From 6eab04a87677a37cf15b52e2b4b4fd57917102ad Mon Sep 17 00:00:00 2001 From: "Justin P. Mattock" Date: Fri, 8 Apr 2011 19:49:08 -0700 Subject: treewide: remove extra semicolons Signed-off-by: Justin P. Mattock Signed-off-by: Jiri Kosina --- net/netfilter/ipset/ip_set_bitmap_ip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index bca96990218d..cc2992299e74 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -293,7 +293,7 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], for (; !before(ip_to, ip); ip += map->hosts) { id = ip_to_id(map, ip); - ret = adtfn(set, &id, timeout);; + ret = adtfn(set, &id, timeout); if (ret && !ip_set_eexist(ret, flags)) return ret; -- cgit v1.2.3 From 0e8a835aa59d08d702af0fcfd296e2218b2e344b Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Wed, 13 Apr 2011 13:43:23 +0200 Subject: netfilter: ipset: bitmap:ip,mac type requires "src" for MAC Enforce that the second "src/dst" parameter of the set match and SET target must be "src", because we have access to the source MAC only in the packet. The previous behaviour, that the type required the second parameter but actually ignored the value was counter-intuitive and confusing. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- net/netfilter/ipset/ip_set_bitmap_ipmac.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 00a33242e90c..a274300b6a56 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -343,6 +343,10 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, ipset_adtfn adtfn = set->variant->adt[adt]; struct ipmac data; + /* MAC can be src only */ + if (!(flags & IPSET_DIM_TWO_SRC)) + return 0; + data.id = ntohl(ip4addr(skb, flags & IPSET_DIM_ONE_SRC)); if (data.id < map->first_ip || data.id > map->last_ip) return -IPSET_ERR_BITMAP_RANGE; -- cgit v1.2.3 From eafbd3fde6fc5ada0d61307367e408813b04928a Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Wed, 13 Apr 2011 13:45:57 +0200 Subject: netfilter: ipset: set match and SET target fixes The SET target with --del-set did not work due to using wrongly the internal dimension of --add-set instead of --del-set. Also, the checkentries did not release the set references when returned an error. Bugs reported by Lennert Buytenhek. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- net/netfilter/xt_set.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 061d48cec137..b3babaed7719 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -81,6 +81,7 @@ set_match_v0_checkentry(const struct xt_mtchk_param *par) if (info->match_set.u.flags[IPSET_DIM_MAX-1] != 0) { pr_warning("Protocol error: set match dimension " "is over the limit!\n"); + ip_set_nfnl_put(info->match_set.index); return -ERANGE; } @@ -135,6 +136,8 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par) if (index == IPSET_INVALID_ID) { pr_warning("Cannot find del_set index %u as target\n", info->del_set.index); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); return -ENOENT; } } @@ -142,6 +145,10 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par) info->del_set.u.flags[IPSET_DIM_MAX-1] != 0) { pr_warning("Protocol error: SET target dimension " "is over the limit!\n"); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); + if (info->del_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->del_set.index); return -ERANGE; } @@ -192,6 +199,7 @@ set_match_checkentry(const struct xt_mtchk_param *par) if (info->match_set.dim > IPSET_DIM_MAX) { pr_warning("Protocol error: set match dimension " "is over the limit!\n"); + ip_set_nfnl_put(info->match_set.index); return -ERANGE; } @@ -219,7 +227,7 @@ set_target(struct sk_buff *skb, const struct xt_action_param *par) if (info->del_set.index != IPSET_INVALID_ID) ip_set_del(info->del_set.index, skb, par->family, - info->add_set.dim, + info->del_set.dim, info->del_set.flags); return XT_CONTINUE; @@ -245,13 +253,19 @@ set_target_checkentry(const struct xt_tgchk_param *par) if (index == IPSET_INVALID_ID) { pr_warning("Cannot find del_set index %u as target\n", info->del_set.index); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); return -ENOENT; } } if (info->add_set.dim > IPSET_DIM_MAX || - info->del_set.flags > IPSET_DIM_MAX) { + info->del_set.dim > IPSET_DIM_MAX) { pr_warning("Protocol error: SET target dimension " "is over the limit!\n"); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); + if (info->del_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->del_set.index); return -ERANGE; } -- cgit v1.2.3 From a8a8a0937e22a5fd55aeb22586724ba6bb70aadd Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 19 Apr 2011 15:59:15 +0200 Subject: netfilter: ipset: Fix the order of listing of sets A restoreable saving of sets requires that list:set type of sets come last and the code part which should have taken into account the ordering was broken. The patch fixes the listing order. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- net/netfilter/ipset/ip_set_core.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e88ac3c3ed07..d87e03bc8ef8 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1022,8 +1022,9 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) if (cb->args[1] >= ip_set_max) goto out; - pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]); max = cb->args[0] == DUMP_ONE ? cb->args[1] + 1 : ip_set_max; +dump_last: + pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]); for (; cb->args[1] < max; cb->args[1]++) { index = (ip_set_id_t) cb->args[1]; set = ip_set_list[index]; @@ -1038,8 +1039,8 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) * so that lists (unions of sets) are dumped last. */ if (cb->args[0] != DUMP_ONE && - !((cb->args[0] == DUMP_ALL) ^ - (set->type->features & IPSET_DUMP_LAST))) + ((cb->args[0] == DUMP_ALL) == + !!(set->type->features & IPSET_DUMP_LAST))) continue; pr_debug("List set: %s\n", set->name); if (!cb->args[2]) { @@ -1083,6 +1084,12 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) goto release_refcount; } } + /* If we dump all sets, continue with dumping last ones */ + if (cb->args[0] == DUMP_ALL) { + cb->args[0] = DUMP_LAST; + cb->args[1] = 0; + goto dump_last; + } goto out; nla_put_failure: @@ -1093,11 +1100,6 @@ release_refcount: pr_debug("release set %s\n", ip_set_list[index]->name); ip_set_put_byindex(index); } - - /* If we dump all sets, continue with dumping last ones */ - if (cb->args[0] == DUMP_ALL && cb->args[1] >= max && !cb->args[2]) - cb->args[0] = DUMP_LAST; - out: if (nlh) { nlmsg_end(skb, nlh); -- cgit v1.2.3 From 358b1361bed42f4e6cbf8956a73aebf193957d4a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 21 Apr 2011 10:55:07 +0200 Subject: netfilter: ctnetlink: fix timestamp support for new conntracks This patch fixes the missing initialization of the start time if the timestamp support is enabled. libnetfilter_conntrack/utils# conntrack -E & libnetfilter_conntrack/utils# ./conntrack_create tcp 6 109 ESTABLISHED src=1.1.1.1 dst=2.2.2.2 sport=1025 dport=21 packets=0 bytes=0 [UNREPLIED] src=2.2.2.2 dst=1.1.1.1 sport=21 dport=1025 packets=0 bytes=0 mark=0 delta-time=1303296401 use=2 Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_netlink.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 30bf8a167fc8..482e90c61850 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1334,6 +1334,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, struct nf_conn *ct; int err = -EINVAL; struct nf_conntrack_helper *helper; + struct nf_conn_tstamp *tstamp; ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) @@ -1451,6 +1452,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = master_ct; } + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) + tstamp->start = ktime_to_ns(ktime_get_real()); add_timer(&ct->timeout); nf_conntrack_hash_insert(ct); -- cgit v1.2.3 From 954d70388307eb1ccb328d9f960657022a316243 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 21 Apr 2011 10:57:21 +0200 Subject: netfilter: fix ebtables compat support commit 255d0dc34068a976 (netfilter: x_table: speedup compat operations) made ebtables not working anymore. 1) xt_compat_calc_jump() is not an exact match lookup 2) compat_table_info() has a typo in xt_compat_init_offsets() call 3) compat_do_replace() misses a xt_compat_init_offsets() call Reported-by: dann frazier Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy --- net/bridge/netfilter/ebtables.c | 3 ++- net/netfilter/x_tables.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'net/netfilter') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 893669caa8de..9707079bc40a 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1766,7 +1766,7 @@ static int compat_table_info(const struct ebt_table_info *info, newinfo->entries_size = size; - xt_compat_init_offsets(AF_INET, info->nentries); + xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries); return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); } @@ -2240,6 +2240,7 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); + xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) goto out_unlock; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index a9adf4c6b299..8a025a585d2f 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -455,6 +455,7 @@ void xt_compat_flush_offsets(u_int8_t af) vfree(xt[af].compat_tab); xt[af].compat_tab = NULL; xt[af].number = 0; + xt[af].cur = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); @@ -473,8 +474,7 @@ int xt_compat_calc_jump(u_int8_t af, unsigned int offset) else return mid ? tmp[mid - 1].delta : 0; } - WARN_ON_ONCE(1); - return 0; + return left ? tmp[left - 1].delta : 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); -- cgit v1.2.3 From 1f8d36a1869f5efae4fadf6baf01f02211040b97 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 18 Mar 2011 12:07:09 +0800 Subject: net,rcu: convert call_rcu(__nf_ct_ext_free_rcu) to kfree_rcu() The rcu callback __nf_ct_ext_free_rcu() just calls a kfree(), so we use kfree_rcu() instead of the call_rcu(__nf_ct_ext_free_rcu). Signed-off-by: Lai Jiangshan Acked-by: David S. Miller Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- net/netfilter/nf_conntrack_extend.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 80a23ed62bb0..05ecdc281a53 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -68,12 +68,6 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) return (void *)(*ext) + off; } -static void __nf_ct_ext_free_rcu(struct rcu_head *head) -{ - struct nf_ct_ext *ext = container_of(head, struct nf_ct_ext, rcu); - kfree(ext); -} - void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) { struct nf_ct_ext *old, *new; @@ -114,7 +108,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) (void *)old + old->offset[i]); rcu_read_unlock(); } - call_rcu(&old->rcu, __nf_ct_ext_free_rcu); + kfree_rcu(old, rcu); ct->ext = new; } -- cgit v1.2.3 From 88b4a0347a81539884df5ad535e10cf9fa87d8d4 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 18 Mar 2011 12:15:02 +0800 Subject: net,rcu: convert call_rcu(xt_osf_finger_free_rcu) to kfree_rcu() The rcu callback xt_osf_finger_free_rcu() just calls a kfree(), so we use kfree_rcu() instead of the call_rcu(xt_osf_finger_free_rcu). Signed-off-by: Lai Jiangshan Acked-by: David S. Miller Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- net/netfilter/xt_osf.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 4327e101c047..846f895cb656 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -62,13 +62,6 @@ static const struct nla_policy xt_osf_policy[OSF_ATTR_MAX + 1] = { [OSF_ATTR_FINGER] = { .len = sizeof(struct xt_osf_user_finger) }, }; -static void xt_osf_finger_free_rcu(struct rcu_head *rcu_head) -{ - struct xt_osf_finger *f = container_of(rcu_head, struct xt_osf_finger, rcu_head); - - kfree(f); -} - static int xt_osf_add_callback(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const osf_attrs[]) @@ -133,7 +126,7 @@ static int xt_osf_remove_callback(struct sock *ctnl, struct sk_buff *skb, * We are protected by nfnl mutex. */ list_del_rcu(&sf->finger_entry); - call_rcu(&sf->rcu_head, xt_osf_finger_free_rcu); + kfree_rcu(sf, rcu_head); err = 0; break; @@ -414,7 +407,7 @@ static void __exit xt_osf_fini(void) list_for_each_entry_rcu(f, &xt_osf_fingers[i], finger_entry) { list_del_rcu(&f->finger_entry); - call_rcu(&f->rcu_head, xt_osf_finger_free_rcu); + kfree_rcu(f, rcu_head); } } rcu_read_unlock(); -- cgit v1.2.3 From 421eab4cf318ce47c1daae391e54d1b427c6687b Mon Sep 17 00:00:00 2001 From: Hans Schillstrom Date: Tue, 3 May 2011 22:09:30 +0200 Subject: IPVS: Change of socket usage to enable name space exit. If the sync daemons run in a name space while it crashes or get killed, there is no way to stop them except for a reboot. When all patches are there, ip_vs_core will handle register_pernet_(), i.e. ip_vs_sync_init() and ip_vs_sync_cleanup() will be removed. Kernel threads should not increment the use count of a socket. By calling sk_change_net() after creating a socket this is avoided. sock_release cant be used intead sk_release_kernel() should be used. Thanks Eric W Biederman for your advices. Signed-off-by: Hans Schillstrom [horms@verge.net.au: minor edit to changelog] Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_core.c | 2 +- net/netfilter/ipvs/ip_vs_sync.c | 58 ++++++++++++++++++++++++++--------------- 2 files changed, 38 insertions(+), 22 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 07accf6b2401..a0791dc05a27 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1896,7 +1896,7 @@ static int __net_init __ip_vs_init(struct net *net) static void __net_exit __ip_vs_cleanup(struct net *net) { - IP_VS_DBG(10, "ipvs netns %d released\n", net_ipvs(net)->gen); + IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); } static struct pernet_operations ipvs_core_ops = { diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 3e7961e85e9c..0cce95310820 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1303,13 +1303,18 @@ static struct socket *make_send_sock(struct net *net) struct socket *sock; int result; - /* First create a socket */ - result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); + /* First create a socket move it to right name space later */ + result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - + /* + * Kernel sockets that are a part of a namespace, should not + * hold a reference to a namespace in order to allow to stop it. + * After sk_change_net should be released using sk_release_kernel. + */ + sk_change_net(sock->sk, net); result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); @@ -1334,8 +1339,8 @@ static struct socket *make_send_sock(struct net *net) return sock; - error: - sock_release(sock); +error: + sk_release_kernel(sock->sk); return ERR_PTR(result); } @@ -1350,12 +1355,17 @@ static struct socket *make_receive_sock(struct net *net) int result; /* First create a socket */ - result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); + result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - + /* + * Kernel sockets that are a part of a namespace, should not + * hold a reference to a namespace in order to allow to stop it. + * After sk_change_net should be released using sk_release_kernel. + */ + sk_change_net(sock->sk, net); /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = 1; @@ -1377,8 +1387,8 @@ static struct socket *make_receive_sock(struct net *net) return sock; - error: - sock_release(sock); +error: + sk_release_kernel(sock->sk); return ERR_PTR(result); } @@ -1473,7 +1483,7 @@ static int sync_thread_master(void *data) ip_vs_sync_buff_release(sb); /* release the sending multicast socket */ - sock_release(tinfo->sock); + sk_release_kernel(tinfo->sock->sk); kfree(tinfo); return 0; @@ -1513,7 +1523,7 @@ static int sync_thread_backup(void *data) } /* release the sending multicast socket */ - sock_release(tinfo->sock); + sk_release_kernel(tinfo->sock->sk); kfree(tinfo->buf); kfree(tinfo); @@ -1601,7 +1611,7 @@ outtinfo: outbuf: kfree(buf); outsocket: - sock_release(sock); + sk_release_kernel(sock->sk); out: return result; } @@ -1610,6 +1620,7 @@ out: int stop_sync_thread(struct net *net, int state) { struct netns_ipvs *ipvs = net_ipvs(net); + int retc = -EINVAL; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); @@ -1629,7 +1640,7 @@ int stop_sync_thread(struct net *net, int state) spin_lock_bh(&ipvs->sync_lock); ipvs->sync_state &= ~IP_VS_STATE_MASTER; spin_unlock_bh(&ipvs->sync_lock); - kthread_stop(ipvs->master_thread); + retc = kthread_stop(ipvs->master_thread); ipvs->master_thread = NULL; } else if (state == IP_VS_STATE_BACKUP) { if (!ipvs->backup_thread) @@ -1639,16 +1650,14 @@ int stop_sync_thread(struct net *net, int state) task_pid_nr(ipvs->backup_thread)); ipvs->sync_state &= ~IP_VS_STATE_BACKUP; - kthread_stop(ipvs->backup_thread); + retc = kthread_stop(ipvs->backup_thread); ipvs->backup_thread = NULL; - } else { - return -EINVAL; } /* decrease the module use count */ ip_vs_use_count_dec(); - return 0; + return retc; } /* @@ -1670,8 +1679,15 @@ static int __net_init __ip_vs_sync_init(struct net *net) static void __ip_vs_sync_cleanup(struct net *net) { - stop_sync_thread(net, IP_VS_STATE_MASTER); - stop_sync_thread(net, IP_VS_STATE_BACKUP); + int retc; + + retc = stop_sync_thread(net, IP_VS_STATE_MASTER); + if (retc && retc != -ESRCH) + pr_err("Failed to stop Master Daemon\n"); + + retc = stop_sync_thread(net, IP_VS_STATE_BACKUP); + if (retc && retc != -ESRCH) + pr_err("Failed to stop Backup Daemon\n"); } static struct pernet_operations ipvs_sync_ops = { @@ -1682,10 +1698,10 @@ static struct pernet_operations ipvs_sync_ops = { int __init ip_vs_sync_init(void) { - return register_pernet_subsys(&ipvs_sync_ops); + return register_pernet_device(&ipvs_sync_ops); } void ip_vs_sync_cleanup(void) { - unregister_pernet_subsys(&ipvs_sync_ops); + unregister_pernet_device(&ipvs_sync_ops); } -- cgit v1.2.3 From 74973f6fbfcd1b084c3ccc75b783a6dacac94a10 Mon Sep 17 00:00:00 2001 From: Hans Schillstrom Date: Tue, 3 May 2011 22:09:31 +0200 Subject: IPVS: init and cleanup restructuring DESCRIPTION This patch tries to restore the initial init and cleanup sequences that was before namspace patch. Netns also requires action when net devices unregister which has never been implemented. I.e this patch also covers when a device moves into a network namespace, and has to be released. IMPLEMENTATION The number of calls to register_pernet_device have been reduced to one for the ip_vs.ko Schedulers still have their own calls. This patch adds a function __ip_vs_service_cleanup() and an enable flag for the netfilter hooks. The nf hooks will be enabled when the first service is loaded and never disabled again, except when a namespace exit starts. Signed-off-by: Hans Schillstrom Acked-by: Julian Anastasov [horms@verge.net.au: minor edit to changelog] Signed-off-by: Simon Horman --- include/net/ip_vs.h | 17 ++++++ net/netfilter/ipvs/ip_vs_app.c | 15 +---- net/netfilter/ipvs/ip_vs_conn.c | 12 +--- net/netfilter/ipvs/ip_vs_core.c | 101 +++++++++++++++++++++++++++++--- net/netfilter/ipvs/ip_vs_ctl.c | 120 ++++++++++++++++++++++++++++++++------- net/netfilter/ipvs/ip_vs_est.c | 14 +---- net/netfilter/ipvs/ip_vs_proto.c | 11 +--- net/netfilter/ipvs/ip_vs_sync.c | 13 +---- 8 files changed, 223 insertions(+), 80 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 4d1b71ae82ba..02f67021e079 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -791,6 +791,7 @@ struct ip_vs_app { /* IPVS in network namespace */ struct netns_ipvs { int gen; /* Generation */ + int enable; /* enable like nf_hooks do */ /* * Hash table: for real service lookups */ @@ -1089,6 +1090,22 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) atomic_inc(&ctl_cp->n_control); } +/* + * IPVS netns init & cleanup functions + */ +extern int __ip_vs_estimator_init(struct net *net); +extern int __ip_vs_control_init(struct net *net); +extern int __ip_vs_protocol_init(struct net *net); +extern int __ip_vs_app_init(struct net *net); +extern int __ip_vs_conn_init(struct net *net); +extern int __ip_vs_sync_init(struct net *net); +extern void __ip_vs_conn_cleanup(struct net *net); +extern void __ip_vs_app_cleanup(struct net *net); +extern void __ip_vs_protocol_cleanup(struct net *net); +extern void __ip_vs_control_cleanup(struct net *net); +extern void __ip_vs_estimator_cleanup(struct net *net); +extern void __ip_vs_sync_cleanup(struct net *net); +extern void __ip_vs_service_cleanup(struct net *net); /* * IPVS application functions diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 2dc6de13ac18..51f3af7c4743 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -576,7 +576,7 @@ static const struct file_operations ip_vs_app_fops = { }; #endif -static int __net_init __ip_vs_app_init(struct net *net) +int __net_init __ip_vs_app_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -585,26 +585,17 @@ static int __net_init __ip_vs_app_init(struct net *net) return 0; } -static void __net_exit __ip_vs_app_cleanup(struct net *net) +void __net_exit __ip_vs_app_cleanup(struct net *net) { proc_net_remove(net, "ip_vs_app"); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_app_init, - .exit = __ip_vs_app_cleanup, -}; - int __init ip_vs_app_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_app_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index f289306cbf12..5092505f27a7 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1258,22 +1258,17 @@ int __net_init __ip_vs_conn_init(struct net *net) return 0; } -static void __net_exit __ip_vs_conn_cleanup(struct net *net) +void __net_exit __ip_vs_conn_cleanup(struct net *net) { /* flush all the connection entries first */ ip_vs_conn_flush(net); proc_net_remove(net, "ip_vs_conn"); proc_net_remove(net, "ip_vs_conn_sync"); } -static struct pernet_operations ipvs_conn_ops = { - .init = __ip_vs_conn_init, - .exit = __ip_vs_conn_cleanup, -}; int __init ip_vs_conn_init(void) { int idx; - int retc; /* Compute size and mask */ ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; @@ -1309,17 +1304,14 @@ int __init ip_vs_conn_init(void) rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); } - retc = register_pernet_subsys(&ipvs_conn_ops); - /* calculate the random value for connection hash */ get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); - return retc; + return 0; } void ip_vs_conn_cleanup(void) { - unregister_pernet_subsys(&ipvs_conn_ops); /* Release the empty cache */ kmem_cache_destroy(ip_vs_conn_cachep); vfree(ip_vs_conn_tab); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a0791dc05a27..a74dae6c5dbc 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1113,6 +1113,9 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) return NF_ACCEPT; net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { @@ -1343,6 +1346,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) return NF_ACCEPT; /* The packet looks wrong, ignore */ net = skb_net(skb); + pd = ip_vs_proto_data_get(net, cih->protocol); if (!pd) return NF_ACCEPT; @@ -1529,6 +1533,11 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); /* Bad... Do not break raw sockets */ @@ -1562,7 +1571,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } - net = skb_net(skb); /* Protocol supported? */ pd = ip_vs_proto_data_get(net, iph.protocol); if (unlikely(!pd)) @@ -1588,7 +1596,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); - net = skb_net(skb); ipvs = net_ipvs(net); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { @@ -1743,10 +1750,16 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp(skb, &r, hooknum); } @@ -1757,10 +1770,16 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp_v6(skb, &r, hooknum); } #endif @@ -1884,21 +1903,72 @@ static int __net_init __ip_vs_init(struct net *net) pr_err("%s(): no memory.\n", __func__); return -ENOMEM; } + /* Hold the beast until a service is registerd */ + ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ ipvs->gen = atomic_read(&ipvs_netns_cnt); atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; + + if (__ip_vs_estimator_init(net) < 0) + goto estimator_fail; + + if (__ip_vs_control_init(net) < 0) + goto control_fail; + + if (__ip_vs_protocol_init(net) < 0) + goto protocol_fail; + + if (__ip_vs_app_init(net) < 0) + goto app_fail; + + if (__ip_vs_conn_init(net) < 0) + goto conn_fail; + + if (__ip_vs_sync_init(net) < 0) + goto sync_fail; + printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", sizeof(struct netns_ipvs), ipvs->gen); return 0; +/* + * Error handling + */ + +sync_fail: + __ip_vs_conn_cleanup(net); +conn_fail: + __ip_vs_app_cleanup(net); +app_fail: + __ip_vs_protocol_cleanup(net); +protocol_fail: + __ip_vs_control_cleanup(net); +control_fail: + __ip_vs_estimator_cleanup(net); +estimator_fail: + return -ENOMEM; } static void __net_exit __ip_vs_cleanup(struct net *net) { + __ip_vs_service_cleanup(net); /* ip_vs_flush() with locks */ + __ip_vs_conn_cleanup(net); + __ip_vs_app_cleanup(net); + __ip_vs_protocol_cleanup(net); + __ip_vs_control_cleanup(net); + __ip_vs_estimator_cleanup(net); IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); } +static void __net_exit __ip_vs_dev_cleanup(struct net *net) +{ + EnterFunction(2); + net_ipvs(net)->enable = 0; /* Disable packet reception */ + __ip_vs_sync_cleanup(net); + LeaveFunction(2); +} + static struct pernet_operations ipvs_core_ops = { .init = __ip_vs_init, .exit = __ip_vs_cleanup, @@ -1906,6 +1976,10 @@ static struct pernet_operations ipvs_core_ops = { .size = sizeof(struct netns_ipvs), }; +static struct pernet_operations ipvs_core_dev_ops = { + .exit = __ip_vs_dev_cleanup, +}; + /* * Initialize IP Virtual Server */ @@ -1913,10 +1987,6 @@ static int __init ip_vs_init(void) { int ret; - ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ - if (ret < 0) - return ret; - ip_vs_estimator_init(); ret = ip_vs_control_init(); if (ret < 0) { @@ -1944,15 +2014,28 @@ static int __init ip_vs_init(void) goto cleanup_conn; } + ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ + if (ret < 0) + goto cleanup_sync; + + ret = register_pernet_device(&ipvs_core_dev_ops); + if (ret < 0) + goto cleanup_sub; + ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); if (ret < 0) { pr_err("can't register hooks.\n"); - goto cleanup_sync; + goto cleanup_dev; } pr_info("ipvs loaded.\n"); + return ret; +cleanup_dev: + unregister_pernet_device(&ipvs_core_dev_ops); +cleanup_sub: + unregister_pernet_subsys(&ipvs_core_ops); cleanup_sync: ip_vs_sync_cleanup(); cleanup_conn: @@ -1964,20 +2047,20 @@ cleanup_sync: ip_vs_control_cleanup(); cleanup_estimator: ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ return ret; } static void __exit ip_vs_cleanup(void) { nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); + unregister_pernet_device(&ipvs_core_dev_ops); + unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ ip_vs_sync_cleanup(); ip_vs_conn_cleanup(); ip_vs_app_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ pr_info("ipvs unloaded.\n"); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index ae47090bf45f..ea722810faf3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -69,6 +69,11 @@ int ip_vs_get_debug_level(void) } #endif + +/* Protos */ +static void __ip_vs_del_service(struct ip_vs_service *svc); + + #ifdef CONFIG_IP_VS_IPV6 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ static int __ip_vs_addr_is_local_v6(struct net *net, @@ -1214,6 +1219,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, write_unlock_bh(&__ip_vs_svc_lock); *svc_p = svc; + /* Now there is a service - full throttle */ + ipvs->enable = 1; return 0; @@ -1472,6 +1479,84 @@ static int ip_vs_flush(struct net *net) return 0; } +/* + * Delete service by {netns} in the service table. + * Called by __ip_vs_cleanup() + */ +void __ip_vs_service_cleanup(struct net *net) +{ + EnterFunction(2); + /* Check for "full" addressed entries */ + mutex_lock(&__ip_vs_mutex); + ip_vs_flush(net); + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); +} +/* + * Release dst hold by dst_cache + */ +static inline void +__ip_vs_dev_reset(struct ip_vs_dest *dest, struct net_device *dev) +{ + spin_lock_bh(&dest->dst_lock); + if (dest->dst_cache && dest->dst_cache->dev == dev) { + IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n", + dev->name, + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port), + atomic_read(&dest->refcnt)); + ip_vs_dst_reset(dest); + } + spin_unlock_bh(&dest->dst_lock); + +} +/* + * Netdev event receiver + * Currently only NETDEV_UNREGISTER is handled, i.e. if we hold a reference to + * a device that is "unregister" it must be released. + */ +static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = ptr; + struct net *net = dev_net(dev); + struct ip_vs_service *svc; + struct ip_vs_dest *dest; + unsigned int idx; + + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); + EnterFunction(2); + mutex_lock(&__ip_vs_mutex); + for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { + list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + } + + list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + + } + } + + list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) { + __ip_vs_dev_reset(dest, dev); + } + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); + return NOTIFY_DONE; +} /* * Zero counters in a service or all services @@ -3588,6 +3673,10 @@ void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { } #endif +static struct notifier_block ip_vs_dst_notifier = { + .notifier_call = ip_vs_dst_event, +}; + int __net_init __ip_vs_control_init(struct net *net) { int idx; @@ -3626,7 +3715,7 @@ err: return -ENOMEM; } -static void __net_exit __ip_vs_control_cleanup(struct net *net) +void __net_exit __ip_vs_control_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -3639,11 +3728,6 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net) free_percpu(ipvs->tot_stats.cpustats); } -static struct pernet_operations ipvs_control_ops = { - .init = __ip_vs_control_init, - .exit = __ip_vs_control_cleanup, -}; - int __init ip_vs_control_init(void) { int idx; @@ -3657,33 +3741,32 @@ int __init ip_vs_control_init(void) INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); } - ret = register_pernet_subsys(&ipvs_control_ops); - if (ret) { - pr_err("cannot register namespace.\n"); - goto err; - } - smp_wmb(); /* Do we really need it now ? */ ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); - goto err_net; + goto err_sock; } ret = ip_vs_genl_register(); if (ret) { pr_err("cannot register Generic Netlink interface.\n"); - nf_unregister_sockopt(&ip_vs_sockopts); - goto err_net; + goto err_genl; } + ret = register_netdevice_notifier(&ip_vs_dst_notifier); + if (ret < 0) + goto err_notf; + LeaveFunction(2); return 0; -err_net: - unregister_pernet_subsys(&ipvs_control_ops); -err: +err_notf: + ip_vs_genl_unregister(); +err_genl: + nf_unregister_sockopt(&ip_vs_sockopts); +err_sock: return ret; } @@ -3691,7 +3774,6 @@ err: void ip_vs_control_cleanup(void) { EnterFunction(2); - unregister_pernet_subsys(&ipvs_control_ops); ip_vs_genl_unregister(); nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 8c8766ca56ad..508cce98777c 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -192,7 +192,7 @@ void ip_vs_read_estimator(struct ip_vs_stats_user *dst, dst->outbps = (e->outbps + 0xF) >> 5; } -static int __net_init __ip_vs_estimator_init(struct net *net) +int __net_init __ip_vs_estimator_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -203,24 +203,16 @@ static int __net_init __ip_vs_estimator_init(struct net *net) return 0; } -static void __net_exit __ip_vs_estimator_exit(struct net *net) +void __net_exit __ip_vs_estimator_cleanup(struct net *net) { del_timer_sync(&net_ipvs(net)->est_timer); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_estimator_init, - .exit = __ip_vs_estimator_exit, -}; int __init ip_vs_estimator_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_estimator_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 17484a4416ef..eb86028536fc 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -316,7 +316,7 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, /* * per network name-space init */ -static int __net_init __ip_vs_protocol_init(struct net *net) +int __net_init __ip_vs_protocol_init(struct net *net) { #ifdef CONFIG_IP_VS_PROTO_TCP register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp); @@ -336,7 +336,7 @@ static int __net_init __ip_vs_protocol_init(struct net *net) return 0; } -static void __net_exit __ip_vs_protocol_cleanup(struct net *net) +void __net_exit __ip_vs_protocol_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd; @@ -349,11 +349,6 @@ static void __net_exit __ip_vs_protocol_cleanup(struct net *net) } } -static struct pernet_operations ipvs_proto_ops = { - .init = __ip_vs_protocol_init, - .exit = __ip_vs_protocol_cleanup, -}; - int __init ip_vs_protocol_init(void) { char protocols[64]; @@ -382,7 +377,6 @@ int __init ip_vs_protocol_init(void) REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif pr_info("Registered protocols (%s)\n", &protocols[2]); - return register_pernet_subsys(&ipvs_proto_ops); return 0; } @@ -393,7 +387,6 @@ void ip_vs_protocol_cleanup(void) struct ip_vs_protocol *pp; int i; - unregister_pernet_subsys(&ipvs_proto_ops); /* unregister all the ipvs protocols */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pp = ip_vs_proto_table[i]) != NULL) diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 0cce95310820..e292e5bddc70 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1663,7 +1663,7 @@ int stop_sync_thread(struct net *net, int state) /* * Initialize data struct for each netns */ -static int __net_init __ip_vs_sync_init(struct net *net) +int __net_init __ip_vs_sync_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -1677,7 +1677,7 @@ static int __net_init __ip_vs_sync_init(struct net *net) return 0; } -static void __ip_vs_sync_cleanup(struct net *net) +void __ip_vs_sync_cleanup(struct net *net) { int retc; @@ -1690,18 +1690,11 @@ static void __ip_vs_sync_cleanup(struct net *net) pr_err("Failed to stop Backup Daemon\n"); } -static struct pernet_operations ipvs_sync_ops = { - .init = __ip_vs_sync_init, - .exit = __ip_vs_sync_cleanup, -}; - - int __init ip_vs_sync_init(void) { - return register_pernet_device(&ipvs_sync_ops); + return 0; } void ip_vs_sync_cleanup(void) { - unregister_pernet_device(&ipvs_sync_ops); } -- cgit v1.2.3 From 315c34dae0069d0c67abd714bb846cd466289c7f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 21 Apr 2011 10:55:07 +0200 Subject: netfilter: ctnetlink: fix timestamp support for new conntracks This patch fixes the missing initialization of the start time if the timestamp support is enabled. libnetfilter_conntrack/utils# conntrack -E & libnetfilter_conntrack/utils# ./conntrack_create tcp 6 109 ESTABLISHED src=1.1.1.1 dst=2.2.2.2 sport=1025 dport=21 packets=0 bytes=0 [UNREPLIED] src=2.2.2.2 dst=1.1.1.1 sport=21 dport=1025 packets=0 bytes=0 mark=0 delta-time=1303296401 use=2 Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_netlink.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 30bf8a167fc8..482e90c61850 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1334,6 +1334,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, struct nf_conn *ct; int err = -EINVAL; struct nf_conntrack_helper *helper; + struct nf_conn_tstamp *tstamp; ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) @@ -1451,6 +1452,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = master_ct; } + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) + tstamp->start = ktime_to_ns(ktime_get_real()); add_timer(&ct->timeout); nf_conntrack_hash_insert(ct); -- cgit v1.2.3 From 5a6351eecf8c87afed9c883bb6341d09406d74ba Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 21 Apr 2011 10:57:21 +0200 Subject: netfilter: fix ebtables compat support commit 255d0dc34068a976 (netfilter: x_table: speedup compat operations) made ebtables not working anymore. 1) xt_compat_calc_jump() is not an exact match lookup 2) compat_table_info() has a typo in xt_compat_init_offsets() call 3) compat_do_replace() misses a xt_compat_init_offsets() call Reported-by: dann frazier Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy --- net/bridge/netfilter/ebtables.c | 3 ++- net/netfilter/x_tables.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'net/netfilter') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 893669caa8de..9707079bc40a 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1766,7 +1766,7 @@ static int compat_table_info(const struct ebt_table_info *info, newinfo->entries_size = size; - xt_compat_init_offsets(AF_INET, info->nentries); + xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries); return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); } @@ -2240,6 +2240,7 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); + xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) goto out_unlock; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index a9adf4c6b299..8a025a585d2f 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -455,6 +455,7 @@ void xt_compat_flush_offsets(u_int8_t af) vfree(xt[af].compat_tab); xt[af].compat_tab = NULL; xt[af].number = 0; + xt[af].cur = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); @@ -473,8 +474,7 @@ int xt_compat_calc_jump(u_int8_t af, unsigned int offset) else return mid ? tmp[mid - 1].delta : 0; } - WARN_ON_ONCE(1); - return 0; + return left ? tmp[left - 1].delta : 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); -- cgit v1.2.3 From 1ae132b0347907ac95b8bc9dba37934f59d2a508 Mon Sep 17 00:00:00 2001 From: Hans Schillstrom Date: Tue, 3 May 2011 22:09:30 +0200 Subject: IPVS: Change of socket usage to enable name space exit. If the sync daemons run in a name space while it crashes or get killed, there is no way to stop them except for a reboot. When all patches are there, ip_vs_core will handle register_pernet_(), i.e. ip_vs_sync_init() and ip_vs_sync_cleanup() will be removed. Kernel threads should not increment the use count of a socket. By calling sk_change_net() after creating a socket this is avoided. sock_release cant be used intead sk_release_kernel() should be used. Thanks Eric W Biederman for your advices. Signed-off-by: Hans Schillstrom [horms@verge.net.au: minor edit to changelog] Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_core.c | 2 +- net/netfilter/ipvs/ip_vs_sync.c | 58 ++++++++++++++++++++++++++--------------- 2 files changed, 38 insertions(+), 22 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 07accf6b2401..a0791dc05a27 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1896,7 +1896,7 @@ static int __net_init __ip_vs_init(struct net *net) static void __net_exit __ip_vs_cleanup(struct net *net) { - IP_VS_DBG(10, "ipvs netns %d released\n", net_ipvs(net)->gen); + IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); } static struct pernet_operations ipvs_core_ops = { diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 3e7961e85e9c..0cce95310820 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1303,13 +1303,18 @@ static struct socket *make_send_sock(struct net *net) struct socket *sock; int result; - /* First create a socket */ - result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); + /* First create a socket move it to right name space later */ + result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - + /* + * Kernel sockets that are a part of a namespace, should not + * hold a reference to a namespace in order to allow to stop it. + * After sk_change_net should be released using sk_release_kernel. + */ + sk_change_net(sock->sk, net); result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); @@ -1334,8 +1339,8 @@ static struct socket *make_send_sock(struct net *net) return sock; - error: - sock_release(sock); +error: + sk_release_kernel(sock->sk); return ERR_PTR(result); } @@ -1350,12 +1355,17 @@ static struct socket *make_receive_sock(struct net *net) int result; /* First create a socket */ - result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); + result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - + /* + * Kernel sockets that are a part of a namespace, should not + * hold a reference to a namespace in order to allow to stop it. + * After sk_change_net should be released using sk_release_kernel. + */ + sk_change_net(sock->sk, net); /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = 1; @@ -1377,8 +1387,8 @@ static struct socket *make_receive_sock(struct net *net) return sock; - error: - sock_release(sock); +error: + sk_release_kernel(sock->sk); return ERR_PTR(result); } @@ -1473,7 +1483,7 @@ static int sync_thread_master(void *data) ip_vs_sync_buff_release(sb); /* release the sending multicast socket */ - sock_release(tinfo->sock); + sk_release_kernel(tinfo->sock->sk); kfree(tinfo); return 0; @@ -1513,7 +1523,7 @@ static int sync_thread_backup(void *data) } /* release the sending multicast socket */ - sock_release(tinfo->sock); + sk_release_kernel(tinfo->sock->sk); kfree(tinfo->buf); kfree(tinfo); @@ -1601,7 +1611,7 @@ outtinfo: outbuf: kfree(buf); outsocket: - sock_release(sock); + sk_release_kernel(sock->sk); out: return result; } @@ -1610,6 +1620,7 @@ out: int stop_sync_thread(struct net *net, int state) { struct netns_ipvs *ipvs = net_ipvs(net); + int retc = -EINVAL; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); @@ -1629,7 +1640,7 @@ int stop_sync_thread(struct net *net, int state) spin_lock_bh(&ipvs->sync_lock); ipvs->sync_state &= ~IP_VS_STATE_MASTER; spin_unlock_bh(&ipvs->sync_lock); - kthread_stop(ipvs->master_thread); + retc = kthread_stop(ipvs->master_thread); ipvs->master_thread = NULL; } else if (state == IP_VS_STATE_BACKUP) { if (!ipvs->backup_thread) @@ -1639,16 +1650,14 @@ int stop_sync_thread(struct net *net, int state) task_pid_nr(ipvs->backup_thread)); ipvs->sync_state &= ~IP_VS_STATE_BACKUP; - kthread_stop(ipvs->backup_thread); + retc = kthread_stop(ipvs->backup_thread); ipvs->backup_thread = NULL; - } else { - return -EINVAL; } /* decrease the module use count */ ip_vs_use_count_dec(); - return 0; + return retc; } /* @@ -1670,8 +1679,15 @@ static int __net_init __ip_vs_sync_init(struct net *net) static void __ip_vs_sync_cleanup(struct net *net) { - stop_sync_thread(net, IP_VS_STATE_MASTER); - stop_sync_thread(net, IP_VS_STATE_BACKUP); + int retc; + + retc = stop_sync_thread(net, IP_VS_STATE_MASTER); + if (retc && retc != -ESRCH) + pr_err("Failed to stop Master Daemon\n"); + + retc = stop_sync_thread(net, IP_VS_STATE_BACKUP); + if (retc && retc != -ESRCH) + pr_err("Failed to stop Backup Daemon\n"); } static struct pernet_operations ipvs_sync_ops = { @@ -1682,10 +1698,10 @@ static struct pernet_operations ipvs_sync_ops = { int __init ip_vs_sync_init(void) { - return register_pernet_subsys(&ipvs_sync_ops); + return register_pernet_device(&ipvs_sync_ops); } void ip_vs_sync_cleanup(void) { - unregister_pernet_subsys(&ipvs_sync_ops); + unregister_pernet_device(&ipvs_sync_ops); } -- cgit v1.2.3 From 7a4f0761fce32ff4918a7c23b08db564ad33092d Mon Sep 17 00:00:00 2001 From: Hans Schillstrom Date: Tue, 3 May 2011 22:09:31 +0200 Subject: IPVS: init and cleanup restructuring DESCRIPTION This patch tries to restore the initial init and cleanup sequences that was before namspace patch. Netns also requires action when net devices unregister which has never been implemented. I.e this patch also covers when a device moves into a network namespace, and has to be released. IMPLEMENTATION The number of calls to register_pernet_device have been reduced to one for the ip_vs.ko Schedulers still have their own calls. This patch adds a function __ip_vs_service_cleanup() and an enable flag for the netfilter hooks. The nf hooks will be enabled when the first service is loaded and never disabled again, except when a namespace exit starts. Signed-off-by: Hans Schillstrom Acked-by: Julian Anastasov [horms@verge.net.au: minor edit to changelog] Signed-off-by: Simon Horman --- include/net/ip_vs.h | 17 ++++++ net/netfilter/ipvs/ip_vs_app.c | 15 +---- net/netfilter/ipvs/ip_vs_conn.c | 12 +--- net/netfilter/ipvs/ip_vs_core.c | 101 +++++++++++++++++++++++++++++--- net/netfilter/ipvs/ip_vs_ctl.c | 120 ++++++++++++++++++++++++++++++++------- net/netfilter/ipvs/ip_vs_est.c | 14 +---- net/netfilter/ipvs/ip_vs_proto.c | 11 +--- net/netfilter/ipvs/ip_vs_sync.c | 13 +---- 8 files changed, 223 insertions(+), 80 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d516f00c8e0f..86aefed6140b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -791,6 +791,7 @@ struct ip_vs_app { /* IPVS in network namespace */ struct netns_ipvs { int gen; /* Generation */ + int enable; /* enable like nf_hooks do */ /* * Hash table: for real service lookups */ @@ -1089,6 +1090,22 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) atomic_inc(&ctl_cp->n_control); } +/* + * IPVS netns init & cleanup functions + */ +extern int __ip_vs_estimator_init(struct net *net); +extern int __ip_vs_control_init(struct net *net); +extern int __ip_vs_protocol_init(struct net *net); +extern int __ip_vs_app_init(struct net *net); +extern int __ip_vs_conn_init(struct net *net); +extern int __ip_vs_sync_init(struct net *net); +extern void __ip_vs_conn_cleanup(struct net *net); +extern void __ip_vs_app_cleanup(struct net *net); +extern void __ip_vs_protocol_cleanup(struct net *net); +extern void __ip_vs_control_cleanup(struct net *net); +extern void __ip_vs_estimator_cleanup(struct net *net); +extern void __ip_vs_sync_cleanup(struct net *net); +extern void __ip_vs_service_cleanup(struct net *net); /* * IPVS application functions diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 2dc6de13ac18..51f3af7c4743 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -576,7 +576,7 @@ static const struct file_operations ip_vs_app_fops = { }; #endif -static int __net_init __ip_vs_app_init(struct net *net) +int __net_init __ip_vs_app_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -585,26 +585,17 @@ static int __net_init __ip_vs_app_init(struct net *net) return 0; } -static void __net_exit __ip_vs_app_cleanup(struct net *net) +void __net_exit __ip_vs_app_cleanup(struct net *net) { proc_net_remove(net, "ip_vs_app"); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_app_init, - .exit = __ip_vs_app_cleanup, -}; - int __init ip_vs_app_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_app_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index c97bd45975be..d3fd91bbba49 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1258,22 +1258,17 @@ int __net_init __ip_vs_conn_init(struct net *net) return 0; } -static void __net_exit __ip_vs_conn_cleanup(struct net *net) +void __net_exit __ip_vs_conn_cleanup(struct net *net) { /* flush all the connection entries first */ ip_vs_conn_flush(net); proc_net_remove(net, "ip_vs_conn"); proc_net_remove(net, "ip_vs_conn_sync"); } -static struct pernet_operations ipvs_conn_ops = { - .init = __ip_vs_conn_init, - .exit = __ip_vs_conn_cleanup, -}; int __init ip_vs_conn_init(void) { int idx; - int retc; /* Compute size and mask */ ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; @@ -1309,17 +1304,14 @@ int __init ip_vs_conn_init(void) rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); } - retc = register_pernet_subsys(&ipvs_conn_ops); - /* calculate the random value for connection hash */ get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); - return retc; + return 0; } void ip_vs_conn_cleanup(void) { - unregister_pernet_subsys(&ipvs_conn_ops); /* Release the empty cache */ kmem_cache_destroy(ip_vs_conn_cachep); vfree(ip_vs_conn_tab); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a0791dc05a27..a74dae6c5dbc 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1113,6 +1113,9 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) return NF_ACCEPT; net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { @@ -1343,6 +1346,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) return NF_ACCEPT; /* The packet looks wrong, ignore */ net = skb_net(skb); + pd = ip_vs_proto_data_get(net, cih->protocol); if (!pd) return NF_ACCEPT; @@ -1529,6 +1533,11 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); /* Bad... Do not break raw sockets */ @@ -1562,7 +1571,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } - net = skb_net(skb); /* Protocol supported? */ pd = ip_vs_proto_data_get(net, iph.protocol); if (unlikely(!pd)) @@ -1588,7 +1596,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); - net = skb_net(skb); ipvs = net_ipvs(net); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { @@ -1743,10 +1750,16 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp(skb, &r, hooknum); } @@ -1757,10 +1770,16 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp_v6(skb, &r, hooknum); } #endif @@ -1884,21 +1903,72 @@ static int __net_init __ip_vs_init(struct net *net) pr_err("%s(): no memory.\n", __func__); return -ENOMEM; } + /* Hold the beast until a service is registerd */ + ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ ipvs->gen = atomic_read(&ipvs_netns_cnt); atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; + + if (__ip_vs_estimator_init(net) < 0) + goto estimator_fail; + + if (__ip_vs_control_init(net) < 0) + goto control_fail; + + if (__ip_vs_protocol_init(net) < 0) + goto protocol_fail; + + if (__ip_vs_app_init(net) < 0) + goto app_fail; + + if (__ip_vs_conn_init(net) < 0) + goto conn_fail; + + if (__ip_vs_sync_init(net) < 0) + goto sync_fail; + printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", sizeof(struct netns_ipvs), ipvs->gen); return 0; +/* + * Error handling + */ + +sync_fail: + __ip_vs_conn_cleanup(net); +conn_fail: + __ip_vs_app_cleanup(net); +app_fail: + __ip_vs_protocol_cleanup(net); +protocol_fail: + __ip_vs_control_cleanup(net); +control_fail: + __ip_vs_estimator_cleanup(net); +estimator_fail: + return -ENOMEM; } static void __net_exit __ip_vs_cleanup(struct net *net) { + __ip_vs_service_cleanup(net); /* ip_vs_flush() with locks */ + __ip_vs_conn_cleanup(net); + __ip_vs_app_cleanup(net); + __ip_vs_protocol_cleanup(net); + __ip_vs_control_cleanup(net); + __ip_vs_estimator_cleanup(net); IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); } +static void __net_exit __ip_vs_dev_cleanup(struct net *net) +{ + EnterFunction(2); + net_ipvs(net)->enable = 0; /* Disable packet reception */ + __ip_vs_sync_cleanup(net); + LeaveFunction(2); +} + static struct pernet_operations ipvs_core_ops = { .init = __ip_vs_init, .exit = __ip_vs_cleanup, @@ -1906,6 +1976,10 @@ static struct pernet_operations ipvs_core_ops = { .size = sizeof(struct netns_ipvs), }; +static struct pernet_operations ipvs_core_dev_ops = { + .exit = __ip_vs_dev_cleanup, +}; + /* * Initialize IP Virtual Server */ @@ -1913,10 +1987,6 @@ static int __init ip_vs_init(void) { int ret; - ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ - if (ret < 0) - return ret; - ip_vs_estimator_init(); ret = ip_vs_control_init(); if (ret < 0) { @@ -1944,15 +2014,28 @@ static int __init ip_vs_init(void) goto cleanup_conn; } + ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ + if (ret < 0) + goto cleanup_sync; + + ret = register_pernet_device(&ipvs_core_dev_ops); + if (ret < 0) + goto cleanup_sub; + ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); if (ret < 0) { pr_err("can't register hooks.\n"); - goto cleanup_sync; + goto cleanup_dev; } pr_info("ipvs loaded.\n"); + return ret; +cleanup_dev: + unregister_pernet_device(&ipvs_core_dev_ops); +cleanup_sub: + unregister_pernet_subsys(&ipvs_core_ops); cleanup_sync: ip_vs_sync_cleanup(); cleanup_conn: @@ -1964,20 +2047,20 @@ cleanup_sync: ip_vs_control_cleanup(); cleanup_estimator: ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ return ret; } static void __exit ip_vs_cleanup(void) { nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); + unregister_pernet_device(&ipvs_core_dev_ops); + unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ ip_vs_sync_cleanup(); ip_vs_conn_cleanup(); ip_vs_app_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ pr_info("ipvs unloaded.\n"); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index ae47090bf45f..ea722810faf3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -69,6 +69,11 @@ int ip_vs_get_debug_level(void) } #endif + +/* Protos */ +static void __ip_vs_del_service(struct ip_vs_service *svc); + + #ifdef CONFIG_IP_VS_IPV6 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ static int __ip_vs_addr_is_local_v6(struct net *net, @@ -1214,6 +1219,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, write_unlock_bh(&__ip_vs_svc_lock); *svc_p = svc; + /* Now there is a service - full throttle */ + ipvs->enable = 1; return 0; @@ -1472,6 +1479,84 @@ static int ip_vs_flush(struct net *net) return 0; } +/* + * Delete service by {netns} in the service table. + * Called by __ip_vs_cleanup() + */ +void __ip_vs_service_cleanup(struct net *net) +{ + EnterFunction(2); + /* Check for "full" addressed entries */ + mutex_lock(&__ip_vs_mutex); + ip_vs_flush(net); + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); +} +/* + * Release dst hold by dst_cache + */ +static inline void +__ip_vs_dev_reset(struct ip_vs_dest *dest, struct net_device *dev) +{ + spin_lock_bh(&dest->dst_lock); + if (dest->dst_cache && dest->dst_cache->dev == dev) { + IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n", + dev->name, + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port), + atomic_read(&dest->refcnt)); + ip_vs_dst_reset(dest); + } + spin_unlock_bh(&dest->dst_lock); + +} +/* + * Netdev event receiver + * Currently only NETDEV_UNREGISTER is handled, i.e. if we hold a reference to + * a device that is "unregister" it must be released. + */ +static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = ptr; + struct net *net = dev_net(dev); + struct ip_vs_service *svc; + struct ip_vs_dest *dest; + unsigned int idx; + + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); + EnterFunction(2); + mutex_lock(&__ip_vs_mutex); + for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { + list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + } + + list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + + } + } + + list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) { + __ip_vs_dev_reset(dest, dev); + } + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); + return NOTIFY_DONE; +} /* * Zero counters in a service or all services @@ -3588,6 +3673,10 @@ void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { } #endif +static struct notifier_block ip_vs_dst_notifier = { + .notifier_call = ip_vs_dst_event, +}; + int __net_init __ip_vs_control_init(struct net *net) { int idx; @@ -3626,7 +3715,7 @@ err: return -ENOMEM; } -static void __net_exit __ip_vs_control_cleanup(struct net *net) +void __net_exit __ip_vs_control_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -3639,11 +3728,6 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net) free_percpu(ipvs->tot_stats.cpustats); } -static struct pernet_operations ipvs_control_ops = { - .init = __ip_vs_control_init, - .exit = __ip_vs_control_cleanup, -}; - int __init ip_vs_control_init(void) { int idx; @@ -3657,33 +3741,32 @@ int __init ip_vs_control_init(void) INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); } - ret = register_pernet_subsys(&ipvs_control_ops); - if (ret) { - pr_err("cannot register namespace.\n"); - goto err; - } - smp_wmb(); /* Do we really need it now ? */ ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); - goto err_net; + goto err_sock; } ret = ip_vs_genl_register(); if (ret) { pr_err("cannot register Generic Netlink interface.\n"); - nf_unregister_sockopt(&ip_vs_sockopts); - goto err_net; + goto err_genl; } + ret = register_netdevice_notifier(&ip_vs_dst_notifier); + if (ret < 0) + goto err_notf; + LeaveFunction(2); return 0; -err_net: - unregister_pernet_subsys(&ipvs_control_ops); -err: +err_notf: + ip_vs_genl_unregister(); +err_genl: + nf_unregister_sockopt(&ip_vs_sockopts); +err_sock: return ret; } @@ -3691,7 +3774,6 @@ err: void ip_vs_control_cleanup(void) { EnterFunction(2); - unregister_pernet_subsys(&ipvs_control_ops); ip_vs_genl_unregister(); nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 8c8766ca56ad..508cce98777c 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -192,7 +192,7 @@ void ip_vs_read_estimator(struct ip_vs_stats_user *dst, dst->outbps = (e->outbps + 0xF) >> 5; } -static int __net_init __ip_vs_estimator_init(struct net *net) +int __net_init __ip_vs_estimator_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -203,24 +203,16 @@ static int __net_init __ip_vs_estimator_init(struct net *net) return 0; } -static void __net_exit __ip_vs_estimator_exit(struct net *net) +void __net_exit __ip_vs_estimator_cleanup(struct net *net) { del_timer_sync(&net_ipvs(net)->est_timer); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_estimator_init, - .exit = __ip_vs_estimator_exit, -}; int __init ip_vs_estimator_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_estimator_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 17484a4416ef..eb86028536fc 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -316,7 +316,7 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, /* * per network name-space init */ -static int __net_init __ip_vs_protocol_init(struct net *net) +int __net_init __ip_vs_protocol_init(struct net *net) { #ifdef CONFIG_IP_VS_PROTO_TCP register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp); @@ -336,7 +336,7 @@ static int __net_init __ip_vs_protocol_init(struct net *net) return 0; } -static void __net_exit __ip_vs_protocol_cleanup(struct net *net) +void __net_exit __ip_vs_protocol_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd; @@ -349,11 +349,6 @@ static void __net_exit __ip_vs_protocol_cleanup(struct net *net) } } -static struct pernet_operations ipvs_proto_ops = { - .init = __ip_vs_protocol_init, - .exit = __ip_vs_protocol_cleanup, -}; - int __init ip_vs_protocol_init(void) { char protocols[64]; @@ -382,7 +377,6 @@ int __init ip_vs_protocol_init(void) REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif pr_info("Registered protocols (%s)\n", &protocols[2]); - return register_pernet_subsys(&ipvs_proto_ops); return 0; } @@ -393,7 +387,6 @@ void ip_vs_protocol_cleanup(void) struct ip_vs_protocol *pp; int i; - unregister_pernet_subsys(&ipvs_proto_ops); /* unregister all the ipvs protocols */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pp = ip_vs_proto_table[i]) != NULL) diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 0cce95310820..e292e5bddc70 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1663,7 +1663,7 @@ int stop_sync_thread(struct net *net, int state) /* * Initialize data struct for each netns */ -static int __net_init __ip_vs_sync_init(struct net *net) +int __net_init __ip_vs_sync_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -1677,7 +1677,7 @@ static int __net_init __ip_vs_sync_init(struct net *net) return 0; } -static void __ip_vs_sync_cleanup(struct net *net) +void __ip_vs_sync_cleanup(struct net *net) { int retc; @@ -1690,18 +1690,11 @@ static void __ip_vs_sync_cleanup(struct net *net) pr_err("Failed to stop Backup Daemon\n"); } -static struct pernet_operations ipvs_sync_ops = { - .init = __ip_vs_sync_init, - .exit = __ip_vs_sync_cleanup, -}; - - int __init ip_vs_sync_init(void) { - return register_pernet_device(&ipvs_sync_ops); + return 0; } void ip_vs_sync_cleanup(void) { - unregister_pernet_device(&ipvs_sync_ops); } -- cgit v1.2.3 From 1ed2f73d90fb49bcf5704aee7e9084adb882bfc5 Mon Sep 17 00:00:00 2001 From: Fernando Luis Vazquez Cao Date: Tue, 10 May 2011 10:00:21 +0200 Subject: netfilter: IPv6: fix DSCP mangle code The mask indicates the bits one wants to zero out, so it needs to be inverted before applying to the original TOS field. Signed-off-by: Fernando Luis Vazquez Cao Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_DSCP.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_DSCP.c b/net/netfilter/xt_DSCP.c index 0a229191e55b..ae8271652efa 100644 --- a/net/netfilter/xt_DSCP.c +++ b/net/netfilter/xt_DSCP.c @@ -99,7 +99,7 @@ tos_tg6(struct sk_buff *skb, const struct xt_action_param *par) u_int8_t orig, nv; orig = ipv6_get_dsfield(iph); - nv = (orig & info->tos_mask) ^ info->tos_value; + nv = (orig & ~info->tos_mask) ^ info->tos_value; if (orig != nv) { if (!skb_make_writable(skb, sizeof(struct iphdr))) -- cgit v1.2.3 From 93bbce1ad0cd788190dd7d6c17d289f771fe3d0d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 10 May 2011 12:13:36 +0200 Subject: netfilter: revert a2361c8735e07322023aedc36e4938b35af31eb0 This patch reverts a2361c8735e07322023aedc36e4938b35af31eb0: "[PATCH] netfilter: xt_conntrack: warn about use in raw table" Florian Wesphal says: "... when the packet was sent from the local machine the skb already has ->nfct attached, and -m conntrack seems to do the right thing." Acked-by: Jan Engelhardt Reported-by: Florian Wesphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_conntrack.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 481a86fdc409..61805d7b38aa 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -272,11 +272,6 @@ static int conntrack_mt_check(const struct xt_mtchk_param *par) { int ret; - if (strcmp(par->table, "raw") == 0) { - pr_info("state is undetermined at the time of raw table\n"); - return -EINVAL; - } - ret = nf_ct_l3proto_try_module_get(par->family); if (ret < 0) pr_info("cannot load conntrack support for proto=%u\n", -- cgit v1.2.3 From e58b34425bfcb08c6bc8c520b82c37ffcec87072 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 12 May 2011 18:22:34 -0400 Subject: ipvs: Use IP_VS_RT_MODE_* instead of magic constants. [ Add some cases I missed, from Julian Anastasov ] Signed-off-by: David S. Miller --- net/netfilter/ipvs/ip_vs_xmit.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 6132b213eddc..5d393c5a802d 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -229,8 +229,6 @@ out_err: /* * Get route to destination or remote server - * rt_mode: flags, &1=Allow local dest, &2=Allow non-local dest, - * &4=Allow redirect from remote daddr to local */ static struct rt6_info * __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, @@ -274,13 +272,14 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, } local = __ip_vs_is_local_route6(rt); - if (!((local ? 1 : 2) & rt_mode)) { + if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) & + rt_mode)) { IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n", local ? "local":"non-local", daddr); dst_release(&rt->dst); return NULL; } - if (local && !(rt_mode & 4) && + if (local && !(rt_mode & IP_VS_RT_MODE_RDR) && !((ort = (struct rt6_info *) skb_dst(skb)) && __ip_vs_is_local_route6(ort))) { IP_VS_DBG_RL("Redirect from non-local address %pI6 to local " @@ -440,7 +439,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); - if (!(rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr, NULL, 0, 2))) + if (!(rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr, NULL, 0, + IP_VS_RT_MODE_NON_LOCAL))) goto tx_error_icmp; /* MTU checking */ @@ -632,7 +632,9 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, - 0, 1|2|4))) + 0, (IP_VS_RT_MODE_LOCAL | + IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_RDR)))) goto tx_error_icmp; local = __ip_vs_is_local_route6(rt); /* @@ -875,7 +877,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, - &saddr, 1, 1|2))) + &saddr, 1, (IP_VS_RT_MODE_LOCAL | + IP_VS_RT_MODE_NON_LOCAL)))) goto tx_error_icmp; if (__ip_vs_is_local_route6(rt)) { dst_release(&rt->dst); @@ -1050,7 +1053,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, - 0, 1|2))) + 0, (IP_VS_RT_MODE_LOCAL | + IP_VS_RT_MODE_NON_LOCAL)))) goto tx_error_icmp; if (__ip_vs_is_local_route6(rt)) { dst_release(&rt->dst); @@ -1254,7 +1258,9 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, */ if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, - 0, 1|2|4))) + 0, (IP_VS_RT_MODE_LOCAL | + IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_RDR)))) goto tx_error_icmp; local = __ip_vs_is_local_route6(rt); -- cgit v1.2.3 From 44e3125ccd521585e73e6dd228b283ab26993c68 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 9 May 2011 14:38:06 -0700 Subject: ipvs: Eliminate rt->rt_dst usage in __ip_vs_get_out_rt(). We can simply track what destination address is used based upon which code block is taken at the top of the function. Signed-off-by: David S. Miller --- net/netfilter/ipvs/ip_vs_xmit.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 5d393c5a802d..3f3e0f4c38a5 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -110,6 +110,7 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, &dest->addr.ip, atomic_read(&rt->dst.__refcnt), rtos); } + daddr = dest->addr.ip; spin_unlock(&dest->dst_lock); } else { rt = ip_route_output(net, daddr, 0, rtos, 0); @@ -125,7 +126,7 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, rt_mode)) { IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n", (rt->rt_flags & RTCF_LOCAL) ? - "local":"non-local", &rt->rt_dst); + "local":"non-local", &daddr); ip_rt_put(rt); return NULL; } @@ -133,14 +134,14 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, !((ort = skb_rtable(skb)) && ort->rt_flags & RTCF_LOCAL)) { IP_VS_DBG_RL("Redirect from non-local address %pI4 to local " "requires NAT method, dest: %pI4\n", - &ip_hdr(skb)->daddr, &rt->rt_dst); + &ip_hdr(skb)->daddr, &daddr); ip_rt_put(rt); return NULL; } if (unlikely(!local && ipv4_is_loopback(ip_hdr(skb)->saddr))) { IP_VS_DBG_RL("Stopping traffic from loopback address %pI4 " "to non-local address, dest: %pI4\n", - &ip_hdr(skb)->saddr, &rt->rt_dst); + &ip_hdr(skb)->saddr, &daddr); ip_rt_put(rt); return NULL; } -- cgit v1.2.3 From c92f5ca2e5120796c56455e0a4b7cc0dfd6ceb49 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 10 May 2011 12:46:05 +0000 Subject: ipvs: Remove all remaining references to rt->rt_{src,dst} Remove all remaining references to rt->rt_{src,dst} by using dest->dst_saddr to cache saddr (used for TUN mode). For ICMP in FORWARD hook just restrict the rt_mode for NAT to disable LOCALNODE. All other modes do not allow IP_VS_RT_MODE_RDR, so we should be safe with the ICMP forwarding. Using cp->daddr as replacement for rt_dst is safe for all modes except BYPASS, even when cp->dest is NULL because it is cp->daddr that is used to assign cp->dest for sync-ed connections. Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- include/net/ip_vs.h | 9 +++--- net/netfilter/ipvs/ip_vs_core.c | 24 ++------------ net/netfilter/ipvs/ip_vs_xmit.c | 72 +++++++++++++++++++++++++++-------------- 3 files changed, 54 insertions(+), 51 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9d1f510ab6d0..4fff432aeade 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -665,9 +665,7 @@ struct ip_vs_dest { struct dst_entry *dst_cache; /* destination cache entry */ u32 dst_rtos; /* RT_TOS(tos) for dst */ u32 dst_cookie; -#ifdef CONFIG_IP_VS_IPV6 - struct in6_addr dst_saddr; -#endif + union nf_inet_addr dst_saddr; /* for virtual service */ struct ip_vs_service *svc; /* service it belongs to */ @@ -1253,7 +1251,8 @@ extern int ip_vs_tunnel_xmit extern int ip_vs_dr_xmit (struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp); extern int ip_vs_icmp_xmit -(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, int offset); +(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, + int offset, unsigned int hooknum); extern void ip_vs_dst_reset(struct ip_vs_dest *dest); #ifdef CONFIG_IP_VS_IPV6 @@ -1267,7 +1266,7 @@ extern int ip_vs_dr_xmit_v6 (struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp); extern int ip_vs_icmp_xmit_v6 (struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, - int offset); + int offset, unsigned int hooknum); #endif #ifdef CONFIG_SYSCTL diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a74dae6c5dbc..bfa808f4da13 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1382,15 +1382,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol) offset += 2 * sizeof(__u16); - verdict = ip_vs_icmp_xmit(skb, cp, pp, offset); - /* LOCALNODE from FORWARD hook is not supported */ - if (verdict == NF_ACCEPT && hooknum == NF_INET_FORWARD && - skb_rtable(skb)->rt_flags & RTCF_LOCAL) { - IP_VS_DBG(1, "%s(): " - "local delivery to %pI4 but in FORWARD\n", - __func__, &skb_rtable(skb)->rt_dst); - verdict = NF_DROP; - } + verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum); out: __ip_vs_conn_put(cp); @@ -1412,7 +1404,6 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, verdict; - struct rt6_info *rt; *related = 1; @@ -1474,23 +1465,12 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) if (!cp) return NF_ACCEPT; - verdict = NF_DROP; - /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->nexthdr || IPPROTO_UDP == cih->nexthdr || IPPROTO_SCTP == cih->nexthdr) offset += 2 * sizeof(__u16); - verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset); - /* LOCALNODE from FORWARD hook is not supported */ - if (verdict == NF_ACCEPT && hooknum == NF_INET_FORWARD && - (rt = (struct rt6_info *) skb_dst(skb)) && - rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK) { - IP_VS_DBG(1, "%s(): " - "local delivery to %pI6 but in FORWARD\n", - __func__, &rt->rt6i_dst); - verdict = NF_DROP; - } + verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum); __ip_vs_conn_put(cp); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 3f3e0f4c38a5..ee319a4338b0 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -87,7 +87,7 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos) /* Get route to destination or remote server */ static struct rtable * __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, - __be32 daddr, u32 rtos, int rt_mode) + __be32 daddr, u32 rtos, int rt_mode, __be32 *ret_saddr) { struct net *net = dev_net(skb_dst(skb)->dev); struct rtable *rt; /* Route to the other host */ @@ -98,7 +98,12 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, spin_lock(&dest->dst_lock); if (!(rt = (struct rtable *) __ip_vs_dst_check(dest, rtos))) { - rt = ip_route_output(net, dest->addr.ip, 0, rtos, 0); + struct flowi4 fl4; + + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = dest->addr.ip; + fl4.flowi4_tos = rtos; + rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) { spin_unlock(&dest->dst_lock); IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", @@ -106,19 +111,30 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, return NULL; } __ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0); - IP_VS_DBG(10, "new dst %pI4, refcnt=%d, rtos=%X\n", - &dest->addr.ip, + dest->dst_saddr.ip = fl4.saddr; + IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d, " + "rtos=%X\n", + &dest->addr.ip, &dest->dst_saddr.ip, atomic_read(&rt->dst.__refcnt), rtos); } daddr = dest->addr.ip; + if (ret_saddr) + *ret_saddr = dest->dst_saddr.ip; spin_unlock(&dest->dst_lock); } else { - rt = ip_route_output(net, daddr, 0, rtos, 0); + struct flowi4 fl4; + + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = daddr; + fl4.flowi4_tos = rtos; + rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) { IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr); return NULL; } + if (ret_saddr) + *ret_saddr = fl4.saddr; } local = rt->rt_flags & RTCF_LOCAL; @@ -249,7 +265,7 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, u32 cookie; dst = __ip_vs_route_output_v6(net, &dest->addr.in6, - &dest->dst_saddr, + &dest->dst_saddr.in6, do_xfrm); if (!dst) { spin_unlock(&dest->dst_lock); @@ -259,11 +275,11 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; __ip_vs_dst_set(dest, 0, dst_clone(&rt->dst), cookie); IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n", - &dest->addr.in6, &dest->dst_saddr, + &dest->addr.in6, &dest->dst_saddr.in6, atomic_read(&rt->dst.__refcnt)); } if (ret_saddr) - ipv6_addr_copy(ret_saddr, &dest->dst_saddr); + ipv6_addr_copy(ret_saddr, &dest->dst_saddr.in6); spin_unlock(&dest->dst_lock); } else { dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm); @@ -386,7 +402,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); if (!(rt = __ip_vs_get_out_rt(skb, NULL, iph->daddr, RT_TOS(iph->tos), - IP_VS_RT_MODE_NON_LOCAL))) + IP_VS_RT_MODE_NON_LOCAL, NULL))) goto tx_error_icmp; /* MTU checking */ @@ -518,7 +534,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, RT_TOS(iph->tos), IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | - IP_VS_RT_MODE_RDR))) + IP_VS_RT_MODE_RDR, NULL))) goto tx_error_icmp; local = rt->rt_flags & RTCF_LOCAL; /* @@ -540,7 +556,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #endif /* From world but DNAT to loopback address? */ - if (local && ipv4_is_loopback(rt->rt_dst) && + if (local && ipv4_is_loopback(cp->daddr.ip) && rt_is_input_route(skb_rtable(skb))) { IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): " "stopping DNAT to loopback address"); @@ -751,6 +767,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { struct rtable *rt; /* Route to the other host */ + __be32 saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ struct iphdr *old_iph = ip_hdr(skb); u8 tos = old_iph->tos; @@ -764,7 +781,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(tos), IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL))) + IP_VS_RT_MODE_NON_LOCAL, + &saddr))) goto tx_error_icmp; if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); @@ -832,8 +850,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->frag_off = df; iph->protocol = IPPROTO_IPIP; iph->tos = tos; - iph->daddr = rt->rt_dst; - iph->saddr = rt->rt_src; + iph->daddr = cp->daddr.ip; + iph->saddr = saddr; iph->ttl = old_iph->ttl; ip_select_ident(iph, &rt->dst, NULL); @@ -996,7 +1014,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(iph->tos), IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL))) + IP_VS_RT_MODE_NON_LOCAL, NULL))) goto tx_error_icmp; if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); @@ -1114,12 +1132,13 @@ tx_error: */ int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset) + struct ip_vs_protocol *pp, int offset, unsigned int hooknum) { struct rtable *rt; /* Route to the other host */ int mtu; int rc; int local; + int rt_mode; EnterFunction(10); @@ -1140,11 +1159,13 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, * mangle and send the packet here (only for VS/NAT) */ + /* LOCALNODE from FORWARD hook is not supported */ + rt_mode = (hooknum != NF_INET_FORWARD) ? + IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(ip_hdr(skb)->tos), - IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL | - IP_VS_RT_MODE_RDR))) + rt_mode, NULL))) goto tx_error_icmp; local = rt->rt_flags & RTCF_LOCAL; @@ -1167,7 +1188,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #endif /* From world but DNAT to loopback address? */ - if (local && ipv4_is_loopback(rt->rt_dst) && + if (local && ipv4_is_loopback(cp->daddr.ip) && rt_is_input_route(skb_rtable(skb))) { IP_VS_DBG(1, "%s(): " "stopping DNAT to loopback %pI4\n", @@ -1232,12 +1253,13 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #ifdef CONFIG_IP_VS_IPV6 int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset) + struct ip_vs_protocol *pp, int offset, unsigned int hooknum) { struct rt6_info *rt; /* Route to the other host */ int mtu; int rc; int local; + int rt_mode; EnterFunction(10); @@ -1258,10 +1280,12 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, * mangle and send the packet here (only for VS/NAT) */ + /* LOCALNODE from FORWARD hook is not supported */ + rt_mode = (hooknum != NF_INET_FORWARD) ? + IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, - 0, (IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL | - IP_VS_RT_MODE_RDR)))) + 0, rt_mode))) goto tx_error_icmp; local = __ip_vs_is_local_route6(rt); -- cgit v1.2.3 From 0f08190fe8af3cdb6ba19690eb0fa253ecef4bde Mon Sep 17 00:00:00 2001 From: Hans Schillstrom Date: Sun, 15 May 2011 17:20:29 +0200 Subject: IPVS: fix netns if reading ip_vs_* procfs entries Without this patch every access to ip_vs in procfs will increase the netns count i.e. an unbalanced get_net()/put_net(). (ipvsadm commands also use procfs.) The result is you can't exit a netns if reading ip_vs_* procfs entries. Signed-off-by: Hans Schillstrom Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_app.c | 2 +- net/netfilter/ipvs/ip_vs_conn.c | 4 ++-- net/netfilter/ipvs/ip_vs_ctl.c | 6 +++--- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 51f3af7c4743..059af3120be7 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -572,7 +572,7 @@ static const struct file_operations ip_vs_app_fops = { .open = ip_vs_app_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; #endif diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index d3fd91bbba49..bf28ac2fc99b 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1046,7 +1046,7 @@ static const struct file_operations ip_vs_conn_fops = { .open = ip_vs_conn_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; static const char *ip_vs_origin_name(unsigned flags) @@ -1114,7 +1114,7 @@ static const struct file_operations ip_vs_conn_sync_fops = { .open = ip_vs_conn_sync_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; #endif diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index ea722810faf3..37890f228b19 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2066,7 +2066,7 @@ static const struct file_operations ip_vs_info_fops = { .open = ip_vs_info_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; #endif @@ -2109,7 +2109,7 @@ static const struct file_operations ip_vs_stats_fops = { .open = ip_vs_stats_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) @@ -2178,7 +2178,7 @@ static const struct file_operations ip_vs_stats_percpu_fops = { .open = ip_vs_stats_percpu_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; #endif -- cgit v1.2.3 From 274ea0e2a4cdf18110e5931b8ecbfef6353e5293 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 16 May 2011 14:42:26 +0200 Subject: netfilter: nf_ct_sip: validate Content-Length in TCP SIP messages Verify that the message length of a single SIP message, which is calculated based on the Content-Length field contained in the SIP message, does not exceed the packet boundaries. Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_sip.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index bcf47eb518ef..1f81abde131f 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1461,6 +1461,8 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, end += strlen("\r\n\r\n") + clen; msglen = origlen = end - dptr; + if (msglen > datalen) + return NF_DROP; ret = process_sip_msg(skb, ct, dataoff, &dptr, &msglen); if (ret != NF_ACCEPT) -- cgit v1.2.3 From e6e4d9ed11fb1fab8b3256a3dc14d71b5e984ac4 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 16 May 2011 14:45:39 +0200 Subject: netfilter: nf_ct_sip: fix SDP parsing in TCP SIP messages for some Cisco phones Some Cisco phones do not place the Content-Length field at the end of the SIP message. This is valid, due to a misunderstanding of the specification the parser expects the SDP body to start directly after the Content-Length field. Fix the parser to scan for \r\n\r\n to locate the beginning of the SDP body. Reported-by: Teresa Kang Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_sip.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 1f81abde131f..c05c0dc33499 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1419,6 +1419,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, const char *dptr, *end; s16 diff, tdiff = 0; int ret = NF_ACCEPT; + bool term; typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust; if (ctinfo != IP_CT_ESTABLISHED && @@ -1453,10 +1454,15 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, if (dptr + matchoff == end) break; - if (end + strlen("\r\n\r\n") > dptr + datalen) - break; - if (end[0] != '\r' || end[1] != '\n' || - end[2] != '\r' || end[3] != '\n') + term = false; + for (; end + strlen("\r\n\r\n") <= dptr + datalen; end++) { + if (end[0] == '\r' && end[1] == '\n' && + end[2] == '\r' && end[3] == '\n') { + term = true; + break; + } + } + if (!term) break; end += strlen("\r\n\r\n") + clen; -- cgit v1.2.3 From 9184a9cba622d9e38462ce11dff7da094b4fea84 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 24 May 2011 10:20:19 +0200 Subject: netfilter: ipset: fix ip_set_flush return code ip_set_flush returned -EPROTO instead of -IPSET_ERR_PROTOCOL, fixed Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- 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 72d1ac611fdc..8041befc6555 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -815,7 +815,7 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb, ip_set_id_t i; if (unlikely(protocol_failed(attr))) - return -EPROTO; + return -IPSET_ERR_PROTOCOL; if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < ip_set_max; i++) -- cgit v1.2.3 From c74c0bfe0b61cf41a897c2444c038e0d3f600556 Mon Sep 17 00:00:00 2001 From: Hans Schillstrom Date: Tue, 24 May 2011 14:11:05 +0200 Subject: IPVS: bug in ip_vs_ftp, same list heaad used in all netns. When ip_vs was adapted to netns the ftp application was not adapted in a correct way. However this is a fix to avoid kernel errors. In the long term another solution might be chosen. I.e the ports that the ftp appl, uses should be per netns. Signed-off-by: Hans Schillstrom Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 3 ++- net/netfilter/ipvs/ip_vs_ftp.c | 27 +++++++++++++++++++-------- 2 files changed, 21 insertions(+), 9 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 4fff432aeade..481f856c650f 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -797,7 +797,8 @@ struct netns_ipvs { struct list_head rs_table[IP_VS_RTAB_SIZE]; /* ip_vs_app */ struct list_head app_list; - + /* ip_vs_ftp */ + struct ip_vs_app *ftp_app; /* ip_vs_proto */ #define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */ struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE]; diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 6b5dd6ddaae9..af63553fa332 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -411,25 +411,35 @@ static struct ip_vs_app ip_vs_ftp = { static int __net_init __ip_vs_ftp_init(struct net *net) { int i, ret; - struct ip_vs_app *app = &ip_vs_ftp; + struct ip_vs_app *app; + struct netns_ipvs *ipvs = net_ipvs(net); + + app = kmemdup(&ip_vs_ftp, sizeof(struct ip_vs_app), GFP_KERNEL); + if (!app) + return -ENOMEM; + INIT_LIST_HEAD(&app->a_list); + INIT_LIST_HEAD(&app->incs_list); + ipvs->ftp_app = app; ret = register_ip_vs_app(net, app); if (ret) - return ret; + goto err_exit; for (i=0; iprotocol, ports[i]); if (ret) - break; + goto err_unreg; pr_info("%s: loaded support on port[%d] = %d\n", app->name, i, ports[i]); } + return 0; - if (ret) - unregister_ip_vs_app(net, app); - +err_unreg: + unregister_ip_vs_app(net, app); +err_exit: + kfree(ipvs->ftp_app); return ret; } /* @@ -437,9 +447,10 @@ static int __net_init __ip_vs_ftp_init(struct net *net) */ static void __ip_vs_ftp_exit(struct net *net) { - struct ip_vs_app *app = &ip_vs_ftp; + struct netns_ipvs *ipvs = net_ipvs(net); - unregister_ip_vs_app(net, app); + unregister_ip_vs_app(net, ipvs->ftp_app); + kfree(ipvs->ftp_app); } static struct pernet_operations ip_vs_ftp_ops = { -- cgit v1.2.3 From c7ac8679bec9397afe8918f788cbcef88c38da54 Mon Sep 17 00:00:00 2001 From: Greg Rose Date: Fri, 10 Jun 2011 01:27:09 +0000 Subject: rtnetlink: Compute and store minimum ifinfo dump size The message size allocated for rtnl ifinfo dumps was limited to a single page. This is not enough for additional interface info available with devices that support SR-IOV and caused a bug in which VF info would not be displayed if more than approximately 40 VFs were created per interface. Implement a new function pointer for the rtnl_register service that will calculate the amount of data required for the ifinfo dump and allocate enough data to satisfy the request. Signed-off-by: Greg Rose Signed-off-by: Jeff Kirsher --- drivers/infiniband/core/netlink.c | 2 +- include/linux/netlink.h | 6 ++-- include/net/rtnetlink.h | 7 +++-- net/bridge/br_netlink.c | 15 ++++++--- net/core/fib_rules.c | 6 ++-- net/core/neighbour.c | 11 ++++--- net/core/rtnetlink.c | 60 +++++++++++++++++++++++++++++------- net/dcb/dcbnl.c | 4 +-- net/decnet/dn_dev.c | 6 ++-- net/decnet/dn_fib.c | 4 +-- net/decnet/dn_route.c | 5 +-- net/ipv4/devinet.c | 6 ++-- net/ipv4/fib_frontend.c | 6 ++-- net/ipv4/inet_diag.c | 2 +- net/ipv4/ipmr.c | 3 +- net/ipv4/route.c | 2 +- net/ipv6/addrconf.c | 16 ++++++---- net/ipv6/addrlabel.c | 9 ++++-- net/ipv6/ip6_fib.c | 3 +- net/ipv6/ip6mr.c | 3 +- net/ipv6/route.c | 6 ++-- net/netfilter/ipset/ip_set_core.c | 2 +- net/netfilter/nf_conntrack_netlink.c | 4 +-- net/netlink/af_netlink.c | 17 ++++++---- net/netlink/genetlink.c | 2 +- net/phonet/pn_netlink.c | 13 ++++---- net/sched/act_api.c | 7 +++-- net/sched/cls_api.c | 6 ++-- net/sched/sch_api.c | 12 ++++---- net/xfrm/xfrm_user.c | 3 +- 30 files changed, 158 insertions(+), 90 deletions(-) (limited to 'net/netfilter') diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c index 4a5abaf0a25c..9227f4acd79c 100644 --- a/drivers/infiniband/core/netlink.c +++ b/drivers/infiniband/core/netlink.c @@ -148,7 +148,7 @@ static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; return netlink_dump_start(nls, skb, nlh, client->cb_table[op].dump, - NULL); + NULL, 0); } } diff --git a/include/linux/netlink.h b/include/linux/netlink.h index a9dd89552f9c..fdd0188a167e 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -221,7 +221,8 @@ struct netlink_callback { int (*dump)(struct sk_buff * skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); - int family; + u16 family; + u16 min_dump_alloc; long args[6]; }; @@ -259,7 +260,8 @@ __nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags) extern int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, int (*dump)(struct sk_buff *skb, struct netlink_callback*), - int (*done)(struct netlink_callback*)); + int (*done)(struct netlink_callback*), + u16 min_dump_alloc); #define NL_NONROOT_RECV 0x1 diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 4093ca78cf60..678f1ffaf843 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -6,11 +6,14 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, void *); typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); +typedef u16 (*rtnl_calcit_func)(struct sk_buff *); extern int __rtnl_register(int protocol, int msgtype, - rtnl_doit_func, rtnl_dumpit_func); + rtnl_doit_func, rtnl_dumpit_func, + rtnl_calcit_func); extern void rtnl_register(int protocol, int msgtype, - rtnl_doit_func, rtnl_dumpit_func); + rtnl_doit_func, rtnl_dumpit_func, + rtnl_calcit_func); extern int rtnl_unregister(int protocol, int msgtype); extern void rtnl_unregister_all(int protocol); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index ffb0dc4cc0e8..6814083a92f4 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -218,19 +218,24 @@ int __init br_netlink_init(void) if (err < 0) goto err1; - err = __rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, br_dump_ifinfo); + err = __rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, + br_dump_ifinfo, NULL); if (err) goto err2; - err = __rtnl_register(PF_BRIDGE, RTM_SETLINK, br_rtm_setlink, NULL); + err = __rtnl_register(PF_BRIDGE, RTM_SETLINK, + br_rtm_setlink, NULL, NULL); if (err) goto err3; - err = __rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, br_fdb_add, NULL); + err = __rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, + br_fdb_add, NULL, NULL); if (err) goto err3; - err = __rtnl_register(PF_BRIDGE, RTM_DELNEIGH, br_fdb_delete, NULL); + err = __rtnl_register(PF_BRIDGE, RTM_DELNEIGH, + br_fdb_delete, NULL, NULL); if (err) goto err3; - err = __rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, br_fdb_dump); + err = __rtnl_register(PF_BRIDGE, RTM_GETNEIGH, + NULL, br_fdb_dump, NULL); if (err) goto err3; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 008dc70b064b..e7ab0c0285b5 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -740,9 +740,9 @@ static struct pernet_operations fib_rules_net_ops = { static int __init fib_rules_init(void) { int err; - rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL); - rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL); - rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule); + rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, NULL); err = register_pernet_subsys(&fib_rules_net_ops); if (err < 0) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 799f06e03a22..ceb505b1507c 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2909,12 +2909,13 @@ EXPORT_SYMBOL(neigh_sysctl_unregister); static int __init neigh_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL); - rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL); - rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info); + rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info, NULL); - rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info); - rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL); + rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info, + NULL); + rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL, NULL); return 0; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index abd936d8a716..a798fc6f2aa1 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -56,9 +56,11 @@ struct rtnl_link { rtnl_doit_func doit; rtnl_dumpit_func dumpit; + rtnl_calcit_func calcit; }; static DEFINE_MUTEX(rtnl_mutex); +static u16 min_ifinfo_dump_size; void rtnl_lock(void) { @@ -144,12 +146,28 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) return tab ? tab[msgindex].dumpit : NULL; } +static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex) +{ + struct rtnl_link *tab; + + if (protocol <= RTNL_FAMILY_MAX) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + + if (tab == NULL || tab[msgindex].calcit == NULL) + tab = rtnl_msg_handlers[PF_UNSPEC]; + + return tab ? tab[msgindex].calcit : NULL; +} + /** * __rtnl_register - Register a rtnetlink message type * @protocol: Protocol family or PF_UNSPEC * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message + * @calcit: Function pointer to calc size of dump message * * Registers the specified function pointers (at least one of them has * to be non-NULL) to be called whenever a request message for the @@ -162,7 +180,8 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) * Returns 0 on success or a negative error code. */ int __rtnl_register(int protocol, int msgtype, - rtnl_doit_func doit, rtnl_dumpit_func dumpit) + rtnl_doit_func doit, rtnl_dumpit_func dumpit, + rtnl_calcit_func calcit) { struct rtnl_link *tab; int msgindex; @@ -185,6 +204,9 @@ int __rtnl_register(int protocol, int msgtype, if (dumpit) tab[msgindex].dumpit = dumpit; + if (calcit) + tab[msgindex].calcit = calcit; + return 0; } EXPORT_SYMBOL_GPL(__rtnl_register); @@ -199,9 +221,10 @@ EXPORT_SYMBOL_GPL(__rtnl_register); * of memory implies no sense in continuing. */ void rtnl_register(int protocol, int msgtype, - rtnl_doit_func doit, rtnl_dumpit_func dumpit) + rtnl_doit_func doit, rtnl_dumpit_func dumpit, + rtnl_calcit_func calcit) { - if (__rtnl_register(protocol, msgtype, doit, dumpit) < 0) + if (__rtnl_register(protocol, msgtype, doit, dumpit, calcit) < 0) panic("Unable to register rtnetlink message handler, " "protocol = %d, message type = %d\n", protocol, msgtype); @@ -1818,6 +1841,11 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) return err; } +static u16 rtnl_calcit(struct sk_buff *skb) +{ + return min_ifinfo_dump_size; +} + static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) { int idx; @@ -1847,11 +1875,14 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; + size_t if_info_size; - skb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL); + skb = nlmsg_new((if_info_size = if_nlmsg_size(dev)), GFP_KERNEL); if (skb == NULL) goto errout; + min_ifinfo_dump_size = max_t(u16, if_info_size, min_ifinfo_dump_size); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ @@ -1902,14 +1933,20 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { struct sock *rtnl; rtnl_dumpit_func dumpit; + rtnl_calcit_func calcit; + u16 min_dump_alloc = 0; dumpit = rtnl_get_dumpit(family, type); if (dumpit == NULL) return -EOPNOTSUPP; + calcit = rtnl_get_calcit(family, type); + if (calcit) + min_dump_alloc = calcit(skb); __rtnl_unlock(); rtnl = net->rtnl; - err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL); + err = netlink_dump_start(rtnl, skb, nlh, dumpit, + NULL, min_dump_alloc); rtnl_lock(); return err; } @@ -2019,12 +2056,13 @@ void __init rtnetlink_init(void) netlink_set_nonroot(NETLINK_ROUTE, NL_NONROOT_RECV); register_netdevice_notifier(&rtnetlink_dev_notifier); - rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, rtnl_dump_ifinfo); - rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL); - rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL); - rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL); + rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, + rtnl_dump_ifinfo, rtnl_calcit); + rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all); - rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all); + rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL); + rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL); } diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 3609eacaf4ce..ed1bb8c65a9e 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1819,8 +1819,8 @@ static int __init dcbnl_init(void) { INIT_LIST_HEAD(&dcb_app_list); - rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL); - rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL); + rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, NULL); return 0; } diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index cf26ac74a188..3780fd6e7bfe 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -1414,9 +1414,9 @@ void __init dn_dev_init(void) dn_dev_devices_on(); - rtnl_register(PF_DECnet, RTM_NEWADDR, dn_nl_newaddr, NULL); - rtnl_register(PF_DECnet, RTM_DELADDR, dn_nl_deladdr, NULL); - rtnl_register(PF_DECnet, RTM_GETADDR, NULL, dn_nl_dump_ifaddr); + rtnl_register(PF_DECnet, RTM_NEWADDR, dn_nl_newaddr, NULL, NULL); + rtnl_register(PF_DECnet, RTM_DELADDR, dn_nl_deladdr, NULL, NULL); + rtnl_register(PF_DECnet, RTM_GETADDR, NULL, dn_nl_dump_ifaddr, NULL); proc_net_fops_create(&init_net, "decnet_dev", S_IRUGO, &dn_dev_seq_fops); diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 1c74ed36ce8f..104324d6d535 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -763,8 +763,8 @@ void __init dn_fib_init(void) register_dnaddr_notifier(&dn_fib_dnaddr_notifier); - rtnl_register(PF_DECnet, RTM_NEWROUTE, dn_fib_rtm_newroute, NULL); - rtnl_register(PF_DECnet, RTM_DELROUTE, dn_fib_rtm_delroute, NULL); + rtnl_register(PF_DECnet, RTM_NEWROUTE, dn_fib_rtm_newroute, NULL, NULL); + rtnl_register(PF_DECnet, RTM_DELROUTE, dn_fib_rtm_delroute, NULL, NULL); } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 74544bc6fdec..2949ca474ede 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1841,10 +1841,11 @@ void __init dn_route_init(void) proc_net_fops_create(&init_net, "decnet_cache", S_IRUGO, &dn_rt_cache_seq_fops); #ifdef CONFIG_DECNET_ROUTER - rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute, dn_fib_dump); + rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute, + dn_fib_dump, NULL); #else rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute, - dn_cache_dump); + dn_cache_dump, NULL); #endif } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 0d4a184af16f..37b3c188d8b3 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1833,8 +1833,8 @@ void __init devinet_init(void) rtnl_af_register(&inet_af_ops); - rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL); - rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL); - rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr); + rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL); + rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL); + rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 22524716fe70..92fc5f69f5da 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1124,9 +1124,9 @@ static struct pernet_operations fib_net_ops = { void __init ip_fib_init(void) { - rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL); - rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL); - rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib); + rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); + rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); + rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); register_pernet_subsys(&fib_net_ops); register_netdevice_notifier(&fib_netdev_notifier); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 6ffe94ca5bc9..5ff47656fced 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -871,7 +871,7 @@ static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } return netlink_dump_start(idiagnl, skb, nlh, - inet_diag_dump, NULL); + inet_diag_dump, NULL, 0); } return inet_diag_get_exact(skb, nlh); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 30a7763c400e..aae2bd8cd924 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2544,7 +2544,8 @@ int __init ip_mr_init(void) goto add_proto_fail; } #endif - rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, NULL, ipmr_rtm_dumproute); + rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, + NULL, ipmr_rtm_dumproute, NULL); return 0; #ifdef CONFIG_IP_PIMSM_V2 diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 52b0b956508b..aa29c6291353 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3295,7 +3295,7 @@ int __init ip_rt_init(void) xfrm_init(); xfrm4_init(ip_rt_max_size); #endif - rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL); + rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL); #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3e369425df58..05838c7fcf64 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4727,16 +4727,20 @@ int __init addrconf_init(void) if (err < 0) goto errout_af; - err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo); + err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo, + NULL); if (err < 0) goto errout; /* Only the first call to __rtnl_register can fail */ - __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL); - __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL); - __rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, inet6_dump_ifaddr); - __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, inet6_dump_ifmcaddr); - __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr); + __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, NULL); + __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, NULL); + __rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, + inet6_dump_ifaddr, NULL); + __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, + inet6_dump_ifmcaddr, NULL); + __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, + inet6_dump_ifacaddr, NULL); ipv6_addr_label_rtnl_register(); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index c8993e5a337c..2d8ddba9ee58 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -592,8 +592,11 @@ out: void __init ipv6_addr_label_rtnl_register(void) { - __rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel, NULL); - __rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel, NULL); - __rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get, ip6addrlbl_dump); + __rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel, + NULL, NULL); + __rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel, + NULL, NULL); + __rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get, + ip6addrlbl_dump, NULL); } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 4076a0b14b20..3030bdfd3ca4 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1586,7 +1586,8 @@ int __init fib6_init(void) if (ret) goto out_kmem_cache_create; - ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib); + ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib, + NULL); if (ret) goto out_unregister_subsys; out: diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 82a809901f8e..705c82886281 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1354,7 +1354,8 @@ int __init ip6_mr_init(void) goto add_proto_fail; } #endif - rtnl_register(RTNL_FAMILY_IP6MR, RTM_GETROUTE, NULL, ip6mr_rtm_dumproute); + rtnl_register(RTNL_FAMILY_IP6MR, RTM_GETROUTE, NULL, + ip6mr_rtm_dumproute, NULL); return 0; #ifdef CONFIG_IPV6_PIMSM_V2 add_proto_fail: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index de2b1decd786..216ff31a0cc9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2925,9 +2925,9 @@ int __init ip6_route_init(void) goto xfrm6_init; ret = -ENOBUFS; - if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL) || - __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL) || - __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL)) + if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, NULL) || + __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, NULL) || + __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL, NULL)) goto fib6_rules_init; ret = register_netdevice_notifier(&ip6_route_dev_notifier); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 8041befc6555..333b0bedf298 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1120,7 +1120,7 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb, return netlink_dump_start(ctnl, skb, nlh, ip_set_dump_start, - ip_set_dump_done); + ip_set_dump_done, 0); } /* Add, del and test */ diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 482e90c61850..7dec88a1755b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -970,7 +970,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_DUMP) return netlink_dump_start(ctnl, skb, nlh, ctnetlink_dump_table, - ctnetlink_done); + ctnetlink_done, 0); err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) @@ -1840,7 +1840,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_DUMP) { return netlink_dump_start(ctnl, skb, nlh, ctnetlink_exp_dump_table, - ctnetlink_exp_done); + ctnetlink_exp_done, 0); } err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6ef64adf7362..0b92f75491b1 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1659,13 +1659,10 @@ static int netlink_dump(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); struct netlink_callback *cb; - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct nlmsghdr *nlh; int len, err = -ENOBUFS; - - skb = sock_rmalloc(sk, NLMSG_GOODSIZE, 0, GFP_KERNEL); - if (!skb) - goto errout; + int alloc_size; mutex_lock(nlk->cb_mutex); @@ -1675,6 +1672,12 @@ static int netlink_dump(struct sock *sk) goto errout_skb; } + alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); + + skb = sock_rmalloc(sk, alloc_size, 0, GFP_KERNEL); + if (!skb) + goto errout; + len = cb->dump(skb, cb); if (len > 0) { @@ -1721,7 +1724,8 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, int (*dump)(struct sk_buff *skb, struct netlink_callback *), - int (*done)(struct netlink_callback *)) + int (*done)(struct netlink_callback *), + u16 min_dump_alloc) { struct netlink_callback *cb; struct sock *sk; @@ -1735,6 +1739,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->dump = dump; cb->done = done; cb->nlh = nlh; + cb->min_dump_alloc = min_dump_alloc; atomic_inc(&skb->users); cb->skb = skb; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 1781d99145e2..482fa571b4ee 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -525,7 +525,7 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) genl_unlock(); err = netlink_dump_start(net->genl_sock, skb, nlh, - ops->dumpit, ops->done); + ops->dumpit, ops->done, 0); genl_lock(); return err; } diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index 438accb7a5a8..d61f6761777d 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -289,15 +289,16 @@ out: int __init phonet_netlink_register(void) { - int err = __rtnl_register(PF_PHONET, RTM_NEWADDR, addr_doit, NULL); + int err = __rtnl_register(PF_PHONET, RTM_NEWADDR, addr_doit, + NULL, NULL); if (err) return err; /* Further __rtnl_register() cannot fail */ - __rtnl_register(PF_PHONET, RTM_DELADDR, addr_doit, NULL); - __rtnl_register(PF_PHONET, RTM_GETADDR, NULL, getaddr_dumpit); - __rtnl_register(PF_PHONET, RTM_NEWROUTE, route_doit, NULL); - __rtnl_register(PF_PHONET, RTM_DELROUTE, route_doit, NULL); - __rtnl_register(PF_PHONET, RTM_GETROUTE, NULL, route_dumpit); + __rtnl_register(PF_PHONET, RTM_DELADDR, addr_doit, NULL, NULL); + __rtnl_register(PF_PHONET, RTM_GETADDR, NULL, getaddr_dumpit, NULL); + __rtnl_register(PF_PHONET, RTM_NEWROUTE, route_doit, NULL, NULL); + __rtnl_register(PF_PHONET, RTM_DELROUTE, route_doit, NULL, NULL); + __rtnl_register(PF_PHONET, RTM_GETROUTE, NULL, route_dumpit, NULL); return 0; } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index a606025814a1..2f64262ab5d2 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1115,9 +1115,10 @@ nlmsg_failure: static int __init tc_action_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL); - rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL); - rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action); + rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action, + NULL); return 0; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index bb2c523f8158..9563887f219f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -610,10 +610,10 @@ EXPORT_SYMBOL(tcf_exts_dump_stats); static int __init tc_filter_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL); - rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, NULL); rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter, - tc_dump_tfilter); + tc_dump_tfilter, NULL); return 0; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 6b8627661c98..8182aefafb02 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1792,12 +1792,12 @@ static int __init pktsched_init(void) register_qdisc(&pfifo_head_drop_qdisc_ops); register_qdisc(&mq_qdisc_ops); - rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL); - rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL); - rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc); - rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL); - rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL); - rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass); + rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass, NULL); return 0; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c658cb3bc7c3..0256b8a0a7cf 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2299,7 +2299,8 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (link->dump == NULL) return -EINVAL; - return netlink_dump_start(net->xfrm.nlsk, skb, nlh, link->dump, link->done); + return netlink_dump_start(net->xfrm.nlsk, skb, nlh, + link->dump, link->done, 0); } err = nlmsg_parse(nlh, xfrm_msg_min[type], attrs, XFRMA_MAX, -- cgit v1.2.3