// SPDX-License-Identifier: GPL-2.0 /* * IPVS An implementation of the IP virtual server support for the * LINUX operating system. IPVS is now implemented as a module * over the NetFilter framework. IPVS can be used to build a * high-performance and highly available server based on a * cluster of servers. * * Version 1, is capable of handling both version 0 and 1 messages. * Version 0 is the plain old format. * Note Version 0 receivers will just drop Ver 1 messages. * Version 1 is capable of handle IPv6, Persistence data, * time-outs, and firewall marks. * In ver.1 "ip_vs_sync_conn_options" will be sent in netw. order. * Ver. 0 can be turned on by sysctl -w net.ipv4.vs.sync_version=0 * * Definitions Message: is a complete datagram * Sync_conn: is a part of a Message * Param Data is an option to a Sync_conn. * * Authors: Wensong Zhang <[email protected]> * * ip_vs_sync: sync connection info from master load balancer to backups * through multicast * * Changes: * Alexandre Cassen : Added master & backup support at a time. * Alexandre Cassen : Added SyncID support for incoming sync * messages filtering. * Justin Ossevoort : Fix endian problem on sync message size. * Hans Schillstrom : Added Version 1: i.e. IPv6, * Persistence support, fwmark and time-out. */ #define KMSG_COMPONENT … #define pr_fmt(fmt) … #include <linux/module.h> #include <linux/slab.h> #include <linux/inetdevice.h> #include <linux/net.h> #include <linux/completion.h> #include <linux/delay.h> #include <linux/skbuff.h> #include <linux/in.h> #include <linux/igmp.h> /* for ip_mc_join_group */ #include <linux/udp.h> #include <linux/err.h> #include <linux/kthread.h> #include <linux/wait.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/unaligned.h> /* Used for ntoh_seq and hton_seq */ #include <net/ip.h> #include <net/sock.h> #include <net/ip_vs.h> #define IP_VS_SYNC_GROUP … #define IP_VS_SYNC_PORT … #define SYNC_PROTO_VER … static struct lock_class_key __ipvs_sync_key; /* * IPVS sync connection entry * Version 0, i.e. original version. */ struct ip_vs_sync_conn_v0 { … }; struct ip_vs_sync_conn_options { … }; /* Sync Connection format (sync_conn) 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Type | Protocol | Ver. | Size | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Flags | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | State | cport | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | vport | dport | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | fwmark | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | timeout (in sec.) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | ... | | IP-Addresses (v4 or v6) | | ... | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ Optional Parameters. +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Param. Type | Param. Length | Param. data | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | ... | | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | Param Type | Param. Length | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Param data | | Last Param data should be padded for 32 bit alignment | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ /* * Type 0, IPv4 sync connection format */ struct ip_vs_sync_v4 { … }; /* * Type 2 messages IPv6 */ struct ip_vs_sync_v6 { … }; ip_vs_sync_conn; /* Bits in Type field in above */ #define STYPE_INET6 … #define STYPE_F_INET6 … #define SVER_SHIFT … #define SVER_MASK … #define IPVS_OPT_SEQ_DATA … #define IPVS_OPT_PE_DATA … #define IPVS_OPT_PE_NAME … #define IPVS_OPT_PARAM … #define IPVS_OPT_F_SEQ_DATA … #define IPVS_OPT_F_PE_DATA … #define IPVS_OPT_F_PE_NAME … #define IPVS_OPT_F_PARAM … struct ip_vs_sync_thread_data { … }; /* Version 0 definition of packet sizes */ #define SIMPLE_CONN_SIZE … #define FULL_CONN_SIZE … /* The master mulitcasts messages (Datagrams) to the backup load balancers in the following format. Version 1: Note, first byte should be Zero, so ver 0 receivers will drop the packet. 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | 0 | SyncID | Size | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Count Conns | Version | Reserved, set to Zero | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | | IPVS Sync Connection (1) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | . | ~ . ~ | . | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | | IPVS Sync Connection (n) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ Version 0 Header 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Count Conns | SyncID | Size | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | IPVS Sync Connection (1) | */ /* Version 0 header */ struct ip_vs_sync_mesg_v0 { … }; /* Version 1 header */ struct ip_vs_sync_mesg { … }; ipvs_sockaddr; struct ip_vs_sync_buff { … }; /* * Copy of struct ip_vs_seq * From unaligned network order to aligned host order */ static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho) { … } /* * Copy of struct ip_vs_seq * From Aligned host order to unaligned network order */ static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no) { … } static inline struct ip_vs_sync_buff * sb_dequeue(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) { … } /* * Create a new sync buffer for Version 1 proto. */ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(struct netns_ipvs *ipvs, unsigned int len) { … } static inline void ip_vs_sync_buff_release(struct ip_vs_sync_buff *sb) { … } static inline void sb_queue_tail(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) { … } /* * Get the current sync buffer if it has been created for more * than the specified time or the specified time is zero. */ static inline struct ip_vs_sync_buff * get_curr_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms, unsigned long time) { … } static inline int select_master_thread_id(struct netns_ipvs *ipvs, struct ip_vs_conn *cp) { … } /* * Create a new sync buffer for Version 0 proto. */ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs, unsigned int len) { … } /* Check if connection is controlled by persistence */ static inline bool in_persistence(struct ip_vs_conn *cp) { … } /* Check if conn should be synced. * pkts: conn packets, use sysctl_sync_threshold to avoid packet check * - (1) sync_refresh_period: reduce sync rate. Additionally, retry * sync_retries times with period of sync_refresh_period/8 * - (2) if both sync_refresh_period and sync_period are 0 send sync only * for state changes or only once when pkts matches sync_threshold * - (3) templates: rate can be reduced only with sync_refresh_period or * with (2) */ static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { … } /* * Version 0 , could be switched in by sys_ctl. * Add an ip_vs_conn information into the current sync_buff. */ static void ip_vs_sync_conn_v0(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { … } /* * Add an ip_vs_conn information into the current sync_buff. * Called by ip_vs_in. * Sending Version 1 messages */ void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { … } /* * fill_param used by version 1 */ static inline int ip_vs_conn_fill_param_sync(struct netns_ipvs *ipvs, int af, union ip_vs_sync_conn *sc, struct ip_vs_conn_param *p, __u8 *pe_data, unsigned int pe_data_len, __u8 *pe_name, unsigned int pe_name_len) { … } /* * Connection Add / Update. * Common for version 0 and 1 reception of backup sync_conns. * Param: ... * timeout is in sec. */ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *param, unsigned int flags, unsigned int state, unsigned int protocol, unsigned int type, const union nf_inet_addr *daddr, __be16 dport, unsigned long timeout, __u32 fwmark, struct ip_vs_sync_conn_options *opt) { … } /* * Process received multicast message for Version 0 */ static void ip_vs_process_message_v0(struct netns_ipvs *ipvs, const char *buffer, const size_t buflen) { … } /* * Handle options */ static inline int ip_vs_proc_seqopt(__u8 *p, unsigned int plen, __u32 *opt_flags, struct ip_vs_sync_conn_options *opt) { … } static int ip_vs_proc_str(__u8 *p, unsigned int plen, unsigned int *data_len, __u8 **data, unsigned int maxlen, __u32 *opt_flags, __u32 flag) { … } /* * Process a Version 1 sync. connection */ static inline int ip_vs_proc_sync_conn(struct netns_ipvs *ipvs, __u8 *p, __u8 *msg_end) { … } /* * Process received multicast message and create the corresponding * ip_vs_conn entries. * Handles Version 0 & 1 */ static void ip_vs_process_message(struct netns_ipvs *ipvs, __u8 *buffer, const size_t buflen) { … } /* * Setup sndbuf (mode=1) or rcvbuf (mode=0) */ static void set_sock_size(struct sock *sk, int mode, int val) { … } /* * Setup loopback of outgoing multicasts on a sending socket */ static void set_mcast_loop(struct sock *sk, u_char loop) { … } /* * Specify TTL for outgoing multicasts on a sending socket */ static void set_mcast_ttl(struct sock *sk, u_char ttl) { … } /* Control fragmentation of messages */ static void set_mcast_pmtudisc(struct sock *sk, int val) { … } /* * Specifiy default interface for outgoing multicasts */ static int set_mcast_if(struct sock *sk, struct net_device *dev) { … } /* * Join a multicast group. * the group is specified by a class D multicast address 224.0.0.0/8 * in the in_addr structure passed in as a parameter. */ static int join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev) { … } #ifdef CONFIG_IP_VS_IPV6 static int join_mcast_group6(struct sock *sk, struct in6_addr *addr, struct net_device *dev) { … } #endif static int bind_mcastif_addr(struct socket *sock, struct net_device *dev) { … } static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, struct ipvs_sync_daemon_cfg *c, int id) { … } /* * Set up sending multicast socket over UDP */ static int make_send_sock(struct netns_ipvs *ipvs, int id, struct net_device *dev, struct socket **sock_ret) { … } /* * Set up receiving multicast socket over UDP */ static int make_receive_sock(struct netns_ipvs *ipvs, int id, struct net_device *dev, struct socket **sock_ret) { … } static int ip_vs_send_async(struct socket *sock, const char *buffer, const size_t length) { … } static int ip_vs_send_sync_msg(struct socket *sock, struct ip_vs_sync_mesg *msg) { … } static int ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen) { … } /* Wakeup the master thread for sending */ static void master_wakeup_work_handler(struct work_struct *work) { … } /* Get next buffer to send */ static inline struct ip_vs_sync_buff * next_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) { … } static int sync_thread_master(void *data) { … } static int sync_thread_backup(void *data) { … } int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, int state) { … } int stop_sync_thread(struct netns_ipvs *ipvs, int state) { … } /* * Initialize data struct for each netns */ int __net_init ip_vs_sync_net_init(struct netns_ipvs *ipvs) { … } void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs) { … }
Codebase Browser
linux