From mboxrd@z Thu Jan 1 00:00:00 1970 From: ebiederm@xmission.com (Eric W. Biederman) Subject: [PATCH -next 5/6] netfilter: Per network namespace netfilter hooks. Date: Fri, 10 Jul 2015 18:15:06 -0500 Message-ID: <87fv4vr4ed.fsf_-_@x220.int.ebiederm.org> References: <87616ppt3h.fsf@x220.int.ebiederm.org> <87r3pae5hn.fsf@x220.int.ebiederm.org> <878uansj4d.fsf_-_@x220.int.ebiederm.org> Mime-Version: 1.0 Content-Type: text/plain Cc: , , Stephen Hemminger , Juanjo Ciarlante , Wensong Zhang , Simon Horman , Julian Anastasov , Patrick McHardy , Jozsef Kadlecsik , Jamal Hadi Salim , Steffen Klassert , Herbert Xu , David Miller To: Pablo Neira Ayuso Return-path: Received: from out01.mta.xmission.com ([166.70.13.231]:55551 "EHLO out01.mta.xmission.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753178AbbGJXUo (ORCPT ); Fri, 10 Jul 2015 19:20:44 -0400 In-Reply-To: <878uansj4d.fsf_-_@x220.int.ebiederm.org> (Eric W. Biederman's message of "Fri, 10 Jul 2015 18:11:46 -0500") Sender: netfilter-devel-owner@vger.kernel.org List-ID: - Add a new set of functions for registering and unregistering per network namespace hooks. - Modify the old global namespace hook functions to use the per network namespace hooks in their implementation, so their remains a single list that needs to be walked for any hook (this is important for keeping the hook priority working and for keeping the code walking the hooks simple). - Only allow registering the per netdevice hooks in the network namespace where the network device lives. - Dynamically allocate the structures in the per network namespace hook list in nf_register_net_hook, and unregister them in nf_unregister_net_hook. Dynamic allocate is required somewhere as the number of network namespaces are not fixed so we might as well allocate them in the registration function. The chain of registered hooks on any list is expected to be small so the cost of walking that list to find the entry we are unregistering should also be small. Performing the management of the dynamically allocated list entries in the registration and unregistration functions keeps the complexity from spreading. Signed-off-by: "Eric W. Biederman" --- include/linux/netfilter.h | 15 +++- include/net/netns/netfilter.h | 1 + net/netfilter/core.c | 184 +++++++++++++++++++++++++++++++++++++----- 3 files changed, 175 insertions(+), 25 deletions(-) diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d7826e59779e..4903e392a6ac 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -11,6 +11,8 @@ #include #include #include +#include +#include #ifdef CONFIG_NETFILTER static inline int NF_DROP_GETERR(int verdict) @@ -118,6 +120,13 @@ struct nf_sockopt_ops { }; /* Function to register/unregister hook points. */ +int nf_register_net_hook(struct net *net, const struct nf_hook_ops *ops); +void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *ops); +int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n); +void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n); + int nf_register_hook(struct nf_hook_ops *reg); void nf_unregister_hook(struct nf_hook_ops *reg); int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); @@ -128,8 +137,6 @@ void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); int nf_register_sockopt(struct nf_sockopt_ops *reg); void nf_unregister_sockopt(struct nf_sockopt_ops *reg); -extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; - #ifdef HAVE_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; @@ -167,10 +174,10 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, int (*okfn)(struct sock *, struct sk_buff *), int thresh) { - struct list_head *nf_hook_list = &nf_hooks[pf][hook]; + struct net *net = dev_net(indev?indev:outdev); + struct list_head *nf_hook_list = &net->nf.hooks[pf][hook]; if (nf_hook_list_active(nf_hook_list, pf, hook)) { struct nf_hook_state state; - nf_hook_state_init(&state, nf_hook_list, hook, thresh, pf, indev, outdev, sk, okfn); return nf_hook_slow(skb, &state); diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 532e4ba64f49..38aa4983e2a9 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -14,5 +14,6 @@ struct netns_nf { #ifdef CONFIG_SYSCTL struct ctl_table_header *nf_log_dir_header; #endif + struct list_head hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; }; #endif diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 8bbcdfcdbfbd..320ae65dc09a 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -52,9 +52,6 @@ void nf_unregister_afinfo(const struct nf_afinfo *afinfo) } EXPORT_SYMBOL_GPL(nf_unregister_afinfo); -struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly; -EXPORT_SYMBOL(nf_hooks); - #ifdef HAVE_JUMP_LABEL struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; EXPORT_SYMBOL(nf_hooks_needed); @@ -62,27 +59,40 @@ EXPORT_SYMBOL(nf_hooks_needed); static DEFINE_MUTEX(nf_hook_mutex); -static struct list_head *find_nf_hook_list(const struct nf_hook_ops *reg) +static struct list_head *find_nf_hook_list(struct net *net, + const struct nf_hook_ops *reg) { struct list_head *nf_hook_list = NULL; if (reg->pf != NFPROTO_NETDEV) - nf_hook_list = &nf_hooks[reg->pf][reg->hooknum]; + nf_hook_list = &net->nf.hooks[reg->pf][reg->hooknum]; else if (reg->hooknum == NF_NETDEV_INGRESS) { #ifdef CONFIG_NETFILTER_INGRESS - if (reg->dev) + if (reg->dev && (dev_net(reg->dev) == net)) nf_hook_list = ®->dev->nf_hooks_ingress; #endif } return nf_hook_list; } -int nf_register_hook(struct nf_hook_ops *reg) +int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) { struct list_head *nf_hook_list; - struct nf_hook_ops *elem; + struct nf_hook_ops *elem, *new; + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return -ENOMEM; + + new->hook = reg->hook; + new->dev = reg->dev; + new->owner = reg->owner; + new->priv = reg->priv; + new->pf = reg->pf; + new->hooknum = reg->hooknum; + new->priority = reg->priority; - nf_hook_list = find_nf_hook_list(reg); + nf_hook_list = find_nf_hook_list(net, reg); if (!nf_hook_list) return -ENOENT; @@ -91,7 +101,7 @@ int nf_register_hook(struct nf_hook_ops *reg) if (reg->priority < elem->priority) break; } - list_add_rcu(®->list, elem->list.prev); + list_add_rcu(&new->list, elem->list.prev); mutex_unlock(&nf_hook_mutex); #ifdef CONFIG_NETFILTER_INGRESS if ((reg->pf == NFPROTO_NETDEV) && (reg->hooknum == NF_NETDEV_INGRESS)) @@ -102,13 +112,35 @@ int nf_register_hook(struct nf_hook_ops *reg) #endif return 0; } -EXPORT_SYMBOL(nf_register_hook); +EXPORT_SYMBOL(nf_register_net_hook); -void nf_unregister_hook(struct nf_hook_ops *reg) +void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) { + struct list_head *nf_hook_list; + struct nf_hook_ops *elem; + + nf_hook_list = find_nf_hook_list(net, reg); + if (!nf_hook_list) + return; + mutex_lock(&nf_hook_mutex); - list_del_rcu(®->list); + list_for_each_entry(elem, nf_hook_list, list) { + if ((reg->hook == elem->hook) && + (reg->dev == elem->dev) && + (reg->owner == elem->owner) && + (reg->priv == elem->priv) && + (reg->pf == elem->pf) && + (reg->hooknum == elem->hooknum) && + (reg->priority == elem->priority)) { + list_del_rcu(&elem->list); + break; + } + } mutex_unlock(&nf_hook_mutex); + if (&elem->list == nf_hook_list) { + WARN(1, "nf_unregister_net_hook: hook not found!\n"); + return; + } #ifdef CONFIG_NETFILTER_INGRESS if ((reg->pf == NFPROTO_NETDEV) && (reg->hooknum == NF_NETDEV_INGRESS)) net_dec_ingress_queue(); @@ -117,7 +149,78 @@ void nf_unregister_hook(struct nf_hook_ops *reg) static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]); #endif synchronize_net(); - nf_queue_nf_hook_drop(reg); + nf_queue_nf_hook_drop(elem); + kfree(elem); +} +EXPORT_SYMBOL(nf_unregister_net_hook); + +int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n) +{ + unsigned int i; + int err = 0; + + for (i = 0; i < n; i++) { + err = nf_register_net_hook(net, ®[i]); + if (err) + goto err; + } + return err; + +err: + if (i > 0) + nf_unregister_net_hooks(net, reg, i); + return err; +} +EXPORT_SYMBOL(nf_register_net_hooks); + +void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n) +{ + while (n-- > 0) + nf_unregister_net_hook(net, ®[n]); +} +EXPORT_SYMBOL(nf_unregister_net_hooks); + +static LIST_HEAD(nf_hook_list); + +int nf_register_hook(struct nf_hook_ops *reg) +{ + struct net *net, *last; + int ret; + + rtnl_lock(); + for_each_net(net) { + ret = nf_register_net_hook(net, reg); + if (ret && ret != -ENOENT) + goto rollback; + } + list_add_tail(®->list, &nf_hook_list); + rtnl_unlock(); + + return 0; +rollback: + last = net; + for_each_net(net) { + if (net == last) + break; + nf_unregister_net_hook(net, reg); + } + rtnl_unlock(); + return ret; +} +EXPORT_SYMBOL(nf_register_hook); + +void nf_unregister_hook(struct nf_hook_ops *reg) +{ + struct net *net; + + rtnl_lock(); + list_del(®->list); + for_each_net(net) { + nf_unregister_net_hook(net, reg); + } + rtnl_unlock(); } EXPORT_SYMBOL(nf_unregister_hook); @@ -294,8 +397,47 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); EXPORT_SYMBOL(nf_nat_decode_session_hook); #endif +static int nf_register_hook_list(struct net *net) +{ + struct nf_hook_ops *elem; + int ret; + + rtnl_lock(); + list_for_each_entry(elem, &nf_hook_list, list) { + ret = nf_register_net_hook(net, elem); + if (ret && ret != -ENOENT) + goto out_undo; + } + rtnl_unlock(); + return 0; + +out_undo: + list_for_each_entry_continue_reverse(elem, &nf_hook_list, list) { + nf_unregister_net_hook(net, elem); + } + rtnl_unlock(); + return ret; +} + +static void nf_unregister_hook_list(struct net *net) +{ + struct nf_hook_ops *elem; + + rtnl_lock(); + list_for_each_entry(elem, &nf_hook_list, list) + nf_unregister_net_hook(net, elem); + rtnl_unlock(); +} + static int __net_init netfilter_net_init(struct net *net) { + int i, h, ret; + + for (i = 0; i < ARRAY_SIZE(net->nf.hooks); i++) { + for (h = 0; h < NF_MAX_HOOKS; h++) + INIT_LIST_HEAD(&net->nf.hooks[i][h]); + } + #ifdef CONFIG_PROC_FS net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter", net->proc_net); @@ -306,11 +448,16 @@ static int __net_init netfilter_net_init(struct net *net) return -ENOMEM; } #endif - return 0; + ret = nf_register_hook_list(net); + if (ret) + remove_proc_entry("netfilter", net->proc_net); + + return ret; } static void __net_exit netfilter_net_exit(struct net *net) { + nf_unregister_hook_list(net); remove_proc_entry("netfilter", net->proc_net); } @@ -321,12 +468,7 @@ static struct pernet_operations netfilter_net_ops = { int __init netfilter_init(void) { - int i, h, ret; - - for (i = 0; i < ARRAY_SIZE(nf_hooks); i++) { - for (h = 0; h < NF_MAX_HOOKS; h++) - INIT_LIST_HEAD(&nf_hooks[i][h]); - } + int ret; ret = register_pernet_subsys(&netfilter_net_ops); if (ret < 0) -- 2.2.1