diff options
Diffstat (limited to 'net/netfilter')
-rw-r--r-- | net/netfilter/ipset/ip_set_bitmap_ip.c | 4 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_core.c | 7 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_hash_ip.c | 14 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_hash_ipmark.c | 13 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_hash_ipport.c | 13 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_hash_ipportip.c | 13 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_hash_ipportnet.c | 13 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_hash_net.c | 17 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_hash_netiface.c | 15 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_hash_netnet.c | 23 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_hash_netport.c | 19 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_hash_netportnet.c | 40 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto.c | 7 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto_sctp.c | 170 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto_tcp.c | 15 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_standalone.c | 16 | ||||
-rw-r--r-- | net/netfilter/nf_tables_api.c | 261 | ||||
-rw-r--r-- | net/netfilter/nft_payload.c | 2 | ||||
-rw-r--r-- | net/netfilter/nft_set_rbtree.c | 332 |
19 files changed, 562 insertions, 432 deletions
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index a8ce04a4bb72..e4fa00abde6a 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -308,8 +308,8 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], return -IPSET_ERR_BITMAP_RANGE; pr_debug("mask_bits %u, netmask %u\n", mask_bits, netmask); - hosts = 2 << (32 - netmask - 1); - elements = 2 << (netmask - mask_bits - 1); + hosts = 2U << (32 - netmask - 1); + elements = 2UL << (netmask - mask_bits - 1); } if (elements > IPSET_BITMAP_MAX_RANGE + 1) return -IPSET_ERR_BITMAP_RANGE_SIZE; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e7ba5b6dd2b7..46ebee9400da 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1698,9 +1698,10 @@ call_ad(struct net *net, struct sock *ctnl, struct sk_buff *skb, ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); ip_set_unlock(set); retried = true; - } while (ret == -EAGAIN && - set->variant->resize && - (ret = set->variant->resize(set, retried)) == 0); + } while (ret == -ERANGE || + (ret == -EAGAIN && + set->variant->resize && + (ret = set->variant->resize(set, retried)) == 0)); if (!ret || (ret == -IPSET_ERR_EXIST && eexist)) return 0; diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index e30513cefd90..c9f4e3859663 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -100,11 +100,11 @@ static int hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_ip4 *h = set->data; + struct hash_ip4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ip4_elem e = { 0 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0, hosts; + u32 ip = 0, ip_to = 0, hosts, i = 0; int ret = 0; if (tb[IPSET_ATTR_LINENO]) @@ -149,14 +149,14 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); - /* 64bit division is not allowed on 32bit */ - if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) - return -ERANGE; - if (retried) ip = ntohl(h->next.ip); - for (; ip <= ip_to;) { + for (; ip <= ip_to; i++) { e.ip = htonl(ip); + if (i > IPSET_MAX_RANGE) { + hash_ip4_data_next(&h->next, &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index 153de3457423..a22ec1a6f6ec 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -97,11 +97,11 @@ static int hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_ipmark4 *h = set->data; + struct hash_ipmark4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipmark4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip, ip_to = 0; + u32 ip, ip_to = 0, i = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -148,13 +148,14 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ip_set_mask_from_to(ip, ip_to, cidr); } - if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE) - return -ERANGE; - if (retried) ip = ntohl(h->next.ip); - for (; ip <= ip_to; ip++) { + for (; ip <= ip_to; ip++, i++) { e.ip = htonl(ip); + if (i > IPSET_MAX_RANGE) { + hash_ipmark4_data_next(&h->next, &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 2ffbd0b78a8c..e977b5a9c48d 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -112,11 +112,11 @@ static int hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_ipport4 *h = set->data; + struct hash_ipport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip, ip_to = 0, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to, i = 0; bool with_ports = false; int ret; @@ -184,17 +184,18 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } - if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) - return -ERANGE; - if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; - for (; p <= port_to; p++) { + for (; p <= port_to; p++, i++) { e.ip = htonl(ip); e.port = htons(p); + if (i > IPSET_MAX_RANGE) { + hash_ipport4_data_next(&h->next, &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 334fb1ad0e86..39a01934b153 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -108,11 +108,11 @@ static int hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_ipportip4 *h = set->data; + struct hash_ipportip4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip, ip_to = 0, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to, i = 0; bool with_ports = false; int ret; @@ -180,17 +180,18 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } - if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) - return -ERANGE; - if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; - for (; p <= port_to; p++) { + for (; p <= port_to; p++, i++) { e.ip = htonl(ip); e.port = htons(p); + if (i > IPSET_MAX_RANGE) { + hash_ipportip4_data_next(&h->next, &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 7df94f437f60..5c6de605a9fb 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -160,12 +160,12 @@ static int hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_ipportnet4 *h = set->data; + struct hash_ipportnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, p = 0, port, port_to; - u32 ip2_from = 0, ip2_to = 0, ip2; + u32 ip2_from = 0, ip2_to = 0, ip2, i = 0; bool with_ports = false; u8 cidr; int ret; @@ -253,9 +253,6 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } - if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) - return -ERANGE; - ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); @@ -282,9 +279,15 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], for (; p <= port_to; p++) { e.port = htons(p); do { + i++; e.ip2 = htonl(ip2); ip2 = ip_set_range_to_cidr(ip2, ip2_to, &cidr); e.cidr = cidr - 1; + if (i > IPSET_MAX_RANGE) { + hash_ipportnet4_data_next(&h->next, + &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 1422739d9aa2..ce0a9ce5a91f 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -136,11 +136,11 @@ static int hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_net4 *h = set->data; + struct hash_net4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { .cidr = HOST_MASK }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0, ipn, n = 0; + u32 ip = 0, ip_to = 0, i = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -188,19 +188,16 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } - ipn = ip; - do { - ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); - n++; - } while (ipn++ < ip_to); - - if (n > IPSET_MAX_RANGE) - return -ERANGE; if (retried) ip = ntohl(h->next.ip); do { + i++; e.ip = htonl(ip); + if (i > IPSET_MAX_RANGE) { + hash_net4_data_next(&h->next, &e); + return -ERANGE; + } ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 9810f5bf63f5..031073286236 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -202,7 +202,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0, ipn, n = 0; + u32 ip = 0, ip_to = 0, i = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -256,19 +256,16 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr); } - ipn = ip; - do { - ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); - n++; - } while (ipn++ < ip_to); - - if (n > IPSET_MAX_RANGE) - return -ERANGE; if (retried) ip = ntohl(h->next.ip); do { + i++; e.ip = htonl(ip); + if (i > IPSET_MAX_RANGE) { + hash_netiface4_data_next(&h->next, &e); + return -ERANGE; + } ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index cdfb78c6e0d3..8fbe649c9dd3 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -166,13 +166,12 @@ static int hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_netnet4 *h = set->data; + struct hash_netnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0; - u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn; - u64 n = 0, m = 0; + u32 ip2 = 0, ip2_from = 0, ip2_to = 0, i = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -248,19 +247,6 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } - ipn = ip; - do { - ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); - n++; - } while (ipn++ < ip_to); - ipn = ip2_from; - do { - ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); - m++; - } while (ipn++ < ip2_to); - - if (n*m > IPSET_MAX_RANGE) - return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); @@ -273,7 +259,12 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], e.ip[0] = htonl(ip); ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); do { + i++; e.ip[1] = htonl(ip2); + if (i > IPSET_MAX_RANGE) { + hash_netnet4_data_next(&h->next, &e); + return -ERANGE; + } ip2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 09cf72eb37f8..d1a0628df4ef 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -154,12 +154,11 @@ static int hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_netport4 *h = set->data; + struct hash_netport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn; - u64 n = 0; + u32 port, port_to, p = 0, ip = 0, ip_to = 0, i = 0; bool with_ports = false; u8 cidr; int ret; @@ -236,14 +235,6 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); } - ipn = ip; - do { - ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr); - n++; - } while (ipn++ < ip_to); - - if (n*(port_to - port + 1) > IPSET_MAX_RANGE) - return -ERANGE; if (retried) { ip = ntohl(h->next.ip); @@ -255,8 +246,12 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], e.ip = htonl(ip); ip = ip_set_range_to_cidr(ip, ip_to, &cidr); e.cidr = cidr - 1; - for (; p <= port_to; p++) { + for (; p <= port_to; p++, i++) { e.port = htons(p); + if (i > IPSET_MAX_RANGE) { + hash_netport4_data_next(&h->next, &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 19bcdb3141f6..005a7ce87217 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -173,17 +173,26 @@ hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } +static u32 +hash_netportnet4_range_to_cidr(u32 from, u32 to, u8 *cidr) +{ + if (from == 0 && to == UINT_MAX) { + *cidr = 0; + return to; + } + return ip_set_range_to_cidr(from, to, cidr); +} + static int hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_netportnet4 *h = set->data; + struct hash_netportnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, p = 0, port, port_to; - u32 ip2_from = 0, ip2_to = 0, ip2, ipn; - u64 n = 0, m = 0; + u32 ip2_from = 0, ip2_to = 0, ip2, i = 0; bool with_ports = false; int ret; @@ -285,19 +294,6 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } - ipn = ip; - do { - ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); - n++; - } while (ipn++ < ip_to); - ipn = ip2_from; - do { - ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); - m++; - } while (ipn++ < ip2_to); - - if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE) - return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); @@ -310,13 +306,19 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], do { e.ip[0] = htonl(ip); - ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); + ip = hash_netportnet4_range_to_cidr(ip, ip_to, &e.cidr[0]); for (; p <= port_to; p++) { e.port = htons(p); do { + i++; e.ip[1] = htonl(ip2); - ip2 = ip_set_range_to_cidr(ip2, ip2_to, - &e.cidr[1]); + if (i > IPSET_MAX_RANGE) { + hash_netportnet4_data_next(&h->next, + &e); + return -ERANGE; + } + ip2 = hash_netportnet4_range_to_cidr(ip2, + ip2_to, &e.cidr[1]); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 99323fb12d0f..ccef340be575 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -141,6 +141,7 @@ unsigned int nf_confirm(void *priv, struct nf_conn *ct; bool seqadj_needed; __be16 frag_off; + int start; u8 pnum; ct = nf_ct_get(skb, &ctinfo); @@ -163,9 +164,11 @@ unsigned int nf_confirm(void *priv, break; case NFPROTO_IPV6: pnum = ipv6_hdr(skb)->nexthdr; - protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off); - if (protoff < 0 || (frag_off & htons(~0x7)) != 0) + start = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off); + if (start < 0 || (frag_off & htons(~0x7)) != 0) return nf_conntrack_confirm(skb); + + protoff = start; break; default: return nf_conntrack_confirm(skb); diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index d88b92a8ffca..945dd40e7077 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -27,22 +27,16 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_timeout.h> -/* FIXME: Examine ipfilter's timeouts and conntrack transitions more - closely. They're more complex. --RR - - And so for me for SCTP :D -Kiran */ - static const char *const sctp_conntrack_names[] = { - "NONE", - "CLOSED", - "COOKIE_WAIT", - "COOKIE_ECHOED", - "ESTABLISHED", - "SHUTDOWN_SENT", - "SHUTDOWN_RECD", - "SHUTDOWN_ACK_SENT", - "HEARTBEAT_SENT", - "HEARTBEAT_ACKED", + [SCTP_CONNTRACK_NONE] = "NONE", + [SCTP_CONNTRACK_CLOSED] = "CLOSED", + [SCTP_CONNTRACK_COOKIE_WAIT] = "COOKIE_WAIT", + [SCTP_CONNTRACK_COOKIE_ECHOED] = "COOKIE_ECHOED", + [SCTP_CONNTRACK_ESTABLISHED] = "ESTABLISHED", + [SCTP_CONNTRACK_SHUTDOWN_SENT] = "SHUTDOWN_SENT", + [SCTP_CONNTRACK_SHUTDOWN_RECD] = "SHUTDOWN_RECD", + [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = "SHUTDOWN_ACK_SENT", + [SCTP_CONNTRACK_HEARTBEAT_SENT] = "HEARTBEAT_SENT", }; #define SECS * HZ @@ -54,13 +48,11 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_CLOSED] = 10 SECS, [SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS, [SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS, - [SCTP_CONNTRACK_ESTABLISHED] = 5 DAYS, + [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS, [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, - [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, - [SCTP_CONNTRACK_DATA_SENT] = 30 SECS, }; #define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 @@ -74,8 +66,6 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { #define sSR SCTP_CONNTRACK_SHUTDOWN_RECD #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT #define sHS SCTP_CONNTRACK_HEARTBEAT_SENT -#define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED -#define sDS SCTP_CONNTRACK_DATA_SENT #define sIV SCTP_CONNTRACK_MAX /* @@ -98,10 +88,6 @@ SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of the SHUTDOWN chunk. Connection is closed. HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow. -HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK/DATA/SACK in the direction - opposite to that of the HEARTBEAT/DATA chunk. Secondary connection - is established. -DATA_SENT - We have seen a DATA/SACK in a new flow. */ /* TODO @@ -115,38 +101,36 @@ cookie echoed to closed. */ /* SCTP conntrack state transitions */ -static const u8 sctp_conntracks[2][12][SCTP_CONNTRACK_MAX] = { +static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */ -/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA, sCW}, -/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL}, -/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS, sCL}, -/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA, sSA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't have Stale cookie*/ -/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't come in orig dir */ -/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA, sCL}, -/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}, -/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}, -/* data/sack */ {sDS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ +/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW}, +/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL}, +/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, +/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL}, +/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA}, +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/ +/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ +/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL}, +/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, +/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, }, { /* REPLY */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */ -/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV}, -/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL, sIV}, -/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR, sIV}, -/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA, sIV}, -/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA, sIV}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* Can't come in reply dir */ -/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA, sIV}, -/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA, sIV}, -/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sHA}, -/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA}, -/* data/sack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA}, +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ +/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* INIT in sCL Big TODO */ +/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV}, +/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV}, +/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV}, +/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV}, +/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV}, +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ +/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV}, +/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV}, +/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, +/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sES}, } }; @@ -160,8 +144,8 @@ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) #define for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count) \ for ((offset) = (dataoff) + sizeof(struct sctphdr), (count) = 0; \ - (offset) < (skb)->len && \ - ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))); \ + ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))) && \ + (sch)->length; \ (offset) += (ntohs((sch)->length) + 3) & ~3, (count)++) /* Some validity checks to make sure the chunks are fine */ @@ -258,11 +242,6 @@ static int sctp_new_state(enum ip_conntrack_dir dir, pr_debug("SCTP_CID_HEARTBEAT_ACK"); i = 10; break; - case SCTP_CID_DATA: - case SCTP_CID_SACK: - pr_debug("SCTP_CID_DATA/SACK"); - i = 11; - break; default: /* Other chunks like DATA or SACK do not change the state */ pr_debug("Unknown chunk type, Will stay in %s\n", @@ -316,9 +295,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, ih->init_tag); ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag; - } else if (sch->type == SCTP_CID_HEARTBEAT || - sch->type == SCTP_CID_DATA || - sch->type == SCTP_CID_SACK) { + } else if (sch->type == SCTP_CID_HEARTBEAT) { pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; @@ -404,19 +381,19 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, if (!sctp_new(ct, skb, sh, dataoff)) return -NF_ACCEPT; - } else { - /* Check the verification tag (Sec 8.5) */ - if (!test_bit(SCTP_CID_INIT, map) && - !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) && - !test_bit(SCTP_CID_COOKIE_ECHO, map) && - !test_bit(SCTP_CID_ABORT, map) && - !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && - !test_bit(SCTP_CID_HEARTBEAT, map) && - !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && - sh->vtag != ct->proto.sctp.vtag[dir]) { - pr_debug("Verification tag check failed\n"); - goto out; - } + } + + /* Check the verification tag (Sec 8.5) */ + if (!test_bit(SCTP_CID_INIT, map) && + !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) && + !test_bit(SCTP_CID_COOKIE_ECHO, map) && + !test_bit(SCTP_CID_ABORT, map) && + !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && + !test_bit(SCTP_CID_HEARTBEAT, map) && + !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && + sh->vtag != ct->proto.sctp.vtag[dir]) { + pr_debug("Verification tag check failed\n"); + goto out; } old_state = new_state = SCTP_CONNTRACK_NONE; @@ -424,22 +401,29 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { /* Special cases of Verification tag check (Sec 8.5.1) */ if (sch->type == SCTP_CID_INIT) { - /* Sec 8.5.1 (A) */ + /* (A) vtag MUST be zero */ if (sh->vtag != 0) goto out_unlock; } else if (sch->type == SCTP_CID_ABORT) { - /* Sec 8.5.1 (B) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir]) + /* (B) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_SHUTDOWN_COMPLETE) { - /* Sec 8.5.1 (C) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir] && - sch->flags & SCTP_CHUNK_FLAG_T) + /* (C) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_COOKIE_ECHO) { - /* Sec 8.5.1 (D) */ + /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; } else if (sch->type == SCTP_CID_HEARTBEAT) { @@ -476,11 +460,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; } - } else if (sch->type == SCTP_CID_DATA || sch->type == SCTP_CID_SACK) { - if (ct->proto.sctp.vtag[dir] == 0) { - pr_debug("Setting vtag %x for dir %d\n", sh->vtag, dir); - ct->proto.sctp.vtag[dir] = sh->vtag; - } } old_state = ct->proto.sctp.state; @@ -518,8 +497,12 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } ct->proto.sctp.state = new_state; - if (old_state != new_state) + if (old_state != new_state) { nf_conntrack_event_cache(IPCT_PROTOINFO, ct); + if (new_state == SCTP_CONNTRACK_ESTABLISHED && + !test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) + nf_conntrack_event_cache(IPCT_ASSURED, ct); + } } spin_unlock_bh(&ct->lock); @@ -533,14 +516,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); - if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED && - dir == IP_CT_DIR_REPLY && - new_state == SCTP_CONNTRACK_ESTABLISHED) { - pr_debug("Setting assured bit\n"); - set_bit(IPS_ASSURED_BIT, &ct->status); - nf_conntrack_event_cache(IPCT_ASSURED, ct); - } - return NF_ACCEPT; out_unlock: @@ -701,7 +676,6 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, - [CTA_TIMEOUT_SCTP_DATA_SENT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 656631083177..3ac1af6f59fc 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1068,6 +1068,13 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, ct->proto.tcp.last_flags |= IP_CT_EXP_CHALLENGE_ACK; } + + /* possible challenge ack reply to syn */ + if (old_state == TCP_CONNTRACK_SYN_SENT && + index == TCP_ACK_SET && + dir == IP_CT_DIR_REPLY) + ct->proto.tcp.last_ack = ntohl(th->ack_seq); + spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "packet (index %d) in dir %d ignored, state %s", @@ -1193,6 +1200,14 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, * segments we ignored. */ goto in_window; } + + /* Reset in response to a challenge-ack we let through earlier */ + if (old_state == TCP_CONNTRACK_SYN_SENT && + ct->proto.tcp.last_index == TCP_ACK_SET && + ct->proto.tcp.last_dir == IP_CT_DIR_REPLY && + ntohl(th->seq) == ct->proto.tcp.last_ack) + goto in_window; + break; default: /* Keep compilers happy. */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 0250725e38a4..460294bd4b60 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -601,8 +601,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT, - NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED, - NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST, @@ -887,18 +885,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { - .procname = "nf_conntrack_sctp_timeout_heartbeat_acked", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT] = { - .procname = "nf_conntrack_sctp_timeout_data_sent", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = { @@ -1042,8 +1028,6 @@ static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, XASSIGN(SHUTDOWN_RECD, sn); XASSIGN(SHUTDOWN_ACK_SENT, sn); XASSIGN(HEARTBEAT_SENT, sn); - XASSIGN(HEARTBEAT_ACKED, sn); - XASSIGN(DATA_SENT, sn); #undef XASSIGN #endif } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 832b881f7c17..8c09e4d12ac1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -465,8 +465,9 @@ static int nft_delrule_by_chain(struct nft_ctx *ctx) return 0; } -static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, - struct nft_set *set) +static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, + struct nft_set *set, + const struct nft_set_desc *desc) { struct nft_trans *trans; @@ -474,17 +475,28 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, if (trans == NULL) return -ENOMEM; - if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] != NULL) { + if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] && !desc) { nft_trans_set_id(trans) = ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID])); nft_activate_next(ctx->net, set); } nft_trans_set(trans) = set; + if (desc) { + nft_trans_set_update(trans) = true; + nft_trans_set_gc_int(trans) = desc->gc_int; + nft_trans_set_timeout(trans) = desc->timeout; + } nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } +static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, + struct nft_set *set) +{ + return __nft_trans_set_add(ctx, msg_type, set, NULL); +} + static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) { int err; @@ -3780,8 +3792,7 @@ static bool nft_set_ops_candidate(const struct nft_set_type *type, u32 flags) static const struct nft_set_ops * nft_select_set_ops(const struct nft_ctx *ctx, const struct nlattr * const nla[], - const struct nft_set_desc *desc, - enum nft_set_policies policy) + const struct nft_set_desc *desc) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nft_set_ops *ops, *bops; @@ -3810,7 +3821,7 @@ nft_select_set_ops(const struct nft_ctx *ctx, if (!ops->estimate(desc, flags, &est)) continue; - switch (policy) { + switch (desc->policy) { case NFT_SET_POL_PERFORMANCE: if (est.lookup < best.lookup) break; @@ -4045,8 +4056,10 @@ static int nf_tables_fill_set_concat(struct sk_buff *skb, static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, const struct nft_set *set, u16 event, u16 flags) { - struct nlmsghdr *nlh; + u64 timeout = READ_ONCE(set->timeout); + u32 gc_int = READ_ONCE(set->gc_int); u32 portid = ctx->portid; + struct nlmsghdr *nlh; struct nlattr *nest; u32 seq = ctx->seq; int i; @@ -4082,13 +4095,13 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, nla_put_be32(skb, NFTA_SET_OBJ_TYPE, htonl(set->objtype))) goto nla_put_failure; - if (set->timeout && + if (timeout && nla_put_be64(skb, NFTA_SET_TIMEOUT, - nf_jiffies64_to_msecs(set->timeout), + nf_jiffies64_to_msecs(timeout), NFTA_SET_PAD)) goto nla_put_failure; - if (set->gc_int && - nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(set->gc_int))) + if (gc_int && + nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(gc_int))) goto nla_put_failure; if (set->policy != NFT_SET_POL_PERFORMANCE) { @@ -4389,15 +4402,94 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc, return err; } +static int nft_set_expr_alloc(struct nft_ctx *ctx, struct nft_set *set, + const struct nlattr * const *nla, + struct nft_expr **exprs, int *num_exprs, + u32 flags) +{ + struct nft_expr *expr; + int err, i; + + if (nla[NFTA_SET_EXPR]) { + expr = nft_set_elem_expr_alloc(ctx, set, nla[NFTA_SET_EXPR]); + if (IS_ERR(expr)) { + err = PTR_ERR(expr); + goto err_set_expr_alloc; + } + exprs[0] = expr; + (*num_exprs)++; + } else if (nla[NFTA_SET_EXPRESSIONS]) { + struct nlattr *tmp; + int left; + + if (!(flags & NFT_SET_EXPR)) { + err = -EINVAL; + goto err_set_expr_alloc; + } + i = 0; + nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { + if (i == NFT_SET_EXPR_MAX) { + err = -E2BIG; + goto err_set_expr_alloc; + } + if (nla_type(tmp) != NFTA_LIST_ELEM) { + err = -EINVAL; + goto err_set_expr_alloc; + } + expr = nft_set_elem_expr_alloc(ctx, set, tmp); + if (IS_ERR(expr)) { + err = PTR_ERR(expr); + goto err_set_expr_alloc; + } + exprs[i++] = expr; + (*num_exprs)++; + } + } + + return 0; + +err_set_expr_alloc: + for (i = 0; i < *num_exprs; i++) + nft_expr_destroy(ctx, exprs[i]); + + return err; +} + +static bool nft_set_is_same(const struct nft_set *set, + const struct nft_set_desc *desc, + struct nft_expr *exprs[], u32 num_exprs, u32 flags) +{ + int i; + + if (set->ktype != desc->ktype || + set->dtype != desc->dtype || + set->flags != flags || + set->klen != desc->klen || + set->dlen != desc->dlen || + set->field_count != desc->field_count || + set->num_exprs != num_exprs) + return false; + + for (i = 0; i < desc->field_count; i++) { + if (set->field_len[i] != desc->field_len[i]) + return false; + } + + for (i = 0; i < num_exprs; i++) { + if (set->exprs[i]->ops != exprs[i]->ops) + return false; + } + + return true; +} + static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - u32 ktype, dtype, flags, policy, gc_int, objtype; struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_set_ops *ops; - struct nft_expr *expr = NULL; struct net *net = info->net; struct nft_set_desc desc; struct nft_table *table; @@ -4405,10 +4497,11 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, struct nft_set *set; struct nft_ctx ctx; size_t alloc_size; - u64 timeout; + int num_exprs = 0; char *name; int err, i; u16 udlen; + u32 flags; u64 size; if (nla[NFTA_SET_TABLE] == NULL || @@ -4419,10 +4512,10 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, memset(&desc, 0, sizeof(desc)); - ktype = NFT_DATA_VALUE; + desc.ktype = NFT_DATA_VALUE; if (nla[NFTA_SET_KEY_TYPE] != NULL) { - ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE])); - if ((ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK) + desc.ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE])); + if ((desc.ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK) return -EINVAL; } @@ -4447,17 +4540,17 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, return -EOPNOTSUPP; } - dtype = 0; + desc.dtype = 0; if (nla[NFTA_SET_DATA_TYPE] != NULL) { if (!(flags & NFT_SET_MAP)) return -EINVAL; - dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE])); - if ((dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK && - dtype != NFT_DATA_VERDICT) + desc.dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE])); + if ((desc.dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK && + desc.dtype != NFT_DATA_VERDICT) return -EINVAL; - if (dtype != NFT_DATA_VERDICT) { + if (desc.dtype != NFT_DATA_VERDICT) { if (nla[NFTA_SET_DATA_LEN] == NULL) return -EINVAL; desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN])); @@ -4472,34 +4565,34 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (!(flags & NFT_SET_OBJECT)) return -EINVAL; - objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE])); - if (objtype == NFT_OBJECT_UNSPEC || - objtype > NFT_OBJECT_MAX) + desc.objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE])); + if (desc.objtype == NFT_OBJECT_UNSPEC || + desc.objtype > NFT_OBJECT_MAX) return -EOPNOTSUPP; } else if (flags & NFT_SET_OBJECT) return -EINVAL; else - objtype = NFT_OBJECT_UNSPEC; + desc.objtype = NFT_OBJECT_UNSPEC; - timeout = 0; + desc.timeout = 0; if (nla[NFTA_SET_TIMEOUT] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; - err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &timeout); + err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout); if (err) return err; } - gc_int = 0; + desc.gc_int = 0; if (nla[NFTA_SET_GC_INTERVAL] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; - gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL])); + desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL])); } - policy = NFT_SET_POL_PERFORMANCE; + desc.policy = NFT_SET_POL_PERFORMANCE; if (nla[NFTA_SET_POLICY] != NULL) - policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY])); + desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY])); if (nla[NFTA_SET_DESC] != NULL) { err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]); @@ -4531,6 +4624,8 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, return PTR_ERR(set); } } else { + struct nft_expr *exprs[NFT_SET_EXPR_MAX] = {}; + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return -EEXIST; @@ -4538,13 +4633,29 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - return 0; + err = nft_set_expr_alloc(&ctx, set, nla, exprs, &num_exprs, flags); + if (err < 0) + return err; + + err = 0; + if (!nft_set_is_same(set, &desc, exprs, num_exprs, flags)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); + err = -EEXIST; + } + + for (i = 0; i < num_exprs; i++) + nft_expr_destroy(&ctx, exprs[i]); + + if (err < 0) + return err; + + return __nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set, &desc); } if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; - ops = nft_select_set_ops(&ctx, nla, &desc, policy); + ops = nft_select_set_ops(&ctx, nla, &desc); if (IS_ERR(ops)) return PTR_ERR(ops); @@ -4584,18 +4695,18 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, set->table = table; write_pnet(&set->net, net); set->ops = ops; - set->ktype = ktype; + set->ktype = desc.ktype; set->klen = desc.klen; - set->dtype = dtype; - set->objtype = objtype; + set->dtype = desc.dtype; + set->objtype = desc.objtype; set->dlen = desc.dlen; set->flags = flags; set->size = desc.size; - set->policy = policy; + set->policy = desc.policy; set->udlen = udlen; set->udata = udata; - set->timeout = timeout; - set->gc_int = gc_int; + set->timeout = desc.timeout; + set->gc_int = desc.gc_int; set->field_count = desc.field_count; for (i = 0; i < desc.field_count; i++) @@ -4605,43 +4716,11 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (err < 0) goto err_set_init; - if (nla[NFTA_SET_EXPR]) { - expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]); - if (IS_ERR(expr)) { - err = PTR_ERR(expr); - goto err_set_expr_alloc; - } - set->exprs[0] = expr; - set->num_exprs++; - } else if (nla[NFTA_SET_EXPRESSIONS]) { - struct nft_expr *expr; - struct nlattr *tmp; - int left; - - if (!(flags & NFT_SET_EXPR)) { - err = -EINVAL; - goto err_set_expr_alloc; - } - i = 0; - nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { - if (i == NFT_SET_EXPR_MAX) { - err = -E2BIG; - goto err_set_expr_alloc; - } - if (nla_type(tmp) != NFTA_LIST_ELEM) { - err = -EINVAL; - goto err_set_expr_alloc; - } - expr = nft_set_elem_expr_alloc(&ctx, set, tmp); - if (IS_ERR(expr)) { - err = PTR_ERR(expr); - goto err_set_expr_alloc; - } - set->exprs[i++] = expr; - set->num_exprs++; - } - } + err = nft_set_expr_alloc(&ctx, set, nla, set->exprs, &num_exprs, flags); + if (err < 0) + goto err_set_destroy; + set->num_exprs = num_exprs; set->handle = nf_tables_alloc_handle(table); err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); @@ -4655,7 +4734,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, err_set_expr_alloc: for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(&ctx, set->exprs[i]); - +err_set_destroy: ops->destroy(set); err_set_init: kfree(set->name); @@ -6008,7 +6087,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; } else if (set->flags & NFT_SET_TIMEOUT && !(flags & NFT_SET_ELEM_INTERVAL_END)) { - timeout = set->timeout; + timeout = READ_ONCE(set->timeout); } expiration = 0; @@ -6109,7 +6188,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_parse_key_end; - if (timeout != set->timeout) { + if (timeout != READ_ONCE(set->timeout)) { err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); if (err < 0) goto err_parse_key_end; @@ -9031,14 +9110,20 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_NEWSET: - nft_clear(net, nft_trans_set(trans)); - /* This avoids hitting -EBUSY when deleting the table - * from the transaction. - */ - if (nft_set_is_anonymous(nft_trans_set(trans)) && - !list_empty(&nft_trans_set(trans)->bindings)) - trans->ctx.table->use--; + if (nft_trans_set_update(trans)) { + struct nft_set *set = nft_trans_set(trans); + WRITE_ONCE(set->timeout, nft_trans_set_timeout(trans)); + WRITE_ONCE(set->gc_int, nft_trans_set_gc_int(trans)); + } else { + nft_clear(net, nft_trans_set(trans)); + /* This avoids hitting -EBUSY when deleting the table + * from the transaction. + */ + if (nft_set_is_anonymous(nft_trans_set(trans)) && + !list_empty(&nft_trans_set(trans)->bindings)) + trans->ctx.table->use--; + } nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), NFT_MSG_NEWSET, GFP_KERNEL); nft_trans_destroy(trans); @@ -9260,6 +9345,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: + if (nft_trans_set_update(trans)) { + nft_trans_destroy(trans); + break; + } trans->ctx.table->use--; if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 17b418a5a593..3a3c7746e88f 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -63,7 +63,7 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) return false; if (offset + len > VLAN_ETH_HLEN + vlan_hlen) - ethlen -= offset + len - VLAN_ETH_HLEN + vlan_hlen; + ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen; memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 7325bee7d144..19ea4d3c3553 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -38,10 +38,12 @@ static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe) return !nft_rbtree_interval_end(rbe); } -static bool nft_rbtree_equal(const struct nft_set *set, const void *this, - const struct nft_rbtree_elem *interval) +static int nft_rbtree_cmp(const struct nft_set *set, + const struct nft_rbtree_elem *e1, + const struct nft_rbtree_elem *e2) { - return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0; + return memcmp(nft_set_ext_key(&e1->ext), nft_set_ext_key(&e2->ext), + set->klen); } static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, @@ -52,7 +54,6 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set const struct nft_rbtree_elem *rbe, *interval = NULL; u8 genmask = nft_genmask_cur(net); const struct rb_node *parent; - const void *this; int d; parent = rcu_dereference_raw(priv->root.rb_node); @@ -62,12 +63,11 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set rbe = rb_entry(parent, struct nft_rbtree_elem, node); - this = nft_set_ext_key(&rbe->ext); - d = memcmp(this, key, set->klen); + d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen); if (d < 0) { parent = rcu_dereference_raw(parent->rb_left); if (interval && - nft_rbtree_equal(set, this, interval) && + !nft_rbtree_cmp(set, rbe, interval) && nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(interval)) continue; @@ -215,154 +215,216 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, return rbe; } +static int nft_rbtree_gc_elem(const struct nft_set *__set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + struct nft_set *set = (struct nft_set *)__set; + struct rb_node *prev = rb_prev(&rbe->node); + struct nft_rbtree_elem *rbe_prev; + struct nft_set_gc_batch *gcb; + + gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); + if (!gcb) + return -ENOMEM; + + /* search for expired end interval coming before this element. */ + do { + rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); + if (nft_rbtree_interval_end(rbe_prev)) + break; + + prev = rb_prev(prev); + } while (prev != NULL); + + rb_erase(&rbe_prev->node, &priv->root); + rb_erase(&rbe->node, &priv->root); + atomic_sub(2, &set->nelems); + + nft_set_gc_batch_add(gcb, rbe); + nft_set_gc_batch_complete(gcb); + + return 0; +} + +static bool nft_rbtree_update_first(const struct nft_set *set, + struct nft_rbtree_elem *rbe, + struct rb_node *first) +{ + struct nft_rbtree_elem *first_elem; + + first_elem = rb_entry(first, struct nft_rbtree_elem, node); + /* this element is closest to where the new element is to be inserted: + * update the first element for the node list path. + */ + if (nft_rbtree_cmp(set, rbe, first_elem) < 0) + return true; + + return false; +} + static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, struct nft_set_ext **ext) { - bool overlap = false, dup_end_left = false, dup_end_right = false; + struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; + struct rb_node *node, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); - struct nft_rbtree_elem *rbe; - struct rb_node *parent, **p; - int d; + int d, err; - /* Detect overlaps as we descend the tree. Set the flag in these cases: - * - * a1. _ _ __>| ?_ _ __| (insert end before existing end) - * a2. _ _ ___| ?_ _ _>| (insert end after existing end) - * a3. _ _ ___? >|_ _ __| (insert start before existing end) - * - * and clear it later on, as we eventually reach the points indicated by - * '?' above, in the cases described below. We'll always meet these - * later, locally, due to tree ordering, and overlaps for the intervals - * that are the closest together are always evaluated last. - * - * b1. _ _ __>| !_ _ __| (insert end before existing start) - * b2. _ _ ___| !_ _ _>| (insert end after existing start) - * b3. _ _ ___! >|_ _ __| (insert start after existing end, as a leaf) - * '--' no nodes falling in this range - * b4. >|_ _ ! (insert start before existing start) - * - * Case a3. resolves to b3.: - * - if the inserted start element is the leftmost, because the '0' - * element in the tree serves as end element - * - otherwise, if an existing end is found immediately to the left. If - * there are existing nodes in between, we need to further descend the - * tree before we can conclude the new start isn't causing an overlap - * - * or to b4., which, preceded by a3., means we already traversed one or - * more existing intervals entirely, from the right. - * - * For a new, rightmost pair of elements, we'll hit cases b3. and b2., - * in that order. - * - * The flag is also cleared in two special cases: - * - * b5. |__ _ _!|<_ _ _ (insert start right before existing end) - * b6. |__ _ >|!__ _ _ (insert end right after existing start) - * - * which always happen as last step and imply that no further - * overlapping is possible. - * - * Another special case comes from the fact that start elements matching - * an already existing start element are allowed: insertion is not - * performed but we return -EEXIST in that case, and the error will be - * cleared by the caller if NLM_F_EXCL is not present in the request. - * This way, request for insertion of an exact overlap isn't reported as - * error to userspace if not desired. - * - * However, if the existing start matches a pre-existing start, but the - * end element doesn't match the corresponding pre-existing end element, - * we need to report a partial overlap. This is a local condition that - * can be noticed without need for a tracking flag, by checking for a - * local duplicated end for a corresponding start, from left and right, - * separately. + /* Descend the tree to search for an existing element greater than the + * key value to insert that is greater than the new element. This is the + * first element to walk the ordered elements to find possible overlap. */ - parent = NULL; p = &priv->root.rb_node; while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); - d = memcmp(nft_set_ext_key(&rbe->ext), - nft_set_ext_key(&new->ext), - set->klen); + d = nft_rbtree_cmp(set, rbe, new); + if (d < 0) { p = &parent->rb_left; - - if (nft_rbtree_interval_start(new)) { - if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext) && !*p) - overlap = false; - } else { - if (dup_end_left && !*p) - return -ENOTEMPTY; - - overlap = nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, - genmask) && - !nft_set_elem_expired(&rbe->ext); - - if (overlap) { - dup_end_right = true; - continue; - } - } } else if (d > 0) { - p = &parent->rb_right; + if (!first || + nft_rbtree_update_first(set, rbe, first)) + first = &rbe->node; - if (nft_rbtree_interval_end(new)) { - if (dup_end_right && !*p) - return -ENOTEMPTY; - - overlap = nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, - genmask) && - !nft_set_elem_expired(&rbe->ext); - - if (overlap) { - dup_end_left = true; - continue; - } - } else if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) { - overlap = nft_rbtree_interval_end(rbe); - } + p = &parent->rb_right; } else { - if (nft_rbtree_interval_end(rbe) && - nft_rbtree_interval_start(new)) { + if (nft_rbtree_interval_end(rbe)) p = &parent->rb_left; - - if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) - overlap = false; - } else if (nft_rbtree_interval_start(rbe) && - nft_rbtree_interval_end(new)) { + else p = &parent->rb_right; + } + } + + if (!first) + first = rb_first(&priv->root); + + /* Detect overlap by going through the list of valid tree nodes. + * Values stored in the tree are in reversed order, starting from + * highest to lowest value. + */ + for (node = first; node != NULL; node = rb_next(node)) { + rbe = rb_entry(node, struct nft_rbtree_elem, node); - if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) - overlap = false; - } else if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) { - *ext = &rbe->ext; - return -EEXIST; - } else { - overlap = false; - if (nft_rbtree_interval_end(rbe)) - p = &parent->rb_left; - else - p = &parent->rb_right; + if (!nft_set_elem_active(&rbe->ext, genmask)) + continue; + + /* perform garbage collection to avoid bogus overlap reports. */ + if (nft_set_elem_expired(&rbe->ext)) { + err = nft_rbtree_gc_elem(set, priv, rbe); + if (err < 0) + return err; + + continue; + } + + d = nft_rbtree_cmp(set, rbe, new); + if (d == 0) { + /* Matching end element: no need to look for an + * overlapping greater or equal element. + */ + if (nft_rbtree_interval_end(rbe)) { + rbe_le = rbe; + break; + } + + /* first element that is greater or equal to key value. */ + if (!rbe_ge) { + rbe_ge = rbe; + continue; + } + + /* this is a closer more or equal element, update it. */ + if (nft_rbtree_cmp(set, rbe_ge, new) != 0) { + rbe_ge = rbe; + continue; + } + + /* element is equal to key value, make sure flags are + * the same, an existing more or equal start element + * must not be replaced by more or equal end element. + */ + if ((nft_rbtree_interval_start(new) && + nft_rbtree_interval_start(rbe_ge)) || + (nft_rbtree_interval_end(new) && + nft_rbtree_interval_end(rbe_ge))) { + rbe_ge = rbe; + continue; } + } else if (d > 0) { + /* annotate element greater than the new element. */ + rbe_ge = rbe; + continue; + } else if (d < 0) { + /* annotate element less than the new element. */ + rbe_le = rbe; + break; } + } - dup_end_left = dup_end_right = false; + /* - new start element matching existing start element: full overlap + * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. + */ + if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) && + nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) { + *ext = &rbe_ge->ext; + return -EEXIST; } - if (overlap) + /* - new end element matching existing end element: full overlap + * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. + */ + if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) && + nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) { + *ext = &rbe_le->ext; + return -EEXIST; + } + + /* - new start element with existing closest, less or equal key value + * being a start element: partial overlap, reported as -ENOTEMPTY. + * Anonymous sets allow for two consecutive start element since they + * are constant, skip them to avoid bogus overlap reports. + */ + if (!nft_set_is_anonymous(set) && rbe_le && + nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new)) + return -ENOTEMPTY; + + /* - new end element with existing closest, less or equal key value + * being a end element: partial overlap, reported as -ENOTEMPTY. + */ + if (rbe_le && + nft_rbtree_interval_end(rbe_le) && nft_rbtree_interval_end(new)) return -ENOTEMPTY; + /* - new end element with existing closest, greater or equal key value + * being an end element: partial overlap, reported as -ENOTEMPTY + */ + if (rbe_ge && + nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new)) + return -ENOTEMPTY; + + /* Accepted element: pick insertion point depending on key value */ + parent = NULL; + p = &priv->root.rb_node; + while (*p != NULL) { + parent = *p; + rbe = rb_entry(parent, struct nft_rbtree_elem, node); + d = nft_rbtree_cmp(set, rbe, new); + + if (d < 0) + p = &parent->rb_left; + else if (d > 0) + p = &parent->rb_right; + else if (nft_rbtree_interval_end(rbe)) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + rb_link_node_rcu(&new->node, parent, p); rb_insert_color(&new->node, &priv->root); return 0; @@ -501,23 +563,37 @@ static void nft_rbtree_gc(struct work_struct *work) struct nft_rbtree *priv; struct rb_node *node; struct nft_set *set; + struct net *net; + u8 genmask; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + genmask = nft_genmask_cur(net); write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { rbe = rb_entry(node, struct nft_rbtree_elem, node); + if (!nft_set_elem_active(&rbe->ext, genmask)) + continue; + + /* elements are reversed in the rbtree for historical reasons, + * from highest to lowest value, that is why end element is + * always visited before the start element. + */ if (nft_rbtree_interval_end(rbe)) { rbe_end = rbe; continue; } if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) + + if (nft_set_elem_mark_busy(&rbe->ext)) { + rbe_end = NULL; continue; + } if (rbe_prev) { rb_erase(&rbe_prev->node, &priv->root); |