diff options
60 files changed, 3478 insertions, 1427 deletions
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index e144f54185c0..1697036336b6 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -10,6 +10,7 @@ header-y += nfnetlink.h header-y += nfnetlink_acct.h header-y += nfnetlink_compat.h header-y += nfnetlink_conntrack.h +header-y += nfnetlink_cttimeout.h header-y += nfnetlink_log.h header-y += nfnetlink_queue.h header-y += x_tables.h @@ -22,6 +23,7 @@ header-y += xt_CT.h header-y += xt_DSCP.h header-y += xt_IDLETIMER.h header-y += xt_LED.h +header-y += xt_LOG.h header-y += xt_MARK.h header-y += xt_nfacct.h header-y += xt_NFLOG.h diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 3540c6e262f7..2f8e18a23227 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -11,6 +11,8 @@ * published by the Free Software Foundation. */ +#include <linux/types.h> + /* The protocol version */ #define IPSET_PROTOCOL 6 @@ -148,6 +150,7 @@ enum ipset_cmd_flags { IPSET_FLAG_LIST_SETNAME = (1 << IPSET_FLAG_BIT_LIST_SETNAME), IPSET_FLAG_BIT_LIST_HEADER = 2, IPSET_FLAG_LIST_HEADER = (1 << IPSET_FLAG_BIT_LIST_HEADER), + IPSET_FLAG_CMD_MAX = 15, /* Lower half */ }; /* Flags at CADT attribute level */ @@ -156,6 +159,9 @@ enum ipset_cadt_flags { IPSET_FLAG_BEFORE = (1 << IPSET_FLAG_BIT_BEFORE), IPSET_FLAG_BIT_PHYSDEV = 1, IPSET_FLAG_PHYSDEV = (1 << IPSET_FLAG_BIT_PHYSDEV), + IPSET_FLAG_BIT_NOMATCH = 2, + IPSET_FLAG_NOMATCH = (1 << IPSET_FLAG_BIT_NOMATCH), + IPSET_FLAG_CADT_MAX = 15, /* Upper half */ }; /* Commands with settype-specific attributes */ @@ -168,19 +174,10 @@ enum ipset_adt { IPSET_CADT_MAX, }; -#ifdef __KERNEL__ -#include <linux/ip.h> -#include <linux/ipv6.h> -#include <linux/netlink.h> -#include <linux/netfilter.h> -#include <linux/netfilter/x_tables.h> -#include <linux/vmalloc.h> -#include <net/netlink.h> - /* Sets are identified by an index in kernel space. Tweak with ip_set_id_t * and IPSET_INVALID_ID if you want to increase the max number of sets. */ -typedef u16 ip_set_id_t; +typedef __u16 ip_set_id_t; #define IPSET_INVALID_ID 65535 @@ -203,6 +200,15 @@ enum ip_set_kopt { IPSET_DIM_THREE_SRC = (1 << IPSET_DIM_THREE), }; +#ifdef __KERNEL__ +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/x_tables.h> +#include <linux/vmalloc.h> +#include <net/netlink.h> + /* Set features */ enum ip_set_feature { IPSET_TYPE_IP_FLAG = 0, @@ -288,7 +294,10 @@ struct ip_set_type { u8 features; /* Set type dimension */ u8 dimension; - /* Supported family: may be AF_UNSPEC for both AF_INET/AF_INET6 */ + /* + * Supported family: may be NFPROTO_UNSPEC for both + * NFPROTO_IPV4/NFPROTO_IPV6. + */ u8 family; /* Type revisions */ u8 revision_min, revision_max; @@ -450,6 +459,8 @@ bitmap_bytes(u32 a, u32 b) return 4 * ((((b - a + 8) / 8) + 3) / 4); } +#endif /* __KERNEL__ */ + /* Interface to iptables/ip6tables */ #define SO_IP_SET 83 @@ -475,6 +486,4 @@ struct ip_set_req_version { unsigned version; }; -#endif /* __KERNEL__ */ - #endif /*_IP_SET_H */ diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index b89fb79cb44f..05a5d72680be 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -113,6 +113,12 @@ htable_bits(u32 hashsize) } #ifdef IP_SET_HASH_WITH_NETS +#ifdef IP_SET_HASH_WITH_NETS_PACKED +/* When cidr is packed with nomatch, cidr - 1 is stored in the entry */ +#define CIDR(cidr) (cidr + 1) +#else +#define CIDR(cidr) (cidr) +#endif #define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128) @@ -262,6 +268,12 @@ ip_set_hash_destroy(struct ip_set *set) #define type_pf_data_list TOKEN(TYPE, PF, _data_list) #define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist) #define type_pf_data_next TOKEN(TYPE, PF, _data_next) +#define type_pf_data_flags TOKEN(TYPE, PF, _data_flags) +#ifdef IP_SET_HASH_WITH_NETS +#define type_pf_data_match TOKEN(TYPE, PF, _data_match) +#else +#define type_pf_data_match(d) 1 +#endif #define type_pf_elem TOKEN(TYPE, PF, _elem) #define type_pf_telem TOKEN(TYPE, PF, _telem) @@ -308,8 +320,10 @@ ip_set_hash_destroy(struct ip_set *set) * we spare the maintenance of the internal counters. */ static int type_pf_elem_add(struct hbucket *n, const struct type_pf_elem *value, - u8 ahash_max) + u8 ahash_max, u32 cadt_flags) { + struct type_pf_elem *data; + if (n->pos >= n->size) { void *tmp; @@ -330,7 +344,13 @@ type_pf_elem_add(struct hbucket *n, const struct type_pf_elem *value, n->value = tmp; n->size += AHASH_INIT_SIZE; } - type_pf_data_copy(ahash_data(n, n->pos++), value); + data = ahash_data(n, n->pos++); + type_pf_data_copy(data, value); +#ifdef IP_SET_HASH_WITH_NETS + /* Resizing won't overwrite stored flags */ + if (cadt_flags) + type_pf_data_flags(data, cadt_flags); +#endif return 0; } @@ -353,9 +373,12 @@ retry: htable_bits++; pr_debug("attempt to resize set %s from %u to %u, t %p\n", set->name, orig->htable_bits, htable_bits, orig); - if (!htable_bits) + if (!htable_bits) { /* In case we have plenty of memory :-) */ + pr_warning("Cannot increase the hashsize of set %s further\n", + set->name); return -IPSET_ERR_HASH_FULL; + } t = ip_set_alloc(sizeof(*t) + jhash_size(htable_bits) * sizeof(struct hbucket)); if (!t) @@ -368,7 +391,7 @@ retry: for (j = 0; j < n->pos; j++) { data = ahash_data(n, j); m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_add(m, data, AHASH_MAX(h)); + ret = type_pf_elem_add(m, data, AHASH_MAX(h), 0); if (ret < 0) { read_unlock_bh(&set->lock); ahash_destroy(t); @@ -406,9 +429,14 @@ type_pf_add(struct ip_set *set, void *value, u32 timeout, u32 flags) struct hbucket *n; int i, ret = 0; u32 key, multi = 0; + u32 cadt_flags = flags >> 16; - if (h->elements >= h->maxelem) + if (h->elements >= h->maxelem) { + if (net_ratelimit()) + pr_warning("Set %s is full, maxelem %u reached\n", + set->name, h->maxelem); return -IPSET_ERR_HASH_FULL; + } rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); @@ -416,11 +444,17 @@ type_pf_add(struct ip_set *set, void *value, u32 timeout, u32 flags) n = hbucket(t, key); for (i = 0; i < n->pos; i++) if (type_pf_data_equal(ahash_data(n, i), d, &multi)) { +#ifdef IP_SET_HASH_WITH_NETS + if (flags & IPSET_FLAG_EXIST) + /* Support overwriting just the flags */ + type_pf_data_flags(ahash_data(n, i), + cadt_flags); +#endif ret = -IPSET_ERR_EXIST; goto out; } TUNE_AHASH_MAX(h, multi); - ret = type_pf_elem_add(n, value, AHASH_MAX(h)); + ret = type_pf_elem_add(n, value, AHASH_MAX(h), cadt_flags); if (ret != 0) { if (ret == -EAGAIN) type_pf_data_next(h, d); @@ -428,7 +462,7 @@ type_pf_add(struct ip_set *set, void *value, u32 timeout, u32 flags) } #ifdef IP_SET_HASH_WITH_NETS - add_cidr(h, d->cidr, HOST_MASK); + add_cidr(h, CIDR(d->cidr), HOST_MASK); #endif h->elements++; out: @@ -463,7 +497,7 @@ type_pf_del(struct ip_set *set, void *value, u32 timeout, u32 flags) n->pos--; h->elements--; #ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, d->cidr, HOST_MASK); + del_cidr(h, CIDR(d->cidr), HOST_MASK); #endif if (n->pos + AHASH_INIT_SIZE < n->size) { void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) @@ -506,7 +540,7 @@ type_pf_test_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) for (i = 0; i < n->pos; i++) { data = ahash_data(n, i); if (type_pf_data_equal(data, d, &multi)) - return 1; + return type_pf_data_match(data); } } return 0; @@ -528,7 +562,7 @@ type_pf_test(struct ip_set *set, void *value, u32 timeout, u32 flags) #ifdef IP_SET_HASH_WITH_NETS /* If we test an IP address and not a network address, * try all possible network sizes */ - if (d->cidr == SET_HOST_MASK(set->family)) + if (CIDR(d->cidr) == SET_HOST_MASK(set->family)) return type_pf_test_cidrs(set, d, timeout); #endif @@ -537,7 +571,7 @@ type_pf_test(struct ip_set *set, void *value, u32 timeout, u32 flags) for (i = 0; i < n->pos; i++) { data = ahash_data(n, i); if (type_pf_data_equal(data, d, &multi)) - return 1; + return type_pf_data_match(data); } return 0; } @@ -693,7 +727,7 @@ type_pf_data_timeout_set(struct type_pf_elem *data, u32 timeout) static int type_pf_elem_tadd(struct hbucket *n, const struct type_pf_elem *value, - u8 ahash_max, u32 timeout) + u8 ahash_max, u32 cadt_flags, u32 timeout) { struct type_pf_elem *data; @@ -720,6 +754,11 @@ type_pf_elem_tadd(struct hbucket *n, const struct type_pf_elem *value, data = ahash_tdata(n, n->pos++); type_pf_data_copy(data, value); type_pf_data_timeout_set(data, timeout); +#ifdef IP_SET_HASH_WITH_NETS + /* Resizing won't overwrite stored flags */ + if (cadt_flags) + type_pf_data_flags(data, cadt_flags); +#endif return 0; } @@ -740,7 +779,7 @@ type_pf_expire(struct ip_set_hash *h) if (type_pf_data_expired(data)) { pr_debug("expired %u/%u\n", i, j); #ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, data->cidr, HOST_MASK); + del_cidr(h, CIDR(data->cidr), HOST_MASK); #endif if (j != n->pos - 1) /* Not last one */ @@ -790,9 +829,12 @@ type_pf_tresize(struct ip_set *set, bool retried) retry: ret = 0; htable_bits++; - if (!htable_bits) + if (!htable_bits) { /* In case we have plenty of memory :-) */ + pr_warning("Cannot increase the hashsize of set %s further\n", + set->name); return -IPSET_ERR_HASH_FULL; + } t = ip_set_alloc(sizeof(*t) + jhash_size(htable_bits) * sizeof(struct hbucket)); if (!t) @@ -805,7 +847,7 @@ retry: for (j = 0; j < n->pos; j++) { data = ahash_tdata(n, j); m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), + ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), 0, type_pf_data_timeout(data)); if (ret < 0) { read_unlock_bh(&set->lock); @@ -839,12 +881,17 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) int ret = 0, i, j = AHASH_MAX(h) + 1; bool flag_exist = flags & IPSET_FLAG_EXIST; u32 key, multi = 0; + u32 cadt_flags = flags >> 16; if (h->elements >= h->maxelem) /* FIXME: when set is full, we slow down here */ type_pf_expire(h); - if (h->elements >= h->maxelem) + if (h->elements >= h->maxelem) { + if (net_ratelimit()) + pr_warning("Set %s is full, maxelem %u reached\n", + set->name, h->maxelem); return -IPSET_ERR_HASH_FULL; + } rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); @@ -854,6 +901,7 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) data = ahash_tdata(n, i); if (type_pf_data_equal(data, d, &multi)) { if (type_pf_data_expired(data) || flag_exist) + /* Just timeout value may be updated */ j = i; else { ret = -IPSET_ERR_EXIST; @@ -866,15 +914,18 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) if (j != AHASH_MAX(h) + 1) { data = ahash_tdata(n, j); #ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, data->cidr, HOST_MASK); - add_cidr(h, d->cidr, HOST_MASK); + del_cidr(h, CIDR(data->cidr), HOST_MASK); + add_cidr(h, CIDR(d->cidr), HOST_MASK); #endif type_pf_data_copy(data, d); type_pf_data_timeout_set(data, timeout); +#ifdef IP_SET_HASH_WITH_NETS + type_pf_data_flags(data, cadt_flags); +#endif goto out; } TUNE_AHASH_MAX(h, multi); - ret = type_pf_elem_tadd(n, d, AHASH_MAX(h), timeout); + ret = type_pf_elem_tadd(n, d, AHASH_MAX(h), cadt_flags, timeout); if (ret != 0) { if (ret == -EAGAIN) type_pf_data_next(h, d); @@ -882,7 +933,7 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) } #ifdef IP_SET_HASH_WITH_NETS - add_cidr(h, d->cidr, HOST_MASK); + add_cidr(h, CIDR(d->cidr), HOST_MASK); #endif h->elements++; out: @@ -916,7 +967,7 @@ type_pf_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags) n->pos--; h->elements--; #ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, d->cidr, HOST_MASK); + del_cidr(h, CIDR(d->cidr), HOST_MASK); #endif if (n->pos + AHASH_INIT_SIZE < n->size) { void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) @@ -954,8 +1005,17 @@ type_pf_ttest_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) n = hbucket(t, key); for (i = 0; i < n->pos; i++) { data = ahash_tdata(n, i); - if (type_pf_data_equal(data, d, &multi)) - return !type_pf_data_expired(data); +#ifdef IP_SET_HASH_WITH_MULTI + if (type_pf_data_equal(data, d, &multi)) { + if (!type_pf_data_expired(data)) + return type_pf_data_match(data); + multi = 0; + } +#else + if (type_pf_data_equal(data, d, &multi) && + !type_pf_data_expired(data)) + return type_pf_data_match(data); +#endif } } return 0; @@ -973,15 +1033,16 @@ type_pf_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags) u32 key, multi = 0; #ifdef IP_SET_HASH_WITH_NETS - if (d->cidr == SET_HOST_MASK(set->family)) + if (CIDR(d->cidr) == SET_HOST_MASK(set->family)) return type_pf_ttest_cidrs(set, d, timeout); #endif key = HKEY(d, h->initval, t->htable_bits); n = hbucket(t, key); for (i = 0; i < n->pos; i++) { data = ahash_tdata(n, i); - if (type_pf_data_equal(data, d, &multi)) - return !type_pf_data_expired(data); + if (type_pf_data_equal(data, d, &multi) && + !type_pf_data_expired(data)) + return type_pf_data_match(data); } return 0; } @@ -1094,14 +1155,17 @@ type_pf_gc_init(struct ip_set *set) #undef type_pf_data_isnull #undef type_pf_data_copy #undef type_pf_data_zero_out +#undef type_pf_data_netmask #undef type_pf_data_list #undef type_pf_data_tlist +#undef type_pf_data_next +#undef type_pf_data_flags +#undef type_pf_data_match #undef type_pf_elem #undef type_pf_telem #undef type_pf_data_timeout #undef type_pf_data_expired -#undef type_pf_data_netmask #undef type_pf_data_timeout_set #undef type_pf_elem_add @@ -1111,6 +1175,7 @@ type_pf_gc_init(struct ip_set *set) #undef type_pf_test #undef type_pf_elem_tadd +#undef type_pf_del_telem #undef type_pf_expire #undef type_pf_tadd #undef type_pf_tdel diff --git a/include/linux/netfilter/nf_conntrack_tcp.h b/include/linux/netfilter/nf_conntrack_tcp.h index 6e135f97e59a..e59868ae12d4 100644 --- a/include/linux/netfilter/nf_conntrack_tcp.h +++ b/include/linux/netfilter/nf_conntrack_tcp.h @@ -18,7 +18,10 @@ enum tcp_conntrack { TCP_CONNTRACK_LISTEN, /* obsolete */ #define TCP_CONNTRACK_SYN_SENT2 TCP_CONNTRACK_LISTEN TCP_CONNTRACK_MAX, - TCP_CONNTRACK_IGNORE + TCP_CONNTRACK_IGNORE, + TCP_CONNTRACK_RETRANS, + TCP_CONNTRACK_UNACK, + TCP_CONNTRACK_TIMEOUT_MAX }; /* Window scaling is advertised by the sender */ diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index b64454c2f79f..6fd1f0d07e64 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -49,7 +49,8 @@ struct nfgenmsg { #define NFNL_SUBSYS_OSF 5 #define NFNL_SUBSYS_IPSET 6 #define NFNL_SUBSYS_ACCT 7 -#define NFNL_SUBSYS_COUNT 8 +#define NFNL_SUBSYS_CTNETLINK_TIMEOUT 8 +#define NFNL_SUBSYS_COUNT 9 #ifdef __KERNEL__ diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index d498a4426ebf..e58e4b93c108 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -173,10 +173,21 @@ enum ctattr_expect { CTA_EXPECT_HELP_NAME, CTA_EXPECT_ZONE, CTA_EXPECT_FLAGS, + CTA_EXPECT_CLASS, + CTA_EXPECT_NAT, + CTA_EXPECT_FN, __CTA_EXPECT_MAX }; #define CTA_EXPECT_MAX (__CTA_EXPECT_MAX - 1) +enum ctattr_expect_nat { + CTA_EXPECT_NAT_UNSPEC, + CTA_EXPECT_NAT_DIR, + CTA_EXPECT_NAT_TUPLE, + __CTA_EXPECT_NAT_MAX +}; +#define CTA_EXPECT_NAT_MAX (__CTA_EXPECT_NAT_MAX - 1) + enum ctattr_help { CTA_HELP_UNSPEC, CTA_HELP_NAME, diff --git a/include/linux/netfilter/nfnetlink_cttimeout.h b/include/linux/netfilter/nfnetlink_cttimeout.h new file mode 100644 index 000000000000..a2810a7c5e30 --- /dev/null +++ b/include/linux/netfilter/nfnetlink_cttimeout.h @@ -0,0 +1,114 @@ +#ifndef _CTTIMEOUT_NETLINK_H +#define _CTTIMEOUT_NETLINK_H +#include <linux/netfilter/nfnetlink.h> + +enum ctnl_timeout_msg_types { + IPCTNL_MSG_TIMEOUT_NEW, + IPCTNL_MSG_TIMEOUT_GET, + IPCTNL_MSG_TIMEOUT_DELETE, + + IPCTNL_MSG_TIMEOUT_MAX +}; + +enum ctattr_timeout { + CTA_TIMEOUT_UNSPEC, + CTA_TIMEOUT_NAME, + CTA_TIMEOUT_L3PROTO, + CTA_TIMEOUT_L4PROTO, + CTA_TIMEOUT_DATA, + CTA_TIMEOUT_USE, + __CTA_TIMEOUT_MAX +}; +#define CTA_TIMEOUT_MAX (__CTA_TIMEOUT_MAX - 1) + +enum ctattr_timeout_generic { + CTA_TIMEOUT_GENERIC_UNSPEC, + CTA_TIMEOUT_GENERIC_TIMEOUT, + __CTA_TIMEOUT_GENERIC_MAX +}; +#define CTA_TIMEOUT_GENERIC_MAX (__CTA_TIMEOUT_GENERIC_MAX - 1) + +enum ctattr_timeout_tcp { + CTA_TIMEOUT_TCP_UNSPEC, + CTA_TIMEOUT_TCP_SYN_SENT, + CTA_TIMEOUT_TCP_SYN_RECV, + CTA_TIMEOUT_TCP_ESTABLISHED, + CTA_TIMEOUT_TCP_FIN_WAIT, + CTA_TIMEOUT_TCP_CLOSE_WAIT, + CTA_TIMEOUT_TCP_LAST_ACK, + CTA_TIMEOUT_TCP_TIME_WAIT, + CTA_TIMEOUT_TCP_CLOSE, + CTA_TIMEOUT_TCP_SYN_SENT2, + CTA_TIMEOUT_TCP_RETRANS, + CTA_TIMEOUT_TCP_UNACK, + __CTA_TIMEOUT_TCP_MAX +}; +#define CTA_TIMEOUT_TCP_MAX (__CTA_TIMEOUT_TCP_MAX - 1) + +enum ctattr_timeout_udp { + CTA_TIMEOUT_UDP_UNSPEC, + CTA_TIMEOUT_UDP_UNREPLIED, + CTA_TIMEOUT_UDP_REPLIED, + __CTA_TIMEOUT_UDP_MAX +}; +#define CTA_TIMEOUT_UDP_MAX (__CTA_TIMEOUT_UDP_MAX - 1) + +enum ctattr_timeout_udplite { + CTA_TIMEOUT_UDPLITE_UNSPEC, + CTA_TIMEOUT_UDPLITE_UNREPLIED, + CTA_TIMEOUT_UDPLITE_REPLIED, + __CTA_TIMEOUT_UDPLITE_MAX +}; +#define CTA_TIMEOUT_UDPLITE_MAX (__CTA_TIMEOUT_UDPLITE_MAX - 1) + +enum ctattr_timeout_icmp { + CTA_TIMEOUT_ICMP_UNSPEC, + CTA_TIMEOUT_ICMP_TIMEOUT, + __CTA_TIMEOUT_ICMP_MAX +}; +#define CTA_TIMEOUT_ICMP_MAX (__CTA_TIMEOUT_ICMP_MAX - 1) + +enum ctattr_timeout_dccp { + CTA_TIMEOUT_DCCP_UNSPEC, + CTA_TIMEOUT_DCCP_REQUEST, + CTA_TIMEOUT_DCCP_RESPOND, + CTA_TIMEOUT_DCCP_PARTOPEN, + CTA_TIMEOUT_DCCP_OPEN, + CTA_TIMEOUT_DCCP_CLOSEREQ, + CTA_TIMEOUT_DCCP_CLOSING, + CTA_TIMEOUT_DCCP_TIMEWAIT, + __CTA_TIMEOUT_DCCP_MAX +}; +#define CTA_TIMEOUT_DCCP_MAX (__CTA_TIMEOUT_DCCP_MAX - 1) + +enum ctattr_timeout_sctp { + CTA_TIMEOUT_SCTP_UNSPEC, + CTA_TIMEOUT_SCTP_CLOSED, + CTA_TIMEOUT_SCTP_COOKIE_WAIT, + CTA_TIMEOUT_SCTP_COOKIE_ECHOED, + CTA_TIMEOUT_SCTP_ESTABLISHED, + CTA_TIMEOUT_SCTP_SHUTDOWN_SENT, + CTA_TIMEOUT_SCTP_SHUTDOWN_RECD, + CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, + __CTA_TIMEOUT_SCTP_MAX +}; +#define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1) + +enum ctattr_timeout_icmpv6 { + CTA_TIMEOUT_ICMPV6_UNSPEC, + CTA_TIMEOUT_ICMPV6_TIMEOUT, + __CTA_TIMEOUT_ICMPV6_MAX +}; +#define CTA_TIMEOUT_ICMPV6_MAX (__CTA_TIMEOUT_ICMPV6_MAX - 1) + +enum ctattr_timeout_gre { + CTA_TIMEOUT_GRE_UNSPEC, + CTA_TIMEOUT_GRE_UNREPLIED, + CTA_TIMEOUT_GRE_REPLIED, + __CTA_TIMEOUT_GRE_MAX +}; +#define CTA_TIMEOUT_GRE_MAX (__CTA_TIMEOUT_GRE_MAX - 1) + +#define CTNL_TIMEOUT_NAME_MAX 32 + +#endif diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h index b56e76811c04..a064b8af360c 100644 --- a/include/linux/netfilter/xt_CT.h +++ b/include/linux/netfilter/xt_CT.h @@ -16,4 +16,16 @@ struct xt_ct_target_info { struct nf_conn *ct __attribute__((aligned(8))); }; +struct xt_ct_target_info_v1 { + __u16 flags; + __u16 zone; + __u32 ct_events; + __u32 exp_events; + char helper[16]; + char timeout[32]; + + /* Used internally by the kernel */ + struct nf_conn *ct __attribute__((aligned(8))); +}; + #endif /* _XT_CT_H */ diff --git a/include/linux/netfilter/xt_LOG.h b/include/linux/netfilter/xt_LOG.h new file mode 100644 index 000000000000..cac079095305 --- /dev/null +++ b/include/linux/netfilter/xt_LOG.h @@ -0,0 +1,19 @@ +#ifndef _XT_LOG_H +#define _XT_LOG_H + +/* make sure not to change this without changing nf_log.h:NF_LOG_* (!) */ +#define XT_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ +#define XT_LOG_TCPOPT 0x02 /* Log TCP options */ +#define XT_LOG_IPOPT 0x04 /* Log IP options */ +#define XT_LOG_UID 0x08 /* Log UID owning local socket */ +#define XT_LOG_NFLOG 0x10 /* Unsupported, don't reuse */ +#define XT_LOG_MACDECODE 0x20 /* Decode MAC header */ +#define XT_LOG_MASK 0x2f + +struct xt_log_info { + unsigned char level; + unsigned char logflags; + char prefix[30]; +}; + +#endif /* _XT_LOG_H */ diff --git a/include/linux/netfilter_ipv4/Kbuild b/include/linux/netfilter_ipv4/Kbuild index f9930c87fff3..31f8bec95650 100644 --- a/include/linux/netfilter_ipv4/Kbuild +++ b/include/linux/netfilter_ipv4/Kbuild @@ -4,11 +4,9 @@ header-y += ipt_CLUSTERIP.h header-y += ipt_ECN.h header-y += ipt_LOG.h header-y += ipt_REJECT.h -header-y += ipt_SAME.h header-y += ipt_TTL.h header-y += ipt_ULOG.h header-y += ipt_addrtype.h header-y += ipt_ah.h header-y += ipt_ecn.h -header-y += ipt_realm.h header-y += ipt_ttl.h diff --git a/include/linux/netfilter_ipv4/ipt_LOG.h b/include/linux/netfilter_ipv4/ipt_LOG.h index dcdbadf9fd4a..5d8152077d71 100644 --- a/include/linux/netfilter_ipv4/ipt_LOG.h +++ b/include/linux/netfilter_ipv4/ipt_LOG.h @@ -1,6 +1,8 @@ #ifndef _IPT_LOG_H #define _IPT_LOG_H +#warning "Please update iptables, this file will be removed soon!" + /* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */ #define IPT_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ #define IPT_LOG_TCPOPT 0x02 /* Log TCP options */ diff --git a/include/linux/netfilter_ipv4/ipt_SAME.h b/include/linux/netfilter_ipv4/ipt_SAME.h deleted file mode 100644 index 5bca78267afd..000000000000 --- a/include/linux/netfilter_ipv4/ipt_SAME.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef _IPT_SAME_H -#define _IPT_SAME_H - -#include <linux/types.h> - -#define IPT_SAME_MAX_RANGE 10 - -#define IPT_SAME_NODST 0x01 - -struct ipt_same_info { - unsigned char info; - __u32 rangesize; - __u32 ipnum; - __u32 *iparray; - - /* hangs off end. */ - struct nf_nat_range range[IPT_SAME_MAX_RANGE]; -}; - -#endif /*_IPT_SAME_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_realm.h b/include/linux/netfilter_ipv4/ipt_realm.h deleted file mode 100644 index b3996eaa0188..000000000000 --- a/include/linux/netfilter_ipv4/ipt_realm.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef _IPT_REALM_H -#define _IPT_REALM_H - -#include <linux/netfilter/xt_realm.h> -#define ipt_realm_info xt_realm_info - -#endif /* _IPT_REALM_H */ diff --git a/include/linux/netfilter_ipv6/ip6t_LOG.h b/include/linux/netfilter_ipv6/ip6t_LOG.h index 9dd5579e02ec..3dd0bc4e0735 100644 --- a/include/linux/netfilter_ipv6/ip6t_LOG.h +++ b/include/linux/netfilter_ipv6/ip6t_LOG.h @@ -1,6 +1,8 @@ #ifndef _IP6T_LOG_H #define _IP6T_LOG_H +#warning "Please update iptables, this file will be removed soon!" + /* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */ #define IP6T_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ #define IP6T_LOG_TCPOPT 0x02 /* Log TCP options */ diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 2dcf31703acb..96755c3798a5 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -20,6 +20,9 @@ enum nf_ct_ext_id { #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP NF_CT_EXT_TSTAMP, #endif +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + NF_CT_EXT_TIMEOUT, +#endif NF_CT_EXT_NUM, }; @@ -29,6 +32,7 @@ enum nf_ct_ext_id { #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone #define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp +#define NF_CT_EXT_TIMEOUT_TYPE struct nf_conn_timeout /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index f1c1311adc2c..5767dc242dee 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -69,4 +69,17 @@ extern int nf_conntrack_broadcast_help(struct sk_buff *skb, enum ip_conntrack_info ctinfo, unsigned int timeout); +struct nf_ct_helper_expectfn { + struct list_head head; + const char *name; + void (*expectfn)(struct nf_conn *ct, struct nf_conntrack_expect *exp); +}; + +void nf_ct_helper_expectfn_register(struct nf_ct_helper_expectfn *n); +void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n); +struct nf_ct_helper_expectfn * +nf_ct_helper_expectfn_find_by_name(const char *name); +struct nf_ct_helper_expectfn * +nf_ct_helper_expectfn_find_by_symbol(const void *symbol); + #endif /*_NF_CONNTRACK_HELPER_H*/ diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index e3d3ee3c06a2..90c67c7db7e9 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -39,12 +39,13 @@ struct nf_conntrack_l4proto { unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum); + unsigned int hooknum, + unsigned int *timeouts); /* Called when a new connection for this protocol found; * returns TRUE if it's OK. If so, packet() called next. */ bool (*new)(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff); + unsigned int dataoff, unsigned int *timeouts); /* Called when a conntrack entry is destroyed */ void (*destroy)(struct nf_conn *ct); @@ -60,6 +61,9 @@ struct nf_conntrack_l4proto { /* Print out the private part of the conntrack. */ int (*print_conntrack)(struct seq_file *s, struct nf_conn *); + /* Return the array of timeouts for this protocol. */ + unsigned int *(*get_timeouts)(struct net *net); + /* convert protoinfo to nfnetink attributes */ int (*to_nlattr)(struct sk_buff *skb, struct nlattr *nla, struct nf_conn *ct); @@ -79,6 +83,17 @@ struct nf_conntrack_l4proto { size_t nla_size; +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + struct { + size_t obj_size; + int (*nlattr_to_obj)(struct nlattr *tb[], void *data); + int (*obj_to_nlattr)(struct sk_buff *skb, const void *data); + + unsigned int nlattr_max; + const struct nla_policy *nla_policy; + } ctnl_timeout; +#endif + #ifdef CONFIG_SYSCTL struct ctl_table_header **ctl_table_header; struct ctl_table *ctl_table; diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h new file mode 100644 index 000000000000..0e04db4a0865 --- /dev/null +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -0,0 +1,78 @@ +#ifndef _NF_CONNTRACK_TIMEOUT_H +#define _NF_CONNTRACK_TIMEOUT_H + +#include <net/net_namespace.h> +#include <linux/netfilter/nf_conntrack_common.h> +#include <linux/netfilter/nf_conntrack_tuple_common.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_extend.h> + +#define CTNL_TIMEOUT_NAME_MAX 32 + +struct ctnl_timeout { + struct list_head head; + struct rcu_head rcu_head; + atomic_t refcnt; + char name[CTNL_TIMEOUT_NAME_MAX]; + __u16 l3num; + __u8 l4num; + char data[0]; +}; + +struct nf_conn_timeout { + struct ctnl_timeout *timeout; +}; + +#define NF_CT_TIMEOUT_EXT_DATA(__t) (unsigned int *) &((__t)->timeout->data) + +static inline +struct nf_conn_timeout *nf_ct_timeout_find(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + return nf_ct_ext_find(ct, NF_CT_EXT_TIMEOUT); +#else + return NULL; +#endif +} + +static inline +struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct, + struct ctnl_timeout *timeout, + gfp_t gfp) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + struct nf_conn_timeout *timeout_ext; + + timeout_ext = nf_ct_ext_add(ct, NF_CT_EXT_TIMEOUT, gfp); + if (timeout_ext == NULL) + return NULL; + + timeout_ext->timeout = timeout; + + return timeout_ext; +#else + return NULL; +#endif +}; + +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT +extern int nf_conntrack_timeout_init(struct net *net); +extern void nf_conntrack_timeout_fini(struct net *net); +#else +static inline int nf_conntrack_timeout_init(struct net *net) +{ + return 0; +} + +static inline void nf_conntrack_timeout_fini(struct net *net) +{ + return; +} +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ + +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT +extern struct ctnl_timeout *(*nf_ct_timeout_find_get_hook)(const char *name); +extern void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout); +#endif + +#endif /* _NF_CONNTRACK_TIMEOUT_H */ diff --git a/include/net/netfilter/xt_log.h b/include/net/netfilter/xt_log.h index 0dfb34a5b53c..7e1544e8f70d 100644 --- a/include/net/netfilter/xt_log.h +++ b/include/net/netfilter/xt_log.h @@ -6,7 +6,7 @@ struct sbuff { }; static struct sbuff emergency, *emergency_ptr = &emergency; -static int sb_add(struct sbuff *m, const char *f, ...) +static __printf(2, 3) int sb_add(struct sbuff *m, const char *f, ...) { va_list args; int len; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 74dfc9e5211f..fcc543cd987a 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -123,15 +123,6 @@ config IP_NF_TARGET_REJECT To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_LOG - tristate "LOG target support" - default m if NETFILTER_ADVANCED=n - help - This option adds a `LOG' target, which allows you to create rules in - any iptables table which records the packet header to the syslog. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_TARGET_ULOG tristate "ULOG target support" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 213a462b739b..240b68469a7a 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -54,7 +54,6 @@ obj-$(CONFIG_IP_NF_MATCH_RPFILTER) += ipt_rpfilter.o # targets obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o -obj-$(CONFIG_IP_NF_TARGET_LOG) += ipt_LOG.o obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o obj-$(CONFIG_IP_NF_TARGET_NETMAP) += ipt_NETMAP.o obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c deleted file mode 100644 index d76d6c9ed946..000000000000 --- a/net/ipv4/netfilter/ipt_LOG.c +++ /dev/null @@ -1,516 +0,0 @@ -/* - * This is a module which is used for logging packets. - */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/spinlock.h> -#include <linux/skbuff.h> -#include <linux/if_arp.h> -#include <linux/ip.h> -#include <net/icmp.h> -#include <net/udp.h> -#include <net/tcp.h> -#include <net/route.h> - -#include <linux/netfilter.h> -#include <linux/netfilter/x_tables.h> -#include <linux/netfilter_ipv4/ipt_LOG.h> -#include <net/netfilter/nf_log.h> -#include <net/netfilter/xt_log.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); -MODULE_DESCRIPTION("Xtables: IPv4 packet logging to syslog"); - -/* One level of recursion won't kill us */ -static void dump_packet(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb, - unsigned int iphoff) -{ - struct iphdr _iph; - const struct iphdr *ih; - unsigned int logflags; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - else - logflags = NF_LOG_MASK; - - ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); - if (ih == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Important fields: - * TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */ - /* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */ - sb_add(m, "SRC=%pI4 DST=%pI4 ", - &ih->saddr, &ih->daddr); - - /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ - sb_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", - ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, - ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); - - /* Max length: 6 "CE DF MF " */ - if (ntohs(ih->frag_off) & IP_CE) - sb_add(m, "CE "); - if (ntohs(ih->frag_off) & IP_DF) - sb_add(m, "DF "); - if (ntohs(ih->frag_off) & IP_MF) - sb_add(m, "MF "); - - /* Max length: 11 "FRAG:65535 " */ - if (ntohs(ih->frag_off) & IP_OFFSET) - sb_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); - - if ((logflags & IPT_LOG_IPOPT) && - ih->ihl * 4 > sizeof(struct iphdr)) { - const unsigned char *op; - unsigned char _opt[4 * 15 - sizeof(struct iphdr)]; - unsigned int i, optsize; - - optsize = ih->ihl * 4 - sizeof(struct iphdr); - op = skb_header_pointer(skb, iphoff+sizeof(_iph), - optsize, _opt); - if (op == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - sb_add(m, "OPT ("); - for (i = 0; i < optsize; i++) - sb_add(m, "%02X", op[i]); - sb_add(m, ") "); - } - - switch (ih->protocol) { - case IPPROTO_TCP: { - struct tcphdr _tcph; - const struct tcphdr *th; - - /* Max length: 10 "PROTO=TCP " */ - sb_add(m, "PROTO=TCP "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - th = skb_header_pointer(skb, iphoff + ih->ihl * 4, - sizeof(_tcph), &_tcph); - if (th == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u ", - ntohs(th->source), ntohs(th->dest)); - /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ - if (logflags & IPT_LOG_TCPSEQ) - sb_add(m, "SEQ=%u ACK=%u ", - ntohl(th->seq), ntohl(th->ack_seq)); - /* Max length: 13 "WINDOW=65535 " */ - sb_add(m, "WINDOW=%u ", ntohs(th->window)); - /* Max length: 9 "RES=0x3F " */ - sb_add(m, "RES=0x%02x ", (u8)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); - /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ - if (th->cwr) - sb_add(m, "CWR "); - if (th->ece) - sb_add(m, "ECE "); - if (th->urg) - sb_add(m, "URG "); - if (th->ack) - sb_add(m, "ACK "); - if (th->psh) - sb_add(m, "PSH "); - if (th->rst) - sb_add(m, "RST "); - if (th->syn) - sb_add(m, "SYN "); - if (th->fin) - sb_add(m, "FIN "); - /* Max length: 11 "URGP=65535 " */ - sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); - - if ((logflags & IPT_LOG_TCPOPT) && - th->doff * 4 > sizeof(struct tcphdr)) { - unsigned char _opt[4 * 15 - sizeof(struct tcphdr)]; - const unsigned char *op; - unsigned int i, optsize; - - optsize = th->doff * 4 - sizeof(struct tcphdr); - op = skb_header_pointer(skb, - iphoff+ih->ihl*4+sizeof(_tcph), - optsize, _opt); - if (op == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - sb_add(m, "OPT ("); - for (i = 0; i < optsize; i++) - sb_add(m, "%02X", op[i]); - sb_add(m, ") "); - } - break; - } - case IPPROTO_UDP: - case IPPROTO_UDPLITE: { - struct udphdr _udph; - const struct udphdr *uh; - - if (ih->protocol == IPPROTO_UDP) - /* Max length: 10 "PROTO=UDP " */ - sb_add(m, "PROTO=UDP " ); - else /* Max length: 14 "PROTO=UDPLITE " */ - sb_add(m, "PROTO=UDPLITE "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - uh = skb_header_pointer(skb, iphoff+ih->ihl*4, - sizeof(_udph), &_udph); - if (uh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u LEN=%u ", - ntohs(uh->source), ntohs(uh->dest), - ntohs(uh->len)); - break; - } - case IPPROTO_ICMP: { - struct icmphdr _icmph; - const struct icmphdr *ich; - static const size_t required_len[NR_ICMP_TYPES+1] - = { [ICMP_ECHOREPLY] = 4, - [ICMP_DEST_UNREACH] - = 8 + sizeof(struct iphdr), - [ICMP_SOURCE_QUENCH] - = 8 + sizeof(struct iphdr), - [ICMP_REDIRECT] - = 8 + sizeof(struct iphdr), - [ICMP_ECHO] = 4, - [ICMP_TIME_EXCEEDED] - = 8 + sizeof(struct iphdr), - [ICMP_PARAMETERPROB] - = 8 + sizeof(struct iphdr), - [ICMP_TIMESTAMP] = 20, - [ICMP_TIMESTAMPREPLY] = 20, - [ICMP_ADDRESS] = 12, - [ICMP_ADDRESSREPLY] = 12 }; - - /* Max length: 11 "PROTO=ICMP " */ - sb_add(m, "PROTO=ICMP "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ich = skb_header_pointer(skb, iphoff + ih->ihl * 4, - sizeof(_icmph), &_icmph); - if (ich == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Max length: 18 "TYPE=255 CODE=255 " */ - sb_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code); - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - if (ich->type <= NR_ICMP_TYPES && - required_len[ich->type] && - skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - switch (ich->type) { - case ICMP_ECHOREPLY: - case ICMP_ECHO: - /* Max length: 19 "ID=65535 SEQ=65535 " */ - sb_add(m, "ID=%u SEQ=%u ", - ntohs(ich->un.echo.id), - ntohs(ich->un.echo.sequence)); - break; - - case ICMP_PARAMETERPROB: - /* Max length: 14 "PARAMETER=255 " */ - sb_add(m, "PARAMETER=%u ", - ntohl(ich->un.gateway) >> 24); - break; - case ICMP_REDIRECT: - /* Max length: 24 "GATEWAY=255.255.255.255 " */ - sb_add(m, "GATEWAY=%pI4 ", &ich->un.gateway); - /* Fall through */ - case ICMP_DEST_UNREACH: - case ICMP_SOURCE_QUENCH: - case ICMP_TIME_EXCEEDED: - /* Max length: 3+maxlen */ - if (!iphoff) { /* Only recurse once. */ - sb_add(m, "["); - dump_packet(m, info, skb, - iphoff + ih->ihl*4+sizeof(_icmph)); - sb_add(m, "] "); - } - - /* Max length: 10 "MTU=65535 " */ - if (ich->type == ICMP_DEST_UNREACH && - ich->code == ICMP_FRAG_NEEDED) - sb_add(m, "MTU=%u ", ntohs(ich->un.frag.mtu)); - } - break; - } - /* Max Length */ - case IPPROTO_AH: { - struct ip_auth_hdr _ahdr; - const struct ip_auth_hdr *ah; - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 9 "PROTO=AH " */ - sb_add(m, "PROTO=AH "); - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ah = skb_header_pointer(skb, iphoff+ih->ihl*4, - sizeof(_ahdr), &_ahdr); - if (ah == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Length: 15 "SPI=0xF1234567 " */ - sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); - break; - } - case IPPROTO_ESP: { - struct ip_esp_hdr _esph; - const struct ip_esp_hdr *eh; - - /* Max length: 10 "PROTO=ESP " */ - sb_add(m, "PROTO=ESP "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - eh = skb_header_pointer(skb, iphoff+ih->ihl*4, - sizeof(_esph), &_esph); - if (eh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Length: 15 "SPI=0xF1234567 " */ - sb_add(m, "SPI=0x%x ", ntohl(eh->spi)); - break; - } - /* Max length: 10 "PROTO 255 " */ - default: - sb_add(m, "PROTO=%u ", ih->protocol); - } - - /* Max length: 15 "UID=4294967295 " */ - if ((logflags & IPT_LOG_UID) && !iphoff && skb->sk) { - read_lock_bh(&skb->sk->sk_callback_lock); - if (skb->sk->sk_socket && skb->sk->sk_socket->file) - sb_add(m, "UID=%u GID=%u ", - skb->sk->sk_socket->file->f_cred->fsuid, - skb->sk->sk_socket->file->f_cred->fsgid); - read_unlock_bh(&skb->sk->sk_callback_lock); - } - - /* Max length: 16 "MARK=0xFFFFFFFF " */ - if (!iphoff && skb->mark) - sb_add(m, "MARK=0x%x ", skb->mark); - - /* Proto Max log string length */ - /* IP: 40+46+6+11+127 = 230 */ - /* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */ - /* UDP: 10+max(25,20) = 35 */ - /* UDPLITE: 14+max(25,20) = 39 */ - /* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */ - /* ESP: 10+max(25)+15 = 50 */ - /* AH: 9+max(25)+15 = 49 */ - /* unknown: 10 */ - - /* (ICMP allows recursion one level deep) */ - /* maxlen = IP + ICMP + IP + max(TCP,UDP,ICMP,unknown) */ - /* maxlen = 230+ 91 + 230 + 252 = 803 */ -} - -static void dump_mac_header(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - unsigned int logflags = 0; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - - if (!(logflags & IPT_LOG_MACDECODE)) - goto fallback; - - switch (dev->type) { - case ARPHRD_ETHER: - sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, - ntohs(eth_hdr(skb)->h_proto)); - return; - default: - break; - } - -fallback: - sb_add(m, "MAC="); - if (dev->hard_header_len && - skb->mac_header != skb->network_header) { - const unsigned char *p = skb_mac_header(skb); - unsigned int i; - - sb_add(m, "%02x", *p++); - for (i = 1; i < dev->hard_header_len; i++, p++) - sb_add(m, ":%02x", *p); - } - sb_add(m, " "); -} - -static struct nf_loginfo default_loginfo = { - .type = NF_LOG_TYPE_LOG, - .u = { - .log = { - .level = 5, - .logflags = NF_LOG_MASK, - }, - }, -}; - -static void -ipt_log_packet(u_int8_t pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, - const char *prefix) -{ - struct sbuff *m = sb_open(); - - if (!loginfo) - loginfo = &default_loginfo; - - sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, - prefix, - in ? in->name : "", - out ? out->name : ""); -#ifdef CONFIG_BRIDGE_NETFILTER - if (skb->nf_bridge) { - const struct net_device *physindev; - const struct net_device *physoutdev; - - physindev = skb->nf_bridge->physindev; - if (physindev && in != physindev) - sb_add(m, "PHYSIN=%s ", physindev->name); - physoutdev = skb->nf_bridge->physoutdev; - if (physoutdev && out != physoutdev) - sb_add(m, "PHYSOUT=%s ", physoutdev->name); - } -#endif - - if (in != NULL) - dump_mac_header(m, loginfo, skb); - - dump_packet(m, loginfo, skb, 0); - - sb_close(m); -} - -static unsigned int -log_tg(struct sk_buff *skb, const struct xt_action_param *par) -{ - const struct ipt_log_info *loginfo = par->targinfo; - struct nf_loginfo li; - - li.type = NF_LOG_TYPE_LOG; - li.u.log.level = loginfo->level; - li.u.log.logflags = loginfo->logflags; - - ipt_log_packet(NFPROTO_IPV4, par->hooknum, skb, par->in, par->out, &li, - loginfo->prefix); - return XT_CONTINUE; -} - -static int log_tg_check(const struct xt_tgchk_param *par) -{ - const struct ipt_log_info *loginfo = par->targinfo; - - if (loginfo->level >= 8) { - pr_debug("level %u >= 8\n", loginfo->level); - return -EINVAL; - } - if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { - pr_debug("prefix is not null-terminated\n"); - return -EINVAL; - } - return 0; -} - -static struct xt_target log_tg_reg __read_mostly = { - .name = "LOG", - .family = NFPROTO_IPV4, - .target = log_tg, - .targetsize = sizeof(struct ipt_log_info), - .checkentry = log_tg_check, - .me = THIS_MODULE, -}; - -static struct nf_logger ipt_log_logger __read_mostly = { - .name = "ipt_LOG", - .logfn = &ipt_log_packet, - .me = THIS_MODULE, -}; - -static int __init log_tg_init(void) -{ - int ret; - - ret = xt_register_target(&log_tg_reg); - if (ret < 0) - return ret; - nf_log_register(NFPROTO_IPV4, &ipt_log_logger); - return 0; -} - -static void __exit log_tg_exit(void) -{ - nf_log_unregister(&ipt_log_logger); - xt_unregister_target(&log_tg_reg); -} - -module_init(log_tg_init); -module_exit(log_tg_exit); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index ab5b27a2916f..7cbe9cb261c2 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -75,25 +75,31 @@ static int icmp_print_tuple(struct seq_file *s, ntohs(tuple->src.u.icmp.id)); } +static unsigned int *icmp_get_timeouts(struct net *net) +{ + return &nf_ct_icmp_timeout; +} + /* Returns verdict for packet, or -1 for invalid. */ static int icmp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeout) { /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout); + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { static const u_int8_t valid_new[] = { [ICMP_ECHO] = 1, @@ -263,6 +269,44 @@ static int icmp_nlattr_tuple_size(void) } #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeout = data; + + if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ; + } else { + /* Set default ICMP timeout. */ + *timeout = nf_ct_icmp_timeout; + } + return 0; +} + +static int +icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ)); + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { + [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static struct ctl_table_header *icmp_sysctl_header; static struct ctl_table icmp_sysctl_table[] = { @@ -298,6 +342,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = .invert_tuple = icmp_invert_tuple, .print_tuple = icmp_print_tuple, .packet = icmp_packet, + .get_timeouts = icmp_get_timeouts, .new = icmp_new, .error = icmp_error, .destroy = NULL, @@ -308,6 +353,15 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = icmp_timeout_nlattr_to_obj, + .obj_to_nlattr = icmp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_ICMP_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = icmp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_header = &icmp_sysctl_header, .ctl_table = icmp_sysctl_table, diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index a708933dc230..abb52adf5acd 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -686,6 +686,11 @@ static struct pernet_operations nf_nat_net_ops = { .exit = nf_nat_net_exit, }; +static struct nf_ct_helper_expectfn follow_master_nat = { + .name = "nat-follow-master", + .expectfn = nf_nat_follow_master, +}; + static int __init nf_nat_init(void) { size_t i; @@ -717,6 +722,8 @@ static int __init nf_nat_init(void) l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET); + nf_ct_helper_expectfn_register(&follow_master_nat); + BUG_ON(nf_nat_seq_adjust_hook != NULL); RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); @@ -736,6 +743,7 @@ static void __exit nf_nat_cleanup(void) unregister_pernet_subsys(&nf_nat_net_ops); nf_ct_l3proto_put(l3proto); nf_ct_extend_unregister(&nat_extend); + nf_ct_helper_expectfn_unregister(&follow_master_nat); RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); RCU_INIT_POINTER(nf_ct_nat_offset, NULL); diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index dc1dd912baf4..82536701e3a3 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -568,6 +568,16 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, return 0; } +static struct nf_ct_helper_expectfn q931_nat = { + .name = "Q.931", + .expectfn = ip_nat_q931_expect, +}; + +static struct nf_ct_helper_expectfn callforwarding_nat = { + .name = "callforwarding", + .expectfn = ip_nat_callforwarding_expect, +}; + /****************************************************************************/ static int __init init(void) { @@ -590,6 +600,8 @@ static int __init init(void) RCU_INIT_POINTER(nat_h245_hook, nat_h245); RCU_INIT_POINTER(nat_callforwarding_hook, nat_callforwarding); RCU_INIT_POINTER(nat_q931_hook, nat_q931); + nf_ct_helper_expectfn_register(&q931_nat); + nf_ct_helper_expectfn_register(&callforwarding_nat); return 0; } @@ -605,6 +617,8 @@ static void __exit fini(void) RCU_INIT_POINTER(nat_h245_hook, NULL); RCU_INIT_POINTER(nat_callforwarding_hook, NULL); RCU_INIT_POINTER(nat_q931_hook, NULL); + nf_ct_helper_expectfn_unregister(&q931_nat); + nf_ct_helper_expectfn_unregister(&callforwarding_nat); synchronize_rcu(); } diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index d0319f96269f..57932c43960e 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -526,6 +526,11 @@ err1: return NF_DROP; } +static struct nf_ct_helper_expectfn sip_nat = { + .name = "sip", + .expectfn = ip_nat_sip_expected, +}; + static void __exit nf_nat_sip_fini(void) { RCU_INIT_POINTER(nf_nat_sip_hook, NULL); @@ -535,6 +540,7 @@ static void __exit nf_nat_sip_fini(void) RCU_INIT_POINTER(nf_nat_sdp_port_hook, NULL); RCU_INIT_POINTER(nf_nat_sdp_session_hook, NULL); RCU_INIT_POINTER(nf_nat_sdp_media_hook, NULL); + nf_ct_helper_expectfn_unregister(&sip_nat); synchronize_rcu(); } @@ -554,6 +560,7 @@ static int __init nf_nat_sip_init(void) RCU_INIT_POINTER(nf_nat_sdp_port_hook, ip_nat_sdp_port); RCU_INIT_POINTER(nf_nat_sdp_session_hook, ip_nat_sdp_session); RCU_INIT_POINTER(nf_nat_sdp_media_hook, ip_nat_sdp_media); + nf_ct_helper_expectfn_register(&sip_nat); return 0; } diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 9a68fb5b9e77..d33cddd16fbb 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -154,15 +154,6 @@ config IP6_NF_TARGET_HL (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_TARGET_HL. -config IP6_NF_TARGET_LOG - tristate "LOG target support" - default m if NETFILTER_ADVANCED=n - help - This option adds a `LOG' target, which allows you to create rules in - any iptables table which records the packet header to the syslog. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_FILTER tristate "Packet filtering" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 2eaed96db02c..d4dfd0a21097 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -31,5 +31,4 @@ obj-$(CONFIG_IP6_NF_MATCH_RPFILTER) += ip6t_rpfilter.o obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o # targets -obj-$(CONFIG_IP6_NF_TARGET_LOG) += ip6t_LOG.o obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c deleted file mode 100644 index e6af8d72f26b..000000000000 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ /dev/null @@ -1,527 +0,0 @@ -/* - * This is a module which is used for logging packets. - */ - -/* (C) 2001 Jan Rekorajski <baggins@pld.org.pl> - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/if_arp.h> -#include <linux/ip.h> -#include <linux/spinlock.h> -#include <linux/icmpv6.h> -#include <net/udp.h> -#include <net/tcp.h> -#include <net/ipv6.h> -#include <linux/netfilter.h> -#include <linux/netfilter/x_tables.h> -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <net/netfilter/nf_log.h> -#include <net/netfilter/xt_log.h> - -MODULE_AUTHOR("Jan Rekorajski <baggins@pld.org.pl>"); -MODULE_DESCRIPTION("Xtables: IPv6 packet logging to syslog"); -MODULE_LICENSE("GPL"); - -struct in_device; -#include <net/route.h> -#include <linux/netfilter_ipv6/ip6t_LOG.h> - -/* One level of recursion won't kill us */ -static void dump_packet(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb, unsigned int ip6hoff, - int recurse) -{ - u_int8_t currenthdr; - int fragment; - struct ipv6hdr _ip6h; - const struct ipv6hdr *ih; - unsigned int ptr; - unsigned int hdrlen = 0; - unsigned int logflags; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - else - logflags = NF_LOG_MASK; - - ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); - if (ih == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ - sb_add(m, "SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); - - /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ - sb_add(m, "LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", - ntohs(ih->payload_len) + sizeof(struct ipv6hdr), - (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, - ih->hop_limit, - (ntohl(*(__be32 *)ih) & 0x000fffff)); - - fragment = 0; - ptr = ip6hoff + sizeof(struct ipv6hdr); - currenthdr = ih->nexthdr; - while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) { - struct ipv6_opt_hdr _hdr; - const struct ipv6_opt_hdr *hp; - - hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); - if (hp == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 48 "OPT (...) " */ - if (logflags & IP6T_LOG_IPOPT) - sb_add(m, "OPT ( "); - - switch (currenthdr) { - case IPPROTO_FRAGMENT: { - struct frag_hdr _fhdr; - const struct frag_hdr *fh; - - sb_add(m, "FRAG:"); - fh = skb_header_pointer(skb, ptr, sizeof(_fhdr), - &_fhdr); - if (fh == NULL) { - sb_add(m, "TRUNCATED "); - return; - } - - /* Max length: 6 "65535 " */ - sb_add(m, "%u ", ntohs(fh->frag_off) & 0xFFF8); - - /* Max length: 11 "INCOMPLETE " */ - if (fh->frag_off & htons(0x0001)) - sb_add(m, "INCOMPLETE "); - - sb_add(m, "ID:%08x ", ntohl(fh->identification)); - - if (ntohs(fh->frag_off) & 0xFFF8) - fragment = 1; - - hdrlen = 8; - - break; - } - case IPPROTO_DSTOPTS: - case IPPROTO_ROUTING: - case IPPROTO_HOPOPTS: - if (fragment) { - if (logflags & IP6T_LOG_IPOPT) - sb_add(m, ")"); - return; - } - hdrlen = ipv6_optlen(hp); - break; - /* Max Length */ - case IPPROTO_AH: - if (logflags & IP6T_LOG_IPOPT) { - struct ip_auth_hdr _ahdr; - const struct ip_auth_hdr *ah; - - /* Max length: 3 "AH " */ - sb_add(m, "AH "); - - if (fragment) { - sb_add(m, ")"); - return; - } - - ah = skb_header_pointer(skb, ptr, sizeof(_ahdr), - &_ahdr); - if (ah == NULL) { - /* - * Max length: 26 "INCOMPLETE [65535 - * bytes] )" - */ - sb_add(m, "INCOMPLETE [%u bytes] )", - skb->len - ptr); - return; - } - - /* Length: 15 "SPI=0xF1234567 */ - sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); - - } - - hdrlen = (hp->hdrlen+2)<<2; - break; - case IPPROTO_ESP: - if (logflags & IP6T_LOG_IPOPT) { - struct ip_esp_hdr _esph; - const struct ip_esp_hdr *eh; - - /* Max length: 4 "ESP " */ - sb_add(m, "ESP "); - - if (fragment) { - sb_add(m, ")"); - return; - } - - /* - * Max length: 26 "INCOMPLETE [65535 bytes] )" - */ - eh = skb_header_pointer(skb, ptr, sizeof(_esph), - &_esph); - if (eh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] )", - skb->len - ptr); - return; - } - - /* Length: 16 "SPI=0xF1234567 )" */ - sb_add(m, "SPI=0x%x )", ntohl(eh->spi) ); - - } - return; - default: - /* Max length: 20 "Unknown Ext Hdr 255" */ - sb_add(m, "Unknown Ext Hdr %u", currenthdr); - return; - } - if (logflags & IP6T_LOG_IPOPT) - sb_add(m, ") "); - - currenthdr = hp->nexthdr; - ptr += hdrlen; - } - - switch (currenthdr) { - case IPPROTO_TCP: { - struct tcphdr _tcph; - const struct tcphdr *th; - - /* Max length: 10 "PROTO=TCP " */ - sb_add(m, "PROTO=TCP "); - - if (fragment) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - th = skb_header_pointer(skb, ptr, sizeof(_tcph), &_tcph); - if (th == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); - return; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u ", - ntohs(th->source), ntohs(th->dest)); - /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ - if (logflags & IP6T_LOG_TCPSEQ) - sb_add(m, "SEQ=%u ACK=%u ", - ntohl(th->seq), ntohl(th->ack_seq)); - /* Max length: 13 "WINDOW=65535 " */ - sb_add(m, "WINDOW=%u ", ntohs(th->window)); - /* Max length: 9 "RES=0x3C " */ - sb_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); - /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ - if (th->cwr) - sb_add(m, "CWR "); - if (th->ece) - sb_add(m, "ECE "); - if (th->urg) - sb_add(m, "URG "); - if (th->ack) - sb_add(m, "ACK "); - if (th->psh) - sb_add(m, "PSH "); - if (th->rst) - sb_add(m, "RST "); - if (th->syn) - sb_add(m, "SYN "); - if (th->fin) - sb_add(m, "FIN "); - /* Max length: 11 "URGP=65535 " */ - sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); - - if ((logflags & IP6T_LOG_TCPOPT) && - th->doff * 4 > sizeof(struct tcphdr)) { - u_int8_t _opt[60 - sizeof(struct tcphdr)]; - const u_int8_t *op; - unsigned int i; - unsigned int optsize = th->doff * 4 - - sizeof(struct tcphdr); - - op = skb_header_pointer(skb, - ptr + sizeof(struct tcphdr), - optsize, _opt); - if (op == NULL) { - sb_add(m, "OPT (TRUNCATED)"); - return; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - sb_add(m, "OPT ("); - for (i =0; i < optsize; i++) - sb_add(m, "%02X", op[i]); - sb_add(m, ") "); - } - break; - } - case IPPROTO_UDP: - case IPPROTO_UDPLITE: { - struct udphdr _udph; - const struct udphdr *uh; - - if (currenthdr == IPPROTO_UDP) - /* Max length: 10 "PROTO=UDP " */ - sb_add(m, "PROTO=UDP " ); - else /* Max length: 14 "PROTO=UDPLITE " */ - sb_add(m, "PROTO=UDPLITE "); - - if (fragment) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - uh = skb_header_pointer(skb, ptr, sizeof(_udph), &_udph); - if (uh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); - return; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u LEN=%u ", - ntohs(uh->source), ntohs(uh->dest), - ntohs(uh->len)); - break; - } - case IPPROTO_ICMPV6: { - struct icmp6hdr _icmp6h; - const struct icmp6hdr *ic; - - /* Max length: 13 "PROTO=ICMPv6 " */ - sb_add(m, "PROTO=ICMPv6 "); - - if (fragment) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h); - if (ic == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); - return; - } - - /* Max length: 18 "TYPE=255 CODE=255 " */ - sb_add(m, "TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code); - - switch (ic->icmp6_type) { - case ICMPV6_ECHO_REQUEST: - case ICMPV6_ECHO_REPLY: - /* Max length: 19 "ID=65535 SEQ=65535 " */ - sb_add(m, "ID=%u SEQ=%u ", - ntohs(ic->icmp6_identifier), - ntohs(ic->icmp6_sequence)); - break; - case ICMPV6_MGM_QUERY: - case ICMPV6_MGM_REPORT: - case ICMPV6_MGM_REDUCTION: - break; - - case ICMPV6_PARAMPROB: - /* Max length: 17 "POINTER=ffffffff " */ - sb_add(m, "POINTER=%08x ", ntohl(ic->icmp6_pointer)); - /* Fall through */ - case ICMPV6_DEST_UNREACH: - case ICMPV6_PKT_TOOBIG: - case ICMPV6_TIME_EXCEED: - /* Max length: 3+maxlen */ - if (recurse) { - sb_add(m, "["); - dump_packet(m, info, skb, - ptr + sizeof(_icmp6h), 0); - sb_add(m, "] "); - } - - /* Max length: 10 "MTU=65535 " */ - if (ic->icmp6_type == ICMPV6_PKT_TOOBIG) - sb_add(m, "MTU=%u ", ntohl(ic->icmp6_mtu)); - } - break; - } - /* Max length: 10 "PROTO=255 " */ - default: - sb_add(m, "PROTO=%u ", currenthdr); - } - - /* Max length: 15 "UID=4294967295 " */ - if ((logflags & IP6T_LOG_UID) && recurse && skb->sk) { - read_lock_bh(&skb->sk->sk_callback_lock); - if (skb->sk->sk_socket && skb->sk->sk_socket->file) - sb_add(m, "UID=%u GID=%u ", - skb->sk->sk_socket->file->f_cred->fsuid, - skb->sk->sk_socket->file->f_cred->fsgid); - read_unlock_bh(&skb->sk->sk_callback_lock); - } - - /* Max length: 16 "MARK=0xFFFFFFFF " */ - if (!recurse && skb->mark) - sb_add(m, "MARK=0x%x ", skb->mark); -} - -static void dump_mac_header(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - unsigned int logflags = 0; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - - if (!(logflags & IP6T_LOG_MACDECODE)) - goto fallback; - - switch (dev->type) { - case ARPHRD_ETHER: - sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, - ntohs(eth_hdr(skb)->h_proto)); - return; - default: - break; - } - -fallback: - sb_add(m, "MAC="); - if (dev->hard_header_len && - skb->mac_header != skb->network_header) { - const unsigned char *p = skb_mac_header(skb); - unsigned int len = dev->hard_header_len; - unsigned int i; - - if (dev->type == ARPHRD_SIT && - (p -= ETH_HLEN) < skb->head) - p = NULL; - - if (p != NULL) { - sb_add(m, "%02x", *p++); - for (i = 1; i < len; i++) - sb_add(m, ":%02x", *p++); - } - sb_add(m, " "); - - if (dev->type == ARPHRD_SIT) { - const struct iphdr *iph = - (struct iphdr *)skb_mac_header(skb); - sb_add(m, "TUNNEL=%pI4->%pI4 ", &iph->saddr, &iph->daddr); - } - } else - sb_add(m, " "); -} - -static struct nf_loginfo default_loginfo = { - .type = NF_LOG_TYPE_LOG, - .u = { - .log = { - .level = 5, - .logflags = NF_LOG_MASK, - }, - }, -}; - -static void -ip6t_log_packet(u_int8_t pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, - const char *prefix) -{ - struct sbuff *m = sb_open(); - - if (!loginfo) - loginfo = &default_loginfo; - - sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, - prefix, - in ? in->name : "", - out ? out->name : ""); - - if (in != NULL) - dump_mac_header(m, loginfo, skb); - - dump_packet(m, loginfo, skb, skb_network_offset(skb), 1); - - sb_close(m); -} - -static unsigned int -log_tg6(struct sk_buff *skb, const struct xt_action_param *par) -{ - const struct ip6t_log_info *loginfo = par->targinfo; - struct nf_loginfo li; - - li.type = NF_LOG_TYPE_LOG; - li.u.log.level = loginfo->level; - li.u.log.logflags = loginfo->logflags; - - ip6t_log_packet(NFPROTO_IPV6, par->hooknum, skb, par->in, par->out, - &li, loginfo->prefix); - return XT_CONTINUE; -} - - -static int log_tg6_check(const struct xt_tgchk_param *par) -{ - const struct ip6t_log_info *loginfo = par->targinfo; - - if (loginfo->level >= 8) { - pr_debug("level %u >= 8\n", loginfo->level); - return -EINVAL; - } - if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { - pr_debug("prefix not null-terminated\n"); - return -EINVAL; - } - return 0; -} - -static struct xt_target log_tg6_reg __read_mostly = { - .name = "LOG", - .family = NFPROTO_IPV6, - .target = log_tg6, - .targetsize = sizeof(struct ip6t_log_info), - .checkentry = log_tg6_check, - .me = THIS_MODULE, -}; - -static struct nf_logger ip6t_logger __read_mostly = { - .name = "ip6t_LOG", - .logfn = &ip6t_log_packet, - .me = THIS_MODULE, -}; - -static int __init log_tg6_init(void) -{ - int ret; - - ret = xt_register_target(&log_tg6_reg); - if (ret < 0) - return ret; - nf_log_register(NFPROTO_IPV6, &ip6t_logger); - return 0; -} - -static void __exit log_tg6_exit(void) -{ - nf_log_unregister(&ip6t_logger); - xt_unregister_target(&log_tg6_reg); -} - -module_init(log_tg6_init); -module_exit(log_tg6_exit); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 7c05e7eacbc6..92cc9f2931ae 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -88,25 +88,31 @@ static int icmpv6_print_tuple(struct seq_file *s, ntohs(tuple->src.u.icmp.id)); } +static unsigned int *icmpv6_get_timeouts(struct net *net) +{ + return &nf_ct_icmpv6_timeout; +} + /* Returns verdict for packet, or -1 for invalid. */ static int icmpv6_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeout) { /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmpv6_timeout); + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { static const u_int8_t valid_new[] = { [ICMPV6_ECHO_REQUEST - 128] = 1, @@ -270,6 +276,44 @@ static int icmpv6_nlattr_tuple_size(void) } #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeout = data; + + if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) { + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ; + } else { + /* Set default ICMPv6 timeout. */ + *timeout = nf_ct_icmpv6_timeout; + } + return 0; +} + +static int +icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ)); + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { + [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static struct ctl_table_header *icmpv6_sysctl_header; static struct ctl_table icmpv6_sysctl_table[] = { @@ -293,6 +337,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = .invert_tuple = icmpv6_invert_tuple, .print_tuple = icmpv6_print_tuple, .packet = icmpv6_packet, + .get_timeouts = icmpv6_get_timeouts, .new = icmpv6_new, .error = icmpv6_error, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) @@ -301,6 +346,15 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = .nlattr_to_tuple = icmpv6_nlattr_to_tuple, .nla_policy = icmpv6_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, + .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_ICMP_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = icmpv6_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_header = &icmpv6_sysctl_header, .ctl_table = icmpv6_sysctl_table, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index f8ac4ef0b794..0c6f67e8f2e5 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -103,6 +103,16 @@ config NF_CONNTRACK_EVENTS If unsure, say `N'. +config NF_CONNTRACK_TIMEOUT + bool 'Connection tracking timeout' + depends on NETFILTER_ADVANCED + help + This option enables support for connection tracking timeout + extension. This allows you to attach timeout policies to flow + via the CT target. + + If unsure, say `N'. + config NF_CONNTRACK_TIMESTAMP bool 'Connection tracking timestamping' depends on NETFILTER_ADVANCED @@ -314,6 +324,17 @@ config NF_CT_NETLINK help This option enables support for a netlink-based userspace interface +config NF_CT_NETLINK_TIMEOUT + tristate 'Connection tracking timeout tuning via Netlink' + select NETFILTER_NETLINK + depends on NETFILTER_ADVANCED + help + This option enables support for connection tracking timeout + fine-grain tuning. This allows you to attach specific timeout + policies to flows, instead of using the global timeout policy. + + If unsure, say `N'. + endif # NF_CONNTRACK # transparent proxy support @@ -524,6 +545,15 @@ config NETFILTER_XT_TARGET_LED For more information on the LEDs available on your system, see Documentation/leds/leds-class.txt +config NETFILTER_XT_TARGET_LOG + tristate "LOG target support" + default m if NETFILTER_ADVANCED=n + help + This option adds a `LOG' target, which allows you to create rules in + any iptables table which records the packet header to the syslog. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_MARK tristate '"MARK" target support' depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 40f4c3d636c5..ca3676586f51 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -1,6 +1,7 @@ netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o +nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o @@ -22,6 +23,7 @@ obj-$(CONFIG_NF_CT_PROTO_UDPLITE) += nf_conntrack_proto_udplite.o # netlink interface for nf_conntrack obj-$(CONFIG_NF_CT_NETLINK) += nf_conntrack_netlink.o +obj-$(CONFIG_NF_CT_NETLINK_TIMEOUT) += nfnetlink_cttimeout.o # connection tracking helpers nf_conntrack_h323-objs := nf_conntrack_h323_main.o nf_conntrack_h323_asn1.o @@ -58,6 +60,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_CT) += xt_CT.o obj-$(CONFIG_NETFILTER_XT_TARGET_DSCP) += xt_DSCP.o obj-$(CONFIG_NETFILTER_XT_TARGET_HL) += xt_HL.o obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o +obj-$(CONFIG_NETFILTER_XT_TARGET_LOG) += xt_LOG.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o obj-$(CONFIG_NETFILTER_XT_TARGET_NOTRACK) += xt_NOTRACK.o diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index e3e73997c3be..a72a4dff0031 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -442,7 +442,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map, map->timeout = IPSET_NO_TIMEOUT; set->data = map; - set->family = AF_INET; + set->family = NFPROTO_IPV4; return true; } @@ -550,7 +550,7 @@ static struct ip_set_type bitmap_ip_type __read_mostly = { .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP, .dimension = IPSET_DIM_ONE, - .family = AF_INET, + .family = NFPROTO_IPV4, .revision_min = 0, .revision_max = 0, .create = bitmap_ip_create, diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 56096f544978..81324c12c5be 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -543,7 +543,7 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map, map->timeout = IPSET_NO_TIMEOUT; set->data = map; - set->family = AF_INET; + set->family = NFPROTO_IPV4; return true; } @@ -623,7 +623,7 @@ static struct ip_set_type bitmap_ipmac_type = { .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_MAC, .dimension = IPSET_DIM_TWO, - .family = AF_INET, + .family = NFPROTO_IPV4, .revision_min = 0, .revision_max = 0, .create = bitmap_ipmac_create, diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 29ba93bb94be..382ec28ba72e 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -422,7 +422,7 @@ init_map_port(struct ip_set *set, struct bitmap_port *map, map->timeout = IPSET_NO_TIMEOUT; set->data = map; - set->family = AF_UNSPEC; + set->family = NFPROTO_UNSPEC; return true; } @@ -483,7 +483,7 @@ static struct ip_set_type bitmap_port_type = { .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_PORT, .dimension = IPSET_DIM_ONE, - .family = AF_UNSPEC, + .family = NFPROTO_UNSPEC, .revision_min = 0, .revision_max = 0, .create = bitmap_port_create, diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e7f90e7082b4..e6c1c9605a58 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -69,7 +69,7 @@ find_set_type(const char *name, u8 family, u8 revision) list_for_each_entry_rcu(type, &ip_set_type_list, list) if (STREQ(type->name, name) && - (type->family == family || type->family == AF_UNSPEC) && + (type->family == family || type->family == NFPROTO_UNSPEC) && revision >= type->revision_min && revision <= type->revision_max) return type; @@ -149,7 +149,7 @@ __find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max, rcu_read_lock(); list_for_each_entry_rcu(type, &ip_set_type_list, list) if (STREQ(type->name, name) && - (type->family == family || type->family == AF_UNSPEC)) { + (type->family == family || type->family == NFPROTO_UNSPEC)) { found = true; if (type->revision_min < *min) *min = type->revision_min; @@ -164,8 +164,8 @@ __find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max, __find_set_type_minmax(name, family, min, max, true); } -#define family_name(f) ((f) == AF_INET ? "inet" : \ - (f) == AF_INET6 ? "inet6" : "any") +#define family_name(f) ((f) == NFPROTO_IPV4 ? "inet" : \ + (f) == NFPROTO_IPV6 ? "inet6" : "any") /* Register a set type structure. The type is identified by * the unique triple of name, family and revision. @@ -354,7 +354,7 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, pr_debug("set %s, index %u\n", set->name, index); if (opt->dim < set->type->dimension || - !(opt->family == set->family || set->family == AF_UNSPEC)) + !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return 0; read_lock_bh(&set->lock); @@ -387,7 +387,7 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, pr_debug("set %s, index %u\n", set->name, index); if (opt->dim < set->type->dimension || - !(opt->family == set->family || set->family == AF_UNSPEC)) + !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return 0; write_lock_bh(&set->lock); @@ -410,7 +410,7 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, pr_debug("set %s, index %u\n", set->name, index); if (opt->dim < set->type->dimension || - !(opt->family == set->family || set->family == AF_UNSPEC)) + !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return 0; write_lock_bh(&set->lock); @@ -575,7 +575,7 @@ start_msg(struct sk_buff *skb, u32 pid, u32 seq, unsigned int flags, return NULL; nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_INET; + nfmsg->nfgen_family = NFPROTO_IPV4; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c index 1f03556666f4..6fdf88ae2353 100644 --- a/net/netfilter/ipset/ip_set_getport.c +++ b/net/netfilter/ipset/ip_set_getport.c @@ -136,10 +136,10 @@ ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, __be16 *port) u8 proto; switch (pf) { - case AF_INET: + case NFPROTO_IPV4: ret = ip_set_get_ip4_port(skb, src, port, &proto); break; - case AF_INET6: + case NFPROTO_IPV6: ret = ip_set_get_ip6_port(skb, src, port, &proto); break; default: diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 4015fcaf87bc..5139dea6019e 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -366,11 +366,11 @@ hash_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) u8 netmask, hbits; struct ip_set_hash *h; - if (!(set->family == AF_INET || set->family == AF_INET6)) + if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; - netmask = set->family == AF_INET ? 32 : 128; + netmask = set->family == NFPROTO_IPV4 ? 32 : 128; pr_debug("Create set %s with family %s\n", - set->name, set->family == AF_INET ? "inet" : "inet6"); + set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6"); if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || @@ -389,8 +389,8 @@ hash_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) if (tb[IPSET_ATTR_NETMASK]) { netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]); - if ((set->family == AF_INET && netmask > 32) || - (set->family == AF_INET6 && netmask > 128) || + if ((set->family == NFPROTO_IPV4 && netmask > 32) || + (set->family == NFPROTO_IPV6 && netmask > 128) || netmask == 0) return -IPSET_ERR_INVALID_NETMASK; } @@ -419,15 +419,15 @@ hash_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) if (tb[IPSET_ATTR_TIMEOUT]) { h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_ip4_tvariant : &hash_ip6_tvariant; - if (set->family == AF_INET) + if (set->family == NFPROTO_IPV4) hash_ip4_gc_init(set); else hash_ip6_gc_init(set); } else { - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_ip4_variant : &hash_ip6_variant; } @@ -443,7 +443,7 @@ static struct ip_set_type hash_ip_type __read_mostly = { .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP, .dimension = IPSET_DIM_ONE, - .family = AF_UNSPEC, + .family = NFPROTO_UNSPEC, .revision_min = 0, .revision_max = 0, .create = hash_ip_create, diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 37d667e3f6f8..9c27e249c171 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -450,7 +450,7 @@ hash_ipport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; u8 hbits; - if (!(set->family == AF_INET || set->family == AF_INET6)) + if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || @@ -490,15 +490,15 @@ hash_ipport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) if (tb[IPSET_ATTR_TIMEOUT]) { h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_ipport4_tvariant : &hash_ipport6_tvariant; - if (set->family == AF_INET) + if (set->family == NFPROTO_IPV4) hash_ipport4_gc_init(set); else hash_ipport6_gc_init(set); } else { - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_ipport4_variant : &hash_ipport6_variant; } @@ -514,7 +514,7 @@ static struct ip_set_type hash_ipport_type __read_mostly = { .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, .dimension = IPSET_DIM_TWO, - .family = AF_UNSPEC, + .family = NFPROTO_UNSPEC, .revision_min = 0, .revision_max = 1, /* SCTP and UDPLITE support added */ .create = hash_ipport_create, diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index e69e2718fbe1..9134057c0728 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -468,7 +468,7 @@ hash_ipportip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; u8 hbits; - if (!(set->family == AF_INET || set->family == AF_INET6)) + if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || @@ -508,15 +508,15 @@ hash_ipportip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) if (tb[IPSET_ATTR_TIMEOUT]) { h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_ipportip4_tvariant : &hash_ipportip6_tvariant; - if (set->family == AF_INET) + if (set->family == NFPROTO_IPV4) hash_ipportip4_gc_init(set); else hash_ipportip6_gc_init(set); } else { - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_ipportip4_variant : &hash_ipportip6_variant; } @@ -532,7 +532,7 @@ static struct ip_set_type hash_ipportip_type __read_mostly = { .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, .dimension = IPSET_DIM_THREE, - .family = AF_UNSPEC, + .family = NFPROTO_UNSPEC, .revision_min = 0, .revision_max = 1, /* SCTP and UDPLITE support added */ .create = hash_ipportip_create, diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 64199b4e93c9..5d05e6969862 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -41,12 +41,19 @@ hash_ipportnet_same_set(const struct ip_set *a, const struct ip_set *b); /* The type variant functions: IPv4 */ +/* We squeeze the "nomatch" flag into cidr: we don't support cidr == 0 + * However this way we have to store internally cidr - 1, + * dancing back and forth. + */ +#define IP_SET_HASH_WITH_NETS_PACKED + /* Member elements without timeout */ struct hash_ipportnet4_elem { __be32 ip; __be32 ip2; __be16 port; - u8 cidr; + u8 cidr:7; + u8 nomatch:1; u8 proto; }; @@ -55,7 +62,8 @@ struct hash_ipportnet4_telem { __be32 ip; __be32 ip2; __be16 port; - u8 cidr; + u8 cidr:7; + u8 nomatch:1; u8 proto; unsigned long timeout; }; @@ -86,10 +94,22 @@ hash_ipportnet4_data_copy(struct hash_ipportnet4_elem *dst, } static inline void +hash_ipportnet4_data_flags(struct hash_ipportnet4_elem *dst, u32 flags) +{ + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline bool +hash_ipportnet4_data_match(const struct hash_ipportnet4_elem *elem) +{ + return !elem->nomatch; +} + +static inline void hash_ipportnet4_data_netmask(struct hash_ipportnet4_elem *elem, u8 cidr) { elem->ip2 &= ip_set_netmask(cidr); - elem->cidr = cidr; + elem->cidr = cidr - 1; } static inline void @@ -102,11 +122,15 @@ static bool hash_ipportnet4_data_list(struct sk_buff *skb, const struct hash_ipportnet4_elem *data) { + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP2, data->ip2); NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr + 1); NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; nla_put_failure: @@ -119,14 +143,17 @@ hash_ipportnet4_data_tlist(struct sk_buff *skb, { const struct hash_ipportnet4_telem *tdata = (const struct hash_ipportnet4_telem *)data; + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP2, tdata->ip2); NLA_PUT_NET16(skb, IPSET_ATTR_PORT, tdata->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr + 1); NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(ip_set_timeout_get(tdata->timeout))); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; @@ -158,13 +185,11 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet4_elem data = { - .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1 }; - if (data.cidr == 0) - return -EINVAL; if (adt == IPSET_TEST) - data.cidr = HOST_MASK; + data.cidr = HOST_MASK - 1; if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) @@ -172,7 +197,7 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip); ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &data.ip2); - data.ip2 &= ip_set_netmask(data.cidr); + data.ip2 &= ip_set_netmask(data.cidr + 1); return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } @@ -183,17 +208,19 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_ipportnet4_elem data = { .cidr = HOST_MASK }; + struct hash_ipportnet4_elem data = { .cidr = HOST_MASK - 1 }; u32 ip, ip_to = 0, p = 0, port, port_to; u32 ip2_from = 0, ip2_to, ip2_last, ip2; u32 timeout = h->timeout; bool with_ports = false; + u8 cidr; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (tb[IPSET_ATTR_LINENO]) @@ -208,9 +235,10 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], return ret; if (tb[IPSET_ATTR_CIDR2]) { - data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!data.cidr) + cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]); + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; + data.cidr = cidr - 1; } if (tb[IPSET_ATTR_PORT]) @@ -236,12 +264,18 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } + if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) { + u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) + flags |= (cadt_flags << 16); + } + with_ports = with_ports && tb[IPSET_ATTR_PORT_TO]; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_IP_TO] || with_ports || tb[IPSET_ATTR_IP2_TO])) { data.ip = htonl(ip); - data.ip2 = htonl(ip2_from & ip_set_hostmask(data.cidr)); + data.ip2 = htonl(ip2_from & ip_set_hostmask(data.cidr + 1)); ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -275,7 +309,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (ip2_from + UINT_MAX == ip2_to) return -IPSET_ERR_HASH_RANGE; } else { - ip_set_mask_from_to(ip2_from, ip2_to, data.cidr); + ip_set_mask_from_to(ip2_from, ip2_to, data.cidr + 1); } if (retried) @@ -290,7 +324,8 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], while (!after(ip2, ip2_to)) { data.ip2 = htonl(ip2); ip2_last = ip_set_range_to_cidr(ip2, ip2_to, - &data.cidr); + &cidr); + data.cidr = cidr - 1; ret = adtfn(set, &data, timeout, flags); if (ret && !ip_set_eexist(ret, flags)) @@ -321,7 +356,8 @@ struct hash_ipportnet6_elem { union nf_inet_addr ip; union nf_inet_addr ip2; __be16 port; - u8 cidr; + u8 cidr:7; + u8 nomatch:1; u8 proto; }; @@ -329,7 +365,8 @@ struct hash_ipportnet6_telem { union nf_inet_addr ip; union nf_inet_addr ip2; __be16 port; - u8 cidr; + u8 cidr:7; + u8 nomatch:1; u8 proto; unsigned long timeout; }; @@ -360,6 +397,18 @@ hash_ipportnet6_data_copy(struct hash_ipportnet6_elem *dst, } static inline void +hash_ipportnet6_data_flags(struct hash_ipportnet6_elem *dst, u32 flags) +{ + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline bool +hash_ipportnet6_data_match(const struct hash_ipportnet6_elem *elem) +{ + return !elem->nomatch; +} + +static inline void hash_ipportnet6_data_zero_out(struct hash_ipportnet6_elem *elem) { elem->proto = 0; @@ -378,18 +427,22 @@ static inline void hash_ipportnet6_data_netmask(struct hash_ipportnet6_elem *elem, u8 cidr) { ip6_netmask(&elem->ip2, cidr); - elem->cidr = cidr; + elem->cidr = cidr - 1; } static bool hash_ipportnet6_data_list(struct sk_buff *skb, const struct hash_ipportnet6_elem *data) { + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP2, &data->ip2); NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr + 1); NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; nla_put_failure: @@ -402,14 +455,17 @@ hash_ipportnet6_data_tlist(struct sk_buff *skb, { const struct hash_ipportnet6_telem *e = (const struct hash_ipportnet6_telem *)data; + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP2, &data->ip2); NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr + 1); NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(ip_set_timeout_get(e->timeout))); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; nla_put_failure: @@ -438,13 +494,11 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet6_elem data = { - .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1 }; - if (data.cidr == 0) - return -EINVAL; if (adt == IPSET_TEST) - data.cidr = HOST_MASK; + data.cidr = HOST_MASK - 1; if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) @@ -452,7 +506,7 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6); ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &data.ip2.in6); - ip6_netmask(&data.ip2, data.cidr); + ip6_netmask(&data.ip2, data.cidr + 1); return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } @@ -463,16 +517,18 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_ipportnet6_elem data = { .cidr = HOST_MASK }; + struct hash_ipportnet6_elem data = { .cidr = HOST_MASK - 1 }; u32 port, port_to; u32 timeout = h->timeout; bool with_ports = false; + u8 cidr; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) return -IPSET_ERR_PROTOCOL; @@ -490,13 +546,14 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; - if (tb[IPSET_ATTR_CIDR2]) - data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - - if (!data.cidr) - return -IPSET_ERR_INVALID_CIDR; + if (tb[IPSET_ATTR_CIDR2]) { + cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]); + if (!cidr || cidr > HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + data.cidr = cidr - 1; + } - ip6_netmask(&data.ip2, data.cidr); + ip6_netmask(&data.ip2, data.cidr + 1); if (tb[IPSET_ATTR_PORT]) data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); @@ -521,6 +578,12 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } + if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) { + u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) + flags |= (cadt_flags << 16); + } + if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; @@ -554,7 +617,7 @@ hash_ipportnet_create(struct ip_set *set, struct nlattr *tb[], u32 flags) u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; u8 hbits; - if (!(set->family == AF_INET || set->family == AF_INET6)) + if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || @@ -573,7 +636,7 @@ hash_ipportnet_create(struct ip_set *set, struct nlattr *tb[], u32 flags) h = kzalloc(sizeof(*h) + sizeof(struct ip_set_hash_nets) - * (set->family == AF_INET ? 32 : 128), GFP_KERNEL); + * (set->family == NFPROTO_IPV4 ? 32 : 128), GFP_KERNEL); if (!h) return -ENOMEM; @@ -596,16 +659,16 @@ hash_ipportnet_create(struct ip_set *set, struct nlattr *tb[], u32 flags) if (tb[IPSET_ATTR_TIMEOUT]) { h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_ipportnet4_tvariant : &hash_ipportnet6_tvariant; - if (set->family == AF_INET) + if (set->family == NFPROTO_IPV4) hash_ipportnet4_gc_init(set); else hash_ipportnet6_gc_init(set); } else { - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_ipportnet4_variant : &hash_ipportnet6_variant; } @@ -621,10 +684,11 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = { .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, .dimension = IPSET_DIM_THREE, - .family = AF_UNSPEC, + .family = NFPROTO_UNSPEC, .revision_min = 0, /* 1 SCTP and UDPLITE support added */ - .revision_max = 2, /* Range as input support for IPv4 added */ + /* 2 Range as input support for IPv4 added */ + .revision_max = 3, /* nomatch flag support added */ .create = hash_ipportnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, @@ -643,6 +707,7 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = { [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_CIDR2] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, + [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, }, diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 28988196775e..7c3d945517cf 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -43,7 +43,7 @@ hash_net_same_set(const struct ip_set *a, const struct ip_set *b); struct hash_net4_elem { __be32 ip; u16 padding0; - u8 padding1; + u8 nomatch; u8 cidr; }; @@ -51,7 +51,7 @@ struct hash_net4_elem { struct hash_net4_telem { __be32 ip; u16 padding0; - u8 padding1; + u8 nomatch; u8 cidr; unsigned long timeout; }; @@ -61,7 +61,8 @@ hash_net4_data_equal(const struct hash_net4_elem *ip1, const struct hash_net4_elem *ip2, u32 *multi) { - return ip1->ip == ip2->ip && ip1->cidr == ip2->cidr; + return ip1->ip == ip2->ip && + ip1->cidr == ip2->cidr; } static inline bool @@ -76,6 +77,19 @@ hash_net4_data_copy(struct hash_net4_elem *dst, { dst->ip = src->ip; dst->cidr = src->cidr; + dst->nomatch = src->nomatch; +} + +static inline void +hash_net4_data_flags(struct hash_net4_elem *dst, u32 flags) +{ + dst->nomatch = flags & IPSET_FLAG_NOMATCH; +} + +static inline bool +hash_net4_data_match(const struct hash_net4_elem *elem) +{ + return !elem->nomatch; } static inline void @@ -95,8 +109,12 @@ hash_net4_data_zero_out(struct hash_net4_elem *elem) static bool hash_net4_data_list(struct sk_buff *skb, const struct hash_net4_elem *data) { + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; nla_put_failure: @@ -108,11 +126,14 @@ hash_net4_data_tlist(struct sk_buff *skb, const struct hash_net4_elem *data) { const struct hash_net4_telem *tdata = (const struct hash_net4_telem *)data; + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); NLA_PUT_U8(skb, IPSET_ATTR_CIDR, tdata->cidr); NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(ip_set_timeout_get(tdata->timeout))); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; @@ -167,7 +188,8 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], int ret; if (unlikely(!tb[IPSET_ATTR_IP] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (tb[IPSET_ATTR_LINENO]) @@ -179,7 +201,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!data.cidr) + if (!data.cidr || data.cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } @@ -189,6 +211,12 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } + if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) { + u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) + flags |= (cadt_flags << 16); + } + if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { data.ip = htonl(ip & ip_set_hostmask(data.cidr)); ret = adtfn(set, &data, timeout, flags); @@ -236,14 +264,14 @@ hash_net_same_set(const struct ip_set *a, const struct ip_set *b) struct hash_net6_elem { union nf_inet_addr ip; u16 padding0; - u8 padding1; + u8 nomatch; u8 cidr; }; struct hash_net6_telem { union nf_inet_addr ip; u16 padding0; - u8 padding1; + u8 nomatch; u8 cidr; unsigned long timeout; }; @@ -269,6 +297,19 @@ hash_net6_data_copy(struct hash_net6_elem *dst, { dst->ip.in6 = src->ip.in6; dst->cidr = src->cidr; + dst->nomatch = src->nomatch; +} + +static inline void +hash_net6_data_flags(struct hash_net6_elem *dst, u32 flags) +{ + dst->nomatch = flags & IPSET_FLAG_NOMATCH; +} + +static inline bool +hash_net6_data_match(const struct hash_net6_elem *elem) +{ + return !elem->nomatch; } static inline void @@ -296,8 +337,12 @@ hash_net6_data_netmask(struct hash_net6_elem *elem, u8 cidr) static bool hash_net6_data_list(struct sk_buff *skb, const struct hash_net6_elem *data) { + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; nla_put_failure: @@ -309,11 +354,14 @@ hash_net6_data_tlist(struct sk_buff *skb, const struct hash_net6_elem *data) { const struct hash_net6_telem *e = (const struct hash_net6_telem *)data; + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); NLA_PUT_U8(skb, IPSET_ATTR_CIDR, e->cidr); NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(ip_set_timeout_get(e->timeout))); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; nla_put_failure: @@ -366,7 +414,8 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], int ret; if (unlikely(!tb[IPSET_ATTR_IP] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; @@ -381,7 +430,7 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!data.cidr) + if (!data.cidr || data.cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip6_netmask(&data.ip, data.cidr); @@ -392,6 +441,12 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } + if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) { + u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) + flags |= (cadt_flags << 16); + } + ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; @@ -406,7 +461,7 @@ hash_net_create(struct ip_set *set, struct nlattr *tb[], u32 flags) struct ip_set_hash *h; u8 hbits; - if (!(set->family == AF_INET || set->family == AF_INET6)) + if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || @@ -425,7 +480,7 @@ hash_net_create(struct ip_set *set, struct nlattr *tb[], u32 flags) h = kzalloc(sizeof(*h) + sizeof(struct ip_set_hash_nets) - * (set->family == AF_INET ? 32 : 128), GFP_KERNEL); + * (set->family == NFPROTO_IPV4 ? 32 : 128), GFP_KERNEL); if (!h) return -ENOMEM; @@ -448,15 +503,15 @@ hash_net_create(struct ip_set *set, struct nlattr *tb[], u32 flags) if (tb[IPSET_ATTR_TIMEOUT]) { h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_net4_tvariant : &hash_net6_tvariant; - if (set->family == AF_INET) + if (set->family == NFPROTO_IPV4) hash_net4_gc_init(set); else hash_net6_gc_init(set); } else { - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_net4_variant : &hash_net6_variant; } @@ -472,9 +527,10 @@ static struct ip_set_type hash_net_type __read_mostly = { .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP, .dimension = IPSET_DIM_ONE, - .family = AF_UNSPEC, + .family = NFPROTO_UNSPEC, .revision_min = 0, - .revision_max = 1, /* Range as input support for IPv4 added */ + /* = 1 Range as input support for IPv4 added */ + .revision_max = 2, /* nomatch flag support added */ .create = hash_net_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, @@ -488,6 +544,7 @@ static struct ip_set_type hash_net_type __read_mostly = { [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .me = THIS_MODULE, }; diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index e13095deb50d..f24037ff4322 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -163,7 +163,8 @@ struct hash_netiface4_elem_hashed { __be32 ip; u8 physdev; u8 cidr; - u16 padding; + u8 nomatch; + u8 padding; }; #define HKEY_DATALEN sizeof(struct hash_netiface4_elem_hashed) @@ -173,7 +174,8 @@ struct hash_netiface4_elem { __be32 ip; u8 physdev; u8 cidr; - u16 padding; + u8 nomatch; + u8 padding; const char *iface; }; @@ -182,7 +184,8 @@ struct hash_netiface4_telem { __be32 ip; u8 physdev; u8 cidr; - u16 padding; + u8 nomatch; + u8 padding; const char *iface; unsigned long timeout; }; @@ -207,11 +210,25 @@ hash_netiface4_data_isnull(const struct hash_netiface4_elem *elem) static inline void hash_netiface4_data_copy(struct hash_netiface4_elem *dst, - const struct hash_netiface4_elem *src) { + const struct hash_netiface4_elem *src) +{ dst->ip = src->ip; dst->cidr = src->cidr; dst->physdev = src->physdev; dst->iface = src->iface; + dst->nomatch = src->nomatch; +} + +static inline void +hash_netiface4_data_flags(struct hash_netiface4_elem *dst, u32 flags) +{ + dst->nomatch = flags & IPSET_FLAG_NOMATCH; +} + +static inline bool +hash_netiface4_data_match(const struct hash_netiface4_elem *elem) +{ + return !elem->nomatch; } static inline void @@ -233,11 +250,13 @@ hash_netiface4_data_list(struct sk_buff *skb, { u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0; + if (data->nomatch) + flags |= IPSET_FLAG_NOMATCH; NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, flags); + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; nla_put_failure: @@ -252,11 +271,13 @@ hash_netiface4_data_tlist(struct sk_buff *skb, (const struct hash_netiface4_telem *)data; u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0; + if (data->nomatch) + flags |= IPSET_FLAG_NOMATCH; NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, flags); + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(ip_set_timeout_get(tdata->timeout))); @@ -361,7 +382,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!data.cidr) + if (!data.cidr || data.cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } @@ -387,6 +408,8 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_PHYSDEV) data.physdev = 1; + if (adt == IPSET_ADD && (cadt_flags & IPSET_FLAG_NOMATCH)) + flags |= (cadt_flags << 16); } if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { @@ -440,7 +463,8 @@ struct hash_netiface6_elem_hashed { union nf_inet_addr ip; u8 physdev; u8 cidr; - u16 padding; + u8 nomatch; + u8 padding; }; #define HKEY_DATALEN sizeof(struct hash_netiface6_elem_hashed) @@ -449,7 +473,8 @@ struct hash_netiface6_elem { union nf_inet_addr ip; u8 physdev; u8 cidr; - u16 padding; + u8 nomatch; + u8 padding; const char *iface; }; @@ -457,7 +482,8 @@ struct hash_netiface6_telem { union nf_inet_addr ip; u8 physdev; u8 cidr; - u16 padding; + u8 nomatch; + u8 padding; const char *iface; unsigned long timeout; }; @@ -488,8 +514,21 @@ hash_netiface6_data_copy(struct hash_netiface6_elem *dst, } static inline void +hash_netiface6_data_flags(struct hash_netiface6_elem *dst, u32 flags) +{ + dst->nomatch = flags & IPSET_FLAG_NOMATCH; +} + +static inline bool +hash_netiface6_data_match(const struct hash_netiface6_elem *elem) +{ + return !elem->nomatch; +} + +static inline void hash_netiface6_data_zero_out(struct hash_netiface6_elem *elem) { + elem->cidr = 0; } static inline void @@ -514,11 +553,13 @@ hash_netiface6_data_list(struct sk_buff *skb, { u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0; + if (data->nomatch) + flags |= IPSET_FLAG_NOMATCH; NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, flags); + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; nla_put_failure: @@ -533,11 +574,13 @@ hash_netiface6_data_tlist(struct sk_buff *skb, (const struct hash_netiface6_telem *)data; u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0; + if (data->nomatch) + flags |= IPSET_FLAG_NOMATCH; NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); if (flags) - NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, flags); + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(ip_set_timeout_get(e->timeout))); return 0; @@ -636,7 +679,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!data.cidr) + if (!data.cidr || data.cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip6_netmask(&data.ip, data.cidr); @@ -662,6 +705,8 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_PHYSDEV) data.physdev = 1; + if (adt == IPSET_ADD && (cadt_flags & IPSET_FLAG_NOMATCH)) + flags |= (cadt_flags << 16); } ret = adtfn(set, &data, timeout, flags); @@ -678,7 +723,7 @@ hash_netiface_create(struct ip_set *set, struct nlattr *tb[], u32 flags) u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; u8 hbits; - if (!(set->family == AF_INET || set->family == AF_INET6)) + if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || @@ -697,7 +742,7 @@ hash_netiface_create(struct ip_set *set, struct nlattr *tb[], u32 flags) h = kzalloc(sizeof(*h) + sizeof(struct ip_set_hash_nets) - * (set->family == AF_INET ? 32 : 128), GFP_KERNEL); + * (set->family == NFPROTO_IPV4 ? 32 : 128), GFP_KERNEL); if (!h) return -ENOMEM; @@ -722,15 +767,15 @@ hash_netiface_create(struct ip_set *set, struct nlattr *tb[], u32 flags) if (tb[IPSET_ATTR_TIMEOUT]) { h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_netiface4_tvariant : &hash_netiface6_tvariant; - if (set->family == AF_INET) + if (set->family == NFPROTO_IPV4) hash_netiface4_gc_init(set); else hash_netiface6_gc_init(set); } else { - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_netiface4_variant : &hash_netiface6_variant; } @@ -746,8 +791,9 @@ static struct ip_set_type hash_netiface_type __read_mostly = { .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_IFACE, .dimension = IPSET_DIM_TWO, - .family = AF_UNSPEC, + .family = NFPROTO_UNSPEC, .revision_min = 0, + .revision_max = 1, /* nomatch flag support added */ .create = hash_netiface_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 8f9de7207ec9..ce2e77100b64 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -40,12 +40,19 @@ hash_netport_same_set(const struct ip_set *a, const struct ip_set *b); /* The type variant functions: IPv4 */ +/* We squeeze the "nomatch" flag into cidr: we don't support cidr == 0 + * However this way we have to store internally cidr - 1, + * dancing back and forth. + */ +#define IP_SET_HASH_WITH_NETS_PACKED + /* Member elements without timeout */ struct hash_netport4_elem { __be32 ip; __be16 port; u8 proto; - u8 cidr; + u8 cidr:7; + u8 nomatch:1; }; /* Member elements with timeout support */ @@ -53,7 +60,8 @@ struct hash_netport4_telem { __be32 ip; __be16 port; u8 proto; - u8 cidr; + u8 cidr:7; + u8 nomatch:1; unsigned long timeout; }; @@ -82,13 +90,26 @@ hash_netport4_data_copy(struct hash_netport4_elem *dst, dst->port = src->port; dst->proto = src->proto; dst->cidr = src->cidr; + dst->nomatch = src->nomatch; +} + +static inline void +hash_netport4_data_flags(struct hash_netport4_elem *dst, u32 flags) +{ + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline bool +hash_netport4_data_match(const struct hash_netport4_elem *elem) +{ + return !elem->nomatch; } static inline void hash_netport4_data_netmask(struct hash_netport4_elem *elem, u8 cidr) { elem->ip &= ip_set_netmask(cidr); - elem->cidr = cidr; + elem->cidr = cidr - 1; } static inline void @@ -101,10 +122,14 @@ static bool hash_netport4_data_list(struct sk_buff *skb, const struct hash_netport4_elem *data) { + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr + 1); NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; nla_put_failure: @@ -117,13 +142,16 @@ hash_netport4_data_tlist(struct sk_buff *skb, { const struct hash_netport4_telem *tdata = (const struct hash_netport4_telem *)data; + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); NLA_PUT_NET16(skb, IPSET_ATTR_PORT, tdata->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr + 1); NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(ip_set_timeout_get(tdata->timeout))); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; @@ -154,20 +182,18 @@ hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem data = { - .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1 }; - if (data.cidr == 0) - return -EINVAL; if (adt == IPSET_TEST) - data.cidr = HOST_MASK; + data.cidr = HOST_MASK - 1; if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) return -EINVAL; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip); - data.ip &= ip_set_netmask(data.cidr); + data.ip &= ip_set_netmask(data.cidr + 1); return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } @@ -178,16 +204,18 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netport4_elem data = { .cidr = HOST_MASK }; + struct hash_netport4_elem data = { .cidr = HOST_MASK - 1 }; u32 port, port_to, p = 0, ip = 0, ip_to, last; u32 timeout = h->timeout; bool with_ports = false; + u8 cidr; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (tb[IPSET_ATTR_LINENO]) @@ -198,9 +226,10 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], return ret; if (tb[IPSET_ATTR_CIDR]) { - data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!data.cidr) + cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; + data.cidr = cidr - 1; } if (tb[IPSET_ATTR_PORT]) @@ -227,8 +256,15 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], } with_ports = with_ports && tb[IPSET_ATTR_PORT_TO]; + + if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) { + u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) + flags |= (cadt_flags << 16); + } + if (adt == IPSET_TEST || !(with_ports || tb[IPSET_ATTR_IP_TO])) { - data.ip = htonl(ip & ip_set_hostmask(data.cidr)); + data.ip = htonl(ip & ip_set_hostmask(data.cidr + 1)); ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -248,14 +284,15 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } else { - ip_set_mask_from_to(ip, ip_to, data.cidr); + ip_set_mask_from_to(ip, ip_to, data.cidr + 1); } if (retried) ip = h->next.ip; while (!after(ip, ip_to)) { data.ip = htonl(ip); - last = ip_set_range_to_cidr(ip, ip_to, &data.cidr); + last = ip_set_range_to_cidr(ip, ip_to, &cidr); + data.cidr = cidr - 1; p = retried && ip == h->next.ip ? h->next.port : port; for (; p <= port_to; p++) { data.port = htons(p); @@ -288,14 +325,16 @@ struct hash_netport6_elem { union nf_inet_addr ip; __be16 port; u8 proto; - u8 cidr; + u8 cidr:7; + u8 nomatch:1; }; struct hash_netport6_telem { union nf_inet_addr ip; __be16 port; u8 proto; - u8 cidr; + u8 cidr:7; + u8 nomatch:1; unsigned long timeout; }; @@ -324,6 +363,18 @@ hash_netport6_data_copy(struct hash_netport6_elem *dst, } static inline void +hash_netport6_data_flags(struct hash_netport6_elem *dst, u32 flags) +{ + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline bool +hash_netport6_data_match(const struct hash_netport6_elem *elem) +{ + return !elem->nomatch; +} + +static inline void hash_netport6_data_zero_out(struct hash_netport6_elem *elem) { elem->proto = 0; @@ -342,17 +393,21 @@ static inline void hash_netport6_data_netmask(struct hash_netport6_elem *elem, u8 cidr) { ip6_netmask(&elem->ip, cidr); - elem->cidr = cidr; + elem->cidr = cidr - 1; } static bool hash_netport6_data_list(struct sk_buff *skb, const struct hash_netport6_elem *data) { + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr + 1); NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; nla_put_failure: @@ -365,13 +420,16 @@ hash_netport6_data_tlist(struct sk_buff *skb, { const struct hash_netport6_telem *e = (const struct hash_netport6_telem *)data; + u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); - NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr + 1); NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(ip_set_timeout_get(e->timeout))); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)); return 0; nla_put_failure: @@ -400,20 +458,18 @@ hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem data = { - .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1, }; - if (data.cidr == 0) - return -EINVAL; if (adt == IPSET_TEST) - data.cidr = HOST_MASK; + data.cidr = HOST_MASK - 1; if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) return -EINVAL; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6); - ip6_netmask(&data.ip, data.cidr); + ip6_netmask(&data.ip, data.cidr + 1); return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } @@ -424,16 +480,18 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netport6_elem data = { .cidr = HOST_MASK }; + struct hash_netport6_elem data = { .cidr = HOST_MASK - 1 }; u32 port, port_to; u32 timeout = h->timeout; bool with_ports = false; + u8 cidr; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; @@ -445,11 +503,13 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; - if (tb[IPSET_ATTR_CIDR]) - data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!data.cidr) - return -IPSET_ERR_INVALID_CIDR; - ip6_netmask(&data.ip, data.cidr); + if (tb[IPSET_ATTR_CIDR]) { + cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + if (!cidr || cidr > HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + data.cidr = cidr - 1; + } + ip6_netmask(&data.ip, data.cidr + 1); if (tb[IPSET_ATTR_PORT]) data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); @@ -474,6 +534,12 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } + if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) { + u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) + flags |= (cadt_flags << 16); + } + if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; @@ -507,7 +573,7 @@ hash_netport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; u8 hbits; - if (!(set->family == AF_INET || set->family == AF_INET6)) + if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || @@ -526,7 +592,7 @@ hash_netport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) h = kzalloc(sizeof(*h) + sizeof(struct ip_set_hash_nets) - * (set->family == AF_INET ? 32 : 128), GFP_KERNEL); + * (set->family == NFPROTO_IPV4 ? 32 : 128), GFP_KERNEL); if (!h) return -ENOMEM; @@ -549,15 +615,15 @@ hash_netport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) if (tb[IPSET_ATTR_TIMEOUT]) { h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_netport4_tvariant : &hash_netport6_tvariant; - if (set->family == AF_INET) + if (set->family == NFPROTO_IPV4) hash_netport4_gc_init(set); else hash_netport6_gc_init(set); } else { - set->variant = set->family == AF_INET + set->variant = set->family == NFPROTO_IPV4 ? &hash_netport4_variant : &hash_netport6_variant; } @@ -573,10 +639,11 @@ static struct ip_set_type hash_netport_type __read_mostly = { .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, .dimension = IPSET_DIM_TWO, - .family = AF_UNSPEC, + .family = NFPROTO_UNSPEC, .revision_min = 0, /* 1 SCTP and UDPLITE support added */ - .revision_max = 2, /* Range as input support for IPv4 added */ + /* 2, Range as input support for IPv4 added */ + .revision_max = 3, /* nomatch flag support added */ .create = hash_netport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, @@ -595,6 +662,7 @@ static struct ip_set_type hash_netport_type __read_mostly = { [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .me = THIS_MODULE, }; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 4d10819d462e..7e095f9005f0 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -575,7 +575,7 @@ static struct ip_set_type list_set_type __read_mostly = { .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_NAME | IPSET_DUMP_LAST, .dimension = IPSET_DIM_ONE, - .family = AF_UNSPEC, + .family = NFPROTO_UNSPEC, .revision_min = 0, .revision_max = 0, .create = list_set_create, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ed86a3be678e..81e2aa4ca1fe 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -44,6 +44,7 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> +#include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_core.h> @@ -763,7 +764,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_l3proto *l3proto, struct nf_conntrack_l4proto *l4proto, struct sk_buff *skb, - unsigned int dataoff, u32 hash) + unsigned int dataoff, u32 hash, + unsigned int *timeouts) { struct nf_conn *ct; struct nf_conn_help *help; @@ -782,7 +784,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, if (IS_ERR(ct)) return (struct nf_conntrack_tuple_hash *)ct; - if (!l4proto->new(ct, skb, dataoff)) { + if (!l4proto->new(ct, skb, dataoff, timeouts)) { nf_conntrack_free(ct); pr_debug("init conntrack: can't track with proto module\n"); return NULL; @@ -848,7 +850,8 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_l3proto *l3proto, struct nf_conntrack_l4proto *l4proto, int *set_reply, - enum ip_conntrack_info *ctinfo) + enum ip_conntrack_info *ctinfo, + unsigned int *timeouts) { struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; @@ -868,7 +871,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, h = __nf_conntrack_find_get(net, zone, &tuple, hash); if (!h) { h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto, - skb, dataoff, hash); + skb, dataoff, hash, timeouts); if (!h) return NULL; if (IS_ERR(h)) @@ -909,6 +912,8 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, enum ip_conntrack_info ctinfo; struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; + struct nf_conn_timeout *timeout_ext; + unsigned int *timeouts; unsigned int dataoff; u_int8_t protonum; int set_reply = 0; @@ -955,8 +960,19 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, goto out; } + /* Decide what timeout policy we want to apply to this flow. */ + if (tmpl) { + timeout_ext = nf_ct_timeout_find(tmpl); + if (timeout_ext) + timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext); + else + timeouts = l4proto->get_timeouts(net); + } else + timeouts = l4proto->get_timeouts(net); + ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, - l3proto, l4proto, &set_reply, &ctinfo); + l3proto, l4proto, &set_reply, &ctinfo, + timeouts); if (!ct) { /* Not valid part of a connection */ NF_CT_STAT_INC_ATOMIC(net, invalid); @@ -973,7 +989,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, NF_CT_ASSERT(skb->nfct); - ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum); + ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum, timeouts); if (ret <= 0) { /* Invalid: inverse of the return code tells * the netfilter core what to do */ @@ -1327,6 +1343,7 @@ static void nf_conntrack_cleanup_net(struct net *net) } nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); + nf_conntrack_timeout_fini(net); nf_conntrack_ecache_fini(net); nf_conntrack_tstamp_fini(net); nf_conntrack_acct_fini(net); @@ -1558,9 +1575,14 @@ static int nf_conntrack_init_net(struct net *net) ret = nf_conntrack_ecache_init(net); if (ret < 0) goto err_ecache; + ret = nf_conntrack_timeout_init(net); + if (ret < 0) + goto err_timeout; return 0; +err_timeout: + nf_conntrack_timeout_fini(net); err_ecache: nf_conntrack_tstamp_fini(net); err_tstamp: diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 14af6329bdda..5bd3047ddeec 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -32,9 +32,11 @@ static DEFINE_MUTEX(nf_ct_ecache_mutex); void nf_ct_deliver_cached_events(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); - unsigned long events; + unsigned long events, missed; struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; + struct nf_ct_event item; + int ret; rcu_read_lock(); notify = rcu_dereference(net->ct.nf_conntrack_event_cb); @@ -47,31 +49,32 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct) events = xchg(&e->cache, 0); - if (nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct) && events) { - struct nf_ct_event item = { - .ct = ct, - .pid = 0, - .report = 0 - }; - int ret; - /* We make a copy of the missed event cache without taking - * the lock, thus we may send missed events twice. However, - * this does not harm and it happens very rarely. */ - unsigned long missed = e->missed; - - if (!((events | missed) & e->ctmask)) - goto out_unlock; - - ret = notify->fcn(events | missed, &item); - if (unlikely(ret < 0 || missed)) { - spin_lock_bh(&ct->lock); - if (ret < 0) - e->missed |= events; - else - e->missed &= ~missed; - spin_unlock_bh(&ct->lock); - } - } + if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct) || !events) + goto out_unlock; + + /* We make a copy of the missed event cache without taking + * the lock, thus we may send missed events twice. However, + * this does not harm and it happens very rarely. */ + missed = e->missed; + + if (!((events | missed) & e->ctmask)) + goto out_unlock; + + item.ct = ct; + item.pid = 0; + item.report = 0; + + ret = notify->fcn(events | missed, &item); + + if (likely(ret >= 0 && !missed)) + goto out_unlock; + + spin_lock_bh(&ct->lock); + if (ret < 0) + e->missed |= events; + else + e->missed &= ~missed; + spin_unlock_bh(&ct->lock); out_unlock: rcu_read_unlock(); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index bbe23baa19b6..436b7cb79ba4 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -181,6 +181,60 @@ void nf_ct_helper_destroy(struct nf_conn *ct) } } +static LIST_HEAD(nf_ct_helper_expectfn_list); + +void nf_ct_helper_expectfn_register(struct nf_ct_helper_expectfn *n) +{ + spin_lock_bh(&nf_conntrack_lock); + list_add_rcu(&n->head, &nf_ct_helper_expectfn_list); + spin_unlock_bh(&nf_conntrack_lock); +} +EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_register); + +void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n) +{ + spin_lock_bh(&nf_conntrack_lock); + list_del_rcu(&n->head); + spin_unlock_bh(&nf_conntrack_lock); +} +EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister); + +struct nf_ct_helper_expectfn * +nf_ct_helper_expectfn_find_by_name(const char *name) +{ + struct nf_ct_helper_expectfn *cur; + bool found = false; + + rcu_read_lock(); + list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) { + if (!strcmp(cur->name, name)) { + found = true; + break; + } + } + rcu_read_unlock(); + return found ? cur : NULL; +} +EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_name); + +struct nf_ct_helper_expectfn * +nf_ct_helper_expectfn_find_by_symbol(const void *symbol) +{ + struct nf_ct_helper_expectfn *cur; + bool found = false; + + rcu_read_lock(); + list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) { + if (cur->expectfn == symbol) { + found = true; + break; + } + } + rcu_read_unlock(); + return found ? cur : NULL; +} +EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_symbol); + int nf_conntrack_helper_register(struct nf_conntrack_helper *me) { unsigned int h = helper_hash(&me->tuple); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 04fb409623d2..c1ea64c6c70d 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -110,15 +110,16 @@ ctnetlink_dump_tuples(struct sk_buff *skb, struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; + rcu_read_lock(); l3proto = __nf_ct_l3proto_find(tuple->src.l3num); ret = ctnetlink_dump_tuples_ip(skb, tuple, l3proto); - if (unlikely(ret < 0)) - return ret; - - l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum); - ret = ctnetlink_dump_tuples_proto(skb, tuple, l4proto); - + if (ret >= 0) { + l4proto = __nf_ct_l4proto_find(tuple->src.l3num, + tuple->dst.protonum); + ret = ctnetlink_dump_tuples_proto(skb, tuple, l4proto); + } + rcu_read_unlock(); return ret; } @@ -712,9 +713,11 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_nulls_node *n; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; + int res; #ifdef CONFIG_NF_CONNTRACK_MARK const struct ctnetlink_dump_filter *filter = cb->data; #endif + spin_lock_bh(&nf_conntrack_lock); last = (struct nf_conn *)cb->args[1]; for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) { @@ -740,11 +743,14 @@ restart: continue; } #endif - if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - NFNL_MSG_TYPE( - cb->nlh->nlmsg_type), - ct) < 0) { + rcu_read_lock(); + res = + ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + NFNL_MSG_TYPE(cb->nlh->nlmsg_type), + ct); + rcu_read_unlock(); + if (res < 0) { nf_conntrack_get(&ct->ct_general); cb->args[1] = (unsigned long)ct; goto out; @@ -1649,14 +1655,16 @@ ctnetlink_exp_dump_mask(struct sk_buff *skb, if (!nest_parms) goto nla_put_failure; + rcu_read_lock(); l3proto = __nf_ct_l3proto_find(tuple->src.l3num); ret = ctnetlink_dump_tuples_ip(skb, &m, l3proto); - - if (unlikely(ret < 0)) - goto nla_put_failure; - - l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum); + if (ret >= 0) { + l4proto = __nf_ct_l4proto_find(tuple->src.l3num, + tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto); + } + rcu_read_unlock(); + if (unlikely(ret < 0)) goto nla_put_failure; @@ -1675,6 +1683,11 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, struct nf_conn *master = exp->master; long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ; struct nf_conn_help *help; +#ifdef CONFIG_NF_NAT_NEEDED + struct nlattr *nest_parms; + struct nf_conntrack_tuple nat_tuple = {}; +#endif + struct nf_ct_helper_expectfn *expfn; if (timeout < 0) timeout = 0; @@ -1688,9 +1701,29 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, CTA_EXPECT_MASTER) < 0) goto nla_put_failure; +#ifdef CONFIG_NF_NAT_NEEDED + if (exp->saved_ip || exp->saved_proto.all) { + nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT | NLA_F_NESTED); + if (!nest_parms) + goto nla_put_failure; + + NLA_PUT_BE32(skb, CTA_EXPECT_NAT_DIR, htonl(exp->dir)); + + nat_tuple.src.l3num = nf_ct_l3num(master); + nat_tuple.src.u3.ip = exp->saved_ip; + nat_tuple.dst.protonum = nf_ct_protonum(master); + nat_tuple.src.u = exp->saved_proto; + + if (ctnetlink_exp_dump_tuple(skb, &nat_tuple, + CTA_EXPECT_NAT_TUPLE) < 0) + goto nla_put_failure; + nla_nest_end(skb, nest_parms); + } +#endif NLA_PUT_BE32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)); NLA_PUT_BE32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)); NLA_PUT_BE32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)); + NLA_PUT_BE32(skb, CTA_EXPECT_CLASS, htonl(exp->class)); help = nfct_help(master); if (help) { struct nf_conntrack_helper *helper; @@ -1699,6 +1732,9 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, if (helper) NLA_PUT_STRING(skb, CTA_EXPECT_HELP_NAME, helper->name); } + expfn = nf_ct_helper_expectfn_find_by_symbol(exp->expectfn); + if (expfn != NULL) + NLA_PUT_STRING(skb, CTA_EXPECT_FN, expfn->name); return 0; @@ -1856,6 +1892,9 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING }, [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, + [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, + [CTA_EXPECT_NAT] = { .type = NLA_NESTED }, + [CTA_EXPECT_FN] = { .type = NLA_NUL_STRING }, }; static int @@ -2031,6 +2070,41 @@ ctnetlink_change_expect(struct nf_conntrack_expect *x, return -EOPNOTSUPP; } +static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { + [CTA_EXPECT_NAT_DIR] = { .type = NLA_U32 }, + [CTA_EXPECT_NAT_TUPLE] = { .type = NLA_NESTED }, +}; + +static int +ctnetlink_parse_expect_nat(const struct nlattr *attr, + struct nf_conntrack_expect *exp, + u_int8_t u3) +{ +#ifdef CONFIG_NF_NAT_NEEDED + struct nlattr *tb[CTA_EXPECT_NAT_MAX+1]; + struct nf_conntrack_tuple nat_tuple = {}; + int err; + + nla_parse_nested(tb, CTA_EXPECT_NAT_MAX, attr, exp_nat_nla_policy); + + if (!tb[CTA_EXPECT_NAT_DIR] || !tb[CTA_EXPECT_NAT_TUPLE]) + return -EINVAL; + + err = ctnetlink_parse_tuple((const struct nlattr * const *)tb, + &nat_tuple, CTA_EXPECT_NAT_TUPLE, u3); + if (err < 0) + return err; + + exp->saved_ip = nat_tuple.src.u3.ip; + exp->saved_proto = nat_tuple.src.u; + exp->dir = ntohl(nla_get_be32(tb[CTA_EXPECT_NAT_DIR])); + + return 0; +#else + return -EOPNOTSUPP; +#endif +} + static int ctnetlink_create_expect(struct net *net, u16 zone, const struct nlattr * const cda[], @@ -2042,6 +2116,8 @@ ctnetlink_create_expect(struct net *net, u16 zone, struct nf_conntrack_expect *exp; struct nf_conn *ct; struct nf_conn_help *help; + struct nf_conntrack_helper *helper = NULL; + u_int32_t class = 0; int err = 0; /* caller guarantees that those three CTA_EXPECT_* exist */ @@ -2060,6 +2136,40 @@ ctnetlink_create_expect(struct net *net, u16 zone, if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); + + /* Look for helper of this expectation */ + if (cda[CTA_EXPECT_HELP_NAME]) { + const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); + + helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), + nf_ct_protonum(ct)); + if (helper == NULL) { +#ifdef CONFIG_MODULES + if (request_module("nfct-helper-%s", helpname) < 0) { + err = -EOPNOTSUPP; + goto out; + } + + helper = __nf_conntrack_helper_find(helpname, + nf_ct_l3num(ct), + nf_ct_protonum(ct)); + if (helper) { + err = -EAGAIN; + goto out; + } +#endif + err = -EOPNOTSUPP; + goto out; + } + } + + if (cda[CTA_EXPECT_CLASS] && helper) { + class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS])); + if (class > helper->expect_class_max) { + err = -EINVAL; + goto out; + } + } exp = nf_ct_expect_alloc(ct); if (!exp) { err = -ENOMEM; @@ -2086,18 +2196,35 @@ ctnetlink_create_expect(struct net *net, u16 zone, } else exp->flags = 0; } + if (cda[CTA_EXPECT_FN]) { + const char *name = nla_data(cda[CTA_EXPECT_FN]); + struct nf_ct_helper_expectfn *expfn; + + expfn = nf_ct_helper_expectfn_find_by_name(name); + if (expfn == NULL) { + err = -EINVAL; + goto err_out; + } + exp->expectfn = expfn->expectfn; + } else + exp->expectfn = NULL; - exp->class = 0; - exp->expectfn = NULL; + exp->class = class; exp->master = ct; - exp->helper = NULL; + exp->helper = helper; memcpy(&exp->tuple, &tuple, sizeof(struct nf_conntrack_tuple)); memcpy(&exp->mask.src.u3, &mask.src.u3, sizeof(exp->mask.src.u3)); exp->mask.src.u.all = mask.src.u.all; + if (cda[CTA_EXPECT_NAT]) { + err = ctnetlink_parse_expect_nat(cda[CTA_EXPECT_NAT], + exp, u3); + if (err < 0) + goto err_out; + } err = nf_ct_expect_related_report(exp, pid, report); +err_out: nf_ct_expect_put(exp); - out: nf_ct_put(nf_ct_tuplehash_to_ctrack(h)); return err; diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index d6dde6dc09e6..24fdce256cb0 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -423,7 +423,7 @@ static bool dccp_invert_tuple(struct nf_conntrack_tuple *inv, } static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { struct net *net = nf_ct_net(ct); struct dccp_net *dn; @@ -472,12 +472,17 @@ static u64 dccp_ack_seq(const struct dccp_hdr *dh) ntohl(dhack->dccph_ack_nr_low); } +static unsigned int *dccp_get_timeouts(struct net *net) +{ + return dccp_pernet(net)->dccp_timeout; +} + static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int hooknum) + u_int8_t pf, unsigned int hooknum, + unsigned int *timeouts) { struct net *net = nf_ct_net(ct); - struct dccp_net *dn; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct dccp_hdr _dh, *dh; u_int8_t type, old_state, new_state; @@ -559,8 +564,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, if (new_state != old_state) nf_conntrack_event_cache(IPCT_PROTOINFO, ct); - dn = dccp_pernet(net); - nf_ct_refresh_acct(ct, ctinfo, skb, dn->dccp_timeout[new_state]); + nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); return NF_ACCEPT; } @@ -702,8 +706,60 @@ static int dccp_nlattr_size(void) return nla_total_size(0) /* CTA_PROTOINFO_DCCP */ + nla_policy_len(dccp_nla_policy, CTA_PROTOINFO_DCCP_MAX + 1); } + #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + struct dccp_net *dn = dccp_pernet(&init_net); + unsigned int *timeouts = data; + int i; + + /* set default DCCP timeouts. */ + for (i=0; i<CT_DCCP_MAX; i++) + timeouts[i] = dn->dccp_timeout[i]; + + /* there's a 1:1 mapping between attributes and protocol states. */ + for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) { + if (tb[i]) { + timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; + } + } + return 0; +} + +static int +dccp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + int i; + + for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) + NLA_PUT_BE32(skb, i, htonl(timeouts[i] / HZ)); + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = { + [CTA_TIMEOUT_DCCP_REQUEST] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_RESPOND] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_PARTOPEN] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_OPEN] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_CLOSEREQ] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_CLOSING] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_TIMEWAIT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL /* template, data assigned later */ static struct ctl_table dccp_sysctl_table[] = { @@ -767,6 +823,7 @@ static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = { .invert_tuple = dccp_invert_tuple, .new = dccp_new, .packet = dccp_packet, + .get_timeouts = dccp_get_timeouts, .error = dccp_error, .print_tuple = dccp_print_tuple, .print_conntrack = dccp_print_conntrack, @@ -779,6 +836,15 @@ static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = dccp_timeout_nlattr_to_obj, + .obj_to_nlattr = dccp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_DCCP_MAX, + .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, + .nla_policy = dccp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ }; static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { @@ -789,6 +855,7 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { .invert_tuple = dccp_invert_tuple, .new = dccp_new, .packet = dccp_packet, + .get_timeouts = dccp_get_timeouts, .error = dccp_error, .print_tuple = dccp_print_tuple, .print_conntrack = dccp_print_conntrack, @@ -801,6 +868,15 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = dccp_timeout_nlattr_to_obj, + .obj_to_nlattr = dccp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_DCCP_MAX, + .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, + .nla_policy = dccp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ }; static __net_init int dccp_net_init(struct net *net) diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index e2091d0c7a2f..835e24c58f0d 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -40,25 +40,70 @@ static int generic_print_tuple(struct seq_file *s, return 0; } +static unsigned int *generic_get_timeouts(struct net *net) +{ + return &nf_ct_generic_timeout; +} + /* Returns verdict for packet, or -1 for invalid. */ -static int packet(struct nf_conn *ct, - const struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - u_int8_t pf, - unsigned int hooknum) +static int generic_packet(struct nf_conn *ct, + const struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + u_int8_t pf, + unsigned int hooknum, + unsigned int *timeout) { - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_generic_timeout); + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ -static bool new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) +static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, + unsigned int dataoff, unsigned int *timeouts) { return true; } +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int generic_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeout = data; + + if (tb[CTA_TIMEOUT_GENERIC_TIMEOUT]) + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_GENERIC_TIMEOUT])) * HZ; + else { + /* Set default generic timeout. */ + *timeout = nf_ct_generic_timeout; + } + + return 0; +} + +static int +generic_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_GENERIC_TIMEOUT, htonl(*timeout / HZ)); + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +generic_timeout_nla_policy[CTA_TIMEOUT_GENERIC_MAX+1] = { + [CTA_TIMEOUT_GENERIC_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static struct ctl_table_header *generic_sysctl_header; static struct ctl_table generic_sysctl_table[] = { @@ -93,8 +138,18 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_generic __read_mostly = .pkt_to_tuple = generic_pkt_to_tuple, .invert_tuple = generic_invert_tuple, .print_tuple = generic_print_tuple, - .packet = packet, - .new = new, + .packet = generic_packet, + .get_timeouts = generic_get_timeouts, + .new = generic_new, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = generic_timeout_nlattr_to_obj, + .obj_to_nlattr = generic_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_GENERIC_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = generic_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_header = &generic_sysctl_header, .ctl_table = generic_sysctl_table, diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index f0338791b822..659648c4b14a 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -41,8 +41,16 @@ #include <linux/netfilter/nf_conntrack_proto_gre.h> #include <linux/netfilter/nf_conntrack_pptp.h> -#define GRE_TIMEOUT (30 * HZ) -#define GRE_STREAM_TIMEOUT (180 * HZ) +enum grep_conntrack { + GRE_CT_UNREPLIED, + GRE_CT_REPLIED, + GRE_CT_MAX +}; + +static unsigned int gre_timeouts[GRE_CT_MAX] = { + [GRE_CT_UNREPLIED] = 30*HZ, + [GRE_CT_REPLIED] = 180*HZ, +}; static int proto_gre_net_id __read_mostly; struct netns_proto_gre { @@ -227,13 +235,19 @@ static int gre_print_conntrack(struct seq_file *s, struct nf_conn *ct) (ct->proto.gre.stream_timeout / HZ)); } +static unsigned int *gre_get_timeouts(struct net *net) +{ + return gre_timeouts; +} + /* Returns verdict for packet, and may modify conntrack */ static int gre_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeouts) { /* If we've seen traffic both ways, this is a GRE connection. * Extend timeout. */ @@ -252,15 +266,15 @@ static int gre_packet(struct nf_conn *ct, /* Called when a new connection for this protocol found. */ static bool gre_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { pr_debug(": "); nf_ct_dump_tuple(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); /* initialize to sane value. Ideally a conntrack helper * (e.g. in case of pptp) is increasing them */ - ct->proto.gre.stream_timeout = GRE_STREAM_TIMEOUT; - ct->proto.gre.timeout = GRE_TIMEOUT; + ct->proto.gre.stream_timeout = timeouts[GRE_CT_REPLIED]; + ct->proto.gre.timeout = timeouts[GRE_CT_UNREPLIED]; return true; } @@ -278,6 +292,52 @@ static void gre_destroy(struct nf_conn *ct) nf_ct_gre_keymap_destroy(master); } +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int gre_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeouts = data; + + /* set default timeouts for GRE. */ + timeouts[GRE_CT_UNREPLIED] = gre_timeouts[GRE_CT_UNREPLIED]; + timeouts[GRE_CT_REPLIED] = gre_timeouts[GRE_CT_REPLIED]; + + if (tb[CTA_TIMEOUT_GRE_UNREPLIED]) { + timeouts[GRE_CT_UNREPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_GRE_UNREPLIED])) * HZ; + } + if (tb[CTA_TIMEOUT_GRE_REPLIED]) { + timeouts[GRE_CT_REPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_GRE_REPLIED])) * HZ; + } + return 0; +} + +static int +gre_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_GRE_UNREPLIED, + htonl(timeouts[GRE_CT_UNREPLIED] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_GRE_REPLIED, + htonl(timeouts[GRE_CT_REPLIED] / HZ)); + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = { + [CTA_TIMEOUT_GRE_UNREPLIED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_GRE_REPLIED] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + /* protocol helper struct */ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { .l3proto = AF_INET, @@ -287,6 +347,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { .invert_tuple = gre_invert_tuple, .print_tuple = gre_print_tuple, .print_conntrack = gre_print_conntrack, + .get_timeouts = gre_get_timeouts, .packet = gre_packet, .new = gre_new, .destroy = gre_destroy, @@ -297,6 +358,15 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = gre_timeout_nlattr_to_obj, + .obj_to_nlattr = gre_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_GRE_MAX, + .obj_size = sizeof(unsigned int) * GRE_CT_MAX, + .nla_policy = gre_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ }; static int proto_gre_net_init(struct net *net) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index afa69136061a..72b5088592dc 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -279,13 +279,19 @@ static int sctp_new_state(enum ip_conntrack_dir dir, return sctp_conntracks[dir][i][cur_state]; } +static unsigned int *sctp_get_timeouts(struct net *net) +{ + return sctp_timeouts; +} + /* Returns verdict for packet, or -NF_ACCEPT for invalid. */ static int sctp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeouts) { enum sctp_conntrack new_state, old_state; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); @@ -370,7 +376,7 @@ static int sctp_packet(struct nf_conn *ct, } spin_unlock_bh(&ct->lock); - nf_ct_refresh_acct(ct, ctinfo, skb, sctp_timeouts[new_state]); + nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED && dir == IP_CT_DIR_REPLY && @@ -390,7 +396,7 @@ out: /* Called when a new connection for this protocol found. */ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { enum sctp_conntrack new_state; const struct sctphdr *sh; @@ -543,6 +549,57 @@ static int sctp_nlattr_size(void) } #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeouts = data; + int i; + + /* set default SCTP timeouts. */ + for (i=0; i<SCTP_CONNTRACK_MAX; i++) + timeouts[i] = sctp_timeouts[i]; + + /* there's a 1:1 mapping between attributes and protocol states. */ + for (i=CTA_TIMEOUT_SCTP_UNSPEC+1; i<CTA_TIMEOUT_SCTP_MAX+1; i++) { + if (tb[i]) { + timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; + } + } + return 0; +} + +static int +sctp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + int i; + + for (i=CTA_TIMEOUT_SCTP_UNSPEC+1; i<CTA_TIMEOUT_SCTP_MAX+1; i++) + NLA_PUT_BE32(skb, i, htonl(timeouts[i] / HZ)); + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { + [CTA_TIMEOUT_SCTP_CLOSED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_COOKIE_WAIT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_COOKIE_ECHOED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_ESTABLISHED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_SHUTDOWN_SENT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_SHUTDOWN_RECD] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + + #ifdef CONFIG_SYSCTL static unsigned int sctp_sysctl_table_users; static struct ctl_table_header *sctp_sysctl_header; @@ -664,6 +721,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { .print_tuple = sctp_print_tuple, .print_conntrack = sctp_print_conntrack, .packet = sctp_packet, + .get_timeouts = sctp_get_timeouts, .new = sctp_new, .me = THIS_MODULE, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -675,6 +733,15 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = sctp_timeout_nlattr_to_obj, + .obj_to_nlattr = sctp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_SCTP_MAX, + .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, + .nla_policy = sctp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &sctp_sysctl_table_users, .ctl_table_header = &sctp_sysctl_header, @@ -694,6 +761,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = { .print_tuple = sctp_print_tuple, .print_conntrack = sctp_print_conntrack, .packet = sctp_packet, + .get_timeouts = sctp_get_timeouts, .new = sctp_new, .me = THIS_MODULE, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -704,6 +772,15 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = { .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = sctp_timeout_nlattr_to_obj, + .obj_to_nlattr = sctp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_SCTP_MAX, + .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, + .nla_policy = sctp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #endif #ifdef CONFIG_SYSCTL .ctl_table_users = &sctp_sysctl_table_users, diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 97b9f3ebf28c..361eade62a09 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -64,13 +64,7 @@ static const char *const tcp_conntrack_names[] = { #define HOURS * 60 MINS #define DAYS * 24 HOURS -/* RFC1122 says the R2 limit should be at least 100 seconds. - Linux uses 15 packets as limit, which corresponds - to ~13-30min depending on RTO. */ -static unsigned int nf_ct_tcp_timeout_max_retrans __read_mostly = 5 MINS; -static unsigned int nf_ct_tcp_timeout_unacknowledged __read_mostly = 5 MINS; - -static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = { +static unsigned int tcp_timeouts[TCP_CONNTRACK_TIMEOUT_MAX] __read_mostly = { [TCP_CONNTRACK_SYN_SENT] = 2 MINS, [TCP_CONNTRACK_SYN_RECV] = 60 SECS, [TCP_CONNTRACK_ESTABLISHED] = 5 DAYS, @@ -80,6 +74,11 @@ static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = { [TCP_CONNTRACK_TIME_WAIT] = 2 MINS, [TCP_CONNTRACK_CLOSE] = 10 SECS, [TCP_CONNTRACK_SYN_SENT2] = 2 MINS, +/* RFC1122 says the R2 limit should be at least 100 seconds. + Linux uses 15 packets as limit, which corresponds + to ~13-30min depending on RTO. */ + [TCP_CONNTRACK_RETRANS] = 5 MINS, + [TCP_CONNTRACK_UNACK] = 5 MINS, }; #define sNO TCP_CONNTRACK_NONE @@ -814,13 +813,19 @@ static int tcp_error(struct net *net, struct nf_conn *tmpl, return NF_ACCEPT; } +static unsigned int *tcp_get_timeouts(struct net *net) +{ + return tcp_timeouts; +} + /* Returns verdict for packet, or -1 for invalid. */ static int tcp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeouts) { struct net *net = nf_ct_net(ct); struct nf_conntrack_tuple *tuple; @@ -1015,14 +1020,14 @@ static int tcp_packet(struct nf_conn *ct, ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT; if (ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans && - tcp_timeouts[new_state] > nf_ct_tcp_timeout_max_retrans) - timeout = nf_ct_tcp_timeout_max_retrans; + timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) + timeout = timeouts[TCP_CONNTRACK_RETRANS]; else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) & IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED && - tcp_timeouts[new_state] > nf_ct_tcp_timeout_unacknowledged) - timeout = nf_ct_tcp_timeout_unacknowledged; + timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK]) + timeout = timeouts[TCP_CONNTRACK_UNACK]; else - timeout = tcp_timeouts[new_state]; + timeout = timeouts[new_state]; spin_unlock_bh(&ct->lock); if (new_state != old_state) @@ -1054,7 +1059,7 @@ static int tcp_packet(struct nf_conn *ct, /* Called when a new connection for this protocol found. */ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { enum tcp_conntrack new_state; const struct tcphdr *th; @@ -1239,6 +1244,113 @@ static int tcp_nlattr_tuple_size(void) } #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeouts = data; + int i; + + /* set default TCP timeouts. */ + for (i=0; i<TCP_CONNTRACK_TIMEOUT_MAX; i++) + timeouts[i] = tcp_timeouts[i]; + + if (tb[CTA_TIMEOUT_TCP_SYN_SENT]) { + timeouts[TCP_CONNTRACK_SYN_SENT] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_SYN_RECV]) { + timeouts[TCP_CONNTRACK_SYN_RECV] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_RECV]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_ESTABLISHED]) { + timeouts[TCP_CONNTRACK_ESTABLISHED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_ESTABLISHED]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_FIN_WAIT]) { + timeouts[TCP_CONNTRACK_FIN_WAIT] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_FIN_WAIT]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_CLOSE_WAIT]) { + timeouts[TCP_CONNTRACK_CLOSE_WAIT] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_CLOSE_WAIT]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_LAST_ACK]) { + timeouts[TCP_CONNTRACK_LAST_ACK] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_LAST_ACK]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_TIME_WAIT]) { + timeouts[TCP_CONNTRACK_TIME_WAIT] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_TIME_WAIT]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_CLOSE]) { + timeouts[TCP_CONNTRACK_CLOSE] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_CLOSE]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_SYN_SENT2]) { + timeouts[TCP_CONNTRACK_SYN_SENT2] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT2]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_RETRANS]) { + timeouts[TCP_CONNTRACK_RETRANS] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_RETRANS]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_UNACK]) { + timeouts[TCP_CONNTRACK_UNACK] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_UNACK]))*HZ; + } + return 0; +} + +static int +tcp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_SENT, + htonl(timeouts[TCP_CONNTRACK_SYN_SENT] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_RECV, + htonl(timeouts[TCP_CONNTRACK_SYN_RECV] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_ESTABLISHED, + htonl(timeouts[TCP_CONNTRACK_ESTABLISHED] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_FIN_WAIT, + htonl(timeouts[TCP_CONNTRACK_FIN_WAIT] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_CLOSE_WAIT, + htonl(timeouts[TCP_CONNTRACK_CLOSE_WAIT] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_LAST_ACK, + htonl(timeouts[TCP_CONNTRACK_LAST_ACK] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_TIME_WAIT, + htonl(timeouts[TCP_CONNTRACK_TIME_WAIT] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_CLOSE, + htonl(timeouts[TCP_CONNTRACK_CLOSE] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_SENT2, + htonl(timeouts[TCP_CONNTRACK_SYN_SENT2] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_RETRANS, + htonl(timeouts[TCP_CONNTRACK_RETRANS] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_UNACK, + htonl(timeouts[TCP_CONNTRACK_UNACK] / HZ)); + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { + [CTA_TIMEOUT_TCP_SYN_SENT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_SYN_RECV] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_ESTABLISHED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_FIN_WAIT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_CLOSE_WAIT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_LAST_ACK] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_TIME_WAIT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_CLOSE] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_SYN_SENT2] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static unsigned int tcp_sysctl_table_users; static struct ctl_table_header *tcp_sysctl_header; @@ -1301,14 +1413,14 @@ static struct ctl_table tcp_sysctl_table[] = { }, { .procname = "nf_conntrack_tcp_timeout_max_retrans", - .data = &nf_ct_tcp_timeout_max_retrans, + .data = &tcp_timeouts[TCP_CONNTRACK_RETRANS], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_tcp_timeout_unacknowledged", - .data = &nf_ct_tcp_timeout_unacknowledged, + .data = &tcp_timeouts[TCP_CONNTRACK_UNACK], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -1404,7 +1516,7 @@ static struct ctl_table tcp_compat_sysctl_table[] = { }, { .procname = "ip_conntrack_tcp_timeout_max_retrans", - .data = &nf_ct_tcp_timeout_max_retrans, + .data = &tcp_timeouts[TCP_CONNTRACK_RETRANS], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -1445,6 +1557,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly = .print_tuple = tcp_print_tuple, .print_conntrack = tcp_print_conntrack, .packet = tcp_packet, + .get_timeouts = tcp_get_timeouts, .new = tcp_new, .error = tcp_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -1456,6 +1569,16 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly = .nlattr_tuple_size = tcp_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = tcp_timeout_nlattr_to_obj, + .obj_to_nlattr = tcp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_TCP_MAX, + .obj_size = sizeof(unsigned int) * + TCP_CONNTRACK_TIMEOUT_MAX, + .nla_policy = tcp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &tcp_sysctl_table_users, .ctl_table_header = &tcp_sysctl_header, @@ -1477,6 +1600,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly = .print_tuple = tcp_print_tuple, .print_conntrack = tcp_print_conntrack, .packet = tcp_packet, + .get_timeouts = tcp_get_timeouts, .new = tcp_new, .error = tcp_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -1488,6 +1612,16 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly = .nlattr_tuple_size = tcp_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = tcp_timeout_nlattr_to_obj, + .obj_to_nlattr = tcp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_TCP_MAX, + .obj_size = sizeof(unsigned int) * + TCP_CONNTRACK_TIMEOUT_MAX, + .nla_policy = tcp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &tcp_sysctl_table_users, .ctl_table_header = &tcp_sysctl_header, diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 5f35757fbff0..a9073dc1548d 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -25,8 +25,16 @@ #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> -static unsigned int nf_ct_udp_timeout __read_mostly = 30*HZ; -static unsigned int nf_ct_udp_timeout_stream __read_mostly = 180*HZ; +enum udp_conntrack { + UDP_CT_UNREPLIED, + UDP_CT_REPLIED, + UDP_CT_MAX +}; + +static unsigned int udp_timeouts[UDP_CT_MAX] = { + [UDP_CT_UNREPLIED] = 30*HZ, + [UDP_CT_REPLIED] = 180*HZ, +}; static bool udp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, @@ -63,30 +71,38 @@ static int udp_print_tuple(struct seq_file *s, ntohs(tuple->dst.u.udp.port)); } +static unsigned int *udp_get_timeouts(struct net *net) +{ + return udp_timeouts; +} + /* Returns verdict for packet, and may modify conntracktype */ static int udp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeouts) { /* If we've seen traffic both ways, this is some kind of UDP stream. Extend timeout. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udp_timeout_stream); + nf_ct_refresh_acct(ct, ctinfo, skb, + timeouts[UDP_CT_REPLIED]); /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); - } else - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udp_timeout); - + } else { + nf_ct_refresh_acct(ct, ctinfo, skb, + timeouts[UDP_CT_UNREPLIED]); + } return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ static bool udp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { return true; } @@ -136,20 +152,66 @@ static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, return NF_ACCEPT; } +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int udp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeouts = data; + + /* set default timeouts for UDP. */ + timeouts[UDP_CT_UNREPLIED] = udp_timeouts[UDP_CT_UNREPLIED]; + timeouts[UDP_CT_REPLIED] = udp_timeouts[UDP_CT_REPLIED]; + + if (tb[CTA_TIMEOUT_UDP_UNREPLIED]) { + timeouts[UDP_CT_UNREPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_UDP_UNREPLIED])) * HZ; + } + if (tb[CTA_TIMEOUT_UDP_REPLIED]) { + timeouts[UDP_CT_REPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_UDP_REPLIED])) * HZ; + } + return 0; +} + +static int +udp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_UDP_UNREPLIED, + htonl(timeouts[UDP_CT_UNREPLIED] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_UDP_REPLIED, + htonl(timeouts[UDP_CT_REPLIED] / HZ)); + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +udp_timeout_nla_policy[CTA_TIMEOUT_UDP_MAX+1] = { + [CTA_TIMEOUT_UDP_UNREPLIED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_UDP_REPLIED] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static unsigned int udp_sysctl_table_users; static struct ctl_table_header *udp_sysctl_header; static struct ctl_table udp_sysctl_table[] = { { .procname = "nf_conntrack_udp_timeout", - .data = &nf_ct_udp_timeout, + .data = &udp_timeouts[UDP_CT_UNREPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_udp_timeout_stream", - .data = &nf_ct_udp_timeout_stream, + .data = &udp_timeouts[UDP_CT_REPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -160,14 +222,14 @@ static struct ctl_table udp_sysctl_table[] = { static struct ctl_table udp_compat_sysctl_table[] = { { .procname = "ip_conntrack_udp_timeout", - .data = &nf_ct_udp_timeout, + .data = &udp_timeouts[UDP_CT_UNREPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ip_conntrack_udp_timeout_stream", - .data = &nf_ct_udp_timeout_stream, + .data = &udp_timeouts[UDP_CT_REPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -186,6 +248,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly = .invert_tuple = udp_invert_tuple, .print_tuple = udp_print_tuple, .packet = udp_packet, + .get_timeouts = udp_get_timeouts, .new = udp_new, .error = udp_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -194,6 +257,15 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = udp_timeout_nlattr_to_obj, + .obj_to_nlattr = udp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_UDP_MAX, + .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, + .nla_policy = udp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &udp_sysctl_table_users, .ctl_table_header = &udp_sysctl_header, @@ -214,6 +286,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly = .invert_tuple = udp_invert_tuple, .print_tuple = udp_print_tuple, .packet = udp_packet, + .get_timeouts = udp_get_timeouts, .new = udp_new, .error = udp_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -222,6 +295,15 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = udp_timeout_nlattr_to_obj, + .obj_to_nlattr = udp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_UDP_MAX, + .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, + .nla_policy = udp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &udp_sysctl_table_users, .ctl_table_header = &udp_sysctl_header, diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index f52ca1181013..e0606392cda0 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -24,8 +24,16 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_log.h> -static unsigned int nf_ct_udplite_timeout __read_mostly = 30*HZ; -static unsigned int nf_ct_udplite_timeout_stream __read_mostly = 180*HZ; +enum udplite_conntrack { + UDPLITE_CT_UNREPLIED, + UDPLITE_CT_REPLIED, + UDPLITE_CT_MAX +}; + +static unsigned int udplite_timeouts[UDPLITE_CT_MAX] = { + [UDPLITE_CT_UNREPLIED] = 30*HZ, + [UDPLITE_CT_REPLIED] = 180*HZ, +}; static bool udplite_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, @@ -60,31 +68,38 @@ static int udplite_print_tuple(struct seq_file *s, ntohs(tuple->dst.u.udp.port)); } +static unsigned int *udplite_get_timeouts(struct net *net) +{ + return udplite_timeouts; +} + /* Returns verdict for packet, and may modify conntracktype */ static int udplite_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeouts) { /* If we've seen traffic both ways, this is some kind of UDP stream. Extend timeout. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { nf_ct_refresh_acct(ct, ctinfo, skb, - nf_ct_udplite_timeout_stream); + timeouts[UDPLITE_CT_REPLIED]); /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); - } else - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udplite_timeout); - + } else { + nf_ct_refresh_acct(ct, ctinfo, skb, + timeouts[UDPLITE_CT_UNREPLIED]); + } return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ static bool udplite_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { return true; } @@ -141,20 +156,66 @@ static int udplite_error(struct net *net, struct nf_conn *tmpl, return NF_ACCEPT; } +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int udplite_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeouts = data; + + /* set default timeouts for UDPlite. */ + timeouts[UDPLITE_CT_UNREPLIED] = udplite_timeouts[UDPLITE_CT_UNREPLIED]; + timeouts[UDPLITE_CT_REPLIED] = udplite_timeouts[UDPLITE_CT_REPLIED]; + + if (tb[CTA_TIMEOUT_UDPLITE_UNREPLIED]) { + timeouts[UDPLITE_CT_UNREPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_UDPLITE_UNREPLIED])) * HZ; + } + if (tb[CTA_TIMEOUT_UDPLITE_REPLIED]) { + timeouts[UDPLITE_CT_REPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_UDPLITE_REPLIED])) * HZ; + } + return 0; +} + +static int +udplite_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_UDPLITE_UNREPLIED, + htonl(timeouts[UDPLITE_CT_UNREPLIED] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_UDPLITE_REPLIED, + htonl(timeouts[UDPLITE_CT_REPLIED] / HZ)); + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +udplite_timeout_nla_policy[CTA_TIMEOUT_UDPLITE_MAX+1] = { + [CTA_TIMEOUT_UDPLITE_UNREPLIED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_UDPLITE_REPLIED] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static unsigned int udplite_sysctl_table_users; static struct ctl_table_header *udplite_sysctl_header; static struct ctl_table udplite_sysctl_table[] = { { .procname = "nf_conntrack_udplite_timeout", - .data = &nf_ct_udplite_timeout, + .data = &udplite_timeouts[UDPLITE_CT_UNREPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_udplite_timeout_stream", - .data = &nf_ct_udplite_timeout_stream, + .data = &udplite_timeouts[UDPLITE_CT_REPLIED], .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -172,6 +233,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly = .invert_tuple = udplite_invert_tuple, .print_tuple = udplite_print_tuple, .packet = udplite_packet, + .get_timeouts = udplite_get_timeouts, .new = udplite_new, .error = udplite_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -180,6 +242,16 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly = .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = udplite_timeout_nlattr_to_obj, + .obj_to_nlattr = udplite_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_UDPLITE_MAX, + .obj_size = sizeof(unsigned int) * + CTA_TIMEOUT_UDPLITE_MAX, + .nla_policy = udplite_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &udplite_sysctl_table_users, .ctl_table_header = &udplite_sysctl_header, @@ -196,6 +268,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly = .invert_tuple = udplite_invert_tuple, .print_tuple = udplite_print_tuple, .packet = udplite_packet, + .get_timeouts = udplite_get_timeouts, .new = udplite_new, .error = udplite_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -204,6 +277,16 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly = .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = udplite_timeout_nlattr_to_obj, + .obj_to_nlattr = udplite_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_UDPLITE_MAX, + .obj_size = sizeof(unsigned int) * + CTA_TIMEOUT_UDPLITE_MAX, + .nla_policy = udplite_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &udplite_sysctl_table_users, .ctl_table_header = &udplite_sysctl_header, diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c new file mode 100644 index 000000000000..a878ce5b252c --- /dev/null +++ b/net/netfilter/nf_conntrack_timeout.c @@ -0,0 +1,60 @@ +/* + * (C) 2012 by Pablo Neira Ayuso <pablo@netfilter.org> + * (C) 2012 by Vyatta Inc. <http://www.vyatta.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation (or any later at your option). + */ + +#include <linux/types.h> +#include <linux/netfilter.h> +#include <linux/skbuff.h> +#include <linux/vmalloc.h> +#include <linux/stddef.h> +#include <linux/err.h> +#include <linux/percpu.h> +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/slab.h> +#include <linux/export.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_extend.h> +#include <net/netfilter/nf_conntrack_timeout.h> + +struct ctnl_timeout * +(*nf_ct_timeout_find_get_hook)(const char *name) __read_mostly; +EXPORT_SYMBOL_GPL(nf_ct_timeout_find_get_hook); + +void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout) __read_mostly; +EXPORT_SYMBOL_GPL(nf_ct_timeout_put_hook); + +static struct nf_ct_ext_type timeout_extend __read_mostly = { + .len = sizeof(struct nf_conn_timeout), + .align = __alignof__(struct nf_conn_timeout), + .id = NF_CT_EXT_TIMEOUT, +}; + +int nf_conntrack_timeout_init(struct net *net) +{ + int ret = 0; + + if (net_eq(net, &init_net)) { + ret = nf_ct_extend_register(&timeout_extend); + if (ret < 0) { + printk(KERN_ERR "nf_ct_timeout: Unable to register " + "timeout extension.\n"); + return ret; + } + } + + return 0; +} + +void nf_conntrack_timeout_fini(struct net *net) +{ + if (net_eq(net, &init_net)) + nf_ct_extend_unregister(&timeout_extend); +} diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c new file mode 100644 index 000000000000..fec29a43de4d --- /dev/null +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -0,0 +1,429 @@ +/* + * (C) 2012 by Pablo Neira Ayuso <pablo@netfilter.org> + * (C) 2012 by Vyatta Inc. <http://www.vyatta.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation (or any later at your option). + */ +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/rculist.h> +#include <linux/rculist_nulls.h> +#include <linux/types.h> +#include <linux/timer.h> +#include <linux/security.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/netlink.h> +#include <linux/spinlock.h> +#include <linux/interrupt.h> +#include <linux/slab.h> + +#include <linux/netfilter.h> +#include <net/netlink.h> +#include <net/sock.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_l3proto.h> +#include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_tuple.h> +#include <net/netfilter/nf_conntrack_timeout.h> + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_DESCRIPTION("cttimeout: Extended Netfilter Connection Tracking timeout tuning"); + +static LIST_HEAD(cttimeout_list); + +static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = { + [CTA_TIMEOUT_NAME] = { .type = NLA_NUL_STRING }, + [CTA_TIMEOUT_L3PROTO] = { .type = NLA_U16 }, + [CTA_TIMEOUT_L4PROTO] = { .type = NLA_U8 }, + [CTA_TIMEOUT_DATA] = { .type = NLA_NESTED }, +}; + +static int +ctnl_timeout_parse_policy(struct ctnl_timeout *timeout, + struct nf_conntrack_l4proto *l4proto, + const struct nlattr *attr) +{ + int ret = 0; + + if (likely(l4proto->ctnl_timeout.nlattr_to_obj)) { + struct nlattr *tb[l4proto->ctnl_timeout.nlattr_max+1]; + + nla_parse_nested(tb, l4proto->ctnl_timeout.nlattr_max, + attr, l4proto->ctnl_timeout.nla_policy); + + ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, &timeout->data); + } + return ret; +} + +static int +cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + __u16 l3num; + __u8 l4num; + struct nf_conntrack_l4proto *l4proto; + struct ctnl_timeout *timeout, *matching = NULL; + char *name; + int ret; + + if (!cda[CTA_TIMEOUT_NAME] || + !cda[CTA_TIMEOUT_L3PROTO] || + !cda[CTA_TIMEOUT_L4PROTO] || + !cda[CTA_TIMEOUT_DATA]) + return -EINVAL; + + name = nla_data(cda[CTA_TIMEOUT_NAME]); + l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO])); + l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); + + list_for_each_entry(timeout, &cttimeout_list, head) { + if (strncmp(timeout->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) + continue; + + if (nlh->nlmsg_flags & NLM_F_EXCL) + return -EEXIST; + + matching = timeout; + break; + } + + l4proto = __nf_ct_l4proto_find(l3num, l4num); + + /* This protocol is not supportted, skip. */ + if (l4proto->l4proto != l4num) + return -EOPNOTSUPP; + + 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->l4num != l4num) + return -EINVAL; + + ret = ctnl_timeout_parse_policy(matching, l4proto, + cda[CTA_TIMEOUT_DATA]); + return ret; + } + return -EBUSY; + } + + timeout = kzalloc(sizeof(struct ctnl_timeout) + + l4proto->ctnl_timeout.obj_size, GFP_KERNEL); + if (timeout == NULL) + return -ENOMEM; + + ret = ctnl_timeout_parse_policy(timeout, l4proto, + cda[CTA_TIMEOUT_DATA]); + if (ret < 0) + goto err; + + strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME])); + timeout->l3num = l3num; + timeout->l4num = l4num; + atomic_set(&timeout->refcnt, 1); + list_add_tail_rcu(&timeout->head, &cttimeout_list); + + return 0; +err: + kfree(timeout); + return ret; +} + +static int +ctnl_timeout_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, + int event, struct ctnl_timeout *timeout) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + unsigned int flags = pid ? NLM_F_MULTI : 0; + struct nf_conntrack_l4proto *l4proto; + + event |= NFNL_SUBSYS_CTNETLINK_TIMEOUT << 8; + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = AF_UNSPEC; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + NLA_PUT_STRING(skb, CTA_TIMEOUT_NAME, timeout->name); + NLA_PUT_BE16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num)); + NLA_PUT_U8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4num); + NLA_PUT_BE32(skb, CTA_TIMEOUT_USE, + htonl(atomic_read(&timeout->refcnt))); + + l4proto = __nf_ct_l4proto_find(timeout->l3num, timeout->l4num); + + /* If the timeout object does not match the layer 4 protocol tracker, + * then skip dumping the data part since we don't know how to + * interpret it. This may happen for UPDlite, SCTP and DCCP since + * you can unload the module. + */ + if (timeout->l4num != l4proto->l4proto) + goto out; + + if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) { + struct nlattr *nest_parms; + int ret; + + nest_parms = nla_nest_start(skb, + CTA_TIMEOUT_DATA | NLA_F_NESTED); + if (!nest_parms) + goto nla_put_failure; + + ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, &timeout->data); + if (ret < 0) + goto nla_put_failure; + + nla_nest_end(skb, nest_parms); + } +out: + nlmsg_end(skb, nlh); + return skb->len; + +nlmsg_failure: +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -1; +} + +static int +ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ctnl_timeout *cur, *last; + + if (cb->args[2]) + return 0; + + last = (struct ctnl_timeout *)cb->args[1]; + if (cb->args[1]) + cb->args[1] = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(cur, &cttimeout_list, head) { + if (last && cur != last) + continue; + + if (ctnl_timeout_fill_info(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + NFNL_MSG_TYPE(cb->nlh->nlmsg_type), + IPCTNL_MSG_TIMEOUT_NEW, cur) < 0) { + cb->args[1] = (unsigned long)cur; + break; + } + } + if (!cb->args[1]) + cb->args[2] = 1; + rcu_read_unlock(); + return skb->len; +} + +static int +cttimeout_get_timeout(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + int ret = -ENOENT; + char *name; + struct ctnl_timeout *cur; + + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = ctnl_timeout_dump, + }; + return netlink_dump_start(ctnl, skb, nlh, &c); + } + + if (!cda[CTA_TIMEOUT_NAME]) + return -EINVAL; + name = nla_data(cda[CTA_TIMEOUT_NAME]); + + list_for_each_entry(cur, &cttimeout_list, head) { + struct sk_buff *skb2; + + if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) + continue; + + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) { + ret = -ENOMEM; + break; + } + + ret = ctnl_timeout_fill_info(skb2, NETLINK_CB(skb).pid, + nlh->nlmsg_seq, + NFNL_MSG_TYPE(nlh->nlmsg_type), + IPCTNL_MSG_TIMEOUT_NEW, cur); + if (ret <= 0) { + kfree_skb(skb2); + break; + } + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, + MSG_DONTWAIT); + if (ret > 0) + ret = 0; + + /* this avoids a loop in nfnetlink. */ + return ret == -EAGAIN ? -ENOBUFS : ret; + } + return ret; +} + +/* try to delete object, fail if it is still in use. */ +static int ctnl_timeout_try_del(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 are protected by nfnl mutex. */ + list_del_rcu(&timeout->head); + kfree_rcu(timeout, rcu_head); + } else { + /* still in use, restore reference counter. */ + atomic_inc(&timeout->refcnt); + ret = -EBUSY; + } + return ret; +} + +static int +cttimeout_del_timeout(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + char *name; + struct ctnl_timeout *cur; + int ret = -ENOENT; + + if (!cda[CTA_TIMEOUT_NAME]) { + list_for_each_entry(cur, &cttimeout_list, head) + ctnl_timeout_try_del(cur); + + return 0; + } + name = nla_data(cda[CTA_TIMEOUT_NAME]); + + list_for_each_entry(cur, &cttimeout_list, head) { + if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) + continue; + + ret = ctnl_timeout_try_del(cur); + if (ret < 0) + return ret; + + break; + } + return ret; +} + +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT +static struct ctnl_timeout *ctnl_timeout_find_get(const char *name) +{ + struct ctnl_timeout *timeout, *matching = NULL; + + rcu_read_lock(); + list_for_each_entry_rcu(timeout, &cttimeout_list, head) { + if (strncmp(timeout->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) + continue; + + if (!try_module_get(THIS_MODULE)) + goto err; + + if (!atomic_inc_not_zero(&timeout->refcnt)) { + module_put(THIS_MODULE); + goto err; + } + matching = timeout; + break; + } +err: + rcu_read_unlock(); + return matching; +} + +static void ctnl_timeout_put(struct ctnl_timeout *timeout) +{ + atomic_dec(&timeout->refcnt); + module_put(THIS_MODULE); +} +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ + +static const struct nfnl_callback cttimeout_cb[IPCTNL_MSG_TIMEOUT_MAX] = { + [IPCTNL_MSG_TIMEOUT_NEW] = { .call = cttimeout_new_timeout, + .attr_count = CTA_TIMEOUT_MAX, + .policy = cttimeout_nla_policy }, + [IPCTNL_MSG_TIMEOUT_GET] = { .call = cttimeout_get_timeout, + .attr_count = CTA_TIMEOUT_MAX, + .policy = cttimeout_nla_policy }, + [IPCTNL_MSG_TIMEOUT_DELETE] = { .call = cttimeout_del_timeout, + .attr_count = CTA_TIMEOUT_MAX, + .policy = cttimeout_nla_policy }, +}; + +static const struct nfnetlink_subsystem cttimeout_subsys = { + .name = "conntrack_timeout", + .subsys_id = NFNL_SUBSYS_CTNETLINK_TIMEOUT, + .cb_count = IPCTNL_MSG_TIMEOUT_MAX, + .cb = cttimeout_cb, +}; + +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_TIMEOUT); + +static int __init cttimeout_init(void) +{ + int ret; + + ret = nfnetlink_subsys_register(&cttimeout_subsys); + if (ret < 0) { + pr_err("cttimeout_init: cannot register cttimeout with " + "nfnetlink.\n"); + goto err_out; + } +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, ctnl_timeout_find_get); + RCU_INIT_POINTER(nf_ct_timeout_put_hook, ctnl_timeout_put); +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ + return 0; + +err_out: + return ret; +} + +static void __exit cttimeout_exit(void) +{ + struct ctnl_timeout *cur, *tmp; + + pr_info("cttimeout: unregistering from nfnetlink.\n"); + + nfnetlink_subsys_unregister(&cttimeout_subsys); + list_for_each_entry_safe(cur, tmp, &cttimeout_list, head) { + list_del_rcu(&cur->head); + /* We are sure that our objects have no clients at this point, + * it's safe to release them all without checking refcnt. + */ + kfree_rcu(cur, rcu_head); + } +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL); + RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL); +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ +} + +module_init(cttimeout_init); +module_exit(cttimeout_exit); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 0221d10de75a..b873445df444 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -16,10 +16,11 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_ecache.h> +#include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> -static unsigned int xt_ct_target(struct sk_buff *skb, - const struct xt_action_param *par) +static unsigned int xt_ct_target_v0(struct sk_buff *skb, + const struct xt_action_param *par) { const struct xt_ct_target_info *info = par->targinfo; struct nf_conn *ct = info->ct; @@ -35,6 +36,23 @@ static unsigned int xt_ct_target(struct sk_buff *skb, return XT_CONTINUE; } +static unsigned int xt_ct_target_v1(struct sk_buff *skb, + const struct xt_action_param *par) +{ + const struct xt_ct_target_info_v1 *info = par->targinfo; + struct nf_conn *ct = info->ct; + + /* Previously seen (loopback)? Ignore. */ + if (skb->nfct != NULL) + return XT_CONTINUE; + + atomic_inc(&ct->ct_general.use); + skb->nfct = &ct->ct_general; + skb->nfctinfo = IP_CT_NEW; + + return XT_CONTINUE; +} + static u8 xt_ct_find_proto(const struct xt_tgchk_param *par) { if (par->family == NFPROTO_IPV4) { @@ -53,7 +71,7 @@ static u8 xt_ct_find_proto(const struct xt_tgchk_param *par) return 0; } -static int xt_ct_tg_check(const struct xt_tgchk_param *par) +static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) { struct xt_ct_target_info *info = par->targinfo; struct nf_conntrack_tuple t; @@ -130,7 +148,137 @@ err1: return ret; } -static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par) +static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) +{ + struct xt_ct_target_info_v1 *info = par->targinfo; + struct nf_conntrack_tuple t; + struct nf_conn_help *help; + struct nf_conn *ct; + int ret = 0; + u8 proto; + + if (info->flags & ~XT_CT_NOTRACK) + return -EINVAL; + + if (info->flags & XT_CT_NOTRACK) { + ct = nf_ct_untracked_get(); + atomic_inc(&ct->ct_general.use); + goto out; + } + +#ifndef CONFIG_NF_CONNTRACK_ZONES + if (info->zone) + goto err1; +#endif + + ret = nf_ct_l3proto_try_module_get(par->family); + if (ret < 0) + goto err1; + + memset(&t, 0, sizeof(t)); + ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL); + ret = PTR_ERR(ct); + if (IS_ERR(ct)) + goto err2; + + ret = 0; + if ((info->ct_events || info->exp_events) && + !nf_ct_ecache_ext_add(ct, info->ct_events, info->exp_events, + GFP_KERNEL)) + goto err3; + + if (info->helper[0]) { + ret = -ENOENT; + proto = xt_ct_find_proto(par); + if (!proto) { + pr_info("You must specify a L4 protocol, " + "and not use inversions on it.\n"); + goto err3; + } + + ret = -ENOMEM; + help = nf_ct_helper_ext_add(ct, GFP_KERNEL); + if (help == NULL) + goto err3; + + ret = -ENOENT; + help->helper = nf_conntrack_helper_try_module_get(info->helper, + par->family, + proto); + if (help->helper == NULL) { + pr_info("No such helper \"%s\"\n", info->helper); + goto err3; + } + } + +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + if (info->timeout) { + typeof(nf_ct_timeout_find_get_hook) timeout_find_get; + struct ctnl_timeout *timeout; + struct nf_conn_timeout *timeout_ext; + + timeout_find_get = + rcu_dereference(nf_ct_timeout_find_get_hook); + + if (timeout_find_get) { + const struct ipt_entry *e = par->entryinfo; + + if (e->ip.invflags & IPT_INV_PROTO) { + ret = -EINVAL; + pr_info("You cannot use inversion on " + "L4 protocol\n"); + goto err3; + } + timeout = timeout_find_get(info->timeout); + if (timeout == NULL) { + ret = -ENOENT; + pr_info("No such timeout policy \"%s\"\n", + info->timeout); + goto err3; + } + if (timeout->l3num != par->family) { + ret = -EINVAL; + pr_info("Timeout policy `%s' can only be " + "used by L3 protocol number %d\n", + info->timeout, timeout->l3num); + goto err3; + } + if (timeout->l4num != e->ip.proto) { + ret = -EINVAL; + pr_info("Timeout policy `%s' can only be " + "used by L4 protocol number %d\n", + info->timeout, timeout->l4num); + goto err3; + } + timeout_ext = nf_ct_timeout_ext_add(ct, timeout, + GFP_KERNEL); + if (timeout_ext == NULL) { + ret = -ENOMEM; + goto err3; + } + } else { + ret = -ENOENT; + pr_info("Timeout policy base is empty\n"); + goto err3; + } + } +#endif + + __set_bit(IPS_TEMPLATE_BIT, &ct->status); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); +out: + info->ct = ct; + return 0; + +err3: + nf_conntrack_free(ct); +err2: + nf_ct_l3proto_module_put(par->family); +err1: + return ret; +} + +static void xt_ct_tg_destroy_v0(const struct xt_tgdtor_param *par) { struct xt_ct_target_info *info = par->targinfo; struct nf_conn *ct = info->ct; @@ -146,25 +294,67 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par) nf_ct_put(info->ct); } -static struct xt_target xt_ct_tg __read_mostly = { - .name = "CT", - .family = NFPROTO_UNSPEC, - .targetsize = sizeof(struct xt_ct_target_info), - .checkentry = xt_ct_tg_check, - .destroy = xt_ct_tg_destroy, - .target = xt_ct_target, - .table = "raw", - .me = THIS_MODULE, +static void xt_ct_tg_destroy_v1(const struct xt_tgdtor_param *par) +{ + struct xt_ct_target_info_v1 *info = par->targinfo; + struct nf_conn *ct = info->ct; + struct nf_conn_help *help; +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + struct nf_conn_timeout *timeout_ext; + typeof(nf_ct_timeout_put_hook) timeout_put; +#endif + if (!nf_ct_is_untracked(ct)) { + help = nfct_help(ct); + if (help) + module_put(help->helper->me); + + nf_ct_l3proto_module_put(par->family); + +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + timeout_put = rcu_dereference(nf_ct_timeout_put_hook); + + if (timeout_put) { + timeout_ext = nf_ct_timeout_find(ct); + if (timeout_ext) + timeout_put(timeout_ext->timeout); + } +#endif + } + nf_ct_put(info->ct); +} + +static struct xt_target xt_ct_tg_reg[] __read_mostly = { + { + .name = "CT", + .family = NFPROTO_UNSPEC, + .targetsize = sizeof(struct xt_ct_target_info), + .checkentry = xt_ct_tg_check_v0, + .destroy = xt_ct_tg_destroy_v0, + .target = xt_ct_target_v0, + .table = "raw", + .me = THIS_MODULE, + }, + { + .name = "CT", + .family = NFPROTO_UNSPEC, + .revision = 1, + .targetsize = sizeof(struct xt_ct_target_info_v1), + .checkentry = xt_ct_tg_check_v1, + .destroy = xt_ct_tg_destroy_v1, + .target = xt_ct_target_v1, + .table = "raw", + .me = THIS_MODULE, + }, }; static int __init xt_ct_tg_init(void) { - return xt_register_target(&xt_ct_tg); + return xt_register_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg)); } static void __exit xt_ct_tg_exit(void) { - xt_unregister_target(&xt_ct_tg); + xt_unregister_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg)); } module_init(xt_ct_tg_init); diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c new file mode 100644 index 000000000000..f99f8dee238b --- /dev/null +++ b/net/netfilter/xt_LOG.c @@ -0,0 +1,925 @@ +/* + * This is a module which is used for logging packets. + */ + +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/skbuff.h> +#include <linux/if_arp.h> +#include <linux/ip.h> +#include <net/ipv6.h> +#include <net/icmp.h> +#include <net/udp.h> +#include <net/tcp.h> +#include <net/route.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_LOG.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <net/netfilter/nf_log.h> +#include <net/netfilter/xt_log.h> + +static struct nf_loginfo default_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = 5, + .logflags = NF_LOG_MASK, + }, + }, +}; + +static int dump_udp_header(struct sbuff *m, const struct sk_buff *skb, + u8 proto, int fragment, unsigned int offset) +{ + struct udphdr _udph; + const struct udphdr *uh; + + if (proto == IPPROTO_UDP) + /* Max length: 10 "PROTO=UDP " */ + sb_add(m, "PROTO=UDP "); + else /* Max length: 14 "PROTO=UDPLITE " */ + sb_add(m, "PROTO=UDPLITE "); + + if (fragment) + goto out; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); + if (uh == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); + + return 1; + } + + /* Max length: 20 "SPT=65535 DPT=65535 " */ + sb_add(m, "SPT=%u DPT=%u LEN=%u ", ntohs(uh->source), ntohs(uh->dest), + ntohs(uh->len)); + +out: + return 0; +} + +static int dump_tcp_header(struct sbuff *m, const struct sk_buff *skb, + u8 proto, int fragment, unsigned int offset, + unsigned int logflags) +{ + struct tcphdr _tcph; + const struct tcphdr *th; + + /* Max length: 10 "PROTO=TCP " */ + sb_add(m, "PROTO=TCP "); + + if (fragment) + return 0; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); + if (th == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); + return 1; + } + + /* Max length: 20 "SPT=65535 DPT=65535 " */ + sb_add(m, "SPT=%u DPT=%u ", ntohs(th->source), ntohs(th->dest)); + /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ + if (logflags & XT_LOG_TCPSEQ) + sb_add(m, "SEQ=%u ACK=%u ", ntohl(th->seq), ntohl(th->ack_seq)); + + /* Max length: 13 "WINDOW=65535 " */ + sb_add(m, "WINDOW=%u ", ntohs(th->window)); + /* Max length: 9 "RES=0x3C " */ + sb_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & + TCP_RESERVED_BITS) >> 22)); + /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ + if (th->cwr) + sb_add(m, "CWR "); + if (th->ece) + sb_add(m, "ECE "); + if (th->urg) + sb_add(m, "URG "); + if (th->ack) + sb_add(m, "ACK "); + if (th->psh) + sb_add(m, "PSH "); + if (th->rst) + sb_add(m, "RST "); + if (th->syn) + sb_add(m, "SYN "); + if (th->fin) + sb_add(m, "FIN "); + /* Max length: 11 "URGP=65535 " */ + sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); + + if ((logflags & XT_LOG_TCPOPT) && th->doff*4 > sizeof(struct tcphdr)) { + u_int8_t _opt[60 - sizeof(struct tcphdr)]; + const u_int8_t *op; + unsigned int i; + unsigned int optsize = th->doff*4 - sizeof(struct tcphdr); + + op = skb_header_pointer(skb, offset + sizeof(struct tcphdr), + optsize, _opt); + if (op == NULL) { + sb_add(m, "OPT (TRUNCATED)"); + return 1; + } + + /* Max length: 127 "OPT (" 15*4*2chars ") " */ + sb_add(m, "OPT ("); + for (i = 0; i < optsize; i++) + sb_add(m, "%02X", op[i]); + + sb_add(m, ") "); + } + + return 0; +} + +/* One level of recursion won't kill us */ +static void dump_ipv4_packet(struct sbuff *m, + const struct nf_loginfo *info, + const struct sk_buff *skb, + unsigned int iphoff) +{ + struct iphdr _iph; + const struct iphdr *ih; + unsigned int logflags; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_MASK; + + ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); + if (ih == NULL) { + sb_add(m, "TRUNCATED"); + return; + } + + /* Important fields: + * TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */ + /* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */ + sb_add(m, "SRC=%pI4 DST=%pI4 ", + &ih->saddr, &ih->daddr); + + /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ + sb_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", + ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, + ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); + + /* Max length: 6 "CE DF MF " */ + if (ntohs(ih->frag_off) & IP_CE) + sb_add(m, "CE "); + if (ntohs(ih->frag_off) & IP_DF) + sb_add(m, "DF "); + if (ntohs(ih->frag_off) & IP_MF) + sb_add(m, "MF "); + + /* Max length: 11 "FRAG:65535 " */ + if (ntohs(ih->frag_off) & IP_OFFSET) + sb_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); + + if ((logflags & XT_LOG_IPOPT) && + ih->ihl * 4 > sizeof(struct iphdr)) { + const unsigned char *op; + unsigned char _opt[4 * 15 - sizeof(struct iphdr)]; + unsigned int i, optsize; + + optsize = ih->ihl * 4 - sizeof(struct iphdr); + op = skb_header_pointer(skb, iphoff+sizeof(_iph), + optsize, _opt); + if (op == NULL) { + sb_add(m, "TRUNCATED"); + return; + } + + /* Max length: 127 "OPT (" 15*4*2chars ") " */ + sb_add(m, "OPT ("); + for (i = 0; i < optsize; i++) + sb_add(m, "%02X", op[i]); + sb_add(m, ") "); + } + + switch (ih->protocol) { + case IPPROTO_TCP: + if (dump_tcp_header(m, skb, ih->protocol, + ntohs(ih->frag_off) & IP_OFFSET, + iphoff+ih->ihl*4, logflags)) + return; + break; + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + if (dump_udp_header(m, skb, ih->protocol, + ntohs(ih->frag_off) & IP_OFFSET, + iphoff+ih->ihl*4)) + return; + break; + case IPPROTO_ICMP: { + struct icmphdr _icmph; + const struct icmphdr *ich; + static const size_t required_len[NR_ICMP_TYPES+1] + = { [ICMP_ECHOREPLY] = 4, + [ICMP_DEST_UNREACH] + = 8 + sizeof(struct iphdr), + [ICMP_SOURCE_QUENCH] + = 8 + sizeof(struct iphdr), + [ICMP_REDIRECT] + = 8 + sizeof(struct iphdr), + [ICMP_ECHO] = 4, + [ICMP_TIME_EXCEEDED] + = 8 + sizeof(struct iphdr), + [ICMP_PARAMETERPROB] + = 8 + sizeof(struct iphdr), + [ICMP_TIMESTAMP] = 20, + [ICMP_TIMESTAMPREPLY] = 20, + [ICMP_ADDRESS] = 12, + [ICMP_ADDRESSREPLY] = 12 }; + + /* Max length: 11 "PROTO=ICMP " */ + sb_add(m, "PROTO=ICMP "); + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ich = skb_header_pointer(skb, iphoff + ih->ihl * 4, + sizeof(_icmph), &_icmph); + if (ich == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + /* Max length: 18 "TYPE=255 CODE=255 " */ + sb_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code); + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + if (ich->type <= NR_ICMP_TYPES && + required_len[ich->type] && + skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { + sb_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + switch (ich->type) { + case ICMP_ECHOREPLY: + case ICMP_ECHO: + /* Max length: 19 "ID=65535 SEQ=65535 " */ + sb_add(m, "ID=%u SEQ=%u ", + ntohs(ich->un.echo.id), + ntohs(ich->un.echo.sequence)); + break; + + case ICMP_PARAMETERPROB: + /* Max length: 14 "PARAMETER=255 " */ + sb_add(m, "PARAMETER=%u ", + ntohl(ich->un.gateway) >> 24); + break; + case ICMP_REDIRECT: + /* Max length: 24 "GATEWAY=255.255.255.255 " */ + sb_add(m, "GATEWAY=%pI4 ", &ich->un.gateway); + /* Fall through */ + case ICMP_DEST_UNREACH: + case ICMP_SOURCE_QUENCH: + case ICMP_TIME_EXCEEDED: + /* Max length: 3+maxlen */ + if (!iphoff) { /* Only recurse once. */ + sb_add(m, "["); + dump_ipv4_packet(m, info, skb, + iphoff + ih->ihl*4+sizeof(_icmph)); + sb_add(m, "] "); + } + + /* Max length: 10 "MTU=65535 " */ + if (ich->type == ICMP_DEST_UNREACH && + ich->code == ICMP_FRAG_NEEDED) + sb_add(m, "MTU=%u ", ntohs(ich->un.frag.mtu)); + } + break; + } + /* Max Length */ + case IPPROTO_AH: { + struct ip_auth_hdr _ahdr; + const struct ip_auth_hdr *ah; + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 9 "PROTO=AH " */ + sb_add(m, "PROTO=AH "); + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ah = skb_header_pointer(skb, iphoff+ih->ihl*4, + sizeof(_ahdr), &_ahdr); + if (ah == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + /* Length: 15 "SPI=0xF1234567 " */ + sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); + break; + } + case IPPROTO_ESP: { + struct ip_esp_hdr _esph; + const struct ip_esp_hdr *eh; + + /* Max length: 10 "PROTO=ESP " */ + sb_add(m, "PROTO=ESP "); + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + eh = skb_header_pointer(skb, iphoff+ih->ihl*4, + sizeof(_esph), &_esph); + if (eh == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + /* Length: 15 "SPI=0xF1234567 " */ + sb_add(m, "SPI=0x%x ", ntohl(eh->spi)); + break; + } + /* Max length: 10 "PROTO 255 " */ + default: + sb_add(m, "PROTO=%u ", ih->protocol); + } + + /* Max length: 15 "UID=4294967295 " */ + if ((logflags & XT_LOG_UID) && !iphoff && skb->sk) { + read_lock_bh(&skb->sk->sk_callback_lock); + if (skb->sk->sk_socket && skb->sk->sk_socket->file) + sb_add(m, "UID=%u GID=%u ", + skb->sk->sk_socket->file->f_cred->fsuid, + skb->sk->sk_socket->file->f_cred->fsgid); + read_unlock_bh(&skb->sk->sk_callback_lock); + } + + /* Max length: 16 "MARK=0xFFFFFFFF " */ + if (!iphoff && skb->mark) + sb_add(m, "MARK=0x%x ", skb->mark); + + /* Proto Max log string length */ + /* IP: 40+46+6+11+127 = 230 */ + /* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */ + /* UDP: 10+max(25,20) = 35 */ + /* UDPLITE: 14+max(25,20) = 39 */ + /* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */ + /* ESP: 10+max(25)+15 = 50 */ + /* AH: 9+max(25)+15 = 49 */ + /* unknown: 10 */ + + /* (ICMP allows recursion one level deep) */ + /* maxlen = IP + ICMP + IP + max(TCP,UDP,ICMP,unknown) */ + /* maxlen = 230+ 91 + 230 + 252 = 803 */ +} + +static void dump_ipv4_mac_header(struct sbuff *m, + const struct nf_loginfo *info, + const struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + unsigned int logflags = 0; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + + if (!(logflags & XT_LOG_MACDECODE)) + goto fallback; + + switch (dev->type) { + case ARPHRD_ETHER: + sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + ntohs(eth_hdr(skb)->h_proto)); + return; + default: + break; + } + +fallback: + sb_add(m, "MAC="); + if (dev->hard_header_len && + skb->mac_header != skb->network_header) { + const unsigned char *p = skb_mac_header(skb); + unsigned int i; + + sb_add(m, "%02x", *p++); + for (i = 1; i < dev->hard_header_len; i++, p++) + sb_add(m, ":%02x", *p); + } + sb_add(m, " "); +} + +static void +log_packet_common(struct sbuff *m, + u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, + prefix, + in ? in->name : "", + out ? out->name : ""); +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge) { + const struct net_device *physindev; + const struct net_device *physoutdev; + + physindev = skb->nf_bridge->physindev; + if (physindev && in != physindev) + sb_add(m, "PHYSIN=%s ", physindev->name); + physoutdev = skb->nf_bridge->physoutdev; + if (physoutdev && out != physoutdev) + sb_add(m, "PHYSOUT=%s ", physoutdev->name); + } +#endif +} + + +static void +ipt_log_packet(u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + struct sbuff *m = sb_open(); + + if (!loginfo) + loginfo = &default_loginfo; + + log_packet_common(m, pf, hooknum, skb, in, out, loginfo, prefix); + + if (in != NULL) + dump_ipv4_mac_header(m, loginfo, skb); + + dump_ipv4_packet(m, loginfo, skb, 0); + + sb_close(m); +} + +#if IS_ENABLED(CONFIG_IPV6) +/* One level of recursion won't kill us */ +static void dump_ipv6_packet(struct sbuff *m, + const struct nf_loginfo *info, + const struct sk_buff *skb, unsigned int ip6hoff, + int recurse) +{ + u_int8_t currenthdr; + int fragment; + struct ipv6hdr _ip6h; + const struct ipv6hdr *ih; + unsigned int ptr; + unsigned int hdrlen = 0; + unsigned int logflags; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_MASK; + + ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); + if (ih == NULL) { + sb_add(m, "TRUNCATED"); + return; + } + + /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ + sb_add(m, "SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); + + /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ + sb_add(m, "LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", + ntohs(ih->payload_len) + sizeof(struct ipv6hdr), + (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, + ih->hop_limit, + (ntohl(*(__be32 *)ih) & 0x000fffff)); + + fragment = 0; + ptr = ip6hoff + sizeof(struct ipv6hdr); + currenthdr = ih->nexthdr; + while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) { + struct ipv6_opt_hdr _hdr; + const struct ipv6_opt_hdr *hp; + + hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); + if (hp == NULL) { + sb_add(m, "TRUNCATED"); + return; + } + + /* Max length: 48 "OPT (...) " */ + if (logflags & XT_LOG_IPOPT) + sb_add(m, "OPT ( "); + + switch (currenthdr) { + case IPPROTO_FRAGMENT: { + struct frag_hdr _fhdr; + const struct frag_hdr *fh; + + sb_add(m, "FRAG:"); + fh = skb_header_pointer(skb, ptr, sizeof(_fhdr), + &_fhdr); + if (fh == NULL) { + sb_add(m, "TRUNCATED "); + return; + } + + /* Max length: 6 "65535 " */ + sb_add(m, "%u ", ntohs(fh->frag_off) & 0xFFF8); + + /* Max length: 11 "INCOMPLETE " */ + if (fh->frag_off & htons(0x0001)) + sb_add(m, "INCOMPLETE "); + + sb_add(m, "ID:%08x ", ntohl(fh->identification)); + + if (ntohs(fh->frag_off) & 0xFFF8) + fragment = 1; + + hdrlen = 8; + + break; + } + case IPPROTO_DSTOPTS: + case IPPROTO_ROUTING: + case IPPROTO_HOPOPTS: + if (fragment) { + if (logflags & XT_LOG_IPOPT) + sb_add(m, ")"); + return; + } + hdrlen = ipv6_optlen(hp); + break; + /* Max Length */ + case IPPROTO_AH: + if (logflags & XT_LOG_IPOPT) { + struct ip_auth_hdr _ahdr; + const struct ip_auth_hdr *ah; + + /* Max length: 3 "AH " */ + sb_add(m, "AH "); + + if (fragment) { + sb_add(m, ")"); + return; + } + + ah = skb_header_pointer(skb, ptr, sizeof(_ahdr), + &_ahdr); + if (ah == NULL) { + /* + * Max length: 26 "INCOMPLETE [65535 + * bytes] )" + */ + sb_add(m, "INCOMPLETE [%u bytes] )", + skb->len - ptr); + return; + } + + /* Length: 15 "SPI=0xF1234567 */ + sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); + + } + + hdrlen = (hp->hdrlen+2)<<2; + break; + case IPPROTO_ESP: + if (logflags & XT_LOG_IPOPT) { + struct ip_esp_hdr _esph; + const struct ip_esp_hdr *eh; + + /* Max length: 4 "ESP " */ + sb_add(m, "ESP "); + + if (fragment) { + sb_add(m, ")"); + return; + } + + /* + * Max length: 26 "INCOMPLETE [65535 bytes] )" + */ + eh = skb_header_pointer(skb, ptr, sizeof(_esph), + &_esph); + if (eh == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] )", + skb->len - ptr); + return; + } + + /* Length: 16 "SPI=0xF1234567 )" */ + sb_add(m, "SPI=0x%x )", ntohl(eh->spi)); + + } + return; + default: + /* Max length: 20 "Unknown Ext Hdr 255" */ + sb_add(m, "Unknown Ext Hdr %u", currenthdr); + return; + } + if (logflags & XT_LOG_IPOPT) + sb_add(m, ") "); + + currenthdr = hp->nexthdr; + ptr += hdrlen; + } + + switch (currenthdr) { + case IPPROTO_TCP: + if (dump_tcp_header(m, skb, currenthdr, fragment, ptr, + logflags)) + return; + break; + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + if (dump_udp_header(m, skb, currenthdr, fragment, ptr)) + return; + break; + case IPPROTO_ICMPV6: { + struct icmp6hdr _icmp6h; + const struct icmp6hdr *ic; + + /* Max length: 13 "PROTO=ICMPv6 " */ + sb_add(m, "PROTO=ICMPv6 "); + + if (fragment) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h); + if (ic == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); + return; + } + + /* Max length: 18 "TYPE=255 CODE=255 " */ + sb_add(m, "TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code); + + switch (ic->icmp6_type) { + case ICMPV6_ECHO_REQUEST: + case ICMPV6_ECHO_REPLY: + /* Max length: 19 "ID=65535 SEQ=65535 " */ + sb_add(m, "ID=%u SEQ=%u ", + ntohs(ic->icmp6_identifier), + ntohs(ic->icmp6_sequence)); + break; + case ICMPV6_MGM_QUERY: + case ICMPV6_MGM_REPORT: + case ICMPV6_MGM_REDUCTION: + break; + + case ICMPV6_PARAMPROB: + /* Max length: 17 "POINTER=ffffffff " */ + sb_add(m, "POINTER=%08x ", ntohl(ic->icmp6_pointer)); + /* Fall through */ + case ICMPV6_DEST_UNREACH: + case ICMPV6_PKT_TOOBIG: + case ICMPV6_TIME_EXCEED: + /* Max length: 3+maxlen */ + if (recurse) { + sb_add(m, "["); + dump_ipv6_packet(m, info, skb, + ptr + sizeof(_icmp6h), 0); + sb_add(m, "] "); + } + + /* Max length: 10 "MTU=65535 " */ + if (ic->icmp6_type == ICMPV6_PKT_TOOBIG) + sb_add(m, "MTU=%u ", ntohl(ic->icmp6_mtu)); + } + break; + } + /* Max length: 10 "PROTO=255 " */ + default: + sb_add(m, "PROTO=%u ", currenthdr); + } + + /* Max length: 15 "UID=4294967295 " */ + if ((logflags & XT_LOG_UID) && recurse && skb->sk) { + read_lock_bh(&skb->sk->sk_callback_lock); + if (skb->sk->sk_socket && skb->sk->sk_socket->file) + sb_add(m, "UID=%u GID=%u ", + skb->sk->sk_socket->file->f_cred->fsuid, + skb->sk->sk_socket->file->f_cred->fsgid); + read_unlock_bh(&skb->sk->sk_callback_lock); + } + + /* Max length: 16 "MARK=0xFFFFFFFF " */ + if (!recurse && skb->mark) + sb_add(m, "MARK=0x%x ", skb->mark); +} + +static void dump_ipv6_mac_header(struct sbuff *m, + const struct nf_loginfo *info, + const struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + unsigned int logflags = 0; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + + if (!(logflags & XT_LOG_MACDECODE)) + goto fallback; + + switch (dev->type) { + case ARPHRD_ETHER: + sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + ntohs(eth_hdr(skb)->h_proto)); + return; + default: + break; + } + +fallback: + sb_add(m, "MAC="); + if (dev->hard_header_len && + skb->mac_header != skb->network_header) { + const unsigned char *p = skb_mac_header(skb); + unsigned int len = dev->hard_header_len; + unsigned int i; + + if (dev->type == ARPHRD_SIT) { + p -= ETH_HLEN; + + if (p < skb->head) + p = NULL; + } + + if (p != NULL) { + sb_add(m, "%02x", *p++); + for (i = 1; i < len; i++) + sb_add(m, ":%02x", *p++); + } + sb_add(m, " "); + + if (dev->type == ARPHRD_SIT) { + const struct iphdr *iph = + (struct iphdr *)skb_mac_header(skb); + sb_add(m, "TUNNEL=%pI4->%pI4 ", &iph->saddr, + &iph->daddr); + } + } else + sb_add(m, " "); +} + +static void +ip6t_log_packet(u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + struct sbuff *m = sb_open(); + + if (!loginfo) + loginfo = &default_loginfo; + + log_packet_common(m, pf, hooknum, skb, in, out, loginfo, prefix); + + if (in != NULL) + dump_ipv6_mac_header(m, loginfo, skb); + + dump_ipv6_packet(m, loginfo, skb, skb_network_offset(skb), 1); + + sb_close(m); +} +#endif + +static unsigned int +log_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_log_info *loginfo = par->targinfo; + struct nf_loginfo li; + + li.type = NF_LOG_TYPE_LOG; + li.u.log.level = loginfo->level; + li.u.log.logflags = loginfo->logflags; + + if (par->family == NFPROTO_IPV4) + ipt_log_packet(NFPROTO_IPV4, par->hooknum, skb, par->in, + par->out, &li, loginfo->prefix); +#if IS_ENABLED(CONFIG_IPV6) + else if (par->family == NFPROTO_IPV6) + ip6t_log_packet(NFPROTO_IPV6, par->hooknum, skb, par->in, + par->out, &li, loginfo->prefix); +#endif + else + WARN_ON_ONCE(1); + + return XT_CONTINUE; +} + +static int log_tg_check(const struct xt_tgchk_param *par) +{ + const struct xt_log_info *loginfo = par->targinfo; + + if (par->family != NFPROTO_IPV4 && par->family != NFPROTO_IPV6) + return -EINVAL; + + if (loginfo->level >= 8) { + pr_debug("level %u >= 8\n", loginfo->level); + return -EINVAL; + } + + if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { + pr_debug("prefix is not null-terminated\n"); + return -EINVAL; + } + + return 0; +} + +static struct xt_target log_tg_regs[] __read_mostly = { + { + .name = "LOG", + .family = NFPROTO_IPV4, + .target = log_tg, + .targetsize = sizeof(struct xt_log_info), + .checkentry = log_tg_check, + .me = THIS_MODULE, + }, +#if IS_ENABLED(CONFIG_IPV6) + { + .name = "LOG", + .family = NFPROTO_IPV6, + .target = log_tg, + .targetsize = sizeof(struct xt_log_info), + .checkentry = log_tg_check, + .me = THIS_MODULE, + }, +#endif +}; + +static struct nf_logger ipt_log_logger __read_mostly = { + .name = "ipt_LOG", + .logfn = &ipt_log_packet, + .me = THIS_MODULE, +}; + +#if IS_ENABLED(CONFIG_IPV6) +static struct nf_logger ip6t_log_logger __read_mostly = { + .name = "ip6t_LOG", + .logfn = &ip6t_log_packet, + .me = THIS_MODULE, +}; +#endif + +static int __init log_tg_init(void) +{ + int ret; + + ret = xt_register_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs)); + if (ret < 0) + return ret; + + nf_log_register(NFPROTO_IPV4, &ipt_log_logger); +#if IS_ENABLED(CONFIG_IPV6) + nf_log_register(NFPROTO_IPV6, &ip6t_log_logger); +#endif + return 0; +} + +static void __exit log_tg_exit(void) +{ + nf_log_unregister(&ipt_log_logger); +#if IS_ENABLED(CONFIG_IPV6) + nf_log_unregister(&ip6t_log_logger); +#endif + xt_unregister_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs)); +} + +module_init(log_tg_init); +module_exit(log_tg_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); +MODULE_AUTHOR("Jan Rekorajski <baggins@pld.org.pl>"); +MODULE_DESCRIPTION("Xtables: IPv4/IPv6 packet logging"); +MODULE_ALIAS("ipt_LOG"); +MODULE_ALIAS("ip6t_LOG"); |