From 27e7190efd5b2f728686a8293af6d9bd34c4e562 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 May 2013 11:10:57 +0000 Subject: netfilter: xt_CT: optimize XT_CT_NOTRACK The percpu untracked ct are not currently used for XT_CT_NOTRACK. xt_ct_tg_check()/xt_ct_target() provides a single ct. Thats not optimal as the ct->ct_general.use cache line will bounce among cpus. Use the intended [1] thing : xt_ct_target() should select the percpu object. [1] Refs : commit 5bfddbd46a95c97 ("netfilter: nf_conntrack: IPS_UNTRACKED bit") commit b3c5163fe0193a7 ("netfilter: nf_conntrack: per_cpu untracking") Signed-off-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_CT.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index a60261cb0e80..da35ac06a975 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -26,6 +26,9 @@ static inline int xt_ct_target(struct sk_buff *skb, struct nf_conn *ct) if (skb->nfct != NULL) return XT_CONTINUE; + /* special case the untracked ct : we want the percpu object */ + if (!ct) + ct = nf_ct_untracked_get(); atomic_inc(&ct->ct_general.use); skb->nfct = &ct->ct_general; skb->nfctinfo = IP_CT_NEW; @@ -186,8 +189,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, int ret = -EOPNOTSUPP; if (info->flags & XT_CT_NOTRACK) { - ct = nf_ct_untracked_get(); - atomic_inc(&ct->ct_general.use); + ct = NULL; goto out; } @@ -311,7 +313,7 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par, struct nf_conn *ct = info->ct; struct nf_conn_help *help; - if (!nf_ct_is_untracked(ct)) { + if (ct && !nf_ct_is_untracked(ct)) { help = nfct_help(ct); if (help) module_put(help->helper->me); @@ -319,8 +321,8 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par, nf_ct_l3proto_module_put(par->family); xt_ct_destroy_timeout(ct); + nf_ct_put(info->ct); } - nf_ct_put(info->ct); } static void xt_ct_tg_destroy_v0(const struct xt_tgdtor_param *par) -- cgit v1.2.3 From 00028aa37098168048728acc32ab0206687f2920 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 May 2013 11:01:06 +0000 Subject: netfilter: xt_socket: use IP early demux With IP early demux added in linux-3.6, we perform TCP lookup in IP layer before iptables hooks. We can avoid doing a second lookup in xt_socket. Signed-off-by: Eric Dumazet Acked-by: David S. Miller Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_socket.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 63b2bdb59e95..02704245710e 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -107,7 +107,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, { const struct iphdr *iph = ip_hdr(skb); struct udphdr _hdr, *hp = NULL; - struct sock *sk; + struct sock *sk = skb->sk; __be32 uninitialized_var(daddr), uninitialized_var(saddr); __be16 uninitialized_var(dport), uninitialized_var(sport); u8 uninitialized_var(protocol); @@ -155,9 +155,11 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, } #endif - sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol, - saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY); - if (sk != NULL) { + if (!sk) + sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol, + saddr, daddr, sport, dport, + par->in, NFT_LOOKUP_ANY); + if (sk) { bool wildcard; bool transparent = true; @@ -173,7 +175,8 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); - xt_socket_put_sk(sk); + if (sk != skb->sk) + xt_socket_put_sk(sk); if (wildcard || !transparent) sk = NULL; @@ -260,7 +263,7 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) { struct ipv6hdr *iph = ipv6_hdr(skb); struct udphdr _hdr, *hp = NULL; - struct sock *sk; + struct sock *sk = skb->sk; struct in6_addr *daddr = NULL, *saddr = NULL; __be16 uninitialized_var(dport), uninitialized_var(sport); int thoff = 0, uninitialized_var(tproto); @@ -291,9 +294,11 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) return false; } - sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, - saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY); - if (sk != NULL) { + if (!sk) + sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, + saddr, daddr, sport, dport, + par->in, NFT_LOOKUP_ANY); + if (sk) { bool wildcard; bool transparent = true; @@ -309,7 +314,8 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); - xt_socket_put_sk(sk); + if (sk != skb->sk) + xt_socket_put_sk(sk); if (wildcard || !transparent) sk = NULL; -- cgit v1.2.3 From 6d11cfdba52af08b889fd6d3ee4212930493eb38 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 22 May 2013 22:42:36 +0000 Subject: netfilter: don't panic on error while walking through the init path Don't panic if we hit an error while adding the nf_log or pernet netfilter support, just bail out. Signed-off-by: Pablo Neira Ayuso Acked-by: Gao feng --- include/linux/netfilter.h | 2 +- net/netfilter/core.c | 21 +++++++++++++++------ net/netfilter/nf_log.c | 5 +---- net/socket.c | 4 +++- 4 files changed, 20 insertions(+), 12 deletions(-) (limited to 'net/netfilter') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0060fde3160e..de70f7b45b68 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -35,7 +35,7 @@ static inline void nf_inet_addr_mask(const union nf_inet_addr *a1, result->all[3] = a1->all[3] & mask->all[3]; } -extern void netfilter_init(void); +extern int netfilter_init(void); /* Largest hook number + 1 */ #define NF_MAX_HOOKS 8 diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 07c865a31a3d..300539db7bb1 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -302,17 +302,26 @@ static struct pernet_operations netfilter_net_ops = { .exit = netfilter_net_exit, }; -void __init netfilter_init(void) +int __init netfilter_init(void) { - int i, h; + int i, h, ret; + for (i = 0; i < ARRAY_SIZE(nf_hooks); i++) { for (h = 0; h < NF_MAX_HOOKS; h++) INIT_LIST_HEAD(&nf_hooks[i][h]); } - if (register_pernet_subsys(&netfilter_net_ops) < 0) - panic("cannot create netfilter proc entry"); + ret = register_pernet_subsys(&netfilter_net_ops); + if (ret < 0) + goto err; + + ret = netfilter_log_init(); + if (ret < 0) + goto err_pernet; - if (netfilter_log_init() < 0) - panic("cannot initialize nf_log"); + return 0; +err_pernet: + unregister_pernet_subsys(&netfilter_net_ops); +err: + return ret; } diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 388656d5a9ec..bd5474adcabc 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -368,10 +368,7 @@ static int __net_init nf_log_net_init(struct net *net) return 0; out_sysctl: - /* For init_net: errors will trigger panic, don't unroll on error. */ - if (!net_eq(net, &init_net)) - remove_proc_entry("nf_log", net->nf.proc_netfilter); - + remove_proc_entry("nf_log", net->nf.proc_netfilter); return ret; } diff --git a/net/socket.c b/net/socket.c index 6b94633ca61d..734194d36242 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2612,7 +2612,9 @@ static int __init sock_init(void) */ #ifdef CONFIG_NETFILTER - netfilter_init(); + err = netfilter_init(); + if (err) + goto out; #endif #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING -- cgit v1.2.3 From a38e5e230e3f4e7bc9195d3e7a81567c888257ca Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 22 May 2013 14:50:32 +0900 Subject: ipvs: use cond_resched_rcu() helper when walking connections This avoids the situation where walking of a large number of connections may prevent scheduling for a long time while also avoiding excessive calls to rcu_read_unlock() and rcu_read_lock(). Note that in the case of !CONFIG_PREEMPT_RCU this will add a call to cond_resched(). Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Acked-by: Peter Zijlstra Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_conn.c | 23 ++++++++--------------- 1 file changed, 8 insertions(+), 15 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index a083bda322b6..c8c52a98590b 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -975,8 +975,7 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) return cp; } } - rcu_read_unlock(); - rcu_read_lock(); + cond_resched_rcu(); } return NULL; @@ -1015,8 +1014,7 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) iter->l = &ip_vs_conn_tab[idx]; return cp; } - rcu_read_unlock(); - rcu_read_lock(); + cond_resched_rcu(); } iter->l = NULL; return NULL; @@ -1206,17 +1204,13 @@ void ip_vs_random_dropentry(struct net *net) int idx; struct ip_vs_conn *cp, *cp_c; + rcu_read_lock(); /* * Randomly scan 1/32 of the whole table every second */ for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) { unsigned int hash = net_random() & ip_vs_conn_tab_mask; - /* - * Lock is actually needed in this loop. - */ - rcu_read_lock(); - hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) /* connection template */ @@ -1252,8 +1246,9 @@ void ip_vs_random_dropentry(struct net *net) __ip_vs_conn_put(cp); } } - rcu_read_unlock(); + cond_resched_rcu(); } + rcu_read_unlock(); } @@ -1267,11 +1262,8 @@ static void ip_vs_conn_flush(struct net *net) struct netns_ipvs *ipvs = net_ipvs(net); flush_again: + rcu_read_lock(); for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { - /* - * Lock is actually needed in this loop. - */ - rcu_read_lock(); hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { if (!ip_vs_conn_net_eq(cp, net)) @@ -1286,8 +1278,9 @@ flush_again: __ip_vs_conn_put(cp); } } - rcu_read_unlock(); + cond_resched_rcu(); } + rcu_read_unlock(); /* the counter may be not NULL, because maybe some conn entries are run by slow timer handler or unhashed but still referred */ -- cgit v1.2.3 From 079956742452494326081349a66942654498cafa Mon Sep 17 00:00:00 2001 From: Zhang Yanfei Date: Mon, 29 Apr 2013 11:55:10 -0700 Subject: ipvs: change type of netns_ipvs->sysctl_sync_qlen_max This member of struct netns_ipvs is calculated from nr_free_buffer_pages so change its type to unsigned long in case of overflow. Also, type of its related proc var sync_qlen_max and the return type of function sysctl_sync_qlen_max() should be changed to unsigned long, too. Besides, the type of ipvs_master_sync_state->sync_queue_len should be changed to unsigned long accordingly. Signed-off-by: Zhang Yanfei Cc: Julian Anastasov Cc: David Miller Signed-off-by: Andrew Morton Signed-off-by: Simon Horman --- include/net/ip_vs.h | 8 ++++---- net/netfilter/ipvs/ip_vs_ctl.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 4c062ccff9aa..4405886980c7 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -905,7 +905,7 @@ struct ip_vs_app { struct ipvs_master_sync_state { struct list_head sync_queue; struct ip_vs_sync_buff *sync_buff; - int sync_queue_len; + unsigned long sync_queue_len; unsigned int sync_queue_delay; struct task_struct *master_thread; struct delayed_work master_wakeup_work; @@ -998,7 +998,7 @@ struct netns_ipvs { int sysctl_snat_reroute; int sysctl_sync_ver; int sysctl_sync_ports; - int sysctl_sync_qlen_max; + unsigned long sysctl_sync_qlen_max; int sysctl_sync_sock_size; int sysctl_cache_bypass; int sysctl_expire_nodest_conn; @@ -1085,7 +1085,7 @@ static inline int sysctl_sync_ports(struct netns_ipvs *ipvs) return ACCESS_ONCE(ipvs->sysctl_sync_ports); } -static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs) +static inline unsigned long sysctl_sync_qlen_max(struct netns_ipvs *ipvs) { return ipvs->sysctl_sync_qlen_max; } @@ -1138,7 +1138,7 @@ static inline int sysctl_sync_ports(struct netns_ipvs *ipvs) return 1; } -static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs) +static inline unsigned long sysctl_sync_qlen_max(struct netns_ipvs *ipvs) { return IPVS_SYNC_QLEN_MAX; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5b142fb16480..70146496e73a 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1716,9 +1716,9 @@ static struct ctl_table vs_vars[] = { }, { .procname = "sync_qlen_max", - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_doulongvec_minmax, }, { .procname = "sync_sock_size", -- cgit v1.2.3 From 9d5242b19269432ea388d766312ed49f184f83fd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 25 May 2013 01:46:10 +0000 Subject: netfilter: nfnetlink_queue: avoid peer_portid test The portid is set to NETLINK_CB(skb).portid at create time. The run-time check will always be false. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_queue_core.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 2e0e835baf72..cff4449f01d2 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -509,10 +509,6 @@ __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, } spin_lock_bh(&queue->lock); - if (!queue->peer_portid) { - err = -EINVAL; - goto err_out_free_nskb; - } if (queue->queue_total >= queue->queue_maxlen) { if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { failopen = 1; -- cgit v1.2.3 From 4e7dba99c9e606e304f104ce4071d8b5ba93957e Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Wed, 22 May 2013 14:59:10 +0200 Subject: netfilter: Implement RFC 1123 for FTP conntrack The FTP conntrack code currently only accepts the following format for the 227 response for PASV: 227 Entering Passive Mode (148,100,81,40,31,161). It doesn't accept the following format from an obscure server: 227 Data transfer will passively listen to 67,218,99,134,50,144 From RFC 1123: The format of the 227 reply to a PASV command is not well standardized. In particular, an FTP client cannot assume that the parentheses shown on page 40 of RFC-959 will be present (and in fact, Figure 3 on page 43 omits them). Therefore, a User-FTP program that interprets the PASV reply must scan the reply for the first digit of the host and port numbers. This patch adds support for the RFC 1123 clarification by: - Allowing a search filter to specify NUL as the terminator so that try_number will return successfully if the array of numbers has been filled when an unexpected character is encountered. - Using space as the separator for the 227 reply and then scanning for the first digit of the number sequence. The number sequence is parsed out using the existing try_rfc959 but with a NUL terminator. References: https://bugzilla.novell.com/show_bug.cgi?id=466279 References: http://bugzilla.netfilter.org/show_bug.cgi?id=574 Reported-by: Mark Post Signed-off-by: Jeff Mahoney Signed-off-by: Jiri Slaby Cc: Pablo Neira Ayuso Cc: Patrick McHardy Cc: "David S. Miller" Cc: netfilter-devel@vger.kernel.org Cc: netfilter@vger.kernel.org Cc: coreteam@netfilter.org Cc: netdev@vger.kernel.org Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_ftp.c | 73 +++++++++++++++++++++++++++++----------- 1 file changed, 54 insertions(+), 19 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 6b217074237b..b8a0924064ef 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -55,10 +55,14 @@ unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb, struct nf_conntrack_expect *exp); EXPORT_SYMBOL_GPL(nf_nat_ftp_hook); -static int try_rfc959(const char *, size_t, struct nf_conntrack_man *, char); -static int try_eprt(const char *, size_t, struct nf_conntrack_man *, char); +static int try_rfc959(const char *, size_t, struct nf_conntrack_man *, + char, unsigned int *); +static int try_rfc1123(const char *, size_t, struct nf_conntrack_man *, + char, unsigned int *); +static int try_eprt(const char *, size_t, struct nf_conntrack_man *, + char, unsigned int *); static int try_epsv_response(const char *, size_t, struct nf_conntrack_man *, - char); + char, unsigned int *); static struct ftp_search { const char *pattern; @@ -66,7 +70,7 @@ static struct ftp_search { char skip; char term; enum nf_ct_ftp_type ftptype; - int (*getnum)(const char *, size_t, struct nf_conntrack_man *, char); + int (*getnum)(const char *, size_t, struct nf_conntrack_man *, char, unsigned int *); } search[IP_CT_DIR_MAX][2] = { [IP_CT_DIR_ORIGINAL] = { { @@ -90,10 +94,8 @@ static struct ftp_search { { .pattern = "227 ", .plen = sizeof("227 ") - 1, - .skip = '(', - .term = ')', .ftptype = NF_CT_FTP_PASV, - .getnum = try_rfc959, + .getnum = try_rfc1123, }, { .pattern = "229 ", @@ -132,8 +134,9 @@ static int try_number(const char *data, size_t dlen, u_int32_t array[], i++; else { /* Unexpected character; true if it's the - terminator and we're finished. */ - if (*data == term && i == array_size - 1) + terminator (or we don't care about one) + and we're finished. */ + if ((*data == term || !term) && i == array_size - 1) return len; pr_debug("Char %u (got %u nums) `%u' unexpected\n", @@ -148,7 +151,8 @@ static int try_number(const char *data, size_t dlen, u_int32_t array[], /* Returns 0, or length of numbers: 192,168,1,1,5,6 */ static int try_rfc959(const char *data, size_t dlen, - struct nf_conntrack_man *cmd, char term) + struct nf_conntrack_man *cmd, char term, + unsigned int *offset) { int length; u_int32_t array[6]; @@ -163,6 +167,33 @@ static int try_rfc959(const char *data, size_t dlen, return length; } +/* + * From RFC 1123: + * The format of the 227 reply to a PASV command is not + * well standardized. In particular, an FTP client cannot + * assume that the parentheses shown on page 40 of RFC-959 + * will be present (and in fact, Figure 3 on page 43 omits + * them). Therefore, a User-FTP program that interprets + * the PASV reply must scan the reply for the first digit + * of the host and port numbers. + */ +static int try_rfc1123(const char *data, size_t dlen, + struct nf_conntrack_man *cmd, char term, + unsigned int *offset) +{ + int i; + for (i = 0; i < dlen; i++) + if (isdigit(data[i])) + break; + + if (i == dlen) + return 0; + + *offset += i; + + return try_rfc959(data + i, dlen - i, cmd, 0, offset); +} + /* Grab port: number up to delimiter */ static int get_port(const char *data, int start, size_t dlen, char delim, __be16 *port) @@ -191,7 +222,7 @@ static int get_port(const char *data, int start, size_t dlen, char delim, /* Returns 0, or length of numbers: |1|132.235.1.2|6275| or |2|3ffe::1|6275| */ static int try_eprt(const char *data, size_t dlen, struct nf_conntrack_man *cmd, - char term) + char term, unsigned int *offset) { char delim; int length; @@ -239,7 +270,8 @@ static int try_eprt(const char *data, size_t dlen, struct nf_conntrack_man *cmd, /* Returns 0, or length of numbers: |||6446| */ static int try_epsv_response(const char *data, size_t dlen, - struct nf_conntrack_man *cmd, char term) + struct nf_conntrack_man *cmd, char term, + unsigned int *offset) { char delim; @@ -261,9 +293,10 @@ static int find_pattern(const char *data, size_t dlen, unsigned int *numlen, struct nf_conntrack_man *cmd, int (*getnum)(const char *, size_t, - struct nf_conntrack_man *, char)) + struct nf_conntrack_man *, char, + unsigned int *)) { - size_t i; + size_t i = plen; pr_debug("find_pattern `%s': dlen = %Zu\n", pattern, dlen); if (dlen == 0) @@ -293,16 +326,18 @@ static int find_pattern(const char *data, size_t dlen, pr_debug("Pattern matches!\n"); /* Now we've found the constant string, try to skip to the 'skip' character */ - for (i = plen; data[i] != skip; i++) - if (i == dlen - 1) return -1; + if (skip) { + for (i = plen; data[i] != skip; i++) + if (i == dlen - 1) return -1; - /* Skip over the last character */ - i++; + /* Skip over the last character */ + i++; + } pr_debug("Skipped up to `%c'!\n", skip); *numoff = i; - *numlen = getnum(data + i, dlen - i, cmd, term); + *numlen = getnum(data + i, dlen - i, cmd, term, numoff); if (!*numlen) return -1; -- cgit v1.2.3 From 351638e7deeed2ec8ce451b53d33921b3da68f83 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 28 May 2013 01:30:21 +0000 Subject: net: pass info struct via netdevice notifier So far, only net_device * could be passed along with netdevice notifier event. This patch provides a possibility to pass custom structure able to provide info that event listener needs to know. Signed-off-by: Jiri Pirko v2->v3: fix typo on simeth shortened dev_getter shortened notifier_info struct name v1->v2: fix notifier_call parameter in call_netdevice_notifier() Signed-off-by: David S. Miller --- arch/ia64/hp/sim/simeth.c | 2 +- arch/mips/txx9/generic/setup_tx4939.c | 3 +- drivers/infiniband/core/cma.c | 4 +- drivers/infiniband/hw/mlx4/main.c | 2 +- drivers/net/bonding/bond_main.c | 2 +- drivers/net/can/led.c | 4 +- drivers/net/ethernet/broadcom/cnic.c | 2 +- drivers/net/ethernet/marvell/skge.c | 2 +- drivers/net/ethernet/marvell/sky2.c | 2 +- .../net/ethernet/qlogic/netxen/netxen_nic_main.c | 2 +- drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 2 +- drivers/net/ethernet/sfc/efx.c | 2 +- drivers/net/hamradio/bpqether.c | 7 +-- drivers/net/macvlan.c | 2 +- drivers/net/macvtap.c | 2 +- drivers/net/netconsole.c | 5 +- drivers/net/ppp/pppoe.c | 2 +- drivers/net/team/team.c | 2 +- drivers/net/wan/dlci.c | 2 +- drivers/net/wan/hdlc.c | 2 +- drivers/net/wan/lapbether.c | 2 +- drivers/scsi/fcoe/fcoe.c | 2 +- drivers/scsi/fcoe/fcoe_transport.c | 2 +- drivers/staging/csr/netdev.c | 2 +- drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.c | 2 +- drivers/staging/ft1000/ft1000-usb/ft1000_proc.c | 2 +- drivers/staging/silicom/bpctl_mod.c | 2 +- include/linux/netdevice.h | 13 +++++ net/8021q/vlan.c | 2 +- net/appletalk/aarp.c | 2 +- net/appletalk/ddp.c | 2 +- net/atm/clip.c | 4 +- net/atm/mpc.c | 6 +-- net/ax25/af_ax25.c | 6 +-- net/batman-adv/hard-interface.c | 2 +- net/bridge/br_notify.c | 2 +- net/caif/caif_dev.c | 4 +- net/caif/caif_usb.c | 4 +- net/can/af_can.c | 4 +- net/can/bcm.c | 4 +- net/can/gw.c | 4 +- net/can/raw.c | 4 +- net/core/dev.c | 56 ++++++++++++++++++---- net/core/drop_monitor.c | 4 +- net/core/dst.c | 2 +- net/core/fib_rules.c | 4 +- net/core/netprio_cgroup.c | 2 +- net/core/pktgen.c | 2 +- net/core/rtnetlink.c | 2 +- net/decnet/af_decnet.c | 4 +- net/ieee802154/6lowpan.c | 5 +- net/ipv4/arp.c | 2 +- net/ipv4/devinet.c | 2 +- net/ipv4/fib_frontend.c | 2 +- net/ipv4/ipmr.c | 2 +- net/ipv4/netfilter/ipt_MASQUERADE.c | 2 +- net/ipv6/addrconf.c | 4 +- net/ipv6/ip6mr.c | 2 +- net/ipv6/ndisc.c | 2 +- net/ipv6/netfilter/ip6t_MASQUERADE.c | 2 +- net/ipv6/route.c | 4 +- net/ipx/af_ipx.c | 2 +- net/iucv/af_iucv.c | 2 +- net/mac80211/iface.c | 5 +- net/netfilter/ipvs/ip_vs_ctl.c | 4 +- net/netfilter/nfnetlink_queue_core.c | 2 +- net/netfilter/xt_TEE.c | 2 +- net/netlabel/netlabel_unlabeled.c | 7 ++- net/netrom/af_netrom.c | 2 +- net/openvswitch/dp_notify.c | 2 +- net/packet/af_packet.c | 5 +- net/phonet/pn_dev.c | 4 +- net/rose/af_rose.c | 6 +-- net/sched/act_mirred.c | 2 +- net/tipc/eth_media.c | 4 +- net/tipc/ib_media.c | 4 +- net/wireless/core.c | 5 +- net/x25/af_x25.c | 2 +- net/xfrm/xfrm_policy.c | 2 +- security/selinux/netif.c | 2 +- 80 files changed, 172 insertions(+), 127 deletions(-) (limited to 'net/netfilter') diff --git a/arch/ia64/hp/sim/simeth.c b/arch/ia64/hp/sim/simeth.c index c13064e422df..d1b04c4c95e3 100644 --- a/arch/ia64/hp/sim/simeth.c +++ b/arch/ia64/hp/sim/simeth.c @@ -268,7 +268,7 @@ static __inline__ int dev_is_ethdev(struct net_device *dev) static int simeth_device_event(struct notifier_block *this,unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct simeth_local *local; struct in_device *in_dev; struct in_ifaddr **ifap = NULL; diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c index 729a50991780..b7eccbd17bf7 100644 --- a/arch/mips/txx9/generic/setup_tx4939.c +++ b/arch/mips/txx9/generic/setup_tx4939.c @@ -331,7 +331,8 @@ static int tx4939_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + if (event == NETDEV_CHANGE && netif_carrier_ok(dev)) { __u64 bit = 0; if (dev->irq == TXX9_IRQ_BASE + TX4939_IR_ETH(0)) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 71c2c7116802..34fbc2f60a09 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3269,9 +3269,9 @@ static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id } static int cma_netdev_callback(struct notifier_block *self, unsigned long event, - void *ctx) + void *ptr) { - struct net_device *ndev = (struct net_device *)ctx; + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct cma_device *cma_dev; struct rdma_id_private *id_priv; int ret = NOTIFY_DONE; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 23d734349d8e..a188d3178559 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1161,7 +1161,7 @@ static void netdev_removed(struct mlx4_ib_dev *dev, int port) static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct mlx4_ib_dev *ibdev; struct net_device *oldnd; struct mlx4_ib_iboe *iboe; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 29b846cbfb48..f4489d65bf33 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3277,7 +3277,7 @@ static int bond_slave_netdev_event(unsigned long event, static int bond_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *event_dev = (struct net_device *)ptr; + struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); pr_debug("event_dev: %s, event: %lx\n", event_dev ? event_dev->name : "None", diff --git a/drivers/net/can/led.c b/drivers/net/can/led.c index f27fca65dc4a..a3d99a8fd2d1 100644 --- a/drivers/net/can/led.c +++ b/drivers/net/can/led.c @@ -88,9 +88,9 @@ EXPORT_SYMBOL_GPL(devm_can_led_init); /* NETDEV rename notifier to rename the associated led triggers too */ static int can_led_notifier(struct notifier_block *nb, unsigned long msg, - void *data) + void *ptr) { - struct net_device *netdev = data; + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct can_priv *priv = safe_candev_priv(netdev); char name[CAN_LED_NAME_SZ]; diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 6b0dc131b20e..d78d4cf140ed 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -5622,7 +5622,7 @@ static void cnic_rcv_netevent(struct cnic_local *cp, unsigned long event, static int cnic_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *netdev = ptr; + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct cnic_dev *dev; int new_dev = 0; diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 171f4b3dda07..c896079728e1 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -3706,7 +3706,7 @@ static const struct file_operations skge_debug_fops = { static int skge_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct skge_port *skge; struct dentry *d; diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index d175bbd3ffd3..e09a8c6f8536 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4642,7 +4642,7 @@ static const struct file_operations sky2_debug_fops = { static int sky2_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct sky2_port *sky2 = netdev_priv(dev); if (dev->netdev_ops->ndo_open != sky2_open || !sky2_debug) diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index af951f343ff6..51e13d92761e 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -3311,7 +3311,7 @@ static int netxen_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netxen_adapter *adapter; - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net_device *orig_dev = dev; struct net_device *slave; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index da82f2eb73b4..6bb56d43614b 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -3530,7 +3530,7 @@ static int qlcnic_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct qlcnic_adapter *adapter; - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); recheck: if (dev == NULL) diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 39e4cb39de29..46cc11d5e205 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2120,7 +2120,7 @@ static void efx_update_name(struct efx_nic *efx) static int efx_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *net_dev = ptr; + struct net_device *net_dev = netdev_notifier_info_to_dev(ptr); if (net_dev->netdev_ops == &efx_netdev_ops && event == NETDEV_CHANGENAME) diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 02de6c891670..f91bf0ddf031 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -103,7 +103,7 @@ static struct packet_type bpq_packet_type __read_mostly = { }; static struct notifier_block bpq_dev_notifier = { - .notifier_call =bpq_device_event, + .notifier_call = bpq_device_event, }; @@ -544,9 +544,10 @@ static void bpq_free_device(struct net_device *ndev) /* * Handle device status changes. */ -static int bpq_device_event(struct notifier_block *this,unsigned long event, void *ptr) +static int bpq_device_event(struct notifier_block *this, + unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 1c502bb0c916..edfddc5f61b4 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -921,7 +921,7 @@ static struct rtnl_link_ops macvlan_link_ops = { static int macvlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvlan_dev *vlan, *next; struct macvlan_port *port; LIST_HEAD(list_kill); diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 59e9605de316..68efb91a5633 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -1053,7 +1053,7 @@ EXPORT_SYMBOL_GPL(macvtap_get_socket); static int macvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvlan_dev *vlan; struct device *classdev; dev_t devt; diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 59ac143dec25..1d1d0a12765c 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -653,12 +653,11 @@ static struct configfs_subsystem netconsole_subsys = { /* Handle network interface device notifications */ static int netconsole_netdev_event(struct notifier_block *this, - unsigned long event, - void *ptr) + unsigned long event, void *ptr) { unsigned long flags; struct netconsole_target *nt; - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); bool stopped = false; if (!(event == NETDEV_CHANGENAME || event == NETDEV_UNREGISTER || diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index bb07ba94c3aa..5f66e30d9823 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -338,7 +338,7 @@ static void pppoe_flush_dev(struct net_device *dev) static int pppoe_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* Only look at sockets that are using this specific device. */ switch (event) { diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 7c43261975bd..9273f48a512b 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2647,7 +2647,7 @@ static void team_port_change_check(struct team_port *port, bool linkup) static int team_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *) ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct team_port *port; port = team_port_get_rtnl(dev); diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c index 147614ed86aa..70ac59929f80 100644 --- a/drivers/net/wan/dlci.c +++ b/drivers/net/wan/dlci.c @@ -477,7 +477,7 @@ static void dlci_setup(struct net_device *dev) static int dlci_dev_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *) ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev_net(dev) != &init_net) return NOTIFY_DONE; diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c index a0a932c63d0a..9c33ca918e19 100644 --- a/drivers/net/wan/hdlc.c +++ b/drivers/net/wan/hdlc.c @@ -99,7 +99,7 @@ static inline void hdlc_proto_stop(struct net_device *dev) static int hdlc_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); hdlc_device *hdlc; unsigned long flags; int on; diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index a73b49eb87e3..a33a46fa88dd 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -370,7 +370,7 @@ static int lapbeth_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct lapbethdev *lapbeth; - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev_net(dev) != &init_net) return NOTIFY_DONE; diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index 292b24f9bf93..ee721b6cbcdf 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -1975,7 +1975,7 @@ static int fcoe_device_notification(struct notifier_block *notifier, { struct fcoe_ctlr_device *cdev; struct fc_lport *lport = NULL; - struct net_device *netdev = ptr; + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct fcoe_ctlr *ctlr; struct fcoe_interface *fcoe; struct fcoe_port *port; diff --git a/drivers/scsi/fcoe/fcoe_transport.c b/drivers/scsi/fcoe/fcoe_transport.c index f3a5a53e8631..01adbe0ec53b 100644 --- a/drivers/scsi/fcoe/fcoe_transport.c +++ b/drivers/scsi/fcoe/fcoe_transport.c @@ -704,7 +704,7 @@ static struct net_device *fcoe_if_to_netdev(const char *buffer) static int libfcoe_device_notification(struct notifier_block *notifier, ulong event, void *ptr) { - struct net_device *netdev = ptr; + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_UNREGISTER: diff --git a/drivers/staging/csr/netdev.c b/drivers/staging/csr/netdev.c index a0177d998978..d49cdf84a496 100644 --- a/drivers/staging/csr/netdev.c +++ b/drivers/staging/csr/netdev.c @@ -2891,7 +2891,7 @@ void uf_net_get_name(struct net_device *dev, char *name, int len) */ static int uf_netdev_event(struct notifier_block *notif, unsigned long event, void* ptr) { - struct net_device *netdev = ptr; + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); netInterface_priv_t *interfacePriv = (netInterface_priv_t *)netdev_priv(netdev); unifi_priv_t *priv = NULL; static const CsrWifiMacAddress broadcast_address = {{0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}}; diff --git a/drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.c b/drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.c index 94e426e4d98b..b2330f1df7e7 100644 --- a/drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.c +++ b/drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.c @@ -164,7 +164,7 @@ static const struct file_operations ft1000_proc_fops = { static int ft1000NotifyProc(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ft1000_info *info; info = netdev_priv(dev); diff --git a/drivers/staging/ft1000/ft1000-usb/ft1000_proc.c b/drivers/staging/ft1000/ft1000-usb/ft1000_proc.c index eca6f0292b4b..5ead942be680 100644 --- a/drivers/staging/ft1000/ft1000-usb/ft1000_proc.c +++ b/drivers/staging/ft1000/ft1000-usb/ft1000_proc.c @@ -166,7 +166,7 @@ static const struct file_operations ft1000_proc_fops = { static int ft1000NotifyProc(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ft1000_info *info; struct proc_dir_entry *ft1000_proc_file; diff --git a/drivers/staging/silicom/bpctl_mod.c b/drivers/staging/silicom/bpctl_mod.c index b7e570ccb759..c8ddb99e8526 100644 --- a/drivers/staging/silicom/bpctl_mod.c +++ b/drivers/staging/silicom/bpctl_mod.c @@ -133,7 +133,7 @@ static unsigned long str_to_hex(char *p); static int bp_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); static bpctl_dev_t *pbpctl_dev = NULL, *pbpctl_dev_m = NULL; int dev_num = 0, ret = 0, ret_d = 0, time_left = 0; /* printk("BP_PROC_SUPPORT event =%d %s %d\n", event,dev->name, dev->ifindex ); */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6b2bb460d1d7..13a34848b5e1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1599,6 +1599,19 @@ struct packet_offload { extern int register_netdevice_notifier(struct notifier_block *nb); extern int unregister_netdevice_notifier(struct notifier_block *nb); + +struct netdev_notifier_info { + struct net_device *dev; +}; + +static inline struct net_device * +netdev_notifier_info_to_dev(const struct netdev_notifier_info *info) +{ + return info->dev; +} + +extern int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev, + struct netdev_notifier_info *info); extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 9424f3718ea7..2fb2d88e8c2e 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -341,7 +341,7 @@ static void __vlan_device_event(struct net_device *dev, unsigned long event) static int vlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vlan_group *grp; struct vlan_info *vlan_info; int i, flgs; diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 173a2e82f486..690356fa52b9 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -332,7 +332,7 @@ static void aarp_expire_timeout(unsigned long unused) static int aarp_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); int ct; if (!net_eq(dev_net(dev), &init_net)) diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index ef12839a7cfe..7fee50d637f9 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -644,7 +644,7 @@ static inline void atalk_dev_down(struct net_device *dev) static int ddp_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/atm/clip.c b/net/atm/clip.c index 8ae3a7879335..cce241eb01d9 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -539,9 +539,9 @@ static int clip_create(int number) } static int clip_device_event(struct notifier_block *this, unsigned long event, - void *arg) + void *ptr) { - struct net_device *dev = arg; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/atm/mpc.c b/net/atm/mpc.c index d4cc1be5c364..3af12755cd04 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -998,14 +998,12 @@ int msg_to_mpoad(struct k_message *mesg, struct mpoa_client *mpc) } static int mpoa_event_listener(struct notifier_block *mpoa_notifier, - unsigned long event, void *dev_ptr) + unsigned long event, void *ptr) { - struct net_device *dev; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct mpoa_client *mpc; struct lec_priv *priv; - dev = dev_ptr; - if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index e277e38f736b..4b4d2b779ec1 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -111,9 +111,9 @@ again: * Handle device status changes. */ static int ax25_device_event(struct notifier_block *this, unsigned long event, - void *ptr) + void *ptr) { - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; @@ -1974,7 +1974,7 @@ static struct packet_type ax25_packet_type __read_mostly = { }; static struct notifier_block ax25_dev_notifier = { - .notifier_call =ax25_device_event, + .notifier_call = ax25_device_event, }; static int __init ax25_init(void) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 522243aff2f3..b6504eac0ed8 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -595,7 +595,7 @@ void batadv_hardif_remove_interfaces(void) static int batadv_hard_if_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *net_dev = ptr; + struct net_device *net_dev = netdev_notifier_info_to_dev(ptr); struct batadv_hard_iface *hard_iface; struct batadv_hard_iface *primary_if = NULL; struct batadv_priv *bat_priv; diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c index 1644b3e1f947..3a3f371b2841 100644 --- a/net/bridge/br_notify.c +++ b/net/bridge/br_notify.c @@ -31,7 +31,7 @@ struct notifier_block br_device_notifier = { */ static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; bool changed_addr; diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 1f9ece1a9c34..4dca159435cf 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -352,9 +352,9 @@ EXPORT_SYMBOL(caif_enroll_dev); /* notify Caif of device events */ static int caif_device_notify(struct notifier_block *me, unsigned long what, - void *arg) + void *ptr) { - struct net_device *dev = arg; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct caif_device_entry *caifd = NULL; struct caif_dev_common *caifdev; struct cfcnfg *cfg; diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index 942e00a425fd..75ed04b78fa4 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -121,9 +121,9 @@ static struct packet_type caif_usb_type __read_mostly = { }; static int cfusbl_device_notify(struct notifier_block *me, unsigned long what, - void *arg) + void *ptr) { - struct net_device *dev = arg; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct caif_dev_common common; struct cflayer *layer, *link_support; struct usbnet *usbnet; diff --git a/net/can/af_can.c b/net/can/af_can.c index c4e50852c9f4..3ab8dd2e1282 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -794,9 +794,9 @@ EXPORT_SYMBOL(can_proto_unregister); * af_can notifier to create/remove CAN netdevice specific structs */ static int can_notifier(struct notifier_block *nb, unsigned long msg, - void *data) + void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dev_rcv_lists *d; if (!net_eq(dev_net(dev), &init_net)) diff --git a/net/can/bcm.c b/net/can/bcm.c index 8f113e6ff327..46f20bfafc0e 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1350,9 +1350,9 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock, * notification handler for netdevice status changes */ static int bcm_notifier(struct notifier_block *nb, unsigned long msg, - void *data) + void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct bcm_sock *bo = container_of(nb, struct bcm_sock, notifier); struct sock *sk = &bo->sk; struct bcm_op *op; diff --git a/net/can/gw.c b/net/can/gw.c index 3ee690e8c7d3..2f291f961a17 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -445,9 +445,9 @@ static inline void cgw_unregister_filter(struct cgw_job *gwj) } static int cgw_notifier(struct notifier_block *nb, - unsigned long msg, void *data) + unsigned long msg, void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/can/raw.c b/net/can/raw.c index 1085e65f848e..641e1c895123 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -239,9 +239,9 @@ static int raw_enable_allfilters(struct net_device *dev, struct sock *sk) } static int raw_notifier(struct notifier_block *nb, - unsigned long msg, void *data) + unsigned long msg, void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct raw_sock *ro = container_of(nb, struct raw_sock, notifier); struct sock *sk = &ro->sk; diff --git a/net/core/dev.c b/net/core/dev.c index 5f747974ac58..54fce6006a83 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1391,6 +1391,20 @@ void dev_disable_lro(struct net_device *dev) } EXPORT_SYMBOL(dev_disable_lro); +static void netdev_notifier_info_init(struct netdev_notifier_info *info, + struct net_device *dev) +{ + info->dev = dev; +} + +static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, + struct net_device *dev) +{ + struct netdev_notifier_info info; + + netdev_notifier_info_init(&info, dev); + return nb->notifier_call(nb, val, &info); +} static int dev_boot_phase = 1; @@ -1423,7 +1437,7 @@ int register_netdevice_notifier(struct notifier_block *nb) goto unlock; for_each_net(net) { for_each_netdev(net, dev) { - err = nb->notifier_call(nb, NETDEV_REGISTER, dev); + err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); err = notifier_to_errno(err); if (err) goto rollback; @@ -1431,7 +1445,7 @@ int register_netdevice_notifier(struct notifier_block *nb) if (!(dev->flags & IFF_UP)) continue; - nb->notifier_call(nb, NETDEV_UP, dev); + call_netdevice_notifier(nb, NETDEV_UP, dev); } } @@ -1447,10 +1461,11 @@ rollback: goto outroll; if (dev->flags & IFF_UP) { - nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); - nb->notifier_call(nb, NETDEV_DOWN, dev); + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); } - nb->notifier_call(nb, NETDEV_UNREGISTER, dev); + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } } @@ -1488,10 +1503,11 @@ int unregister_netdevice_notifier(struct notifier_block *nb) for_each_net(net) { for_each_netdev(net, dev) { if (dev->flags & IFF_UP) { - nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); - nb->notifier_call(nb, NETDEV_DOWN, dev); + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); } - nb->notifier_call(nb, NETDEV_UNREGISTER, dev); + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } } unlock: @@ -1500,6 +1516,25 @@ unlock: } EXPORT_SYMBOL(unregister_netdevice_notifier); +/** + * call_netdevice_notifiers_info - call all network notifier blocks + * @val: value passed unmodified to notifier function + * @dev: net_device pointer passed unmodified to notifier function + * @info: notifier information data + * + * Call all network notifier blocks. Parameters and return value + * are as for raw_notifier_call_chain(). + */ + +int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev, + struct netdev_notifier_info *info) +{ + ASSERT_RTNL(); + netdev_notifier_info_init(info, dev); + return raw_notifier_call_chain(&netdev_chain, val, info); +} +EXPORT_SYMBOL(call_netdevice_notifiers_info); + /** * call_netdevice_notifiers - call all network notifier blocks * @val: value passed unmodified to notifier function @@ -1511,8 +1546,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { - ASSERT_RTNL(); - return raw_notifier_call_chain(&netdev_chain, val, dev); + struct netdev_notifier_info info; + + return call_netdevice_notifiers_info(val, dev, &info); } EXPORT_SYMBOL(call_netdevice_notifiers); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index d23b6682f4e9..5e78d44333b9 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -295,9 +295,9 @@ static int net_dm_cmd_trace(struct sk_buff *skb, } static int dropmon_net_event(struct notifier_block *ev_block, - unsigned long event, void *ptr) + unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dm_hw_stat_delta *new_stat = NULL; struct dm_hw_stat_delta *tmp; diff --git a/net/core/dst.c b/net/core/dst.c index df9cc810ec8e..ca4231ec7347 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -372,7 +372,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, static int dst_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dst_entry *dst, *last = NULL; switch (event) { diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index d5a9f8ead0d8..21735440c44a 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -705,9 +705,9 @@ static void detach_rules(struct list_head *rules, struct net_device *dev) static int fib_rules_event(struct notifier_block *this, unsigned long event, - void *ptr) + void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct fib_rules_ops *ops; diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 0777d0aa18c3..e533259dce3c 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -261,7 +261,7 @@ struct cgroup_subsys net_prio_subsys = { static int netprio_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netprio_map *old; /* diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 11f2704c3810..795498fd4587 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1921,7 +1921,7 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d static int pktgen_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct pktgen_net *pn = net_generic(dev_net(dev), pg_net_id); if (pn->pktgen_exiting) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a08bd2b7fe3f..49c14451d8ab 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2667,7 +2667,7 @@ static void rtnetlink_rcv(struct sk_buff *skb) static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_UP: diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index c21f200eed93..dd4d506ef923 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -2078,9 +2078,9 @@ out_err: } static int dn_device_event(struct notifier_block *this, unsigned long event, - void *ptr) + void *ptr) { - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index 55e1fd5b3e56..3b9d5f20bd1c 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -1352,10 +1352,9 @@ static inline void lowpan_netlink_fini(void) } static int lowpan_device_event(struct notifier_block *unused, - unsigned long event, - void *ptr) + unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); LIST_HEAD(del_list); struct lowpan_dev_record *entry, *tmp; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 247ec1951c35..bf574029a183 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1234,7 +1234,7 @@ out: static int arp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_CHANGEADDR: diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index dfc39d4d48b7..b047e2d8a614 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1333,7 +1333,7 @@ static void inetdev_send_gratuitous_arp(struct net_device *dev, static int inetdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c7629a209f9d..05a4888dede9 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1038,7 +1038,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev; struct net *net = dev_net(dev); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9d9610ae7855..f975399f3522 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1609,7 +1609,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) static int ipmr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct mr_table *mrt; struct vif_device *v; diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 5d5d4d1be9c2..dd5508bde799 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -108,7 +108,7 @@ static int masq_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - const struct net_device *dev = ptr; + const struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_DOWN) { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 432e084b6b62..bce073b4bbd4 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2826,9 +2826,9 @@ static void addrconf_ip6_tnl_config(struct net_device *dev) } static int addrconf_notify(struct notifier_block *this, unsigned long event, - void *data) + void *ptr) { - struct net_device *dev = (struct net_device *) data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev = __in6_dev_get(dev); int run_pending = 0; int err; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 241fb8ad9fcf..583e8d435f9a 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1319,7 +1319,7 @@ static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc, static int ip6mr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct mr6_table *mrt; struct mif_device *v; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 2712ab22a174..a0962697a257 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1568,7 +1568,7 @@ int ndisc_rcv(struct sk_buff *skb) static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct inet6_dev *idev; diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 60e9053bab05..b76257cd7e1e 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -71,7 +71,7 @@ static int device_cmp(struct nf_conn *ct, void *ifindex) static int masq_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - const struct net_device *dev = ptr; + const struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_DOWN) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ad0aa6b0b86a..194c3cde1536 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2681,9 +2681,9 @@ errout: } static int ip6_route_dev_notify(struct notifier_block *this, - unsigned long event, void *data) + unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) { diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index f547a47d381c..7a1e0fc1bd4d 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -330,7 +330,7 @@ static __inline__ void __ipxitf_put(struct ipx_interface *intrfc) static int ipxitf_device_event(struct notifier_block *notifier, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ipx_interface *i, *tmp; if (!net_eq(dev_net(dev), &init_net)) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index ae691651b721..168aff5e60de 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -2293,7 +2293,7 @@ out_unlock: static int afiucv_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *event_dev = (struct net_device *)ptr; + struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); struct sock *sk; struct iucv_sock *iucv; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 60f1ce5e5e52..d2c3fd178dbe 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1717,10 +1717,9 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) } static int netdev_notify(struct notifier_block *nb, - unsigned long state, - void *ndev) + unsigned long state, void *ptr) { - struct net_device *dev = ndev; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ieee80211_sub_if_data *sdata; if (state != NETDEV_CHANGENAME) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5b142fb16480..7c3ed429789e 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1487,9 +1487,9 @@ ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev) * Currently only NETDEV_DOWN is handled to release refs to cached dsts */ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, - void *ptr) + void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_service *svc; diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 4e27fa035814..0f2ac8f2e7b7 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -800,7 +800,7 @@ static int nfqnl_rcv_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* Drop any packets associated with the downed device */ if (event == NETDEV_DOWN) diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index bd93e51d30ac..292934d23482 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -200,7 +200,7 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) static int tee_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct xt_tee_priv *priv; priv = container_of(this, struct xt_tee_priv, notifier); diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 8a6c6ea466d8..af3531926ee0 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -708,7 +708,7 @@ unlhsh_remove_return: * netlbl_unlhsh_netdev_handler - Network device notification handler * @this: notifier block * @event: the event - * @ptr: the network device (cast to void) + * @ptr: the netdevice notifier info (cast to void) * * Description: * Handle network device events, although at present all we care about is a @@ -717,10 +717,9 @@ unlhsh_remove_return: * */ static int netlbl_unlhsh_netdev_handler(struct notifier_block *this, - unsigned long event, - void *ptr) + unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netlbl_unlhsh_iface *iface = NULL; if (!net_eq(dev_net(dev), &init_net)) diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ec0c80fde69f..698814bfa7ad 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -117,7 +117,7 @@ static void nr_kill_by_device(struct net_device *dev) */ static int nr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index ef4feec6cd84..c3235675f359 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -78,7 +78,7 @@ static int dp_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct ovs_net *ovs_net; - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vport *vport = NULL; if (!ovs_is_internal_dev(dev)) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8ec1bca7f859..79fe63246b27 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3331,10 +3331,11 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, } -static int packet_notifier(struct notifier_block *this, unsigned long msg, void *data) +static int packet_notifier(struct notifier_block *this, + unsigned long msg, void *ptr) { struct sock *sk; - struct net_device *dev = data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); rcu_read_lock(); diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 45a7df6575de..56a6146ac94b 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -292,9 +292,9 @@ static void phonet_route_autodel(struct net_device *dev) /* notify Phonet of device events */ static int phonet_device_notify(struct notifier_block *me, unsigned long what, - void *arg) + void *ptr) { - struct net_device *dev = arg; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (what) { case NETDEV_REGISTER: diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 9c8347451597..e98fcfbe6007 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -202,10 +202,10 @@ static void rose_kill_by_device(struct net_device *dev) /* * Handle device status changes. */ -static int rose_device_event(struct notifier_block *this, unsigned long event, - void *ptr) +static int rose_device_event(struct notifier_block *this, + unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 5d676edc22a6..977c10e0631b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -243,7 +243,7 @@ nla_put_failure: static int mirred_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tcf_mirred *m; if (event == NETDEV_UNREGISTER) diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 120a676a3360..fc60bea63169 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -251,9 +251,9 @@ static void disable_bearer(struct tipc_bearer *tb_ptr) * specified device. */ static int recv_notification(struct notifier_block *nb, unsigned long evt, - void *dv) + void *ptr) { - struct net_device *dev = (struct net_device *)dv; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct eth_bearer *eb_ptr = ð_bearers[0]; struct eth_bearer *stop = ð_bearers[MAX_ETH_BEARERS]; diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c index 2a2864c25e15..baa9df4327d9 100644 --- a/net/tipc/ib_media.c +++ b/net/tipc/ib_media.c @@ -244,9 +244,9 @@ static void disable_bearer(struct tipc_bearer *tb_ptr) * specified device. */ static int recv_notification(struct notifier_block *nb, unsigned long evt, - void *dv) + void *ptr) { - struct net_device *dev = (struct net_device *)dv; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ib_bearer *ib_ptr = &ib_bearers[0]; struct ib_bearer *stop = &ib_bearers[MAX_IB_BEARERS]; diff --git a/net/wireless/core.c b/net/wireless/core.c index 73405e00c800..01e41191f1bf 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -886,10 +886,9 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev, } static int cfg80211_netdev_notifier_call(struct notifier_block *nb, - unsigned long state, - void *ndev) + unsigned long state, void *ptr) { - struct net_device *dev = ndev; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev; int ret; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 37ca9694aabe..1d964e23853f 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -224,7 +224,7 @@ static void x25_kill_by_device(struct net_device *dev) static int x25_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct x25_neigh *nb; if (!net_eq(dev_net(dev), &init_net)) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 23cea0f74336..536ccc95de89 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2784,7 +2784,7 @@ static void __net_init xfrm_dst_ops_init(struct net *net) static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_DOWN: diff --git a/security/selinux/netif.c b/security/selinux/netif.c index 47a49d1a6f6a..694e9e43855f 100644 --- a/security/selinux/netif.c +++ b/security/selinux/netif.c @@ -264,7 +264,7 @@ static int sel_netif_avc_callback(u32 event) static int sel_netif_netdev_notifier_handler(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev_net(dev) != &init_net) return NOTIFY_DONE; -- cgit v1.2.3 From 938177e9f3e0238c1712210f7bb6def38a5c8d7f Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 30 May 2013 16:39:29 +0000 Subject: netfilter: Correct calculation using skb->tail and skb-network_header This corrects an regression introduced by "net: Use 16bits for *_headers fields of struct skbuff" when NET_SKBUFF_DATA_USES_OFFSET is not set. In that case skb->tail will be a pointer whereas skb->network_header will be an offset from head. This is corrected by using wrappers that ensure that calculations are always made using pointers. Reported-by: Stephen Rothwell Reported-by: Chen Gang Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- net/netfilter/nf_nat_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index 5fea563afe30..85e20a919081 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -104,7 +104,7 @@ static void mangle_contents(struct sk_buff *skb, /* move post-replacement */ memmove(data + match_offset + rep_len, data + match_offset + match_len, - skb->tail - (skb->network_header + dataoff + + skb_tail_pointer(skb) - (skb_network_header(skb) + dataoff + match_offset + match_len)); /* insert data from buffer */ -- cgit v1.2.3 From 991a6b735ff47710769545b11e481bb140b2e6f7 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 1 Jun 2013 15:31:40 +0200 Subject: netfilter: nfnetlink_acct: fix incomplete dumping of objects Fix broken incomplete object dumping if the list of objects does not fit into one single netlink message. Reported-by: Gabriel Lazar Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_acct.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index dc3fd5d44464..c7b6d466a662 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -149,9 +149,12 @@ nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); list_for_each_entry_rcu(cur, &nfnl_acct_list, head) { - if (last && cur != last) - continue; + if (last) { + if (cur != last) + continue; + last = NULL; + } if (nfnl_acct_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), -- cgit v1.2.3 From 37bc4f8dfa72fb43b84381abca39cfdbbc8ff2df Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 1 Jun 2013 15:36:02 +0200 Subject: netfilter: nfnetlink_cttimeout: fix incomplete dumping of objects Fix broken incomplete object dumping if the list of objects does not fit into one single netlink message. Reported-by: Gabriel Lazar Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_cttimeout.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 701c88a20fea..65074dfb9383 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -220,9 +220,12 @@ ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); list_for_each_entry_rcu(cur, &cttimeout_list, head) { - if (last && cur != last) - continue; + if (last) { + if (cur != last) + continue; + last = NULL; + } if (ctnl_timeout_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), -- cgit v1.2.3 From 9cefbbc9c8f9abe0bc514dcfca46e8051ee84050 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 4 Jun 2013 22:22:15 +0000 Subject: netfilter: nfnetlink_queue: cleanup copy_range usage For every packet queued, we check if configured copy_range is 0, and treat that as 'copy entire packet'. We can move this check to the queue configuration, and can set copy_range appropriately. Also, convert repetitive '0xffff - NLA_HDRLEN' to a macro. [ queue initialization still used 0xffff, although its harmless since the initial setting is overwritten on queue config ] Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_queue_core.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index cff4449f01d2..3c4218141d70 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -41,6 +41,14 @@ #define NFQNL_QMAX_DEFAULT 1024 +/* We're using struct nlattr which has 16bit nla_len. Note that nla_len + * includes the header length. Thus, the maximum packet length that we + * support is 65531 bytes. We send truncated packets if the specified length + * is larger than that. Userspace can check for presence of NFQA_CAP_LEN + * attribute to detect truncation. + */ +#define NFQNL_MAX_COPY_RANGE (0xffff - NLA_HDRLEN) + struct nfqnl_instance { struct hlist_node hlist; /* global list of queues */ struct rcu_head rcu; @@ -122,7 +130,7 @@ instance_create(struct nfnl_queue_net *q, u_int16_t queue_num, inst->queue_num = queue_num; inst->peer_portid = portid; inst->queue_maxlen = NFQNL_QMAX_DEFAULT; - inst->copy_range = 0xffff; + inst->copy_range = NFQNL_MAX_COPY_RANGE; inst->copy_mode = NFQNL_COPY_NONE; spin_lock_init(&inst->lock); INIT_LIST_HEAD(&inst->queue_list); @@ -333,10 +341,9 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, return NULL; data_len = ACCESS_ONCE(queue->copy_range); - if (data_len == 0 || data_len > entskb->len) + if (data_len > entskb->len) data_len = entskb->len; - if (!entskb->head_frag || skb_headlen(entskb) < L1_CACHE_BYTES || skb_shinfo(entskb)->nr_frags >= MAX_SKB_FRAGS) @@ -727,13 +734,8 @@ nfqnl_set_mode(struct nfqnl_instance *queue, case NFQNL_COPY_PACKET: queue->copy_mode = mode; - /* We're using struct nlattr which has 16bit nla_len. Note that - * nla_len includes the header length. Thus, the maximum packet - * length that we support is 65531 bytes. We send truncated - * packets if the specified length is larger than that. - */ - if (range > 0xffff - NLA_HDRLEN) - queue->copy_range = 0xffff - NLA_HDRLEN; + if (range == 0 || range > NFQNL_MAX_COPY_RANGE) + queue->copy_range = NFQNL_MAX_COPY_RANGE; else queue->copy_range = range; break; -- cgit v1.2.3 From 7f87712c0152511a1842698ad8dca425fee2dc4f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 4 Jun 2013 22:22:16 +0000 Subject: netfilter: nfnetlink_queue: only add CAP_LEN attr when needed CAP_LEN contains the size of the network packet we're queueing to userspace, i.e. normally it is the same as the NFQA_PAYLOAD attribute len. Include it only in the unlikely case when NFQA_PAYLOAD is truncated due to copy_range limitations. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_queue_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 3c4218141d70..eb2cde836b9a 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -472,7 +472,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0) goto nla_put_failure; - if (cap_len > 0 && nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len))) + if (cap_len > data_len && + nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len))) goto nla_put_failure; if (nfqnl_put_packet_info(skb, entskb)) -- cgit v1.2.3 From 409b545ac10d9548929557a75ad86540f59a2c83 Mon Sep 17 00:00:00 2001 From: Phil Oester Date: Tue, 4 Jun 2013 05:09:27 +0000 Subject: netfilter: xt_TCPMSS: Fix violation of RFC879 in absence of MSS option The clamp-mss-to-pmtu option of the xt_TCPMSS target can cause issues connecting to websites if there was no MSS option present in the original SYN packet from the client. In these cases, it may add a MSS higher than the default specified in RFC879. Fix this by never setting a value > 536 if no MSS option was specified by the client. This closes netfilter's bugzilla #662. Signed-off-by: Phil Oester Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_TCPMSS.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index a75240f0d42b..afaebc766933 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -125,6 +125,12 @@ tcpmss_mangle_packet(struct sk_buff *skb, skb_put(skb, TCPOLEN_MSS); + /* RFC 879 states that the default MSS is 536 without specific + * knowledge that the destination host is prepared to accept larger. + * Since no MSS was provided, we MUST NOT set a value > 536. + */ + newmss = min(newmss, (u16)536); + opt = (u_int8_t *)tcph + sizeof(struct tcphdr); memmove(opt + TCPOLEN_MSS, opt, tcplen - sizeof(struct tcphdr)); -- cgit v1.2.3 From 7b8dfe289fdde0066be343a3e0271ad6d7b6dbcf Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 7 Jun 2013 18:42:00 +0200 Subject: netfilter: nfnetlink_queue: fix missing HW protocol Locally generated IPv4 and IPv6 traffic gets skb->protocol unset, thus passing zero. ip6tables -I OUTPUT -j NFQUEUE libmnl/examples/netfilter# ./nf-queue 0 & ping6 ::1 packet received (id=1 hw=0x0000 hook=3) ^^^^^^ Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_queue_core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 4e27fa035814..5352b2d2d5bf 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -637,9 +637,6 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) if (queue->copy_mode == NFQNL_COPY_NONE) return -EINVAL; - if ((queue->flags & NFQA_CFG_F_GSO) || !skb_is_gso(entry->skb)) - return __nfqnl_enqueue_packet(net, queue, entry); - skb = entry->skb; switch (entry->pf) { @@ -651,6 +648,9 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) break; } + if ((queue->flags & NFQA_CFG_F_GSO) || !skb_is_gso(skb)) + return __nfqnl_enqueue_packet(net, queue, entry); + nf_bridge_adjust_skb_data(skb); segs = skb_gso_segment(skb, 0); /* Does not use PTR_ERR to limit the number of error codes that can be -- cgit v1.2.3 From a8241c63517ec0b900695daa9003cddc41c536a1 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 3 Jun 2013 12:00:49 +0300 Subject: ipvs: info leak in __ip_vs_get_dest_entries() The entry struct has a 2 byte hole after ->port and another 4 byte hole after ->stats.outpkts. You must have CAP_NET_ADMIN in your namespace to hit this information leak. Signed-off-by: Dan Carpenter Acked-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_ctl.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5b142fb16480..9e6c2a075a4c 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2542,6 +2542,7 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get, struct ip_vs_dest *dest; struct ip_vs_dest_entry entry; + memset(&entry, 0, sizeof(entry)); list_for_each_entry(dest, &svc->destinations, n_list) { if (count >= get->num_dests) break; -- cgit v1.2.3 From ed82c437320c48a4032492f4a55a7e2c934158b6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 11 Jun 2013 01:51:31 +0200 Subject: netfilter: xt_TCPOPTSTRIP: don't use tcp_hdr() In (bc6bcb5 netfilter: xt_TCPOPTSTRIP: fix possible mangling beyond packet boundary), the use of tcp_hdr was introduced. However, we cannot assume that skb->transport_header is set for non-local packets. Cc: Florian Westphal Reported-by: Phil Oester Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_TCPOPTSTRIP.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_TCPOPTSTRIP.c b/net/netfilter/xt_TCPOPTSTRIP.c index 1eb1a44bfd3d..b68fa191710f 100644 --- a/net/netfilter/xt_TCPOPTSTRIP.c +++ b/net/netfilter/xt_TCPOPTSTRIP.c @@ -48,11 +48,13 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, return NF_DROP; len = skb->len - tcphoff; - if (len < (int)sizeof(struct tcphdr) || - tcp_hdr(skb)->doff * 4 > len) + if (len < (int)sizeof(struct tcphdr)) return NF_DROP; tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); + if (tcph->doff * 4 > len) + return NF_DROP; + opt = (u_int8_t *)tcph; /* -- cgit v1.2.3 From 45203a3b380cee28f570475c0d28c169f908c209 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 6 Jun 2013 08:43:22 -0700 Subject: net_sched: add 64bit rate estimators struct gnet_stats_rate_est contains u32 fields, so the bytes per second field can wrap at 34360Mbit. Add a new gnet_stats_rate_est64 structure to get 64bit bps/pps fields, and switch the kernel to use this structure natively. This structure is dumped to user space as a new attribute : TCA_STATS_RATE_EST64 Old tc command will now display the capped bps (to 34360Mbit), instead of wrapped values, and updated tc command will display correct information. Old tc command output, after patch : eric:~# tc -s -d qd sh dev lo qdisc pfifo 8001: root refcnt 2 limit 1000p Sent 80868245400 bytes 1978837 pkt (dropped 0, overlimits 0 requeues 0) rate 34360Mbit 189696pps backlog 0b 0p requeues 0 This patch carefully reorganizes "struct Qdisc" layout to get optimal performance on SMP. Signed-off-by: Eric Dumazet Cc: Ben Hutchings Signed-off-by: David S. Miller --- include/net/act_api.h | 2 +- include/net/gen_stats.h | 10 +++++----- include/net/netfilter/xt_rateest.h | 2 +- include/net/sch_generic.h | 13 +++++++------ include/uapi/linux/gen_stats.h | 11 +++++++++++ net/core/gen_estimator.c | 12 ++++++------ net/core/gen_stats.c | 22 +++++++++++++++++----- net/netfilter/xt_rateest.c | 2 +- net/sched/sch_cbq.c | 2 +- net/sched/sch_drr.c | 2 +- net/sched/sch_hfsc.c | 2 +- net/sched/sch_htb.c | 2 +- net/sched/sch_qfq.c | 2 +- 13 files changed, 54 insertions(+), 30 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/act_api.h b/include/net/act_api.h index 06ef7e926a66..b8ffac7b6bab 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -18,7 +18,7 @@ struct tcf_common { struct tcf_t tcfc_tm; struct gnet_stats_basic_packed tcfc_bstats; struct gnet_stats_queue tcfc_qstats; - struct gnet_stats_rate_est tcfc_rate_est; + struct gnet_stats_rate_est64 tcfc_rate_est; spinlock_t tcfc_lock; struct rcu_head tcfc_rcu; }; diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index a79b6cfb02a8..cf8439ba4d11 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -30,7 +30,7 @@ extern int gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b); extern int gnet_stats_copy_rate_est(struct gnet_dump *d, const struct gnet_stats_basic_packed *b, - struct gnet_stats_rate_est *r); + struct gnet_stats_rate_est64 *r); extern int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q); extern int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len); @@ -38,13 +38,13 @@ extern int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len); extern int gnet_stats_finish_copy(struct gnet_dump *d); extern int gen_new_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_rate_est *rate_est, + struct gnet_stats_rate_est64 *rate_est, spinlock_t *stats_lock, struct nlattr *opt); extern void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_rate_est *rate_est); + struct gnet_stats_rate_est64 *rate_est); extern int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_rate_est *rate_est, + struct gnet_stats_rate_est64 *rate_est, spinlock_t *stats_lock, struct nlattr *opt); extern bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, - const struct gnet_stats_rate_est *rate_est); + const struct gnet_stats_rate_est64 *rate_est); #endif diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h index 5a2978d1cb22..495c71f66e7e 100644 --- a/include/net/netfilter/xt_rateest.h +++ b/include/net/netfilter/xt_rateest.h @@ -6,7 +6,7 @@ struct xt_rateest { struct gnet_stats_basic_packed bstats; spinlock_t lock; /* keep rstats and lock on same cache line to speedup xt_rateest_mt() */ - struct gnet_stats_rate_est rstats; + struct gnet_stats_rate_est64 rstats; /* following fields not accessed in hot path */ struct hlist_node list; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index e7f4e21cc3e1..df5676029827 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -58,14 +58,12 @@ struct Qdisc { * multiqueue device. */ #define TCQ_F_WARN_NONWC (1 << 16) - int padded; + u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; struct list_head list; u32 handle; u32 parent; - atomic_t refcnt; - struct gnet_stats_rate_est rate_est; int (*reshape_fail)(struct sk_buff *skb, struct Qdisc *q); @@ -76,8 +74,9 @@ struct Qdisc { */ struct Qdisc *__parent; struct netdev_queue *dev_queue; - struct Qdisc *next_sched; + struct gnet_stats_rate_est64 rate_est; + struct Qdisc *next_sched; struct sk_buff *gso_skb; /* * For performance sake on SMP, we put highly modified fields at the end @@ -88,8 +87,10 @@ struct Qdisc { unsigned int __state; struct gnet_stats_queue qstats; struct rcu_head rcu_head; - spinlock_t busylock; - u32 limit; + int padded; + atomic_t refcnt; + + spinlock_t busylock ____cacheline_aligned_in_smp; }; static inline bool qdisc_is_running(const struct Qdisc *qdisc) diff --git a/include/uapi/linux/gen_stats.h b/include/uapi/linux/gen_stats.h index 552c8a0a12d1..6487317ea619 100644 --- a/include/uapi/linux/gen_stats.h +++ b/include/uapi/linux/gen_stats.h @@ -9,6 +9,7 @@ enum { TCA_STATS_RATE_EST, TCA_STATS_QUEUE, TCA_STATS_APP, + TCA_STATS_RATE_EST64, __TCA_STATS_MAX, }; #define TCA_STATS_MAX (__TCA_STATS_MAX - 1) @@ -37,6 +38,16 @@ struct gnet_stats_rate_est { __u32 pps; }; +/** + * struct gnet_stats_rate_est64 - rate estimator + * @bps: current byte rate + * @pps: current packet rate + */ +struct gnet_stats_rate_est64 { + __u64 bps; + __u64 pps; +}; + /** * struct gnet_stats_queue - queuing statistics * @qlen: queue length diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index d9d198aa9fed..6b5b6e7013ca 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -82,7 +82,7 @@ struct gen_estimator { struct list_head list; struct gnet_stats_basic_packed *bstats; - struct gnet_stats_rate_est *rate_est; + struct gnet_stats_rate_est64 *rate_est; spinlock_t *stats_lock; int ewma_log; u64 last_bytes; @@ -167,7 +167,7 @@ static void gen_add_node(struct gen_estimator *est) static struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats, - const struct gnet_stats_rate_est *rate_est) + const struct gnet_stats_rate_est64 *rate_est) { struct rb_node *p = est_root.rb_node; @@ -203,7 +203,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats * */ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_rate_est *rate_est, + struct gnet_stats_rate_est64 *rate_est, spinlock_t *stats_lock, struct nlattr *opt) { @@ -258,7 +258,7 @@ EXPORT_SYMBOL(gen_new_estimator); * Note : Caller should respect an RCU grace period before freeing stats_lock */ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_rate_est *rate_est) + struct gnet_stats_rate_est64 *rate_est) { struct gen_estimator *e; @@ -290,7 +290,7 @@ EXPORT_SYMBOL(gen_kill_estimator); * Returns 0 on success or a negative error code. */ int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_rate_est *rate_est, + struct gnet_stats_rate_est64 *rate_est, spinlock_t *stats_lock, struct nlattr *opt) { gen_kill_estimator(bstats, rate_est); @@ -306,7 +306,7 @@ EXPORT_SYMBOL(gen_replace_estimator); * Returns true if estimator is active, and false if not. */ bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, - const struct gnet_stats_rate_est *rate_est) + const struct gnet_stats_rate_est64 *rate_est) { bool res; diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index ddedf211e588..9d3d9e78397b 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -143,18 +143,30 @@ EXPORT_SYMBOL(gnet_stats_copy_basic); int gnet_stats_copy_rate_est(struct gnet_dump *d, const struct gnet_stats_basic_packed *b, - struct gnet_stats_rate_est *r) + struct gnet_stats_rate_est64 *r) { + struct gnet_stats_rate_est est; + int res; + if (b && !gen_estimator_active(b, r)) return 0; + est.bps = min_t(u64, UINT_MAX, r->bps); + /* we have some time before reaching 2^32 packets per second */ + est.pps = r->pps; + if (d->compat_tc_stats) { - d->tc_stats.bps = r->bps; - d->tc_stats.pps = r->pps; + d->tc_stats.bps = est.bps; + d->tc_stats.pps = est.pps; } - if (d->tail) - return gnet_stats_copy(d, TCA_STATS_RATE_EST, r, sizeof(*r)); + if (d->tail) { + res = gnet_stats_copy(d, TCA_STATS_RATE_EST, &est, sizeof(est)); + if (res < 0 || est.bps == r->bps) + return res; + /* emit 64bit stats only if needed */ + return gnet_stats_copy(d, TCA_STATS_RATE_EST64, r, sizeof(*r)); + } return 0; } diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c index ed0db15ab00e..7720b036d76a 100644 --- a/net/netfilter/xt_rateest.c +++ b/net/netfilter/xt_rateest.c @@ -18,7 +18,7 @@ static bool xt_rateest_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rateest_match_info *info = par->matchinfo; - struct gnet_stats_rate_est *r; + struct gnet_stats_rate_est64 *r; u_int32_t bps1, bps2, pps1, pps2; bool ret = true; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 1bc210ffcba2..71a568862557 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -130,7 +130,7 @@ struct cbq_class { psched_time_t penalized; struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; - struct gnet_stats_rate_est rate_est; + struct gnet_stats_rate_est64 rate_est; struct tc_cbq_xstats xstats; struct tcf_proto *filter_list; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 759b308d1a8d..8302717ea303 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -25,7 +25,7 @@ struct drr_class { struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; - struct gnet_stats_rate_est rate_est; + struct gnet_stats_rate_est64 rate_est; struct list_head alist; struct Qdisc *qdisc; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 9facea03faeb..c4075610502c 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -114,7 +114,7 @@ struct hfsc_class { struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; - struct gnet_stats_rate_est rate_est; + struct gnet_stats_rate_est64 rate_est; unsigned int level; /* class level in hierarchy */ struct tcf_proto *filter_list; /* filter list */ unsigned int filter_cnt; /* filter count */ diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index adaedd79389c..162fb800754c 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -78,7 +78,7 @@ struct htb_class { /* general class parameters */ struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; - struct gnet_stats_rate_est rate_est; + struct gnet_stats_rate_est64 rate_est; struct tc_htb_xstats xstats; /* our special stats */ int refcnt; /* usage count of this class */ diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index d51852bba01c..7c195d972bf0 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -138,7 +138,7 @@ struct qfq_class { struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; - struct gnet_stats_rate_est rate_est; + struct gnet_stats_rate_est64 rate_est; struct Qdisc *qdisc; struct list_head alist; /* Link for active-classes list. */ struct qfq_aggregate *agg; /* Parent aggregate. */ -- cgit v1.2.3 From 70d19f805f8c047fc0a28dec9306b3773971c8d9 Mon Sep 17 00:00:00 2001 From: Phil Oester Date: Wed, 12 Jun 2013 10:44:51 +0200 Subject: netfilter: xt_TCPMSS: Fix IPv6 default MSS too As a followup to commit 409b545a ("netfilter: xt_TCPMSS: Fix violation of RFC879 in absence of MSS option"), John Heffner points out that IPv6 has a higher MTU than IPv4, and thus a higher minimum MSS. Update TCPMSS target to account for this, and update RFC comment. While at it, point to more recent reference RFC1122 instead of RFC879. Signed-off-by: Phil Oester Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_TCPMSS.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index afaebc766933..6640a224f9fb 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -45,11 +45,12 @@ optlen(const u_int8_t *opt, unsigned int offset) static int tcpmss_mangle_packet(struct sk_buff *skb, - const struct xt_tcpmss_info *info, + const struct xt_action_param *par, unsigned int in_mtu, unsigned int tcphoff, unsigned int minlen) { + const struct xt_tcpmss_info *info = par->targinfo; struct tcphdr *tcph; unsigned int tcplen, i; __be16 oldval; @@ -125,11 +126,17 @@ tcpmss_mangle_packet(struct sk_buff *skb, skb_put(skb, TCPOLEN_MSS); - /* RFC 879 states that the default MSS is 536 without specific - * knowledge that the destination host is prepared to accept larger. - * Since no MSS was provided, we MUST NOT set a value > 536. + /* + * IPv4: RFC 1122 states "If an MSS option is not received at + * connection setup, TCP MUST assume a default send MSS of 536". + * IPv6: RFC 2460 states IPv6 has a minimum MTU of 1280 and a minimum + * length IPv6 header of 60, ergo the default MSS value is 1220 + * Since no MSS was provided, we must use the default values */ - newmss = min(newmss, (u16)536); + if (par->family == NFPROTO_IPV4) + newmss = min(newmss, (u16)536); + else + newmss = min(newmss, (u16)1220); opt = (u_int8_t *)tcph + sizeof(struct tcphdr); memmove(opt + TCPOLEN_MSS, opt, tcplen - sizeof(struct tcphdr)); @@ -188,7 +195,7 @@ tcpmss_tg4(struct sk_buff *skb, const struct xt_action_param *par) __be16 newlen; int ret; - ret = tcpmss_mangle_packet(skb, par->targinfo, + ret = tcpmss_mangle_packet(skb, par, tcpmss_reverse_mtu(skb, PF_INET), iph->ihl * 4, sizeof(*iph) + sizeof(struct tcphdr)); @@ -217,7 +224,7 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par) tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr, &frag_off); if (tcphoff < 0) return NF_DROP; - ret = tcpmss_mangle_packet(skb, par->targinfo, + ret = tcpmss_mangle_packet(skb, par, tcpmss_reverse_mtu(skb, PF_INET6), tcphoff, sizeof(*ipv6h) + sizeof(struct tcphdr)); -- cgit v1.2.3 From b396966c4688522863572927cb30aa874b3ec504 Mon Sep 17 00:00:00 2001 From: Phil Oester Date: Wed, 12 Jun 2013 10:58:20 +0200 Subject: netfilter: xt_TCPMSS: Fix missing fragmentation handling Similar to commit bc6bcb59 ("netfilter: xt_TCPOPTSTRIP: fix possible mangling beyond packet boundary"), add safe fragment handling to xt_TCPMSS. Signed-off-by: Phil Oester Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_TCPMSS.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 6640a224f9fb..7011c71646f0 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -57,6 +57,10 @@ tcpmss_mangle_packet(struct sk_buff *skb, u16 newmss; u8 *opt; + /* This is a fragment, no TCP header is available */ + if (par->fragoff != 0) + return XT_CONTINUE; + if (!skb_make_writable(skb, skb->len)) return -1; -- cgit v1.2.3 From fe2c6338fd2c6f383c4d4164262f35c8f3708e1f Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 11 Jun 2013 23:04:25 -0700 Subject: net: Convert uses of typedef ctl_table to struct ctl_table Reduce the uses of this unnecessary typedef. Done via perl script: $ git grep --name-only -w ctl_table net | \ xargs perl -p -i -e '\ sub trim { my ($local) = @_; $local =~ s/(^\s+|\s+$)//g; return $local; } \ s/\b(? Signed-off-by: David S. Miller --- net/ax25/sysctl_net_ax25.c | 2 +- net/bridge/br_netfilter.c | 4 ++-- net/core/neighbour.c | 6 ++--- net/core/sysctl_net_core.c | 8 +++---- net/decnet/dn_dev.c | 6 ++--- net/decnet/sysctl_net_decnet.c | 6 ++--- net/ipv4/devinet.c | 6 ++--- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 2 +- net/ipv4/route.c | 4 ++-- net/ipv4/sysctl_net_ipv4.c | 31 +++++++++++++------------- net/ipv6/addrconf.c | 10 ++++----- net/ipv6/icmp.c | 2 +- net/ipv6/route.c | 4 ++-- net/ipv6/sysctl_net_ipv6.c | 4 ++-- net/irda/irsysctl.c | 6 ++--- net/netfilter/ipvs/ip_vs_ctl.c | 8 +++---- net/netfilter/ipvs/ip_vs_lblc.c | 2 +- net/netfilter/ipvs/ip_vs_lblcr.c | 2 +- net/netfilter/nf_conntrack_standalone.c | 4 ++-- net/netfilter/nf_log.c | 2 +- net/netrom/sysctl_net_netrom.c | 2 +- net/phonet/sysctl.c | 4 ++-- net/rds/ib_sysctl.c | 2 +- net/rds/iw_sysctl.c | 2 +- net/rds/sysctl.c | 2 +- net/rose/sysctl_net_rose.c | 2 +- net/sctp/sysctl.c | 10 ++++----- net/sunrpc/sysctl.c | 10 ++++----- net/sunrpc/xprtrdma/svc_rdma.c | 8 +++---- net/sunrpc/xprtrdma/transport.c | 4 ++-- net/sunrpc/xprtsock.c | 4 ++-- net/unix/sysctl_net_unix.c | 2 +- 32 files changed, 86 insertions(+), 85 deletions(-) (limited to 'net/netfilter') diff --git a/net/ax25/sysctl_net_ax25.c b/net/ax25/sysctl_net_ax25.c index d5744b752511..919a5ce47515 100644 --- a/net/ax25/sysctl_net_ax25.c +++ b/net/ax25/sysctl_net_ax25.c @@ -29,7 +29,7 @@ static int min_proto[1], max_proto[] = { AX25_PROTO_MAX }; static int min_ds_timeout[1], max_ds_timeout[] = {65535000}; #endif -static const ctl_table ax25_param_table[] = { +static const struct ctl_table ax25_param_table[] = { { .procname = "ip_default_mode", .maxlen = sizeof(int), diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 1ed75bfd8d1d..f87736270eaa 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -992,7 +992,7 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = { #ifdef CONFIG_SYSCTL static -int brnf_sysctl_call_tables(ctl_table * ctl, int write, +int brnf_sysctl_call_tables(struct ctl_table *ctl, int write, void __user * buffer, size_t * lenp, loff_t * ppos) { int ret; @@ -1004,7 +1004,7 @@ int brnf_sysctl_call_tables(ctl_table * ctl, int write, return ret; } -static ctl_table brnf_table[] = { +static struct ctl_table brnf_table[] = { { .procname = "bridge-nf-call-arptables", .data = &brnf_call_arptables, diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5c56b217b999..decaa4b9db2f 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2765,11 +2765,11 @@ EXPORT_SYMBOL(neigh_app_ns); static int zero; static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN); -static int proc_unres_qlen(ctl_table *ctl, int write, void __user *buffer, - size_t *lenp, loff_t *ppos) +static int proc_unres_qlen(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { int size, ret; - ctl_table tmp = *ctl; + struct ctl_table tmp = *ctl; tmp.extra1 = &zero; tmp.extra2 = &unres_qlen_max; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 4b48f39582b0..637a42e5d589 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -24,12 +24,12 @@ static int one = 1; #ifdef CONFIG_RPS -static int rps_sock_flow_sysctl(ctl_table *table, int write, +static int rps_sock_flow_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { unsigned int orig_size, size; int ret, i; - ctl_table tmp = { + struct ctl_table tmp = { .data = &size, .maxlen = sizeof(size), .mode = table->mode @@ -91,7 +91,7 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write, #ifdef CONFIG_NET_FLOW_LIMIT static DEFINE_MUTEX(flow_limit_update_mutex); -static int flow_limit_cpu_sysctl(ctl_table *table, int write, +static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -156,7 +156,7 @@ done: return ret; } -static int flow_limit_table_len_sysctl(ctl_table *table, int write, +static int flow_limit_table_len_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 7d9197063ebb..dd0dfb25f4b1 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -158,11 +158,11 @@ static int max_t3[] = { 8191 }; /* Must fit in 16 bits when multiplied by BCT3MU static int min_priority[1]; static int max_priority[] = { 127 }; /* From DECnet spec */ -static int dn_forwarding_proc(ctl_table *, int, +static int dn_forwarding_proc(struct ctl_table *, int, void __user *, size_t *, loff_t *); static struct dn_dev_sysctl_table { struct ctl_table_header *sysctl_header; - ctl_table dn_dev_vars[5]; + struct ctl_table dn_dev_vars[5]; } dn_dev_sysctl = { NULL, { @@ -242,7 +242,7 @@ static void dn_dev_sysctl_unregister(struct dn_dev_parms *parms) } } -static int dn_forwarding_proc(ctl_table *table, int write, +static int dn_forwarding_proc(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c index a55eeccaa72f..5325b541c526 100644 --- a/net/decnet/sysctl_net_decnet.c +++ b/net/decnet/sysctl_net_decnet.c @@ -132,7 +132,7 @@ static int parse_addr(__le16 *addr, char *str) return 0; } -static int dn_node_address_handler(ctl_table *table, int write, +static int dn_node_address_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -183,7 +183,7 @@ static int dn_node_address_handler(ctl_table *table, int write, return 0; } -static int dn_def_dev_handler(ctl_table *table, int write, +static int dn_def_dev_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -246,7 +246,7 @@ static int dn_def_dev_handler(ctl_table *table, int write, return 0; } -static ctl_table dn_table[] = { +static struct ctl_table dn_table[] = { { .procname = "node_address", .maxlen = 7, diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 3469506c106d..8d48c392adcc 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1942,7 +1942,7 @@ static void inet_forward_change(struct net *net) } } -static int devinet_conf_proc(ctl_table *ctl, int write, +static int devinet_conf_proc(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -1985,7 +1985,7 @@ static int devinet_conf_proc(ctl_table *ctl, int write, return ret; } -static int devinet_sysctl_forward(ctl_table *ctl, int write, +static int devinet_sysctl_forward(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -2028,7 +2028,7 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, return ret; } -static int ipv4_doint_and_flush(ctl_table *ctl, int write, +static int ipv4_doint_and_flush(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 567d84168bd2..0a2e0e3e95ba 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -223,7 +223,7 @@ static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = { static int log_invalid_proto_min = 0; static int log_invalid_proto_max = 255; -static ctl_table ip_ct_sysctl_table[] = { +static struct ctl_table ip_ct_sysctl_table[] = { { .procname = "ip_conntrack_max", .maxlen = sizeof(int), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 198ea596f2d9..f3fa42eac461 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2448,7 +2448,7 @@ static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; -static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, +static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -2463,7 +2463,7 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, return -EINVAL; } -static ctl_table ipv4_route_table[] = { +static struct ctl_table ipv4_route_table[] = { { .procname = "gc_thresh", .data = &ipv4_dst_ops.gc_thresh, diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index fa2f63fc453b..b2c123c44d69 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -49,13 +49,13 @@ static void set_local_port_range(int range[2]) } /* Validate changes from /proc interface. */ -static int ipv4_local_port_range(ctl_table *table, int write, +static int ipv4_local_port_range(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; int range[2]; - ctl_table tmp = { + struct ctl_table tmp = { .data = &range, .maxlen = sizeof(range), .mode = table->mode, @@ -100,7 +100,7 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig } /* Validate changes from /proc interface. */ -static int ipv4_ping_group_range(ctl_table *table, int write, +static int ipv4_ping_group_range(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -108,7 +108,7 @@ static int ipv4_ping_group_range(ctl_table *table, int write, int ret; gid_t urange[2]; kgid_t low, high; - ctl_table tmp = { + struct ctl_table tmp = { .data = &urange, .maxlen = sizeof(urange), .mode = table->mode, @@ -135,11 +135,11 @@ static int ipv4_ping_group_range(ctl_table *table, int write, return ret; } -static int proc_tcp_congestion_control(ctl_table *ctl, int write, +static int proc_tcp_congestion_control(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char val[TCP_CA_NAME_MAX]; - ctl_table tbl = { + struct ctl_table tbl = { .data = val, .maxlen = TCP_CA_NAME_MAX, }; @@ -153,12 +153,12 @@ static int proc_tcp_congestion_control(ctl_table *ctl, int write, return ret; } -static int proc_tcp_available_congestion_control(ctl_table *ctl, +static int proc_tcp_available_congestion_control(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX, }; + struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX, }; int ret; tbl.data = kmalloc(tbl.maxlen, GFP_USER); @@ -170,12 +170,12 @@ static int proc_tcp_available_congestion_control(ctl_table *ctl, return ret; } -static int proc_allowed_congestion_control(ctl_table *ctl, +static int proc_allowed_congestion_control(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX }; + struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX }; int ret; tbl.data = kmalloc(tbl.maxlen, GFP_USER); @@ -190,7 +190,7 @@ static int proc_allowed_congestion_control(ctl_table *ctl, return ret; } -static int ipv4_tcp_mem(ctl_table *ctl, int write, +static int ipv4_tcp_mem(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -201,7 +201,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, struct mem_cgroup *memcg; #endif - ctl_table tmp = { + struct ctl_table tmp = { .data = &vec, .maxlen = sizeof(vec), .mode = ctl->mode, @@ -233,10 +233,11 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, return 0; } -static int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer, - size_t *lenp, loff_t *ppos) +static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) { - ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; + struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; int ret; u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */ diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 21010fddb203..80449121afa2 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4620,13 +4620,13 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) #ifdef CONFIG_SYSCTL static -int addrconf_sysctl_forward(ctl_table *ctl, int write, +int addrconf_sysctl_forward(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; - ctl_table lctl; + struct ctl_table lctl; int ret; /* @@ -4705,13 +4705,13 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) } static -int addrconf_sysctl_disable(ctl_table *ctl, int write, +int addrconf_sysctl_disable(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; - ctl_table lctl; + struct ctl_table lctl; int ret; /* @@ -4733,7 +4733,7 @@ int addrconf_sysctl_disable(ctl_table *ctl, int write, static struct addrconf_sysctl_table { struct ctl_table_header *sysctl_header; - ctl_table addrconf_vars[DEVCONF_MAX+1]; + struct ctl_table addrconf_vars[DEVCONF_MAX+1]; } addrconf_sysctl __read_mostly = { .sysctl_header = NULL, .addrconf_vars = { diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 4b4890bbe16d..7cfc8d284870 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -976,7 +976,7 @@ int icmpv6_err_convert(u8 type, u8 code, int *err) EXPORT_SYMBOL(icmpv6_err_convert); #ifdef CONFIG_SYSCTL -ctl_table ipv6_icmp_table_template[] = { +struct ctl_table ipv6_icmp_table_template[] = { { .procname = "ratelimit", .data = &init_net.ipv6.sysctl.icmpv6_time, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2b874185ebb2..7ca87b37c0ef 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2790,7 +2790,7 @@ static const struct file_operations rt6_stats_seq_fops = { #ifdef CONFIG_SYSCTL static -int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, +int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net *net; @@ -2805,7 +2805,7 @@ int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, return 0; } -ctl_table ipv6_route_table_template[] = { +struct ctl_table ipv6_route_table_template[] = { { .procname = "flush", .data = &init_net.ipv6.sysctl.flush_delay, diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index e85c48bd404f..107b2f1d90ae 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -16,7 +16,7 @@ #include #include -static ctl_table ipv6_table_template[] = { +static struct ctl_table ipv6_table_template[] = { { .procname = "bindv6only", .data = &init_net.ipv6.sysctl.bindv6only, @@ -27,7 +27,7 @@ static ctl_table ipv6_table_template[] = { { } }; -static ctl_table ipv6_rotable[] = { +static struct ctl_table ipv6_rotable[] = { { .procname = "mld_max_msf", .data = &sysctl_mld_max_msf, diff --git a/net/irda/irsysctl.c b/net/irda/irsysctl.c index de73f6496db5..d6a59651767a 100644 --- a/net/irda/irsysctl.c +++ b/net/irda/irsysctl.c @@ -73,7 +73,7 @@ static int min_lap_keepalive_time = 100; /* 100us */ /* For other sysctl, I've no idea of the range. Maybe Dag could help * us on that - Jean II */ -static int do_devname(ctl_table *table, int write, +static int do_devname(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -90,7 +90,7 @@ static int do_devname(ctl_table *table, int write, } -static int do_discovery(ctl_table *table, int write, +static int do_discovery(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -111,7 +111,7 @@ static int do_discovery(ctl_table *table, int write, } /* One file */ -static ctl_table irda_table[] = { +static struct ctl_table irda_table[] = { { .procname = "discovery", .data = &sysctl_discovery, diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index df05c1c276f0..edb88fbcb1bd 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1575,7 +1575,7 @@ static int zero; static int three = 3; static int -proc_do_defense_mode(ctl_table *table, int write, +proc_do_defense_mode(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; @@ -1596,7 +1596,7 @@ proc_do_defense_mode(ctl_table *table, int write, } static int -proc_do_sync_threshold(ctl_table *table, int write, +proc_do_sync_threshold(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; @@ -1616,7 +1616,7 @@ proc_do_sync_threshold(ctl_table *table, int write, } static int -proc_do_sync_mode(ctl_table *table, int write, +proc_do_sync_mode(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; @@ -1634,7 +1634,7 @@ proc_do_sync_mode(ctl_table *table, int write, } static int -proc_do_sync_ports(ctl_table *table, int write, +proc_do_sync_ports(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 5ea26bd87743..44595b8ae37f 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -118,7 +118,7 @@ struct ip_vs_lblc_table { * IPVS LBLC sysctl table */ #ifdef CONFIG_SYSCTL -static ctl_table vs_vars_table[] = { +static struct ctl_table vs_vars_table[] = { { .procname = "lblc_expiration", .data = NULL, diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 50123c2ab484..876937db0bf4 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -299,7 +299,7 @@ struct ip_vs_lblcr_table { * IPVS LBLCR sysctl table */ -static ctl_table vs_vars_table[] = { +static struct ctl_table vs_vars_table[] = { { .procname = "lblcr_expiration", .data = NULL, diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index bd700b4013c1..f641751dba9d 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -408,7 +408,7 @@ static int log_invalid_proto_max = 255; static struct ctl_table_header *nf_ct_netfilter_header; -static ctl_table nf_ct_sysctl_table[] = { +static struct ctl_table nf_ct_sysctl_table[] = { { .procname = "nf_conntrack_max", .data = &nf_conntrack_max, @@ -458,7 +458,7 @@ static ctl_table nf_ct_sysctl_table[] = { #define NET_NF_CONNTRACK_MAX 2089 -static ctl_table nf_ct_netfilter_table[] = { +static struct ctl_table nf_ct_netfilter_table[] = { { .procname = "nf_conntrack_max", .data = &nf_conntrack_max, diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 4b60a87b7596..85296d4eac0e 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -245,7 +245,7 @@ static const struct file_operations nflog_file_ops = { static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1]; -static int nf_log_proc_dostring(ctl_table *table, int write, +static int nf_log_proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; diff --git a/net/netrom/sysctl_net_netrom.c b/net/netrom/sysctl_net_netrom.c index 42f630b9a698..ba1c368b3f18 100644 --- a/net/netrom/sysctl_net_netrom.c +++ b/net/netrom/sysctl_net_netrom.c @@ -34,7 +34,7 @@ static int min_reset[] = {0}, max_reset[] = {1}; static struct ctl_table_header *nr_table_header; -static ctl_table nr_table[] = { +static struct ctl_table nr_table[] = { { .procname = "default_path_quality", .data = &sysctl_netrom_default_path_quality, diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c index d6bbbbd0af18..c02a8c4bc11f 100644 --- a/net/phonet/sysctl.c +++ b/net/phonet/sysctl.c @@ -61,13 +61,13 @@ void phonet_get_local_port_range(int *min, int *max) } while (read_seqretry(&local_port_range_lock, seq)); } -static int proc_local_port_range(ctl_table *table, int write, +static int proc_local_port_range(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; int range[2] = {local_port_range[0], local_port_range[1]}; - ctl_table tmp = { + struct ctl_table tmp = { .data = &range, .maxlen = sizeof(range), .mode = table->mode, diff --git a/net/rds/ib_sysctl.c b/net/rds/ib_sysctl.c index 7e643bafb4af..e4e41b3afce7 100644 --- a/net/rds/ib_sysctl.c +++ b/net/rds/ib_sysctl.c @@ -61,7 +61,7 @@ static unsigned long rds_ib_sysctl_max_unsig_wr_max = 64; */ unsigned int rds_ib_sysctl_flow_control = 0; -static ctl_table rds_ib_sysctl_table[] = { +static struct ctl_table rds_ib_sysctl_table[] = { { .procname = "max_send_wr", .data = &rds_ib_sysctl_max_send_wr, diff --git a/net/rds/iw_sysctl.c b/net/rds/iw_sysctl.c index 5d5ebd576f3f..89c91515ed0c 100644 --- a/net/rds/iw_sysctl.c +++ b/net/rds/iw_sysctl.c @@ -55,7 +55,7 @@ static unsigned long rds_iw_sysctl_max_unsig_bytes_max = ~0UL; unsigned int rds_iw_sysctl_flow_control = 1; -static ctl_table rds_iw_sysctl_table[] = { +static struct ctl_table rds_iw_sysctl_table[] = { { .procname = "max_send_wr", .data = &rds_iw_sysctl_max_send_wr, diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c index 907214b4c4d0..b5cb2aa08f33 100644 --- a/net/rds/sysctl.c +++ b/net/rds/sysctl.c @@ -49,7 +49,7 @@ unsigned int rds_sysctl_max_unacked_bytes = (16 << 20); unsigned int rds_sysctl_ping_enable = 1; -static ctl_table rds_sysctl_rds_table[] = { +static struct ctl_table rds_sysctl_rds_table[] = { { .procname = "reconnect_min_delay_ms", .data = &rds_sysctl_reconnect_min_jiffies, diff --git a/net/rose/sysctl_net_rose.c b/net/rose/sysctl_net_rose.c index 94ca9c2ccd69..89a9278795a9 100644 --- a/net/rose/sysctl_net_rose.c +++ b/net/rose/sysctl_net_rose.c @@ -24,7 +24,7 @@ static int min_window[] = {1}, max_window[] = {7}; static struct ctl_table_header *rose_table_header; -static ctl_table rose_table[] = { +static struct ctl_table rose_table[] = { { .procname = "restart_request_timeout", .data = &sysctl_rose_restart_request_timeout, diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index bf3c6e8fc401..9a5c4c9eddaf 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -62,12 +62,12 @@ extern long sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; extern int sysctl_sctp_wmem[3]; -static int proc_sctp_do_hmac_alg(ctl_table *ctl, +static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -static ctl_table sctp_table[] = { +static struct ctl_table sctp_table[] = { { .procname = "sctp_mem", .data = &sysctl_sctp_mem, @@ -93,7 +93,7 @@ static ctl_table sctp_table[] = { { /* sentinel */ } }; -static ctl_table sctp_net_table[] = { +static struct ctl_table sctp_net_table[] = { { .procname = "rto_initial", .data = &init_net.sctp.rto_initial, @@ -300,14 +300,14 @@ static ctl_table sctp_net_table[] = { { /* sentinel */ } }; -static int proc_sctp_do_hmac_alg(ctl_table *ctl, +static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; char tmp[8]; - ctl_table tbl; + struct ctl_table tbl; int ret; int changed = 0; char *none = "none"; diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index af7d339add9d..c99c58e2ee66 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -40,7 +40,7 @@ EXPORT_SYMBOL_GPL(nlm_debug); #ifdef RPC_DEBUG static struct ctl_table_header *sunrpc_table_header; -static ctl_table sunrpc_table[]; +static struct ctl_table sunrpc_table[]; void rpc_register_sysctl(void) @@ -58,7 +58,7 @@ rpc_unregister_sysctl(void) } } -static int proc_do_xprt(ctl_table *table, int write, +static int proc_do_xprt(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[256]; @@ -73,7 +73,7 @@ static int proc_do_xprt(ctl_table *table, int write, } static int -proc_dodebug(ctl_table *table, int write, +proc_dodebug(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[20], c, *s; @@ -135,7 +135,7 @@ done: } -static ctl_table debug_table[] = { +static struct ctl_table debug_table[] = { { .procname = "rpc_debug", .data = &rpc_debug, @@ -173,7 +173,7 @@ static ctl_table debug_table[] = { { } }; -static ctl_table sunrpc_table[] = { +static struct ctl_table sunrpc_table[] = { { .procname = "sunrpc", .mode = 0555, diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 8343737e85f4..c1b6270262c2 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -84,7 +84,7 @@ struct workqueue_struct *svc_rdma_wq; * resets the associated statistic to zero. Any read returns it's * current value. */ -static int read_reset_stat(ctl_table *table, int write, +static int read_reset_stat(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -119,7 +119,7 @@ static int read_reset_stat(ctl_table *table, int write, } static struct ctl_table_header *svcrdma_table_header; -static ctl_table svcrdma_parm_table[] = { +static struct ctl_table svcrdma_parm_table[] = { { .procname = "max_requests", .data = &svcrdma_max_requests, @@ -214,7 +214,7 @@ static ctl_table svcrdma_parm_table[] = { { }, }; -static ctl_table svcrdma_table[] = { +static struct ctl_table svcrdma_table[] = { { .procname = "svc_rdma", .mode = 0555, @@ -223,7 +223,7 @@ static ctl_table svcrdma_table[] = { { }, }; -static ctl_table svcrdma_root_table[] = { +static struct ctl_table svcrdma_root_table[] = { { .procname = "sunrpc", .mode = 0555, diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 794312f22b9b..285dc0884115 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -86,7 +86,7 @@ static unsigned int max_memreg = RPCRDMA_LAST - 1; static struct ctl_table_header *sunrpc_table_header; -static ctl_table xr_tunables_table[] = { +static struct ctl_table xr_tunables_table[] = { { .procname = "rdma_slot_table_entries", .data = &xprt_rdma_slot_table_entries, @@ -138,7 +138,7 @@ static ctl_table xr_tunables_table[] = { { }, }; -static ctl_table sunrpc_table[] = { +static struct ctl_table sunrpc_table[] = { { .procname = "sunrpc", .mode = 0555, diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ffd50348a509..412de7cfcc80 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -87,7 +87,7 @@ static struct ctl_table_header *sunrpc_table_header; * FIXME: changing the UDP slot table size should also resize the UDP * socket buffers for existing UDP transports */ -static ctl_table xs_tunables_table[] = { +static struct ctl_table xs_tunables_table[] = { { .procname = "udp_slot_table_entries", .data = &xprt_udp_slot_table_entries, @@ -143,7 +143,7 @@ static ctl_table xs_tunables_table[] = { { }, }; -static ctl_table sunrpc_table[] = { +static struct ctl_table sunrpc_table[] = { { .procname = "sunrpc", .mode = 0555, diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c index 8800604c93f4..b3d515021b74 100644 --- a/net/unix/sysctl_net_unix.c +++ b/net/unix/sysctl_net_unix.c @@ -15,7 +15,7 @@ #include -static ctl_table unix_table[] = { +static struct ctl_table unix_table[] = { { .procname = "max_dgram_qlen", .data = &init_net.unx.sysctl_max_dgram_qlen, -- cgit v1.2.3 From 06f3d7f973ec04290d86b7dd91b48d38d90433dc Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 18 Jun 2013 10:08:06 +0300 Subject: ipvs: SCTP ports should be writable in ICMP packets Make sure that SCTP ports are writable when embedded in ICMP from client, so that ip_vs_nat_icmp can translate them safely. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 05565d2b3a61..23b8eb53a569 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1442,7 +1442,8 @@ ignore_ipip: /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); - if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol) + if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol || + IPPROTO_SCTP == cih->protocol) offset += 2 * sizeof(__u16); verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph); -- cgit v1.2.3 From 130ffbc2638ddc290fcbabe1b9ce6a5d333a6a97 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 12 Jun 2013 17:54:51 +0200 Subject: netfilter: check return code from nla_parse_tested These are the only calls under net/ that do not check nla_parse_nested() for its error code, but simply continue execution. If parsing of netlink attributes fails, we should return with an error instead of continuing. In nearly all of these calls we have a policy attached, that is being type verified during nla_parse_nested(), which we would miss checking for otherwise. Signed-off-by: Daniel Borkmann Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 30 +++++++++++++++++++++++------- net/netfilter/nfnetlink_cthelper.c | 16 ++++++++++++---- net/netfilter/nfnetlink_cttimeout.c | 6 ++++-- 3 files changed, 39 insertions(+), 13 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 6d0f8a17c5b7..f83a52298efe 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -828,7 +828,9 @@ ctnetlink_parse_tuple_ip(struct nlattr *attr, struct nf_conntrack_tuple *tuple) struct nf_conntrack_l3proto *l3proto; int ret = 0; - nla_parse_nested(tb, CTA_IP_MAX, attr, NULL); + ret = nla_parse_nested(tb, CTA_IP_MAX, attr, NULL); + if (ret < 0) + return ret; rcu_read_lock(); l3proto = __nf_ct_l3proto_find(tuple->src.l3num); @@ -895,7 +897,9 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[], memset(tuple, 0, sizeof(*tuple)); - nla_parse_nested(tb, CTA_TUPLE_MAX, cda[type], tuple_nla_policy); + err = nla_parse_nested(tb, CTA_TUPLE_MAX, cda[type], tuple_nla_policy); + if (err < 0) + return err; if (!tb[CTA_TUPLE_IP]) return -EINVAL; @@ -946,9 +950,12 @@ static inline int ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, struct nlattr **helpinfo) { + int err; struct nlattr *tb[CTA_HELP_MAX+1]; - nla_parse_nested(tb, CTA_HELP_MAX, attr, help_nla_policy); + err = nla_parse_nested(tb, CTA_HELP_MAX, attr, help_nla_policy); + if (err < 0) + return err; if (!tb[CTA_HELP_NAME]) return -EINVAL; @@ -1431,7 +1438,9 @@ ctnetlink_change_protoinfo(struct nf_conn *ct, const struct nlattr * const cda[] struct nf_conntrack_l4proto *l4proto; int err = 0; - nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, protoinfo_policy); + err = nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, protoinfo_policy); + if (err < 0) + return err; rcu_read_lock(); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); @@ -1452,9 +1461,12 @@ static const struct nla_policy nat_seq_policy[CTA_NAT_SEQ_MAX+1] = { static inline int change_nat_seq_adj(struct nf_nat_seq *natseq, const struct nlattr * const attr) { + int err; struct nlattr *cda[CTA_NAT_SEQ_MAX+1]; - nla_parse_nested(cda, CTA_NAT_SEQ_MAX, attr, nat_seq_policy); + err = nla_parse_nested(cda, CTA_NAT_SEQ_MAX, attr, nat_seq_policy); + if (err < 0) + return err; if (!cda[CTA_NAT_SEQ_CORRECTION_POS]) return -EINVAL; @@ -2115,7 +2127,9 @@ ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct) struct nlattr *cda[CTA_MAX+1]; int ret; - nla_parse_nested(cda, CTA_MAX, attr, ct_nla_policy); + ret = nla_parse_nested(cda, CTA_MAX, attr, ct_nla_policy); + if (ret < 0) + return ret; spin_lock_bh(&nf_conntrack_lock); ret = ctnetlink_nfqueue_parse_ct((const struct nlattr **)cda, ct); @@ -2710,7 +2724,9 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, struct nf_conntrack_tuple nat_tuple = {}; int err; - nla_parse_nested(tb, CTA_EXPECT_NAT_MAX, attr, exp_nat_nla_policy); + err = nla_parse_nested(tb, CTA_EXPECT_NAT_MAX, attr, exp_nat_nla_policy); + if (err < 0) + return err; if (!tb[CTA_EXPECT_NAT_DIR] || !tb[CTA_EXPECT_NAT_TUPLE]) return -EINVAL; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index a191b6db657e..9e287cb56a04 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -67,9 +67,12 @@ static int nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple, const struct nlattr *attr) { + int err; struct nlattr *tb[NFCTH_TUPLE_MAX+1]; - nla_parse_nested(tb, NFCTH_TUPLE_MAX, attr, nfnl_cthelper_tuple_pol); + err = nla_parse_nested(tb, NFCTH_TUPLE_MAX, attr, nfnl_cthelper_tuple_pol); + if (err < 0) + return err; if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM]) return -EINVAL; @@ -121,9 +124,12 @@ static int nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy, const struct nlattr *attr) { + int err; struct nlattr *tb[NFCTH_POLICY_MAX+1]; - nla_parse_nested(tb, NFCTH_POLICY_MAX, attr, nfnl_cthelper_expect_pol); + err = nla_parse_nested(tb, NFCTH_POLICY_MAX, attr, nfnl_cthelper_expect_pol); + if (err < 0) + return err; if (!tb[NFCTH_POLICY_NAME] || !tb[NFCTH_POLICY_EXPECT_MAX] || @@ -153,8 +159,10 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper, struct nf_conntrack_expect_policy *expect_policy; struct nlattr *tb[NFCTH_POLICY_SET_MAX+1]; - nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr, - nfnl_cthelper_expect_policy_set); + ret = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr, + nfnl_cthelper_expect_policy_set); + if (ret < 0) + return ret; if (!tb[NFCTH_POLICY_SET_NUM]) return -EINVAL; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 65074dfb9383..50580494148d 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -59,8 +59,10 @@ ctnl_timeout_parse_policy(struct ctnl_timeout *timeout, if (likely(l4proto->ctnl_timeout.nlattr_to_obj)) { struct nlattr *tb[l4proto->ctnl_timeout.nlattr_max+1]; - nla_parse_nested(tb, l4proto->ctnl_timeout.nlattr_max, - attr, l4proto->ctnl_timeout.nla_policy); + ret = nla_parse_nested(tb, l4proto->ctnl_timeout.nlattr_max, + attr, l4proto->ctnl_timeout.nla_policy); + if (ret < 0) + return ret; ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, &timeout->data); -- cgit v1.2.3 From 6547a221871f139cc56328a38105d47c14874cbe Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Jun 2013 17:31:28 +0200 Subject: netfilter: nf_conntrack: avoid large timeout for mid-stream pickup When loose tracking is enabled (default), non-syn packets cause creation of new conntracks in established state with default timeout for established state (5 days). This causes the table to fill up with UNREPLIED when the 'new ack' packet happened to be the last-ack of a previous, already timed-out connection. Consider: A 192.168.x.52792 > 10.184.y.80: F, 426:426(0) ack 9237 win 255 B 10.184.y.80 > 192.168.x.52792: ., ack 427 win 123 <61 second pause> C 10.184.y.80 > 192.168.x.52792: F, 9237:9237(0) ack 427 win 123 D 192.168.x.52792 > 10.184.y.80: ., ack 9238 win 255 B moves conntrack to CLOSE_WAIT and will kill it after 60 second timeout, C is ignored (FIN set), but last packet (D) causes new ct with 5-days timeout. Use UNACK timeout (5 minutes) instead to get rid of these entries sooner when in ESTABLISHED state without having seen traffic in both directions. Signed-off-by: Florian Westphal Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_tcp.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 4d4d8f1d01fc..7dcc376eea5f 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1043,6 +1043,12 @@ static int tcp_packet(struct nf_conn *ct, nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } + /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection + * pickup with loose=1. Avoid large ESTABLISHED timeout. + */ + if (new_state == TCP_CONNTRACK_ESTABLISHED && + timeout > timeouts[TCP_CONNTRACK_UNACK]) + timeout = timeouts[TCP_CONNTRACK_UNACK]; } else if (!test_bit(IPS_ASSURED_BIT, &ct->status) && (old_state == TCP_CONNTRACK_SYN_RECV || old_state == TCP_CONNTRACK_ESTABLISHED) -- cgit v1.2.3 From 681f130f39e10087475383e6771b9366e26bab0c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 20 Jun 2013 05:52:22 -0700 Subject: netfilter: xt_socket: add XT_SOCKET_NOWILDCARD flag xt_socket module can be a nice replacement to conntrack module in some cases (SYN filtering for example) But it lacks the ability to match the 3rd packet of TCP handshake (ACK coming from the client). Add a XT_SOCKET_NOWILDCARD flag to disable the wildcard mechanism. The wildcard is the legacy socket match behavior, that ignores LISTEN sockets bound to INADDR_ANY (or ipv6 equivalent) iptables -I INPUT -p tcp --syn -j SYN_CHAIN iptables -I INPUT -m socket --nowildcard -j ACCEPT Signed-off-by: Eric Dumazet Cc: Patrick McHardy Cc: Jesper Dangaard Brouer Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/xt_socket.h | 7 ++++ net/netfilter/xt_socket.c | 70 ++++++++++++++++++++++++++++---- 2 files changed, 69 insertions(+), 8 deletions(-) (limited to 'net/netfilter') diff --git a/include/uapi/linux/netfilter/xt_socket.h b/include/uapi/linux/netfilter/xt_socket.h index 26d7217bd4f1..6315e2ac3474 100644 --- a/include/uapi/linux/netfilter/xt_socket.h +++ b/include/uapi/linux/netfilter/xt_socket.h @@ -5,10 +5,17 @@ enum { XT_SOCKET_TRANSPARENT = 1 << 0, + XT_SOCKET_NOWILDCARD = 1 << 1, }; struct xt_socket_mtinfo1 { __u8 flags; }; +#define XT_SOCKET_FLAGS_V1 XT_SOCKET_TRANSPARENT + +struct xt_socket_mtinfo2 { + __u8 flags; +}; +#define XT_SOCKET_FLAGS_V2 (XT_SOCKET_TRANSPARENT | XT_SOCKET_NOWILDCARD) #endif /* _XT_SOCKET_H */ diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 02704245710e..f8b71911037a 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -163,8 +163,11 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, bool wildcard; bool transparent = true; - /* Ignore sockets listening on INADDR_ANY */ - wildcard = (sk->sk_state != TCP_TIME_WAIT && + /* Ignore sockets listening on INADDR_ANY, + * unless XT_SOCKET_NOWILDCARD is set + */ + wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && + sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->inet_rcv_saddr == 0); /* Ignore non-transparent sockets, @@ -197,7 +200,7 @@ socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par) } static bool -socket_mt4_v1(const struct sk_buff *skb, struct xt_action_param *par) +socket_mt4_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) { return socket_match(skb, par, par->matchinfo); } @@ -259,7 +262,7 @@ extract_icmp6_fields(const struct sk_buff *skb, } static bool -socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) +socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) { struct ipv6hdr *iph = ipv6_hdr(skb); struct udphdr _hdr, *hp = NULL; @@ -302,8 +305,11 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) bool wildcard; bool transparent = true; - /* Ignore sockets listening on INADDR_ANY */ - wildcard = (sk->sk_state != TCP_TIME_WAIT && + /* Ignore sockets listening on INADDR_ANY + * unless XT_SOCKET_NOWILDCARD is set + */ + wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && + sk->sk_state != TCP_TIME_WAIT && ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)); /* Ignore non-transparent sockets, @@ -331,6 +337,28 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) } #endif +static int socket_mt_v1_check(const struct xt_mtchk_param *par) +{ + const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; + + if (info->flags & ~XT_SOCKET_FLAGS_V1) { + pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V1); + return -EINVAL; + } + return 0; +} + +static int socket_mt_v2_check(const struct xt_mtchk_param *par) +{ + const struct xt_socket_mtinfo2 *info = (struct xt_socket_mtinfo2 *) par->matchinfo; + + if (info->flags & ~XT_SOCKET_FLAGS_V2) { + pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V2); + return -EINVAL; + } + return 0; +} + static struct xt_match socket_mt_reg[] __read_mostly = { { .name = "socket", @@ -345,7 +373,8 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .name = "socket", .revision = 1, .family = NFPROTO_IPV4, - .match = socket_mt4_v1, + .match = socket_mt4_v1_v2, + .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), @@ -356,7 +385,32 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .name = "socket", .revision = 1, .family = NFPROTO_IPV6, - .match = socket_mt6_v1, + .match = socket_mt6_v1_v2, + .checkentry = socket_mt_v1_check, + .matchsize = sizeof(struct xt_socket_mtinfo1), + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, +#endif + { + .name = "socket", + .revision = 2, + .family = NFPROTO_IPV4, + .match = socket_mt4_v1_v2, + .checkentry = socket_mt_v2_check, + .matchsize = sizeof(struct xt_socket_mtinfo1), + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, +#ifdef XT_SOCKET_HAVE_IPV6 + { + .name = "socket", + .revision = 2, + .family = NFPROTO_IPV6, + .match = socket_mt6_v1_v2, + .checkentry = socket_mt_v2_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), -- cgit v1.2.3 From 5aed93875cd88502f04a0d4517b8a2d89a849773 Mon Sep 17 00:00:00 2001 From: Balazs Peter Odor Date: Sat, 22 Jun 2013 19:24:43 +0200 Subject: netfilter: nf_nat_sip: fix mangling In (b20ab9c netfilter: nf_ct_helper: better logging for dropped packets) there were some missing brackets around the logging information, thus always returning drop. Closes https://bugzilla.kernel.org/show_bug.cgi?id=60061 Signed-off-by: Balazs Peter Odor Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_sip.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index 96ccdf78a29f..dac11f73868e 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -230,9 +230,10 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, &ct->tuplehash[!dir].tuple.src.u3, false); if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, - poff, plen, buffer, buflen)) + poff, plen, buffer, buflen)) { nf_ct_helper_log(skb, ct, "cannot mangle received"); return NF_DROP; + } } /* The rport= parameter (RFC 3581) contains the port number -- cgit v1.2.3 From 797a7d66d2048fe8a4ac1ba58c5d4752d64b1ac4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 21 Jun 2013 16:51:30 +0200 Subject: netfilter: ctnetlink: send event when conntrack label was modified commit 0ceabd83875b72a29f33db4ab703d6ba40ea4c58 (netfilter: ctnetlink: deliver labels to userspace) sets the event bit when we raced with another packet, instead of raising the event bit when the label bit is set for the first time. commit 9b21f6a90924dfe8e5e686c314ddb441fb06501e (netfilter: ctnetlink: allow userspace to modify labels) forgot to update the event mask in the "conntrack already exists" case. Both issues result in CTA_LABELS attribute not getting included in the conntrack event. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_labels.c | 2 +- net/netfilter/nf_conntrack_netlink.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c index 8fe2e99428b7..355d2ef08094 100644 --- a/net/netfilter/nf_conntrack_labels.c +++ b/net/netfilter/nf_conntrack_labels.c @@ -45,7 +45,7 @@ int nf_connlabel_set(struct nf_conn *ct, u16 bit) if (test_bit(bit, labels->bits)) return 0; - if (test_and_set_bit(bit, labels->bits)) + if (!test_and_set_bit(bit, labels->bits)) nf_conntrack_event_cache(IPCT_LABEL, ct); return 0; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 6d0f8a17c5b7..ecf065f94032 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1825,6 +1825,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | + (1 << IPCT_LABEL) | (1 << IPCT_PROTOINFO) | (1 << IPCT_NATSEQADJ) | (1 << IPCT_MARK), -- cgit v1.2.3 From bba54de5bdd107d3841b560f1a9cb0ed06e79533 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 16 Jun 2013 09:09:36 +0300 Subject: ipvs: provide iph to schedulers Before now the schedulers needed access only to IP addresses and it was easy to get them from skb by using ip_vs_fill_iph_addr_only. New changes for the SH scheduler will need the protocol and ports which is difficult to get from skb for the IPv6 case. As we have all the data in the iph structure, to avoid the same slow lookups provide the iph to schedulers. Signed-off-by: Julian Anastasov Acked-by: Hans Schillstrom Signed-off-by: Simon Horman --- include/net/ip_vs.h | 28 ++-------------------------- net/netfilter/ipvs/ip_vs_core.c | 4 ++-- net/netfilter/ipvs/ip_vs_dh.c | 10 ++++------ net/netfilter/ipvs/ip_vs_lblc.c | 12 +++++------- net/netfilter/ipvs/ip_vs_lblcr.c | 12 +++++------- net/netfilter/ipvs/ip_vs_lc.c | 3 ++- net/netfilter/ipvs/ip_vs_nq.c | 3 ++- net/netfilter/ipvs/ip_vs_rr.c | 3 ++- net/netfilter/ipvs/ip_vs_sed.c | 3 ++- net/netfilter/ipvs/ip_vs_sh.c | 10 ++++------ net/netfilter/ipvs/ip_vs_wlc.c | 3 ++- net/netfilter/ipvs/ip_vs_wrr.c | 3 ++- 12 files changed, 34 insertions(+), 60 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 4405886980c7..f5faf859876e 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -197,31 +197,6 @@ ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr) } } -/* This function is a faster version of ip_vs_fill_iph_skb(). - * Where we only populate {s,d}addr (and avoid calling ipv6_find_hdr()). - * This is used by the some of the ip_vs_*_schedule() functions. - * (Mostly done to avoid ABI breakage of external schedulers) - */ -static inline void -ip_vs_fill_iph_addr_only(int af, const struct sk_buff *skb, - struct ip_vs_iphdr *iphdr) -{ -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - const struct ipv6hdr *iph = - (struct ipv6hdr *)skb_network_header(skb); - iphdr->saddr.in6 = iph->saddr; - iphdr->daddr.in6 = iph->daddr; - } else -#endif - { - const struct iphdr *iph = - (struct iphdr *)skb_network_header(skb); - iphdr->saddr.ip = iph->saddr; - iphdr->daddr.ip = iph->daddr; - } -} - static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst, const union nf_inet_addr *src) { @@ -814,7 +789,8 @@ struct ip_vs_scheduler { /* selecting a server from the given service */ struct ip_vs_dest* (*schedule)(struct ip_vs_service *svc, - const struct sk_buff *skb); + const struct sk_buff *skb, + struct ip_vs_iphdr *iph); }; /* The persistence engine object */ diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 05565d2b3a61..e9b0330f220d 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -305,7 +305,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * return *ignored=0 i.e. ICMP and NF_DROP */ sched = rcu_dereference(svc->scheduler); - dest = sched->schedule(svc, skb); + dest = sched->schedule(svc, skb, iph); if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); @@ -452,7 +452,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, } sched = rcu_dereference(svc->scheduler); - dest = sched->schedule(svc, skb); + dest = sched->schedule(svc, skb, iph); if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); return NULL; diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c index ccab120df45e..c3b84546ea9e 100644 --- a/net/netfilter/ipvs/ip_vs_dh.c +++ b/net/netfilter/ipvs/ip_vs_dh.c @@ -214,18 +214,16 @@ static inline int is_overloaded(struct ip_vs_dest *dest) * Destination hashing scheduling */ static struct ip_vs_dest * -ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) +ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest; struct ip_vs_dh_state *s; - struct ip_vs_iphdr iph; - - ip_vs_fill_iph_addr_only(svc->af, skb, &iph); IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); s = (struct ip_vs_dh_state *) svc->sched_data; - dest = ip_vs_dh_get(svc->af, s, &iph.daddr); + dest = ip_vs_dh_get(svc->af, s, &iph->daddr); if (!dest || !(dest->flags & IP_VS_DEST_F_AVAILABLE) || atomic_read(&dest->weight) <= 0 @@ -235,7 +233,7 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) } IP_VS_DBG_BUF(6, "DH: destination IP address %s --> server %s:%d\n", - IP_VS_DBG_ADDR(svc->af, &iph.daddr), + IP_VS_DBG_ADDR(svc->af, &iph->daddr), IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port)); diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 44595b8ae37f..1383b0eadc0e 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -487,19 +487,17 @@ is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc) * Locality-Based (weighted) Least-Connection scheduling */ static struct ip_vs_dest * -ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) +ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) { struct ip_vs_lblc_table *tbl = svc->sched_data; - struct ip_vs_iphdr iph; struct ip_vs_dest *dest = NULL; struct ip_vs_lblc_entry *en; - ip_vs_fill_iph_addr_only(svc->af, skb, &iph); - IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); /* First look in our cache */ - en = ip_vs_lblc_get(svc->af, tbl, &iph.daddr); + en = ip_vs_lblc_get(svc->af, tbl, &iph->daddr); if (en) { /* We only hold a read lock, but this is atomic */ en->lastuse = jiffies; @@ -529,12 +527,12 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) /* If we fail to create a cache entry, we'll just use the valid dest */ spin_lock_bh(&svc->sched_lock); if (!tbl->dead) - ip_vs_lblc_new(tbl, &iph.daddr, dest); + ip_vs_lblc_new(tbl, &iph->daddr, dest); spin_unlock_bh(&svc->sched_lock); out: IP_VS_DBG_BUF(6, "LBLC: destination IP address %s --> server %s:%d\n", - IP_VS_DBG_ADDR(svc->af, &iph.daddr), + IP_VS_DBG_ADDR(svc->af, &iph->daddr), IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port)); return dest; diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 876937db0bf4..3cd85b2fc67c 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -655,19 +655,17 @@ is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc) * Locality-Based (weighted) Least-Connection scheduling */ static struct ip_vs_dest * -ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) +ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) { struct ip_vs_lblcr_table *tbl = svc->sched_data; - struct ip_vs_iphdr iph; struct ip_vs_dest *dest; struct ip_vs_lblcr_entry *en; - ip_vs_fill_iph_addr_only(svc->af, skb, &iph); - IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); /* First look in our cache */ - en = ip_vs_lblcr_get(svc->af, tbl, &iph.daddr); + en = ip_vs_lblcr_get(svc->af, tbl, &iph->daddr); if (en) { en->lastuse = jiffies; @@ -718,12 +716,12 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) /* If we fail to create a cache entry, we'll just use the valid dest */ spin_lock_bh(&svc->sched_lock); if (!tbl->dead) - ip_vs_lblcr_new(tbl, &iph.daddr, dest); + ip_vs_lblcr_new(tbl, &iph->daddr, dest); spin_unlock_bh(&svc->sched_lock); out: IP_VS_DBG_BUF(6, "LBLCR: destination IP address %s --> server %s:%d\n", - IP_VS_DBG_ADDR(svc->af, &iph.daddr), + IP_VS_DBG_ADDR(svc->af, &iph->daddr), IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port)); return dest; diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c index 5128e338a749..2bdcb1cf2127 100644 --- a/net/netfilter/ipvs/ip_vs_lc.c +++ b/net/netfilter/ipvs/ip_vs_lc.c @@ -26,7 +26,8 @@ * Least Connection scheduling */ static struct ip_vs_dest * -ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) +ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least = NULL; unsigned int loh = 0, doh; diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c index 646cfd4baa73..d8d9860934fe 100644 --- a/net/netfilter/ipvs/ip_vs_nq.c +++ b/net/netfilter/ipvs/ip_vs_nq.c @@ -55,7 +55,8 @@ ip_vs_nq_dest_overhead(struct ip_vs_dest *dest) * Weighted Least Connection scheduling */ static struct ip_vs_dest * -ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) +ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least = NULL; unsigned int loh = 0, doh; diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c index c35986c793d9..176b87c35e34 100644 --- a/net/netfilter/ipvs/ip_vs_rr.c +++ b/net/netfilter/ipvs/ip_vs_rr.c @@ -55,7 +55,8 @@ static int ip_vs_rr_del_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest) * Round-Robin Scheduling */ static struct ip_vs_dest * -ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) +ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) { struct list_head *p; struct ip_vs_dest *dest, *last; diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c index f3205925359a..a5284cc3d882 100644 --- a/net/netfilter/ipvs/ip_vs_sed.c +++ b/net/netfilter/ipvs/ip_vs_sed.c @@ -59,7 +59,8 @@ ip_vs_sed_dest_overhead(struct ip_vs_dest *dest) * Weighted Least Connection scheduling */ static struct ip_vs_dest * -ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) +ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least; unsigned int loh, doh; diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index a65edfe4b16c..e0d5d1653566 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -227,18 +227,16 @@ static inline int is_overloaded(struct ip_vs_dest *dest) * Source Hashing scheduling */ static struct ip_vs_dest * -ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) +ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest; struct ip_vs_sh_state *s; - struct ip_vs_iphdr iph; - - ip_vs_fill_iph_addr_only(svc->af, skb, &iph); IP_VS_DBG(6, "ip_vs_sh_schedule(): Scheduling...\n"); s = (struct ip_vs_sh_state *) svc->sched_data; - dest = ip_vs_sh_get(svc->af, s, &iph.saddr); + dest = ip_vs_sh_get(svc->af, s, &iph->saddr); if (!dest || !(dest->flags & IP_VS_DEST_F_AVAILABLE) || atomic_read(&dest->weight) <= 0 @@ -248,7 +246,7 @@ ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) } IP_VS_DBG_BUF(6, "SH: source IP address %s --> server %s:%d\n", - IP_VS_DBG_ADDR(svc->af, &iph.saddr), + IP_VS_DBG_ADDR(svc->af, &iph->saddr), IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port)); diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c index c60a81c4ce9a..6dc1fa128840 100644 --- a/net/netfilter/ipvs/ip_vs_wlc.c +++ b/net/netfilter/ipvs/ip_vs_wlc.c @@ -31,7 +31,8 @@ * Weighted Least Connection scheduling */ static struct ip_vs_dest * -ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) +ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least; unsigned int loh, doh; diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c index 0e68555bceb9..0546cd572d6b 100644 --- a/net/netfilter/ipvs/ip_vs_wrr.c +++ b/net/netfilter/ipvs/ip_vs_wrr.c @@ -162,7 +162,8 @@ static int ip_vs_wrr_dest_changed(struct ip_vs_service *svc, * Weighted Round-Robin Scheduling */ static struct ip_vs_dest * -ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) +ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *last, *stop = NULL; struct ip_vs_wrr_mark *mark = svc->sched_data; -- cgit v1.2.3 From c6c96c188336b2b95d5f14facd101f1e4165a9d3 Mon Sep 17 00:00:00 2001 From: Alexander Frolkin Date: Thu, 13 Jun 2013 08:56:15 +0100 Subject: ipvs: sloppy TCP and SCTP This adds support for sloppy TCP and SCTP modes to IPVS. When enabled (sysctls net.ipv4.vs.sloppy_tcp and net.ipv4.vs.sloppy_sctp), allows IPVS to create connection state on any packet, not just a TCP SYN (or SCTP INIT). This allows connections to fail over from one IPVS director to another mid-flight. Signed-off-by: Alexander Frolkin Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 24 ++++++++++++++++++++++++ net/netfilter/ipvs/ip_vs_ctl.c | 14 ++++++++++++++ net/netfilter/ipvs/ip_vs_proto_sctp.c | 18 ++++++++++-------- net/netfilter/ipvs/ip_vs_proto_tcp.c | 14 ++++++++------ 4 files changed, 56 insertions(+), 14 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index f5faf859876e..95860dfdfbe3 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -978,6 +978,8 @@ struct netns_ipvs { int sysctl_sync_sock_size; int sysctl_cache_bypass; int sysctl_expire_nodest_conn; + int sysctl_sloppy_tcp; + int sysctl_sloppy_sctp; int sysctl_expire_quiescent_template; int sysctl_sync_threshold[2]; unsigned int sysctl_sync_refresh_period; @@ -1020,6 +1022,8 @@ struct netns_ipvs { #define DEFAULT_SYNC_THRESHOLD 3 #define DEFAULT_SYNC_PERIOD 50 #define DEFAULT_SYNC_VER 1 +#define DEFAULT_SLOPPY_TCP 0 +#define DEFAULT_SLOPPY_SCTP 0 #define DEFAULT_SYNC_REFRESH_PERIOD (0U * HZ) #define DEFAULT_SYNC_RETRIES 0 #define IPVS_SYNC_WAKEUP_RATE 8 @@ -1056,6 +1060,16 @@ static inline int sysctl_sync_ver(struct netns_ipvs *ipvs) return ipvs->sysctl_sync_ver; } +static inline int sysctl_sloppy_tcp(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_sloppy_tcp; +} + +static inline int sysctl_sloppy_sctp(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_sloppy_sctp; +} + static inline int sysctl_sync_ports(struct netns_ipvs *ipvs) { return ACCESS_ONCE(ipvs->sysctl_sync_ports); @@ -1109,6 +1123,16 @@ static inline int sysctl_sync_ver(struct netns_ipvs *ipvs) return DEFAULT_SYNC_VER; } +static inline int sysctl_sloppy_tcp(struct netns_ipvs *ipvs) +{ + return DEFAULT_SLOPPY_TCP; +} + +static inline int sysctl_sloppy_sctp(struct netns_ipvs *ipvs) +{ + return DEFAULT_SLOPPY_SCTP; +} + static inline int sysctl_sync_ports(struct netns_ipvs *ipvs) { return 1; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 47e510819f54..da035fc01eb2 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1738,6 +1738,18 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "sloppy_tcp", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sloppy_sctp", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "expire_quiescent_template", .maxlen = sizeof(int), @@ -3723,6 +3735,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) tbl[idx++].data = &ipvs->sysctl_sync_sock_size; tbl[idx++].data = &ipvs->sysctl_cache_bypass; tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn; + tbl[idx++].data = &ipvs->sysctl_sloppy_tcp; + tbl[idx++].data = &ipvs->sysctl_sloppy_sctp; tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template; ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD; ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD; diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 86464881cd20..df29d6417043 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -15,6 +15,7 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, { struct net *net; struct ip_vs_service *svc; + struct netns_ipvs *ipvs; sctp_chunkhdr_t _schunkh, *sch; sctp_sctphdr_t *sh, _sctph; @@ -27,13 +28,14 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, if (sch == NULL) return 0; net = skb_net(skb); + ipvs = net_ipvs(net); rcu_read_lock(); - if ((sch->type == SCTP_CID_INIT) && + if ((sch->type == SCTP_CID_INIT || sysctl_sloppy_sctp(ipvs)) && (svc = ip_vs_service_find(net, af, skb->mark, iph->protocol, &iph->daddr, sh->dest))) { int ignored; - if (ip_vs_todrop(net_ipvs(net))) { + if (ip_vs_todrop(ipvs)) { /* * It seems that we are very loaded. * We have to drop this packet :( @@ -232,21 +234,21 @@ static struct ipvs_sctp_nextstate * STATE : IP_VS_SCTP_S_NONE */ /*next state *//*event */ - {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ }, + {{IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_DATA_CLI */ }, {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ }, {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, + {IP_VS_SCTP_S_INIT_ACK_CLI /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, + {IP_VS_SCTP_S_ECHO_CLI /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, + {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ }, + {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ }, {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, + {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }, diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 50a15944c6c1..e3a697234a98 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -39,6 +39,7 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct net *net; struct ip_vs_service *svc; struct tcphdr _tcph, *th; + struct netns_ipvs *ipvs; th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); if (th == NULL) { @@ -46,14 +47,15 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, return 0; } net = skb_net(skb); + ipvs = net_ipvs(net); /* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */ rcu_read_lock(); - if (th->syn && + if ((th->syn || sysctl_sloppy_tcp(ipvs)) && !th->rst && (svc = ip_vs_service_find(net, af, skb->mark, iph->protocol, &iph->daddr, th->dest))) { int ignored; - if (ip_vs_todrop(net_ipvs(net))) { + if (ip_vs_todrop(ipvs)) { /* * It seems that we are very loaded. * We have to drop this packet :( @@ -401,7 +403,7 @@ static struct tcp_states_t tcp_states [] = { /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }}, /*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sTW }}, -/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, +/*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sSR }}, /* OUTPUT */ @@ -415,7 +417,7 @@ static struct tcp_states_t tcp_states [] = { /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }}, /*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }}, -/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, +/*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; @@ -424,7 +426,7 @@ static struct tcp_states_t tcp_states_dos [] = { /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }}, /*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sSA }}, -/*ack*/ {{sCL, sES, sSS, sSR, sFW, sTW, sCL, sCW, sCL, sLI, sSA }}, +/*ack*/ {{sES, sES, sSS, sSR, sFW, sTW, sCL, sCW, sCL, sLI, sSA }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, /* OUTPUT */ @@ -438,7 +440,7 @@ static struct tcp_states_t tcp_states_dos [] = { /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSA, sES, sES, sSR, sSA, sSA, sSA, sSA, sSA, sSA, sSA }}, /*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }}, -/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, +/*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; -- cgit v1.2.3 From 61e7c420b4b2a797ac209106ba743ab6ebe984d8 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 18 Jun 2013 10:08:07 +0300 Subject: ipvs: replace the SCTP state machine Convert the SCTP state table, so that it is more readable. Change the states to be according to the diagram in RFC 2960 and add more states suitable for middle box. Still, such change in states adds incompatibility if systems in sync setup include this change and others do not include it. With this change we also have proper transitions in INPUT-ONLY mode (DR/TUN) where we see packets only from client. Now we should not switch to 10-second CLOSED state at a time when we should stay in ESTABLISHED state. The short names for states are because we have 16-char space in ipvsadm and 11-char limit for the connection list format. It is a sequence of the TCP implementation where the longest state name is ESTABLISHED. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 21 +- net/netfilter/ipvs/ip_vs_proto_sctp.c | 854 ++++++---------------------------- net/netfilter/ipvs/ip_vs_sync.c | 7 +- 3 files changed, 168 insertions(+), 714 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 95860dfdfbe3..e667df171003 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -380,17 +380,18 @@ enum { */ enum ip_vs_sctp_states { IP_VS_SCTP_S_NONE, - IP_VS_SCTP_S_INIT_CLI, - IP_VS_SCTP_S_INIT_SER, - IP_VS_SCTP_S_INIT_ACK_CLI, - IP_VS_SCTP_S_INIT_ACK_SER, - IP_VS_SCTP_S_ECHO_CLI, - IP_VS_SCTP_S_ECHO_SER, + IP_VS_SCTP_S_INIT1, + IP_VS_SCTP_S_INIT, + IP_VS_SCTP_S_COOKIE_SENT, + IP_VS_SCTP_S_COOKIE_REPLIED, + IP_VS_SCTP_S_COOKIE_WAIT, + IP_VS_SCTP_S_COOKIE, + IP_VS_SCTP_S_COOKIE_ECHOED, IP_VS_SCTP_S_ESTABLISHED, - IP_VS_SCTP_S_SHUT_CLI, - IP_VS_SCTP_S_SHUT_SER, - IP_VS_SCTP_S_SHUT_ACK_CLI, - IP_VS_SCTP_S_SHUT_ACK_SER, + IP_VS_SCTP_S_SHUTDOWN_SENT, + IP_VS_SCTP_S_SHUTDOWN_RECEIVED, + IP_VS_SCTP_S_SHUTDOWN_ACK_SENT, + IP_VS_SCTP_S_REJECTED, IP_VS_SCTP_S_CLOSED, IP_VS_SCTP_S_LAST }; diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index df29d6417043..3c0da8728036 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -185,710 +185,159 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) return 1; } -struct ipvs_sctp_nextstate { - int next_state; -}; enum ipvs_sctp_event_t { - IP_VS_SCTP_EVE_DATA_CLI, - IP_VS_SCTP_EVE_DATA_SER, - IP_VS_SCTP_EVE_INIT_CLI, - IP_VS_SCTP_EVE_INIT_SER, - IP_VS_SCTP_EVE_INIT_ACK_CLI, - IP_VS_SCTP_EVE_INIT_ACK_SER, - IP_VS_SCTP_EVE_COOKIE_ECHO_CLI, - IP_VS_SCTP_EVE_COOKIE_ECHO_SER, - IP_VS_SCTP_EVE_COOKIE_ACK_CLI, - IP_VS_SCTP_EVE_COOKIE_ACK_SER, - IP_VS_SCTP_EVE_ABORT_CLI, - IP_VS_SCTP_EVE__ABORT_SER, - IP_VS_SCTP_EVE_SHUT_CLI, - IP_VS_SCTP_EVE_SHUT_SER, - IP_VS_SCTP_EVE_SHUT_ACK_CLI, - IP_VS_SCTP_EVE_SHUT_ACK_SER, - IP_VS_SCTP_EVE_SHUT_COM_CLI, - IP_VS_SCTP_EVE_SHUT_COM_SER, - IP_VS_SCTP_EVE_LAST + IP_VS_SCTP_DATA = 0, /* DATA, SACK, HEARTBEATs */ + IP_VS_SCTP_INIT, + IP_VS_SCTP_INIT_ACK, + IP_VS_SCTP_COOKIE_ECHO, + IP_VS_SCTP_COOKIE_ACK, + IP_VS_SCTP_SHUTDOWN, + IP_VS_SCTP_SHUTDOWN_ACK, + IP_VS_SCTP_SHUTDOWN_COMPLETE, + IP_VS_SCTP_ERROR, + IP_VS_SCTP_ABORT, + IP_VS_SCTP_EVENT_LAST }; -static enum ipvs_sctp_event_t sctp_events[256] = { - IP_VS_SCTP_EVE_DATA_CLI, - IP_VS_SCTP_EVE_INIT_CLI, - IP_VS_SCTP_EVE_INIT_ACK_CLI, - IP_VS_SCTP_EVE_DATA_CLI, - IP_VS_SCTP_EVE_DATA_CLI, - IP_VS_SCTP_EVE_DATA_CLI, - IP_VS_SCTP_EVE_ABORT_CLI, - IP_VS_SCTP_EVE_SHUT_CLI, - IP_VS_SCTP_EVE_SHUT_ACK_CLI, - IP_VS_SCTP_EVE_DATA_CLI, - IP_VS_SCTP_EVE_COOKIE_ECHO_CLI, - IP_VS_SCTP_EVE_COOKIE_ACK_CLI, - IP_VS_SCTP_EVE_DATA_CLI, - IP_VS_SCTP_EVE_DATA_CLI, - IP_VS_SCTP_EVE_SHUT_COM_CLI, +/* RFC 2960, 3.2 Chunk Field Descriptions */ +static __u8 sctp_events[] = { + [SCTP_CID_DATA] = IP_VS_SCTP_DATA, + [SCTP_CID_INIT] = IP_VS_SCTP_INIT, + [SCTP_CID_INIT_ACK] = IP_VS_SCTP_INIT_ACK, + [SCTP_CID_SACK] = IP_VS_SCTP_DATA, + [SCTP_CID_HEARTBEAT] = IP_VS_SCTP_DATA, + [SCTP_CID_HEARTBEAT_ACK] = IP_VS_SCTP_DATA, + [SCTP_CID_ABORT] = IP_VS_SCTP_ABORT, + [SCTP_CID_SHUTDOWN] = IP_VS_SCTP_SHUTDOWN, + [SCTP_CID_SHUTDOWN_ACK] = IP_VS_SCTP_SHUTDOWN_ACK, + [SCTP_CID_ERROR] = IP_VS_SCTP_ERROR, + [SCTP_CID_COOKIE_ECHO] = IP_VS_SCTP_COOKIE_ECHO, + [SCTP_CID_COOKIE_ACK] = IP_VS_SCTP_COOKIE_ACK, + [SCTP_CID_ECN_ECNE] = IP_VS_SCTP_DATA, + [SCTP_CID_ECN_CWR] = IP_VS_SCTP_DATA, + [SCTP_CID_SHUTDOWN_COMPLETE] = IP_VS_SCTP_SHUTDOWN_COMPLETE, }; -static struct ipvs_sctp_nextstate - sctp_states_table[IP_VS_SCTP_S_LAST][IP_VS_SCTP_EVE_LAST] = { - /* - * STATE : IP_VS_SCTP_S_NONE - */ - /*next state *//*event */ - {{IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ }, - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - {IP_VS_SCTP_S_INIT_ACK_CLI /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - {IP_VS_SCTP_S_ECHO_CLI /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ }, - {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }, - }, - /* - * STATE : IP_VS_SCTP_S_INIT_CLI - * Cient sent INIT and is waiting for reply from server(In ECHO_WAIT) - */ - {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ }, - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - {IP_VS_SCTP_S_INIT_ACK_SER /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ECHO_CLI */ }, - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_ECHO_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - }, - /* - * State : IP_VS_SCTP_S_INIT_SER - * Server sent INIT and waiting for INIT ACK from the client - */ - {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ }, - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - {IP_VS_SCTP_S_INIT_ACK_CLI /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - }, - /* - * State : IP_VS_SCTP_S_INIT_ACK_CLI - * Client sent INIT ACK and waiting for ECHO from the server - */ - {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ }, - /* - * We have got an INIT from client. From the spec.“Upon receipt of - * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with - * an INIT ACK using the same parameters it sent in its original - * INIT chunk (including its Initiate Tag, unchanged”). - */ - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - /* - * INIT_ACK has been resent by the client, let us stay is in - * the same state - */ - {IP_VS_SCTP_S_INIT_ACK_CLI /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - /* - * INIT_ACK sent by the server, close the connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - /* - * ECHO by client, it should not happen, close the connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - /* - * ECHO by server, this is what we are expecting, move to ECHO_SER - */ - {IP_VS_SCTP_S_ECHO_SER /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - /* - * COOKIE ACK from client, it should not happen, close the connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - /* - * Unexpected COOKIE ACK from server, staty in the same state - */ - {IP_VS_SCTP_S_INIT_ACK_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - }, - /* - * State : IP_VS_SCTP_S_INIT_ACK_SER - * Server sent INIT ACK and waiting for ECHO from the client - */ - {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ }, - /* - * We have got an INIT from client. From the spec.“Upon receipt of - * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with - * an INIT ACK using the same parameters it sent in its original - * INIT chunk (including its Initiate Tag, unchanged”). - */ - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - /* - * Unexpected INIT_ACK by the client, let us close the connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - /* - * INIT_ACK resent by the server, let us move to same state - */ - {IP_VS_SCTP_S_INIT_ACK_SER /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - /* - * Client send the ECHO, this is what we are expecting, - * move to ECHO_CLI - */ - {IP_VS_SCTP_S_ECHO_CLI /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - /* - * ECHO received from the server, Not sure what to do, - * let us close it - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - /* - * COOKIE ACK from client, let us stay in the same state - */ - {IP_VS_SCTP_S_INIT_ACK_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - /* - * COOKIE ACK from server, hmm... this should not happen, lets close - * the connection. - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - }, - /* - * State : IP_VS_SCTP_S_ECHO_CLI - * Cient sent ECHO and waiting COOKEI ACK from the Server - */ - {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ }, - /* - * We have got an INIT from client. From the spec.“Upon receipt of - * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with - * an INIT ACK using the same parameters it sent in its original - * INIT chunk (including its Initiate Tag, unchanged”). - */ - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - /* - * INIT_ACK has been by the client, let us close the connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - /* - * INIT_ACK sent by the server, Unexpected INIT ACK, spec says, - * “If an INIT ACK is received by an endpoint in any state other - * than the COOKIE-WAIT state, the endpoint should discard the - * INIT ACK chunk”. Stay in the same state - */ - {IP_VS_SCTP_S_ECHO_CLI /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - /* - * Client resent the ECHO, let us stay in the same state - */ - {IP_VS_SCTP_S_ECHO_CLI /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - /* - * ECHO received from the server, Not sure what to do, - * let us close it - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - /* - * COOKIE ACK from client, this shoud not happen, let's close the - * connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - /* - * COOKIE ACK from server, this is what we are awaiting,lets move to - * ESTABLISHED. - */ - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - }, - /* - * State : IP_VS_SCTP_S_ECHO_SER - * Server sent ECHO and waiting COOKEI ACK from the client - */ - {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ }, - /* - * We have got an INIT from client. From the spec.“Upon receipt of - * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with - * an INIT ACK using the same parameters it sent in its original - * INIT chunk (including its Initiate Tag, unchanged”). - */ - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - /* - * INIT_ACK sent by the server, Unexpected INIT ACK, spec says, - * “If an INIT ACK is received by an endpoint in any state other - * than the COOKIE-WAIT state, the endpoint should discard the - * INIT ACK chunk”. Stay in the same state - */ - {IP_VS_SCTP_S_ECHO_SER /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - /* - * INIT_ACK has been by the server, let us close the connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - /* - * Client sent the ECHO, not sure what to do, let's close the - * connection. - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - /* - * ECHO resent by the server, stay in the same state - */ - {IP_VS_SCTP_S_ECHO_SER /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - /* - * COOKIE ACK from client, this is what we are expecting, let's move - * to ESTABLISHED. - */ - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - /* - * COOKIE ACK from server, this should not happen, lets close the - * connection. - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - }, - /* - * State : IP_VS_SCTP_S_ESTABLISHED - * Association established - */ - {{IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_DATA_SER */ }, - /* - * We have got an INIT from client. From the spec.“Upon receipt of - * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with - * an INIT ACK using the same parameters it sent in its original - * INIT chunk (including its Initiate Tag, unchanged”). - */ - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - /* - * INIT_ACK sent by the server, Unexpected INIT ACK, spec says, - * “If an INIT ACK is received by an endpoint in any state other - * than the COOKIE-WAIT state, the endpoint should discard the - * INIT ACK chunk”. Stay in the same state - */ - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - /* - * Client sent ECHO, Spec(sec 5.2.4) says it may be handled by the - * peer and peer shall move to the ESTABISHED. if it doesn't handle - * it will send ERROR chunk. So, stay in the same state - */ - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - /* - * COOKIE ACK from client, not sure what to do stay in the same state - */ - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - /* - * SHUTDOWN from the client, move to SHUDDOWN_CLI - */ - {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - /* - * SHUTDOWN from the server, move to SHUTDOWN_SER - */ - {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_SHUT_SER */ }, - /* - * client sent SHUDTDOWN_ACK, this should not happen, let's close - * the connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - }, - /* - * State : IP_VS_SCTP_S_SHUT_CLI - * SHUTDOWN sent from the client, waitinf for SHUT ACK from the server - */ - /* - * We received the data chuck, keep the state unchanged. I assume - * that still data chuncks can be received by both the peers in - * SHUDOWN state - */ - - {{IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_DATA_SER */ }, - /* - * We have got an INIT from client. From the spec.“Upon receipt of - * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with - * an INIT ACK using the same parameters it sent in its original - * INIT chunk (including its Initiate Tag, unchanged”). - */ - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - /* - * INIT_ACK sent by the server, Unexpected INIT ACK, spec says, - * “If an INIT ACK is received by an endpoint in any state other - * than the COOKIE-WAIT state, the endpoint should discard the - * INIT ACK chunk”. Stay in the same state - */ - {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - /* - * Client sent ECHO, Spec(sec 5.2.4) says it may be handled by the - * peer and peer shall move to the ESTABISHED. if it doesn't handle - * it will send ERROR chunk. So, stay in the same state - */ - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - /* - * COOKIE ACK from client, not sure what to do stay in the same state - */ - {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - /* - * SHUTDOWN resent from the client, move to SHUDDOWN_CLI - */ - {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - /* - * SHUTDOWN from the server, move to SHUTDOWN_SER - */ - {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_SHUT_SER */ }, - /* - * client sent SHUDTDOWN_ACK, this should not happen, let's close - * the connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - /* - * Server sent SHUTDOWN ACK, this is what we are expecting, let's move - * to SHUDOWN_ACK_SER - */ - {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - /* - * SHUTDOWN COM from client, this should not happen, let's close the - * connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - }, - /* - * State : IP_VS_SCTP_S_SHUT_SER - * SHUTDOWN sent from the server, waitinf for SHUTDOWN ACK from client - */ - /* - * We received the data chuck, keep the state unchanged. I assume - * that still data chuncks can be received by both the peers in - * SHUDOWN state - */ - - {{IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_DATA_SER */ }, - /* - * We have got an INIT from client. From the spec.“Upon receipt of - * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with - * an INIT ACK using the same parameters it sent in its original - * INIT chunk (including its Initiate Tag, unchanged”). - */ - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - /* - * INIT_ACK sent by the server, Unexpected INIT ACK, spec says, - * “If an INIT ACK is received by an endpoint in any state other - * than the COOKIE-WAIT state, the endpoint should discard the - * INIT ACK chunk”. Stay in the same state - */ - {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - /* - * Client sent ECHO, Spec(sec 5.2.4) says it may be handled by the - * peer and peer shall move to the ESTABISHED. if it doesn't handle - * it will send ERROR chunk. So, stay in the same state - */ - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - /* - * COOKIE ACK from client, not sure what to do stay in the same state - */ - {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - /* - * SHUTDOWN resent from the client, move to SHUDDOWN_CLI - */ - {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - /* - * SHUTDOWN resent from the server, move to SHUTDOWN_SER - */ - {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_SHUT_SER */ }, - /* - * client sent SHUDTDOWN_ACK, this is what we are expecting, let's - * move to SHUT_ACK_CLI - */ - {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - /* - * Server sent SHUTDOWN ACK, this should not happen, let's close the - * connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - /* - * SHUTDOWN COM from client, this should not happen, let's close the - * connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - }, - - /* - * State : IP_VS_SCTP_S_SHUT_ACK_CLI - * SHUTDOWN ACK from the client, awaiting for SHUTDOWN COM from server - */ - /* - * We received the data chuck, keep the state unchanged. I assume - * that still data chuncks can be received by both the peers in - * SHUDOWN state - */ - - {{IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_DATA_SER */ }, - /* - * We have got an INIT from client. From the spec.“Upon receipt of - * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with - * an INIT ACK using the same parameters it sent in its original - * INIT chunk (including its Initiate Tag, unchanged”). - */ - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - /* - * INIT_ACK sent by the server, Unexpected INIT ACK, spec says, - * “If an INIT ACK is received by an endpoint in any state other - * than the COOKIE-WAIT state, the endpoint should discard the - * INIT ACK chunk”. Stay in the same state - */ - {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - /* - * Client sent ECHO, Spec(sec 5.2.4) says it may be handled by the - * peer and peer shall move to the ESTABISHED. if it doesn't handle - * it will send ERROR chunk. So, stay in the same state - */ - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - /* - * COOKIE ACK from client, not sure what to do stay in the same state - */ - {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - /* - * SHUTDOWN sent from the client, move to SHUDDOWN_CLI - */ - {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - /* - * SHUTDOWN sent from the server, move to SHUTDOWN_SER - */ - {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_SHUT_SER */ }, - /* - * client resent SHUDTDOWN_ACK, let's stay in the same state - */ - {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - /* - * Server sent SHUTDOWN ACK, this should not happen, let's close the - * connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - /* - * SHUTDOWN COM from client, this should not happen, let's close the - * connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - /* - * SHUTDOWN COMPLETE from server this is what we are expecting. - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - }, - - /* - * State : IP_VS_SCTP_S_SHUT_ACK_SER - * SHUTDOWN ACK from the server, awaiting for SHUTDOWN COM from client - */ - /* - * We received the data chuck, keep the state unchanged. I assume - * that still data chuncks can be received by both the peers in - * SHUDOWN state - */ +/* SCTP States: + * See RFC 2960, 4. SCTP Association State Diagram + * + * New states (not in diagram): + * - INIT1 state: use shorter timeout for dropped INIT packets + * - REJECTED state: use shorter timeout if INIT is rejected with ABORT + * - INIT, COOKIE_SENT, COOKIE_REPLIED, COOKIE states: for better debugging + * + * The states are as seen in real server. In the diagram, INIT1, INIT, + * COOKIE_SENT and COOKIE_REPLIED processing happens in CLOSED state. + * + * States as per packets from client (C) and server (S): + * + * Setup of client connection: + * IP_VS_SCTP_S_INIT1: First C:INIT sent, wait for S:INIT-ACK + * IP_VS_SCTP_S_INIT: Next C:INIT sent, wait for S:INIT-ACK + * IP_VS_SCTP_S_COOKIE_SENT: S:INIT-ACK sent, wait for C:COOKIE-ECHO + * IP_VS_SCTP_S_COOKIE_REPLIED: C:COOKIE-ECHO sent, wait for S:COOKIE-ACK + * + * Setup of server connection: + * IP_VS_SCTP_S_COOKIE_WAIT: S:INIT sent, wait for C:INIT-ACK + * IP_VS_SCTP_S_COOKIE: C:INIT-ACK sent, wait for S:COOKIE-ECHO + * IP_VS_SCTP_S_COOKIE_ECHOED: S:COOKIE-ECHO sent, wait for C:COOKIE-ACK + */ - {{IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_DATA_SER */ }, - /* - * We have got an INIT from client. From the spec.“Upon receipt of - * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with - * an INIT ACK using the same parameters it sent in its original - * INIT chunk (including its Initiate Tag, unchanged”). - */ - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - /* - * INIT_ACK sent by the server, Unexpected INIT ACK, spec says, - * “If an INIT ACK is received by an endpoint in any state other - * than the COOKIE-WAIT state, the endpoint should discard the - * INIT ACK chunk”. Stay in the same state - */ - {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - /* - * Client sent ECHO, Spec(sec 5.2.4) says it may be handled by the - * peer and peer shall move to the ESTABISHED. if it doesn't handle - * it will send ERROR chunk. So, stay in the same state - */ - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - /* - * COOKIE ACK from client, not sure what to do stay in the same state - */ - {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - /* - * SHUTDOWN sent from the client, move to SHUDDOWN_CLI - */ - {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - /* - * SHUTDOWN sent from the server, move to SHUTDOWN_SER - */ - {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_SHUT_SER */ }, - /* - * client sent SHUDTDOWN_ACK, this should not happen let's close - * the connection. - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - /* - * Server resent SHUTDOWN ACK, stay in the same state - */ - {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - /* - * SHUTDOWN COM from client, this what we are expecting, let's close - * the connection - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - /* - * SHUTDOWN COMPLETE from server this should not happen. - */ - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - }, - /* - * State : IP_VS_SCTP_S_CLOSED - */ - {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ }, - {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ }, - {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ }, - {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ } - } +#define sNO IP_VS_SCTP_S_NONE +#define sI1 IP_VS_SCTP_S_INIT1 +#define sIN IP_VS_SCTP_S_INIT +#define sCS IP_VS_SCTP_S_COOKIE_SENT +#define sCR IP_VS_SCTP_S_COOKIE_REPLIED +#define sCW IP_VS_SCTP_S_COOKIE_WAIT +#define sCO IP_VS_SCTP_S_COOKIE +#define sCE IP_VS_SCTP_S_COOKIE_ECHOED +#define sES IP_VS_SCTP_S_ESTABLISHED +#define sSS IP_VS_SCTP_S_SHUTDOWN_SENT +#define sSR IP_VS_SCTP_S_SHUTDOWN_RECEIVED +#define sSA IP_VS_SCTP_S_SHUTDOWN_ACK_SENT +#define sRJ IP_VS_SCTP_S_REJECTED +#define sCL IP_VS_SCTP_S_CLOSED + +static const __u8 sctp_states + [IP_VS_DIR_LAST][IP_VS_SCTP_EVENT_LAST][IP_VS_SCTP_S_LAST] = { + { /* INPUT */ +/* sNO, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL*/ +/* d */{sES, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* i */{sI1, sIN, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sIN, sIN}, +/* i_a */{sCW, sCW, sCW, sCS, sCR, sCO, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* c_e */{sCR, sIN, sIN, sCR, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* c_a */{sES, sI1, sIN, sCS, sCR, sCW, sCO, sES, sES, sSS, sSR, sSA, sRJ, sCL}, +/* s */{sSR, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sSR, sSS, sSR, sSA, sRJ, sCL}, +/* s_a */{sCL, sIN, sIN, sCS, sCR, sCW, sCO, sCE, sES, sCL, sSR, sCL, sRJ, sCL}, +/* s_c */{sCL, sCL, sCL, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sCL, sRJ, sCL}, +/* err */{sCL, sI1, sIN, sCS, sCR, sCW, sCO, sCL, sES, sSS, sSR, sSA, sRJ, sCL}, +/* ab */{sCL, sCL, sCL, sCL, sCL, sRJ, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, + }, + { /* OUTPUT */ +/* sNO, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL*/ +/* d */{sES, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* i */{sCW, sCW, sCW, sCW, sCW, sCW, sCW, sCW, sES, sCW, sCW, sCW, sCW, sCW}, +/* i_a */{sCS, sCS, sCS, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* c_e */{sCE, sCE, sCE, sCE, sCE, sCE, sCE, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* c_a */{sES, sES, sES, sES, sES, sES, sES, sES, sES, sSS, sSR, sSA, sRJ, sCL}, +/* s */{sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSR, sSA, sRJ, sCL}, +/* s_a */{sSA, sSA, sSA, sSA, sSA, sCW, sCO, sCE, sES, sSA, sSA, sSA, sRJ, sCL}, +/* s_c */{sCL, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* err */{sCL, sCL, sCL, sCL, sCL, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* ab */{sCL, sRJ, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, + }, + { /* INPUT-ONLY */ +/* sNO, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL*/ +/* d */{sES, sI1, sIN, sCS, sCR, sES, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* i */{sI1, sIN, sIN, sIN, sIN, sIN, sCO, sCE, sES, sSS, sSR, sSA, sIN, sIN}, +/* i_a */{sCE, sCE, sCE, sCE, sCE, sCE, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* c_e */{sES, sES, sES, sES, sES, sES, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* c_a */{sES, sI1, sIN, sES, sES, sCW, sES, sES, sES, sSS, sSR, sSA, sRJ, sCL}, +/* s */{sSR, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sSR, sSS, sSR, sSA, sRJ, sCL}, +/* s_a */{sCL, sIN, sIN, sCS, sCR, sCW, sCO, sCE, sCL, sCL, sSR, sCL, sRJ, sCL}, +/* s_c */{sCL, sCL, sCL, sCL, sCL, sCW, sCO, sCE, sES, sSS, sCL, sCL, sRJ, sCL}, +/* err */{sCL, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, +/* ab */{sCL, sCL, sCL, sCL, sCL, sRJ, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, + }, }; -/* - * Timeout table[state] - */ +#define IP_VS_SCTP_MAX_RTO ((60 + 1) * HZ) + +/* Timeout table[state] */ static const int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = { - [IP_VS_SCTP_S_NONE] = 2 * HZ, - [IP_VS_SCTP_S_INIT_CLI] = 1 * 60 * HZ, - [IP_VS_SCTP_S_INIT_SER] = 1 * 60 * HZ, - [IP_VS_SCTP_S_INIT_ACK_CLI] = 1 * 60 * HZ, - [IP_VS_SCTP_S_INIT_ACK_SER] = 1 * 60 * HZ, - [IP_VS_SCTP_S_ECHO_CLI] = 1 * 60 * HZ, - [IP_VS_SCTP_S_ECHO_SER] = 1 * 60 * HZ, - [IP_VS_SCTP_S_ESTABLISHED] = 15 * 60 * HZ, - [IP_VS_SCTP_S_SHUT_CLI] = 1 * 60 * HZ, - [IP_VS_SCTP_S_SHUT_SER] = 1 * 60 * HZ, - [IP_VS_SCTP_S_SHUT_ACK_CLI] = 1 * 60 * HZ, - [IP_VS_SCTP_S_SHUT_ACK_SER] = 1 * 60 * HZ, - [IP_VS_SCTP_S_CLOSED] = 10 * HZ, - [IP_VS_SCTP_S_LAST] = 2 * HZ, + [IP_VS_SCTP_S_NONE] = 2 * HZ, + [IP_VS_SCTP_S_INIT1] = (0 + 3 + 1) * HZ, + [IP_VS_SCTP_S_INIT] = IP_VS_SCTP_MAX_RTO, + [IP_VS_SCTP_S_COOKIE_SENT] = IP_VS_SCTP_MAX_RTO, + [IP_VS_SCTP_S_COOKIE_REPLIED] = IP_VS_SCTP_MAX_RTO, + [IP_VS_SCTP_S_COOKIE_WAIT] = IP_VS_SCTP_MAX_RTO, + [IP_VS_SCTP_S_COOKIE] = IP_VS_SCTP_MAX_RTO, + [IP_VS_SCTP_S_COOKIE_ECHOED] = IP_VS_SCTP_MAX_RTO, + [IP_VS_SCTP_S_ESTABLISHED] = 15 * 60 * HZ, + [IP_VS_SCTP_S_SHUTDOWN_SENT] = IP_VS_SCTP_MAX_RTO, + [IP_VS_SCTP_S_SHUTDOWN_RECEIVED] = IP_VS_SCTP_MAX_RTO, + [IP_VS_SCTP_S_SHUTDOWN_ACK_SENT] = IP_VS_SCTP_MAX_RTO, + [IP_VS_SCTP_S_REJECTED] = (0 + 3 + 1) * HZ, + [IP_VS_SCTP_S_CLOSED] = IP_VS_SCTP_MAX_RTO, + [IP_VS_SCTP_S_LAST] = 2 * HZ, }; static const char *sctp_state_name_table[IP_VS_SCTP_S_LAST + 1] = { - [IP_VS_SCTP_S_NONE] = "NONE", - [IP_VS_SCTP_S_INIT_CLI] = "INIT_CLI", - [IP_VS_SCTP_S_INIT_SER] = "INIT_SER", - [IP_VS_SCTP_S_INIT_ACK_CLI] = "INIT_ACK_CLI", - [IP_VS_SCTP_S_INIT_ACK_SER] = "INIT_ACK_SER", - [IP_VS_SCTP_S_ECHO_CLI] = "COOKIE_ECHO_CLI", - [IP_VS_SCTP_S_ECHO_SER] = "COOKIE_ECHO_SER", - [IP_VS_SCTP_S_ESTABLISHED] = "ESTABISHED", - [IP_VS_SCTP_S_SHUT_CLI] = "SHUTDOWN_CLI", - [IP_VS_SCTP_S_SHUT_SER] = "SHUTDOWN_SER", - [IP_VS_SCTP_S_SHUT_ACK_CLI] = "SHUTDOWN_ACK_CLI", - [IP_VS_SCTP_S_SHUT_ACK_SER] = "SHUTDOWN_ACK_SER", - [IP_VS_SCTP_S_CLOSED] = "CLOSED", - [IP_VS_SCTP_S_LAST] = "BUG!" + [IP_VS_SCTP_S_NONE] = "NONE", + [IP_VS_SCTP_S_INIT1] = "INIT1", + [IP_VS_SCTP_S_INIT] = "INIT", + [IP_VS_SCTP_S_COOKIE_SENT] = "C-SENT", + [IP_VS_SCTP_S_COOKIE_REPLIED] = "C-REPLIED", + [IP_VS_SCTP_S_COOKIE_WAIT] = "C-WAIT", + [IP_VS_SCTP_S_COOKIE] = "COOKIE", + [IP_VS_SCTP_S_COOKIE_ECHOED] = "C-ECHOED", + [IP_VS_SCTP_S_ESTABLISHED] = "ESTABLISHED", + [IP_VS_SCTP_S_SHUTDOWN_SENT] = "S-SENT", + [IP_VS_SCTP_S_SHUTDOWN_RECEIVED] = "S-RECEIVED", + [IP_VS_SCTP_S_SHUTDOWN_ACK_SENT] = "S-ACK-SENT", + [IP_VS_SCTP_S_REJECTED] = "REJECTED", + [IP_VS_SCTP_S_CLOSED] = "CLOSED", + [IP_VS_SCTP_S_LAST] = "BUG!", }; @@ -945,17 +394,20 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, } } - event = sctp_events[chunk_type]; + event = (chunk_type < sizeof(sctp_events)) ? + sctp_events[chunk_type] : IP_VS_SCTP_DATA; - /* - * If the direction is IP_VS_DIR_OUTPUT, this event is from server - */ - if (direction == IP_VS_DIR_OUTPUT) - event++; - /* - * get next state + /* Update direction to INPUT_ONLY if necessary + * or delete NO_OUTPUT flag if output packet detected */ - next_state = sctp_states_table[cp->state][event].next_state; + if (cp->flags & IP_VS_CONN_F_NOOUTPUT) { + if (direction == IP_VS_DIR_OUTPUT) + cp->flags &= ~IP_VS_CONN_F_NOOUTPUT; + else + direction = IP_VS_DIR_INPUT_ONLY; + } + + next_state = sctp_states[direction][event][cp->state]; if (next_state != cp->state) { struct ip_vs_dest *dest = cp->dest; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index f6046d9af8d3..2fc66394d86d 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -461,9 +461,10 @@ static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs, } else if (unlikely(cp->protocol == IPPROTO_SCTP)) { if (!((1 << cp->state) & ((1 << IP_VS_SCTP_S_ESTABLISHED) | - (1 << IP_VS_SCTP_S_CLOSED) | - (1 << IP_VS_SCTP_S_SHUT_ACK_CLI) | - (1 << IP_VS_SCTP_S_SHUT_ACK_SER)))) + (1 << IP_VS_SCTP_S_SHUTDOWN_SENT) | + (1 << IP_VS_SCTP_S_SHUTDOWN_RECEIVED) | + (1 << IP_VS_SCTP_S_SHUTDOWN_ACK_SENT) | + (1 << IP_VS_SCTP_S_CLOSED)))) return 0; force = cp->state != cp->old_state; if (force && cp->state != IP_VS_SCTP_S_ESTABLISHED) -- cgit v1.2.3 From acaac5d8bbedf6bd96f53960780942e1ad90d70e Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 18 Jun 2013 10:08:08 +0300 Subject: ipvs: drop SCTP connections depending on state Drop SCTP connections under load (dropentry context) depending on the protocol state, just like for TCP: INIT conns are dropped immediately, established are dropped randomly while connections in progress or shutdown are skipped. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_conn.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index c8c52a98590b..4c8e5c0aa1ab 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1231,6 +1231,18 @@ void ip_vs_random_dropentry(struct net *net) default: continue; } + } else if (cp->protocol == IPPROTO_SCTP) { + switch (cp->state) { + case IP_VS_SCTP_S_INIT1: + case IP_VS_SCTP_S_INIT: + break; + case IP_VS_SCTP_S_ESTABLISHED: + if (todrop_entry(cp)) + break; + continue; + default: + continue; + } } else { if (!todrop_entry(cp)) continue; -- cgit v1.2.3 From eba3b5a78799d21dea05118b294524958f0ab592 Mon Sep 17 00:00:00 2001 From: Alexander Frolkin Date: Wed, 19 Jun 2013 10:54:25 +0100 Subject: ipvs: SH fallback and L4 hashing By default the SH scheduler rejects connections that are hashed onto a realserver of weight 0. This patch adds a flag to make SH choose a different realserver in this case, instead of rejecting the connection. The patch also adds a flag to make SH include the source port (TCP, UDP, SCTP) in the hash as well as the source address. This basically allows for deterministic round-robin load balancing (i.e., where any director in a cluster of directors with identical config will send the same packet the same way). The flags are service flags (IP_VS_SVC_F_SCHED*) so that these options can be set per service. They are set using a new option to ipvsadm. Signed-off-by: Alexander Frolkin Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/uapi/linux/ip_vs.h | 6 +++ net/netfilter/ipvs/ip_vs_sh.c | 100 +++++++++++++++++++++++++++++++++++------- 2 files changed, 91 insertions(+), 15 deletions(-) (limited to 'net/netfilter') diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index a24537725e80..29458223d044 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -20,6 +20,12 @@ #define IP_VS_SVC_F_PERSISTENT 0x0001 /* persistent port */ #define IP_VS_SVC_F_HASHED 0x0002 /* hashed entry */ #define IP_VS_SVC_F_ONEPACKET 0x0004 /* one-packet scheduling */ +#define IP_VS_SVC_F_SCHED1 0x0008 /* scheduler flag 1 */ +#define IP_VS_SVC_F_SCHED2 0x0010 /* scheduler flag 2 */ +#define IP_VS_SVC_F_SCHED3 0x0020 /* scheduler flag 3 */ + +#define IP_VS_SVC_F_SCHED_SH_FALLBACK IP_VS_SVC_F_SCHED1 /* SH fallback */ +#define IP_VS_SVC_F_SCHED_SH_PORT IP_VS_SVC_F_SCHED2 /* SH use port */ /* * Destination Server Flags diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index e0d5d1653566..f16c027df15b 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -48,6 +48,10 @@ #include +#include +#include +#include + /* * IPVS SH bucket @@ -71,10 +75,19 @@ struct ip_vs_sh_state { struct ip_vs_sh_bucket buckets[IP_VS_SH_TAB_SIZE]; }; +/* Helper function to determine if server is unavailable */ +static inline bool is_unavailable(struct ip_vs_dest *dest) +{ + return atomic_read(&dest->weight) <= 0 || + dest->flags & IP_VS_DEST_F_OVERLOAD; +} + /* * Returns hash value for IPVS SH entry */ -static inline unsigned int ip_vs_sh_hashkey(int af, const union nf_inet_addr *addr) +static inline unsigned int +ip_vs_sh_hashkey(int af, const union nf_inet_addr *addr, + __be16 port, unsigned int offset) { __be32 addr_fold = addr->ip; @@ -83,7 +96,8 @@ static inline unsigned int ip_vs_sh_hashkey(int af, const union nf_inet_addr *ad addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif - return (ntohl(addr_fold)*2654435761UL) & IP_VS_SH_TAB_MASK; + return (offset + (ntohs(port) + ntohl(addr_fold))*2654435761UL) & + IP_VS_SH_TAB_MASK; } @@ -91,12 +105,42 @@ static inline unsigned int ip_vs_sh_hashkey(int af, const union nf_inet_addr *ad * Get ip_vs_dest associated with supplied parameters. */ static inline struct ip_vs_dest * -ip_vs_sh_get(int af, struct ip_vs_sh_state *s, const union nf_inet_addr *addr) +ip_vs_sh_get(struct ip_vs_service *svc, struct ip_vs_sh_state *s, + const union nf_inet_addr *addr, __be16 port) { - return rcu_dereference(s->buckets[ip_vs_sh_hashkey(af, addr)].dest); + unsigned int hash = ip_vs_sh_hashkey(svc->af, addr, port, 0); + struct ip_vs_dest *dest = rcu_dereference(s->buckets[hash].dest); + + return (!dest || is_unavailable(dest)) ? NULL : dest; } +/* As ip_vs_sh_get, but with fallback if selected server is unavailable */ +static inline struct ip_vs_dest * +ip_vs_sh_get_fallback(struct ip_vs_service *svc, struct ip_vs_sh_state *s, + const union nf_inet_addr *addr, __be16 port) +{ + unsigned int offset; + unsigned int hash; + struct ip_vs_dest *dest; + + for (offset = 0; offset < IP_VS_SH_TAB_SIZE; offset++) { + hash = ip_vs_sh_hashkey(svc->af, addr, port, offset); + dest = rcu_dereference(s->buckets[hash].dest); + if (!dest) + break; + if (is_unavailable(dest)) + IP_VS_DBG_BUF(6, "SH: selected unavailable server " + "%s:%d (offset %d)", + IP_VS_DBG_ADDR(svc->af, &dest->addr), + ntohs(dest->port), offset); + else + return dest; + } + + return NULL; +} + /* * Assign all the hash buckets of the specified table with the service. */ @@ -213,13 +257,33 @@ static int ip_vs_sh_dest_changed(struct ip_vs_service *svc, } -/* - * If the dest flags is set with IP_VS_DEST_F_OVERLOAD, - * consider that the server is overloaded here. - */ -static inline int is_overloaded(struct ip_vs_dest *dest) +/* Helper function to get port number */ +static inline __be16 +ip_vs_sh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph) { - return dest->flags & IP_VS_DEST_F_OVERLOAD; + __be16 port; + struct tcphdr _tcph, *th; + struct udphdr _udph, *uh; + sctp_sctphdr_t _sctph, *sh; + + switch (iph->protocol) { + case IPPROTO_TCP: + th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); + port = th->source; + break; + case IPPROTO_UDP: + uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph); + port = uh->source; + break; + case IPPROTO_SCTP: + sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph); + port = sh->source; + break; + default: + port = 0; + } + + return port; } @@ -232,15 +296,21 @@ ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, { struct ip_vs_dest *dest; struct ip_vs_sh_state *s; + __be16 port = 0; IP_VS_DBG(6, "ip_vs_sh_schedule(): Scheduling...\n"); + if (svc->flags & IP_VS_SVC_F_SCHED_SH_PORT) + port = ip_vs_sh_get_port(skb, iph); + s = (struct ip_vs_sh_state *) svc->sched_data; - dest = ip_vs_sh_get(svc->af, s, &iph->saddr); - if (!dest - || !(dest->flags & IP_VS_DEST_F_AVAILABLE) - || atomic_read(&dest->weight) <= 0 - || is_overloaded(dest)) { + + if (svc->flags & IP_VS_SVC_F_SCHED_SH_FALLBACK) + dest = ip_vs_sh_get_fallback(svc, s, &iph->saddr, port); + else + dest = ip_vs_sh_get(svc, s, &iph->saddr, port); + + if (!dest) { ip_vs_scheduler_err(svc, "no destination available"); return NULL; } -- cgit v1.2.3 From 4d0c875dcc4923476f364e83912d134da2df224c Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Mon, 24 Jun 2013 22:44:41 +0300 Subject: ipvs: add sync_persist_mode flag Add sync_persist_mode flag to reduce sync traffic by syncing only persistent templates. Signed-off-by: Julian Anastasov Tested-by: Aleksey Chudov Signed-off-by: Simon Horman --- Documentation/networking/ipvs-sysctl.txt | 13 +++++++++++++ include/net/ip_vs.h | 11 +++++++++++ net/netfilter/ipvs/ip_vs_ctl.c | 7 +++++++ net/netfilter/ipvs/ip_vs_sync.c | 12 ++++++++++++ 4 files changed, 43 insertions(+) (limited to 'net/netfilter') diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index 9573d0c48c6e..7a3c04729591 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -181,6 +181,19 @@ snat_reroute - BOOLEAN always be the same as the original route so it is an optimisation to disable snat_reroute and avoid the recalculation. +sync_persist_mode - INTEGER + default 0 + + Controls the synchronisation of connections when using persistence + + 0: All types of connections are synchronised + 1: Attempt to reduce the synchronisation traffic depending on + the connection type. For persistent services avoid synchronisation + for normal connections, do it only for persistence templates. + In such case, for TCP and SCTP it may need enabling sloppy_tcp and + sloppy_sctp flags on backup servers. For non-persistent services + such optimization is not applied, mode 0 is assumed. + sync_version - INTEGER default 1 diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index e667df171003..f0d70f066f3d 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -975,6 +975,7 @@ struct netns_ipvs { int sysctl_snat_reroute; int sysctl_sync_ver; int sysctl_sync_ports; + int sysctl_sync_persist_mode; unsigned long sysctl_sync_qlen_max; int sysctl_sync_sock_size; int sysctl_cache_bypass; @@ -1076,6 +1077,11 @@ static inline int sysctl_sync_ports(struct netns_ipvs *ipvs) return ACCESS_ONCE(ipvs->sysctl_sync_ports); } +static inline int sysctl_sync_persist_mode(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_sync_persist_mode; +} + static inline unsigned long sysctl_sync_qlen_max(struct netns_ipvs *ipvs) { return ipvs->sysctl_sync_qlen_max; @@ -1139,6 +1145,11 @@ static inline int sysctl_sync_ports(struct netns_ipvs *ipvs) return 1; } +static inline int sysctl_sync_persist_mode(struct netns_ipvs *ipvs) +{ + return 0; +} + static inline unsigned long sysctl_sync_qlen_max(struct netns_ipvs *ipvs) { return IPVS_SYNC_QLEN_MAX; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index da035fc01eb2..c8148e487386 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1714,6 +1714,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = &proc_do_sync_ports, }, + { + .procname = "sync_persist_mode", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "sync_qlen_max", .maxlen = sizeof(unsigned long), @@ -3729,6 +3735,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) tbl[idx++].data = &ipvs->sysctl_sync_ver; ipvs->sysctl_sync_ports = 1; tbl[idx++].data = &ipvs->sysctl_sync_ports; + tbl[idx++].data = &ipvs->sysctl_sync_persist_mode; ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32; tbl[idx++].data = &ipvs->sysctl_sync_qlen_max; ipvs->sysctl_sync_sock_size = 0; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 2fc66394d86d..f4484719f3e6 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -425,6 +425,16 @@ ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs) return sb; } +/* Check if connection is controlled by persistence */ +static inline bool in_persistence(struct ip_vs_conn *cp) +{ + for (cp = cp->control; cp; cp = cp->control) { + if (cp->flags & IP_VS_CONN_F_TEMPLATE) + return true; + } + return false; +} + /* 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 @@ -447,6 +457,8 @@ static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs, /* Check if we sync in current state */ if (unlikely(cp->flags & IP_VS_CONN_F_TEMPLATE)) force = 0; + else if (unlikely(sysctl_sync_persist_mode(ipvs) && in_persistence(cp))) + return 0; else if (likely(cp->protocol == IPPROTO_TCP)) { if (!((1 << cp->state) & ((1 << IP_VS_TCP_S_ESTABLISHED) | -- cgit v1.2.3 From 496e4ae7dc944faa1721bfda7e9d834d5611a874 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 29 Jun 2013 14:15:47 +0200 Subject: netfilter: nf_queue: add NFQA_SKB_CSUM_NOTVERIFIED info flag The common case is that TCP/IP checksums have already been verified, e.g. by hardware (rx checksum offload), or conntrack. Userspace can use this flag to determine when the checksum has not been validated yet. If the flag is set, this doesn't necessarily mean that the packet has an invalid checksum, e.g. if NIC doesn't support rx checksum. Userspace that sucessfully enabled NFQA_CFG_F_GSO queue feature flag can infer that IP/TCP checksum has already been validated if either the SKB_INFO attribute is not present or the NFQA_SKB_CSUM_NOTVERIFIED flag is unset. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nfnetlink_queue.h | 2 ++ net/netfilter/nfnetlink_queue_core.c | 16 ++++++++++++++-- 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'net/netfilter') diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h index a2308ae5a73d..3a9b92147339 100644 --- a/include/uapi/linux/netfilter/nfnetlink_queue.h +++ b/include/uapi/linux/netfilter/nfnetlink_queue.h @@ -105,5 +105,7 @@ enum nfqnl_attr_config { #define NFQA_SKB_CSUMNOTREADY (1 << 0) /* packet is GSO (i.e., exceeds device mtu) */ #define NFQA_SKB_GSO (1 << 1) +/* csum not validated (incoming device doesn't support hw checksum, etc.) */ +#define NFQA_SKB_CSUM_NOTVERIFIED (1 << 2) #endif /* _NFNETLINK_QUEUE_H */ diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 299a48ae5dc9..971ea145ab3e 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -280,12 +280,17 @@ nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen) skb_shinfo(to)->nr_frags = j; } -static int nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet) +static int +nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet, + bool csum_verify) { __u32 flags = 0; if (packet->ip_summed == CHECKSUM_PARTIAL) flags = NFQA_SKB_CSUMNOTREADY; + else if (csum_verify) + flags = NFQA_SKB_CSUM_NOTVERIFIED; + if (skb_is_gso(packet)) flags |= NFQA_SKB_GSO; @@ -310,6 +315,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, struct net_device *outdev; struct nf_conn *ct = NULL; enum ip_conntrack_info uninitialized_var(ctinfo); + bool csum_verify; size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfqnl_msg_packet_hdr)) @@ -327,6 +333,12 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, if (entskb->tstamp.tv64) size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp)); + if (entry->hook <= NF_INET_FORWARD || + (entry->hook == NF_INET_POST_ROUTING && entskb->sk == NULL)) + csum_verify = !skb_csum_unnecessary(entskb); + else + csum_verify = false; + outdev = entry->outdev; switch ((enum nfqnl_config_mode)ACCESS_ONCE(queue->copy_mode)) { @@ -476,7 +488,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len))) goto nla_put_failure; - if (nfqnl_put_packet_info(skb, entskb)) + if (nfqnl_put_packet_info(skb, entskb, csum_verify)) goto nla_put_failure; if (data_len) { -- cgit v1.2.3 From f09eca8db0184aeb6b9718a987cfb3653ad7c4ae Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2013 20:16:39 +0200 Subject: netfilter: ctnetlink: fix incorrect NAT expectation dumping nf_ct_expect_alloc leaves unset the expectation NAT fields. However, ctnetlink_exp_dump_expect expects them to be zeroed in case they are not used, which may not be the case. This results in dumping the NAT tuple of the expectation when it should not. Fix it by zeroing the NAT fields of the expectation. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_expect.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index c63b618cd619..4fd1ca94fd4a 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -293,6 +293,11 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class, sizeof(exp->tuple.dst.u3) - len); exp->tuple.dst.u.all = *dst; + +#ifdef CONFIG_NF_NAT_NEEDED + memset(&exp->saved_addr, 0, sizeof(exp->saved_addr)); + memset(&exp->saved_proto, 0, sizeof(exp->saved_proto)); +#endif } EXPORT_SYMBOL_GPL(nf_ct_expect_init); -- cgit v1.2.3 From baf60efa585c78b269f0097288868a51ccc61f55 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 11 Jul 2013 19:22:19 -0700 Subject: netfilter: xt_socket: fix broken v0 support commit 681f130f39e10 ("netfilter: xt_socket: add XT_SOCKET_NOWILDCARD flag") added a potential NULL dereference if an old iptables package uses v0 of the match. Fix this by removing the test on @info in fast path. IPv6 can remove the test as well, as it uses v1 or v2. Reported-by: Neal Cardwell Signed-off-by: Eric Dumazet Cc: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_socket.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index f8b71911037a..20b15916f403 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -172,7 +172,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ - if (info && info->flags & XT_SOCKET_TRANSPARENT) + if (info->flags & XT_SOCKET_TRANSPARENT) transparent = ((sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->transparent) || (sk->sk_state == TCP_TIME_WAIT && @@ -196,7 +196,11 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, static bool socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par) { - return socket_match(skb, par, NULL); + static struct xt_socket_mtinfo1 xt_info_v0 = { + .flags = 0, + }; + + return socket_match(skb, par, &xt_info_v0); } static bool @@ -314,7 +318,7 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ - if (info && info->flags & XT_SOCKET_TRANSPARENT) + if (info->flags & XT_SOCKET_TRANSPARENT) transparent = ((sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->transparent) || (sk->sk_state == TCP_TIME_WAIT && -- cgit v1.2.3 From 024ec3deac33ddbd81f3c887506f132b24ea21a7 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Thu, 25 Jul 2013 10:52:05 +0900 Subject: net/sctp: Refactor SCTP skb checksum computation This patch consolidates the SCTP checksum calculation code from various places to a single new function, sctp_compute_cksum(skb, offset). Signed-off-by: Joe Stringer Reviewed-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: David S. Miller --- include/net/sctp/checksum.h | 15 +++++++++++++++ net/netfilter/ipvs/ip_vs_proto_sctp.c | 23 +++-------------------- net/netfilter/nf_nat_proto_sctp.c | 8 +------- net/sctp/input.c | 10 +--------- 4 files changed, 20 insertions(+), 36 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h index 78b88aa8c810..483e6303458d 100644 --- a/include/net/sctp/checksum.h +++ b/include/net/sctp/checksum.h @@ -85,4 +85,19 @@ static inline __le32 sctp_end_cksum(__u32 crc32) return cpu_to_le32(~crc32); } +/* Calculate the CRC32C checksum of an SCTP packet. */ +static inline __le32 sctp_compute_cksum(const struct sk_buff *skb, + unsigned int offset) +{ + const struct sk_buff *iter; + + __u32 crc32 = sctp_start_cksum(skb->data + offset, + skb_headlen(skb) - offset); + skb_walk_frags(skb, iter) + crc32 = sctp_update_cksum((__u8 *) iter->data, + skb_headlen(iter), crc32); + + return sctp_end_cksum(crc32); +} + #endif /* __sctp_checksum_h__ */ diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 3c0da8728036..23e596e438b3 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -66,15 +66,7 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, static void sctp_nat_csum(struct sk_buff *skb, sctp_sctphdr_t *sctph, unsigned int sctphoff) { - __u32 crc32; - struct sk_buff *iter; - - crc32 = sctp_start_cksum((__u8 *)sctph, skb_headlen(skb) - sctphoff); - skb_walk_frags(skb, iter) - crc32 = sctp_update_cksum((u8 *) iter->data, - skb_headlen(iter), crc32); - sctph->checksum = sctp_end_cksum(crc32); - + sctph->checksum = sctp_compute_cksum(skb, sctphoff); skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -151,10 +143,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) { unsigned int sctphoff; struct sctphdr *sh, _sctph; - struct sk_buff *iter; - __le32 cmp; - __le32 val; - __u32 tmp; + __le32 cmp, val; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) @@ -168,13 +157,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) return 0; cmp = sh->checksum; - - tmp = sctp_start_cksum((__u8 *) sh, skb_headlen(skb)); - skb_walk_frags(skb, iter) - tmp = sctp_update_cksum((__u8 *) iter->data, - skb_headlen(iter), tmp); - - val = sctp_end_cksum(tmp); + val = sctp_compute_cksum(skb, sctphoff); if (val != cmp) { /* CRC failure, dump it. */ diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c index 396e55d46f90..754536f2c674 100644 --- a/net/netfilter/nf_nat_proto_sctp.c +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -34,9 +34,7 @@ sctp_manip_pkt(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { - struct sk_buff *frag; sctp_sctphdr_t *hdr; - __u32 crc32; if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) return false; @@ -51,11 +49,7 @@ sctp_manip_pkt(struct sk_buff *skb, hdr->dest = tuple->dst.u.sctp.port; } - crc32 = sctp_start_cksum((u8 *)hdr, skb_headlen(skb) - hdroff); - skb_walk_frags(skb, frag) - crc32 = sctp_update_cksum((u8 *)frag->data, skb_headlen(frag), - crc32); - hdr->checksum = sctp_end_cksum(crc32); + hdr->checksum = sctp_compute_cksum(skb, hdroff); return true; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 7993495a4c0f..fa91aff02388 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -87,15 +87,7 @@ static inline int sctp_rcv_checksum(struct net *net, struct sk_buff *skb) { struct sctphdr *sh = sctp_hdr(skb); __le32 cmp = sh->checksum; - struct sk_buff *list; - __le32 val; - __u32 tmp = sctp_start_cksum((__u8 *)sh, skb_headlen(skb)); - - skb_walk_frags(skb, list) - tmp = sctp_update_cksum((__u8 *)list->data, skb_headlen(list), - tmp); - - val = sctp_end_cksum(tmp); + __le32 val = sctp_compute_cksum(skb, 0); if (val != cmp) { /* CRC failure, dump it. */ -- cgit v1.2.3 From 5774c94aceade9eadc311957fe31322cc3ad2016 Mon Sep 17 00:00:00 2001 From: Phil Oester Date: Thu, 11 Jul 2013 12:06:58 -0700 Subject: netfilter: xt_addrtype: fix trivial typo Fix typo in error message. Signed-off-by: Phil Oester Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_addrtype.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index 68ff29f60867..fab6eea1bf38 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -202,7 +202,7 @@ static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) return -EINVAL; } if ((info->source | info->dest) >= XT_ADDRTYPE_PROHIBIT) { - pr_err("ipv6 PROHIBT (THROW, NAT ..) matching not supported\n"); + pr_err("ipv6 PROHIBIT (THROW, NAT ..) matching not supported\n"); return -EINVAL; } if ((info->source | info->dest) & XT_ADDRTYPE_BROADCAST) { -- cgit v1.2.3 From 312a0c16c1fa9dd7cb5af413cf73b2fe2806c962 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 28 Jul 2013 22:54:08 +0200 Subject: netfilter: nf_conntrack: constify sk_buff argument to nf_ct_attach() Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 4 ++-- net/netfilter/core.c | 7 ++++--- net/netfilter/nf_conntrack_core.c | 2 +- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'net/netfilter') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index de70f7b45b68..f4bbf2cd22d8 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -314,8 +314,8 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif /*CONFIG_NETFILTER*/ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu; -extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); +extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; +extern void nf_ct_attach(struct sk_buff *, const struct sk_buff *); extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; struct nf_conn; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 2217363ab422..593b16ea45e0 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -234,12 +234,13 @@ EXPORT_SYMBOL(skb_make_writable); /* This does not belong here, but locally generated errors need it if connection tracking in use: without this, connection may not be in hash table, and hence manufactured ICMP or RST packets will not be associated with it. */ -void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu __read_mostly; +void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) + __rcu __read_mostly; EXPORT_SYMBOL(ip_ct_attach); -void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) +void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb) { - void (*attach)(struct sk_buff *, struct sk_buff *); + void (*attach)(struct sk_buff *, const struct sk_buff *); if (skb->nfct) { rcu_read_lock(); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0283baedcdfb..d32afaff72f8 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1192,7 +1192,7 @@ EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_tuple_size); #endif /* Used by ipt_REJECT and ip6t_REJECT. */ -static void nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb) +static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; -- cgit v1.2.3 From 5813a8eb47915e051059562f22ffa521404f6e19 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 29 Jul 2013 15:41:50 +0200 Subject: netfilter: connlabels: remove unneeded includes leftovers from the (never merged) v1 patch. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_labels.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c index 355d2ef08094..bb53f120e79c 100644 --- a/net/netfilter/nf_conntrack_labels.c +++ b/net/netfilter/nf_conntrack_labels.c @@ -8,12 +8,8 @@ * published by the Free Software Foundation. */ -#include #include -#include -#include #include -#include #include #include -- cgit v1.2.3 From 957bec36855f97cc5797fbaaf68b11ac7454df2d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 29 Jul 2013 15:41:51 +0200 Subject: netfilter: nf_queue: relax NFQA_CT attribute check Allow modifying attributes of the conntrack associated with a packet without first requesting ct data via CFG_F_CONNTRACK or extra nfnetlink_conntrack socket. Also remove unneded rcu_read_lock; the entire function is already protected by rcu. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_queue_core.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 971ea145ab3e..ec9de12aa488 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -987,8 +987,7 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, if (entry == NULL) return -ENOENT; - rcu_read_lock(); - if (nfqa[NFQA_CT] && (queue->flags & NFQA_CFG_F_CONNTRACK)) + if (nfqa[NFQA_CT]) ct = nfqnl_ct_parse(entry->skb, nfqa[NFQA_CT], &ctinfo); if (nfqa[NFQA_PAYLOAD]) { @@ -1002,7 +1001,6 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, if (ct) nfqnl_ct_seq_adjust(skb, ct, ctinfo, diff); } - rcu_read_unlock(); if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); -- cgit v1.2.3 From fd158d79d33d3c8b693e3e2d8c0e3068d529c2dc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 29 Jul 2013 15:41:52 +0200 Subject: netfilter: tproxy: remove nf_tproxy_core, keep tw sk assigned to skb The module was "permanent", due to the special tproxy skb->destructor. Nowadays we have tcp early demux and its sock_edemux destructor in networking core which can be used instead. Thanks to early demux changes the input path now also handles "skb->sk is tw socket" correctly, so this no longer needs the special handling introduced with commit d503b30bd648b3cb4e5f50b65d27e389960cc6d9 (netfilter: tproxy: do not assign timewait sockets to skb->sk). Thus: - move assign_sock function to where its needed - don't prevent timewait sockets from being assigned to the skb - remove nf_tproxy_core. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- Documentation/networking/tproxy.txt | 5 ++- include/net/netfilter/nf_tproxy_core.h | 4 --- net/netfilter/Kconfig | 22 +++--------- net/netfilter/Makefile | 3 -- net/netfilter/nf_tproxy_core.c | 62 ---------------------------------- net/netfilter/xt_TPROXY.c | 9 +++++ 6 files changed, 16 insertions(+), 89 deletions(-) delete mode 100644 net/netfilter/nf_tproxy_core.c (limited to 'net/netfilter') diff --git a/Documentation/networking/tproxy.txt b/Documentation/networking/tproxy.txt index 7b5996d9357e..ec11429e1d42 100644 --- a/Documentation/networking/tproxy.txt +++ b/Documentation/networking/tproxy.txt @@ -2,9 +2,8 @@ Transparent proxy support ========================= This feature adds Linux 2.2-like transparent proxy support to current kernels. -To use it, enable NETFILTER_TPROXY, the socket match and the TPROXY target in -your kernel config. You will need policy routing too, so be sure to enable that -as well. +To use it, enable the socket match and the TPROXY target in your kernel config. +You will need policy routing too, so be sure to enable that as well. 1. Making non-local sockets work diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h index 36d9379d4c4b..975ffa4545a9 100644 --- a/include/net/netfilter/nf_tproxy_core.h +++ b/include/net/netfilter/nf_tproxy_core.h @@ -203,8 +203,4 @@ nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, } #endif -/* assign a socket to the skb -- consumes sk */ -void -nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk); - #endif diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 56d22cae5906..c45fc1a60e0d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -410,20 +410,6 @@ config NF_NAT_TFTP endif # NF_CONNTRACK -# transparent proxy support -config NETFILTER_TPROXY - tristate "Transparent proxying support" - depends on IP_NF_MANGLE - depends on NETFILTER_ADVANCED - help - This option enables transparent proxying support, that is, - support for handling non-locally bound IPv4 TCP and UDP sockets. - For it to work you will have to configure certain iptables rules - and use policy routing. For more information on how to set it up - see Documentation/networking/tproxy.txt. - - To compile it as a module, choose M here. If unsure, say N. - config NETFILTER_XTABLES tristate "Netfilter Xtables support (required for ip_tables)" default m if NETFILTER_ADVANCED=n @@ -720,10 +706,10 @@ config NETFILTER_XT_TARGET_TEE this clone be rerouted to another nexthop. config NETFILTER_XT_TARGET_TPROXY - tristate '"TPROXY" target support' - depends on NETFILTER_TPROXY + tristate '"TPROXY" target transparent proxying support' depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED + depends on IP_NF_MANGLE select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES help @@ -731,6 +717,9 @@ config NETFILTER_XT_TARGET_TPROXY REDIRECT. It can only be used in the mangle table and is useful to redirect traffic to a transparent proxy. It does _not_ depend on Netfilter connection tracking and NAT, unlike REDIRECT. + For it to work you will have to configure certain iptables rules + and use policy routing. For more information on how to set it up + see Documentation/networking/tproxy.txt. To compile it as a module, choose M here. If unsure, say N. @@ -1180,7 +1169,6 @@ config NETFILTER_XT_MATCH_SCTP config NETFILTER_XT_MATCH_SOCKET tristate '"socket" match support' - depends on NETFILTER_TPROXY depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED depends on !NF_CONNTRACK || NF_CONNTRACK diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index a1abf87d43bf..ebfa7dc747cd 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -61,9 +61,6 @@ obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o -# transparent proxy support -obj-$(CONFIG_NETFILTER_TPROXY) += nf_tproxy_core.o - # generic X tables obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c deleted file mode 100644 index 474d621cbc2e..000000000000 --- a/net/netfilter/nf_tproxy_core.c +++ /dev/null @@ -1,62 +0,0 @@ -/* - * Transparent proxy support for Linux/iptables - * - * Copyright (c) 2006-2007 BalaBit IT Ltd. - * Author: Balazs Scheidler, Krisztian Kovacs - * - * 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 - -#include -#include -#include -#include -#include - - -static void -nf_tproxy_destructor(struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - - skb->sk = NULL; - skb->destructor = NULL; - - if (sk) - sock_put(sk); -} - -/* consumes sk */ -void -nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) -{ - /* assigning tw sockets complicates things; most - * skb->sk->X checks would have to test sk->sk_state first */ - if (sk->sk_state == TCP_TIME_WAIT) { - inet_twsk_put(inet_twsk(sk)); - return; - } - - skb_orphan(skb); - skb->sk = sk; - skb->destructor = nf_tproxy_destructor; -} -EXPORT_SYMBOL_GPL(nf_tproxy_assign_sock); - -static int __init nf_tproxy_init(void) -{ - pr_info("NF_TPROXY: Transparent proxy support initialized, version 4.1.0\n"); - pr_info("NF_TPROXY: Copyright (c) 2006-2007 BalaBit IT Ltd.\n"); - return 0; -} - -module_init(nf_tproxy_init); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Krisztian Kovacs"); -MODULE_DESCRIPTION("Transparent proxy support core routines"); diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index d7f195388f66..17c40deafa4f 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -117,6 +117,15 @@ tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport, return sk; } +/* assign a socket to the skb -- consumes sk */ +static void +nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) +{ + skb_orphan(skb); + skb->sk = sk; + skb->destructor = sock_edemux; +} + static unsigned int tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, u_int32_t mark_mask, u_int32_t mark_value) -- cgit v1.2.3 From 93742cf8af9dd3b053242b273040aa35fcbf93b3 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 29 Jul 2013 15:41:53 +0200 Subject: netfilter: tproxy: remove nf_tproxy_core.h We've removed nf_tproxy_core.ko, so also remove its header. The lookup helpers are split and then moved to tproxy target/socket match. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tproxy_core.h | 206 --------------------------------- net/netfilter/xt_TPROXY.c | 160 ++++++++++++++++++++++++- net/netfilter/xt_socket.c | 66 ++++++++++- 3 files changed, 220 insertions(+), 212 deletions(-) delete mode 100644 include/net/netfilter/nf_tproxy_core.h (limited to 'net/netfilter') diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h deleted file mode 100644 index 975ffa4545a9..000000000000 --- a/include/net/netfilter/nf_tproxy_core.h +++ /dev/null @@ -1,206 +0,0 @@ -#ifndef _NF_TPROXY_CORE_H -#define _NF_TPROXY_CORE_H - -#include -#include -#include -#include -#include -#include -#include - -#define NFT_LOOKUP_ANY 0 -#define NFT_LOOKUP_LISTENER 1 -#define NFT_LOOKUP_ESTABLISHED 2 - -/* look up and get a reference to a matching socket */ - - -/* This function is used by the 'TPROXY' target and the 'socket' - * match. The following lookups are supported: - * - * Explicit TProxy target rule - * =========================== - * - * This is used when the user wants to intercept a connection matching - * an explicit iptables rule. In this case the sockets are assumed - * matching in preference order: - * - * - match: if there's a fully established connection matching the - * _packet_ tuple, it is returned, assuming the redirection - * already took place and we process a packet belonging to an - * established connection - * - * - match: if there's a listening socket matching the redirection - * (e.g. on-port & on-ip of the connection), it is returned, - * regardless if it was bound to 0.0.0.0 or an explicit - * address. The reasoning is that if there's an explicit rule, it - * does not really matter if the listener is bound to an interface - * or to 0. The user already stated that he wants redirection - * (since he added the rule). - * - * "socket" match based redirection (no specific rule) - * =================================================== - * - * There are connections with dynamic endpoints (e.g. FTP data - * connection) that the user is unable to add explicit rules - * for. These are taken care of by a generic "socket" rule. It is - * assumed that the proxy application is trusted to open such - * connections without explicit iptables rule (except of course the - * generic 'socket' rule). In this case the following sockets are - * matched in preference order: - * - * - match: if there's a fully established connection matching the - * _packet_ tuple - * - * - match: if there's a non-zero bound listener (possibly with a - * non-local address) We don't accept zero-bound listeners, since - * then local services could intercept traffic going through the - * box. - * - * Please note that there's an overlap between what a TPROXY target - * and a socket match will match. Normally if you have both rules the - * "socket" match will be the first one, effectively all packets - * belonging to established connections going through that one. - */ -static inline struct sock * -nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, - const __be32 saddr, const __be32 daddr, - const __be16 sport, const __be16 dport, - const struct net_device *in, int lookup_type) -{ - struct sock *sk; - - /* look up socket */ - switch (protocol) { - case IPPROTO_TCP: - switch (lookup_type) { - case NFT_LOOKUP_ANY: - sk = __inet_lookup(net, &tcp_hashinfo, - saddr, sport, daddr, dport, - in->ifindex); - break; - case NFT_LOOKUP_LISTENER: - sk = inet_lookup_listener(net, &tcp_hashinfo, - saddr, sport, - daddr, dport, - in->ifindex); - - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too */ - - break; - case NFT_LOOKUP_ESTABLISHED: - sk = inet_lookup_established(net, &tcp_hashinfo, - saddr, sport, daddr, dport, - in->ifindex); - break; - default: - WARN_ON(1); - sk = NULL; - break; - } - break; - case IPPROTO_UDP: - sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, - in->ifindex); - if (sk && lookup_type != NFT_LOOKUP_ANY) { - int connected = (sk->sk_state == TCP_ESTABLISHED); - int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0); - - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too */ - if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || - (lookup_type == NFT_LOOKUP_LISTENER && connected)) { - sock_put(sk); - sk = NULL; - } - } - break; - default: - WARN_ON(1); - sk = NULL; - } - - pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n", - protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk); - - return sk; -} - -#if IS_ENABLED(CONFIG_IPV6) -static inline struct sock * -nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, - const struct in6_addr *saddr, const struct in6_addr *daddr, - const __be16 sport, const __be16 dport, - const struct net_device *in, int lookup_type) -{ - struct sock *sk; - - /* look up socket */ - switch (protocol) { - case IPPROTO_TCP: - switch (lookup_type) { - case NFT_LOOKUP_ANY: - sk = inet6_lookup(net, &tcp_hashinfo, - saddr, sport, daddr, dport, - in->ifindex); - break; - case NFT_LOOKUP_LISTENER: - sk = inet6_lookup_listener(net, &tcp_hashinfo, - saddr, sport, - daddr, ntohs(dport), - in->ifindex); - - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too */ - - break; - case NFT_LOOKUP_ESTABLISHED: - sk = __inet6_lookup_established(net, &tcp_hashinfo, - saddr, sport, daddr, ntohs(dport), - in->ifindex); - break; - default: - WARN_ON(1); - sk = NULL; - break; - } - break; - case IPPROTO_UDP: - sk = udp6_lib_lookup(net, saddr, sport, daddr, dport, - in->ifindex); - if (sk && lookup_type != NFT_LOOKUP_ANY) { - int connected = (sk->sk_state == TCP_ESTABLISHED); - int wildcard = ipv6_addr_any(&inet6_sk(sk)->rcv_saddr); - - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too */ - if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || - (lookup_type == NFT_LOOKUP_LISTENER && connected)) { - sock_put(sk); - sk = NULL; - } - } - break; - default: - WARN_ON(1); - sk = NULL; - } - - pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n", - protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk); - - return sk; -} -#endif - -#endif diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 17c40deafa4f..851383a7f461 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -15,7 +15,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -26,13 +28,18 @@ #define XT_TPROXY_HAVE_IPV6 1 #include #include +#include #include #include #endif -#include #include +enum nf_tproxy_lookup_t { + NFT_LOOKUP_LISTENER, + NFT_LOOKUP_ESTABLISHED, +}; + static bool tproxy_sk_is_transparent(struct sock *sk) { if (sk->sk_state != TCP_TIME_WAIT) { @@ -68,6 +75,157 @@ tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) return laddr ? laddr : daddr; } +/* + * This is used when the user wants to intercept a connection matching + * an explicit iptables rule. In this case the sockets are assumed + * matching in preference order: + * + * - match: if there's a fully established connection matching the + * _packet_ tuple, it is returned, assuming the redirection + * already took place and we process a packet belonging to an + * established connection + * + * - match: if there's a listening socket matching the redirection + * (e.g. on-port & on-ip of the connection), it is returned, + * regardless if it was bound to 0.0.0.0 or an explicit + * address. The reasoning is that if there's an explicit rule, it + * does not really matter if the listener is bound to an interface + * or to 0. The user already stated that he wants redirection + * (since he added the rule). + * + * Please note that there's an overlap between what a TPROXY target + * and a socket match will match. Normally if you have both rules the + * "socket" match will be the first one, effectively all packets + * belonging to established connections going through that one. + */ +static inline struct sock * +nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, + const __be32 saddr, const __be32 daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in, + const enum nf_tproxy_lookup_t lookup_type) +{ + struct sock *sk; + + switch (protocol) { + case IPPROTO_TCP: + switch (lookup_type) { + case NFT_LOOKUP_LISTENER: + sk = inet_lookup_listener(net, &tcp_hashinfo, + saddr, sport, + daddr, dport, + in->ifindex); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + break; + case NFT_LOOKUP_ESTABLISHED: + sk = inet_lookup_established(net, &tcp_hashinfo, + saddr, sport, daddr, dport, + in->ifindex); + break; + default: + BUG(); + } + break; + case IPPROTO_UDP: + sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + if (sk) { + int connected = (sk->sk_state == TCP_ESTABLISHED); + int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || + (lookup_type == NFT_LOOKUP_LISTENER && connected)) { + sock_put(sk); + sk = NULL; + } + } + break; + default: + WARN_ON(1); + sk = NULL; + } + + pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n", + protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk); + + return sk; +} + +#if IS_ENABLED(CONFIG_IPV6) +static inline struct sock * +nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, + const struct in6_addr *saddr, const struct in6_addr *daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in, + const enum nf_tproxy_lookup_t lookup_type) +{ + struct sock *sk; + + switch (protocol) { + case IPPROTO_TCP: + switch (lookup_type) { + case NFT_LOOKUP_LISTENER: + sk = inet6_lookup_listener(net, &tcp_hashinfo, + saddr, sport, + daddr, ntohs(dport), + in->ifindex); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + break; + case NFT_LOOKUP_ESTABLISHED: + sk = __inet6_lookup_established(net, &tcp_hashinfo, + saddr, sport, daddr, ntohs(dport), + in->ifindex); + break; + default: + BUG(); + } + break; + case IPPROTO_UDP: + sk = udp6_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + if (sk) { + int connected = (sk->sk_state == TCP_ESTABLISHED); + int wildcard = ipv6_addr_any(&inet6_sk(sk)->rcv_saddr); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || + (lookup_type == NFT_LOOKUP_LISTENER && connected)) { + sock_put(sk); + sk = NULL; + } + } + break; + default: + WARN_ON(1); + sk = NULL; + } + + pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n", + protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk); + + return sk; +} +#endif + /** * tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections * @skb: The skb being processed. diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index f8b71911037a..a7dd108d4063 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -19,12 +19,12 @@ #include #include #include -#include #include #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) #define XT_SOCKET_HAVE_IPV6 1 #include +#include #include #endif @@ -101,6 +101,43 @@ extract_icmp4_fields(const struct sk_buff *skb, return 0; } +/* "socket" match based redirection (no specific rule) + * =================================================== + * + * There are connections with dynamic endpoints (e.g. FTP data + * connection) that the user is unable to add explicit rules + * for. These are taken care of by a generic "socket" rule. It is + * assumed that the proxy application is trusted to open such + * connections without explicit iptables rule (except of course the + * generic 'socket' rule). In this case the following sockets are + * matched in preference order: + * + * - match: if there's a fully established connection matching the + * _packet_ tuple + * + * - match: if there's a non-zero bound listener (possibly with a + * non-local address) We don't accept zero-bound listeners, since + * then local services could intercept traffic going through the + * box. + */ +static struct sock * +xt_socket_get_sock_v4(struct net *net, const u8 protocol, + const __be32 saddr, const __be32 daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in) +{ + switch (protocol) { + case IPPROTO_TCP: + return __inet_lookup(net, &tcp_hashinfo, + saddr, sport, daddr, dport, + in->ifindex); + case IPPROTO_UDP: + return udp4_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + } + return NULL; +} + static bool socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct xt_socket_mtinfo1 *info) @@ -156,9 +193,9 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, #endif if (!sk) - sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol, + sk = xt_socket_get_sock_v4(dev_net(skb->dev), protocol, saddr, daddr, sport, dport, - par->in, NFT_LOOKUP_ANY); + par->in); if (sk) { bool wildcard; bool transparent = true; @@ -261,6 +298,25 @@ extract_icmp6_fields(const struct sk_buff *skb, return 0; } +static struct sock * +xt_socket_get_sock_v6(struct net *net, const u8 protocol, + const struct in6_addr *saddr, const struct in6_addr *daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in) +{ + switch (protocol) { + case IPPROTO_TCP: + return inet6_lookup(net, &tcp_hashinfo, + saddr, sport, daddr, dport, + in->ifindex); + case IPPROTO_UDP: + return udp6_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + } + + return NULL; +} + static bool socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) { @@ -298,9 +354,9 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) } if (!sk) - sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, + sk = xt_socket_get_sock_v6(dev_net(skb->dev), tproto, saddr, daddr, sport, dport, - par->in, NFT_LOOKUP_ANY); + par->in); if (sk) { bool wildcard; bool transparent = true; -- cgit v1.2.3 From 02982c27ba1e1bd9f9d4747214e19ca83aa88d0e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 29 Jul 2013 15:41:54 +0200 Subject: netfilter: nf_conntrack: remove duplicate code in ctnetlink ctnetlink contains copy-paste code from death_by_timeout. In order to avoid changing both places in upcoming event delivery patch, export death_by_timeout functionality and use it in the ctnetlink code. Based on earlier patch from Pablo Neira. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 3 +-- net/netfilter/nf_conntrack_core.c | 29 ++++++++++++++++------------- net/netfilter/nf_conntrack_netlink.c | 18 +++--------------- 3 files changed, 20 insertions(+), 30 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 644d9c223d24..939aced35a02 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -181,8 +181,7 @@ __nf_conntrack_find(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple); extern int nf_conntrack_hash_check_insert(struct nf_conn *ct); -extern void nf_ct_delete_from_lists(struct nf_conn *ct); -extern void nf_ct_dying_timeout(struct nf_conn *ct); +bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report); extern void nf_conntrack_flush_report(struct net *net, u32 portid, int report); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index d32afaff72f8..089e408676fa 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -238,7 +238,7 @@ destroy_conntrack(struct nf_conntrack *nfct) nf_conntrack_free(ct); } -void nf_ct_delete_from_lists(struct nf_conn *ct) +static void nf_ct_delete_from_lists(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); @@ -253,7 +253,6 @@ void nf_ct_delete_from_lists(struct nf_conn *ct) &net->ct.dying); spin_unlock_bh(&nf_conntrack_lock); } -EXPORT_SYMBOL_GPL(nf_ct_delete_from_lists); static void death_by_event(unsigned long ul_conntrack) { @@ -275,7 +274,7 @@ static void death_by_event(unsigned long ul_conntrack) nf_ct_put(ct); } -void nf_ct_dying_timeout(struct nf_conn *ct) +static void nf_ct_dying_timeout(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct); @@ -288,27 +287,33 @@ void nf_ct_dying_timeout(struct nf_conn *ct) (prandom_u32() % net->ct.sysctl_events_retry_timeout); add_timer(&ecache->timeout); } -EXPORT_SYMBOL_GPL(nf_ct_dying_timeout); -static void death_by_timeout(unsigned long ul_conntrack) +bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) { - struct nf_conn *ct = (void *)ul_conntrack; struct nf_conn_tstamp *tstamp; tstamp = nf_conn_tstamp_find(ct); if (tstamp && tstamp->stop == 0) tstamp->stop = ktime_to_ns(ktime_get_real()); - if (!test_bit(IPS_DYING_BIT, &ct->status) && - unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) { + if (!nf_ct_is_dying(ct) && + unlikely(nf_conntrack_event_report(IPCT_DESTROY, ct, + portid, report) < 0)) { /* destroy event was not delivered */ nf_ct_delete_from_lists(ct); nf_ct_dying_timeout(ct); - return; + return false; } set_bit(IPS_DYING_BIT, &ct->status); nf_ct_delete_from_lists(ct); nf_ct_put(ct); + return true; +} +EXPORT_SYMBOL_GPL(nf_ct_delete); + +static void death_by_timeout(unsigned long ul_conntrack) +{ + nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0); } /* @@ -643,10 +648,7 @@ static noinline int early_drop(struct net *net, unsigned int hash) return dropped; if (del_timer(&ct->timeout)) { - death_by_timeout((unsigned long)ct); - /* Check if we indeed killed this entry. Reliable event - delivery may have inserted it into the dying list. */ - if (test_bit(IPS_DYING_BIT, &ct->status)) { + if (nf_ct_delete(ct, 0, 0)) { dropped = 1; NF_CT_STAT_INC_ATOMIC(net, early_drop); } @@ -1253,6 +1255,7 @@ void nf_ct_iterate_cleanup(struct net *net, /* Time to push up daises... */ if (del_timer(&ct->timeout)) death_by_timeout((unsigned long)ct); + /* ... else the timer will get him soon. */ nf_ct_put(ct); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index edc410e778f7..e842c0ded79d 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1038,21 +1038,9 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, } } - if (del_timer(&ct->timeout)) { - if (nf_conntrack_event_report(IPCT_DESTROY, ct, - NETLINK_CB(skb).portid, - nlmsg_report(nlh)) < 0) { - nf_ct_delete_from_lists(ct); - /* we failed to report the event, try later */ - nf_ct_dying_timeout(ct); - nf_ct_put(ct); - return 0; - } - /* death_by_timeout would report the event again */ - set_bit(IPS_DYING_BIT, &ct->status); - nf_ct_delete_from_lists(ct); - nf_ct_put(ct); - } + if (del_timer(&ct->timeout)) + nf_ct_delete(ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); + nf_ct_put(ct); return 0; -- cgit v1.2.3 From 0658cdc8f3babb4a441f5a803a0b644fafcbf9ef Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 28 Jul 2013 22:54:09 +0200 Subject: netfilter: nf_nat: fix locking in nf_nat_seq_adjust() nf_nat_seq_adjust() needs to grab nf_nat_seqofs_lock to protect against concurrent changes to the sequence adjustment data. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_helper.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index 85e20a919081..a7262ed055c6 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -373,6 +373,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, s16 seqoff, ackoff; struct nf_conn_nat *nat = nfct_nat(ct); struct nf_nat_seq *this_way, *other_way; + int res; dir = CTINFO2DIR(ctinfo); @@ -383,6 +384,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, return 0; tcph = (void *)skb->data + protoff; + spin_lock_bh(&nf_nat_seqofs_lock); if (after(ntohl(tcph->seq), this_way->correction_pos)) seqoff = this_way->offset_after; else @@ -407,7 +409,10 @@ nf_nat_seq_adjust(struct sk_buff *skb, tcph->seq = newseq; tcph->ack_seq = newack; - return nf_nat_sack_adjust(skb, protoff, tcph, ct, ctinfo); + res = nf_nat_sack_adjust(skb, protoff, tcph, ct, ctinfo); + spin_unlock_bh(&nf_nat_seqofs_lock); + + return res; } /* Setup NAT on this expected conntrack so it follows master. */ -- cgit v1.2.3 From 2d89c68ac78ae432038ef23371d2fa949d725d43 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 28 Jul 2013 22:54:10 +0200 Subject: netfilter: nf_nat: change sequence number adjustments to 32 bits Using 16 bits is too small, when many adjustments happen the offsets might overflow and break the connection. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- include/net/netfilter/nf_conntrack.h | 2 +- include/net/netfilter/nf_nat.h | 2 +- include/net/netfilter/nf_nat_helper.h | 6 +++--- net/netfilter/nf_conntrack_core.c | 2 +- net/netfilter/nf_conntrack_proto_tcp.c | 4 ++-- net/netfilter/nf_nat_helper.c | 8 ++++---- 7 files changed, 13 insertions(+), 13 deletions(-) (limited to 'net/netfilter') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index f4bbf2cd22d8..655d5d198d49 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -330,7 +330,7 @@ extern struct nfq_ct_hook __rcu *nfq_ct_hook; struct nfq_ct_nat_hook { void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, - u32 ctinfo, int off); + u32 ctinfo, s32 off); }; extern struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook; #else diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 939aced35a02..e5eb8b62538c 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -234,7 +234,7 @@ static inline bool nf_ct_kill(struct nf_conn *ct) } /* These are for NAT. Icky. */ -extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, +extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq); diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index ad14a799fd2e..e2441413675c 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -19,7 +19,7 @@ struct nf_nat_seq { u_int32_t correction_pos; /* sequence number offset before and after last modification */ - int16_t offset_before, offset_after; + int32_t offset_before, offset_after; }; #include diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h index b4d6bfc2af03..194c34794923 100644 --- a/include/net/netfilter/nf_nat_helper.h +++ b/include/net/netfilter/nf_nat_helper.h @@ -41,7 +41,7 @@ extern int nf_nat_mangle_udp_packet(struct sk_buff *skb, extern void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, - __be32 seq, s16 off); + __be32 seq, s32 off); extern int nf_nat_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, @@ -56,11 +56,11 @@ extern int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, extern void nf_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *this); -extern s16 nf_nat_get_offset(const struct nf_conn *ct, +extern s32 nf_nat_get_offset(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq); extern void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - u32 dir, int off); + u32 dir, s32 off); #endif diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 089e408676fa..0934611ff9f3 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1695,7 +1695,7 @@ err_stat: return ret; } -s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, +s32 (*nf_ct_nat_offset)(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq); EXPORT_SYMBOL_GPL(nf_ct_nat_offset); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 7dcc376eea5f..8f308d896324 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -496,7 +496,7 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, } #ifdef CONFIG_NF_NAT_NEEDED -static inline s16 nat_offset(const struct nf_conn *ct, +static inline s32 nat_offset(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq) { @@ -525,7 +525,7 @@ static bool tcp_in_window(const struct nf_conn *ct, struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; __u32 seq, ack, sack, end, win, swin; - s16 receiver_offset; + s32 receiver_offset; bool res; /* diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index a7262ed055c6..ff4a589e3e39 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -68,13 +68,13 @@ adjust_tcp_sequence(u32 seq, } /* Get the offset value, for conntrack */ -s16 nf_nat_get_offset(const struct nf_conn *ct, +s32 nf_nat_get_offset(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq) { struct nf_conn_nat *nat = nfct_nat(ct); struct nf_nat_seq *this_way; - s16 offset; + s32 offset; if (!nat) return 0; @@ -143,7 +143,7 @@ static int enlarge_skb(struct sk_buff *skb, unsigned int extra) } void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, - __be32 seq, s16 off) + __be32 seq, s32 off) { if (!off) return; @@ -370,7 +370,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, struct tcphdr *tcph; int dir; __be32 newseq, newack; - s16 seqoff, ackoff; + s32 seqoff, ackoff; struct nf_conn_nat *nat = nfct_nat(ct); struct nf_nat_seq *this_way, *other_way; int res; -- cgit v1.2.3 From 12e7ada385eada77854174ecaf469a0791277ddd Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 28 Jul 2013 22:54:11 +0200 Subject: netfilter: nf_nat: use per-conntrack locking for sequence number adjustments Get rid of the global lock and use per-conntrack locks for protecting the sequencen number adjustment data. Additionally saves one lock/unlock operation for every TCP packet. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_helper.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index ff4a589e3e39..46b9baa845a6 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -30,8 +30,6 @@ pr_debug("offset_before=%d, offset_after=%d, correction_pos=%u\n", \ x->offset_before, x->offset_after, x->correction_pos); -static DEFINE_SPINLOCK(nf_nat_seqofs_lock); - /* Setup TCP sequence correction given this change at this sequence */ static inline void adjust_tcp_sequence(u32 seq, @@ -49,7 +47,7 @@ adjust_tcp_sequence(u32 seq, pr_debug("adjust_tcp_sequence: Seq_offset before: "); DUMP_OFFSET(this_way); - spin_lock_bh(&nf_nat_seqofs_lock); + spin_lock_bh(&ct->lock); /* SYN adjust. If it's uninitialized, or this is after last * correction, record it: we don't handle more than one @@ -61,31 +59,26 @@ adjust_tcp_sequence(u32 seq, this_way->offset_before = this_way->offset_after; this_way->offset_after += sizediff; } - spin_unlock_bh(&nf_nat_seqofs_lock); + spin_unlock_bh(&ct->lock); pr_debug("adjust_tcp_sequence: Seq_offset after: "); DUMP_OFFSET(this_way); } -/* Get the offset value, for conntrack */ +/* Get the offset value, for conntrack. Caller must have the conntrack locked */ s32 nf_nat_get_offset(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq) { struct nf_conn_nat *nat = nfct_nat(ct); struct nf_nat_seq *this_way; - s32 offset; if (!nat) return 0; this_way = &nat->seq[dir]; - spin_lock_bh(&nf_nat_seqofs_lock); - offset = after(seq, this_way->correction_pos) + return after(seq, this_way->correction_pos) ? this_way->offset_after : this_way->offset_before; - spin_unlock_bh(&nf_nat_seqofs_lock); - - return offset; } /* Frobs data inside this packet, which is linear. */ @@ -384,7 +377,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, return 0; tcph = (void *)skb->data + protoff; - spin_lock_bh(&nf_nat_seqofs_lock); + spin_lock_bh(&ct->lock); if (after(ntohl(tcph->seq), this_way->correction_pos)) seqoff = this_way->offset_after; else @@ -410,7 +403,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, tcph->ack_seq = newack; res = nf_nat_sack_adjust(skb, protoff, tcph, ct, ctinfo); - spin_unlock_bh(&nf_nat_seqofs_lock); + spin_unlock_bh(&ct->lock); return res; } -- cgit v1.2.3 From 71ffe9c77dd7a2b62207953091efa8dafec958dd Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 25 Jul 2013 10:37:49 +0200 Subject: netfilter: xt_TCPMSS: fix handling of malformed TCP header and options Make sure the packet has enough room for the TCP header and that it is not malformed. While at it, store tcph->doff*4 in a variable, as it is used several times. This patch also fixes a possible off by one in case of malformed TCP options. Reported-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_TCPMSS.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 7011c71646f0..6113cc7efffc 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -52,7 +52,8 @@ tcpmss_mangle_packet(struct sk_buff *skb, { const struct xt_tcpmss_info *info = par->targinfo; struct tcphdr *tcph; - unsigned int tcplen, i; + int len, tcp_hdrlen; + unsigned int i; __be16 oldval; u16 newmss; u8 *opt; @@ -64,11 +65,14 @@ tcpmss_mangle_packet(struct sk_buff *skb, if (!skb_make_writable(skb, skb->len)) return -1; - tcplen = skb->len - tcphoff; + len = skb->len - tcphoff; + if (len < (int)sizeof(struct tcphdr)) + return -1; + tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); + tcp_hdrlen = tcph->doff * 4; - /* Header cannot be larger than the packet */ - if (tcplen < tcph->doff*4) + if (len < tcp_hdrlen) return -1; if (info->mss == XT_TCPMSS_CLAMP_PMTU) { @@ -87,9 +91,8 @@ tcpmss_mangle_packet(struct sk_buff *skb, newmss = info->mss; opt = (u_int8_t *)tcph; - for (i = sizeof(struct tcphdr); i < tcph->doff*4; i += optlen(opt, i)) { - if (opt[i] == TCPOPT_MSS && tcph->doff*4 - i >= TCPOLEN_MSS && - opt[i+1] == TCPOLEN_MSS) { + for (i = sizeof(struct tcphdr); i <= tcp_hdrlen - TCPOLEN_MSS; i += optlen(opt, i)) { + if (opt[i] == TCPOPT_MSS && opt[i+1] == TCPOLEN_MSS) { u_int16_t oldmss; oldmss = (opt[i+2] << 8) | opt[i+3]; @@ -112,9 +115,10 @@ tcpmss_mangle_packet(struct sk_buff *skb, } /* There is data after the header so the option can't be added - without moving it, and doing so may make the SYN packet - itself too large. Accept the packet unmodified instead. */ - if (tcplen > tcph->doff*4) + * without moving it, and doing so may make the SYN packet + * itself too large. Accept the packet unmodified instead. + */ + if (len > tcp_hdrlen) return 0; /* @@ -143,10 +147,10 @@ tcpmss_mangle_packet(struct sk_buff *skb, newmss = min(newmss, (u16)1220); opt = (u_int8_t *)tcph + sizeof(struct tcphdr); - memmove(opt + TCPOLEN_MSS, opt, tcplen - sizeof(struct tcphdr)); + memmove(opt + TCPOLEN_MSS, opt, len - sizeof(struct tcphdr)); inet_proto_csum_replace2(&tcph->check, skb, - htons(tcplen), htons(tcplen + TCPOLEN_MSS), 1); + htons(len), htons(len + TCPOLEN_MSS), 1); opt[0] = TCPOPT_MSS; opt[1] = TCPOLEN_MSS; opt[2] = (newmss & 0xff00) >> 8; -- cgit v1.2.3 From a206bcb3b02025b23137f3228109d72e0f835c05 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 25 Jul 2013 10:46:46 +0200 Subject: netfilter: xt_TCPOPTSTRIP: fix possible off by one access Fix a possible off by one access since optlen() touches opt[offset+1] unsafely when i == tcp_hdrlen(skb) - 1. This patch replaces tcp_hdrlen() by the local variable tcp_hdrlen that stores the TCP header length, to save some cycles. Reported-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_TCPOPTSTRIP.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_TCPOPTSTRIP.c b/net/netfilter/xt_TCPOPTSTRIP.c index b68fa191710f..625fa1d636a0 100644 --- a/net/netfilter/xt_TCPOPTSTRIP.c +++ b/net/netfilter/xt_TCPOPTSTRIP.c @@ -38,7 +38,7 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, struct tcphdr *tcph; u_int16_t n, o; u_int8_t *opt; - int len; + int len, tcp_hdrlen; /* This is a fragment, no TCP header is available */ if (par->fragoff != 0) @@ -52,7 +52,9 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, return NF_DROP; tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); - if (tcph->doff * 4 > len) + tcp_hdrlen = tcph->doff * 4; + + if (len < tcp_hdrlen) return NF_DROP; opt = (u_int8_t *)tcph; @@ -61,10 +63,10 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, * Walk through all TCP options - if we find some option to remove, * set all octets to %TCPOPT_NOP and adjust checksum. */ - for (i = sizeof(struct tcphdr); i < tcp_hdrlen(skb); i += optl) { + for (i = sizeof(struct tcphdr); i < tcp_hdrlen - 1; i += optl) { optl = optlen(opt, i); - if (i + optl > tcp_hdrlen(skb)) + if (i + optl > tcp_hdrlen) break; if (!tcpoptstrip_test_bit(info->strip_bmap, opt[i])) -- cgit v1.2.3 From d8b3bfc253d8063fcce9c447ecc4cf3b1735b13a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 4 Aug 2013 11:37:29 +0200 Subject: netfilter: tproxy: fix build with IP6_NF_IPTABLES=n after commit 93742cf (netfilter: tproxy: remove nf_tproxy_core.h) CONFIG_IPV6=y CONFIG_IP6_NF_IPTABLES=n gives us: net/netfilter/xt_TPROXY.c: In function 'nf_tproxy_get_sock_v6': net/netfilter/xt_TPROXY.c:178:4: error: implicit declaration of function 'inet6_lookup_listener' Reported-by: kbuild test robot Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_TPROXY.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 851383a7f461..5d8a3a3cd5a7 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -161,7 +161,7 @@ nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, return sk; } -#if IS_ENABLED(CONFIG_IPV6) +#ifdef XT_TPROXY_HAVE_IPV6 static inline struct sock * nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, const struct in6_addr *saddr, const struct in6_addr *daddr, -- cgit v1.2.3 From e4d091d7bf787cd303383725b8071d0bae76f981 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 1 Aug 2013 12:36:57 +0300 Subject: netfilter: nfnetlink_{log,queue}: fix information leaks in netlink message These structs have a "_pad" member. Also the "phw" structs have an 8 byte "hw_addr[]" array but sometimes only the first 6 bytes are initialized. Signed-off-by: Dan Carpenter Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_log.c | 6 +++++- net/netfilter/nfnetlink_queue_core.c | 5 ++++- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 962e9792e317..d92cc317bf8b 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -419,6 +419,7 @@ __build_packet_message(struct nfnl_log_net *log, nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(inst->group_num); + memset(&pmsg, 0, sizeof(pmsg)); pmsg.hw_protocol = skb->protocol; pmsg.hook = hooknum; @@ -498,7 +499,10 @@ __build_packet_message(struct nfnl_log_net *log, if (indev && skb->dev && skb->mac_header != skb->network_header) { struct nfulnl_msg_packet_hw phw; - int len = dev_parse_header(skb, phw.hw_addr); + int len; + + memset(&phw, 0, sizeof(phw)); + len = dev_parse_header(skb, phw.hw_addr); if (len > 0) { phw.hw_addrlen = htons(len); if (nla_put(inst->skb, NFULA_HWADDR, sizeof(phw), &phw)) diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 971ea145ab3e..8a703c3dd318 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -463,7 +463,10 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, if (indev && entskb->dev && entskb->mac_header != entskb->network_header) { struct nfqnl_msg_packet_hw phw; - int len = dev_parse_header(entskb, phw.hw_addr); + int len; + + memset(&phw, 0, sizeof(phw)); + len = dev_parse_header(entskb, phw.hw_addr); if (len) { phw.hw_addrlen = htons(len); if (nla_put(skb, NFQA_HWADDR, sizeof(phw), &phw)) -- cgit v1.2.3 From 70e3ca79cd0e98d4191aa10b3393c23a9b84a2e8 Mon Sep 17 00:00:00 2001 From: Dragos Foianu Date: Thu, 11 Jul 2013 09:45:42 +0300 Subject: ipvs: fixed spacing at for statements found using checkpatch.pl Signed-off-by: Dragos Foianu Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_lblcr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 3cd85b2fc67c..5199448697f6 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -414,7 +414,7 @@ static void ip_vs_lblcr_flush(struct ip_vs_service *svc) spin_lock_bh(&svc->sched_lock); tbl->dead = 1; - for (i=0; ibucket[i], list) { ip_vs_lblcr_free(en); } @@ -440,7 +440,7 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc) struct ip_vs_lblcr_entry *en; struct hlist_node *next; - for (i=0, j=tbl->rover; irover; i < IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; spin_lock(&svc->sched_lock); @@ -495,7 +495,7 @@ static void ip_vs_lblcr_check_expire(unsigned long data) if (goal > tbl->max_size/2) goal = tbl->max_size/2; - for (i=0, j=tbl->rover; irover; i < IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; spin_lock(&svc->sched_lock); @@ -536,7 +536,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) /* * Initialize the hash buckets */ - for (i=0; ibucket[i]); } tbl->max_size = IP_VS_LBLCR_TAB_SIZE*16; -- cgit v1.2.3 From 54e35cc52346149a7bce8a2f622e215ed17bb56d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 6 Aug 2013 11:20:23 +0200 Subject: ipvs: ip_vs_sh: ip_vs_sh_get_port: check skb_header_pointer for NULL skb_header_pointer could return NULL, so check for it as we do it everywhere else in ipvs code. This fixes a coverity warning. Signed-off-by: Daniel Borkmann Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_sh.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index f16c027df15b..3588faebe529 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -269,14 +269,20 @@ ip_vs_sh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph) switch (iph->protocol) { case IPPROTO_TCP: th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); + if (unlikely(th == NULL)) + return 0; port = th->source; break; case IPPROTO_UDP: uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph); + if (unlikely(uh == NULL)) + return 0; port = uh->source; break; case IPPROTO_SCTP: sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph); + if (unlikely(sh == NULL)) + return 0; port = sh->source; break; default: -- cgit v1.2.3 From c655bc6896b94ee0223393f26155c6daf1e2d148 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 29 Jul 2013 15:41:55 +0200 Subject: netfilter: nf_conntrack: don't send destroy events from iterator Let nf_ct_delete handle delivery of the DESTROY event. Based on earlier patch from Pablo Neira. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 4 +++- net/ipv4/netfilter/ipt_MASQUERADE.c | 2 +- net/ipv6/netfilter/ip6t_MASQUERADE.c | 2 +- net/netfilter/nf_conntrack_core.c | 36 ++++-------------------------------- net/netfilter/nf_conntrack_proto.c | 4 ++-- net/netfilter/nf_nat_core.c | 6 +++--- 6 files changed, 14 insertions(+), 40 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index e5eb8b62538c..0c1288a50e8b 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -248,7 +248,9 @@ extern void nf_ct_untracked_status_or(unsigned long bits); /* Iterate over all conntracks: if iter returns true, it's deleted. */ extern void -nf_ct_iterate_cleanup(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data); +nf_ct_iterate_cleanup(struct net *net, + int (*iter)(struct nf_conn *i, void *data), + void *data, u32 portid, int report); extern void nf_conntrack_free(struct nf_conn *ct); extern struct nf_conn * nf_conntrack_alloc(struct net *net, u16 zone, diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 30e4de940567..00352ce0f0de 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -118,7 +118,7 @@ static int masq_device_event(struct notifier_block *this, NF_CT_ASSERT(dev->ifindex != 0); nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex); + (void *)(long)dev->ifindex, 0, 0); } return NOTIFY_DONE; diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 47bff6107519..3e4e92d5e157 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -76,7 +76,7 @@ static int masq_device_event(struct notifier_block *this, if (event == NETDEV_DOWN) nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex); + (void *)(long)dev->ifindex, 0, 0); return NOTIFY_DONE; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0934611ff9f3..da6f1787a102 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1246,7 +1246,7 @@ found: void nf_ct_iterate_cleanup(struct net *net, int (*iter)(struct nf_conn *i, void *data), - void *data) + void *data, u32 portid, int report) { struct nf_conn *ct; unsigned int bucket = 0; @@ -1254,7 +1254,7 @@ void nf_ct_iterate_cleanup(struct net *net, while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) { /* Time to push up daises... */ if (del_timer(&ct->timeout)) - death_by_timeout((unsigned long)ct); + nf_ct_delete(ct, portid, report); /* ... else the timer will get him soon. */ @@ -1263,30 +1263,6 @@ void nf_ct_iterate_cleanup(struct net *net, } EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup); -struct __nf_ct_flush_report { - u32 portid; - int report; -}; - -static int kill_report(struct nf_conn *i, void *data) -{ - struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data; - struct nf_conn_tstamp *tstamp; - - tstamp = nf_conn_tstamp_find(i); - if (tstamp && tstamp->stop == 0) - tstamp->stop = ktime_to_ns(ktime_get_real()); - - /* If we fail to deliver the event, death_by_timeout() will retry */ - if (nf_conntrack_event_report(IPCT_DESTROY, i, - fr->portid, fr->report) < 0) - return 1; - - /* Avoid the delivery of the destroy event in death_by_timeout(). */ - set_bit(IPS_DYING_BIT, &i->status); - return 1; -} - static int kill_all(struct nf_conn *i, void *data) { return 1; @@ -1304,11 +1280,7 @@ EXPORT_SYMBOL_GPL(nf_ct_free_hashtable); void nf_conntrack_flush_report(struct net *net, u32 portid, int report) { - struct __nf_ct_flush_report fr = { - .portid = portid, - .report = report, - }; - nf_ct_iterate_cleanup(net, kill_report, &fr); + nf_ct_iterate_cleanup(net, kill_all, NULL, portid, report); } EXPORT_SYMBOL_GPL(nf_conntrack_flush_report); @@ -1389,7 +1361,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list) i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { - nf_ct_iterate_cleanup(net, kill_all, NULL); + nf_ct_iterate_cleanup(net, kill_all, NULL, 0, 0); nf_ct_release_dying_list(net); if (atomic_read(&net->ct.count) != 0) busy = 1; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 0ab9636ac57e..ce3004156eeb 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -281,7 +281,7 @@ void nf_ct_l3proto_pernet_unregister(struct net *net, nf_ct_l3proto_unregister_sysctl(net, proto); /* Remove all contrack entries for this protocol */ - nf_ct_iterate_cleanup(net, kill_l3proto, proto); + nf_ct_iterate_cleanup(net, kill_l3proto, proto, 0, 0); } EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_unregister); @@ -476,7 +476,7 @@ void nf_ct_l4proto_pernet_unregister(struct net *net, nf_ct_l4proto_unregister_sysctl(net, pn, l4proto); /* Remove all contrack entries for this protocol */ - nf_ct_iterate_cleanup(net, kill_l4proto, l4proto); + nf_ct_iterate_cleanup(net, kill_l4proto, l4proto, 0, 0); } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 038eee5c8f85..6ff808375b5e 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -497,7 +497,7 @@ static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) rtnl_lock(); for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0); rtnl_unlock(); } @@ -511,7 +511,7 @@ static void nf_nat_l3proto_clean(u8 l3proto) rtnl_lock(); for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0); rtnl_unlock(); } @@ -749,7 +749,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) { struct nf_nat_proto_clean clean = {}; - nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean); + nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean, 0, 0); synchronize_rcu(); nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size); } -- cgit v1.2.3 From 356d7d88e088687b6578ca64601b0a2c9d145296 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 9 Aug 2013 17:21:27 -0700 Subject: netfilter: nf_conntrack: fix tcp_in_window for Fast Open Currently the conntrack checks if the ending sequence of a packet falls within the observed receive window. However it does so even if it has not observe any packet from the remote yet and uses an uninitialized receive window (td_maxwin). If a connection uses Fast Open to send a SYN-data packet which is dropped afterward in the network. The subsequent SYNs retransmits will all fail this check and be discarded, leading to a connection timeout. This is because the SYN retransmit does not contain data payload so end == initial sequence number (isn) + 1 sender->td_end == isn + syn_data_len receiver->td_maxwin == 0 The fix is to only apply this check after td_maxwin is initialized. Reported-by: Michael Chan Signed-off-by: Yuchung Cheng Acked-by: Eric Dumazet Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_tcp.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 7dcc376eea5f..2f8010707d01 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -526,7 +526,7 @@ static bool tcp_in_window(const struct nf_conn *ct, const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; __u32 seq, ack, sack, end, win, swin; s16 receiver_offset; - bool res; + bool res, in_recv_win; /* * Get the required data from the packet. @@ -649,14 +649,18 @@ static bool tcp_in_window(const struct nf_conn *ct, receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); + /* Is the ending sequence in the receive window (if available)? */ + in_recv_win = !receiver->td_maxwin || + after(end, sender->td_end - receiver->td_maxwin - 1); + pr_debug("tcp_in_window: I=%i II=%i III=%i IV=%i\n", before(seq, sender->td_maxend + 1), - after(end, sender->td_end - receiver->td_maxwin - 1), + (in_recv_win ? 1 : 0), before(sack, receiver->td_end + 1), after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)); if (before(seq, sender->td_maxend + 1) && - after(end, sender->td_end - receiver->td_maxwin - 1) && + in_recv_win && before(sack, receiver->td_end + 1) && after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) { /* @@ -725,7 +729,7 @@ static bool tcp_in_window(const struct nf_conn *ct, nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: %s ", before(seq, sender->td_maxend + 1) ? - after(end, sender->td_end - receiver->td_maxwin - 1) ? + in_recv_win ? before(sack, receiver->td_end + 1) ? after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1) ? "BUG" : "ACK is under the lower bound (possible overly delayed ACK)" -- cgit v1.2.3 From 0ef71ee1a5b92c038abefd8991d5368e6031d7de Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 7 Aug 2013 19:12:34 +0200 Subject: netfilter: ctnetlink: refactor ctnetlink_create_expect This patch refactors ctnetlink_create_expect by spliting it in two chunks. As a result, we have a new function ctnetlink_alloc_expect to allocate and to setup the expectation from ctnetlink. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 156 +++++++++++++++++++---------------- 1 file changed, 87 insertions(+), 69 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index e842c0ded79d..9aaa68bbbcdb 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2735,76 +2735,26 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, #endif } -static int -ctnetlink_create_expect(struct net *net, u16 zone, - const struct nlattr * const cda[], - u_int8_t u3, - u32 portid, int report) +static struct nf_conntrack_expect * +ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, + struct nf_conntrack_helper *helper, + struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple *mask) { - struct nf_conntrack_tuple tuple, mask, master_tuple; - struct nf_conntrack_tuple_hash *h = NULL; + u_int32_t class = 0; struct nf_conntrack_expect *exp; - struct nf_conn *ct; struct nf_conn_help *help; - struct nf_conntrack_helper *helper = NULL; - u_int32_t class = 0; - int err = 0; - - /* caller guarantees that those three CTA_EXPECT_* exist */ - err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); - if (err < 0) - return err; - err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3); - if (err < 0) - return err; - err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3); - if (err < 0) - return err; - - /* Look for master conntrack of this expectation */ - h = nf_conntrack_find_get(net, zone, &master_tuple); - if (!h) - return -ENOENT; - ct = nf_ct_tuplehash_to_ctrack(h); - - /* Look for helper of this expectation */ - if (cda[CTA_EXPECT_HELP_NAME]) { - const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); - - helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), - nf_ct_protonum(ct)); - if (helper == NULL) { -#ifdef CONFIG_MODULES - if (request_module("nfct-helper-%s", helpname) < 0) { - err = -EOPNOTSUPP; - goto out; - } - - helper = __nf_conntrack_helper_find(helpname, - nf_ct_l3num(ct), - nf_ct_protonum(ct)); - if (helper) { - err = -EAGAIN; - goto out; - } -#endif - err = -EOPNOTSUPP; - goto out; - } - } + int err; if (cda[CTA_EXPECT_CLASS] && helper) { class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS])); - if (class > helper->expect_class_max) { - err = -EINVAL; - goto out; - } + if (class > helper->expect_class_max) + return ERR_PTR(-EINVAL); } exp = nf_ct_expect_alloc(ct); - if (!exp) { - err = -ENOMEM; - goto out; - } + if (!exp) + return ERR_PTR(-ENOMEM); + help = nfct_help(ct); if (!help) { if (!cda[CTA_EXPECT_TIMEOUT]) { @@ -2842,21 +2792,89 @@ ctnetlink_create_expect(struct net *net, u16 zone, exp->class = class; exp->master = ct; exp->helper = helper; - memcpy(&exp->tuple, &tuple, sizeof(struct nf_conntrack_tuple)); - memcpy(&exp->mask.src.u3, &mask.src.u3, sizeof(exp->mask.src.u3)); - exp->mask.src.u.all = mask.src.u.all; + exp->tuple = *tuple; + exp->mask.src.u3 = mask->src.u3; + exp->mask.src.u.all = mask->src.u.all; if (cda[CTA_EXPECT_NAT]) { err = ctnetlink_parse_expect_nat(cda[CTA_EXPECT_NAT], - exp, u3); + exp, nf_ct_l3num(ct)); if (err < 0) goto err_out; } - err = nf_ct_expect_related_report(exp, portid, report); + return exp; err_out: nf_ct_expect_put(exp); -out: - nf_ct_put(nf_ct_tuplehash_to_ctrack(h)); + return ERR_PTR(err); +} + +static int +ctnetlink_create_expect(struct net *net, u16 zone, + const struct nlattr * const cda[], + u_int8_t u3, u32 portid, int report) +{ + struct nf_conntrack_tuple tuple, mask, master_tuple; + struct nf_conntrack_tuple_hash *h = NULL; + struct nf_conntrack_helper *helper = NULL; + struct nf_conntrack_expect *exp; + struct nf_conn *ct; + int err; + + /* caller guarantees that those three CTA_EXPECT_* exist */ + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); + if (err < 0) + return err; + err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3); + if (err < 0) + return err; + err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3); + if (err < 0) + return err; + + /* Look for master conntrack of this expectation */ + h = nf_conntrack_find_get(net, zone, &master_tuple); + if (!h) + return -ENOENT; + ct = nf_ct_tuplehash_to_ctrack(h); + + if (cda[CTA_EXPECT_HELP_NAME]) { + const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); + + helper = __nf_conntrack_helper_find(helpname, u3, + nf_ct_protonum(ct)); + if (helper == NULL) { +#ifdef CONFIG_MODULES + if (request_module("nfct-helper-%s", helpname) < 0) { + err = -EOPNOTSUPP; + goto err_ct; + } + helper = __nf_conntrack_helper_find(helpname, u3, + nf_ct_protonum(ct)); + if (helper) { + err = -EAGAIN; + goto err_ct; + } +#endif + err = -EOPNOTSUPP; + goto err_ct; + } + } + + exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask); + if (IS_ERR(exp)) { + err = PTR_ERR(exp); + goto err_ct; + } + + err = nf_ct_expect_related_report(exp, portid, report); + if (err < 0) + goto err_exp; + + return 0; +err_exp: + nf_ct_expect_put(exp); +err_ct: + nf_ct_put(ct); return err; } -- cgit v1.2.3 From bd0779370588386e4a67ba5d0b176cfded8e6a53 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 7 Aug 2013 18:13:20 +0200 Subject: netfilter: nfnetlink_queue: allow to attach expectations to conntracks This patch adds the capability to attach expectations via nfnetlink_queue. This is required by conntrack helpers that trigger expectations based on the first packet seen like the TFTP and the DHCPv6 user-space helpers. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 + include/net/netfilter/nfnetlink_queue.h | 8 +++ include/uapi/linux/netfilter/nfnetlink_queue.h | 1 + net/netfilter/nf_conntrack_netlink.c | 95 ++++++++++++++++++++++---- net/netfilter/nfnetlink_queue_core.c | 9 ++- net/netfilter/nfnetlink_queue_ct.c | 15 ++++ 6 files changed, 114 insertions(+), 16 deletions(-) (limited to 'net/netfilter') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 655d5d198d49..e2cf786be22f 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -325,6 +325,8 @@ struct nfq_ct_hook { size_t (*build_size)(const struct nf_conn *ct); int (*build)(struct sk_buff *skb, struct nf_conn *ct); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); + int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, + u32 portid, u32 report); }; extern struct nfq_ct_hook __rcu *nfq_ct_hook; diff --git a/include/net/netfilter/nfnetlink_queue.h b/include/net/netfilter/nfnetlink_queue.h index 86267a529514..aff88ba91391 100644 --- a/include/net/netfilter/nfnetlink_queue.h +++ b/include/net/netfilter/nfnetlink_queue.h @@ -15,6 +15,8 @@ int nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo); void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int diff); +int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, + u32 portid, u32 report); #else inline struct nf_conn * nfqnl_ct_get(struct sk_buff *entskb, size_t *size, enum ip_conntrack_info *ctinfo) @@ -39,5 +41,11 @@ inline void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int diff) { } + +inline int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, + u32 portid, u32 report) +{ + return 0; +} #endif /* NF_CONNTRACK */ #endif diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h index 3a9b92147339..0132bad79de7 100644 --- a/include/uapi/linux/netfilter/nfnetlink_queue.h +++ b/include/uapi/linux/netfilter/nfnetlink_queue.h @@ -46,6 +46,7 @@ enum nfqnl_attr_type { NFQA_CT_INFO, /* enum ip_conntrack_info */ NFQA_CAP_LEN, /* __u32 length of captured packet */ NFQA_SKB_INFO, /* __u32 skb meta information */ + NFQA_EXP, /* nf_conntrack_netlink.h */ __NFQA_MAX }; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 9aaa68bbbcdb..fa61fea63234 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1987,6 +1987,27 @@ out: return err == -EAGAIN ? -ENOBUFS : err; } +static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { + [CTA_EXPECT_MASTER] = { .type = NLA_NESTED }, + [CTA_EXPECT_TUPLE] = { .type = NLA_NESTED }, + [CTA_EXPECT_MASK] = { .type = NLA_NESTED }, + [CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 }, + [CTA_EXPECT_ID] = { .type = NLA_U32 }, + [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING, + .len = NF_CT_HELPER_NAME_LEN - 1 }, + [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, + [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, + [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, + [CTA_EXPECT_NAT] = { .type = NLA_NESTED }, + [CTA_EXPECT_FN] = { .type = NLA_NUL_STRING }, +}; + +static struct nf_conntrack_expect * +ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct, + struct nf_conntrack_helper *helper, + struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple *mask); + #ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT static size_t ctnetlink_nfqueue_build_size(const struct nf_conn *ct) @@ -2127,10 +2148,69 @@ ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct) return ret; } +static int ctnetlink_nfqueue_exp_parse(const struct nlattr * const *cda, + const struct nf_conn *ct, + struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple *mask) +{ + int err; + + err = ctnetlink_parse_tuple(cda, tuple, CTA_EXPECT_TUPLE, + nf_ct_l3num(ct)); + if (err < 0) + return err; + + return ctnetlink_parse_tuple(cda, mask, CTA_EXPECT_MASK, + nf_ct_l3num(ct)); +} + +static int +ctnetlink_nfqueue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, + u32 portid, u32 report) +{ + struct nlattr *cda[CTA_EXPECT_MAX+1]; + struct nf_conntrack_tuple tuple, mask; + struct nf_conntrack_helper *helper; + struct nf_conntrack_expect *exp; + int err; + + err = nla_parse_nested(cda, CTA_EXPECT_MAX, attr, exp_nla_policy); + if (err < 0) + return err; + + err = ctnetlink_nfqueue_exp_parse((const struct nlattr * const *)cda, + ct, &tuple, &mask); + if (err < 0) + return err; + + if (cda[CTA_EXPECT_HELP_NAME]) { + const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); + + helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), + nf_ct_protonum(ct)); + if (helper == NULL) + return -EOPNOTSUPP; + } + + exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct, + helper, &tuple, &mask); + if (IS_ERR(exp)) + return PTR_ERR(exp); + + err = nf_ct_expect_related_report(exp, portid, report); + if (err < 0) { + nf_ct_expect_put(exp); + return err; + } + + return 0; +} + static struct nfq_ct_hook ctnetlink_nfqueue_hook = { .build_size = ctnetlink_nfqueue_build_size, .build = ctnetlink_nfqueue_build, .parse = ctnetlink_nfqueue_parse, + .attach_expect = ctnetlink_nfqueue_attach_expect, }; #endif /* CONFIG_NETFILTER_NETLINK_QUEUE_CT */ @@ -2498,21 +2578,6 @@ static int ctnetlink_dump_exp_ct(struct sock *ctnl, struct sk_buff *skb, return err; } -static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { - [CTA_EXPECT_MASTER] = { .type = NLA_NESTED }, - [CTA_EXPECT_TUPLE] = { .type = NLA_NESTED }, - [CTA_EXPECT_MASK] = { .type = NLA_NESTED }, - [CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 }, - [CTA_EXPECT_ID] = { .type = NLA_U32 }, - [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING, - .len = NF_CT_HELPER_NAME_LEN - 1 }, - [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, - [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, - [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, - [CTA_EXPECT_NAT] = { .type = NLA_NESTED }, - [CTA_EXPECT_FN] = { .type = NLA_NUL_STRING }, -}; - static int ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index ec9de12aa488..e8c9f3bb779c 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -859,6 +859,7 @@ static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = { [NFQA_MARK] = { .type = NLA_U32 }, [NFQA_PAYLOAD] = { .type = NLA_UNSPEC }, [NFQA_CT] = { .type = NLA_UNSPEC }, + [NFQA_EXP] = { .type = NLA_UNSPEC }, }; static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { @@ -987,8 +988,14 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, if (entry == NULL) return -ENOENT; - if (nfqa[NFQA_CT]) + if (nfqa[NFQA_CT]) { ct = nfqnl_ct_parse(entry->skb, nfqa[NFQA_CT], &ctinfo); + if (ct && nfqa[NFQA_EXP]) { + nfqnl_attach_expect(ct, nfqa[NFQA_EXP], + NETLINK_CB(skb).portid, + nlmsg_report(nlh)); + } + } if (nfqa[NFQA_PAYLOAD]) { u16 payload_len = nla_len(nfqa[NFQA_PAYLOAD]); diff --git a/net/netfilter/nfnetlink_queue_ct.c b/net/netfilter/nfnetlink_queue_ct.c index ab61d66bc0b9..be893039966d 100644 --- a/net/netfilter/nfnetlink_queue_ct.c +++ b/net/netfilter/nfnetlink_queue_ct.c @@ -96,3 +96,18 @@ void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, if ((ct->status & IPS_NAT_MASK) && diff) nfq_nat_ct->seq_adjust(skb, ct, ctinfo, diff); } + +int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, + u32 portid, u32 report) +{ + struct nfq_ct_hook *nfq_ct; + + if (nf_ct_is_untracked(ct)) + return 0; + + nfq_ct = rcu_dereference(nfq_ct_hook); + if (nfq_ct == NULL) + return -EOPNOTSUPP; + + return nfq_ct->attach_expect(attr, ct, portid, report); +} -- cgit v1.2.3 From 41d73ec053d2424599c4ed8452b889374d523ade Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 27 Aug 2013 08:50:12 +0200 Subject: netfilter: nf_conntrack: make sequence number adjustments usuable without NAT Split out sequence number adjustments from NAT and move them to the conntrack core to make them usable for SYN proxying. The sequence number adjustment information is moved to a seperate extend. The extend is added to new conntracks when a NAT mapping is set up for a connection using a helper. As a side effect, this saves 24 bytes per connection with NAT in the common case that a connection does not have a helper assigned. Signed-off-by: Patrick McHardy Tested-by: Martin Topholm Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 9 +- include/net/netfilter/nf_conntrack_extend.h | 2 + include/net/netfilter/nf_conntrack_seqadj.h | 49 +++++ include/net/netfilter/nf_nat.h | 10 - include/net/netfilter/nf_nat_helper.h | 19 -- include/uapi/linux/netfilter/nf_conntrack_common.h | 3 +- include/uapi/linux/netfilter/nfnetlink_conntrack.h | 15 +- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 7 +- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 7 +- net/netfilter/Makefile | 2 +- net/netfilter/nf_conntrack_core.c | 16 +- net/netfilter/nf_conntrack_netlink.c | 115 +++++------ net/netfilter/nf_conntrack_proto_tcp.c | 18 +- net/netfilter/nf_conntrack_seqadj.c | 218 ++++++++++++++++++++ net/netfilter/nf_nat_core.c | 16 +- net/netfilter/nf_nat_helper.c | 228 +-------------------- net/netfilter/nf_nat_sip.c | 3 +- net/netfilter/nfnetlink_queue_ct.c | 8 +- 18 files changed, 369 insertions(+), 376 deletions(-) create mode 100644 include/net/netfilter/nf_conntrack_seqadj.h create mode 100644 net/netfilter/nf_conntrack_seqadj.c (limited to 'net/netfilter') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index e2cf786be22f..708fe72ab913 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -319,6 +319,7 @@ extern void nf_ct_attach(struct sk_buff *, const struct sk_buff *); extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; struct nf_conn; +enum ip_conntrack_info; struct nlattr; struct nfq_ct_hook { @@ -327,14 +328,10 @@ struct nfq_ct_hook { int (*parse)(const struct nlattr *attr, struct nf_conn *ct); int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report); -}; -extern struct nfq_ct_hook __rcu *nfq_ct_hook; - -struct nfq_ct_nat_hook { void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, - u32 ctinfo, s32 off); + enum ip_conntrack_info ctinfo, s32 off); }; -extern struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook; +extern struct nfq_ct_hook __rcu *nfq_ct_hook; #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 977bc8a46444..2a22bcbfe6e4 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -9,6 +9,7 @@ enum nf_ct_ext_id { NF_CT_EXT_HELPER, #if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) NF_CT_EXT_NAT, + NF_CT_EXT_SEQADJ, #endif NF_CT_EXT_ACCT, #ifdef CONFIG_NF_CONNTRACK_EVENTS @@ -31,6 +32,7 @@ enum nf_ct_ext_id { #define NF_CT_EXT_HELPER_TYPE struct nf_conn_help #define NF_CT_EXT_NAT_TYPE struct nf_conn_nat +#define NF_CT_EXT_SEQADJ_TYPE struct nf_conn_seqadj #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone diff --git a/include/net/netfilter/nf_conntrack_seqadj.h b/include/net/netfilter/nf_conntrack_seqadj.h new file mode 100644 index 000000000000..30bfbbed9f47 --- /dev/null +++ b/include/net/netfilter/nf_conntrack_seqadj.h @@ -0,0 +1,49 @@ +#ifndef _NF_CONNTRACK_SEQADJ_H +#define _NF_CONNTRACK_SEQADJ_H + +#include + +/** + * struct nf_ct_seqadj - sequence number adjustment information + * + * @correction_pos: position of the last TCP sequence number modification + * @offset_before: sequence number offset before last modification + * @offset_after: sequence number offset after last modification + */ +struct nf_ct_seqadj { + u32 correction_pos; + s32 offset_before; + s32 offset_after; +}; + +struct nf_conn_seqadj { + struct nf_ct_seqadj seq[IP_CT_DIR_MAX]; +}; + +static inline struct nf_conn_seqadj *nfct_seqadj(const struct nf_conn *ct) +{ + return nf_ct_ext_find(ct, NF_CT_EXT_SEQADJ); +} + +static inline struct nf_conn_seqadj *nfct_seqadj_ext_add(struct nf_conn *ct) +{ + return nf_ct_ext_add(ct, NF_CT_EXT_SEQADJ, GFP_ATOMIC); +} + +extern int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo, + __be32 seq, s32 off); +extern void nf_ct_tcp_seqadj_set(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + s32 off); + +extern int nf_ct_seq_adjust(struct sk_buff *skb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff); +extern s32 nf_ct_seq_offset(const struct nf_conn *ct, enum ip_conntrack_dir, + u32 seq); + +extern int nf_conntrack_seqadj_init(void); +extern void nf_conntrack_seqadj_fini(void); + +#endif /* _NF_CONNTRACK_SEQADJ_H */ diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index e2441413675c..59a192420053 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -13,15 +13,6 @@ enum nf_nat_manip_type { #define HOOK2MANIP(hooknum) ((hooknum) != NF_INET_POST_ROUTING && \ (hooknum) != NF_INET_LOCAL_IN) -/* NAT sequence number modifications */ -struct nf_nat_seq { - /* position of the last TCP sequence number modification (if any) */ - u_int32_t correction_pos; - - /* sequence number offset before and after last modification */ - int32_t offset_before, offset_after; -}; - #include #include #include @@ -39,7 +30,6 @@ struct nf_conn; /* The structure embedded in the conntrack structure. */ struct nf_conn_nat { struct hlist_node bysource; - struct nf_nat_seq seq[IP_CT_DIR_MAX]; struct nf_conn *ct; union nf_conntrack_nat_help help; #if defined(CONFIG_IP_NF_TARGET_MASQUERADE) || \ diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h index 194c34794923..404324d1d0c4 100644 --- a/include/net/netfilter/nf_nat_helper.h +++ b/include/net/netfilter/nf_nat_helper.h @@ -39,28 +39,9 @@ extern int nf_nat_mangle_udp_packet(struct sk_buff *skb, const char *rep_buffer, unsigned int rep_len); -extern void nf_nat_set_seq_adjust(struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - __be32 seq, s32 off); -extern int nf_nat_seq_adjust(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff); -extern int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff); - /* Setup NAT on this expected conntrack so it follows master, but goes * to port ct->master->saved_proto. */ extern void nf_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *this); -extern s32 nf_nat_get_offset(const struct nf_conn *ct, - enum ip_conntrack_dir dir, - u32 seq); - -extern void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - u32 dir, s32 off); - #endif diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index d69483fb3825..8dd803818ebe 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -99,7 +99,8 @@ enum ip_conntrack_events { IPCT_PROTOINFO, /* protocol information has changed */ IPCT_HELPER, /* new helper has been set */ IPCT_MARK, /* new mark has been set */ - IPCT_NATSEQADJ, /* NAT is doing sequence adjustment */ + IPCT_SEQADJ, /* sequence adjustment has changed */ + IPCT_NATSEQADJ = IPCT_SEQADJ, IPCT_SECMARK, /* new security mark has been set */ IPCT_LABEL, /* new connlabel has been set */ }; diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index 08fabc6c93f3..acad6c52a652 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -42,8 +42,10 @@ enum ctattr_type { CTA_ID, CTA_NAT_DST, CTA_TUPLE_MASTER, - CTA_NAT_SEQ_ADJ_ORIG, - CTA_NAT_SEQ_ADJ_REPLY, + CTA_SEQ_ADJ_ORIG, + CTA_NAT_SEQ_ADJ_ORIG = CTA_SEQ_ADJ_ORIG, + CTA_SEQ_ADJ_REPLY, + CTA_NAT_SEQ_ADJ_REPLY = CTA_SEQ_ADJ_REPLY, CTA_SECMARK, /* obsolete */ CTA_ZONE, CTA_SECCTX, @@ -165,6 +167,15 @@ enum ctattr_protonat { }; #define CTA_PROTONAT_MAX (__CTA_PROTONAT_MAX - 1) +enum ctattr_seqadj { + CTA_SEQADJ_UNSPEC, + CTA_SEQADJ_CORRECTION_POS, + CTA_SEQADJ_OFFSET_BEFORE, + CTA_SEQADJ_OFFSET_AFTER, + __CTA_SEQADJ_MAX +}; +#define CTA_SEQADJ_MAX (__CTA_SEQADJ_MAX - 1) + enum ctattr_natseq { CTA_NAT_SEQ_UNSPEC, CTA_NAT_SEQ_CORRECTION_POS, diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 0a2e0e3e95ba..86f5b34a4ed1 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -136,11 +137,7 @@ static unsigned int ipv4_confirm(unsigned int hooknum, /* adjust seqs for loopback traffic only in outgoing direction */ if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && !nf_is_loopback_packet(skb)) { - typeof(nf_nat_seq_adjust_hook) seq_adjust; - - seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook); - if (!seq_adjust || - !seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) { + if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) { NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); return NF_DROP; } diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index c9b6a6e6a1e8..d6e4dd8b58df 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -158,11 +159,7 @@ static unsigned int ipv6_confirm(unsigned int hooknum, /* adjust seqs for loopback traffic only in outgoing direction */ if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && !nf_is_loopback_packet(skb)) { - typeof(nf_nat_seq_adjust_hook) seq_adjust; - - seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook); - if (!seq_adjust || - !seq_adjust(skb, ct, ctinfo, protoff)) { + if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); return NF_DROP; } diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index ebfa7dc747cd..89a9c1658f5e 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -1,6 +1,6 @@ netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o -nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o +nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index da6f1787a102..00a7a94d4132 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include #include @@ -1326,6 +1327,7 @@ void nf_conntrack_cleanup_end(void) nf_ct_extend_unregister(&nf_ct_zone_extend); #endif nf_conntrack_proto_fini(); + nf_conntrack_seqadj_fini(); nf_conntrack_labels_fini(); nf_conntrack_helper_fini(); nf_conntrack_timeout_fini(); @@ -1531,6 +1533,10 @@ int nf_conntrack_init_start(void) if (ret < 0) goto err_labels; + ret = nf_conntrack_seqadj_init(); + if (ret < 0) + goto err_seqadj; + #ifdef CONFIG_NF_CONNTRACK_ZONES ret = nf_ct_extend_register(&nf_ct_zone_extend); if (ret < 0) @@ -1555,6 +1561,8 @@ err_proto: nf_ct_extend_unregister(&nf_ct_zone_extend); err_extend: #endif + nf_conntrack_seqadj_fini(); +err_seqadj: nf_conntrack_labels_fini(); err_labels: nf_conntrack_helper_fini(); @@ -1577,9 +1585,6 @@ void nf_conntrack_init_end(void) /* For use by REJECT target */ RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach); RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack); - - /* Howto get NAT offsets */ - RCU_INIT_POINTER(nf_ct_nat_offset, NULL); } /* @@ -1666,8 +1671,3 @@ err_slabname: err_stat: return ret; } - -s32 (*nf_ct_nat_offset)(const struct nf_conn *ct, - enum ip_conntrack_dir dir, - u32 seq); -EXPORT_SYMBOL_GPL(nf_ct_nat_offset); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index fa61fea63234..7c55745ececf 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include @@ -381,9 +382,8 @@ nla_put_failure: return -1; } -#ifdef CONFIG_NF_NAT_NEEDED static int -dump_nat_seq_adj(struct sk_buff *skb, const struct nf_nat_seq *natseq, int type) +dump_ct_seq_adj(struct sk_buff *skb, const struct nf_ct_seqadj *seq, int type) { struct nlattr *nest_parms; @@ -391,12 +391,12 @@ dump_nat_seq_adj(struct sk_buff *skb, const struct nf_nat_seq *natseq, int type) if (!nest_parms) goto nla_put_failure; - if (nla_put_be32(skb, CTA_NAT_SEQ_CORRECTION_POS, - htonl(natseq->correction_pos)) || - nla_put_be32(skb, CTA_NAT_SEQ_OFFSET_BEFORE, - htonl(natseq->offset_before)) || - nla_put_be32(skb, CTA_NAT_SEQ_OFFSET_AFTER, - htonl(natseq->offset_after))) + if (nla_put_be32(skb, CTA_SEQADJ_CORRECTION_POS, + htonl(seq->correction_pos)) || + nla_put_be32(skb, CTA_SEQADJ_OFFSET_BEFORE, + htonl(seq->offset_before)) || + nla_put_be32(skb, CTA_SEQADJ_OFFSET_AFTER, + htonl(seq->offset_after))) goto nla_put_failure; nla_nest_end(skb, nest_parms); @@ -408,27 +408,24 @@ nla_put_failure: } static inline int -ctnetlink_dump_nat_seq_adj(struct sk_buff *skb, const struct nf_conn *ct) +ctnetlink_dump_ct_seq_adj(struct sk_buff *skb, const struct nf_conn *ct) { - struct nf_nat_seq *natseq; - struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); + struct nf_ct_seqadj *seq; - if (!(ct->status & IPS_SEQ_ADJUST) || !nat) + if (!(ct->status & IPS_SEQ_ADJUST) || !seqadj) return 0; - natseq = &nat->seq[IP_CT_DIR_ORIGINAL]; - if (dump_nat_seq_adj(skb, natseq, CTA_NAT_SEQ_ADJ_ORIG) == -1) + seq = &seqadj->seq[IP_CT_DIR_ORIGINAL]; + if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_ORIG) == -1) return -1; - natseq = &nat->seq[IP_CT_DIR_REPLY]; - if (dump_nat_seq_adj(skb, natseq, CTA_NAT_SEQ_ADJ_REPLY) == -1) + seq = &seqadj->seq[IP_CT_DIR_REPLY]; + if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_REPLY) == -1) return -1; return 0; } -#else -#define ctnetlink_dump_nat_seq_adj(a, b) (0) -#endif static inline int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) @@ -502,7 +499,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || ctnetlink_dump_master(skb, ct) < 0 || - ctnetlink_dump_nat_seq_adj(skb, ct) < 0) + ctnetlink_dump_ct_seq_adj(skb, ct) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); @@ -707,8 +704,8 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) ctnetlink_dump_master(skb, ct) < 0) goto nla_put_failure; - if (events & (1 << IPCT_NATSEQADJ) && - ctnetlink_dump_nat_seq_adj(skb, ct) < 0) + if (events & (1 << IPCT_SEQADJ) && + ctnetlink_dump_ct_seq_adj(skb, ct) < 0) goto nla_put_failure; } @@ -1439,66 +1436,65 @@ ctnetlink_change_protoinfo(struct nf_conn *ct, const struct nlattr * const cda[] return err; } -#ifdef CONFIG_NF_NAT_NEEDED -static const struct nla_policy nat_seq_policy[CTA_NAT_SEQ_MAX+1] = { - [CTA_NAT_SEQ_CORRECTION_POS] = { .type = NLA_U32 }, - [CTA_NAT_SEQ_OFFSET_BEFORE] = { .type = NLA_U32 }, - [CTA_NAT_SEQ_OFFSET_AFTER] = { .type = NLA_U32 }, +static const struct nla_policy seqadj_policy[CTA_SEQADJ_MAX+1] = { + [CTA_SEQADJ_CORRECTION_POS] = { .type = NLA_U32 }, + [CTA_SEQADJ_OFFSET_BEFORE] = { .type = NLA_U32 }, + [CTA_SEQADJ_OFFSET_AFTER] = { .type = NLA_U32 }, }; static inline int -change_nat_seq_adj(struct nf_nat_seq *natseq, const struct nlattr * const attr) +change_seq_adj(struct nf_ct_seqadj *seq, const struct nlattr * const attr) { int err; - struct nlattr *cda[CTA_NAT_SEQ_MAX+1]; + struct nlattr *cda[CTA_SEQADJ_MAX+1]; - err = nla_parse_nested(cda, CTA_NAT_SEQ_MAX, attr, nat_seq_policy); + err = nla_parse_nested(cda, CTA_SEQADJ_MAX, attr, seqadj_policy); if (err < 0) return err; - if (!cda[CTA_NAT_SEQ_CORRECTION_POS]) + if (!cda[CTA_SEQADJ_CORRECTION_POS]) return -EINVAL; - natseq->correction_pos = - ntohl(nla_get_be32(cda[CTA_NAT_SEQ_CORRECTION_POS])); + seq->correction_pos = + ntohl(nla_get_be32(cda[CTA_SEQADJ_CORRECTION_POS])); - if (!cda[CTA_NAT_SEQ_OFFSET_BEFORE]) + if (!cda[CTA_SEQADJ_OFFSET_BEFORE]) return -EINVAL; - natseq->offset_before = - ntohl(nla_get_be32(cda[CTA_NAT_SEQ_OFFSET_BEFORE])); + seq->offset_before = + ntohl(nla_get_be32(cda[CTA_SEQADJ_OFFSET_BEFORE])); - if (!cda[CTA_NAT_SEQ_OFFSET_AFTER]) + if (!cda[CTA_SEQADJ_OFFSET_AFTER]) return -EINVAL; - natseq->offset_after = - ntohl(nla_get_be32(cda[CTA_NAT_SEQ_OFFSET_AFTER])); + seq->offset_after = + ntohl(nla_get_be32(cda[CTA_SEQADJ_OFFSET_AFTER])); return 0; } static int -ctnetlink_change_nat_seq_adj(struct nf_conn *ct, - const struct nlattr * const cda[]) +ctnetlink_change_seq_adj(struct nf_conn *ct, + const struct nlattr * const cda[]) { + struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); int ret = 0; - struct nf_conn_nat *nat = nfct_nat(ct); - if (!nat) + if (!seqadj) return 0; - if (cda[CTA_NAT_SEQ_ADJ_ORIG]) { - ret = change_nat_seq_adj(&nat->seq[IP_CT_DIR_ORIGINAL], - cda[CTA_NAT_SEQ_ADJ_ORIG]); + if (cda[CTA_SEQ_ADJ_ORIG]) { + ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_ORIGINAL], + cda[CTA_SEQ_ADJ_ORIG]); if (ret < 0) return ret; ct->status |= IPS_SEQ_ADJUST; } - if (cda[CTA_NAT_SEQ_ADJ_REPLY]) { - ret = change_nat_seq_adj(&nat->seq[IP_CT_DIR_REPLY], - cda[CTA_NAT_SEQ_ADJ_REPLY]); + if (cda[CTA_SEQ_ADJ_REPLY]) { + ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_REPLY], + cda[CTA_SEQ_ADJ_REPLY]); if (ret < 0) return ret; @@ -1507,7 +1503,6 @@ ctnetlink_change_nat_seq_adj(struct nf_conn *ct, return 0; } -#endif static int ctnetlink_attach_labels(struct nf_conn *ct, const struct nlattr * const cda[]) @@ -1573,13 +1568,12 @@ ctnetlink_change_conntrack(struct nf_conn *ct, ct->mark = ntohl(nla_get_be32(cda[CTA_MARK])); #endif -#ifdef CONFIG_NF_NAT_NEEDED - if (cda[CTA_NAT_SEQ_ADJ_ORIG] || cda[CTA_NAT_SEQ_ADJ_REPLY]) { - err = ctnetlink_change_nat_seq_adj(ct, cda); + if (cda[CTA_SEQ_ADJ_ORIG] || cda[CTA_SEQ_ADJ_REPLY]) { + err = ctnetlink_change_seq_adj(ct, cda); if (err < 0) return err; } -#endif + if (cda[CTA_LABELS]) { err = ctnetlink_attach_labels(ct, cda); if (err < 0) @@ -1684,13 +1678,11 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, goto err2; } -#ifdef CONFIG_NF_NAT_NEEDED - if (cda[CTA_NAT_SEQ_ADJ_ORIG] || cda[CTA_NAT_SEQ_ADJ_REPLY]) { - err = ctnetlink_change_nat_seq_adj(ct, cda); + if (cda[CTA_SEQ_ADJ_ORIG] || cda[CTA_SEQ_ADJ_REPLY]) { + err = ctnetlink_change_seq_adj(ct, cda); if (err < 0) goto err2; } -#endif memset(&ct->proto, 0, sizeof(ct->proto)); if (cda[CTA_PROTOINFO]) { @@ -1804,7 +1796,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | (1 << IPCT_PROTOINFO) | - (1 << IPCT_NATSEQADJ) | + (1 << IPCT_SEQADJ) | (1 << IPCT_MARK) | events, ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); @@ -1827,7 +1819,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, (1 << IPCT_HELPER) | (1 << IPCT_LABEL) | (1 << IPCT_PROTOINFO) | - (1 << IPCT_NATSEQADJ) | + (1 << IPCT_SEQADJ) | (1 << IPCT_MARK), ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); @@ -2082,7 +2074,7 @@ ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure; if ((ct->status & IPS_SEQ_ADJUST) && - ctnetlink_dump_nat_seq_adj(skb, ct) < 0) + ctnetlink_dump_ct_seq_adj(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK @@ -2211,6 +2203,7 @@ static struct nfq_ct_hook ctnetlink_nfqueue_hook = { .build = ctnetlink_nfqueue_build, .parse = ctnetlink_nfqueue_parse, .attach_expect = ctnetlink_nfqueue_attach_expect, + .seq_adjust = nf_ct_tcp_seqadj_set, }; #endif /* CONFIG_NETFILTER_NETLINK_QUEUE_CT */ diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index d224e001f14f..984a8d1a3359 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -495,21 +496,6 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, } } -#ifdef CONFIG_NF_NAT_NEEDED -static inline s32 nat_offset(const struct nf_conn *ct, - enum ip_conntrack_dir dir, - u32 seq) -{ - typeof(nf_ct_nat_offset) get_offset = rcu_dereference(nf_ct_nat_offset); - - return get_offset != NULL ? get_offset(ct, dir, seq) : 0; -} -#define NAT_OFFSET(ct, dir, seq) \ - (nat_offset(ct, dir, seq)) -#else -#define NAT_OFFSET(ct, dir, seq) 0 -#endif - static bool tcp_in_window(const struct nf_conn *ct, struct ip_ct_tcp *state, enum ip_conntrack_dir dir, @@ -540,7 +526,7 @@ static bool tcp_in_window(const struct nf_conn *ct, tcp_sack(skb, dataoff, tcph, &sack); /* Take into account NAT sequence number mangling */ - receiver_offset = NAT_OFFSET(ct, !dir, ack - 1); + receiver_offset = nf_ct_seq_offset(ct, !dir, ack - 1); ack -= receiver_offset; sack -= receiver_offset; diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c new file mode 100644 index 000000000000..483eb9ce3216 --- /dev/null +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -0,0 +1,218 @@ +#include +#include +#include + +#include +#include +#include + +int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo, + __be32 seq, s32 off) +{ + struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_ct_seqadj *this_way; + + if (off == 0) + return 0; + + set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); + + spin_lock_bh(&ct->lock); + this_way = &seqadj->seq[dir]; + if (this_way->offset_before == this_way->offset_after || + before(this_way->correction_pos, seq)) { + this_way->correction_pos = seq; + this_way->offset_before = this_way->offset_after; + this_way->offset_after += off; + } + spin_unlock_bh(&ct->lock); + return 0; +} +EXPORT_SYMBOL_GPL(nf_ct_seqadj_set); + +void nf_ct_tcp_seqadj_set(struct sk_buff *skb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + s32 off) +{ + const struct tcphdr *th; + + if (nf_ct_protonum(ct) != IPPROTO_TCP) + return; + + th = (struct tcphdr *)(skb_network_header(skb) + ip_hdrlen(skb)); + nf_ct_seqadj_set(ct, ctinfo, th->seq, off); +} +EXPORT_SYMBOL_GPL(nf_ct_tcp_seqadj_set); + +/* Adjust one found SACK option including checksum correction */ +static void nf_ct_sack_block_adjust(struct sk_buff *skb, + struct tcphdr *tcph, + unsigned int sackoff, + unsigned int sackend, + struct nf_ct_seqadj *seq) +{ + while (sackoff < sackend) { + struct tcp_sack_block_wire *sack; + __be32 new_start_seq, new_end_seq; + + sack = (void *)skb->data + sackoff; + if (after(ntohl(sack->start_seq) - seq->offset_before, + seq->correction_pos)) + new_start_seq = htonl(ntohl(sack->start_seq) - + seq->offset_after); + else + new_start_seq = htonl(ntohl(sack->start_seq) - + seq->offset_before); + + if (after(ntohl(sack->end_seq) - seq->offset_before, + seq->correction_pos)) + new_end_seq = htonl(ntohl(sack->end_seq) - + seq->offset_after); + else + new_end_seq = htonl(ntohl(sack->end_seq) - + seq->offset_before); + + pr_debug("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n", + ntohl(sack->start_seq), new_start_seq, + ntohl(sack->end_seq), new_end_seq); + + inet_proto_csum_replace4(&tcph->check, skb, + sack->start_seq, new_start_seq, 0); + inet_proto_csum_replace4(&tcph->check, skb, + sack->end_seq, new_end_seq, 0); + sack->start_seq = new_start_seq; + sack->end_seq = new_end_seq; + sackoff += sizeof(*sack); + } +} + +/* TCP SACK sequence number adjustment */ +static unsigned int nf_ct_sack_adjust(struct sk_buff *skb, + unsigned int protoff, + struct tcphdr *tcph, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + unsigned int dir, optoff, optend; + struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); + + optoff = protoff + sizeof(struct tcphdr); + optend = protoff + tcph->doff * 4; + + if (!skb_make_writable(skb, optend)) + return 0; + + dir = CTINFO2DIR(ctinfo); + + while (optoff < optend) { + /* Usually: option, length. */ + unsigned char *op = skb->data + optoff; + + switch (op[0]) { + case TCPOPT_EOL: + return 1; + case TCPOPT_NOP: + optoff++; + continue; + default: + /* no partial options */ + if (optoff + 1 == optend || + optoff + op[1] > optend || + op[1] < 2) + return 0; + if (op[0] == TCPOPT_SACK && + op[1] >= 2+TCPOLEN_SACK_PERBLOCK && + ((op[1] - 2) % TCPOLEN_SACK_PERBLOCK) == 0) + nf_ct_sack_block_adjust(skb, tcph, optoff + 2, + optoff+op[1], + &seqadj->seq[!dir]); + optoff += op[1]; + } + } + return 1; +} + +/* TCP sequence number adjustment. Returns 1 on success, 0 on failure */ +int nf_ct_seq_adjust(struct sk_buff *skb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff) +{ + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct tcphdr *tcph; + __be32 newseq, newack; + s32 seqoff, ackoff; + struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); + struct nf_ct_seqadj *this_way, *other_way; + int res; + + this_way = &seqadj->seq[dir]; + other_way = &seqadj->seq[!dir]; + + if (!skb_make_writable(skb, protoff + sizeof(*tcph))) + return 0; + + tcph = (void *)skb->data + protoff; + spin_lock_bh(&ct->lock); + if (after(ntohl(tcph->seq), this_way->correction_pos)) + seqoff = this_way->offset_after; + else + seqoff = this_way->offset_before; + + if (after(ntohl(tcph->ack_seq) - other_way->offset_before, + other_way->correction_pos)) + ackoff = other_way->offset_after; + else + ackoff = other_way->offset_before; + + newseq = htonl(ntohl(tcph->seq) + seqoff); + newack = htonl(ntohl(tcph->ack_seq) - ackoff); + + inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0); + inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0); + + pr_debug("Adjusting sequence number from %u->%u, ack from %u->%u\n", + ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), + ntohl(newack)); + + tcph->seq = newseq; + tcph->ack_seq = newack; + + res = nf_ct_sack_adjust(skb, protoff, tcph, ct, ctinfo); + spin_unlock_bh(&ct->lock); + + return res; +} +EXPORT_SYMBOL_GPL(nf_ct_seq_adjust); + +s32 nf_ct_seq_offset(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq) +{ + struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); + struct nf_ct_seqadj *this_way; + + if (!seqadj) + return 0; + + this_way = &seqadj->seq[dir]; + return after(seq, this_way->correction_pos) ? + this_way->offset_after : this_way->offset_before; +} +EXPORT_SYMBOL_GPL(nf_ct_seq_offset); + +static struct nf_ct_ext_type nf_ct_seqadj_extend __read_mostly = { + .len = sizeof(struct nf_conn_seqadj), + .align = __alignof__(struct nf_conn_seqadj), + .id = NF_CT_EXT_SEQADJ, +}; + +int nf_conntrack_seqadj_init(void) +{ + return nf_ct_extend_register(&nf_ct_seqadj_extend); +} + +void nf_conntrack_seqadj_fini(void) +{ + nf_ct_extend_unregister(&nf_ct_seqadj_extend); +} diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 6ff808375b5e..6f0f4f7f68a5 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -402,6 +403,9 @@ nf_nat_setup_info(struct nf_conn *ct, ct->status |= IPS_SRC_NAT; else ct->status |= IPS_DST_NAT; + + if (nfct_help(ct)) + nfct_seqadj_ext_add(ct); } if (maniptype == NF_NAT_MANIP_SRC) { @@ -764,10 +768,6 @@ static struct nf_ct_helper_expectfn follow_master_nat = { .expectfn = nf_nat_follow_master, }; -static struct nfq_ct_nat_hook nfq_ct_nat = { - .seq_adjust = nf_nat_tcp_seq_adjust, -}; - static int __init nf_nat_init(void) { int ret; @@ -787,14 +787,9 @@ static int __init nf_nat_init(void) /* Initialize fake conntrack so that NAT will skip it */ nf_ct_untracked_status_or(IPS_NAT_DONE_MASK); - BUG_ON(nf_nat_seq_adjust_hook != NULL); - RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, nfnetlink_parse_nat_setup); - BUG_ON(nf_ct_nat_offset != NULL); - RCU_INIT_POINTER(nf_ct_nat_offset, nf_nat_get_offset); - RCU_INIT_POINTER(nfq_ct_nat_hook, &nfq_ct_nat); #ifdef CONFIG_XFRM BUG_ON(nf_nat_decode_session_hook != NULL); RCU_INIT_POINTER(nf_nat_decode_session_hook, __nf_nat_decode_session); @@ -813,10 +808,7 @@ static void __exit nf_nat_cleanup(void) unregister_pernet_subsys(&nf_nat_net_ops); nf_ct_extend_unregister(&nat_extend); nf_ct_helper_expectfn_unregister(&follow_master_nat); - RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); - RCU_INIT_POINTER(nf_ct_nat_offset, NULL); - RCU_INIT_POINTER(nfq_ct_nat_hook, NULL); #ifdef CONFIG_XFRM RCU_INIT_POINTER(nf_nat_decode_session_hook, NULL); #endif diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index 46b9baa845a6..2840abb5bb99 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -20,67 +20,13 @@ #include #include #include +#include #include #include #include #include #include -#define DUMP_OFFSET(x) \ - pr_debug("offset_before=%d, offset_after=%d, correction_pos=%u\n", \ - x->offset_before, x->offset_after, x->correction_pos); - -/* Setup TCP sequence correction given this change at this sequence */ -static inline void -adjust_tcp_sequence(u32 seq, - int sizediff, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo) -{ - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - struct nf_conn_nat *nat = nfct_nat(ct); - struct nf_nat_seq *this_way = &nat->seq[dir]; - - pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", - seq, sizediff); - - pr_debug("adjust_tcp_sequence: Seq_offset before: "); - DUMP_OFFSET(this_way); - - spin_lock_bh(&ct->lock); - - /* SYN adjust. If it's uninitialized, or this is after last - * correction, record it: we don't handle more than one - * adjustment in the window, but do deal with common case of a - * retransmit */ - if (this_way->offset_before == this_way->offset_after || - before(this_way->correction_pos, seq)) { - this_way->correction_pos = seq; - this_way->offset_before = this_way->offset_after; - this_way->offset_after += sizediff; - } - spin_unlock_bh(&ct->lock); - - pr_debug("adjust_tcp_sequence: Seq_offset after: "); - DUMP_OFFSET(this_way); -} - -/* Get the offset value, for conntrack. Caller must have the conntrack locked */ -s32 nf_nat_get_offset(const struct nf_conn *ct, - enum ip_conntrack_dir dir, - u32 seq) -{ - struct nf_conn_nat *nat = nfct_nat(ct); - struct nf_nat_seq *this_way; - - if (!nat) - return 0; - - this_way = &nat->seq[dir]; - return after(seq, this_way->correction_pos) - ? this_way->offset_after : this_way->offset_before; -} - /* Frobs data inside this packet, which is linear. */ static void mangle_contents(struct sk_buff *skb, unsigned int dataoff, @@ -135,30 +81,6 @@ static int enlarge_skb(struct sk_buff *skb, unsigned int extra) return 1; } -void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, - __be32 seq, s32 off) -{ - if (!off) - return; - set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); - adjust_tcp_sequence(ntohl(seq), off, ct, ctinfo); - nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); -} -EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust); - -void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - u32 ctinfo, int off) -{ - const struct tcphdr *th; - - if (nf_ct_protonum(ct) != IPPROTO_TCP) - return; - - th = (struct tcphdr *)(skb_network_header(skb)+ ip_hdrlen(skb)); - nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); -} -EXPORT_SYMBOL_GPL(nf_nat_tcp_seq_adjust); - /* Generic function for mangling variable-length address changes inside * NATed TCP connections (like the PORT XXX,XXX,XXX,XXX,XXX,XXX * command in FTP). @@ -203,8 +125,8 @@ int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, datalen, oldlen); if (adjust && rep_len != match_len) - nf_nat_set_seq_adjust(ct, ctinfo, tcph->seq, - (int)rep_len - (int)match_len); + nf_ct_seqadj_set(ct, ctinfo, tcph->seq, + (int)rep_len - (int)match_len); return 1; } @@ -264,150 +186,6 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, } EXPORT_SYMBOL(nf_nat_mangle_udp_packet); -/* Adjust one found SACK option including checksum correction */ -static void -sack_adjust(struct sk_buff *skb, - struct tcphdr *tcph, - unsigned int sackoff, - unsigned int sackend, - struct nf_nat_seq *natseq) -{ - while (sackoff < sackend) { - struct tcp_sack_block_wire *sack; - __be32 new_start_seq, new_end_seq; - - sack = (void *)skb->data + sackoff; - if (after(ntohl(sack->start_seq) - natseq->offset_before, - natseq->correction_pos)) - new_start_seq = htonl(ntohl(sack->start_seq) - - natseq->offset_after); - else - new_start_seq = htonl(ntohl(sack->start_seq) - - natseq->offset_before); - - if (after(ntohl(sack->end_seq) - natseq->offset_before, - natseq->correction_pos)) - new_end_seq = htonl(ntohl(sack->end_seq) - - natseq->offset_after); - else - new_end_seq = htonl(ntohl(sack->end_seq) - - natseq->offset_before); - - pr_debug("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n", - ntohl(sack->start_seq), new_start_seq, - ntohl(sack->end_seq), new_end_seq); - - inet_proto_csum_replace4(&tcph->check, skb, - sack->start_seq, new_start_seq, 0); - inet_proto_csum_replace4(&tcph->check, skb, - sack->end_seq, new_end_seq, 0); - sack->start_seq = new_start_seq; - sack->end_seq = new_end_seq; - sackoff += sizeof(*sack); - } -} - -/* TCP SACK sequence number adjustment */ -static inline unsigned int -nf_nat_sack_adjust(struct sk_buff *skb, - unsigned int protoff, - struct tcphdr *tcph, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo) -{ - unsigned int dir, optoff, optend; - struct nf_conn_nat *nat = nfct_nat(ct); - - optoff = protoff + sizeof(struct tcphdr); - optend = protoff + tcph->doff * 4; - - if (!skb_make_writable(skb, optend)) - return 0; - - dir = CTINFO2DIR(ctinfo); - - while (optoff < optend) { - /* Usually: option, length. */ - unsigned char *op = skb->data + optoff; - - switch (op[0]) { - case TCPOPT_EOL: - return 1; - case TCPOPT_NOP: - optoff++; - continue; - default: - /* no partial options */ - if (optoff + 1 == optend || - optoff + op[1] > optend || - op[1] < 2) - return 0; - if (op[0] == TCPOPT_SACK && - op[1] >= 2+TCPOLEN_SACK_PERBLOCK && - ((op[1] - 2) % TCPOLEN_SACK_PERBLOCK) == 0) - sack_adjust(skb, tcph, optoff+2, - optoff+op[1], &nat->seq[!dir]); - optoff += op[1]; - } - } - return 1; -} - -/* TCP sequence number adjustment. Returns 1 on success, 0 on failure */ -int -nf_nat_seq_adjust(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff) -{ - struct tcphdr *tcph; - int dir; - __be32 newseq, newack; - s32 seqoff, ackoff; - struct nf_conn_nat *nat = nfct_nat(ct); - struct nf_nat_seq *this_way, *other_way; - int res; - - dir = CTINFO2DIR(ctinfo); - - this_way = &nat->seq[dir]; - other_way = &nat->seq[!dir]; - - if (!skb_make_writable(skb, protoff + sizeof(*tcph))) - return 0; - - tcph = (void *)skb->data + protoff; - spin_lock_bh(&ct->lock); - if (after(ntohl(tcph->seq), this_way->correction_pos)) - seqoff = this_way->offset_after; - else - seqoff = this_way->offset_before; - - if (after(ntohl(tcph->ack_seq) - other_way->offset_before, - other_way->correction_pos)) - ackoff = other_way->offset_after; - else - ackoff = other_way->offset_before; - - newseq = htonl(ntohl(tcph->seq) + seqoff); - newack = htonl(ntohl(tcph->ack_seq) - ackoff); - - inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0); - inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0); - - pr_debug("Adjusting sequence number from %u->%u, ack from %u->%u\n", - ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), - ntohl(newack)); - - tcph->seq = newseq; - tcph->ack_seq = newack; - - res = nf_nat_sack_adjust(skb, protoff, tcph, ct, ctinfo); - spin_unlock_bh(&ct->lock); - - return res; -} - /* Setup NAT on this expected conntrack so it follows master. */ /* If we fail to get a free NAT slot, we'll get dropped on confirm */ void nf_nat_follow_master(struct nf_conn *ct, diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index dac11f73868e..f9790405b7ff 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -20,6 +20,7 @@ #include #include #include +#include #include MODULE_LICENSE("GPL"); @@ -308,7 +309,7 @@ static void nf_nat_sip_seq_adjust(struct sk_buff *skb, unsigned int protoff, return; th = (struct tcphdr *)(skb->data + protoff); - nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); + nf_ct_seqadj_set(ct, ctinfo, th->seq, off); } /* Handles expected signalling connections and media streams */ diff --git a/net/netfilter/nfnetlink_queue_ct.c b/net/netfilter/nfnetlink_queue_ct.c index be893039966d..96cac50e0d12 100644 --- a/net/netfilter/nfnetlink_queue_ct.c +++ b/net/netfilter/nfnetlink_queue_ct.c @@ -87,14 +87,14 @@ nla_put_failure: void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int diff) { - struct nfq_ct_nat_hook *nfq_nat_ct; + struct nfq_ct_hook *nfq_ct; - nfq_nat_ct = rcu_dereference(nfq_ct_nat_hook); - if (nfq_nat_ct == NULL) + nfq_ct = rcu_dereference(nfq_ct_hook); + if (nfq_ct == NULL) return; if ((ct->status & IPS_NAT_MASK) && diff) - nfq_nat_ct->seq_adjust(skb, ct, ctinfo, diff); + nfq_ct->seq_adjust(skb, ct, ctinfo, diff); } int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, -- cgit v1.2.3 From 48b1de4c110a7afa4b85862f6c75af817db26fad Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 27 Aug 2013 08:50:14 +0200 Subject: netfilter: add SYNPROXY core/target Add a SYNPROXY for netfilter. The code is split into two parts, the synproxy core with common functions and an address family specific target. The SYNPROXY receives the connection request from the client, responds with a SYN/ACK containing a SYN cookie and announcing a zero window and checks whether the final ACK from the client contains a valid cookie. It then establishes a connection to the original destination and, if successful, sends a window update to the client with the window size announced by the server. Support for timestamps, SACK, window scaling and MSS options can be statically configured as target parameters if the features of the server are known. If timestamps are used, the timestamp value sent back to the client in the SYN/ACK will be different from the real timestamp of the server. In order to now break PAWS, the timestamps are translated in the direction server->client. Signed-off-by: Patrick McHardy Tested-by: Martin Topholm Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_extend.h | 6 +- include/net/netfilter/nf_conntrack_seqadj.h | 2 + include/net/netfilter/nf_conntrack_synproxy.h | 77 +++++ include/uapi/linux/netfilter/xt_SYNPROXY.h | 16 + net/ipv4/netfilter/Kconfig | 13 + net/ipv4/netfilter/Makefile | 1 + net/ipv4/netfilter/ipt_SYNPROXY.c | 472 ++++++++++++++++++++++++++ net/netfilter/Kconfig | 3 + net/netfilter/Makefile | 3 + net/netfilter/nf_conntrack_core.c | 6 + net/netfilter/nf_conntrack_proto_tcp.c | 16 + net/netfilter/nf_conntrack_seqadj.c | 20 ++ net/netfilter/nf_synproxy_core.c | 432 +++++++++++++++++++++++ 13 files changed, 1066 insertions(+), 1 deletion(-) create mode 100644 include/net/netfilter/nf_conntrack_synproxy.h create mode 100644 include/uapi/linux/netfilter/xt_SYNPROXY.h create mode 100644 net/ipv4/netfilter/ipt_SYNPROXY.c create mode 100644 net/netfilter/nf_synproxy_core.c (limited to 'net/netfilter') diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 2a22bcbfe6e4..ff95434e50ca 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -9,8 +9,8 @@ enum nf_ct_ext_id { NF_CT_EXT_HELPER, #if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) NF_CT_EXT_NAT, - NF_CT_EXT_SEQADJ, #endif + NF_CT_EXT_SEQADJ, NF_CT_EXT_ACCT, #ifdef CONFIG_NF_CONNTRACK_EVENTS NF_CT_EXT_ECACHE, @@ -26,6 +26,9 @@ enum nf_ct_ext_id { #endif #ifdef CONFIG_NF_CONNTRACK_LABELS NF_CT_EXT_LABELS, +#endif +#if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY) + NF_CT_EXT_SYNPROXY, #endif NF_CT_EXT_NUM, }; @@ -39,6 +42,7 @@ enum nf_ct_ext_id { #define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp #define NF_CT_EXT_TIMEOUT_TYPE struct nf_conn_timeout #define NF_CT_EXT_LABELS_TYPE struct nf_conn_labels +#define NF_CT_EXT_SYNPROXY_TYPE struct nf_conn_synproxy /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { diff --git a/include/net/netfilter/nf_conntrack_seqadj.h b/include/net/netfilter/nf_conntrack_seqadj.h index 30bfbbed9f47..f6177a5fe0ca 100644 --- a/include/net/netfilter/nf_conntrack_seqadj.h +++ b/include/net/netfilter/nf_conntrack_seqadj.h @@ -30,6 +30,8 @@ static inline struct nf_conn_seqadj *nfct_seqadj_ext_add(struct nf_conn *ct) return nf_ct_ext_add(ct, NF_CT_EXT_SEQADJ, GFP_ATOMIC); } +extern int nf_ct_seqadj_init(struct nf_conn *ct, enum ip_conntrack_info ctinfo, + s32 off); extern int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo, __be32 seq, s32 off); extern void nf_ct_tcp_seqadj_set(struct sk_buff *skb, diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h new file mode 100644 index 000000000000..806f54a290d6 --- /dev/null +++ b/include/net/netfilter/nf_conntrack_synproxy.h @@ -0,0 +1,77 @@ +#ifndef _NF_CONNTRACK_SYNPROXY_H +#define _NF_CONNTRACK_SYNPROXY_H + +#include + +struct nf_conn_synproxy { + u32 isn; + u32 its; + u32 tsoff; +}; + +static inline struct nf_conn_synproxy *nfct_synproxy(const struct nf_conn *ct) +{ +#if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY) + return nf_ct_ext_find(ct, NF_CT_EXT_SYNPROXY); +#else + return NULL; +#endif +} + +static inline struct nf_conn_synproxy *nfct_synproxy_ext_add(struct nf_conn *ct) +{ +#if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY) + return nf_ct_ext_add(ct, NF_CT_EXT_SYNPROXY, GFP_ATOMIC); +#else + return NULL; +#endif +} + +struct synproxy_stats { + unsigned int syn_received; + unsigned int cookie_invalid; + unsigned int cookie_valid; + unsigned int cookie_retrans; + unsigned int conn_reopened; +}; + +struct synproxy_net { + struct nf_conn *tmpl; + struct synproxy_stats __percpu *stats; +}; + +extern int synproxy_net_id; +static inline struct synproxy_net *synproxy_pernet(struct net *net) +{ + return net_generic(net, synproxy_net_id); +} + +struct synproxy_options { + u8 options; + u8 wscale; + u16 mss; + u32 tsval; + u32 tsecr; +}; + +struct tcphdr; +struct xt_synproxy_info; +extern void synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, + const struct tcphdr *th, + struct synproxy_options *opts); +extern unsigned int synproxy_options_size(const struct synproxy_options *opts); +extern void synproxy_build_options(struct tcphdr *th, + const struct synproxy_options *opts); + +extern void synproxy_init_timestamp_cookie(const struct xt_synproxy_info *info, + struct synproxy_options *opts); +extern void synproxy_check_timestamp_cookie(struct synproxy_options *opts); + +extern unsigned int synproxy_tstamp_adjust(struct sk_buff *skb, + unsigned int protoff, + struct tcphdr *th, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + const struct nf_conn_synproxy *synproxy); + +#endif /* _NF_CONNTRACK_SYNPROXY_H */ diff --git a/include/uapi/linux/netfilter/xt_SYNPROXY.h b/include/uapi/linux/netfilter/xt_SYNPROXY.h new file mode 100644 index 000000000000..2d59fbaa93c6 --- /dev/null +++ b/include/uapi/linux/netfilter/xt_SYNPROXY.h @@ -0,0 +1,16 @@ +#ifndef _XT_SYNPROXY_H +#define _XT_SYNPROXY_H + +#define XT_SYNPROXY_OPT_MSS 0x01 +#define XT_SYNPROXY_OPT_WSCALE 0x02 +#define XT_SYNPROXY_OPT_SACK_PERM 0x04 +#define XT_SYNPROXY_OPT_TIMESTAMP 0x08 +#define XT_SYNPROXY_OPT_ECN 0x10 + +struct xt_synproxy_info { + __u8 options; + __u8 wscale; + __u16 mss; +}; + +#endif /* _XT_SYNPROXY_H */ diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 4e9028017428..1657e39b291f 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -110,6 +110,19 @@ config IP_NF_TARGET_REJECT To compile it as a module, choose M here. If unsure, say N. +config IP_NF_TARGET_SYNPROXY + tristate "SYNPROXY target support" + depends on NF_CONNTRACK && NETFILTER_ADVANCED + select NETFILTER_SYNPROXY + select SYN_COOKIES + help + The SYNPROXY target allows you to intercept TCP connections and + establish them using syncookies before they are passed on to the + server. This allows to avoid conntrack and server resource usage + during SYN-flood attacks. + + To compile it as a module, choose M here. If unsure, say N. + config IP_NF_TARGET_ULOG tristate "ULOG target support (obsolete)" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 007b128eecc9..3622b248b6dd 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -46,6 +46,7 @@ obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o +obj-$(CONFIG_IP_NF_TARGET_SYNPROXY) += ipt_SYNPROXY.o obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o # generic ARP tables diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c new file mode 100644 index 000000000000..94371db6aecc --- /dev/null +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -0,0 +1,472 @@ +/* + * Copyright (c) 2013 Patrick McHardy + * + * 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 +#include +#include + +#include +#include +#include +#include +#include +#include + +static struct iphdr * +synproxy_build_ip(struct sk_buff *skb, u32 saddr, u32 daddr) +{ + struct iphdr *iph; + + skb_reset_network_header(skb); + iph = (struct iphdr *)skb_put(skb, sizeof(*iph)); + iph->version = 4; + iph->ihl = sizeof(*iph) / 4; + iph->tos = 0; + iph->id = 0; + iph->frag_off = htons(IP_DF); + iph->ttl = sysctl_ip_default_ttl; + iph->protocol = IPPROTO_TCP; + iph->check = 0; + iph->saddr = saddr; + iph->daddr = daddr; + + return iph; +} + +static void +synproxy_send_tcp(const struct sk_buff *skb, struct sk_buff *nskb, + struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo, + struct iphdr *niph, struct tcphdr *nth, + unsigned int tcp_hdr_size) +{ + nth->check = ~tcp_v4_check(tcp_hdr_size, niph->saddr, niph->daddr, 0); + nskb->ip_summed = CHECKSUM_PARTIAL; + nskb->csum_start = (unsigned char *)nth - nskb->head; + nskb->csum_offset = offsetof(struct tcphdr, check); + + skb_dst_set_noref(nskb, skb_dst(skb)); + nskb->protocol = htons(ETH_P_IP); + if (ip_route_me_harder(nskb, RTN_UNSPEC)) + goto free_nskb; + + if (nfct) { + nskb->nfct = nfct; + nskb->nfctinfo = ctinfo; + nf_conntrack_get(nfct); + } + + ip_local_out(nskb); + return; + +free_nskb: + kfree_skb(nskb); +} + +static void +synproxy_send_client_synack(const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts) +{ + struct sk_buff *nskb; + struct iphdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + u16 mss = opts->mss; + + iph = ip_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, iph->daddr, iph->saddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->dest; + nth->dest = th->source; + nth->seq = htonl(__cookie_v4_init_sequence(iph, th, &mss)); + nth->ack_seq = htonl(ntohl(th->seq) + 1); + tcp_flag_word(nth) = TCP_FLAG_SYN | TCP_FLAG_ACK; + if (opts->options & XT_SYNPROXY_OPT_ECN) + tcp_flag_word(nth) |= TCP_FLAG_ECE; + nth->doff = tcp_hdr_size / 4; + nth->window = 0; + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + niph, nth, tcp_hdr_size); +} + +static void +synproxy_send_server_syn(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts, u32 recv_seq) +{ + struct sk_buff *nskb; + struct iphdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + + iph = ip_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, iph->saddr, iph->daddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->source; + nth->dest = th->dest; + nth->seq = htonl(recv_seq - 1); + /* ack_seq is used to relay our ISN to the synproxy hook to initialize + * sequence number translation once a connection tracking entry exists. + */ + nth->ack_seq = htonl(ntohl(th->ack_seq) - 1); + tcp_flag_word(nth) = TCP_FLAG_SYN; + if (opts->options & XT_SYNPROXY_OPT_ECN) + tcp_flag_word(nth) |= TCP_FLAG_ECE | TCP_FLAG_CWR; + nth->doff = tcp_hdr_size / 4; + nth->window = th->window; + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, + niph, nth, tcp_hdr_size); +} + +static void +synproxy_send_server_ack(const struct synproxy_net *snet, + const struct ip_ct_tcp *state, + const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts) +{ + struct sk_buff *nskb; + struct iphdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + + iph = ip_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, iph->daddr, iph->saddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->dest; + nth->dest = th->source; + nth->seq = htonl(ntohl(th->ack_seq)); + nth->ack_seq = htonl(ntohl(th->seq) + 1); + tcp_flag_word(nth) = TCP_FLAG_ACK; + nth->doff = tcp_hdr_size / 4; + nth->window = htons(state->seen[IP_CT_DIR_ORIGINAL].td_maxwin); + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); +} + +static void +synproxy_send_client_ack(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts) +{ + struct sk_buff *nskb; + struct iphdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + + iph = ip_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, iph->saddr, iph->daddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->source; + nth->dest = th->dest; + nth->seq = htonl(ntohl(th->seq) + 1); + nth->ack_seq = th->ack_seq; + tcp_flag_word(nth) = TCP_FLAG_ACK; + nth->doff = tcp_hdr_size / 4; + nth->window = ntohs(htons(th->window) >> opts->wscale); + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); +} + +static bool +synproxy_recv_client_ack(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, + struct synproxy_options *opts, u32 recv_seq) +{ + int mss; + + mss = __cookie_v4_check(ip_hdr(skb), th, ntohl(th->ack_seq) - 1); + if (mss == 0) { + this_cpu_inc(snet->stats->cookie_invalid); + return false; + } + + this_cpu_inc(snet->stats->cookie_valid); + opts->mss = mss; + + if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy_check_timestamp_cookie(opts); + + synproxy_send_server_syn(snet, skb, th, opts, recv_seq); + return true; +} + +static unsigned int +synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_synproxy_info *info = par->targinfo; + struct synproxy_net *snet = synproxy_pernet(dev_net(par->in)); + struct synproxy_options opts = {}; + struct tcphdr *th, _th; + + if (nf_ip_checksum(skb, par->hooknum, par->thoff, IPPROTO_TCP)) + return NF_DROP; + + th = skb_header_pointer(skb, par->thoff, sizeof(_th), &_th); + if (th == NULL) + return NF_DROP; + + synproxy_parse_options(skb, par->thoff, th, &opts); + + if (th->syn && !th->ack) { + /* Initial SYN from client */ + this_cpu_inc(snet->stats->syn_received); + + if (th->ece && th->cwr) + opts.options |= XT_SYNPROXY_OPT_ECN; + + opts.options &= info->options; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy_init_timestamp_cookie(info, &opts); + else + opts.options &= ~(XT_SYNPROXY_OPT_WSCALE | + XT_SYNPROXY_OPT_SACK_PERM | + XT_SYNPROXY_OPT_ECN); + + synproxy_send_client_synack(skb, th, &opts); + } else if (th->ack && !(th->fin || th->rst)) + /* ACK from client */ + synproxy_recv_client_ack(snet, skb, th, &opts, ntohl(th->seq)); + + return NF_DROP; +} + +static unsigned int ipv4_synproxy_hook(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct synproxy_net *snet = synproxy_pernet(dev_net(in ? : out)); + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + struct nf_conn_synproxy *synproxy; + struct synproxy_options opts = {}; + const struct ip_ct_tcp *state; + struct tcphdr *th, _th; + unsigned int thoff; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL) + return NF_ACCEPT; + + synproxy = nfct_synproxy(ct); + if (synproxy == NULL) + return NF_ACCEPT; + + if (nf_is_loopback_packet(skb)) + return NF_ACCEPT; + + thoff = ip_hdrlen(skb); + th = skb_header_pointer(skb, thoff, sizeof(_th), &_th); + if (th == NULL) + return NF_DROP; + + state = &ct->proto.tcp; + switch (state->state) { + case TCP_CONNTRACK_CLOSE: + if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { + nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - + ntohl(th->seq) + 1); + break; + } + + if (!th->syn || th->ack || + CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) + break; + + /* Reopened connection - reset the sequence number and timestamp + * adjustments, they will get initialized once the connection is + * reestablished. + */ + nf_ct_seqadj_init(ct, ctinfo, 0); + synproxy->tsoff = 0; + this_cpu_inc(snet->stats->conn_reopened); + + /* fall through */ + case TCP_CONNTRACK_SYN_SENT: + synproxy_parse_options(skb, thoff, th, &opts); + + if (!th->syn && th->ack && + CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + /* Keep-Alives are sent with SEG.SEQ = SND.NXT-1, + * therefore we need to add 1 to make the SYN sequence + * number match the one of first SYN. + */ + if (synproxy_recv_client_ack(snet, skb, th, &opts, + ntohl(th->seq) + 1)) + this_cpu_inc(snet->stats->cookie_retrans); + + return NF_DROP; + } + + synproxy->isn = ntohl(th->ack_seq); + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy->its = opts.tsecr; + break; + case TCP_CONNTRACK_SYN_RECV: + if (!th->syn || !th->ack) + break; + + synproxy_parse_options(skb, thoff, th, &opts); + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy->tsoff = opts.tsval - synproxy->its; + + opts.options &= ~(XT_SYNPROXY_OPT_MSS | + XT_SYNPROXY_OPT_WSCALE | + XT_SYNPROXY_OPT_SACK_PERM); + + swap(opts.tsval, opts.tsecr); + synproxy_send_server_ack(snet, state, skb, th, &opts); + + nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq)); + + swap(opts.tsval, opts.tsecr); + synproxy_send_client_ack(snet, skb, th, &opts); + + consume_skb(skb); + return NF_STOLEN; + default: + break; + } + + synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy); + return NF_ACCEPT; +} + +static int synproxy_tg4_check(const struct xt_tgchk_param *par) +{ + const struct ipt_entry *e = par->entryinfo; + + if (e->ip.proto != IPPROTO_TCP || + e->ip.invflags & XT_INV_PROTO) + return -EINVAL; + + return nf_ct_l3proto_try_module_get(par->family); +} + +static void synproxy_tg4_destroy(const struct xt_tgdtor_param *par) +{ + nf_ct_l3proto_module_put(par->family); +} + +static struct xt_target synproxy_tg4_reg __read_mostly = { + .name = "SYNPROXY", + .family = NFPROTO_IPV4, + .target = synproxy_tg4, + .targetsize = sizeof(struct xt_synproxy_info), + .checkentry = synproxy_tg4_check, + .destroy = synproxy_tg4_destroy, + .me = THIS_MODULE, +}; + +static struct nf_hook_ops ipv4_synproxy_ops[] __read_mostly = { + { + .hook = ipv4_synproxy_hook, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, + }, + { + .hook = ipv4_synproxy_hook, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, + }, +}; + +static int __init synproxy_tg4_init(void) +{ + int err; + + err = nf_register_hooks(ipv4_synproxy_ops, + ARRAY_SIZE(ipv4_synproxy_ops)); + if (err < 0) + goto err1; + + err = xt_register_target(&synproxy_tg4_reg); + if (err < 0) + goto err2; + + return 0; + +err2: + nf_unregister_hooks(ipv4_synproxy_ops, ARRAY_SIZE(ipv4_synproxy_ops)); +err1: + return err; +} + +static void __exit synproxy_tg4_exit(void) +{ + xt_unregister_target(&synproxy_tg4_reg); + nf_unregister_hooks(ipv4_synproxy_ops, ARRAY_SIZE(ipv4_synproxy_ops)); +} + +module_init(synproxy_tg4_init); +module_exit(synproxy_tg4_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy "); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index c45fc1a60e0d..62a171ab204f 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -408,6 +408,9 @@ config NF_NAT_TFTP depends on NF_CONNTRACK && NF_NAT default NF_NAT && NF_CONNTRACK_TFTP +config NETFILTER_SYNPROXY + tristate + endif # NF_CONNTRACK config NETFILTER_XTABLES diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 89a9c1658f5e..c3a0a12907f6 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -61,6 +61,9 @@ obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o +# SYNPROXY +obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o + # generic X tables obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 00a7a94d4132..5d892febd64c 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include #include @@ -799,6 +800,11 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, if (IS_ERR(ct)) return (struct nf_conntrack_tuple_hash *)ct; + if (tmpl && nfct_synproxy(tmpl)) { + nfct_seqadj_ext_add(ct); + nfct_synproxy_ext_add(ct); + } + timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL; if (timeout_ext) timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 984a8d1a3359..44d1ea32570a 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -946,6 +947,21 @@ static int tcp_packet(struct nf_conn *ct, "state %s ", tcp_conntrack_names[old_state]); return NF_ACCEPT; case TCP_CONNTRACK_MAX: + /* Special case for SYN proxy: when the SYN to the server or + * the SYN/ACK from the server is lost, the client may transmit + * a keep-alive packet while in SYN_SENT state. This needs to + * be associated with the original conntrack entry in order to + * generate a new SYN with the correct sequence number. + */ + if (nfct_synproxy(ct) && old_state == TCP_CONNTRACK_SYN_SENT && + index == TCP_ACK_SET && dir == IP_CT_DIR_ORIGINAL && + ct->proto.tcp.last_dir == IP_CT_DIR_ORIGINAL && + ct->proto.tcp.seen[dir].td_end - 1 == ntohl(th->seq)) { + pr_debug("nf_ct_tcp: SYN proxy client keep alive\n"); + spin_unlock_bh(&ct->lock); + return NF_ACCEPT; + } + /* Invalid packet */ pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n", dir, get_conntrack_index(th), old_state); diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index 483eb9ce3216..5f9bfd060dea 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -6,6 +6,26 @@ #include #include +int nf_ct_seqadj_init(struct nf_conn *ct, enum ip_conntrack_info ctinfo, + s32 off) +{ + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_conn_seqadj *seqadj; + struct nf_ct_seqadj *this_way; + + if (off == 0) + return 0; + + set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); + + seqadj = nfct_seqadj(ct); + this_way = &seqadj->seq[dir]; + this_way->offset_before = off; + this_way->offset_after = off; + return 0; +} +EXPORT_SYMBOL_GPL(nf_ct_seqadj_init); + int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo, __be32 seq, s32 off) { diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c new file mode 100644 index 000000000000..d23dc791aca7 --- /dev/null +++ b/net/netfilter/nf_synproxy_core.c @@ -0,0 +1,432 @@ +/* + * Copyright (c) 2013 Patrick McHardy + * + * 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 +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +int synproxy_net_id; +EXPORT_SYMBOL_GPL(synproxy_net_id); + +void +synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, + const struct tcphdr *th, struct synproxy_options *opts) +{ + int length = (th->doff * 4) - sizeof(*th); + u8 buf[40], *ptr; + + ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); + BUG_ON(ptr == NULL); + + opts->options = 0; + while (length > 0) { + int opcode = *ptr++; + int opsize; + + switch (opcode) { + case TCPOPT_EOL: + return; + case TCPOPT_NOP: + length--; + continue; + default: + opsize = *ptr++; + if (opsize < 2) + return; + if (opsize > length) + return; + + switch (opcode) { + case TCPOPT_MSS: + if (opsize == TCPOLEN_MSS) { + opts->mss = get_unaligned_be16(ptr); + opts->options |= XT_SYNPROXY_OPT_MSS; + } + break; + case TCPOPT_WINDOW: + if (opsize == TCPOLEN_WINDOW) { + opts->wscale = *ptr; + if (opts->wscale > 14) + opts->wscale = 14; + opts->options |= XT_SYNPROXY_OPT_WSCALE; + } + break; + case TCPOPT_TIMESTAMP: + if (opsize == TCPOLEN_TIMESTAMP) { + opts->tsval = get_unaligned_be32(ptr); + opts->tsecr = get_unaligned_be32(ptr + 4); + opts->options |= XT_SYNPROXY_OPT_TIMESTAMP; + } + break; + case TCPOPT_SACK_PERM: + if (opsize == TCPOLEN_SACK_PERM) + opts->options |= XT_SYNPROXY_OPT_SACK_PERM; + break; + } + + ptr += opsize - 2; + length -= opsize; + } + } +} +EXPORT_SYMBOL_GPL(synproxy_parse_options); + +unsigned int synproxy_options_size(const struct synproxy_options *opts) +{ + unsigned int size = 0; + + if (opts->options & XT_SYNPROXY_OPT_MSS) + size += TCPOLEN_MSS_ALIGNED; + if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP) + size += TCPOLEN_TSTAMP_ALIGNED; + else if (opts->options & XT_SYNPROXY_OPT_SACK_PERM) + size += TCPOLEN_SACKPERM_ALIGNED; + if (opts->options & XT_SYNPROXY_OPT_WSCALE) + size += TCPOLEN_WSCALE_ALIGNED; + + return size; +} +EXPORT_SYMBOL_GPL(synproxy_options_size); + +void +synproxy_build_options(struct tcphdr *th, const struct synproxy_options *opts) +{ + __be32 *ptr = (__be32 *)(th + 1); + u8 options = opts->options; + + if (options & XT_SYNPROXY_OPT_MSS) + *ptr++ = htonl((TCPOPT_MSS << 24) | + (TCPOLEN_MSS << 16) | + opts->mss); + + if (options & XT_SYNPROXY_OPT_TIMESTAMP) { + if (options & XT_SYNPROXY_OPT_SACK_PERM) + *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | + (TCPOLEN_SACK_PERM << 16) | + (TCPOPT_TIMESTAMP << 8) | + TCPOLEN_TIMESTAMP); + else + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | + TCPOLEN_TIMESTAMP); + + *ptr++ = htonl(opts->tsval); + *ptr++ = htonl(opts->tsecr); + } else if (options & XT_SYNPROXY_OPT_SACK_PERM) + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_SACK_PERM << 8) | + TCPOLEN_SACK_PERM); + + if (options & XT_SYNPROXY_OPT_WSCALE) + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_WINDOW << 16) | + (TCPOLEN_WINDOW << 8) | + opts->wscale); +} +EXPORT_SYMBOL_GPL(synproxy_build_options); + +void synproxy_init_timestamp_cookie(const struct xt_synproxy_info *info, + struct synproxy_options *opts) +{ + opts->tsecr = opts->tsval; + opts->tsval = tcp_time_stamp & ~0x3f; + + if (opts->options & XT_SYNPROXY_OPT_WSCALE) + opts->tsval |= info->wscale; + else + opts->tsval |= 0xf; + + if (opts->options & XT_SYNPROXY_OPT_SACK_PERM) + opts->tsval |= 1 << 4; + + if (opts->options & XT_SYNPROXY_OPT_ECN) + opts->tsval |= 1 << 5; +} +EXPORT_SYMBOL_GPL(synproxy_init_timestamp_cookie); + +void synproxy_check_timestamp_cookie(struct synproxy_options *opts) +{ + opts->wscale = opts->tsecr & 0xf; + if (opts->wscale != 0xf) + opts->options |= XT_SYNPROXY_OPT_WSCALE; + + opts->options |= opts->tsecr & (1 << 4) ? XT_SYNPROXY_OPT_SACK_PERM : 0; + + opts->options |= opts->tsecr & (1 << 5) ? XT_SYNPROXY_OPT_ECN : 0; +} +EXPORT_SYMBOL_GPL(synproxy_check_timestamp_cookie); + +unsigned int synproxy_tstamp_adjust(struct sk_buff *skb, + unsigned int protoff, + struct tcphdr *th, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + const struct nf_conn_synproxy *synproxy) +{ + unsigned int optoff, optend; + u32 *ptr, old; + + if (synproxy->tsoff == 0) + return 1; + + optoff = protoff + sizeof(struct tcphdr); + optend = protoff + th->doff * 4; + + if (!skb_make_writable(skb, optend)) + return 0; + + while (optoff < optend) { + unsigned char *op = skb->data + optoff; + + switch (op[0]) { + case TCPOPT_EOL: + return 1; + case TCPOPT_NOP: + optoff++; + continue; + default: + if (optoff + 1 == optend || + optoff + op[1] > optend || + op[1] < 2) + return 0; + if (op[0] == TCPOPT_TIMESTAMP && + op[1] == TCPOLEN_TIMESTAMP) { + if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) { + ptr = (u32 *)&op[2]; + old = *ptr; + *ptr = htonl(ntohl(*ptr) - + synproxy->tsoff); + } else { + ptr = (u32 *)&op[6]; + old = *ptr; + *ptr = htonl(ntohl(*ptr) + + synproxy->tsoff); + } + inet_proto_csum_replace4(&th->check, skb, + old, *ptr, 0); + return 1; + } + optoff += op[1]; + } + } + return 1; +} +EXPORT_SYMBOL_GPL(synproxy_tstamp_adjust); + +static struct nf_ct_ext_type nf_ct_synproxy_extend __read_mostly = { + .len = sizeof(struct nf_conn_synproxy), + .align = __alignof__(struct nf_conn_synproxy), + .id = NF_CT_EXT_SYNPROXY, +}; + +#ifdef CONFIG_PROC_FS +static void *synproxy_cpu_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct synproxy_net *snet = synproxy_pernet(seq_file_net(seq)); + int cpu; + + if (*pos == 0) + return SEQ_START_TOKEN; + + for (cpu = *pos - 1; cpu < nr_cpu_ids; cpu++) { + if (!cpu_possible(cpu)) + continue; + *pos = cpu + 1; + return per_cpu_ptr(snet->stats, cpu); + } + + return NULL; +} + +static void *synproxy_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct synproxy_net *snet = synproxy_pernet(seq_file_net(seq)); + int cpu; + + for (cpu = *pos; cpu < nr_cpu_ids; cpu++) { + if (!cpu_possible(cpu)) + continue; + *pos = cpu + 1; + return per_cpu_ptr(snet->stats, cpu); + } + + return NULL; +} + +static void synproxy_cpu_seq_stop(struct seq_file *seq, void *v) +{ + return; +} + +static int synproxy_cpu_seq_show(struct seq_file *seq, void *v) +{ + struct synproxy_stats *stats = v; + + if (v == SEQ_START_TOKEN) { + seq_printf(seq, "entries\t\tsyn_received\t" + "cookie_invalid\tcookie_valid\t" + "cookie_retrans\tconn_reopened\n"); + return 0; + } + + seq_printf(seq, "%08x\t%08x\t%08x\t%08x\t%08x\t%08x\n", 0, + stats->syn_received, + stats->cookie_invalid, + stats->cookie_valid, + stats->cookie_retrans, + stats->conn_reopened); + + return 0; +} + +static const struct seq_operations synproxy_cpu_seq_ops = { + .start = synproxy_cpu_seq_start, + .next = synproxy_cpu_seq_next, + .stop = synproxy_cpu_seq_stop, + .show = synproxy_cpu_seq_show, +}; + +static int synproxy_cpu_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &synproxy_cpu_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations synproxy_cpu_seq_fops = { + .owner = THIS_MODULE, + .open = synproxy_cpu_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +static int __net_init synproxy_proc_init(struct net *net) +{ + if (!proc_create("synproxy", S_IRUGO, net->proc_net_stat, + &synproxy_cpu_seq_fops)) + return -ENOMEM; + return 0; +} + +static void __net_exit synproxy_proc_exit(struct net *net) +{ + remove_proc_entry("synproxy", net->proc_net_stat); +} +#else +static int __net_init synproxy_proc_init(struct net *net) +{ + return 0; +} + +static void __net_exit synproxy_proc_exit(struct net *net) +{ + return; +} +#endif /* CONFIG_PROC_FS */ + +static int __net_init synproxy_net_init(struct net *net) +{ + struct synproxy_net *snet = synproxy_pernet(net); + struct nf_conntrack_tuple t; + struct nf_conn *ct; + int err = -ENOMEM; + + memset(&t, 0, sizeof(t)); + ct = nf_conntrack_alloc(net, 0, &t, &t, GFP_KERNEL); + if (IS_ERR(ct)) { + err = PTR_ERR(ct); + goto err1; + } + + __set_bit(IPS_TEMPLATE_BIT, &ct->status); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); + if (!nfct_seqadj_ext_add(ct)) + goto err2; + if (!nfct_synproxy_ext_add(ct)) + goto err2; + + snet->tmpl = ct; + + snet->stats = alloc_percpu(struct synproxy_stats); + if (snet->stats == NULL) + goto err2; + + err = synproxy_proc_init(net); + if (err < 0) + goto err3; + + return 0; + +err3: + free_percpu(snet->stats); +err2: + nf_conntrack_free(ct); +err1: + return err; +} + +static void __net_exit synproxy_net_exit(struct net *net) +{ + struct synproxy_net *snet = synproxy_pernet(net); + + nf_conntrack_free(snet->tmpl); + synproxy_proc_exit(net); + free_percpu(snet->stats); +} + +static struct pernet_operations synproxy_net_ops = { + .init = synproxy_net_init, + .exit = synproxy_net_exit, + .id = &synproxy_net_id, + .size = sizeof(struct synproxy_net), +}; + +static int __init synproxy_core_init(void) +{ + int err; + + err = nf_ct_extend_register(&nf_ct_synproxy_extend); + if (err < 0) + goto err1; + + err = register_pernet_subsys(&synproxy_net_ops); + if (err < 0) + goto err2; + + return 0; + +err2: + nf_ct_extend_unregister(&nf_ct_synproxy_extend); +err1: + return err; +} + +static void __exit synproxy_core_exit(void) +{ + unregister_pernet_subsys(&synproxy_net_ops); + nf_ct_extend_unregister(&nf_ct_synproxy_extend); +} + +module_init(synproxy_core_init); +module_exit(synproxy_core_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy "); -- cgit v1.2.3 From b7e092c05b308674c642ed7fb754d555f0ebba81 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 27 Aug 2013 11:47:26 +0200 Subject: netfilter: ctnetlink: fix uninitialized variable net/netfilter/nf_conntrack_netlink.c: In function 'ctnetlink_nfqueue_attach_expect': 'helper' may be used uninitialized in this function It was only initialized in if CTA_EXPECT_HELP_NAME attribute was present, it must be NULL otherwise. Problem added recently in bd077937 (netfilter: nfnetlink_queue: allow to attach expectations to conntracks). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 7c55745ececf..eea936b70d15 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2162,7 +2162,7 @@ ctnetlink_nfqueue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, { struct nlattr *cda[CTA_EXPECT_MAX+1]; struct nf_conntrack_tuple tuple, mask; - struct nf_conntrack_helper *helper; + struct nf_conntrack_helper *helper = NULL; struct nf_conntrack_expect *exp; int err; -- cgit v1.2.3 From f4de4c89d89df5ead42de9fea895f5b8155270da Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 29 Aug 2013 10:32:09 +0200 Subject: netfilter: synproxy_core: fix warning in __nf_ct_ext_add_length() With CONFIG_NETFILTER_DEBUG we get the following warning during SYNPROXY init: [ 80.558906] WARNING: CPU: 1 PID: 4833 at net/netfilter/nf_conntrack_extend.c:80 __nf_ct_ext_add_length+0x217/0x220 [nf_conntrack]() The reason is that the conntrack template is set to confirmed before adding the extension and it is invalid to add extensions to already confirmed conntracks. Fix by adding the extensions before setting the conntrack to confirmed. Reported-by: Jesper Dangaard Brouer Signed-off-by: Patrick McHardy Acked-by: Jesper Dangaard Brouer Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_synproxy_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index d23dc791aca7..6fd967c6278c 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -356,12 +356,12 @@ static int __net_init synproxy_net_init(struct net *net) goto err1; } - __set_bit(IPS_TEMPLATE_BIT, &ct->status); - __set_bit(IPS_CONFIRMED_BIT, &ct->status); if (!nfct_seqadj_ext_add(ct)) goto err2; if (!nfct_synproxy_ext_add(ct)) goto err2; + __set_bit(IPS_TEMPLATE_BIT, &ct->status); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); snet->tmpl = ct; -- cgit v1.2.3 From 1205e1fa615805c9efa97303b552cf445965752a Mon Sep 17 00:00:00 2001 From: Phil Oester Date: Sun, 1 Sep 2013 08:32:21 -0700 Subject: netfilter: xt_TCPMSS: correct return value in tcpmss_mangle_packet In commit b396966c4 (netfilter: xt_TCPMSS: Fix missing fragmentation handling), I attempted to add safe fragment handling to xt_TCPMSS. However, Andy Padavan of Project N56U correctly points out that returning XT_CONTINUE in this function does not work. The callers (tcpmss_tg[46]) expect to receive a value of 0 in order to return XT_CONTINUE. Signed-off-by: Phil Oester Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_TCPMSS.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 6113cc7efffc..cd24290f3b2f 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -60,7 +60,7 @@ tcpmss_mangle_packet(struct sk_buff *skb, /* This is a fragment, no TCP header is available */ if (par->fragoff != 0) - return XT_CONTINUE; + return 0; if (!skb_make_writable(skb, skb->len)) return -1; -- cgit v1.2.3 From 1a5bbfc3d6b700178b75743a2ba1fd2e58a8f36f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 5 Sep 2013 14:38:03 -0400 Subject: netfilter: Fix build errors with xt_socket.c As reported by Randy Dunlap: ==================== when CONFIG_IPV6=m and CONFIG_NETFILTER_XT_MATCH_SOCKET=y: net/built-in.o: In function `socket_mt6_v1_v2': xt_socket.c:(.text+0x51b55): undefined reference to `udp6_lib_lookup' net/built-in.o: In function `socket_mt_init': xt_socket.c:(.init.text+0x1ef8): undefined reference to `nf_defrag_ipv6_enable' ==================== Like several other modules under net/netfilter/ we have to have a dependency "IPV6 disabled or set compatibly with this module" clause. Reported-by: Randy Dunlap Signed-off-by: David S. Miller --- net/netfilter/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'net/netfilter') diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 62a171ab204f..6e839b6dff2b 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -1175,6 +1175,7 @@ config NETFILTER_XT_MATCH_SOCKET depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED depends on !NF_CONNTRACK || NF_CONNTRACK + depends on (IPV6 || IPV6=n) select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES help -- cgit v1.2.3 From 55524c219aa803887d1c247853842a9566598cba Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 16 Sep 2013 20:00:08 +0200 Subject: netfilter: ipset: Skip really non-first fragments for IPv6 when getting port/protocol Signed-off-by: Jozsef Kadlecsik --- net/netfilter/ipset/ip_set_getport.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c index 6fdf88ae2353..dac156f819ac 100644 --- a/net/netfilter/ipset/ip_set_getport.c +++ b/net/netfilter/ipset/ip_set_getport.c @@ -116,12 +116,12 @@ ip_set_get_ip6_port(const struct sk_buff *skb, bool src, { int protoff; u8 nexthdr; - __be16 frag_off; + __be16 frag_off = 0; nexthdr = ipv6_hdr(skb)->nexthdr; protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); - if (protoff < 0) + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) return false; return get_port(skb, nexthdr, protoff, src, port, proto); -- cgit v1.2.3 From 0f1799ba1a5db4c48b72ac2da2dc70d8c190a73d Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 16 Sep 2013 20:04:53 +0200 Subject: netfilter: ipset: Consistent userspace testing with nomatch flag The "nomatch" commandline flag should invert the matching at testing, similarly to the --return-nomatch flag of the "set" match of iptables. Until now it worked with the elements with "nomatch" flag only. From now on it works with elements without the flag too, i.e: # ipset n test hash:net # ipset a test 10.0.0.0/24 nomatch # ipset t test 10.0.0.1 10.0.0.1 is NOT in set test. # ipset t test 10.0.0.1 nomatch 10.0.0.1 is in set test. # ipset a test 192.168.0.0/24 # ipset t test 192.168.0.1 192.168.0.1 is in set test. # ipset t test 192.168.0.1 nomatch 192.168.0.1 is NOT in set test. Before the patch the results were ... # ipset t test 192.168.0.1 192.168.0.1 is in set test. # ipset t test 192.168.0.1 nomatch 192.168.0.1 is in set test. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 6 ++++-- net/netfilter/ipset/ip_set_core.c | 3 +-- net/netfilter/ipset/ip_set_hash_ipportnet.c | 4 ++-- net/netfilter/ipset/ip_set_hash_net.c | 4 ++-- net/netfilter/ipset/ip_set_hash_netiface.c | 4 ++-- net/netfilter/ipset/ip_set_hash_netport.c | 4 ++-- 6 files changed, 13 insertions(+), 12 deletions(-) (limited to 'net/netfilter') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index d80e2753847c..9ac9fbde7b61 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -296,10 +296,12 @@ ip_set_eexist(int ret, u32 flags) /* Match elements marked with nomatch */ static inline bool -ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt) +ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt, struct ip_set *set) { return adt == IPSET_TEST && - ret == -ENOTEMPTY && ((flags >> 16) & IPSET_FLAG_NOMATCH); + (set->type->features & IPSET_TYPE_NOMATCH) && + ((flags >> 16) & IPSET_FLAG_NOMATCH) && + (ret > 0 || ret == -ENOTEMPTY); } /* Check the NLA_F_NET_BYTEORDER flag */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index f77139007983..c8c303c3386f 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1489,8 +1489,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb, if (ret == -EAGAIN) ret = 1; - return (ret < 0 && ret != -ENOTEMPTY) ? ret : - ret > 0 ? 0 : -IPSET_ERR_EXIST; + return ret > 0 ? 0 : -IPSET_ERR_EXIST; } /* Get headed data of a set */ diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index c6a525373be4..f15f3e28b9c3 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -260,7 +260,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], e.ip = htonl(ip); e.ip2 = htonl(ip2_from & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -544,7 +544,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index da740ceb56ae..223e9f546d0f 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -199,7 +199,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret: ip_set_eexist(ret, flags) ? 0 : ret; } @@ -396,7 +396,7 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 84ae6f6ce624..7d798d5d5cd3 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -368,7 +368,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -634,7 +634,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 9a0869853be5..09d6690bee6f 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -244,7 +244,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !(with_ports || tb[IPSET_ATTR_IP_TO])) { e.ip = htonl(ip & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -489,7 +489,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } -- cgit v1.2.3 From 169faa2e19478b02027df04582ec7543dba1dd16 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 16 Sep 2013 20:07:35 +0200 Subject: netfilter: ipset: Validate the set family and not the set type family at swapping This closes netfilter bugzilla #843, reported by Quentin Armitage. Signed-off-by: Jozsef Kadlecsik --- net/netfilter/ipset/ip_set_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index c8c303c3386f..f2e30fb31e78 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1052,7 +1052,7 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, * Not an artificial restriction anymore, as we must prevent * possible loops created by swapping in setlist type of sets. */ if (!(from->type->features == to->type->features && - from->type->family == to->type->family)) + from->family == to->family)) return -IPSET_ERR_TYPE_MISMATCH; strncpy(from_name, from->name, IPSET_MAXNAMELEN); -- cgit v1.2.3 From 2cf55125c64d64cc106e204d53b107094762dfdf Mon Sep 17 00:00:00 2001 From: Oliver Smith Date: Mon, 16 Sep 2013 20:30:57 +0200 Subject: netfilter: ipset: Fix serious failure in CIDR tracking This fixes a serious bug affecting all hash types with a net element - specifically, if a CIDR value is deleted such that none of the same size exist any more, all larger (less-specific) values will then fail to match. Adding back any prefix with a CIDR equal to or more specific than the one deleted will fix it. Steps to reproduce: ipset -N test hash:net ipset -A test 1.1.0.0/16 ipset -A test 2.2.2.0/24 ipset -T test 1.1.1.1 #1.1.1.1 IS in set ipset -D test 2.2.2.0/24 ipset -T test 1.1.1.1 #1.1.1.1 IS NOT in set This is due to the fact that the nets counter was unconditionally decremented prior to the iteration that shifts up the entries. Now, we first check if there is a proceeding entry and if not, decrement it and return. Otherwise, we proceed to iterate and then zero the last element, which, in most cases, will already be zero. Signed-off-by: Oliver Smith Signed-off-by: Jozsef Kadlecsik --- net/netfilter/ipset/ip_set_hash_gen.h | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 57beb1762b2d..707bc520d629 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -325,18 +325,22 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length) static void mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length) { - u8 i, j; - - for (i = 0; i < nets_length - 1 && h->nets[i].cidr != cidr; i++) - ; - h->nets[i].nets--; - - if (h->nets[i].nets != 0) - return; - - for (j = i; j < nets_length - 1 && h->nets[j].nets; j++) { - h->nets[j].cidr = h->nets[j + 1].cidr; - h->nets[j].nets = h->nets[j + 1].nets; + u8 i, j, net_end = nets_length - 1; + + for (i = 0; i < nets_length; i++) { + if (h->nets[i].cidr != cidr) + continue; + if (h->nets[i].nets > 1 || i == net_end || + h->nets[i + 1].nets == 0) { + h->nets[i].nets--; + return; + } + for (j = i; j < net_end && h->nets[j].nets; j++) { + h->nets[j].cidr = h->nets[j + 1].cidr; + h->nets[j].nets = h->nets[j + 1].nets; + } + h->nets[j].nets = 0; + return; } } #endif -- cgit v1.2.3 From 0a0d80eb39aa465b7bdf6f7754d0ba687eb3d2a7 Mon Sep 17 00:00:00 2001 From: Gao feng Date: Tue, 17 Sep 2013 13:03:47 +0200 Subject: netfilter: nfnetlink_queue: use network skb for sequence adjustment Instead of the netlink skb. Signed-off-by: Gao feng Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_queue_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 95a98c8c1da6..ae2e5c11d01a 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -1009,7 +1009,7 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, verdict = NF_DROP; if (ct) - nfqnl_ct_seq_adjust(skb, ct, ctinfo, diff); + nfqnl_ct_seq_adjust(entry->skb, ct, ctinfo, diff); } if (nfqa[NFQA_MARK]) -- cgit v1.2.3 From c16526a7b99c1c28e9670a8c8e3dbcf741bb32be Mon Sep 17 00:00:00 2001 From: Simon Kirby Date: Sat, 10 Aug 2013 01:26:18 -0700 Subject: ipvs: fix overflow on dest weight multiply Schedulers such as lblc and lblcr require the weight to be as high as the maximum number of active connections. In commit b552f7e3a9524abcbcdf ("ipvs: unify the formula to estimate the overhead of processing connections"), the consideration of inactconns and activeconns was cleaned up to always count activeconns as 256 times more important than inactconns. In cases where 3000 or more connections are expected, a weight of 3000 * 256 * 3000 connections overflows the 32-bit signed result used to determine if rescheduling is required. On amd64, this merely changes the multiply and comparison instructions to 64-bit. On x86, a 64-bit result is already present from imull, so only a few more comparison instructions are emitted. Signed-off-by: Simon Kirby Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_lblc.c | 4 ++-- net/netfilter/ipvs/ip_vs_lblcr.c | 12 ++++++------ net/netfilter/ipvs/ip_vs_nq.c | 8 ++++---- net/netfilter/ipvs/ip_vs_sed.c | 8 ++++---- net/netfilter/ipvs/ip_vs_wlc.c | 6 +++--- 6 files changed, 20 insertions(+), 20 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index f0d70f066f3d..fe782ed2fe72 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1649,7 +1649,7 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) /* CONFIG_IP_VS_NFCT */ #endif -static inline unsigned int +static inline int ip_vs_dest_conn_overhead(struct ip_vs_dest *dest) { /* diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 1383b0eadc0e..eb814bf74e64 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -443,8 +443,8 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 5199448697f6..e65f7c573090 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -200,8 +200,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) continue; doh = ip_vs_dest_conn_overhead(dest); - if ((loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) + if (((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { least = dest; loh = doh; @@ -246,8 +246,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) dest = rcu_dereference_protected(e->dest, 1); doh = ip_vs_dest_conn_overhead(dest); /* moh/mw < doh/dw ==> moh*dw < doh*mw, where mw,dw>0 */ - if ((moh * atomic_read(&dest->weight) < - doh * atomic_read(&most->weight)) + if (((__s64)moh * atomic_read(&dest->weight) < + (__s64)doh * atomic_read(&most->weight)) && (atomic_read(&dest->weight) > 0)) { most = dest; moh = doh; @@ -611,8 +611,8 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c index d8d9860934fe..961a6de9bb29 100644 --- a/net/netfilter/ipvs/ip_vs_nq.c +++ b/net/netfilter/ipvs/ip_vs_nq.c @@ -40,7 +40,7 @@ #include -static inline unsigned int +static inline int ip_vs_nq_dest_overhead(struct ip_vs_dest *dest) { /* @@ -59,7 +59,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least = NULL; - unsigned int loh = 0, doh; + int loh = 0, doh; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); @@ -92,8 +92,8 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, } if (!least || - (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight))) { + ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight))) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c index a5284cc3d882..e446b9fa7424 100644 --- a/net/netfilter/ipvs/ip_vs_sed.c +++ b/net/netfilter/ipvs/ip_vs_sed.c @@ -44,7 +44,7 @@ #include -static inline unsigned int +static inline int ip_vs_sed_dest_overhead(struct ip_vs_dest *dest) { /* @@ -63,7 +63,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least; - unsigned int loh, doh; + int loh, doh; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); @@ -99,8 +99,8 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_sed_dest_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c index 6dc1fa128840..b5b4650d50a9 100644 --- a/net/netfilter/ipvs/ip_vs_wlc.c +++ b/net/netfilter/ipvs/ip_vs_wlc.c @@ -35,7 +35,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least; - unsigned int loh, doh; + int loh, doh; IP_VS_DBG(6, "ip_vs_wlc_schedule(): Scheduling...\n"); @@ -71,8 +71,8 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } -- cgit v1.2.3 From bcbde4c0a7556cca72874c5e1efa4dccb5198a2b Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 12 Sep 2013 11:21:07 +0300 Subject: ipvs: make the service replacement more robust commit 578bc3ef1e473a ("ipvs: reorganize dest trash") added IP_VS_DEST_STATE_REMOVING flag and RCU callback named ip_vs_dest_wait_readers() to keep dests and services after removal for at least a RCU grace period. But we have the following corner cases: - we can not reuse the same dest if its service is removed while IP_VS_DEST_STATE_REMOVING is still set because another dest removal in the first grace period can not extend this period. It can happen when ipvsadm -C && ipvsadm -R is used. - dest->svc can be replaced but ip_vs_in_stats() and ip_vs_out_stats() have no explicit read memory barriers when accessing dest->svc. It can happen that dest->svc was just freed (replaced) while we use it to update the stats. We solve the problems as follows: - IP_VS_DEST_STATE_REMOVING is removed and we ensure a fixed idle period for the dest (IP_VS_DEST_TRASH_PERIOD). idle_start will remember when for first time after deletion we noticed dest->refcnt=0. Later, the connections can grab a reference while in RCU grace period but if refcnt becomes 0 we can safely free the dest and its svc. - dest->svc becomes RCU pointer. As result, we add explicit RCU locking in ip_vs_in_stats() and ip_vs_out_stats(). - __ip_vs_unbind_svc is renamed to __ip_vs_svc_put(), it now can free the service immediately or after a RCU grace period. dest->svc is not set to NULL anymore. As result, unlinked dests and their services are freed always after IP_VS_DEST_TRASH_PERIOD period, unused services are freed after a RCU grace period. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 7 +--- net/netfilter/ipvs/ip_vs_core.c | 12 +++++- net/netfilter/ipvs/ip_vs_ctl.c | 86 +++++++++++++++++------------------------ 3 files changed, 47 insertions(+), 58 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index fe782ed2fe72..9c4d37ec45a1 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -723,8 +723,6 @@ struct ip_vs_dest_dst { struct rcu_head rcu_head; }; -/* In grace period after removing */ -#define IP_VS_DEST_STATE_REMOVING 0x01 /* * The real server destination forwarding entry * with ip address, port number, and so on. @@ -742,7 +740,7 @@ struct ip_vs_dest { atomic_t refcnt; /* reference counter */ struct ip_vs_stats stats; /* statistics */ - unsigned long state; /* state flags */ + unsigned long idle_start; /* start time, jiffies */ /* connection counters and thresholds */ atomic_t activeconns; /* active connections */ @@ -756,14 +754,13 @@ struct ip_vs_dest { struct ip_vs_dest_dst __rcu *dest_dst; /* cached dst info */ /* for virtual service */ - struct ip_vs_service *svc; /* service it belongs to */ + struct ip_vs_service __rcu *svc; /* service it belongs to */ __u16 protocol; /* which protocol (TCP/UDP) */ __be16 vport; /* virtual port number */ union nf_inet_addr vaddr; /* virtual IP address */ __u32 vfwmark; /* firewall mark of service */ struct list_head t_list; /* in dest_trash */ - struct rcu_head rcu_head; unsigned int in_rs_table:1; /* we are in rs_table */ }; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4f69e83ff836..74fd00c27210 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -116,6 +116,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; + struct ip_vs_service *svc; s = this_cpu_ptr(dest->stats.cpustats); s->ustats.inpkts++; @@ -123,11 +124,14 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->ustats.inbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(dest->svc->stats.cpustats); + rcu_read_lock(); + svc = rcu_dereference(dest->svc); + s = this_cpu_ptr(svc->stats.cpustats); s->ustats.inpkts++; u64_stats_update_begin(&s->syncp); s->ustats.inbytes += skb->len; u64_stats_update_end(&s->syncp); + rcu_read_unlock(); s = this_cpu_ptr(ipvs->tot_stats.cpustats); s->ustats.inpkts++; @@ -146,6 +150,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; + struct ip_vs_service *svc; s = this_cpu_ptr(dest->stats.cpustats); s->ustats.outpkts++; @@ -153,11 +158,14 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->ustats.outbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(dest->svc->stats.cpustats); + rcu_read_lock(); + svc = rcu_dereference(dest->svc); + s = this_cpu_ptr(svc->stats.cpustats); s->ustats.outpkts++; u64_stats_update_begin(&s->syncp); s->ustats.outbytes += skb->len; u64_stats_update_end(&s->syncp); + rcu_read_unlock(); s = this_cpu_ptr(ipvs->tot_stats.cpustats); s->ustats.outpkts++; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c8148e487386..a3df9bddc4f7 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -460,7 +460,7 @@ static inline void __ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc) { atomic_inc(&svc->refcnt); - dest->svc = svc; + rcu_assign_pointer(dest->svc, svc); } static void ip_vs_service_free(struct ip_vs_service *svc) @@ -470,18 +470,25 @@ static void ip_vs_service_free(struct ip_vs_service *svc) kfree(svc); } -static void -__ip_vs_unbind_svc(struct ip_vs_dest *dest) +static void ip_vs_service_rcu_free(struct rcu_head *head) { - struct ip_vs_service *svc = dest->svc; + struct ip_vs_service *svc; + + svc = container_of(head, struct ip_vs_service, rcu_head); + ip_vs_service_free(svc); +} - dest->svc = NULL; +static void __ip_vs_svc_put(struct ip_vs_service *svc, bool do_delay) +{ if (atomic_dec_and_test(&svc->refcnt)) { IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n", svc->fwmark, IP_VS_DBG_ADDR(svc->af, &svc->addr), ntohs(svc->port)); - ip_vs_service_free(svc); + if (do_delay) + call_rcu(&svc->rcu_head, ip_vs_service_rcu_free); + else + ip_vs_service_free(svc); } } @@ -667,11 +674,6 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->refcnt)); - /* We can not reuse dest while in grace period - * because conns still can use dest->svc - */ - if (test_bit(IP_VS_DEST_STATE_REMOVING, &dest->state)) - continue; if (dest->af == svc->af && ip_vs_addr_equal(svc->af, &dest->addr, daddr) && dest->port == dport && @@ -697,8 +699,10 @@ out: static void ip_vs_dest_free(struct ip_vs_dest *dest) { + struct ip_vs_service *svc = rcu_dereference_protected(dest->svc, 1); + __ip_vs_dst_cache_reset(dest); - __ip_vs_unbind_svc(dest); + __ip_vs_svc_put(svc, false); free_percpu(dest->stats.cpustats); kfree(dest); } @@ -771,6 +775,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct ip_vs_dest_user_kern *udest, int add) { struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct ip_vs_service *old_svc; struct ip_vs_scheduler *sched; int conn_flags; @@ -792,13 +797,14 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, atomic_set(&dest->conn_flags, conn_flags); /* bind the service */ - if (!dest->svc) { + old_svc = rcu_dereference_protected(dest->svc, 1); + if (!old_svc) { __ip_vs_bind_svc(dest, svc); } else { - if (dest->svc != svc) { - __ip_vs_unbind_svc(dest); + if (old_svc != svc) { ip_vs_zero_stats(&dest->stats); __ip_vs_bind_svc(dest, svc); + __ip_vs_svc_put(old_svc, true); } } @@ -998,16 +1004,6 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) return 0; } -static void ip_vs_dest_wait_readers(struct rcu_head *head) -{ - struct ip_vs_dest *dest = container_of(head, struct ip_vs_dest, - rcu_head); - - /* End of grace period after unlinking */ - clear_bit(IP_VS_DEST_STATE_REMOVING, &dest->state); -} - - /* * Delete a destination (must be already unlinked from the service) */ @@ -1023,20 +1019,16 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest, */ ip_vs_rs_unhash(dest); - if (!cleanup) { - set_bit(IP_VS_DEST_STATE_REMOVING, &dest->state); - call_rcu(&dest->rcu_head, ip_vs_dest_wait_readers); - } - spin_lock_bh(&ipvs->dest_trash_lock); 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)); if (list_empty(&ipvs->dest_trash) && !cleanup) mod_timer(&ipvs->dest_trash_timer, - jiffies + IP_VS_DEST_TRASH_PERIOD); + jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); /* dest lives in trash without reference */ list_add(&dest->t_list, &ipvs->dest_trash); + dest->idle_start = 0; spin_unlock_bh(&ipvs->dest_trash_lock); ip_vs_dest_put(dest); } @@ -1108,24 +1100,30 @@ static void ip_vs_dest_trash_expire(unsigned long data) struct net *net = (struct net *) data; struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_dest *dest, *next; + unsigned long now = jiffies; spin_lock(&ipvs->dest_trash_lock); list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) { - /* Skip if dest is in grace period */ - if (test_bit(IP_VS_DEST_STATE_REMOVING, &dest->state)) - continue; if (atomic_read(&dest->refcnt) > 0) continue; + if (dest->idle_start) { + if (time_before(now, dest->idle_start + + IP_VS_DEST_TRASH_PERIOD)) + continue; + } else { + dest->idle_start = max(1UL, now); + continue; + } IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u from trash\n", dest->vfwmark, - IP_VS_DBG_ADDR(dest->svc->af, &dest->addr), + IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port)); list_del(&dest->t_list); ip_vs_dest_free(dest); } if (!list_empty(&ipvs->dest_trash)) mod_timer(&ipvs->dest_trash_timer, - jiffies + IP_VS_DEST_TRASH_PERIOD); + jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); spin_unlock(&ipvs->dest_trash_lock); } @@ -1320,14 +1318,6 @@ out: return ret; } -static void ip_vs_service_rcu_free(struct rcu_head *head) -{ - struct ip_vs_service *svc; - - svc = container_of(head, struct ip_vs_service, rcu_head); - ip_vs_service_free(svc); -} - /* * Delete a service from the service list * - The service must be unlinked, unlocked and not referenced! @@ -1376,13 +1366,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) /* * Free the service if nobody refers to it */ - if (atomic_dec_and_test(&svc->refcnt)) { - IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n", - svc->fwmark, - IP_VS_DBG_ADDR(svc->af, &svc->addr), - ntohs(svc->port)); - call_rcu(&svc->rcu_head, ip_vs_service_rcu_free); - } + __ip_vs_svc_put(svc, true); /* decrease the module use count */ ip_vs_use_count_dec(); -- cgit v1.2.3 From 2f3d771a35fee21a1f17364b46b3c8cc66dc6892 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 12 Sep 2013 11:21:08 +0300 Subject: ipvs: do not use dest after ip_vs_dest_put in LBLC commit c2a4ffb70eef39 ("ipvs: convert lblc scheduler to rcu") allows RCU readers to use dest after calling ip_vs_dest_put(). In the corner case it can race with ip_vs_dest_trash_expire() which can release the dest while it is being returned to the RCU readers as scheduling result. To fix the problem do not allow en->dest to be replaced and defer the ip_vs_dest_put() call by using RCU callback. Now en->dest does not need to be RCU pointer. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_lblc.c | 68 +++++++++++++++++++---------------------- 1 file changed, 31 insertions(+), 37 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index eb814bf74e64..eff13c94498e 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -93,7 +93,7 @@ struct ip_vs_lblc_entry { struct hlist_node list; int af; /* address family */ union nf_inet_addr addr; /* destination IP address */ - struct ip_vs_dest __rcu *dest; /* real server (cache) */ + struct ip_vs_dest *dest; /* real server (cache) */ unsigned long lastuse; /* last used time */ struct rcu_head rcu_head; }; @@ -130,20 +130,21 @@ static struct ctl_table vs_vars_table[] = { }; #endif -static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) +static void ip_vs_lblc_rcu_free(struct rcu_head *head) { - struct ip_vs_dest *dest; + struct ip_vs_lblc_entry *en = container_of(head, + struct ip_vs_lblc_entry, + rcu_head); - hlist_del_rcu(&en->list); - /* - * We don't kfree dest because it is referred either by its service - * or the trash dest list. - */ - dest = rcu_dereference_protected(en->dest, 1); - ip_vs_dest_put(dest); - kfree_rcu(en, rcu_head); + ip_vs_dest_put(en->dest); + kfree(en); } +static inline void ip_vs_lblc_del(struct ip_vs_lblc_entry *en) +{ + hlist_del_rcu(&en->list); + call_rcu(&en->rcu_head, ip_vs_lblc_rcu_free); +} /* * Returns hash value for IPVS LBLC entry @@ -203,30 +204,23 @@ ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr, struct ip_vs_lblc_entry *en; en = ip_vs_lblc_get(dest->af, tbl, daddr); - if (!en) { - en = kmalloc(sizeof(*en), GFP_ATOMIC); - if (!en) - return NULL; - - en->af = dest->af; - ip_vs_addr_copy(dest->af, &en->addr, daddr); - en->lastuse = jiffies; + if (en) { + if (en->dest == dest) + return en; + ip_vs_lblc_del(en); + } + en = kmalloc(sizeof(*en), GFP_ATOMIC); + if (!en) + return NULL; - ip_vs_dest_hold(dest); - RCU_INIT_POINTER(en->dest, dest); + en->af = dest->af; + ip_vs_addr_copy(dest->af, &en->addr, daddr); + en->lastuse = jiffies; - ip_vs_lblc_hash(tbl, en); - } else { - struct ip_vs_dest *old_dest; + ip_vs_dest_hold(dest); + en->dest = dest; - old_dest = rcu_dereference_protected(en->dest, 1); - if (old_dest != dest) { - ip_vs_dest_put(old_dest); - ip_vs_dest_hold(dest); - /* No ordering constraints for refcnt */ - RCU_INIT_POINTER(en->dest, dest); - } - } + ip_vs_lblc_hash(tbl, en); return en; } @@ -246,7 +240,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc) tbl->dead = 1; for (i=0; ibucket[i], list) { - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); } } @@ -281,7 +275,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) sysctl_lblc_expiration(svc))) continue; - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); } spin_unlock(&svc->sched_lock); @@ -335,7 +329,7 @@ static void ip_vs_lblc_check_expire(unsigned long data) if (time_before(now, en->lastuse + ENTRY_TIMEOUT)) continue; - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); goal--; } @@ -511,7 +505,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, * free up entries from the trash at any time. */ - dest = rcu_dereference(en->dest); + dest = en->dest; if ((dest->flags & IP_VS_DEST_F_AVAILABLE) && atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc)) goto out; @@ -631,7 +625,7 @@ static void __exit ip_vs_lblc_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler); unregister_pernet_subsys(&ip_vs_lblc_ops); - synchronize_rcu(); + rcu_barrier(); } -- cgit v1.2.3 From 742617b176909e586a4cf9b142c996c25986fce8 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 12 Sep 2013 11:21:09 +0300 Subject: ipvs: do not use dest after ip_vs_dest_put in LBLCR commit c5549571f975ab ("ipvs: convert lblcr scheduler to rcu") allows RCU readers to use dest after calling ip_vs_dest_put(). In the corner case it can race with ip_vs_dest_trash_expire() which can release the dest while it is being returned to the RCU readers as scheduling result. To fix the problem do not allow e->dest to be replaced and defer the ip_vs_dest_put() call by using RCU callback. Now e->dest does not need to be RCU pointer. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_lblcr.c | 50 ++++++++++++++++------------------------ 1 file changed, 20 insertions(+), 30 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index e65f7c573090..0b8550089a2e 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -89,7 +89,7 @@ */ struct ip_vs_dest_set_elem { struct list_head list; /* list link */ - struct ip_vs_dest __rcu *dest; /* destination server */ + struct ip_vs_dest *dest; /* destination server */ struct rcu_head rcu_head; }; @@ -107,11 +107,7 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, if (check) { list_for_each_entry(e, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - if (d == dest) - /* already existed */ + if (e->dest == dest) return; } } @@ -121,7 +117,7 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, return; ip_vs_dest_hold(dest); - RCU_INIT_POINTER(e->dest, dest); + e->dest = dest; list_add_rcu(&e->list, &set->list); atomic_inc(&set->size); @@ -129,22 +125,27 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, set->lastmod = jiffies; } +static void ip_vs_lblcr_elem_rcu_free(struct rcu_head *head) +{ + struct ip_vs_dest_set_elem *e; + + e = container_of(head, struct ip_vs_dest_set_elem, rcu_head); + ip_vs_dest_put(e->dest); + kfree(e); +} + static void ip_vs_dest_set_erase(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) { struct ip_vs_dest_set_elem *e; list_for_each_entry(e, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - if (d == dest) { + if (e->dest == dest) { /* HIT */ atomic_dec(&set->size); set->lastmod = jiffies; - ip_vs_dest_put(dest); list_del_rcu(&e->list); - kfree_rcu(e, rcu_head); + call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); break; } } @@ -155,16 +156,8 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) struct ip_vs_dest_set_elem *e, *ep; list_for_each_entry_safe(e, ep, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - /* - * We don't kfree dest because it is referred either - * by its service or by the trash dest list. - */ - ip_vs_dest_put(d); list_del_rcu(&e->list); - kfree_rcu(e, rcu_head); + call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); } } @@ -175,12 +168,9 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) struct ip_vs_dest *dest, *least; int loh, doh; - if (set == NULL) - return NULL; - /* select the first destination server, whose weight > 0 */ list_for_each_entry_rcu(e, &set->list, list) { - least = rcu_dereference(e->dest); + least = e->dest; if (least->flags & IP_VS_DEST_F_OVERLOAD) continue; @@ -195,7 +185,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) /* find the destination with the weighted least load */ nextstage: list_for_each_entry_continue_rcu(e, &set->list, list) { - dest = rcu_dereference(e->dest); + dest = e->dest; if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; @@ -232,7 +222,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) /* select the first destination server, whose weight > 0 */ list_for_each_entry(e, &set->list, list) { - most = rcu_dereference_protected(e->dest, 1); + most = e->dest; if (atomic_read(&most->weight) > 0) { moh = ip_vs_dest_conn_overhead(most); goto nextstage; @@ -243,7 +233,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) /* find the destination with the weighted most load */ nextstage: list_for_each_entry_continue(e, &set->list, list) { - dest = rcu_dereference_protected(e->dest, 1); + dest = e->dest; doh = ip_vs_dest_conn_overhead(dest); /* moh/mw < doh/dw ==> moh*dw < doh*mw, where mw,dw>0 */ if (((__s64)moh * atomic_read(&dest->weight) < @@ -819,7 +809,7 @@ static void __exit ip_vs_lblcr_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler); unregister_pernet_subsys(&ip_vs_lblcr_ops); - synchronize_rcu(); + rcu_barrier(); } -- cgit v1.2.3 From d1ee4fea0b6946dd8bc61b46db35ea80af7af34b Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 12 Sep 2013 11:21:10 +0300 Subject: ipvs: stats should not depend on CPU 0 When reading percpu stats we need to properly reset the sum when CPU 0 is not present in the possible mask. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_est.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 6bee6d0c73a5..1425e9a924c4 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -59,12 +59,13 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, struct ip_vs_cpu_stats __percpu *stats) { int i; + bool add = false; for_each_possible_cpu(i) { struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i); unsigned int start; __u64 inbytes, outbytes; - if (i) { + if (add) { sum->conns += s->ustats.conns; sum->inpkts += s->ustats.inpkts; sum->outpkts += s->ustats.outpkts; @@ -76,6 +77,7 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, sum->inbytes += inbytes; sum->outbytes += outbytes; } else { + add = true; sum->conns = s->ustats.conns; sum->inpkts = s->ustats.inpkts; sum->outpkts = s->ustats.outpkts; -- cgit v1.2.3 From 703133de331a7a7df47f31fb9de51dc6f68a9de8 Mon Sep 17 00:00:00 2001 From: Ansis Atteka Date: Wed, 18 Sep 2013 15:29:53 -0700 Subject: ip: generate unique IP identificator if local fragmentation is allowed If local fragmentation is allowed, then ip_select_ident() and ip_select_ident_more() need to generate unique IDs to ensure correct defragmentation on the peer. For example, if IPsec (tunnel mode) has to encrypt large skbs that have local_df bit set, then all IP fragments that belonged to different ESP datagrams would have used the same identificator. If one of these IP fragments would get lost or reordered, then peer could possibly stitch together wrong IP fragments that did not belong to the same datagram. This would lead to a packet loss or data corruption. Signed-off-by: Ansis Atteka Signed-off-by: David S. Miller --- drivers/net/ppp/pptp.c | 2 +- include/net/ip.h | 12 ++++++++---- net/ipv4/igmp.c | 4 ++-- net/ipv4/inetpeer.c | 4 ++-- net/ipv4/ip_output.c | 6 +++--- net/ipv4/ipmr.c | 2 +- net/ipv4/raw.c | 2 +- net/ipv4/xfrm4_mode_tunnel.c | 2 +- net/netfilter/ipvs/ip_vs_xmit.c | 2 +- 9 files changed, 20 insertions(+), 16 deletions(-) (limited to 'net/netfilter') diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 6fa5ae00039f..01805319e1e0 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -281,7 +281,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) nf_reset(skb); skb->ip_summed = CHECKSUM_NONE; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); ip_send_check(iph); ip_local_out(skb); diff --git a/include/net/ip.h b/include/net/ip.h index 48f55979d842..5e5268807a1c 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -264,9 +264,11 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst) extern void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more); -static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, struct sock *sk) +static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk) { - if (iph->frag_off & htons(IP_DF)) { + struct iphdr *iph = ip_hdr(skb); + + if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) { /* This is only to work around buggy Windows95/2000 * VJ compression implementations. If the ID field * does not change, they drop every other packet in @@ -278,9 +280,11 @@ static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, str __ip_select_ident(iph, dst, 0); } -static inline void ip_select_ident_more(struct iphdr *iph, struct dst_entry *dst, struct sock *sk, int more) +static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more) { - if (iph->frag_off & htons(IP_DF)) { + struct iphdr *iph = ip_hdr(skb); + + if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) { if (sk && inet_sk(sk)->inet_daddr) { iph->id = htons(inet_sk(sk)->inet_id); inet_sk(sk)->inet_id += 1 + more; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d6c0e64ec97f..dace87f06e5f 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(pip, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 000e3d239d64..33d5537881ed 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -32,8 +32,8 @@ * At the moment of writing this notes identifier of IP packets is generated * to be unpredictable using this code only for packets subjected * (actually or potentially) to defragmentation. I.e. DF packets less than - * PMTU in size uses a constant ID and do not use this code (see - * ip_select_ident() in include/net/ip.h). + * PMTU in size when local fragmentation is disabled use a constant ID and do + * not use this code (see ip_select_ident() in include/net/ip.h). * * Route cache entries hold references to our nodes. * New cache entries get references via lookup by destination IP address in diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index eae2e262fbe5..a04d872c54f9 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(iph, &rt->dst, sk); + ip_select_ident(skb, &rt->dst, sk); if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -386,7 +386,7 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_more(iph, &rt->dst, sk, + ip_select_ident_more(skb, &rt->dst, sk, (skb_shinfo(skb)->gso_segs ?: 1) - 1); skb->priority = sk->sk_priority; @@ -1324,7 +1324,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); - ip_select_ident(iph, &rt->dst, sk); + ip_select_ident(skb, &rt->dst, sk); if (opt) { iph->ihl += opt->optlen>>2; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9ae54b09254f..62212c772a4b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1658,7 +1658,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(iph, skb_dst(skb), NULL); + ip_select_ident(skb, skb_dst(skb), NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a86c7ae71881..bfec521c717f 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -387,7 +387,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index eb1dd4d643f2..b5663c37f089 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -117,7 +117,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); - ip_select_ident(top_iph, dst->child, NULL); + ip_select_ident(skb, dst->child, NULL); top_iph->ttl = ip4_dst_hoplimit(dst->child); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b75ff6429a04..c47444e4cf8c 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -883,7 +883,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = old_iph->ttl; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; -- cgit v1.2.3 From f4a87e7bd2eaef26a3ca25437ce8b807de2966ad Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 30 Sep 2013 08:51:46 +0100 Subject: netfilter: synproxy: fix BUG_ON triggered by corrupt TCP packets TCP packets hitting the SYN proxy through the SYNPROXY target are not validated by TCP conntrack. When th->doff is below 5, an underflow happens when calculating the options length, causing skb_header_pointer() to return NULL and triggering the BUG_ON(). Handle this case gracefully by checking for NULL instead of using BUG_ON(). Reported-by: Martin Topholm Tested-by: Martin Topholm Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_synproxy.h | 2 +- net/ipv4/netfilter/ipt_SYNPROXY.c | 10 +++++++--- net/ipv6/netfilter/ip6t_SYNPROXY.c | 10 +++++++--- net/netfilter/nf_synproxy_core.c | 12 +++++++----- 4 files changed, 22 insertions(+), 12 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h index 806f54a290d6..f572f313d6f1 100644 --- a/include/net/netfilter/nf_conntrack_synproxy.h +++ b/include/net/netfilter/nf_conntrack_synproxy.h @@ -56,7 +56,7 @@ struct synproxy_options { struct tcphdr; struct xt_synproxy_info; -extern void synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, +extern bool synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, const struct tcphdr *th, struct synproxy_options *opts); extern unsigned int synproxy_options_size(const struct synproxy_options *opts); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 67e17dcda65e..b6346bf2fde3 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -267,7 +267,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) if (th == NULL) return NF_DROP; - synproxy_parse_options(skb, par->thoff, th, &opts); + if (!synproxy_parse_options(skb, par->thoff, th, &opts)) + return NF_DROP; if (th->syn && !(th->ack || th->fin || th->rst)) { /* Initial SYN from client */ @@ -350,7 +351,8 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum, /* fall through */ case TCP_CONNTRACK_SYN_SENT: - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; if (!th->syn && th->ack && CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { @@ -373,7 +375,9 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum, if (!th->syn || !th->ack) break; - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy->tsoff = opts.tsval - synproxy->its; diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index 19cfea8dbcaa..2748b042da72 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -282,7 +282,8 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) if (th == NULL) return NF_DROP; - synproxy_parse_options(skb, par->thoff, th, &opts); + if (!synproxy_parse_options(skb, par->thoff, th, &opts)) + return NF_DROP; if (th->syn && !(th->ack || th->fin || th->rst)) { /* Initial SYN from client */ @@ -372,7 +373,8 @@ static unsigned int ipv6_synproxy_hook(unsigned int hooknum, /* fall through */ case TCP_CONNTRACK_SYN_SENT: - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; if (!th->syn && th->ack && CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { @@ -395,7 +397,9 @@ static unsigned int ipv6_synproxy_hook(unsigned int hooknum, if (!th->syn || !th->ack) break; - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy->tsoff = opts.tsval - synproxy->its; diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 6fd967c6278c..cdf4567ba9b3 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -24,7 +24,7 @@ int synproxy_net_id; EXPORT_SYMBOL_GPL(synproxy_net_id); -void +bool synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, const struct tcphdr *th, struct synproxy_options *opts) { @@ -32,7 +32,8 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, u8 buf[40], *ptr; ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); - BUG_ON(ptr == NULL); + if (ptr == NULL) + return false; opts->options = 0; while (length > 0) { @@ -41,16 +42,16 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, switch (opcode) { case TCPOPT_EOL: - return; + return true; case TCPOPT_NOP: length--; continue; default: opsize = *ptr++; if (opsize < 2) - return; + return true; if (opsize > length) - return; + return true; switch (opcode) { case TCPOPT_MSS: @@ -84,6 +85,7 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, length -= opsize; } } + return true; } EXPORT_SYMBOL_GPL(synproxy_parse_options); -- cgit v1.2.3