diff options
Diffstat (limited to 'net/netfilter')
46 files changed, 1158 insertions, 879 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 95e757c37..9266ceebd 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -609,9 +609,8 @@ config NETFILTER_XT_MARK The target allows you to create rules in the "mangle" table which alter the netfilter mark (nfmark) field associated with the packet. - Prior to routing, the nfmark can influence the routing method (see - "Use netfilter MARK value as routing key") and can also be used by - other subsystems to change their behavior. + Prior to routing, the nfmark can influence the routing method and can + also be used by other subsystems to change their behavior. config NETFILTER_XT_CONNMARK tristate 'ctmark target and match support' @@ -753,9 +752,8 @@ config NETFILTER_XT_TARGET_HMARK The target allows you to create rules in the "raw" and "mangle" tables which set the skbuff mark by means of hash calculation within a given - range. The nfmark can influence the routing method (see "Use netfilter - MARK value as routing key") and can also be used by other subsystems to - change their behaviour. + range. The nfmark can influence the routing method and can also be used + by other subsystems to change their behaviour. To compile it as a module, choose M here. If unsure, say N. diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index d7024b2ed..5117bcb7d 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -395,6 +395,20 @@ static const char *const tcp_state_name_table[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_LAST] = "BUG!", }; +static const bool tcp_state_active_table[IP_VS_TCP_S_LAST] = { + [IP_VS_TCP_S_NONE] = false, + [IP_VS_TCP_S_ESTABLISHED] = true, + [IP_VS_TCP_S_SYN_SENT] = true, + [IP_VS_TCP_S_SYN_RECV] = true, + [IP_VS_TCP_S_FIN_WAIT] = false, + [IP_VS_TCP_S_TIME_WAIT] = false, + [IP_VS_TCP_S_CLOSE] = false, + [IP_VS_TCP_S_CLOSE_WAIT] = false, + [IP_VS_TCP_S_LAST_ACK] = false, + [IP_VS_TCP_S_LISTEN] = false, + [IP_VS_TCP_S_SYNACK] = true, +}; + #define sNO IP_VS_TCP_S_NONE #define sES IP_VS_TCP_S_ESTABLISHED #define sSS IP_VS_TCP_S_SYN_SENT @@ -418,6 +432,13 @@ static const char * tcp_state_name(int state) return tcp_state_name_table[state] ? tcp_state_name_table[state] : "?"; } +static bool tcp_state_active(int state) +{ + if (state >= IP_VS_TCP_S_LAST) + return false; + return tcp_state_active_table[state]; +} + static struct tcp_states_t tcp_states [] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ @@ -540,12 +561,12 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, if (dest) { if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && - (new_state != IP_VS_TCP_S_ESTABLISHED)) { + !tcp_state_active(new_state)) { atomic_dec(&dest->activeconns); atomic_inc(&dest->inactconns); cp->flags |= IP_VS_CONN_F_INACTIVE; } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && - (new_state == IP_VS_TCP_S_ESTABLISHED)) { + tcp_state_active(new_state)) { atomic_inc(&dest->activeconns); atomic_dec(&dest->inactconns); cp->flags &= ~IP_VS_CONN_F_INACTIVE; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 9f530adad..9934b0c93 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -83,6 +83,13 @@ void nf_conntrack_lock(spinlock_t *lock) __acquires(lock) spin_lock(lock); while (unlikely(nf_conntrack_locks_all)) { spin_unlock(lock); + + /* + * Order the 'nf_conntrack_locks_all' load vs. the + * spin_unlock_wait() loads below, to ensure + * that 'nf_conntrack_locks_all_lock' is indeed held: + */ + smp_rmb(); /* spin_lock(&nf_conntrack_locks_all_lock) */ spin_unlock_wait(&nf_conntrack_locks_all_lock); spin_lock(lock); } @@ -128,6 +135,14 @@ static void nf_conntrack_all_lock(void) spin_lock(&nf_conntrack_locks_all_lock); nf_conntrack_locks_all = true; + /* + * Order the above store of 'nf_conntrack_locks_all' against + * the spin_unlock_wait() loads below, such that if + * nf_conntrack_lock() observes 'nf_conntrack_locks_all' + * we must observe nf_conntrack_locks[] held: + */ + smp_mb(); /* spin_lock(&nf_conntrack_locks_all_lock) */ + for (i = 0; i < CONNTRACK_LOCKS; i++) { spin_unlock_wait(&nf_conntrack_locks[i]); } @@ -135,7 +150,13 @@ static void nf_conntrack_all_lock(void) static void nf_conntrack_all_unlock(void) { - nf_conntrack_locks_all = false; + /* + * All prior stores must be complete before we clear + * 'nf_conntrack_locks_all'. Otherwise nf_conntrack_lock() + * might observe the false value but not the entire + * critical section: + */ + smp_store_release(&nf_conntrack_locks_all, false); spin_unlock(&nf_conntrack_locks_all_lock); } @@ -327,16 +348,10 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, tmpl->status = IPS_TEMPLATE; write_pnet(&tmpl->ct_net, net); - - if (nf_ct_zone_add(tmpl, flags, zone) < 0) - goto out_free; - + nf_ct_zone_add(tmpl, zone); atomic_set(&tmpl->ct_general.use, 0); return tmpl; -out_free: - kfree(tmpl); - return NULL; } EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc); @@ -466,6 +481,23 @@ 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) +{ + struct hlist_nulls_head *hptr; + unsigned int sequence, hsz; + + 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)); + + *hash = hptr; + *hsize = hsz; +} +EXPORT_SYMBOL_GPL(nf_conntrack_get_ht); + /* * Warning : * - Caller must take a reference on returned object @@ -824,67 +856,69 @@ EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken); /* There's a small race here where we may free a just-assured connection. Too bad: we're in trouble anyway. */ -static noinline int early_drop(struct net *net, unsigned int _hash) +static unsigned int early_drop_list(struct net *net, + struct hlist_nulls_head *head) { - /* Use oldest entry, which is roughly LRU */ struct nf_conntrack_tuple_hash *h; - struct nf_conn *tmp; struct hlist_nulls_node *n; - unsigned int i, hash, sequence; - struct nf_conn *ct = NULL; - spinlock_t *lockp; - bool ret = false; + unsigned int drops = 0; + struct nf_conn *tmp; - i = 0; + hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) { + tmp = nf_ct_tuplehash_to_ctrack(h); - local_bh_disable(); -restart: - sequence = read_seqcount_begin(&nf_conntrack_generation); - for (; i < NF_CT_EVICTION_RANGE; i++) { - hash = scale_hash(_hash++); - lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS]; - nf_conntrack_lock(lockp); - if (read_seqcount_retry(&nf_conntrack_generation, sequence)) { - spin_unlock(lockp); - goto restart; - } - hlist_nulls_for_each_entry_rcu(h, n, &nf_conntrack_hash[hash], - hnnode) { - tmp = nf_ct_tuplehash_to_ctrack(h); - - if (test_bit(IPS_ASSURED_BIT, &tmp->status) || - !net_eq(nf_ct_net(tmp), net) || - nf_ct_is_dying(tmp)) - continue; - - if (atomic_inc_not_zero(&tmp->ct_general.use)) { - ct = tmp; - break; - } - } + if (test_bit(IPS_ASSURED_BIT, &tmp->status) || + !net_eq(nf_ct_net(tmp), net) || + nf_ct_is_dying(tmp)) + continue; - spin_unlock(lockp); - if (ct) - break; + if (!atomic_inc_not_zero(&tmp->ct_general.use)) + continue; + + /* kill only if still in same netns -- might have moved due to + * SLAB_DESTROY_BY_RCU rules. + * + * We steal the timer reference. If that fails timer has + * already fired or someone else deleted it. Just drop ref + * and move to next entry. + */ + if (net_eq(nf_ct_net(tmp), net) && + nf_ct_is_confirmed(tmp) && + del_timer(&tmp->timeout) && + nf_ct_delete(tmp, 0, 0)) + drops++; + + nf_ct_put(tmp); } - local_bh_enable(); + return drops; +} - if (!ct) - return false; +static noinline int early_drop(struct net *net, unsigned int _hash) +{ + unsigned int i; - /* kill only if in same netns -- might have moved due to - * SLAB_DESTROY_BY_RCU rules - */ - if (net_eq(nf_ct_net(ct), net) && del_timer(&ct->timeout)) { - if (nf_ct_delete(ct, 0, 0)) { - NF_CT_STAT_INC_ATOMIC(net, early_drop); - ret = true; + for (i = 0; i < NF_CT_EVICTION_RANGE; i++) { + struct hlist_nulls_head *ct_hash; + unsigned hash, sequence, 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)); + + drops = early_drop_list(net, &ct_hash[hash]); + rcu_read_unlock(); + + if (drops) { + NF_CT_STAT_ADD_ATOMIC(net, early_drop, drops); + return true; } } - nf_ct_put(ct); - return ret; + return false; } static struct nf_conn * @@ -930,16 +964,13 @@ __nf_conntrack_alloc(struct net *net, offsetof(struct nf_conn, proto) - offsetof(struct nf_conn, __nfct_init_offset[0])); - if (zone && nf_ct_zone_add(ct, GFP_ATOMIC, zone) < 0) - goto out_free; + nf_ct_zone_add(ct, zone); /* Because we use RCU lookups, we set ct_general.use to zero before * this is inserted in any list. */ atomic_set(&ct->ct_general.use, 0); return ct; -out_free: - kmem_cache_free(nf_conntrack_cachep, ct); out: atomic_dec(&net->ct.count); return ERR_PTR(-ENOMEM); @@ -1004,9 +1035,9 @@ 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; @@ -1343,14 +1374,6 @@ bool __nf_ct_kill_acct(struct nf_conn *ct, } EXPORT_SYMBOL_GPL(__nf_ct_kill_acct); -#ifdef CONFIG_NF_CONNTRACK_ZONES -static struct nf_ct_ext_type nf_ct_zone_extend __read_mostly = { - .len = sizeof(struct nf_conntrack_zone), - .align = __alignof__(struct nf_conntrack_zone), - .id = NF_CT_EXT_ZONE, -}; -#endif - #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> @@ -1533,9 +1556,6 @@ void nf_conntrack_cleanup_end(void) nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size); -#ifdef CONFIG_NF_CONNTRACK_ZONES - nf_ct_extend_unregister(&nf_ct_zone_extend); -#endif nf_conntrack_proto_fini(); nf_conntrack_seqadj_fini(); nf_conntrack_labels_fini(); @@ -1625,24 +1645,14 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) } EXPORT_SYMBOL_GPL(nf_ct_alloc_hashtable); -int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) +int nf_conntrack_hash_resize(unsigned int hashsize) { - int i, bucket, rc; - unsigned int hashsize, old_size; + int i, bucket; + unsigned int old_size; struct hlist_nulls_head *hash, *old_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; - if (current->nsproxy->net_ns != &init_net) - return -EOPNOTSUPP; - - /* On boot, we can set this without any fancy locking. */ - if (!nf_conntrack_htable_size) - return param_set_uint(val, kp); - - rc = kstrtouint(val, 0, &hashsize); - if (rc) - return rc; if (!hashsize) return -EINVAL; @@ -1650,6 +1660,12 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) if (!hash) return -ENOMEM; + old_size = nf_conntrack_htable_size; + if (old_size == hashsize) { + nf_ct_free_hashtable(hash, hashsize); + return 0; + } + local_bh_disable(); nf_conntrack_all_lock(); write_seqcount_begin(&nf_conntrack_generation); @@ -1685,6 +1701,25 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) nf_ct_free_hashtable(old_hash, old_size); return 0; } + +int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) +{ + unsigned int hashsize; + int rc; + + if (current->nsproxy->net_ns != &init_net) + return -EOPNOTSUPP; + + /* On boot, we can set this without any fancy locking. */ + if (!nf_conntrack_htable_size) + return param_set_uint(val, kp); + + rc = kstrtouint(val, 0, &hashsize); + if (rc) + return rc; + + return nf_conntrack_hash_resize(hashsize); +} EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize); module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, @@ -1741,7 +1776,7 @@ int nf_conntrack_init_start(void) nf_conntrack_cachep = kmem_cache_create("nf_conntrack", sizeof(struct nf_conn), 0, - SLAB_DESTROY_BY_RCU, NULL); + SLAB_DESTROY_BY_RCU | SLAB_HWCACHE_ALIGN, NULL); if (!nf_conntrack_cachep) goto err_cachep; @@ -1781,11 +1816,6 @@ int nf_conntrack_init_start(void) if (ret < 0) goto err_seqadj; -#ifdef CONFIG_NF_CONNTRACK_ZONES - ret = nf_ct_extend_register(&nf_ct_zone_extend); - if (ret < 0) - goto err_extend; -#endif ret = nf_conntrack_proto_init(); if (ret < 0) goto err_proto; @@ -1801,10 +1831,6 @@ int nf_conntrack_init_start(void) return 0; err_proto: -#ifdef CONFIG_NF_CONNTRACK_ZONES - nf_ct_extend_unregister(&nf_ct_zone_extend); -err_extend: -#endif nf_conntrack_seqadj_fini(); err_seqadj: nf_conntrack_labels_fini(); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 9e3693128..f8dbacf66 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -574,7 +574,7 @@ static int exp_seq_show(struct seq_file *s, void *v) helper = rcu_dereference(nfct_help(expect->master)->helper); if (helper) { seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name); - if (helper->expect_policy[expect->class].name) + if (helper->expect_policy[expect->class].name[0]) seq_printf(s, "/%s", helper->expect_policy[expect->class].name); } diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 1a9545965..02bcf00c2 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -73,7 +73,7 @@ void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id, size_t var_alloc_len, gfp_t gfp) { struct nf_ct_ext *old, *new; - int i, newlen, newoff; + int newlen, newoff; struct nf_ct_ext_type *t; /* Conntrack must not be confirmed to avoid races on reallocation. */ @@ -99,19 +99,8 @@ void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id, return NULL; if (new != old) { - for (i = 0; i < NF_CT_EXT_NUM; i++) { - if (!__nf_ct_ext_exist(old, i)) - continue; - - rcu_read_lock(); - t = rcu_dereference(nf_ct_ext_types[i]); - if (t && t->move) - t->move((void *)new + new->offset[i], - (void *)old + old->offset[i]); - rcu_read_unlock(); - } kfree_rcu(old, rcu); - ct->ext = new; + rcu_assign_pointer(ct->ext, new); } new->offset[id] = newoff; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 19efeba02..43147005b 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -572,7 +572,7 @@ static int nf_ct_ftp_from_nlattr(struct nlattr *attr, struct nf_conn *ct) return 0; } -static struct nf_conntrack_helper ftp[MAX_PORTS][2] __read_mostly; +static struct nf_conntrack_helper ftp[MAX_PORTS * 2] __read_mostly; static const struct nf_conntrack_expect_policy ftp_exp_policy = { .max_expected = 1, @@ -582,24 +582,13 @@ static const struct nf_conntrack_expect_policy ftp_exp_policy = { /* don't make this __exit, since it's called from __init ! */ static void nf_conntrack_ftp_fini(void) { - int i, j; - for (i = 0; i < ports_c; i++) { - for (j = 0; j < 2; j++) { - if (ftp[i][j].me == NULL) - continue; - - pr_debug("unregistering helper for pf: %d port: %d\n", - ftp[i][j].tuple.src.l3num, ports[i]); - nf_conntrack_helper_unregister(&ftp[i][j]); - } - } - + nf_conntrack_helpers_unregister(ftp, ports_c * 2); kfree(ftp_buffer); } static int __init nf_conntrack_ftp_init(void) { - int i, j = -1, ret = 0; + int i, ret = 0; ftp_buffer = kmalloc(65536, GFP_KERNEL); if (!ftp_buffer) @@ -611,32 +600,21 @@ static int __init nf_conntrack_ftp_init(void) /* FIXME should be configurable whether IPv4 and IPv6 FTP connections are tracked or not - YK */ for (i = 0; i < ports_c; i++) { - ftp[i][0].tuple.src.l3num = PF_INET; - ftp[i][1].tuple.src.l3num = PF_INET6; - for (j = 0; j < 2; j++) { - ftp[i][j].data_len = sizeof(struct nf_ct_ftp_master); - ftp[i][j].tuple.src.u.tcp.port = htons(ports[i]); - ftp[i][j].tuple.dst.protonum = IPPROTO_TCP; - ftp[i][j].expect_policy = &ftp_exp_policy; - ftp[i][j].me = THIS_MODULE; - ftp[i][j].help = help; - ftp[i][j].from_nlattr = nf_ct_ftp_from_nlattr; - if (ports[i] == FTP_PORT) - sprintf(ftp[i][j].name, "ftp"); - else - sprintf(ftp[i][j].name, "ftp-%d", ports[i]); - - pr_debug("registering helper for pf: %d port: %d\n", - ftp[i][j].tuple.src.l3num, ports[i]); - ret = nf_conntrack_helper_register(&ftp[i][j]); - if (ret) { - pr_err("failed to register helper for pf: %d port: %d\n", - ftp[i][j].tuple.src.l3num, ports[i]); - ports_c = i; - nf_conntrack_ftp_fini(); - return ret; - } - } + nf_ct_helper_init(&ftp[2 * i], AF_INET, IPPROTO_TCP, "ftp", + FTP_PORT, ports[i], ports[i], &ftp_exp_policy, + 0, sizeof(struct nf_ct_ftp_master), help, + nf_ct_ftp_from_nlattr, THIS_MODULE); + nf_ct_helper_init(&ftp[2 * i + 1], AF_INET6, IPPROTO_TCP, "ftp", + FTP_PORT, ports[i], ports[i], &ftp_exp_policy, + 0, sizeof(struct nf_ct_ftp_master), help, + nf_ct_ftp_from_nlattr, THIS_MODULE); + } + + ret = nf_conntrack_helpers_register(ftp, ports_c * 2); + if (ret < 0) { + pr_err("failed to register helpers\n"); + kfree(ftp_buffer); + return ret; } return 0; diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index bcd5ed6b7..89b2e4692 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -846,9 +846,10 @@ int DecodeQ931(unsigned char *buf, size_t sz, Q931 *q931) sz -= len; /* Message Type */ - if (sz < 1) + if (sz < 2) return H323_ERROR_BOUND; q931->MessageType = *p++; + sz--; PRINT("MessageType = %02X\n", q931->MessageType); if (*p & 0x80) { p++; diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 9511af04d..5c0db5c64 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1273,19 +1273,6 @@ static struct nf_conntrack_expect *find_expect(struct nf_conn *ct, } /****************************************************************************/ -static int set_expect_timeout(struct nf_conntrack_expect *exp, - unsigned int timeout) -{ - if (!exp || !del_timer(&exp->timeout)) - return 0; - - exp->timeout.expires = jiffies + timeout * HZ; - add_timer(&exp->timeout); - - return 1; -} - -/****************************************************************************/ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int protoff, unsigned char **data, @@ -1486,7 +1473,8 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, "timeout to %u seconds for", info->timeout); nf_ct_dump_tuple(&exp->tuple); - set_expect_timeout(exp, info->timeout); + mod_timer_pending(&exp->timeout, + jiffies + info->timeout * HZ); } spin_unlock_bh(&nf_conntrack_expect_lock); } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 196cb3964..b989b81ac 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -389,11 +389,40 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, struct net *net) { struct nf_conntrack_tuple_hash *h; + const struct hlist_nulls_node *nn; + int cpu; + + /* Get rid of expecteds, set helpers to NULL. */ + for_each_possible_cpu(cpu) { + struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + + spin_lock_bh(&pcpu->lock); + hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode) + unhelp(h, me); + spin_unlock_bh(&pcpu->lock); + } +} + +void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) +{ + struct nf_conntrack_tuple_hash *h; struct nf_conntrack_expect *exp; const struct hlist_node *next; const struct hlist_nulls_node *nn; + unsigned int last_hsize; + spinlock_t *lock; + struct net *net; unsigned int i; - int cpu; + + mutex_lock(&nf_ct_helper_mutex); + hlist_del_rcu(&me->hnode); + nf_ct_helper_count--; + mutex_unlock(&nf_ct_helper_mutex); + + /* Make sure every nothing is still using the helper unless its a + * connection in the hash. + */ + synchronize_rcu(); /* Get rid of expectations */ spin_lock_bh(&nf_conntrack_expect_lock); @@ -413,47 +442,85 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, } spin_unlock_bh(&nf_conntrack_expect_lock); - /* Get rid of expecteds, set helpers to NULL. */ - for_each_possible_cpu(cpu) { - struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + rtnl_lock(); + for_each_net(net) + __nf_conntrack_helper_unregister(me, net); + rtnl_unlock(); - spin_lock_bh(&pcpu->lock); - hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode) - unhelp(h, me); - spin_unlock_bh(&pcpu->lock); - } local_bh_disable(); - for (i = 0; i < nf_conntrack_htable_size; i++) { - nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); - if (i < nf_conntrack_htable_size) { - hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) - unhelp(h, me); +restart: + last_hsize = nf_conntrack_htable_size; + for (i = 0; i < last_hsize; i++) { + lock = &nf_conntrack_locks[i % CONNTRACK_LOCKS]; + nf_conntrack_lock(lock); + if (last_hsize != nf_conntrack_htable_size) { + spin_unlock(lock); + goto restart; } - spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) + unhelp(h, me); + spin_unlock(lock); } local_bh_enable(); } +EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); -void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) +void nf_ct_helper_init(struct nf_conntrack_helper *helper, + u16 l3num, u16 protonum, const char *name, + u16 default_port, u16 spec_port, u32 id, + const struct nf_conntrack_expect_policy *exp_pol, + u32 expect_class_max, u32 data_len, + int (*help)(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo), + int (*from_nlattr)(struct nlattr *attr, + struct nf_conn *ct), + struct module *module) { - struct net *net; + helper->tuple.src.l3num = l3num; + helper->tuple.dst.protonum = protonum; + helper->tuple.src.u.all = htons(spec_port); + helper->expect_policy = exp_pol; + helper->expect_class_max = expect_class_max; + helper->data_len = data_len; + helper->help = help; + helper->from_nlattr = from_nlattr; + helper->me = module; + + if (spec_port == default_port) + snprintf(helper->name, sizeof(helper->name), "%s", name); + else + snprintf(helper->name, sizeof(helper->name), "%s-%u", name, id); +} +EXPORT_SYMBOL_GPL(nf_ct_helper_init); - mutex_lock(&nf_ct_helper_mutex); - hlist_del_rcu(&me->hnode); - nf_ct_helper_count--; - mutex_unlock(&nf_ct_helper_mutex); +int nf_conntrack_helpers_register(struct nf_conntrack_helper *helper, + unsigned int n) +{ + unsigned int i; + int err = 0; - /* Make sure every nothing is still using the helper unless its a - * connection in the hash. - */ - synchronize_rcu(); + for (i = 0; i < n; i++) { + err = nf_conntrack_helper_register(&helper[i]); + if (err < 0) + goto err; + } - rtnl_lock(); - for_each_net(net) - __nf_conntrack_helper_unregister(me, net); - rtnl_unlock(); + return err; +err: + if (i > 0) + nf_conntrack_helpers_unregister(helper, i); + return err; } -EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); +EXPORT_SYMBOL_GPL(nf_conntrack_helpers_register); + +void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *helper, + unsigned int n) +{ + while (n-- > 0) + nf_conntrack_helper_unregister(&helper[n]); +} +EXPORT_SYMBOL_GPL(nf_conntrack_helpers_unregister); static struct nf_ct_ext_type helper_extend __read_mostly = { .len = sizeof(struct nf_conn_help), diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index f97ac61d2..1972a149f 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -255,27 +255,18 @@ static int __init nf_conntrack_irc_init(void) ports[ports_c++] = IRC_PORT; for (i = 0; i < ports_c; i++) { - irc[i].tuple.src.l3num = AF_INET; - irc[i].tuple.src.u.tcp.port = htons(ports[i]); - irc[i].tuple.dst.protonum = IPPROTO_TCP; - irc[i].expect_policy = &irc_exp_policy; - irc[i].me = THIS_MODULE; - irc[i].help = help; - - if (ports[i] == IRC_PORT) - sprintf(irc[i].name, "irc"); - else - sprintf(irc[i].name, "irc-%u", i); - - ret = nf_conntrack_helper_register(&irc[i]); - if (ret) { - pr_err("failed to register helper for pf: %u port: %u\n", - irc[i].tuple.src.l3num, ports[i]); - ports_c = i; - nf_conntrack_irc_fini(); - return ret; - } + nf_ct_helper_init(&irc[i], AF_INET, IPPROTO_TCP, "irc", + IRC_PORT, ports[i], i, &irc_exp_policy, + 0, 0, help, NULL, THIS_MODULE); + } + + ret = nf_conntrack_helpers_register(&irc[0], ports_c); + if (ret) { + pr_err("failed to register helpers\n"); + kfree(irc_buffer); + return ret; } + return 0; } @@ -283,10 +274,7 @@ static int __init nf_conntrack_irc_init(void) * it is needed by the init function */ static void nf_conntrack_irc_fini(void) { - int i; - - for (i = 0; i < ports_c; i++) - nf_conntrack_helper_unregister(&irc[i]); + nf_conntrack_helpers_unregister(irc, ports_c); kfree(irc_buffer); } diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c index 252e6a7cd..bcab8bde7 100644 --- a/net/netfilter/nf_conntrack_labels.c +++ b/net/netfilter/nf_conntrack_labels.c @@ -16,23 +16,6 @@ static spinlock_t nf_connlabels_lock; -int nf_connlabel_set(struct nf_conn *ct, u16 bit) -{ - struct nf_conn_labels *labels = nf_ct_labels_find(ct); - - if (!labels || BIT_WORD(bit) >= labels->words) - return -ENOSPC; - - if (test_bit(bit, labels->bits)) - return 0; - - if (!test_and_set_bit(bit, labels->bits)) - nf_conntrack_event_cache(IPCT_LABEL, ct); - - return 0; -} -EXPORT_SYMBOL_GPL(nf_connlabel_set); - static int replace_u32(u32 *address, u32 mask, u32 new) { u32 old, tmp; @@ -60,7 +43,7 @@ int nf_connlabels_replace(struct nf_conn *ct, if (!labels) return -ENOSPC; - size = labels->words * sizeof(long); + size = sizeof(labels->bits); if (size < (words32 * sizeof(u32))) words32 = size / sizeof(u32); @@ -80,16 +63,11 @@ EXPORT_SYMBOL_GPL(nf_connlabels_replace); int nf_connlabels_get(struct net *net, unsigned int bits) { - size_t words; - - words = BIT_WORD(bits) + 1; - if (words > NF_CT_LABELS_MAX_SIZE / sizeof(long)) + if (BIT_WORD(bits) >= NF_CT_LABELS_MAX_SIZE / sizeof(long)) return -ERANGE; spin_lock(&nf_connlabels_lock); net->ct.labels_used++; - if (words > net->ct.label_words) - net->ct.label_words = words; spin_unlock(&nf_connlabels_lock); return 0; @@ -100,8 +78,6 @@ void nf_connlabels_put(struct net *net) { spin_lock(&nf_connlabels_lock); net->ct.labels_used--; - if (net->ct.labels_used == 0) - net->ct.label_words = 0; spin_unlock(&nf_connlabels_lock); } EXPORT_SYMBOL_GPL(nf_connlabels_put); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index a18d1ceab..fdfc71f41 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -346,25 +346,25 @@ static inline int ctnetlink_label_size(const struct nf_conn *ct) if (!labels) return 0; - return nla_total_size(labels->words * sizeof(long)); + return nla_total_size(sizeof(labels->bits)); } static int ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); - unsigned int len, i; + unsigned int i; if (!labels) return 0; - len = labels->words * sizeof(long); i = 0; do { if (labels->bits[i] != 0) - return nla_put(skb, CTA_LABELS, len, labels->bits); + return nla_put(skb, CTA_LABELS, sizeof(labels->bits), + labels->bits); i++; - } while (i < labels->words); + } while (i < ARRAY_SIZE(labels->bits)); return 0; } @@ -1894,6 +1894,8 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) return -EINVAL; + if (otuple.dst.protonum != rtuple.dst.protonum) + return -EINVAL; ct = ctnetlink_create_conntrack(net, &zone, cda, &otuple, &rtuple, u3); @@ -2362,12 +2364,8 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, return PTR_ERR(exp); err = nf_ct_expect_related_report(exp, portid, report); - if (err < 0) { - nf_ct_expect_put(exp); - return err; - } - - return 0; + nf_ct_expect_put(exp); + return err; } static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index 3fcbaab83..9dcb9ee9b 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -166,7 +166,7 @@ out: return ret; } -static struct nf_conntrack_helper sane[MAX_PORTS][2] __read_mostly; +static struct nf_conntrack_helper sane[MAX_PORTS * 2] __read_mostly; static const struct nf_conntrack_expect_policy sane_exp_policy = { .max_expected = 1, @@ -176,22 +176,13 @@ static const struct nf_conntrack_expect_policy sane_exp_policy = { /* don't make this __exit, since it's called from __init ! */ static void nf_conntrack_sane_fini(void) { - int i, j; - - for (i = 0; i < ports_c; i++) { - for (j = 0; j < 2; j++) { - pr_debug("unregistering helper for pf: %d port: %d\n", - sane[i][j].tuple.src.l3num, ports[i]); - nf_conntrack_helper_unregister(&sane[i][j]); - } - } - + nf_conntrack_helpers_unregister(sane, ports_c * 2); kfree(sane_buffer); } static int __init nf_conntrack_sane_init(void) { - int i, j = -1, ret = 0; + int i, ret = 0; sane_buffer = kmalloc(65536, GFP_KERNEL); if (!sane_buffer) @@ -203,31 +194,23 @@ static int __init nf_conntrack_sane_init(void) /* FIXME should be configurable whether IPv4 and IPv6 connections are tracked or not - YK */ for (i = 0; i < ports_c; i++) { - sane[i][0].tuple.src.l3num = PF_INET; - sane[i][1].tuple.src.l3num = PF_INET6; - for (j = 0; j < 2; j++) { - sane[i][j].data_len = sizeof(struct nf_ct_sane_master); - sane[i][j].tuple.src.u.tcp.port = htons(ports[i]); - sane[i][j].tuple.dst.protonum = IPPROTO_TCP; - sane[i][j].expect_policy = &sane_exp_policy; - sane[i][j].me = THIS_MODULE; - sane[i][j].help = help; - if (ports[i] == SANE_PORT) - sprintf(sane[i][j].name, "sane"); - else - sprintf(sane[i][j].name, "sane-%d", ports[i]); - - pr_debug("registering helper for pf: %d port: %d\n", - sane[i][j].tuple.src.l3num, ports[i]); - ret = nf_conntrack_helper_register(&sane[i][j]); - if (ret) { - pr_err("failed to register helper for pf: %d port: %d\n", - sane[i][j].tuple.src.l3num, ports[i]); - ports_c = i; - nf_conntrack_sane_fini(); - return ret; - } - } + nf_ct_helper_init(&sane[2 * i], AF_INET, IPPROTO_TCP, "sane", + SANE_PORT, ports[i], ports[i], + &sane_exp_policy, 0, + sizeof(struct nf_ct_sane_master), help, NULL, + THIS_MODULE); + nf_ct_helper_init(&sane[2 * i + 1], AF_INET6, IPPROTO_TCP, "sane", + SANE_PORT, ports[i], ports[i], + &sane_exp_policy, 0, + sizeof(struct nf_ct_sane_master), help, NULL, + THIS_MODULE); + } + + ret = nf_conntrack_helpers_register(sane, ports_c * 2); + if (ret < 0) { + pr_err("failed to register helpers\n"); + kfree(sane_buffer); + return ret; } return 0; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index f72ba5587..7d77217de 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1383,7 +1383,7 @@ static int process_sip_response(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) { + if (!cseq && *(*dptr + matchoff) != '0') { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } @@ -1446,7 +1446,7 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) { + if (!cseq && *(*dptr + matchoff) != '0') { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } @@ -1589,7 +1589,7 @@ static int sip_help_udp(struct sk_buff *skb, unsigned int protoff, return process_sip_msg(skb, ct, protoff, dataoff, &dptr, &datalen); } -static struct nf_conntrack_helper sip[MAX_PORTS][4] __read_mostly; +static struct nf_conntrack_helper sip[MAX_PORTS * 4] __read_mostly; static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1] = { [SIP_EXPECT_SIGNALLING] = { @@ -1616,20 +1616,12 @@ static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1 static void nf_conntrack_sip_fini(void) { - int i, j; - - for (i = 0; i < ports_c; i++) { - for (j = 0; j < ARRAY_SIZE(sip[i]); j++) { - if (sip[i][j].me == NULL) - continue; - nf_conntrack_helper_unregister(&sip[i][j]); - } - } + nf_conntrack_helpers_unregister(sip, ports_c * 4); } static int __init nf_conntrack_sip_init(void) { - int i, j, ret; + int i, ret; if (ports_c == 0) ports[ports_c++] = SIP_PORT; @@ -1637,43 +1629,32 @@ static int __init nf_conntrack_sip_init(void) for (i = 0; i < ports_c; i++) { memset(&sip[i], 0, sizeof(sip[i])); - sip[i][0].tuple.src.l3num = AF_INET; - sip[i][0].tuple.dst.protonum = IPPROTO_UDP; - sip[i][0].help = sip_help_udp; - sip[i][1].tuple.src.l3num = AF_INET; - sip[i][1].tuple.dst.protonum = IPPROTO_TCP; - sip[i][1].help = sip_help_tcp; - - sip[i][2].tuple.src.l3num = AF_INET6; - sip[i][2].tuple.dst.protonum = IPPROTO_UDP; - sip[i][2].help = sip_help_udp; - sip[i][3].tuple.src.l3num = AF_INET6; - sip[i][3].tuple.dst.protonum = IPPROTO_TCP; - sip[i][3].help = sip_help_tcp; - - for (j = 0; j < ARRAY_SIZE(sip[i]); j++) { - sip[i][j].data_len = sizeof(struct nf_ct_sip_master); - sip[i][j].tuple.src.u.udp.port = htons(ports[i]); - sip[i][j].expect_policy = sip_exp_policy; - sip[i][j].expect_class_max = SIP_EXPECT_MAX; - sip[i][j].me = THIS_MODULE; - - if (ports[i] == SIP_PORT) - sprintf(sip[i][j].name, "sip"); - else - sprintf(sip[i][j].name, "sip-%u", i); - - pr_debug("port #%u: %u\n", i, ports[i]); + nf_ct_helper_init(&sip[4 * i], AF_INET, IPPROTO_UDP, "sip", + SIP_PORT, ports[i], i, sip_exp_policy, + SIP_EXPECT_MAX, + sizeof(struct nf_ct_sip_master), sip_help_udp, + NULL, THIS_MODULE); + nf_ct_helper_init(&sip[4 * i + 1], AF_INET, IPPROTO_TCP, "sip", + SIP_PORT, ports[i], i, sip_exp_policy, + SIP_EXPECT_MAX, + sizeof(struct nf_ct_sip_master), sip_help_tcp, + NULL, THIS_MODULE); + nf_ct_helper_init(&sip[4 * i + 2], AF_INET6, IPPROTO_UDP, "sip", + SIP_PORT, ports[i], i, sip_exp_policy, + SIP_EXPECT_MAX, + sizeof(struct nf_ct_sip_master), sip_help_udp, + NULL, THIS_MODULE); + nf_ct_helper_init(&sip[4 * i + 3], AF_INET6, IPPROTO_TCP, "sip", + SIP_PORT, ports[i], i, sip_exp_policy, + SIP_EXPECT_MAX, + sizeof(struct nf_ct_sip_master), sip_help_tcp, + NULL, THIS_MODULE); + } - ret = nf_conntrack_helper_register(&sip[i][j]); - if (ret) { - pr_err("failed to register helper for pf: %u port: %u\n", - sip[i][j].tuple.src.l3num, ports[i]); - ports_c = i; - nf_conntrack_sip_fini(); - return ret; - } - } + ret = nf_conntrack_helpers_register(sip, ports_c * 4); + if (ret < 0) { + pr_err("failed to register helpers\n"); + return ret; } return 0; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index c026c472e..9f267c3ff 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -48,6 +48,8 @@ EXPORT_SYMBOL_GPL(print_tuple); struct ct_iter_state { struct seq_net_private p; + struct hlist_nulls_head *hash; + unsigned int htable_size; unsigned int bucket; u_int64_t time_now; }; @@ -58,9 +60,10 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) struct hlist_nulls_node *n; for (st->bucket = 0; - st->bucket < nf_conntrack_htable_size; + st->bucket < st->htable_size; st->bucket++) { - n = rcu_dereference(hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket])); + n = rcu_dereference( + hlist_nulls_first_rcu(&st->hash[st->bucket])); if (!is_a_nulls(n)) return n; } @@ -75,12 +78,11 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, head = rcu_dereference(hlist_nulls_next_rcu(head)); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { - if (++st->bucket >= nf_conntrack_htable_size) + if (++st->bucket >= st->htable_size) return NULL; } head = rcu_dereference( - hlist_nulls_first_rcu( - &nf_conntrack_hash[st->bucket])); + hlist_nulls_first_rcu(&st->hash[st->bucket])); } return head; } @@ -102,6 +104,8 @@ static void *ct_seq_start(struct seq_file *seq, loff_t *pos) st->time_now = ktime_get_real_ns(); rcu_read_lock(); + + nf_conntrack_get_ht(&st->hash, &st->htable_size); return ct_get_idx(seq, *pos); } @@ -201,6 +205,7 @@ static int ct_seq_show(struct seq_file *s, void *v) struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; + struct net *net = seq_file_net(s); int ret = 0; NF_CT_ASSERT(ct); @@ -211,6 +216,9 @@ static int ct_seq_show(struct seq_file *s, void *v) if (NF_CT_DIRECTION(hash)) goto release; + if (!net_eq(nf_ct_net(ct), net)) + goto release; + l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); NF_CT_ASSERT(l3proto); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); @@ -434,8 +442,29 @@ static void nf_conntrack_standalone_fini_proc(struct net *net) #ifdef CONFIG_SYSCTL /* Log invalid packets of a given protocol */ -static int log_invalid_proto_min = 0; -static int log_invalid_proto_max = 255; +static int log_invalid_proto_min __read_mostly; +static int log_invalid_proto_max __read_mostly = 255; + +/* size the user *wants to set */ +static unsigned int nf_conntrack_htable_size_user __read_mostly; + +static int +nf_conntrack_hash_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (ret < 0 || !write) + return ret; + + /* update ret, we might not be able to satisfy request */ + ret = nf_conntrack_hash_resize(nf_conntrack_htable_size_user); + + /* update it to the actual value used by conntrack */ + nf_conntrack_htable_size_user = nf_conntrack_htable_size; + return ret; +} static struct ctl_table_header *nf_ct_netfilter_header; @@ -456,10 +485,10 @@ static struct ctl_table nf_ct_sysctl_table[] = { }, { .procname = "nf_conntrack_buckets", - .data = &nf_conntrack_htable_size, + .data = &nf_conntrack_htable_size_user, .maxlen = sizeof(unsigned int), - .mode = 0444, - .proc_handler = proc_dointvec, + .mode = 0644, + .proc_handler = nf_conntrack_hash_sysctl, }, { .procname = "nf_conntrack_checksum", @@ -515,6 +544,9 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) if (net->user_ns != &init_user_ns) table[0].procname = NULL; + if (!net_eq(&init_net, net)) + table[2].mode = 0444; + net->ct.sysctl_header = register_net_sysctl(net, "net/netfilter", table); if (!net->ct.sysctl_header) goto out_unregister_netfilter; @@ -604,6 +636,8 @@ static int __init nf_conntrack_standalone_init(void) ret = -ENOMEM; goto out_sysctl; } + + nf_conntrack_htable_size_user = nf_conntrack_htable_size; #endif ret = register_pernet_subsys(&nf_conntrack_net_ops); diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c index 2e65b5430..b1227dc6f 100644 --- a/net/netfilter/nf_conntrack_tftp.c +++ b/net/netfilter/nf_conntrack_tftp.c @@ -97,7 +97,7 @@ static int tftp_help(struct sk_buff *skb, return ret; } -static struct nf_conntrack_helper tftp[MAX_PORTS][2] __read_mostly; +static struct nf_conntrack_helper tftp[MAX_PORTS * 2] __read_mostly; static const struct nf_conntrack_expect_policy tftp_exp_policy = { .max_expected = 1, @@ -106,47 +106,29 @@ static const struct nf_conntrack_expect_policy tftp_exp_policy = { static void nf_conntrack_tftp_fini(void) { - int i, j; - - for (i = 0; i < ports_c; i++) { - for (j = 0; j < 2; j++) - nf_conntrack_helper_unregister(&tftp[i][j]); - } + nf_conntrack_helpers_unregister(tftp, ports_c * 2); } static int __init nf_conntrack_tftp_init(void) { - int i, j, ret; + int i, ret; if (ports_c == 0) ports[ports_c++] = TFTP_PORT; for (i = 0; i < ports_c; i++) { - memset(&tftp[i], 0, sizeof(tftp[i])); - - tftp[i][0].tuple.src.l3num = AF_INET; - tftp[i][1].tuple.src.l3num = AF_INET6; - for (j = 0; j < 2; j++) { - tftp[i][j].tuple.dst.protonum = IPPROTO_UDP; - tftp[i][j].tuple.src.u.udp.port = htons(ports[i]); - tftp[i][j].expect_policy = &tftp_exp_policy; - tftp[i][j].me = THIS_MODULE; - tftp[i][j].help = tftp_help; - - if (ports[i] == TFTP_PORT) - sprintf(tftp[i][j].name, "tftp"); - else - sprintf(tftp[i][j].name, "tftp-%u", i); - - ret = nf_conntrack_helper_register(&tftp[i][j]); - if (ret) { - pr_err("failed to register helper for pf: %u port: %u\n", - tftp[i][j].tuple.src.l3num, ports[i]); - ports_c = i; - nf_conntrack_tftp_fini(); - return ret; - } - } + nf_ct_helper_init(&tftp[2 * i], AF_INET, IPPROTO_UDP, "tftp", + TFTP_PORT, ports[i], i, &tftp_exp_policy, + 0, 0, tftp_help, NULL, THIS_MODULE); + nf_ct_helper_init(&tftp[2 * i + 1], AF_INET6, IPPROTO_UDP, "tftp", + TFTP_PORT, ports[i], i, &tftp_exp_policy, + 0, 0, tftp_help, NULL, THIS_MODULE); + } + + ret = nf_conntrack_helpers_register(tftp, ports_c * 2); + if (ret < 0) { + pr_err("failed to register helpers\n"); + return ret; } return 0; } diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index a5d41dfa9..aa5847a16 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -159,6 +159,20 @@ int nf_logger_find_get(int pf, enum nf_log_type type) struct nf_logger *logger; int ret = -ENOENT; + if (pf == NFPROTO_INET) { + ret = nf_logger_find_get(NFPROTO_IPV4, type); + if (ret < 0) + return ret; + + ret = nf_logger_find_get(NFPROTO_IPV6, type); + if (ret < 0) { + nf_logger_put(NFPROTO_IPV4, type); + return ret; + } + + return 0; + } + if (rcu_access_pointer(loggers[pf][type]) == NULL) request_module("nf-logger-%u-%u", pf, type); @@ -167,7 +181,7 @@ int nf_logger_find_get(int pf, enum nf_log_type type) if (logger == NULL) goto out; - if (logger && try_module_get(logger->me)) + if (try_module_get(logger->me)) ret = 0; out: rcu_read_unlock(); @@ -179,6 +193,12 @@ void nf_logger_put(int pf, enum nf_log_type type) { struct nf_logger *logger; + if (pf == NFPROTO_INET) { + nf_logger_put(NFPROTO_IPV4, type); + nf_logger_put(NFPROTO_IPV6, type); + return; + } + BUG_ON(loggers[pf][type] == NULL); rcu_read_lock(); @@ -398,16 +418,17 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write, { const struct nf_logger *logger; char buf[NFLOGGER_NAME_LEN]; - size_t size = *lenp; int r = 0; int tindex = (unsigned long)table->extra1; struct net *net = current->nsproxy->net_ns; if (write) { - if (size > sizeof(buf)) - size = sizeof(buf); - if (copy_from_user(buf, buffer, size)) - return -EFAULT; + struct ctl_table tmp = *table; + + tmp.data = buf; + r = proc_dostring(&tmp, write, buffer, lenp, ppos); + if (r) + return r; if (!strcmp(buf, "NONE")) { nf_log_unbind_pf(net, tindex); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 6877a396f..ecee105bb 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -30,17 +30,19 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <linux/netfilter/nf_nat.h> -static DEFINE_SPINLOCK(nf_nat_lock); - static DEFINE_MUTEX(nf_nat_proto_mutex); static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO] __read_mostly; static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO] __read_mostly; -static struct hlist_head *nf_nat_bysource __read_mostly; -static unsigned int nf_nat_htable_size __read_mostly; -static unsigned int nf_nat_hash_rnd __read_mostly; +struct nf_nat_conn_key { + const struct net *net; + const struct nf_conntrack_tuple *tuple; + const struct nf_conntrack_zone *zone; +}; + +static struct rhashtable nf_nat_bysource_table; inline const struct nf_nat_l3proto * __nf_nat_l3proto_find(u8 family) @@ -119,19 +121,17 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) EXPORT_SYMBOL(nf_xfrm_me_harder); #endif /* CONFIG_XFRM */ -/* We keep an extra hash for each conntrack, for fast searching. */ -static inline unsigned int -hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) +static u32 nf_nat_bysource_hash(const void *data, u32 len, u32 seed) { - unsigned int hash; - - get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd)); + const struct nf_conntrack_tuple *t; + const struct nf_conn *ct = data; + t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* Original src, to ensure we map it consistently if poss. */ - hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32), - tuple->dst.protonum ^ nf_nat_hash_rnd ^ net_hash_mix(n)); - return reciprocal_scale(hash, nf_nat_htable_size); + seed ^= net_hash_mix(nf_ct_net(ct)); + return jhash2((const u32 *)&t->src, sizeof(t->src) / sizeof(u32), + t->dst.protonum ^ seed); } /* Is this tuple already taken? (not by us) */ @@ -187,6 +187,26 @@ same_src(const struct nf_conn *ct, t->src.u.all == tuple->src.u.all); } +static int nf_nat_bysource_cmp(struct rhashtable_compare_arg *arg, + const void *obj) +{ + const struct nf_nat_conn_key *key = arg->key; + const struct nf_conn *ct = obj; + + return same_src(ct, key->tuple) && + net_eq(nf_ct_net(ct), key->net) && + nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL); +} + +static struct rhashtable_params nf_nat_bysource_params = { + .head_offset = offsetof(struct nf_conn, nat_bysource), + .obj_hashfn = nf_nat_bysource_hash, + .obj_cmpfn = nf_nat_bysource_cmp, + .nelem_hint = 256, + .min_size = 1024, + .nulls_base = (1U << RHT_BASE_SHIFT), +}; + /* Only called for SRC manip */ static int find_appropriate_src(struct net *net, @@ -197,25 +217,23 @@ find_appropriate_src(struct net *net, struct nf_conntrack_tuple *result, const struct nf_nat_range *range) { - unsigned int h = hash_by_src(net, tuple); - const struct nf_conn_nat *nat; const struct nf_conn *ct; + struct nf_nat_conn_key key = { + .net = net, + .tuple = tuple, + .zone = zone + }; - hlist_for_each_entry_rcu(nat, &nf_nat_bysource[h], bysource) { - ct = nat->ct; - if (same_src(ct, tuple) && - net_eq(net, nf_ct_net(ct)) && - nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) { - /* Copy source part from reply tuple. */ - nf_ct_invert_tuplepr(result, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - result->dst = tuple->dst; - - if (in_range(l3proto, l4proto, result, range)) - return 1; - } - } - return 0; + ct = rhashtable_lookup_fast(&nf_nat_bysource_table, &key, + nf_nat_bysource_params); + if (!ct) + return 0; + + nf_ct_invert_tuplepr(result, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + result->dst = tuple->dst; + + return in_range(l3proto, l4proto, result, range); } /* For [FUTURE] fragmentation handling, we want the least-used @@ -387,7 +405,6 @@ nf_nat_setup_info(struct nf_conn *ct, const struct nf_nat_range *range, enum nf_nat_manip_type maniptype) { - struct net *net = nf_ct_net(ct); struct nf_conntrack_tuple curr_tuple, new_tuple; struct nf_conn_nat *nat; @@ -424,21 +441,18 @@ 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) { - unsigned int srchash; - - srchash = hash_by_src(net, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - spin_lock_bh(&nf_nat_lock); - /* nf_conntrack_alter_reply might re-allocate extension aera */ - nat = nfct_nat(ct); - nat->ct = ct; - hlist_add_head_rcu(&nat->bysource, - &nf_nat_bysource[srchash]); - spin_unlock_bh(&nf_nat_lock); + int err; + + err = rhashtable_insert_fast(&nf_nat_bysource_table, + &ct->nat_bysource, + nf_nat_bysource_params); + if (err) + return NF_DROP; } /* It's done. */ @@ -543,7 +557,7 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) if (nf_nat_proto_remove(ct, data)) return 1; - if (!nat || !nat->ct) + if (!nat) return 0; /* This netns is being destroyed, and conntrack has nat null binding. @@ -555,11 +569,10 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) if (!del_timer(&ct->timeout)) return 1; - spin_lock_bh(&nf_nat_lock); - hlist_del_rcu(&nat->bysource); ct->status &= ~IPS_NAT_DONE_MASK; - nat->ct = NULL; - spin_unlock_bh(&nf_nat_lock); + + rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); add_timer(&ct->timeout); @@ -688,35 +701,17 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) { struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT); - if (nat == NULL || nat->ct == NULL) - return; - - NF_CT_ASSERT(nat->ct->status & IPS_SRC_NAT_DONE); - - spin_lock_bh(&nf_nat_lock); - hlist_del_rcu(&nat->bysource); - spin_unlock_bh(&nf_nat_lock); -} - -static void nf_nat_move_storage(void *new, void *old) -{ - struct nf_conn_nat *new_nat = new; - struct nf_conn_nat *old_nat = old; - struct nf_conn *ct = old_nat->ct; - - if (!ct || !(ct->status & IPS_SRC_NAT_DONE)) + if (!nat) return; - spin_lock_bh(&nf_nat_lock); - hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); - spin_unlock_bh(&nf_nat_lock); + rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); } static struct nf_ct_ext_type nat_extend __read_mostly = { .len = sizeof(struct nf_conn_nat), .align = __alignof__(struct nf_conn_nat), .destroy = nf_nat_cleanup_conntrack, - .move = nf_nat_move_storage, .id = NF_CT_EXT_NAT, .flags = NF_CT_EXT_F_PREALLOC, }; @@ -813,7 +808,7 @@ 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 @@ -845,16 +840,13 @@ static int __init nf_nat_init(void) { int ret; - /* Leave them the same for the moment. */ - nf_nat_htable_size = nf_conntrack_htable_size; - - nf_nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, 0); - if (!nf_nat_bysource) - return -ENOMEM; + ret = rhashtable_init(&nf_nat_bysource_table, &nf_nat_bysource_params); + if (ret) + return ret; ret = nf_ct_extend_register(&nat_extend); if (ret < 0) { - nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); + rhashtable_destroy(&nf_nat_bysource_table); printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); return ret; } @@ -878,7 +870,7 @@ static int __init nf_nat_init(void) return 0; cleanup_extend: - nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); + rhashtable_destroy(&nf_nat_bysource_table); nf_ct_extend_unregister(&nat_extend); return ret; } @@ -896,8 +888,8 @@ static void __exit nf_nat_cleanup(void) #endif for (i = 0; i < NFPROTO_NUMPROTO; i++) kfree(nf_nat_l4protos[i]); - synchronize_net(); - nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); + + rhashtable_destroy(&nf_nat_bysource_table); } MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index cf7c74599..7e1c876c7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -131,29 +131,8 @@ static void nft_trans_destroy(struct nft_trans *trans) kfree(trans); } -static int nft_register_basechain(struct nft_base_chain *basechain, - unsigned int hook_nops) -{ - struct net *net = read_pnet(&basechain->pnet); - - if (basechain->flags & NFT_BASECHAIN_DISABLED) - return 0; - - return nf_register_net_hooks(net, basechain->ops, hook_nops); -} - -static void nft_unregister_basechain(struct nft_base_chain *basechain, - unsigned int hook_nops) -{ - struct net *net = read_pnet(&basechain->pnet); - - if (basechain->flags & NFT_BASECHAIN_DISABLED) - return; - - nf_unregister_net_hooks(net, basechain->ops, hook_nops); -} - -static int nf_tables_register_hooks(const struct nft_table *table, +static int nf_tables_register_hooks(struct net *net, + const struct nft_table *table, struct nft_chain *chain, unsigned int hook_nops) { @@ -161,10 +140,12 @@ static int nf_tables_register_hooks(const struct nft_table *table, !(chain->flags & NFT_BASE_CHAIN)) return 0; - return nft_register_basechain(nft_base_chain(chain), hook_nops); + return nf_register_net_hooks(net, nft_base_chain(chain)->ops, + hook_nops); } -static void nf_tables_unregister_hooks(const struct nft_table *table, +static void nf_tables_unregister_hooks(struct net *net, + const struct nft_table *table, struct nft_chain *chain, unsigned int hook_nops) { @@ -172,12 +153,9 @@ static void nf_tables_unregister_hooks(const struct nft_table *table, !(chain->flags & NFT_BASE_CHAIN)) return; - nft_unregister_basechain(nft_base_chain(chain), hook_nops); + nf_unregister_net_hooks(net, nft_base_chain(chain)->ops, hook_nops); } -/* Internal table flags */ -#define NFT_TABLE_INACTIVE (1 << 15) - static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) { struct nft_trans *trans; @@ -187,7 +165,7 @@ static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) return -ENOMEM; if (msg_type == NFT_MSG_NEWTABLE) - ctx->table->flags |= NFT_TABLE_INACTIVE; + nft_activate_next(ctx->net, ctx->table); list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; @@ -201,7 +179,7 @@ static int nft_deltable(struct nft_ctx *ctx) if (err < 0) return err; - list_del_rcu(&ctx->table->list); + nft_deactivate_next(ctx->net, ctx->table); return err; } @@ -214,7 +192,7 @@ static int nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) return -ENOMEM; if (msg_type == NFT_MSG_NEWCHAIN) - ctx->chain->flags |= NFT_CHAIN_INACTIVE; + nft_activate_next(ctx->net, ctx->chain); list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; @@ -229,47 +207,17 @@ static int nft_delchain(struct nft_ctx *ctx) return err; ctx->table->use--; - list_del_rcu(&ctx->chain->list); + nft_deactivate_next(ctx->net, ctx->chain); return err; } -static inline bool -nft_rule_is_active(struct net *net, const struct nft_rule *rule) -{ - return (rule->genmask & nft_genmask_cur(net)) == 0; -} - -static inline int -nft_rule_is_active_next(struct net *net, const struct nft_rule *rule) -{ - return (rule->genmask & nft_genmask_next(net)) == 0; -} - -static inline void -nft_rule_activate_next(struct net *net, struct nft_rule *rule) -{ - /* Now inactive, will be active in the future */ - rule->genmask = nft_genmask_cur(net); -} - -static inline void -nft_rule_deactivate_next(struct net *net, struct nft_rule *rule) -{ - rule->genmask = nft_genmask_next(net); -} - -static inline void nft_rule_clear(struct net *net, struct nft_rule *rule) -{ - rule->genmask &= ~nft_genmask_next(net); -} - static int nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule) { /* You cannot delete the same rule twice */ - if (nft_rule_is_active_next(ctx->net, rule)) { - nft_rule_deactivate_next(ctx->net, rule); + if (nft_is_active_next(ctx->net, rule)) { + nft_deactivate_next(ctx->net, rule); ctx->chain->use--; return 0; } @@ -322,9 +270,6 @@ static int nft_delrule_by_chain(struct nft_ctx *ctx) return 0; } -/* Internal set flag */ -#define NFT_SET_INACTIVE (1 << 15) - static int nft_trans_set_add(struct nft_ctx *ctx, int msg_type, struct nft_set *set) { @@ -337,7 +282,7 @@ static int nft_trans_set_add(struct nft_ctx *ctx, int msg_type, if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] != NULL) { nft_trans_set_id(trans) = ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID])); - set->flags |= NFT_SET_INACTIVE; + nft_activate_next(ctx->net, set); } nft_trans_set(trans) = set; list_add_tail(&trans->list, &ctx->net->nft.commit_list); @@ -353,7 +298,7 @@ static int nft_delset(struct nft_ctx *ctx, struct nft_set *set) if (err < 0) return err; - list_del_rcu(&set->list); + nft_deactivate_next(ctx->net, set); ctx->table->use--; return err; @@ -364,26 +309,29 @@ static int nft_delset(struct nft_ctx *ctx, struct nft_set *set) */ static struct nft_table *nft_table_lookup(const struct nft_af_info *afi, - const struct nlattr *nla) + const struct nlattr *nla, + u8 genmask) { struct nft_table *table; list_for_each_entry(table, &afi->tables, list) { - if (!nla_strcmp(nla, table->name)) + if (!nla_strcmp(nla, table->name) && + nft_active_genmask(table, genmask)) return table; } return NULL; } static struct nft_table *nf_tables_table_lookup(const struct nft_af_info *afi, - const struct nlattr *nla) + const struct nlattr *nla, + u8 genmask) { struct nft_table *table; if (nla == NULL) return ERR_PTR(-EINVAL); - table = nft_table_lookup(afi, nla); + table = nft_table_lookup(afi, nla, genmask); if (table != NULL) return table; @@ -524,6 +472,8 @@ static int nf_tables_dump_tables(struct sk_buff *skb, if (idx > s_idx) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); + if (!nft_is_active(net, table)) + continue; if (nf_tables_fill_table_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, @@ -548,6 +498,7 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_cur(net); const struct nft_af_info *afi; const struct nft_table *table; struct sk_buff *skb2; @@ -565,11 +516,9 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk, if (IS_ERR(afi)) return PTR_ERR(afi); - table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME]); + table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], genmask); if (IS_ERR(table)) return PTR_ERR(table); - if (table->flags & NFT_TABLE_INACTIVE) - return -ENOENT; skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb2) @@ -588,17 +537,21 @@ err: return err; } -static int nf_tables_table_enable(const struct nft_af_info *afi, +static int nf_tables_table_enable(struct net *net, + const struct nft_af_info *afi, struct nft_table *table) { struct nft_chain *chain; int err, i = 0; list_for_each_entry(chain, &table->chains, list) { + if (!nft_is_active_next(net, chain)) + continue; if (!(chain->flags & NFT_BASE_CHAIN)) continue; - err = nft_register_basechain(nft_base_chain(chain), afi->nops); + err = nf_register_net_hooks(net, nft_base_chain(chain)->ops, + afi->nops); if (err < 0) goto err; @@ -607,26 +560,34 @@ static int nf_tables_table_enable(const struct nft_af_info *afi, return 0; err: list_for_each_entry(chain, &table->chains, list) { + if (!nft_is_active_next(net, chain)) + continue; if (!(chain->flags & NFT_BASE_CHAIN)) continue; if (i-- <= 0) break; - nft_unregister_basechain(nft_base_chain(chain), afi->nops); + nf_unregister_net_hooks(net, nft_base_chain(chain)->ops, + afi->nops); } return err; } -static void nf_tables_table_disable(const struct nft_af_info *afi, +static void nf_tables_table_disable(struct net *net, + const struct nft_af_info *afi, struct nft_table *table) { struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) { - if (chain->flags & NFT_BASE_CHAIN) - nft_unregister_basechain(nft_base_chain(chain), - afi->nops); + if (!nft_is_active_next(net, chain)) + continue; + if (!(chain->flags & NFT_BASE_CHAIN)) + continue; + + nf_unregister_net_hooks(net, nft_base_chain(chain)->ops, + afi->nops); } } @@ -656,7 +617,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) nft_trans_table_enable(trans) = false; } else if (!(flags & NFT_TABLE_F_DORMANT) && ctx->table->flags & NFT_TABLE_F_DORMANT) { - ret = nf_tables_table_enable(ctx->afi, ctx->table); + ret = nf_tables_table_enable(ctx->net, ctx->afi, ctx->table); if (ret >= 0) { ctx->table->flags &= ~NFT_TABLE_F_DORMANT; nft_trans_table_enable(trans) = true; @@ -678,6 +639,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_next(net); const struct nlattr *name; struct nft_af_info *afi; struct nft_table *table; @@ -691,7 +653,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, return PTR_ERR(afi); name = nla[NFTA_TABLE_NAME]; - table = nf_tables_table_lookup(afi, name); + table = nf_tables_table_lookup(afi, name, genmask); if (IS_ERR(table)) { if (PTR_ERR(table) != -ENOENT) return PTR_ERR(table); @@ -699,8 +661,6 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, } if (table != NULL) { - if (table->flags & NFT_TABLE_INACTIVE) - return -ENOENT; if (nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (nlh->nlmsg_flags & NLM_F_REPLACE) @@ -752,6 +712,9 @@ static int nft_flush_table(struct nft_ctx *ctx) struct nft_set *set, *ns; list_for_each_entry(chain, &ctx->table->chains, list) { + if (!nft_is_active_next(ctx->net, chain)) + continue; + ctx->chain = chain; err = nft_delrule_by_chain(ctx); @@ -760,6 +723,9 @@ static int nft_flush_table(struct nft_ctx *ctx) } list_for_each_entry_safe(set, ns, &ctx->table->sets, list) { + if (!nft_is_active_next(ctx->net, set)) + continue; + if (set->flags & NFT_SET_ANONYMOUS && !list_empty(&set->bindings)) continue; @@ -770,6 +736,9 @@ static int nft_flush_table(struct nft_ctx *ctx) } list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) { + if (!nft_is_active_next(ctx->net, chain)) + continue; + ctx->chain = chain; err = nft_delchain(ctx); @@ -795,6 +764,9 @@ static int nft_flush(struct nft_ctx *ctx, int family) ctx->afi = afi; list_for_each_entry_safe(table, nt, &afi->tables, list) { + if (!nft_is_active_next(ctx->net, table)) + continue; + if (nla[NFTA_TABLE_NAME] && nla_strcmp(nla[NFTA_TABLE_NAME], table->name) != 0) continue; @@ -815,6 +787,7 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_next(net); struct nft_af_info *afi; struct nft_table *table; int family = nfmsg->nfgen_family; @@ -828,7 +801,7 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk, if (IS_ERR(afi)) return PTR_ERR(afi); - table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME]); + table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], genmask); if (IS_ERR(table)) return PTR_ERR(table); @@ -875,12 +848,14 @@ EXPORT_SYMBOL_GPL(nft_unregister_chain_type); */ static struct nft_chain * -nf_tables_chain_lookup_byhandle(const struct nft_table *table, u64 handle) +nf_tables_chain_lookup_byhandle(const struct nft_table *table, u64 handle, + u8 genmask) { struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) { - if (chain->handle == handle) + if (chain->handle == handle && + nft_active_genmask(chain, genmask)) return chain; } @@ -888,7 +863,8 @@ nf_tables_chain_lookup_byhandle(const struct nft_table *table, u64 handle) } static struct nft_chain *nf_tables_chain_lookup(const struct nft_table *table, - const struct nlattr *nla) + const struct nlattr *nla, + u8 genmask) { struct nft_chain *chain; @@ -896,7 +872,8 @@ static struct nft_chain *nf_tables_chain_lookup(const struct nft_table *table, return ERR_PTR(-EINVAL); list_for_each_entry(chain, &table->chains, list) { - if (!nla_strcmp(nla, chain->name)) + if (!nla_strcmp(nla, chain->name) && + nft_active_genmask(chain, genmask)) return chain; } @@ -1079,6 +1056,8 @@ static int nf_tables_dump_chains(struct sk_buff *skb, if (idx > s_idx) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); + if (!nft_is_active(net, chain)) + continue; if (nf_tables_fill_chain_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, @@ -1104,6 +1083,7 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_cur(net); const struct nft_af_info *afi; const struct nft_table *table; const struct nft_chain *chain; @@ -1122,17 +1102,13 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, if (IS_ERR(afi)) return PTR_ERR(afi); - table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]); + table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], genmask); if (IS_ERR(table)) return PTR_ERR(table); - if (table->flags & NFT_TABLE_INACTIVE) - return -ENOENT; - chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]); + chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); if (IS_ERR(chain)) return PTR_ERR(chain); - if (chain->flags & NFT_CHAIN_INACTIVE) - return -ENOENT; skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb2) @@ -1231,6 +1207,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, 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; @@ -1247,7 +1224,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (IS_ERR(afi)) return PTR_ERR(afi); - table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]); + table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], genmask); if (IS_ERR(table)) return PTR_ERR(table); @@ -1256,11 +1233,11 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (nla[NFTA_CHAIN_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE])); - chain = nf_tables_chain_lookup_byhandle(table, handle); + chain = nf_tables_chain_lookup_byhandle(table, handle, genmask); if (IS_ERR(chain)) return PTR_ERR(chain); } else { - chain = nf_tables_chain_lookup(table, name); + chain = nf_tables_chain_lookup(table, name, genmask); if (IS_ERR(chain)) { if (PTR_ERR(chain) != -ENOENT) return PTR_ERR(chain); @@ -1291,16 +1268,20 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, struct nft_stats *stats = NULL; struct nft_trans *trans; - if (chain->flags & NFT_CHAIN_INACTIVE) - return -ENOENT; if (nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - if (nla[NFTA_CHAIN_HANDLE] && name && - !IS_ERR(nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]))) - return -EEXIST; + if (nla[NFTA_CHAIN_HANDLE] && name) { + struct nft_chain *chain2; + + chain2 = nf_tables_chain_lookup(table, + nla[NFTA_CHAIN_NAME], + genmask); + if (IS_ERR(chain2)) + return PTR_ERR(chain2); + } if (nla[NFTA_CHAIN_COUNTERS]) { if (!(chain->flags & NFT_BASE_CHAIN)) @@ -1424,7 +1405,6 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, rcu_assign_pointer(basechain->stats, stats); } - write_pnet(&basechain->pnet, net); basechain->type = type; chain = &basechain->chain; @@ -1455,7 +1435,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, chain->table = table; nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN); - err = nf_tables_register_hooks(table, chain, afi->nops); + err = nf_tables_register_hooks(net, table, chain, afi->nops); if (err < 0) goto err1; @@ -1468,7 +1448,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, list_add_tail_rcu(&chain->list, &table->chains); return 0; err2: - nf_tables_unregister_hooks(table, chain, afi->nops); + nf_tables_unregister_hooks(net, table, chain, afi->nops); err1: nf_tables_chain_destroy(chain); return err; @@ -1479,6 +1459,7 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_next(net); struct nft_af_info *afi; struct nft_table *table; struct nft_chain *chain; @@ -1489,11 +1470,11 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, if (IS_ERR(afi)) return PTR_ERR(afi); - table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]); + table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], genmask); if (IS_ERR(table)) return PTR_ERR(table); - chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]); + chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); if (IS_ERR(chain)) return PTR_ERR(chain); if (chain->use > 0) @@ -1878,10 +1859,16 @@ err: return err; } +struct nft_rule_dump_ctx { + char table[NFT_TABLE_MAXNAMELEN]; + char chain[NFT_CHAIN_MAXNAMELEN]; +}; + static int nf_tables_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + const struct nft_rule_dump_ctx *ctx = cb->data; const struct nft_af_info *afi; const struct nft_table *table; const struct nft_chain *chain; @@ -1898,9 +1885,17 @@ static int nf_tables_dump_rules(struct sk_buff *skb, continue; list_for_each_entry_rcu(table, &afi->tables, list) { + if (ctx && ctx->table[0] && + strcmp(ctx->table, table->name) != 0) + continue; + list_for_each_entry_rcu(chain, &table->chains, list) { + if (ctx && ctx->chain[0] && + strcmp(ctx->chain, chain->name) != 0) + continue; + list_for_each_entry_rcu(rule, &chain->rules, list) { - if (!nft_rule_is_active(net, rule)) + if (!nft_is_active(net, rule)) goto cont; if (idx < s_idx) goto cont; @@ -1928,11 +1923,18 @@ done: return skb->len; } +static int nf_tables_dump_rules_done(struct netlink_callback *cb) +{ + kfree(cb->data); + return 0; +} + static int nf_tables_getrule(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_cur(net); const struct nft_af_info *afi; const struct nft_table *table; const struct nft_chain *chain; @@ -1944,7 +1946,25 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_rules, + .done = nf_tables_dump_rules_done, }; + + if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { + struct nft_rule_dump_ctx *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + if (nla[NFTA_RULE_TABLE]) + nla_strlcpy(ctx->table, nla[NFTA_RULE_TABLE], + sizeof(ctx->table)); + if (nla[NFTA_RULE_CHAIN]) + nla_strlcpy(ctx->chain, nla[NFTA_RULE_CHAIN], + sizeof(ctx->chain)); + c.data = ctx; + } + return netlink_dump_start(nlsk, skb, nlh, &c); } @@ -1952,17 +1972,13 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, if (IS_ERR(afi)) return PTR_ERR(afi); - table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]); + table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], genmask); if (IS_ERR(table)) return PTR_ERR(table); - if (table->flags & NFT_TABLE_INACTIVE) - return -ENOENT; - chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]); + chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) return PTR_ERR(chain); - if (chain->flags & NFT_CHAIN_INACTIVE) - return -ENOENT; rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) @@ -2011,6 +2027,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_next(net); struct nft_af_info *afi; struct nft_table *table; struct nft_chain *chain; @@ -2031,11 +2048,11 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, if (IS_ERR(afi)) return PTR_ERR(afi); - table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]); + table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], genmask); if (IS_ERR(table)) return PTR_ERR(table); - chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]); + chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) return PTR_ERR(chain); @@ -2104,7 +2121,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, if (rule == NULL) goto err1; - nft_rule_activate_next(net, rule); + nft_activate_next(net, rule); rule->handle = handle; rule->dlen = size; @@ -2126,14 +2143,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } if (nlh->nlmsg_flags & NLM_F_REPLACE) { - if (nft_rule_is_active_next(net, old_rule)) { + if (nft_is_active_next(net, old_rule)) { trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE, old_rule); if (trans == NULL) { err = -ENOMEM; goto err2; } - nft_rule_deactivate_next(net, old_rule); + nft_deactivate_next(net, old_rule); chain->use--; list_add_tail_rcu(&rule->list, &old_rule->list); } else { @@ -2176,6 +2193,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_next(net); struct nft_af_info *afi; struct nft_table *table; struct nft_chain *chain = NULL; @@ -2187,12 +2205,13 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, if (IS_ERR(afi)) return PTR_ERR(afi); - table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]); + table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], genmask); if (IS_ERR(table)) return PTR_ERR(table); if (nla[NFTA_RULE_CHAIN]) { - chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]); + chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], + genmask); if (IS_ERR(chain)) return PTR_ERR(chain); } @@ -2212,6 +2231,9 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, } } else { list_for_each_entry(chain, &table->chains, list) { + if (!nft_is_active_next(net, chain)) + continue; + ctx.chain = chain; err = nft_delrule_by_chain(&ctx); if (err < 0) @@ -2341,7 +2363,8 @@ static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + u8 genmask) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi = NULL; @@ -2357,7 +2380,8 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, if (afi == NULL) return -EAFNOSUPPORT; - table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]); + table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE], + genmask); if (IS_ERR(table)) return PTR_ERR(table); } @@ -2367,7 +2391,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, } struct nft_set *nf_tables_set_lookup(const struct nft_table *table, - const struct nlattr *nla) + const struct nlattr *nla, u8 genmask) { struct nft_set *set; @@ -2375,22 +2399,27 @@ struct nft_set *nf_tables_set_lookup(const struct nft_table *table, return ERR_PTR(-EINVAL); list_for_each_entry(set, &table->sets, list) { - if (!nla_strcmp(nla, set->name)) + if (!nla_strcmp(nla, set->name) && + nft_active_genmask(set, genmask)) return set; } return ERR_PTR(-ENOENT); } struct nft_set *nf_tables_set_lookup_byid(const struct net *net, - const struct nlattr *nla) + const struct nlattr *nla, + u8 genmask) { struct nft_trans *trans; u32 id = ntohl(nla_get_be32(nla)); list_for_each_entry(trans, &net->nft.commit_list, list) { + struct nft_set *set = nft_trans_set(trans); + if (trans->msg_type == NFT_MSG_NEWSET && - id == nft_trans_set_id(trans)) - return nft_trans_set(trans); + id == nft_trans_set_id(trans) && + nft_active_genmask(set, genmask)) + return set; } return ERR_PTR(-ENOENT); } @@ -2415,6 +2444,8 @@ cont: list_for_each_entry(i, &ctx->table->sets, list) { int tmp; + if (!nft_is_active_next(ctx->net, set)) + continue; if (!sscanf(i->name, name, &tmp)) continue; if (tmp < min || tmp >= min + BITS_PER_BYTE * PAGE_SIZE) @@ -2434,6 +2465,8 @@ cont: snprintf(set->name, sizeof(set->name), name, min + n); list_for_each_entry(i, &ctx->table->sets, list) { + if (!nft_is_active_next(ctx->net, i)) + continue; if (!strcmp(set->name, i->name)) return -ENFILE; } @@ -2582,6 +2615,8 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) list_for_each_entry_rcu(set, &table->sets, list) { if (idx < s_idx) goto cont; + if (!nft_is_active(net, set)) + goto cont; ctx_set = *ctx; ctx_set.table = table; @@ -2618,6 +2653,7 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { + u8 genmask = nft_genmask_cur(net); const struct nft_set *set; struct nft_ctx ctx; struct sk_buff *skb2; @@ -2625,7 +2661,7 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, int err; /* Verify existence before starting dump */ - err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla); + err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, genmask); if (err < 0) return err; @@ -2652,11 +2688,9 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, if (!nla[NFTA_SET_TABLE]) return -EINVAL; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]); + set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) return PTR_ERR(set); - if (set->flags & NFT_SET_INACTIVE) - return -ENOENT; skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (skb2 == NULL) @@ -2695,6 +2729,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_next(net); const struct nft_set_ops *ops; struct nft_af_info *afi; struct nft_table *table; @@ -2792,13 +2827,13 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (IS_ERR(afi)) return PTR_ERR(afi); - table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]); + table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE], genmask); if (IS_ERR(table)) return PTR_ERR(table); nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla); - set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME]); + set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) { if (PTR_ERR(set) != -ENOENT) return PTR_ERR(set); @@ -2845,7 +2880,6 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, } INIT_LIST_HEAD(&set->bindings); - write_pnet(&set->pnet, net); set->ops = ops; set->ktype = ktype; set->klen = desc.klen; @@ -2897,6 +2931,7 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + u8 genmask = nft_genmask_next(net); struct nft_set *set; struct nft_ctx ctx; int err; @@ -2906,11 +2941,11 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_TABLE] == NULL) return -EINVAL; - err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla); + err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, genmask); if (err < 0) return err; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]); + set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) return PTR_ERR(set); if (!list_empty(&set->bindings)) @@ -2975,7 +3010,7 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, list_del_rcu(&binding->list); if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS && - !(set->flags & NFT_SET_INACTIVE)) + nft_is_active(ctx->net, set)) nf_tables_set_destroy(ctx, set); } @@ -3031,7 +3066,8 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + u8 genmask) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_af_info *afi; @@ -3041,7 +3077,8 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net, if (IS_ERR(afi)) return PTR_ERR(afi); - table = nf_tables_table_lookup(afi, nla[NFTA_SET_ELEM_LIST_TABLE]); + table = nf_tables_table_lookup(afi, nla[NFTA_SET_ELEM_LIST_TABLE], + genmask); if (IS_ERR(table)) return PTR_ERR(table); @@ -3138,6 +3175,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); + u8 genmask = nft_genmask_cur(net); const struct nft_set *set; struct nft_set_dump_args args; struct nft_ctx ctx; @@ -3154,17 +3192,14 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) return err; err = nft_ctx_init_from_elemattr(&ctx, net, cb->skb, cb->nlh, - (void *)nla); + (void *)nla, genmask); if (err < 0) return err; - if (ctx.table->flags & NFT_TABLE_INACTIVE) - return -ENOENT; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]); + set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], + genmask); if (IS_ERR(set)) return PTR_ERR(set); - if (set->flags & NFT_SET_INACTIVE) - return -ENOENT; event = NFT_MSG_NEWSETELEM; event |= NFNL_SUBSYS_NFTABLES << 8; @@ -3218,21 +3253,19 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { + u8 genmask = nft_genmask_cur(net); const struct nft_set *set; struct nft_ctx ctx; int err; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask); if (err < 0) return err; - if (ctx.table->flags & NFT_TABLE_INACTIVE) - return -ENOENT; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]); + set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], + genmask); if (IS_ERR(set)) return PTR_ERR(set); - if (set->flags & NFT_SET_INACTIVE) - return -ENOENT; if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -3525,7 +3558,7 @@ 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(set, &elem); + err = set->ops->insert(ctx->net, set, &elem); if (err < 0) goto err5; @@ -3550,6 +3583,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { + u8 genmask = nft_genmask_next(net); const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; @@ -3558,15 +3592,17 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask); if (err < 0) return err; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]); + set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], + genmask); if (IS_ERR(set)) { if (nla[NFTA_SET_ELEM_LIST_SET_ID]) { set = nf_tables_set_lookup_byid(net, - nla[NFTA_SET_ELEM_LIST_SET_ID]); + nla[NFTA_SET_ELEM_LIST_SET_ID], + genmask); } if (IS_ERR(set)) return PTR_ERR(set); @@ -3646,7 +3682,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, goto err3; } - priv = set->ops->deactivate(set, &elem); + priv = set->ops->deactivate(ctx->net, set, &elem); if (priv == NULL) { err = -ENOENT; goto err4; @@ -3672,6 +3708,7 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { + u8 genmask = nft_genmask_next(net); const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; @@ -3680,11 +3717,12 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask); if (err < 0) return err; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]); + set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], + genmask); if (IS_ERR(set)) return PTR_ERR(set); if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) @@ -3952,36 +3990,40 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { if (!nft_trans_table_enable(trans)) { - nf_tables_table_disable(trans->ctx.afi, + nf_tables_table_disable(net, + trans->ctx.afi, trans->ctx.table); trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; } } else { - trans->ctx.table->flags &= ~NFT_TABLE_INACTIVE; + nft_clear(net, trans->ctx.table); } nf_tables_table_notify(&trans->ctx, NFT_MSG_NEWTABLE); nft_trans_destroy(trans); break; case NFT_MSG_DELTABLE: + list_del_rcu(&trans->ctx.table->list); nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) nft_chain_commit_update(trans); else - trans->ctx.chain->flags &= ~NFT_CHAIN_INACTIVE; + nft_clear(net, trans->ctx.chain); nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); nft_trans_destroy(trans); break; case NFT_MSG_DELCHAIN: + list_del_rcu(&trans->ctx.chain->list); nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN); - nf_tables_unregister_hooks(trans->ctx.table, + nf_tables_unregister_hooks(trans->ctx.net, + trans->ctx.table, trans->ctx.chain, trans->ctx.afi->nops); break; case NFT_MSG_NEWRULE: - nft_rule_clear(trans->ctx.net, nft_trans_rule(trans)); + nft_clear(trans->ctx.net, nft_trans_rule(trans)); nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), NFT_MSG_NEWRULE); @@ -3994,7 +4036,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) NFT_MSG_DELRULE); break; case NFT_MSG_NEWSET: - nft_trans_set(trans)->flags &= ~NFT_SET_INACTIVE; + nft_clear(net, nft_trans_set(trans)); /* This avoids hitting -EBUSY when deleting the table * from the transaction. */ @@ -4007,13 +4049,14 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELSET: + list_del_rcu(&nft_trans_set(trans)->list); nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), NFT_MSG_DELSET, GFP_KERNEL); break; case NFT_MSG_NEWSETELEM: te = (struct nft_trans_elem *)trans->data; - te->set->ops->activate(te->set, &te->elem); + te->set->ops->activate(net, te->set, &te->elem); nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, NFT_MSG_NEWSETELEM, 0); @@ -4078,7 +4121,8 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { if (nft_trans_table_enable(trans)) { - nf_tables_table_disable(trans->ctx.afi, + nf_tables_table_disable(net, + trans->ctx.afi, trans->ctx.table); trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; } @@ -4088,8 +4132,7 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) } break; case NFT_MSG_DELTABLE: - list_add_tail_rcu(&trans->ctx.table->list, - &trans->ctx.afi->tables); + nft_clear(trans->ctx.net, trans->ctx.table); nft_trans_destroy(trans); break; case NFT_MSG_NEWCHAIN: @@ -4100,15 +4143,15 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) } else { trans->ctx.table->use--; list_del_rcu(&trans->ctx.chain->list); - nf_tables_unregister_hooks(trans->ctx.table, + nf_tables_unregister_hooks(trans->ctx.net, + trans->ctx.table, trans->ctx.chain, trans->ctx.afi->nops); } break; case NFT_MSG_DELCHAIN: trans->ctx.table->use++; - list_add_tail_rcu(&trans->ctx.chain->list, - &trans->ctx.table->chains); + nft_clear(trans->ctx.net, trans->ctx.chain); nft_trans_destroy(trans); break; case NFT_MSG_NEWRULE: @@ -4117,7 +4160,7 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; - nft_rule_clear(trans->ctx.net, nft_trans_rule(trans)); + nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: @@ -4126,8 +4169,7 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELSET: trans->ctx.table->use++; - list_add_tail_rcu(&nft_trans_set(trans)->list, - &trans->ctx.table->sets); + nft_clear(trans->ctx.net, nft_trans_set(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: @@ -4139,7 +4181,7 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) case NFT_MSG_DELSETELEM: te = (struct nft_trans_elem *)trans->data; - te->set->ops->activate(te->set, &te->elem); + te->set->ops->activate(net, te->set, &te->elem); te->set->ndeact--; nft_trans_destroy(trans); @@ -4274,6 +4316,8 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, } list_for_each_entry(set, &ctx->table->sets, list) { + if (!nft_is_active_next(ctx->net, set)) + continue; if (!(set->flags & NFT_SET_MAP) || set->dtype != NFT_DATA_VERDICT) continue; @@ -4432,6 +4476,7 @@ static const struct nla_policy nft_verdict_policy[NFTA_VERDICT_MAX + 1] = { static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, struct nft_data_desc *desc, const struct nlattr *nla) { + u8 genmask = nft_genmask_next(ctx->net); struct nlattr *tb[NFTA_VERDICT_MAX + 1]; struct nft_chain *chain; int err; @@ -4464,7 +4509,7 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (!tb[NFTA_VERDICT_CHAIN]) return -EINVAL; chain = nf_tables_chain_lookup(ctx->table, - tb[NFTA_VERDICT_CHAIN]); + tb[NFTA_VERDICT_CHAIN], genmask); if (IS_ERR(chain)) return PTR_ERR(chain); if (chain->flags & NFT_BASE_CHAIN) @@ -4642,7 +4687,7 @@ int __nft_release_basechain(struct nft_ctx *ctx) BUG_ON(!(ctx->chain->flags & NFT_BASE_CHAIN)); - nf_tables_unregister_hooks(ctx->chain->table, ctx->chain, + nf_tables_unregister_hooks(ctx->net, ctx->chain->table, ctx->chain, ctx->afi->nops); list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { list_del(&rule->list); @@ -4671,7 +4716,8 @@ static void __nft_release_afinfo(struct net *net, struct nft_af_info *afi) list_for_each_entry_safe(table, nt, &afi->tables, list) { list_for_each_entry(chain, &table->chains, list) - nf_tables_unregister_hooks(table, chain, afi->nops); + nf_tables_unregister_hooks(net, table, chain, + afi->nops); /* No packets are walking on these chains anymore. */ ctx.table = table; list_for_each_entry(chain, &table->chains, list) { diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c index 5eefe4a35..75d696f11 100644 --- a/net/netfilter/nf_tables_netdev.c +++ b/net/netfilter/nf_tables_netdev.c @@ -30,7 +30,6 @@ nft_netdev_set_pktinfo_ipv4(struct nft_pktinfo *pkt, if (!iph) return; - iph = ip_hdr(skb); if (iph->ihl < 5 || iph->version != 4) return; diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 39eb1cc62..fa24a5b39 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -237,7 +237,7 @@ 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_acct.c b/net/netfilter/nfnetlink_acct.c index 1b4de4bd6..d44d89b56 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -326,14 +326,14 @@ static int nfnl_acct_try_del(struct nf_acct *cur) { int ret = 0; - /* we want to avoid races with nfnl_acct_find_get. */ - if (atomic_dec_and_test(&cur->refcnt)) { + /* We want to avoid races with nfnl_acct_put. So only when the current + * refcnt is 1, we decrease it to 0. + */ + if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) { /* We are protected by nfnl mutex. */ list_del_rcu(&cur->head); kfree_rcu(cur, rcu_head); } else { - /* still in use, restore reference counter. */ - atomic_inc(&cur->refcnt); ret = -EBUSY; } return ret; @@ -343,12 +343,12 @@ static int nfnl_acct_del(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const tb[]) { - char *acct_name; - struct nf_acct *cur; + struct nf_acct *cur, *tmp; int ret = -ENOENT; + char *acct_name; if (!tb[NFACCT_NAME]) { - list_for_each_entry(cur, &net->nfnl_acct_list, head) + list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head) nfnl_acct_try_del(cur); return 0; @@ -443,7 +443,7 @@ void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct) } EXPORT_SYMBOL_GPL(nfnl_acct_update); -static void nfnl_overquota_report(struct nf_acct *nfacct) +static void nfnl_overquota_report(struct net *net, struct nf_acct *nfacct) { int ret; struct sk_buff *skb; @@ -458,11 +458,12 @@ static void nfnl_overquota_report(struct nf_acct *nfacct) kfree_skb(skb); return; } - netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, + netlink_broadcast(net->nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, GFP_ATOMIC); } -int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) +int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb, + struct nf_acct *nfacct) { u64 now; u64 *quota; @@ -480,7 +481,7 @@ int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) if (now >= *quota && !test_and_set_bit(NFACCT_OVERQUOTA_BIT, &nfacct->flags)) { - nfnl_overquota_report(nfacct); + nfnl_overquota_report(net, nfacct); } return ret; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 3c84f1432..139e0867e 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -98,31 +98,28 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, break; } - l4proto = nf_ct_l4proto_find_get(l3num, l4num); - - /* This protocol is not supportted, skip. */ - if (l4proto->l4proto != l4num) { - ret = -EOPNOTSUPP; - goto err_proto_put; - } - if (matching) { if (nlh->nlmsg_flags & NLM_F_REPLACE) { /* You cannot replace one timeout policy by another of * different kind, sorry. */ if (matching->l3num != l3num || - matching->l4proto->l4proto != l4num) { - ret = -EINVAL; - goto err_proto_put; - } - - ret = ctnl_timeout_parse_policy(&matching->data, - l4proto, net, - cda[CTA_TIMEOUT_DATA]); - return ret; + matching->l4proto->l4proto != l4num) + return -EINVAL; + + return ctnl_timeout_parse_policy(&matching->data, + matching->l4proto, net, + cda[CTA_TIMEOUT_DATA]); } - ret = -EBUSY; + + return -EBUSY; + } + + l4proto = nf_ct_l4proto_find_get(l3num, l4num); + + /* This protocol is not supportted, skip. */ + if (l4proto->l4proto != l4num) { + ret = -EOPNOTSUPP; goto err_proto_put; } @@ -303,16 +300,33 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) { struct nf_conntrack_tuple_hash *h; const struct hlist_nulls_node *nn; - int i; + unsigned int last_hsize; + spinlock_t *lock; + int i, cpu; + + for_each_possible_cpu(cpu) { + struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + + spin_lock_bh(&pcpu->lock); + hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode) + untimeout(h, timeout); + spin_unlock_bh(&pcpu->lock); + } local_bh_disable(); - for (i = 0; i < nf_conntrack_htable_size; i++) { - nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); - if (i < nf_conntrack_htable_size) { - hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) - untimeout(h, timeout); +restart: + last_hsize = nf_conntrack_htable_size; + for (i = 0; i < last_hsize; i++) { + lock = &nf_conntrack_locks[i % CONNTRACK_LOCKS]; + nf_conntrack_lock(lock); + if (last_hsize != nf_conntrack_htable_size) { + spin_unlock(lock); + goto restart; } - spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + + hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) + untimeout(h, timeout); + spin_unlock(lock); } local_bh_enable(); } @@ -322,16 +336,16 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) { int ret = 0; - /* we want to avoid races with nf_ct_timeout_find_get. */ - if (atomic_dec_and_test(&timeout->refcnt)) { + /* We want to avoid races with ctnl_timeout_put. So only when the + * current refcnt is 1, we decrease it to 0. + */ + if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) { /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); nf_ct_l4proto_put(timeout->l4proto); ctnl_untimeout(net, timeout); kfree_rcu(timeout, rcu_head); } else { - /* still in use, restore reference counter. */ - atomic_inc(&timeout->refcnt); ret = -EBUSY; } return ret; @@ -342,12 +356,13 @@ static int cttimeout_del_timeout(struct net *net, struct sock *ctnl, const struct nlmsghdr *nlh, const struct nlattr * const cda[]) { - struct ctnl_timeout *cur; + struct ctnl_timeout *cur, *tmp; int ret = -ENOENT; char *name; if (!cda[CTA_TIMEOUT_NAME]) { - list_for_each_entry(cur, &net->nfct_timeout_list, head) + list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, + head) ctnl_timeout_try_del(net, cur); return 0; @@ -535,7 +550,9 @@ err: static void ctnl_timeout_put(struct ctnl_timeout *timeout) { - atomic_dec(&timeout->refcnt); + if (atomic_dec_and_test(&timeout->refcnt)) + kfree_rcu(timeout, rcu_head); + module_put(THIS_MODULE); } #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ @@ -583,7 +600,9 @@ static void __net_exit cttimeout_net_exit(struct net *net) list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) { list_del_rcu(&cur->head); nf_ct_l4proto_put(cur->l4proto); - kfree_rcu(cur, rcu_head); + + if (atomic_dec_and_test(&cur->refcnt)) + kfree_rcu(cur, rcu_head); } } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 11f81c838..6577db524 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -700,10 +700,13 @@ nfulnl_log_packet(struct net *net, break; case NFULNL_COPY_PACKET: - if (inst->copy_range > skb->len) + data_len = inst->copy_range; + if ((li->u.ulog.flags & NF_LOG_F_COPY_LEN) && + (li->u.ulog.copy_len < data_len)) + data_len = li->u.ulog.copy_len; + + if (data_len > skb->len) data_len = skb->len; - else - data_len = inst->copy_range; size += nla_total_size(data_len); break; @@ -1144,6 +1147,7 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ULOG); MODULE_ALIAS_NF_LOGGER(AF_INET, 1); MODULE_ALIAS_NF_LOGGER(AF_INET6, 1); MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1); +MODULE_ALIAS_NF_LOGGER(3, 1); /* NFPROTO_ARP */ module_init(nfnetlink_log_init); module_exit(nfnetlink_log_fini); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 5d36a0926..f49f45081 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1145,10 +1145,8 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, struct nfnl_queue_net *q = nfnl_queue_pernet(net); int err; - queue = instance_lookup(q, queue_num); - if (!queue) - queue = verdict_instance_lookup(q, queue_num, - NETLINK_CB(skb).portid); + queue = verdict_instance_lookup(q, queue_num, + NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 6228c422c..c21e7eb8d 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -23,6 +23,20 @@ #include <linux/netfilter_arp/arp_tables.h> #include <net/netfilter/nf_tables.h> +struct nft_xt { + struct list_head head; + struct nft_expr_ops ops; + unsigned int refcnt; +}; + +static void nft_xt_put(struct nft_xt *xt) +{ + if (--xt->refcnt == 0) { + list_del(&xt->head); + kfree(xt); + } +} + static int nft_compat_chain_validate_dependency(const char *tablename, const struct nft_chain *chain) { @@ -260,6 +274,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) if (par.target->destroy != NULL) par.target->destroy(&par); + nft_xt_put(container_of(expr->ops, struct nft_xt, ops)); module_put(target->me); } @@ -442,6 +457,7 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) if (par.match->destroy != NULL) par.match->destroy(&par); + nft_xt_put(container_of(expr->ops, struct nft_xt, ops)); module_put(match->me); } @@ -612,11 +628,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { static LIST_HEAD(nft_match_list); -struct nft_xt { - struct list_head head; - struct nft_expr_ops ops; -}; - static struct nft_expr_type nft_match_type; static bool nft_match_cmp(const struct xt_match *match, @@ -634,6 +645,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, struct xt_match *match; char *mt_name; u32 rev, family; + int err; if (tb[NFTA_MATCH_NAME] == NULL || tb[NFTA_MATCH_REV] == NULL || @@ -652,6 +664,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, if (!try_module_get(match->me)) return ERR_PTR(-ENOENT); + nft_match->refcnt++; return &nft_match->ops; } } @@ -660,14 +673,19 @@ nft_match_select_ops(const struct nft_ctx *ctx, if (IS_ERR(match)) return ERR_PTR(-ENOENT); - if (match->matchsize > nla_len(tb[NFTA_MATCH_INFO])) - return ERR_PTR(-EINVAL); + if (match->matchsize > nla_len(tb[NFTA_MATCH_INFO])) { + err = -EINVAL; + goto err; + } /* This is the first time we use this match, allocate operations */ nft_match = kzalloc(sizeof(struct nft_xt), GFP_KERNEL); - if (nft_match == NULL) - return ERR_PTR(-ENOMEM); + if (nft_match == NULL) { + err = -ENOMEM; + goto err; + } + nft_match->refcnt = 1; nft_match->ops.type = &nft_match_type; nft_match->ops.size = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize)); nft_match->ops.eval = nft_match_eval; @@ -680,14 +698,9 @@ nft_match_select_ops(const struct nft_ctx *ctx, list_add(&nft_match->head, &nft_match_list); return &nft_match->ops; -} - -static void nft_match_release(void) -{ - struct nft_xt *nft_match, *tmp; - - list_for_each_entry_safe(nft_match, tmp, &nft_match_list, head) - kfree(nft_match); +err: + module_put(match->me); + return ERR_PTR(err); } static struct nft_expr_type nft_match_type __read_mostly = { @@ -717,6 +730,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, struct xt_target *target; char *tg_name; u32 rev, family; + int err; if (tb[NFTA_TARGET_NAME] == NULL || tb[NFTA_TARGET_REV] == NULL || @@ -735,6 +749,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, if (!try_module_get(target->me)) return ERR_PTR(-ENOENT); + nft_target->refcnt++; return &nft_target->ops; } } @@ -743,14 +758,19 @@ nft_target_select_ops(const struct nft_ctx *ctx, if (IS_ERR(target)) return ERR_PTR(-ENOENT); - if (target->targetsize > nla_len(tb[NFTA_TARGET_INFO])) - return ERR_PTR(-EINVAL); + if (target->targetsize > nla_len(tb[NFTA_TARGET_INFO])) { + err = -EINVAL; + goto err; + } /* This is the first time we use this target, allocate operations */ nft_target = kzalloc(sizeof(struct nft_xt), GFP_KERNEL); - if (nft_target == NULL) - return ERR_PTR(-ENOMEM); + if (nft_target == NULL) { + err = -ENOMEM; + goto err; + } + nft_target->refcnt = 1; nft_target->ops.type = &nft_target_type; nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); nft_target->ops.init = nft_target_init; @@ -767,14 +787,9 @@ nft_target_select_ops(const struct nft_ctx *ctx, list_add(&nft_target->head, &nft_target_list); return &nft_target->ops; -} - -static void nft_target_release(void) -{ - struct nft_xt *nft_target, *tmp; - - list_for_each_entry_safe(nft_target, tmp, &nft_target_list, head) - kfree(nft_target); +err: + module_put(target->me); + return ERR_PTR(err); } static struct nft_expr_type nft_target_type __read_mostly = { @@ -819,8 +834,6 @@ static void __exit nft_compat_module_exit(void) nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); - nft_match_release(); - nft_target_release(); } MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 81fbb4507..51e180f2a 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -109,18 +109,11 @@ static void nft_ct_get_eval(const struct nft_expr *expr, #ifdef CONFIG_NF_CONNTRACK_LABELS case NFT_CT_LABELS: { struct nf_conn_labels *labels = nf_ct_labels_find(ct); - unsigned int size; - if (!labels) { + if (labels) + memcpy(dest, labels->bits, NF_CT_LABELS_MAX_SIZE); + else memset(dest, 0, NF_CT_LABELS_MAX_SIZE); - return; - } - - size = labels->words * sizeof(long); - memcpy(dest, labels->bits, size); - if (size < NF_CT_LABELS_MAX_SIZE) - memset(((char *) dest) + size, 0, - NF_CT_LABELS_MAX_SIZE - size); return; } #endif @@ -351,6 +344,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, if (err < 0) return err; + if (priv->key == NFT_CT_BYTES || priv->key == NFT_CT_PKTS) + nf_ct_set_acct(ctx->net, true); + return 0; } @@ -359,6 +355,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_ct *priv = nft_expr_priv(expr); + bool label_got = false; unsigned int len; int err; @@ -377,6 +374,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, err = nf_connlabels_get(ctx->net, (len * BITS_PER_BYTE) - 1); if (err) return err; + label_got = true; break; #endif default: @@ -386,17 +384,28 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, priv->sreg = nft_parse_register(tb[NFTA_CT_SREG]); err = nft_validate_register_load(priv->sreg, len); if (err < 0) - return err; + goto err1; err = nft_ct_l3proto_try_module_get(ctx->afi->family); if (err < 0) - return err; + goto err1; return 0; + +err1: + if (label_got) + nf_connlabels_put(ctx->net); + return err; +} + +static void nft_ct_get_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + nft_ct_l3proto_module_put(ctx->afi->family); } -static void nft_ct_destroy(const struct nft_ctx *ctx, - const struct nft_expr *expr) +static void nft_ct_set_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { struct nft_ct *priv = nft_expr_priv(expr); @@ -468,7 +477,7 @@ static const struct nft_expr_ops nft_ct_get_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), .eval = nft_ct_get_eval, .init = nft_ct_get_init, - .destroy = nft_ct_destroy, + .destroy = nft_ct_get_destroy, .dump = nft_ct_get_dump, }; @@ -477,7 +486,7 @@ static const struct nft_expr_ops nft_ct_set_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), .eval = nft_ct_set_eval, .init = nft_ct_set_init, - .destroy = nft_ct_destroy, + .destroy = nft_ct_set_destroy, .dump = nft_ct_set_dump, }; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 78d4914fb..0af26699b 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -103,6 +103,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_dynset *priv = nft_expr_priv(expr); + u8 genmask = nft_genmask_next(ctx->net); struct nft_set *set; u64 timeout; int err; @@ -112,11 +113,13 @@ static int nft_dynset_init(const struct nft_ctx *ctx, tb[NFTA_DYNSET_SREG_KEY] == NULL) return -EINVAL; - set = nf_tables_set_lookup(ctx->table, tb[NFTA_DYNSET_SET_NAME]); + set = nf_tables_set_lookup(ctx->table, tb[NFTA_DYNSET_SET_NAME], + genmask); if (IS_ERR(set)) { if (tb[NFTA_DYNSET_SET_ID]) set = nf_tables_set_lookup_byid(ctx->net, - tb[NFTA_DYNSET_SET_ID]); + tb[NFTA_DYNSET_SET_ID], + genmask); if (IS_ERR(set)) return PTR_ERR(set); } diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index ba7aed13e..82c264e40 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -59,6 +59,7 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_exthdr *priv = nft_expr_priv(expr); + u32 offset, len; if (tb[NFTA_EXTHDR_DREG] == NULL || tb[NFTA_EXTHDR_TYPE] == NULL || @@ -66,9 +67,15 @@ 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])); + + if (offset > U8_MAX || len > U8_MAX) + return -ERANGE; + priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); - priv->offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET])); - priv->len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN])); + priv->offset = offset; + priv->len = len; priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]); return nft_validate_register_store(ctx, priv->dreg, NULL, diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index f39c53a15..564fa7929 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -71,13 +71,13 @@ static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg, return 0; } -static bool nft_hash_lookup(const struct nft_set *set, const u32 *key, - const struct nft_set_ext **ext) +static bool nft_hash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_hash *priv = nft_set_priv(set); const struct nft_hash_elem *he; struct nft_hash_cmp_arg arg = { - .genmask = nft_genmask_cur(read_pnet(&set->pnet)), + .genmask = nft_genmask_cur(net), .set = set, .key = key, }; @@ -125,13 +125,13 @@ err1: return false; } -static int nft_hash_insert(const struct nft_set *set, +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(read_pnet(&set->pnet)), + .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, }; @@ -140,22 +140,23 @@ static int nft_hash_insert(const struct nft_set *set, nft_hash_params); } -static void nft_hash_activate(const struct nft_set *set, +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(set, &he->ext); + nft_set_elem_change_active(net, set, &he->ext); nft_set_elem_clear_busy(&he->ext); } -static void *nft_hash_deactivate(const struct nft_set *set, +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(read_pnet(&set->pnet)), + .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, }; @@ -163,8 +164,9 @@ static void *nft_hash_deactivate(const struct nft_set *set, 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_set_elem_change_active(set, &he->ext); + 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; } diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 319c22b4b..24a73bb26 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -52,7 +52,14 @@ static int nft_log_init(const struct nft_ctx *ctx, struct nft_log *priv = nft_expr_priv(expr); struct nf_loginfo *li = &priv->loginfo; const struct nlattr *nla; - int ret; + int err; + + li->type = NF_LOG_TYPE_LOG; + if (tb[NFTA_LOG_LEVEL] != NULL && + tb[NFTA_LOG_GROUP] != NULL) + return -EINVAL; + if (tb[NFTA_LOG_GROUP] != NULL) + li->type = NF_LOG_TYPE_ULOG; nla = tb[NFTA_LOG_PREFIX]; if (nla != NULL) { @@ -64,13 +71,6 @@ static int nft_log_init(const struct nft_ctx *ctx, priv->prefix = (char *)nft_log_null_prefix; } - li->type = NF_LOG_TYPE_LOG; - if (tb[NFTA_LOG_LEVEL] != NULL && - tb[NFTA_LOG_GROUP] != NULL) - return -EINVAL; - if (tb[NFTA_LOG_GROUP] != NULL) - li->type = NF_LOG_TYPE_ULOG; - switch (li->type) { case NF_LOG_TYPE_LOG: if (tb[NFTA_LOG_LEVEL] != NULL) { @@ -79,6 +79,11 @@ static int nft_log_init(const struct nft_ctx *ctx, } else { li->u.log.level = LOGLEVEL_WARNING; } + if (li->u.log.level > LOGLEVEL_DEBUG) { + err = -EINVAL; + goto err1; + } + if (tb[NFTA_LOG_FLAGS] != NULL) { li->u.log.logflags = ntohl(nla_get_be32(tb[NFTA_LOG_FLAGS])); @@ -87,6 +92,7 @@ static int nft_log_init(const struct nft_ctx *ctx, case NF_LOG_TYPE_ULOG: li->u.ulog.group = ntohs(nla_get_be16(tb[NFTA_LOG_GROUP])); if (tb[NFTA_LOG_SNAPLEN] != NULL) { + li->u.ulog.flags |= NF_LOG_F_COPY_LEN; li->u.ulog.copy_len = ntohl(nla_get_be32(tb[NFTA_LOG_SNAPLEN])); } @@ -97,20 +103,16 @@ static int nft_log_init(const struct nft_ctx *ctx, break; } - if (ctx->afi->family == NFPROTO_INET) { - ret = nf_logger_find_get(NFPROTO_IPV4, li->type); - if (ret < 0) - return ret; + err = nf_logger_find_get(ctx->afi->family, li->type); + if (err < 0) + goto err1; - ret = nf_logger_find_get(NFPROTO_IPV6, li->type); - if (ret < 0) { - nf_logger_put(NFPROTO_IPV4, li->type); - return ret; - } - return 0; - } + return 0; - return nf_logger_find_get(ctx->afi->family, li->type); +err1: + if (priv->prefix != nft_log_null_prefix) + kfree(priv->prefix); + return err; } static void nft_log_destroy(const struct nft_ctx *ctx, @@ -122,12 +124,7 @@ static void nft_log_destroy(const struct nft_ctx *ctx, if (priv->prefix != nft_log_null_prefix) kfree(priv->prefix); - if (ctx->afi->family == NFPROTO_INET) { - nf_logger_put(NFPROTO_IPV4, li->type); - nf_logger_put(NFPROTO_IPV6, li->type); - } else { - nf_logger_put(ctx->afi->family, li->type); - } + nf_logger_put(ctx->afi->family, li->type); } static int nft_log_dump(struct sk_buff *skb, const struct nft_expr *expr) @@ -153,7 +150,7 @@ static int nft_log_dump(struct sk_buff *skb, const struct nft_expr *expr) if (nla_put_be16(skb, NFTA_LOG_GROUP, htons(li->u.ulog.group))) goto nla_put_failure; - if (li->u.ulog.copy_len) { + if (li->u.ulog.flags & NF_LOG_F_COPY_LEN) { if (nla_put_be32(skb, NFTA_LOG_SNAPLEN, htonl(li->u.ulog.copy_len))) goto nla_put_failure; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index b3c31ef80..e164325d1 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -22,6 +22,7 @@ struct nft_lookup { struct nft_set *set; enum nft_registers sreg:8; enum nft_registers dreg:8; + bool invert; struct nft_set_binding binding; }; @@ -32,14 +33,20 @@ static void nft_lookup_eval(const struct nft_expr *expr, const struct nft_lookup *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; const struct nft_set_ext *ext; + bool found; - if (set->ops->lookup(set, ®s->data[priv->sreg], &ext)) { - if (set->flags & NFT_SET_MAP) - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), set->dlen); + found = set->ops->lookup(pkt->net, set, ®s->data[priv->sreg], &ext) ^ + priv->invert; + + if (!found) { + regs->verdict.code = NFT_BREAK; return; } - regs->verdict.code = NFT_BREAK; + + if (found && set->flags & NFT_SET_MAP) + nft_data_copy(®s->data[priv->dreg], + nft_set_ext_data(ext), set->dlen); + } static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = { @@ -47,6 +54,7 @@ static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = { [NFTA_LOOKUP_SET_ID] = { .type = NLA_U32 }, [NFTA_LOOKUP_SREG] = { .type = NLA_U32 }, [NFTA_LOOKUP_DREG] = { .type = NLA_U32 }, + [NFTA_LOOKUP_FLAGS] = { .type = NLA_U32 }, }; static int nft_lookup_init(const struct nft_ctx *ctx, @@ -54,18 +62,21 @@ static int nft_lookup_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_lookup *priv = nft_expr_priv(expr); + u8 genmask = nft_genmask_next(ctx->net); struct nft_set *set; + u32 flags; int err; if (tb[NFTA_LOOKUP_SET] == NULL || tb[NFTA_LOOKUP_SREG] == NULL) return -EINVAL; - set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET]); + set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET], genmask); if (IS_ERR(set)) { if (tb[NFTA_LOOKUP_SET_ID]) { set = nf_tables_set_lookup_byid(ctx->net, - tb[NFTA_LOOKUP_SET_ID]); + tb[NFTA_LOOKUP_SET_ID], + genmask); } if (IS_ERR(set)) return PTR_ERR(set); @@ -79,7 +90,22 @@ static int nft_lookup_init(const struct nft_ctx *ctx, if (err < 0) return err; + if (tb[NFTA_LOOKUP_FLAGS]) { + flags = ntohl(nla_get_be32(tb[NFTA_LOOKUP_FLAGS])); + + if (flags & ~NFT_LOOKUP_F_INV) + return -EINVAL; + + if (flags & NFT_LOOKUP_F_INV) { + if (set->flags & NFT_SET_MAP) + return -EINVAL; + priv->invert = true; + } + } + if (tb[NFTA_LOOKUP_DREG] != NULL) { + if (priv->invert) + return -EINVAL; if (!(set->flags & NFT_SET_MAP)) return -EINVAL; @@ -112,6 +138,7 @@ static void nft_lookup_destroy(const struct nft_ctx *ctx, static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_lookup *priv = nft_expr_priv(expr); + u32 flags = priv->invert ? NFT_LOOKUP_F_INV : 0; if (nla_put_string(skb, NFTA_LOOKUP_SET, priv->set->name)) goto nla_put_failure; @@ -120,6 +147,8 @@ static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr) if (priv->set->flags & NFT_SET_MAP) if (nft_dump_register(skb, NFTA_LOOKUP_DREG, priv->dreg)) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_LOOKUP_FLAGS, htonl(flags))) + goto nla_put_failure; return 0; nla_put_failure: diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index f4bad9dc1..8a6bc7630 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -199,13 +199,6 @@ err: } EXPORT_SYMBOL_GPL(nft_meta_get_eval); -/* don't change or set _LOOPBACK, _USER, etc. */ -static bool pkt_type_ok(u32 p) -{ - return p == PACKET_HOST || p == PACKET_BROADCAST || - p == PACKET_MULTICAST || p == PACKET_OTHERHOST; -} - void nft_meta_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -223,7 +216,7 @@ void nft_meta_set_eval(const struct nft_expr *expr, break; case NFT_META_PKTTYPE: if (skb->pkt_type != value && - pkt_type_ok(value) && pkt_type_ok(skb->pkt_type)) + skb_pkt_type_ok(value) && skb_pkt_type_ok(skb->pkt_type)) skb->pkt_type = value; break; case NFT_META_NFTRACE: @@ -298,10 +291,16 @@ int nft_meta_get_init(const struct nft_ctx *ctx, } EXPORT_SYMBOL_GPL(nft_meta_get_init); -static int nft_meta_set_init_pkttype(const struct nft_ctx *ctx) +int nft_meta_set_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) { + struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; + if (priv->key != NFT_META_PKTTYPE) + return 0; + switch (ctx->afi->family) { case NFPROTO_BRIDGE: hooks = 1 << NF_BR_PRE_ROUTING; @@ -315,6 +314,7 @@ static int nft_meta_set_init_pkttype(const struct nft_ctx *ctx) return nft_chain_validate_hooks(ctx->chain, hooks); } +EXPORT_SYMBOL_GPL(nft_meta_set_validate); int nft_meta_set_init(const struct nft_ctx *ctx, const struct nft_expr *expr, @@ -334,15 +334,16 @@ int nft_meta_set_init(const struct nft_ctx *ctx, len = sizeof(u8); break; case NFT_META_PKTTYPE: - err = nft_meta_set_init_pkttype(ctx); - if (err) - return err; len = sizeof(u8); break; default: return -EOPNOTSUPP; } + err = nft_meta_set_validate(ctx, expr, NULL); + if (err < 0) + return err; + priv->sreg = nft_parse_register(tb[NFTA_META_SREG]); err = nft_validate_register_load(priv->sreg, len); if (err < 0) @@ -414,6 +415,7 @@ static const struct nft_expr_ops nft_meta_set_ops = { .init = nft_meta_set_init, .destroy = nft_meta_set_destroy, .dump = nft_meta_set_dump, + .validate = nft_meta_set_validate, }; static const struct nft_expr_ops * diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c index 7201d57b5..ffe9ae062 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_rbtree.c @@ -41,13 +41,13 @@ static bool nft_rbtree_equal(const struct nft_set *set, const void *this, return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0; } -static bool nft_rbtree_lookup(const struct nft_set *set, const u32 *key, - const struct nft_set_ext **ext) +static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { const struct nft_rbtree *priv = nft_set_priv(set); const struct nft_rbtree_elem *rbe, *interval = NULL; + u8 genmask = nft_genmask_cur(net); const struct rb_node *parent; - u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); const void *this; int d; @@ -70,7 +70,6 @@ static bool nft_rbtree_lookup(const struct nft_set *set, const u32 *key, } else if (d > 0) parent = parent->rb_right; else { -found: if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; @@ -84,22 +83,25 @@ found: } } - if (set->flags & NFT_SET_INTERVAL && interval != NULL) { - rbe = interval; - goto found; + if (set->flags & NFT_SET_INTERVAL && interval != NULL && + nft_set_elem_active(&interval->ext, genmask) && + !nft_rbtree_interval_end(interval)) { + spin_unlock_bh(&nft_rbtree_lock); + *ext = &interval->ext; + return true; } out: spin_unlock_bh(&nft_rbtree_lock); return false; } -static int __nft_rbtree_insert(const struct nft_set *set, +static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new) { struct nft_rbtree *priv = nft_set_priv(set); + u8 genmask = nft_genmask_next(net); struct nft_rbtree_elem *rbe; struct rb_node *parent, **p; - u8 genmask = nft_genmask_next(read_pnet(&set->pnet)); int d; parent = NULL; @@ -132,14 +134,14 @@ static int __nft_rbtree_insert(const struct nft_set *set, return 0; } -static int nft_rbtree_insert(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) { struct nft_rbtree_elem *rbe = elem->priv; int err; spin_lock_bh(&nft_rbtree_lock); - err = __nft_rbtree_insert(set, rbe); + err = __nft_rbtree_insert(net, set, rbe); spin_unlock_bh(&nft_rbtree_lock); return err; @@ -156,21 +158,23 @@ static void nft_rbtree_remove(const struct nft_set *set, spin_unlock_bh(&nft_rbtree_lock); } -static void nft_rbtree_activate(const struct nft_set *set, +static void nft_rbtree_activate(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_rbtree_elem *rbe = elem->priv; - nft_set_elem_change_active(set, &rbe->ext); + nft_set_elem_change_active(net, set, &rbe->ext); } -static void *nft_rbtree_deactivate(const struct nft_set *set, +static void *nft_rbtree_deactivate(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem) { const struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent = priv->root.rb_node; struct nft_rbtree_elem *rbe, *this = elem->priv; - u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); + u8 genmask = nft_genmask_next(net); int d; while (parent != NULL) { @@ -196,7 +200,7 @@ static void *nft_rbtree_deactivate(const struct nft_set *set, parent = parent->rb_right; continue; } - nft_set_elem_change_active(set, &rbe->ext); + nft_set_elem_change_active(net, set, &rbe->ext); return rbe; } } diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 0522fc9bf..c64de3f73 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -26,11 +26,27 @@ const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = { }; EXPORT_SYMBOL_GPL(nft_reject_policy); +int nft_reject_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT)); +} +EXPORT_SYMBOL_GPL(nft_reject_validate); + int nft_reject_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); + int err; + + err = nft_reject_validate(ctx, expr, NULL); + if (err < 0) + return err; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 759ca5248..e79d9ca2f 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -66,7 +66,11 @@ static int nft_reject_inet_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); - int icmp_code; + int icmp_code, err; + + err = nft_reject_validate(ctx, expr, NULL); + if (err < 0) + return err; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; @@ -124,6 +128,7 @@ static const struct nft_expr_ops nft_reject_inet_ops = { .eval = nft_reject_inet_eval, .init = nft_reject_inet_init, .dump = nft_reject_inet_dump, + .validate = nft_reject_validate, }; static struct nft_expr_type nft_reject_inet_type __read_mostly = { diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 2675d580c..e0aa7c1d0 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -702,6 +702,56 @@ int xt_check_entry_offsets(const void *base, } EXPORT_SYMBOL(xt_check_entry_offsets); +/** + * xt_alloc_entry_offsets - allocate array to store rule head offsets + * + * @size: number of entries + * + * Return: NULL or kmalloc'd or vmalloc'd array + */ +unsigned int *xt_alloc_entry_offsets(unsigned int size) +{ + unsigned int *off; + + off = kcalloc(size, sizeof(unsigned int), GFP_KERNEL | __GFP_NOWARN); + + if (off) + return off; + + if (size < (SIZE_MAX / sizeof(unsigned int))) + off = vmalloc(size * sizeof(unsigned int)); + + return off; +} +EXPORT_SYMBOL(xt_alloc_entry_offsets); + +/** + * xt_find_jump_offset - check if target is a valid jump offset + * + * @offsets: array containing all valid rule start offsets of a rule blob + * @target: the jump target to search for + * @size: entries in @offset + */ +bool xt_find_jump_offset(const unsigned int *offsets, + unsigned int target, unsigned int size) +{ + int m, low = 0, hi = size; + + while (hi > low) { + m = (low + hi) / 2u; + + if (offsets[m] > target) + hi = m; + else if (offsets[m] < target) + low = m + 1; + else + return true; + } + + return false; +} +EXPORT_SYMBOL(xt_find_jump_offset); + int xt_check_target(struct xt_tgchk_param *par, unsigned int size, u_int8_t proto, bool inv_proto) { @@ -1460,6 +1510,9 @@ xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn) uint8_t hooknum; struct nf_hook_ops *ops; + if (!num_hooks) + return ERR_PTR(-EINVAL); + ops = kmalloc(sizeof(*ops) * num_hooks, GFP_KERNEL); if (ops == NULL) return ERR_PTR(-ENOMEM); diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c index a1fa2c800..018eed7e1 100644 --- a/net/netfilter/xt_NFLOG.c +++ b/net/netfilter/xt_NFLOG.c @@ -33,6 +33,9 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) li.u.ulog.group = info->group; li.u.ulog.qthreshold = info->threshold; + if (info->flags & XT_NFLOG_F_COPY_LEN) + li.u.ulog.flags |= NF_LOG_F_COPY_LEN; + nfulnl_log_packet(net, par->family, par->hooknum, skb, par->in, par->out, &li, info->prefix); return XT_CONTINUE; diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 604df6fae..515131f9e 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -137,7 +137,7 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) cfg.est.ewma_log = info->ewma_log; ret = gen_new_estimator(&est->bstats, NULL, &est->rstats, - &est->lock, &cfg.opt); + &est->lock, NULL, &cfg.opt); if (ret < 0) goto err2; diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 7f4414d26..663c4c3c9 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -127,6 +127,8 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, daddr, dport, in->ifindex); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in * xt_socket, since xt_TPROXY needs 0 bound @@ -195,6 +197,8 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, daddr, ntohs(dport), in->ifindex); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in * xt_socket, since xt_TPROXY needs 0 bound diff --git a/net/netfilter/xt_TRACE.c b/net/netfilter/xt_TRACE.c index df48967af..858d189a1 100644 --- a/net/netfilter/xt_TRACE.c +++ b/net/netfilter/xt_TRACE.c @@ -4,12 +4,23 @@ #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> +#include <net/netfilter/nf_log.h> MODULE_DESCRIPTION("Xtables: packet flow tracing"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_TRACE"); MODULE_ALIAS("ip6t_TRACE"); +static int trace_tg_check(const struct xt_tgchk_param *par) +{ + return nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); +} + +static void trace_tg_destroy(const struct xt_tgdtor_param *par) +{ + nf_logger_put(par->family, NF_LOG_TYPE_LOG); +} + static unsigned int trace_tg(struct sk_buff *skb, const struct xt_action_param *par) { @@ -18,12 +29,14 @@ trace_tg(struct sk_buff *skb, const struct xt_action_param *par) } static struct xt_target trace_tg_reg __read_mostly = { - .name = "TRACE", - .revision = 0, - .family = NFPROTO_UNSPEC, - .table = "raw", - .target = trace_tg, - .me = THIS_MODULE, + .name = "TRACE", + .revision = 0, + .family = NFPROTO_UNSPEC, + .table = "raw", + .target = trace_tg, + .checkentry = trace_tg_check, + .destroy = trace_tg_destroy, + .me = THIS_MODULE, }; static int __init trace_tg_init(void) diff --git a/net/netfilter/xt_connlabel.c b/net/netfilter/xt_connlabel.c index a79af2555..03d66f1c5 100644 --- a/net/netfilter/xt_connlabel.c +++ b/net/netfilter/xt_connlabel.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_labels.h> #include <linux/netfilter/x_tables.h> @@ -18,21 +19,12 @@ MODULE_DESCRIPTION("Xtables: add/match connection trackling labels"); MODULE_ALIAS("ipt_connlabel"); MODULE_ALIAS("ip6t_connlabel"); -static bool connlabel_match(const struct nf_conn *ct, u16 bit) -{ - struct nf_conn_labels *labels = nf_ct_labels_find(ct); - - if (!labels) - return false; - - return BIT_WORD(bit) < labels->words && test_bit(bit, labels->bits); -} - static bool connlabel_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_connlabel_mtinfo *info = par->matchinfo; enum ip_conntrack_info ctinfo; + struct nf_conn_labels *labels; struct nf_conn *ct; bool invert = info->options & XT_CONNLABEL_OP_INVERT; @@ -40,10 +32,21 @@ connlabel_mt(const struct sk_buff *skb, struct xt_action_param *par) if (ct == NULL || nf_ct_is_untracked(ct)) return invert; - if (info->options & XT_CONNLABEL_OP_SET) - return (nf_connlabel_set(ct, info->bit) == 0) ^ invert; + labels = nf_ct_labels_find(ct); + if (!labels) + return invert; + + if (test_bit(info->bit, labels->bits)) + return !invert; + + if (info->options & XT_CONNLABEL_OP_SET) { + if (!test_and_set_bit(info->bit, labels->bits)) + nf_conntrack_event_cache(IPCT_LABEL, ct); + + return !invert; + } - return connlabel_match(ct, info->bit) ^ invert; + return invert; } static int connlabel_mt_check(const struct xt_mtchk_param *par) diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index 3048a7e3a..cf3275938 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -26,7 +26,7 @@ static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par) nfnl_acct_update(skb, info->nfacct); - overquota = nfnl_acct_overquota(skb, info->nfacct); + overquota = nfnl_acct_overquota(par->net, skb, info->nfacct); return overquota == NFACCT_UNDERQUOTA ? false : true; } diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index 1302b475a..a20e731b5 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -21,11 +21,39 @@ static int owner_check(const struct xt_mtchk_param *par) { struct xt_owner_match_info *info = par->matchinfo; + struct net *net = par->net; - /* For now only allow adding matches from the initial user namespace */ + /* Only allow the common case where the userns of the writer + * matches the userns of the network namespace. + */ if ((info->match & (XT_OWNER_UID|XT_OWNER_GID)) && - (current_user_ns() != &init_user_ns)) + (current_user_ns() != net->user_ns)) return -EINVAL; + + /* Ensure the uids are valid */ + if (info->match & XT_OWNER_UID) { + kuid_t uid_min = make_kuid(net->user_ns, info->uid_min); + kuid_t uid_max = make_kuid(net->user_ns, info->uid_max); + + if (!uid_valid(uid_min) || !uid_valid(uid_max) || + (info->uid_max < info->uid_min) || + uid_lt(uid_max, uid_min)) { + return -EINVAL; + } + } + + /* Ensure the gids are valid */ + if (info->match & XT_OWNER_GID) { + kgid_t gid_min = make_kgid(net->user_ns, info->gid_min); + kgid_t gid_max = make_kgid(net->user_ns, info->gid_max); + + if (!gid_valid(gid_min) || !gid_valid(gid_max) || + (info->gid_max < info->gid_min) || + gid_lt(gid_max, gid_min)) { + return -EINVAL; + } + } + return 0; } @@ -35,6 +63,7 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) const struct xt_owner_match_info *info = par->matchinfo; const struct file *filp; struct sock *sk = skb_to_full_sk(skb); + struct net *net = par->net; if (sk == NULL || sk->sk_socket == NULL) return (info->match ^ info->invert) == 0; @@ -51,8 +80,8 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) (XT_OWNER_UID | XT_OWNER_GID)) == 0; if (info->match & XT_OWNER_UID) { - kuid_t uid_min = make_kuid(&init_user_ns, info->uid_min); - kuid_t uid_max = make_kuid(&init_user_ns, info->uid_max); + kuid_t uid_min = make_kuid(net->user_ns, info->uid_min); + kuid_t uid_max = make_kuid(net->user_ns, info->uid_max); if ((uid_gte(filp->f_cred->fsuid, uid_min) && uid_lte(filp->f_cred->fsuid, uid_max)) ^ !(info->invert & XT_OWNER_UID)) @@ -60,8 +89,8 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) } if (info->match & XT_OWNER_GID) { - kgid_t gid_min = make_kgid(&init_user_ns, info->gid_min); - kgid_t gid_max = make_kgid(&init_user_ns, info->gid_max); + kgid_t gid_min = make_kgid(net->user_ns, info->gid_min); + kgid_t gid_max = make_kgid(net->user_ns, info->gid_max); if ((gid_gte(filp->f_cred->fsgid, gid_min) && gid_lte(filp->f_cred->fsgid, gid_max)) ^ !(info->invert & XT_OWNER_GID)) diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index 1caaccbc3..e5f18988a 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -102,14 +102,14 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || info->bitmask & ~XT_PHYSDEV_OP_MASK) return -EINVAL; - if (info->bitmask & XT_PHYSDEV_OP_OUT && + if (info->bitmask & (XT_PHYSDEV_OP_OUT | XT_PHYSDEV_OP_ISOUT) && (!(info->bitmask & XT_PHYSDEV_OP_BRIDGED) || 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 in the OUTPUT, FORWARD and " - "POSTROUTING chains for non-bridged traffic is not " - "supported anymore.\n"); + 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_tcpudp.c b/net/netfilter/xt_tcpudp.c index c14d4645d..ade024c90 100644 --- a/net/netfilter/xt_tcpudp.c +++ b/net/netfilter/xt_tcpudp.c @@ -83,8 +83,6 @@ static bool tcp_mt(const struct sk_buff *skb, struct xt_action_param *par) return false; } -#define FWINVTCP(bool, invflg) ((bool) ^ !!(tcpinfo->invflags & (invflg))) - th = skb_header_pointer(skb, par->thoff, sizeof(_tcph), &_tcph); if (th == NULL) { /* We've been asked to examine this packet, and we @@ -102,9 +100,8 @@ static bool tcp_mt(const struct sk_buff *skb, struct xt_action_param *par) ntohs(th->dest), !!(tcpinfo->invflags & XT_TCP_INV_DSTPT))) return false; - if (!FWINVTCP((((unsigned char *)th)[13] & tcpinfo->flg_mask) - == tcpinfo->flg_cmp, - XT_TCP_INV_FLAGS)) + if (!NF_INVF(tcpinfo, XT_TCP_INV_FLAGS, + (((unsigned char *)th)[13] & tcpinfo->flg_mask) == tcpinfo->flg_cmp)) return false; if (tcpinfo->option) { if (th->doff * 4 < sizeof(_tcph)) { |