diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 996711d8a7b4..41d04e9d088a 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -1,7 +1,6 @@ #ifndef _NFNETLINK_H #define _NFNETLINK_H - #include #include #include @@ -10,13 +9,16 @@ struct nfnl_callback { int (*call)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]); + const struct nlattr * const cda[], + struct netlink_ext_ack *extack); int (*call_rcu)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]); + const struct nlattr * const cda[], + struct netlink_ext_ack *extack); int (*call_batch)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]); + const struct nlattr * const cda[], + struct netlink_ext_ack *extack); const struct nla_policy *policy; /* netlink attribute policy */ const u_int16_t attr_count; /* number of nlattr's */ }; diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index e0cbf17af780..2c2a5514b0df 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -122,8 +122,6 @@ extern unsigned int ebt_do_table(struct sk_buff *skb, #define BASE_CHAIN (par->hook_mask & (1 << NF_BR_NUMHOOKS)) /* Clear the bit in the hook mask that tells if the rule is on a base chain */ #define CLEAR_BASE_CHAIN_BIT (par->hook_mask &= ~(1 << NF_BR_NUMHOOKS)) -/* True if the target is not a standard target */ -#define INVALID_TARGET (info->target < -NUM_STANDARD_TARGETS || info->target >= 0) static inline bool ebt_invalid_target(int target) { diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index fe80bb48ab1f..a24a57593202 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -158,6 +158,7 @@ extern struct net init_net; struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net); +void net_ns_barrier(void); #else /* CONFIG_NET_NS */ #include #include @@ -168,6 +169,8 @@ static inline struct net *copy_net_ns(unsigned long flags, return ERR_PTR(-EINVAL); return old_net; } + +static inline void net_ns_barrier(void) {} #endif /* CONFIG_NET_NS */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 8ece3612d0cd..48407569585d 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -225,9 +225,13 @@ extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct, u32 seq); /* Iterate over all conntracks: if iter returns true, it's deleted. */ -void nf_ct_iterate_cleanup(struct net *net, - int (*iter)(struct nf_conn *i, void *data), - void *data, u32 portid, int report); +void nf_ct_iterate_cleanup_net(struct net *net, + int (*iter)(struct nf_conn *i, void *data), + void *data, u32 portid, int report); + +/* also set unconfirmed conntracks as dying. Only use in module exit path. */ +void nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), + void *data); struct nf_conntrack_zone; diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index e01559b4d781..6d14b36e3a49 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -71,7 +71,7 @@ struct nf_conntrack_l3proto { struct module *me; }; -extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX]; +extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[NFPROTO_NUMPROTO]; #ifdef CONFIG_SYSCTL /* Protocol pernet registration. */ @@ -100,7 +100,7 @@ extern struct nf_conntrack_l3proto nf_conntrack_l3proto_generic; static inline struct nf_conntrack_l3proto * __nf_ct_l3proto_find(u_int16_t l3proto) { - if (unlikely(l3proto >= AF_MAX)) + if (unlikely(l3proto >= NFPROTO_NUMPROTO)) return &nf_conntrack_l3proto_generic; return rcu_dereference(nf_ct_l3protos[l3proto]); } diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 8a8bab8d7b15..bd5be0d691d5 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -281,6 +281,23 @@ struct nft_set_estimate { enum nft_set_class space; }; +/** + * struct nft_set_type - nf_tables set type + * + * @select_ops: function to select nft_set_ops + * @ops: default ops, used when no select_ops functions is present + * @list: used internally + * @owner: module reference + */ +struct nft_set_type { + const struct nft_set_ops *(*select_ops)(const struct nft_ctx *, + const struct nft_set_desc *desc, + u32 flags); + const struct nft_set_ops *ops; + struct list_head list; + struct module *owner; +}; + struct nft_set_ext; struct nft_expr; @@ -297,8 +314,6 @@ struct nft_expr; * @privsize: function to return size of set private data * @init: initialize private data of new set instance * @destroy: destroy private data of set instance - * @list: nf_tables_set_ops list node - * @owner: module reference * @elemsize: element private size * @features: features supported by the implementation */ @@ -336,7 +351,8 @@ struct nft_set_ops { struct nft_set *set, struct nft_set_iter *iter); - unsigned int (*privsize)(const struct nlattr * const nla[]); + unsigned int (*privsize)(const struct nlattr * const nla[], + const struct nft_set_desc *desc); bool (*estimate)(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est); @@ -345,14 +361,13 @@ struct nft_set_ops { const struct nlattr * const nla[]); void (*destroy)(const struct nft_set *set); - struct list_head list; - struct module *owner; unsigned int elemsize; u32 features; + const struct nft_set_type *type; }; -int nft_register_set(struct nft_set_ops *ops); -void nft_unregister_set(struct nft_set_ops *ops); +int nft_register_set(struct nft_set_type *type); +void nft_unregister_set(struct nft_set_type *type); /** * struct nft_set - nf_tables set instance diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index e0bb624c3845..dfc86a0199da 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -61,7 +61,7 @@ static int ebt_dnat_tg_check(const struct xt_tgchk_param *par) (strcmp(par->table, "broute") != 0 || hook_mask & ~(1 << NF_BR_BROUTING))) return -EINVAL; - if (INVALID_TARGET) + if (ebt_invalid_target(info->target)) return -EINVAL; return 0; } diff --git a/net/bridge/netfilter/ebt_mark.c b/net/bridge/netfilter/ebt_mark.c index 66697cbd0a8b..19f0f9592d32 100644 --- a/net/bridge/netfilter/ebt_mark.c +++ b/net/bridge/netfilter/ebt_mark.c @@ -44,7 +44,7 @@ static int ebt_mark_tg_check(const struct xt_tgchk_param *par) tmp = info->target | ~EBT_VERDICT_BITS; if (BASE_CHAIN && tmp == EBT_RETURN) return -EINVAL; - if (tmp < -NUM_STANDARD_TARGETS || tmp >= 0) + if (ebt_invalid_target(tmp)) return -EINVAL; tmp = info->target & ~EBT_VERDICT_BITS; if (tmp != MARK_SET_VALUE && tmp != MARK_OR_VALUE && diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 8d2a85e0594e..a7223eaf490b 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -47,7 +47,7 @@ static int ebt_redirect_tg_check(const struct xt_tgchk_param *par) (strcmp(par->table, "broute") != 0 || hook_mask & ~(1 << NF_BR_BROUTING))) return -EINVAL; - if (INVALID_TARGET) + if (ebt_invalid_target(info->target)) return -EINVAL; return 0; } diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index e56ccd060d26..11cf9e9e9222 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -51,7 +51,7 @@ static int ebt_snat_tg_check(const struct xt_tgchk_param *par) if (BASE_CHAIN && tmp == EBT_RETURN) return -EINVAL; - if (tmp < -NUM_STANDARD_TARGETS || tmp >= 0) + if (ebt_invalid_target(tmp)) return -EINVAL; tmp = info->target | EBT_VERDICT_BITS; if ((tmp & ~NAT_ARP_BIT) != ~NAT_ARP_BIT) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 2178db8e47cd..6a2f41288249 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -501,6 +501,23 @@ static void cleanup_net(struct work_struct *work) net_drop_ns(net); } } + +/** + * net_ns_barrier - wait until concurrent net_cleanup_work is done + * + * cleanup_net runs from work queue and will first remove namespaces + * from the global list, then run net exit functions. + * + * Call this in module exit path to make sure that all netns + * ->exit ops have been invoked before the function is removed. + */ +void net_ns_barrier(void) +{ + mutex_lock(&net_mutex); + mutex_unlock(&net_mutex); +} +EXPORT_SYMBOL(net_ns_barrier); + static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 038f293c2376..7d72decb80f9 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -47,7 +47,7 @@ struct clusterip_config { __be32 clusterip; /* the IP address */ u_int8_t clustermac[ETH_ALEN]; /* the MAC address */ - struct net_device *dev; /* device */ + int ifindex; /* device ifindex */ u_int16_t num_total_nodes; /* total number of nodes */ unsigned long local_nodes; /* node number array */ @@ -57,6 +57,9 @@ struct clusterip_config { enum clusterip_hashmode hash_mode; /* which hashing mode */ u_int32_t hash_initval; /* hash initialization */ struct rcu_head rcu; + + char ifname[IFNAMSIZ]; /* device ifname */ + struct notifier_block notifier; /* refresh c->ifindex in it */ }; #ifdef CONFIG_PROC_FS @@ -98,9 +101,8 @@ clusterip_config_put(struct clusterip_config *c) * entry(rule) is removed, remove the config from lists, but don't free it * yet, since proc-files could still be holding references */ static inline void -clusterip_config_entry_put(struct clusterip_config *c) +clusterip_config_entry_put(struct net *net, struct clusterip_config *c) { - struct net *net = dev_net(c->dev); struct clusterip_net *cn = net_generic(net, clusterip_net_id); local_bh_disable(); @@ -109,8 +111,7 @@ clusterip_config_entry_put(struct clusterip_config *c) spin_unlock(&cn->lock); local_bh_enable(); - dev_mc_del(c->dev, c->clustermac); - dev_put(c->dev); + unregister_netdevice_notifier(&c->notifier); /* In case anyone still accesses the file, the open/close * functions are also incrementing the refcount on their own, @@ -170,19 +171,55 @@ clusterip_config_init_nodelist(struct clusterip_config *c, set_bit(i->local_nodes[n] - 1, &c->local_nodes); } -static struct clusterip_config * -clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, - struct net_device *dev) +static int +clusterip_netdev_event(struct notifier_block *this, unsigned long event, + void *ptr) { - struct net *net = dev_net(dev); + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct clusterip_config *c; + + c = container_of(this, struct clusterip_config, notifier); + switch (event) { + case NETDEV_REGISTER: + if (!strcmp(dev->name, c->ifname)) { + c->ifindex = dev->ifindex; + dev_mc_add(dev, c->clustermac); + } + break; + case NETDEV_UNREGISTER: + if (dev->ifindex == c->ifindex) { + dev_mc_del(dev, c->clustermac); + c->ifindex = -1; + } + break; + case NETDEV_CHANGENAME: + if (!strcmp(dev->name, c->ifname)) { + c->ifindex = dev->ifindex; + dev_mc_add(dev, c->clustermac); + } else if (dev->ifindex == c->ifindex) { + dev_mc_del(dev, c->clustermac); + c->ifindex = -1; + } + break; + } + + return NOTIFY_DONE; +} + +static struct clusterip_config * +clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, + __be32 ip, const char *iniface) +{ struct clusterip_net *cn = net_generic(net, clusterip_net_id); + struct clusterip_config *c; + int err; c = kzalloc(sizeof(*c), GFP_ATOMIC); if (!c) return ERR_PTR(-ENOMEM); - c->dev = dev; + strcpy(c->ifname, iniface); + c->ifindex = -1; c->clusterip = ip; memcpy(&c->clustermac, &i->clustermac, ETH_ALEN); c->num_total_nodes = i->num_total_nodes; @@ -213,17 +250,27 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, cn->procdir, &clusterip_proc_fops, c); if (!c->pde) { - spin_lock_bh(&cn->lock); - list_del_rcu(&c->list); - spin_unlock_bh(&cn->lock); - kfree(c); - - return ERR_PTR(-ENOMEM); + err = -ENOMEM; + goto err; } } #endif - return c; + c->notifier.notifier_call = clusterip_netdev_event; + err = register_netdevice_notifier(&c->notifier); + if (!err) + return c; + +#ifdef CONFIG_PROC_FS + proc_remove(c->pde); +err: +#endif + spin_lock_bh(&cn->lock); + list_del_rcu(&c->list); + spin_unlock_bh(&cn->lock); + kfree(c); + + return ERR_PTR(err); } #ifdef CONFIG_PROC_FS @@ -425,14 +472,13 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) e->ip.iniface); return -ENOENT; } + dev_put(dev); - config = clusterip_config_init(cipinfo, - e->ip.dst.s_addr, dev); - if (IS_ERR(config)) { - dev_put(dev); + config = clusterip_config_init(par->net, cipinfo, + e->ip.dst.s_addr, + e->ip.iniface); + if (IS_ERR(config)) return PTR_ERR(config); - } - dev_mc_add(config->dev, config->clustermac); } } cipinfo->config = config; @@ -458,7 +504,7 @@ static void clusterip_tg_destroy(const struct xt_tgdtor_param *par) /* if no more entries are referencing the config, remove it * from the list and destroy the proc entry */ - clusterip_config_entry_put(cipinfo->config); + clusterip_config_entry_put(par->net, cipinfo->config); clusterip_config_put(cipinfo->config); @@ -558,10 +604,9 @@ arp_mangle(void *priv, * addresses on different interfacs. However, in the CLUSTERIP case * this wouldn't work, since we didn't subscribe the mcast group on * other interfaces */ - if (c->dev != state->out) { - pr_debug("not mangling arp reply on different " - "interface: cip'%s'-skb'%s'\n", - c->dev->name, state->out->name); + if (c->ifindex != state->out->ifindex) { + pr_debug("not mangling arp reply on different interface: cip'%d'-skb'%d'\n", + c->ifindex, state->out->ifindex); clusterip_config_put(c); return NF_ACCEPT; } @@ -743,14 +788,20 @@ static const struct file_operations clusterip_proc_fops = { static int clusterip_net_init(struct net *net) { struct clusterip_net *cn = net_generic(net, clusterip_net_id); + int ret; INIT_LIST_HEAD(&cn->configs); spin_lock_init(&cn->lock); + ret = nf_register_net_hook(net, &cip_arp_ops); + if (ret < 0) + return ret; + #ifdef CONFIG_PROC_FS cn->procdir = proc_mkdir("ipt_CLUSTERIP", net->proc_net); if (!cn->procdir) { + nf_unregister_net_hook(net, &cip_arp_ops); pr_err("Unable to proc dir entry\n"); return -ENOMEM; } @@ -765,6 +816,7 @@ static void clusterip_net_exit(struct net *net) struct clusterip_net *cn = net_generic(net, clusterip_net_id); proc_remove(cn->procdir); #endif + nf_unregister_net_hook(net, &cip_arp_ops); } static struct pernet_operations clusterip_net_ops = { @@ -786,17 +838,11 @@ static int __init clusterip_tg_init(void) if (ret < 0) goto cleanup_subsys; - ret = nf_register_hook(&cip_arp_ops); - if (ret < 0) - goto cleanup_target; - pr_info("ClusterIP Version %s loaded successfully\n", CLUSTERIP_VERSION); return 0; -cleanup_target: - xt_unregister_target(&clusterip_tg_reg); cleanup_subsys: unregister_pernet_subsys(&clusterip_net_ops); return ret; @@ -806,7 +852,6 @@ static void __exit clusterip_tg_exit(void) { pr_info("ClusterIP Version %s unloading\n", CLUSTERIP_VERSION); - nf_unregister_hook(&cip_arp_ops); xt_unregister_target(&clusterip_tg_reg); unregister_pernet_subsys(&clusterip_net_ops); diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index dc1dea15c1b4..f39037fca923 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -98,8 +98,8 @@ static int masq_device_event(struct notifier_block *this, */ NF_CT_ASSERT(dev->ifindex != 0); - nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_ct_iterate_cleanup_net(net, device_cmp, + (void *)(long)dev->ifindex, 0, 0); } return NOTIFY_DONE; diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 2297c9f073ba..d7b679037bae 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -75,8 +75,8 @@ static int masq_device_event(struct notifier_block *this, struct net *net = dev_net(dev); if (event == NETDEV_DOWN) - nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_ct_iterate_cleanup_net(net, device_cmp, + (void *)(long)dev->ifindex, 0, 0); return NOTIFY_DONE; } @@ -99,7 +99,7 @@ static void iterate_cleanup_work(struct work_struct *work) w = container_of(work, struct masq_dev_work, work); index = w->ifindex; - nf_ct_iterate_cleanup(w->net, device_cmp, (void *)index, 0, 0); + nf_ct_iterate_cleanup_net(w->net, device_cmp, (void *)index, 0, 0); put_net(w->net); kfree(w); @@ -110,12 +110,12 @@ static void iterate_cleanup_work(struct work_struct *work) /* ipv6 inet notifier is an atomic notifier, i.e. we cannot * schedule. * - * Unfortunately, nf_ct_iterate_cleanup can run for a long + * Unfortunately, nf_ct_iterate_cleanup_net can run for a long * time if there are lots of conntracks and the system * handles high softirq load, so it frequently calls cond_resched * while iterating the conntrack table. * - * So we defer nf_ct_iterate_cleanup walk to the system workqueue. + * So we defer nf_ct_iterate_cleanup_net walk to the system workqueue. * * As we can have 'a lot' of inet_events (depending on amount * of ipv6 addresses being deleted), we also need to add an upper diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index c9b78e7b342f..913380919301 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -70,10 +70,9 @@ obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o obj-$(CONFIG_NF_DUP_NETDEV) += nf_dup_netdev.o # nf_tables -nf_tables-objs += nf_tables_core.o nf_tables_api.o nf_tables_trace.o -nf_tables-objs += nft_immediate.o nft_cmp.o nft_range.o -nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o -nf_tables-objs += nft_lookup.o nft_dynset.o +nf_tables-objs := nf_tables_core.o nf_tables_api.o nf_tables_trace.o \ + nft_immediate.o nft_cmp.o nft_range.o nft_bitwise.o \ + nft_byteorder.o nft_payload.o nft_lookup.o nft_dynset.o obj-$(CONFIG_NF_TABLES) += nf_tables.o obj-$(CONFIG_NF_TABLES_INET) += nf_tables_inet.o diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index ba6a5516dc7c..e495b5e484b1 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -841,14 +841,16 @@ find_free_id(struct ip_set_net *inst, const char *name, ip_set_id_t *index, static int ip_set_none(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } static int ip_set_create(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *set, *clash = NULL; @@ -989,7 +991,8 @@ ip_set_destroy_set(struct ip_set *set) static int ip_set_destroy(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *s; @@ -1067,7 +1070,8 @@ ip_set_flush_set(struct ip_set *set) static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *s; @@ -1106,7 +1110,8 @@ ip_set_setname2_policy[IPSET_ATTR_CMD_MAX + 1] = { static int ip_set_rename(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *set, *s; @@ -1155,7 +1160,8 @@ out: static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *from, *to; @@ -1428,7 +1434,8 @@ out: static int ip_set_dump(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { if (unlikely(protocol_failed(attr))) return -IPSET_ERR_PROTOCOL; @@ -1513,7 +1520,8 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, static int ip_set_uadd(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *set; @@ -1567,7 +1575,8 @@ static int ip_set_uadd(struct net *net, struct sock *ctnl, struct sk_buff *skb, static int ip_set_udel(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *set; @@ -1621,7 +1630,8 @@ static int ip_set_udel(struct net *net, struct sock *ctnl, struct sk_buff *skb, static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *set; @@ -1656,7 +1666,8 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, static int ip_set_header(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct ip_set_net *inst = ip_set_pernet(net); const struct ip_set *set; @@ -1712,7 +1723,8 @@ static const struct nla_policy ip_set_type_policy[IPSET_ATTR_CMD_MAX + 1] = { static int ip_set_type(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct sk_buff *skb2; struct nlmsghdr *nlh2; @@ -1770,7 +1782,8 @@ ip_set_protocol_policy[IPSET_ATTR_CMD_MAX + 1] = { static int ip_set_protocol(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[]) + const struct nlattr * const attr[], + struct netlink_ext_ack *extack) { struct sk_buff *skb2; struct nlmsghdr *nlh2; diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index 03d2ccffa9fa..20edd589fe06 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -197,8 +197,8 @@ static void __exit nf_conntrack_amanda_fini(void) { int i; - nf_conntrack_helper_unregister(&amanda_helper[0]); - nf_conntrack_helper_unregister(&amanda_helper[1]); + nf_conntrack_helpers_unregister(amanda_helper, + ARRAY_SIZE(amanda_helper)); for (i = 0; i < ARRAY_SIZE(search); i++) textsearch_destroy(search[i].ts); } @@ -218,16 +218,12 @@ static int __init nf_conntrack_amanda_init(void) goto err1; } } - ret = nf_conntrack_helper_register(&amanda_helper[0]); + ret = nf_conntrack_helpers_register(amanda_helper, + ARRAY_SIZE(amanda_helper)); if (ret < 0) goto err1; - ret = nf_conntrack_helper_register(&amanda_helper[1]); - if (ret < 0) - goto err2; return 0; -err2: - nf_conntrack_helper_unregister(&amanda_helper[0]); err1: while (--i >= 0) textsearch_destroy(search[i].ts); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e847dbaa0c6b..9979f46c81dc 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1586,13 +1586,12 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) /* Bring out ya dead! */ static struct nf_conn * -get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), +get_next_corpse(int (*iter)(struct nf_conn *i, void *data), void *data, unsigned int *bucket) { struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct hlist_nulls_node *n; - int cpu; spinlock_t *lockp; for (; *bucket < nf_conntrack_htable_size; (*bucket)++) { @@ -1604,8 +1603,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; ct = nf_ct_tuplehash_to_ctrack(h); - if (net_eq(nf_ct_net(ct), net) && - iter(ct, data)) + if (iter(ct, data)) goto found; } } @@ -1614,18 +1612,6 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), cond_resched(); } - for_each_possible_cpu(cpu) { - struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); - - spin_lock_bh(&pcpu->lock); - hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) { - ct = nf_ct_tuplehash_to_ctrack(h); - if (iter(ct, data)) - set_bit(IPS_DYING_BIT, &ct->status); - } - spin_unlock_bh(&pcpu->lock); - cond_resched(); - } return NULL; found: atomic_inc(&ct->ct_general.use); @@ -1634,31 +1620,142 @@ found: return ct; } -void nf_ct_iterate_cleanup(struct net *net, - int (*iter)(struct nf_conn *i, void *data), - void *data, u32 portid, int report) +static void nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data), + void *data, u32 portid, int report) { + unsigned int bucket = 0, sequence; struct nf_conn *ct; - unsigned int bucket = 0; + + might_sleep(); + + for (;;) { + sequence = read_seqcount_begin(&nf_conntrack_generation); + + while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { + /* Time to push up daises... */ + + nf_ct_delete(ct, portid, report); + nf_ct_put(ct); + cond_resched(); + } + + if (!read_seqcount_retry(&nf_conntrack_generation, sequence)) + break; + bucket = 0; + } +} + +struct iter_data { + int (*iter)(struct nf_conn *i, void *data); + void *data; + struct net *net; +}; + +static int iter_net_only(struct nf_conn *i, void *data) +{ + struct iter_data *d = data; + + if (!net_eq(d->net, nf_ct_net(i))) + return 0; + + return d->iter(i, d->data); +} + +static void +__nf_ct_unconfirmed_destroy(struct net *net) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; + struct ct_pcpu *pcpu; + + pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + + spin_lock_bh(&pcpu->lock); + hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) { + struct nf_conn *ct; + + ct = nf_ct_tuplehash_to_ctrack(h); + + /* we cannot call iter() on unconfirmed list, the + * owning cpu can reallocate ct->ext at any time. + */ + set_bit(IPS_DYING_BIT, &ct->status); + } + spin_unlock_bh(&pcpu->lock); + cond_resched(); + } +} + +void nf_ct_iterate_cleanup_net(struct net *net, + int (*iter)(struct nf_conn *i, void *data), + void *data, u32 portid, int report) +{ + struct iter_data d; might_sleep(); if (atomic_read(&net->ct.count) == 0) return; - while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) { - /* Time to push up daises... */ + __nf_ct_unconfirmed_destroy(net); - nf_ct_delete(ct, portid, report); - nf_ct_put(ct); - cond_resched(); - } + d.iter = iter; + d.data = data; + d.net = net; + + synchronize_net(); + + nf_ct_iterate_cleanup(iter_net_only, &d, portid, report); } -EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup); +EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup_net); + +/** + * nf_ct_iterate_destroy - destroy unconfirmed conntracks and iterate table + * @iter: callback to invoke for each conntrack + * @data: data to pass to @iter + * + * Like nf_ct_iterate_cleanup, but first marks conntracks on the + * unconfirmed list as dying (so they will not be inserted into + * main table). + * + * Can only be called in module exit path. + */ +void +nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data) +{ + struct net *net; + + rtnl_lock(); + for_each_net(net) { + if (atomic_read(&net->ct.count) == 0) + continue; + __nf_ct_unconfirmed_destroy(net); + } + rtnl_unlock(); + + /* Need to wait for netns cleanup worker to finish, if its + * running -- it might have deleted a net namespace from + * the global list, so our __nf_ct_unconfirmed_destroy() might + * not have affected all namespaces. + */ + net_ns_barrier(); + + /* a conntrack could have been unlinked from unconfirmed list + * before we grabbed pcpu lock in __nf_ct_unconfirmed_destroy(). + * This makes sure its inserted into conntrack table. + */ + synchronize_net(); + + nf_ct_iterate_cleanup(iter, data, 0, 0); +} +EXPORT_SYMBOL_GPL(nf_ct_iterate_destroy); static int kill_all(struct nf_conn *i, void *data) { - return 1; + return net_eq(nf_ct_net(i), data); } void nf_ct_free_hashtable(void *hash, unsigned int size) @@ -1723,7 +1820,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list) i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { - nf_ct_iterate_cleanup(net, kill_all, NULL, 0, 0); + nf_ct_iterate_cleanup(kill_all, net, 0, 0); if (atomic_read(&net->ct.count) != 0) busy = 1; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 3bcdc718484e..f71f0d2558fd 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1815,14 +1815,44 @@ static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = { }, }; +static int __init h323_helper_init(void) +{ + int ret; + + ret = nf_conntrack_helper_register(&nf_conntrack_helper_h245); + if (ret < 0) + return ret; + ret = nf_conntrack_helpers_register(nf_conntrack_helper_q931, + ARRAY_SIZE(nf_conntrack_helper_q931)); + if (ret < 0) + goto err1; + ret = nf_conntrack_helpers_register(nf_conntrack_helper_ras, + ARRAY_SIZE(nf_conntrack_helper_ras)); + if (ret < 0) + goto err2; + + return 0; +err2: + nf_conntrack_helpers_unregister(nf_conntrack_helper_q931, + ARRAY_SIZE(nf_conntrack_helper_q931)); +err1: + nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); + return ret; +} + +static void __exit h323_helper_exit(void) +{ + nf_conntrack_helpers_unregister(nf_conntrack_helper_ras, + ARRAY_SIZE(nf_conntrack_helper_ras)); + nf_conntrack_helpers_unregister(nf_conntrack_helper_q931, + ARRAY_SIZE(nf_conntrack_helper_q931)); + nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); +} + /****************************************************************************/ static void __exit nf_conntrack_h323_fini(void) { - nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[1]); - nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[0]); - nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[1]); - nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[0]); - nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); + h323_helper_exit(); kfree(h323_buffer); pr_debug("nf_ct_h323: fini\n"); } @@ -1837,32 +1867,11 @@ static int __init nf_conntrack_h323_init(void) h323_buffer = kmalloc(65536, GFP_KERNEL); if (!h323_buffer) return -ENOMEM; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_h245); + ret = h323_helper_init(); if (ret < 0) goto err1; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[0]); - if (ret < 0) - goto err2; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[1]); - if (ret < 0) - goto err3; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[0]); - if (ret < 0) - goto err4; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[1]); - if (ret < 0) - goto err5; pr_debug("nf_ct_h323: init success\n"); return 0; - -err5: - nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[0]); -err4: - nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[1]); -err3: - nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[0]); -err2: - nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); err1: kfree(h323_buffer); return ret; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 7f6100ca63be..9129bb3b5153 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -285,16 +285,16 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); /* appropriate ct lock protecting must be taken by caller */ -static inline int unhelp(struct nf_conntrack_tuple_hash *i, - const struct nf_conntrack_helper *me) +static int unhelp(struct nf_conn *ct, void *me) { - struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i); struct nf_conn_help *help = nfct_help(ct); if (help && rcu_dereference_raw(help->helper) == me) { nf_conntrack_event(IPCT_HELPER, ct); RCU_INIT_POINTER(help->helper, NULL); } + + /* We are not intended to delete this conntrack. */ return 0; } @@ -437,33 +437,10 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_helper_register); -static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, - struct net *net) -{ - struct nf_conntrack_tuple_hash *h; - const struct hlist_nulls_node *nn; - int cpu; - - /* Get rid of expecteds, set helpers to NULL. */ - for_each_possible_cpu(cpu) { - struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); - - spin_lock_bh(&pcpu->lock); - hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode) - unhelp(h, me); - spin_unlock_bh(&pcpu->lock); - } -} - void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) { - struct nf_conntrack_tuple_hash *h; struct nf_conntrack_expect *exp; const struct hlist_node *next; - const struct hlist_nulls_node *nn; - unsigned int last_hsize; - spinlock_t *lock; - struct net *net; unsigned int i; mutex_lock(&nf_ct_helper_mutex); @@ -491,26 +468,7 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) } spin_unlock_bh(&nf_conntrack_expect_lock); - rtnl_lock(); - for_each_net(net) - __nf_conntrack_helper_unregister(me, net); - rtnl_unlock(); - - local_bh_disable(); -restart: - last_hsize = nf_conntrack_htable_size; - for (i = 0; i < last_hsize; i++) { - lock = &nf_conntrack_locks[i % CONNTRACK_LOCKS]; - nf_conntrack_lock(lock); - if (last_hsize != nf_conntrack_htable_size) { - spin_unlock(lock); - goto restart; - } - hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) - unhelp(h, me); - spin_unlock(lock); - } - local_bh_enable(); + nf_ct_iterate_destroy(unhelp, me); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index a8be9b72e6cd..7999e70c3bfb 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -636,11 +636,11 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) if (events & (1 << IPCT_DESTROY)) { type = IPCTNL_MSG_CT_DELETE; group = NFNLGRP_CONNTRACK_DESTROY; - } else if (events & ((1 << IPCT_NEW) | (1 << IPCT_RELATED))) { + } else if (events & ((1 << IPCT_NEW) | (1 << IPCT_RELATED))) { type = IPCTNL_MSG_CT_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; group = NFNLGRP_CONNTRACK_NEW; - } else if (events) { + } else if (events) { type = IPCTNL_MSG_CT_NEW; group = NFNLGRP_CONNTRACK_UPDATE; } else @@ -1122,8 +1122,8 @@ static int ctnetlink_flush_conntrack(struct net *net, return PTR_ERR(filter); } - nf_ct_iterate_cleanup(net, ctnetlink_filter_match, filter, - portid, report); + nf_ct_iterate_cleanup_net(net, ctnetlink_filter_match, filter, + portid, report); kfree(filter); return 0; @@ -1132,7 +1132,8 @@ static int ctnetlink_flush_conntrack(struct net *net, static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; @@ -1184,7 +1185,8 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; @@ -1345,7 +1347,8 @@ ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb) static int ctnetlink_get_ct_dying(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -1367,7 +1370,8 @@ ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb) static int ctnetlink_get_ct_unconfirmed(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -1906,7 +1910,8 @@ err1: static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; @@ -2071,7 +2076,8 @@ ctnetlink_ct_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) static int ctnetlink_stat_ct_cpu(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -2116,7 +2122,8 @@ nlmsg_failure: static int ctnetlink_stat_ct(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct sk_buff *skb2; int err; @@ -2778,7 +2785,8 @@ out: static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { int err; struct nfgenmsg *nfmsg = nlmsg_data(nlh); @@ -2822,7 +2830,8 @@ static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; @@ -2834,7 +2843,8 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, if (nlh->nlmsg_flags & NLM_F_DUMP) { if (cda[CTA_EXPECT_MASTER]) - return ctnetlink_dump_exp_ct(net, ctnl, skb, nlh, cda); + return ctnetlink_dump_exp_ct(net, ctnl, skb, nlh, cda, + extack); else { struct netlink_dump_control c = { .dump = ctnetlink_exp_dump_table, @@ -2902,7 +2912,8 @@ out: static int ctnetlink_del_expect(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; @@ -3190,7 +3201,8 @@ err_ct: static int ctnetlink_new_expect(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; @@ -3296,7 +3308,8 @@ ctnetlink_exp_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) static int ctnetlink_stat_exp_cpu(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 2de6c1fe3261..1dcad229c3cc 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -28,8 +28,8 @@ #include #include -static struct nf_conntrack_l4proto __rcu **nf_ct_protos[PF_MAX] __read_mostly; -struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX] __read_mostly; +static struct nf_conntrack_l4proto __rcu **nf_ct_protos[NFPROTO_NUMPROTO] __read_mostly; +struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[NFPROTO_NUMPROTO] __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_l3protos); static DEFINE_MUTEX(nf_ct_proto_mutex); @@ -68,7 +68,7 @@ nf_ct_unregister_sysctl(struct ctl_table_header **header, struct nf_conntrack_l4proto * __nf_ct_l4proto_find(u_int16_t l3proto, u_int8_t l4proto) { - if (unlikely(l3proto >= AF_MAX || nf_ct_protos[l3proto] == NULL)) + if (unlikely(l3proto >= NFPROTO_NUMPROTO || nf_ct_protos[l3proto] == NULL)) return &nf_conntrack_l4proto_generic; return rcu_dereference(nf_ct_protos[l3proto][l4proto]); @@ -212,7 +212,7 @@ int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto) int ret = 0; struct nf_conntrack_l3proto *old; - if (proto->l3proto >= AF_MAX) + if (proto->l3proto >= NFPROTO_NUMPROTO) return -EBUSY; if (proto->tuple_to_nlattr && !proto->nlattr_tuple_size) @@ -254,7 +254,7 @@ EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_register); void nf_ct_l3proto_unregister(struct nf_conntrack_l3proto *proto) { - BUG_ON(proto->l3proto >= AF_MAX); + BUG_ON(proto->l3proto >= NFPROTO_NUMPROTO); mutex_lock(&nf_ct_proto_mutex); BUG_ON(rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], @@ -265,6 +265,8 @@ void nf_ct_l3proto_unregister(struct nf_conntrack_l3proto *proto) mutex_unlock(&nf_ct_proto_mutex); synchronize_rcu(); + /* Remove all contrack entries for this protocol */ + nf_ct_iterate_destroy(kill_l3proto, proto); } EXPORT_SYMBOL_GPL(nf_ct_l3proto_unregister); @@ -280,9 +282,6 @@ void nf_ct_l3proto_pernet_unregister(struct net *net, */ if (proto->net_ns_put) proto->net_ns_put(net); - - /* Remove all contrack entries for this protocol */ - nf_ct_iterate_cleanup(net, kill_l3proto, proto, 0, 0); } EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_unregister); @@ -342,7 +341,7 @@ int nf_ct_l4proto_register_one(struct nf_conntrack_l4proto *l4proto) { int ret = 0; - if (l4proto->l3proto >= PF_MAX) + if (l4proto->l3proto >= ARRAY_SIZE(nf_ct_protos)) return -EBUSY; if ((l4proto->to_nlattr && !l4proto->nlattr_size) || @@ -421,17 +420,23 @@ out: } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register_one); -void nf_ct_l4proto_unregister_one(struct nf_conntrack_l4proto *l4proto) -{ - BUG_ON(l4proto->l3proto >= PF_MAX); +static void __nf_ct_l4proto_unregister_one(struct nf_conntrack_l4proto *l4proto) + +{ + BUG_ON(l4proto->l3proto >= ARRAY_SIZE(nf_ct_protos)); - mutex_lock(&nf_ct_proto_mutex); BUG_ON(rcu_dereference_protected( nf_ct_protos[l4proto->l3proto][l4proto->l4proto], lockdep_is_held(&nf_ct_proto_mutex) ) != l4proto); rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto], &nf_conntrack_l4proto_generic); +} + +void nf_ct_l4proto_unregister_one(struct nf_conntrack_l4proto *l4proto) +{ + mutex_lock(&nf_ct_proto_mutex); + __nf_ct_l4proto_unregister_one(l4proto); mutex_unlock(&nf_ct_proto_mutex); synchronize_rcu(); @@ -448,9 +453,6 @@ void nf_ct_l4proto_pernet_unregister_one(struct net *net, pn->users--; nf_ct_l4proto_unregister_sysctl(net, pn, l4proto); - - /* Remove all contrack entries for this protocol */ - nf_ct_iterate_cleanup(net, kill_l4proto, l4proto, 0, 0); } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister_one); @@ -500,8 +502,14 @@ EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register); void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *l4proto[], unsigned int num_proto) { + mutex_lock(&nf_ct_proto_mutex); while (num_proto-- != 0) - nf_ct_l4proto_unregister_one(l4proto[num_proto]); + __nf_ct_l4proto_unregister_one(l4proto[num_proto]); + mutex_unlock(&nf_ct_proto_mutex); + + synchronize_net(); + /* Remove all contrack entries for this protocol */ + nf_ct_iterate_destroy(kill_l4proto, l4proto); } EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister); @@ -548,7 +556,7 @@ void nf_conntrack_proto_pernet_fini(struct net *net) int nf_conntrack_proto_init(void) { unsigned int i; - for (i = 0; i < AF_MAX; i++) + for (i = 0; i < NFPROTO_NUMPROTO; i++) rcu_assign_pointer(nf_ct_l3protos[i], &nf_conntrack_l3proto_generic); return 0; @@ -558,6 +566,6 @@ void nf_conntrack_proto_fini(void) { unsigned int i; /* free l3proto protocol tables */ - for (i = 0; i < PF_MAX; i++) + for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++) kfree(nf_ct_protos[i]); } diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index c9d7f95768ab..f4a566e67213 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -13,6 +13,7 @@ #include #include #include +#include static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev) { diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 6c72922d20ca..832c5a08d9a5 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -582,12 +582,8 @@ static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) .l3proto = l3proto, .l4proto = l4proto, }; - struct net *net; - rtnl_lock(); - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0); - rtnl_unlock(); + nf_ct_iterate_destroy(nf_nat_proto_remove, &clean); } static void nf_nat_l3proto_clean(u8 l3proto) @@ -595,13 +591,8 @@ static void nf_nat_l3proto_clean(u8 l3proto) struct nf_nat_proto_clean clean = { .l3proto = l3proto, }; - struct net *net; - rtnl_lock(); - - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0); - rtnl_unlock(); + nf_ct_iterate_destroy(nf_nat_proto_remove, &clean); } /* Protocol registration. */ @@ -822,17 +813,6 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, } #endif -static void __net_exit nf_nat_net_exit(struct net *net) -{ - struct nf_nat_proto_clean clean = {}; - - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean, 0, 0); -} - -static struct pernet_operations nf_nat_net_ops = { - .exit = nf_nat_net_exit, -}; - static struct nf_ct_helper_expectfn follow_master_nat = { .name = "nat-follow-master", .expectfn = nf_nat_follow_master, @@ -853,10 +833,6 @@ static int __init nf_nat_init(void) return ret; } - ret = register_pernet_subsys(&nf_nat_net_ops); - if (ret < 0) - goto cleanup_extend; - nf_ct_helper_expectfn_register(&follow_master_nat); BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); @@ -867,18 +843,15 @@ static int __init nf_nat_init(void) RCU_INIT_POINTER(nf_nat_decode_session_hook, __nf_nat_decode_session); #endif return 0; - - cleanup_extend: - rhltable_destroy(&nf_nat_bysource_table); - nf_ct_extend_unregister(&nat_extend); - return ret; } static void __exit nf_nat_cleanup(void) { + struct nf_nat_proto_clean clean = {}; unsigned int i; - unregister_pernet_subsys(&nf_nat_net_ops); + nf_ct_iterate_destroy(nf_nat_proto_clean, &clean); + nf_ct_extend_unregister(&nat_extend); nf_ct_helper_expectfn_unregister(&follow_master_nat); RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index da314be0c048..7843efa33c59 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -386,7 +387,7 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table) return ++table->hgenerator; } -static const struct nf_chain_type *chain_type[AF_MAX][NFT_CHAIN_T_MAX]; +static const struct nf_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX]; static const struct nf_chain_type * __nf_tables_chain_type_lookup(int family, const struct nlattr *nla) @@ -534,7 +535,8 @@ done: static int nf_tables_gettable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_cur(net); @@ -677,7 +679,8 @@ err: static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -830,7 +833,8 @@ out: static int nf_tables_deltable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -869,6 +873,9 @@ int nft_register_chain_type(const struct nf_chain_type *ctype) { int err = 0; + if (WARN_ON(ctype->family >= NFPROTO_NUMPROTO)) + return -EINVAL; + nfnl_lock(NFNL_SUBSYS_NFTABLES); if (chain_type[ctype->family][ctype->type] != NULL) { err = -EBUSY; @@ -1123,7 +1130,8 @@ done: static int nf_tables_getchain(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_cur(net); @@ -1319,7 +1327,8 @@ static void nft_chain_release_hook(struct nft_chain_hook *hook) static int nf_tables_newchain(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nlattr * uninitialized_var(name); @@ -1557,7 +1566,8 @@ err1: static int nf_tables_delchain(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -2038,7 +2048,8 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) static int nf_tables_getrule(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_cur(net); @@ -2131,7 +2142,8 @@ static struct nft_expr_info *info; static int nf_tables_newrule(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -2313,7 +2325,8 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, static int nf_tables_delrule(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -2377,64 +2390,77 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, * Sets */ -static LIST_HEAD(nf_tables_set_ops); +static LIST_HEAD(nf_tables_set_types); -int nft_register_set(struct nft_set_ops *ops) +int nft_register_set(struct nft_set_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_add_tail_rcu(&ops->list, &nf_tables_set_ops); + list_add_tail_rcu(&type->list, &nf_tables_set_types); nfnl_unlock(NFNL_SUBSYS_NFTABLES); return 0; } EXPORT_SYMBOL_GPL(nft_register_set); -void nft_unregister_set(struct nft_set_ops *ops) +void nft_unregister_set(struct nft_set_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_del_rcu(&ops->list); + list_del_rcu(&type->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_set); +#define NFT_SET_FEATURES (NFT_SET_INTERVAL | NFT_SET_MAP | \ + NFT_SET_TIMEOUT | NFT_SET_OBJECT) + +static bool nft_set_ops_candidate(const struct nft_set_ops *ops, u32 flags) +{ + return (flags & ops->features) == (flags & NFT_SET_FEATURES); +} + /* * Select a set implementation based on the data characteristics and the * given policy. The total memory use might not be known if no size is * given, in that case the amount of memory per element is used. */ static const struct nft_set_ops * -nft_select_set_ops(const struct nlattr * const nla[], +nft_select_set_ops(const struct nft_ctx *ctx, + const struct nlattr * const nla[], const struct nft_set_desc *desc, enum nft_set_policies policy) { const struct nft_set_ops *ops, *bops; struct nft_set_estimate est, best; - u32 features; + const struct nft_set_type *type; + u32 flags = 0; #ifdef CONFIG_MODULES - if (list_empty(&nf_tables_set_ops)) { + if (list_empty(&nf_tables_set_types)) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); request_module("nft-set"); nfnl_lock(NFNL_SUBSYS_NFTABLES); - if (!list_empty(&nf_tables_set_ops)) + if (!list_empty(&nf_tables_set_types)) return ERR_PTR(-EAGAIN); } #endif - features = 0; - if (nla[NFTA_SET_FLAGS] != NULL) { - features = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); - features &= NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_TIMEOUT | - NFT_SET_OBJECT; - } + if (nla[NFTA_SET_FLAGS] != NULL) + flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); bops = NULL; best.size = ~0; best.lookup = ~0; best.space = ~0; - list_for_each_entry(ops, &nf_tables_set_ops, list) { - if ((ops->features & features) != features) + list_for_each_entry(type, &nf_tables_set_types, list) { + if (!type->select_ops) + ops = type->ops; + else + ops = type->select_ops(ctx, desc, flags); + if (!ops) continue; - if (!ops->estimate(desc, features, &est)) + + if (!nft_set_ops_candidate(ops, flags)) + continue; + if (!ops->estimate(desc, flags, &est)) continue; switch (policy) { @@ -2465,10 +2491,10 @@ nft_select_set_ops(const struct nlattr * const nla[], break; } - if (!try_module_get(ops->owner)) + if (!try_module_get(type->owner)) continue; if (bops != NULL) - module_put(bops->owner); + module_put(bops->type->owner); bops = ops; best = est; @@ -2816,7 +2842,8 @@ static int nf_tables_dump_sets_done(struct netlink_callback *cb) static int nf_tables_getset(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { u8 genmask = nft_genmask_cur(net); const struct nft_set *set; @@ -2892,7 +2919,8 @@ static int nf_tables_set_desc_parse(const struct nft_ctx *ctx, static int nf_tables_newset(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -3029,7 +3057,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (!(nlh->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; - ops = nft_select_set_ops(nla, &desc, policy); + ops = nft_select_set_ops(&ctx, nla, &desc, policy); if (IS_ERR(ops)) return PTR_ERR(ops); @@ -3039,12 +3067,13 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, size = 0; if (ops->privsize != NULL) - size = ops->privsize(nla); + size = ops->privsize(nla, &desc); - err = -ENOMEM; - set = kzalloc(sizeof(*set) + size + udlen, GFP_KERNEL); - if (set == NULL) + set = kvzalloc(sizeof(*set) + size + udlen, GFP_KERNEL); + if (!set) { + err = -ENOMEM; goto err1; + } nla_strlcpy(name, nla[NFTA_SET_NAME], sizeof(set->name)); err = nf_tables_set_alloc_name(&ctx, set, name); @@ -3087,17 +3116,17 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err3: ops->destroy(set); err2: - kfree(set); + kvfree(set); err1: - module_put(ops->owner); + module_put(ops->type->owner); return err; } static void nft_set_destroy(struct nft_set *set) { set->ops->destroy(set); - module_put(set->ops->owner); - kfree(set); + module_put(set->ops->type->owner); + kvfree(set); } static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) @@ -3109,7 +3138,8 @@ static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set static int nf_tables_delset(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -3469,7 +3499,8 @@ static int nf_tables_dump_set_done(struct netlink_callback *cb) static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { u8 genmask = nft_genmask_cur(net); const struct nft_set *set; @@ -3870,7 +3901,8 @@ err1: static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { u8 genmask = nft_genmask_next(net); const struct nlattr *attr; @@ -4067,7 +4099,8 @@ err1: static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { u8 genmask = nft_genmask_next(net); const struct nlattr *attr; @@ -4277,7 +4310,8 @@ static const struct nft_object_type *nft_obj_type_get(u32 objtype) static int nf_tables_newobj(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nft_object_type *type; @@ -4471,7 +4505,8 @@ nft_obj_filter_alloc(const struct nlattr * const nla[]) static int nf_tables_getobj(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_cur(net); @@ -4549,8 +4584,9 @@ static void nft_obj_destroy(struct nft_object *obj) } static int nf_tables_delobj(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + struct sk_buff *skb, const struct nlmsghdr *nlh, + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); @@ -4680,7 +4716,8 @@ err: static int nf_tables_getgen(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) { struct sk_buff *skb2; int err; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 80f5ecf2c3d7..92b05e188fd1 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -201,7 +201,8 @@ replay: if (nc->call_rcu) { err = nc->call_rcu(net, net->nfnl, skb, nlh, - (const struct nlattr **)cda); + (const struct nlattr **)cda, + extack); rcu_read_unlock(); } else { rcu_read_unlock(); @@ -211,7 +212,8 @@ replay: err = -EAGAIN; else if (nc->call) err = nc->call(net, net->nfnl, skb, nlh, - (const struct nlattr **)cda); + (const struct nlattr **)cda, + extack); else err = -EINVAL; nfnl_unlock(subsys_id); @@ -226,9 +228,11 @@ struct nfnl_err { struct list_head head; struct nlmsghdr *nlh; int err; + struct netlink_ext_ack extack; }; -static int nfnl_err_add(struct list_head *list, struct nlmsghdr *nlh, int err) +static int nfnl_err_add(struct list_head *list, struct nlmsghdr *nlh, int err, + const struct netlink_ext_ack *extack) { struct nfnl_err *nfnl_err; @@ -238,6 +242,7 @@ static int nfnl_err_add(struct list_head *list, struct nlmsghdr *nlh, int err) nfnl_err->nlh = nlh; nfnl_err->err = err; + nfnl_err->extack = *extack; list_add_tail(&nfnl_err->head, list); return 0; @@ -262,7 +267,8 @@ static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb) struct nfnl_err *nfnl_err, *next; list_for_each_entry_safe(nfnl_err, next, err_list, head) { - netlink_ack(skb, nfnl_err->nlh, nfnl_err->err, NULL); + netlink_ack(skb, nfnl_err->nlh, nfnl_err->err, + &nfnl_err->extack); nfnl_err_del(nfnl_err); } } @@ -280,6 +286,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); const struct nfnetlink_subsystem *ss; const struct nfnl_callback *nc; + struct netlink_ext_ack extack; LIST_HEAD(err_list); u32 status; int err; @@ -325,6 +332,7 @@ replay: while (skb->len >= nlmsg_total_size(0)) { int msglen, type; + memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; @@ -384,7 +392,8 @@ replay: if (nc->call_batch) { err = nc->call_batch(net, net->nfnl, skb, nlh, - (const struct nlattr **)cda); + (const struct nlattr **)cda, + &extack); } /* The lock was released to autoload some module, we @@ -402,7 +411,7 @@ ack: * processed, this avoids that the same error is * reported several times when replaying the batch. */ - if (nfnl_err_add(&err_list, nlh, err) < 0) { + if (nfnl_err_add(&err_list, nlh, err, &extack) < 0) { /* We failed to enqueue an error, reset the * list of errors and send OOM to userspace * pointing to the batch header. diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 9898fb4d0512..c45e6d4358ab 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -49,7 +49,8 @@ struct nfacct_filter { static int nfnl_acct_new(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { struct nf_acct *nfacct, *matching = NULL; char *acct_name; @@ -264,7 +265,8 @@ nfacct_filter_alloc(const struct nlattr * const attr) static int nfnl_acct_get(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { int ret = -ENOENT; struct nf_acct *cur; @@ -343,7 +345,8 @@ static int nfnl_acct_try_del(struct nf_acct *cur) static int nfnl_acct_del(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { struct nf_acct *cur, *tmp; int ret = -ENOENT; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index be678a323598..41628b393673 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -398,7 +398,8 @@ nfnl_cthelper_update(const struct nlattr * const tb[], static int nfnl_cthelper_new(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { const char *helper_name; struct nf_conntrack_helper *cur, *helper = NULL; @@ -599,7 +600,8 @@ out: static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { int ret = -ENOENT; struct nf_conntrack_helper *cur; @@ -666,7 +668,8 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, static int nfnl_cthelper_del(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { char *helper_name = NULL; struct nf_conntrack_helper *cur; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index a3e7bb54d96a..400e9ae97153 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -69,7 +69,8 @@ ctnl_timeout_parse_policy(void *timeouts, struct nf_conntrack_l4proto *l4proto, static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { __u16 l3num; __u8 l4num; @@ -239,7 +240,8 @@ ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) static int cttimeout_get_timeout(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { int ret = -ENOENT; char *name; @@ -287,49 +289,20 @@ static int cttimeout_get_timeout(struct net *net, struct sock *ctnl, return ret; } -static void untimeout(struct nf_conntrack_tuple_hash *i, - struct ctnl_timeout *timeout) +static int untimeout(struct nf_conn *ct, void *timeout) { - struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i); struct nf_conn_timeout *timeout_ext = nf_ct_timeout_find(ct); if (timeout_ext && (!timeout || timeout_ext->timeout == timeout)) RCU_INIT_POINTER(timeout_ext->timeout, NULL); + + /* We are not intended to delete this conntrack. */ + return 0; } static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) { - struct nf_conntrack_tuple_hash *h; - const struct hlist_nulls_node *nn; - unsigned int last_hsize; - spinlock_t *lock; - int i, cpu; - - for_each_possible_cpu(cpu) { - struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); - - spin_lock_bh(&pcpu->lock); - hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode) - untimeout(h, timeout); - spin_unlock_bh(&pcpu->lock); - } - - local_bh_disable(); -restart: - last_hsize = nf_conntrack_htable_size; - for (i = 0; i < last_hsize; i++) { - lock = &nf_conntrack_locks[i % CONNTRACK_LOCKS]; - nf_conntrack_lock(lock); - if (last_hsize != nf_conntrack_htable_size) { - spin_unlock(lock); - goto restart; - } - - hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) - untimeout(h, timeout); - spin_unlock(lock); - } - local_bh_enable(); + nf_ct_iterate_cleanup_net(net, untimeout, timeout, 0, 0); } /* try to delete object, fail if it is still in use. */ @@ -355,7 +328,8 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) static int cttimeout_del_timeout(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { struct ctnl_timeout *cur, *tmp; int ret = -ENOENT; @@ -386,7 +360,8 @@ static int cttimeout_del_timeout(struct net *net, struct sock *ctnl, static int cttimeout_default_set(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { __u16 l3num; __u8 l4num; @@ -475,7 +450,8 @@ nla_put_failure: static int cttimeout_default_get(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]) + const struct nlattr * const cda[], + struct netlink_ext_ack *extack) { __u16 l3num; __u8 l4num; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 94ec0d0765a8..c684ba95dbb4 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -795,7 +795,8 @@ static struct notifier_block nfulnl_rtnl_notifier = { static int nfulnl_recv_unsupp(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[]) + const struct nlattr * const nfqa[], + struct netlink_ext_ack *extack) { return -ENOTSUPP; } @@ -818,7 +819,8 @@ static const struct nla_policy nfula_cfg_policy[NFULA_CFG_MAX+1] = { static int nfulnl_recv_config(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfula[]) + const struct nlattr * const nfula[], + struct netlink_ext_ack *extack) { struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int16_t group_num = ntohs(nfmsg->res_id); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 1b17a1b445a3..16fa04086880 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1032,7 +1032,8 @@ static int nfq_id_after(unsigned int id, unsigned int max) static int nfqnl_recv_verdict_batch(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[]) + const struct nlattr * const nfqa[], + struct netlink_ext_ack *extack) { struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nf_queue_entry *entry, *tmp; @@ -1136,7 +1137,8 @@ static int nfqa_parse_bridge(struct nf_queue_entry *entry, static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[]) + const struct nlattr * const nfqa[], + struct netlink_ext_ack *extack) { struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int16_t queue_num = ntohs(nfmsg->res_id); @@ -1200,7 +1202,8 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, static int nfqnl_recv_unsupp(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[]) + const struct nlattr * const nfqa[], + struct netlink_ext_ack *extack) { return -ENOTSUPP; } @@ -1217,7 +1220,8 @@ static const struct nf_queue_handler nfqh = { static int nfqnl_recv_config(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[]) + const struct nlattr * const nfqa[], + struct netlink_ext_ack *extack) { struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int16_t queue_num = ntohs(nfmsg->res_id); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index f753ec69f790..f5a7cb68694e 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -530,7 +530,8 @@ nla_put_failure: static int nfnl_compat_get(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { int ret = 0, target; struct nfgenmsg *nfmsg; diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index d3eb640bc784..c7383d8f88d0 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -23,9 +23,9 @@ struct nft_rt { enum nft_registers dreg:8; }; -void nft_rt_get_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static void nft_rt_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_rt *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; @@ -72,9 +72,9 @@ const struct nla_policy nft_rt_policy[NFTA_RT_MAX + 1] = { [NFTA_RT_KEY] = { .type = NLA_U32 }, }; -int nft_rt_get_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_rt_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_rt *priv = nft_expr_priv(expr); unsigned int len; @@ -103,8 +103,8 @@ int nft_rt_get_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, len); } -int nft_rt_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) +static int nft_rt_get_dump(struct sk_buff *skb, + const struct nft_expr *expr) { const struct nft_rt *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index b988162b5b15..734989c40579 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -236,7 +236,8 @@ static inline u32 nft_bitmap_total_size(u32 klen) return sizeof(struct nft_bitmap) + nft_bitmap_size(klen); } -static unsigned int nft_bitmap_privsize(const struct nlattr * const nla[]) +static unsigned int nft_bitmap_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { u32 klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN])); @@ -278,7 +279,9 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, return true; } +static struct nft_set_type nft_bitmap_type; static struct nft_set_ops nft_bitmap_ops __read_mostly = { + .type = &nft_bitmap_type, .privsize = nft_bitmap_privsize, .elemsize = offsetof(struct nft_bitmap_elem, ext), .estimate = nft_bitmap_estimate, @@ -291,17 +294,21 @@ static struct nft_set_ops nft_bitmap_ops __read_mostly = { .activate = nft_bitmap_activate, .lookup = nft_bitmap_lookup, .walk = nft_bitmap_walk, +}; + +static struct nft_set_type nft_bitmap_type __read_mostly = { + .ops = &nft_bitmap_ops, .owner = THIS_MODULE, }; static int __init nft_bitmap_module_init(void) { - return nft_register_set(&nft_bitmap_ops); + return nft_register_set(&nft_bitmap_type); } static void __exit nft_bitmap_module_exit(void) { - nft_unregister_set(&nft_bitmap_ops); + nft_unregister_set(&nft_bitmap_type); } module_init(nft_bitmap_module_init); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 3d3a6df4ce70..0fa01d772c5e 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -22,45 +22,43 @@ #include /* We target a hash table size of 4, element hint is 75% of final size */ -#define NFT_HASH_ELEMENT_HINT 3 +#define NFT_RHASH_ELEMENT_HINT 3 -struct nft_hash { +struct nft_rhash { struct rhashtable ht; struct delayed_work gc_work; }; -struct nft_hash_elem { +struct nft_rhash_elem { struct rhash_head node; struct nft_set_ext ext; }; -struct nft_hash_cmp_arg { +struct nft_rhash_cmp_arg { const struct nft_set *set; const u32 *key; u8 genmask; }; -static const struct rhashtable_params nft_hash_params; - -static inline u32 nft_hash_key(const void *data, u32 len, u32 seed) +static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed) { - const struct nft_hash_cmp_arg *arg = data; + const struct nft_rhash_cmp_arg *arg = data; return jhash(arg->key, len, seed); } -static inline u32 nft_hash_obj(const void *data, u32 len, u32 seed) +static inline u32 nft_rhash_obj(const void *data, u32 len, u32 seed) { - const struct nft_hash_elem *he = data; + const struct nft_rhash_elem *he = data; return jhash(nft_set_ext_key(&he->ext), len, seed); } -static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg, - const void *ptr) +static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) { - const struct nft_hash_cmp_arg *x = arg->key; - const struct nft_hash_elem *he = ptr; + const struct nft_rhash_cmp_arg *x = arg->key; + const struct nft_rhash_elem *he = ptr; if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) return 1; @@ -71,41 +69,49 @@ static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg, return 0; } -static bool nft_hash_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +static const struct rhashtable_params nft_rhash_params = { + .head_offset = offsetof(struct nft_rhash_elem, node), + .hashfn = nft_rhash_key, + .obj_hashfn = nft_rhash_obj, + .obj_cmpfn = nft_rhash_cmp, + .automatic_shrinking = true, +}; + +static bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { - struct nft_hash *priv = nft_set_priv(set); - const struct nft_hash_elem *he; - struct nft_hash_cmp_arg arg = { + struct nft_rhash *priv = nft_set_priv(set); + const struct nft_rhash_elem *he; + struct nft_rhash_cmp_arg arg = { .genmask = nft_genmask_cur(net), .set = set, .key = key, }; - he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_rhash_params); if (he != NULL) *ext = &he->ext; return !!he; } -static bool nft_hash_update(struct nft_set *set, const u32 *key, - void *(*new)(struct nft_set *, - const struct nft_expr *, - struct nft_regs *regs), - const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_set_ext **ext) +static bool nft_rhash_update(struct nft_set *set, const u32 *key, + void *(*new)(struct nft_set *, + const struct nft_expr *, + struct nft_regs *regs), + const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_set_ext **ext) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he, *prev; - struct nft_hash_cmp_arg arg = { + struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_elem *he, *prev; + struct nft_rhash_cmp_arg arg = { .genmask = NFT_GENMASK_ANY, .set = set, .key = key, }; - he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_rhash_params); if (he != NULL) goto out; @@ -114,7 +120,7 @@ static bool nft_hash_update(struct nft_set *set, const u32 *key, goto err1; prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node, - nft_hash_params); + nft_rhash_params); if (IS_ERR(prev)) goto err2; @@ -134,21 +140,21 @@ err1: return false; } -static int nft_hash_insert(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, - struct nft_set_ext **ext) +static int nft_rhash_insert(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, + struct nft_set_ext **ext) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he = elem->priv; - struct nft_hash_cmp_arg arg = { + struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_elem *he = elem->priv; + struct nft_rhash_cmp_arg arg = { .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, }; - struct nft_hash_elem *prev; + struct nft_rhash_elem *prev; prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node, - nft_hash_params); + nft_rhash_params); if (IS_ERR(prev)) return PTR_ERR(prev); if (prev) { @@ -158,19 +164,19 @@ static int nft_hash_insert(const struct net *net, const struct nft_set *set, return 0; } -static void nft_hash_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) +static void nft_rhash_activate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { - struct nft_hash_elem *he = elem->priv; + struct nft_rhash_elem *he = elem->priv; nft_set_elem_change_active(net, set, &he->ext); nft_set_elem_clear_busy(&he->ext); } -static bool nft_hash_flush(const struct net *net, - const struct nft_set *set, void *priv) +static bool nft_rhash_flush(const struct net *net, + const struct nft_set *set, void *priv) { - struct nft_hash_elem *he = priv; + struct nft_rhash_elem *he = priv; if (!nft_set_elem_mark_busy(&he->ext) || !nft_is_active(net, &he->ext)) { @@ -180,22 +186,22 @@ static bool nft_hash_flush(const struct net *net, return false; } -static void *nft_hash_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static void *nft_rhash_deactivate(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he; - struct nft_hash_cmp_arg arg = { + struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_elem *he; + struct nft_rhash_cmp_arg arg = { .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, }; rcu_read_lock(); - he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_rhash_params); if (he != NULL && - !nft_hash_flush(net, set, he)) + !nft_rhash_flush(net, set, he)) he = NULL; rcu_read_unlock(); @@ -203,21 +209,21 @@ static void *nft_hash_deactivate(const struct net *net, return he; } -static void nft_hash_remove(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static void nft_rhash_remove(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he = elem->priv; + struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_elem *he = elem->priv; - rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); + rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); } -static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_iter *iter) +static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_set_iter *iter) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he; + struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_elem *he; struct rhashtable_iter hti; struct nft_set_elem elem; int err; @@ -266,16 +272,16 @@ out: rhashtable_walk_exit(&hti); } -static void nft_hash_gc(struct work_struct *work) +static void nft_rhash_gc(struct work_struct *work) { struct nft_set *set; - struct nft_hash_elem *he; - struct nft_hash *priv; + struct nft_rhash_elem *he; + struct nft_rhash *priv; struct nft_set_gc_batch *gcb = NULL; struct rhashtable_iter hti; int err; - priv = container_of(work, struct nft_hash, gc_work.work); + priv = container_of(work, struct nft_rhash, gc_work.work); set = nft_set_container_of(priv); err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); @@ -301,7 +307,7 @@ static void nft_hash_gc(struct work_struct *work) gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); if (gcb == NULL) goto out; - rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); + rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, he); } @@ -315,82 +321,290 @@ schedule: nft_set_gc_interval(set)); } -static unsigned int nft_hash_privsize(const struct nlattr * const nla[]) +static unsigned int nft_rhash_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { - return sizeof(struct nft_hash); + return sizeof(struct nft_rhash); } -static const struct rhashtable_params nft_hash_params = { - .head_offset = offsetof(struct nft_hash_elem, node), - .hashfn = nft_hash_key, - .obj_hashfn = nft_hash_obj, - .obj_cmpfn = nft_hash_cmp, - .automatic_shrinking = true, -}; - -static int nft_hash_init(const struct nft_set *set, - const struct nft_set_desc *desc, - const struct nlattr * const tb[]) +static int nft_rhash_init(const struct nft_set *set, + const struct nft_set_desc *desc, + const struct nlattr * const tb[]) { - struct nft_hash *priv = nft_set_priv(set); - struct rhashtable_params params = nft_hash_params; + struct nft_rhash *priv = nft_set_priv(set); + struct rhashtable_params params = nft_rhash_params; int err; - params.nelem_hint = desc->size ?: NFT_HASH_ELEMENT_HINT; + params.nelem_hint = desc->size ?: NFT_RHASH_ELEMENT_HINT; params.key_len = set->klen; err = rhashtable_init(&priv->ht, ¶ms); if (err < 0) return err; - INIT_DEFERRABLE_WORK(&priv->gc_work, nft_hash_gc); + INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rhash_gc); if (set->flags & NFT_SET_TIMEOUT) queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); return 0; } -static void nft_hash_elem_destroy(void *ptr, void *arg) +static void nft_rhash_elem_destroy(void *ptr, void *arg) { nft_set_elem_destroy(arg, ptr, true); } -static void nft_hash_destroy(const struct nft_set *set) +static void nft_rhash_destroy(const struct nft_set *set) { - struct nft_hash *priv = nft_set_priv(set); + struct nft_rhash *priv = nft_set_priv(set); cancel_delayed_work_sync(&priv->gc_work); - rhashtable_free_and_destroy(&priv->ht, nft_hash_elem_destroy, + rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)set); } -static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, - struct nft_set_estimate *est) +static u32 nft_hash_buckets(u32 size) { - unsigned int esize; - - esize = sizeof(struct nft_hash_elem); - if (desc->size) { - est->size = sizeof(struct nft_hash) + - roundup_pow_of_two(desc->size * 4 / 3) * - sizeof(struct nft_hash_elem *) + - desc->size * esize; - } else { - /* Resizing happens when the load drops below 30% or goes - * above 75%. The average of 52.5% load (approximated by 50%) - * is used for the size estimation of the hash buckets, - * meaning we calculate two buckets per element. - */ - est->size = esize + 2 * sizeof(struct nft_hash_elem *); - } + return roundup_pow_of_two(size * 4 / 3); +} +static bool nft_rhash_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + est->size = ~0; est->lookup = NFT_SET_CLASS_O_1; est->space = NFT_SET_CLASS_O_N; return true; } +struct nft_hash { + u32 seed; + u32 buckets; + struct hlist_head table[]; +}; + +struct nft_hash_elem { + struct hlist_node node; + struct nft_set_ext ext; +}; + +static bool nft_hash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) +{ + struct nft_hash *priv = nft_set_priv(set); + u8 genmask = nft_genmask_cur(net); + const struct nft_hash_elem *he; + u32 hash; + + hash = jhash(key, set->klen, priv->seed); + hash = reciprocal_scale(hash, priv->buckets); + hlist_for_each_entry_rcu(he, &priv->table[hash], node) { + if (!memcmp(nft_set_ext_key(&he->ext), key, set->klen) && + nft_set_elem_active(&he->ext, genmask)) { + *ext = &he->ext; + return true; + } + } + return false; +} + +/* nft_hash_select_ops() makes sure key size can be either 2 or 4 bytes . */ +static inline u32 nft_hash_key(const u32 *key, u32 klen) +{ + if (klen == 4) + return *key; + + return *(u16 *)key; +} + +static bool nft_hash_lookup_fast(const struct net *net, + const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) +{ + struct nft_hash *priv = nft_set_priv(set); + u8 genmask = nft_genmask_cur(net); + const struct nft_hash_elem *he; + u32 hash, k1, k2; + + k1 = nft_hash_key(key, set->klen); + hash = jhash_1word(k1, priv->seed); + hash = reciprocal_scale(hash, priv->buckets); + hlist_for_each_entry_rcu(he, &priv->table[hash], node) { + k2 = nft_hash_key(nft_set_ext_key(&he->ext)->data, set->klen); + if (k1 == k2 && + nft_set_elem_active(&he->ext, genmask)) { + *ext = &he->ext; + return true; + } + } + return false; +} + +static int nft_hash_insert(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, + struct nft_set_ext **ext) +{ + struct nft_hash_elem *this = elem->priv, *he; + struct nft_hash *priv = nft_set_priv(set); + u8 genmask = nft_genmask_next(net); + u32 hash; + + hash = jhash(nft_set_ext_key(&this->ext), set->klen, priv->seed); + hash = reciprocal_scale(hash, priv->buckets); + hlist_for_each_entry(he, &priv->table[hash], node) { + if (!memcmp(nft_set_ext_key(&this->ext), + nft_set_ext_key(&he->ext), set->klen) && + nft_set_elem_active(&he->ext, genmask)) { + *ext = &he->ext; + return -EEXIST; + } + } + hlist_add_head_rcu(&this->node, &priv->table[hash]); + return 0; +} + +static void nft_hash_activate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_hash_elem *he = elem->priv; + + nft_set_elem_change_active(net, set, &he->ext); +} + +static bool nft_hash_flush(const struct net *net, + const struct nft_set *set, void *priv) +{ + struct nft_hash_elem *he = priv; + + nft_set_elem_change_active(net, set, &he->ext); + return true; +} + +static void *nft_hash_deactivate(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *this = elem->priv, *he; + u8 genmask = nft_genmask_next(net); + u32 hash; + + hash = jhash(nft_set_ext_key(&this->ext), set->klen, priv->seed); + hash = reciprocal_scale(hash, priv->buckets); + hlist_for_each_entry(he, &priv->table[hash], node) { + if (!memcmp(nft_set_ext_key(&this->ext), &elem->key.val, + set->klen) || + nft_set_elem_active(&he->ext, genmask)) { + nft_set_elem_change_active(net, set, &he->ext); + return he; + } + } + return NULL; +} + +static void nft_hash_remove(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_hash_elem *he = elem->priv; + + hlist_del_rcu(&he->node); +} + +static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_set_iter *iter) +{ + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he; + struct nft_set_elem elem; + int i; + + for (i = 0; i < priv->buckets; i++) { + hlist_for_each_entry_rcu(he, &priv->table[i], node) { + if (iter->count < iter->skip) + goto cont; + if (!nft_set_elem_active(&he->ext, iter->genmask)) + goto cont; + + elem.priv = he; + + iter->err = iter->fn(ctx, set, iter, &elem); + if (iter->err < 0) + return; +cont: + iter->count++; + } + } +} + +static unsigned int nft_hash_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) +{ + return sizeof(struct nft_hash) + + nft_hash_buckets(desc->size) * sizeof(struct hlist_head); +} + +static int nft_hash_init(const struct nft_set *set, + const struct nft_set_desc *desc, + const struct nlattr * const tb[]) +{ + struct nft_hash *priv = nft_set_priv(set); + + priv->buckets = nft_hash_buckets(desc->size); + get_random_bytes(&priv->seed, sizeof(priv->seed)); + + return 0; +} + +static void nft_hash_destroy(const struct nft_set *set) +{ + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he; + struct hlist_node *next; + int i; + + for (i = 0; i < priv->buckets; i++) { + hlist_for_each_entry_safe(he, next, &priv->table[i], node) { + hlist_del_rcu(&he->node); + nft_set_elem_destroy(set, he, true); + } + } +} + +static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + est->size = sizeof(struct nft_hash) + + nft_hash_buckets(desc->size) * sizeof(struct hlist_head) + + desc->size * sizeof(struct nft_hash_elem); + est->lookup = NFT_SET_CLASS_O_1; + est->space = NFT_SET_CLASS_O_N; + + return true; +} + +static struct nft_set_type nft_hash_type; +static struct nft_set_ops nft_rhash_ops __read_mostly = { + .type = &nft_hash_type, + .privsize = nft_rhash_privsize, + .elemsize = offsetof(struct nft_rhash_elem, ext), + .estimate = nft_rhash_estimate, + .init = nft_rhash_init, + .destroy = nft_rhash_destroy, + .insert = nft_rhash_insert, + .activate = nft_rhash_activate, + .deactivate = nft_rhash_deactivate, + .flush = nft_rhash_flush, + .remove = nft_rhash_remove, + .lookup = nft_rhash_lookup, + .update = nft_rhash_update, + .walk = nft_rhash_walk, + .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, +}; + static struct nft_set_ops nft_hash_ops __read_mostly = { + .type = &nft_hash_type, .privsize = nft_hash_privsize, .elemsize = offsetof(struct nft_hash_elem, ext), .estimate = nft_hash_estimate, @@ -402,20 +616,57 @@ static struct nft_set_ops nft_hash_ops __read_mostly = { .flush = nft_hash_flush, .remove = nft_hash_remove, .lookup = nft_hash_lookup, - .update = nft_hash_update, .walk = nft_hash_walk, - .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, + .features = NFT_SET_MAP | NFT_SET_OBJECT, +}; + +static struct nft_set_ops nft_hash_fast_ops __read_mostly = { + .type = &nft_hash_type, + .privsize = nft_hash_privsize, + .elemsize = offsetof(struct nft_hash_elem, ext), + .estimate = nft_hash_estimate, + .init = nft_hash_init, + .destroy = nft_hash_destroy, + .insert = nft_hash_insert, + .activate = nft_hash_activate, + .deactivate = nft_hash_deactivate, + .flush = nft_hash_flush, + .remove = nft_hash_remove, + .lookup = nft_hash_lookup_fast, + .walk = nft_hash_walk, + .features = NFT_SET_MAP | NFT_SET_OBJECT, +}; + +static const struct nft_set_ops * +nft_hash_select_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, + u32 flags) +{ + if (desc->size) { + switch (desc->klen) { + case 2: + case 4: + return &nft_hash_fast_ops; + default: + return &nft_hash_ops; + } + } + + return &nft_rhash_ops; +} + +static struct nft_set_type nft_hash_type __read_mostly = { + .select_ops = nft_hash_select_ops, .owner = THIS_MODULE, }; static int __init nft_hash_module_init(void) { - return nft_register_set(&nft_hash_ops); + return nft_register_set(&nft_hash_type); } static void __exit nft_hash_module_exit(void) { - nft_unregister_set(&nft_hash_ops); + nft_unregister_set(&nft_hash_type); } module_init(nft_hash_module_init); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index fbdbaa00dd5f..bce5382f1d49 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -251,7 +251,8 @@ cont: read_unlock_bh(&priv->lock); } -static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[]) +static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { return sizeof(struct nft_rbtree); } @@ -283,13 +284,11 @@ static void nft_rbtree_destroy(const struct nft_set *set) static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est) { - unsigned int nsize; - - nsize = sizeof(struct nft_rbtree_elem); if (desc->size) - est->size = sizeof(struct nft_rbtree) + desc->size * nsize; + est->size = sizeof(struct nft_rbtree) + + desc->size * sizeof(struct nft_rbtree_elem); else - est->size = nsize; + est->size = ~0; est->lookup = NFT_SET_CLASS_O_LOG_N; est->space = NFT_SET_CLASS_O_N; @@ -297,7 +296,9 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, return true; } +static struct nft_set_type nft_rbtree_type; static struct nft_set_ops nft_rbtree_ops __read_mostly = { + .type = &nft_rbtree_type, .privsize = nft_rbtree_privsize, .elemsize = offsetof(struct nft_rbtree_elem, ext), .estimate = nft_rbtree_estimate, @@ -311,17 +312,21 @@ static struct nft_set_ops nft_rbtree_ops __read_mostly = { .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT, +}; + +static struct nft_set_type nft_rbtree_type __read_mostly = { + .ops = &nft_rbtree_ops, .owner = THIS_MODULE, }; static int __init nft_rbtree_module_init(void) { - return nft_register_set(&nft_rbtree_ops); + return nft_register_set(&nft_rbtree_type); } static void __exit nft_rbtree_module_exit(void) { - nft_unregister_set(&nft_rbtree_ops); + nft_unregister_set(&nft_rbtree_type); } module_init(nft_rbtree_module_init); diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index c05fefcec238..71cfa9551d08 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -63,7 +63,8 @@ static const struct nla_policy xt_osf_policy[OSF_ATTR_MAX + 1] = { static int xt_osf_add_callback(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const osf_attrs[]) + const struct nlattr * const osf_attrs[], + struct netlink_ext_ack *extack) { struct xt_osf_user_finger *f; struct xt_osf_finger *kf = NULL, *sf; @@ -107,7 +108,8 @@ static int xt_osf_add_callback(struct net *net, struct sock *ctnl, static int xt_osf_remove_callback(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const osf_attrs[]) + const struct nlattr * const osf_attrs[], + struct netlink_ext_ack *extack) { struct xt_osf_user_finger *f; struct xt_osf_finger *sf;