diff options
Diffstat (limited to 'net/netfilter')
38 files changed, 1242 insertions, 629 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index bbc45f8a7b2d..9b28864cc36a 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -162,6 +162,7 @@ config NF_CT_PROTO_SCTP bool 'SCTP protocol connection tracking support' depends on NETFILTER_ADVANCED default y + select LIBCRC32C help With this option enabled, the layer 3 independent connection tracking code will be able to do state tracking on SCTP connections. @@ -397,7 +398,6 @@ config NF_NAT_PROTO_SCTP bool default NF_NAT && NF_CT_PROTO_SCTP depends on NF_NAT && NF_CT_PROTO_SCTP - select LIBCRC32C config NF_NAT_AMANDA tristate @@ -467,10 +467,10 @@ config NF_TABLES_NETDEV This option enables support for the "netdev" table. config NFT_EXTHDR - tristate "Netfilter nf_tables IPv6 exthdr module" + tristate "Netfilter nf_tables exthdr module" help This option adds the "exthdr" expression that you can use to match - IPv6 extension headers. + IPv6 extension headers and tcp options. config NFT_META tristate "Netfilter nf_tables meta module" @@ -509,6 +509,12 @@ config NFT_SET_HASH This option adds the "hash" set type that is used to build one-way mappings between matchings and actions. +config NFT_SET_BITMAP + tristate "Netfilter nf_tables bitmap set module" + help + This option adds the "bitmap" set type that is used to build sets + whose keys are smaller or equal to 16 bits. + config NFT_COUNTER tristate "Netfilter nf_tables counter module" help diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index ca30d1960f1d..c9b78e7b342f 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -7,7 +7,6 @@ nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o -nf_conntrack-$(CONFIG_NF_CT_PROTO_UDPLITE) += nf_conntrack_proto_udplite.o obj-$(CONFIG_NETFILTER) = netfilter.o @@ -47,7 +46,6 @@ nf_nat-y := nf_nat_core.o nf_nat_proto_unknown.o nf_nat_proto_common.o \ # NAT protocols (nf_nat) nf_nat-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o nf_nat-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o -nf_nat-$(CONFIG_NF_NAT_PROTO_UDPLITE) += nf_nat_proto_udplite.o # generic transport layer logging obj-$(CONFIG_NF_LOG_COMMON) += nf_log_common.o @@ -95,6 +93,7 @@ obj-$(CONFIG_NFT_REJECT) += nft_reject.o obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o obj-$(CONFIG_NFT_SET_RBTREE) += nft_set_rbtree.o obj-$(CONFIG_NFT_SET_HASH) += nft_set_hash.o +obj-$(CONFIG_NFT_SET_BITMAP) += nft_set_bitmap.o obj-$(CONFIG_NFT_COUNTER) += nft_counter.o obj-$(CONFIG_NFT_LOG) += nft_log.o obj-$(CONFIG_NFT_MASQ) += nft_masq.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index ce6adfae521a..a87a6f8a74d8 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -375,7 +375,7 @@ void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb) { void (*attach)(struct sk_buff *, const struct sk_buff *); - if (skb->nfct) { + if (skb->_nfct) { rcu_read_lock(); attach = rcu_dereference(ip_ct_attach); if (attach) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 55e0169caa4c..5aeb0dde6ccc 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -426,10 +426,9 @@ ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol */ svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, vport); - if (svc == NULL - && protocol == IPPROTO_TCP - && atomic_read(&ipvs->ftpsvc_counter) - && (vport == FTPDATA || ntohs(vport) >= PROT_SOCK)) { + if (!svc && protocol == IPPROTO_TCP && + atomic_read(&ipvs->ftpsvc_counter) && + (vport == FTPDATA || ntohs(vport) >= inet_prot_sock(ipvs->net))) { /* * Check if ftp service entry exists, the packet * might belong to FTP data connections. @@ -711,7 +710,6 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af, dest->vport == svc->port))) { /* HIT */ list_del(&dest->t_list); - ip_vs_dest_hold(dest); goto out; } } @@ -741,7 +739,7 @@ static void ip_vs_dest_free(struct ip_vs_dest *dest) * When the ip_vs_control_clearup is activated by ipvs module exit, * the service tables must have been flushed and all the connections * are expired, and the refcnt of each destination in the trash must - * be 0, so we simply release them here. + * be 1, so we simply release them here. */ static void ip_vs_trash_cleanup(struct netns_ipvs *ipvs) { @@ -1080,11 +1078,10 @@ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest, if (list_empty(&ipvs->dest_trash) && !cleanup) mod_timer(&ipvs->dest_trash_timer, jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); - /* dest lives in trash without reference */ + /* dest lives in trash with reference */ list_add(&dest->t_list, &ipvs->dest_trash); dest->idle_start = 0; spin_unlock_bh(&ipvs->dest_trash_lock); - ip_vs_dest_put(dest); } @@ -1160,7 +1157,7 @@ static void ip_vs_dest_trash_expire(unsigned long data) spin_lock(&ipvs->dest_trash_lock); list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) { - if (atomic_read(&dest->refcnt) > 0) + if (atomic_read(&dest->refcnt) > 1) continue; if (dest->idle_start) { if (time_before(now, dest->idle_start + diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 4e8083c5e01d..071b97fcbefb 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -350,16 +350,31 @@ static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct) spin_unlock(&pcpu->lock); } +#define NFCT_ALIGN(len) (((len) + NFCT_INFOMASK) & ~NFCT_INFOMASK) + /* Released via destroy_conntrack() */ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, const struct nf_conntrack_zone *zone, gfp_t flags) { - struct nf_conn *tmpl; + struct nf_conn *tmpl, *p; - tmpl = kzalloc(sizeof(*tmpl), flags); - if (tmpl == NULL) - return NULL; + if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK) { + tmpl = kzalloc(sizeof(*tmpl) + NFCT_INFOMASK, flags); + if (!tmpl) + return NULL; + + p = tmpl; + tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p); + if (tmpl != p) { + tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p); + tmpl->proto.tmpl_padto = (char *)tmpl - (char *)p; + } + } else { + tmpl = kzalloc(sizeof(*tmpl), flags); + if (!tmpl) + return NULL; + } tmpl->status = IPS_TEMPLATE; write_pnet(&tmpl->ct_net, net); @@ -374,7 +389,11 @@ void nf_ct_tmpl_free(struct nf_conn *tmpl) { nf_ct_ext_destroy(tmpl); nf_ct_ext_free(tmpl); - kfree(tmpl); + + if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK) + kfree((char *)tmpl - tmpl->proto.tmpl_padto); + else + kfree(tmpl); } EXPORT_SYMBOL_GPL(nf_ct_tmpl_free); @@ -686,12 +705,12 @@ static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, !nfct_nat(ct) && !nf_ct_is_dying(ct) && atomic_inc_not_zero(&ct->ct_general.use)) { - nf_ct_acct_merge(ct, ctinfo, (struct nf_conn *)skb->nfct); - nf_conntrack_put(skb->nfct); - /* Assign conntrack already in hashes to this skbuff. Don't - * modify skb->nfctinfo to ensure consistent stateful filtering. - */ - skb->nfct = &ct->ct_general; + enum ip_conntrack_info oldinfo; + struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo); + + nf_ct_acct_merge(ct, ctinfo, loser_ct); + nf_conntrack_put(&loser_ct->ct_general); + nf_ct_set(skb, ct, oldinfo); return NF_ACCEPT; } NF_CT_STAT_INC(net, drop); @@ -1218,7 +1237,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, return &ct->tuplehash[IP_CT_DIR_ORIGINAL]; } -/* On success, returns conntrack ptr, sets skb->nfct and ctinfo */ +/* On success, returns conntrack ptr, sets skb->_nfct | ctinfo */ static inline struct nf_conn * resolve_normal_ct(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, @@ -1277,8 +1296,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, } *set_reply = 0; } - skb->nfct = &ct->ct_general; - skb->nfctinfo = *ctinfo; + nf_ct_set(skb, ct, *ctinfo); return ct; } @@ -1286,7 +1304,7 @@ unsigned int nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, struct sk_buff *skb) { - struct nf_conn *ct, *tmpl = NULL; + struct nf_conn *ct, *tmpl; enum ip_conntrack_info ctinfo; struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; @@ -1296,14 +1314,14 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, int set_reply = 0; int ret; - if (skb->nfct) { + tmpl = nf_ct_get(skb, &ctinfo); + if (tmpl) { /* Previously seen (loopback or untracked)? Ignore. */ - tmpl = (struct nf_conn *)skb->nfct; if (!nf_ct_is_template(tmpl)) { NF_CT_STAT_INC_ATOMIC(net, ignore); return NF_ACCEPT; } - skb->nfct = NULL; + skb->_nfct = 0; } /* rcu_read_lock()ed by nf_hook_thresh */ @@ -1324,8 +1342,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, * inverse of the return code tells to the netfilter * core what to do with the packet. */ if (l4proto->error != NULL) { - ret = l4proto->error(net, tmpl, skb, dataoff, &ctinfo, - pf, hooknum); + ret = l4proto->error(net, tmpl, skb, dataoff, pf, hooknum); if (ret <= 0) { NF_CT_STAT_INC_ATOMIC(net, error); NF_CT_STAT_INC_ATOMIC(net, invalid); @@ -1333,7 +1350,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, goto out; } /* ICMP[v6] protocol trackers may assign one conntrack. */ - if (skb->nfct) + if (skb->_nfct) goto out; } repeat: @@ -1353,7 +1370,7 @@ repeat: goto out; } - NF_CT_ASSERT(skb->nfct); + NF_CT_ASSERT(skb_nfct(skb)); /* Decide what timeout policy we want to apply to this flow. */ timeouts = nf_ct_timeout_lookup(net, ct, l4proto); @@ -1363,8 +1380,8 @@ repeat: /* Invalid: inverse of the return code tells * the netfilter core what to do */ pr_debug("nf_conntrack_in: Can't track with proto module\n"); - nf_conntrack_put(skb->nfct); - skb->nfct = NULL; + nf_conntrack_put(&ct->ct_general); + skb->_nfct = 0; NF_CT_STAT_INC_ATOMIC(net, invalid); if (ret == -NF_DROP) NF_CT_STAT_INC_ATOMIC(net, drop); @@ -1522,9 +1539,8 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) ctinfo = IP_CT_RELATED; /* Attach to new skbuff, and increment count */ - nskb->nfct = &ct->ct_general; - nskb->nfctinfo = ctinfo; - nf_conntrack_get(nskb->nfct); + nf_ct_set(nskb, ct, ctinfo); + nf_conntrack_get(skb_nfct(nskb)); } /* Bring out ya dead! */ @@ -1860,7 +1876,8 @@ int nf_conntrack_init_start(void) nf_conntrack_max = max_factor * nf_conntrack_htable_size; nf_conntrack_cachep = kmem_cache_create("nf_conntrack", - sizeof(struct nf_conn), 0, + sizeof(struct nf_conn), + NFCT_INFOMASK + 1, SLAB_DESTROY_BY_RCU | SLAB_HWCACHE_ALIGN, NULL); if (!nf_conntrack_cachep) goto err_cachep; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index f8dbacf66795..e19a69787d99 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -353,7 +353,7 @@ void nf_ct_expect_put(struct nf_conntrack_expect *exp) } EXPORT_SYMBOL_GPL(nf_ct_expect_put); -static int nf_ct_expect_insert(struct nf_conntrack_expect *exp) +static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) { struct nf_conn_help *master_help = nfct_help(exp->master); struct nf_conntrack_helper *helper; @@ -380,7 +380,6 @@ static int nf_ct_expect_insert(struct nf_conntrack_expect *exp) add_timer(&exp->timeout); NF_CT_STAT_INC(net, expect_create); - return 0; } /* Race with expectations being used means we could have none to find; OK. */ @@ -464,9 +463,8 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, if (ret <= 0) goto out; - ret = nf_ct_expect_insert(expect); - if (ret < 0) - goto out; + nf_ct_expect_insert(expect); + spin_unlock_bh(&nf_conntrack_expect_lock); nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report); return ret; diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index b68ce6ac13b3..93dd1c5b7bff 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -561,7 +561,6 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, static int dccp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum) { struct dccp_hdr _dh, *dh; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index a0efde38da44..33279aab583d 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -22,7 +22,9 @@ #include <linux/seq_file.h> #include <linux/spinlock.h> #include <linux/interrupt.h> +#include <net/sctp/checksum.h> +#include <net/netfilter/nf_log.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_ecache.h> @@ -505,6 +507,34 @@ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, return true; } +static int sctp_error(struct net *net, struct nf_conn *tpl, struct sk_buff *skb, + unsigned int dataoff, + u8 pf, unsigned int hooknum) +{ + const struct sctphdr *sh; + struct sctphdr _sctph; + const char *logmsg; + + sh = skb_header_pointer(skb, dataoff, sizeof(_sctph), &_sctph); + if (!sh) { + logmsg = "nf_ct_sctp: short packet "; + goto out_invalid; + } + if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && + skb->ip_summed == CHECKSUM_NONE) { + if (sh->checksum != sctp_compute_cksum(skb, dataoff)) { + logmsg = "nf_ct_sctp: bad CRC "; + goto out_invalid; + } + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + return NF_ACCEPT; +out_invalid: + if (LOG_INVALID(net, IPPROTO_SCTP)) + nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, "%s", logmsg); + return -NF_ACCEPT; +} + #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> @@ -752,6 +782,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { .packet = sctp_packet, .get_timeouts = sctp_get_timeouts, .new = sctp_new, + .error = sctp_error, .me = THIS_MODULE, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .to_nlattr = sctp_to_nlattr, @@ -786,6 +817,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = { .packet = sctp_packet, .get_timeouts = sctp_get_timeouts, .new = sctp_new, + .error = sctp_error, .me = THIS_MODULE, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .to_nlattr = sctp_to_nlattr, diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 69f687740c76..b122e9dacfed 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -750,7 +750,6 @@ static const u8 tcp_valid_flags[(TCPHDR_FIN|TCPHDR_SYN|TCPHDR_RST|TCPHDR_ACK| static int tcp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum) { diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 20f35ed68030..f6ebce6178ca 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -108,8 +108,60 @@ static bool udp_new(struct nf_conn *ct, const struct sk_buff *skb, return true; } +#ifdef CONFIG_NF_CT_PROTO_UDPLITE +static int udplite_error(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, + unsigned int dataoff, + u8 pf, unsigned int hooknum) +{ + unsigned int udplen = skb->len - dataoff; + const struct udphdr *hdr; + struct udphdr _hdr; + unsigned int cscov; + + /* Header is too small? */ + hdr = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); + if (!hdr) { + if (LOG_INVALID(net, IPPROTO_UDPLITE)) + nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, + "nf_ct_udplite: short packet "); + return -NF_ACCEPT; + } + + cscov = ntohs(hdr->len); + if (cscov == 0) { + cscov = udplen; + } else if (cscov < sizeof(*hdr) || cscov > udplen) { + if (LOG_INVALID(net, IPPROTO_UDPLITE)) + nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, + "nf_ct_udplite: invalid checksum coverage "); + return -NF_ACCEPT; + } + + /* UDPLITE mandates checksums */ + if (!hdr->check) { + if (LOG_INVALID(net, IPPROTO_UDPLITE)) + nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, + "nf_ct_udplite: checksum missing "); + return -NF_ACCEPT; + } + + /* Checksum invalid? Ignore. */ + if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && + nf_checksum_partial(skb, hooknum, dataoff, cscov, IPPROTO_UDP, + pf)) { + if (LOG_INVALID(net, IPPROTO_UDPLITE)) + nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, + "nf_ct_udplite: bad UDPLite checksum "); + return -NF_ACCEPT; + } + + return NF_ACCEPT; +} +#endif + static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, - unsigned int dataoff, enum ip_conntrack_info *ctinfo, + unsigned int dataoff, u_int8_t pf, unsigned int hooknum) { @@ -290,6 +342,41 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly = }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udp4); +#ifdef CONFIG_NF_CT_PROTO_UDPLITE +struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly = +{ + .l3proto = PF_INET, + .l4proto = IPPROTO_UDPLITE, + .name = "udplite", + .allow_clash = true, + .pkt_to_tuple = udp_pkt_to_tuple, + .invert_tuple = udp_invert_tuple, + .print_tuple = udp_print_tuple, + .packet = udp_packet, + .get_timeouts = udp_get_timeouts, + .new = udp_new, + .error = udplite_error, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, + .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, + .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 */ + .init_net = udp_init_net, + .get_net_proto = udp_get_net_proto, +}; +EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite4); +#endif + struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly = { .l3proto = PF_INET6, @@ -322,3 +409,38 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly = .get_net_proto = udp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udp6); + +#ifdef CONFIG_NF_CT_PROTO_UDPLITE +struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly = +{ + .l3proto = PF_INET6, + .l4proto = IPPROTO_UDPLITE, + .name = "udplite", + .allow_clash = true, + .pkt_to_tuple = udp_pkt_to_tuple, + .invert_tuple = udp_invert_tuple, + .print_tuple = udp_print_tuple, + .packet = udp_packet, + .get_timeouts = udp_get_timeouts, + .new = udp_new, + .error = udplite_error, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, + .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, + .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 */ + .init_net = udp_init_net, + .get_net_proto = udp_get_net_proto, +}; +EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite6); +#endif diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c deleted file mode 100644 index c35f7bf05d8c..000000000000 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ /dev/null @@ -1,324 +0,0 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * (C) 2007 Patrick McHardy <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/types.h> -#include <linux/timer.h> -#include <linux/udp.h> -#include <linux/seq_file.h> -#include <linux/skbuff.h> -#include <linux/ipv6.h> -#include <net/ip6_checksum.h> -#include <net/checksum.h> - -#include <linux/netfilter.h> -#include <linux/netfilter_ipv4.h> -#include <linux/netfilter_ipv6.h> -#include <net/netfilter/nf_conntrack_l4proto.h> -#include <net/netfilter/nf_conntrack_ecache.h> -#include <net/netfilter/nf_log.h> - -static unsigned int udplite_timeouts[UDPLITE_CT_MAX] = { - [UDPLITE_CT_UNREPLIED] = 30*HZ, - [UDPLITE_CT_REPLIED] = 180*HZ, -}; - -static inline struct nf_udplite_net *udplite_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.udplite; -} - -static bool udplite_pkt_to_tuple(const struct sk_buff *skb, - unsigned int dataoff, - struct net *net, - struct nf_conntrack_tuple *tuple) -{ - const struct udphdr *hp; - struct udphdr _hdr; - - /* Actually only need first 4 bytes to get ports. */ - hp = skb_header_pointer(skb, dataoff, 4, &_hdr); - if (hp == NULL) - return false; - - tuple->src.u.udp.port = hp->source; - tuple->dst.u.udp.port = hp->dest; - return true; -} - -static bool udplite_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) -{ - tuple->src.u.udp.port = orig->dst.u.udp.port; - tuple->dst.u.udp.port = orig->src.u.udp.port; - return true; -} - -/* Print out the per-protocol part of the tuple. */ -static void udplite_print_tuple(struct seq_file *s, - const struct nf_conntrack_tuple *tuple) -{ - seq_printf(s, "sport=%hu dport=%hu ", - ntohs(tuple->src.u.udp.port), - ntohs(tuple->dst.u.udp.port)); -} - -static unsigned int *udplite_get_timeouts(struct net *net) -{ - return udplite_pernet(net)->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 *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, - 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, - 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 *timeouts) -{ - return true; -} - -static int udplite_error(struct net *net, struct nf_conn *tmpl, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info *ctinfo, - u_int8_t pf, - unsigned int hooknum) -{ - unsigned int udplen = skb->len - dataoff; - const struct udphdr *hdr; - struct udphdr _hdr; - unsigned int cscov; - - /* Header is too small? */ - hdr = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); - if (hdr == NULL) { - if (LOG_INVALID(net, IPPROTO_UDPLITE)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_udplite: short packet "); - return -NF_ACCEPT; - } - - cscov = ntohs(hdr->len); - if (cscov == 0) - cscov = udplen; - else if (cscov < sizeof(*hdr) || cscov > udplen) { - if (LOG_INVALID(net, IPPROTO_UDPLITE)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_udplite: invalid checksum coverage "); - return -NF_ACCEPT; - } - - /* UDPLITE mandates checksums */ - if (!hdr->check) { - if (LOG_INVALID(net, IPPROTO_UDPLITE)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_udplite: checksum missing "); - return -NF_ACCEPT; - } - - /* Checksum invalid? Ignore. */ - if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && - nf_checksum_partial(skb, hooknum, dataoff, cscov, IPPROTO_UDP, - pf)) { - if (LOG_INVALID(net, IPPROTO_UDPLITE)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_udplite: bad UDPLite checksum "); - return -NF_ACCEPT; - } - - 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[], - struct net *net, void *data) -{ - unsigned int *timeouts = data; - struct nf_udplite_net *un = udplite_pernet(net); - - /* set default timeouts for UDPlite. */ - timeouts[UDPLITE_CT_UNREPLIED] = un->timeouts[UDPLITE_CT_UNREPLIED]; - timeouts[UDPLITE_CT_REPLIED] = un->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; - - if (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))) - goto nla_put_failure; - 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 struct ctl_table udplite_sysctl_table[] = { - { - .procname = "nf_conntrack_udplite_timeout", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_udplite_timeout_stream", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { } -}; -#endif /* CONFIG_SYSCTL */ - -static int udplite_kmemdup_sysctl_table(struct nf_proto_net *pn, - struct nf_udplite_net *un) -{ -#ifdef CONFIG_SYSCTL - if (pn->ctl_table) - return 0; - - pn->ctl_table = kmemdup(udplite_sysctl_table, - sizeof(udplite_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_table) - return -ENOMEM; - - pn->ctl_table[0].data = &un->timeouts[UDPLITE_CT_UNREPLIED]; - pn->ctl_table[1].data = &un->timeouts[UDPLITE_CT_REPLIED]; -#endif - return 0; -} - -static int udplite_init_net(struct net *net, u_int16_t proto) -{ - struct nf_udplite_net *un = udplite_pernet(net); - struct nf_proto_net *pn = &un->pn; - - if (!pn->users) { - int i; - - for (i = 0 ; i < UDPLITE_CT_MAX; i++) - un->timeouts[i] = udplite_timeouts[i]; - } - - return udplite_kmemdup_sysctl_table(pn, un); -} - -struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly = -{ - .l3proto = PF_INET, - .l4proto = IPPROTO_UDPLITE, - .name = "udplite", - .allow_clash = true, - .pkt_to_tuple = udplite_pkt_to_tuple, - .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) - .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, - .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, -#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 */ - .init_net = udplite_init_net, -}; -EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite4); - -struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly = -{ - .l3proto = PF_INET6, - .l4proto = IPPROTO_UDPLITE, - .name = "udplite", - .allow_clash = true, - .pkt_to_tuple = udplite_pkt_to_tuple, - .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) - .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, - .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, -#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 */ - .init_net = udplite_init_net, -}; -EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite6); diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index c3fc14e021ec..24174c520239 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -809,13 +809,11 @@ static int refresh_signalling_expectation(struct nf_conn *ct, exp->tuple.dst.protonum != proto || exp->tuple.dst.u.udp.port != port) continue; - if (!del_timer(&exp->timeout)) - continue; - exp->flags &= ~NF_CT_EXPECT_INACTIVE; - exp->timeout.expires = jiffies + expires * HZ; - add_timer(&exp->timeout); - found = 1; - break; + if (mod_timer_pending(&exp->timeout, jiffies + expires * HZ)) { + exp->flags &= ~NF_CT_EXPECT_INACTIVE; + found = 1; + break; + } } spin_unlock_bh(&nf_conntrack_expect_lock); return found; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index d009ae663453..2256147dcaad 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -642,6 +642,9 @@ static int __init nf_conntrack_standalone_init(void) if (ret < 0) goto out_start; + BUILD_BUG_ON(SKB_NFCT_PTRMASK != NFCT_PTRMASK); + BUILD_BUG_ON(NFCT_INFOMASK <= IP_CT_NUMBER); + #ifdef CONFIG_SYSCTL nf_ct_netfilter_header = register_net_sysctl(&init_net, "net", nf_ct_netfilter_table); diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index ffb9e8ada899..8d85a0598b60 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -15,6 +15,9 @@ #define NFLOGGER_NAME_LEN 64 +int sysctl_nf_log_all_netns __read_mostly; +EXPORT_SYMBOL(sysctl_nf_log_all_netns); + static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly; static DEFINE_MUTEX(nf_log_mutex); @@ -413,6 +416,18 @@ static const struct file_operations nflog_file_ops = { #ifdef CONFIG_SYSCTL static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1]; +static struct ctl_table_header *nf_log_sysctl_fhdr; + +static struct ctl_table nf_log_sysctl_ftable[] = { + { + .procname = "nf_log_all_netns", + .data = &sysctl_nf_log_all_netns, + .maxlen = sizeof(sysctl_nf_log_all_netns), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; static int nf_log_proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -482,6 +497,10 @@ static int netfilter_log_sysctl_init(struct net *net) nf_log_sysctl_table[i].extra1 = (void *)(unsigned long) i; } + nf_log_sysctl_fhdr = register_net_sysctl(net, "net/netfilter", + nf_log_sysctl_ftable); + if (!nf_log_sysctl_fhdr) + goto err_freg; } for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) @@ -498,6 +517,9 @@ static int netfilter_log_sysctl_init(struct net *net) err_reg: if (!net_eq(net, &init_net)) kfree(table); + else + unregister_net_sysctl_table(nf_log_sysctl_fhdr); +err_freg: err_alloc: return -ENOMEM; } @@ -510,6 +532,8 @@ static void netfilter_log_sysctl_exit(struct net *net) unregister_net_sysctl_table(net->nf.nf_log_dir_header); if (!net_eq(net, &init_net)) kfree(table); + else + unregister_net_sysctl_table(nf_log_sysctl_fhdr); } #else static int netfilter_log_sysctl_init(struct net *net) diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index 2840abb5bb99..211661cb2c90 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -60,7 +60,7 @@ static void mangle_contents(struct sk_buff *skb, __skb_trim(skb, skb->len + rep_len - match_len); } - if (nf_ct_l3num((struct nf_conn *)skb->nfct) == NFPROTO_IPV4) { + if (nf_ct_l3num((struct nf_conn *)skb_nfct(skb)) == NFPROTO_IPV4) { /* fix IP hdr checksum information */ ip_hdr(skb)->tot_len = htons(skb->len); ip_send_check(ip_hdr(skb)); diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c index b1e627227b6e..edd4a77dc09a 100644 --- a/net/netfilter/nf_nat_proto_udp.c +++ b/net/netfilter/nf_nat_proto_udp.c @@ -30,20 +30,15 @@ udp_unique_tuple(const struct nf_nat_l3proto *l3proto, &udp_port_rover); } -static bool -udp_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, - unsigned int iphdroff, unsigned int hdroff, - const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype) +static void +__udp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, struct udphdr *hdr, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype, bool do_csum) { - struct udphdr *hdr; __be16 *portptr, newport; - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) - return false; - hdr = (struct udphdr *)(skb->data + hdroff); - if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ newport = tuple->src.u.udp.port; @@ -53,7 +48,7 @@ udp_manip_pkt(struct sk_buff *skb, newport = tuple->dst.u.udp.port; portptr = &hdr->dest; } - if (hdr->check || skb->ip_summed == CHECKSUM_PARTIAL) { + if (do_csum) { l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, @@ -62,9 +57,68 @@ udp_manip_pkt(struct sk_buff *skb, hdr->check = CSUM_MANGLED_0; } *portptr = newport; +} + +static bool udp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct udphdr *hdr; + bool do_csum; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + + hdr = (struct udphdr *)(skb->data + hdroff); + do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL; + + __udp_manip_pkt(skb, l3proto, iphdroff, hdr, tuple, maniptype, do_csum); + return true; +} + +#ifdef CONFIG_NF_NAT_PROTO_UDPLITE +static u16 udplite_port_rover; + +static bool udplite_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct udphdr *hdr; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + + hdr = (struct udphdr *)(skb->data + hdroff); + __udp_manip_pkt(skb, l3proto, iphdroff, hdr, tuple, maniptype, true); return true; } +static void +udplite_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &udplite_port_rover); +} + +const struct nf_nat_l4proto nf_nat_l4proto_udplite = { + .l4proto = IPPROTO_UDPLITE, + .manip_pkt = udplite_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = udplite_unique_tuple, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; +#endif /* CONFIG_NF_NAT_PROTO_UDPLITE */ + const struct nf_nat_l4proto nf_nat_l4proto_udp = { .l4proto = IPPROTO_UDP, .manip_pkt = udp_manip_pkt, diff --git a/net/netfilter/nf_nat_proto_udplite.c b/net/netfilter/nf_nat_proto_udplite.c deleted file mode 100644 index 366bfbfd82a1..000000000000 --- a/net/netfilter/nf_nat_proto_udplite.c +++ /dev/null @@ -1,73 +0,0 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> - * (C) 2008 Patrick McHardy <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/types.h> -#include <linux/udp.h> - -#include <linux/netfilter.h> -#include <net/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_l3proto.h> -#include <net/netfilter/nf_nat_l4proto.h> - -static u16 udplite_port_rover; - -static void -udplite_unique_tuple(const struct nf_nat_l3proto *l3proto, - struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct) -{ - nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, - &udplite_port_rover); -} - -static bool -udplite_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, - unsigned int iphdroff, unsigned int hdroff, - const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype) -{ - struct udphdr *hdr; - __be16 *portptr, newport; - - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) - return false; - - hdr = (struct udphdr *)(skb->data + hdroff); - - if (maniptype == NF_NAT_MANIP_SRC) { - /* Get rid of source port */ - newport = tuple->src.u.udp.port; - portptr = &hdr->source; - } else { - /* Get rid of dst port */ - newport = tuple->dst.u.udp.port; - portptr = &hdr->dest; - } - - l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); - inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, false); - if (!hdr->check) - hdr->check = CSUM_MANGLED_0; - - *portptr = newport; - return true; -} - -const struct nf_nat_l4proto nf_nat_l4proto_udplite = { - .l4proto = IPPROTO_UDPLITE, - .manip_pkt = udplite_manip_pkt, - .in_range = nf_nat_l4proto_in_range, - .unique_tuple = udplite_unique_tuple, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, -#endif -}; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1b913760f205..ff7304ae58ac 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -240,6 +240,10 @@ static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type, if (trans == NULL) return NULL; + if (msg_type == NFT_MSG_NEWRULE && ctx->nla[NFTA_RULE_ID] != NULL) { + nft_trans_rule_id(trans) = + ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID])); + } nft_trans_rule(trans) = rule; list_add_tail(&trans->list, &ctx->net->nft.commit_list); @@ -576,6 +580,28 @@ err: return err; } +static void _nf_tables_table_disable(struct net *net, + const struct nft_af_info *afi, + struct nft_table *table, + u32 cnt) +{ + struct nft_chain *chain; + u32 i = 0; + + list_for_each_entry(chain, &table->chains, list) { + if (!nft_is_active_next(net, chain)) + continue; + if (!(chain->flags & NFT_BASE_CHAIN)) + continue; + + if (cnt && i++ == cnt) + break; + + nf_unregister_net_hooks(net, nft_base_chain(chain)->ops, + afi->nops); + } +} + static int nf_tables_table_enable(struct net *net, const struct nft_af_info *afi, struct nft_table *table) @@ -598,18 +624,8 @@ static int nf_tables_table_enable(struct net *net, } return 0; err: - list_for_each_entry(chain, &table->chains, list) { - if (!nft_is_active_next(net, chain)) - continue; - if (!(chain->flags & NFT_BASE_CHAIN)) - continue; - - if (i-- <= 0) - break; - - nf_unregister_net_hooks(net, nft_base_chain(chain)->ops, - afi->nops); - } + if (i) + _nf_tables_table_disable(net, afi, table, i); return err; } @@ -617,17 +633,7 @@ static void nf_tables_table_disable(struct net *net, const struct nft_af_info *afi, struct nft_table *table) { - struct nft_chain *chain; - - list_for_each_entry(chain, &table->chains, list) { - if (!nft_is_active_next(net, chain)) - continue; - if (!(chain->flags & NFT_BASE_CHAIN)) - continue; - - nf_unregister_net_hooks(net, nft_base_chain(chain)->ops, - afi->nops); - } + _nf_tables_table_disable(net, afi, table, 0); } static int nf_tables_updtable(struct nft_ctx *ctx) @@ -696,10 +702,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (IS_ERR(table)) { if (PTR_ERR(table) != -ENOENT) return PTR_ERR(table); - table = NULL; - } - - if (table != NULL) { + } else { if (nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (nlh->nlmsg_flags & NLM_F_REPLACE) @@ -2294,6 +2297,22 @@ err1: return err; } +static struct nft_rule *nft_rule_lookup_byid(const struct net *net, + const struct nlattr *nla) +{ + u32 id = ntohl(nla_get_be32(nla)); + struct nft_trans *trans; + + list_for_each_entry(trans, &net->nft.commit_list, list) { + struct nft_rule *rule = nft_trans_rule(trans); + + if (trans->msg_type == NFT_MSG_NEWRULE && + id == nft_trans_rule_id(trans)) + return rule; + } + return ERR_PTR(-ENOENT); +} + static int nf_tables_delrule(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -2332,6 +2351,12 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, return PTR_ERR(rule); err = nft_delrule(&ctx, rule); + } else if (nla[NFTA_RULE_ID]) { + rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]); + if (IS_ERR(rule)) + return PTR_ERR(rule); + + err = nft_delrule(&ctx, rule); } else { err = nft_delrule_by_chain(&ctx); } @@ -2399,12 +2424,14 @@ nft_select_set_ops(const struct nlattr * const nla[], features = 0; if (nla[NFTA_SET_FLAGS] != NULL) { features = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); - features &= NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_TIMEOUT; + features &= NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_TIMEOUT | + NFT_SET_OBJECT; } - bops = NULL; - best.size = ~0; - best.class = ~0; + bops = NULL; + best.size = ~0; + best.lookup = ~0; + best.space = ~0; list_for_each_entry(ops, &nf_tables_set_ops, list) { if ((ops->features & features) != features) @@ -2414,16 +2441,27 @@ nft_select_set_ops(const struct nlattr * const nla[], switch (policy) { case NFT_SET_POL_PERFORMANCE: - if (est.class < best.class) - break; - if (est.class == best.class && est.size < best.size) + if (est.lookup < best.lookup) break; + if (est.lookup == best.lookup) { + if (!desc->size) { + if (est.space < best.space) + break; + } else if (est.size < best.size) { + break; + } + } continue; case NFT_SET_POL_MEMORY: - if (est.size < best.size) - break; - if (est.size == best.size && est.class < best.class) + if (!desc->size) { + if (est.space < best.space) + break; + if (est.space == best.space && + est.lookup < best.lookup) + break; + } else if (est.size < best.size) { break; + } continue; default: break; @@ -2966,10 +3004,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (IS_ERR(set)) { if (PTR_ERR(set) != -ENOENT) return PTR_ERR(set); - set = NULL; - } - - if (set != NULL) { + } else { if (nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (nlh->nlmsg_flags & NLM_F_REPLACE) @@ -3125,6 +3160,7 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, iter.count = 0; iter.err = 0; iter.fn = nf_tables_bind_check_setelem; + iter.flush = false; set->ops->walk(ctx, set, &iter); if (iter.err < 0) @@ -3378,6 +3414,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) args.iter.count = 0; args.iter.err = 0; args.iter.fn = nf_tables_dump_setelem; + args.iter.flush = false; set->ops->walk(&ctx, set, &args.iter); nla_nest_end(skb, nest); @@ -3756,7 +3793,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, return 0; err6: - set->ops->remove(set, &elem); + set->ops->remove(ctx->net, set, &elem); err5: kfree(trans); err4: @@ -3902,7 +3939,7 @@ static int nft_flush_set(const struct nft_ctx *ctx, if (!trans) return -ENOMEM; - if (!set->ops->deactivate_one(ctx->net, set, elem->priv)) { + if (!set->ops->flush(ctx->net, set, elem->priv)) { err = -ENOENT; goto err1; } @@ -3940,15 +3977,14 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, return -EBUSY; if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) { - struct nft_set_dump_args args = { - .iter = { - .genmask = genmask, - .fn = nft_flush_set, - }, + struct nft_set_iter iter = { + .genmask = genmask, + .fn = nft_flush_set, + .flush = true, }; - set->ops->walk(&ctx, set, &args.iter); + set->ops->walk(&ctx, set, &iter); - return args.iter.err; + return iter.err; } nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { @@ -4163,10 +4199,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, if (err != -ENOENT) return err; - obj = NULL; - } - - if (obj != NULL) { + } else { if (nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; @@ -4811,7 +4844,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, NFT_MSG_DELSETELEM, 0); - te->set->ops->remove(te->set, &te->elem); + te->set->ops->remove(net, te->set, &te->elem); atomic_dec(&te->set->nelems); te->set->ndeact--; break; @@ -4932,7 +4965,7 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) case NFT_MSG_NEWSETELEM: te = (struct nft_trans_elem *)trans->data; - te->set->ops->remove(te->set, &te->elem); + te->set->ops->remove(net, te->set, &te->elem); atomic_dec(&te->set->nelems); break; case NFT_MSG_DELSETELEM: @@ -4966,6 +4999,11 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) return 0; } +static bool nf_tables_valid_genid(struct net *net, u32 genid) +{ + return net->nft.base_seq == genid; +} + static const struct nfnetlink_subsystem nf_tables_subsys = { .name = "nf_tables", .subsys_id = NFNL_SUBSYS_NFTABLES, @@ -4973,6 +5011,7 @@ static const struct nfnetlink_subsystem nf_tables_subsys = { .cb = nf_tables_cb, .commit = nf_tables_commit, .abort = nf_tables_abort, + .valid_genid = nf_tables_valid_genid, }; int nft_chain_validate_dependency(const struct nft_chain *chain, @@ -5098,6 +5137,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, iter.count = 0; iter.err = 0; iter.fn = nf_tables_loop_check_setelem; + iter.flush = false; set->ops->walk(ctx, set, &iter); if (iter.err < 0) diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index a09fa9fd8f3d..a2148d0bc50e 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -3,7 +3,7 @@ * * (C) 2001 by Jay Schulist <jschlst@samba.org>, * (C) 2002-2005 by Harald Welte <laforge@gnumonks.org> - * (C) 2005,2007 by Pablo Neira Ayuso <pablo@netfilter.org> + * (C) 2005-2017 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial netfilter messages via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) @@ -100,9 +100,9 @@ int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n) } EXPORT_SYMBOL_GPL(nfnetlink_subsys_unregister); -static inline const struct nfnetlink_subsystem *nfnetlink_get_subsys(u_int16_t type) +static inline const struct nfnetlink_subsystem *nfnetlink_get_subsys(u16 type) { - u_int8_t subsys_id = NFNL_SUBSYS_ID(type); + u8 subsys_id = NFNL_SUBSYS_ID(type); if (subsys_id >= NFNL_SUBSYS_COUNT) return NULL; @@ -111,9 +111,9 @@ static inline const struct nfnetlink_subsystem *nfnetlink_get_subsys(u_int16_t t } static inline const struct nfnl_callback * -nfnetlink_find_client(u_int16_t type, const struct nfnetlink_subsystem *ss) +nfnetlink_find_client(u16 type, const struct nfnetlink_subsystem *ss) { - u_int8_t cb_id = NFNL_MSG_TYPE(type); + u8 cb_id = NFNL_MSG_TYPE(type); if (cb_id >= ss->cb_count) return NULL; @@ -185,7 +185,7 @@ replay: { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); - u_int8_t cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); + u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); struct nlattr *cda[ss->cb[cb_id].attr_count + 1]; struct nlattr *attr = (void *)nlh + min_len; int attrlen = nlh->nlmsg_len - min_len; @@ -273,7 +273,7 @@ enum { }; static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, - u_int16_t subsys_id) + u16 subsys_id, u32 genid) { struct sk_buff *oskb = skb; struct net *net = sock_net(skb->sk); @@ -315,6 +315,12 @@ replay: return kfree_skb(skb); } + if (genid && ss->valid_genid && !ss->valid_genid(net, genid)) { + nfnl_unlock(subsys_id); + netlink_ack(oskb, nlh, -ERESTART); + return kfree_skb(skb); + } + while (skb->len >= nlmsg_total_size(0)) { int msglen, type; @@ -365,7 +371,7 @@ replay: { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); - u_int8_t cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); + u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); struct nlattr *cda[ss->cb[cb_id].attr_count + 1]; struct nlattr *attr = (void *)nlh + min_len; int attrlen = nlh->nlmsg_len - min_len; @@ -436,11 +442,51 @@ done: kfree_skb(skb); } +static const struct nla_policy nfnl_batch_policy[NFNL_BATCH_MAX + 1] = { + [NFNL_BATCH_GENID] = { .type = NLA_U32 }, +}; + +static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); + struct nlattr *attr = (void *)nlh + min_len; + struct nlattr *cda[NFNL_BATCH_MAX + 1]; + int attrlen = nlh->nlmsg_len - min_len; + struct nfgenmsg *nfgenmsg; + int msglen, err; + u32 gen_id = 0; + u16 res_id; + + msglen = NLMSG_ALIGN(nlh->nlmsg_len); + if (msglen > skb->len) + msglen = skb->len; + + if (nlh->nlmsg_len < NLMSG_HDRLEN || + skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) + return; + + err = nla_parse(cda, NFNL_BATCH_MAX, attr, attrlen, nfnl_batch_policy); + if (err < 0) { + netlink_ack(skb, nlh, err); + return; + } + if (cda[NFNL_BATCH_GENID]) + gen_id = ntohl(nla_get_be32(cda[NFNL_BATCH_GENID])); + + nfgenmsg = nlmsg_data(nlh); + skb_pull(skb, msglen); + /* Work around old nft using host byte order */ + if (nfgenmsg->res_id == NFNL_SUBSYS_NFTABLES) + res_id = NFNL_SUBSYS_NFTABLES; + else + res_id = ntohs(nfgenmsg->res_id); + + nfnetlink_rcv_batch(skb, nlh, res_id, gen_id); +} + static void nfnetlink_rcv(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); - u_int16_t res_id; - int msglen; if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) @@ -451,28 +497,10 @@ static void nfnetlink_rcv(struct sk_buff *skb) return; } - if (nlh->nlmsg_type == NFNL_MSG_BATCH_BEGIN) { - struct nfgenmsg *nfgenmsg; - - msglen = NLMSG_ALIGN(nlh->nlmsg_len); - if (msglen > skb->len) - msglen = skb->len; - - if (nlh->nlmsg_len < NLMSG_HDRLEN || - skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) - return; - - nfgenmsg = nlmsg_data(nlh); - skb_pull(skb, msglen); - /* Work around old nft using host byte order */ - if (nfgenmsg->res_id == NFNL_SUBSYS_NFTABLES) - res_id = NFNL_SUBSYS_NFTABLES; - else - res_id = ntohs(nfgenmsg->res_id); - nfnetlink_rcv_batch(skb, nlh, res_id); - } else { + if (nlh->nlmsg_type == NFNL_MSG_BATCH_BEGIN) + nfnetlink_rcv_skb_batch(skb, nlh); + else netlink_rcv_skb(skb, &nfnetlink_rcv_msg); - } } #ifdef CONFIG_MODULES diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index e6baeaebe653..c6b8022c0e47 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -32,6 +32,11 @@ struct nft_ct { }; }; +#ifdef CONFIG_NF_CONNTRACK_ZONES +static DEFINE_PER_CPU(struct nf_conn *, nft_ct_pcpu_template); +static unsigned int nft_ct_pcpu_template_refcnt __read_mostly; +#endif + static u64 nft_ct_get_eval_counter(const struct nf_conn_counter *c, enum nft_ct_keys k, enum ip_conntrack_dir d) @@ -129,12 +134,40 @@ static void nft_ct_get_eval(const struct nft_expr *expr, memcpy(dest, &count, sizeof(count)); return; } + case NFT_CT_AVGPKT: { + const struct nf_conn_acct *acct = nf_conn_acct_find(ct); + u64 avgcnt = 0, bcnt = 0, pcnt = 0; + + if (acct) { + pcnt = nft_ct_get_eval_counter(acct->counter, + NFT_CT_PKTS, priv->dir); + bcnt = nft_ct_get_eval_counter(acct->counter, + NFT_CT_BYTES, priv->dir); + if (pcnt != 0) + avgcnt = div64_u64(bcnt, pcnt); + } + + memcpy(dest, &avgcnt, sizeof(avgcnt)); + return; + } case NFT_CT_L3PROTOCOL: *dest = nf_ct_l3num(ct); return; case NFT_CT_PROTOCOL: *dest = nf_ct_protonum(ct); return; +#ifdef CONFIG_NF_CONNTRACK_ZONES + case NFT_CT_ZONE: { + const struct nf_conntrack_zone *zone = nf_ct_zone(ct); + + if (priv->dir < IP_CT_DIR_MAX) + *dest = nf_ct_zone_id(zone, priv->dir); + else + *dest = zone->id; + + return; + } +#endif default: break; } @@ -163,6 +196,53 @@ err: regs->verdict.code = NFT_BREAK; } +#ifdef CONFIG_NF_CONNTRACK_ZONES +static void nft_ct_set_zone_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nf_conntrack_zone zone = { .dir = NF_CT_DEFAULT_ZONE_DIR }; + const struct nft_ct *priv = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; + enum ip_conntrack_info ctinfo; + u16 value = regs->data[priv->sreg]; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (ct) /* already tracked */ + return; + + zone.id = value; + + switch (priv->dir) { + case IP_CT_DIR_ORIGINAL: + zone.dir = NF_CT_ZONE_DIR_ORIG; + break; + case IP_CT_DIR_REPLY: + zone.dir = NF_CT_ZONE_DIR_REPL; + break; + default: + break; + } + + ct = this_cpu_read(nft_ct_pcpu_template); + + if (likely(atomic_read(&ct->ct_general.use) == 1)) { + nf_ct_zone_add(ct, &zone); + } else { + /* previous skb got queued to userspace */ + ct = nf_ct_tmpl_alloc(nft_net(pkt), &zone, GFP_ATOMIC); + if (!ct) { + regs->verdict.code = NF_DROP; + return; + } + } + + atomic_inc(&ct->ct_general.use); + nf_ct_set(skb, ct, IP_CT_NEW); +} +#endif + static void nft_ct_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -241,6 +321,45 @@ static void nft_ct_netns_put(struct net *net, uint8_t family) nf_ct_netns_put(net, family); } +#ifdef CONFIG_NF_CONNTRACK_ZONES +static void nft_ct_tmpl_put_pcpu(void) +{ + struct nf_conn *ct; + int cpu; + + for_each_possible_cpu(cpu) { + ct = per_cpu(nft_ct_pcpu_template, cpu); + if (!ct) + break; + nf_ct_put(ct); + per_cpu(nft_ct_pcpu_template, cpu) = NULL; + } +} + +static bool nft_ct_tmpl_alloc_pcpu(void) +{ + struct nf_conntrack_zone zone = { .id = 0 }; + struct nf_conn *tmp; + int cpu; + + if (nft_ct_pcpu_template_refcnt) + return true; + + for_each_possible_cpu(cpu) { + tmp = nf_ct_tmpl_alloc(&init_net, &zone, GFP_KERNEL); + if (!tmp) { + nft_ct_tmpl_put_pcpu(); + return false; + } + + atomic_set(&tmp->ct_general.use, 1); + per_cpu(nft_ct_pcpu_template, cpu) = tmp; + } + + return true; +} +#endif + static int nft_ct_get_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -250,6 +369,7 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, int err; priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); + priv->dir = IP_CT_DIR_MAX; switch (priv->key) { case NFT_CT_DIRECTION: if (tb[NFTA_CT_DIRECTION] != NULL) @@ -316,11 +436,14 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, break; case NFT_CT_BYTES: case NFT_CT_PKTS: - /* no direction? return sum of original + reply */ - if (tb[NFTA_CT_DIRECTION] == NULL) - priv->dir = IP_CT_DIR_MAX; + case NFT_CT_AVGPKT: len = sizeof(u64); break; +#ifdef CONFIG_NF_CONNTRACK_ZONES + case NFT_CT_ZONE: + len = sizeof(u16); + break; +#endif default: return -EOPNOTSUPP; } @@ -346,21 +469,41 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, if (err < 0) return err; - if (priv->key == NFT_CT_BYTES || priv->key == NFT_CT_PKTS) + if (priv->key == NFT_CT_BYTES || + priv->key == NFT_CT_PKTS || + priv->key == NFT_CT_AVGPKT) nf_ct_set_acct(ctx->net, true); return 0; } +static void __nft_ct_set_destroy(const struct nft_ctx *ctx, struct nft_ct *priv) +{ + switch (priv->key) { +#ifdef CONFIG_NF_CONNTRACK_LABELS + case NFT_CT_LABELS: + nf_connlabels_put(ctx->net); + break; +#endif +#ifdef CONFIG_NF_CONNTRACK_ZONES + case NFT_CT_ZONE: + if (--nft_ct_pcpu_template_refcnt == 0) + nft_ct_tmpl_put_pcpu(); +#endif + default: + break; + } +} + static int nft_ct_set_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_ct *priv = nft_expr_priv(expr); - bool label_got = false; unsigned int len; int err; + priv->dir = IP_CT_DIR_MAX; priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); switch (priv->key) { #ifdef CONFIG_NF_CONNTRACK_MARK @@ -378,13 +521,30 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, err = nf_connlabels_get(ctx->net, (len * BITS_PER_BYTE) - 1); if (err) return err; - label_got = true; + break; +#endif +#ifdef CONFIG_NF_CONNTRACK_ZONES + case NFT_CT_ZONE: + if (!nft_ct_tmpl_alloc_pcpu()) + return -ENOMEM; + nft_ct_pcpu_template_refcnt++; break; #endif default: return -EOPNOTSUPP; } + if (tb[NFTA_CT_DIRECTION]) { + priv->dir = nla_get_u8(tb[NFTA_CT_DIRECTION]); + switch (priv->dir) { + case IP_CT_DIR_ORIGINAL: + case IP_CT_DIR_REPLY: + break; + default: + return -EINVAL; + } + } + priv->sreg = nft_parse_register(tb[NFTA_CT_SREG]); err = nft_validate_register_load(priv->sreg, len); if (err < 0) @@ -397,8 +557,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, return 0; err1: - if (label_got) - nf_connlabels_put(ctx->net); + __nft_ct_set_destroy(ctx, priv); return err; } @@ -413,16 +572,7 @@ static void nft_ct_set_destroy(const struct nft_ctx *ctx, { struct nft_ct *priv = nft_expr_priv(expr); - switch (priv->key) { -#ifdef CONFIG_NF_CONNTRACK_LABELS - case NFT_CT_LABELS: - nf_connlabels_put(ctx->net); - break; -#endif - default: - break; - } - + __nft_ct_set_destroy(ctx, priv); nft_ct_netns_put(ctx->net, ctx->afi->family); } @@ -445,6 +595,8 @@ static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) break; case NFT_CT_BYTES: case NFT_CT_PKTS: + case NFT_CT_AVGPKT: + case NFT_CT_ZONE: if (priv->dir < IP_CT_DIR_MAX && nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir)) goto nla_put_failure; @@ -467,6 +619,17 @@ static int nft_ct_set_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key))) goto nla_put_failure; + + switch (priv->key) { + case NFT_CT_ZONE: + if (priv->dir < IP_CT_DIR_MAX && + nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir)) + goto nla_put_failure; + break; + default: + break; + } + return 0; nla_put_failure: @@ -492,6 +655,17 @@ static const struct nft_expr_ops nft_ct_set_ops = { .dump = nft_ct_set_dump, }; +#ifdef CONFIG_NF_CONNTRACK_ZONES +static const struct nft_expr_ops nft_ct_set_zone_ops = { + .type = &nft_ct_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), + .eval = nft_ct_set_zone_eval, + .init = nft_ct_set_init, + .destroy = nft_ct_set_destroy, + .dump = nft_ct_set_dump, +}; +#endif + static const struct nft_expr_ops * nft_ct_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -505,8 +679,13 @@ nft_ct_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_CT_DREG]) return &nft_ct_get_ops; - if (tb[NFTA_CT_SREG]) + if (tb[NFTA_CT_SREG]) { +#ifdef CONFIG_NF_CONNTRACK_ZONES + if (nla_get_be32(tb[NFTA_CT_KEY]) == htonl(NFT_CT_ZONE)) + return &nft_ct_set_zone_ops; +#endif return &nft_ct_set_ops; + } return ERR_PTR(-EINVAL); } @@ -534,8 +713,7 @@ static void nft_notrack_eval(const struct nft_expr *expr, ct = nf_ct_untracked_get(); atomic_inc(&ct->ct_general.use); - skb->nfct = &ct->ct_general; - skb->nfctinfo = IP_CT_NEW; + nf_ct_set(skb, ct, IP_CT_NEW); } static struct nft_expr_type nft_notrack_type; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 47beb3abcc9d..c308920b194c 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -15,19 +15,29 @@ #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> -// FIXME: -#include <net/ipv6.h> +#include <net/tcp.h> struct nft_exthdr { u8 type; u8 offset; u8 len; + u8 op; enum nft_registers dreg:8; + u8 flags; }; -static void nft_exthdr_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static unsigned int optlen(const u8 *opt, unsigned int offset) +{ + /* Beware zero-length options: make finite progress */ + if (opt[offset] <= TCPOPT_NOP || opt[offset + 1] == 0) + return 1; + else + return opt[offset + 1]; +} + +static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { struct nft_exthdr *priv = nft_expr_priv(expr); u32 *dest = ®s->data[priv->dreg]; @@ -35,8 +45,12 @@ static void nft_exthdr_eval(const struct nft_expr *expr, int err; err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL); - if (err < 0) + if (priv->flags & NFT_EXTHDR_F_PRESENT) { + *dest = (err >= 0); + return; + } else if (err < 0) { goto err; + } offset += priv->offset; dest[priv->len / NFT_REG32_SIZE] = 0; @@ -47,11 +61,59 @@ err: regs->verdict.code = NFT_BREAK; } +static void nft_exthdr_tcp_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + u8 buff[sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE]; + struct nft_exthdr *priv = nft_expr_priv(expr); + unsigned int i, optl, tcphdr_len, offset; + u32 *dest = ®s->data[priv->dreg]; + struct tcphdr *tcph; + u8 *opt; + + if (!pkt->tprot_set || pkt->tprot != IPPROTO_TCP) + goto err; + + tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, sizeof(*tcph), buff); + if (!tcph) + goto err; + + tcphdr_len = __tcp_hdrlen(tcph); + if (tcphdr_len < sizeof(*tcph)) + goto err; + + tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, tcphdr_len, buff); + if (!tcph) + goto err; + + opt = (u8 *)tcph; + for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) { + optl = optlen(opt, i); + + if (priv->type != opt[i]) + continue; + + if (i + optl > tcphdr_len || priv->len + priv->offset > optl) + goto err; + + offset = i + priv->offset; + dest[priv->len / NFT_REG32_SIZE] = 0; + memcpy(dest, opt + offset, priv->len); + + return; + } + +err: + regs->verdict.code = NFT_BREAK; +} + static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { [NFTA_EXTHDR_DREG] = { .type = NLA_U32 }, [NFTA_EXTHDR_TYPE] = { .type = NLA_U8 }, [NFTA_EXTHDR_OFFSET] = { .type = NLA_U32 }, [NFTA_EXTHDR_LEN] = { .type = NLA_U32 }, + [NFTA_EXTHDR_FLAGS] = { .type = NLA_U32 }, }; static int nft_exthdr_init(const struct nft_ctx *ctx, @@ -59,13 +121,13 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_exthdr *priv = nft_expr_priv(expr); - u32 offset, len; + u32 offset, len, flags = 0, op = NFT_EXTHDR_OP_IPV6; int err; - if (tb[NFTA_EXTHDR_DREG] == NULL || - tb[NFTA_EXTHDR_TYPE] == NULL || - tb[NFTA_EXTHDR_OFFSET] == NULL || - tb[NFTA_EXTHDR_LEN] == NULL) + if (!tb[NFTA_EXTHDR_DREG] || + !tb[NFTA_EXTHDR_TYPE] || + !tb[NFTA_EXTHDR_OFFSET] || + !tb[NFTA_EXTHDR_LEN]) return -EINVAL; err = nft_parse_u32_check(tb[NFTA_EXTHDR_OFFSET], U8_MAX, &offset); @@ -76,10 +138,27 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, if (err < 0) return err; + if (tb[NFTA_EXTHDR_FLAGS]) { + err = nft_parse_u32_check(tb[NFTA_EXTHDR_FLAGS], U8_MAX, &flags); + if (err < 0) + return err; + + if (flags & ~NFT_EXTHDR_F_PRESENT) + return -EINVAL; + } + + if (tb[NFTA_EXTHDR_OP]) { + err = nft_parse_u32_check(tb[NFTA_EXTHDR_OP], U8_MAX, &op); + if (err < 0) + return err; + } + priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); priv->offset = offset; priv->len = len; priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]); + priv->flags = flags; + priv->op = op; return nft_validate_register_store(ctx, priv->dreg, NULL, NFT_DATA_VALUE, priv->len); @@ -97,6 +176,10 @@ static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; if (nla_put_be32(skb, NFTA_EXTHDR_LEN, htonl(priv->len))) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_EXTHDR_FLAGS, htonl(priv->flags))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_EXTHDR_OP, htonl(priv->op))) + goto nla_put_failure; return 0; nla_put_failure: @@ -104,17 +187,45 @@ nla_put_failure: } static struct nft_expr_type nft_exthdr_type; -static const struct nft_expr_ops nft_exthdr_ops = { +static const struct nft_expr_ops nft_exthdr_ipv6_ops = { .type = &nft_exthdr_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), - .eval = nft_exthdr_eval, + .eval = nft_exthdr_ipv6_eval, .init = nft_exthdr_init, .dump = nft_exthdr_dump, }; +static const struct nft_expr_ops nft_exthdr_tcp_ops = { + .type = &nft_exthdr_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), + .eval = nft_exthdr_tcp_eval, + .init = nft_exthdr_init, + .dump = nft_exthdr_dump, +}; + +static const struct nft_expr_ops * +nft_exthdr_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + u32 op; + + if (!tb[NFTA_EXTHDR_OP]) + return &nft_exthdr_ipv6_ops; + + op = ntohl(nla_get_u32(tb[NFTA_EXTHDR_OP])); + switch (op) { + case NFT_EXTHDR_OP_TCPOPT: + return &nft_exthdr_tcp_ops; + case NFT_EXTHDR_OP_IPV6: + return &nft_exthdr_ipv6_ops; + } + + return ERR_PTR(-EOPNOTSUPP); +} + static struct nft_expr_type nft_exthdr_type __read_mostly = { .name = "exthdr", - .ops = &nft_exthdr_ops, + .select_ops = &nft_exthdr_select_ops, .policy = nft_exthdr_policy, .maxattr = NFTA_EXTHDR_MAX, .owner = THIS_MODULE, diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 66c7f4b4c49b..e1f5ca9b423b 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -154,13 +154,36 @@ void nft_meta_get_eval(const struct nft_expr *expr, *dest = PACKET_BROADCAST; break; case NFPROTO_IPV6: - if (ipv6_hdr(skb)->daddr.s6_addr[0] == 0xFF) + *dest = PACKET_MULTICAST; + break; + case NFPROTO_NETDEV: + switch (skb->protocol) { + case htons(ETH_P_IP): { + int noff = skb_network_offset(skb); + struct iphdr *iph, _iph; + + iph = skb_header_pointer(skb, noff, + sizeof(_iph), &_iph); + if (!iph) + goto err; + + if (ipv4_is_multicast(iph->daddr)) + *dest = PACKET_MULTICAST; + else + *dest = PACKET_BROADCAST; + + break; + } + case htons(ETH_P_IPV6): *dest = PACKET_MULTICAST; - else - *dest = PACKET_BROADCAST; + break; + default: + WARN_ON_ONCE(1); + goto err; + } break; default: - WARN_ON(1); + WARN_ON_ONCE(1); goto err; } break; diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c new file mode 100644 index 000000000000..97f9649bcc7e --- /dev/null +++ b/net/netfilter/nft_set_bitmap.c @@ -0,0 +1,314 @@ +/* + * Copyright (c) 2017 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/list.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> + +/* This bitmap uses two bits to represent one element. These two bits determine + * the element state in the current and the future generation. + * + * An element can be in three states. The generation cursor is represented using + * the ^ character, note that this cursor shifts on every succesful transaction. + * If no transaction is going on, we observe all elements are in the following + * state: + * + * 11 = this element is active in the current generation. In case of no updates, + * ^ it stays active in the next generation. + * 00 = this element is inactive in the current generation. In case of no + * ^ updates, it stays inactive in the next generation. + * + * On transaction handling, we observe these two temporary states: + * + * 01 = this element is inactive in the current generation and it becomes active + * ^ in the next one. This happens when the element is inserted but commit + * path has not yet been executed yet, so activation is still pending. On + * transaction abortion, the element is removed. + * 10 = this element is active in the current generation and it becomes inactive + * ^ in the next one. This happens when the element is deactivated but commit + * path has not yet been executed yet, so removal is still pending. On + * transation abortion, the next generation bit is reset to go back to + * restore its previous state. + */ +struct nft_bitmap { + u16 bitmap_size; + u8 bitmap[]; +}; + +static inline void nft_bitmap_location(u32 key, u32 *idx, u32 *off) +{ + u32 k = (key << 1); + + *idx = k / BITS_PER_BYTE; + *off = k % BITS_PER_BYTE; +} + +/* Fetch the two bits that represent the element and check if it is active based + * on the generation mask. + */ +static inline bool +nft_bitmap_active(const u8 *bitmap, u32 idx, u32 off, u8 genmask) +{ + return (bitmap[idx] & (0x3 << off)) & (genmask << off); +} + +static bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) +{ + const struct nft_bitmap *priv = nft_set_priv(set); + u8 genmask = nft_genmask_cur(net); + u32 idx, off; + + nft_bitmap_location(*key, &idx, &off); + + return nft_bitmap_active(priv->bitmap, idx, off, genmask); +} + +static int nft_bitmap_insert(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, + struct nft_set_ext **_ext) +{ + struct nft_bitmap *priv = nft_set_priv(set); + struct nft_set_ext *ext = elem->priv; + u8 genmask = nft_genmask_next(net); + u32 idx, off; + + nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off); + if (nft_bitmap_active(priv->bitmap, idx, off, genmask)) + return -EEXIST; + + /* Enter 01 state. */ + priv->bitmap[idx] |= (genmask << off); + + return 0; +} + +static void nft_bitmap_remove(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_bitmap *priv = nft_set_priv(set); + struct nft_set_ext *ext = elem->priv; + u8 genmask = nft_genmask_next(net); + u32 idx, off; + + nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off); + /* Enter 00 state. */ + priv->bitmap[idx] &= ~(genmask << off); +} + +static void nft_bitmap_activate(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_bitmap *priv = nft_set_priv(set); + struct nft_set_ext *ext = elem->priv; + u8 genmask = nft_genmask_next(net); + u32 idx, off; + + nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off); + /* Enter 11 state. */ + priv->bitmap[idx] |= (genmask << off); +} + +static bool nft_bitmap_flush(const struct net *net, + const struct nft_set *set, void *ext) +{ + struct nft_bitmap *priv = nft_set_priv(set); + u8 genmask = nft_genmask_next(net); + u32 idx, off; + + nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off); + /* Enter 10 state, similar to deactivation. */ + priv->bitmap[idx] &= ~(genmask << off); + + return true; +} + +static struct nft_set_ext *nft_bitmap_ext_alloc(const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_set_ext_tmpl tmpl; + struct nft_set_ext *ext; + + nft_set_ext_prepare(&tmpl); + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + + ext = kzalloc(tmpl.len, GFP_KERNEL); + if (!ext) + return NULL; + + nft_set_ext_init(ext, &tmpl); + memcpy(nft_set_ext_key(ext), elem->key.val.data, set->klen); + + return ext; +} + +static void *nft_bitmap_deactivate(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_bitmap *priv = nft_set_priv(set); + u8 genmask = nft_genmask_next(net); + struct nft_set_ext *ext; + u32 idx, off, key = 0; + + memcpy(&key, elem->key.val.data, set->klen); + nft_bitmap_location(key, &idx, &off); + + if (!nft_bitmap_active(priv->bitmap, idx, off, genmask)) + return NULL; + + /* We have no real set extension since this is a bitmap, allocate this + * dummy object that is released from the commit/abort path. + */ + ext = nft_bitmap_ext_alloc(set, elem); + if (!ext) + return NULL; + + /* Enter 10 state. */ + priv->bitmap[idx] &= ~(genmask << off); + + return ext; +} + +static void nft_bitmap_walk(const struct nft_ctx *ctx, + struct nft_set *set, + struct nft_set_iter *iter) +{ + const struct nft_bitmap *priv = nft_set_priv(set); + struct nft_set_ext_tmpl tmpl; + struct nft_set_elem elem; + struct nft_set_ext *ext; + int idx, off; + u16 key; + + nft_set_ext_prepare(&tmpl); + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + + for (idx = 0; idx < priv->bitmap_size; idx++) { + for (off = 0; off < BITS_PER_BYTE; off += 2) { + if (iter->count < iter->skip) + goto cont; + + if (!nft_bitmap_active(priv->bitmap, idx, off, + iter->genmask)) + goto cont; + + ext = kzalloc(tmpl.len, GFP_KERNEL); + if (!ext) { + iter->err = -ENOMEM; + return; + } + nft_set_ext_init(ext, &tmpl); + key = ((idx * BITS_PER_BYTE) + off) >> 1; + memcpy(nft_set_ext_key(ext), &key, set->klen); + + elem.priv = ext; + iter->err = iter->fn(ctx, set, iter, &elem); + + /* On set flush, this dummy extension object is released + * from the commit/abort path. + */ + if (!iter->flush) + kfree(ext); + + if (iter->err < 0) + return; +cont: + iter->count++; + } + } +} + +/* The bitmap size is pow(2, key length in bits) / bits per byte. This is + * multiplied by two since each element takes two bits. For 8 bit keys, the + * bitmap consumes 66 bytes. For 16 bit keys, 16388 bytes. + */ +static inline u32 nft_bitmap_size(u32 klen) +{ + return ((2 << ((klen * BITS_PER_BYTE) - 1)) / BITS_PER_BYTE) << 1; +} + +static inline u32 nft_bitmap_total_size(u32 klen) +{ + return sizeof(struct nft_bitmap) + nft_bitmap_size(klen); +} + +static unsigned int nft_bitmap_privsize(const struct nlattr * const nla[]) +{ + u32 klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN])); + + return nft_bitmap_total_size(klen); +} + +static int nft_bitmap_init(const struct nft_set *set, + const struct nft_set_desc *desc, + const struct nlattr * const nla[]) +{ + struct nft_bitmap *priv = nft_set_priv(set); + + priv->bitmap_size = nft_bitmap_total_size(set->klen); + + return 0; +} + +static void nft_bitmap_destroy(const struct nft_set *set) +{ +} + +static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + /* Make sure bitmaps we don't get bitmaps larger than 16 Kbytes. */ + if (desc->klen > 2) + return false; + + est->size = nft_bitmap_total_size(desc->klen); + est->lookup = NFT_SET_CLASS_O_1; + est->space = NFT_SET_CLASS_O_1; + + return true; +} + +static struct nft_set_ops nft_bitmap_ops __read_mostly = { + .privsize = nft_bitmap_privsize, + .estimate = nft_bitmap_estimate, + .init = nft_bitmap_init, + .destroy = nft_bitmap_destroy, + .insert = nft_bitmap_insert, + .remove = nft_bitmap_remove, + .deactivate = nft_bitmap_deactivate, + .flush = nft_bitmap_flush, + .activate = nft_bitmap_activate, + .lookup = nft_bitmap_lookup, + .walk = nft_bitmap_walk, + .owner = THIS_MODULE, +}; + +static int __init nft_bitmap_module_init(void) +{ + return nft_register_set(&nft_bitmap_ops); +} + +static void __exit nft_bitmap_module_exit(void) +{ + nft_unregister_set(&nft_bitmap_ops); +} + +module_init(nft_bitmap_module_init); +module_exit(nft_bitmap_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index e36069fb76ae..5f652720fc78 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -167,8 +167,8 @@ static void nft_hash_activate(const struct net *net, const struct nft_set *set, nft_set_elem_clear_busy(&he->ext); } -static bool nft_hash_deactivate_one(const struct net *net, - const struct nft_set *set, void *priv) +static bool nft_hash_flush(const struct net *net, + const struct nft_set *set, void *priv) { struct nft_hash_elem *he = priv; @@ -195,7 +195,7 @@ static void *nft_hash_deactivate(const struct net *net, rcu_read_lock(); he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); if (he != NULL && - !nft_hash_deactivate_one(net, set, he)) + !nft_hash_flush(net, set, he)) he = NULL; rcu_read_unlock(); @@ -203,7 +203,8 @@ static void *nft_hash_deactivate(const struct net *net, return he; } -static void nft_hash_remove(const struct nft_set *set, +static void nft_hash_remove(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_hash *priv = nft_set_priv(set); @@ -383,7 +384,8 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, est->size = esize + 2 * sizeof(struct nft_hash_elem *); } - est->class = NFT_SET_CLASS_O_1; + est->lookup = NFT_SET_CLASS_O_1; + est->space = NFT_SET_CLASS_O_N; return true; } @@ -397,12 +399,12 @@ static struct nft_set_ops nft_hash_ops __read_mostly = { .insert = nft_hash_insert, .activate = nft_hash_activate, .deactivate = nft_hash_deactivate, - .deactivate_one = nft_hash_deactivate_one, + .flush = nft_hash_flush, .remove = nft_hash_remove, .lookup = nft_hash_lookup, .update = nft_hash_update, .walk = nft_hash_walk, - .features = NFT_SET_MAP | NFT_SET_TIMEOUT, + .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .owner = THIS_MODULE, }; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index f06f55ee516d..71e8fb886a73 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -151,7 +151,8 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, return err; } -static void nft_rbtree_remove(const struct nft_set *set, +static void nft_rbtree_remove(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_rbtree *priv = nft_set_priv(set); @@ -171,8 +172,8 @@ static void nft_rbtree_activate(const struct net *net, nft_set_elem_change_active(net, set, &rbe->ext); } -static bool nft_rbtree_deactivate_one(const struct net *net, - const struct nft_set *set, void *priv) +static bool nft_rbtree_flush(const struct net *net, + const struct nft_set *set, void *priv) { struct nft_rbtree_elem *rbe = priv; @@ -213,7 +214,7 @@ static void *nft_rbtree_deactivate(const struct net *net, parent = parent->rb_right; continue; } - nft_rbtree_deactivate_one(net, set, rbe); + nft_rbtree_flush(net, set, rbe); return rbe; } } @@ -290,7 +291,8 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, else est->size = nsize; - est->class = NFT_SET_CLASS_O_LOG_N; + est->lookup = NFT_SET_CLASS_O_LOG_N; + est->space = NFT_SET_CLASS_O_N; return true; } @@ -304,11 +306,11 @@ static struct nft_set_ops nft_rbtree_ops __read_mostly = { .insert = nft_rbtree_insert, .remove = nft_rbtree_remove, .deactivate = nft_rbtree_deactivate, - .deactivate_one = nft_rbtree_deactivate_one, + .flush = nft_rbtree_flush, .activate = nft_rbtree_activate, .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, - .features = NFT_SET_INTERVAL | NFT_SET_MAP, + .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT, .owner = THIS_MODULE, }; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 2ff499680cc6..016db6be94b9 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -262,6 +262,60 @@ struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision) } EXPORT_SYMBOL_GPL(xt_request_find_target); + +static int xt_obj_to_user(u16 __user *psize, u16 size, + void __user *pname, const char *name, + u8 __user *prev, u8 rev) +{ + if (put_user(size, psize)) + return -EFAULT; + if (copy_to_user(pname, name, strlen(name) + 1)) + return -EFAULT; + if (put_user(rev, prev)) + return -EFAULT; + + return 0; +} + +#define XT_OBJ_TO_USER(U, K, TYPE, C_SIZE) \ + xt_obj_to_user(&U->u.TYPE##_size, C_SIZE ? : K->u.TYPE##_size, \ + U->u.user.name, K->u.kernel.TYPE->name, \ + &U->u.user.revision, K->u.kernel.TYPE->revision) + +int xt_data_to_user(void __user *dst, const void *src, + int usersize, int size) +{ + usersize = usersize ? : size; + if (copy_to_user(dst, src, usersize)) + return -EFAULT; + if (usersize != size && clear_user(dst + usersize, size - usersize)) + return -EFAULT; + + return 0; +} +EXPORT_SYMBOL_GPL(xt_data_to_user); + +#define XT_DATA_TO_USER(U, K, TYPE, C_SIZE) \ + xt_data_to_user(U->data, K->data, \ + K->u.kernel.TYPE->usersize, \ + C_SIZE ? : K->u.kernel.TYPE->TYPE##size) + +int xt_match_to_user(const struct xt_entry_match *m, + struct xt_entry_match __user *u) +{ + return XT_OBJ_TO_USER(u, m, match, 0) || + XT_DATA_TO_USER(u, m, match, 0); +} +EXPORT_SYMBOL_GPL(xt_match_to_user); + +int xt_target_to_user(const struct xt_entry_target *t, + struct xt_entry_target __user *u) +{ + return XT_OBJ_TO_USER(u, t, target, 0) || + XT_DATA_TO_USER(u, t, target, 0); +} +EXPORT_SYMBOL_GPL(xt_target_to_user); + static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) { const struct xt_match *m; @@ -565,17 +619,14 @@ int xt_compat_match_to_user(const struct xt_entry_match *m, int off = xt_compat_match_offset(match); u_int16_t msize = m->u.user.match_size - off; - if (copy_to_user(cm, m, sizeof(*cm)) || - put_user(msize, &cm->u.user.match_size) || - copy_to_user(cm->u.user.name, m->u.kernel.match->name, - strlen(m->u.kernel.match->name) + 1)) + if (XT_OBJ_TO_USER(cm, m, match, msize)) return -EFAULT; if (match->compat_to_user) { if (match->compat_to_user((void __user *)cm->data, m->data)) return -EFAULT; } else { - if (copy_to_user(cm->data, m->data, msize - sizeof(*cm))) + if (XT_DATA_TO_USER(cm, m, match, msize - sizeof(*cm))) return -EFAULT; } @@ -923,17 +974,14 @@ int xt_compat_target_to_user(const struct xt_entry_target *t, int off = xt_compat_target_offset(target); u_int16_t tsize = t->u.user.target_size - off; - if (copy_to_user(ct, t, sizeof(*ct)) || - put_user(tsize, &ct->u.user.target_size) || - copy_to_user(ct->u.user.name, t->u.kernel.target->name, - strlen(t->u.kernel.target->name) + 1)) + if (XT_OBJ_TO_USER(ct, t, target, tsize)) return -EFAULT; if (target->compat_to_user) { if (target->compat_to_user((void __user *)ct->data, t->data)) return -EFAULT; } else { - if (copy_to_user(ct->data, t->data, tsize - sizeof(*ct))) + if (XT_DATA_TO_USER(ct, t, target, tsize - sizeof(*ct))) return -EFAULT; } diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 95c750358747..b008db0184b8 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -23,15 +23,14 @@ static inline int xt_ct_target(struct sk_buff *skb, struct nf_conn *ct) { /* Previously seen (loopback)? Ignore. */ - if (skb->nfct != NULL) + if (skb->_nfct != 0) return XT_CONTINUE; /* special case the untracked ct : we want the percpu object */ if (!ct) ct = nf_ct_untracked_get(); atomic_inc(&ct->ct_general.use); - skb->nfct = &ct->ct_general; - skb->nfctinfo = IP_CT_NEW; + nf_ct_set(skb, ct, IP_CT_NEW); return XT_CONTINUE; } @@ -373,6 +372,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = { .name = "CT", .family = NFPROTO_UNSPEC, .targetsize = sizeof(struct xt_ct_target_info), + .usersize = offsetof(struct xt_ct_target_info, ct), .checkentry = xt_ct_tg_check_v0, .destroy = xt_ct_tg_destroy_v0, .target = xt_ct_target_v0, @@ -384,6 +384,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = { .family = NFPROTO_UNSPEC, .revision = 1, .targetsize = sizeof(struct xt_ct_target_info_v1), + .usersize = offsetof(struct xt_ct_target_info, ct), .checkentry = xt_ct_tg_check_v1, .destroy = xt_ct_tg_destroy_v1, .target = xt_ct_target_v1, @@ -395,6 +396,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = { .family = NFPROTO_UNSPEC, .revision = 2, .targetsize = sizeof(struct xt_ct_target_info_v1), + .usersize = offsetof(struct xt_ct_target_info, ct), .checkentry = xt_ct_tg_check_v2, .destroy = xt_ct_tg_destroy_v1, .target = xt_ct_target_v1, @@ -407,12 +409,11 @@ static unsigned int notrack_tg(struct sk_buff *skb, const struct xt_action_param *par) { /* Previously seen (loopback)? Ignore. */ - if (skb->nfct != NULL) + if (skb->_nfct != 0) return XT_CONTINUE; - skb->nfct = &nf_ct_untracked_get()->ct_general; - skb->nfctinfo = IP_CT_NEW; - nf_conntrack_get(skb->nfct); + nf_ct_set(skb, nf_ct_untracked_get(), IP_CT_NEW); + nf_conntrack_get(skb_nfct(skb)); return XT_CONTINUE; } diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 91a373a3f534..498b54fd04d7 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -162,6 +162,7 @@ static struct xt_target xt_rateest_tg_reg __read_mostly = { .checkentry = xt_rateest_tg_checkentry, .destroy = xt_rateest_tg_destroy, .targetsize = sizeof(struct xt_rateest_target_info), + .usersize = offsetof(struct xt_rateest_target_info, est), .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 1c57ace75ae6..86b0580b2216 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -133,6 +133,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = { .family = NFPROTO_IPV4, .target = tee_tg4, .targetsize = sizeof(struct xt_tee_tginfo), + .usersize = offsetof(struct xt_tee_tginfo, priv), .checkentry = tee_tg_check, .destroy = tee_tg_destroy, .me = THIS_MODULE, @@ -144,6 +145,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = { .family = NFPROTO_IPV6, .target = tee_tg6, .targetsize = sizeof(struct xt_tee_tginfo), + .usersize = offsetof(struct xt_tee_tginfo, priv), .checkentry = tee_tg_check, .destroy = tee_tg_destroy, .me = THIS_MODULE, diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 2dedaa23ab0a..38986a95216c 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -110,6 +110,7 @@ static struct xt_match bpf_mt_reg[] __read_mostly = { .match = bpf_mt, .destroy = bpf_mt_destroy, .matchsize = sizeof(struct xt_bpf_info), + .usersize = offsetof(struct xt_bpf_info, filter), .me = THIS_MODULE, }, { @@ -120,6 +121,7 @@ static struct xt_match bpf_mt_reg[] __read_mostly = { .match = bpf_mt_v1, .destroy = bpf_mt_destroy_v1, .matchsize = sizeof(struct xt_bpf_info_v1), + .usersize = offsetof(struct xt_bpf_info_v1, filter), .me = THIS_MODULE, }, }; diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index a086a914865f..1db1ce59079f 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -122,6 +122,7 @@ static struct xt_match cgroup_mt_reg[] __read_mostly = { .checkentry = cgroup_mt_check_v1, .match = cgroup_mt_v1, .matchsize = sizeof(struct xt_cgroup_info_v1), + .usersize = offsetof(struct xt_cgroup_info_v1, priv), .destroy = cgroup_mt_destroy_v1, .me = THIS_MODULE, .hooks = (1 << NF_INET_LOCAL_OUT) | diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 2aff2b7c4689..b8fd4ab762ed 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -218,7 +218,7 @@ count_tree(struct net *net, struct rb_root *root, int diff; bool addit; - rbconn = container_of(*rbnode, struct xt_connlimit_rb, node); + rbconn = rb_entry(*rbnode, struct xt_connlimit_rb, node); parent = *rbnode; diff = same_source_net(addr, mask, &rbconn->addr, family); @@ -398,7 +398,7 @@ static void destroy_tree(struct rb_root *r) struct rb_node *node; while ((node = rb_first(r)) != NULL) { - rbconn = container_of(node, struct xt_connlimit_rb, node); + rbconn = rb_entry(node, struct xt_connlimit_rb, node); rb_erase(node, r); @@ -431,6 +431,7 @@ static struct xt_match connlimit_mt_reg __read_mostly = { .checkentry = connlimit_mt_check, .match = connlimit_mt, .matchsize = sizeof(struct xt_connlimit_info), + .usersize = offsetof(struct xt_connlimit_info, data), .destroy = connlimit_mt_destroy, .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 10063408141d..26ef70c50e3b 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -838,6 +838,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .family = NFPROTO_IPV4, .match = hashlimit_mt_v1, .matchsize = sizeof(struct xt_hashlimit_mtinfo1), + .usersize = offsetof(struct xt_hashlimit_mtinfo1, hinfo), .checkentry = hashlimit_mt_check_v1, .destroy = hashlimit_mt_destroy_v1, .me = THIS_MODULE, @@ -848,6 +849,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .family = NFPROTO_IPV4, .match = hashlimit_mt, .matchsize = sizeof(struct xt_hashlimit_mtinfo2), + .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, @@ -859,6 +861,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .family = NFPROTO_IPV6, .match = hashlimit_mt_v1, .matchsize = sizeof(struct xt_hashlimit_mtinfo1), + .usersize = offsetof(struct xt_hashlimit_mtinfo1, hinfo), .checkentry = hashlimit_mt_check_v1, .destroy = hashlimit_mt_destroy_v1, .me = THIS_MODULE, @@ -869,6 +872,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .family = NFPROTO_IPV6, .match = hashlimit_mt, .matchsize = sizeof(struct xt_hashlimit_mtinfo2), + .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index bef850596558..dab962df1787 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -192,6 +192,8 @@ static struct xt_match limit_mt_reg __read_mostly = { .compatsize = sizeof(struct compat_xt_rateinfo), .compat_from_user = limit_mt_compat_from_user, .compat_to_user = limit_mt_compat_to_user, +#else + .usersize = offsetof(struct xt_rateinfo, prev), #endif .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_pkttype.c b/net/netfilter/xt_pkttype.c index 57efb703ff18..1ef99151b3ba 100644 --- a/net/netfilter/xt_pkttype.c +++ b/net/netfilter/xt_pkttype.c @@ -33,8 +33,7 @@ pkttype_mt(const struct sk_buff *skb, struct xt_action_param *par) else if (xt_family(par) == NFPROTO_IPV4 && ipv4_is_multicast(ip_hdr(skb)->daddr)) type = PACKET_MULTICAST; - else if (xt_family(par) == NFPROTO_IPV6 && - ipv6_hdr(skb)->daddr.s6_addr[0] == 0xFF) + else if (xt_family(par) == NFPROTO_IPV6) type = PACKET_MULTICAST; else type = PACKET_BROADCAST; diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c index 44c8eb4c9d66..10d61a6eed71 100644 --- a/net/netfilter/xt_quota.c +++ b/net/netfilter/xt_quota.c @@ -73,6 +73,7 @@ static struct xt_match quota_mt_reg __read_mostly = { .checkentry = quota_mt_check, .destroy = quota_mt_destroy, .matchsize = sizeof(struct xt_quota_info), + .usersize = offsetof(struct xt_quota_info, master), .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c index 1db02f6fca54..755d2f6693a2 100644 --- a/net/netfilter/xt_rateest.c +++ b/net/netfilter/xt_rateest.c @@ -133,6 +133,7 @@ static struct xt_match xt_rateest_mt_reg __read_mostly = { .checkentry = xt_rateest_mt_checkentry, .destroy = xt_rateest_mt_destroy, .matchsize = sizeof(struct xt_rateest_match_info), + .usersize = offsetof(struct xt_rateest_match_info, est1), .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_string.c b/net/netfilter/xt_string.c index 0bc3460319c8..423293ee57c2 100644 --- a/net/netfilter/xt_string.c +++ b/net/netfilter/xt_string.c @@ -77,6 +77,7 @@ static struct xt_match xt_string_mt_reg __read_mostly = { .match = string_mt, .destroy = string_mt_destroy, .matchsize = sizeof(struct xt_string_info), + .usersize = offsetof(struct xt_string_info, config), .me = THIS_MODULE, }; |