ATTR_STATS] = { .type = NLA_NESTED }, +}; + +/* Policy used for attributes in nested attribute IPVS_CMD_ATTR_DEST */ +static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = { + [IPVS_DEST_ATTR_ADDR] = { .type = NLA_BINARY, + .len = sizeof(union nf_inet_addr) }, + [IPVS_DEST_ATTR_PORT] = { .type = NLA_U16 }, + [IPVS_DEST_ATTR_FWD_METHOD] = { .type = NLA_U32 }, + [IPVS_DEST_ATTR_WEIGHT] = { .type = NLA_U32 }, + [IPVS_DEST_ATTR_U_THRESH] = { .type = NLA_U32 }, + [IPVS_DEST_ATTR_L_THRESH] = { .type = NLA_U32 }, + [IPVS_DEST_ATTR_ACTIVE_CONNS] = { .type = NLA_U32 }, + [IPVS_DEST_ATTR_INACT_CONNS] = { .type = NLA_U32 }, + [IPVS_DEST_ATTR_PERSIST_CONNS] = { .type = NLA_U32 }, + [IPVS_DEST_ATTR_STATS] = { .type = NLA_NESTED }, +}; + +static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type, + struct ip_vs_stats *stats) +{ + struct nlattr *nl_stats = nla_nest_start(skb, container_type); + if (!nl_stats) + return -EMSGSIZE; + + spin_lock_bh(&stats->lock); + + NLA_PUT_U32(skb, IPVS_STATS_ATTR_CONNS, stats->ustats.conns); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPKTS, stats->ustats.inpkts); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPKTS, stats->ustats.outpkts); + NLA_PUT_U64(skb, IPVS_STATS_ATTR_INBYTES, stats->ustats.inbytes); + NLA_PUT_U64(skb, IPVS_STATS_ATTR_OUTBYTES, stats->ustats.outbytes); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_CPS, stats->ustats.cps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPPS, stats->ustats.inpps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPPS, stats->ustats.outpps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_INBPS, stats->ustats.inbps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTBPS, stats->ustats.outbps); + + spin_unlock_bh(&stats->lock); + + nla_nest_end(skb, nl_stats); + + return 0; + +nla_put_failure: + spin_unlock_bh(&stats->lock); + nla_nest_cancel(skb, nl_stats); + return -EMSGSIZE; +} + +static int ip_vs_genl_fill_service(struct sk_buff *skb, + struct ip_vs_service *svc) +{ + struct nlattr *nl_service; + struct ip_vs_flags flags = { .flags = svc->flags, + .mask = ~0 }; + + nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE); + if (!nl_service) + return -EMSGSIZE; + + NLA_PUT_U16(skb, IPVS_SVC_ATTR_AF, svc->af); + + if (svc->fwmark) { + NLA_PUT_U32(skb, IPVS_SVC_ATTR_FWMARK, svc->fwmark); + } else { + NLA_PUT_U16(skb, IPVS_SVC_ATTR_PROTOCOL, svc->protocol); + NLA_PUT(skb, IPVS_SVC_ATTR_ADDR, sizeof(svc->addr), &svc->addr); + NLA_PUT_U16(skb, IPVS_SVC_ATTR_PORT, svc->port); + } + + NLA_PUT_STRING(skb, IPVS_SVC_ATTR_SCHED_NAME, svc->scheduler->name); + NLA_PUT(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags); + NLA_PUT_U32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ); + NLA_PUT_U32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask); + + if (ip_vs_genl_fill_stats(skb, IPVS_SVC_ATTR_STATS, &svc->stats)) + goto nla_put_failure; + + nla_nest_end(skb, nl_service); + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nl_service); + return -EMSGSIZE; +} + +static int ip_vs_genl_dump_service(struct sk_buff *skb, + struct ip_vs_service *svc, + struct netlink_callback *cb) +{ + void *hdr; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + &ip_vs_genl_family, NLM_F_MULTI, + IPVS_CMD_NEW_SERVICE); + if (!hdr) + return -EMSGSIZE; + + if (ip_vs_genl_fill_service(skb, svc) < 0) + goto nla_put_failure; + + return genlmsg_end(skb, hdr); + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int ip_vs_genl_dump_services(struct sk_buff *skb, + struct netlink_callback *cb) +{ + int idx = 0, i; + int start = cb->args[0]; + struct ip_vs_service *svc; + + mutex_lock(&__ip_vs_mutex); + for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { + list_for_each_entry(svc, &ip_vs_svc_table[i], s_list) { + if (++idx <= start) + continue; + if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { + idx--; + goto nla_put_failure; + } + } + } + + for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { + list_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) { + if (++idx <= start) + continue; + if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { + idx--; + goto nla_put_failure; + } + } + } + +nla_put_failure: + mutex_unlock(&__ip_vs_mutex); + cb->args[0] = idx; + + return skb->len; +} + +static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, + struct nlattr *nla, int full_entry) +{ + struct nlattr *attrs[IPVS_SVC_ATTR_MAX + 1]; + struct nlattr *nla_af, *nla_port, *nla_fwmark, *nla_protocol, *nla_addr; + + /* Parse mandatory identifying service fields first */ + if (nla == NULL || + nla_parse_nested(attrs, IPVS_SVC_ATTR_MAX, nla, ip_vs_svc_policy)) + return -EINVAL; + + nla_af = attrs[IPVS_SVC_ATTR_AF]; + nla_protocol = attrs[IPVS_SVC_ATTR_PROTOCOL]; + nla_addr = attrs[IPVS_SVC_ATTR_ADDR]; + nla_port = attrs[IPVS_SVC_ATTR_PORT]; + nla_fwmark = attrs[IPVS_SVC_ATTR_FWMARK]; + + if (!(nla_af && (nla_fwmark || (nla_port && nla_protocol && nla_addr)))) + return -EINVAL; + + usvc->af = nla_get_u16(nla_af); +#ifdef CONFIG_IP_VS_IPV6 + if (usvc->af != AF_INET && usvc->af != AF_INET6) +#else + if (usvc->af != AF_INET) +#endif + return -EAFNOSUPPORT; + + if (nla_fwmark) { + usvc->protocol = IPPROTO_TCP; + usvc->fwmark = nla_get_u32(nla_fwmark); + } else { + usvc->protocol = nla_get_u16(nla_protocol); + nla_memcpy(&usvc->addr, nla_addr, sizeof(usvc->addr)); + usvc->port = nla_get_u16(nla_port); + usvc->fwmark = 0; + } + + /* If a full entry was requested, check for the additional fields */ + if (full_entry) { + struct nlattr *nla_sched, *nla_flags, *nla_timeout, + *nla_netmask; + struct ip_vs_flags flags; + struct ip_vs_service *svc; + + nla_sched = attrs[IPVS_SVC_ATTR_SCHED_NAME]; + nla_flags = attrs[IPVS_SVC_ATTR_FLAGS]; + nla_timeout = attrs[IPVS_SVC_ATTR_TIMEOUT]; + nla_netmask = attrs[IPVS_SVC_ATTR_NETMASK]; + + if (!(nla_sched && nla_flags && nla_timeout && nla_netmask)) + return -EINVAL; + + nla_memcpy(&flags, nla_flags, sizeof(flags)); + + /* prefill flags from service if it already exists */ + if (usvc->fwmark) + svc = __ip_vs_svc_fwm_get(usvc->af, usvc->fwmark); + else + svc = __ip_vs_service_get(usvc->af, usvc->protocol, + &usvc->addr, usvc->port); + if (svc) { + usvc->flags = svc->flags; + ip_vs_service_put(svc); + } else + usvc->flags = 0; + + /* set new flags from userland */ + usvc->flags = (usvc->flags & ~flags.mask) | + (flags.flags & flags.mask); + usvc->sched_name = nla_data(nla_sched); + usvc->timeout = nla_get_u32(nla_timeout); + usvc->netmask = nla_get_u32(nla_netmask); + } + + return 0; +} + +static struct ip_vs_service *ip_vs_genl_find_service(struct nlattr *nla) +{ + struct ip_vs_service_user_kern usvc; + int ret; + + ret = ip_vs_genl_parse_service(&usvc, nla, 0); + if (ret) + return ERR_PTR(ret); + + if (usvc.fwmark) + return __ip_vs_svc_fwm_get(usvc.af, usvc.fwmark); + else + return __ip_vs_service_get(usvc.af, usvc.protocol, + &usvc.addr, usvc.port); +} + +static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest) +{ + struct nlattr *nl_dest; + + nl_dest = nla_nest_start(skb, IPVS_CMD_ATTR_DEST); + if (!nl_dest) + return -EMSGSIZE; + + NLA_PUT(skb, IPVS_DEST_ATTR_ADDR, sizeof(dest->addr), &dest->addr); + NLA_PUT_U16(skb, IPVS_DEST_ATTR_PORT, dest->port); + + NLA_PUT_U32(skb, IPVS_DEST_ATTR_FWD_METHOD, + atomic_read(&dest->conn_flags) & IP_VS_CONN_F_FWD_MASK); + NLA_PUT_U32(skb, IPVS_DEST_ATTR_WEIGHT, atomic_read(&dest->weight)); + NLA_PUT_U32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold); + NLA_PUT_U32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold); + NLA_PUT_U32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS, + atomic_read(&dest->activeconns)); + NLA_PUT_U32(skb, IPVS_DEST_ATTR_INACT_CONNS, + atomic_read(&dest->inactconns)); + NLA_PUT_U32(skb, IPVS_DEST_ATTR_PERSIST_CONNS, + atomic_read(&dest->persistconns)); + + if (ip_vs_genl_fill_stats(skb, IPVS_DEST_ATTR_STATS, &dest->stats)) + goto nla_put_failure; + + nla_nest_end(skb, nl_dest); + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nl_dest); + return -EMSGSIZE; +} + +static int ip_vs_genl_dump_dest(struct sk_buff *skb, struct ip_vs_dest *dest, + struct netlink_callback *cb) +{ + void *hdr; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + &ip_vs_genl_family, NLM_F_MULTI, + IPVS_CMD_NEW_DEST); + if (!hdr) + return -EMSGSIZE; + + if (ip_vs_genl_fill_dest(skb, dest) < 0) + goto nla_put_failure; + + return genlmsg_end(skb, hdr); + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int ip_vs_genl_dump_dests(struct sk_buff *skb, + struct netlink_callback *cb) +{ + int idx = 0; + int start = cb->args[0]; + struct ip_vs_service *svc; + struct ip_vs_dest *dest; + struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1]; + + mutex_lock(&__ip_vs_mutex); + + /* Try to find the service for which to dump destinations */ + if (nlmsg_parse(cb->nlh, GENL_HDRLEN, attrs, + IPVS_CMD_ATTR_MAX, ip_vs_cmd_policy)) + goto out_err; + + svc = ip_vs_genl_find_service(attrs[IPVS_CMD_ATTR_SERVICE]); + if (IS_ERR(svc) || svc == NULL) + goto out_err; + + /* Dump the destinations */ + list_for_each_entry(dest, &svc->destinations, n_list) { + if (++idx <= start) + continue; + if (ip_vs_genl_dump_dest(skb, dest, cb) < 0) { + idx--; + goto nla_put_failure; + } + } + +nla_put_failure: + cb->args[0] = idx; + ip_vs_service_put(svc); + +out_err: + mutex_unlock(&__ip_vs_mutex); + + return skb->len; +} + +static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, + struct nlattr *nla, int full_entry) +{ + struct nlattr *attrs[IPVS_DEST_ATTR_MAX + 1]; + struct nlattr *nla_addr, *nla_port; + + /* Parse mandatory identifying destination fields first */ + if (nla == NULL || + nla_parse_nested(attrs, IPVS_DEST_ATTR_MAX, nla, ip_vs_dest_policy)) + return -EINVAL; + + nla_addr = attrs[IPVS_DEST_ATTR_ADDR]; + nla_port = attrs[IPVS_DEST_ATTR_PORT]; + + if (!(nla_addr && nla_port)) + return -EINVAL; + + nla_memcpy(&udest->addr, nla_addr, sizeof(udest->addr)); + udest->port = nla_get_u16(nla_port); + + /* If a full entry was requested, check for the additional fields */ + if (full_entry) { + struct nlattr *nla_fwd, *nla_weight, *nla_u_thresh, + *nla_l_thresh; + + nla_fwd = attrs[IPVS_DEST_ATTR_FWD_METHOD]; + nla_weight = attrs[IPVS_DEST_ATTR_WEIGHT]; + nla_u_thresh = attrs[IPVS_DEST_ATTR_U_THRESH]; + nla_l_thresh = attrs[IPVS_DEST_ATTR_L_THRESH]; + + if (!(nla_fwd && nla_weight && nla_u_thresh && nla_l_thresh)) + return -EINVAL; + + udest->conn_flags = nla_get_u32(nla_fwd) + & IP_VS_CONN_F_FWD_MASK; + udest->weight = nla_get_u32(nla_weight); + udest->u_threshold = nla_get_u32(nla_u_thresh); + udest->l_threshold = nla_get_u32(nla_l_thresh); + } + + return 0; +} + +static int ip_vs_genl_fill_daemon(struct sk_buff *skb, __be32 state, + const char *mcast_ifn, __be32 syncid) +{ + struct nlattr *nl_daemon; + + nl_daemon = nla_nest_start(skb, IPVS_CMD_ATTR_DAEMON); + if (!nl_daemon) + return -EMSGSIZE; + + NLA_PUT_U32(skb, IPVS_DAEMON_ATTR_STATE, state); + NLA_PUT_STRING(skb, IPVS_DAEMON_ATTR_MCAST_IFN, mcast_ifn); + NLA_PUT_U32(skb, IPVS_DAEMON_ATTR_SYNC_ID, syncid); + + nla_nest_end(skb, nl_daemon); + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nl_daemon); + return -EMSGSIZE; +} + +static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __be32 state, + const char *mcast_ifn, __be32 syncid, + struct netlink_callback *cb) +{ + void *hdr; + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + &ip_vs_genl_family, NLM_F_MULTI, + IPVS_CMD_NEW_DAEMON); + if (!hdr) + return -EMSGSIZE; + + if (ip_vs_genl_fill_daemon(skb, state, mcast_ifn, syncid)) + goto nla_put_failure; + + return genlmsg_end(skb, hdr); + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int ip_vs_genl_dump_daemons(struct sk_buff *skb, + struct netlink_callback *cb) +{ + mutex_lock(&__ip_vs_mutex); + if ((ip_vs_sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) { + if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER, + ip_vs_master_mcast_ifn, + ip_vs_master_syncid, cb) < 0) + goto nla_put_failure; + + cb->args[0] = 1; + } + + if ((ip_vs_sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) { + if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_BACKUP, + ip_vs_backup_mcast_ifn, + ip_vs_backup_syncid, cb) < 0) + goto nla_put_failure; + + cb->args[1] = 1; + } + +nla_put_failure: + mutex_unlock(&__ip_vs_mutex); + + return skb->len; +} + +static int ip_vs_genl_new_daemon(struct nlattr **attrs) +{ + if (!(attrs[IPVS_DAEMON_ATTR_STATE] && + attrs[IPVS_DAEMON_ATTR_MCAST_IFN] && + attrs[IPVS_DAEMON_ATTR_SYNC_ID])) + return -EINVAL; + + return start_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]), + nla_data(attrs[IPVS_DAEMON_ATTR_MCAST_IFN]), + nla_get_u32(attrs[IPVS_DAEMON_ATTR_SYNC_ID])); +} + +static int ip_vs_genl_del_daemon(struct nlattr **attrs) +{ + if (!attrs[IPVS_DAEMON_ATTR_STATE]) + return -EINVAL; + + return stop_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); +} + +static int ip_vs_genl_set_config(struct nlattr **attrs) +{ + struct ip_vs_timeout_user t; + + __ip_vs_get_timeouts(&t); + + if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]) + t.tcp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]); + + if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP_FIN]) + t.tcp_fin_timeout = + nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP_FIN]); + + if (attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]) + t.udp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]); + + return ip_vs_set_timeout(&t); +} + +static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) +{ + struct ip_vs_service *svc = NULL; + struct ip_vs_service_user_kern usvc; + struct ip_vs_dest_user_kern udest; + int ret = 0, cmd; + int need_full_svc = 0, need_full_dest = 0; + + cmd = info->genlhdr->cmd; + + mutex_lock(&__ip_vs_mutex); + + if (cmd == IPVS_CMD_FLUSH) { + ret = ip_vs_flush(); + goto out; + } else if (cmd == IPVS_CMD_SET_CONFIG) { + ret = ip_vs_genl_set_config(info->attrs); + goto out; + } else if (cmd == IPVS_CMD_NEW_DAEMON || + cmd == IPVS_CMD_DEL_DAEMON) { + + struct nlattr *daemon_attrs[IPVS_DAEMON_ATTR_MAX + 1]; + + if (!info->attrs[IPVS_CMD_ATTR_DAEMON] || + nla_parse_nested(daemon_attrs, IPVS_DAEMON_ATTR_MAX, + info->attrs[IPVS_CMD_ATTR_DAEMON], + ip_vs_daemon_policy)) { + ret = -EINVAL; + goto out; + } + + if (cmd == IPVS_CMD_NEW_DAEMON) + ret = ip_vs_genl_new_daemon(daemon_attrs); + else + ret = ip_vs_genl_del_daemon(daemon_attrs); + goto out; + } else if (cmd == IPVS_CMD_ZERO && + !info->attrs[IPVS_CMD_ATTR_SERVICE]) { + ret = ip_vs_zero_all(); + goto out; + } + + /* All following commands require a service argument, so check if we + * received a valid one. We need a full service specification when + * adding / editing a service. Only identifying members otherwise. */ + if (cmd == IPVS_CMD_NEW_SERVICE || cmd == IPVS_CMD_SET_SERVICE) + need_full_svc = 1; + + ret = ip_vs_genl_parse_service(&usvc, + info->attrs[IPVS_CMD_ATTR_SERVICE], + need_full_svc); + if (ret) + goto out; + + /* Lookup the exact service by <protocol, addr, port> or fwmark */ + if (usvc.fwmark == 0) + svc = __ip_vs_service_get(usvc.af, usvc.protocol, + &usvc.addr, usvc.port); + else + svc = __ip_vs_svc_fwm_get(usvc.af, usvc.fwmark); + + /* Unless we're adding a new service, the service must already exist */ + if ((cmd != IPVS_CMD_NEW_SERVICE) && (svc == NULL)) { + ret = -ESRCH; + goto out; + } + + /* Destination commands require a valid destination argument. For + * adding / editing a destination, we need a full destination + * specification. */ + if (cmd == IPVS_CMD_NEW_DEST || cmd == IPVS_CMD_SET_DEST || + cmd == IPVS_CMD_DEL_DEST) { + if (cmd != IPVS_CMD_DEL_DEST) + need_full_dest = 1; + + ret = ip_vs_genl_parse_dest(&udest, + info->attrs[IPVS_CMD_ATTR_DEST], + need_full_dest); + if (ret) + goto out; + } + + switch (cmd) { + case IPVS_CMD_NEW_SERVICE: + if (svc == NULL) + ret = ip_vs_add_service(&usvc, &svc); + else + ret = -EEXIST; + break; + case IPVS_CMD_SET_SERVICE: + ret = ip_vs_edit_service(svc, &usvc); + break; + case IPVS_CMD_DEL_SERVICE: + ret = ip_vs_del_service(svc); + break; + case IPVS_CMD_NEW_DEST: + ret = ip_vs_add_dest(svc, &udest); + break; + case IPVS_CMD_SET_DEST: + ret = ip_vs_edit_dest(svc, &udest); + break; + case IPVS_CMD_DEL_DEST: + ret = ip_vs_del_dest(svc, &udest); + break; + case IPVS_CMD_ZERO: + ret = ip_vs_zero_service(svc); + break; + default: + ret = -EINVAL; + } + +out: + if (svc) + ip_vs_service_put(svc); + mutex_unlock(&__ip_vs_mutex); + + return ret; +} + +static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *msg; + void *reply; + int ret, cmd, reply_cmd; + + cmd = info->genlhdr->cmd; + + if (cmd == IPVS_CMD_GET_SERVICE) + reply_cmd = IPVS_CMD_NEW_SERVICE; + else if (cmd == IPVS_CMD_GET_INFO) + reply_cmd = IPVS_CMD_SET_INFO; + else if (cmd == IPVS_CMD_GET_CONFIG) + reply_cmd = IPVS_CMD_SET_CONFIG; + else { + IP_VS_ERR("unknown Generic Netlink command\n"); + return -EINVAL; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&__ip_vs_mutex); + + reply = genlmsg_put_reply(msg, info, &ip_vs_genl_family, 0, reply_cmd); + if (reply == NULL) + goto nla_put_failure; + + switch (cmd) { + case IPVS_CMD_GET_SERVICE: + { + struct ip_vs_service *svc; + + svc = ip_vs_genl_find_service(info->attrs[IPVS_CMD_ATTR_SERVICE]); + if (IS_ERR(svc)) { + ret = PTR_ERR(svc); + goto out_err; + } else if (svc) { + ret = ip_vs_genl_fill_service(msg, svc); + ip_vs_service_put(svc); + if (ret) + goto nla_put_failure; + } else { + ret = -ESRCH; + goto out_err; + } + + break; + } + + case IPVS_CMD_GET_CONFIG: + { + struct ip_vs_timeout_user t; + + __ip_vs_get_timeouts(&t); +#ifdef CONFIG_IP_VS_PROTO_TCP + NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP, t.tcp_timeout); + NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP_FIN, + t.tcp_fin_timeout); +#endif +#ifdef CONFIG_IP_VS_PROTO_UDP + NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_UDP, t.udp_timeout); +#endif + + break; + } + + case IPVS_CMD_GET_INFO: + NLA_PUT_U32(msg, IPVS_INFO_ATTR_VERSION, IP_VS_VERSION_CODE); + NLA_PUT_U32(msg, IPVS_INFO_ATTR_CONN_TAB_SIZE, + IP_VS_CONN_TAB_SIZE); + break; + } + + genlmsg_end(msg, reply); + ret = genlmsg_unicast(msg, info->snd_pid); + goto out; + +nla_put_failure: + IP_VS_ERR("not enough space in Netlink message\n"); + ret = -EMSGSIZE; + +out_err: + nlmsg_free(msg); +out: + mutex_unlock(&__ip_vs_mutex); + + return ret; +} + + +static struct genl_ops ip_vs_genl_ops[] __read_mostly = { + { + .cmd = IPVS_CMD_NEW_SERVICE, + .flags = GENL_ADMIN_PERM, + .policy = ip_vs_cmd_policy, + .doit = ip_vs_genl_set_cmd, + }, + { + .cmd = IPVS_CMD_SET_SERVICE, + .flags = GENL_ADMIN_PERM, + .policy = ip_vs_cmd_policy, + .doit = ip_vs_genl_set_cmd, + }, + { + .cmd = IPVS_CMD_DEL_SERVICE, + .flags = GENL_ADMIN_PERM, + .policy = ip_vs_cmd_policy, + .doit = ip_vs_genl_set_cmd, + }, + { + .cmd = IPVS_CMD_GET_SERVICE, + .flags = GENL_ADMIN_PERM, + .doit = ip_vs_genl_get_cmd, + .dumpit = ip_vs_genl_dump_services, + .policy = ip_vs_cmd_policy, + }, + { + .cmd = IPVS_CMD_NEW_DEST, + .flags = GENL_ADMIN_PERM, + .policy = ip_vs_cmd_policy, + .doit = ip_vs_genl_set_cmd, + }, + { + .cmd = IPVS_CMD_SET_DEST, + .flags = GENL_ADMIN_PERM, + .policy = ip_vs_cmd_policy, + .doit = ip_vs_genl_set_cmd, + }, + { + .cmd = IPVS_CMD_DEL_DEST, + .flags = GENL_ADMIN_PERM, + .policy = ip_vs_cmd_policy, + .doit = ip_vs_genl_set_cmd, + }, + { + .cmd = IPVS_CMD_GET_DEST, + .flags = GENL_ADMIN_PERM, + .policy = ip_vs_cmd_policy, + .dumpit = ip_vs_genl_dump_dests, + }, + { + .cmd = IPVS_CMD_NEW_DAEMON, + .flags = GENL_ADMIN_PERM, + .policy = ip_vs_cmd_policy, + .doit = ip_vs_genl_set_cmd, + }, + { + .cmd = IPVS_CMD_DEL_DAEMON, + .flags = GENL_ADMIN_PERM, + .policy = ip_vs_cmd_policy, + .doit = ip_vs_genl_set_cmd, + }, + { + .cmd = IPVS_CMD_GET_DAEMON, + .flags = GENL_ADMIN_PERM, + .dumpit = ip_vs_genl_dump_daemons, + }, + { + .cmd = IPVS_CMD_SET_CONFIG, + .flags = GENL_ADMIN_PERM, + .policy = ip_vs_cmd_policy, + .doit = ip_vs_genl_set_cmd, + }, + { + .cmd = IPVS_CMD_GET_CONFIG, + .flags = GENL_ADMIN_PERM, + .doit = ip_vs_genl_get_cmd, + }, + { + .cmd = IPVS_CMD_GET_INFO, + .flags = GENL_ADMIN_PERM, + .doit = ip_vs_genl_get_cmd, + }, + { + .cmd = IPVS_CMD_ZERO, + .flags = GENL_ADMIN_PERM, + .policy = ip_vs_cmd_policy, + .doit = ip_vs_genl_set_cmd, + }, + { + .cmd = IPVS_CMD_FLUSH, + .flags = GENL_ADMIN_PERM, + .doit = ip_vs_genl_set_cmd, + }, +}; + +static int __init ip_vs_genl_register(void) +{ + int ret, i; + + ret = genl_register_family(&ip_vs_genl_family); + if (ret) + return ret; + + for (i = 0; i < ARRAY_SIZE(ip_vs_genl_ops); i++) { + ret = genl_register_ops(&ip_vs_genl_family, &ip_vs_genl_ops[i]); + if (ret) + goto err_out; + } + return 0; + +err_out: + genl_unregister_family(&ip_vs_genl_family); + return ret; +} + +static void ip_vs_genl_unregister(void) +{ + genl_unregister_family(&ip_vs_genl_family); +} + +/* End of Generic Netlink interface definitions */ + int __init ip_vs_control_init(void) { @@ -2334,6 +3394,13 @@ int __init ip_vs_control_init(void) return ret; } + ret = ip_vs_genl_register(); + if (ret) { + IP_VS_ERR("cannot register Generic Netlink interface.\n"); + nf_unregister_sockopt(&ip_vs_sockopts); + return ret; + } + proc_net_fops_create(&init_net, "ip_vs", 0, &ip_vs_info_fops); proc_net_fops_create(&init_net, "ip_vs_stats",0, &ip_vs_stats_fops); @@ -2368,6 +3435,7 @@ void ip_vs_control_cleanup(void) unregister_sysctl_table(sysctl_header); proc_net_remove(&init_net, "ip_vs_stats"); proc_net_remove(&init_net, "ip_vs"); + ip_vs_genl_unregister(); nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); } diff --git a/net/ipv4/ipvs/ip_vs_dh.c b/net/ipv4/ipvs/ip_vs_dh.c index fa66824..a16943f 100644 --- a/net/ipv4/ipvs/ip_vs_dh.c +++ b/net/ipv4/ipvs/ip_vs_dh.c @@ -218,7 +218,7 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) IP_VS_DBG(6, "DH: destination IP address %u.%u.%u.%u " "--> server %u.%u.%u.%u:%d\n", NIPQUAD(iph->daddr), - NIPQUAD(dest->addr), + NIPQUAD(dest->addr.ip), ntohs(dest->port)); return dest; @@ -234,6 +234,9 @@ static struct ip_vs_scheduler ip_vs_dh_scheduler = .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_dh_scheduler.n_list), +#ifdef CONFIG_IP_VS_IPV6 + .supports_ipv6 = 0, +#endif .init_service = ip_vs_dh_init_svc, .done_service = ip_vs_dh_done_svc, .update_service = ip_vs_dh_update_svc, diff --git a/net/ipv4/ipvs/ip_vs_est.c b/net/ipv4/ipvs/ip_vs_est.c index 5a20f93..2eb2860 100644 --- a/net/ipv4/ipvs/ip_vs_est.c +++ b/net/ipv4/ipvs/ip_vs_est.c @@ -65,37 +65,37 @@ static void estimation_timer(unsigned long arg) s = container_of(e, struct ip_vs_stats, est); spin_lock(&s->lock); - n_conns = s->conns; - n_inpkts = s->inpkts; - n_outpkts = s->outpkts; - n_inbytes = s->inbytes; - n_outbytes = s->outbytes; + n_conns = s->ustats.conns; + n_inpkts = s->ustats.inpkts; + n_outpkts = s->ustats.outpkts; + n_inbytes = s->ustats.inbytes; + n_outbytes = s->ustats.outbytes; /* scaled by 2^10, but divided 2 seconds */ rate = (n_conns - e->last_conns)<<9; e->last_conns = n_conns; e->cps += ((long)rate - (long)e->cps)>>2; - s->cps = (e->cps+0x1FF)>>10; + s->ustats.cps = (e->cps+0x1FF)>>10; rate = (n_inpkts - e->last_inpkts)<<9; e->last_inpkts = n_inpkts; e->inpps += ((long)rate - (long)e->inpps)>>2; - s->inpps = (e->inpps+0x1FF)>>10; + s->ustats.inpps = (e->inpps+0x1FF)>>10; rate = (n_outpkts - e->last_outpkts)<<9; e->last_outpkts = n_outpkts; e->outpps += ((long)rate - (long)e->outpps)>>2; - s->outpps = (e->outpps+0x1FF)>>10; + s->ustats.outpps = (e->outpps+0x1FF)>>10; rate = (n_inbytes - e->last_inbytes)<<4; e->last_inbytes = n_inbytes; e->inbps += ((long)rate - (long)e->inbps)>>2; - s->inbps = (e->inbps+0xF)>>5; + s->ustats.inbps = (e->inbps+0xF)>>5; rate = (n_outbytes - e->last_outbytes)<<4; e->last_outbytes = n_outbytes; e->outbps += ((long)rate - (long)e->outbps)>>2; - s->outbps = (e->outbps+0xF)>>5; + s->ustats.outbps = (e->outbps+0xF)>>5; spin_unlock(&s->lock); } spin_unlock(&est_lock); @@ -108,24 +108,22 @@ void ip_vs_new_estimator(struct ip_vs_stats *stats) INIT_LIST_HEAD(&est->list); - est->last_conns = stats->conns; - est->cps = stats->cps<<10; + est->last_conns = stats->ustats.conns; + est->cps = stats->ustats.cps<<10; - est->last_inpkts = stats->inpkts; - est->inpps = stats->inpps<<10; + est->last_inpkts = stats->ustats.inpkts; + est->inpps = stats->ustats.inpps<<10; - est->last_outpkts = stats->outpkts; - est->outpps = stats->outpps<<10; + est->last_outpkts = stats->ustats.outpkts; + est->outpps = stats->ustats.outpps<<10; - est->last_inbytes = stats->inbytes; - est->inbps = stats->inbps<<5; + est->last_inbytes = stats->ustats.inbytes; + est->inbps = stats->ustats.inbps<<5; - est->last_outbytes = stats->outbytes; - est->outbps = stats->outbps<<5; + est->last_outbytes = stats->ustats.outbytes; + est->outbps = stats->ustats.outbps<<5; spin_lock_bh(&est_lock); - if (list_empty(&est_list)) - mod_timer(&est_timer, jiffies + 2 * HZ); list_add(&est->list, &est_list); spin_unlock_bh(&est_lock); } @@ -136,11 +134,6 @@ void ip_vs_kill_estimator(struct ip_vs_stats *stats) spin_lock_bh(&est_lock); list_del(&est->list); - while (list_empty(&est_list) && try_to_del_timer_sync(&est_timer) < 0) { - spin_unlock_bh(&est_lock); - cpu_relax(); - spin_lock_bh(&est_lock); - } spin_unlock_bh(&est_lock); } @@ -160,3 +153,14 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats) est->inbps = 0; est->outbps = 0; } + +int __init ip_vs_estimator_init(void) +{ + mod_timer(&est_timer, jiffies + 2 * HZ); + return 0; +} + +void ip_vs_estimator_cleanup(void) +{ + del_timer_sync(&est_timer); +} diff --git a/net/ipv4/ipvs/ip_vs_ftp.c b/net/ipv4/ipvs/ip_vs_ftp.c index c1c758e..2e7dbd8 100644 --- a/net/ipv4/ipvs/ip_vs_ftp.c +++ b/net/ipv4/ipvs/ip_vs_ftp.c @@ -140,13 +140,21 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, struct tcphdr *th; char *data, *data_limit; char *start, *end; - __be32 from; + union nf_inet_addr from; __be16 port; struct ip_vs_conn *n_cp; char buf[24]; /* xxx.xxx.xxx.xxx,ppp,ppp\000 */ unsigned buf_len; int ret; +#ifdef CONFIG_IP_VS_IPV6 + /* This application helper doesn't work with IPv6 yet, + * so turn this into a no-op for IPv6 packets + */ + if (cp->af == AF_INET6) + return 1; +#endif + *diff = 0; /* Only useful for established sessions */ @@ -166,24 +174,25 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, if (ip_vs_ftp_get_addrport(data, data_limit, SERVER_STRING, sizeof(SERVER_STRING)-1, ')', - &from, &port, + &from.ip, &port, &start, &end) != 1) return 1; IP_VS_DBG(7, "PASV response (%u.%u.%u.%u:%d) -> " "%u.%u.%u.%u:%d detected\n", - NIPQUAD(from), ntohs(port), NIPQUAD(cp->caddr), 0); + NIPQUAD(from.ip), ntohs(port), + NIPQUAD(cp->caddr.ip), 0); /* * Now update or create an connection entry for it */ - n_cp = ip_vs_conn_out_get(iph->protocol, from, port, - cp->caddr, 0); + n_cp = ip_vs_conn_out_get(AF_INET, iph->protocol, &from, port, + &cp->caddr, 0); if (!n_cp) { - n_cp = ip_vs_conn_new(IPPROTO_TCP, - cp->caddr, 0, - cp->vaddr, port, - from, port, + n_cp = ip_vs_conn_new(AF_INET, IPPROTO_TCP, + &cp->caddr, 0, + &cp->vaddr, port, + &from, port, IP_VS_CONN_F_NO_CPORT, cp->dest); if (!n_cp) @@ -196,9 +205,9 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, /* * Replace the old passive address with the new one */ - from = n_cp->vaddr; + from.ip = n_cp->vaddr.ip; port = n_cp->vport; - sprintf(buf,"%d,%d,%d,%d,%d,%d", NIPQUAD(from), + sprintf(buf, "%d,%d,%d,%d,%d,%d", NIPQUAD(from.ip), (ntohs(port)>>8)&255, ntohs(port)&255); buf_len = strlen(buf); @@ -243,10 +252,18 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, struct tcphdr *th; char *data, *data_start, *data_limit; char *start, *end; - __be32 to; + union nf_inet_addr to; __be16 port; struct ip_vs_conn *n_cp; +#ifdef CONFIG_IP_VS_IPV6 + /* This application helper doesn't work with IPv6 yet, + * so turn this into a no-op for IPv6 packets + */ + if (cp->af == AF_INET6) + return 1; +#endif + /* no diff required for incoming packets */ *diff = 0; @@ -291,12 +308,12 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, */ if (ip_vs_ftp_get_addrport(data_start, data_limit, CLIENT_STRING, sizeof(CLIENT_STRING)-1, - '\r', &to, &port, + '\r', &to.ip, &port, &start, &end) != 1) return 1; IP_VS_DBG(7, "PORT %u.%u.%u.%u:%d detected\n", - NIPQUAD(to), ntohs(port)); + NIPQUAD(to.ip), ntohs(port)); /* Passive mode off */ cp->app_data = NULL; @@ -306,16 +323,16 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, */ IP_VS_DBG(7, "protocol %s %u.%u.%u.%u:%d %u.%u.%u.%u:%d\n", ip_vs_proto_name(iph->protocol), - NIPQUAD(to), ntohs(port), NIPQUAD(cp->vaddr), 0); + NIPQUAD(to.ip), ntohs(port), NIPQUAD(cp->vaddr.ip), 0); - n_cp = ip_vs_conn_in_get(iph->protocol, - to, port, - cp->vaddr, htons(ntohs(cp->vport)-1)); + n_cp = ip_vs_conn_in_get(AF_INET, iph->protocol, + &to, port, + &cp->vaddr, htons(ntohs(cp->vport)-1)); if (!n_cp) { - n_cp = ip_vs_conn_new(IPPROTO_TCP, - to, port, - cp->vaddr, htons(ntohs(cp->vport)-1), - cp->daddr, htons(ntohs(cp->dport)-1), + n_cp = ip_vs_conn_new(AF_INET, IPPROTO_TCP, + &to, port, + &cp->vaddr, htons(ntohs(cp->vport)-1), + &cp->daddr, htons(ntohs(cp->dport)-1), 0, cp->dest); if (!n_cp) diff --git a/net/ipv4/ipvs/ip_vs_lblc.c b/net/ipv4/ipvs/ip_vs_lblc.c index 7a6a319..6ecef35 100644 --- a/net/ipv4/ipvs/ip_vs_lblc.c +++ b/net/ipv4/ipvs/ip_vs_lblc.c @@ -96,7 +96,6 @@ struct ip_vs_lblc_entry { * IPVS lblc hash table */ struct ip_vs_lblc_table { - rwlock_t lock; /* lock for this table */ struct list_head bucket[IP_VS_LBLC_TAB_SIZE]; /* hash bucket */ atomic_t entries; /* number of entries */ int max_size; /* maximum size of entries */ @@ -123,31 +122,6 @@ static ctl_table vs_vars_table[] = { static struct ctl_table_header * sysctl_header; -/* - * new/free a ip_vs_lblc_entry, which is a mapping of a destionation - * IP address to a server. - */ -static inline struct ip_vs_lblc_entry * -ip_vs_lblc_new(__be32 daddr, struct ip_vs_dest *dest) -{ - struct ip_vs_lblc_entry *en; - - en = kmalloc(sizeof(struct ip_vs_lblc_entry), GFP_ATOMIC); - if (en == NULL) { - IP_VS_ERR("ip_vs_lblc_new(): no memory\n"); - return NULL; - } - - INIT_LIST_HEAD(&en->list); - en->addr = daddr; - - atomic_inc(&dest->refcnt); - en->dest = dest; - - return en; -} - - static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) { list_del(&en->list); @@ -173,55 +147,66 @@ static inline unsigned ip_vs_lblc_hashkey(__be32 addr) * Hash an entry in the ip_vs_lblc_table. * returns bool success. */ -static int +static void ip_vs_lblc_hash(struct ip_vs_lblc_table *tbl, struct ip_vs_lblc_entry *en) { - unsigned hash; - - if (!list_empty(&en->list)) { - IP_VS_ERR("ip_vs_lblc_hash(): request for already hashed, " - "called from %p\n", __builtin_return_address(0)); - return 0; - } - - /* - * Hash by destination IP address - */ - hash = ip_vs_lblc_hashkey(en->addr); + unsigned hash = ip_vs_lblc_hashkey(en->addr); - write_lock(&tbl->lock); list_add(&en->list, &tbl->bucket[hash]); atomic_inc(&tbl->entries); - write_unlock(&tbl->lock); - - return 1; } /* - * Get ip_vs_lblc_entry associated with supplied parameters. + * Get ip_vs_lblc_entry associated with supplied parameters. Called under read + * lock */ static inline struct ip_vs_lblc_entry * ip_vs_lblc_get(struct ip_vs_lblc_table *tbl, __be32 addr) { - unsigned hash; + unsigned hash = ip_vs_lblc_hashkey(addr); struct ip_vs_lblc_entry *en; - hash = ip_vs_lblc_hashkey(addr); + list_for_each_entry(en, &tbl->bucket[hash], list) + if (en->addr == addr) + return en; - read_lock(&tbl->lock); + return NULL; +} - list_for_each_entry(en, &tbl->bucket[hash], list) { - if (en->addr == addr) { - /* HIT */ - read_unlock(&tbl->lock); - return en; + +/* + * Create or update an ip_vs_lblc_entry, which is a mapping of a destination IP + * address to a server. Called under write lock. + */ +static inline struct ip_vs_lblc_entry * +ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, __be32 daddr, + struct ip_vs_dest *dest) +{ + struct ip_vs_lblc_entry *en; + + en = ip_vs_lblc_get(tbl, daddr); + if (!en) { + en = kmalloc(sizeof(*en), GFP_ATOMIC); + if (!en) { + IP_VS_ERR("ip_vs_lblc_new(): no memory\n"); + return NULL; } - } - read_unlock(&tbl->lock); + en->addr = daddr; + en->lastuse = jiffies; - return NULL; + atomic_inc(&dest->refcnt); + en->dest = dest; + + ip_vs_lblc_hash(tbl, en); + } else if (en->dest != dest) { + atomic_dec(&en->dest->refcnt); + atomic_inc(&dest->refcnt); + en->dest = dest; + } + + return en; } @@ -230,30 +215,29 @@ ip_vs_lblc_get(struct ip_vs_lblc_table *tbl, __be32 addr) */ static void ip_vs_lblc_flush(struct ip_vs_lblc_table *tbl) { - int i; struct ip_vs_lblc_entry *en, *nxt; + int i; for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) { - write_lock(&tbl->lock); list_for_each_entry_safe(en, nxt, &tbl->bucket[i], list) { ip_vs_lblc_free(en); atomic_dec(&tbl->entries); } - write_unlock(&tbl->lock); } } -static inline void ip_vs_lblc_full_check(struct ip_vs_lblc_table *tbl) +static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) { + struct ip_vs_lblc_table *tbl = svc->sched_data; + struct ip_vs_lblc_entry *en, *nxt; unsigned long now = jiffies; int i, j; - struct ip_vs_lblc_entry *en, *nxt; for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLC_TAB_MASK; - write_lock(&tbl->lock); + write_lock(&svc->sched_lock); list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) { if (time_before(now, en->lastuse + sysctl_ip_vs_lblc_expiration)) @@ -262,7 +246,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_lblc_table *tbl) ip_vs_lblc_free(en); atomic_dec(&tbl->entries); } - write_unlock(&tbl->lock); + write_unlock(&svc->sched_lock); } tbl->rover = j; } @@ -281,17 +265,16 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_lblc_table *tbl) */ static void ip_vs_lblc_check_expire(unsigned long data) { - struct ip_vs_lblc_table *tbl; + struct ip_vs_service *svc = (struct ip_vs_service *) data; + struct ip_vs_lblc_table *tbl = svc->sched_data; unsigned long now = jiffies; int goal; int i, j; struct ip_vs_lblc_entry *en, *nxt; - tbl = (struct ip_vs_lblc_table *)data; - if ((tbl->counter % COUNT_FOR_FULL_EXPIRATION) == 0) { /* do full expiration check */ - ip_vs_lblc_full_check(tbl); + ip_vs_lblc_full_check(svc); tbl->counter = 1; goto out; } @@ -308,7 +291,7 @@ static void ip_vs_lblc_check_expire(unsigned long data) for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLC_TAB_MASK; - write_lock(&tbl->lock); + write_lock(&svc->sched_lock); list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) { if (time_before(now, en->lastuse + ENTRY_TIMEOUT)) continue; @@ -317,7 +300,7 @@ static void ip_vs_lblc_check_expire(unsigned long data) atomic_dec(&tbl->entries); goal--; } - write_unlock(&tbl->lock); + write_unlock(&svc->sched_lock); if (goal <= 0) break; } @@ -336,15 +319,14 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) /* * Allocate the ip_vs_lblc_table for this service */ - tbl = kmalloc(sizeof(struct ip_vs_lblc_table), GFP_ATOMIC); + tbl = kmalloc(sizeof(*tbl), GFP_ATOMIC); if (tbl == NULL) { IP_VS_ERR("ip_vs_lblc_init_svc(): no memory\n"); return -ENOMEM; } svc->sched_data = tbl; IP_VS_DBG(6, "LBLC hash table (memory=%Zdbytes) allocated for " - "current service\n", - sizeof(struct ip_vs_lblc_table)); + "current service\n", sizeof(*tbl)); /* * Initialize the hash buckets @@ -352,7 +334,6 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) { INIT_LIST_HEAD(&tbl->bucket[i]); } - rwlock_init(&tbl->lock); tbl->max_size = IP_VS_LBLC_TAB_SIZE*16; tbl->rover = 0; tbl->counter = 1; @@ -361,9 +342,8 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) * Hook periodic timer for garbage collection */ setup_timer(&tbl->periodic_timer, ip_vs_lblc_check_expire, - (unsigned long)tbl); - tbl->periodic_timer.expires = jiffies+CHECK_EXPIRE_INTERVAL; - add_timer(&tbl->periodic_timer); + (unsigned long)svc); + mod_timer(&tbl->periodic_timer, jiffies + CHECK_EXPIRE_INTERVAL); return 0; } @@ -380,22 +360,16 @@ static int ip_vs_lblc_done_svc(struct ip_vs_service *svc) ip_vs_lblc_flush(tbl); /* release the table itself */ - kfree(svc->sched_data); + kfree(tbl); IP_VS_DBG(6, "LBLC hash table (memory=%Zdbytes) released\n", - sizeof(struct ip_vs_lblc_table)); + sizeof(*tbl)); return 0; } -static int ip_vs_lblc_update_svc(struct ip_vs_service *svc) -{ - return 0; -} - - static inline struct ip_vs_dest * -__ip_vs_wlc_schedule(struct ip_vs_service *svc, struct iphdr *iph) +__ip_vs_lblc_schedule(struct ip_vs_service *svc, struct iphdr *iph) { struct ip_vs_dest *dest, *least; int loh, doh; @@ -448,7 +422,7 @@ __ip_vs_wlc_schedule(struct ip_vs_service *svc, struct iphdr *iph) IP_VS_DBG(6, "LBLC: server %d.%d.%d.%d:%d " "activeconns %d refcnt %d weight %d overhead %d\n", - NIPQUAD(least->addr), ntohs(least->port), + NIPQUAD(least->addr.ip), ntohs(least->port), atomic_read(&least->activeconns), atomic_read(&least->refcnt), atomic_read(&least->weight), loh); @@ -484,47 +458,55 @@ is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc) static struct ip_vs_dest * ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) { - struct ip_vs_dest *dest; - struct ip_vs_lblc_table *tbl; - struct ip_vs_lblc_entry *en; + struct ip_vs_lblc_table *tbl = svc->sched_data; struct iphdr *iph = ip_hdr(skb); + struct ip_vs_dest *dest = NULL; + struct ip_vs_lblc_entry *en; IP_VS_DBG(6, "ip_vs_lblc_schedule(): Scheduling...\n"); - tbl = (struct ip_vs_lblc_table *)svc->sched_data; + /* First look in our cache */ + read_lock(&svc->sched_lock); en = ip_vs_lblc_get(tbl, iph->daddr); - if (en == NULL) { - dest = __ip_vs_wlc_schedule(svc, iph); - if (dest == NULL) { - IP_VS_DBG(1, "no destination available\n"); - return NULL; - } - en = ip_vs_lblc_new(iph->daddr, dest); - if (en == NULL) { - return NULL; - } - ip_vs_lblc_hash(tbl, en); - } else { - dest = en->dest; - if (!(dest->flags & IP_VS_DEST_F_AVAILABLE) - || atomic_read(&dest->weight) <= 0 - || is_overloaded(dest, svc)) { - dest = __ip_vs_wlc_schedule(svc, iph); - if (dest == NULL) { - IP_VS_DBG(1, "no destination available\n"); - return NULL; - } - atomic_dec(&en->dest->refcnt); - atomic_inc(&dest->refcnt); - en->dest = dest; - } + if (en) { + /* We only hold a read lock, but this is atomic */ + en->lastuse = jiffies; + + /* + * If the destination is not available, i.e. it's in the trash, + * we must ignore it, as it may be removed from under our feet, + * if someone drops our reference count. Our caller only makes + * sure that destinations, that are not in the trash, are not + * moved to the trash, while we are scheduling. But anyone can + * free up entries from the trash at any time. + */ + + if (en->dest->flags & IP_VS_DEST_F_AVAILABLE) + dest = en->dest; + } + read_unlock(&svc->sched_lock); + + /* If the destination has a weight and is not overloaded, use it */ + if (dest && atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc)) + goto out; + + /* No cache entry or it is invalid, time to schedule */ + dest = __ip_vs_lblc_schedule(svc, iph); + if (!dest) { + IP_VS_DBG(1, "no destination available\n"); + return NULL; } - en->lastuse = jiffies; + /* If we fail to create a cache entry, we'll just use the valid dest */ + write_lock(&svc->sched_lock); + ip_vs_lblc_new(tbl, iph->daddr, dest); + write_unlock(&svc->sched_lock); + +out: IP_VS_DBG(6, "LBLC: destination IP address %u.%u.%u.%u " "--> server %u.%u.%u.%u:%d\n", - NIPQUAD(en->addr), - NIPQUAD(dest->addr), + NIPQUAD(iph->daddr), + NIPQUAD(dest->addr.ip), ntohs(dest->port)); return dest; @@ -540,9 +522,11 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler = .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_lblc_scheduler.n_list), +#ifdef CONFIG_IP_VS_IPV6 + .supports_ipv6 = 0, +#endif .init_service = ip_vs_lblc_init_svc, .done_service = ip_vs_lblc_done_svc, - .update_service = ip_vs_lblc_update_svc, .schedule = ip_vs_lblc_schedule, }; diff --git a/net/ipv4/ipvs/ip_vs_lblcr.c b/net/ipv4/ipvs/ip_vs_lblcr.c index c234e73..1f75ea8 100644 --- a/net/ipv4/ipvs/ip_vs_lblcr.c +++ b/net/ipv4/ipvs/ip_vs_lblcr.c @@ -106,7 +106,7 @@ ip_vs_dest_set_insert(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) return NULL; } - e = kmalloc(sizeof(struct ip_vs_dest_list), GFP_ATOMIC); + e = kmalloc(sizeof(*e), GFP_ATOMIC); if (e == NULL) { IP_VS_ERR("ip_vs_dest_set_insert(): no memory\n"); return NULL; @@ -116,11 +116,9 @@ ip_vs_dest_set_insert(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) e->dest = dest; /* link it to the list */ - write_lock(&set->lock); e->next = set->list; set->list = e; atomic_inc(&set->size); - write_unlock(&set->lock); set->lastmod = jiffies; return e; @@ -131,7 +129,6 @@ ip_vs_dest_set_erase(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) { struct ip_vs_dest_list *e, **ep; - write_lock(&set->lock); for (ep=&set->list, e=*ep; e!=NULL; e=*ep) { if (e->dest == dest) { /* HIT */ @@ -144,7 +141,6 @@ ip_vs_dest_set_erase(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) } ep = &e->next; } - write_unlock(&set->lock); } static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) @@ -174,7 +170,6 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) if (set == NULL) return NULL; - read_lock(&set->lock); /* select the first destination server, whose weight > 0 */ for (e=set->list; e!=NULL; e=e->next) { least = e->dest; @@ -188,7 +183,6 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) goto nextstage; } } - read_unlock(&set->lock); return NULL; /* find the destination with the weighted least load */ @@ -207,11 +201,10 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) loh = doh; } } - read_unlock(&set->lock); IP_VS_DBG(6, "ip_vs_dest_set_min: server %d.%d.%d.%d:%d " "activeconns %d refcnt %d weight %d overhead %d\n", - NIPQUAD(least->addr), ntohs(least->port), + NIPQUAD(least->addr.ip), ntohs(least->port), atomic_read(&least->activeconns), atomic_read(&least->refcnt), atomic_read(&least->weight), loh); @@ -229,7 +222,6 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) if (set == NULL) return NULL; - read_lock(&set->lock); /* select the first destination server, whose weight > 0 */ for (e=set->list; e!=NULL; e=e->next) { most = e->dest; @@ -239,7 +231,6 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) goto nextstage; } } - read_unlock(&set->lock); return NULL; /* find the destination with the weighted most load */ @@ -256,11 +247,10 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) moh = doh; } } - read_unlock(&set->lock); IP_VS_DBG(6, "ip_vs_dest_set_max: server %d.%d.%d.%d:%d " "activeconns %d refcnt %d weight %d overhead %d\n", - NIPQUAD(most->addr), ntohs(most->port), + NIPQUAD(most->addr.ip), ntohs(most->port), atomic_read(&most->activeconns), atomic_read(&most->refcnt), atomic_read(&most->weight), moh); @@ -284,7 +274,6 @@ struct ip_vs_lblcr_entry { * IPVS lblcr hash table */ struct ip_vs_lblcr_table { - rwlock_t lock; /* lock for this table */ struct list_head bucket[IP_VS_LBLCR_TAB_SIZE]; /* hash bucket */ atomic_t entries; /* number of entries */ int max_size; /* maximum size of entries */ @@ -311,32 +300,6 @@ static ctl_table vs_vars_table[] = { static struct ctl_table_header * sysctl_header; -/* - * new/free a ip_vs_lblcr_entry, which is a mapping of a destination - * IP address to a server. - */ -static inline struct ip_vs_lblcr_entry *ip_vs_lblcr_new(__be32 daddr) -{ - struct ip_vs_lblcr_entry *en; - - en = kmalloc(sizeof(struct ip_vs_lblcr_entry), GFP_ATOMIC); - if (en == NULL) { - IP_VS_ERR("ip_vs_lblcr_new(): no memory\n"); - return NULL; - } - - INIT_LIST_HEAD(&en->list); - en->addr = daddr; - - /* initilize its dest set */ - atomic_set(&(en->set.size), 0); - en->set.list = NULL; - rwlock_init(&en->set.lock); - - return en; -} - - static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en) { list_del(&en->list); @@ -358,55 +321,68 @@ static inline unsigned ip_vs_lblcr_hashkey(__be32 addr) * Hash an entry in the ip_vs_lblcr_table. * returns bool success. */ -static int +static void ip_vs_lblcr_hash(struct ip_vs_lblcr_table *tbl, struct ip_vs_lblcr_entry *en) { - unsigned hash; + unsigned hash = ip_vs_lblcr_hashkey(en->addr); - if (!list_empty(&en->list)) { - IP_VS_ERR("ip_vs_lblcr_hash(): request for already hashed, " - "called from %p\n", __builtin_return_address(0)); - return 0; - } - - /* - * Hash by destination IP address - */ - hash = ip_vs_lblcr_hashkey(en->addr); - - write_lock(&tbl->lock); list_add(&en->list, &tbl->bucket[hash]); atomic_inc(&tbl->entries); - write_unlock(&tbl->lock); - - return 1; } /* - * Get ip_vs_lblcr_entry associated with supplied parameters. + * Get ip_vs_lblcr_entry associated with supplied parameters. Called under + * read lock. */ static inline struct ip_vs_lblcr_entry * ip_vs_lblcr_get(struct ip_vs_lblcr_table *tbl, __be32 addr) { - unsigned hash; + unsigned hash = ip_vs_lblcr_hashkey(addr); struct ip_vs_lblcr_entry *en; - hash = ip_vs_lblcr_hashkey(addr); + list_for_each_entry(en, &tbl->bucket[hash], list) + if (en->addr == addr) + return en; - read_lock(&tbl->lock); + return NULL; +} - list_for_each_entry(en, &tbl->bucket[hash], list) { - if (en->addr == addr) { - /* HIT */ - read_unlock(&tbl->lock); - return en; + +/* + * Create or update an ip_vs_lblcr_entry, which is a mapping of a destination + * IP address to a server. Called under write lock. + */ +static inline struct ip_vs_lblcr_entry * +ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, __be32 daddr, + struct ip_vs_dest *dest) +{ + struct ip_vs_lblcr_entry *en; + + en = ip_vs_lblcr_get(tbl, daddr); + if (!en) { + en = kmalloc(sizeof(*en), GFP_ATOMIC); + if (!en) { + IP_VS_ERR("ip_vs_lblcr_new(): no memory\n"); + return NULL; } + + en->addr = daddr; + en->lastuse = jiffies; + + /* initilize its dest set */ + atomic_set(&(en->set.size), 0); + en->set.list = NULL; + rwlock_init(&en->set.lock); + + ip_vs_lblcr_hash(tbl, en); } - read_unlock(&tbl->lock); + write_lock(&en->set.lock); + ip_vs_dest_set_insert(&en->set, dest); + write_unlock(&en->set.lock); - return NULL; + return en; } @@ -418,19 +394,18 @@ static void ip_vs_lblcr_flush(struct ip_vs_lblcr_table *tbl) int i; struct ip_vs_lblcr_entry *en, *nxt; + /* No locking required, only called during cleanup. */ for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) { - write_lock(&tbl->lock); list_for_each_entry_safe(en, nxt, &tbl->bucket[i], list) { ip_vs_lblcr_free(en); - atomic_dec(&tbl->entries); } - write_unlock(&tbl->lock); } } -static inline void ip_vs_lblcr_full_check(struct ip_vs_lblcr_table *tbl) +static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc) { + struct ip_vs_lblcr_table *tbl = svc->sched_data; unsigned long now = jiffies; int i, j; struct ip_vs_lblcr_entry *en, *nxt; @@ -438,7 +413,7 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_lblcr_table *tbl) for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; - write_lock(&tbl->lock); + write_lock(&svc->sched_lock); list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) { if (time_after(en->lastuse+sysctl_ip_vs_lblcr_expiration, now)) @@ -447,7 +422,7 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_lblcr_table *tbl) ip_vs_lblcr_free(en); atomic_dec(&tbl->entries); } - write_unlock(&tbl->lock); + write_unlock(&svc->sched_lock); } tbl->rover = j; } @@ -466,17 +441,16 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_lblcr_table *tbl) */ static void ip_vs_lblcr_check_expire(unsigned long data) { - struct ip_vs_lblcr_table *tbl; + struct ip_vs_service *svc = (struct ip_vs_service *) data; + struct ip_vs_lblcr_table *tbl = svc->sched_data; unsigned long now = jiffies; int goal; int i, j; struct ip_vs_lblcr_entry *en, *nxt; - tbl = (struct ip_vs_lblcr_table *)data; - if ((tbl->counter % COUNT_FOR_FULL_EXPIRATION) == 0) { /* do full expiration check */ - ip_vs_lblcr_full_check(tbl); + ip_vs_lblcr_full_check(svc); tbl->counter = 1; goto out; } @@ -493,7 +467,7 @@ static void ip_vs_lblcr_check_expire(unsigned long data) for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; - write_lock(&tbl->lock); + write_lock(&svc->sched_lock); list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) { if (time_before(now, en->lastuse+ENTRY_TIMEOUT)) continue; @@ -502,7 +476,7 @@ static void ip_vs_lblcr_check_expire(unsigned long data) atomic_dec(&tbl->entries); goal--; } - write_unlock(&tbl->lock); + write_unlock(&svc->sched_lock); if (goal <= 0) break; } @@ -520,15 +494,14 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) /* * Allocate the ip_vs_lblcr_table for this service */ - tbl = kmalloc(sizeof(struct ip_vs_lblcr_table), GFP_ATOMIC); + tbl = kmalloc(sizeof(*tbl), GFP_ATOMIC); if (tbl == NULL) { IP_VS_ERR("ip_vs_lblcr_init_svc(): no memory\n"); return -ENOMEM; } svc->sched_data = tbl; IP_VS_DBG(6, "LBLCR hash table (memory=%Zdbytes) allocated for " - "current service\n", - sizeof(struct ip_vs_lblcr_table)); + "current service\n", sizeof(*tbl)); /* * Initialize the hash buckets @@ -536,7 +509,6 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) { INIT_LIST_HEAD(&tbl->bucket[i]); } - rwlock_init(&tbl->lock); tbl->max_size = IP_VS_LBLCR_TAB_SIZE*16; tbl->rover = 0; tbl->counter = 1; @@ -545,9 +517,8 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) * Hook periodic timer for garbage collection */ setup_timer(&tbl->periodic_timer, ip_vs_lblcr_check_expire, - (unsigned long)tbl); - tbl->periodic_timer.expires = jiffies+CHECK_EXPIRE_INTERVAL; - add_timer(&tbl->periodic_timer); + (unsigned long)svc); + mod_timer(&tbl->periodic_timer, jiffies + CHECK_EXPIRE_INTERVAL); return 0; } @@ -564,22 +535,16 @@ static int ip_vs_lblcr_done_svc(struct ip_vs_service *svc) ip_vs_lblcr_flush(tbl); /* release the table itself */ - kfree(svc->sched_data); + kfree(tbl); IP_VS_DBG(6, "LBLCR hash table (memory=%Zdbytes) released\n", - sizeof(struct ip_vs_lblcr_table)); + sizeof(*tbl)); return 0; } -static int ip_vs_lblcr_update_svc(struct ip_vs_service *svc) -{ - return 0; -} - - static inline struct ip_vs_dest * -__ip_vs_wlc_schedule(struct ip_vs_service *svc, struct iphdr *iph) +__ip_vs_lblcr_schedule(struct ip_vs_service *svc, struct iphdr *iph) { struct ip_vs_dest *dest, *least; int loh, doh; @@ -633,7 +598,7 @@ __ip_vs_wlc_schedule(struct ip_vs_service *svc, struct iphdr *iph) IP_VS_DBG(6, "LBLCR: server %d.%d.%d.%d:%d " "activeconns %d refcnt %d weight %d overhead %d\n", - NIPQUAD(least->addr), ntohs(least->port), + NIPQUAD(least->addr.ip), ntohs(least->port), atomic_read(&least->activeconns), atomic_read(&least->refcnt), atomic_read(&least->weight), loh); @@ -669,51 +634,79 @@ is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc) static struct ip_vs_dest * ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) { - struct ip_vs_dest *dest; - struct ip_vs_lblcr_table *tbl; - struct ip_vs_lblcr_entry *en; + struct ip_vs_lblcr_table *tbl = svc->sched_data; struct iphdr *iph = ip_hdr(skb); + struct ip_vs_dest *dest = NULL; + struct ip_vs_lblcr_entry *en; IP_VS_DBG(6, "ip_vs_lblcr_schedule(): Scheduling...\n"); - tbl = (struct ip_vs_lblcr_table *)svc->sched_data; + /* First look in our cache */ + read_lock(&svc->sched_lock); en = ip_vs_lblcr_get(tbl, iph->daddr); - if (en == NULL) { - dest = __ip_vs_wlc_schedule(svc, iph); - if (dest == NULL) { - IP_VS_DBG(1, "no destination available\n"); - return NULL; - } - en = ip_vs_lblcr_new(iph->daddr); - if (en == NULL) { - return NULL; - } - ip_vs_dest_set_insert(&en->set, dest); - ip_vs_lblcr_hash(tbl, en); - } else { + if (en) { + /* We only hold a read lock, but this is atomic */ + en->lastuse = jiffies; + + /* Get the least loaded destination */ + read_lock(&en->set.lock); dest = ip_vs_dest_set_min(&en->set); - if (!dest || is_overloaded(dest, svc)) { - dest = __ip_vs_wlc_schedule(svc, iph); - if (dest == NULL) { - IP_VS_DBG(1, "no destination available\n"); - return NULL; - } - ip_vs_dest_set_insert(&en->set, dest); - } + read_unlock(&en->set.lock); + + /* More than one destination + enough time passed by, cleanup */ if (atomic_read(&en->set.size) > 1 && - jiffies-en->set.lastmod > sysctl_ip_vs_lblcr_expiration) { + time_after(jiffies, en->set.lastmod + + sysctl_ip_vs_lblcr_expiration)) { struct ip_vs_dest *m; + + write_lock(&en->set.lock); m = ip_vs_dest_set_max(&en->set); if (m) ip_vs_dest_set_erase(&en->set, m); + write_unlock(&en->set.lock); } + + /* If the destination is not overloaded, use it */ + if (dest && !is_overloaded(dest, svc)) { + read_unlock(&svc->sched_lock); + goto out; + } + + /* The cache entry is invalid, time to schedule */ + dest = __ip_vs_lblcr_schedule(svc, iph); + if (!dest) { + IP_VS_DBG(1, "no destination available\n"); + read_unlock(&svc->sched_lock); + return NULL; + } + + /* Update our cache entry */ + write_lock(&en->set.lock); + ip_vs_dest_set_insert(&en->set, dest); + write_unlock(&en->set.lock); + } + read_unlock(&svc->sched_lock); + + if (dest) + goto out; + + /* No cache entry, time to schedule */ + dest = __ip_vs_lblcr_schedule(svc, iph); + if (!dest) { + IP_VS_DBG(1, "no destination available\n"); + return NULL; } - en->lastuse = jiffies; + /* If we fail to create a cache entry, we'll just use the valid dest */ + write_lock(&svc->sched_lock); + ip_vs_lblcr_new(tbl, iph->daddr, dest); + write_unlock(&svc->sched_lock); + +out: IP_VS_DBG(6, "LBLCR: destination IP address %u.%u.%u.%u " "--> server %u.%u.%u.%u:%d\n", - NIPQUAD(en->addr), - NIPQUAD(dest->addr), + NIPQUAD(iph->daddr), + NIPQUAD(dest->addr.ip), ntohs(dest->port)); return dest; @@ -729,9 +722,11 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler = .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_lblcr_scheduler.n_list), +#ifdef CONFIG_IP_VS_IPV6 + .supports_ipv6 = 0, +#endif .init_service = ip_vs_lblcr_init_svc, .done_service = ip_vs_lblcr_done_svc, - .update_service = ip_vs_lblcr_update_svc, .schedule = ip_vs_lblcr_schedule, }; diff --git a/net/ipv4/ipvs/ip_vs_lc.c b/net/ipv4/ipvs/ip_vs_lc.c index ebcdbf7..b69f808 100644 --- a/net/ipv4/ipvs/ip_vs_lc.c +++ b/net/ipv4/ipvs/ip_vs_lc.c @@ -20,24 +20,6 @@ #include <net/ip_vs.h> -static int ip_vs_lc_init_svc(struct ip_vs_service *svc) -{ - return 0; -} - - -static int ip_vs_lc_done_svc(struct ip_vs_service *svc) -{ - return 0; -} - - -static int ip_vs_lc_update_svc(struct ip_vs_service *svc) -{ - return 0; -} - - static inline unsigned int ip_vs_lc_dest_overhead(struct ip_vs_dest *dest) { @@ -85,10 +67,10 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) } if (least) - IP_VS_DBG(6, "LC: server %u.%u.%u.%u:%u activeconns %d inactconns %d\n", - NIPQUAD(least->addr), ntohs(least->port), - atomic_read(&least->activeconns), - atomic_read(&least->inactconns)); + IP_VS_DBG_BUF(6, "LC: server %s:%u activeconns %d inactconns %d\n", + IP_VS_DBG_ADDR(svc->af, &least->addr), ntohs(least->port), + atomic_read(&least->activeconns), + atomic_read(&least->inactconns)); return least; } @@ -99,9 +81,9 @@ static struct ip_vs_scheduler ip_vs_lc_scheduler = { .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_lc_scheduler.n_list), - .init_service = ip_vs_lc_init_svc, - .done_service = ip_vs_lc_done_svc, - .update_service = ip_vs_lc_update_svc, +#ifdef CONFIG_IP_VS_IPV6 + .supports_ipv6 = 1, +#endif .schedule = ip_vs_lc_schedule, }; diff --git a/net/ipv4/ipvs/ip_vs_nq.c b/net/ipv4/ipvs/ip_vs_nq.c index 92f3a67..9a2d803 100644 --- a/net/ipv4/ipvs/ip_vs_nq.c +++ b/net/ipv4/ipvs/ip_vs_nq.c @@ -37,27 +37,6 @@ #include <net/ip_vs.h> -static int -ip_vs_nq_init_svc(struct ip_vs_service *svc) -{ - return 0; -} - - -static int -ip_vs_nq_done_svc(struct ip_vs_service *svc) -{ - return 0; -} - - -static int -ip_vs_nq_update_svc(struct ip_vs_service *svc) -{ - return 0; -} - - static inline unsigned int ip_vs_nq_dest_overhead(struct ip_vs_dest *dest) { @@ -120,12 +99,12 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) return NULL; out: - IP_VS_DBG(6, "NQ: server %u.%u.%u.%u:%u " - "activeconns %d refcnt %d weight %d overhead %d\n", - NIPQUAD(least->addr), ntohs(least->port), - atomic_read(&least->activeconns), - atomic_read(&least->refcnt), - atomic_read(&least->weight), loh); + IP_VS_DBG_BUF(6, "NQ: server %s:%u " + "activeconns %d refcnt %d weight %d overhead %d\n", + IP_VS_DBG_ADDR(svc->af, &least->addr), ntohs(least->port), + atomic_read(&least->activeconns), + atomic_read(&least->refcnt), + atomic_read(&least->weight), loh); return least; } @@ -137,9 +116,9 @@ static struct ip_vs_scheduler ip_vs_nq_scheduler = .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_nq_scheduler.n_list), - .init_service = ip_vs_nq_init_svc, - .done_service = ip_vs_nq_done_svc, - .update_service = ip_vs_nq_update_svc, +#ifdef CONFIG_IP_VS_IPV6 + .supports_ipv6 = 1, +#endif .schedule = ip_vs_nq_schedule, }; diff --git a/net/ipv4/ipvs/ip_vs_proto.c b/net/ipv4/ipvs/ip_vs_proto.c index 6099a88..0791f9e 100644 --- a/net/ipv4/ipvs/ip_vs_proto.c +++ b/net/ipv4/ipvs/ip_vs_proto.c @@ -151,11 +151,11 @@ const char * ip_vs_state_name(__u16 proto, int state) } -void -ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp, - const struct sk_buff *skb, - int offset, - const char *msg) +static void +ip_vs_tcpudp_debug_packet_v4(struct ip_vs_protocol *pp, + const struct sk_buff *skb, + int offset, + const char *msg) { char buf[128]; struct iphdr _iph, *ih; @@ -189,6 +189,61 @@ ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp, printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf); } +#ifdef CONFIG_IP_VS_IPV6 +static void +ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp, + const struct sk_buff *skb, + int offset, + const char *msg) +{ + char buf[192]; + struct ipv6hdr _iph, *ih; + + ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); + if (ih == NULL) + sprintf(buf, "%s TRUNCATED", pp->name); + else if (ih->nexthdr == IPPROTO_FRAGMENT) + sprintf(buf, "%s " NIP6_FMT "->" NIP6_FMT " frag", + pp->name, NIP6(ih->saddr), + NIP6(ih->daddr)); + else { + __be16 _ports[2], *pptr; + + pptr = skb_header_pointer(skb, offset + sizeof(struct ipv6hdr), + sizeof(_ports), _ports); + if (pptr == NULL) + sprintf(buf, "%s TRUNCATED " NIP6_FMT "->" NIP6_FMT, + pp->name, + NIP6(ih->saddr), + NIP6(ih->daddr)); + else + sprintf(buf, "%s " NIP6_FMT ":%u->" NIP6_FMT ":%u", + pp->name, + NIP6(ih->saddr), + ntohs(pptr[0]), + NIP6(ih->daddr), + ntohs(pptr[1])); + } + + printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf); +} +#endif + + +void +ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp, + const struct sk_buff *skb, + int offset, + const char *msg) +{ +#ifdef CONFIG_IP_VS_IPV6 + if (skb->protocol == htons(ETH_P_IPV6)) + ip_vs_tcpudp_debug_packet_v6(pp, skb, offset, msg); + else +#endif + ip_vs_tcpudp_debug_packet_v4(pp, skb, offset, msg); +} + int __init ip_vs_protocol_init(void) { diff --git a/net/ipv4/ipvs/ip_vs_proto_ah.c b/net/ipv4/ipvs/ip_vs_proto_ah.c deleted file mode 100644 index 73e0ea8..0000000 --- a/net/ipv4/ipvs/ip_vs_proto_ah.c +++ /dev/null @@ -1,178 +0,0 @@ -/* - * ip_vs_proto_ah.c: AH IPSec load balancing support for IPVS - * - * Authors: Julian Anastasov <ja@ssi.bg>, February 2002 - * Wensong Zhang <wensong@linuxvirtualserver.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation; - * - */ - -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/netfilter.h> -#include <linux/netfilter_ipv4.h> - -#include <net/ip_vs.h> - - -/* TODO: - -struct isakmp_hdr { - __u8 icookie[8]; - __u8 rcookie[8]; - __u8 np; - __u8 version; - __u8 xchgtype; - __u8 flags; - __u32 msgid; - __u32 length; -}; - -*/ - -#define PORT_ISAKMP 500 - - -static struct ip_vs_conn * -ah_conn_in_get(const struct sk_buff *skb, - struct ip_vs_protocol *pp, - const struct iphdr *iph, - unsigned int proto_off, - int inverse) -{ - struct ip_vs_conn *cp; - - if (likely(!inverse)) { - cp = ip_vs_conn_in_get(IPPROTO_UDP, - iph->saddr, - htons(PORT_ISAKMP), - iph->daddr, - htons(PORT_ISAKMP)); - } else { - cp = ip_vs_conn_in_get(IPPROTO_UDP, - iph->daddr, - htons(PORT_ISAKMP), - iph->saddr, - htons(PORT_ISAKMP)); - } - - if (!cp) { - /* - * We are not sure if the packet is from our - * service, so our conn_schedule hook should return NF_ACCEPT - */ - IP_VS_DBG(12, "Unknown ISAKMP entry for outin packet " - "%s%s %u.%u.%u.%u->%u.%u.%u.%u\n", - inverse ? "ICMP+" : "", - pp->name, - NIPQUAD(iph->saddr), - NIPQUAD(iph->daddr)); - } - - return cp; -} - - -static struct ip_vs_conn * -ah_conn_out_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, - const struct iphdr *iph, unsigned int proto_off, int inverse) -{ - struct ip_vs_conn *cp; - - if (likely(!inverse)) { - cp = ip_vs_conn_out_get(IPPROTO_UDP, - iph->saddr, - htons(PORT_ISAKMP), - iph->daddr, - htons(PORT_ISAKMP)); - } else { - cp = ip_vs_conn_out_get(IPPROTO_UDP, - iph->daddr, - htons(PORT_ISAKMP), - iph->saddr, - htons(PORT_ISAKMP)); - } - - if (!cp) { - IP_VS_DBG(12, "Unknown ISAKMP entry for inout packet " - "%s%s %u.%u.%u.%u->%u.%u.%u.%u\n", - inverse ? "ICMP+" : "", - pp->name, - NIPQUAD(iph->saddr), - NIPQUAD(iph->daddr)); - } - - return cp; -} - - -static int -ah_conn_schedule(struct sk_buff *skb, - struct ip_vs_protocol *pp, - int *verdict, struct ip_vs_conn **cpp) -{ - /* - * AH is only related traffic. Pass the packet to IP stack. - */ - *verdict = NF_ACCEPT; - return 0; -} - - -static void -ah_debug_packet(struct ip_vs_protocol *pp, const struct sk_buff *skb, - int offset, const char *msg) -{ - char buf[256]; - struct iphdr _iph, *ih; - - ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); - if (ih == NULL) - sprintf(buf, "%s TRUNCATED", pp->name); - else - sprintf(buf, "%s %u.%u.%u.%u->%u.%u.%u.%u", - pp->name, NIPQUAD(ih->saddr), - NIPQUAD(ih->daddr)); - - printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf); -} - - -static void ah_init(struct ip_vs_protocol *pp) -{ - /* nothing to do now */ -} - - -static void ah_exit(struct ip_vs_protocol *pp) -{ - /* nothing to do now */ -} - - -struct ip_vs_protocol ip_vs_protocol_ah = { - .name = "AH", - .protocol = IPPROTO_AH, - .num_states = 1, - .dont_defrag = 1, - .init = ah_init, - .exit = ah_exit, - .conn_schedule = ah_conn_schedule, - .conn_in_get = ah_conn_in_get, - .conn_out_get = ah_conn_out_get, - .snat_handler = NULL, - .dnat_handler = NULL, - .csum_check = NULL, - .state_transition = NULL, - .register_app = NULL, - .unregister_app = NULL, - .app_conn_bind = NULL, - .debug_packet = ah_debug_packet, - .timeout_change = NULL, /* ISAKMP */ - .set_state_timeout = NULL, -}; diff --git a/net/ipv4/ipvs/ip_vs_proto_ah_esp.c b/net/ipv4/ipvs/ip_vs_proto_ah_esp.c new file mode 100644 index 0000000..80ab0c8 --- /dev/null +++ b/net/ipv4/ipvs/ip_vs_proto_ah_esp.c @@ -0,0 +1,235 @@ +/* + * ip_vs_proto_ah_esp.c: AH/ESP IPSec load balancing support for IPVS + * + * Authors: Julian Anastasov <ja@ssi.bg>, February 2002 + * Wensong Zhang <wensong@linuxvirtualserver.org> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation; + * + */ + +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv4.h> + +#include <net/ip_vs.h> + + +/* TODO: + +struct isakmp_hdr { + __u8 icookie[8]; + __u8 rcookie[8]; + __u8 np; + __u8 version; + __u8 xchgtype; + __u8 flags; + __u32 msgid; + __u32 length; +}; + +*/ + +#define PORT_ISAKMP 500 + + +static struct ip_vs_conn * +ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, + const struct ip_vs_iphdr *iph, unsigned int proto_off, + int inverse) +{ + struct ip_vs_conn *cp; + + if (likely(!inverse)) { + cp = ip_vs_conn_in_get(af, IPPROTO_UDP, + &iph->saddr, + htons(PORT_ISAKMP), + &iph->daddr, + htons(PORT_ISAKMP)); + } else { + cp = ip_vs_conn_in_get(af, IPPROTO_UDP, + &iph->daddr, + htons(PORT_ISAKMP), + &iph->saddr, + htons(PORT_ISAKMP)); + } + + if (!cp) { + /* + * We are not sure if the packet is from our + * service, so our conn_schedule hook should return NF_ACCEPT + */ + IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for outin packet " + "%s%s %s->%s\n", + inverse ? "ICMP+" : "", + pp->name, + IP_VS_DBG_ADDR(af, &iph->saddr), + IP_VS_DBG_ADDR(af, &iph->daddr)); + } + + return cp; +} + + +static struct ip_vs_conn * +ah_esp_conn_out_get(int af, const struct sk_buff *skb, + struct ip_vs_protocol *pp, + const struct ip_vs_iphdr *iph, + unsigned int proto_off, + int inverse) +{ + struct ip_vs_conn *cp; + + if (likely(!inverse)) { + cp = ip_vs_conn_out_get(af, IPPROTO_UDP, + &iph->saddr, + htons(PORT_ISAKMP), + &iph->daddr, + htons(PORT_ISAKMP)); + } else { + cp = ip_vs_conn_out_get(af, IPPROTO_UDP, + &iph->daddr, + htons(PORT_ISAKMP), + &iph->saddr, + htons(PORT_ISAKMP)); + } + + if (!cp) { + IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet " + "%s%s %s->%s\n", + inverse ? "ICMP+" : "", + pp->name, + IP_VS_DBG_ADDR(af, &iph->saddr), + IP_VS_DBG_ADDR(af, &iph->daddr)); + } + + return cp; +} + + +static int +ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, + int *verdict, struct ip_vs_conn **cpp) +{ + /* + * AH/ESP is only related traffic. Pass the packet to IP stack. + */ + *verdict = NF_ACCEPT; + return 0; +} + + +static void +ah_esp_debug_packet_v4(struct ip_vs_protocol *pp, const struct sk_buff *skb, + int offset, const char *msg) +{ + char buf[256]; + struct iphdr _iph, *ih; + + ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); + if (ih == NULL) + sprintf(buf, "%s TRUNCATED", pp->name); + else + sprintf(buf, "%s %u.%u.%u.%u->%u.%u.%u.%u", + pp->name, NIPQUAD(ih->saddr), + NIPQUAD(ih->daddr)); + + printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf); +} + +#ifdef CONFIG_IP_VS_IPV6 +static void +ah_esp_debug_packet_v6(struct ip_vs_protocol *pp, const struct sk_buff *skb, + int offset, const char *msg) +{ + char buf[256]; + struct ipv6hdr _iph, *ih; + + ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); + if (ih == NULL) + sprintf(buf, "%s TRUNCATED", pp->name); + else + sprintf(buf, "%s " NIP6_FMT "->" NIP6_FMT, + pp->name, NIP6(ih->saddr), + NIP6(ih->daddr)); + + printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf); +} +#endif + +static void +ah_esp_debug_packet(struct ip_vs_protocol *pp, const struct sk_buff *skb, + int offset, const char *msg) +{ +#ifdef CONFIG_IP_VS_IPV6 + if (skb->protocol == htons(ETH_P_IPV6)) + ah_esp_debug_packet_v6(pp, skb, offset, msg); + else +#endif + ah_esp_debug_packet_v4(pp, skb, offset, msg); +} + + +static void ah_esp_init(struct ip_vs_protocol *pp) +{ + /* nothing to do now */ +} + + +static void ah_esp_exit(struct ip_vs_protocol *pp) +{ + /* nothing to do now */ +} + + +#ifdef CONFIG_IP_VS_PROTO_AH +struct ip_vs_protocol ip_vs_protocol_ah = { + .name = "AH", + .protocol = IPPROTO_AH, + .num_states = 1, + .dont_defrag = 1, + .init = ah_esp_init, + .exit = ah_esp_exit, + .conn_schedule = ah_esp_conn_schedule, + .conn_in_get = ah_esp_conn_in_get, + .conn_out_get = ah_esp_conn_out_get, + .snat_handler = NULL, + .dnat_handler = NULL, + .csum_check = NULL, + .state_transition = NULL, + .register_app = NULL, + .unregister_app = NULL, + .app_conn_bind = NULL, + .debug_packet = ah_esp_debug_packet, + .timeout_change = NULL, /* ISAKMP */ + .set_state_timeout = NULL, +}; +#endif + +#ifdef CONFIG_IP_VS_PROTO_ESP +struct ip_vs_protocol ip_vs_protocol_esp = { + .name = "ESP", + .protocol = IPPROTO_ESP, + .num_states = 1, + .dont_defrag = 1, + .init = ah_esp_init, + .exit = ah_esp_exit, + .conn_schedule = ah_esp_conn_schedule, + .conn_in_get = ah_esp_conn_in_get, + .conn_out_get = ah_esp_conn_out_get, + .snat_handler = NULL, + .dnat_handler = NULL, + .csum_check = NULL, + .state_transition = NULL, + .register_app = NULL, + .unregister_app = NULL, + .app_conn_bind = NULL, + .debug_packet = ah_esp_debug_packet, + .timeout_change = NULL, /* ISAKMP */ +}; +#endif diff --git a/net/ipv4/ipvs/ip_vs_proto_esp.c b/net/ipv4/ipvs/ip_vs_proto_esp.c deleted file mode 100644 index 21d70c8..0000000 --- a/net/ipv4/ipvs/ip_vs_proto_esp.c +++ /dev/null @@ -1,176 +0,0 @@ -/* - * ip_vs_proto_esp.c: ESP IPSec load balancing support for IPVS - * - * Authors: Julian Anastasov <ja@ssi.bg>, February 2002 - * Wensong Zhang <wensong@linuxvirtualserver.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation; - * - */ - -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/netfilter.h> -#include <linux/netfilter_ipv4.h> - -#include <net/ip_vs.h> - - -/* TODO: - -struct isakmp_hdr { - __u8 icookie[8]; - __u8 rcookie[8]; - __u8 np; - __u8 version; - __u8 xchgtype; - __u8 flags; - __u32 msgid; - __u32 length; -}; - -*/ - -#define PORT_ISAKMP 500 - - -static struct ip_vs_conn * -esp_conn_in_get(const struct sk_buff *skb, - struct ip_vs_protocol *pp, - const struct iphdr *iph, - unsigned int proto_off, - int inverse) -{ - struct ip_vs_conn *cp; - - if (likely(!inverse)) { - cp = ip_vs_conn_in_get(IPPROTO_UDP, - iph->saddr, - htons(PORT_ISAKMP), - iph->daddr, - htons(PORT_ISAKMP)); - } else { - cp = ip_vs_conn_in_get(IPPROTO_UDP, - iph->daddr, - htons(PORT_ISAKMP), - iph->saddr, - htons(PORT_ISAKMP)); - } - - if (!cp) { - /* - * We are not sure if the packet is from our - * service, so our conn_schedule hook should return NF_ACCEPT - */ - IP_VS_DBG(12, "Unknown ISAKMP entry for outin packet " - "%s%s %u.%u.%u.%u->%u.%u.%u.%u\n", - inverse ? "ICMP+" : "", - pp->name, - NIPQUAD(iph->saddr), - NIPQUAD(iph->daddr)); - } - - return cp; -} - - -static struct ip_vs_conn * -esp_conn_out_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, - const struct iphdr *iph, unsigned int proto_off, int inverse) -{ - struct ip_vs_conn *cp; - - if (likely(!inverse)) { - cp = ip_vs_conn_out_get(IPPROTO_UDP, - iph->saddr, - htons(PORT_ISAKMP), - iph->daddr, - htons(PORT_ISAKMP)); - } else { - cp = ip_vs_conn_out_get(IPPROTO_UDP, - iph->daddr, - htons(PORT_ISAKMP), - iph->saddr, - htons(PORT_ISAKMP)); - } - - if (!cp) { - IP_VS_DBG(12, "Unknown ISAKMP entry for inout packet " - "%s%s %u.%u.%u.%u->%u.%u.%u.%u\n", - inverse ? "ICMP+" : "", - pp->name, - NIPQUAD(iph->saddr), - NIPQUAD(iph->daddr)); - } - - return cp; -} - - -static int -esp_conn_schedule(struct sk_buff *skb, struct ip_vs_protocol *pp, - int *verdict, struct ip_vs_conn **cpp) -{ - /* - * ESP is only related traffic. Pass the packet to IP stack. - */ - *verdict = NF_ACCEPT; - return 0; -} - - -static void -esp_debug_packet(struct ip_vs_protocol *pp, const struct sk_buff *skb, - int offset, const char *msg) -{ - char buf[256]; - struct iphdr _iph, *ih; - - ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); - if (ih == NULL) - sprintf(buf, "%s TRUNCATED", pp->name); - else - sprintf(buf, "%s %u.%u.%u.%u->%u.%u.%u.%u", - pp->name, NIPQUAD(ih->saddr), - NIPQUAD(ih->daddr)); - - printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf); -} - - -static void esp_init(struct ip_vs_protocol *pp) -{ - /* nothing to do now */ -} - - -static void esp_exit(struct ip_vs_protocol *pp) -{ - /* nothing to do now */ -} - - -struct ip_vs_protocol ip_vs_protocol_esp = { - .name = "ESP", - .protocol = IPPROTO_ESP, - .num_states = 1, - .dont_defrag = 1, - .init = esp_init, - .exit = esp_exit, - .conn_schedule = esp_conn_schedule, - .conn_in_get = esp_conn_in_get, - .conn_out_get = esp_conn_out_get, - .snat_handler = NULL, - .dnat_handler = NULL, - .csum_check = NULL, - .state_transition = NULL, - .register_app = NULL, - .unregister_app = NULL, - .app_conn_bind = NULL, - .debug_packet = esp_debug_packet, - .timeout_change = NULL, /* ISAKMP */ -}; diff --git a/net/ipv4/ipvs/ip_vs_proto_tcp.c b/net/ipv4/ipvs/ip_vs_proto_tcp.c index d0ea467..dd4566e 100644 --- a/net/ipv4/ipvs/ip_vs_proto_tcp.c +++ b/net/ipv4/ipvs/ip_vs_proto_tcp.c @@ -18,6 +18,7 @@ #include <linux/tcp.h> /* for tcphdr */ #include <net/ip.h> #include <net/tcp.h> /* for csum_tcpudp_magic */ +#include <net/ip6_checksum.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> @@ -25,8 +26,9 @@ 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) +tcp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, + const struct ip_vs_iphdr *iph, unsigned int proto_off, + int inverse) { __be16 _ports[2], *pptr; @@ -35,19 +37,20 @@ tcp_conn_in_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, return NULL; if (likely(!inverse)) { - return ip_vs_conn_in_get(iph->protocol, - iph->saddr, pptr[0], - iph->daddr, pptr[1]); + return ip_vs_conn_in_get(af, 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]); + return ip_vs_conn_in_get(af, 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) +tcp_conn_out_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, + const struct ip_vs_iphdr *iph, unsigned int proto_off, + int inverse) { __be16 _ports[2], *pptr; @@ -56,34 +59,36 @@ tcp_conn_out_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, return NULL; if (likely(!inverse)) { - return ip_vs_conn_out_get(iph->protocol, - iph->saddr, pptr[0], - iph->daddr, pptr[1]); + return ip_vs_conn_out_get(af, 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]); + return ip_vs_conn_out_get(af, iph->protocol, + &iph->daddr, pptr[1], + &iph->saddr, pptr[0]); } } static int -tcp_conn_schedule(struct sk_buff *skb, - struct ip_vs_protocol *pp, +tcp_conn_schedule(int af, 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; + struct ip_vs_iphdr iph; - th = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph); + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + + th = skb_header_pointer(skb, iph.len, 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))) { + (svc = ip_vs_service_get(af, skb->mark, iph.protocol, &iph.daddr, + th->dest))) { if (ip_vs_todrop()) { /* * It seems that we are very loaded. @@ -110,22 +115,62 @@ tcp_conn_schedule(struct sk_buff *skb, static inline void -tcp_fast_csum_update(struct tcphdr *tcph, __be32 oldip, __be32 newip, +tcp_fast_csum_update(int af, struct tcphdr *tcph, + const union nf_inet_addr *oldip, + const union nf_inet_addr *newip, __be16 oldport, __be16 newport) { +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + tcph->check = + csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, + ip_vs_check_diff2(oldport, newport, + ~csum_unfold(tcph->check)))); + else +#endif tcph->check = - csum_fold(ip_vs_check_diff4(oldip, newip, + csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, ip_vs_check_diff2(oldport, newport, ~csum_unfold(tcph->check)))); } +static inline void +tcp_partial_csum_update(int af, struct tcphdr *tcph, + const union nf_inet_addr *oldip, + const union nf_inet_addr *newip, + __be16 oldlen, __be16 newlen) +{ +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + tcph->check = + csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, + ip_vs_check_diff2(oldlen, newlen, + ~csum_unfold(tcph->check)))); + else +#endif + tcph->check = + csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, + ip_vs_check_diff2(oldlen, newlen, + ~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); + unsigned int tcphoff; + int oldlen; + +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + tcphoff = sizeof(struct ipv6hdr); + else +#endif + tcphoff = ip_hdrlen(skb); + oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ if (!skb_make_writable(skb, tcphoff+sizeof(*tcph))) @@ -133,7 +178,7 @@ tcp_snat_handler(struct sk_buff *skb, if (unlikely(cp->app != NULL)) { /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(skb, pp)) + if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ @@ -141,13 +186,17 @@ tcp_snat_handler(struct sk_buff *skb, return 0; } - tcph = (void *)ip_hdr(skb) + tcphoff; + tcph = (void *)skb_network_header(skb) + tcphoff; tcph->source = cp->vport; /* Adjust TCP checksums */ - if (!cp->app) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { + tcp_partial_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, + htonl(oldlen), + htonl(skb->len - tcphoff)); + } else if (!cp->app) { /* Only port and addr are changed, do fast csum update */ - tcp_fast_csum_update(tcph, cp->daddr, cp->vaddr, + tcp_fast_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; @@ -155,9 +204,20 @@ tcp_snat_handler(struct sk_buff *skb, /* 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); +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + tcph->check = csum_ipv6_magic(&cp->vaddr.in6, + &cp->caddr.in6, + skb->len - tcphoff, + cp->protocol, skb->csum); + else +#endif + tcph->check = csum_tcpudp_magic(cp->vaddr.ip, + cp->caddr.ip, + 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); @@ -171,7 +231,16 @@ 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); + unsigned int tcphoff; + int oldlen; + +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + tcphoff = sizeof(struct ipv6hdr); + else +#endif + tcphoff = ip_hdrlen(skb); + oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ if (!skb_make_writable(skb, tcphoff+sizeof(*tcph))) @@ -179,7 +248,7 @@ tcp_dnat_handler(struct sk_buff *skb, if (unlikely(cp->app != NULL)) { /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(skb, pp)) + if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) return 0; /* @@ -190,15 +259,19 @@ tcp_dnat_handler(struct sk_buff *skb, return 0; } - tcph = (void *)ip_hdr(skb) + tcphoff; + tcph = (void *)skb_network_header(skb) + tcphoff; tcph->dest = cp->dport; /* * Adjust TCP checksums */ - if (!cp->app) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { + tcp_partial_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, + htonl(oldlen), + htonl(skb->len - tcphoff)); + } else if (!cp->app) { /* Only port and addr are changed, do fast csum update */ - tcp_fast_csum_update(tcph, cp->vaddr, cp->daddr, + tcp_fast_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; @@ -206,9 +279,19 @@ tcp_dnat_handler(struct sk_buff *skb, /* 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); +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + tcph->check = csum_ipv6_magic(&cp->caddr.in6, + &cp->daddr.in6, + skb->len - tcphoff, + cp->protocol, skb->csum); + else +#endif + tcph->check = csum_tcpudp_magic(cp->caddr.ip, + cp->daddr.ip, + skb->len - tcphoff, + cp->protocol, + skb->csum); skb->ip_summed = CHECKSUM_UNNECESSARY; } return 1; @@ -216,21 +299,43 @@ tcp_dnat_handler(struct sk_buff *skb, static int -tcp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp) +tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) { - const unsigned int tcphoff = ip_hdrlen(skb); + unsigned int tcphoff; + +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + tcphoff = sizeof(struct ipv6hdr); + else +#endif + 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; - } +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) { + if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - tcphoff, + ipv6_hdr(skb)->nexthdr, + skb->csum)) { + IP_VS_DBG_RL_PKT(0, pp, skb, 0, + "Failed checksum for"); + return 0; + } + } else +#endif + 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. */ @@ -419,19 +524,23 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, if (new_state != cp->state) { struct ip_vs_dest *dest = cp->dest; - IP_VS_DBG(8, "%s %s [%c%c%c%c] %u.%u.%u.%u:%d->" - "%u.%u.%u.%u:%d state: %s->%s conn->refcnt:%d\n", - pp->name, - (state_off==TCP_DIR_OUTPUT)?"output ":"input ", - th->syn? 'S' : '.', - th->fin? 'F' : '.', - th->ack? 'A' : '.', - th->rst? 'R' : '.', - NIPQUAD(cp->daddr), ntohs(cp->dport), - NIPQUAD(cp->caddr), ntohs(cp->cport), - tcp_state_name(cp->state), - tcp_state_name(new_state), - atomic_read(&cp->refcnt)); + IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] %s:%d->" + "%s:%d state: %s->%s conn->refcnt:%d\n", + pp->name, + ((state_off == TCP_DIR_OUTPUT) ? + "output " : "input "), + th->syn ? 'S' : '.', + th->fin ? 'F' : '.', + th->ack ? 'A' : '.', + th->rst ? 'R' : '.', + IP_VS_DBG_ADDR(cp->af, &cp->daddr), + ntohs(cp->dport), + IP_VS_DBG_ADDR(cp->af, &cp->caddr), + ntohs(cp->cport), + tcp_state_name(cp->state), + tcp_state_name(new_state), + atomic_read(&cp->refcnt)); + if (dest) { if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && (new_state != IP_VS_TCP_S_ESTABLISHED)) { @@ -461,7 +570,13 @@ tcp_state_transition(struct ip_vs_conn *cp, int direction, { struct tcphdr _tcph, *th; - th = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph); +#ifdef CONFIG_IP_VS_IPV6 + int ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); +#else + int ihl = ip_hdrlen(skb); +#endif + + th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph); if (th == NULL) return 0; @@ -546,12 +661,15 @@ tcp_app_conn_bind(struct ip_vs_conn *cp) break; spin_unlock(&tcp_app_lock); - IP_VS_DBG(9, "%s: Binding conn %u.%u.%u.%u:%u->" - "%u.%u.%u.%u:%u to app %s on port %u\n", - __func__, - NIPQUAD(cp->caddr), ntohs(cp->cport), - NIPQUAD(cp->vaddr), ntohs(cp->vport), - inc->name, ntohs(inc->port)); + IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->" + "%s:%u to app %s on port %u\n", + __func__, + IP_VS_DBG_ADDR(cp->af, &cp->caddr), + ntohs(cp->cport), + IP_VS_DBG_ADDR(cp->af, &cp->vaddr), + ntohs(cp->vport), + inc->name, ntohs(inc->port)); + cp->app = inc; if (inc->init_conn) result = inc->init_conn(inc, cp); diff --git a/net/ipv4/ipvs/ip_vs_proto_udp.c b/net/ipv4/ipvs/ip_vs_proto_udp.c index c6be5d5..6eb6039 100644 --- a/net/ipv4/ipvs/ip_vs_proto_udp.c +++ b/net/ipv4/ipvs/ip_vs_proto_udp.c @@ -22,10 +22,12 @@ #include <net/ip_vs.h> #include <net/ip.h> +#include <net/ip6_checksum.h> static struct ip_vs_conn * -udp_conn_in_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, - const struct iphdr *iph, unsigned int proto_off, int inverse) +udp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, + const struct ip_vs_iphdr *iph, unsigned int proto_off, + int inverse) { struct ip_vs_conn *cp; __be16 _ports[2], *pptr; @@ -35,13 +37,13 @@ udp_conn_in_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, return NULL; if (likely(!inverse)) { - cp = ip_vs_conn_in_get(iph->protocol, - iph->saddr, pptr[0], - iph->daddr, pptr[1]); + cp = ip_vs_conn_in_get(af, iph->protocol, + &iph->saddr, pptr[0], + &iph->daddr, pptr[1]); } else { - cp = ip_vs_conn_in_get(iph->protocol, - iph->daddr, pptr[1], - iph->saddr, pptr[0]); + cp = ip_vs_conn_in_get(af, iph->protocol, + &iph->daddr, pptr[1], + &iph->saddr, pptr[0]); } return cp; @@ -49,25 +51,25 @@ udp_conn_in_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, static struct ip_vs_conn * -udp_conn_out_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, - const struct iphdr *iph, unsigned int proto_off, int inverse) +udp_conn_out_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, + const struct ip_vs_iphdr *iph, unsigned int proto_off, + int inverse) { struct ip_vs_conn *cp; __be16 _ports[2], *pptr; - pptr = skb_header_pointer(skb, ip_hdrlen(skb), - sizeof(_ports), _ports); + pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); if (pptr == NULL) return NULL; if (likely(!inverse)) { - cp = ip_vs_conn_out_get(iph->protocol, - iph->saddr, pptr[0], - iph->daddr, pptr[1]); + cp = ip_vs_conn_out_get(af, iph->protocol, + &iph->saddr, pptr[0], + &iph->daddr, pptr[1]); } else { - cp = ip_vs_conn_out_get(iph->protocol, - iph->daddr, pptr[1], - iph->saddr, pptr[0]); + cp = ip_vs_conn_out_get(af, iph->protocol, + &iph->daddr, pptr[1], + &iph->saddr, pptr[0]); } return cp; @@ -75,21 +77,24 @@ udp_conn_out_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, static int -udp_conn_schedule(struct sk_buff *skb, struct ip_vs_protocol *pp, +udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, int *verdict, struct ip_vs_conn **cpp) { struct ip_vs_service *svc; struct udphdr _udph, *uh; + struct ip_vs_iphdr iph; + + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); - uh = skb_header_pointer(skb, ip_hdrlen(skb), - sizeof(_udph), &_udph); + uh = skb_header_pointer(skb, iph.len, sizeof(_udph), &_udph); if (uh == NULL) { *verdict = NF_DROP; return 0; } - if ((svc = ip_vs_service_get(skb->mark, ip_hdr(skb)->protocol, - ip_hdr(skb)->daddr, uh->dest))) { + svc = ip_vs_service_get(af, skb->mark, iph.protocol, + &iph.daddr, uh->dest); + if (svc) { if (ip_vs_todrop()) { /* * It seems that we are very loaded. @@ -116,23 +121,63 @@ udp_conn_schedule(struct sk_buff *skb, struct ip_vs_protocol *pp, static inline void -udp_fast_csum_update(struct udphdr *uhdr, __be32 oldip, __be32 newip, +udp_fast_csum_update(int af, struct udphdr *uhdr, + const union nf_inet_addr *oldip, + const union nf_inet_addr *newip, __be16 oldport, __be16 newport) { - uhdr->check = - csum_fold(ip_vs_check_diff4(oldip, newip, - ip_vs_check_diff2(oldport, newport, - ~csum_unfold(uhdr->check)))); +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + uhdr->check = + csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, + ip_vs_check_diff2(oldport, newport, + ~csum_unfold(uhdr->check)))); + else +#endif + uhdr->check = + csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, + ip_vs_check_diff2(oldport, newport, + ~csum_unfold(uhdr->check)))); if (!uhdr->check) uhdr->check = CSUM_MANGLED_0; } +static inline void +udp_partial_csum_update(int af, struct udphdr *uhdr, + const union nf_inet_addr *oldip, + const union nf_inet_addr *newip, + __be16 oldlen, __be16 newlen) +{ +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + uhdr->check = + csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, + ip_vs_check_diff2(oldlen, newlen, + ~csum_unfold(uhdr->check)))); + else +#endif + uhdr->check = + csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, + ip_vs_check_diff2(oldlen, newlen, + ~csum_unfold(uhdr->check)))); +} + + static int udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp) { struct udphdr *udph; - const unsigned int udphoff = ip_hdrlen(skb); + unsigned int udphoff; + int oldlen; + +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + udphoff = sizeof(struct ipv6hdr); + else +#endif + udphoff = ip_hdrlen(skb); + oldlen = skb->len - udphoff; /* csum_check requires unshared skb */ if (!skb_make_writable(skb, udphoff+sizeof(*udph))) @@ -140,7 +185,7 @@ udp_snat_handler(struct sk_buff *skb, if (unlikely(cp->app != NULL)) { /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(skb, pp)) + if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) return 0; /* @@ -150,15 +195,19 @@ udp_snat_handler(struct sk_buff *skb, return 0; } - udph = (void *)ip_hdr(skb) + udphoff; + udph = (void *)skb_network_header(skb) + udphoff; udph->source = cp->vport; /* * Adjust UDP checksums */ - if (!cp->app && (udph->check != 0)) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { + udp_partial_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr, + htonl(oldlen), + htonl(skb->len - udphoff)); + } else if (!cp->app && (udph->check != 0)) { /* Only port and addr are changed, do fast csum update */ - udp_fast_csum_update(udph, cp->daddr, cp->vaddr, + udp_fast_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; @@ -166,9 +215,19 @@ udp_snat_handler(struct sk_buff *skb, /* full checksum calculation */ udph->check = 0; skb->csum = skb_checksum(skb, udphoff, skb->len - udphoff, 0); - udph->check = csum_tcpudp_magic(cp->vaddr, cp->caddr, - skb->len - udphoff, - cp->protocol, skb->csum); +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + udph->check = csum_ipv6_magic(&cp->vaddr.in6, + &cp->caddr.in6, + skb->len - udphoff, + cp->protocol, skb->csum); + else +#endif + udph->check = csum_tcpudp_magic(cp->vaddr.ip, + cp->caddr.ip, + skb->len - udphoff, + cp->protocol, + skb->csum); if (udph->check == 0) udph->check = CSUM_MANGLED_0; IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n", @@ -184,7 +243,16 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp) { struct udphdr *udph; - unsigned int udphoff = ip_hdrlen(skb); + unsigned int udphoff; + int oldlen; + +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + udphoff = sizeof(struct ipv6hdr); + else +#endif + udphoff = ip_hdrlen(skb); + oldlen = skb->len - udphoff; /* csum_check requires unshared skb */ if (!skb_make_writable(skb, udphoff+sizeof(*udph))) @@ -192,7 +260,7 @@ udp_dnat_handler(struct sk_buff *skb, if (unlikely(cp->app != NULL)) { /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(skb, pp)) + if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) return 0; /* @@ -203,15 +271,19 @@ udp_dnat_handler(struct sk_buff *skb, return 0; } - udph = (void *)ip_hdr(skb) + udphoff; + udph = (void *)skb_network_header(skb) + udphoff; udph->dest = cp->dport; /* * Adjust UDP checksums */ - if (!cp->app && (udph->check != 0)) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { + udp_partial_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr, + htonl(oldlen), + htonl(skb->len - udphoff)); + } else if (!cp->app && (udph->check != 0)) { /* Only port and addr are changed, do fast csum update */ - udp_fast_csum_update(udph, cp->vaddr, cp->daddr, + udp_fast_csum_update(cp->af, udph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; @@ -219,9 +291,19 @@ udp_dnat_handler(struct sk_buff *skb, /* full checksum calculation */ udph->check = 0; skb->csum = skb_checksum(skb, udphoff, skb->len - udphoff, 0); - udph->check = csum_tcpudp_magic(cp->caddr, cp->daddr, - skb->len - udphoff, - cp->protocol, skb->csum); +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + udph->check = csum_ipv6_magic(&cp->caddr.in6, + &cp->daddr.in6, + skb->len - udphoff, + cp->protocol, skb->csum); + else +#endif + udph->check = csum_tcpudp_magic(cp->caddr.ip, + cp->daddr.ip, + skb->len - udphoff, + cp->protocol, + skb->csum); if (udph->check == 0) udph->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -231,10 +313,17 @@ udp_dnat_handler(struct sk_buff *skb, static int -udp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp) +udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) { struct udphdr _udph, *uh; - const unsigned int udphoff = ip_hdrlen(skb); + unsigned int udphoff; + +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + udphoff = sizeof(struct ipv6hdr); + else +#endif + udphoff = ip_hdrlen(skb); uh = skb_header_pointer(skb, udphoff, sizeof(_udph), &_udph); if (uh == NULL) @@ -246,15 +335,28 @@ udp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp) skb->csum = skb_checksum(skb, udphoff, skb->len - udphoff, 0); case CHECKSUM_COMPLETE: - if (csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - udphoff, - ip_hdr(skb)->protocol, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, pp, skb, 0, - "Failed checksum for"); - return 0; - } +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) { + if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - udphoff, + ipv6_hdr(skb)->nexthdr, + skb->csum)) { + IP_VS_DBG_RL_PKT(0, pp, skb, 0, + "Failed checksum for"); + return 0; + } + } else +#endif + if (csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - udphoff, + 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. */ @@ -340,12 +442,15 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp) break; spin_unlock(&udp_app_lock); - IP_VS_DBG(9, "%s: Binding conn %u.%u.%u.%u:%u->" - "%u.%u.%u.%u:%u to app %s on port %u\n", - __func__, - NIPQUAD(cp->caddr), ntohs(cp->cport), - NIPQUAD(cp->vaddr), ntohs(cp->vport), - inc->name, ntohs(inc->port)); + IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->" + "%s:%u to app %s on port %u\n", + __func__, + IP_VS_DBG_ADDR(cp->af, &cp->caddr), + ntohs(cp->cport), + IP_VS_DBG_ADDR(cp->af, &cp->vaddr), + ntohs(cp->vport), + inc->name, ntohs(inc->port)); + cp->app = inc; if (inc->init_conn) result = inc->init_conn(inc, cp); diff --git a/net/ipv4/ipvs/ip_vs_rr.c b/net/ipv4/ipvs/ip_vs_rr.c index 358110d..a22195f 100644 --- a/net/ipv4/ipvs/ip_vs_rr.c +++ b/net/ipv4/ipvs/ip_vs_rr.c @@ -32,12 +32,6 @@ static int ip_vs_rr_init_svc(struct ip_vs_service *svc) } -static int ip_vs_rr_done_svc(struct ip_vs_service *svc) -{ - return 0; -} - - static int ip_vs_rr_update_svc(struct ip_vs_service *svc) { svc->sched_data = &svc->destinations; @@ -80,11 +74,11 @@ ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) out: svc->sched_data = q; write_unlock(&svc->sched_lock); - IP_VS_DBG(6, "RR: server %u.%u.%u.%u:%u " - "activeconns %d refcnt %d weight %d\n", - NIPQUAD(dest->addr), ntohs(dest->port), - atomic_read(&dest->activeconns), - atomic_read(&dest->refcnt), atomic_read(&dest->weight)); + IP_VS_DBG_BUF(6, "RR: server %s:%u " + "activeconns %d refcnt %d weight %d\n", + IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port), + atomic_read(&dest->activeconns), + atomic_read(&dest->refcnt), atomic_read(&dest->weight)); return dest; } @@ -95,8 +89,10 @@ static struct ip_vs_scheduler ip_vs_rr_scheduler = { .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_rr_scheduler.n_list), +#ifdef CONFIG_IP_VS_IPV6 + .supports_ipv6 = 1, +#endif .init_service = ip_vs_rr_init_svc, - .done_service = ip_vs_rr_done_svc, .update_service = ip_vs_rr_update_svc, .schedule = ip_vs_rr_schedule, }; diff --git a/net/ipv4/ipvs/ip_vs_sed.c b/net/ipv4/ipvs/ip_vs_sed.c index 77663d8..7d2f22f 100644 --- a/net/ipv4/ipvs/ip_vs_sed.c +++ b/net/ipv4/ipvs/ip_vs_sed.c @@ -41,27 +41,6 @@ #include <net/ip_vs.h> -static int -ip_vs_sed_init_svc(struct ip_vs_service *svc) -{ - return 0; -} - - -static int -ip_vs_sed_done_svc(struct ip_vs_service *svc) -{ - return 0; -} - - -static int -ip_vs_sed_update_svc(struct ip_vs_service *svc) -{ - return 0; -} - - static inline unsigned int ip_vs_sed_dest_overhead(struct ip_vs_dest *dest) { @@ -122,12 +101,12 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) } } - IP_VS_DBG(6, "SED: server %u.%u.%u.%u:%u " - "activeconns %d refcnt %d weight %d overhead %d\n", - NIPQUAD(least->addr), ntohs(least->port), - atomic_read(&least->activeconns), - atomic_read(&least->refcnt), - atomic_read(&least->weight), loh); + IP_VS_DBG_BUF(6, "SED: server %s:%u " + "activeconns %d refcnt %d weight %d overhead %d\n", + IP_VS_DBG_ADDR(svc->af, &least->addr), ntohs(least->port), + atomic_read(&least->activeconns), + atomic_read(&least->refcnt), + atomic_read(&least->weight), loh); return least; } @@ -139,9 +118,9 @@ static struct ip_vs_scheduler ip_vs_sed_scheduler = .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_sed_scheduler.n_list), - .init_service = ip_vs_sed_init_svc, - .done_service = ip_vs_sed_done_svc, - .update_service = ip_vs_sed_update_svc, +#ifdef CONFIG_IP_VS_IPV6 + .supports_ipv6 = 1, +#endif .schedule = ip_vs_sed_schedule, }; diff --git a/net/ipv4/ipvs/ip_vs_sh.c b/net/ipv4/ipvs/ip_vs_sh.c index 7b979e2..1d96de2 100644 --- a/net/ipv4/ipvs/ip_vs_sh.c +++ b/net/ipv4/ipvs/ip_vs_sh.c @@ -215,7 +215,7 @@ ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) IP_VS_DBG(6, "SH: source IP address %u.%u.%u.%u " "--> server %u.%u.%u.%u:%d\n", NIPQUAD(iph->saddr), - NIPQUAD(dest->addr), + NIPQUAD(dest->addr.ip), ntohs(dest->port)); return dest; @@ -231,6 +231,9 @@ static struct ip_vs_scheduler ip_vs_sh_scheduler = .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_sh_scheduler.n_list), +#ifdef CONFIG_IP_VS_IPV6 + .supports_ipv6 = 0, +#endif .init_service = ip_vs_sh_init_svc, .done_service = ip_vs_sh_done_svc, .update_service = ip_vs_sh_update_svc, diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c index a652da2..28237a5 100644 --- a/net/ipv4/ipvs/ip_vs_sync.c +++ b/net/ipv4/ipvs/ip_vs_sync.c @@ -256,9 +256,9 @@ void ip_vs_sync_conn(struct ip_vs_conn *cp) s->cport = cp->cport; s->vport = cp->vport; s->dport = cp->dport; - s->caddr = cp->caddr; - s->vaddr = cp->vaddr; - s->daddr = cp->daddr; + s->caddr = cp->caddr.ip; + s->vaddr = cp->vaddr.ip; + s->daddr = cp->daddr.ip; s->flags = htons(cp->flags & ~IP_VS_CONN_F_HASHED); s->state = htons(cp->state); if (cp->flags & IP_VS_CONN_F_SEQ_MASK) { @@ -366,21 +366,28 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) } if (!(flags & IP_VS_CONN_F_TEMPLATE)) - cp = ip_vs_conn_in_get(s->protocol, - s->caddr, s->cport, - s->vaddr, s->vport); + cp = ip_vs_conn_in_get(AF_INET, s->protocol, + (union nf_inet_addr *)&s->caddr, + s->cport, + (union nf_inet_addr *)&s->vaddr, + s->vport); else - cp = ip_vs_ct_in_get(s->protocol, - s->caddr, s->cport, - s->vaddr, s->vport); + cp = ip_vs_ct_in_get(AF_INET, s->protocol, + (union nf_inet_addr *)&s->caddr, + s->cport, + (union nf_inet_addr *)&s->vaddr, + s->vport); if (!cp) { /* * Find the appropriate destination for the connection. * If it is not found the connection will remain unbound * but still handled. */ - dest = ip_vs_find_dest(s->daddr, s->dport, - s->vaddr, s->vport, + dest = ip_vs_find_dest(AF_INET, + (union nf_inet_addr *)&s->daddr, + s->dport, + (union nf_inet_addr *)&s->vaddr, + s->vport, s->protocol); /* Set the approprite ativity flag */ if (s->protocol == IPPROTO_TCP) { @@ -389,10 +396,13 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) else flags &= ~IP_VS_CONN_F_INACTIVE; } - cp = ip_vs_conn_new(s->protocol, - s->caddr, s->cport, - s->vaddr, s->vport, - s->daddr, s->dport, + cp = ip_vs_conn_new(AF_INET, s->protocol, + (union nf_inet_addr *)&s->caddr, + s->cport, + (union nf_inet_addr *)&s->vaddr, + s->vport, + (union nf_inet_addr *)&s->daddr, + s->dport, flags, dest); if (dest) atomic_dec(&dest->refcnt); diff --git a/net/ipv4/ipvs/ip_vs_wlc.c b/net/ipv4/ipvs/ip_vs_wlc.c index 9b0ef86..8c596e7 100644 --- a/net/ipv4/ipvs/ip_vs_wlc.c +++ b/net/ipv4/ipvs/ip_vs_wlc.c @@ -25,27 +25,6 @@ #include <net/ip_vs.h> -static int -ip_vs_wlc_init_svc(struct ip_vs_service *svc) -{ - return 0; -} - - -static int -ip_vs_wlc_done_svc(struct ip_vs_service *svc) -{ - return 0; -} - - -static int -ip_vs_wlc_update_svc(struct ip_vs_service *svc) -{ - return 0; -} - - static inline unsigned int ip_vs_wlc_dest_overhead(struct ip_vs_dest *dest) { @@ -110,12 +89,12 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) } } - IP_VS_DBG(6, "WLC: server %u.%u.%u.%u:%u " - "activeconns %d refcnt %d weight %d overhead %d\n", - NIPQUAD(least->addr), ntohs(least->port), - atomic_read(&least->activeconns), - atomic_read(&least->refcnt), - atomic_read(&least->weight), loh); + IP_VS_DBG_BUF(6, "WLC: server %s:%u " + "activeconns %d refcnt %d weight %d overhead %d\n", + IP_VS_DBG_ADDR(svc->af, &least->addr), ntohs(least->port), + atomic_read(&least->activeconns), + atomic_read(&least->refcnt), + atomic_read(&least->weight), loh); return least; } @@ -127,9 +106,9 @@ static struct ip_vs_scheduler ip_vs_wlc_scheduler = .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_wlc_scheduler.n_list), - .init_service = ip_vs_wlc_init_svc, - .done_service = ip_vs_wlc_done_svc, - .update_service = ip_vs_wlc_update_svc, +#ifdef CONFIG_IP_VS_IPV6 + .supports_ipv6 = 1, +#endif .schedule = ip_vs_wlc_schedule, }; diff --git a/net/ipv4/ipvs/ip_vs_wrr.c b/net/ipv4/ipvs/ip_vs_wrr.c index 0d86a79..7ea92fe 100644 --- a/net/ipv4/ipvs/ip_vs_wrr.c +++ b/net/ipv4/ipvs/ip_vs_wrr.c @@ -195,12 +195,12 @@ ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) } } - IP_VS_DBG(6, "WRR: server %u.%u.%u.%u:%u " - "activeconns %d refcnt %d weight %d\n", - NIPQUAD(dest->addr), ntohs(dest->port), - atomic_read(&dest->activeconns), - atomic_read(&dest->refcnt), - atomic_read(&dest->weight)); + IP_VS_DBG_BUF(6, "WRR: server %s:%u " + "activeconns %d refcnt %d weight %d\n", + IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port), + atomic_read(&dest->activeconns), + atomic_read(&dest->refcnt), + atomic_read(&dest->weight)); out: write_unlock(&svc->sched_lock); @@ -213,6 +213,9 @@ static struct ip_vs_scheduler ip_vs_wrr_scheduler = { .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_wrr_scheduler.n_list), +#ifdef CONFIG_IP_VS_IPV6 + .supports_ipv6 = 1, +#endif .init_service = ip_vs_wrr_init_svc, .done_service = ip_vs_wrr_done_svc, .update_service = ip_vs_wrr_update_svc, diff --git a/net/ipv4/ipvs/ip_vs_xmit.c b/net/ipv4/ipvs/ip_vs_xmit.c index 9892d4a..02ddc2b 100644 --- a/net/ipv4/ipvs/ip_vs_xmit.c +++ b/net/ipv4/ipvs/ip_vs_xmit.c @@ -20,6 +20,9 @@ #include <net/udp.h> #include <net/icmp.h> /* for icmp_send */ #include <net/route.h> /* for ip_route_output */ +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <linux/icmpv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> @@ -47,7 +50,8 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos, u32 cookie) if (!dst) return NULL; - if ((dst->obsolete || rtos != dest->dst_rtos) && + if ((dst->obsolete + || (dest->af == AF_INET && rtos != dest->dst_rtos)) && dst->ops->check(dst, cookie) == NULL) { dest->dst_cache = NULL; dst_release(dst); @@ -71,7 +75,7 @@ __ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos) .oif = 0, .nl_u = { .ip4_u = { - .daddr = dest->addr, + .daddr = dest->addr.ip, .saddr = 0, .tos = rtos, } }, }; @@ -80,12 +84,12 @@ __ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos) spin_unlock(&dest->dst_lock); IP_VS_DBG_RL("ip_route_output error, " "dest: %u.%u.%u.%u\n", - NIPQUAD(dest->addr)); + NIPQUAD(dest->addr.ip)); return NULL; } __ip_vs_dst_set(dest, rtos, dst_clone(&rt->u.dst)); IP_VS_DBG(10, "new dst %u.%u.%u.%u, refcnt=%d, rtos=%X\n", - NIPQUAD(dest->addr), + NIPQUAD(dest->addr.ip), atomic_read(&rt->u.dst.__refcnt), rtos); } spin_unlock(&dest->dst_lock); @@ -94,14 +98,14 @@ __ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos) .oif = 0, .nl_u = { .ip4_u = { - .daddr = cp->daddr, + .daddr = cp->daddr.ip, .saddr = 0, .tos = rtos, } }, }; if (ip_route_output_key(&init_net, &rt, &fl)) { IP_VS_DBG_RL("ip_route_output error, dest: " - "%u.%u.%u.%u\n", NIPQUAD(cp->daddr)); + "%u.%u.%u.%u\n", NIPQUAD(cp->daddr.ip)); return NULL; } } @@ -109,6 +113,70 @@ __ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos) return rt; } +#ifdef CONFIG_IP_VS_IPV6 +static struct rt6_info * +__ip_vs_get_out_rt_v6(struct ip_vs_conn *cp) +{ + struct rt6_info *rt; /* Route to the other host */ + struct ip_vs_dest *dest = cp->dest; + + if (dest) { + spin_lock(&dest->dst_lock); + rt = (struct rt6_info *)__ip_vs_dst_check(dest, 0, 0); + if (!rt) { + struct flowi fl = { + .oif = 0, + .nl_u = { + .ip6_u = { + .daddr = dest->addr.in6, + .saddr = { + .s6_addr32 = + { 0, 0, 0, 0 }, + }, + }, + }, + }; + + rt = (struct rt6_info *)ip6_route_output(&init_net, + NULL, &fl); + if (!rt) { + spin_unlock(&dest->dst_lock); + IP_VS_DBG_RL("ip6_route_output error, " + "dest: " NIP6_FMT "\n", + NIP6(dest->addr.in6)); + return NULL; + } + __ip_vs_dst_set(dest, 0, dst_clone(&rt->u.dst)); + IP_VS_DBG(10, "new dst " NIP6_FMT ", refcnt=%d\n", + NIP6(dest->addr.in6), + atomic_read(&rt->u.dst.__refcnt)); + } + spin_unlock(&dest->dst_lock); + } else { + struct flowi fl = { + .oif = 0, + .nl_u = { + .ip6_u = { + .daddr = cp->daddr.in6, + .saddr = { + .s6_addr32 = { 0, 0, 0, 0 }, + }, + }, + }, + }; + + rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl); + if (!rt) { + IP_VS_DBG_RL("ip6_route_output error, dest: " + NIP6_FMT "\n", NIP6(cp->daddr.in6)); + return NULL; + } + } + + return rt; +} +#endif + /* * Release dest->dst_cache before a dest is removed @@ -123,11 +191,11 @@ ip_vs_dst_reset(struct ip_vs_dest *dest) dst_release(old_dst); } -#define IP_VS_XMIT(skb, rt) \ +#define IP_VS_XMIT(pf, skb, rt) \ do { \ (skb)->ipvs_property = 1; \ skb_forward_csum(skb); \ - NF_HOOK(PF_INET, NF_INET_LOCAL_OUT, (skb), NULL, \ + NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \ (rt)->u.dst.dev, dst_output); \ } while (0) @@ -200,7 +268,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(skb, rt); + IP_VS_XMIT(PF_INET, skb, rt); LeaveFunction(10); return NF_STOLEN; @@ -213,6 +281,70 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, return NF_STOLEN; } +#ifdef CONFIG_IP_VS_IPV6 +int +ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, + struct ip_vs_protocol *pp) +{ + struct rt6_info *rt; /* Route to the other host */ + struct ipv6hdr *iph = ipv6_hdr(skb); + int mtu; + struct flowi fl = { + .oif = 0, + .nl_u = { + .ip6_u = { + .daddr = iph->daddr, + .saddr = { .s6_addr32 = {0, 0, 0, 0} }, } }, + }; + + EnterFunction(10); + + rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl); + if (!rt) { + IP_VS_DBG_RL("ip_vs_bypass_xmit_v6(): ip6_route_output error, " + "dest: " NIP6_FMT "\n", NIP6(iph->daddr)); + goto tx_error_icmp; + } + + /* MTU checking */ + mtu = dst_mtu(&rt->u.dst); + if (skb->len > mtu) { + dst_release(&rt->u.dst); + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); + IP_VS_DBG_RL("ip_vs_bypass_xmit_v6(): frag needed\n"); + goto tx_error; + } + + /* + * Call ip_send_check because we are not sure it is called + * after ip_defrag. Is copy-on-write needed? + */ + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(skb == NULL)) { + dst_release(&rt->u.dst); + return NF_STOLEN; + } + + /* drop old route */ + dst_release(skb->dst); + skb->dst = &rt->u.dst; + + /* Another hack: avoid icmp_send in ip_fragment */ + skb->local_df = 1; + + IP_VS_XMIT(PF_INET6, skb, rt); + + LeaveFunction(10); + return NF_STOLEN; + + tx_error_icmp: + dst_link_failure(skb); + tx_error: + kfree_skb(skb); + LeaveFunction(10); + return NF_STOLEN; +} +#endif /* * NAT transmitter (only for outside-to-inside nat forwarding) @@ -264,7 +396,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) goto tx_error; - ip_hdr(skb)->daddr = cp->daddr; + ip_hdr(skb)->daddr = cp->daddr.ip; ip_send_check(ip_hdr(skb)); IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); @@ -276,7 +408,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(skb, rt); + IP_VS_XMIT(PF_INET, skb, rt); LeaveFunction(10); return NF_STOLEN; @@ -292,6 +424,83 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } +#ifdef CONFIG_IP_VS_IPV6 +int +ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, + struct ip_vs_protocol *pp) +{ + struct rt6_info *rt; /* Route to the other host */ + int mtu; + + EnterFunction(10); + + /* check if it is a connection of no-client-port */ + if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) { + __be16 _pt, *p; + p = skb_header_pointer(skb, sizeof(struct ipv6hdr), + sizeof(_pt), &_pt); + if (p == NULL) + goto tx_error; + ip_vs_conn_fill_cport(cp, *p); + IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p)); + } + + rt = __ip_vs_get_out_rt_v6(cp); + if (!rt) + goto tx_error_icmp; + + /* MTU checking */ + mtu = dst_mtu(&rt->u.dst); + if (skb->len > mtu) { + dst_release(&rt->u.dst); + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); + IP_VS_DBG_RL_PKT(0, pp, skb, 0, + "ip_vs_nat_xmit_v6(): frag needed for"); + goto tx_error; + } + + /* copy-on-write the packet before mangling it */ + if (!skb_make_writable(skb, sizeof(struct ipv6hdr))) + goto tx_error_put; + + if (skb_cow(skb, rt->u.dst.dev->hard_header_len)) + goto tx_error_put; + + /* drop old route */ + dst_release(skb->dst); + skb->dst = &rt->u.dst; + + /* mangle the packet */ + if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) + goto tx_error; + ipv6_hdr(skb)->daddr = cp->daddr.in6; + + IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); + + /* FIXME: when application helper enlarges the packet and the length + is larger than the MTU of outgoing device, there will be still + MTU problem. */ + + /* Another hack: avoid icmp_send in ip_fragment */ + skb->local_df = 1; + + IP_VS_XMIT(PF_INET6, skb, rt); + + LeaveFunction(10); + return NF_STOLEN; + +tx_error_icmp: + dst_link_failure(skb); +tx_error: + LeaveFunction(10); + kfree_skb(skb); + return NF_STOLEN; +tx_error_put: + dst_release(&rt->u.dst); + goto tx_error; +} +#endif + /* * IP Tunneling transmitter @@ -423,6 +632,112 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, return NF_STOLEN; } +#ifdef CONFIG_IP_VS_IPV6 +int +ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, + struct ip_vs_protocol *pp) +{ + struct rt6_info *rt; /* Route to the other host */ + struct net_device *tdev; /* Device to other host */ + struct ipv6hdr *old_iph = ipv6_hdr(skb); + sk_buff_data_t old_transport_header = skb->transport_header; + struct ipv6hdr *iph; /* Our new IP header */ + unsigned int max_headroom; /* The extra header space needed */ + int mtu; + + EnterFunction(10); + + if (skb->protocol != htons(ETH_P_IPV6)) { + IP_VS_DBG_RL("ip_vs_tunnel_xmit_v6(): protocol error, " + "ETH_P_IPV6: %d, skb protocol: %d\n", + htons(ETH_P_IPV6), skb->protocol); + goto tx_error; + } + + rt = __ip_vs_get_out_rt_v6(cp); + if (!rt) + goto tx_error_icmp; + + tdev = rt->u.dst.dev; + + mtu = dst_mtu(&rt->u.dst) - sizeof(struct ipv6hdr); + /* TODO IPv6: do we need this check in IPv6? */ + if (mtu < 1280) { + dst_release(&rt->u.dst); + IP_VS_DBG_RL("ip_vs_tunnel_xmit_v6(): mtu less than 1280\n"); + goto tx_error; + } + if (skb->dst) + skb->dst->ops->update_pmtu(skb->dst, mtu); + + if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) { + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); + dst_release(&rt->u.dst); + IP_VS_DBG_RL("ip_vs_tunnel_xmit_v6(): frag needed\n"); + goto tx_error; + } + + /* + * Okay, now see if we can stuff it in the buffer as-is. + */ + max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr); + + if (skb_headroom(skb) < max_headroom + || skb_cloned(skb) || skb_shared(skb)) { + struct sk_buff *new_skb = + skb_realloc_headroom(skb, max_headroom); + if (!new_skb) { + dst_release(&rt->u.dst); + kfree_skb(skb); + IP_VS_ERR_RL("ip_vs_tunnel_xmit_v6(): no memory\n"); + return NF_STOLEN; + } + kfree_skb(skb); + skb = new_skb; + old_iph = ipv6_hdr(skb); + } + + skb->transport_header = old_transport_header; + + skb_push(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + + /* drop old route */ + dst_release(skb->dst); + skb->dst = &rt->u.dst; + + /* + * Push down and install the IPIP header. + */ + iph = ipv6_hdr(skb); + iph->version = 6; + iph->nexthdr = IPPROTO_IPV6; + iph->payload_len = old_iph->payload_len + sizeof(old_iph); + iph->priority = old_iph->priority; + memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl)); + iph->daddr = rt->rt6i_dst.addr; + iph->saddr = cp->vaddr.in6; /* rt->rt6i_src.addr; */ + iph->hop_limit = old_iph->hop_limit; + + /* Another hack: avoid icmp_send in ip_fragment */ + skb->local_df = 1; + + ip6_local_out(skb); + + LeaveFunction(10); + + return NF_STOLEN; + +tx_error_icmp: + dst_link_failure(skb); +tx_error: + kfree_skb(skb); + LeaveFunction(10); + return NF_STOLEN; +} +#endif + /* * Direct Routing transmitter @@ -467,7 +782,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(skb, rt); + IP_VS_XMIT(PF_INET, skb, rt); LeaveFunction(10); return NF_STOLEN; @@ -480,6 +795,60 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, return NF_STOLEN; } +#ifdef CONFIG_IP_VS_IPV6 +int +ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, + struct ip_vs_protocol *pp) +{ + struct rt6_info *rt; /* Route to the other host */ + int mtu; + + EnterFunction(10); + + rt = __ip_vs_get_out_rt_v6(cp); + if (!rt) + goto tx_error_icmp; + + /* MTU checking */ + mtu = dst_mtu(&rt->u.dst); + if (skb->len > mtu) { + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); + dst_release(&rt->u.dst); + IP_VS_DBG_RL("ip_vs_dr_xmit_v6(): frag needed\n"); + goto tx_error; + } + + /* + * Call ip_send_check because we are not sure it is called + * after ip_defrag. Is copy-on-write needed? + */ + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(skb == NULL)) { + dst_release(&rt->u.dst); + return NF_STOLEN; + } + + /* drop old route */ + dst_release(skb->dst); + skb->dst = &rt->u.dst; + + /* Another hack: avoid icmp_send in ip_fragment */ + skb->local_df = 1; + + IP_VS_XMIT(PF_INET6, skb, rt); + + LeaveFunction(10); + return NF_STOLEN; + +tx_error_icmp: + dst_link_failure(skb); +tx_error: + kfree_skb(skb); + LeaveFunction(10); + return NF_STOLEN; +} +#endif + /* * ICMP packet transmitter @@ -540,7 +909,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(skb, rt); + IP_VS_XMIT(PF_INET, skb, rt); rc = NF_STOLEN; goto out; @@ -557,3 +926,79 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, ip_rt_put(rt); goto tx_error; } + +#ifdef CONFIG_IP_VS_IPV6 +int +ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, + struct ip_vs_protocol *pp, int offset) +{ + struct rt6_info *rt; /* Route to the other host */ + int mtu; + int rc; + + EnterFunction(10); + + /* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be + forwarded directly here, because there is no need to + translate address/port back */ + if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { + if (cp->packet_xmit) + rc = cp->packet_xmit(skb, cp, pp); + else + rc = NF_ACCEPT; + /* do not touch skb anymore */ + atomic_inc(&cp->in_pkts); + goto out; + } + + /* + * mangle and send the packet here (only for VS/NAT) + */ + + rt = __ip_vs_get_out_rt_v6(cp); + if (!rt) + goto tx_error_icmp; + + /* MTU checking */ + mtu = dst_mtu(&rt->u.dst); + if (skb->len > mtu) { + dst_release(&rt->u.dst); + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); + IP_VS_DBG_RL("ip_vs_in_icmp(): frag needed\n"); + goto tx_error; + } + + /* copy-on-write the packet before mangling it */ + if (!skb_make_writable(skb, offset)) + goto tx_error_put; + + if (skb_cow(skb, rt->u.dst.dev->hard_header_len)) + goto tx_error_put; + + /* drop the old route when skb is not shared */ + dst_release(skb->dst); + skb->dst = &rt->u.dst; + + ip_vs_nat_icmp_v6(skb, pp, cp, 0); + + /* Another hack: avoid icmp_send in ip_fragment */ + skb->local_df = 1; + + IP_VS_XMIT(PF_INET6, skb, rt); + + rc = NF_STOLEN; + goto out; + +tx_error_icmp: + dst_link_failure(skb); +tx_error: + dev_kfree_skb(skb); + rc = NF_STOLEN; +out: + LeaveFunction(10); + return rc; +tx_error_put: + dst_release(&rt->u.dst); + goto tx_error; +} +#endif |