diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index dbc614dfe0d5..aafa0c04f917 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -115,7 +115,7 @@ struct nf_nat_sip_hooks { unsigned int *datalen); void (*seq_adjust)(struct sk_buff *skb, - unsigned int protoff, s16 off); + unsigned int protoff, s32 off); unsigned int (*expect)(struct sk_buff *skb, unsigned int protoff, diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 417ff51f62fc..e6ca930a3507 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -25,7 +25,9 @@ #include /* for union nf_inet_addr */ #include #include /* for struct ipv6hdr */ +#include #include +#include #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif @@ -1972,8 +1974,8 @@ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph); int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, - unsigned int hooknum, struct ip_vs_iphdr *iph); + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int hooknum, struct ip_vs_iphdr *ciph); void ip_vs_dest_dst_rcu_free(struct rcu_head *head); #ifdef CONFIG_IP_VS_IPV6 @@ -1986,8 +1988,8 @@ int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph); int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, - unsigned int hooknum, struct ip_vs_iphdr *iph); + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int hooknum, struct ip_vs_iphdr *ciph); #endif #ifdef CONFIG_SYSCTL @@ -2059,15 +2061,15 @@ static inline bool ip_vs_conn_use_hash2(struct ip_vs_conn *cp) } void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int dir); + struct ip_vs_conn *cp, int dir, unsigned int toff, + bool has_ports); #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int dir); + struct ip_vs_conn *cp, int dir, unsigned int toff, + bool has_ports, struct ip_vs_iphdr *ciph); #endif -__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset); - static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum) { __be32 diff[2] = { ~old, new }; @@ -2093,6 +2095,33 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } +static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af) +{ + /* Checksum unnecessary or already validated? */ + if (skb_csum_unnecessary(skb)) + return false; + /* LOCAL_OUT ? */ + if (!skb->dev || skb->dev->flags & IFF_LOOPBACK) + return false; + /* !LOCAL_IN (FORWARD) ? */ + if (af == AF_INET6) { + if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL)) + return false; + } else { + if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) + return false; + } + return true; +} + +static inline bool ip_vs_checksum_common_check(struct sk_buff *skb, + int offset, int proto, int af) +{ + if (!ip_vs_checksum_needed(skb, af)) + return true; + return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af); +} + /* Forget current conntrack (unconfirmed) and attach notrack entry */ static inline void ip_vs_notrack(struct sk_buff *skb) { diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index c024345c9bd8..26d6babd92fc 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -161,6 +161,9 @@ static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect, return nf_ct_expect_related_report(expect, 0, 0, flags); } +int nf_ct_expect_related_pair(struct nf_conntrack_expect *expect[], + unsigned int flag); + struct nf_conn_help; void nf_ct_expectation_gc(struct nf_conn_help *master_help); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 9d844354c4d9..3be612145c13 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1294,6 +1294,7 @@ static inline void nft_use_inc_restore(u32 *use) * @sets: sets in the table * @objects: stateful objects in the table * @flowtables: flow tables in the table + * @objname_ht: hashtable for objects lookup by name * @hgenerator: handle generator state * @handle: table handle * @use: number of chain references to this table @@ -1313,6 +1314,7 @@ struct nft_table { struct list_head sets; struct list_head objects; struct list_head flowtables; + struct rhltable objname_ht; u64 hgenerator; u64 handle; u32 use; @@ -1400,7 +1402,7 @@ static inline void *nft_obj_data(const struct nft_object *obj) #define nft_expr_obj(expr) *((struct nft_object **)nft_expr_priv(expr)) struct nft_object *nft_obj_lookup(const struct net *net, - const struct nft_table *table, + struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask); diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 183e8a3ff2ba..6bcd6734769b 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -182,6 +182,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, struct nf_conntrack_expect *rtp_exp, struct nf_conntrack_expect *rtcp_exp) { + struct nf_conntrack_expect *rtp_pair[2] = { rtp_exp, rtcp_exp }; struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); int i; @@ -227,22 +228,13 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, int ret; rtp_exp->tuple.dst.u.udp.port = htons(nated_port); - ret = nf_ct_expect_related(rtp_exp, 0); + rtcp_exp->tuple.dst.u.udp.port = htons(nated_port + 1); + ret = nf_ct_expect_related_pair(rtp_pair, 0); if (ret == 0) { - rtcp_exp->tuple.dst.u.udp.port = - htons(nated_port + 1); - ret = nf_ct_expect_related(rtcp_exp, 0); - if (ret == 0) - break; - else if (ret == -EBUSY) { - nf_ct_unexpect_related(rtp_exp); - continue; - } else if (ret < 0) { - nf_ct_unexpect_related(rtp_exp); - nated_port = 0; - break; - } - } else if (ret != -EBUSY) { + break; + } else if (ret == -EBUSY) { + continue; + } else if (ret < 0) { nated_port = 0; break; } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 8231317b0f1f..b2d77973272d 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -1005,7 +1005,7 @@ overwrite_extensions: #endif if (SET_WITH_COUNTER(set)) ip_set_init_counter(ext_counter(data, set), ext); - if (SET_WITH_COMMENT(set)) + if (SET_WITH_COMMENT(set) && !ext->target) ip_set_init_comment(set, ext_comment(data, set), ext); if (SET_WITH_SKBINFO(set)) ip_set_init_skbinfo(ext_skbinfo(data, set), ext); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index b0e00be85cb1..11cbdbaf561d 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -367,7 +367,7 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th))) return 0; - th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len); + th = (struct tcphdr *)(skb->data + ipvsh->len); /* * Remember seq number in case this pkt gets resized @@ -443,7 +443,7 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th))) return 0; - th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len); + th = (struct tcphdr *)(skb->data + ipvsh->len); /* * Remember seq number in case this pkt gets resized diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 6ed2622363f0..36c5cba03f5b 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -70,25 +70,45 @@ static struct kmem_cache *ip_vs_conn_cachep __read_mostly; * bucket or hash table * - hash table resize works like rehash but always rehashes into new table * - bit lock on bucket serializes all operations that modify the chain + * - on resize, bucket from the old table is locked before bucket from the + * new table * - cp->lock protects conn fields like cp->flags, cp->dest */ -/* Lock conn_tab bucket for conn hash/unhash, not for rehash */ +/** + * conn_tab_lock - Lock conn_tab buckets for conn hash/unhash, not for rehash + * @t: hash table for hn0, new_tbl when new_hash=true + * @t2: hash table for hn1, new_tbl when new_hash2=true + * @cp: connection + * @hash_key: hash key for hn0 + * @hash_key2: hash key for hn1 + * @use2: using hn1 (double hashing) based on the forwarding method + * @new_hash: mode for hn0, hash node (true) or seek node (false) + * @new_hash2: mode for hn1, hash node (true) or seek node (false) + * @head_ret: returned head for hn0 + * @head2_ret: returned head for hn1 + * + * We support 3 modes: + * - seek mode for both nodes, used for unhashing + * - hash mode for both nodes, used for hashing + * - seek hn0 and hash hn1, used when forwarding method is changed + */ static __always_inline void -conn_tab_lock(struct ip_vs_rht *t, struct ip_vs_conn *cp, u32 hash_key, - u32 hash_key2, bool use2, bool new_hash, - struct hlist_bl_head **head_ret, struct hlist_bl_head **head2_ret) +conn_tab_lock(struct ip_vs_rht *t, struct ip_vs_rht *t2, struct ip_vs_conn *cp, + u32 hash_key, u32 hash_key2, bool use2, bool new_hash, + bool new_hash2, struct hlist_bl_head **head_ret, + struct hlist_bl_head **head2_ret) { struct hlist_bl_head *head, *head2; u32 hash_key_new, hash_key_new2; - struct ip_vs_rht *t2 = t; - u32 idx, idx2; + int idx = 0, idx2 = 0; + + /* Advance idx2 when new_hash is not set but hash_key2 + * is for new table + */ + if (new_hash2 && use2 && t != t2) + idx2++; - idx = hash_key & t->mask; - if (use2) - idx2 = hash_key2 & t->mask; - else - idx2 = idx; if (!new_hash) { /* We need to lock the bucket in the right table */ @@ -100,46 +120,45 @@ retry: * both nodes in different tables, use idx/idx2 * for proper lock ordering for heads. */ - idx = hash_key & t->mask; - idx |= IP_VS_RHT_TABLE_ID_MASK; - } - if (use2) { - if (!ip_vs_rht_same_table(t2, hash_key2)) { - /* It is already moved to new table */ - t2 = rcu_dereference(t2->new_tbl); - idx2 = hash_key2 & t2->mask; - idx2 |= IP_VS_RHT_TABLE_ID_MASK; - } - } else { - idx2 = idx; + idx++; } } + if (use2 && !new_hash2 && !ip_vs_rht_same_table(t2, hash_key2)) { + /* It is already moved to new table */ + t2 = rcu_dereference(t2->new_tbl); + idx2++; + } + if (!use2) + idx2 = idx; head = t->buckets + (hash_key & t->mask); head2 = use2 ? t2->buckets + (hash_key2 & t2->mask) : head; - local_bh_disable(); - /* Do not touch seqcount, this is a safe operation */ - - if (idx <= idx2) { + if (idx > idx2 || (head > head2 && idx == idx2)) { + hlist_bl_lock(head2); + hlist_bl_lock(head); + } else { hlist_bl_lock(head); if (head != head2) hlist_bl_lock(head2); - } else { - hlist_bl_lock(head2); - hlist_bl_lock(head); } if (!new_hash) { + bool changed; + /* Ensure hash_key is read under lock */ hash_key_new = READ_ONCE(cp->hn0.hash_key); - hash_key_new2 = READ_ONCE(cp->hn1.hash_key); + changed = hash_key != hash_key_new; + if (use2 && !new_hash2) { + hash_key_new2 = READ_ONCE(cp->hn1.hash_key); + changed |= hash_key2 != hash_key_new2; + } else { + hash_key_new2 = hash_key2; + } /* Hash changed ? */ - if (hash_key != hash_key_new || - (hash_key2 != hash_key_new2 && use2)) { + if (changed) { if (head != head2) hlist_bl_unlock(head2); hlist_bl_unlock(head); - local_bh_enable(); hash_key = hash_key_new; hash_key2 = hash_key_new2; goto retry; @@ -155,7 +174,6 @@ static inline void conn_tab_unlock(struct hlist_bl_head *head, if (head != head2) hlist_bl_unlock(head2); hlist_bl_unlock(head); - local_bh_enable(); } static void ip_vs_conn_expire(struct timer_list *t); @@ -268,8 +286,9 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) use2 = false; } - conn_tab_lock(t, cp, hash_key, hash_key2, use2, true /* new_hash */, - &head, &head2); + local_bh_disable(); + conn_tab_lock(t, t, cp, hash_key, hash_key2, use2, true /* new_hash */, + true /* new_hash2 */, &head, &head2); cp->flags |= IP_VS_CONN_F_HASHED; WRITE_ONCE(cp->hn0.hash_key, hash_key); @@ -280,6 +299,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) hlist_bl_add_head_rcu(&cp->hn1.node, head2); conn_tab_unlock(head, head2); + local_bh_enable(); ret = 1; /* Schedule resizing if load increases */ @@ -306,18 +326,20 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) return refcount_dec_if_one(&cp->refcnt); rcu_read_lock(); + local_bh_disable(); t = rcu_dereference(ipvs->conn_tab); hash_key = READ_ONCE(cp->hn0.hash_key); hash_key2 = READ_ONCE(cp->hn1.hash_key); use2 = ip_vs_conn_use_hash2(cp); - conn_tab_lock(t, cp, hash_key, hash_key2, use2, false /* new_hash */, - &head, &head2); + conn_tab_lock(t, t, cp, hash_key, hash_key2, use2, false /* new_hash */, + false /* new_hash2 */, &head, &head2); if (cp->flags & IP_VS_CONN_F_HASHED) { /* Decrease refcnt and unlink conn only if we are last user */ - if (refcount_dec_if_one(&cp->refcnt)) { + if (use2 == ip_vs_conn_use_hash2(cp) && + refcount_dec_if_one(&cp->refcnt)) { hlist_bl_del_rcu(&cp->hn0.node); if (use2) hlist_bl_del_rcu(&cp->hn1.node); @@ -328,6 +350,7 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) conn_tab_unlock(head, head2); + local_bh_enable(); rcu_read_unlock(); return ret; @@ -632,6 +655,7 @@ void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport) int ntbl; int dir; +restart: /* No packets from inside, so we can do it in 2 steps. */ dir = use2 ? 1 : 0; @@ -686,6 +710,23 @@ retry: /* Protect the cp->flags modification */ spin_lock_bh(&cp->lock); + /* Recheck the forwarding method under lock */ + if (use2 != ip_vs_conn_use_hash2(cp)) { + use2 = !use2; + if (use2) { + spin_unlock_bh(&cp->lock); + /* Restart with new use2 value */ + goto restart; + } + if (dir) { + /* Not started yet, so just skip dir 1 */ + spin_unlock_bh(&cp->lock); + dir--; + goto next_dir; + } + /* Just finish dir 0 */ + } + /* Lock seqcount only for the old bucket, even if we are on new table * because it affects the del operation, not the adding. */ @@ -752,6 +793,61 @@ retry: goto next_dir; } +/* Change forwarding method for hashed conn */ +static void ip_vs_conn_change_fwd_mask(struct ip_vs_conn *cp, u32 new_flags) +{ + struct netns_ipvs *ipvs = cp->ipvs; + struct hlist_bl_head *head, *head2; + u32 hash2, hash_key, hash_key2; + struct ip_vs_rht *t, *t2; + + /* See ip_vs_conn_use_hash2() for reference */ + if ((cp->flags & IP_VS_CONN_F_TEMPLATE) || + /* No change in double hashing ? */ + (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ) == + ((new_flags & IP_VS_CONN_F_FWD_MASK) == IP_VS_CONN_F_MASQ)) { + cp->flags = new_flags; + return; + } + t = rcu_dereference(ipvs->conn_tab); + if (ip_vs_conn_use_hash2(cp)) { + /* Stop double hashing */ + hash_key = READ_ONCE(cp->hn0.hash_key); + hash_key2 = READ_ONCE(cp->hn1.hash_key); + + conn_tab_lock(t, t, cp, hash_key, hash_key2, true /* use2 */, + false /* new_hash */, false /* new_hash2 */, + &head, &head2); + + /* Keep both hash keys in same table */ + hash_key = READ_ONCE(cp->hn0.hash_key); + WRITE_ONCE(cp->hn1.hash_key, hash_key); + hlist_bl_del_rcu(&cp->hn1.node); + cp->flags = new_flags; + + conn_tab_unlock(head, head2); + } else { + /* Start double hashing */ + + hash_key = READ_ONCE(cp->hn0.hash_key); + + t2 = rcu_dereference(t->new_tbl); + hash2 = ip_vs_conn_hashkey_conn(t2, cp, true); + hash_key2 = ip_vs_rht_build_hash_key(t2, hash2); + + /* Change the forwarding method under locked hn0 */ + conn_tab_lock(t, t2, cp, hash_key, hash_key2, true /* use2 */, + false /* new_hash */, true /* new_hash2 */, + &head, &head2); + + WRITE_ONCE(cp->hn1.hash_key, hash_key2); + cp->flags = new_flags; + hlist_bl_add_head_rcu(&cp->hn1.node, head2); + + conn_tab_unlock(head, head2); + } +} + /* Get default load factor to map conn_count/u_thresh to t->size */ static int ip_vs_conn_default_load_factor(struct netns_ipvs *ipvs) { @@ -1014,6 +1110,9 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) flags = cp->flags; /* Bind with the destination and its corresponding transmitter */ if (flags & IP_VS_CONN_F_SYNC) { + /* Synced conns are hashed, so they can not get this flag */ + conn_flags &= ~IP_VS_CONN_F_ONE_PACKET; + /* if the connection is not template and is created * by sync, preserve the activity flag. */ @@ -1021,9 +1120,18 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) conn_flags &= ~IP_VS_CONN_F_INACTIVE; /* connections inherit forwarding method from dest */ flags &= ~(IP_VS_CONN_F_FWD_MASK | IP_VS_CONN_F_NOOUTPUT); + flags |= conn_flags; + /* Changing forwarding method for hashed conn can + * happen only under locks + */ + if (cp->flags & IP_VS_CONN_F_HASHED) + ip_vs_conn_change_fwd_mask(cp, flags); + else + cp->flags = flags; + } else { + flags |= conn_flags; + cp->flags = flags; } - flags |= conn_flags; - cp->flags = flags; cp->dest = dest; IP_VS_DBG_BUF(7, "Bind-dest %s c:%s:%d v:%s:%d " diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index bafab93451d0..6b79e0c4d9e2 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -867,7 +867,7 @@ static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; } #endif -__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) +static __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) { return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); } @@ -924,13 +924,13 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, * - inout: 1=in->out, 0=out->in */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int inout) + struct ip_vs_conn *cp, int inout, unsigned int toff, + bool has_ports) { struct iphdr *iph = ip_hdr(skb); - unsigned int icmp_offset = iph->ihl*4; - struct icmphdr *icmph = (struct icmphdr *)(skb_network_header(skb) + - icmp_offset); + struct icmphdr *icmph = (struct icmphdr *)(skb->data + toff); struct iphdr *ciph = (struct iphdr *)(icmph + 1); + unsigned int coff __maybe_unused = toff + sizeof(struct icmphdr); if (inout) { iph->saddr = cp->vaddr.ip; @@ -945,8 +945,7 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, } /* the TCP/UDP/SCTP port */ - if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol || - IPPROTO_SCTP == ciph->protocol) { + if (has_ports) { __be16 *ports = (void *)ciph + ciph->ihl*4; if (inout) @@ -957,48 +956,40 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, /* And finally the ICMP checksum */ icmph->checksum = 0; - icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset); + icmph->checksum = ip_vs_checksum_complete(skb, toff); skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) - IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, - "Forwarding altered outgoing ICMP"); + IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + "Forwarding altered outgoing ICMP"); else - IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, - "Forwarding altered incoming ICMP"); + IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + "Forwarding altered incoming ICMP"); } #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int inout) + struct ip_vs_conn *cp, int inout, unsigned int toff, + bool has_ports, struct ip_vs_iphdr *ciph) { struct ipv6hdr *iph = ipv6_hdr(skb); - unsigned int icmp_offset = 0; - unsigned int offs = 0; /* header offset*/ - int protocol; struct icmp6hdr *icmph; - struct ipv6hdr *ciph; - unsigned short fragoffs; + struct ipv6hdr *cih; - ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL); - icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset); - offs = icmp_offset + sizeof(struct icmp6hdr); - ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs); - - protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL); + icmph = (struct icmp6hdr *)(skb->data + toff); + cih = (struct ipv6hdr *)(skb->data + ciph->off); if (inout) { iph->saddr = cp->vaddr.in6; - ciph->daddr = cp->vaddr.in6; + cih->daddr = cp->vaddr.in6; } else { iph->daddr = cp->daddr.in6; - ciph->saddr = cp->daddr.in6; + cih->saddr = cp->daddr.in6; } /* the TCP/UDP/SCTP port */ - if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || - IPPROTO_SCTP == protocol)) { - __be16 *ports = (void *)(skb_network_header(skb) + offs); + if (has_ports) { + __be16 *ports = (void *)(skb->data + ciph->len); IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__, ntohs(inout ? ports[1] : ports[0]), @@ -1011,19 +1002,17 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, /* And finally the ICMP checksum */ icmph->icmp6_cksum = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb->len - icmp_offset, + skb->len - toff, IPPROTO_ICMPV6, 0); - skb->csum_start = skb_network_header(skb) - skb->head + icmp_offset; + skb->csum_start = skb_headroom(skb) + toff; skb->csum_offset = offsetof(struct icmp6hdr, icmp6_cksum); skb->ip_summed = CHECKSUM_PARTIAL; if (inout) - IP_VS_DBG_PKT(11, AF_INET6, pp, skb, - (void *)ciph - (void *)iph, + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, ciph->off, "Forwarding altered outgoing ICMPv6"); else - IP_VS_DBG_PKT(11, AF_INET6, pp, skb, - (void *)ciph - (void *)iph, + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, ciph->off, "Forwarding altered incoming ICMPv6"); } #endif @@ -1033,36 +1022,41 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, */ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, - __u8 protocol, struct ip_vs_conn *cp, + struct ip_vs_conn *cp, struct ip_vs_protocol *pp, - unsigned int offset, unsigned int ihl, - unsigned int hooknum) + struct ip_vs_iphdr *ciph, + unsigned int toff, unsigned int hooknum) { + int iproto = af == AF_INET6 ? IPPROTO_ICMPV6 : IPPROTO_ICMP; unsigned int verdict = NF_DROP; + unsigned int ctoff = ciph->len; + bool has_ports = false; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; /* Ensure the checksum is correct */ - if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { + if (!ip_vs_checksum_common_check(skb, toff, iproto, af)) { /* Failed checksum! */ IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n", IP_VS_DBG_ADDR(af, snet)); goto out; } - if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || - IPPROTO_SCTP == protocol) - offset += 2 * sizeof(__u16); - if (skb_ensure_writable(skb, offset)) + if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP || + ciph->protocol == IPPROTO_SCTP) { + ctoff += 2 * sizeof(__u16); + has_ports = true; + } + if (skb_ensure_writable(skb, ctoff)) goto out; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) - ip_vs_nat_icmp_v6(skb, pp, cp, 1); + ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph); else #endif - ip_vs_nat_icmp(skb, pp, cp, 1); + ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; @@ -1090,9 +1084,9 @@ out: * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, - int *related, unsigned int hooknum) + int *related, unsigned int hooknum, + struct ip_vs_iphdr *ipvsh) { - struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; @@ -1107,17 +1101,19 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; + if (!ip_vs_fill_iph_skb(AF_INET, skb, false, ipvsh)) + return NF_ACCEPT; } - iph = ip_hdr(skb); - offset = ihl = iph->ihl * 4; + ihl = ipvsh->len; + offset = ipvsh->len; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), - &iph->saddr, &iph->daddr); + &ipvsh->saddr.ip, &ipvsh->daddr.ip); /* * Work through seeing if this is for us. @@ -1136,7 +1132,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (cih == NULL) + if (!(cih && cih->version == 4 && cih->ihl >= 5)) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(cih->protocol); @@ -1144,8 +1140,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; /* Is the embedded protocol header present? */ - if (unlikely(cih->frag_off & htons(IP_OFFSET) && - pp->dont_defrag)) + if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, @@ -1159,9 +1154,9 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, if (!cp) return NF_ACCEPT; - snet.ip = iph->saddr; - return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, - pp, ciph.len, ihl, hooknum); + snet.ip = ipvsh->saddr.ip; + return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, ihl, + hooknum); } #ifdef CONFIG_IP_VS_IPV6 @@ -1174,7 +1169,6 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, struct ip_vs_conn *cp; struct ip_vs_protocol *pp; union nf_inet_addr snet; - unsigned int offset; *related = 1; ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph); @@ -1210,6 +1204,10 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, if (!pp) return NF_ACCEPT; + /* Is the embedded protocol header present? */ + if (unlikely(ciph.fragoffs && !pp->dont_defrag)) + return NF_ACCEPT; + /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET6, skb, &ciph); @@ -1217,9 +1215,8 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; snet.in6 = ciph.saddr.in6; - offset = ciph.len; - return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, - pp, offset, ipvsh->len, hooknum); + return handle_response_icmp(AF_INET6, skb, &snet, cp, pp, &ciph, + ipvsh->len, hooknum); } #endif @@ -1545,7 +1542,8 @@ ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; - int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum); + int verdict = ip_vs_out_icmp(ipvs, skb, &related, + hooknum, &iph); if (related) return verdict; @@ -1753,9 +1751,8 @@ unk: */ static int ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, - unsigned int hooknum) + unsigned int hooknum, struct ip_vs_iphdr *iph) { - struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; @@ -1765,7 +1762,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int offset, offset2, ihl, verdict; bool tunnel, new_cp = false; union nf_inet_addr *raddr; - char *outer_proto = "IPIP"; + char *outer_proto __maybe_unused = "IPIP"; unsigned int hlen_ipip; int ulen = 0; @@ -1775,17 +1772,19 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; + if (!ip_vs_fill_iph_skb(AF_INET, skb, false, iph)) + return NF_ACCEPT; } - iph = ip_hdr(skb); - offset = ihl = iph->ihl * 4; + ihl = iph->len; + offset = iph->len; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Incoming ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), - &iph->saddr, &iph->daddr); + &iph->saddr.ip, &iph->daddr.ip); /* * Work through seeing if this is for us. @@ -1867,8 +1866,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, pp = pd->pp; /* Is the embedded protocol header present? */ - if (unlikely(cih->frag_off & htons(IP_OFFSET) && - pp->dont_defrag)) + if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, @@ -1876,7 +1874,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, offset2 = offset; ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); - offset = ciph.len; /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. @@ -1898,10 +1895,11 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, verdict = NF_DROP; /* Ensure the checksum is correct */ - if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { + if ((IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ || tunnel) && + !ip_vs_checksum_common_check(skb, ihl, IPPROTO_ICMP, AF_INET)) { /* Failed checksum! */ IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n", - &iph->saddr); + &iph->saddr.ip); goto out; } @@ -1969,10 +1967,7 @@ ignore_tunnel: /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); - if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol || - IPPROTO_SCTP == cih->protocol) - offset += 2 * sizeof(__u16); - verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph); + verdict = ip_vs_icmp_xmit(skb, cp, pp, iph->len, hooknum, &ciph); out: if (likely(!new_cp)) @@ -2032,8 +2027,8 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; pp = pd->pp; - /* Cannot handle fragmented embedded protocol */ - if (ciph.fragoffs) + /* Is the embedded protocol header present? */ + if (ciph.fragoffs && !pp->dont_defrag) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, @@ -2057,23 +2052,22 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, new_cp = true; } - /* VS/TUN, VS/DR and LOCALNODE just let it go */ - if ((hooknum == NF_INET_LOCAL_OUT) && - (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) { - verdict = NF_ACCEPT; + verdict = NF_DROP; + + /* Ensure the checksum is correct */ + if (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ && + !ip_vs_checksum_common_check(skb, iph->len, IPPROTO_ICMPV6, + AF_INET6)) { + /* Failed checksum! */ + IP_VS_DBG(1, "Incoming ICMPv6: failed checksum from %pI6c!\n", + &iph->saddr); goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); - /* Need to mangle contained IPv6 header in ICMPv6 packet */ - offset = ciph.len; - if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol || - IPPROTO_SCTP == ciph.protocol) - offset += 2 * sizeof(__u16); /* Also mangle ports */ - - verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph); + verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, iph->len, hooknum, &ciph); out: if (likely(!new_cp)) @@ -2152,7 +2146,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_in_icmp(ipvs, skb, &related, - hooknum); + hooknum, &iph); if (related) return verdict; @@ -2200,8 +2194,11 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state } if (resched) { - if (!old_ct) + if (!old_ct) { + spin_lock_bh(&cp->lock); cp->flags &= ~IP_VS_CONN_F_NFCT; + spin_unlock_bh(&cp->lock); + } if (!atomic_read(&cp->n_control)) ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); @@ -2217,8 +2214,11 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state if (sysctl_expire_nodest_conn(ipvs)) { bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); - if (!old_ct) + if (!old_ct) { + spin_lock_bh(&cp->lock); cp->flags &= ~IP_VS_CONN_F_NFCT; + spin_unlock_bh(&cp->lock); + } ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); @@ -2288,6 +2288,7 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct netns_ipvs *ipvs = net_ipvs(state->net); + struct ip_vs_iphdr iphdr; int r; /* ipvs enabled in this netns ? */ @@ -2297,10 +2298,9 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb, if (state->pf == NFPROTO_IPV4) { if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; + ip_vs_fill_iph_skb(AF_INET, skb, false, &iphdr); #ifdef CONFIG_IP_VS_IPV6 } else { - struct ip_vs_iphdr iphdr; - ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); if (iphdr.protocol != IPPROTO_ICMPV6) @@ -2310,7 +2310,7 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb, #endif } - return ip_vs_in_icmp(ipvs, skb, &r, state->hook); + return ip_vs_in_icmp(ipvs, skb, &r, state->hook, &iphdr); } static const struct nf_hook_ops ip_vs_ops4[] = { diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index c67317be17df..3dbd3096e163 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -11,7 +11,7 @@ static int sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int sctphoff); + struct ip_vs_iphdr *iph); static int sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -109,7 +109,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!sctp_csum_check(cp->af, skb, pp, sctphoff)) + if (!sctp_csum_check(cp->af, skb, pp, iph)) return 0; /* Call application helper if needed */ @@ -121,7 +121,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - sctph = (void *) skb_network_header(skb) + sctphoff; + sctph = (void *)skb->data + sctphoff; /* Only update csum if we really have to */ if (sctph->source != cp->vport || payload_csum || @@ -157,7 +157,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!sctp_csum_check(cp->af, skb, pp, sctphoff)) + if (!sctp_csum_check(cp->af, skb, pp, iph)) return 0; /* Call application helper if needed */ @@ -169,7 +169,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - sctph = (void *) skb_network_header(skb) + sctphoff; + sctph = (void *)skb->data + sctphoff; /* Only update csum if we really have to */ if (sctph->dest != cp->dport || payload_csum || @@ -187,19 +187,22 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, static int sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int sctphoff) + struct ip_vs_iphdr *iph) { + unsigned int sctphoff = iph->len; struct sctphdr *sh; __le32 cmp, val; + if (!ip_vs_checksum_needed(skb, af)) + return 1; sh = (struct sctphdr *)(skb->data + sctphoff); cmp = sh->checksum; val = sctp_compute_cksum(skb, sctphoff); if (val != cmp) { /* CRC failure, dump it. */ - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); + IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off, + "Failed checksum for"); return 0; } return 1; diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index f86b763efcc4..99a286fdc90c 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -29,7 +29,7 @@ static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int tcphoff); + struct ip_vs_iphdr *iph); static int tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -166,7 +166,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!tcp_csum_check(cp->af, skb, pp, tcphoff)) + if (!tcp_csum_check(cp->af, skb, pp, iph)) return 0; /* Call application helper if needed */ @@ -179,7 +179,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - tcph = (void *)skb_network_header(skb) + tcphoff; + tcph = (void *)skb->data + tcphoff; tcph->source = cp->vport; /* Adjust TCP checksums */ @@ -244,7 +244,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!tcp_csum_check(cp->af, skb, pp, tcphoff)) + if (!tcp_csum_check(cp->af, skb, pp, iph)) return 0; /* @@ -260,7 +260,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - tcph = (void *)skb_network_header(skb) + tcphoff; + tcph = (void *)skb->data + tcphoff; tcph->dest = cp->dport; /* @@ -302,41 +302,13 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int tcphoff) + struct ip_vs_iphdr *iph) { - switch (skb->ip_summed) { - case CHECKSUM_NONE: - skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); - fallthrough; - case CHECKSUM_COMPLETE: -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - tcphoff, - IPPROTO_TCP, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - } else -#endif - if (csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - tcphoff, - ip_hdr(skb)->protocol, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - break; - default: - /* No need to checksum. */ - break; + if (!ip_vs_checksum_common_check(skb, iph->len, IPPROTO_TCP, af)) { + IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off, + "Failed checksum for"); + return 0; } - return 1; } diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 58f9e255927e..f32785682402 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -25,7 +25,7 @@ static int udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int udphoff); + struct ip_vs_iphdr *iph); static int udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -155,7 +155,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!udp_csum_check(cp->af, skb, pp, udphoff)) + if (!udp_csum_check(cp->af, skb, pp, iph)) return 0; /* @@ -170,7 +170,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - udph = (void *)skb_network_header(skb) + udphoff; + udph = (void *)skb->data + udphoff; udph->source = cp->vport; /* @@ -238,7 +238,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!udp_csum_check(cp->af, skb, pp, udphoff)) + if (!udp_csum_check(cp->af, skb, pp, iph)) return 0; /* @@ -254,7 +254,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - udph = (void *)skb_network_header(skb) + udphoff; + udph = (void *)skb->data + udphoff; udph->dest = cp->dport; /* @@ -298,48 +298,20 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, static int udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int udphoff) + struct ip_vs_iphdr *iph) { struct udphdr _udph, *uh; - uh = skb_header_pointer(skb, udphoff, sizeof(_udph), &_udph); + uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph); if (uh == NULL) return 0; - if (uh->check != 0) { - switch (skb->ip_summed) { - case CHECKSUM_NONE: - skb->csum = skb_checksum(skb, udphoff, - skb->len - udphoff, 0); - fallthrough; - case CHECKSUM_COMPLETE: -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - udphoff, - IPPROTO_UDP, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - } else -#endif - if (csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - udphoff, - ip_hdr(skb)->protocol, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - break; - default: - /* No need to checksum. */ - break; - } + if (!uh->check) + return 1; + if (!ip_vs_checksum_common_check(skb, iph->len, IPPROTO_UDP, af)) { + IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off, + "Failed checksum for"); + return 0; } return 1; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 9fef4335da13..0b0c5304993a 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1502,20 +1502,22 @@ tx_error: */ int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, unsigned int hooknum, - struct ip_vs_iphdr *iph) + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int hooknum, struct ip_vs_iphdr *ciph) { struct rtable *rt; /* Route to the other host */ int rc; int local; int rt_mode, was_input; + bool has_ports = false; + unsigned int wlen; /* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be forwarded directly here, because there is no need to translate address/port back */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { if (cp->packet_xmit) - rc = cp->packet_xmit(skb, cp, pp, iph); + rc = cp->packet_xmit(skb, cp, pp, ciph); else rc = NF_ACCEPT; /* do not touch skb anymore */ @@ -1533,7 +1535,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip, rt_mode, - NULL, iph); + NULL, ciph); if (local < 0) goto tx_error; rt = skb_rtable(skb); @@ -1564,14 +1566,21 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } + wlen = ciph->len; + if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP || + ciph->protocol == IPPROTO_SCTP) { + wlen += 2 * sizeof(__u16); /* Also mangle ports */ + has_ports = true; + } + /* copy-on-write the packet before mangling it */ - if (skb_ensure_writable(skb, offset)) + if (skb_ensure_writable(skb, wlen)) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp(skb, pp, cp, 0); + ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; @@ -1587,10 +1596,12 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #ifdef CONFIG_IP_VS_IPV6 int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, unsigned int hooknum, - struct ip_vs_iphdr *ipvsh) + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int hooknum, struct ip_vs_iphdr *ciph) { + bool has_ports = false; struct rt6_info *rt; /* Route to the other host */ + unsigned int wlen; int rc; int local; int rt_mode; @@ -1600,7 +1611,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, translate address/port back */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { if (cp->packet_xmit) - rc = cp->packet_xmit(skb, cp, pp, ipvsh); + rc = cp->packet_xmit(skb, cp, pp, ciph); else rc = NF_ACCEPT; /* do not touch skb anymore */ @@ -1617,7 +1628,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest, - &cp->daddr.in6, NULL, ipvsh, 0, rt_mode); + &cp->daddr.in6, NULL, ciph, 0, rt_mode); if (local < 0) goto tx_error; rt = dst_rt6_info(skb_dst(skb)); @@ -1648,14 +1659,21 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } + wlen = ciph->len; + if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP || + ciph->protocol == IPPROTO_SCTP) { + wlen += 2 * sizeof(__u16); /* Also mangle ports */ + has_ports = true; + } + /* copy-on-write the packet before mangling it */ - if (skb_ensure_writable(skb, offset)) + if (skb_ensure_writable(skb, wlen)) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp_v6(skb, pp, cp, 0); + ip_vs_nat_icmp_v6(skb, pp, cp, 0, toff, has_ports, ciph); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 7ae68d60586a..8a3b9e33e94f 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -427,7 +427,6 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp, exp->timeout += helper->expect_policy[exp->class].timeout * HZ; hlist_add_head_rcu(&exp->lnode, &master_help->expectations); - master_help->expecting[exp->class]++; hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]); cnet = nf_ct_pernet(net); @@ -534,6 +533,7 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, if (ret < 0) goto out; + master_help->expecting[expect->class]++; nf_ct_expect_insert(expect, master_help); nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report); @@ -546,6 +546,39 @@ out: } EXPORT_SYMBOL_GPL(nf_ct_expect_related_report); +int nf_ct_expect_related_pair(struct nf_conntrack_expect *expect[], + unsigned int flags) +{ + struct nf_conn_help *master_help; + int i, ret; + + spin_lock_bh(&nf_conntrack_expect_lock); + master_help = nfct_help(expect[0]->master); + if (!master_help || master_help != nfct_help(expect[1]->master)) { + ret = -EINVAL; + goto out; + } + + for (i = 0; i < 2; i++) { + ret = __nf_ct_expect_check(expect[i], master_help, flags); + if (ret < 0) { + if (i == 1) + master_help->expecting[expect[0]->class]--; + goto out; + } + master_help->expecting[expect[i]->class]++; + } + + for (i = 0; i < 2; i++) { + nf_ct_expect_insert(expect[i], master_help); + nf_ct_expect_event_report(IPEXP_NEW, expect[i], 0, 0); + } +out: + spin_unlock_bh(&nf_conntrack_expect_lock); + return ret; +} +EXPORT_SYMBOL_GPL(nf_ct_expect_related_pair); + void nf_ct_expect_iterate_destroy(bool (*iter)(struct nf_conntrack_expect *e, void *data), void *data) { diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index f3f90a866338..e4a70d1d77b0 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1663,7 +1663,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, unsigned int matchoff, matchlen; unsigned int msglen, origlen; const char *dptr, *end; - s16 diff, tdiff = 0; + s32 diff, tdiff = 0; int ret = NF_ACCEPT; unsigned long clen; bool term; diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index aea02f6aff09..133bd713fe0c 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -321,7 +321,7 @@ next: } static void nf_nat_sip_seq_adjust(struct sk_buff *skb, unsigned int protoff, - s16 off) + s32 off) { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); @@ -592,6 +592,7 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, unsigned int medialen, union nf_inet_addr *rtp_addr) { + struct nf_conntrack_expect *rtp_pair[2] = { rtp_exp, rtcp_exp }; enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); @@ -622,24 +623,15 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, int ret; rtp_exp->tuple.dst.u.udp.port = htons(port); - ret = nf_ct_expect_related(rtp_exp, - NF_CT_EXP_F_SKIP_MASTER); - if (ret == -EBUSY) - continue; - else if (ret < 0) { - port = 0; - break; - } rtcp_exp->tuple.dst.u.udp.port = htons(port + 1); - ret = nf_ct_expect_related(rtcp_exp, - NF_CT_EXP_F_SKIP_MASTER); + + ret = nf_ct_expect_related_pair(rtp_pair, + NF_CT_EXP_F_SKIP_MASTER); if (ret == 0) break; - else if (ret == -EBUSY) { - nf_ct_unexpect_related(rtp_exp); + else if (ret == -EBUSY) continue; - } else if (ret < 0) { - nf_ct_unexpect_related(rtp_exp); + else if (ret < 0) { port = 0; break; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a9eaf9455c77..af357f6c5070 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -45,8 +45,6 @@ enum { NFT_VALIDATE_DO, }; -static struct rhltable nft_objname_ht; - static u32 nft_chain_hash(const void *data, u32 len, u32 seed); static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed); static int nft_chain_hash_cmp(struct rhashtable_compare_arg *, const void *); @@ -1635,6 +1633,10 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, if (err) goto err_chain_ht; + err = rhltable_init(&table->objname_ht, &nft_objname_ht_params); + if (err < 0) + goto err_obj_ht; + INIT_LIST_HEAD(&table->chains); INIT_LIST_HEAD(&table->sets); INIT_LIST_HEAD(&table->objects); @@ -1653,6 +1655,8 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, list_add_tail_rcu(&table->list, &nft_net->tables); return 0; err_trans: + rhltable_destroy(&table->objname_ht); +err_obj_ht: rhltable_destroy(&table->chains_ht); err_chain_ht: kfree(table->udata); @@ -1819,6 +1823,7 @@ static void nf_tables_table_destroy(struct nft_table *table) return; rhltable_destroy(&table->chains_ht); + rhltable_destroy(&table->objname_ht); kfree(table->name); kfree(table->udata); kfree(table); @@ -8086,7 +8091,7 @@ void nft_unregister_obj(struct nft_object_type *obj_type) EXPORT_SYMBOL_GPL(nft_unregister_obj); struct nft_object *nft_obj_lookup(const struct net *net, - const struct nft_table *table, + struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask) { @@ -8102,7 +8107,7 @@ struct nft_object *nft_obj_lookup(const struct net *net, !lockdep_commit_lock_is_held(net)); rcu_read_lock(); - list = rhltable_lookup(&nft_objname_ht, &k, nft_objname_ht_params); + list = rhltable_lookup(&table->objname_ht, &k, nft_objname_ht_params); if (!list) goto out; @@ -8382,7 +8387,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, if (err < 0) goto err_trans; - err = rhltable_insert(&nft_objname_ht, &obj->rhlhead, + err = rhltable_insert(&table->objname_ht, &obj->rhlhead, nft_objname_ht_params); if (err < 0) goto err_obj_ht; @@ -8567,8 +8572,8 @@ nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; - const struct nft_table *table; struct net *net = info->net; + struct nft_table *table; struct nft_object *obj; struct sk_buff *skb2; u32 objtype; @@ -10437,9 +10442,9 @@ static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) nf_tables_commit_chain_free_rules_old(g0); } -static void nft_obj_del(struct nft_object *obj) +static void nft_obj_del(struct nft_table *table, struct nft_object *obj) { - rhltable_remove(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params); + rhltable_remove(&table->objname_ht, &obj->rhlhead, nft_objname_ht_params); list_del_rcu(&obj->list); } @@ -11124,7 +11129,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: - nft_obj_del(nft_trans_obj(trans)); + nft_obj_del(table, nft_trans_obj(trans)); nf_tables_obj_notify(&ctx, nft_trans_obj(trans), trans->msg_type); break; @@ -11416,7 +11421,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); } else { nft_use_dec_restore(&table->use); - nft_obj_del(nft_trans_obj(trans)); + nft_obj_del(table, nft_trans_obj(trans)); } break; case NFT_MSG_DELOBJ: @@ -12043,7 +12048,7 @@ static void __nft_release_table(struct net *net, struct nft_table *table) nft_set_destroy(&ctx, set); } list_for_each_entry_safe(obj, ne, &table->objects, list) { - nft_obj_del(obj); + nft_obj_del(table, obj); nft_use_dec(&table->use); nft_obj_destroy(&ctx, obj); } @@ -12225,10 +12230,6 @@ static int __init nf_tables_module_init(void) if (err < 0) goto err_netdev_notifier; - err = rhltable_init(&nft_objname_ht, &nft_objname_ht_params); - if (err < 0) - goto err_rht_objname; - err = nft_offload_init(); if (err < 0) goto err_offload; @@ -12251,8 +12252,6 @@ err_nfnl_subsys: err_netlink_notifier: nft_offload_exit(); err_offload: - rhltable_destroy(&nft_objname_ht); -err_rht_objname: unregister_netdevice_notifier(&nf_tables_flowtable_notifier); err_netdev_notifier: nf_tables_core_module_exit(); @@ -12274,7 +12273,6 @@ static void __exit nf_tables_module_exit(void) unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_gc_work); rcu_barrier(); - rhltable_destroy(&nft_objname_ht); nf_tables_core_module_exit(); } diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 391539a1ceaa..8a4472fd77d9 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -259,9 +259,7 @@ nla_put_failure: static bool nft_payload_offload_mask(struct nft_offload_reg *reg, u32 priv_len, u32 field_len) { - unsigned int remainder, delta, k; struct nft_data mask = {}; - __be32 remainder_mask; if (priv_len == field_len) { memset(®->mask, 0xff, priv_len); @@ -270,15 +268,7 @@ static bool nft_payload_offload_mask(struct nft_offload_reg *reg, return false; } - memset(&mask, 0xff, field_len); - remainder = priv_len % sizeof(u32); - if (remainder) { - k = priv_len / sizeof(u32); - delta = field_len - priv_len; - remainder_mask = htonl(~((1 << (delta * BITS_PER_BYTE)) - 1)); - mask.data[k] = (__force u32)remainder_mask; - } - + memset(&mask, 0xff, priv_len); memcpy(®->mask, &mask, field_len); return true; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 2704b4b60d1e..9af0fa895f73 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -117,6 +117,7 @@ struct xt_hashlimit_htable { refcount_t use; u_int8_t family; bool rnd_initialized; + bool ratematch; struct hashlimit_cfg3 cfg; /* config */ @@ -323,6 +324,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, kvfree(hinfo); return -ENOMEM; } + hinfo->ratematch = !!(cfg->mode & XT_HASHLIMIT_RATE_MATCH); spin_lock_init(&hinfo->lock); switch (revision) { @@ -872,7 +874,10 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, } /* Check for overflow. */ - if (revision >= 3 && cfg->mode & XT_HASHLIMIT_RATE_MATCH) { + if (cfg->mode & XT_HASHLIMIT_RATE_MATCH) { + if (revision < 3) + return -EINVAL; + if (cfg->avg == 0 || cfg->avg > U32_MAX) { pr_info_ratelimited("invalid rate\n"); return -ERANGE; @@ -905,6 +910,15 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, mutex_unlock(&hashlimit_mutex); return ret; } + } else { + if ((cfg->mode & XT_HASHLIMIT_RATE_MATCH && + !(*hinfo)->ratematch) || + (!(cfg->mode & XT_HASHLIMIT_RATE_MATCH) && + (*hinfo)->ratematch)) { + mutex_unlock(&hashlimit_mutex); + htable_put(*hinfo); + return -EINVAL; + } } mutex_unlock(&hashlimit_mutex); diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh index fb1c59d45567..449c518bd947 100755 --- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh @@ -617,7 +617,11 @@ ip -6 -net "$nsr2" route add default via fee1:3::1 ip -net "$ns2" route add default via 10.0.2.1 ip -6 -net "$ns2" route add default via dead:2::1 +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif tun0 tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun0 accept' +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif tun6 tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun6 accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward \ 'meta oif "veth0" tcp sport 12345 ct mark set 1 flow add @f1 counter name routed_repl accept' @@ -629,7 +633,7 @@ if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "IPIP tunnel"; then fi if test_tcp_forwarding "$ns1" "$ns2" 1 6 "[dead:2::99]" 12345; then - echo "PASS: flow offload for ns1/ns2 IP6IP6 tunnel" + check_counters "flow offload for ns1/ns2 IP6IP6 tunnel" else echo "FAIL: flow offload for ns1/ns2 with IP6IP6 tunnel" 1>&2 ip netns exec "$nsr1" nft list ruleset @@ -642,6 +646,8 @@ ip -net "$nsr1" link set veth1.10 up ip -net "$nsr1" addr add 192.168.20.1/24 dev veth1.10 ip -net "$nsr1" addr add fee1:4::1/64 dev veth1.10 nodad ip netns exec "$nsr1" sysctl net.ipv4.conf.veth1/10.forwarding=1 > /dev/null +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif veth1.10 tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif veth1.10 accept' ip -net "$nsr1" link add name tun0.10 type ipip local 192.168.20.1 remote 192.168.20.2 @@ -649,6 +655,8 @@ ip -net "$nsr1" link set tun0.10 up ip -net "$nsr1" addr add 192.168.200.1/24 dev tun0.10 ip -net "$nsr1" route change default via 192.168.200.2 ip netns exec "$nsr1" sysctl net.ipv4.conf.tun0/10.forwarding=1 > /dev/null +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif tun0.10 tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun0.10 accept' ip -net "$nsr1" link add name tun6.10 type ip6tnl local fee1:4::1 remote fee1:4::2 encaplimit none @@ -656,6 +664,8 @@ ip -net "$nsr1" link set tun6.10 up ip -net "$nsr1" addr add fee1:5::1/64 dev tun6.10 nodad ip -6 -net "$nsr1" route delete default ip -6 -net "$nsr1" route add default via fee1:5::2 +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif tun6.10 tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun6.10 accept' ip -net "$nsr2" link add link veth0 name veth0.10 type vlan id 10 @@ -683,7 +693,7 @@ if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "IPIP tunnel over vlan"; then fi if test_tcp_forwarding "$ns1" "$ns2" 1 6 "[dead:2::99]" 12345; then - echo "PASS: flow offload for ns1/ns2 IP6IP6 tunnel over vlan" + check_counters "flow offload for ns1/ns2 IP6IP6 tunnel over vlan" else echo "FAIL: flow offload for ns1/ns2 with IP6IP6 tunnel over vlan" 1>&2 ip netns exec "$nsr1" nft list ruleset