From 1da40ab6caf924633116582c4c86939c486f20db Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 5 May 2019 15:14:38 +0300 Subject: [PATCH 01/15] ipvs: allow rs_table to contain different real server types Before now rs_table was used only for NAT real servers. Change it to allow TUN real severs from different types, possibly hashed with different port key. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 3 +++ net/netfilter/ipvs/ip_vs_ctl.c | 43 +++++++++++++++++++++++++++------- 2 files changed, 38 insertions(+), 8 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 2ac40135b576..9a8ac8997e34 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1497,6 +1497,9 @@ static inline int ip_vs_todrop(struct netns_ipvs *ipvs) static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; } #endif +#define IP_VS_DFWD_METHOD(dest) (atomic_read(&(dest)->conn_flags) & \ + IP_VS_CONN_F_FWD_MASK) + /* ip_vs_fwd_tag returns the forwarding tag of the connection */ #define IP_VS_FWD_METHOD(cp) (cp->flags & IP_VS_CONN_F_FWD_MASK) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 0e887159425c..30b1a9f9c2e3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -515,15 +515,36 @@ static inline unsigned int ip_vs_rs_hashkey(int af, static void ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest) { unsigned int hash; + __be16 port; if (dest->in_rs_table) return; + switch (IP_VS_DFWD_METHOD(dest)) { + case IP_VS_CONN_F_MASQ: + port = dest->port; + break; + case IP_VS_CONN_F_TUNNEL: + switch (dest->tun_type) { + case IP_VS_CONN_F_TUNNEL_TYPE_GUE: + port = dest->tun_port; + break; + case IP_VS_CONN_F_TUNNEL_TYPE_IPIP: + port = 0; + break; + default: + return; + } + break; + default: + return; + } + /* * Hash by proto,addr,port, * which are the parameters of the real service. */ - hash = ip_vs_rs_hashkey(dest->af, &dest->addr, dest->port); + hash = ip_vs_rs_hashkey(dest->af, &dest->addr, port); hlist_add_head_rcu(&dest->d_list, &ipvs->rs_table[hash]); dest->in_rs_table = 1; @@ -555,7 +576,8 @@ bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, if (dest->port == dport && dest->af == af && ip_vs_addr_equal(af, &dest->addr, daddr) && - (dest->protocol == protocol || dest->vfwmark)) { + (dest->protocol == protocol || dest->vfwmark) && + IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_MASQ) { /* HIT */ return true; } @@ -585,7 +607,8 @@ struct ip_vs_dest *ip_vs_find_real_service(struct netns_ipvs *ipvs, int af, if (dest->port == dport && dest->af == af && ip_vs_addr_equal(af, &dest->addr, daddr) && - (dest->protocol == protocol || dest->vfwmark)) { + (dest->protocol == protocol || dest->vfwmark) && + IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_MASQ) { /* HIT */ return dest; } @@ -831,6 +854,13 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK; conn_flags |= IP_VS_CONN_F_INACTIVE; + /* Need to rehash? */ + if ((udest->conn_flags & IP_VS_CONN_F_FWD_MASK) != + IP_VS_DFWD_METHOD(dest) || + udest->tun_type != dest->tun_type || + udest->tun_port != dest->tun_port) + ip_vs_rs_unhash(dest); + /* set the tunnel info */ dest->tun_type = udest->tun_type; dest->tun_port = udest->tun_port; @@ -839,16 +869,13 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) { conn_flags |= IP_VS_CONN_F_NOOUTPUT; } else { - /* - * Put the real service in rs_table if not present. - * For now only for NAT! - */ - ip_vs_rs_hash(ipvs, dest); /* FTP-NAT requires conntrack for mangling */ if (svc->port == FTPPORT) ip_vs_register_conntrack(svc); } atomic_set(&dest->conn_flags, conn_flags); + /* Put the real service in rs_table if not present. */ + ip_vs_rs_hash(ipvs, dest); /* bind the service */ old_svc = rcu_dereference_protected(dest->svc, 1); From 2aa3c9f48bc28ca0effd9877e010ad54c8a630e5 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 5 May 2019 15:14:39 +0300 Subject: [PATCH 02/15] ipvs: add function to find tunnels Add ip_vs_find_tunnel() to match tunnel headers by family, address and optional port. Use it to properly find the tunnel real server used in received ICMP errors. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 3 +++ net/netfilter/ipvs/ip_vs_core.c | 8 ++++++++ net/netfilter/ipvs/ip_vs_ctl.c | 29 +++++++++++++++++++++++++++++ 3 files changed, 40 insertions(+) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9a8ac8997e34..b01a94ebfc0e 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1404,6 +1404,9 @@ bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, struct ip_vs_dest * ip_vs_find_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); +struct ip_vs_dest *ip_vs_find_tunnel(struct netns_ipvs *ipvs, int af, + const union nf_inet_addr *daddr, + __be16 tun_port); int ip_vs_use_count_inc(void); void ip_vs_use_count_dec(void); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 14457551bcb4..4447ee512b88 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1598,6 +1598,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, struct ip_vs_proto_data *pd; unsigned int offset, offset2, ihl, verdict; bool ipip, new_cp = false; + union nf_inet_addr *raddr; *related = 1; @@ -1636,15 +1637,22 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ + raddr = (union nf_inet_addr *)&cih->daddr; /* Special case for errors for IPIP packets */ ipip = false; if (cih->protocol == IPPROTO_IPIP) { + struct ip_vs_dest *dest; + if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; /* Error for our IPIP must arrive at LOCAL_IN */ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) return NF_ACCEPT; + dest = ip_vs_find_tunnel(ipvs, AF_INET, raddr, 0); + /* Only for known tunnel */ + if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) + return NF_ACCEPT; offset += cih->ihl * 4; cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 30b1a9f9c2e3..d5847e06350f 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -617,6 +617,35 @@ struct ip_vs_dest *ip_vs_find_real_service(struct netns_ipvs *ipvs, int af, return NULL; } +/* Find real service record by . + * In case of multiple records with the same , only + * the first found record is returned. + * + * To be called under RCU lock. + */ +struct ip_vs_dest *ip_vs_find_tunnel(struct netns_ipvs *ipvs, int af, + const union nf_inet_addr *daddr, + __be16 tun_port) +{ + struct ip_vs_dest *dest; + unsigned int hash; + + /* Check for "full" addressed entries */ + hash = ip_vs_rs_hashkey(af, daddr, tun_port); + + hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) { + if (dest->tun_port == tun_port && + dest->af == af && + ip_vs_addr_equal(af, &dest->addr, daddr) && + IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_TUNNEL) { + /* HIT */ + return dest; + } + } + + return NULL; +} + /* Lookup destination by {addr,port} in the given service * Called under RCU lock. */ From 508f744c0de38f517a94cc2d0bf8e118271b9645 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 5 May 2019 15:14:40 +0300 Subject: [PATCH 03/15] ipvs: strip udp tunnel headers from icmp errors Recognize UDP tunnels in received ICMP errors and properly strip the tunnel headers. GUE is what we have for now. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_core.c | 60 +++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4447ee512b88..d1d7b2483fd7 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -39,6 +39,7 @@ #include #include #include /* for icmp_send */ +#include #include #include #include /* net_generic() */ @@ -1579,6 +1580,41 @@ ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, return 1; } +/* Check the UDP tunnel and return its header length */ +static int ipvs_udp_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, + unsigned int offset, __u16 af, + const union nf_inet_addr *daddr, __u8 *proto) +{ + struct udphdr _udph, *udph; + struct ip_vs_dest *dest; + + udph = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); + if (!udph) + goto unk; + offset += sizeof(struct udphdr); + dest = ip_vs_find_tunnel(ipvs, af, daddr, udph->dest); + if (!dest) + goto unk; + if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + struct guehdr _gueh, *gueh; + + gueh = skb_header_pointer(skb, offset, sizeof(_gueh), &_gueh); + if (!gueh) + goto unk; + if (gueh->control != 0 || gueh->version != 0) + goto unk; + /* Later we can support also IPPROTO_IPV6 */ + if (gueh->proto_ctype != IPPROTO_IPIP) + goto unk; + *proto = gueh->proto_ctype; + return sizeof(struct udphdr) + sizeof(struct guehdr) + + (gueh->hlen << 2); + } + +unk: + return 0; +} + /* * Handle ICMP messages in the outside-to-inside direction (incoming). * Find any that might be relevant, check against existing connections, @@ -1658,6 +1694,30 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ ipip = true; + } else if (cih->protocol == IPPROTO_UDP && /* Can be UDP encap */ + /* Error for our tunnel must arrive at LOCAL_IN */ + (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) { + __u8 iproto; + int ulen; + + /* Non-first fragment has no UDP header */ + if (unlikely(cih->frag_off & htons(IP_OFFSET))) + return NF_ACCEPT; + offset2 = offset + cih->ihl * 4; + ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr, + &iproto); + if (ulen > 0) { + /* Skip IP and UDP tunnel headers */ + offset = offset2 + ulen; + /* Now we should be at the original IP header */ + cih = skb_header_pointer(skb, offset, sizeof(_ciph), + &_ciph); + if (cih && cih->version == 4 && cih->ihl >= 5 && + iproto == IPPROTO_IPIP) + ipip = true; + else + return NF_ACCEPT; + } } pd = ip_vs_proto_data_get(ipvs, cih->protocol); From ea6cc2fd8a2b89ab6dcd096ba6dbc1ecbdf26564 Mon Sep 17 00:00:00 2001 From: Lukasz Pawelczyk Date: Fri, 10 May 2019 13:46:22 +0200 Subject: [PATCH 04/15] netfilter: xt_owner: Add supplementary groups option The XT_OWNER_SUPPL_GROUPS flag causes GIDs specified with XT_OWNER_GID to be also checked in the supplementary groups of a process. f_cred->group_info cannot be modified during its lifetime and f_cred holds a reference to it so it's safe to use. Signed-off-by: Lukasz Pawelczyk Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/xt_owner.h | 7 ++++--- net/netfilter/xt_owner.c | 23 ++++++++++++++++++++--- 2 files changed, 24 insertions(+), 6 deletions(-) diff --git a/include/uapi/linux/netfilter/xt_owner.h b/include/uapi/linux/netfilter/xt_owner.h index fa3ad84957d5..9e98c09eda32 100644 --- a/include/uapi/linux/netfilter/xt_owner.h +++ b/include/uapi/linux/netfilter/xt_owner.h @@ -5,9 +5,10 @@ #include enum { - XT_OWNER_UID = 1 << 0, - XT_OWNER_GID = 1 << 1, - XT_OWNER_SOCKET = 1 << 2, + XT_OWNER_UID = 1 << 0, + XT_OWNER_GID = 1 << 1, + XT_OWNER_SOCKET = 1 << 2, + XT_OWNER_SUPPL_GROUPS = 1 << 3, }; struct xt_owner_match_info { diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index 46686fb73784..a8784502aca6 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -91,11 +91,28 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) } if (info->match & XT_OWNER_GID) { + unsigned int i, match = false; kgid_t gid_min = make_kgid(net->user_ns, info->gid_min); kgid_t gid_max = make_kgid(net->user_ns, info->gid_max); - if ((gid_gte(filp->f_cred->fsgid, gid_min) && - gid_lte(filp->f_cred->fsgid, gid_max)) ^ - !(info->invert & XT_OWNER_GID)) + struct group_info *gi = filp->f_cred->group_info; + + if (gid_gte(filp->f_cred->fsgid, gid_min) && + gid_lte(filp->f_cred->fsgid, gid_max)) + match = true; + + if (!match && (info->match & XT_OWNER_SUPPL_GROUPS) && gi) { + for (i = 0; i < gi->ngroups; ++i) { + kgid_t group = gi->gid[i]; + + if (gid_gte(group, gid_min) && + gid_lte(group, gid_max)) { + match = true; + break; + } + } + } + + if (match ^ !(info->invert & XT_OWNER_GID)) return false; } From 5e2ad02e9001fd99cae3c14e52f67bb976e9bee3 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Thu, 16 May 2019 04:02:31 +0900 Subject: [PATCH 05/15] netfilter: nf_flow_table: remove unnecessary variable in flow_offload_tuple The oifidx in the struct flow_offload_tuple is not used anymore. Signed-off-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 2 -- net/netfilter/nf_flow_table_core.c | 1 - 2 files changed, 3 deletions(-) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 3e370cb36263..d8c187936bec 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -53,8 +53,6 @@ struct flow_offload_tuple { u8 l4proto; u8 dir; - int oifidx; - u16 mtu; struct dst_entry *dst_cache; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 948b4ebbe3fb..e3d797252a98 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -53,7 +53,6 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct, ft->dst_port = ctt->dst.u.tcp.port; ft->iifidx = other_dst->dev->ifindex; - ft->oifidx = dst->dev->ifindex; ft->dst_cache = dst; } From 53315ac660b09f8128cd086e3ea0ed5ed5081d55 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 22 May 2019 23:35:11 +0200 Subject: [PATCH 06/15] netfilter: nf_tables: free base chain counters from worker No need to use synchronize_rcu() here, just swap the two pointers and have the release occur from work queue after commit has completed. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 28241e82fd15..2fed78b19abe 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1449,25 +1449,18 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) return newstats; } -static void nft_chain_stats_replace(struct net *net, - struct nft_base_chain *chain, - struct nft_stats __percpu *newstats) +static void nft_chain_stats_replace(struct nft_trans *trans) { - struct nft_stats __percpu *oldstats; + struct nft_base_chain *chain = nft_base_chain(trans->ctx.chain); - if (newstats == NULL) + if (!nft_trans_chain_stats(trans)) return; - if (rcu_access_pointer(chain->stats)) { - oldstats = rcu_dereference_protected(chain->stats, - lockdep_commit_lock_is_held(net)); - rcu_assign_pointer(chain->stats, newstats); - synchronize_rcu(); - free_percpu(oldstats); - } else { - rcu_assign_pointer(chain->stats, newstats); + rcu_swap_protected(chain->stats, nft_trans_chain_stats(trans), + lockdep_commit_lock_is_held(trans->ctx.net)); + + if (!nft_trans_chain_stats(trans)) static_branch_inc(&nft_counters_enabled); - } } static void nf_tables_chain_free_chain_rules(struct nft_chain *chain) @@ -6360,9 +6353,9 @@ static void nft_chain_commit_update(struct nft_trans *trans) if (!nft_is_base_chain(trans->ctx.chain)) return; + nft_chain_stats_replace(trans); + basechain = nft_base_chain(trans->ctx.chain); - nft_chain_stats_replace(trans->ctx.net, basechain, - nft_trans_chain_stats(trans)); switch (nft_trans_chain_policy(trans)) { case NF_DROP: @@ -6379,6 +6372,7 @@ static void nft_commit_release(struct nft_trans *trans) nf_tables_table_destroy(&trans->ctx); break; case NFT_MSG_NEWCHAIN: + free_percpu(nft_trans_chain_stats(trans)); kfree(nft_trans_chain_name(trans)); break; case NFT_MSG_DELCHAIN: From c1a8311679014a79b04c039e32bde34fb68952fd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 May 2019 15:44:05 +0200 Subject: [PATCH 07/15] netfilter: bridge: convert skb_make_writable to skb_ensure_writable Back in the day, skb_ensure_writable did not exist. By now, both functions have the same precondition: I. skb_make_writable will test in this order: 1. wlen > skb->len -> error 2. if not cloned and wlen <= headlen -> OK 3. If cloned and wlen bytes of clone writeable -> OK After those checks, skb is either not cloned but needs to pull from nonlinear area, or writing to head would also alter data of another clone. In both cases skb_make_writable will then call __pskb_pull_tail, which will kmalloc a new memory area to use for skb->head. IOW, after successful skb_make_writable call, the requested length is in linear area and can be modified, even if skb was cloned. II. skb_ensure_writable will do this instead: 1. call pskb_may_pull. This handles case 1 above. After this, wlen is in linear area, but skb might be cloned. 2. return if skb is not cloned 3. return if wlen byte of clone are writeable. 4. fully copy the skb. So post-conditions are the same: *len bytes are writeable in linear area without altering any payload data of a clone, all header pointers might have been changed. Only differences are that skb_ensure_writable is in the core, whereas skb_make_writable lives in netfilter core and the inverted return value. skb_make_writable returns 0 on error, whereas skb_ensure_writable returns negative value. For the normal cases performance is similar: A. skb is not cloned and in linear area: pskb_may_pull is inline helper, so neither function copies. B. skb is cloned, write is in linear area and clone is writeable: both funcions return with step 3. This series removes skb_make_writable from the kernel. While at it, pass the needed value instead, its less confusing that way: There is no special-handling of "0-length" argument in either skb_make_writable or skb_ensure_writable. bridge already makes sure ethernet header is in linear area, only purpose of the make_writable() is is to copy skb->head in case of cloned skbs. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebt_dnat.c | 2 +- net/bridge/netfilter/ebt_redirect.c | 2 +- net/bridge/netfilter/ebt_snat.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index eeae23a73c6a..ed91ea31978a 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -22,7 +22,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) const struct ebt_nat_info *info = par->targinfo; struct net_device *dev; - if (!skb_make_writable(skb, 0)) + if (skb_ensure_writable(skb, ETH_ALEN)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_dest, info->mac); diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 53ef08e6765f..0cad62a4052b 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -21,7 +21,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_redirect_info *info = par->targinfo; - if (!skb_make_writable(skb, 0)) + if (skb_ensure_writable(skb, ETH_ALEN)) return EBT_DROP; if (xt_hooknum(par) != NF_BR_BROUTING) diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index 700d338d5ddb..27443bf229a3 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -22,7 +22,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - if (!skb_make_writable(skb, 0)) + if (skb_ensure_writable(skb, ETH_ALEN * 2)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_source, info->mac); From ec0974df357f94385070c242ee0a280f4e3cc12d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 May 2019 15:44:06 +0200 Subject: [PATCH 08/15] netfilter: ipvs: prefer skb_ensure_writable It does the same thing, use it instead so we can remove skb_make_writable. Signed-off-by: Florian Westphal Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_app.c | 4 ++-- net/netfilter/ipvs/ip_vs_core.c | 4 ++-- net/netfilter/ipvs/ip_vs_ftp.c | 4 ++-- net/netfilter/ipvs/ip_vs_proto_sctp.c | 4 ++-- net/netfilter/ipvs/ip_vs_proto_tcp.c | 4 ++-- net/netfilter/ipvs/ip_vs_proto_udp.c | 4 ++-- net/netfilter/ipvs/ip_vs_xmit.c | 12 ++++++------ 7 files changed, 18 insertions(+), 18 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 7588aeaa605f..ba34ac25ee7b 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -363,7 +363,7 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, struct tcphdr *th; __u32 seq; - if (!skb_make_writable(skb, tcp_offset + sizeof(*th))) + if (skb_ensure_writable(skb, tcp_offset + sizeof(*th))) return 0; th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset); @@ -440,7 +440,7 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, struct tcphdr *th; __u32 seq; - if (!skb_make_writable(skb, tcp_offset + sizeof(*th))) + if (skb_ensure_writable(skb, tcp_offset + sizeof(*th))) return 0; th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index d1d7b2483fd7..90adca9a5510 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -898,7 +898,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol) offset += 2 * sizeof(__u16); - if (!skb_make_writable(skb, offset)) + if (skb_ensure_writable(skb, offset)) goto out; #ifdef CONFIG_IP_VS_IPV6 @@ -1288,7 +1288,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet"); - if (!skb_make_writable(skb, iph->len)) + if (skb_ensure_writable(skb, iph->len)) goto drop; /* mangle the packet */ diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index fe69d46ff779..5cbefa927f09 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -273,7 +273,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; /* Linear packets are much easier to deal with. */ - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return 0; if (cp->app_data == (void *) IP_VS_FTP_PASV) { @@ -439,7 +439,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; /* Linear packets are much easier to deal with. */ - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return 0; data = data_start = ip_vs_ftp_data_ptr(skb, ipvsh); diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index b58ddb7dffd1..a0921adc31a9 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -101,7 +101,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, #endif /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, sctphoff + sizeof(*sctph))) + if (skb_ensure_writable(skb, sctphoff + sizeof(*sctph))) return 0; if (unlikely(cp->app != NULL)) { @@ -148,7 +148,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, #endif /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, sctphoff + sizeof(*sctph))) + if (skb_ensure_writable(skb, sctphoff + sizeof(*sctph))) return 0; if (unlikely(cp->app != NULL)) { diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 00ce07dda980..089ee592a955 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -163,7 +163,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, tcphoff+sizeof(*tcph))) + if (skb_ensure_writable(skb, tcphoff + sizeof(*tcph))) return 0; if (unlikely(cp->app != NULL)) { @@ -241,7 +241,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, tcphoff+sizeof(*tcph))) + if (skb_ensure_writable(skb, tcphoff + sizeof(*tcph))) return 0; if (unlikely(cp->app != NULL)) { diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 92c078abcb3e..de366aa3c03b 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -153,7 +153,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, oldlen = skb->len - udphoff; /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, udphoff+sizeof(*udph))) + if (skb_ensure_writable(skb, udphoff + sizeof(*udph))) return 0; if (unlikely(cp->app != NULL)) { @@ -236,7 +236,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, oldlen = skb->len - udphoff; /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, udphoff+sizeof(*udph))) + if (skb_ensure_writable(skb, udphoff + sizeof(*udph))) return 0; if (unlikely(cp->app != NULL)) { diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 8d6f94b67772..0b41d0504429 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -279,7 +279,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, } /* don't propagate ttl change to cloned packets */ - if (!skb_make_writable(skb, sizeof(struct ipv6hdr))) + if (skb_ensure_writable(skb, sizeof(struct ipv6hdr))) return false; ipv6_hdr(skb)->hop_limit--; @@ -294,7 +294,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, } /* don't propagate ttl change to cloned packets */ - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) return false; /* Decrease ttl */ @@ -796,7 +796,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, } /* copy-on-write the packet before mangling it */ - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) @@ -885,7 +885,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } /* copy-on-write the packet before mangling it */ - if (!skb_make_writable(skb, sizeof(struct ipv6hdr))) + if (skb_ensure_writable(skb, sizeof(struct ipv6hdr))) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) @@ -1404,7 +1404,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, } /* copy-on-write the packet before mangling it */ - if (!skb_make_writable(skb, offset)) + if (skb_ensure_writable(skb, offset)) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) @@ -1493,7 +1493,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } /* copy-on-write the packet before mangling it */ - if (!skb_make_writable(skb, offset)) + if (skb_ensure_writable(skb, offset)) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) From 86f045385462597e96f5481198a6c60d18d109ca Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 May 2019 15:44:07 +0200 Subject: [PATCH 09/15] netfilter: conntrack, nat: prefer skb_ensure_writable like previous patches -- convert conntrack to use the core helper. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_sctp.c | 2 +- net/netfilter/nf_conntrack_seqadj.c | 4 ++-- net/netfilter/nf_nat_helper.c | 4 ++-- net/netfilter/nf_nat_proto.c | 24 ++++++++++++------------ 4 files changed, 17 insertions(+), 17 deletions(-) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 5b8dde266412..07c5208a4ea0 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -339,7 +339,7 @@ static bool sctp_error(struct sk_buff *skb, if (state->hook == NF_INET_PRE_ROUTING && state->net->ct.sysctl_checksum && skb->ip_summed == CHECKSUM_NONE) { - if (!skb_make_writable(skb, dataoff + sizeof(struct sctphdr))) { + if (skb_ensure_writable(skb, dataoff + sizeof(*sh))) { logmsg = "nf_ct_sctp: failed to read header "; goto out_invalid; } diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index dc21a43cd145..3066449f8bd8 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -126,7 +126,7 @@ static unsigned int nf_ct_sack_adjust(struct sk_buff *skb, optoff = protoff + sizeof(struct tcphdr); optend = protoff + tcph->doff * 4; - if (!skb_make_writable(skb, optend)) + if (skb_ensure_writable(skb, optend)) return 0; tcph = (void *)skb->data + protoff; @@ -176,7 +176,7 @@ int nf_ct_seq_adjust(struct sk_buff *skb, this_way = &seqadj->seq[dir]; other_way = &seqadj->seq[!dir]; - if (!skb_make_writable(skb, protoff + sizeof(*tcph))) + if (skb_ensure_writable(skb, protoff + sizeof(*tcph))) return 0; tcph = (void *)skb->data + protoff; diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index ccc06f7539d7..03e8e2d79375 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -98,7 +98,7 @@ bool __nf_nat_mangle_tcp_packet(struct sk_buff *skb, struct tcphdr *tcph; int oldlen, datalen; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return false; if (rep_len > match_len && @@ -148,7 +148,7 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, struct udphdr *udph; int datalen, oldlen; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return false; if (rep_len > match_len && diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 84f5c90a7f21..04a6c1ac2526 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -73,7 +73,7 @@ static bool udp_manip_pkt(struct sk_buff *skb, struct udphdr *hdr; bool do_csum; - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); @@ -91,7 +91,7 @@ static bool udplite_manip_pkt(struct sk_buff *skb, #ifdef CONFIG_NF_CT_PROTO_UDPLITE struct udphdr *hdr; - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); @@ -117,7 +117,7 @@ sctp_manip_pkt(struct sk_buff *skb, if (skb->len >= hdroff + sizeof(*hdr)) hdrsize = sizeof(*hdr); - if (!skb_make_writable(skb, hdroff + hdrsize)) + if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct sctphdr *)(skb->data + hdroff); @@ -158,7 +158,7 @@ tcp_manip_pkt(struct sk_buff *skb, if (skb->len >= hdroff + sizeof(struct tcphdr)) hdrsize = sizeof(struct tcphdr); - if (!skb_make_writable(skb, hdroff + hdrsize)) + if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct tcphdr *)(skb->data + hdroff); @@ -198,7 +198,7 @@ dccp_manip_pkt(struct sk_buff *skb, if (skb->len >= hdroff + sizeof(struct dccp_hdr)) hdrsize = sizeof(struct dccp_hdr); - if (!skb_make_writable(skb, hdroff + hdrsize)) + if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct dccp_hdr *)(skb->data + hdroff); @@ -232,7 +232,7 @@ icmp_manip_pkt(struct sk_buff *skb, { struct icmphdr *hdr; - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmphdr *)(skb->data + hdroff); @@ -250,7 +250,7 @@ icmpv6_manip_pkt(struct sk_buff *skb, { struct icmp6hdr *hdr; - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmp6hdr *)(skb->data + hdroff); @@ -278,7 +278,7 @@ gre_manip_pkt(struct sk_buff *skb, /* pgreh includes two optional 32bit fields which are not required * to be there. That's where the magic '8' comes from */ - if (!skb_make_writable(skb, hdroff + sizeof(*pgreh) - 8)) + if (skb_ensure_writable(skb, hdroff + sizeof(*pgreh) - 8)) return false; greh = (void *)skb->data + hdroff; @@ -350,7 +350,7 @@ static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb, struct iphdr *iph; unsigned int hdroff; - if (!skb_make_writable(skb, iphdroff + sizeof(*iph))) + if (skb_ensure_writable(skb, iphdroff + sizeof(*iph))) return false; iph = (void *)skb->data + iphdroff; @@ -381,7 +381,7 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, int hdroff; u8 nexthdr; - if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h))) + if (skb_ensure_writable(skb, iphdroff + sizeof(*ipv6h))) return false; ipv6h = (void *)skb->data + iphdroff; @@ -565,7 +565,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); - if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) + if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip_checksum(skb, hooknum, hdrlen, 0)) return 0; @@ -787,7 +787,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); - if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) + if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) return 0; From 3862c6a91a431337ead5685d647b83f5a82f7705 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 May 2019 15:44:08 +0200 Subject: [PATCH 10/15] netfilter: ipv4: prefer skb_ensure_writable .. so skb_make_writable can be removed soon. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/arpt_mangle.c | 2 +- net/ipv4/netfilter/ipt_ECN.c | 4 ++-- net/ipv4/netfilter/nf_nat_h323.c | 2 +- net/ipv4/netfilter/nf_nat_snmp_basic_main.c | 2 +- net/netfilter/nf_nat_sip.c | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index 87ca2c42359b..a4e07e5e9c11 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -17,7 +17,7 @@ target(struct sk_buff *skb, const struct xt_action_param *par) unsigned char *arpptr; int pln, hln; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return NF_DROP; arp = arp_hdr(skb); diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index aaaf9a81fbc9..9f6751893660 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -32,7 +32,7 @@ set_ect_ip(struct sk_buff *skb, const struct ipt_ECN_info *einfo) if ((iph->tos & IPT_ECN_IP_MASK) != (einfo->ip_ect & IPT_ECN_IP_MASK)) { __u8 oldtos; - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) return false; iph = ip_hdr(skb); oldtos = iph->tos; @@ -61,7 +61,7 @@ set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo) tcph->cwr == einfo->proto.tcp.cwr)) return true; - if (!skb_make_writable(skb, ip_hdrlen(skb) + sizeof(*tcph))) + if (skb_ensure_writable(skb, ip_hdrlen(skb) + sizeof(*tcph))) return false; tcph = (void *)ip_hdr(skb) + ip_hdrlen(skb); diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 7875c98072eb..15f2b2604890 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -59,7 +59,7 @@ static int set_addr(struct sk_buff *skb, unsigned int protoff, net_notice_ratelimited("nf_nat_h323: nf_nat_mangle_udp_packet error\n"); return -1; } - /* nf_nat_mangle_udp_packet uses skb_make_writable() to copy + /* nf_nat_mangle_udp_packet uses skb_ensure_writable() to copy * or pull everything in a linear buffer, so we can safely * use the skb pointers now */ *data = skb->data + ip_hdrlen(skb) + sizeof(struct udphdr); diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c index 657d2dcec3cc..717b726504fe 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c @@ -186,7 +186,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } - if (!skb_make_writable(skb, skb->len)) { + if (skb_ensure_writable(skb, skb->len)) { nf_ct_helper_log(skb, ct, "cannot mangle packet"); return NF_DROP; } diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index 464387b3600f..07805bf4d62a 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -285,7 +285,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, if (dir == IP_CT_DIR_REPLY && ct_sip_info->forced_dport) { struct udphdr *uh; - if (!skb_make_writable(skb, skb->len)) { + if (skb_ensure_writable(skb, skb->len)) { nf_ct_helper_log(skb, ct, "cannot mangle packet"); return NF_DROP; } From 7418ee4c8810e4ad74fb05a8b8d4cf406738ac81 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 May 2019 15:44:09 +0200 Subject: [PATCH 11/15] netfilter: nf_tables: prefer skb_ensure_writable .. so skb_make_writable can be removed. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_exthdr.c | 3 ++- net/netfilter/nft_payload.c | 6 +++--- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a940c9fd9045..45c8a6c07783 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -156,7 +156,8 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, if (i + optl > tcphdr_len || priv->len + priv->offset > optl) return; - if (!skb_make_writable(pkt->skb, pkt->xt.thoff + i + priv->len)) + if (skb_ensure_writable(pkt->skb, + pkt->xt.thoff + i + priv->len)) return; tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 54e15de4b79a..1465b7d6d2b0 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -243,7 +243,7 @@ static int nft_payload_l4csum_update(const struct nft_pktinfo *pkt, tsum)); } - if (!skb_make_writable(skb, l4csum_offset + sizeof(sum)) || + if (skb_ensure_writable(skb, l4csum_offset + sizeof(sum)) || skb_store_bits(skb, l4csum_offset, &sum, sizeof(sum)) < 0) return -1; @@ -259,7 +259,7 @@ static int nft_payload_csum_inet(struct sk_buff *skb, const u32 *src, return -1; nft_csum_replace(&sum, fsum, tsum); - if (!skb_make_writable(skb, csum_offset + sizeof(sum)) || + if (skb_ensure_writable(skb, csum_offset + sizeof(sum)) || skb_store_bits(skb, csum_offset, &sum, sizeof(sum)) < 0) return -1; @@ -312,7 +312,7 @@ static void nft_payload_set_eval(const struct nft_expr *expr, goto err; } - if (!skb_make_writable(skb, max(offset + priv->len, 0)) || + if (skb_ensure_writable(skb, max(offset + priv->len, 0)) || skb_store_bits(skb, offset, src, priv->len) < 0) goto err; From 8e03707f118cd2f8dc993b01dd15e78da147a29e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 May 2019 15:44:10 +0200 Subject: [PATCH 12/15] netfilter: xt_HL: prefer skb_ensure_writable Also, make the argument to be only the needed size of the header we're altering, no need to pull in the full packet into linear area. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_HL.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/xt_HL.c b/net/netfilter/xt_HL.c index 4653b071bed4..a37b8824221f 100644 --- a/net/netfilter/xt_HL.c +++ b/net/netfilter/xt_HL.c @@ -32,7 +32,7 @@ ttl_tg(struct sk_buff *skb, const struct xt_action_param *par) const struct ipt_TTL_info *info = par->targinfo; int new_ttl; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, sizeof(*iph))) return NF_DROP; iph = ip_hdr(skb); @@ -72,7 +72,7 @@ hl_tg6(struct sk_buff *skb, const struct xt_action_param *par) const struct ip6t_HL_info *info = par->targinfo; int new_hl; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, sizeof(*ip6h))) return NF_DROP; ip6h = ipv6_hdr(skb); From fb2eb1c131f8526905a83bd98fd2d4e7c9f950a0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 May 2019 15:44:11 +0200 Subject: [PATCH 13/15] netfilter: tcpmss, optstrip: prefer skb_ensure_writable This also changes optstrip to only make the tcp header writeable rather than the entire packet. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_TCPMSS.c | 2 +- net/netfilter/xt_TCPOPTSTRIP.c | 30 ++++++++++++++---------------- 2 files changed, 15 insertions(+), 17 deletions(-) diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 98efb202f8b4..3e24443ab81c 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -89,7 +89,7 @@ tcpmss_mangle_packet(struct sk_buff *skb, if (par->fragoff != 0) return 0; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return -1; len = skb->len - tcphoff; diff --git a/net/netfilter/xt_TCPOPTSTRIP.c b/net/netfilter/xt_TCPOPTSTRIP.c index eb92bffff11c..5a274813076a 100644 --- a/net/netfilter/xt_TCPOPTSTRIP.c +++ b/net/netfilter/xt_TCPOPTSTRIP.c @@ -31,33 +31,33 @@ static inline unsigned int optlen(const u_int8_t *opt, unsigned int offset) static unsigned int tcpoptstrip_mangle_packet(struct sk_buff *skb, const struct xt_action_param *par, - unsigned int tcphoff, unsigned int minlen) + unsigned int tcphoff) { const struct xt_tcpoptstrip_target_info *info = par->targinfo; + struct tcphdr *tcph, _th; unsigned int optl, i, j; - struct tcphdr *tcph; u_int16_t n, o; u_int8_t *opt; - int len, tcp_hdrlen; + int tcp_hdrlen; /* This is a fragment, no TCP header is available */ if (par->fragoff != 0) return XT_CONTINUE; - if (!skb_make_writable(skb, skb->len)) + tcph = skb_header_pointer(skb, tcphoff, sizeof(_th), &_th); + if (!tcph) return NF_DROP; - len = skb->len - tcphoff; - if (len < (int)sizeof(struct tcphdr)) - return NF_DROP; - - tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); tcp_hdrlen = tcph->doff * 4; - - if (len < tcp_hdrlen) + if (tcp_hdrlen < sizeof(struct tcphdr)) return NF_DROP; - opt = (u_int8_t *)tcph; + if (skb_ensure_writable(skb, tcphoff + tcp_hdrlen)) + return NF_DROP; + + /* must reload tcph, might have been moved */ + tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); + opt = (u8 *)tcph; /* * Walk through all TCP options - if we find some option to remove, @@ -91,8 +91,7 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, static unsigned int tcpoptstrip_tg4(struct sk_buff *skb, const struct xt_action_param *par) { - return tcpoptstrip_mangle_packet(skb, par, ip_hdrlen(skb), - sizeof(struct iphdr) + sizeof(struct tcphdr)); + return tcpoptstrip_mangle_packet(skb, par, ip_hdrlen(skb)); } #if IS_ENABLED(CONFIG_IP6_NF_MANGLE) @@ -109,8 +108,7 @@ tcpoptstrip_tg6(struct sk_buff *skb, const struct xt_action_param *par) if (tcphoff < 0) return NF_DROP; - return tcpoptstrip_mangle_packet(skb, par, tcphoff, - sizeof(*ipv6h) + sizeof(struct tcphdr)); + return tcpoptstrip_mangle_packet(skb, par, tcphoff); } #endif From 2cf6bffc49dae26edd12af6b57c8c780590380bf Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 May 2019 15:44:12 +0200 Subject: [PATCH 14/15] netfilter: replace skb_make_writable with skb_ensure_writable This converts all remaining users and then removes skb_make_writable. Suggested-by: Daniel Borkmann Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 5 ----- net/netfilter/core.c | 22 ---------------------- net/netfilter/nf_synproxy_core.c | 2 +- net/netfilter/nfnetlink_queue.c | 2 +- net/netfilter/xt_DSCP.c | 8 ++++---- 5 files changed, 6 insertions(+), 33 deletions(-) diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 996bc247ef6e..049aeb40fa35 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -336,11 +336,6 @@ int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); #endif -/* Call this before modifying an existing packet: ensures it is - modifiable and linear to the point you care about (writable_len). - Returns true or false. */ -int skb_make_writable(struct sk_buff *skb, unsigned int writable_len); - struct flowi; struct nf_queue_entry; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index b96fd3f54705..817a9e5d16e4 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -536,28 +536,6 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, } EXPORT_SYMBOL(nf_hook_slow); - -int skb_make_writable(struct sk_buff *skb, unsigned int writable_len) -{ - if (writable_len > skb->len) - return 0; - - /* Not exclusive use of packet? Must copy. */ - if (!skb_cloned(skb)) { - if (writable_len <= skb_headlen(skb)) - return 1; - } else if (skb_clone_writable(skb, writable_len)) - return 1; - - if (writable_len <= skb_headlen(skb)) - writable_len = 0; - else - writable_len -= skb_headlen(skb); - - return !!__pskb_pull_tail(skb, writable_len); -} -EXPORT_SYMBOL(skb_make_writable); - /* This needs to be compiled in any case to avoid dependencies between the * nfnetlink_queue code and nf_conntrack. */ diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 8ff4d22f10b2..3d58a9e93e5a 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -196,7 +196,7 @@ unsigned int synproxy_tstamp_adjust(struct sk_buff *skb, optoff = protoff + sizeof(struct tcphdr); optend = protoff + th->doff * 4; - if (!skb_make_writable(skb, optend)) + if (skb_ensure_writable(skb, optend)) return 0; while (optoff < optend) { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 27dac47b29c2..831f57008d78 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -863,7 +863,7 @@ nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff) } skb_put(e->skb, diff); } - if (!skb_make_writable(e->skb, data_len)) + if (skb_ensure_writable(e->skb, data_len)) return -ENOMEM; skb_copy_to_linear_data(e->skb, data, data_len); e->skb->ip_summed = CHECKSUM_NONE; diff --git a/net/netfilter/xt_DSCP.c b/net/netfilter/xt_DSCP.c index 098ed851b7a7..30d554d6c213 100644 --- a/net/netfilter/xt_DSCP.c +++ b/net/netfilter/xt_DSCP.c @@ -34,7 +34,7 @@ dscp_tg(struct sk_buff *skb, const struct xt_action_param *par) u_int8_t dscp = ipv4_get_dsfield(ip_hdr(skb)) >> XT_DSCP_SHIFT; if (dscp != dinfo->dscp) { - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) return NF_DROP; ipv4_change_dsfield(ip_hdr(skb), @@ -52,7 +52,7 @@ dscp_tg6(struct sk_buff *skb, const struct xt_action_param *par) u_int8_t dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> XT_DSCP_SHIFT; if (dscp != dinfo->dscp) { - if (!skb_make_writable(skb, sizeof(struct ipv6hdr))) + if (skb_ensure_writable(skb, sizeof(struct ipv6hdr))) return NF_DROP; ipv6_change_dsfield(ipv6_hdr(skb), @@ -82,7 +82,7 @@ tos_tg(struct sk_buff *skb, const struct xt_action_param *par) nv = (orig & ~info->tos_mask) ^ info->tos_value; if (orig != nv) { - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) return NF_DROP; iph = ip_hdr(skb); ipv4_change_dsfield(iph, 0, nv); @@ -102,7 +102,7 @@ tos_tg6(struct sk_buff *skb, const struct xt_action_param *par) nv = (orig & ~info->tos_mask) ^ info->tos_value; if (orig != nv) { - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) return NF_DROP; iph = ipv6_hdr(skb); ipv6_change_dsfield(iph, 0, nv); From 29930e314da3833437a2ddc7b17f6a954f38d8fb Mon Sep 17 00:00:00 2001 From: Jacky Hu Date: Thu, 30 May 2019 08:16:40 +0800 Subject: [PATCH 15/15] ipvs: add checksum support for gue encapsulation Add checksum support for gue encapsulation with the tun_flags parameter, which could be one of the values below: IP_VS_TUNNEL_ENCAP_FLAG_NOCSUM IP_VS_TUNNEL_ENCAP_FLAG_CSUM IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM Signed-off-by: Jacky Hu Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 2 + include/uapi/linux/ip_vs.h | 7 ++ net/netfilter/ipvs/ip_vs_ctl.c | 11 ++- net/netfilter/ipvs/ip_vs_xmit.c | 143 ++++++++++++++++++++++++++++---- 4 files changed, 146 insertions(+), 17 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b01a94ebfc0e..cb1ad0cc5c7b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -603,6 +603,7 @@ struct ip_vs_dest_user_kern { u16 tun_type; /* tunnel type */ __be16 tun_port; /* tunnel port */ + u16 tun_flags; /* tunnel flags */ }; @@ -665,6 +666,7 @@ struct ip_vs_dest { atomic_t last_weight; /* server latest weight */ __u16 tun_type; /* tunnel type */ __be16 tun_port; /* tunnel port */ + __u16 tun_flags; /* tunnel flags */ refcount_t refcnt; /* reference counter */ struct ip_vs_stats stats; /* statistics */ diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index e34f436fc79d..e4f18061a4fd 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -131,6 +131,11 @@ enum { IP_VS_CONN_F_TUNNEL_TYPE_MAX, }; +/* Tunnel encapsulation flags */ +#define IP_VS_TUNNEL_ENCAP_FLAG_NOCSUM (0) +#define IP_VS_TUNNEL_ENCAP_FLAG_CSUM (1 << 0) +#define IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM (1 << 1) + /* * The struct ip_vs_service_user and struct ip_vs_dest_user are * used to set IPVS rules through setsockopt. @@ -403,6 +408,8 @@ enum { IPVS_DEST_ATTR_TUN_PORT, /* tunnel port */ + IPVS_DEST_ATTR_TUN_FLAGS, /* tunnel flags */ + __IPVS_DEST_ATTR_MAX, }; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index d5847e06350f..ad19ac08622f 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -893,6 +893,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, /* set the tunnel info */ dest->tun_type = udest->tun_type; dest->tun_port = udest->tun_port; + dest->tun_flags = udest->tun_flags; /* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */ if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) { @@ -2967,6 +2968,7 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = { [IPVS_DEST_ATTR_ADDR_FAMILY] = { .type = NLA_U16 }, [IPVS_DEST_ATTR_TUN_TYPE] = { .type = NLA_U8 }, [IPVS_DEST_ATTR_TUN_PORT] = { .type = NLA_U16 }, + [IPVS_DEST_ATTR_TUN_FLAGS] = { .type = NLA_U16 }, }; static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type, @@ -3273,6 +3275,8 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest) dest->tun_type) || nla_put_be16(skb, IPVS_DEST_ATTR_TUN_PORT, dest->tun_port) || + nla_put_u16(skb, IPVS_DEST_ATTR_TUN_FLAGS, + dest->tun_flags) || nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) || nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) || nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS, @@ -3393,7 +3397,8 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, /* If a full entry was requested, check for the additional fields */ if (full_entry) { struct nlattr *nla_fwd, *nla_weight, *nla_u_thresh, - *nla_l_thresh, *nla_tun_type, *nla_tun_port; + *nla_l_thresh, *nla_tun_type, *nla_tun_port, + *nla_tun_flags; nla_fwd = attrs[IPVS_DEST_ATTR_FWD_METHOD]; nla_weight = attrs[IPVS_DEST_ATTR_WEIGHT]; @@ -3401,6 +3406,7 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, nla_l_thresh = attrs[IPVS_DEST_ATTR_L_THRESH]; nla_tun_type = attrs[IPVS_DEST_ATTR_TUN_TYPE]; nla_tun_port = attrs[IPVS_DEST_ATTR_TUN_PORT]; + nla_tun_flags = attrs[IPVS_DEST_ATTR_TUN_FLAGS]; if (!(nla_fwd && nla_weight && nla_u_thresh && nla_l_thresh)) return -EINVAL; @@ -3416,6 +3422,9 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, if (nla_tun_port) udest->tun_port = nla_get_be16(nla_tun_port); + + if (nla_tun_flags) + udest->tun_flags = nla_get_u16(nla_tun_flags); } return 0; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 0b41d0504429..af3379d5e5bc 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include #include @@ -385,8 +386,13 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (!dest) goto err_put; - if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) + if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { mtu -= sizeof(struct udphdr) + sizeof(struct guehdr); + if ((dest->tun_flags & + IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) + mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV; + } if (mtu < 68) { IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__); goto err_put; @@ -540,8 +546,13 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr); if (!dest) goto err_put; - if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) + if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { mtu -= sizeof(struct udphdr) + sizeof(struct guehdr); + if ((dest->tun_flags & + IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) + mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV; + } if (mtu < IPV6_MIN_MTU) { IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__, IPV6_MIN_MTU); @@ -1006,17 +1017,56 @@ ipvs_gue_encap(struct net *net, struct sk_buff *skb, __be16 sport = udp_flow_src_port(net, skb, 0, 0, false); struct udphdr *udph; /* Our new UDP header */ struct guehdr *gueh; /* Our new GUE header */ + size_t hdrlen, optlen = 0; + void *data; + bool need_priv = false; - skb_push(skb, sizeof(struct guehdr)); + if ((cp->dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) { + optlen += GUE_PLEN_REMCSUM + GUE_LEN_PRIV; + need_priv = true; + } + + hdrlen = sizeof(struct guehdr) + optlen; + + skb_push(skb, hdrlen); gueh = (struct guehdr *)skb->data; gueh->control = 0; gueh->version = 0; - gueh->hlen = 0; + gueh->hlen = optlen >> 2; gueh->flags = 0; gueh->proto_ctype = *next_protocol; + data = &gueh[1]; + + if (need_priv) { + __be32 *flags = data; + u16 csum_start = skb_checksum_start_offset(skb); + __be16 *pd; + + gueh->flags |= GUE_FLAG_PRIV; + *flags = 0; + data += GUE_LEN_PRIV; + + if (csum_start < hdrlen) + return -EINVAL; + + csum_start -= hdrlen; + pd = data; + pd[0] = htons(csum_start); + pd[1] = htons(csum_start + skb->csum_offset); + + if (!skb_is_gso(skb)) { + skb->ip_summed = CHECKSUM_NONE; + skb->encapsulation = 0; + } + + *flags |= GUE_PFLAG_REMCSUM; + data += GUE_PLEN_REMCSUM; + } + skb_push(skb, sizeof(struct udphdr)); skb_reset_transport_header(skb); @@ -1070,6 +1120,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, unsigned int max_headroom; /* The extra header space needed */ int ret, local; int tun_type, gso_type; + int tun_flags; EnterFunction(10); @@ -1092,9 +1143,19 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr); tun_type = cp->dest->tun_type; + tun_flags = cp->dest->tun_flags; - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr); + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + size_t gue_hdrlen, gue_optlen = 0; + + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) { + gue_optlen += GUE_PLEN_REMCSUM + GUE_LEN_PRIV; + } + gue_hdrlen = sizeof(struct guehdr) + gue_optlen; + + max_headroom += sizeof(struct udphdr) + gue_hdrlen; + } /* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */ dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL; @@ -1105,8 +1166,17 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; gso_type = __tun_gso_type_mask(AF_INET, cp->af); - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - gso_type |= SKB_GSO_UDP_TUNNEL; + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) || + (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM)) + gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; + else + gso_type |= SKB_GSO_UDP_TUNNEL; + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) { + gso_type |= SKB_GSO_TUNNEL_REMCSUM; + } + } if (iptunnel_handle_offloads(skb, gso_type)) goto tx_error; @@ -1115,8 +1185,19 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, skb_set_inner_ipproto(skb, next_protocol); - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - ipvs_gue_encap(net, skb, cp, &next_protocol); + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + bool check = false; + + if (ipvs_gue_encap(net, skb, cp, &next_protocol)) + goto tx_error; + + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) || + (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM)) + check = true; + + udp_set_csum(!check, skb, saddr, cp->daddr.ip, skb->len); + } + skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); @@ -1174,6 +1255,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, unsigned int max_headroom; /* The extra header space needed */ int ret, local; int tun_type, gso_type; + int tun_flags; EnterFunction(10); @@ -1197,9 +1279,19 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr); tun_type = cp->dest->tun_type; + tun_flags = cp->dest->tun_flags; - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr); + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + size_t gue_hdrlen, gue_optlen = 0; + + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) { + gue_optlen += GUE_PLEN_REMCSUM + GUE_LEN_PRIV; + } + gue_hdrlen = sizeof(struct guehdr) + gue_optlen; + + max_headroom += sizeof(struct udphdr) + gue_hdrlen; + } skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom, &next_protocol, &payload_len, @@ -1208,8 +1300,17 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; gso_type = __tun_gso_type_mask(AF_INET6, cp->af); - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - gso_type |= SKB_GSO_UDP_TUNNEL; + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) || + (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM)) + gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; + else + gso_type |= SKB_GSO_UDP_TUNNEL; + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) { + gso_type |= SKB_GSO_TUNNEL_REMCSUM; + } + } if (iptunnel_handle_offloads(skb, gso_type)) goto tx_error; @@ -1218,8 +1319,18 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, skb_set_inner_ipproto(skb, next_protocol); - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - ipvs_gue_encap(net, skb, cp, &next_protocol); + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + bool check = false; + + if (ipvs_gue_encap(net, skb, cp, &next_protocol)) + goto tx_error; + + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) || + (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM)) + check = true; + + udp6_set_csum(!check, skb, &saddr, &cp->daddr.in6, skb->len); + } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb);