diff options
author | David S. Miller <davem@davemloft.net> | 2008-08-27 05:11:26 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2008-08-27 05:11:26 -0700 |
commit | 4d40555250320520c5398569457962b3984fc75e (patch) | |
tree | a8f50817e2c43db94983a4eb5bb0e885123821e0 | |
parent | eff253c4272cd2aac95ccff46d3d2e1a495f22b1 (diff) | |
parent | 7fd106785104fa19709fa136abb64c7a9d5db285 (diff) |
Merge branch 'lvs-next-2.6' of git://git.kernel.org/pub/scm/linux/kernel/git/horms/lvs-2.6
-rw-r--r-- | include/linux/ip_vs.h | 160 | ||||
-rw-r--r-- | include/net/ip_vs.h | 2 | ||||
-rw-r--r-- | net/ipv4/ipvs/Kconfig | 6 | ||||
-rw-r--r-- | net/ipv4/ipvs/Makefile | 3 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_core.c | 8 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_ctl.c | 896 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_est.c | 18 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_lblc.c | 213 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_lblcr.c | 238 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_lc.c | 21 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_nq.c | 24 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_proto_ah_esp.c (renamed from net/ipv4/ipvs/ip_vs_proto_ah.c) | 69 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_proto_esp.c | 176 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_rr.c | 7 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_sed.c | 24 | ||||
-rw-r--r-- | net/ipv4/ipvs/ip_vs_wlc.c | 24 |
16 files changed, 1332 insertions, 557 deletions
diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h index ec6eb49af2d8..0f434a28fb58 100644 --- a/include/linux/ip_vs.h +++ b/include/linux/ip_vs.h @@ -242,4 +242,164 @@ struct ip_vs_daemon_user { int syncid; }; +/* + * + * IPVS Generic Netlink interface definitions + * + */ + +/* Generic Netlink family info */ + +#define IPVS_GENL_NAME "IPVS" +#define IPVS_GENL_VERSION 0x1 + +struct ip_vs_flags { + __be32 flags; + __be32 mask; +}; + +/* Generic Netlink command attributes */ +enum { + IPVS_CMD_UNSPEC = 0, + + IPVS_CMD_NEW_SERVICE, /* add service */ + IPVS_CMD_SET_SERVICE, /* modify service */ + IPVS_CMD_DEL_SERVICE, /* delete service */ + IPVS_CMD_GET_SERVICE, /* get service info */ + + IPVS_CMD_NEW_DEST, /* add destination */ + IPVS_CMD_SET_DEST, /* modify destination */ + IPVS_CMD_DEL_DEST, /* delete destination */ + IPVS_CMD_GET_DEST, /* get destination info */ + + IPVS_CMD_NEW_DAEMON, /* start sync daemon */ + IPVS_CMD_DEL_DAEMON, /* stop sync daemon */ + IPVS_CMD_GET_DAEMON, /* get sync daemon status */ + + IPVS_CMD_SET_CONFIG, /* set config settings */ + IPVS_CMD_GET_CONFIG, /* get config settings */ + + IPVS_CMD_SET_INFO, /* only used in GET_INFO reply */ + IPVS_CMD_GET_INFO, /* get general IPVS info */ + + IPVS_CMD_ZERO, /* zero all counters and stats */ + IPVS_CMD_FLUSH, /* flush services and dests */ + + __IPVS_CMD_MAX, +}; + +#define IPVS_CMD_MAX (__IPVS_CMD_MAX - 1) + +/* Attributes used in the first level of commands */ +enum { + IPVS_CMD_ATTR_UNSPEC = 0, + IPVS_CMD_ATTR_SERVICE, /* nested service attribute */ + IPVS_CMD_ATTR_DEST, /* nested destination attribute */ + IPVS_CMD_ATTR_DAEMON, /* nested sync daemon attribute */ + IPVS_CMD_ATTR_TIMEOUT_TCP, /* TCP connection timeout */ + IPVS_CMD_ATTR_TIMEOUT_TCP_FIN, /* TCP FIN wait timeout */ + IPVS_CMD_ATTR_TIMEOUT_UDP, /* UDP timeout */ + __IPVS_CMD_ATTR_MAX, +}; + +#define IPVS_CMD_ATTR_MAX (__IPVS_SVC_ATTR_MAX - 1) + +/* + * Attributes used to describe a service + * + * Used inside nested attribute IPVS_CMD_ATTR_SERVICE + */ +enum { + IPVS_SVC_ATTR_UNSPEC = 0, + IPVS_SVC_ATTR_AF, /* address family */ + IPVS_SVC_ATTR_PROTOCOL, /* virtual service protocol */ + IPVS_SVC_ATTR_ADDR, /* virtual service address */ + IPVS_SVC_ATTR_PORT, /* virtual service port */ + IPVS_SVC_ATTR_FWMARK, /* firewall mark of service */ + + IPVS_SVC_ATTR_SCHED_NAME, /* name of scheduler */ + IPVS_SVC_ATTR_FLAGS, /* virtual service flags */ + IPVS_SVC_ATTR_TIMEOUT, /* persistent timeout */ + IPVS_SVC_ATTR_NETMASK, /* persistent netmask */ + + IPVS_SVC_ATTR_STATS, /* nested attribute for service stats */ + __IPVS_SVC_ATTR_MAX, +}; + +#define IPVS_SVC_ATTR_MAX (__IPVS_SVC_ATTR_MAX - 1) + +/* + * Attributes used to describe a destination (real server) + * + * Used inside nested attribute IPVS_CMD_ATTR_DEST + */ +enum { + IPVS_DEST_ATTR_UNSPEC = 0, + IPVS_DEST_ATTR_ADDR, /* real server address */ + IPVS_DEST_ATTR_PORT, /* real server port */ + + IPVS_DEST_ATTR_FWD_METHOD, /* forwarding method */ + IPVS_DEST_ATTR_WEIGHT, /* destination weight */ + + IPVS_DEST_ATTR_U_THRESH, /* upper threshold */ + IPVS_DEST_ATTR_L_THRESH, /* lower threshold */ + + IPVS_DEST_ATTR_ACTIVE_CONNS, /* active connections */ + IPVS_DEST_ATTR_INACT_CONNS, /* inactive connections */ + IPVS_DEST_ATTR_PERSIST_CONNS, /* persistent connections */ + + IPVS_DEST_ATTR_STATS, /* nested attribute for dest stats */ + __IPVS_DEST_ATTR_MAX, +}; + +#define IPVS_DEST_ATTR_MAX (__IPVS_DEST_ATTR_MAX - 1) + +/* + * Attributes describing a sync daemon + * + * Used inside nested attribute IPVS_CMD_ATTR_DAEMON + */ +enum { + IPVS_DAEMON_ATTR_UNSPEC = 0, + IPVS_DAEMON_ATTR_STATE, /* sync daemon state (master/backup) */ + IPVS_DAEMON_ATTR_MCAST_IFN, /* multicast interface name */ + IPVS_DAEMON_ATTR_SYNC_ID, /* SyncID we belong to */ + __IPVS_DAEMON_ATTR_MAX, +}; + +#define IPVS_DAEMON_ATTR_MAX (__IPVS_DAEMON_ATTR_MAX - 1) + +/* + * Attributes used to describe service or destination entry statistics + * + * Used inside nested attributes IPVS_SVC_ATTR_STATS and IPVS_DEST_ATTR_STATS + */ +enum { + IPVS_STATS_ATTR_UNSPEC = 0, + IPVS_STATS_ATTR_CONNS, /* connections scheduled */ + IPVS_STATS_ATTR_INPKTS, /* incoming packets */ + IPVS_STATS_ATTR_OUTPKTS, /* outgoing packets */ + IPVS_STATS_ATTR_INBYTES, /* incoming bytes */ + IPVS_STATS_ATTR_OUTBYTES, /* outgoing bytes */ + + IPVS_STATS_ATTR_CPS, /* current connection rate */ + IPVS_STATS_ATTR_INPPS, /* current in packet rate */ + IPVS_STATS_ATTR_OUTPPS, /* current out packet rate */ + IPVS_STATS_ATTR_INBPS, /* current in byte rate */ + IPVS_STATS_ATTR_OUTBPS, /* current out byte rate */ + __IPVS_STATS_ATTR_MAX, +}; + +#define IPVS_STATS_ATTR_MAX (__IPVS_STATS_ATTR_MAX - 1) + +/* Attributes used in response to IPVS_CMD_GET_INFO command */ +enum { + IPVS_INFO_ATTR_UNSPEC = 0, + IPVS_INFO_ATTR_VERSION, /* IPVS version number */ + IPVS_INFO_ATTR_CONN_TAB_SIZE, /* size of connection hash table */ + __IPVS_INFO_ATTR_MAX, +}; + +#define IPVS_INFO_ATTR_MAX (__IPVS_INFO_ATTR_MAX - 1) + #endif /* _IP_VS_H */ diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 7312c3dd309f..a25ad243031d 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -683,6 +683,8 @@ extern void ip_vs_sync_conn(struct ip_vs_conn *cp); /* * IPVS rate estimator prototypes (from ip_vs_est.c) */ +extern int ip_vs_estimator_init(void); +extern void ip_vs_estimator_cleanup(void); extern void ip_vs_new_estimator(struct ip_vs_stats *stats); extern void ip_vs_kill_estimator(struct ip_vs_stats *stats); extern void ip_vs_zero_estimator(struct ip_vs_stats *stats); diff --git a/net/ipv4/ipvs/Kconfig b/net/ipv4/ipvs/Kconfig index 09d0c3f35669..2e48a7e27223 100644 --- a/net/ipv4/ipvs/Kconfig +++ b/net/ipv4/ipvs/Kconfig @@ -71,14 +71,20 @@ 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 30e85de9ffff..73a46fe1fe4c 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_core.c b/net/ipv4/ipvs/ip_vs_core.c index a7879eafc3b5..9fbf0a6d7392 100644 --- a/net/ipv4/ipvs/ip_vs_core.c +++ b/net/ipv4/ipvs/ip_vs_core.c @@ -1070,10 +1070,12 @@ 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 +1108,8 @@ 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 +1120,7 @@ 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 6379705a8dcb..ede101eeec17 100644 --- a/net/ipv4/ipvs/ip_vs_ctl.c +++ b/net/ipv4/ipvs/ip_vs_ctl.c @@ -37,6 +37,7 @@ #include <net/ip.h> #include <net/route.h> #include <net/sock.h> +#include <net/genetlink.h> #include <asm/uaccess.h> @@ -868,7 +869,8 @@ 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 +900,8 @@ 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); @@ -948,7 +951,8 @@ 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); @@ -1011,12 +1015,12 @@ 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); } @@ -2320,6 +2324,872 @@ 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->conns); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPKTS, stats->inpkts); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPKTS, stats->outpkts); + NLA_PUT_U64(skb, IPVS_STATS_ATTR_INBYTES, stats->inbytes); + NLA_PUT_U64(skb, IPVS_STATS_ATTR_OUTBYTES, stats->outbytes); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_CPS, stats->cps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPPS, stats->inpps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPPS, stats->outpps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_INBPS, stats->inbps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTBPS, stats->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, AF_INET); + + 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 *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; + + /* For now, only support IPv4 */ + if (nla_get_u16(nla_af) != AF_INET) + 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->fwmark); + else + svc = __ip_vs_service_get(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); + + strlcpy(usvc->sched_name, nla_data(nla_sched), + sizeof(usvc->sched_name)); + 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 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.fwmark); + else + return __ip_vs_service_get(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 *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 usvc; + struct ip_vs_dest_user 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.protocol, usvc.addr, usvc.port); + else + svc = __ip_vs_svc_fwm_get(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 +3204,13 @@ 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 +3245,7 @@ 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_est.c b/net/ipv4/ipvs/ip_vs_est.c index 5a20f93bd7f9..4fb620ec2086 100644 --- a/net/ipv4/ipvs/ip_vs_est.c +++ b/net/ipv4/ipvs/ip_vs_est.c @@ -124,8 +124,6 @@ void ip_vs_new_estimator(struct ip_vs_stats *stats) est->outbps = stats->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_lblc.c b/net/ipv4/ipvs/ip_vs_lblc.c index 7a6a319f544a..d2a43aa3fe4c 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; - } + unsigned hash = ip_vs_lblc_hashkey(en->addr); - /* - * Hash by destination IP address - */ - 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; @@ -484,46 +458,54 @@ 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(iph->daddr), NIPQUAD(dest->addr), ntohs(dest->port)); @@ -542,7 +524,6 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler = .n_list = LIST_HEAD_INIT(ip_vs_lblc_scheduler.n_list), .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 c234e73968a6..375a1ffb6b65 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 */ @@ -207,7 +201,6 @@ 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", @@ -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 */ @@ -256,7 +247,6 @@ 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", @@ -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; - - 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; - } + unsigned hash = ip_vs_lblcr_hashkey(en->addr); - /* - * 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; @@ -669,50 +634,78 @@ 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(iph->daddr), NIPQUAD(dest->addr), ntohs(dest->port)); @@ -731,7 +724,6 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler = .n_list = LIST_HEAD_INIT(ip_vs_lblcr_scheduler.n_list), .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 ebcdbf75ac65..2c3de1b63518 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) { @@ -99,9 +81,6 @@ 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, .schedule = ip_vs_lc_schedule, }; diff --git a/net/ipv4/ipvs/ip_vs_nq.c b/net/ipv4/ipvs/ip_vs_nq.c index 92f3a6770031..5330d5a2de14 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) { @@ -137,9 +116,6 @@ 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, .schedule = ip_vs_nq_schedule, }; diff --git a/net/ipv4/ipvs/ip_vs_proto_ah.c b/net/ipv4/ipvs/ip_vs_proto_ah_esp.c index 73e0ea87c1f5..3f9ebd7639ae 100644 --- a/net/ipv4/ipvs/ip_vs_proto_ah.c +++ b/net/ipv4/ipvs/ip_vs_proto_ah_esp.c @@ -1,5 +1,5 @@ /* - * ip_vs_proto_ah.c: AH IPSec load balancing support for IPVS + * 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> @@ -39,11 +39,11 @@ struct isakmp_hdr { 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) +ah_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; @@ -79,8 +79,8 @@ ah_conn_in_get(const struct sk_buff *skb, 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) +ah_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; @@ -112,12 +112,12 @@ ah_conn_out_get(const struct sk_buff *skb, struct ip_vs_protocol *pp, static int -ah_conn_schedule(struct sk_buff *skb, - struct ip_vs_protocol *pp, - int *verdict, struct ip_vs_conn **cpp) +ah_esp_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. + * AH/ESP is only related traffic. Pass the packet to IP stack. */ *verdict = NF_ACCEPT; return 0; @@ -125,8 +125,8 @@ ah_conn_schedule(struct sk_buff *skb, static void -ah_debug_packet(struct ip_vs_protocol *pp, const struct sk_buff *skb, - int offset, const char *msg) +ah_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; @@ -143,28 +143,29 @@ ah_debug_packet(struct ip_vs_protocol *pp, const struct sk_buff *skb, } -static void ah_init(struct ip_vs_protocol *pp) +static void ah_esp_init(struct ip_vs_protocol *pp) { /* nothing to do now */ } -static void ah_exit(struct ip_vs_protocol *pp) +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_init, - .exit = ah_exit, - .conn_schedule = ah_conn_schedule, - .conn_in_get = ah_conn_in_get, - .conn_out_get = ah_conn_out_get, + .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, @@ -172,7 +173,31 @@ struct ip_vs_protocol ip_vs_protocol_ah = { .register_app = NULL, .unregister_app = NULL, .app_conn_bind = NULL, - .debug_packet = ah_debug_packet, + .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 21d70c8ffa54..000000000000 --- 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_rr.c b/net/ipv4/ipvs/ip_vs_rr.c index 358110d17e59..f74929117534 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; @@ -96,7 +90,6 @@ static struct ip_vs_scheduler ip_vs_rr_scheduler = { .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_rr_scheduler.n_list), .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 77663d84cbd1..53f73bea66ce 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) { @@ -139,9 +118,6 @@ 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, .schedule = ip_vs_sed_schedule, }; diff --git a/net/ipv4/ipvs/ip_vs_wlc.c b/net/ipv4/ipvs/ip_vs_wlc.c index 9b0ef86bb1f7..df7ad8d74766 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) { @@ -127,9 +106,6 @@ 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, .schedule = ip_vs_wlc_schedule, }; |