diff options
Diffstat (limited to 'net/netfilter')
70 files changed, 2235 insertions, 1356 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 9266ceebd112..e8d56d9a4df2 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -474,6 +474,12 @@ config NFT_META This option adds the "meta" expression that you can use to match and to set packet metainformation such as the packet mark. +config NFT_NUMGEN + tristate "Netfilter nf_tables number generator module" + help + This option adds the number generator expression used to perform + incremental counting and random numbers bound to a upper limit. + config NFT_CT depends on NF_CONNTRACK tristate "Netfilter nf_tables conntrack module" @@ -481,13 +487,13 @@ config NFT_CT This option adds the "meta" expression that you can use to match connection tracking information such as the flow state. -config NFT_RBTREE +config NFT_SET_RBTREE tristate "Netfilter nf_tables rbtree set module" help This option adds the "rbtree" set type (Red Black tree) that is used to build interval-based sets. -config NFT_HASH +config NFT_SET_HASH tristate "Netfilter nf_tables hash set module" help This option adds the "hash" set type that is used to build one-way @@ -542,6 +548,12 @@ config NFT_QUEUE This is required if you intend to use the userspace queueing infrastructure (also known as NFQUEUE) from nftables. +config NFT_QUOTA + tristate "Netfilter nf_tables quota module" + help + This option adds the "quota" expression that you can use to match + enforce bytes quotas. + config NFT_REJECT default m if NETFILTER_ADVANCED=n tristate "Netfilter nf_tables reject support" @@ -563,6 +575,12 @@ config NFT_COMPAT x_tables match/target extensions over the nf_tables framework. +config NFT_HASH + tristate "Netfilter nf_tables hash module" + help + This option adds the "hash" expression that you can use to perform + a hash operation on registers. + if NF_TABLES_NETDEV config NF_DUP_NETDEV diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 69134541d65b..c23c3c84416f 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -71,8 +71,9 @@ obj-$(CONFIG_NF_DUP_NETDEV) += nf_dup_netdev.o # nf_tables nf_tables-objs += nf_tables_core.o nf_tables_api.o nf_tables_trace.o -nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o nft_dynset.o +nf_tables-objs += nft_immediate.o nft_cmp.o nft_range.o nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o +nf_tables-objs += nft_lookup.o nft_dynset.o obj-$(CONFIG_NF_TABLES) += nf_tables.o obj-$(CONFIG_NF_TABLES_INET) += nf_tables_inet.o @@ -80,18 +81,21 @@ obj-$(CONFIG_NF_TABLES_NETDEV) += nf_tables_netdev.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o obj-$(CONFIG_NFT_META) += nft_meta.o +obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o obj-$(CONFIG_NFT_CT) += nft_ct.o obj-$(CONFIG_NFT_LIMIT) += nft_limit.o obj-$(CONFIG_NFT_NAT) += nft_nat.o obj-$(CONFIG_NFT_QUEUE) += nft_queue.o +obj-$(CONFIG_NFT_QUOTA) += nft_quota.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o -obj-$(CONFIG_NFT_RBTREE) += nft_rbtree.o -obj-$(CONFIG_NFT_HASH) += nft_hash.o +obj-$(CONFIG_NFT_SET_RBTREE) += nft_set_rbtree.o +obj-$(CONFIG_NFT_SET_HASH) += nft_set_hash.o obj-$(CONFIG_NFT_COUNTER) += nft_counter.o obj-$(CONFIG_NFT_LOG) += nft_log.o obj-$(CONFIG_NFT_MASQ) += nft_masq.o obj-$(CONFIG_NFT_REDIR) += nft_redir.o +obj-$(CONFIG_NFT_HASH) += nft_hash.o # nf_tables netdev obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index f39276d1c2d7..004af030ef1a 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -22,6 +22,7 @@ #include <linux/proc_fs.h> #include <linux/mutex.h> #include <linux/slab.h> +#include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -61,33 +62,41 @@ EXPORT_SYMBOL(nf_hooks_needed); #endif static DEFINE_MUTEX(nf_hook_mutex); +#define nf_entry_dereference(e) \ + rcu_dereference_protected(e, lockdep_is_held(&nf_hook_mutex)) -static struct list_head *nf_find_hook_list(struct net *net, - const struct nf_hook_ops *reg) +static struct nf_hook_entry __rcu **nf_hook_entry_head(struct net *net, const struct nf_hook_ops *reg) { - struct list_head *hook_list = NULL; - if (reg->pf != NFPROTO_NETDEV) - hook_list = &net->nf.hooks[reg->pf][reg->hooknum]; - else if (reg->hooknum == NF_NETDEV_INGRESS) { + return net->nf.hooks[reg->pf]+reg->hooknum; + #ifdef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) { if (reg->dev && dev_net(reg->dev) == net) - hook_list = ®->dev->nf_hooks_ingress; -#endif + return ®->dev->nf_hooks_ingress; } - return hook_list; +#endif + return NULL; } -struct nf_hook_entry { - const struct nf_hook_ops *orig_ops; - struct nf_hook_ops ops; -}; - int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) { - struct list_head *hook_list; - struct nf_hook_entry *entry; - struct nf_hook_ops *elem; + struct nf_hook_entry __rcu **pp; + struct nf_hook_entry *entry, *p; + + if (reg->pf == NFPROTO_NETDEV) { +#ifndef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) + return -EOPNOTSUPP; +#endif + if (reg->hooknum != NF_NETDEV_INGRESS || + !reg->dev || dev_net(reg->dev) != net) + return -EINVAL; + } + + pp = nf_hook_entry_head(net, reg); + if (!pp) + return -EINVAL; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) @@ -95,19 +104,19 @@ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) entry->orig_ops = reg; entry->ops = *reg; - - hook_list = nf_find_hook_list(net, reg); - if (!hook_list) { - kfree(entry); - return -ENOENT; - } + entry->next = NULL; mutex_lock(&nf_hook_mutex); - list_for_each_entry(elem, hook_list, list) { - if (reg->priority < elem->priority) + + /* Find the spot in the list */ + while ((p = nf_entry_dereference(*pp)) != NULL) { + if (reg->priority < p->orig_ops->priority) break; + pp = &p->next; } - list_add_rcu(&entry->ops.list, elem->list.prev); + rcu_assign_pointer(entry->next, p); + rcu_assign_pointer(*pp, entry); + mutex_unlock(&nf_hook_mutex); #ifdef CONFIG_NETFILTER_INGRESS if (reg->pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) @@ -122,24 +131,23 @@ EXPORT_SYMBOL(nf_register_net_hook); void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) { - struct list_head *hook_list; - struct nf_hook_entry *entry; - struct nf_hook_ops *elem; + struct nf_hook_entry __rcu **pp; + struct nf_hook_entry *p; - hook_list = nf_find_hook_list(net, reg); - if (!hook_list) + pp = nf_hook_entry_head(net, reg); + if (WARN_ON_ONCE(!pp)) return; mutex_lock(&nf_hook_mutex); - list_for_each_entry(elem, hook_list, list) { - entry = container_of(elem, struct nf_hook_entry, ops); - if (entry->orig_ops == reg) { - list_del_rcu(&entry->ops.list); + while ((p = nf_entry_dereference(*pp)) != NULL) { + if (p->orig_ops == reg) { + rcu_assign_pointer(*pp, p->next); break; } + pp = &p->next; } mutex_unlock(&nf_hook_mutex); - if (&elem->list == hook_list) { + if (!p) { WARN(1, "nf_unregister_net_hook: hook not found!\n"); return; } @@ -151,10 +159,10 @@ void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]); #endif synchronize_net(); - nf_queue_nf_hook_drop(net, &entry->ops); + nf_queue_nf_hook_drop(net, p); /* other cpu might still process nfqueue verdict that used reg */ synchronize_net(); - kfree(entry); + kfree(p); } EXPORT_SYMBOL(nf_unregister_net_hook); @@ -188,19 +196,17 @@ EXPORT_SYMBOL(nf_unregister_net_hooks); static LIST_HEAD(nf_hook_list); -int nf_register_hook(struct nf_hook_ops *reg) +static int _nf_register_hook(struct nf_hook_ops *reg) { struct net *net, *last; int ret; - rtnl_lock(); for_each_net(net) { ret = nf_register_net_hook(net, reg); if (ret && ret != -ENOENT) goto rollback; } list_add_tail(®->list, &nf_hook_list); - rtnl_unlock(); return 0; rollback: @@ -210,19 +216,34 @@ rollback: break; nf_unregister_net_hook(net, reg); } + return ret; +} + +int nf_register_hook(struct nf_hook_ops *reg) +{ + int ret; + + rtnl_lock(); + ret = _nf_register_hook(reg); rtnl_unlock(); + return ret; } EXPORT_SYMBOL(nf_register_hook); -void nf_unregister_hook(struct nf_hook_ops *reg) +static void _nf_unregister_hook(struct nf_hook_ops *reg) { struct net *net; - rtnl_lock(); list_del(®->list); for_each_net(net) nf_unregister_net_hook(net, reg); +} + +void nf_unregister_hook(struct nf_hook_ops *reg) +{ + rtnl_lock(); + _nf_unregister_hook(reg); rtnl_unlock(); } EXPORT_SYMBOL(nf_unregister_hook); @@ -246,6 +267,26 @@ err: } EXPORT_SYMBOL(nf_register_hooks); +/* Caller MUST take rtnl_lock() */ +int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n) +{ + unsigned int i; + int err = 0; + + for (i = 0; i < n; i++) { + err = _nf_register_hook(®[i]); + if (err) + goto err; + } + return err; + +err: + if (i > 0) + _nf_unregister_hooks(reg, i); + return err; +} +EXPORT_SYMBOL(_nf_register_hooks); + void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) { while (n-- > 0) @@ -253,10 +294,17 @@ void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) } EXPORT_SYMBOL(nf_unregister_hooks); -unsigned int nf_iterate(struct list_head *head, - struct sk_buff *skb, +/* Caller MUST take rtnl_lock */ +void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) +{ + while (n-- > 0) + _nf_unregister_hook(®[n]); +} +EXPORT_SYMBOL(_nf_unregister_hooks); + +unsigned int nf_iterate(struct sk_buff *skb, struct nf_hook_state *state, - struct nf_hook_ops **elemp) + struct nf_hook_entry **entryp) { unsigned int verdict; @@ -264,20 +312,23 @@ unsigned int nf_iterate(struct list_head *head, * The caller must not block between calls to this * function because of risk of continuing from deleted element. */ - list_for_each_entry_continue_rcu((*elemp), head, list) { - if (state->thresh > (*elemp)->priority) + while (*entryp) { + if (state->thresh > (*entryp)->ops.priority) { + *entryp = rcu_dereference((*entryp)->next); continue; + } /* Optimization: we don't need to hold module reference here, since function can't sleep. --RR */ repeat: - verdict = (*elemp)->hook((*elemp)->priv, skb, state); + verdict = (*entryp)->ops.hook((*entryp)->ops.priv, skb, state); if (verdict != NF_ACCEPT) { #ifdef CONFIG_NETFILTER_DEBUG if (unlikely((verdict & NF_VERDICT_MASK) > NF_MAX_VERDICT)) { NFDEBUG("Evil return from %p(%u).\n", - (*elemp)->hook, state->hook); + (*entryp)->ops.hook, state->hook); + *entryp = rcu_dereference((*entryp)->next); continue; } #endif @@ -285,25 +336,23 @@ repeat: return verdict; goto repeat; } + *entryp = rcu_dereference((*entryp)->next); } return NF_ACCEPT; } /* Returns 1 if okfn() needs to be executed by the caller, - * -EPERM for NF_DROP, 0 otherwise. */ + * -EPERM for NF_DROP, 0 otherwise. Caller must hold rcu_read_lock. */ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state) { - struct nf_hook_ops *elem; + struct nf_hook_entry *entry; unsigned int verdict; int ret = 0; - /* We may already have this, but read-locks nest anyway */ - rcu_read_lock(); - - elem = list_entry_rcu(state->hook_list, struct nf_hook_ops, list); + entry = rcu_dereference(state->hook_entries); next_hook: - verdict = nf_iterate(state->hook_list, skb, state, &elem); + verdict = nf_iterate(skb, state, &entry); if (verdict == NF_ACCEPT || verdict == NF_STOP) { ret = 1; } else if ((verdict & NF_VERDICT_MASK) == NF_DROP) { @@ -312,16 +361,10 @@ next_hook: if (ret == 0) ret = -EPERM; } else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) { - int err = nf_queue(skb, elem, state, - verdict >> NF_VERDICT_QBITS); - if (err < 0) { - if (err == -ESRCH && - (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) - goto next_hook; - kfree_skb(skb); - } + ret = nf_queue(skb, state, &entry, verdict); + if (ret == 1 && entry) + goto next_hook; } - rcu_read_unlock(); return ret; } EXPORT_SYMBOL(nf_hook_slow); @@ -441,7 +484,7 @@ static int __net_init netfilter_net_init(struct net *net) for (i = 0; i < ARRAY_SIZE(net->nf.hooks); i++) { for (h = 0; h < NF_MAX_HOOKS; h++) - INIT_LIST_HEAD(&net->nf.hooks[i][h]); + RCU_INIT_POINTER(net->nf.hooks[i][h], NULL); } #ifdef CONFIG_PROC_FS diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c3c809b2e712..a6e44ef2ec9a 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2845,7 +2845,7 @@ static struct genl_family ip_vs_genl_family = { .hdrsize = 0, .name = IPVS_GENL_NAME, .version = IPVS_GENL_VERSION, - .maxattr = IPVS_CMD_MAX, + .maxattr = IPVS_CMD_ATTR_MAX, .netnsok = true, /* Make ipvsadm to work on netns */ }; diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index f04fd8df210b..fc230d99aa3b 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -281,13 +281,10 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) h = nf_conntrack_find_get(cp->ipvs->net, &nf_ct_zone_dflt, &tuple); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); - /* Show what happens instead of calling nf_ct_kill() */ - if (del_timer(&ct->timeout)) { - IP_VS_DBG(7, "%s: ct=%p, deleted conntrack timer for tuple=" + if (nf_ct_kill(ct)) { + IP_VS_DBG(7, "%s: ct=%p, deleted conntrack for tuple=" FMT_TUPLE "\n", __func__, ct, ARG_TUPLE(&tuple)); - if (ct->timeout.function) - ct->timeout.function(ct->timeout.data); } else { IP_VS_DBG(7, "%s: ct=%p, no conntrack timer for tuple=" FMT_TUPLE "\n", diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 1b07578bedf3..9350530c16c1 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -283,6 +283,7 @@ struct ip_vs_sync_buff { */ static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho) { + memset(ho, 0, sizeof(*ho)); ho->init_seq = get_unaligned_be32(&no->init_seq); ho->delta = get_unaligned_be32(&no->delta); ho->previous_delta = get_unaligned_be32(&no->previous_delta); @@ -917,8 +918,10 @@ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *pa kfree(param->pe_data); } - if (opt) - memcpy(&cp->in_seq, opt, sizeof(*opt)); + if (opt) { + cp->in_seq = opt->in_seq; + cp->out_seq = opt->out_seq; + } atomic_set(&cp->in_pkts, sysctl_sync_threshold(ipvs)); cp->state = state; cp->old_state = cp->state; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index dd2c43abf9e2..0f87e5d21be7 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -72,12 +72,27 @@ EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock); struct hlist_nulls_head *nf_conntrack_hash __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_hash); +struct conntrack_gc_work { + struct delayed_work dwork; + u32 last_bucket; + bool exiting; + long next_gc_run; +}; + static __read_mostly struct kmem_cache *nf_conntrack_cachep; static __read_mostly spinlock_t nf_conntrack_locks_all_lock; -static __read_mostly seqcount_t nf_conntrack_generation; static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; +/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */ +#define GC_MAX_BUCKETS_DIV 64u +/* upper bound of scan intervals */ +#define GC_INTERVAL_MAX (2 * HZ) +/* maximum conntracks to evict per gc run */ +#define GC_MAX_EVICTS 256u + +static struct conntrack_gc_work conntrack_gc_work; + void nf_conntrack_lock(spinlock_t *lock) __acquires(lock) { spin_lock(lock); @@ -164,7 +179,7 @@ unsigned int nf_conntrack_htable_size __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; -EXPORT_SYMBOL_GPL(nf_conntrack_max); +seqcount_t nf_conntrack_generation __read_mostly; DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked); EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked); @@ -367,12 +382,10 @@ static void destroy_conntrack(struct nf_conntrack *nfct) { struct nf_conn *ct = (struct nf_conn *)nfct; - struct net *net = nf_ct_net(ct); struct nf_conntrack_l4proto *l4proto; pr_debug("destroy_conntrack(%p)\n", ct); NF_CT_ASSERT(atomic_read(&nfct->use) == 0); - NF_CT_ASSERT(!timer_pending(&ct->timeout)); if (unlikely(nf_ct_is_template(ct))) { nf_ct_tmpl_free(ct); @@ -395,7 +408,6 @@ destroy_conntrack(struct nf_conntrack *nfct) nf_ct_del_from_dying_or_unconfirmed_list(ct); - NF_CT_STAT_INC(net, delete); local_bh_enable(); if (ct->master) @@ -427,7 +439,6 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct) nf_ct_add_to_dying_list(ct); - NF_CT_STAT_INC(net, delete_list); local_bh_enable(); } @@ -435,35 +446,30 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) { struct nf_conn_tstamp *tstamp; + if (test_and_set_bit(IPS_DYING_BIT, &ct->status)) + return false; + tstamp = nf_conn_tstamp_find(ct); if (tstamp && tstamp->stop == 0) tstamp->stop = ktime_get_real_ns(); - if (nf_ct_is_dying(ct)) - goto delete; - if (nf_conntrack_event_report(IPCT_DESTROY, ct, portid, report) < 0) { - /* destroy event was not delivered */ + /* destroy event was not delivered. nf_ct_put will + * be done by event cache worker on redelivery. + */ nf_ct_delete_from_lists(ct); nf_conntrack_ecache_delayed_work(nf_ct_net(ct)); return false; } nf_conntrack_ecache_work(nf_ct_net(ct)); - set_bit(IPS_DYING_BIT, &ct->status); - delete: nf_ct_delete_from_lists(ct); nf_ct_put(ct); return true; } EXPORT_SYMBOL_GPL(nf_ct_delete); -static void death_by_timeout(unsigned long ul_conntrack) -{ - nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0); -} - static inline bool nf_ct_key_equal(struct nf_conntrack_tuple_hash *h, const struct nf_conntrack_tuple *tuple, @@ -481,22 +487,17 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h, net_eq(net, nf_ct_net(ct)); } -/* must be called with rcu read lock held */ -void nf_conntrack_get_ht(struct hlist_nulls_head **hash, unsigned int *hsize) +/* caller must hold rcu readlock and none of the nf_conntrack_locks */ +static void nf_ct_gc_expired(struct nf_conn *ct) { - struct hlist_nulls_head *hptr; - unsigned int sequence, hsz; + if (!atomic_inc_not_zero(&ct->ct_general.use)) + return; - do { - sequence = read_seqcount_begin(&nf_conntrack_generation); - hsz = nf_conntrack_htable_size; - hptr = nf_conntrack_hash; - } while (read_seqcount_retry(&nf_conntrack_generation, sequence)); + if (nf_ct_should_gc(ct)) + nf_ct_kill(ct); - *hash = hptr; - *hsize = hsz; + nf_ct_put(ct); } -EXPORT_SYMBOL_GPL(nf_conntrack_get_ht); /* * Warning : @@ -510,21 +511,26 @@ ____nf_conntrack_find(struct net *net, const struct nf_conntrack_zone *zone, struct nf_conntrack_tuple_hash *h; struct hlist_nulls_head *ct_hash; struct hlist_nulls_node *n; - unsigned int bucket, sequence; + unsigned int bucket, hsize; begin: - do { - sequence = read_seqcount_begin(&nf_conntrack_generation); - bucket = scale_hash(hash); - ct_hash = nf_conntrack_hash; - } while (read_seqcount_retry(&nf_conntrack_generation, sequence)); + nf_conntrack_get_ht(&ct_hash, &hsize); + bucket = reciprocal_scale(hash, hsize); hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[bucket], hnnode) { - if (nf_ct_key_equal(h, tuple, zone, net)) { - NF_CT_STAT_INC_ATOMIC(net, found); - return h; + struct nf_conn *ct; + + ct = nf_ct_tuplehash_to_ctrack(h); + if (nf_ct_is_expired(ct)) { + nf_ct_gc_expired(ct); + continue; } - NF_CT_STAT_INC_ATOMIC(net, searched); + + if (nf_ct_is_dying(ct)) + continue; + + if (nf_ct_key_equal(h, tuple, zone, net)) + return h; } /* * if the nulls value we got at the end of this lookup is @@ -618,7 +624,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) zone, net)) goto out; - add_timer(&ct->timeout); smp_wmb(); /* The caller holds a reference to this object */ atomic_set(&ct->ct_general.use, 2); @@ -771,8 +776,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) /* Timer relative to confirmation time, not original setting time, otherwise we'd get timer wrap in weird delay cases. */ - ct->timeout.expires += jiffies; - add_timer(&ct->timeout); + ct->timeout += nfct_time_stamp; atomic_inc(&ct->ct_general.use); ct->status |= IPS_CONFIRMED; @@ -791,7 +795,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) */ __nf_conntrack_hash_insert(ct, hash, reply_hash); nf_conntrack_double_unlock(hash, reply_hash); - NF_CT_STAT_INC(net, insert); local_bh_enable(); help = nfct_help(ct); @@ -823,29 +826,40 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_head *ct_hash; - unsigned int hash, sequence; + unsigned int hash, hsize; struct hlist_nulls_node *n; struct nf_conn *ct; zone = nf_ct_zone(ignored_conntrack); rcu_read_lock(); - do { - sequence = read_seqcount_begin(&nf_conntrack_generation); - hash = hash_conntrack(net, tuple); - ct_hash = nf_conntrack_hash; - } while (read_seqcount_retry(&nf_conntrack_generation, sequence)); + begin: + nf_conntrack_get_ht(&ct_hash, &hsize); + hash = __hash_conntrack(net, tuple, hsize); hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); - if (ct != ignored_conntrack && - nf_ct_key_equal(h, tuple, zone, net)) { + + if (ct == ignored_conntrack) + continue; + + if (nf_ct_is_expired(ct)) { + nf_ct_gc_expired(ct); + continue; + } + + if (nf_ct_key_equal(h, tuple, zone, net)) { NF_CT_STAT_INC_ATOMIC(net, found); rcu_read_unlock(); return 1; } - NF_CT_STAT_INC_ATOMIC(net, searched); } + + if (get_nulls_value(n) != hash) { + NF_CT_STAT_INC_ATOMIC(net, search_restart); + goto begin; + } + rcu_read_unlock(); return 0; @@ -867,6 +881,11 @@ static unsigned int early_drop_list(struct net *net, hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) { tmp = nf_ct_tuplehash_to_ctrack(h); + if (nf_ct_is_expired(tmp)) { + nf_ct_gc_expired(tmp); + continue; + } + if (test_bit(IPS_ASSURED_BIT, &tmp->status) || !net_eq(nf_ct_net(tmp), net) || nf_ct_is_dying(tmp)) @@ -884,7 +903,6 @@ static unsigned int early_drop_list(struct net *net, */ if (net_eq(nf_ct_net(tmp), net) && nf_ct_is_confirmed(tmp) && - del_timer(&tmp->timeout) && nf_ct_delete(tmp, 0, 0)) drops++; @@ -900,14 +918,11 @@ static noinline int early_drop(struct net *net, unsigned int _hash) for (i = 0; i < NF_CT_EVICTION_RANGE; i++) { struct hlist_nulls_head *ct_hash; - unsigned hash, sequence, drops; + unsigned int hash, hsize, drops; rcu_read_lock(); - do { - sequence = read_seqcount_begin(&nf_conntrack_generation); - hash = scale_hash(_hash++); - ct_hash = nf_conntrack_hash; - } while (read_seqcount_retry(&nf_conntrack_generation, sequence)); + nf_conntrack_get_ht(&ct_hash, &hsize); + hash = reciprocal_scale(_hash++, hsize); drops = early_drop_list(net, &ct_hash[hash]); rcu_read_unlock(); @@ -921,6 +936,99 @@ static noinline int early_drop(struct net *net, unsigned int _hash) return false; } +static void gc_worker(struct work_struct *work) +{ + unsigned int i, goal, buckets = 0, expired_count = 0; + struct conntrack_gc_work *gc_work; + unsigned int ratio, scanned = 0; + unsigned long next_run; + + gc_work = container_of(work, struct conntrack_gc_work, dwork.work); + + goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV; + i = gc_work->last_bucket; + + do { + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_head *ct_hash; + struct hlist_nulls_node *n; + unsigned int hashsz; + struct nf_conn *tmp; + + i++; + rcu_read_lock(); + + nf_conntrack_get_ht(&ct_hash, &hashsz); + if (i >= hashsz) + i = 0; + + hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) { + tmp = nf_ct_tuplehash_to_ctrack(h); + + scanned++; + if (nf_ct_is_expired(tmp)) { + nf_ct_gc_expired(tmp); + expired_count++; + continue; + } + } + + /* could check get_nulls_value() here and restart if ct + * was moved to another chain. But given gc is best-effort + * we will just continue with next hash slot. + */ + rcu_read_unlock(); + cond_resched_rcu_qs(); + } while (++buckets < goal && + expired_count < GC_MAX_EVICTS); + + if (gc_work->exiting) + return; + + /* + * Eviction will normally happen from the packet path, and not + * from this gc worker. + * + * This worker is only here to reap expired entries when system went + * idle after a busy period. + * + * The heuristics below are supposed to balance conflicting goals: + * + * 1. Minimize time until we notice a stale entry + * 2. Maximize scan intervals to not waste cycles + * + * Normally, expired_count will be 0, this increases the next_run time + * to priorize 2) above. + * + * As soon as a timed-out entry is found, move towards 1) and increase + * the scan frequency. + * In case we have lots of evictions next scan is done immediately. + */ + ratio = scanned ? expired_count * 100 / scanned : 0; + if (ratio >= 90 || expired_count == GC_MAX_EVICTS) { + gc_work->next_gc_run = 0; + next_run = 0; + } else if (expired_count) { + gc_work->next_gc_run /= 2U; + next_run = msecs_to_jiffies(1); + } else { + if (gc_work->next_gc_run < GC_INTERVAL_MAX) + gc_work->next_gc_run += msecs_to_jiffies(1); + + next_run = gc_work->next_gc_run; + } + + gc_work->last_bucket = i; + queue_delayed_work(system_long_wq, &gc_work->dwork, next_run); +} + +static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work) +{ + INIT_DELAYED_WORK(&gc_work->dwork, gc_worker); + gc_work->next_gc_run = GC_INTERVAL_MAX; + gc_work->exiting = false; +} + static struct nf_conn * __nf_conntrack_alloc(struct net *net, const struct nf_conntrack_zone *zone, @@ -957,8 +1065,6 @@ __nf_conntrack_alloc(struct net *net, /* save hash for reusing when confirming */ *(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash; ct->status = 0; - /* Don't set timer yet: wait for confirmation */ - setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct); write_pnet(&ct->ct_net, net); memset(&ct->__nfct_init_offset[0], 0, offsetof(struct nf_conn, proto) - @@ -1035,9 +1141,9 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, if (IS_ERR(ct)) return (struct nf_conntrack_tuple_hash *)ct; - if (tmpl && nfct_synproxy(tmpl)) { - nfct_seqadj_ext_add(ct); - nfct_synproxy_ext_add(ct); + if (!nf_ct_add_synproxy(ct, tmpl)) { + nf_conntrack_free(ct); + return ERR_PTR(-ENOMEM); } timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL; @@ -1096,10 +1202,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } spin_unlock(&nf_conntrack_expect_lock); } - if (!exp) { + if (!exp) __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC); - NF_CT_STAT_INC(net, new); - } /* Now it is inserted into the unconfirmed list, bump refcount */ nf_conntrack_get(&ct->ct_general); @@ -1204,7 +1308,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, skb->nfct = NULL; } - /* rcu_read_lock()ed by nf_hook_slow */ + /* rcu_read_lock()ed by nf_hook_thresh */ l3proto = __nf_ct_l3proto_find(pf); ret = l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff, &protonum); @@ -1332,7 +1436,6 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, unsigned long extra_jiffies, int do_acct) { - NF_CT_ASSERT(ct->timeout.data == (unsigned long)ct); NF_CT_ASSERT(skb); /* Only update if this is not a fixed timeout */ @@ -1340,39 +1443,25 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, goto acct; /* If not in hash table, timer will not be active yet */ - if (!nf_ct_is_confirmed(ct)) { - ct->timeout.expires = extra_jiffies; - } else { - unsigned long newtime = jiffies + extra_jiffies; - - /* Only update the timeout if the new timeout is at least - HZ jiffies from the old timeout. Need del_timer for race - avoidance (may already be dying). */ - if (newtime - ct->timeout.expires >= HZ) - mod_timer_pending(&ct->timeout, newtime); - } + if (nf_ct_is_confirmed(ct)) + extra_jiffies += nfct_time_stamp; + ct->timeout = extra_jiffies; acct: if (do_acct) nf_ct_acct_update(ct, ctinfo, skb->len); } EXPORT_SYMBOL_GPL(__nf_ct_refresh_acct); -bool __nf_ct_kill_acct(struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - const struct sk_buff *skb, - int do_acct) +bool nf_ct_kill_acct(struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + const struct sk_buff *skb) { - if (do_acct) - nf_ct_acct_update(ct, ctinfo, skb->len); + nf_ct_acct_update(ct, ctinfo, skb->len); - if (del_timer(&ct->timeout)) { - ct->timeout.function((unsigned long)ct); - return true; - } - return false; + return nf_ct_delete(ct, 0, 0); } -EXPORT_SYMBOL_GPL(__nf_ct_kill_acct); +EXPORT_SYMBOL_GPL(nf_ct_kill_acct); #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -1505,11 +1594,8 @@ void nf_ct_iterate_cleanup(struct net *net, while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) { /* Time to push up daises... */ - if (del_timer(&ct->timeout)) - nf_ct_delete(ct, portid, report); - - /* ... else the timer will get him soon. */ + nf_ct_delete(ct, portid, report); nf_ct_put(ct); cond_resched(); } @@ -1545,6 +1631,7 @@ static int untrack_refs(void) void nf_conntrack_cleanup_start(void) { + conntrack_gc_work.exiting = true; RCU_INIT_POINTER(ip_ct_attach, NULL); } @@ -1554,6 +1641,7 @@ void nf_conntrack_cleanup_end(void) while (untrack_refs() > 0) schedule(); + cancel_delayed_work_sync(&conntrack_gc_work.dwork); nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size); nf_conntrack_proto_fini(); @@ -1828,6 +1916,10 @@ int nf_conntrack_init_start(void) } /* - and look it like as a confirmed connection */ nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED); + + conntrack_gc_work_init(&conntrack_gc_work); + queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, GC_INTERVAL_MAX); + return 0; err_proto: diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index d28011b42845..da9df2d56e66 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -49,8 +49,13 @@ static enum retry_state ecache_work_evict_list(struct ct_pcpu *pcpu) hlist_nulls_for_each_entry(h, n, &pcpu->dying, hnnode) { struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + struct nf_conntrack_ecache *e; - if (nf_ct_is_dying(ct)) + if (!nf_ct_is_confirmed(ct)) + continue; + + e = nf_ct_ecache_find(ct); + if (!e || e->state != NFCT_ECACHE_DESTROY_FAIL) continue; if (nf_conntrack_event(IPCT_DESTROY, ct)) { @@ -58,8 +63,7 @@ static enum retry_state ecache_work_evict_list(struct ct_pcpu *pcpu) break; } - /* we've got the event delivered, now it's dying */ - set_bit(IPS_DYING_BIT, &ct->status); + e->state = NFCT_ECACHE_DESTROY_SENT; refs[evicted] = ct; if (++evicted >= ARRAY_SIZE(refs)) { @@ -130,7 +134,7 @@ int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct, if (!e) goto out_unlock; - if (nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct)) { + if (nf_ct_is_confirmed(ct)) { struct nf_ct_event item = { .ct = ct, .portid = e->portid ? e->portid : portid, @@ -150,11 +154,13 @@ int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct, * triggered by a process, we store the PORTID * to include it in the retransmission. */ - if (eventmask & (1 << IPCT_DESTROY) && - e->portid == 0 && portid != 0) - e->portid = portid; - else + if (eventmask & (1 << IPCT_DESTROY)) { + if (e->portid == 0 && portid != 0) + e->portid = portid; + e->state = NFCT_ECACHE_DESTROY_FAIL; + } else { e->missed |= eventmask; + } } else { e->missed &= ~missed; } diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 43147005bea3..e3ed20060878 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -237,7 +237,7 @@ static int try_eprt(const char *data, size_t dlen, struct nf_conntrack_man *cmd, } delim = data[0]; if (isdigit(delim) || delim < 33 || delim > 126 || data[2] != delim) { - pr_debug("try_eprt: invalid delimitter.\n"); + pr_debug("try_eprt: invalid delimiter.\n"); return 0; } @@ -301,8 +301,6 @@ static int find_pattern(const char *data, size_t dlen, size_t i = plen; pr_debug("find_pattern `%s': dlen = %Zu\n", pattern, dlen); - if (dlen == 0) - return 0; if (dlen <= plen) { /* Short packet: try for partial? */ @@ -311,19 +309,8 @@ static int find_pattern(const char *data, size_t dlen, else return 0; } - if (strncasecmp(data, pattern, plen) != 0) { -#if 0 - size_t i; - - pr_debug("ftp: string mismatch\n"); - for (i = 0; i < plen; i++) { - pr_debug("ftp:char %u `%c'(%u) vs `%c'(%u)\n", - i, data[i], data[i], - pattern[i], pattern[i]); - } -#endif + if (strncasecmp(data, pattern, plen) != 0) return 0; - } pr_debug("Pattern matches!\n"); /* Now we've found the constant string, try to skip diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 5c0db5c64734..f65d93639d12 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -736,7 +736,7 @@ static int callforward_do_filter(struct net *net, const struct nf_afinfo *afinfo; int ret = 0; - /* rcu_read_lock()ed by nf_hook_slow() */ + /* rcu_read_lock()ed by nf_hook_thresh */ afinfo = nf_get_afinfo(family); if (!afinfo) return 0; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index b989b81ac156..7341adf7059d 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -138,9 +138,14 @@ __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum) for (i = 0; i < nf_ct_helper_hsize; i++) { hlist_for_each_entry_rcu(h, &nf_ct_helper_hash[i], hnode) { - if (!strcmp(h->name, name) && - h->tuple.src.l3num == l3num && - h->tuple.dst.protonum == protonum) + if (strcmp(h->name, name)) + continue; + + if (h->tuple.src.l3num != NFPROTO_UNSPEC && + h->tuple.src.l3num != l3num) + continue; + + if (h->tuple.dst.protonum == protonum) return h; } } @@ -189,7 +194,6 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, struct nf_conntrack_helper *helper = NULL; struct nf_conn_help *help; struct net *net = nf_ct_net(ct); - int ret = 0; /* We already got a helper explicitly attached. The function * nf_conntrack_alter_reply - in case NAT is in use - asks for looking @@ -223,15 +227,13 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, if (helper == NULL) { if (help) RCU_INIT_POINTER(help->helper, NULL); - goto out; + return 0; } if (help == NULL) { help = nf_ct_helper_ext_add(ct, helper, flags); - if (help == NULL) { - ret = -ENOMEM; - goto out; - } + if (help == NULL) + return -ENOMEM; } else { /* We only allow helper re-assignment of the same sort since * we cannot reallocate the helper extension area. @@ -240,13 +242,13 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, if (tmp && tmp->help != helper->help) { RCU_INIT_POINTER(help->helper, NULL); - goto out; + return 0; } } rcu_assign_pointer(help->helper, helper); -out: - return ret; + + return 0; } EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); @@ -349,7 +351,7 @@ void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct, /* Called from the helper function, this call never fails */ help = nfct_help(ct); - /* rcu_read_lock()ed by nf_hook_slow */ + /* rcu_read_lock()ed by nf_hook_thresh */ helper = rcu_dereference(help->helper); nf_log_packet(nf_ct_net(ct), nf_ct_l3num(ct), 0, skb, NULL, NULL, NULL, diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index fdfc71f416b7..27540455dc62 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -149,10 +149,7 @@ nla_put_failure: static int ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct) { - long timeout = ((long)ct->timeout.expires - (long)jiffies) / HZ; - - if (timeout < 0) - timeout = 0; + long timeout = nf_ct_expires(ct) / HZ; if (nla_put_be32(skb, CTA_TIMEOUT, htonl(timeout))) goto nla_put_failure; @@ -818,14 +815,23 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_nulls_node *n; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; - int res; + struct nf_conn *nf_ct_evict[8]; + int res, i; spinlock_t *lockp; last = (struct nf_conn *)cb->args[1]; + i = 0; local_bh_disable(); for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) { restart: + while (i) { + i--; + if (nf_ct_should_gc(nf_ct_evict[i])) + nf_ct_kill(nf_ct_evict[i]); + nf_ct_put(nf_ct_evict[i]); + } + lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS]; nf_conntrack_lock(lockp); if (cb->args[0] >= nf_conntrack_htable_size) { @@ -837,6 +843,13 @@ restart: if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; ct = nf_ct_tuplehash_to_ctrack(h); + if (nf_ct_is_expired(ct)) { + if (i < ARRAY_SIZE(nf_ct_evict) && + atomic_inc_not_zero(&ct->ct_general.use)) + nf_ct_evict[i++] = ct; + continue; + } + if (!net_eq(net, nf_ct_net(ct))) continue; @@ -878,6 +891,13 @@ out: if (last) nf_ct_put(last); + while (i) { + i--; + if (nf_ct_should_gc(nf_ct_evict[i])) + nf_ct_kill(nf_ct_evict[i]); + nf_ct_put(nf_ct_evict[i]); + } + return skb->len; } @@ -1147,9 +1167,7 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, } } - if (del_timer(&ct->timeout)) - nf_ct_delete(ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); - + nf_ct_delete(ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_put(ct); return 0; @@ -1517,11 +1535,10 @@ static int ctnetlink_change_timeout(struct nf_conn *ct, { u_int32_t timeout = ntohl(nla_get_be32(cda[CTA_TIMEOUT])); - if (!del_timer(&ct->timeout)) - return -ETIME; + ct->timeout = nfct_time_stamp + timeout * HZ; - ct->timeout.expires = jiffies + timeout * HZ; - add_timer(&ct->timeout); + if (test_bit(IPS_DYING_BIT, &ct->status)) + return -ETIME; return 0; } @@ -1719,9 +1736,8 @@ ctnetlink_create_conntrack(struct net *net, if (!cda[CTA_TIMEOUT]) goto err1; - ct->timeout.expires = ntohl(nla_get_be32(cda[CTA_TIMEOUT])); - ct->timeout.expires = jiffies + ct->timeout.expires * HZ; + ct->timeout = nfct_time_stamp + ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; rcu_read_lock(); if (cda[CTA_HELP]) { @@ -1968,13 +1984,9 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(cpu); - if (nla_put_be32(skb, CTA_STATS_SEARCHED, htonl(st->searched)) || - nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || - nla_put_be32(skb, CTA_STATS_NEW, htonl(st->new)) || + if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || nla_put_be32(skb, CTA_STATS_IGNORE, htonl(st->ignore)) || - nla_put_be32(skb, CTA_STATS_DELETE, htonl(st->delete)) || - nla_put_be32(skb, CTA_STATS_DELETE_LIST, htonl(st->delete_list)) || nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) || nla_put_be32(skb, CTA_STATS_INSERT_FAILED, htonl(st->insert_failed)) || diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 5588c7ae1ac2..f60a4755d71e 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -157,8 +157,7 @@ static int destroy_sibling_or_exp(struct net *net, struct nf_conn *ct, pr_debug("setting timeout of conntrack %p to 0\n", sibling); sibling->proto.gre.timeout = 0; sibling->proto.gre.stream_timeout = 0; - if (del_timer(&sibling->timeout)) - sibling->timeout.function((unsigned long)sibling); + nf_ct_kill(sibling); nf_ct_put(sibling); return 1; } else { diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index b65d5864b6d9..8d2c7d8c666a 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -159,54 +159,6 @@ static int kill_l4proto(struct nf_conn *i, void *data) nf_ct_l3num(i) == l4proto->l3proto; } -static struct nf_ip_net *nf_ct_l3proto_net(struct net *net, - struct nf_conntrack_l3proto *l3proto) -{ - if (l3proto->l3proto == PF_INET) - return &net->ct.nf_ct_proto; - else - return NULL; -} - -static int nf_ct_l3proto_register_sysctl(struct net *net, - struct nf_conntrack_l3proto *l3proto) -{ - int err = 0; - struct nf_ip_net *in = nf_ct_l3proto_net(net, l3proto); - /* nf_conntrack_l3proto_ipv6 doesn't support sysctl */ - if (in == NULL) - return 0; - -#if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) - if (in->ctl_table != NULL) { - err = nf_ct_register_sysctl(net, - &in->ctl_table_header, - l3proto->ctl_table_path, - in->ctl_table); - if (err < 0) { - kfree(in->ctl_table); - in->ctl_table = NULL; - } - } -#endif - return err; -} - -static void nf_ct_l3proto_unregister_sysctl(struct net *net, - struct nf_conntrack_l3proto *l3proto) -{ - struct nf_ip_net *in = nf_ct_l3proto_net(net, l3proto); - - if (in == NULL) - return; -#if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) - if (in->ctl_table_header != NULL) - nf_ct_unregister_sysctl(&in->ctl_table_header, - &in->ctl_table, - 0); -#endif -} - int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto) { int ret = 0; @@ -241,7 +193,7 @@ EXPORT_SYMBOL_GPL(nf_ct_l3proto_register); int nf_ct_l3proto_pernet_register(struct net *net, struct nf_conntrack_l3proto *proto) { - int ret = 0; + int ret; if (proto->init_net) { ret = proto->init_net(net); @@ -249,7 +201,7 @@ int nf_ct_l3proto_pernet_register(struct net *net, return ret; } - return nf_ct_l3proto_register_sysctl(net, proto); + return 0; } EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_register); @@ -272,8 +224,6 @@ EXPORT_SYMBOL_GPL(nf_ct_l3proto_unregister); void nf_ct_l3proto_pernet_unregister(struct net *net, struct nf_conntrack_l3proto *proto) { - nf_ct_l3proto_unregister_sysctl(net, proto); - /* Remove all contrack entries for this protocol */ nf_ct_iterate_cleanup(net, kill_l3proto, proto, 0, 0); } @@ -312,26 +262,6 @@ int nf_ct_l4proto_register_sysctl(struct net *net, } } } -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - if (l4proto->l3proto != AF_INET6 && pn->ctl_compat_table != NULL) { - if (err < 0) { - nf_ct_kfree_compat_sysctl_table(pn); - goto out; - } - err = nf_ct_register_sysctl(net, - &pn->ctl_compat_header, - "net/ipv4/netfilter", - pn->ctl_compat_table); - if (err == 0) - goto out; - - nf_ct_kfree_compat_sysctl_table(pn); - nf_ct_unregister_sysctl(&pn->ctl_table_header, - &pn->ctl_table, - pn->users); - } -out: -#endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ return err; } @@ -346,13 +276,6 @@ void nf_ct_l4proto_unregister_sysctl(struct net *net, nf_ct_unregister_sysctl(&pn->ctl_table_header, &pn->ctl_table, pn->users); - -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - if (l4proto->l3proto != AF_INET6 && pn->ctl_compat_header != NULL) - nf_ct_unregister_sysctl(&pn->ctl_compat_header, - &pn->ctl_compat_table, - 0); -#endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 399a38fd685a..a45bee52dccc 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -402,7 +402,8 @@ static bool dccp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, { struct dccp_hdr _hdr, *dh; - dh = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); + /* Actually only need first 4 bytes to get ports. */ + dh = skb_header_pointer(skb, dataoff, 4, &_hdr); if (dh == NULL) return false; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 86dc752e5349..d5868bad33a7 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -151,17 +151,6 @@ static struct ctl_table generic_sysctl_table[] = { }, { } }; -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT -static struct ctl_table generic_compat_sysctl_table[] = { - { - .procname = "ip_conntrack_generic_timeout", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { } -}; -#endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ static int generic_kmemdup_sysctl_table(struct nf_proto_net *pn, @@ -179,40 +168,14 @@ static int generic_kmemdup_sysctl_table(struct nf_proto_net *pn, return 0; } -static int generic_kmemdup_compat_sysctl_table(struct nf_proto_net *pn, - struct nf_generic_net *gn) -{ -#ifdef CONFIG_SYSCTL -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - pn->ctl_compat_table = kmemdup(generic_compat_sysctl_table, - sizeof(generic_compat_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_compat_table) - return -ENOMEM; - - pn->ctl_compat_table[0].data = &gn->timeout; -#endif -#endif - return 0; -} - static int generic_init_net(struct net *net, u_int16_t proto) { - int ret; struct nf_generic_net *gn = generic_pernet(net); struct nf_proto_net *pn = &gn->pn; gn->timeout = nf_ct_generic_timeout; - ret = generic_kmemdup_compat_sysctl_table(pn, gn); - if (ret < 0) - return ret; - - ret = generic_kmemdup_sysctl_table(pn, gn); - if (ret < 0) - nf_ct_kfree_compat_sysctl_table(pn); - - return ret; + return generic_kmemdup_sysctl_table(pn, gn); } static struct nf_proto_net *generic_get_net_proto(struct net *net) diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index a96451a7af20..9a715f88b2f1 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -192,15 +192,15 @@ static bool gre_invert_tuple(struct nf_conntrack_tuple *tuple, static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { - const struct gre_hdr_pptp *pgrehdr; - struct gre_hdr_pptp _pgrehdr; + const struct pptp_gre_header *pgrehdr; + struct pptp_gre_header _pgrehdr; __be16 srckey; - const struct gre_hdr *grehdr; - struct gre_hdr _grehdr; + const struct gre_base_hdr *grehdr; + struct gre_base_hdr _grehdr; /* first only delinearize old RFC1701 GRE header */ grehdr = skb_header_pointer(skb, dataoff, sizeof(_grehdr), &_grehdr); - if (!grehdr || grehdr->version != GRE_VERSION_PPTP) { + if (!grehdr || (grehdr->flags & GRE_VERSION) != GRE_VERSION_1) { /* try to behave like "nf_conntrack_proto_generic" */ tuple->src.u.all = 0; tuple->dst.u.all = 0; @@ -212,8 +212,8 @@ static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, if (!pgrehdr) return true; - if (ntohs(grehdr->protocol) != GRE_PROTOCOL_PPTP) { - pr_debug("GRE_VERSION_PPTP but unknown proto\n"); + if (grehdr->protocol != GRE_PROTO_PPP) { + pr_debug("Unsupported GRE proto(0x%x)\n", ntohs(grehdr->protocol)); return false; } diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 1d7ab960a9e6..982ea62606c7 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -161,8 +161,8 @@ static bool sctp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, const struct sctphdr *hp; struct sctphdr _hdr; - /* Actually only need first 8 bytes. */ - hp = skb_header_pointer(skb, dataoff, 8, &_hdr); + /* Actually only need first 4 bytes to get ports. */ + hp = skb_header_pointer(skb, dataoff, 4, &_hdr); if (hp == NULL) return false; @@ -705,54 +705,6 @@ static struct ctl_table sctp_sysctl_table[] = { }, { } }; - -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT -static struct ctl_table sctp_compat_sysctl_table[] = { - { - .procname = "ip_conntrack_sctp_timeout_closed", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_sctp_timeout_cookie_wait", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_sctp_timeout_cookie_echoed", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_sctp_timeout_established", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_sctp_timeout_shutdown_sent", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_sctp_timeout_shutdown_recd", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_sctp_timeout_shutdown_ack_sent", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { } -}; -#endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn, @@ -781,32 +733,8 @@ static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn, return 0; } -static int sctp_kmemdup_compat_sysctl_table(struct nf_proto_net *pn, - struct sctp_net *sn) -{ -#ifdef CONFIG_SYSCTL -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - pn->ctl_compat_table = kmemdup(sctp_compat_sysctl_table, - sizeof(sctp_compat_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_compat_table) - return -ENOMEM; - - pn->ctl_compat_table[0].data = &sn->timeouts[SCTP_CONNTRACK_CLOSED]; - pn->ctl_compat_table[1].data = &sn->timeouts[SCTP_CONNTRACK_COOKIE_WAIT]; - pn->ctl_compat_table[2].data = &sn->timeouts[SCTP_CONNTRACK_COOKIE_ECHOED]; - pn->ctl_compat_table[3].data = &sn->timeouts[SCTP_CONNTRACK_ESTABLISHED]; - pn->ctl_compat_table[4].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_SENT]; - pn->ctl_compat_table[5].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_RECD]; - pn->ctl_compat_table[6].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT]; -#endif -#endif - return 0; -} - static int sctp_init_net(struct net *net, u_int16_t proto) { - int ret; struct sctp_net *sn = sctp_pernet(net); struct nf_proto_net *pn = &sn->pn; @@ -817,18 +745,7 @@ static int sctp_init_net(struct net *net, u_int16_t proto) sn->timeouts[i] = sctp_timeouts[i]; } - if (proto == AF_INET) { - ret = sctp_kmemdup_compat_sysctl_table(pn, sn); - if (ret < 0) - return ret; - - ret = sctp_kmemdup_sysctl_table(pn, sn); - if (ret < 0) - nf_ct_kfree_compat_sysctl_table(pn); - } else - ret = sctp_kmemdup_sysctl_table(pn, sn); - - return ret; + return sctp_kmemdup_sysctl_table(pn, sn); } static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 70c8381641a7..69f687740c76 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -282,8 +282,8 @@ static bool tcp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *hp; struct tcphdr _hdr; - /* Actually only need first 8 bytes. */ - hp = skb_header_pointer(skb, dataoff, 8, &_hdr); + /* Actually only need first 4 bytes to get ports. */ + hp = skb_header_pointer(skb, dataoff, 4, &_hdr); if (hp == NULL) return false; @@ -1481,90 +1481,6 @@ static struct ctl_table tcp_sysctl_table[] = { }, { } }; - -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT -static struct ctl_table tcp_compat_sysctl_table[] = { - { - .procname = "ip_conntrack_tcp_timeout_syn_sent", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_tcp_timeout_syn_sent2", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_tcp_timeout_syn_recv", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_tcp_timeout_established", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_tcp_timeout_fin_wait", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_tcp_timeout_close_wait", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_tcp_timeout_last_ack", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_tcp_timeout_time_wait", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_tcp_timeout_close", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_tcp_timeout_max_retrans", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_tcp_loose", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "ip_conntrack_tcp_be_liberal", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "ip_conntrack_tcp_max_retrans", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { } -}; -#endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ static int tcp_kmemdup_sysctl_table(struct nf_proto_net *pn, @@ -1597,38 +1513,8 @@ static int tcp_kmemdup_sysctl_table(struct nf_proto_net *pn, return 0; } -static int tcp_kmemdup_compat_sysctl_table(struct nf_proto_net *pn, - struct nf_tcp_net *tn) -{ -#ifdef CONFIG_SYSCTL -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - pn->ctl_compat_table = kmemdup(tcp_compat_sysctl_table, - sizeof(tcp_compat_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_compat_table) - return -ENOMEM; - - pn->ctl_compat_table[0].data = &tn->timeouts[TCP_CONNTRACK_SYN_SENT]; - pn->ctl_compat_table[1].data = &tn->timeouts[TCP_CONNTRACK_SYN_SENT2]; - pn->ctl_compat_table[2].data = &tn->timeouts[TCP_CONNTRACK_SYN_RECV]; - pn->ctl_compat_table[3].data = &tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; - pn->ctl_compat_table[4].data = &tn->timeouts[TCP_CONNTRACK_FIN_WAIT]; - pn->ctl_compat_table[5].data = &tn->timeouts[TCP_CONNTRACK_CLOSE_WAIT]; - pn->ctl_compat_table[6].data = &tn->timeouts[TCP_CONNTRACK_LAST_ACK]; - pn->ctl_compat_table[7].data = &tn->timeouts[TCP_CONNTRACK_TIME_WAIT]; - pn->ctl_compat_table[8].data = &tn->timeouts[TCP_CONNTRACK_CLOSE]; - pn->ctl_compat_table[9].data = &tn->timeouts[TCP_CONNTRACK_RETRANS]; - pn->ctl_compat_table[10].data = &tn->tcp_loose; - pn->ctl_compat_table[11].data = &tn->tcp_be_liberal; - pn->ctl_compat_table[12].data = &tn->tcp_max_retrans; -#endif -#endif - return 0; -} - static int tcp_init_net(struct net *net, u_int16_t proto) { - int ret; struct nf_tcp_net *tn = tcp_pernet(net); struct nf_proto_net *pn = &tn->pn; @@ -1643,18 +1529,7 @@ static int tcp_init_net(struct net *net, u_int16_t proto) tn->tcp_max_retrans = nf_ct_tcp_max_retrans; } - if (proto == AF_INET) { - ret = tcp_kmemdup_compat_sysctl_table(pn, tn); - if (ret < 0) - return ret; - - ret = tcp_kmemdup_sysctl_table(pn, tn); - if (ret < 0) - nf_ct_kfree_compat_sysctl_table(pn); - } else - ret = tcp_kmemdup_sysctl_table(pn, tn); - - return ret; + return tcp_kmemdup_sysctl_table(pn, tn); } static struct nf_proto_net *tcp_get_net_proto(struct net *net) diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 4fd040575ffe..20f35ed68030 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -44,8 +44,8 @@ static bool udp_pkt_to_tuple(const struct sk_buff *skb, const struct udphdr *hp; struct udphdr _hdr; - /* Actually only need first 8 bytes. */ - hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); + /* Actually only need first 4 bytes to get ports. */ + hp = skb_header_pointer(skb, dataoff, 4, &_hdr); if (hp == NULL) return false; @@ -218,23 +218,6 @@ static struct ctl_table udp_sysctl_table[] = { }, { } }; -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT -static struct ctl_table udp_compat_sysctl_table[] = { - { - .procname = "ip_conntrack_udp_timeout", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "ip_conntrack_udp_timeout_stream", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { } -}; -#endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ static int udp_kmemdup_sysctl_table(struct nf_proto_net *pn, @@ -254,27 +237,8 @@ static int udp_kmemdup_sysctl_table(struct nf_proto_net *pn, return 0; } -static int udp_kmemdup_compat_sysctl_table(struct nf_proto_net *pn, - struct nf_udp_net *un) -{ -#ifdef CONFIG_SYSCTL -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - pn->ctl_compat_table = kmemdup(udp_compat_sysctl_table, - sizeof(udp_compat_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_compat_table) - return -ENOMEM; - - pn->ctl_compat_table[0].data = &un->timeouts[UDP_CT_UNREPLIED]; - pn->ctl_compat_table[1].data = &un->timeouts[UDP_CT_REPLIED]; -#endif -#endif - return 0; -} - static int udp_init_net(struct net *net, u_int16_t proto) { - int ret; struct nf_udp_net *un = udp_pernet(net); struct nf_proto_net *pn = &un->pn; @@ -285,18 +249,7 @@ static int udp_init_net(struct net *net, u_int16_t proto) un->timeouts[i] = udp_timeouts[i]; } - if (proto == AF_INET) { - ret = udp_kmemdup_compat_sysctl_table(pn, un); - if (ret < 0) - return ret; - - ret = udp_kmemdup_sysctl_table(pn, un); - if (ret < 0) - nf_ct_kfree_compat_sysctl_table(pn); - } else - ret = udp_kmemdup_sysctl_table(pn, un); - - return ret; + return udp_kmemdup_sysctl_table(pn, un); } static struct nf_proto_net *udp_get_net_proto(struct net *net) diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 9d692f5adb94..029206e8dec4 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -54,7 +54,8 @@ static bool udplite_pkt_to_tuple(const struct sk_buff *skb, const struct udphdr *hp; struct udphdr _hdr; - hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); + /* Actually only need first 4 bytes to get ports. */ + hp = skb_header_pointer(skb, dataoff, 4, &_hdr); if (hp == NULL) return false; diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index dff0f0cc59e4..ef7063eced7c 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -169,7 +169,7 @@ int nf_ct_seq_adjust(struct sk_buff *skb, s32 seqoff, ackoff; struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); struct nf_ct_seqadj *this_way, *other_way; - int res; + int res = 1; this_way = &seqadj->seq[dir]; other_way = &seqadj->seq[!dir]; @@ -184,27 +184,31 @@ int nf_ct_seq_adjust(struct sk_buff *skb, else seqoff = this_way->offset_before; + newseq = htonl(ntohl(tcph->seq) + seqoff); + inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, false); + pr_debug("Adjusting sequence number from %u->%u\n", + ntohl(tcph->seq), ntohl(newseq)); + tcph->seq = newseq; + + if (!tcph->ack) + goto out; + if (after(ntohl(tcph->ack_seq) - other_way->offset_before, other_way->correction_pos)) ackoff = other_way->offset_after; else ackoff = other_way->offset_before; - newseq = htonl(ntohl(tcph->seq) + seqoff); newack = htonl(ntohl(tcph->ack_seq) - ackoff); - - inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, false); inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, false); - - pr_debug("Adjusting sequence number from %u->%u, ack from %u->%u\n", + pr_debug("Adjusting ack number from %u->%u, ack from %u->%u\n", ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), ntohl(newack)); - - tcph->seq = newseq; tcph->ack_seq = newack; res = nf_ct_sack_adjust(skb, protoff, tcph, ct, ctinfo); +out: spin_unlock_bh(&ct->lock); return res; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 7d77217de6a3..c3fc14e021ec 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -83,9 +83,10 @@ static int digits_len(const struct nf_conn *ct, const char *dptr, static int iswordc(const char c) { if (isalnum(c) || c == '!' || c == '"' || c == '%' || - (c >= '(' && c <= '/') || c == ':' || c == '<' || c == '>' || + (c >= '(' && c <= '+') || c == ':' || c == '<' || c == '>' || c == '?' || (c >= '[' && c <= ']') || c == '_' || c == '`' || - c == '{' || c == '}' || c == '~') + c == '{' || c == '}' || c == '~' || (c >= '-' && c <= '/') || + c == '\'') return 1; return 0; } @@ -329,13 +330,12 @@ static const char *sip_follow_continuation(const char *dptr, const char *limit) static const char *sip_skip_whitespace(const char *dptr, const char *limit) { for (; dptr < limit; dptr++) { - if (*dptr == ' ') + if (*dptr == ' ' || *dptr == '\t') continue; if (*dptr != '\r' && *dptr != '\n') break; dptr = sip_follow_continuation(dptr, limit); - if (dptr == NULL) - return NULL; + break; } return dptr; } @@ -1436,9 +1436,12 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, handler = &sip_handlers[i]; if (handler->request == NULL) continue; - if (*datalen < handler->len || + if (*datalen < handler->len + 2 || strncasecmp(*dptr, handler->method, handler->len)) continue; + if ((*dptr)[handler->len] != ' ' || + !isalpha((*dptr)[handler->len+1])) + continue; if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CSEQ, &matchoff, &matchlen) <= 0) { diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 9f267c3ffb39..5f446cd9f3fd 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -212,6 +212,11 @@ static int ct_seq_show(struct seq_file *s, void *v) if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) return 0; + if (nf_ct_should_gc(ct)) { + nf_ct_kill(ct); + goto release; + } + /* we only want to print DIR_ORIGINAL */ if (NF_CT_DIRECTION(hash)) goto release; @@ -228,8 +233,7 @@ static int ct_seq_show(struct seq_file *s, void *v) seq_printf(s, "%-8s %u %-8s %u %ld ", l3proto->name, nf_ct_l3num(ct), l4proto->name, nf_ct_protonum(ct), - timer_pending(&ct->timeout) - ? (long)(ct->timeout.expires - jiffies)/HZ : 0); + nf_ct_expires(ct) / HZ); if (l4proto->print_conntrack) l4proto->print_conntrack(s, ct); @@ -353,13 +357,13 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", nr_conntracks, - st->searched, + 0, st->found, - st->new, + 0, st->invalid, st->ignore, - st->delete, - st->delete_list, + 0, + 0, st->insert, st->insert_failed, st->drop, diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 065522564ac6..9fdb655f85bc 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -13,13 +13,13 @@ /* core.c */ -unsigned int nf_iterate(struct list_head *head, struct sk_buff *skb, - struct nf_hook_state *state, struct nf_hook_ops **elemp); +unsigned int nf_iterate(struct sk_buff *skb, struct nf_hook_state *state, + struct nf_hook_entry **entryp); /* nf_queue.c */ -int nf_queue(struct sk_buff *skb, struct nf_hook_ops *elem, - struct nf_hook_state *state, unsigned int queuenum); -void nf_queue_nf_hook_drop(struct net *net, struct nf_hook_ops *ops); +int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, + struct nf_hook_entry **entryp, unsigned int verdict); +void nf_queue_nf_hook_drop(struct net *net, const struct nf_hook_entry *entry); int __init netfilter_queue_init(void); /* nf_log.c */ diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index aa5847a16713..3dca90dc24ad 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -39,12 +39,12 @@ static struct nf_logger *__find_logger(int pf, const char *str_logger) return NULL; } -void nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger) +int nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger) { const struct nf_logger *log; - if (pf == NFPROTO_UNSPEC) - return; + if (pf == NFPROTO_UNSPEC || pf >= ARRAY_SIZE(net->nf.nf_loggers)) + return -EOPNOTSUPP; mutex_lock(&nf_log_mutex); log = nft_log_dereference(net->nf.nf_loggers[pf]); @@ -52,6 +52,8 @@ void nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger) rcu_assign_pointer(net->nf.nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); + + return 0; } EXPORT_SYMBOL(nf_log_set); @@ -420,7 +422,7 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write, char buf[NFLOGGER_NAME_LEN]; int r = 0; int tindex = (unsigned long)table->extra1; - struct net *net = current->nsproxy->net_ns; + struct net *net = table->extra2; if (write) { struct ctl_table tmp = *table; @@ -474,7 +476,6 @@ static int netfilter_log_sysctl_init(struct net *net) 3, "%d", i); nf_log_sysctl_table[i].procname = nf_log_sysctl_fnames[i]; - nf_log_sysctl_table[i].data = NULL; nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN; nf_log_sysctl_table[i].mode = 0644; nf_log_sysctl_table[i].proc_handler = @@ -484,6 +485,9 @@ static int netfilter_log_sysctl_init(struct net *net) } } + for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) + table[i].extra2 = net; + net->nf.nf_log_dir_header = register_net_sysctl(net, "net/netfilter/nf_log", table); diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c index a5aa5967b8e1..119fe1cb1ea9 100644 --- a/net/netfilter/nf_log_common.c +++ b/net/netfilter/nf_log_common.c @@ -77,7 +77,7 @@ int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, nf_log_buf_add(m, "SPT=%u DPT=%u ", ntohs(th->source), ntohs(th->dest)); /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ - if (logflags & XT_LOG_TCPSEQ) { + if (logflags & NF_LOG_TCPSEQ) { nf_log_buf_add(m, "SEQ=%u ACK=%u ", ntohl(th->seq), ntohl(th->ack_seq)); } @@ -107,7 +107,7 @@ int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, /* Max length: 11 "URGP=65535 " */ nf_log_buf_add(m, "URGP=%u ", ntohs(th->urg_ptr)); - if ((logflags & XT_LOG_TCPOPT) && th->doff*4 > sizeof(struct tcphdr)) { + if ((logflags & NF_LOG_TCPOPT) && th->doff*4 > sizeof(struct tcphdr)) { u_int8_t _opt[60 - sizeof(struct tcphdr)]; const u_int8_t *op; unsigned int i; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index de31818417b8..bbb8f3df79f7 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -441,7 +441,8 @@ nf_nat_setup_info(struct nf_conn *ct, ct->status |= IPS_DST_NAT; if (nfct_help(ct)) - nfct_seqadj_ext_add(ct); + if (!nfct_seqadj_ext_add(ct)) + return NF_DROP; } if (maniptype == NF_NAT_MANIP_SRC) { @@ -565,16 +566,10 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack() * will delete entry from already-freed table. */ - if (!del_timer(&ct->timeout)) - return 1; - ct->status &= ~IPS_NAT_DONE_MASK; - rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, nf_nat_bysource_params); - add_timer(&ct->timeout); - /* don't delete conntrack. Although that would make things a lot * simpler, we'd end up flushing all conntracks on nat rmmod. */ @@ -807,7 +802,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, if (err < 0) return err; - return nf_nat_setup_info(ct, &range, manip); + return nf_nat_setup_info(ct, &range, manip) == NF_DROP ? -ENOMEM : 0; } #else static int diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index b19ad20a705c..8f08d759844a 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -96,25 +96,19 @@ void nf_queue_entry_get_refs(struct nf_queue_entry *entry) } EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); -void nf_queue_nf_hook_drop(struct net *net, struct nf_hook_ops *ops) +void nf_queue_nf_hook_drop(struct net *net, const struct nf_hook_entry *entry) { const struct nf_queue_handler *qh; rcu_read_lock(); qh = rcu_dereference(net->nf.queue_handler); if (qh) - qh->nf_hook_drop(net, ops); + qh->nf_hook_drop(net, entry); rcu_read_unlock(); } -/* - * Any packet that leaves via this function must come back - * through nf_reinject(). - */ -int nf_queue(struct sk_buff *skb, - struct nf_hook_ops *elem, - struct nf_hook_state *state, - unsigned int queuenum) +static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, + unsigned int queuenum) { int status = -ENOENT; struct nf_queue_entry *entry = NULL; @@ -141,7 +135,6 @@ int nf_queue(struct sk_buff *skb, *entry = (struct nf_queue_entry) { .skb = skb, - .elem = elem, .state = *state, .size = sizeof(*entry) + afinfo->route_key_size, }; @@ -163,13 +156,38 @@ err: return status; } +/* Packets leaving via this function must come back through nf_reinject(). */ +int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, + struct nf_hook_entry **entryp, unsigned int verdict) +{ + struct nf_hook_entry *entry = *entryp; + int ret; + + RCU_INIT_POINTER(state->hook_entries, entry); + ret = __nf_queue(skb, state, verdict >> NF_VERDICT_QBITS); + if (ret < 0) { + if (ret == -ESRCH && + (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) { + *entryp = rcu_dereference(entry->next); + return 1; + } + kfree_skb(skb); + } + + return 0; +} + void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) { + struct nf_hook_entry *hook_entry; struct sk_buff *skb = entry->skb; - struct nf_hook_ops *elem = entry->elem; const struct nf_afinfo *afinfo; + struct nf_hook_ops *elem; int err; + hook_entry = rcu_dereference(entry->state.hook_entries); + elem = &hook_entry->ops; + nf_queue_entry_release_refs(entry); /* Continue traversal iff userspace said ok... */ @@ -185,26 +203,26 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) entry->state.thresh = INT_MIN; if (verdict == NF_ACCEPT) { - next_hook: - verdict = nf_iterate(entry->state.hook_list, - skb, &entry->state, &elem); + hook_entry = rcu_dereference(hook_entry->next); + if (hook_entry) +next_hook: + verdict = nf_iterate(skb, &entry->state, &hook_entry); } switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: case NF_STOP: +okfn: local_bh_disable(); entry->state.okfn(entry->state.net, entry->state.sk, skb); local_bh_enable(); break; case NF_QUEUE: - err = nf_queue(skb, elem, &entry->state, - verdict >> NF_VERDICT_QBITS); - if (err < 0) { - if (err == -ESRCH && - (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) + err = nf_queue(skb, &entry->state, &hook_entry, verdict); + if (err == 1) { + if (hook_entry) goto next_hook; - kfree_skb(skb); + goto okfn; } break; case NF_STOLEN: diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7e1c876c7608..026581b04ea8 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1196,6 +1196,83 @@ static void nf_tables_chain_destroy(struct nft_chain *chain) } } +struct nft_chain_hook { + u32 num; + u32 priority; + const struct nf_chain_type *type; + struct net_device *dev; +}; + +static int nft_chain_parse_hook(struct net *net, + const struct nlattr * const nla[], + struct nft_af_info *afi, + struct nft_chain_hook *hook, bool create) +{ + struct nlattr *ha[NFTA_HOOK_MAX + 1]; + const struct nf_chain_type *type; + struct net_device *dev; + int err; + + err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK], + nft_hook_policy); + if (err < 0) + return err; + + if (ha[NFTA_HOOK_HOOKNUM] == NULL || + ha[NFTA_HOOK_PRIORITY] == NULL) + return -EINVAL; + + hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); + if (hook->num >= afi->nhooks) + return -EINVAL; + + hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); + + type = chain_type[afi->family][NFT_CHAIN_T_DEFAULT]; + if (nla[NFTA_CHAIN_TYPE]) { + type = nf_tables_chain_type_lookup(afi, nla[NFTA_CHAIN_TYPE], + create); + if (IS_ERR(type)) + return PTR_ERR(type); + } + if (!(type->hook_mask & (1 << hook->num))) + return -EOPNOTSUPP; + if (!try_module_get(type->owner)) + return -ENOENT; + + hook->type = type; + + hook->dev = NULL; + if (afi->flags & NFT_AF_NEEDS_DEV) { + char ifname[IFNAMSIZ]; + + if (!ha[NFTA_HOOK_DEV]) { + module_put(type->owner); + return -EOPNOTSUPP; + } + + nla_strlcpy(ifname, ha[NFTA_HOOK_DEV], IFNAMSIZ); + dev = dev_get_by_name(net, ifname); + if (!dev) { + module_put(type->owner); + return -ENOENT; + } + hook->dev = dev; + } else if (ha[NFTA_HOOK_DEV]) { + module_put(type->owner); + return -EOPNOTSUPP; + } + + return 0; +} + +static void nft_chain_release_hook(struct nft_chain_hook *hook) +{ + module_put(hook->type->owner); + if (hook->dev != NULL) + dev_put(hook->dev); +} + static int nf_tables_newchain(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -1206,10 +1283,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, struct nft_table *table; struct nft_chain *chain; struct nft_base_chain *basechain = NULL; - struct nlattr *ha[NFTA_HOOK_MAX + 1]; u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; - struct net_device *dev = NULL; u8 policy = NF_ACCEPT; u64 handle = 0; unsigned int i; @@ -1273,6 +1348,37 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; + if (nla[NFTA_CHAIN_HOOK]) { + struct nft_base_chain *basechain; + struct nft_chain_hook hook; + struct nf_hook_ops *ops; + + if (!(chain->flags & NFT_BASE_CHAIN)) + return -EBUSY; + + err = nft_chain_parse_hook(net, nla, afi, &hook, + create); + if (err < 0) + return err; + + basechain = nft_base_chain(chain); + if (basechain->type != hook.type) { + nft_chain_release_hook(&hook); + return -EBUSY; + } + + for (i = 0; i < afi->nops; i++) { + ops = &basechain->ops[i]; + if (ops->hooknum != hook.num || + ops->priority != hook.priority || + ops->dev != hook.dev) { + nft_chain_release_hook(&hook); + return -EBUSY; + } + } + nft_chain_release_hook(&hook); + } + if (nla[NFTA_CHAIN_HANDLE] && name) { struct nft_chain *chain2; @@ -1320,102 +1426,53 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, return -EOVERFLOW; if (nla[NFTA_CHAIN_HOOK]) { - const struct nf_chain_type *type; + struct nft_chain_hook hook; struct nf_hook_ops *ops; nf_hookfn *hookfn; - u32 hooknum, priority; - - type = chain_type[family][NFT_CHAIN_T_DEFAULT]; - if (nla[NFTA_CHAIN_TYPE]) { - type = nf_tables_chain_type_lookup(afi, - nla[NFTA_CHAIN_TYPE], - create); - if (IS_ERR(type)) - return PTR_ERR(type); - } - err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK], - nft_hook_policy); + err = nft_chain_parse_hook(net, nla, afi, &hook, create); if (err < 0) return err; - if (ha[NFTA_HOOK_HOOKNUM] == NULL || - ha[NFTA_HOOK_PRIORITY] == NULL) - return -EINVAL; - - hooknum = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); - if (hooknum >= afi->nhooks) - return -EINVAL; - priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); - - if (!(type->hook_mask & (1 << hooknum))) - return -EOPNOTSUPP; - if (!try_module_get(type->owner)) - return -ENOENT; - hookfn = type->hooks[hooknum]; - - if (afi->flags & NFT_AF_NEEDS_DEV) { - char ifname[IFNAMSIZ]; - - if (!ha[NFTA_HOOK_DEV]) { - module_put(type->owner); - return -EOPNOTSUPP; - } - - nla_strlcpy(ifname, ha[NFTA_HOOK_DEV], IFNAMSIZ); - dev = dev_get_by_name(net, ifname); - if (!dev) { - module_put(type->owner); - return -ENOENT; - } - } else if (ha[NFTA_HOOK_DEV]) { - module_put(type->owner); - return -EOPNOTSUPP; - } basechain = kzalloc(sizeof(*basechain), GFP_KERNEL); if (basechain == NULL) { - module_put(type->owner); - if (dev != NULL) - dev_put(dev); + nft_chain_release_hook(&hook); return -ENOMEM; } - if (dev != NULL) - strncpy(basechain->dev_name, dev->name, IFNAMSIZ); + if (hook.dev != NULL) + strncpy(basechain->dev_name, hook.dev->name, IFNAMSIZ); if (nla[NFTA_CHAIN_COUNTERS]) { stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); if (IS_ERR(stats)) { - module_put(type->owner); + nft_chain_release_hook(&hook); kfree(basechain); - if (dev != NULL) - dev_put(dev); return PTR_ERR(stats); } basechain->stats = stats; } else { stats = netdev_alloc_pcpu_stats(struct nft_stats); if (stats == NULL) { - module_put(type->owner); + nft_chain_release_hook(&hook); kfree(basechain); - if (dev != NULL) - dev_put(dev); return -ENOMEM; } rcu_assign_pointer(basechain->stats, stats); } - basechain->type = type; + hookfn = hook.type->hooks[hook.num]; + basechain->type = hook.type; chain = &basechain->chain; for (i = 0; i < afi->nops; i++) { ops = &basechain->ops[i]; ops->pf = family; - ops->hooknum = hooknum; - ops->priority = priority; + ops->hooknum = hook.num; + ops->priority = hook.priority; ops->priv = chain; ops->hook = afi->hooks[ops->hooknum]; - ops->dev = dev; + ops->dev = hook.dev; if (hookfn) ops->hook = hookfn; if (afi->hook_ops_init) @@ -2899,12 +2956,14 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err2; + goto err3; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; +err3: + ops->destroy(set); err2: kfree(set); err1: @@ -3395,14 +3454,15 @@ void *nft_set_elem_init(const struct nft_set *set, return elem; } -void nft_set_elem_destroy(const struct nft_set *set, void *elem) +void nft_set_elem_destroy(const struct nft_set *set, void *elem, + bool destroy_expr) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem); nft_data_uninit(nft_set_ext_key(ext), NFT_DATA_VALUE); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_uninit(nft_set_ext_data(ext), set->dtype); - if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) + if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext)); kfree(elem); @@ -3426,12 +3486,12 @@ static int nft_setelem_parse_flags(const struct nft_set *set, } static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, - const struct nlattr *attr) + const struct nlattr *attr, u32 nlmsg_flags) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_data_desc d1, d2; struct nft_set_ext_tmpl tmpl; - struct nft_set_ext *ext; + struct nft_set_ext *ext, *ext2; struct nft_set_elem elem; struct nft_set_binding *binding; struct nft_userdata *udata; @@ -3508,6 +3568,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, dreg = nft_type_to_reg(set->dtype); list_for_each_entry(binding, &set->bindings, list) { struct nft_ctx bind_ctx = { + .net = ctx->net, .afi = ctx->afi, .table = ctx->table, .chain = (struct nft_chain *)binding->chain, @@ -3558,9 +3619,19 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err4; ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; - err = set->ops->insert(ctx->net, set, &elem); - if (err < 0) + err = set->ops->insert(ctx->net, set, &elem, &ext2); + if (err) { + if (err == -EEXIST) { + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && + nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) && + memcmp(nft_set_ext_data(ext), + nft_set_ext_data(ext2), set->dlen) != 0) + err = -EBUSY; + else if (!(nlmsg_flags & NLM_F_EXCL)) + err = 0; + } goto err5; + } nft_trans_elem(trans) = elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); @@ -3616,7 +3687,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) return -ENFILE; - err = nft_add_set_elem(&ctx, set, attr); + err = nft_add_set_elem(&ctx, set, attr, nlh->nlmsg_flags); if (err < 0) { atomic_dec(&set->nelems); break; @@ -3745,7 +3816,7 @@ void nft_set_gc_batch_release(struct rcu_head *rcu) gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu); for (i = 0; i < gcb->head.cnt; i++) - nft_set_elem_destroy(gcb->head.set, gcb->elems[i]); + nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true); kfree(gcb); } EXPORT_SYMBOL_GPL(nft_set_gc_batch_release); @@ -3963,7 +4034,7 @@ static void nf_tables_commit_release(struct nft_trans *trans) break; case NFT_MSG_DELSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), - nft_trans_elem(trans).priv); + nft_trans_elem(trans).priv, true); break; } kfree(trans); @@ -4104,7 +4175,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), - nft_trans_elem(trans).priv); + nft_trans_elem(trans).priv, true); break; } kfree(trans); @@ -4343,6 +4414,31 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, } /** + * nft_parse_u32_check - fetch u32 attribute and check for maximum value + * + * @attr: netlink attribute to fetch value from + * @max: maximum value to be stored in dest + * @dest: pointer to the variable + * + * Parse, check and store a given u32 netlink attribute into variable. + * This function returns -ERANGE if the value goes over maximum value. + * Otherwise a 0 is returned and the attribute value is stored in the + * destination variable. + */ +int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) +{ + u32 val; + + val = ntohl(nla_get_be32(attr)); + if (val > max) + return -ERANGE; + + *dest = val; + return 0; +} +EXPORT_SYMBOL_GPL(nft_parse_u32_check); + +/** * nft_parse_register - parse a register value from a netlink attribute * * @attr: netlink attribute diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index fb8b5892b5ff..0dd5c695482f 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -34,7 +34,7 @@ static struct nf_loginfo trace_loginfo = { .u = { .log = { .level = LOGLEVEL_WARNING, - .logflags = NF_LOG_MASK, + .logflags = NF_LOG_DEFAULT_MASK, }, }, }; @@ -93,12 +93,15 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr, if (priv->base == NFT_PAYLOAD_NETWORK_HEADER) ptr = skb_network_header(skb); - else + else { + if (!pkt->tprot_set) + return false; ptr = skb_network_header(skb) + pkt->xt.thoff; + } ptr += priv->offset; - if (unlikely(ptr + priv->len >= skb_tail_pointer(skb))) + if (unlikely(ptr + priv->len > skb_tail_pointer(skb))) return false; *dest = 0; @@ -260,8 +263,13 @@ int __init nf_tables_core_module_init(void) if (err < 0) goto err7; - return 0; + err = nft_range_module_init(); + if (err < 0) + goto err8; + return 0; +err8: + nft_dynset_module_exit(); err7: nft_payload_module_exit(); err6: diff --git a/net/netfilter/nf_tables_inet.c b/net/netfilter/nf_tables_inet.c index 6b5f76295d3d..f713cc205669 100644 --- a/net/netfilter/nf_tables_inet.c +++ b/net/netfilter/nf_tables_inet.c @@ -82,7 +82,10 @@ static int __init nf_tables_inet_init(void) { int ret; - nft_register_chain_type(&filter_inet); + ret = nft_register_chain_type(&filter_inet); + if (ret < 0) + return ret; + ret = register_pernet_subsys(&nf_tables_inet_net_ops); if (ret < 0) nft_unregister_chain_type(&filter_inet); diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c index 75d696f11045..9e2ae424b640 100644 --- a/net/netfilter/nf_tables_netdev.c +++ b/net/netfilter/nf_tables_netdev.c @@ -15,78 +15,6 @@ #include <net/netfilter/nf_tables_ipv4.h> #include <net/netfilter/nf_tables_ipv6.h> -static inline void -nft_netdev_set_pktinfo_ipv4(struct nft_pktinfo *pkt, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct iphdr *iph, _iph; - u32 len, thoff; - - nft_set_pktinfo(pkt, skb, state); - - iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph), - &_iph); - if (!iph) - return; - - if (iph->ihl < 5 || iph->version != 4) - return; - - len = ntohs(iph->tot_len); - thoff = iph->ihl * 4; - if (skb->len < len) - return; - else if (len < thoff) - return; - - pkt->tprot = iph->protocol; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET; -} - -static inline void -__nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ -#if IS_ENABLED(CONFIG_IPV6) - struct ipv6hdr *ip6h, _ip6h; - unsigned int thoff = 0; - unsigned short frag_off; - int protohdr; - u32 pkt_len; - - ip6h = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*ip6h), - &_ip6h); - if (!ip6h) - return; - - if (ip6h->version != 6) - return; - - pkt_len = ntohs(ip6h->payload_len); - if (pkt_len + sizeof(*ip6h) > skb->len) - return; - - protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); - if (protohdr < 0) - return; - - pkt->tprot = protohdr; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = frag_off; -#endif -} - -static inline void nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - nft_set_pktinfo(pkt, skb, state); - __nft_netdev_set_pktinfo_ipv6(pkt, skb, state); -} - static unsigned int nft_do_chain_netdev(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -95,13 +23,13 @@ nft_do_chain_netdev(void *priv, struct sk_buff *skb, switch (skb->protocol) { case htons(ETH_P_IP): - nft_netdev_set_pktinfo_ipv4(&pkt, skb, state); + nft_set_pktinfo_ipv4_validate(&pkt, skb, state); break; case htons(ETH_P_IPV6): - nft_netdev_set_pktinfo_ipv6(&pkt, skb, state); + nft_set_pktinfo_ipv6_validate(&pkt, skb, state); break; default: - nft_set_pktinfo(&pkt, skb, state); + nft_set_pktinfo_unspec(&pkt, skb, state); break; } @@ -221,14 +149,25 @@ static int __init nf_tables_netdev_init(void) { int ret; - nft_register_chain_type(&nft_filter_chain_netdev); - ret = register_pernet_subsys(&nf_tables_netdev_net_ops); - if (ret < 0) { - nft_unregister_chain_type(&nft_filter_chain_netdev); + ret = nft_register_chain_type(&nft_filter_chain_netdev); + if (ret) return ret; - } - register_netdevice_notifier(&nf_tables_netdev_notifier); + + ret = register_pernet_subsys(&nf_tables_netdev_net_ops); + if (ret) + goto err1; + + ret = register_netdevice_notifier(&nf_tables_netdev_notifier); + if (ret) + goto err2; + return 0; + +err2: + unregister_pernet_subsys(&nf_tables_netdev_net_ops); +err1: + nft_unregister_chain_type(&nft_filter_chain_netdev); + return ret; } static void __exit nf_tables_netdev_exit(void) diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 39eb1cc62e91..ab695f8e2d29 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -113,20 +113,22 @@ static int nf_trace_fill_pkt_info(struct sk_buff *nlskb, const struct nft_pktinfo *pkt) { const struct sk_buff *skb = pkt->skb; - unsigned int len = min_t(unsigned int, - pkt->xt.thoff - skb_network_offset(skb), - NFT_TRACETYPE_NETWORK_HSIZE); int off = skb_network_offset(skb); + unsigned int len, nh_end; + nh_end = pkt->tprot_set ? pkt->xt.thoff : skb->len; + len = min_t(unsigned int, nh_end - skb_network_offset(skb), + NFT_TRACETYPE_NETWORK_HSIZE); if (trace_fill_header(nlskb, NFTA_TRACE_NETWORK_HEADER, skb, off, len)) return -1; - len = min_t(unsigned int, skb->len - pkt->xt.thoff, - NFT_TRACETYPE_TRANSPORT_HSIZE); - - if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb, - pkt->xt.thoff, len)) - return -1; + if (pkt->tprot_set) { + len = min_t(unsigned int, skb->len - pkt->xt.thoff, + NFT_TRACETYPE_TRANSPORT_HSIZE); + if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb, + pkt->xt.thoff, len)) + return -1; + } if (!skb_mac_header_was_set(skb)) return 0; @@ -237,7 +239,7 @@ void nft_trace_notify(struct nft_traceinfo *info) break; case NFT_TRACETYPE_POLICY: if (nla_put_be32(skb, NFTA_TRACE_POLICY, - info->basechain->policy)) + htonl(info->basechain->policy))) goto nla_put_failure; break; } diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index e924e95fcc7f..3b79f34b5095 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -43,7 +43,7 @@ nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff, if (help == NULL) return NF_DROP; - /* rcu_read_lock()ed by nf_hook_slow */ + /* rcu_read_lock()ed by nf_hook_thresh */ helper = rcu_dereference(help->helper); if (helper == NULL) return NF_DROP; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 6577db524ef6..eb086a192c5a 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -442,7 +442,9 @@ __build_packet_message(struct nfnl_log_net *log, if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, htonl(indev->ifindex)) || /* this is the bridge group "brX" */ - /* rcu_read_lock()ed by nf_hook_slow or nf_log_packet */ + /* rcu_read_lock()ed by nf_hook_thresh or + * nf_log_packet. + */ nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; @@ -477,7 +479,9 @@ __build_packet_message(struct nfnl_log_net *log, if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, htonl(outdev->ifindex)) || /* this is the bridge group "brX" */ - /* rcu_read_lock()ed by nf_hook_slow or nf_log_packet */ + /* rcu_read_lock()ed by nf_hook_thresh or + * nf_log_packet. + */ nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) goto nla_put_failure; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index f49f45081acb..af832c526048 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -740,7 +740,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) struct net *net = entry->state.net; struct nfnl_queue_net *q = nfnl_queue_pernet(net); - /* rcu_read_lock()ed by nf_hook_slow() */ + /* rcu_read_lock()ed by nf_hook_thresh */ queue = instance_lookup(q, queuenum); if (!queue) return -ESRCH; @@ -917,12 +917,14 @@ static struct notifier_block nfqnl_dev_notifier = { .notifier_call = nfqnl_rcv_dev_event, }; -static int nf_hook_cmp(struct nf_queue_entry *entry, unsigned long ops_ptr) +static int nf_hook_cmp(struct nf_queue_entry *entry, unsigned long entry_ptr) { - return entry->elem == (struct nf_hook_ops *)ops_ptr; + return rcu_access_pointer(entry->state.hook_entries) == + (struct nf_hook_entry *)entry_ptr; } -static void nfqnl_nf_hook_drop(struct net *net, struct nf_hook_ops *hook) +static void nfqnl_nf_hook_drop(struct net *net, + const struct nf_hook_entry *hook) { struct nfnl_queue_net *q = nfnl_queue_pernet(net); int i; @@ -1522,9 +1524,16 @@ static int __init nfnetlink_queue_init(void) goto cleanup_netlink_notifier; } - register_netdevice_notifier(&nfqnl_dev_notifier); + status = register_netdevice_notifier(&nfqnl_dev_notifier); + if (status < 0) { + pr_err("nf_queue: failed to register netdevice notifier\n"); + goto cleanup_netlink_subsys; + } + return status; +cleanup_netlink_subsys: + nfnetlink_subsys_unregister(&nfqnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfqnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_queue_net_ops); diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index d71cc18fa35d..31c15ed2e5fc 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -52,6 +52,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, { struct nft_bitwise *priv = nft_expr_priv(expr); struct nft_data_desc d1, d2; + u32 len; int err; if (tb[NFTA_BITWISE_SREG] == NULL || @@ -61,7 +62,12 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_XOR] == NULL) return -EINVAL; - priv->len = ntohl(nla_get_be32(tb[NFTA_BITWISE_LEN])); + err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len); + if (err < 0) + return err; + + priv->len = len; + priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]); err = nft_validate_register_load(priv->sreg, priv->len); if (err < 0) diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index b78c28ba465f..ee63d981268d 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -99,6 +99,7 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_byteorder *priv = nft_expr_priv(expr); + u32 size, len; int err; if (tb[NFTA_BYTEORDER_SREG] == NULL || @@ -117,7 +118,12 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, return -EINVAL; } - priv->size = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_SIZE])); + err = nft_parse_u32_check(tb[NFTA_BYTEORDER_SIZE], U8_MAX, &size); + if (err < 0) + return err; + + priv->size = size; + switch (priv->size) { case 2: case 4: @@ -128,7 +134,12 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, } priv->sreg = nft_parse_register(tb[NFTA_BYTEORDER_SREG]); - priv->len = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_LEN])); + err = nft_parse_u32_check(tb[NFTA_BYTEORDER_LEN], U8_MAX, &len); + if (err < 0) + return err; + + priv->len = len; + err = nft_validate_register_load(priv->sreg, priv->len); if (err < 0) return err; diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index e25b35d70e4d..2e53739812b1 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -84,6 +84,9 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; + if (desc.len > U8_MAX) + return -ERANGE; + priv->op = ntohl(nla_get_be32(tb[NFTA_CMP_OP])); priv->len = desc.len; return 0; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 51e180f2a003..d7b0d171172a 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -128,15 +128,18 @@ static void nft_ct_get_eval(const struct nft_expr *expr, memcpy(dest, &count, sizeof(count)); return; } + case NFT_CT_L3PROTOCOL: + *dest = nf_ct_l3num(ct); + return; + case NFT_CT_PROTOCOL: + *dest = nf_ct_protonum(ct); + return; default: break; } tuple = &ct->tuplehash[priv->dir].tuple; switch (priv->key) { - case NFT_CT_L3PROTOCOL: - *dest = nf_ct_l3num(ct); - return; case NFT_CT_SRC: memcpy(dest, tuple->src.u3.all, nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16); @@ -145,9 +148,6 @@ static void nft_ct_get_eval(const struct nft_expr *expr, memcpy(dest, tuple->dst.u3.all, nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16); return; - case NFT_CT_PROTOCOL: - *dest = nf_ct_protonum(ct); - return; case NFT_CT_PROTO_SRC: *dest = (__force __u16)tuple->src.u.all; return; @@ -283,8 +283,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, case NFT_CT_L3PROTOCOL: case NFT_CT_PROTOCOL: - if (tb[NFTA_CT_DIRECTION] == NULL) - return -EINVAL; + /* For compatibility, do not report error if NFTA_CT_DIRECTION + * attribute is specified. + */ len = sizeof(u8); break; case NFT_CT_SRC: @@ -363,6 +364,8 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, switch (priv->key) { #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: + if (tb[NFTA_CT_DIRECTION]) + return -EINVAL; len = FIELD_SIZEOF(struct nf_conn, mark); break; #endif @@ -432,8 +435,6 @@ static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; switch (priv->key) { - case NFT_CT_L3PROTOCOL: - case NFT_CT_PROTOCOL: case NFT_CT_SRC: case NFT_CT_DST: case NFT_CT_PROTO_SRC: diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 0af26699bf04..31ca94793aa9 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -22,6 +22,7 @@ struct nft_dynset { enum nft_dynset_ops op:8; enum nft_registers sreg_key:8; enum nft_registers sreg_data:8; + bool invert; u64 timeout; struct nft_expr *expr; struct nft_set_binding binding; @@ -43,18 +44,22 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, ®s->data[priv->sreg_key], ®s->data[priv->sreg_data], timeout, GFP_ATOMIC); - if (elem == NULL) { - if (set->size) - atomic_dec(&set->nelems); - return NULL; - } + if (elem == NULL) + goto err1; ext = nft_set_elem_ext(set, elem); if (priv->expr != NULL && nft_expr_clone(nft_set_ext_expr(ext), priv->expr) < 0) - return NULL; + goto err2; return elem; + +err2: + nft_set_elem_destroy(set, elem, false); +err1: + if (set->size) + atomic_dec(&set->nelems); + return NULL; } static void nft_dynset_eval(const struct nft_expr *expr, @@ -82,10 +87,14 @@ static void nft_dynset_eval(const struct nft_expr *expr, if (sexpr != NULL) sexpr->ops->eval(sexpr, regs, pkt); + + if (priv->invert) + regs->verdict.code = NFT_BREAK; return; } out: - regs->verdict.code = NFT_BREAK; + if (!priv->invert) + regs->verdict.code = NFT_BREAK; } static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = { @@ -96,6 +105,7 @@ static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = { [NFTA_DYNSET_SREG_DATA] = { .type = NLA_U32 }, [NFTA_DYNSET_TIMEOUT] = { .type = NLA_U64 }, [NFTA_DYNSET_EXPR] = { .type = NLA_NESTED }, + [NFTA_DYNSET_FLAGS] = { .type = NLA_U32 }, }; static int nft_dynset_init(const struct nft_ctx *ctx, @@ -113,6 +123,15 @@ static int nft_dynset_init(const struct nft_ctx *ctx, tb[NFTA_DYNSET_SREG_KEY] == NULL) return -EINVAL; + if (tb[NFTA_DYNSET_FLAGS]) { + u32 flags = ntohl(nla_get_be32(tb[NFTA_DYNSET_FLAGS])); + + if (flags & ~NFT_DYNSET_F_INV) + return -EINVAL; + if (flags & NFT_DYNSET_F_INV) + priv->invert = true; + } + set = nf_tables_set_lookup(ctx->table, tb[NFTA_DYNSET_SET_NAME], genmask); if (IS_ERR(set)) { @@ -124,6 +143,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, return PTR_ERR(set); } + if (set->ops->update == NULL) + return -EOPNOTSUPP; + if (set->flags & NFT_SET_CONSTANT) return -EBUSY; @@ -143,7 +165,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (tb[NFTA_DYNSET_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = be64_to_cpu(nla_get_be64(tb[NFTA_DYNSET_TIMEOUT])); + timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( + tb[NFTA_DYNSET_TIMEOUT]))); } priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]); @@ -220,6 +243,7 @@ static void nft_dynset_destroy(const struct nft_ctx *ctx, static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_dynset *priv = nft_expr_priv(expr); + u32 flags = priv->invert ? NFT_DYNSET_F_INV : 0; if (nft_dump_register(skb, NFTA_DYNSET_SREG_KEY, priv->sreg_key)) goto nla_put_failure; @@ -230,11 +254,14 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name)) goto nla_put_failure; - if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, cpu_to_be64(priv->timeout), + if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, + cpu_to_be64(jiffies_to_msecs(priv->timeout)), NFTA_DYNSET_PAD)) goto nla_put_failure; if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr)) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_DYNSET_FLAGS, htonl(flags))) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 82c264e40278..47beb3abcc9d 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -60,6 +60,7 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, { struct nft_exthdr *priv = nft_expr_priv(expr); u32 offset, len; + int err; if (tb[NFTA_EXTHDR_DREG] == NULL || tb[NFTA_EXTHDR_TYPE] == NULL || @@ -67,11 +68,13 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, tb[NFTA_EXTHDR_LEN] == NULL) return -EINVAL; - offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET])); - len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN])); + err = nft_parse_u32_check(tb[NFTA_EXTHDR_OFFSET], U8_MAX, &offset); + if (err < 0) + return err; - if (offset > U8_MAX || len > U8_MAX) - return -ERANGE; + err = nft_parse_u32_check(tb[NFTA_EXTHDR_LEN], U8_MAX, &len); + if (err < 0) + return err; priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); priv->offset = offset; diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 564fa7929ed5..baf694de3935 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -1,395 +1,146 @@ /* - * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2016 Laura Garcia <nevola@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. * - * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> -#include <linux/list.h> -#include <linux/log2.h> -#include <linux/jhash.h> #include <linux/netlink.h> -#include <linux/workqueue.h> -#include <linux/rhashtable.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> - -/* We target a hash table size of 4, element hint is 75% of final size */ -#define NFT_HASH_ELEMENT_HINT 3 +#include <net/netfilter/nf_tables_core.h> +#include <linux/jhash.h> struct nft_hash { - struct rhashtable ht; - struct delayed_work gc_work; -}; - -struct nft_hash_elem { - struct rhash_head node; - struct nft_set_ext ext; + enum nft_registers sreg:8; + enum nft_registers dreg:8; + u8 len; + u32 modulus; + u32 seed; + u32 offset; }; -struct nft_hash_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) -{ - const struct nft_hash_cmp_arg *arg = data; - - return jhash(arg->key, len, seed); -} - -static inline u32 nft_hash_obj(const void *data, u32 len, u32 seed) -{ - const struct nft_hash_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) -{ - const struct nft_hash_cmp_arg *x = arg->key; - const struct nft_hash_elem *he = ptr; - - if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) - return 1; - if (nft_set_elem_expired(&he->ext)) - return 1; - if (!nft_set_elem_active(&he->ext, x->genmask)) - return 1; - 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) -{ - struct nft_hash *priv = nft_set_priv(set); - const struct nft_hash_elem *he; - struct nft_hash_cmp_arg arg = { - .genmask = nft_genmask_cur(net), - .set = set, - .key = key, - }; - - he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_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) -{ - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he; - struct nft_hash_cmp_arg arg = { - .genmask = NFT_GENMASK_ANY, - .set = set, - .key = key, - }; - - he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); - if (he != NULL) - goto out; - - he = new(set, expr, regs); - if (he == NULL) - goto err1; - if (rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node, - nft_hash_params)) - goto err2; -out: - *ext = &he->ext; - return true; - -err2: - nft_set_elem_destroy(set, he); -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_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he = elem->priv; - struct nft_hash_cmp_arg arg = { - .genmask = nft_genmask_next(net), - .set = set, - .key = elem->key.val.data, - }; - - return rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node, - nft_hash_params); -} - -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); - nft_set_elem_clear_busy(&he->ext); -} - -static void *nft_hash_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static void nft_hash_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he; - struct nft_hash_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); - if (he != NULL) { - if (!nft_set_elem_mark_busy(&he->ext) || - !nft_is_active(net, &he->ext)) - nft_set_elem_change_active(net, set, &he->ext); - else - he = NULL; - } - rcu_read_unlock(); + struct nft_hash *priv = nft_expr_priv(expr); + const void *data = ®s->data[priv->sreg]; + u32 h; - return he; + h = reciprocal_scale(jhash(data, priv->len, priv->seed), priv->modulus); + regs->data[priv->dreg] = h + priv->offset; } -static void nft_hash_remove(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; - - rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); -} +static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { + [NFTA_HASH_SREG] = { .type = NLA_U32 }, + [NFTA_HASH_DREG] = { .type = NLA_U32 }, + [NFTA_HASH_LEN] = { .type = NLA_U32 }, + [NFTA_HASH_MODULUS] = { .type = NLA_U32 }, + [NFTA_HASH_SEED] = { .type = NLA_U32 }, + [NFTA_HASH_OFFSET] = { .type = NLA_U32 }, +}; -static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, - struct nft_set_iter *iter) +static int nft_hash_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he; - struct rhashtable_iter hti; - struct nft_set_elem elem; - int err; - - err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); - iter->err = err; - if (err) - return; - - err = rhashtable_walk_start(&hti); - if (err && err != -EAGAIN) { - iter->err = err; - goto out; - } - - while ((he = rhashtable_walk_next(&hti))) { - if (IS_ERR(he)) { - err = PTR_ERR(he); - if (err != -EAGAIN) { - iter->err = err; - goto out; - } + struct nft_hash *priv = nft_expr_priv(expr); + u32 len; - continue; - } + if (!tb[NFTA_HASH_SREG] || + !tb[NFTA_HASH_DREG] || + !tb[NFTA_HASH_LEN] || + !tb[NFTA_HASH_SEED] || + !tb[NFTA_HASH_MODULUS]) + return -EINVAL; - if (iter->count < iter->skip) - goto cont; - if (nft_set_elem_expired(&he->ext)) - goto cont; - if (!nft_set_elem_active(&he->ext, iter->genmask)) - goto cont; + if (tb[NFTA_HASH_OFFSET]) + priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); - elem.priv = he; + priv->sreg = nft_parse_register(tb[NFTA_HASH_SREG]); + priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); - iter->err = iter->fn(ctx, set, iter, &elem); - if (iter->err < 0) - goto out; + len = ntohl(nla_get_be32(tb[NFTA_HASH_LEN])); + if (len == 0 || len > U8_MAX) + return -ERANGE; -cont: - iter->count++; - } + priv->len = len; -out: - rhashtable_walk_stop(&hti); - rhashtable_walk_exit(&hti); -} - -static void nft_hash_gc(struct work_struct *work) -{ - struct nft_set *set; - struct nft_hash_elem *he; - struct nft_hash *priv; - struct nft_set_gc_batch *gcb = NULL; - struct rhashtable_iter hti; - int err; - - priv = container_of(work, struct nft_hash, gc_work.work); - set = nft_set_container_of(priv); - - err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); - if (err) - goto schedule; + priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); + if (priv->modulus <= 1) + return -ERANGE; - err = rhashtable_walk_start(&hti); - if (err && err != -EAGAIN) - goto out; + if (priv->offset + priv->modulus - 1 < priv->offset) + return -EOVERFLOW; - while ((he = rhashtable_walk_next(&hti))) { - if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) - goto out; - continue; - } + priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED])); - if (!nft_set_elem_expired(&he->ext)) - continue; - if (nft_set_elem_mark_busy(&he->ext)) - continue; - - 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); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, he); - } -out: - rhashtable_walk_stop(&hti); - rhashtable_walk_exit(&hti); - - nft_set_gc_batch_complete(gcb); -schedule: - queue_delayed_work(system_power_efficient_wq, &priv->gc_work, - nft_set_gc_interval(set)); + return nft_validate_register_load(priv->sreg, len) && + nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, sizeof(u32)); } -static unsigned int nft_hash_privsize(const struct nlattr * const nla[]) +static int nft_hash_dump(struct sk_buff *skb, + const struct nft_expr *expr) { - return sizeof(struct nft_hash); -} - -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, -}; + const struct nft_hash *priv = nft_expr_priv(expr); -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); - struct rhashtable_params params = nft_hash_params; - int err; - - params.nelem_hint = desc->size ?: NFT_HASH_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); - if (set->flags & NFT_SET_TIMEOUT) - queue_delayed_work(system_power_efficient_wq, &priv->gc_work, - nft_set_gc_interval(set)); + if (nft_dump_register(skb, NFTA_HASH_SREG, priv->sreg)) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg)) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_HASH_LEN, htonl(priv->len))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed))) + goto nla_put_failure; + if (priv->offset != 0) + if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset))) + goto nla_put_failure; return 0; -} -static void nft_hash_elem_destroy(void *ptr, void *arg) -{ - nft_set_elem_destroy((const struct nft_set *)arg, ptr); +nla_put_failure: + return -1; } -static void nft_hash_destroy(const struct nft_set *set) -{ - struct nft_hash *priv = nft_set_priv(set); - - cancel_delayed_work_sync(&priv->gc_work); - rhashtable_free_and_destroy(&priv->ht, nft_hash_elem_destroy, - (void *)set); -} - -static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, - struct nft_set_estimate *est) -{ - 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 *); - } - - est->class = NFT_SET_CLASS_O_1; - - return true; -} - -static struct nft_set_ops nft_hash_ops __read_mostly = { - .privsize = nft_hash_privsize, - .elemsize = offsetof(struct nft_hash_elem, ext), - .estimate = nft_hash_estimate, +static struct nft_expr_type nft_hash_type; +static const struct nft_expr_ops nft_hash_ops = { + .type = &nft_hash_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_hash)), + .eval = nft_hash_eval, .init = nft_hash_init, - .destroy = nft_hash_destroy, - .insert = nft_hash_insert, - .activate = nft_hash_activate, - .deactivate = nft_hash_deactivate, - .remove = nft_hash_remove, - .lookup = nft_hash_lookup, - .update = nft_hash_update, - .walk = nft_hash_walk, - .features = NFT_SET_MAP | NFT_SET_TIMEOUT, + .dump = nft_hash_dump, +}; + +static struct nft_expr_type nft_hash_type __read_mostly = { + .name = "hash", + .ops = &nft_hash_ops, + .policy = nft_hash_policy, + .maxattr = NFTA_HASH_MAX, .owner = THIS_MODULE, }; static int __init nft_hash_module_init(void) { - return nft_register_set(&nft_hash_ops); + return nft_register_expr(&nft_hash_type); } static void __exit nft_hash_module_exit(void) { - nft_unregister_set(&nft_hash_ops); + nft_unregister_expr(&nft_hash_type); } module_init(nft_hash_module_init); module_exit(nft_hash_module_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_SET(); +MODULE_AUTHOR("Laura Garcia <nevola@gmail.com>"); +MODULE_ALIAS_NFT_EXPR("hash"); diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index db3b746858e3..d17018ff54e6 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -53,6 +53,10 @@ static int nft_immediate_init(const struct nft_ctx *ctx, tb[NFTA_IMMEDIATE_DATA]); if (err < 0) return err; + + if (desc.len > U8_MAX) + return -ERANGE; + priv->dlen = desc.len; priv->dreg = nft_parse_register(tb[NFTA_IMMEDIATE_DREG]); diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 070b98938e02..c6baf412236d 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -145,7 +145,7 @@ static int nft_limit_pkts_init(const struct nft_ctx *ctx, if (err < 0) return err; - priv->cost = div_u64(priv->limit.nsecs, priv->limit.rate); + priv->cost = div64_u64(priv->limit.nsecs, priv->limit.rate); return 0; } @@ -170,7 +170,7 @@ static void nft_limit_pkt_bytes_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { struct nft_limit *priv = nft_expr_priv(expr); - u64 cost = div_u64(priv->nsecs * pkt->skb->len, priv->rate); + u64 cost = div64_u64(priv->nsecs * pkt->skb->len, priv->rate); if (nft_limit_eval(priv, cost)) regs->verdict.code = NFT_BREAK; diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 24a73bb26e94..1b01404bb33f 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -58,8 +58,11 @@ static int nft_log_init(const struct nft_ctx *ctx, if (tb[NFTA_LOG_LEVEL] != NULL && tb[NFTA_LOG_GROUP] != NULL) return -EINVAL; - if (tb[NFTA_LOG_GROUP] != NULL) + if (tb[NFTA_LOG_GROUP] != NULL) { li->type = NF_LOG_TYPE_ULOG; + if (tb[NFTA_LOG_FLAGS] != NULL) + return -EINVAL; + } nla = tb[NFTA_LOG_PREFIX]; if (nla != NULL) { @@ -87,6 +90,10 @@ static int nft_log_init(const struct nft_ctx *ctx, if (tb[NFTA_LOG_FLAGS] != NULL) { li->u.log.logflags = ntohl(nla_get_be32(tb[NFTA_LOG_FLAGS])); + if (li->u.log.logflags & ~NF_LOG_MASK) { + err = -EINVAL; + goto err1; + } } break; case NF_LOG_TYPE_ULOG: diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index e164325d1bc0..8166b6994cc7 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -43,7 +43,7 @@ static void nft_lookup_eval(const struct nft_expr *expr, return; } - if (found && set->flags & NFT_SET_MAP) + if (set->flags & NFT_SET_MAP) nft_data_copy(®s->data[priv->dreg], nft_set_ext_data(ext), set->dlen); diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 8a6bc7630912..6c1e0246706e 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -52,6 +52,8 @@ void nft_meta_get_eval(const struct nft_expr *expr, *dest = pkt->pf; break; case NFT_META_L4PROTO: + if (!pkt->tprot_set) + goto err; *dest = pkt->tprot; break; case NFT_META_PRIORITY: diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c new file mode 100644 index 000000000000..55bc5ab78d4a --- /dev/null +++ b/net/netfilter/nft_numgen.c @@ -0,0 +1,212 @@ +/* + * Copyright (c) 2016 Laura Garcia <nevola@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <linux/static_key.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> + +static DEFINE_PER_CPU(struct rnd_state, nft_numgen_prandom_state); + +struct nft_ng_inc { + enum nft_registers dreg:8; + u32 modulus; + atomic_t counter; + u32 offset; +}; + +static void nft_ng_inc_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_ng_inc *priv = nft_expr_priv(expr); + u32 nval, oval; + + do { + oval = atomic_read(&priv->counter); + nval = (oval + 1 < priv->modulus) ? oval + 1 : 0; + } while (atomic_cmpxchg(&priv->counter, oval, nval) != oval); + + regs->data[priv->dreg] = nval + priv->offset; +} + +static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { + [NFTA_NG_DREG] = { .type = NLA_U32 }, + [NFTA_NG_MODULUS] = { .type = NLA_U32 }, + [NFTA_NG_TYPE] = { .type = NLA_U32 }, + [NFTA_NG_OFFSET] = { .type = NLA_U32 }, +}; + +static int nft_ng_inc_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_ng_inc *priv = nft_expr_priv(expr); + + if (tb[NFTA_NG_OFFSET]) + priv->offset = ntohl(nla_get_be32(tb[NFTA_NG_OFFSET])); + + priv->modulus = ntohl(nla_get_be32(tb[NFTA_NG_MODULUS])); + if (priv->modulus == 0) + return -ERANGE; + + if (priv->offset + priv->modulus - 1 < priv->offset) + return -EOVERFLOW; + + priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]); + atomic_set(&priv->counter, 0); + + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, sizeof(u32)); +} + +static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, + u32 modulus, enum nft_ng_types type, u32 offset) +{ + if (nft_dump_register(skb, NFTA_NG_DREG, dreg)) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_NG_MODULUS, htonl(modulus))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_NG_TYPE, htonl(type))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_NG_OFFSET, htonl(offset))) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_ng_inc *priv = nft_expr_priv(expr); + + return nft_ng_dump(skb, priv->dreg, priv->modulus, NFT_NG_INCREMENTAL, + priv->offset); +} + +struct nft_ng_random { + enum nft_registers dreg:8; + u32 modulus; + u32 offset; +}; + +static void nft_ng_random_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_ng_random *priv = nft_expr_priv(expr); + struct rnd_state *state = this_cpu_ptr(&nft_numgen_prandom_state); + u32 val; + + val = reciprocal_scale(prandom_u32_state(state), priv->modulus); + regs->data[priv->dreg] = val + priv->offset; +} + +static int nft_ng_random_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_ng_random *priv = nft_expr_priv(expr); + + if (tb[NFTA_NG_OFFSET]) + priv->offset = ntohl(nla_get_be32(tb[NFTA_NG_OFFSET])); + + priv->modulus = ntohl(nla_get_be32(tb[NFTA_NG_MODULUS])); + if (priv->modulus == 0) + return -ERANGE; + + if (priv->offset + priv->modulus - 1 < priv->offset) + return -EOVERFLOW; + + prandom_init_once(&nft_numgen_prandom_state); + + priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]); + + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, sizeof(u32)); +} + +static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_ng_random *priv = nft_expr_priv(expr); + + return nft_ng_dump(skb, priv->dreg, priv->modulus, NFT_NG_RANDOM, + priv->offset); +} + +static struct nft_expr_type nft_ng_type; +static const struct nft_expr_ops nft_ng_inc_ops = { + .type = &nft_ng_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_inc)), + .eval = nft_ng_inc_eval, + .init = nft_ng_inc_init, + .dump = nft_ng_inc_dump, +}; + +static const struct nft_expr_ops nft_ng_random_ops = { + .type = &nft_ng_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), + .eval = nft_ng_random_eval, + .init = nft_ng_random_init, + .dump = nft_ng_random_dump, +}; + +static const struct nft_expr_ops * +nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) +{ + u32 type; + + if (!tb[NFTA_NG_DREG] || + !tb[NFTA_NG_MODULUS] || + !tb[NFTA_NG_TYPE]) + return ERR_PTR(-EINVAL); + + type = ntohl(nla_get_be32(tb[NFTA_NG_TYPE])); + + switch (type) { + case NFT_NG_INCREMENTAL: + return &nft_ng_inc_ops; + case NFT_NG_RANDOM: + return &nft_ng_random_ops; + } + + return ERR_PTR(-EINVAL); +} + +static struct nft_expr_type nft_ng_type __read_mostly = { + .name = "numgen", + .select_ops = &nft_ng_select_ops, + .policy = nft_ng_policy, + .maxattr = NFTA_NG_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_ng_module_init(void) +{ + return nft_register_expr(&nft_ng_type); +} + +static void __exit nft_ng_module_exit(void) +{ + nft_unregister_expr(&nft_ng_type); +} + +module_init(nft_ng_module_init); +module_exit(nft_ng_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Laura Garcia <nevola@gmail.com>"); +MODULE_ALIAS_NFT_EXPR("numgen"); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 12cd4bf16d17..b2f88617611a 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -92,6 +92,8 @@ static void nft_payload_eval(const struct nft_expr *expr, offset = skb_network_offset(skb); break; case NFT_PAYLOAD_TRANSPORT_HEADER: + if (!pkt->tprot_set) + goto err; offset = pkt->xt.thoff; break; default: @@ -184,6 +186,8 @@ static void nft_payload_set_eval(const struct nft_expr *expr, offset = skb_network_offset(skb); break; case NFT_PAYLOAD_TRANSPORT_HEADER: + if (!pkt->tprot_set) + goto err; offset = pkt->xt.thoff; break; default: diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index 61d216eb7917..393d359a1889 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -22,9 +22,10 @@ static u32 jhash_initval __read_mostly; struct nft_queue { - u16 queuenum; - u16 queues_total; - u16 flags; + enum nft_registers sreg_qnum:8; + u16 queuenum; + u16 queues_total; + u16 flags; }; static void nft_queue_eval(const struct nft_expr *expr, @@ -54,31 +55,78 @@ static void nft_queue_eval(const struct nft_expr *expr, regs->verdict.code = ret; } +static void nft_queue_sreg_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_queue *priv = nft_expr_priv(expr); + u32 queue, ret; + + queue = regs->data[priv->sreg_qnum]; + + ret = NF_QUEUE_NR(queue); + if (priv->flags & NFT_QUEUE_FLAG_BYPASS) + ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; + + regs->verdict.code = ret; +} + static const struct nla_policy nft_queue_policy[NFTA_QUEUE_MAX + 1] = { [NFTA_QUEUE_NUM] = { .type = NLA_U16 }, [NFTA_QUEUE_TOTAL] = { .type = NLA_U16 }, [NFTA_QUEUE_FLAGS] = { .type = NLA_U16 }, + [NFTA_QUEUE_SREG_QNUM] = { .type = NLA_U32 }, }; static int nft_queue_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_queue *priv = nft_expr_priv(expr); + u32 maxid; - if (tb[NFTA_QUEUE_NUM] == NULL) - return -EINVAL; - - init_hashrandom(&jhash_initval); priv->queuenum = ntohs(nla_get_be16(tb[NFTA_QUEUE_NUM])); - if (tb[NFTA_QUEUE_TOTAL] != NULL) + if (tb[NFTA_QUEUE_TOTAL]) priv->queues_total = ntohs(nla_get_be16(tb[NFTA_QUEUE_TOTAL])); - if (tb[NFTA_QUEUE_FLAGS] != NULL) { + else + priv->queues_total = 1; + + if (priv->queues_total == 0) + return -EINVAL; + + maxid = priv->queues_total - 1 + priv->queuenum; + if (maxid > U16_MAX) + return -ERANGE; + + if (tb[NFTA_QUEUE_FLAGS]) { + priv->flags = ntohs(nla_get_be16(tb[NFTA_QUEUE_FLAGS])); + if (priv->flags & ~NFT_QUEUE_FLAG_MASK) + return -EINVAL; + } + return 0; +} + +static int nft_queue_sreg_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_queue *priv = nft_expr_priv(expr); + int err; + + priv->sreg_qnum = nft_parse_register(tb[NFTA_QUEUE_SREG_QNUM]); + err = nft_validate_register_load(priv->sreg_qnum, sizeof(u32)); + if (err < 0) + return err; + + if (tb[NFTA_QUEUE_FLAGS]) { priv->flags = ntohs(nla_get_be16(tb[NFTA_QUEUE_FLAGS])); if (priv->flags & ~NFT_QUEUE_FLAG_MASK) return -EINVAL; + if (priv->flags & NFT_QUEUE_FLAG_CPU_FANOUT) + return -EOPNOTSUPP; } + return 0; } @@ -97,6 +145,21 @@ nla_put_failure: return -1; } +static int +nft_queue_sreg_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_queue *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_QUEUE_SREG_QNUM, priv->sreg_qnum) || + nla_put_be16(skb, NFTA_QUEUE_FLAGS, htons(priv->flags))) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + static struct nft_expr_type nft_queue_type; static const struct nft_expr_ops nft_queue_ops = { .type = &nft_queue_type, @@ -106,9 +169,35 @@ static const struct nft_expr_ops nft_queue_ops = { .dump = nft_queue_dump, }; +static const struct nft_expr_ops nft_queue_sreg_ops = { + .type = &nft_queue_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_queue)), + .eval = nft_queue_sreg_eval, + .init = nft_queue_sreg_init, + .dump = nft_queue_sreg_dump, +}; + +static const struct nft_expr_ops * +nft_queue_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (tb[NFTA_QUEUE_NUM] && tb[NFTA_QUEUE_SREG_QNUM]) + return ERR_PTR(-EINVAL); + + init_hashrandom(&jhash_initval); + + if (tb[NFTA_QUEUE_NUM]) + return &nft_queue_ops; + + if (tb[NFTA_QUEUE_SREG_QNUM]) + return &nft_queue_sreg_ops; + + return ERR_PTR(-EINVAL); +} + static struct nft_expr_type nft_queue_type __read_mostly = { .name = "queue", - .ops = &nft_queue_ops, + .select_ops = &nft_queue_select_ops, .policy = nft_queue_policy, .maxattr = NFTA_QUEUE_MAX, .owner = THIS_MODULE, diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c new file mode 100644 index 000000000000..c00104c07095 --- /dev/null +++ b/net/netfilter/nft_quota.c @@ -0,0 +1,121 @@ +/* + * Copyright (c) 2016 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/atomic.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> + +struct nft_quota { + u64 quota; + bool invert; + atomic64_t remain; +}; + +static inline bool nft_overquota(struct nft_quota *priv, + const struct nft_pktinfo *pkt) +{ + return atomic64_sub_return(pkt->skb->len, &priv->remain) < 0; +} + +static void nft_quota_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_quota *priv = nft_expr_priv(expr); + + if (nft_overquota(priv, pkt) ^ priv->invert) + regs->verdict.code = NFT_BREAK; +} + +static const struct nla_policy nft_quota_policy[NFTA_QUOTA_MAX + 1] = { + [NFTA_QUOTA_BYTES] = { .type = NLA_U64 }, + [NFTA_QUOTA_FLAGS] = { .type = NLA_U32 }, +}; + +static int nft_quota_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_quota *priv = nft_expr_priv(expr); + u32 flags = 0; + u64 quota; + + if (!tb[NFTA_QUOTA_BYTES]) + return -EINVAL; + + quota = be64_to_cpu(nla_get_be64(tb[NFTA_QUOTA_BYTES])); + if (quota > S64_MAX) + return -EOVERFLOW; + + if (tb[NFTA_QUOTA_FLAGS]) { + flags = ntohl(nla_get_be32(tb[NFTA_QUOTA_FLAGS])); + if (flags & ~NFT_QUOTA_F_INV) + return -EINVAL; + } + + priv->quota = quota; + priv->invert = (flags & NFT_QUOTA_F_INV) ? true : false; + atomic64_set(&priv->remain, quota); + + return 0; +} + +static int nft_quota_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_quota *priv = nft_expr_priv(expr); + u32 flags = priv->invert ? NFT_QUOTA_F_INV : 0; + + if (nla_put_be64(skb, NFTA_QUOTA_BYTES, cpu_to_be64(priv->quota), + NFTA_QUOTA_PAD) || + nla_put_be32(skb, NFTA_QUOTA_FLAGS, htonl(flags))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_quota_type; +static const struct nft_expr_ops nft_quota_ops = { + .type = &nft_quota_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_quota)), + .eval = nft_quota_eval, + .init = nft_quota_init, + .dump = nft_quota_dump, +}; + +static struct nft_expr_type nft_quota_type __read_mostly = { + .name = "quota", + .ops = &nft_quota_ops, + .policy = nft_quota_policy, + .maxattr = NFTA_QUOTA_MAX, + .flags = NFT_EXPR_STATEFUL, + .owner = THIS_MODULE, +}; + +static int __init nft_quota_module_init(void) +{ + return nft_register_expr(&nft_quota_type); +} + +static void __exit nft_quota_module_exit(void) +{ + nft_unregister_expr(&nft_quota_type); +} + +module_init(nft_quota_module_init); +module_exit(nft_quota_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_ALIAS_NFT_EXPR("quota"); diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c new file mode 100644 index 000000000000..fbc88009ca2e --- /dev/null +++ b/net/netfilter/nft_range.c @@ -0,0 +1,150 @@ +/* + * Copyright (c) 2016 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> +#include <net/netfilter/nf_tables.h> + +struct nft_range_expr { + struct nft_data data_from; + struct nft_data data_to; + enum nft_registers sreg:8; + u8 len; + enum nft_range_ops op:8; +}; + +static void nft_range_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_range_expr *priv = nft_expr_priv(expr); + int d1, d2; + + d1 = memcmp(®s->data[priv->sreg], &priv->data_from, priv->len); + d2 = memcmp(®s->data[priv->sreg], &priv->data_to, priv->len); + switch (priv->op) { + case NFT_RANGE_EQ: + if (d1 < 0 || d2 > 0) + regs->verdict.code = NFT_BREAK; + break; + case NFT_RANGE_NEQ: + if (d1 >= 0 && d2 <= 0) + regs->verdict.code = NFT_BREAK; + break; + } +} + +static const struct nla_policy nft_range_policy[NFTA_RANGE_MAX + 1] = { + [NFTA_RANGE_SREG] = { .type = NLA_U32 }, + [NFTA_RANGE_OP] = { .type = NLA_U32 }, + [NFTA_RANGE_FROM_DATA] = { .type = NLA_NESTED }, + [NFTA_RANGE_TO_DATA] = { .type = NLA_NESTED }, +}; + +static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_range_expr *priv = nft_expr_priv(expr); + struct nft_data_desc desc_from, desc_to; + int err; + u32 op; + + err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from), + &desc_from, tb[NFTA_RANGE_FROM_DATA]); + if (err < 0) + return err; + + err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to), + &desc_to, tb[NFTA_RANGE_TO_DATA]); + if (err < 0) + goto err1; + + if (desc_from.len != desc_to.len) { + err = -EINVAL; + goto err2; + } + + priv->sreg = nft_parse_register(tb[NFTA_RANGE_SREG]); + err = nft_validate_register_load(priv->sreg, desc_from.len); + if (err < 0) + goto err2; + + err = nft_parse_u32_check(tb[NFTA_RANGE_OP], U8_MAX, &op); + if (err < 0) + goto err2; + + switch (op) { + case NFT_RANGE_EQ: + case NFT_RANGE_NEQ: + break; + default: + err = -EINVAL; + goto err2; + } + + priv->op = op; + priv->len = desc_from.len; + return 0; +err2: + nft_data_uninit(&priv->data_to, desc_to.type); +err1: + nft_data_uninit(&priv->data_from, desc_from.type); + return err; +} + +static int nft_range_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_range_expr *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_RANGE_SREG, priv->sreg)) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_RANGE_OP, htonl(priv->op))) + goto nla_put_failure; + + if (nft_data_dump(skb, NFTA_RANGE_FROM_DATA, &priv->data_from, + NFT_DATA_VALUE, priv->len) < 0 || + nft_data_dump(skb, NFTA_RANGE_TO_DATA, &priv->data_to, + NFT_DATA_VALUE, priv->len) < 0) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_range_type; +static const struct nft_expr_ops nft_range_ops = { + .type = &nft_range_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_range_expr)), + .eval = nft_range_eval, + .init = nft_range_init, + .dump = nft_range_dump, +}; + +static struct nft_expr_type nft_range_type __read_mostly = { + .name = "range", + .ops = &nft_range_ops, + .policy = nft_range_policy, + .maxattr = NFTA_RANGE_MAX, + .owner = THIS_MODULE, +}; + +int __init nft_range_module_init(void) +{ + return nft_register_expr(&nft_range_type); +} + +void nft_range_module_exit(void) +{ + nft_unregister_expr(&nft_range_type); +} diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c new file mode 100644 index 000000000000..a3dface3e6e6 --- /dev/null +++ b/net/netfilter/nft_set_hash.c @@ -0,0 +1,413 @@ +/* + * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/list.h> +#include <linux/log2.h> +#include <linux/jhash.h> +#include <linux/netlink.h> +#include <linux/workqueue.h> +#include <linux/rhashtable.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> + +/* We target a hash table size of 4, element hint is 75% of final size */ +#define NFT_HASH_ELEMENT_HINT 3 + +struct nft_hash { + struct rhashtable ht; + struct delayed_work gc_work; +}; + +struct nft_hash_elem { + struct rhash_head node; + struct nft_set_ext ext; +}; + +struct nft_hash_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) +{ + const struct nft_hash_cmp_arg *arg = data; + + return jhash(arg->key, len, seed); +} + +static inline u32 nft_hash_obj(const void *data, u32 len, u32 seed) +{ + const struct nft_hash_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) +{ + const struct nft_hash_cmp_arg *x = arg->key; + const struct nft_hash_elem *he = ptr; + + if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) + return 1; + if (nft_set_elem_expired(&he->ext)) + return 1; + if (!nft_set_elem_active(&he->ext, x->genmask)) + return 1; + 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) +{ + struct nft_hash *priv = nft_set_priv(set); + const struct nft_hash_elem *he; + struct nft_hash_cmp_arg arg = { + .genmask = nft_genmask_cur(net), + .set = set, + .key = key, + }; + + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_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) +{ + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he, *prev; + struct nft_hash_cmp_arg arg = { + .genmask = NFT_GENMASK_ANY, + .set = set, + .key = key, + }; + + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + if (he != NULL) + goto out; + + he = new(set, expr, regs); + if (he == NULL) + goto err1; + + prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node, + nft_hash_params); + if (IS_ERR(prev)) + goto err2; + + /* Another cpu may race to insert the element with the same key */ + if (prev) { + nft_set_elem_destroy(set, he, true); + he = prev; + } + +out: + *ext = &he->ext; + return true; + +err2: + nft_set_elem_destroy(set, he, true); +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) +{ + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he = elem->priv; + struct nft_hash_cmp_arg arg = { + .genmask = nft_genmask_next(net), + .set = set, + .key = elem->key.val.data, + }; + struct nft_hash_elem *prev; + + prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node, + nft_hash_params); + if (IS_ERR(prev)) + return PTR_ERR(prev); + if (prev) { + *ext = &prev->ext; + return -EEXIST; + } + 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); + nft_set_elem_clear_busy(&he->ext); +} + +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 *he; + struct nft_hash_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); + if (he != NULL) { + if (!nft_set_elem_mark_busy(&he->ext) || + !nft_is_active(net, &he->ext)) + nft_set_elem_change_active(net, set, &he->ext); + else + he = NULL; + } + rcu_read_unlock(); + + return he; +} + +static void nft_hash_remove(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; + + rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); +} + +static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, + struct nft_set_iter *iter) +{ + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he; + struct rhashtable_iter hti; + struct nft_set_elem elem; + int err; + + err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); + iter->err = err; + if (err) + return; + + err = rhashtable_walk_start(&hti); + if (err && err != -EAGAIN) { + iter->err = err; + goto out; + } + + while ((he = rhashtable_walk_next(&hti))) { + if (IS_ERR(he)) { + err = PTR_ERR(he); + if (err != -EAGAIN) { + iter->err = err; + goto out; + } + + continue; + } + + if (iter->count < iter->skip) + goto cont; + if (nft_set_elem_expired(&he->ext)) + 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) + goto out; + +cont: + iter->count++; + } + +out: + rhashtable_walk_stop(&hti); + rhashtable_walk_exit(&hti); +} + +static void nft_hash_gc(struct work_struct *work) +{ + struct nft_set *set; + struct nft_hash_elem *he; + struct nft_hash *priv; + struct nft_set_gc_batch *gcb = NULL; + struct rhashtable_iter hti; + int err; + + priv = container_of(work, struct nft_hash, gc_work.work); + set = nft_set_container_of(priv); + + err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); + if (err) + goto schedule; + + err = rhashtable_walk_start(&hti); + if (err && err != -EAGAIN) + goto out; + + while ((he = rhashtable_walk_next(&hti))) { + if (IS_ERR(he)) { + if (PTR_ERR(he) != -EAGAIN) + goto out; + continue; + } + + if (!nft_set_elem_expired(&he->ext)) + continue; + if (nft_set_elem_mark_busy(&he->ext)) + continue; + + 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); + atomic_dec(&set->nelems); + nft_set_gc_batch_add(gcb, he); + } +out: + rhashtable_walk_stop(&hti); + rhashtable_walk_exit(&hti); + + nft_set_gc_batch_complete(gcb); +schedule: + queue_delayed_work(system_power_efficient_wq, &priv->gc_work, + nft_set_gc_interval(set)); +} + +static unsigned int nft_hash_privsize(const struct nlattr * const nla[]) +{ + return sizeof(struct nft_hash); +} + +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[]) +{ + struct nft_hash *priv = nft_set_priv(set); + struct rhashtable_params params = nft_hash_params; + int err; + + params.nelem_hint = desc->size ?: NFT_HASH_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); + 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) +{ + nft_set_elem_destroy((const struct nft_set *)arg, ptr, true); +} + +static void nft_hash_destroy(const struct nft_set *set) +{ + struct nft_hash *priv = nft_set_priv(set); + + cancel_delayed_work_sync(&priv->gc_work); + rhashtable_free_and_destroy(&priv->ht, nft_hash_elem_destroy, + (void *)set); +} + +static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + 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 *); + } + + est->class = NFT_SET_CLASS_O_1; + + return true; +} + +static struct nft_set_ops nft_hash_ops __read_mostly = { + .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, + .remove = nft_hash_remove, + .lookup = nft_hash_lookup, + .update = nft_hash_update, + .walk = nft_hash_walk, + .features = NFT_SET_MAP | NFT_SET_TIMEOUT, + .owner = THIS_MODULE, +}; + +static int __init nft_hash_module_init(void) +{ + return nft_register_set(&nft_hash_ops); +} + +static void __exit nft_hash_module_exit(void) +{ + nft_unregister_set(&nft_hash_ops); +} + +module_init(nft_hash_module_init); +module_exit(nft_hash_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_set_rbtree.c index ffe9ae062d23..36493a7cae88 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -96,7 +96,8 @@ out: } static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, - struct nft_rbtree_elem *new) + struct nft_rbtree_elem *new, + struct nft_set_ext **ext) { struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); @@ -124,8 +125,10 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, else if (!nft_rbtree_interval_end(rbe) && nft_rbtree_interval_end(new)) p = &parent->rb_right; - else + else { + *ext = &rbe->ext; return -EEXIST; + } } } } @@ -135,13 +138,14 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, } static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + const struct nft_set_elem *elem, + struct nft_set_ext **ext) { struct nft_rbtree_elem *rbe = elem->priv; int err; spin_lock_bh(&nft_rbtree_lock); - err = __nft_rbtree_insert(net, set, rbe); + err = __nft_rbtree_insert(net, set, rbe, ext); spin_unlock_bh(&nft_rbtree_lock); return err; @@ -262,7 +266,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_set_elem_destroy(set, rbe); + nft_set_elem_destroy(set, rbe, true); } } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index e0aa7c1d0224..fc4977456c30 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1513,7 +1513,7 @@ xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn) if (!num_hooks) return ERR_PTR(-EINVAL); - ops = kmalloc(sizeof(*ops) * num_hooks, GFP_KERNEL); + ops = kcalloc(num_hooks, sizeof(*ops), GFP_KERNEL); if (ops == NULL) return ERR_PTR(-ENOMEM); diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c index 018eed7e1ff1..8668a5c18dc3 100644 --- a/net/netfilter/xt_NFLOG.c +++ b/net/netfilter/xt_NFLOG.c @@ -32,6 +32,7 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) li.u.ulog.copy_len = info->len; li.u.ulog.group = info->group; li.u.ulog.qthreshold = info->threshold; + li.u.ulog.flags = 0; if (info->flags & XT_NFLOG_F_COPY_LEN) li.u.ulog.flags |= NF_LOG_F_COPY_LEN; diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 515131f9e021..dbd6c4a12b97 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -24,7 +24,6 @@ static DEFINE_MUTEX(xt_rateest_mutex); #define RATEEST_HSIZE 16 static struct hlist_head rateest_hash[RATEEST_HSIZE] __read_mostly; static unsigned int jhash_rnd __read_mostly; -static bool rnd_inited __read_mostly; static unsigned int xt_rateest_hash(const char *name) { @@ -99,10 +98,7 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) } cfg; int ret; - if (unlikely(!rnd_inited)) { - get_random_bytes(&jhash_rnd, sizeof(jhash_rnd)); - rnd_inited = true; - } + net_get_random_once(&jhash_rnd, sizeof(jhash_rnd)); est = xt_rateest_lookup(info->name); if (est) { diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index e118397254af..872db2d0e2a9 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -110,18 +110,14 @@ tcpmss_mangle_packet(struct sk_buff *skb, if (info->mss == XT_TCPMSS_CLAMP_PMTU) { struct net *net = par->net; unsigned int in_mtu = tcpmss_reverse_mtu(net, skb, family); + unsigned int min_mtu = min(dst_mtu(skb_dst(skb)), in_mtu); - if (dst_mtu(skb_dst(skb)) <= minlen) { + if (min_mtu <= minlen) { net_err_ratelimited("unknown or invalid path-MTU (%u)\n", - dst_mtu(skb_dst(skb))); + min_mtu); return -1; } - if (in_mtu <= minlen) { - net_err_ratelimited("unknown or invalid path-MTU (%u)\n", - in_mtu); - return -1; - } - newmss = min(dst_mtu(skb_dst(skb)), in_mtu) - minlen; + newmss = min_mtu - minlen; } else newmss = info->mss; diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 6e57a3966dc5..0471db4032c5 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -89,6 +89,8 @@ static int tee_tg_check(const struct xt_tgchk_param *par) return -EINVAL; if (info->oif[0]) { + int ret; + if (info->oif[sizeof(info->oif)-1] != '\0') return -EINVAL; @@ -101,7 +103,11 @@ static int tee_tg_check(const struct xt_tgchk_param *par) priv->notifier.notifier_call = tee_netdev_event; info->priv = priv; - register_netdevice_notifier(&priv->notifier); + ret = register_netdevice_notifier(&priv->notifier); + if (ret) { + kfree(priv); + return ret; + } } else info->priv = NULL; diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 99bbc829868d..b6dc322593a3 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -366,14 +366,8 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) unsigned int i; int ret; - if (unlikely(!connlimit_rnd)) { - u_int32_t rand; + net_get_random_once(&connlimit_rnd, sizeof(connlimit_rnd)); - do { - get_random_bytes(&rand, sizeof(rand)); - } while (!rand); - cmpxchg(&connlimit_rnd, 0, rand); - } ret = nf_ct_l3proto_try_module_get(par->family); if (ret < 0) { pr_info("cannot load conntrack support for " diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 69f78e96fdb4..b83e158e116a 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -44,7 +44,7 @@ connmark_tg(struct sk_buff *skb, const struct xt_action_param *par) u_int32_t newmark; ct = nf_ct_get(skb, &ctinfo); - if (ct == NULL) + if (ct == NULL || nf_ct_is_untracked(ct)) return XT_CONTINUE; switch (info->mode) { @@ -97,7 +97,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par) const struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); - if (ct == NULL) + if (ct == NULL || nf_ct_is_untracked(ct)) return false; return ((ct->mark & info->mask) == info->mark) ^ info->invert; diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 188404b9b002..a3b8f697cfc5 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -233,10 +233,8 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par, return false; if (info->match_flags & XT_CONNTRACK_EXPIRES) { - unsigned long expires = 0; + unsigned long expires = nf_ct_expires(ct) / HZ; - if (timer_pending(&ct->timeout)) - expires = (ct->timeout.expires - jiffies) / HZ; if ((expires >= info->expires_min && expires <= info->expires_max) ^ !(info->invert_flags & XT_CONNTRACK_EXPIRES)) diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 178696852bde..b89b688e9d01 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -56,6 +56,7 @@ static inline struct hashlimit_net *hashlimit_pernet(struct net *net) } /* need to declare this at the top */ +static const struct file_operations dl_file_ops_v1; static const struct file_operations dl_file_ops; /* hash table crap */ @@ -86,8 +87,8 @@ struct dsthash_ent { unsigned long expires; /* precalculated expiry time */ struct { unsigned long prev; /* last modification */ - u_int32_t credit; - u_int32_t credit_cap, cost; + u_int64_t credit; + u_int64_t credit_cap, cost; } rateinfo; struct rcu_head rcu; }; @@ -98,7 +99,7 @@ struct xt_hashlimit_htable { u_int8_t family; bool rnd_initialized; - struct hashlimit_cfg1 cfg; /* config */ + struct hashlimit_cfg2 cfg; /* config */ /* used internally */ spinlock_t lock; /* lock for list_head */ @@ -114,6 +115,30 @@ struct xt_hashlimit_htable { struct hlist_head hash[0]; /* hashtable itself */ }; +static int +cfg_copy(struct hashlimit_cfg2 *to, void *from, int revision) +{ + if (revision == 1) { + struct hashlimit_cfg1 *cfg = (struct hashlimit_cfg1 *)from; + + to->mode = cfg->mode; + to->avg = cfg->avg; + to->burst = cfg->burst; + to->size = cfg->size; + to->max = cfg->max; + to->gc_interval = cfg->gc_interval; + to->expire = cfg->expire; + to->srcmask = cfg->srcmask; + to->dstmask = cfg->dstmask; + } else if (revision == 2) { + memcpy(to, from, sizeof(struct hashlimit_cfg2)); + } else { + return -EINVAL; + } + + return 0; +} + static DEFINE_MUTEX(hashlimit_mutex); /* protects htables list */ static struct kmem_cache *hashlimit_cachep __read_mostly; @@ -215,16 +240,18 @@ dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) } static void htable_gc(struct work_struct *work); -static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, - u_int8_t family) +static int htable_create(struct net *net, struct hashlimit_cfg2 *cfg, + const char *name, u_int8_t family, + struct xt_hashlimit_htable **out_hinfo, + int revision) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; - unsigned int size; - unsigned int i; + unsigned int size, i; + int ret; - if (minfo->cfg.size) { - size = minfo->cfg.size; + if (cfg->size) { + size = cfg->size; } else { size = (totalram_pages << PAGE_SHIFT) / 16384 / sizeof(struct list_head); @@ -238,10 +265,14 @@ static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, sizeof(struct list_head) * size); if (hinfo == NULL) return -ENOMEM; - minfo->hinfo = hinfo; + *out_hinfo = hinfo; /* copy match config into hashtable config */ - memcpy(&hinfo->cfg, &minfo->cfg, sizeof(hinfo->cfg)); + ret = cfg_copy(&hinfo->cfg, (void *)cfg, 2); + + if (ret) + return ret; + hinfo->cfg.size = size; if (hinfo->cfg.max == 0) hinfo->cfg.max = 8 * hinfo->cfg.size; @@ -255,17 +286,18 @@ static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; - hinfo->name = kstrdup(minfo->name, GFP_KERNEL); + hinfo->name = kstrdup(name, GFP_KERNEL); if (!hinfo->name) { vfree(hinfo); return -ENOMEM; } spin_lock_init(&hinfo->lock); - hinfo->pde = proc_create_data(minfo->name, 0, + hinfo->pde = proc_create_data(name, 0, (family == NFPROTO_IPV4) ? hashlimit_net->ipt_hashlimit : hashlimit_net->ip6t_hashlimit, - &dl_file_ops, hinfo); + (revision == 1) ? &dl_file_ops_v1 : &dl_file_ops, + hinfo); if (hinfo->pde == NULL) { kfree(hinfo->name); vfree(hinfo); @@ -398,7 +430,8 @@ static void htable_put(struct xt_hashlimit_htable *hinfo) (slowest userspace tool allows), which means CREDITS_PER_JIFFY*HZ*60*60*24 < 2^32 ie. */ -#define MAX_CPJ (0xFFFFFFFF / (HZ*60*60*24)) +#define MAX_CPJ_v1 (0xFFFFFFFF / (HZ*60*60*24)) +#define MAX_CPJ (0xFFFFFFFFFFFFFFFFULL / (HZ*60*60*24)) /* Repeated shift and or gives us all 1s, final shift and add 1 gives * us the power of 2 below the theoretical max, so GCC simply does a @@ -408,9 +441,12 @@ static void htable_put(struct xt_hashlimit_htable *hinfo) #define _POW2_BELOW8(x) (_POW2_BELOW4(x)|_POW2_BELOW4((x)>>4)) #define _POW2_BELOW16(x) (_POW2_BELOW8(x)|_POW2_BELOW8((x)>>8)) #define _POW2_BELOW32(x) (_POW2_BELOW16(x)|_POW2_BELOW16((x)>>16)) +#define _POW2_BELOW64(x) (_POW2_BELOW32(x)|_POW2_BELOW32((x)>>32)) #define POW2_BELOW32(x) ((_POW2_BELOW32(x)>>1) + 1) +#define POW2_BELOW64(x) ((_POW2_BELOW64(x)>>1) + 1) -#define CREDITS_PER_JIFFY POW2_BELOW32(MAX_CPJ) +#define CREDITS_PER_JIFFY POW2_BELOW64(MAX_CPJ) +#define CREDITS_PER_JIFFY_v1 POW2_BELOW32(MAX_CPJ_v1) /* in byte mode, the lowest possible rate is one packet/second. * credit_cap is used as a counter that tells us how many times we can @@ -425,14 +461,25 @@ static u32 xt_hashlimit_len_to_chunks(u32 len) } /* Precision saver. */ -static u32 user2credits(u32 user) +static u64 user2credits(u64 user, int revision) { - /* If multiplying would overflow... */ - if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY)) - /* Divide first. */ - return (user / XT_HASHLIMIT_SCALE) * HZ * CREDITS_PER_JIFFY; + if (revision == 1) { + /* If multiplying would overflow... */ + if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY_v1)) + /* Divide first. */ + return div64_u64(user, XT_HASHLIMIT_SCALE) + * HZ * CREDITS_PER_JIFFY_v1; + + return div64_u64(user * HZ * CREDITS_PER_JIFFY_v1, + XT_HASHLIMIT_SCALE); + } else { + if (user > 0xFFFFFFFFFFFFFFFFULL / (HZ*CREDITS_PER_JIFFY)) + return div64_u64(user, XT_HASHLIMIT_SCALE_v2) + * HZ * CREDITS_PER_JIFFY; - return (user * HZ * CREDITS_PER_JIFFY) / XT_HASHLIMIT_SCALE; + return div64_u64(user * HZ * CREDITS_PER_JIFFY, + XT_HASHLIMIT_SCALE_v2); + } } static u32 user2credits_byte(u32 user) @@ -442,10 +489,11 @@ static u32 user2credits_byte(u32 user) return (u32) (us >> 32); } -static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) +static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, + u32 mode, int revision) { unsigned long delta = now - dh->rateinfo.prev; - u32 cap; + u64 cap, cpj; if (delta == 0) return; @@ -453,7 +501,7 @@ static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) dh->rateinfo.prev = now; if (mode & XT_HASHLIMIT_BYTES) { - u32 tmp = dh->rateinfo.credit; + u64 tmp = dh->rateinfo.credit; dh->rateinfo.credit += CREDITS_PER_JIFFY_BYTES * delta; cap = CREDITS_PER_JIFFY_BYTES * HZ; if (tmp >= dh->rateinfo.credit) {/* overflow */ @@ -461,7 +509,9 @@ static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) return; } } else { - dh->rateinfo.credit += delta * CREDITS_PER_JIFFY; + cpj = (revision == 1) ? + CREDITS_PER_JIFFY_v1 : CREDITS_PER_JIFFY; + dh->rateinfo.credit += delta * cpj; cap = dh->rateinfo.credit_cap; } if (dh->rateinfo.credit > cap) @@ -469,7 +519,7 @@ static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) } static void rateinfo_init(struct dsthash_ent *dh, - struct xt_hashlimit_htable *hinfo) + struct xt_hashlimit_htable *hinfo, int revision) { dh->rateinfo.prev = jiffies; if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { @@ -478,8 +528,8 @@ static void rateinfo_init(struct dsthash_ent *dh, dh->rateinfo.credit_cap = hinfo->cfg.burst; } else { dh->rateinfo.credit = user2credits(hinfo->cfg.avg * - hinfo->cfg.burst); - dh->rateinfo.cost = user2credits(hinfo->cfg.avg); + hinfo->cfg.burst, revision); + dh->rateinfo.cost = user2credits(hinfo->cfg.avg, revision); dh->rateinfo.credit_cap = dh->rateinfo.credit; } } @@ -603,15 +653,15 @@ static u32 hashlimit_byte_cost(unsigned int len, struct dsthash_ent *dh) } static bool -hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) +hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, + struct xt_hashlimit_htable *hinfo, + const struct hashlimit_cfg2 *cfg, int revision) { - const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; - struct xt_hashlimit_htable *hinfo = info->hinfo; unsigned long now = jiffies; struct dsthash_ent *dh; struct dsthash_dst dst; bool race = false; - u32 cost; + u64 cost; if (hashlimit_init_dst(hinfo, &dst, skb, par->thoff) < 0) goto hotdrop; @@ -626,18 +676,18 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) } else if (race) { /* Already got an entry, update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_recalc(dh, now, hinfo->cfg.mode); + rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } else { dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_init(dh, hinfo); + rateinfo_init(dh, hinfo, revision); } } else { /* update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_recalc(dh, now, hinfo->cfg.mode); + rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } - if (info->cfg.mode & XT_HASHLIMIT_BYTES) + if (cfg->mode & XT_HASHLIMIT_BYTES) cost = hashlimit_byte_cost(skb->len, dh); else cost = dh->rateinfo.cost; @@ -647,84 +697,157 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) dh->rateinfo.credit -= cost; spin_unlock(&dh->lock); rcu_read_unlock_bh(); - return !(info->cfg.mode & XT_HASHLIMIT_INVERT); + return !(cfg->mode & XT_HASHLIMIT_INVERT); } spin_unlock(&dh->lock); rcu_read_unlock_bh(); /* default match is underlimit - so over the limit, we need to invert */ - return info->cfg.mode & XT_HASHLIMIT_INVERT; + return cfg->mode & XT_HASHLIMIT_INVERT; hotdrop: par->hotdrop = true; return false; } -static int hashlimit_mt_check(const struct xt_mtchk_param *par) +static bool +hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; + struct xt_hashlimit_htable *hinfo = info->hinfo; + struct hashlimit_cfg2 cfg = {}; + int ret; + + ret = cfg_copy(&cfg, (void *)&info->cfg, 1); + + if (ret) + return ret; + + return hashlimit_mt_common(skb, par, hinfo, &cfg, 1); +} + +static bool +hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + struct xt_hashlimit_htable *hinfo = info->hinfo; + + return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 2); +} + +static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, + struct xt_hashlimit_htable **hinfo, + struct hashlimit_cfg2 *cfg, + const char *name, int revision) { struct net *net = par->net; - struct xt_hashlimit_mtinfo1 *info = par->matchinfo; int ret; - if (info->cfg.gc_interval == 0 || info->cfg.expire == 0) - return -EINVAL; - if (info->name[sizeof(info->name)-1] != '\0') + if (cfg->gc_interval == 0 || cfg->expire == 0) return -EINVAL; if (par->family == NFPROTO_IPV4) { - if (info->cfg.srcmask > 32 || info->cfg.dstmask > 32) + if (cfg->srcmask > 32 || cfg->dstmask > 32) return -EINVAL; } else { - if (info->cfg.srcmask > 128 || info->cfg.dstmask > 128) + if (cfg->srcmask > 128 || cfg->dstmask > 128) return -EINVAL; } - if (info->cfg.mode & ~XT_HASHLIMIT_ALL) { + if (cfg->mode & ~XT_HASHLIMIT_ALL) { pr_info("Unknown mode mask %X, kernel too old?\n", - info->cfg.mode); + cfg->mode); return -EINVAL; } /* Check for overflow. */ - if (info->cfg.mode & XT_HASHLIMIT_BYTES) { - if (user2credits_byte(info->cfg.avg) == 0) { - pr_info("overflow, rate too high: %u\n", info->cfg.avg); + if (cfg->mode & XT_HASHLIMIT_BYTES) { + if (user2credits_byte(cfg->avg) == 0) { + pr_info("overflow, rate too high: %llu\n", cfg->avg); return -EINVAL; } - } else if (info->cfg.burst == 0 || - user2credits(info->cfg.avg * info->cfg.burst) < - user2credits(info->cfg.avg)) { - pr_info("overflow, try lower: %u/%u\n", - info->cfg.avg, info->cfg.burst); + } else if (cfg->burst == 0 || + user2credits(cfg->avg * cfg->burst, revision) < + user2credits(cfg->avg, revision)) { + pr_info("overflow, try lower: %llu/%llu\n", + cfg->avg, cfg->burst); return -ERANGE; } mutex_lock(&hashlimit_mutex); - info->hinfo = htable_find_get(net, info->name, par->family); - if (info->hinfo == NULL) { - ret = htable_create(net, info, par->family); + *hinfo = htable_find_get(net, name, par->family); + if (*hinfo == NULL) { + ret = htable_create(net, cfg, name, par->family, + hinfo, revision); if (ret < 0) { mutex_unlock(&hashlimit_mutex); return ret; } } mutex_unlock(&hashlimit_mutex); + return 0; } -static void hashlimit_mt_destroy(const struct xt_mtdtor_param *par) +static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) +{ + struct xt_hashlimit_mtinfo1 *info = par->matchinfo; + struct hashlimit_cfg2 cfg = {}; + int ret; + + if (info->name[sizeof(info->name) - 1] != '\0') + return -EINVAL; + + ret = cfg_copy(&cfg, (void *)&info->cfg, 1); + + if (ret) + return ret; + + return hashlimit_mt_check_common(par, &info->hinfo, + &cfg, info->name, 1); +} + +static int hashlimit_mt_check(const struct xt_mtchk_param *par) +{ + struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + + if (info->name[sizeof(info->name) - 1] != '\0') + return -EINVAL; + + return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg, + info->name, 2); +} + +static void hashlimit_mt_destroy_v1(const struct xt_mtdtor_param *par) { const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; htable_put(info->hinfo); } +static void hashlimit_mt_destroy(const struct xt_mtdtor_param *par) +{ + const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + + htable_put(info->hinfo); +} + static struct xt_match hashlimit_mt_reg[] __read_mostly = { { .name = "hashlimit", .revision = 1, .family = NFPROTO_IPV4, - .match = hashlimit_mt, + .match = hashlimit_mt_v1, .matchsize = sizeof(struct xt_hashlimit_mtinfo1), + .checkentry = hashlimit_mt_check_v1, + .destroy = hashlimit_mt_destroy_v1, + .me = THIS_MODULE, + }, + { + .name = "hashlimit", + .revision = 2, + .family = NFPROTO_IPV4, + .match = hashlimit_mt, + .matchsize = sizeof(struct xt_hashlimit_mtinfo2), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, @@ -734,8 +857,18 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .name = "hashlimit", .revision = 1, .family = NFPROTO_IPV6, - .match = hashlimit_mt, + .match = hashlimit_mt_v1, .matchsize = sizeof(struct xt_hashlimit_mtinfo1), + .checkentry = hashlimit_mt_check_v1, + .destroy = hashlimit_mt_destroy_v1, + .me = THIS_MODULE, + }, + { + .name = "hashlimit", + .revision = 2, + .family = NFPROTO_IPV6, + .match = hashlimit_mt, + .matchsize = sizeof(struct xt_hashlimit_mtinfo2), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, @@ -786,18 +919,12 @@ static void dl_seq_stop(struct seq_file *s, void *v) spin_unlock_bh(&htable->lock); } -static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, - struct seq_file *s) +static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, + struct seq_file *s) { - const struct xt_hashlimit_htable *ht = s->private; - - spin_lock(&ent->lock); - /* recalculate to show accurate numbers */ - rateinfo_recalc(ent, jiffies, ht->cfg.mode); - switch (family) { case NFPROTO_IPV4: - seq_printf(s, "%ld %pI4:%u->%pI4:%u %u %u %u\n", + seq_printf(s, "%ld %pI4:%u->%pI4:%u %llu %llu %llu\n", (long)(ent->expires - jiffies)/HZ, &ent->dst.ip.src, ntohs(ent->dst.src_port), @@ -808,7 +935,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, break; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: - seq_printf(s, "%ld %pI6:%u->%pI6:%u %u %u %u\n", + seq_printf(s, "%ld %pI6:%u->%pI6:%u %llu %llu %llu\n", (long)(ent->expires - jiffies)/HZ, &ent->dst.ip6.src, ntohs(ent->dst.src_port), @@ -821,10 +948,52 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, default: BUG(); } +} + +static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, + struct seq_file *s) +{ + const struct xt_hashlimit_htable *ht = s->private; + + spin_lock(&ent->lock); + /* recalculate to show accurate numbers */ + rateinfo_recalc(ent, jiffies, ht->cfg.mode, 1); + + dl_seq_print(ent, family, s); + + spin_unlock(&ent->lock); + return seq_has_overflowed(s); +} + +static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, + struct seq_file *s) +{ + const struct xt_hashlimit_htable *ht = s->private; + + spin_lock(&ent->lock); + /* recalculate to show accurate numbers */ + rateinfo_recalc(ent, jiffies, ht->cfg.mode, 2); + + dl_seq_print(ent, family, s); + spin_unlock(&ent->lock); return seq_has_overflowed(s); } +static int dl_seq_show_v1(struct seq_file *s, void *v) +{ + struct xt_hashlimit_htable *htable = s->private; + unsigned int *bucket = (unsigned int *)v; + struct dsthash_ent *ent; + + if (!hlist_empty(&htable->hash[*bucket])) { + hlist_for_each_entry(ent, &htable->hash[*bucket], node) + if (dl_seq_real_show_v1(ent, htable->family, s)) + return -1; + } + return 0; +} + static int dl_seq_show(struct seq_file *s, void *v) { struct xt_hashlimit_htable *htable = s->private; @@ -839,6 +1008,13 @@ static int dl_seq_show(struct seq_file *s, void *v) return 0; } +static const struct seq_operations dl_seq_ops_v1 = { + .start = dl_seq_start, + .next = dl_seq_next, + .stop = dl_seq_stop, + .show = dl_seq_show_v1 +}; + static const struct seq_operations dl_seq_ops = { .start = dl_seq_start, .next = dl_seq_next, @@ -846,17 +1022,37 @@ static const struct seq_operations dl_seq_ops = { .show = dl_seq_show }; +static int dl_proc_open_v1(struct inode *inode, struct file *file) +{ + int ret = seq_open(file, &dl_seq_ops_v1); + + if (!ret) { + struct seq_file *sf = file->private_data; + sf->private = PDE_DATA(inode); + } + return ret; +} + static int dl_proc_open(struct inode *inode, struct file *file) { int ret = seq_open(file, &dl_seq_ops); if (!ret) { struct seq_file *sf = file->private_data; + sf->private = PDE_DATA(inode); } return ret; } +static const struct file_operations dl_file_ops_v1 = { + .owner = THIS_MODULE, + .open = dl_proc_open_v1, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release +}; + static const struct file_operations dl_file_ops = { .owner = THIS_MODULE, .open = dl_proc_open, diff --git a/net/netfilter/xt_helper.c b/net/netfilter/xt_helper.c index 9f4ab00c8050..f679dd4c272a 100644 --- a/net/netfilter/xt_helper.c +++ b/net/netfilter/xt_helper.c @@ -41,7 +41,7 @@ helper_mt(const struct sk_buff *skb, struct xt_action_param *par) if (!master_help) return ret; - /* rcu_read_lock()ed by nf_hook_slow */ + /* rcu_read_lock()ed by nf_hook_thresh */ helper = rcu_dereference(master_help->helper); if (!helper) return ret; @@ -65,7 +65,7 @@ static int helper_mt_check(const struct xt_mtchk_param *par) par->family); return ret; } - info->name[29] = '\0'; + info->name[sizeof(info->name) - 1] = '\0'; return 0; } diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c index 89d53104c6b3..000e70377f85 100644 --- a/net/netfilter/xt_ipcomp.c +++ b/net/netfilter/xt_ipcomp.c @@ -26,6 +26,8 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Fan Du <fan.du@windriver.com>"); MODULE_DESCRIPTION("Xtables: IPv4/6 IPsec-IPComp SPI match"); +MODULE_ALIAS("ipt_ipcomp"); +MODULE_ALIAS("ip6t_ipcomp"); /* Returns 1 if the spi is matched by the range, 0 otherwise */ static inline bool diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index e5f18988aee0..bb33598e4530 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -107,8 +107,8 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) info->invert & XT_PHYSDEV_OP_BRIDGED) && par->hook_mask & ((1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_POST_ROUTING))) { - pr_info("using --physdev-out and --physdev-is-out are only" - "supported in the FORWARD and POSTROUTING chains with" + pr_info("using --physdev-out and --physdev-is-out are only " + "supported in the FORWARD and POSTROUTING chains with " "bridged traffic.\n"); if (par->hook_mask & (1 << NF_INET_LOCAL_OUT)) return -EINVAL; diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index d725a27743a1..e3b7a09b103e 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -110,7 +110,6 @@ static const struct file_operations recent_old_fops, recent_mt_fops; #endif static u_int32_t hash_rnd __read_mostly; -static bool hash_rnd_inited __read_mostly; static inline unsigned int recent_entry_hash4(const union nf_inet_addr *addr) { @@ -340,10 +339,8 @@ static int recent_mt_check(const struct xt_mtchk_param *par, int ret = -EINVAL; size_t sz; - if (unlikely(!hash_rnd_inited)) { - get_random_bytes(&hash_rnd, sizeof(hash_rnd)); - hash_rnd_inited = true; - } + net_get_random_once(&hash_rnd, sizeof(hash_rnd)); + if (info->check_set & ~XT_RECENT_VALID_FLAGS) { pr_info("Unsupported user space flags (%08x)\n", info->check_set); diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index ef36a56a02c6..4dedb96d1a06 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -68,7 +68,7 @@ match_packet(const struct sk_buff *skb, ++i, offset, sch->type, htons(sch->length), sch->flags); #endif - offset += WORD_ROUND(ntohs(sch->length)); + offset += SCTP_PAD4(ntohs(sch->length)); pr_debug("skb->len: %d\toffset: %d\n", skb->len, offset); |