diff options
Diffstat (limited to 'net/ipv4')
79 files changed, 2180 insertions, 1446 deletions
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index f8c49ce5b28..f032688d20d 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -55,4 +55,4 @@ obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ - xfrm4_output.o + xfrm4_output.o xfrm4_protocol.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ecd2c3f245c..d156b3c5f36 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -254,7 +254,6 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, struct inet_sock *inet; struct proto *answer_prot; unsigned char answer_flags; - char answer_no_check; int try_loading_module = 0; int err; @@ -312,7 +311,6 @@ lookup_protocol: sock->ops = answer->ops; answer_prot = answer->prot; - answer_no_check = answer->no_check; answer_flags = answer->flags; rcu_read_unlock(); @@ -324,7 +322,6 @@ lookup_protocol: goto out; err = 0; - sk->sk_no_check = answer_no_check; if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; @@ -1002,7 +999,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_TCP, .prot = &tcp_prot, .ops = &inet_stream_ops, - .no_check = 0, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }, @@ -1012,7 +1008,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_UDP, .prot = &udp_prot, .ops = &inet_dgram_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_PERMANENT, }, @@ -1021,7 +1016,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_ICMP, .prot = &ping_prot, .ops = &inet_dgram_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, }, @@ -1030,7 +1024,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_IP, /* wild card */ .prot = &raw_prot, .ops = &inet_sockraw_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, } }; @@ -1261,10 +1254,12 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_GRE | + SKB_GSO_GRE_CSUM | SKB_GSO_IPIP | SKB_GSO_SIT | SKB_GSO_TCPV6 | SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM | SKB_GSO_MPLS | 0))) goto out; @@ -1296,8 +1291,11 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); - /* Note : following gso_segment() might change skb->encapsulation */ - udpfrag = !skb->encapsulation && proto == IPPROTO_UDP; + if (skb->encapsulation && + skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP)) + udpfrag = proto == IPPROTO_UDP && encap; + else + udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) @@ -1431,6 +1429,9 @@ static int inet_gro_complete(struct sk_buff *skb, int nhoff) int proto = iph->protocol; int err = -ENOSYS; + if (skb->encapsulation) + skb_set_inner_network_header(skb, nhoff); + csum_replace2(&iph->check, iph->tot_len, newlen); iph->tot_len = newlen; @@ -1473,22 +1474,20 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family, } EXPORT_SYMBOL_GPL(inet_ctl_sock_create); -unsigned long snmp_fold_field(void __percpu *mib[], int offt) +unsigned long snmp_fold_field(void __percpu *mib, int offt) { unsigned long res = 0; - int i, j; + int i; - for_each_possible_cpu(i) { - for (j = 0; j < SNMP_ARRAY_SZ; j++) - res += *(((unsigned long *) per_cpu_ptr(mib[j], i)) + offt); - } + for_each_possible_cpu(i) + res += *(((unsigned long *) per_cpu_ptr(mib, i)) + offt); return res; } EXPORT_SYMBOL_GPL(snmp_fold_field); #if BITS_PER_LONG==32 -u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset) +u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_offset) { u64 res = 0; int cpu; @@ -1499,12 +1498,12 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset) u64 v; unsigned int start; - bhptr = per_cpu_ptr(mib[0], cpu); + bhptr = per_cpu_ptr(mib, cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { - start = u64_stats_fetch_begin_bh(syncp); + start = u64_stats_fetch_begin_irq(syncp); v = *(((u64 *) bhptr) + offt); - } while (u64_stats_fetch_retry_bh(syncp, start)); + } while (u64_stats_fetch_retry_irq(syncp, start)); res += v; } @@ -1513,25 +1512,6 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset) EXPORT_SYMBOL_GPL(snmp_fold_field64); #endif -int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align) -{ - BUG_ON(ptr == NULL); - ptr[0] = __alloc_percpu(mibsize, align); - if (!ptr[0]) - return -ENOMEM; - -#if SNMP_ARRAY_SZ == 2 - ptr[1] = __alloc_percpu(mibsize, align); - if (!ptr[1]) { - free_percpu(ptr[0]); - ptr[0] = NULL; - return -ENOMEM; - } -#endif - return 0; -} -EXPORT_SYMBOL_GPL(snmp_mib_init); - #ifdef CONFIG_IP_MULTICAST static const struct net_protocol igmp_protocol = { .handler = igmp_rcv, @@ -1567,40 +1547,30 @@ static __net_init int ipv4_mib_init_net(struct net *net) { int i; - if (snmp_mib_init((void __percpu **)net->mib.tcp_statistics, - sizeof(struct tcp_mib), - __alignof__(struct tcp_mib)) < 0) + net->mib.tcp_statistics = alloc_percpu(struct tcp_mib); + if (!net->mib.tcp_statistics) goto err_tcp_mib; - if (snmp_mib_init((void __percpu **)net->mib.ip_statistics, - sizeof(struct ipstats_mib), - __alignof__(struct ipstats_mib)) < 0) + net->mib.ip_statistics = alloc_percpu(struct ipstats_mib); + if (!net->mib.ip_statistics) goto err_ip_mib; for_each_possible_cpu(i) { struct ipstats_mib *af_inet_stats; - af_inet_stats = per_cpu_ptr(net->mib.ip_statistics[0], i); + af_inet_stats = per_cpu_ptr(net->mib.ip_statistics, i); u64_stats_init(&af_inet_stats->syncp); -#if SNMP_ARRAY_SZ == 2 - af_inet_stats = per_cpu_ptr(net->mib.ip_statistics[1], i); - u64_stats_init(&af_inet_stats->syncp); -#endif } - if (snmp_mib_init((void __percpu **)net->mib.net_statistics, - sizeof(struct linux_mib), - __alignof__(struct linux_mib)) < 0) + net->mib.net_statistics = alloc_percpu(struct linux_mib); + if (!net->mib.net_statistics) goto err_net_mib; - if (snmp_mib_init((void __percpu **)net->mib.udp_statistics, - sizeof(struct udp_mib), - __alignof__(struct udp_mib)) < 0) + net->mib.udp_statistics = alloc_percpu(struct udp_mib); + if (!net->mib.udp_statistics) goto err_udp_mib; - if (snmp_mib_init((void __percpu **)net->mib.udplite_statistics, - sizeof(struct udp_mib), - __alignof__(struct udp_mib)) < 0) + net->mib.udplite_statistics = alloc_percpu(struct udp_mib); + if (!net->mib.udplite_statistics) goto err_udplite_mib; - if (snmp_mib_init((void __percpu **)net->mib.icmp_statistics, - sizeof(struct icmp_mib), - __alignof__(struct icmp_mib)) < 0) + net->mib.icmp_statistics = alloc_percpu(struct icmp_mib); + if (!net->mib.icmp_statistics) goto err_icmp_mib; net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib), GFP_KERNEL); @@ -1611,17 +1581,17 @@ static __net_init int ipv4_mib_init_net(struct net *net) return 0; err_icmpmsg_mib: - snmp_mib_free((void __percpu **)net->mib.icmp_statistics); + free_percpu(net->mib.icmp_statistics); err_icmp_mib: - snmp_mib_free((void __percpu **)net->mib.udplite_statistics); + free_percpu(net->mib.udplite_statistics); err_udplite_mib: - snmp_mib_free((void __percpu **)net->mib.udp_statistics); + free_percpu(net->mib.udp_statistics); err_udp_mib: - snmp_mib_free((void __percpu **)net->mib.net_statistics); + free_percpu(net->mib.net_statistics); err_net_mib: - snmp_mib_free((void __percpu **)net->mib.ip_statistics); + free_percpu(net->mib.ip_statistics); err_ip_mib: - snmp_mib_free((void __percpu **)net->mib.tcp_statistics); + free_percpu(net->mib.tcp_statistics); err_tcp_mib: return -ENOMEM; } @@ -1629,12 +1599,12 @@ err_tcp_mib: static __net_exit void ipv4_mib_exit_net(struct net *net) { kfree(net->mib.icmpmsg_statistics); - snmp_mib_free((void __percpu **)net->mib.icmp_statistics); - snmp_mib_free((void __percpu **)net->mib.udplite_statistics); - snmp_mib_free((void __percpu **)net->mib.udp_statistics); - snmp_mib_free((void __percpu **)net->mib.net_statistics); - snmp_mib_free((void __percpu **)net->mib.ip_statistics); - snmp_mib_free((void __percpu **)net->mib.tcp_statistics); + free_percpu(net->mib.icmp_statistics); + free_percpu(net->mib.udplite_statistics); + free_percpu(net->mib.udp_statistics); + free_percpu(net->mib.net_statistics); + free_percpu(net->mib.ip_statistics); + free_percpu(net->mib.tcp_statistics); } static __net_initdata struct pernet_operations ipv4_mib_ops = { @@ -1647,6 +1617,39 @@ static int __init init_ipv4_mibs(void) return register_pernet_subsys(&ipv4_mib_ops); } +static __net_init int inet_init_net(struct net *net) +{ + /* + * Set defaults for local port range + */ + seqlock_init(&net->ipv4.ip_local_ports.lock); + net->ipv4.ip_local_ports.range[0] = 32768; + net->ipv4.ip_local_ports.range[1] = 61000; + + seqlock_init(&net->ipv4.ping_group_range.lock); + /* + * Sane defaults - nobody may create ping sockets. + * Boot scripts should set this to distro-specific group. + */ + net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1); + net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0); + return 0; +} + +static __net_exit void inet_exit_net(struct net *net) +{ +} + +static __net_initdata struct pernet_operations af_inet_ops = { + .init = inet_init_net, + .exit = inet_exit_net, +}; + +static int __init init_inet_pernet_ops(void) +{ + return register_pernet_subsys(&af_inet_ops); +} + static int ipv4_proc_init(void); /* @@ -1700,13 +1703,9 @@ static int __init inet_init(void) BUILD_BUG_ON(sizeof(struct inet_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb)); - sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL); - if (!sysctl_local_reserved_ports) - goto out; - rc = proto_register(&tcp_prot, 1); if (rc) - goto out_free_reserved_ports; + goto out; rc = proto_register(&udp_prot, 1); if (rc) @@ -1791,6 +1790,9 @@ static int __init inet_init(void) if (ip_mr_init()) pr_crit("%s: Cannot init ipv4 mroute\n", __func__); #endif + + if (init_inet_pernet_ops()) + pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__); /* * Initialise per-cpu ipv4 mibs */ @@ -1813,8 +1815,6 @@ out_unregister_udp_proto: proto_unregister(&udp_prot); out_unregister_tcp_proto: proto_unregister(&tcp_prot); -out_free_reserved_ports: - kfree(sysctl_local_reserved_ports); goto out; } diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 717902669d2..a2afa89513a 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -155,6 +155,10 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) struct iphdr *iph, *top_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; ahp = x->data; ahash = ahp->ahash; @@ -167,14 +171,19 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah = ip_auth_hdr(skb); ihl = ip_hdrlen(skb); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } err = -ENOMEM; - iph = ah_alloc_tmp(ahash, nfrags, ihl); + iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + seqhi_len); if (!iph) goto out; - - icv = ah_tmp_icv(ahash, iph, ihl); + seqhi = (__be32 *)((char *)iph + ihl); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memset(ah->auth_data, 0, ahp->icv_trunc_len); @@ -210,10 +219,15 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah_output_done, skb); AH_SKB_CB(skb)->tmp = iph; @@ -295,6 +309,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) struct ip_auth_hdr *ah; struct ah_data *ahp; int err = -ENOMEM; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; if (!pskb_may_pull(skb, sizeof(*ah))) goto out; @@ -335,14 +353,22 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) iph = ip_hdr(skb); ihl = ip_hdrlen(skb); - work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } + + work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + + ahp->icv_trunc_len + seqhi_len); if (!work_iph) goto out; - auth_data = ah_tmp_auth(work_iph, ihl); + seqhi = (__be32 *)((char *)work_iph + ihl); + auth_data = ah_tmp_auth(seqhi, seqhi_len); icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memcpy(work_iph, iph, ihl); memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); @@ -361,10 +387,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, ihl); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah_input_done, skb); AH_SKB_CB(skb)->tmp = work_iph; @@ -397,7 +428,7 @@ out: return err; } -static void ah4_err(struct sk_buff *skb, u32 info) +static int ah4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; @@ -407,23 +438,25 @@ static void ah4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0); xfrm_state_put(x); + + return 0; } static int ah_init_state(struct xfrm_state *x) @@ -505,6 +538,10 @@ static void ah_destroy(struct xfrm_state *x) kfree(ahp); } +static int ah4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} static const struct xfrm_type ah_type = { @@ -518,11 +555,12 @@ static const struct xfrm_type ah_type = .output = ah_output }; -static const struct net_protocol ah4_protocol = { +static struct xfrm4_protocol ah4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = ah4_rcv_cb, .err_handler = ah4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init ah4_init(void) @@ -531,7 +569,7 @@ static int __init ah4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&ah4_protocol, IPPROTO_AH) < 0) { + if (xfrm4_protocol_register(&ah4_protocol, IPPROTO_AH) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ah_type, AF_INET); return -EAGAIN; @@ -541,7 +579,7 @@ static int __init ah4_init(void) static void __exit ah4_fini(void) { - if (inet_del_protocol(&ah4_protocol, IPPROTO_AH) < 0) + if (xfrm4_protocol_deregister(&ah4_protocol, IPPROTO_AH) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ah_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 8b5134c582f..a3095fdefbe 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -86,18 +86,26 @@ out: } EXPORT_SYMBOL(ip4_datagram_connect); +/* Because UDP xmit path can manipulate sk_dst_cache without holding + * socket lock, we need to use sk_dst_set() here, + * even if we own the socket lock. + */ void ip4_datagram_release_cb(struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; + struct dst_entry *dst; struct flowi4 fl4; struct rtable *rt; - if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0)) - return; - rcu_read_lock(); + + dst = __sk_dst_get(sk); + if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) { + rcu_read_unlock(); + return; + } inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; @@ -105,8 +113,10 @@ void ip4_datagram_release_cb(struct sock *sk) inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); - if (!IS_ERR(rt)) - __sk_dst_set(sk, &rt->dst); + + dst = !IS_ERR(rt) ? &rt->dst : NULL; + sk_dst_set(sk, dst); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ip4_datagram_release_cb); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index ac2dff3c2c1..e9449376b58 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -106,7 +106,6 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { #define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE]; -static DEFINE_SPINLOCK(inet_addr_hash_lock); static u32 inet_addr_hash(struct net *net, __be32 addr) { @@ -119,16 +118,14 @@ static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa) { u32 hash = inet_addr_hash(net, ifa->ifa_local); - spin_lock(&inet_addr_hash_lock); + ASSERT_RTNL(); hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]); - spin_unlock(&inet_addr_hash_lock); } static void inet_hash_remove(struct in_ifaddr *ifa) { - spin_lock(&inet_addr_hash_lock); + ASSERT_RTNL(); hlist_del_init_rcu(&ifa->hash); - spin_unlock(&inet_addr_hash_lock); } /** @@ -830,7 +827,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) ifa_existing = find_matching_ifa(ifa); if (!ifa_existing) { /* It would be best to check for !NLM_F_CREATE here but - * userspace alreay relies on not having to provide this. + * userspace already relies on not having to provide this. */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); @@ -1443,7 +1440,8 @@ static size_t inet_nlmsg_size(void) + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ - + nla_total_size(4); /* IFA_FLAGS */ + + nla_total_size(4) /* IFA_FLAGS */ + + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } static inline u32 cstamp_delta(unsigned long cstamp) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 7785b28061a..360b565918c 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -473,7 +473,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu) net_adj) & ~(blksize - 1)) + net_adj - 2; } -static void esp4_err(struct sk_buff *skb, u32 info) +static int esp4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; @@ -483,23 +483,25 @@ static void esp4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0); xfrm_state_put(x); + + return 0; } static void esp_destroy(struct xfrm_state *x) @@ -672,6 +674,11 @@ error: return err; } +static int esp4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type esp_type = { .description = "ESP4", @@ -685,11 +692,12 @@ static const struct xfrm_type esp_type = .output = esp_output }; -static const struct net_protocol esp4_protocol = { +static struct xfrm4_protocol esp4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = esp4_rcv_cb, .err_handler = esp4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init esp4_init(void) @@ -698,7 +706,7 @@ static int __init esp4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&esp4_protocol, IPPROTO_ESP) < 0) { + if (xfrm4_protocol_register(&esp4_protocol, IPPROTO_ESP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&esp_type, AF_INET); return -EAGAIN; @@ -708,7 +716,7 @@ static int __init esp4_init(void) static void __exit esp4_fini(void) { - if (inet_del_protocol(&esp4_protocol, IPPROTO_ESP) < 0) + if (xfrm4_protocol_deregister(&esp4_protocol, IPPROTO_ESP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&esp_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c7539e22868..255aa9946fe 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -250,7 +250,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, bool dev_match; fl4.flowi4_oif = 0; - fl4.flowi4_iif = oif; + fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_tos = tos; @@ -659,7 +659,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) && ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED) - return ip_rt_dump(skb, cb); + return skb->len; s_h = cb->args[0]; s_e = cb->args[1]; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b53f0bf84dc..b10cd43a472 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -631,6 +631,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, .daddr = nh->nh_gw, .flowi4_scope = cfg->fc_scope + 1, .flowi4_oif = nh->nh_oif, + .flowi4_iif = LOOPBACK_IFINDEX, }; /* It is not necessary, but requires a bit of thinking */ @@ -820,13 +821,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); if (fi == NULL) goto failure; + fib_info_cnt++; if (cfg->fc_mx) { fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); if (!fi->fib_metrics) goto failure; } else fi->fib_metrics = (u32 *) dst_default_metrics; - fib_info_cnt++; fi->fib_net = hold_net(net); fi->fib_protocol = cfg->fc_protocol; diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 1863422fb7d..0485bf7f8f0 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -68,6 +68,7 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi, skb_push(skb, hdr_len); + skb_reset_transport_header(skb); greh = (struct gre_base_hdr *)skb->data; greh->flags = tnl_flags_to_gre_flags(tpi->flags); greh->protocol = tpi->proto; @@ -84,7 +85,8 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi, ptr--; } if (tpi->flags&TUNNEL_CSUM && - !(skb_shinfo(skb)->gso_type & SKB_GSO_GRE)) { + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_GRE|SKB_GSO_GRE_CSUM))) { *ptr = 0; *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0, skb->len, 0)); @@ -93,28 +95,6 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi, } EXPORT_SYMBOL_GPL(gre_build_header); -static __sum16 check_checksum(struct sk_buff *skb) -{ - __sum16 csum = 0; - - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - csum = csum_fold(skb->csum); - - if (!csum) - break; - /* Fall through. */ - - case CHECKSUM_NONE: - skb->csum = 0; - csum = __skb_checksum_complete(skb); - skb->ip_summed = CHECKSUM_COMPLETE; - break; - } - - return csum; -} - static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err) { @@ -141,7 +121,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, options = (__be32 *)(greh + 1); if (greh->flags & GRE_CSUM) { - if (check_checksum(skb)) { + if (skb_checksum_simple_validate(skb)) { *csum_err = true; return -EINVAL; } @@ -182,6 +162,14 @@ static int gre_cisco_rcv(struct sk_buff *skb) int i; bool csum_err = false; +#ifdef CONFIG_NET_IPGRE_BROADCAST + if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { + /* Looped back packet, drop it! */ + if (rt_is_output_route(skb_rtable(skb))) + goto drop; + } +#endif + if (parse_gre_header(skb, &tpi, &csum_err) < 0) goto drop; diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index f1d32280cb5..f0bdd47bbbc 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -42,6 +42,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_GRE | + SKB_GSO_GRE_CSUM | SKB_GSO_IPIP))) goto out; @@ -55,6 +56,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, goto out; csum = !!(greh->flags & GRE_CSUM); + if (csum) + skb->encap_hdr_csum = 1; if (unlikely(!pskb_may_pull(skb, ghl))) goto out; @@ -94,10 +97,13 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, } } - greh = (struct gre_base_hdr *)(skb->data); + skb_reset_transport_header(skb); + + greh = (struct gre_base_hdr *) + skb_transport_header(skb); pcsum = (__be32 *)(greh + 1); *pcsum = 0; - *(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0)); + *(__sum16 *)pcsum = gso_make_checksum(skb, 0); } __skb_push(skb, tnl_hlen - ghl); @@ -125,10 +131,12 @@ static __sum16 gro_skb_checksum(struct sk_buff *skb) csum_partial(skb->data, skb_gro_offset(skb), 0)); sum = csum_fold(NAPI_GRO_CB(skb)->csum); if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) { - if (unlikely(!sum)) + if (unlikely(!sum) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev); - } else + } else { skb->ip_summed = CHECKSUM_COMPLETE; + skb->csum_complete_sw = 1; + } return sum; } @@ -255,6 +263,9 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff) int err = -ENOENT; __be16 type; + skb->encapsulation = 1; + skb_shinfo(skb)->gso_type = SKB_GSO_GRE; + type = greh->protocol; if (greh->flags & GRE_KEY) grehlen += GRE_HEADER_SECTION; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 0134663fdbc..42b7bcf8045 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -337,6 +337,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) struct sock *sk; struct inet_sock *inet; __be32 daddr, saddr; + u32 mark = IP4_REPLY_MARK(net, skb->mark); if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb)) return; @@ -349,6 +350,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) icmp_param->data.icmph.checksum = 0; inet->tos = ip_hdr(skb)->tos; + sk->sk_mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); ipc.opt = NULL; @@ -364,6 +366,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; fl4.saddr = saddr; + fl4.flowi4_mark = mark; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_proto = IPPROTO_ICMP; security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); @@ -382,7 +385,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, const struct iphdr *iph, - __be32 saddr, u8 tos, + __be32 saddr, u8 tos, u32 mark, int type, int code, struct icmp_bxm *param) { @@ -394,6 +397,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->daddr = (param->replyopts.opt.opt.srr ? param->replyopts.opt.opt.faddr : iph->saddr); fl4->saddr = saddr; + fl4->flowi4_mark = mark; fl4->flowi4_tos = RT_TOS(tos); fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; @@ -491,6 +495,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) struct flowi4 fl4; __be32 saddr; u8 tos; + u32 mark; struct net *net; struct sock *sk; @@ -592,6 +597,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) | IPTOS_PREC_INTERNETCONTROL) : iph->tos; + mark = IP4_REPLY_MARK(net, skb_in->mark); if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb_in)) goto out_unlock; @@ -608,13 +614,14 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) icmp_param->skb = skb_in; icmp_param->offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; + sk->sk_mark = mark; ipc.addr = iph->saddr; ipc.opt = &icmp_param->replyopts.opt; ipc.tx_flags = 0; ipc.ttl = 0; ipc.tos = -1; - rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, + rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark, type, code, icmp_param); if (IS_ERR(rt)) goto out_unlock; @@ -732,8 +739,6 @@ static void icmp_unreach(struct sk_buff *skb) /* fall through */ case 0: info = ntohs(icmph->un.frag.mtu); - if (!info) - goto out; } break; case ICMP_SR_FAILED: @@ -908,16 +913,8 @@ int icmp_rcv(struct sk_buff *skb) ICMP_INC_STATS_BH(net, ICMP_MIB_INMSGS); - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (!csum_fold(skb->csum)) - break; - /* fall through */ - case CHECKSUM_NONE: - skb->csum = 0; - if (__skb_checksum_complete(skb)) - goto csum_error; - } + if (skb_checksum_simple_validate(skb)) + goto csum_error; if (!pskb_pull(skb, sizeof(*icmph))) goto error; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 97e4d1655d2..db710b059ba 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; @@ -988,16 +988,8 @@ int igmp_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct igmphdr))) goto drop; - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (!csum_fold(skb->csum)) - break; - /* fall through */ - case CHECKSUM_NONE: - skb->csum = 0; - if (__skb_checksum_complete(skb)) - goto drop; - } + if (skb_checksum_simple_validate(skb)) + goto drop; ih = igmp_hdr(skb); switch (ih->type) { @@ -1952,6 +1944,10 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) rtnl_lock(); in_dev = ip_mc_find_dev(net, imr); + if (!in_dev) { + ret = -ENODEV; + goto out; + } ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = rtnl_dereference(*imlp)) != NULL; @@ -1969,16 +1965,14 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) *imlp = iml->next_rcu; - if (in_dev) - ip_mc_dec_group(in_dev, group); + ip_mc_dec_group(in_dev, group); rtnl_unlock(); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); return 0; } - if (!in_dev) - ret = -ENODEV; +out: rtnl_unlock(); return ret; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0d1e2cb877e..14d02ea905b 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -29,19 +29,16 @@ const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n"; EXPORT_SYMBOL(inet_csk_timer_bug_msg); #endif -unsigned long *sysctl_local_reserved_ports; -EXPORT_SYMBOL(sysctl_local_reserved_ports); - void inet_get_local_port_range(struct net *net, int *low, int *high) { unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); - *low = net->ipv4.sysctl_local_ports.range[0]; - *high = net->ipv4.sysctl_local_ports.range[1]; - } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); + *low = net->ipv4.ip_local_ports.range[0]; + *high = net->ipv4.ip_local_ports.range[1]; + } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq)); } EXPORT_SYMBOL(inet_get_local_port_range); @@ -113,7 +110,7 @@ again: smallest_size = -1; do { - if (inet_is_reserved_local_port(rover)) + if (inet_is_local_reserved_port(net, rover)) goto next_nolock; head = &hashinfo->bhash[inet_bhashfn(net, rover, hashinfo->bhash_size)]; @@ -408,7 +405,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, struct net *net = sock_net(sk); int flags = inet_sk_flowi_flags(sk); - flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, + flowi4_init_output(fl4, sk->sk_bound_dev_if, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, flags, @@ -445,7 +442,7 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk, rcu_read_lock(); opt = rcu_dereference(newinet->inet_opt); - flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, + flowi4_init_output(fl4, sk->sk_bound_dev_if, inet_rsk(req)->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, @@ -680,6 +677,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num); newsk->sk_write_space = sk_stream_write_space; + newsk->sk_mark = inet_rsk(req)->ir_mark; + newicsk->icsk_retransmits = 0; newicsk->icsk_backoff = 0; newicsk->icsk_probes_out = 0; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index bb075fc9a14..3b01959bf4b 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -208,7 +208,7 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force) } work = frag_mem_limit(nf) - nf->low_thresh; - while (work > 0) { + while (work > 0 || force) { spin_lock(&nf->lru_lock); if (list_empty(&nf->lru_list)) { @@ -278,9 +278,10 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, atomic_inc(&qp->refcnt); hlist_add_head(&qp->list, &hb->chain); + inet_frag_lru_add(nf, qp); spin_unlock(&hb->chain_lock); read_unlock(&f->lock); - inet_frag_lru_add(nf, qp); + return qp; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 8b9cf279450..43116e8c8e1 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -274,7 +274,7 @@ struct sock *__inet_lookup_established(struct net *net, const __be32 daddr, const u16 hnum, const int dif) { - INET_ADDR_COOKIE(acookie, saddr, daddr) + INET_ADDR_COOKIE(acookie, saddr, daddr); const __portpair ports = INET_COMBINED_PORTS(sport, hnum); struct sock *sk; const struct hlist_nulls_node *node; @@ -327,7 +327,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, __be32 daddr = inet->inet_rcv_saddr; __be32 saddr = inet->inet_daddr; int dif = sk->sk_bound_dev_if; - INET_ADDR_COOKIE(acookie, saddr, daddr) + INET_ADDR_COOKIE(acookie, saddr, daddr); const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); struct net *net = sock_net(sk); unsigned int hash = inet_ehashfn(net, daddr, lport, @@ -500,7 +500,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, local_bh_disable(); for (i = 1; i <= remaining; i++) { port = low + (i + offset) % remaining; - if (inet_is_reserved_local_port(port)) + if (inet_is_local_reserved_port(net, port)) continue; head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 48f42446511..bd5f5928167 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -26,20 +26,7 @@ * Theory of operations. * We keep one entry for each peer IP address. The nodes contains long-living * information about the peer which doesn't depend on routes. - * At this moment this information consists only of ID field for the next - * outgoing IP packet. This field is incremented with each packet as encoded - * in inet_getid() function (include/net/inetpeer.h). - * At the moment of writing this notes identifier of IP packets is generated - * to be unpredictable using this code only for packets subjected - * (actually or potentially) to defragmentation. I.e. DF packets less than - * PMTU in size when local fragmentation is disabled use a constant ID and do - * not use this code (see ip_select_ident() in include/net/ip.h). * - * Route cache entries hold references to our nodes. - * New cache entries get references via lookup by destination IP address in - * the avl tree. The reference is grabbed only when it's needed i.e. only - * when we try to output IP packet which needs an unpredictable ID (see - * __ip_select_ident() in net/ipv4/route.c). * Nodes are removed only when reference counter goes to 0. * When it's happened the node may be removed when a sufficient amount of * time has been passed since its last use. The less-recently-used entry can @@ -62,7 +49,6 @@ * refcnt: atomically against modifications on other CPU; * usually under some other lock to prevent node disappearing * daddr: unchangeable - * ip_id_count: atomic value (no lock needed) */ static struct kmem_cache *peer_cachep __read_mostly; @@ -120,7 +106,7 @@ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min static void inetpeer_gc_worker(struct work_struct *work) { struct inet_peer *p, *n, *c; - LIST_HEAD(list); + struct list_head list; spin_lock_bh(&gc_lock); list_replace_init(&gc_list, &list); @@ -497,10 +483,6 @@ relookup: p->daddr = *daddr; atomic_set(&p->refcnt, 1); atomic_set(&p->rid, 0); - atomic_set(&p->ip_id_count, - (daddr->family == AF_INET) ? - secure_ip_id(daddr->addr.a4) : - secure_ipv6_id(daddr->addr.a6)); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; /* 60*HZ is arbitrary, but chosen enough high so that the first @@ -522,7 +504,7 @@ EXPORT_SYMBOL_GPL(inet_getpeer); void inet_putpeer(struct inet_peer *p) { p->dtime = (__u32)jiffies; - smp_mb__before_atomic_dec(); + smp_mb__before_atomic(); atomic_dec(&p->refcnt); } EXPORT_SYMBOL_GPL(inet_putpeer); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e9f1217a8af..3a83ce5efa8 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -39,6 +39,24 @@ #include <net/route.h> #include <net/xfrm.h> +static bool ip_may_fragment(const struct sk_buff *skb) +{ + return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) || + skb->ignore_df; +} + +static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu) + return false; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + + static int ip_forward_finish(struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); @@ -59,6 +77,10 @@ int ip_forward(struct sk_buff *skb) struct rtable *rt; /* Route we use */ struct ip_options *opt = &(IPCB(skb)->opt); + /* that should never happen */ + if (skb->pkt_type != PACKET_HOST) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -68,9 +90,6 @@ int ip_forward(struct sk_buff *skb) if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb)) return NET_RX_SUCCESS; - if (skb->pkt_type != PACKET_HOST) - goto drop; - skb_forward_csum(skb); /* @@ -91,8 +110,7 @@ int ip_forward(struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); - if (unlikely(skb->len > mtu && !skb_is_gso(skb) && - (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { + if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index c10a3ce5cbf..ed32313e307 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -232,8 +232,9 @@ static void ip_expire(unsigned long arg) * "Fragment Reassembly Timeout" message, per RFC792. */ if (qp->user == IP_DEFRAG_AF_PACKET || - (qp->user == IP_DEFRAG_CONNTRACK_IN && - skb_rtable(head)->rt_type != RTN_LOCAL)) + ((qp->user >= IP_DEFRAG_CONNTRACK_IN) && + (qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) && + (skb_rtable(head)->rt_type != RTN_LOCAL))) goto out_rcu_unlock; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index ec4f762efda..9b842544aea 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -410,7 +410,7 @@ static int ipgre_open(struct net_device *dev) struct flowi4 fl4; struct rtable *rt; - rt = ip_route_output_gre(dev_net(dev), &fl4, + rt = ip_route_output_gre(t->net, &fl4, t->parms.iph.daddr, t->parms.iph.saddr, t->parms.o_key, @@ -434,7 +434,7 @@ static int ipgre_close(struct net_device *dev) if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) { struct in_device *in_dev; - in_dev = inetdev_by_index(dev_net(dev), t->mlink); + in_dev = inetdev_by_index(t->net, t->mlink); if (in_dev) ip_mc_dec_group(in_dev, t->parms.iph.daddr); } @@ -463,6 +463,7 @@ static const struct net_device_ops ipgre_netdev_ops = { static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; + dev->type = ARPHRD_IPGRE; ip_tunnel_setup(dev, ipgre_net_id); } @@ -477,7 +478,7 @@ static void __gre_tunnel_init(struct net_device *dev) dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4; dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 4; - dev->features |= NETIF_F_NETNS_LOCAL | GRE_FEATURES; + dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) { @@ -501,7 +502,6 @@ static int ipgre_tunnel_init(struct net_device *dev) memcpy(dev->dev_addr, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); - dev->type = ARPHRD_IPGRE; dev->flags = IFF_NOARP; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->addr_len = 4; @@ -649,6 +649,7 @@ static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); dev->netdev_ops = &gre_tap_netdev_ops; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index f4ab72e19af..ad382499bac 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -288,6 +288,10 @@ int ip_options_compile(struct net *net, optptr++; continue; } + if (unlikely(l < 2)) { + pp_ptr = optptr; + goto error; + } optlen = optptr[1]; if (optlen < 2 || optlen > l) { pp_ptr = optptr; @@ -364,7 +368,7 @@ int ip_options_compile(struct net *net, } if (optptr[2] <= optlen) { unsigned char *timeptr = NULL; - if (optptr[2]+3 > optptr[1]) { + if (optptr[2]+3 > optlen) { pp_ptr = optptr + 2; goto error; } @@ -376,7 +380,7 @@ int ip_options_compile(struct net *net, optptr[2] += 4; break; case IPOPT_TS_TSANDADDR: - if (optptr[2]+7 > optptr[1]) { + if (optptr[2]+7 > optlen) { pp_ptr = optptr + 2; goto error; } @@ -390,7 +394,7 @@ int ip_options_compile(struct net *net, optptr[2] += 8; break; case IPOPT_TS_PRESPEC: - if (optptr[2]+7 > optptr[1]) { + if (optptr[2]+7 > optlen) { pp_ptr = optptr + 2; goto error; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8971780aec7..8d3b6b0e985 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -101,17 +101,17 @@ int __ip_local_out(struct sk_buff *skb) skb_dst(skb)->dev, dst_output); } -int ip_local_out(struct sk_buff *skb) +int ip_local_out_sk(struct sock *sk, struct sk_buff *skb) { int err; err = __ip_local_out(skb); if (likely(err == 1)) - err = dst_output(skb); + err = dst_output_sk(sk, skb); return err; } -EXPORT_SYMBOL_GPL(ip_local_out); +EXPORT_SYMBOL_GPL(ip_local_out_sk); static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) { @@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(skb, &rt->dst, sk); + ip_select_ident(skb, sk); if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -211,6 +211,48 @@ static inline int ip_finish_output2(struct sk_buff *skb) return -EINVAL; } +static int ip_finish_output_gso(struct sk_buff *skb) +{ + netdev_features_t features; + struct sk_buff *segs; + int ret = 0; + + /* common case: locally created skb or seglen is <= mtu */ + if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) || + skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb)) + return ip_finish_output2(skb); + + /* Slowpath - GSO segment length is exceeding the dst MTU. + * + * This can happen in two cases: + * 1) TCP GRO packet, DF bit not set + * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly + * from host network stack. + */ + features = netif_skb_features(skb); + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR(segs)) { + kfree_skb(skb); + return -ENOMEM; + } + + consume_skb(skb); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = ip_fragment(segs, ip_finish_output2); + + if (err && ret == 0) + ret = err; + segs = nskb; + } while (segs); + + return ret; +} + static int ip_finish_output(struct sk_buff *skb) { #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) @@ -220,15 +262,17 @@ static int ip_finish_output(struct sk_buff *skb) return dst_output(skb); } #endif - if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb)) + if (skb_is_gso(skb)) + return ip_finish_output_gso(skb); + + if (skb->len > ip_skb_dst_mtu(skb)) return ip_fragment(skb, ip_finish_output2); - else - return ip_finish_output2(skb); + + return ip_finish_output2(skb); } -int ip_mc_output(struct sk_buff *skb) +int ip_mc_output(struct sock *sk, struct sk_buff *skb) { - struct sock *sk = skb->sk; struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; @@ -287,7 +331,7 @@ int ip_mc_output(struct sk_buff *skb) !(IPCB(skb)->flags & IPSKB_REROUTED)); } -int ip_output(struct sk_buff *skb) +int ip_output(struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; @@ -315,9 +359,9 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) sizeof(fl4->saddr) + sizeof(fl4->daddr)); } -int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl) +/* Note: skb->sk can be different from sk, in case of tunnels */ +int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) { - struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); struct ip_options_rcu *inet_opt; struct flowi4 *fl4; @@ -371,7 +415,7 @@ packet_routed: skb_reset_network_header(skb); iph = ip_hdr(skb); *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff)); - if (ip_dont_fragment(sk, &rt->dst) && !skb->local_df) + if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; @@ -386,9 +430,9 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_more(skb, &rt->dst, sk, - (skb_shinfo(skb)->gso_segs ?: 1) - 1); + ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1); + /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -422,9 +466,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) to->ipvs_property = from->ipvs_property; #endif @@ -449,7 +490,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) __be16 not_last_frag; struct rtable *rt = skb_rtable(skb); int err = 0; - bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; dev = rt->dst.dev; @@ -459,8 +499,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) iph = ip_hdr(skb); - mtu = ip_dst_mtu_maybe_forward(&rt->dst, forwarding); - if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) || + mtu = ip_skb_dst_mtu(skb); + if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); @@ -825,8 +865,7 @@ static int __ip_append_data(struct sock *sk, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ? - mtu : 0xFFFF; + maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -1149,8 +1188,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ? - mtu : 0xFFFF; + maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu; if (cork->length + size > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -1311,11 +1349,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * to fragment the frame generated here. No matter, what transforms * how transforms change size of the packet, it will come out. */ - if (inet->pmtudisc < IP_PMTUDISC_DO) - skb->local_df = 1; + skb->ignore_df = ip_sk_ignore_df(sk); /* DF bit is set when we want to see DF on outgoing frames. - * If local_df is set too, we still allow to fragment this frame + * If ignore_df is set too, we still allow to fragment this frame * locally. */ if (inet->pmtudisc == IP_PMTUDISC_DO || inet->pmtudisc == IP_PMTUDISC_PROBE || @@ -1341,7 +1378,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); - ip_select_ident(skb, &rt->dst, sk); + ip_select_ident(skb, sk); if (opt) { iph->ihl += opt->optlen>>2; @@ -1508,7 +1545,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, daddr = replyopts.opt.opt.faddr; } - flowi4_init_output(&fl4, arg->bound_dev_if, 0, + flowi4_init_output(&fl4, arg->bound_dev_if, + IP4_REPLY_MARK(net, skb->mark), RT_TOS(arg->tos), RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 580dd96666e..64741b93863 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -186,7 +186,8 @@ void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) } EXPORT_SYMBOL(ip_cmsg_recv); -int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) +int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, + bool allow_ipv6) { int err, val; struct cmsghdr *cmsg; @@ -194,6 +195,22 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; +#if defined(CONFIG_IPV6) + if (allow_ipv6 && + cmsg->cmsg_level == SOL_IPV6 && + cmsg->cmsg_type == IPV6_PKTINFO) { + struct in6_pktinfo *src_info; + + if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info))) + return -EINVAL; + src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); + if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) + return -EINVAL; + ipc->oif = src_info->ipi6_ifindex; + ipc->addr = src_info->ipi6_addr.s6_addr32[3]; + continue; + } +#endif if (cmsg->cmsg_level != SOL_IP) continue; switch (cmsg->cmsg_type) { @@ -626,7 +643,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, inet->nodefrag = val ? 1 : 0; break; case IP_MTU_DISCOVER: - if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_INTERFACE) + if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) goto e_inval; inet->pmtudisc = val; break; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index bd28f386bd0..6f9de61dce5 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -73,12 +73,7 @@ static void __tunnel_dst_set(struct ip_tunnel_dst *idst, { struct dst_entry *old_dst; - if (dst) { - if (dst->flags & DST_NOCACHE) - dst = NULL; - else - dst_clone(dst); - } + dst_clone(dst); old_dst = xchg((__force struct dst_entry **)&idst->dst, dst); dst_release(old_dst); } @@ -93,83 +88,33 @@ static void tunnel_dst_reset(struct ip_tunnel *t) tunnel_dst_set(t, NULL); } -static void tunnel_dst_reset_all(struct ip_tunnel *t) +void ip_tunnel_dst_reset_all(struct ip_tunnel *t) { int i; for_each_possible_cpu(i) __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); } +EXPORT_SYMBOL(ip_tunnel_dst_reset_all); -static struct dst_entry *tunnel_dst_get(struct ip_tunnel *t) +static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) { struct dst_entry *dst; rcu_read_lock(); dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst); - if (dst) - dst_hold(dst); - rcu_read_unlock(); - return dst; -} - -static struct dst_entry *tunnel_dst_check(struct ip_tunnel *t, u32 cookie) -{ - struct dst_entry *dst = tunnel_dst_get(t); - - if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { - tunnel_dst_reset(t); - return NULL; - } - - return dst; -} - -/* Often modified stats are per cpu, other are shared (netdev->stats) */ -struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *tot) -{ - int i; - - for_each_possible_cpu(i) { - const struct pcpu_sw_netstats *tstats = - per_cpu_ptr(dev->tstats, i); - u64 rx_packets, rx_bytes, tx_packets, tx_bytes; - unsigned int start; - - do { - start = u64_stats_fetch_begin_bh(&tstats->syncp); - rx_packets = tstats->rx_packets; - tx_packets = tstats->tx_packets; - rx_bytes = tstats->rx_bytes; - tx_bytes = tstats->tx_bytes; - } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); - - tot->rx_packets += rx_packets; - tot->tx_packets += tx_packets; - tot->rx_bytes += rx_bytes; - tot->tx_bytes += tx_bytes; + if (dst && !atomic_inc_not_zero(&dst->__refcnt)) + dst = NULL; + if (dst) { + if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + tunnel_dst_reset(t); + dst_release(dst); + dst = NULL; + } } - - tot->multicast = dev->stats.multicast; - - tot->rx_crc_errors = dev->stats.rx_crc_errors; - tot->rx_fifo_errors = dev->stats.rx_fifo_errors; - tot->rx_length_errors = dev->stats.rx_length_errors; - tot->rx_frame_errors = dev->stats.rx_frame_errors; - tot->rx_errors = dev->stats.rx_errors; - - tot->tx_fifo_errors = dev->stats.tx_fifo_errors; - tot->tx_carrier_errors = dev->stats.tx_carrier_errors; - tot->tx_dropped = dev->stats.tx_dropped; - tot->tx_aborted_errors = dev->stats.tx_aborted_errors; - tot->tx_errors = dev->stats.tx_errors; - - tot->collisions = dev->stats.collisions; - - return tot; + rcu_read_unlock(); + return (struct rtable *)dst; } -EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, __be16 flags, __be32 key) @@ -224,6 +169,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, hlist_for_each_entry_rcu(t, head, hash_node) { if (remote != t->parms.iph.daddr || + t->parms.iph.saddr != 0 || !(t->dev->flags & IFF_UP)) continue; @@ -240,10 +186,11 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { - if ((local != t->parms.iph.saddr && - (local != t->parms.iph.daddr || - !ipv4_is_multicast(local))) || - !(t->dev->flags & IFF_UP)) + if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) && + (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) + continue; + + if (!(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) @@ -260,6 +207,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, hlist_for_each_entry_rcu(t, head, hash_node) { if (t->parms.i_key != key || + t->parms.iph.saddr != 0 || + t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) continue; @@ -286,13 +235,17 @@ static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, { unsigned int h; __be32 remote; + __be32 i_key = parms->i_key; if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr)) remote = parms->iph.daddr; else remote = 0; - h = ip_tunnel_hash(parms->i_key, remote); + if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI)) + i_key = 0; + + h = ip_tunnel_hash(i_key, remote); return &itn->tunnels[h]; } @@ -315,6 +268,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; __be32 key = parms->i_key; + __be16 flags = parms->i_flags; int link = parms->link; struct ip_tunnel *t = NULL; struct hlist_head *head = ip_bucket(itn, parms); @@ -322,9 +276,9 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && - key == t->parms.i_key && link == t->parms.link && - type == t->dev->type) + type == t->dev->type && + ip_tunnel_key_match(&t->parms, flags, key)) break; } return t; @@ -442,14 +396,13 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, struct ip_tunnel_net *itn, struct ip_tunnel_parm *parms) { - struct ip_tunnel *nt, *fbt; + struct ip_tunnel *nt; struct net_device *dev; BUG_ON(!itn->fb_tunnel_dev); - fbt = netdev_priv(itn->fb_tunnel_dev); dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms); if (IS_ERR(dev)) - return NULL; + return ERR_CAST(dev); dev->mtu = ip_tunnel_bind_dev(dev); @@ -467,9 +420,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { - /* Looped back packet, drop it! */ - if (rt_is_output_route(skb_rtable(skb))) - goto drop; tunnel->dev->stats.multicast++; skb->pkt_type = PACKET_BROADCAST; } @@ -492,6 +442,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } + skb_reset_network_header(skb); + err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) @@ -584,13 +536,14 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi4 fl4; u8 tos, ttl; __be16 df; - struct rtable *rt = NULL; /* Route to the other host */ + struct rtable *rt; /* Route to the other host */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst; int err; - bool connected = true; + bool connected; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); + connected = (tunnel->parms.iph.daddr != 0); dst = tnl_params->daddr; if (dst == 0) { @@ -657,8 +610,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link); - if (connected) - rt = (struct rtable *)tunnel_dst_check(tunnel, 0); + rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL; if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); @@ -716,12 +668,13 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, dev->needed_headroom = max_headroom; if (skb_cow_head(skb, dev->needed_headroom)) { + ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); return; } - err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, protocol, + err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); iptunnel_xmit_stats(err, &dev->stats, dev->tstats); @@ -766,26 +719,25 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, if (set_mtu) dev->mtu = mtu; } - tunnel_dst_reset_all(t); + ip_tunnel_dst_reset_all(t); netdev_state_change(dev); } int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { int err = 0; - struct ip_tunnel *t; - struct net *net = dev_net(dev); - struct ip_tunnel *tunnel = netdev_priv(dev); - struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id); + struct ip_tunnel *t = netdev_priv(dev); + struct net *net = t->net; + struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id); BUG_ON(!itn->fb_tunnel_dev); switch (cmd) { case SIOCGETTUNNEL: - t = NULL; - if (dev == itn->fb_tunnel_dev) + if (dev == itn->fb_tunnel_dev) { t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); - if (t == NULL) - t = netdev_priv(dev); + if (t == NULL) + t = netdev_priv(dev); + } memcpy(p, &t->parms, sizeof(*p)); break; @@ -796,16 +748,20 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) goto done; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); - if (!(p->i_flags&TUNNEL_KEY)) - p->i_key = 0; - if (!(p->o_flags&TUNNEL_KEY)) - p->o_key = 0; + if (!(p->i_flags & VTI_ISVTI)) { + if (!(p->i_flags & TUNNEL_KEY)) + p->i_key = 0; + if (!(p->o_flags & TUNNEL_KEY)) + p->o_key = 0; + } t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); - if (!t && (cmd == SIOCADDTUNNEL)) + if (!t && (cmd == SIOCADDTUNNEL)) { t = ip_tunnel_create(net, itn, p); - + err = PTR_ERR_OR_ZERO(t); + break; + } if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { if (t != NULL) { if (t->dev != dev) { @@ -832,8 +788,9 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) if (t) { err = 0; ip_tunnel_update(itn, t, dev, p, true); - } else - err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); + } else { + err = -ENOENT; + } break; case SIOCDELTUNNEL: @@ -927,6 +884,7 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, */ if (!IS_ERR(itn->fb_tunnel_dev)) { itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev); ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); } rtnl_unlock(); @@ -1048,19 +1006,13 @@ int ip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; - int i, err; + int err; dev->destructor = ip_tunnel_dev_free; - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ipt_stats; - ipt_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ipt_stats->syncp); - } - tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); if (!tunnel->dst_cache) { free_percpu(dev->tstats); @@ -1095,7 +1047,7 @@ void ip_tunnel_uninit(struct net_device *dev) if (itn->fb_tunnel_dev != dev) ip_tunnel_del(netdev_priv(dev)); - tunnel_dst_reset_all(tunnel); + ip_tunnel_dst_reset_all(tunnel); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 6156f4ef5e9..f4c987bb7e9 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -46,7 +46,7 @@ #include <net/netns/generic.h> #include <net/rtnetlink.h> -int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb, +int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, __u8 proto, __u8 tos, __u8 ttl, __be16 df, bool xnet) { @@ -74,9 +74,9 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb, iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; - __ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1); + __ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1); - err = ip_local_out(skb); + err = ip_local_out_sk(sk, skb); if (unlikely(net_xmit_eval(err))) pkt_len = 0; return pkt_len; @@ -135,6 +135,14 @@ struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, return skb; } + /* If packet is not gso and we are resolving any partial checksum, + * clear encapsulation flag. This allows setting CHECKSUM_PARTIAL + * on the outer header without confusing devices that implement + * NETIF_F_IP_CSUM with encapsulation. + */ + if (csum_help) + skb->encapsulation = 0; + if (skb->ip_summed == CHECKSUM_PARTIAL && csum_help) { err = skb_checksum_help(skb); if (unlikely(err)) @@ -148,3 +156,49 @@ error: return ERR_PTR(err); } EXPORT_SYMBOL_GPL(iptunnel_handle_offloads); + +/* Often modified stats are per cpu, other are shared (netdev->stats) */ +struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) +{ + int i; + + for_each_possible_cpu(i) { + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_irq(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; + } + + tot->multicast = dev->stats.multicast; + + tot->rx_crc_errors = dev->stats.rx_crc_errors; + tot->rx_fifo_errors = dev->stats.rx_fifo_errors; + tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_frame_errors = dev->stats.rx_frame_errors; + tot->rx_errors = dev->stats.rx_errors; + + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + + tot->collisions = dev->stats.collisions; + + return tot; +} +EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 48eafae5176..b8960f3527f 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -34,6 +34,7 @@ #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> +#include <linux/icmpv6.h> #include <net/sock.h> #include <net/ip.h> @@ -49,8 +50,8 @@ static struct rtnl_link_ops vti_link_ops __read_mostly; static int vti_net_id __read_mostly; static int vti_tunnel_init(struct net_device *dev); -/* We dont digest the packet therefore let the packet pass */ -static int vti_rcv(struct sk_buff *skb) +static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) { struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); @@ -60,79 +61,120 @@ static int vti_rcv(struct sk_buff *skb) tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); if (tunnel != NULL) { - struct pcpu_sw_netstats *tstats; - u32 oldmark = skb->mark; - int ret; - - - /* temporarily mark the skb with the tunnel o_key, to - * only match policies with this mark. - */ - skb->mark = be32_to_cpu(tunnel->parms.o_key); - ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb); - skb->mark = oldmark; - if (!ret) - return -1; - - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); - - secpath_reset(skb); - skb->dev = tunnel->dev; + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; + skb->mark = be32_to_cpu(tunnel->parms.i_key); + + return xfrm_input(skb, nexthdr, spi, encap_type); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; +} + +static int vti_rcv(struct sk_buff *skb) +{ + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + return vti_input(skb, ip_hdr(skb)->protocol, 0, 0); +} + +static int vti_rcv_cb(struct sk_buff *skb, int err) +{ + unsigned short family; + struct net_device *dev; + struct pcpu_sw_netstats *tstats; + struct xfrm_state *x; + struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; + + if (!tunnel) return 1; + + dev = tunnel->dev; + + if (err) { + dev->stats.rx_errors++; + dev->stats.rx_dropped++; + + return 0; } - return -1; + x = xfrm_input_state(skb); + family = x->inner_mode->afinfo->family; + + if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + return -EPERM; + + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev))); + skb->dev = dev; + + tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + return 0; } -/* This function assumes it is being called from dev_queue_xmit() - * and that skb is filled properly by that function. - */ +static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src) +{ + xfrm_address_t *daddr = (xfrm_address_t *)&dst; + xfrm_address_t *saddr = (xfrm_address_t *)&src; -static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) + /* if there is no transform then this tunnel is not functional. + * Or if the xfrm is not mode tunnel. + */ + if (!x || x->props.mode != XFRM_MODE_TUNNEL || + x->props.family != AF_INET) + return false; + + if (!dst) + return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET); + + if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET)) + return false; + + return true; +} + +static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, + struct flowi *fl) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct iphdr *tiph = &tunnel->parms.iph; - u8 tos; - struct rtable *rt; /* Route to the other host */ + struct ip_tunnel_parm *parms = &tunnel->parms; + struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ - struct iphdr *old_iph = ip_hdr(skb); - __be32 dst = tiph->daddr; - struct flowi4 fl4; int err; - if (skb->protocol != htons(ETH_P_IP)) - goto tx_error; - - tos = old_iph->tos; + if (!dst) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } - memset(&fl4, 0, sizeof(fl4)); - flowi4_init_output(&fl4, tunnel->parms.link, - be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos), - RT_SCOPE_UNIVERSE, - IPPROTO_IPIP, 0, - dst, tiph->saddr, 0, 0); - rt = ip_route_output_key(dev_net(dev), &fl4); - if (IS_ERR(rt)) { + dst_hold(dst); + dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0); + if (IS_ERR(dst)) { dev->stats.tx_carrier_errors++; goto tx_error_icmp; } - /* if there is no transform then this tunnel is not functional. - * Or if the xfrm is not mode tunnel. - */ - if (!rt->dst.xfrm || - rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) { + + if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { dev->stats.tx_carrier_errors++; - ip_rt_put(rt); + dst_release(dst); goto tx_error_icmp; } - tdev = rt->dst.dev; + + tdev = dst->dev; if (tdev == dev) { - ip_rt_put(rt); + dst_release(dst); dev->stats.collisions++; goto tx_error; } @@ -146,10 +188,8 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) tunnel->err_count = 0; } - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - nf_reset(skb); + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); + skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; err = dst_output(skb); @@ -166,6 +206,98 @@ tx_error: return NETDEV_TX_OK; } +/* This function assumes it is being called from dev_queue_xmit() + * and that skb is filled properly by that function. + */ +static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct flowi fl; + + memset(&fl, 0, sizeof(fl)); + + skb->mark = be32_to_cpu(tunnel->parms.o_key); + + switch (skb->protocol) { + case htons(ETH_P_IP): + xfrm_decode_session(skb, &fl, AF_INET); + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + break; + case htons(ETH_P_IPV6): + xfrm_decode_session(skb, &fl, AF_INET6); + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + break; + default: + dev->stats.tx_errors++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + + return vti_xmit(skb, dev, &fl); +} + +static int vti4_err(struct sk_buff *skb, u32 info) +{ + __be32 spi; + __u32 mark; + struct xfrm_state *x; + struct ip_tunnel *tunnel; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah ; + struct ip_comp_hdr *ipch; + struct net *net = dev_net(skb->dev); + const struct iphdr *iph = (const struct iphdr *)skb->data; + int protocol = iph->protocol; + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->daddr, iph->saddr, 0); + if (!tunnel) + return -1; + + mark = be32_to_cpu(tunnel->parms.o_key); + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return 0; + case ICMP_REDIRECT: + break; + default: + return 0; + } + + x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET); + if (!x) + return 0; + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0); + else + ipv4_redirect(skb, net, 0, 0, protocol, 0); + xfrm_state_put(x); + + return 0; +} + static int vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -181,12 +313,19 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EINVAL; } + if (!(p.i_flags & GRE_KEY)) + p.i_key = 0; + if (!(p.o_flags & GRE_KEY)) + p.o_key = 0; + + p.i_flags = VTI_ISVTI; + err = ip_tunnel_ioctl(dev, &p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { - p.i_flags |= GRE_KEY | VTI_ISVTI; + p.i_flags |= GRE_KEY; p.o_flags |= GRE_KEY; } @@ -207,6 +346,7 @@ static const struct net_device_ops vti_netdev_ops = { static void vti_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &vti_netdev_ops; + dev->type = ARPHRD_TUNNEL; ip_tunnel_setup(dev, vti_net_id); } @@ -218,13 +358,11 @@ static int vti_tunnel_init(struct net_device *dev) memcpy(dev->dev_addr, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); - dev->type = ARPHRD_TUNNEL; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); dev->mtu = ETH_DATA_LEN; dev->flags = IFF_NOARP; dev->iflink = 0; dev->addr_len = 4; - dev->features |= NETIF_F_NETNS_LOCAL; dev->features |= NETIF_F_LLTX; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; @@ -241,9 +379,28 @@ static void __net_init vti_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; } -static struct xfrm_tunnel_notifier vti_handler __read_mostly = { +static struct xfrm4_protocol vti_esp4_protocol __read_mostly = { .handler = vti_rcv, - .priority = 1, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, +}; + +static struct xfrm4_protocol vti_ah4_protocol __read_mostly = { + .handler = vti_rcv, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, +}; + +static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { + .handler = vti_rcv, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, }; static int __net_init vti_init_net(struct net *net) @@ -287,6 +444,8 @@ static void vti_netlink_parms(struct nlattr *data[], if (!data) return; + parms->i_flags = VTI_ISVTI; + if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); @@ -382,10 +541,31 @@ static int __init vti_init(void) err = register_pernet_device(&vti_net_ops); if (err < 0) return err; - err = xfrm4_mode_tunnel_input_register(&vti_handler); + err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP); if (err < 0) { unregister_pernet_device(&vti_net_ops); pr_info("vti init: can't register tunnel\n"); + + return err; + } + + err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH); + if (err < 0) { + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); + unregister_pernet_device(&vti_net_ops); + pr_info("vti init: can't register tunnel\n"); + + return err; + } + + err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP); + if (err < 0) { + xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); + unregister_pernet_device(&vti_net_ops); + pr_info("vti init: can't register tunnel\n"); + + return err; } err = rtnl_link_register(&vti_link_ops); @@ -395,7 +575,9 @@ static int __init vti_init(void) return err; rtnl_link_failed: - xfrm4_mode_tunnel_input_deregister(&vti_handler); + xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); + xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); return err; } @@ -403,8 +585,13 @@ rtnl_link_failed: static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); - if (xfrm4_mode_tunnel_input_deregister(&vti_handler)) + if (xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP)) pr_info("vti close: can't deregister tunnel\n"); + if (xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH)) + pr_info("vti close: can't deregister tunnel\n"); + if (xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP)) + pr_info("vti close: can't deregister tunnel\n"); + unregister_pernet_device(&vti_net_ops); } diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 826be4cb482..c0855d50a3f 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -23,7 +23,7 @@ #include <net/protocol.h> #include <net/sock.h> -static void ipcomp4_err(struct sk_buff *skb, u32 info) +static int ipcomp4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); __be32 spi; @@ -34,24 +34,26 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } spi = htonl(ntohs(ipch->cpi)); x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0); xfrm_state_put(x); + + return 0; } /* We always hold one tunnel user reference to indicate a tunnel */ @@ -147,6 +149,11 @@ out: return err; } +static int ipcomp4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type ipcomp_type = { .description = "IPCOMP4", .owner = THIS_MODULE, @@ -157,11 +164,12 @@ static const struct xfrm_type ipcomp_type = { .output = ipcomp_output }; -static const struct net_protocol ipcomp4_protocol = { +static struct xfrm4_protocol ipcomp4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = ipcomp4_rcv_cb, .err_handler = ipcomp4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init ipcomp4_init(void) @@ -170,7 +178,7 @@ static int __init ipcomp4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) { + if (xfrm4_protocol_register(&ipcomp4_protocol, IPPROTO_COMP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ipcomp_type, AF_INET); return -EAGAIN; @@ -180,7 +188,7 @@ static int __init ipcomp4_init(void) static void __exit ipcomp4_fini(void) { - if (inet_del_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) + if (xfrm4_protocol_deregister(&ipcomp4_protocol, IPPROTO_COMP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ipcomp_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index efa1138fa52..b3e86ea7b71 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -273,7 +273,7 @@ static int __init ic_open_devs(void) msleep(1); - if time_before(jiffies, next_msg) + if (time_before(jiffies, next_msg)) continue; elapsed = jiffies_to_msecs(jiffies - start); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 812b1835146..62eaa005e14 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -149,13 +149,13 @@ static int ipip_err(struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, - t->dev->ifindex, 0, IPPROTO_IPIP, 0); + t->parms.link, 0, IPPROTO_IPIP, 0); err = 0; goto out; } if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, IPPROTO_IPIP, 0); err = 0; goto out; @@ -486,4 +486,5 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ipip"); MODULE_ALIAS_NETDEV("tunl0"); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b9b3472975b..65bcaa78904 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -455,7 +455,7 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) struct mr_table *mrt; struct flowi4 fl4 = { .flowi4_oif = dev->ifindex, - .flowi4_iif = skb->skb_iif, + .flowi4_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi4_mark = skb->mark, }; int err; @@ -484,7 +484,7 @@ static void reg_vif_setup(struct net_device *dev) dev->type = ARPHRD_PIMREG; dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 8; dev->flags = IFF_NOARP; - dev->netdev_ops = ®_vif_netdev_ops, + dev->netdev_ops = ®_vif_netdev_ops; dev->destructor = free_netdev; dev->features |= NETIF_F_NETNS_LOCAL; } @@ -1663,7 +1663,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(skb, skb_dst(skb), NULL); + ip_select_ident(skb, NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); @@ -2255,13 +2255,14 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, } static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc_cache *c, int cmd) + u32 portid, u32 seq, struct mfc_cache *c, int cmd, + int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; - nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -2329,7 +2330,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, if (skb == NULL) goto errout; - err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; @@ -2368,7 +2369,8 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ipmr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) goto done; next_entry: e++; @@ -2382,7 +2384,8 @@ next_entry: if (ipmr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) { + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) { spin_unlock_bh(&mfc_unres_lock); goto done; } diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index c3e0adea9c2..7ebd6e37875 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -61,7 +61,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type) skb_dst_set(skb, NULL); dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0); if (IS_ERR(dst)) - return PTR_ERR(dst);; + return PTR_ERR(dst); skb_dst_set(skb, dst); } #endif diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 81c6910cfa9..a26ce035e3f 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -61,6 +61,11 @@ config NFT_CHAIN_NAT_IPV4 packet transformations such as the source, destination address and source and destination ports. +config NFT_REJECT_IPV4 + depends on NF_TABLES_IPV4 + default NFT_REJECT + tristate + config NF_TABLES_ARP depends on NF_TABLES tristate "ARP nf_tables support" diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index c16be9d5842..90b82405331 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o +obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o # generic IP tables diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 59da7cde072..f95b6f93814 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1044,8 +1044,10 @@ static int __do_replace(struct net *net, const char *name, xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, - sizeof(struct xt_counters) * num_counters) != 0) - ret = -EFAULT; + sizeof(struct xt_counters) * num_counters) != 0) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("arptables: counters copy to user failed while replacing table\n"); + } vfree(counters); xt_table_unlock(t); return ret; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 718dfbd30cb..99e810f8467 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1231,8 +1231,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, - sizeof(struct xt_counters) * num_counters) != 0) - ret = -EFAULT; + sizeof(struct xt_counters) * num_counters) != 0) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n"); + } vfree(counters); xt_table_unlock(t); return ret; diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index c49dcd0284a..4bfaedf9b34 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -89,11 +89,8 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) if (ipv4_is_multicast(iph->daddr)) { if (ipv4_is_zeronet(iph->saddr)) return ipv4_is_local_multicast(iph->daddr) ^ invert; - flow.flowi4_iif = 0; - } else { - flow.flowi4_iif = LOOPBACK_IFINDEX; } - + flow.flowi4_iif = LOOPBACK_IFINDEX; flow.daddr = iph->saddr; flow.saddr = rpfilter_get_saddr(iph->daddr); flow.flowi4_oif = 0; diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index ee2886126e3..f1787c04a4d 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -91,17 +91,9 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, if (nf_ct_is_untracked(ct)) return NF_ACCEPT; - nat = nfct_nat(ct); - if (!nat) { - /* NAT module was loaded late. */ - if (nf_ct_is_confirmed(ct)) - return NF_ACCEPT; - nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); - if (nat == NULL) { - pr_debug("failed to add NAT extension\n"); - return NF_ACCEPT; - } - } + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; switch (ctinfo) { case IP_CT_RELATED: diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 12e13bd82b5..b8f6381c7d0 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -22,7 +22,6 @@ #endif #include <net/netfilter/nf_conntrack_zones.h> -/* Returns new sk_buff, or NULL */ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) { int err; @@ -33,8 +32,10 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) err = ip_defrag(skb, user); local_bh_enable(); - if (!err) + if (!err) { ip_send_check(ip_hdr(skb)); + skb->ignore_df = 1; + } return err; } diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 9eea059dd62..574f7ebba0b 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -229,7 +229,10 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, ret = nf_ct_expect_related(rtcp_exp); if (ret == 0) break; - else if (ret != -EBUSY) { + 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; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index d551e31b416..7c676671329 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1198,8 +1198,8 @@ static int snmp_translate(struct nf_conn *ct, map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); } else { /* DNAT replies */ - map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip); - map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); + map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip); + map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip); } if (map.from == map.to) diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c index b5b256d45e6..3964157d826 100644 --- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c @@ -48,15 +48,9 @@ static unsigned int nf_nat_fn(const struct nf_hook_ops *ops, NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET))); - nat = nfct_nat(ct); - if (nat == NULL) { - /* Conntrack module was loaded late, can't add extension. */ - if (nf_ct_is_confirmed(ct)) - return NF_ACCEPT; - nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); - if (nat == NULL) - return NF_ACCEPT; - } + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; switch (ctinfo) { case IP_CT_RELATED: diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c new file mode 100644 index 00000000000..e79718a382f --- /dev/null +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -0,0 +1,75 @@ +/* + * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2013 Eric Leblond <eric@regit.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/icmp.h> +#include <net/netfilter/ipv4/nf_reject.h> +#include <net/netfilter/nft_reject.h> + +void nft_reject_ipv4_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + struct nft_reject *priv = nft_expr_priv(expr); + + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + nf_send_unreach(pkt->skb, priv->icmp_code); + break; + case NFT_REJECT_TCP_RST: + nf_send_reset(pkt->skb, pkt->ops->hooknum); + break; + } + + data[NFT_REG_VERDICT].verdict = NF_DROP; +} +EXPORT_SYMBOL_GPL(nft_reject_ipv4_eval); + +static struct nft_expr_type nft_reject_ipv4_type; +static const struct nft_expr_ops nft_reject_ipv4_ops = { + .type = &nft_reject_ipv4_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), + .eval = nft_reject_ipv4_eval, + .init = nft_reject_init, + .dump = nft_reject_dump, +}; + +static struct nft_expr_type nft_reject_ipv4_type __read_mostly = { + .family = NFPROTO_IPV4, + .name = "reject", + .ops = &nft_reject_ipv4_ops, + .policy = nft_reject_policy, + .maxattr = NFTA_REJECT_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_reject_ipv4_module_init(void) +{ + return nft_register_expr(&nft_reject_ipv4_type); +} + +static void __exit nft_reject_ipv4_module_exit(void) +{ + nft_unregister_expr(&nft_reject_ipv4_type); +} + +module_init(nft_reject_ipv4_module_init); +module_exit(nft_reject_ipv4_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "reject"); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 2d11c094296..044a0ddf6a7 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -236,15 +236,15 @@ exit: static void inet_get_ping_group_range_net(struct net *net, kgid_t *low, kgid_t *high) { - kgid_t *data = net->ipv4.sysctl_ping_group_range; + kgid_t *data = net->ipv4.ping_group_range.range; unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ping_group_range.lock); *low = data[0]; *high = data[1]; - } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); + } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq)); } @@ -252,26 +252,33 @@ int ping_init_sock(struct sock *sk) { struct net *net = sock_net(sk); kgid_t group = current_egid(); - struct group_info *group_info = get_current_groups(); - int i, j, count = group_info->ngroups; + struct group_info *group_info; + int i, j, count; kgid_t low, high; + int ret = 0; inet_get_ping_group_range_net(net, &low, &high); if (gid_lte(low, group) && gid_lte(group, high)) return 0; + group_info = get_current_groups(); + count = group_info->ngroups; for (i = 0; i < group_info->nblocks; i++) { int cp_count = min_t(int, NGROUPS_PER_BLOCK, count); for (j = 0; j < cp_count; j++) { kgid_t gid = group_info->blocks[i][j]; if (gid_lte(low, gid) && gid_lte(gid, high)) - return 0; + goto out_release_group; } count -= cp_count; } - return -EACCES; + ret = -EACCES; + +out_release_group: + put_group_info(group_info); + return ret; } EXPORT_SYMBOL_GPL(ping_init_sock); @@ -727,7 +734,7 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m sock_tx_timestamp(sk, &ipc.tx_flags); if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); if (err) return err; if (ipc.opt) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index a6c8a80ec9d..ae0af9386f7 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -273,6 +273,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK), SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE), SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE), + SNMP_MIB_ITEM("TCPFastOpenActiveFail", LINUX_MIB_TCPFASTOPENACTIVEFAIL), SNMP_MIB_ITEM("TCPFastOpenPassive", LINUX_MIB_TCPFASTOPENPASSIVE), SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL), SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW), @@ -280,6 +281,11 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES), SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS), SNMP_MIB_ITEM("TCPAutoCorking", LINUX_MIB_TCPAUTOCORKING), + SNMP_MIB_ITEM("TCPFromZeroWindowAdv", LINUX_MIB_TCPFROMZEROWINDOWADV), + SNMP_MIB_ITEM("TCPToZeroWindowAdv", LINUX_MIB_TCPTOZEROWINDOWADV), + SNMP_MIB_ITEM("TCPWantZeroWindowAdv", LINUX_MIB_TCPWANTZEROWINDOWADV), + SNMP_MIB_ITEM("TCPSynRetrans", LINUX_MIB_TCPSYNRETRANS), + SNMP_MIB_ITEM("TCPOrigDataSent", LINUX_MIB_TCPORIGDATASENT), SNMP_MIB_SENTINEL }; @@ -339,15 +345,15 @@ static void icmp_put(struct seq_file *seq) for (i = 0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " Out%s", icmpmibmap[i].name); seq_printf(seq, "\nIcmp: %lu %lu %lu", - snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INMSGS), - snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INERRORS), - snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_CSUMERRORS)); + snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INMSGS), + snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INERRORS), + snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_CSUMERRORS)); for (i = 0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " %lu", atomic_long_read(ptr + icmpmibmap[i].index)); seq_printf(seq, " %lu %lu", - snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTMSGS), - snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTERRORS)); + snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTMSGS), + snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTERRORS)); for (i = 0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " %lu", atomic_long_read(ptr + (icmpmibmap[i].index | 0x100))); @@ -373,7 +379,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v) BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0); for (i = 0; snmp4_ipstats_list[i].name != NULL; i++) seq_printf(seq, " %llu", - snmp_fold_field64((void __percpu **)net->mib.ip_statistics, + snmp_fold_field64(net->mib.ip_statistics, snmp4_ipstats_list[i].entry, offsetof(struct ipstats_mib, syncp))); @@ -389,11 +395,11 @@ static int snmp_seq_show(struct seq_file *seq, void *v) /* MaxConn field is signed, RFC 2012 */ if (snmp4_tcp_list[i].entry == TCP_MIB_MAXCONN) seq_printf(seq, " %ld", - snmp_fold_field((void __percpu **)net->mib.tcp_statistics, + snmp_fold_field(net->mib.tcp_statistics, snmp4_tcp_list[i].entry)); else seq_printf(seq, " %lu", - snmp_fold_field((void __percpu **)net->mib.tcp_statistics, + snmp_fold_field(net->mib.tcp_statistics, snmp4_tcp_list[i].entry)); } @@ -404,7 +410,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v) seq_puts(seq, "\nUdp:"); for (i = 0; snmp4_udp_list[i].name != NULL; i++) seq_printf(seq, " %lu", - snmp_fold_field((void __percpu **)net->mib.udp_statistics, + snmp_fold_field(net->mib.udp_statistics, snmp4_udp_list[i].entry)); /* the UDP and UDP-Lite MIBs are the same */ @@ -415,7 +421,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v) seq_puts(seq, "\nUdpLite:"); for (i = 0; snmp4_udp_list[i].name != NULL; i++) seq_printf(seq, " %lu", - snmp_fold_field((void __percpu **)net->mib.udplite_statistics, + snmp_fold_field(net->mib.udplite_statistics, snmp4_udp_list[i].entry)); seq_putc(seq, '\n'); @@ -452,7 +458,7 @@ static int netstat_seq_show(struct seq_file *seq, void *v) seq_puts(seq, "\nTcpExt:"); for (i = 0; snmp4_net_list[i].name != NULL; i++) seq_printf(seq, " %lu", - snmp_fold_field((void __percpu **)net->mib.net_statistics, + snmp_fold_field(net->mib.net_statistics, snmp4_net_list[i].entry)); seq_puts(seq, "\nIpExt:"); @@ -462,7 +468,7 @@ static int netstat_seq_show(struct seq_file *seq, void *v) seq_puts(seq, "\nIpExt:"); for (i = 0; snmp4_ipextstats_list[i].name != NULL; i++) seq_printf(seq, " %llu", - snmp_fold_field64((void __percpu **)net->mib.ip_statistics, + snmp_fold_field64(net->mib.ip_statistics, snmp4_ipextstats_list[i].entry, offsetof(struct ipstats_mib, syncp))); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index c04518f4850..2c65160565e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -389,7 +389,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } @@ -524,7 +524,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); if (err) goto out; if (ipc.opt) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 25071b48921..190199851c9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -89,6 +89,7 @@ #include <linux/rcupdate.h> #include <linux/times.h> #include <linux/slab.h> +#include <linux/jhash.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -139,11 +140,6 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); -static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int how) -{ -} - static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) { WARN_ON(1); @@ -162,7 +158,6 @@ static struct dst_ops ipv4_dst_ops = { .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, - .ifdown = ipv4_dst_ifdown, .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, @@ -194,7 +189,7 @@ const __u8 ip_tos2prio[16] = { EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); -#define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field) +#define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field) #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) @@ -462,39 +457,45 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, return neigh_create(&arp_tbl, pkey, dev); } -/* - * Peer allocation may fail only in serious out-of-memory conditions. However - * we still can generate some output. - * Random ID selection looks a bit dangerous because we have no chances to - * select ID being unique in a reasonable period of time. - * But broken packet identifier may be better than no packet at all. +#define IP_IDENTS_SZ 2048u +struct ip_ident_bucket { + atomic_t id; + u32 stamp32; +}; + +static struct ip_ident_bucket *ip_idents __read_mostly; + +/* In order to protect privacy, we add a perturbation to identifiers + * if one generator is seldom used. This makes hard for an attacker + * to infer how many packets were sent between two points in time. */ -static void ip_select_fb_ident(struct iphdr *iph) +u32 ip_idents_reserve(u32 hash, int segs) { - static DEFINE_SPINLOCK(ip_fb_id_lock); - static u32 ip_fallback_id; - u32 salt; + struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ; + u32 old = ACCESS_ONCE(bucket->stamp32); + u32 now = (u32)jiffies; + u32 delta = 0; + + if (old != now && cmpxchg(&bucket->stamp32, old, now) == old) + delta = prandom_u32_max(now - old); - spin_lock_bh(&ip_fb_id_lock); - salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr); - iph->id = htons(salt & 0xFFFF); - ip_fallback_id = salt; - spin_unlock_bh(&ip_fb_id_lock); + return atomic_add_return(segs + delta, &bucket->id) - segs; } +EXPORT_SYMBOL(ip_idents_reserve); -void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) +void __ip_select_ident(struct iphdr *iph, int segs) { - struct net *net = dev_net(dst->dev); - struct inet_peer *peer; + static u32 ip_idents_hashrnd __read_mostly; + u32 hash, id; - peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1); - if (peer) { - iph->id = htons(inet_getid(peer, more)); - inet_putpeer(peer); - return; - } + net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd)); - ip_select_fb_ident(iph); + hash = jhash_3words((__force u32)iph->daddr, + (__force u32)iph->saddr, + iph->protocol, + ip_idents_hashrnd); + id = ip_idents_reserve(hash, segs); + iph->id = htons(id); } EXPORT_SYMBOL(__ip_select_ident); @@ -697,7 +698,6 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, out_unlock: spin_unlock_bh(&fnhe_lock); - return; } static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, @@ -1000,6 +1000,9 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, struct flowi4 fl4; struct rtable *rt; + if (!mark) + mark = IP4_REPLY_MARK(net, skb->mark); + __build_flow_key(&fl4, NULL, iph, oif, RT_TOS(iph->tos), protocol, mark, flow_flags); rt = __ip_route_output_key(net, &fl4); @@ -1017,6 +1020,10 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) struct rtable *rt; __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); + + if (!fl4.flowi4_mark) + fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark); + rt = __ip_route_output_key(sock_net(sk), &fl4); if (!IS_ERR(rt)) { __ip_rt_update_pmtu(rt, &fl4, mtu); @@ -1029,7 +1036,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; struct rtable *rt; - struct dst_entry *dst; + struct dst_entry *odst = NULL; bool new = false; bh_lock_sock(sk); @@ -1037,16 +1044,17 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) if (!ip_sk_accept_pmtu(sk)) goto out; - rt = (struct rtable *) __sk_dst_get(sk); + odst = sk_dst_get(sk); - if (sock_owned_by_user(sk) || !rt) { + if (sock_owned_by_user(sk) || !odst) { __ipv4_sk_update_pmtu(skb, sk, mtu); goto out; } __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); - if (!__sk_dst_check(sk, 0)) { + rt = (struct rtable *)odst; + if (odst->obsolete && odst->ops->check(odst, 0) == NULL) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; @@ -1056,8 +1064,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu); - dst = dst_check(&rt->dst, 0); - if (!dst) { + if (!dst_check(&rt->dst, 0)) { if (new) dst_release(&rt->dst); @@ -1069,10 +1076,11 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) } if (new) - __sk_dst_set(sk, &rt->dst); + sk_dst_set(sk, &rt->dst); out: bh_unlock_sock(sk); + dst_release(odst); } EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); @@ -1136,7 +1144,7 @@ static void ipv4_link_failure(struct sk_buff *skb) dst_set_expires(&rt->dst, 0); } -static int ip_rt_bug(struct sk_buff *skb) +static int ip_rt_bug(struct sock *sk, struct sk_buff *skb) { pr_debug("%s: %pI4 -> %pI4, %s\n", __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, @@ -1526,7 +1534,7 @@ static int __mkroute_input(struct sk_buff *skb, struct in_device *out_dev; unsigned int flags = 0; bool do_cache; - u32 itag; + u32 itag = 0; /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res)); @@ -1597,6 +1605,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rth->dst.output = ip_output; @@ -1695,25 +1704,27 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; err = fib_lookup(net, &fl4, &res); - if (err != 0) + if (err != 0) { + if (!IN_DEV_FORWARD(in_dev)) + err = -EHOSTUNREACH; goto no_route; - - RT_CACHE_STAT_INC(in_slow_tot); + } if (res.type == RTN_BROADCAST) goto brd_input; if (res.type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, - LOOPBACK_IFINDEX, - dev, in_dev, &itag); + 0, dev, in_dev, &itag); if (err < 0) goto martian_source_keep_err; goto local_input; } - if (!IN_DEV_FORWARD(in_dev)) + if (!IN_DEV_FORWARD(in_dev)) { + err = -EHOSTUNREACH; goto no_route; + } if (res.type != RTN_UNICAST) goto martian_destination; @@ -1768,6 +1779,7 @@ local_input: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; @@ -2220,7 +2232,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or new->__use = 1; new->input = dst_discard; - new->output = dst_discard; + new->output = dst_discard_sk; new->dev = ort->dst.dev; if (new->dev) @@ -2359,7 +2371,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, } } else #endif - if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) + if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex)) goto nla_put_failure; } @@ -2470,11 +2482,6 @@ errout_free: goto errout; } -int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) -{ - return skb->len; -} - void ip_rt_multicast_event(struct in_device *in_dev) { rt_cache_flush(dev_net(in_dev->dev)); @@ -2712,6 +2719,12 @@ int __init ip_rt_init(void) { int rc = 0; + ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL); + if (!ip_idents) + panic("IP: failed to allocate ip_idents\n"); + + prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents)); + #ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index f2ed13c2125..c86624b36a6 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -303,6 +303,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->ir_rmt_port = th->source; ireq->ir_loc_addr = ip_hdr(skb)->daddr; ireq->ir_rmt_addr = ip_hdr(skb)->saddr; + ireq->ir_mark = inet_request_mark(sk, skb); ireq->ecn_ok = ecn_ok; ireq->snd_wscale = tcp_opt.snd_wscale; ireq->sack_ok = tcp_opt.sack_ok; @@ -339,7 +340,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark, + flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, inet_sk_flowi_flags(sk), (opt && opt->srr) ? opt->faddr : ireq->ir_rmt_addr, diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 44eba052b43..79a007c5255 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -45,10 +45,10 @@ static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; /* Update system visible IP port range */ static void set_local_port_range(struct net *net, int range[2]) { - write_seqlock(&net->ipv4.sysctl_local_ports.lock); - net->ipv4.sysctl_local_ports.range[0] = range[0]; - net->ipv4.sysctl_local_ports.range[1] = range[1]; - write_sequnlock(&net->ipv4.sysctl_local_ports.lock); + write_seqlock(&net->ipv4.ip_local_ports.lock); + net->ipv4.ip_local_ports.range[0] = range[0]; + net->ipv4.ip_local_ports.range[1] = range[1]; + write_sequnlock(&net->ipv4.ip_local_ports.lock); } /* Validate changes from /proc interface. */ @@ -57,7 +57,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, size_t *lenp, loff_t *ppos) { struct net *net = - container_of(table->data, struct net, ipv4.sysctl_local_ports.range); + container_of(table->data, struct net, ipv4.ip_local_ports.range); int ret; int range[2]; struct ctl_table tmp = { @@ -87,14 +87,14 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low { kgid_t *data = table->data; struct net *net = - container_of(table->data, struct net, ipv4.sysctl_ping_group_range); + container_of(table->data, struct net, ipv4.ping_group_range.range); unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); *low = data[0]; *high = data[1]; - } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); + } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq)); } /* Update system visible IP port range */ @@ -102,11 +102,11 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig { kgid_t *data = table->data; struct net *net = - container_of(table->data, struct net, ipv4.sysctl_ping_group_range); - write_seqlock(&net->ipv4.sysctl_local_ports.lock); + container_of(table->data, struct net, ipv4.ping_group_range.range); + write_seqlock(&net->ipv4.ip_local_ports.lock); data[0] = low; data[1] = high; - write_sequnlock(&net->ipv4.sysctl_local_ports.lock); + write_sequnlock(&net->ipv4.ip_local_ports.lock); } /* Validate changes from /proc interface. */ @@ -437,13 +437,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .procname = "ip_local_reserved_ports", - .data = NULL, /* initialized in sysctl_ipv4_init */ - .maxlen = 65536, - .mode = 0644, - .proc_handler = proc_do_large_bitmap, - }, - { .procname = "igmp_max_memberships", .data = &sysctl_igmp_max_memberships, .maxlen = sizeof(int), @@ -805,7 +798,7 @@ static struct ctl_table ipv4_net_table[] = { }, { .procname = "ping_group_range", - .data = &init_net.ipv4.sysctl_ping_group_range, + .data = &init_net.ipv4.ping_group_range.range, .maxlen = sizeof(gid_t)*2, .mode = 0644, .proc_handler = ipv4_ping_group_range, @@ -819,12 +812,19 @@ static struct ctl_table ipv4_net_table[] = { }, { .procname = "ip_local_port_range", - .maxlen = sizeof(init_net.ipv4.sysctl_local_ports.range), - .data = &init_net.ipv4.sysctl_local_ports.range, + .maxlen = sizeof(init_net.ipv4.ip_local_ports.range), + .data = &init_net.ipv4.ip_local_ports.range, .mode = 0644, .proc_handler = ipv4_local_port_range, }, { + .procname = "ip_local_reserved_ports", + .data = &init_net.ipv4.sysctl_local_reserved_ports, + .maxlen = 65536, + .mode = 0644, + .proc_handler = proc_do_large_bitmap, + }, + { .procname = "ip_no_pmtu_disc", .data = &init_net.ipv4.sysctl_ip_no_pmtu_disc, .maxlen = sizeof(int), @@ -838,6 +838,20 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "fwmark_reflect", + .data = &init_net.ipv4.sysctl_fwmark_reflect, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "tcp_fwmark_accept", + .data = &init_net.ipv4.sysctl_tcp_fwmark_accept, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { } }; @@ -858,26 +872,18 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) table[i].data += (void *)net - (void *)&init_net; } - /* - * Sane defaults - nobody may create ping sockets. - * Boot scripts should set this to distro-specific group. - */ - net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1); - net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0); - - /* - * Set defaults for local port range - */ - seqlock_init(&net->ipv4.sysctl_local_ports.lock); - net->ipv4.sysctl_local_ports.range[0] = 32768; - net->ipv4.sysctl_local_ports.range[1] = 61000; - net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); if (net->ipv4.ipv4_hdr == NULL) goto err_reg; + net->ipv4.sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL); + if (!net->ipv4.sysctl_local_reserved_ports) + goto err_ports; + return 0; +err_ports: + unregister_net_sysctl_table(net->ipv4.ipv4_hdr); err_reg: if (!net_eq(net, &init_net)) kfree(table); @@ -889,6 +895,7 @@ static __net_exit void ipv4_sysctl_exit_net(struct net *net) { struct ctl_table *table; + kfree(net->ipv4.sysctl_local_reserved_ports); table = net->ipv4.ipv4_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.ipv4_hdr); kfree(table); @@ -902,16 +909,6 @@ static __net_initdata struct pernet_operations ipv4_sysctl_ops = { static __init int sysctl_ipv4_init(void) { struct ctl_table_header *hdr; - struct ctl_table *i; - - for (i = ipv4_table; i->procname; i++) { - if (strcmp(i->procname, "ip_local_reserved_ports") == 0) { - i->data = sysctl_local_reserved_ports; - break; - } - } - if (!i->procname) - return -EINVAL; hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table); if (hdr == NULL) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4475b3bb494..9d2118e5fbc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -387,7 +387,7 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsq_node); icsk->icsk_rto = TCP_TIMEOUT_INIT; - tp->mdev = TCP_TIMEOUT_INIT; + tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -1044,7 +1044,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp) } } -static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) +static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, + int *copied, size_t size) { struct tcp_sock *tp = tcp_sk(sk); int err, flags; @@ -1059,11 +1060,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) if (unlikely(tp->fastopen_req == NULL)) return -ENOBUFS; tp->fastopen_req->data = msg; + tp->fastopen_req->size = size; flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, flags); - *size = tp->fastopen_req->copied; + *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); return err; } @@ -1083,7 +1085,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flags = msg->msg_flags; if (flags & MSG_FASTOPEN) { - err = tcp_sendmsg_fastopen(sk, msg, &copied_syn); + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) @@ -1106,7 +1108,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { copied = tcp_send_rcvq(sk, msg, size); - goto out; + goto out_nopush; } err = -EINVAL; @@ -1280,6 +1282,7 @@ wait_for_memory: out: if (copied) tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); +out_nopush: release_sock(sk); return copied + copied_syn; @@ -2229,7 +2232,7 @@ adjudge_to_death: /* This is a (useful) BSD violating of the RFC. There is a * problem with TCP as specified in that the other end could * keep a socket open forever with no application left this end. - * We use a 3 minute timeout (about the same as BSD) then kill + * We use a 1 minute timeout (about the same as BSD) then kill * our end. If they send after that then tough - BUT: long enough * that we won't make the old 4*rto = almost no time - whoops * reset mistake. @@ -2339,7 +2342,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); - tp->srtt = 0; + tp->srtt_us = 0; if ((tp->write_seq += tp->max_window + 2) == 0) tp->write_seq = 1; icsk->icsk_backoff = 0; @@ -2783,8 +2786,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) info->tcpi_pmtu = icsk->icsk_pmtu_cookie; info->tcpi_rcv_ssthresh = tp->rcv_ssthresh; - info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3; - info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2; + info->tcpi_rtt = tp->srtt_us >> 3; + info->tcpi_rttvar = tp->mdev_us >> 2; info->tcpi_snd_ssthresh = tp->snd_ssthresh; info->tcpi_snd_cwnd = tp->snd_cwnd; info->tcpi_advmss = tp->advmss; @@ -2794,6 +2797,11 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) info->tcpi_rcv_space = tp->rcvq_space.space; info->tcpi_total_retrans = tp->total_retrans; + + info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ? + sk->sk_pacing_rate : ~0ULL; + info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ? + sk->sk_max_pacing_rate : ~0ULL; } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -2909,6 +2917,14 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_USER_TIMEOUT: val = jiffies_to_msecs(icsk->icsk_user_timeout); break; + + case TCP_FASTOPEN: + if (icsk->icsk_accept_queue.fastopenq != NULL) + val = icsk->icsk_accept_queue.fastopenq->max_qlen; + else + val = 0; + break; + case TCP_TIMESTAMP: val = tcp_time_stamp + tp->tsoffset; break; diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index 821846fb0a7..d5de69bc04f 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -140,13 +140,12 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) ca->cnt = 1; } -static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, - u32 in_flight) +static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); - if (!tcp_is_cwnd_limited(sk, in_flight)) + if (!tcp_is_cwnd_limited(sk)) return; if (tp->snd_cwnd <= tp->snd_ssthresh) diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index ad37bf18ae4..7b09d8b49fa 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -276,27 +276,6 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) return err; } -/* RFC2861 Check whether we are limited by application or congestion window - * This is the inverse of cwnd check in tcp_tso_should_defer - */ -bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) -{ - const struct tcp_sock *tp = tcp_sk(sk); - u32 left; - - if (in_flight >= tp->snd_cwnd) - return true; - - left = tp->snd_cwnd - in_flight; - if (sk_can_gso(sk) && - left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd && - left * tp->mss_cache < sk->sk_gso_max_size && - left < sk->sk_gso_max_segs) - return true; - return left <= tcp_max_tso_deferred_mss(tp); -} -EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited); - /* Slow start is used when congestion window is no greater than the slow start * threshold. We base on RFC2581 and also handle stretch ACKs properly. * We do not implement RFC3465 Appropriate Byte Counting (ABC) per se but @@ -338,11 +317,11 @@ EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai); /* This is Jacobson's slow start and congestion avoidance. * SIGCOMM '88, p. 328. */ -void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight) +void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); - if (!tcp_is_cwnd_limited(sk, in_flight)) + if (!tcp_is_cwnd_limited(sk)) return; /* In "safe" area, increase. */ @@ -362,21 +341,12 @@ u32 tcp_reno_ssthresh(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_reno_ssthresh); -/* Lower bound on congestion window with halving. */ -u32 tcp_reno_min_cwnd(const struct sock *sk) -{ - const struct tcp_sock *tp = tcp_sk(sk); - return tp->snd_ssthresh/2; -} -EXPORT_SYMBOL_GPL(tcp_reno_min_cwnd); - struct tcp_congestion_ops tcp_reno = { .flags = TCP_CONG_NON_RESTRICTED, .name = "reno", .owner = THIS_MODULE, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, }; /* Initial congestion control used (until SYN) @@ -388,6 +358,5 @@ struct tcp_congestion_ops tcp_init_congestion_ops = { .owner = THIS_MODULE, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, }; EXPORT_SYMBOL_GPL(tcp_init_congestion_ops); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 828e4c3ffba..a9bd8a4828a 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -304,13 +304,12 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) ca->cnt = 1; } -static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, - u32 in_flight) +static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); - if (!tcp_is_cwnd_limited(sk, in_flight)) + if (!tcp_is_cwnd_limited(sk)) return; if (tp->snd_cwnd <= tp->snd_ssthresh) { @@ -409,7 +408,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT; ratio += cnt; - ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT); + ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT); } /* Some calls are for duplicates without timetamps */ @@ -476,10 +475,6 @@ static int __init cubictcp_register(void) /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); - /* hystart needs ms clock resolution */ - if (hystart && HZ < 1000) - cubictcp.flags |= TCP_CONG_RTT_STAMP; - return tcp_register_congestion_control(&cubictcp); } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index f195d9316e5..9771563ab56 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -72,25 +72,224 @@ error: kfree(ctx); return err; } -/* Computes the fastopen cookie for the IP path. - * The path is a 128 bits long (pad with zeros for IPv4). - * - * The caller must check foc->len to determine if a valid cookie - * has been generated successfully. -*/ -void tcp_fastopen_cookie_gen(__be32 src, __be32 dst, - struct tcp_fastopen_cookie *foc) +static bool __tcp_fastopen_cookie_gen(const void *path, + struct tcp_fastopen_cookie *foc) { - __be32 path[4] = { src, dst, 0, 0 }; struct tcp_fastopen_context *ctx; + bool ok = false; tcp_fastopen_init_key_once(true); rcu_read_lock(); ctx = rcu_dereference(tcp_fastopen_ctx); if (ctx) { - crypto_cipher_encrypt_one(ctx->tfm, foc->val, (__u8 *)path); + crypto_cipher_encrypt_one(ctx->tfm, foc->val, path); foc->len = TCP_FASTOPEN_COOKIE_SIZE; + ok = true; } rcu_read_unlock(); + return ok; +} + +/* Generate the fastopen cookie by doing aes128 encryption on both + * the source and destination addresses. Pad 0s for IPv4 or IPv4-mapped-IPv6 + * addresses. For the longer IPv6 addresses use CBC-MAC. + * + * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE. + */ +static bool tcp_fastopen_cookie_gen(struct request_sock *req, + struct sk_buff *syn, + struct tcp_fastopen_cookie *foc) +{ + if (req->rsk_ops->family == AF_INET) { + const struct iphdr *iph = ip_hdr(syn); + + __be32 path[4] = { iph->saddr, iph->daddr, 0, 0 }; + return __tcp_fastopen_cookie_gen(path, foc); + } + +#if IS_ENABLED(CONFIG_IPV6) + if (req->rsk_ops->family == AF_INET6) { + const struct ipv6hdr *ip6h = ipv6_hdr(syn); + struct tcp_fastopen_cookie tmp; + + if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) { + struct in6_addr *buf = (struct in6_addr *) tmp.val; + int i = 4; + + for (i = 0; i < 4; i++) + buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i]; + return __tcp_fastopen_cookie_gen(buf, foc); + } + } +#endif + return false; +} + +static bool tcp_fastopen_create_child(struct sock *sk, + struct sk_buff *skb, + struct dst_entry *dst, + struct request_sock *req) +{ + struct tcp_sock *tp; + struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; + struct sock *child; + + req->num_retrans = 0; + req->num_timeout = 0; + req->sk = NULL; + + child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); + if (child == NULL) + return false; + + spin_lock(&queue->fastopenq->lock); + queue->fastopenq->qlen++; + spin_unlock(&queue->fastopenq->lock); + + /* Initialize the child socket. Have to fix some values to take + * into account the child is a Fast Open socket and is created + * only out of the bits carried in the SYN packet. + */ + tp = tcp_sk(child); + + tp->fastopen_rsk = req; + /* Do a hold on the listner sk so that if the listener is being + * closed, the child that has been accepted can live on and still + * access listen_lock. + */ + sock_hold(sk); + tcp_rsk(req)->listener = sk; + + /* RFC1323: The window in SYN & SYN/ACK segments is never + * scaled. So correct it appropriately. + */ + tp->snd_wnd = ntohs(tcp_hdr(skb)->window); + + /* Activate the retrans timer so that SYNACK can be retransmitted. + * The request socket is not added to the SYN table of the parent + * because it's been added to the accept queue directly. + */ + inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, + TCP_TIMEOUT_INIT, TCP_RTO_MAX); + + /* Add the child socket directly into the accept queue */ + inet_csk_reqsk_queue_add(sk, req, child); + + /* Now finish processing the fastopen child socket. */ + inet_csk(child)->icsk_af_ops->rebuild_header(child); + tcp_init_congestion_control(child); + tcp_mtup_init(child); + tcp_init_metrics(child); + tcp_init_buffer_space(child); + + /* Queue the data carried in the SYN packet. We need to first + * bump skb's refcnt because the caller will attempt to free it. + * + * XXX (TFO) - we honor a zero-payload TFO request for now, + * (any reason not to?) but no need to queue the skb since + * there is no data. How about SYN+FIN? + */ + if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1) { + skb = skb_get(skb); + skb_dst_drop(skb); + __skb_pull(skb, tcp_hdr(skb)->doff * 4); + skb_set_owner_r(skb, child); + __skb_queue_tail(&child->sk_receive_queue, skb); + tp->syn_data_acked = 1; + } + tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + sk->sk_data_ready(sk); + bh_unlock_sock(child); + sock_put(child); + WARN_ON(req->sk == NULL); + return true; +} +EXPORT_SYMBOL(tcp_fastopen_create_child); + +static bool tcp_fastopen_queue_check(struct sock *sk) +{ + struct fastopen_queue *fastopenq; + + /* Make sure the listener has enabled fastopen, and we don't + * exceed the max # of pending TFO requests allowed before trying + * to validating the cookie in order to avoid burning CPU cycles + * unnecessarily. + * + * XXX (TFO) - The implication of checking the max_qlen before + * processing a cookie request is that clients can't differentiate + * between qlen overflow causing Fast Open to be disabled + * temporarily vs a server not supporting Fast Open at all. + */ + fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq; + if (fastopenq == NULL || fastopenq->max_qlen == 0) + return false; + + if (fastopenq->qlen >= fastopenq->max_qlen) { + struct request_sock *req1; + spin_lock(&fastopenq->lock); + req1 = fastopenq->rskq_rst_head; + if ((req1 == NULL) || time_after(req1->expires, jiffies)) { + spin_unlock(&fastopenq->lock); + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENLISTENOVERFLOW); + return false; + } + fastopenq->rskq_rst_head = req1->dl_next; + fastopenq->qlen--; + spin_unlock(&fastopenq->lock); + reqsk_free(req1); + } + return true; +} + +/* Returns true if we should perform Fast Open on the SYN. The cookie (foc) + * may be updated and return the client in the SYN-ACK later. E.g., Fast Open + * cookie request (foc->len == 0). + */ +bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + struct dst_entry *dst) +{ + struct tcp_fastopen_cookie valid_foc = { .len = -1 }; + bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; + + if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) && + (syn_data || foc->len >= 0) && + tcp_fastopen_queue_check(sk))) { + foc->len = -1; + return false; + } + + if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD)) + goto fastopen; + + if (tcp_fastopen_cookie_gen(req, skb, &valid_foc) && + foc->len == TCP_FASTOPEN_COOKIE_SIZE && + foc->len == valid_foc.len && + !memcmp(foc->val, valid_foc.val, foc->len)) { + /* Cookie is valid. Create a (full) child socket to accept + * the data in SYN before returning a SYN-ACK to ack the + * data. If we fail to create the socket, fall back and + * ack the ISN only but includes the same cookie. + * + * Note: Data-less SYN with valid cookie is allowed to send + * data in SYN_RECV state. + */ +fastopen: + if (tcp_fastopen_create_child(sk, skb, dst, req)) { + foc->len = -1; + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENPASSIVE); + return true; + } + } + + NET_INC_STATS_BH(sock_net(sk), foc->len ? + LINUX_MIB_TCPFASTOPENPASSIVEFAIL : + LINUX_MIB_TCPFASTOPENCOOKIEREQD); + *foc = valid_foc; + return false; } +EXPORT_SYMBOL(tcp_try_fastopen); diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c index 8ed9305dfdf..1c4908280d9 100644 --- a/net/ipv4/tcp_highspeed.c +++ b/net/ipv4/tcp_highspeed.c @@ -109,12 +109,12 @@ static void hstcp_init(struct sock *sk) tp->snd_cwnd_clamp = min_t(u32, tp->snd_cwnd_clamp, 0xffffffff/128); } -static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight) +static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct hstcp *ca = inet_csk_ca(sk); - if (!tcp_is_cwnd_limited(sk, in_flight)) + if (!tcp_is_cwnd_limited(sk)) return; if (tp->snd_cwnd <= tp->snd_ssthresh) @@ -162,7 +162,6 @@ static struct tcp_congestion_ops tcp_highspeed __read_mostly = { .init = hstcp_init, .ssthresh = hstcp_ssthresh, .cong_avoid = hstcp_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .owner = THIS_MODULE, .name = "highspeed" diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 4a194acfd92..031361311a8 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -227,12 +227,12 @@ static u32 htcp_recalc_ssthresh(struct sock *sk) return max((tp->snd_cwnd * ca->beta) >> 7, 2U); } -static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight) +static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct htcp *ca = inet_csk_ca(sk); - if (!tcp_is_cwnd_limited(sk, in_flight)) + if (!tcp_is_cwnd_limited(sk)) return; if (tp->snd_cwnd <= tp->snd_ssthresh) diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index 478fe82611b..d8f8f05a495 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -21,7 +21,7 @@ struct hybla { u32 rho2; /* Rho * Rho, integer part */ u32 rho_3ls; /* Rho parameter, <<3 */ u32 rho2_7ls; /* Rho^2, <<7 */ - u32 minrtt; /* Minimum smoothed round trip time value seen */ + u32 minrtt_us; /* Minimum smoothed round trip time value seen */ }; /* Hybla reference round trip time (default= 1/40 sec = 25 ms), in ms */ @@ -35,7 +35,9 @@ static inline void hybla_recalc_param (struct sock *sk) { struct hybla *ca = inet_csk_ca(sk); - ca->rho_3ls = max_t(u32, tcp_sk(sk)->srtt / msecs_to_jiffies(rtt0), 8); + ca->rho_3ls = max_t(u32, + tcp_sk(sk)->srtt_us / (rtt0 * USEC_PER_MSEC), + 8U); ca->rho = ca->rho_3ls >> 3; ca->rho2_7ls = (ca->rho_3ls * ca->rho_3ls) << 1; ca->rho2 = ca->rho2_7ls >> 7; @@ -59,7 +61,7 @@ static void hybla_init(struct sock *sk) hybla_recalc_param(sk); /* set minimum rtt as this is the 1st ever seen */ - ca->minrtt = tp->srtt; + ca->minrtt_us = tp->srtt_us; tp->snd_cwnd = ca->rho; } @@ -85,8 +87,7 @@ static inline u32 hybla_fraction(u32 odds) * o Give cwnd a new value based on the model proposed * o remember increments <1 */ -static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked, - u32 in_flight) +static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct hybla *ca = inet_csk_ca(sk); @@ -94,16 +95,16 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked, int is_slowstart = 0; /* Recalculate rho only if this srtt is the lowest */ - if (tp->srtt < ca->minrtt){ + if (tp->srtt_us < ca->minrtt_us) { hybla_recalc_param(sk); - ca->minrtt = tp->srtt; + ca->minrtt_us = tp->srtt_us; } - if (!tcp_is_cwnd_limited(sk, in_flight)) + if (!tcp_is_cwnd_limited(sk)) return; if (!ca->hybla_en) { - tcp_reno_cong_avoid(sk, ack, acked, in_flight); + tcp_reno_cong_avoid(sk, ack, acked); return; } @@ -166,7 +167,6 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked, static struct tcp_congestion_ops tcp_hybla __read_mostly = { .init = hybla_init, .ssthresh = tcp_reno_ssthresh, - .min_cwnd = tcp_reno_min_cwnd, .cong_avoid = hybla_cong_avoid, .set_state = hybla_state, diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index e498a62b8f9..5999b3972e6 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -255,8 +255,7 @@ static void tcp_illinois_state(struct sock *sk, u8 new_state) /* * Increase window in response to successful acknowledgment. */ -static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked, - u32 in_flight) +static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); @@ -265,7 +264,7 @@ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked, update_params(sk); /* RFC2861 only increase cwnd if fully utilized */ - if (!tcp_is_cwnd_limited(sk, in_flight)) + if (!tcp_is_cwnd_limited(sk)) return; /* In slow start */ @@ -325,10 +324,8 @@ static void tcp_illinois_info(struct sock *sk, u32 ext, } static struct tcp_congestion_ops tcp_illinois __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_illinois_init, .ssthresh = tcp_illinois_ssthresh, - .min_cwnd = tcp_reno_min_cwnd, .cong_avoid = tcp_illinois_cong_avoid, .set_state = tcp_illinois_state, .get_info = tcp_illinois_info, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 65cf90e063d..40639c288dc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -667,10 +667,11 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) * To save cycles in the RFC 1323 implementation it was better to break * it up into three procedures. -- erics */ -static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) +static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) { struct tcp_sock *tp = tcp_sk(sk); - long m = mrtt; /* RTT */ + long m = mrtt_us; /* RTT */ + u32 srtt = tp->srtt_us; /* The following amusing code comes from Jacobson's * article in SIGCOMM '88. Note that rtt and mdev @@ -688,14 +689,12 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) * does not matter how to _calculate_ it. Seems, it was trap * that VJ failed to avoid. 8) */ - if (m == 0) - m = 1; - if (tp->srtt != 0) { - m -= (tp->srtt >> 3); /* m is now error in rtt est */ - tp->srtt += m; /* rtt = 7/8 rtt + 1/8 new */ + if (srtt != 0) { + m -= (srtt >> 3); /* m is now error in rtt est */ + srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) { m = -m; /* m is now abs(error) */ - m -= (tp->mdev >> 2); /* similar update on mdev */ + m -= (tp->mdev_us >> 2); /* similar update on mdev */ /* This is similar to one of Eifel findings. * Eifel blocks mdev updates when rtt decreases. * This solution is a bit different: we use finer gain @@ -707,27 +706,29 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) if (m > 0) m >>= 3; } else { - m -= (tp->mdev >> 2); /* similar update on mdev */ + m -= (tp->mdev_us >> 2); /* similar update on mdev */ } - tp->mdev += m; /* mdev = 3/4 mdev + 1/4 new */ - if (tp->mdev > tp->mdev_max) { - tp->mdev_max = tp->mdev; - if (tp->mdev_max > tp->rttvar) - tp->rttvar = tp->mdev_max; + tp->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ + if (tp->mdev_us > tp->mdev_max_us) { + tp->mdev_max_us = tp->mdev_us; + if (tp->mdev_max_us > tp->rttvar_us) + tp->rttvar_us = tp->mdev_max_us; } if (after(tp->snd_una, tp->rtt_seq)) { - if (tp->mdev_max < tp->rttvar) - tp->rttvar -= (tp->rttvar - tp->mdev_max) >> 2; + if (tp->mdev_max_us < tp->rttvar_us) + tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2; tp->rtt_seq = tp->snd_nxt; - tp->mdev_max = tcp_rto_min(sk); + tp->mdev_max_us = tcp_rto_min_us(sk); } } else { /* no previous measure. */ - tp->srtt = m << 3; /* take the measured time to be rtt */ - tp->mdev = m << 1; /* make sure rto = 3*rtt */ - tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); + srtt = m << 3; /* take the measured time to be rtt */ + tp->mdev_us = m << 1; /* make sure rto = 3*rtt */ + tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk)); + tp->mdev_max_us = tp->rttvar_us; tp->rtt_seq = tp->snd_nxt; } + tp->srtt_us = max(1U, srtt); } /* Set the sk_pacing_rate to allow proper sizing of TSO packets. @@ -742,18 +743,12 @@ static void tcp_update_pacing_rate(struct sock *sk) u64 rate; /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */ - rate = (u64)tp->mss_cache * 2 * (HZ << 3); + rate = (u64)tp->mss_cache * 2 * (USEC_PER_SEC << 3); rate *= max(tp->snd_cwnd, tp->packets_out); - /* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3), - * be conservative and assume srtt = 1 (125 us instead of 1.25 ms) - * We probably need usec resolution in the future. - * Note: This also takes care of possible srtt=0 case, - * when tcp_rtt_estimator() was not yet called. - */ - if (tp->srtt > 8 + 2) - do_div(rate, tp->srtt); + if (likely(tp->srtt_us)) + do_div(rate, tp->srtt_us); /* ACCESS_ONCE() is needed because sch_fq fetches sk_pacing_rate * without any lock. We want to make sure compiler wont store @@ -1111,7 +1106,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, } /* D-SACK for already forgotten data... Do dumb counting. */ - if (dup_sack && tp->undo_marker && tp->undo_retrans && + if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 && !after(end_seq_0, prior_snd_una) && after(end_seq_0, tp->undo_marker)) tp->undo_retrans--; @@ -1120,10 +1115,10 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, } struct tcp_sacktag_state { - int reord; - int fack_count; - int flag; - s32 rtt; /* RTT measured by SACKing never-retransmitted data */ + int reord; + int fack_count; + long rtt_us; /* RTT measured by SACKing never-retransmitted data */ + int flag; }; /* Check if skb is fully within the SACK block. In presence of GSO skbs, @@ -1167,12 +1162,12 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, unsigned int new_len = (pkt_len / mss) * mss; if (!in_sack && new_len < pkt_len) { new_len += mss; - if (new_len > skb->len) + if (new_len >= skb->len) return 0; } pkt_len = new_len; } - err = tcp_fragment(sk, skb, pkt_len, mss); + err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC); if (err < 0) return err; } @@ -1184,14 +1179,15 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, - int dup_sack, int pcount, u32 xmit_time) + int dup_sack, int pcount, + const struct skb_mstamp *xmit_time) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { - if (tp->undo_marker && tp->undo_retrans && + if (tp->undo_marker && tp->undo_retrans > 0 && after(end_seq, tp->undo_marker)) tp->undo_retrans--; if (sacked & TCPCB_SACKED_ACKED) @@ -1225,8 +1221,13 @@ static u8 tcp_sacktag_one(struct sock *sk, if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; /* Pick the earliest sequence sacked for RTT */ - if (state->rtt < 0) - state->rtt = tcp_time_stamp - xmit_time; + if (state->rtt_us < 0) { + struct skb_mstamp now; + + skb_mstamp_get(&now); + state->rtt_us = skb_mstamp_us_delta(&now, + xmit_time); + } } if (sacked & TCPCB_LOST) { @@ -1285,7 +1286,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, - TCP_SKB_CB(skb)->when); + &skb->skb_mstamp); if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; @@ -1563,7 +1564,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->end_seq, dup_sack, tcp_skb_pcount(skb), - TCP_SKB_CB(skb)->when); + &skb->skb_mstamp); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -1620,7 +1621,7 @@ static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_bl static int tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, - u32 prior_snd_una, s32 *sack_rtt) + u32 prior_snd_una, long *sack_rtt_us) { struct tcp_sock *tp = tcp_sk(sk); const unsigned char *ptr = (skb_transport_header(ack_skb) + @@ -1638,7 +1639,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, state.flag = 0; state.reord = tp->packets_out; - state.rtt = -1; + state.rtt_us = -1L; if (!tp->sacked_out) { if (WARN_ON(tp->fackets_out)) @@ -1822,7 +1823,7 @@ out: WARN_ON((int)tp->retrans_out < 0); WARN_ON((int)tcp_packets_in_flight(tp) < 0); #endif - *sack_rtt = state.rtt; + *sack_rtt_us = state.rtt_us; return state.flag; } @@ -1892,7 +1893,7 @@ static void tcp_clear_retrans_partial(struct tcp_sock *tp) tp->lost_out = 0; tp->undo_marker = 0; - tp->undo_retrans = 0; + tp->undo_retrans = -1; } void tcp_clear_retrans(struct tcp_sock *tp) @@ -1943,8 +1944,9 @@ void tcp_enter_loss(struct sock *sk, int how) if (skb == tcp_send_head(sk)) break; - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) tp->undo_marker = 0; + TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; @@ -2032,10 +2034,12 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag) * available, or RTO is scheduled to fire first. */ if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 || - (flag & FLAG_ECE) || !tp->srtt) + (flag & FLAG_ECE) || !tp->srtt_us) return false; - delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2)); + delay = max(usecs_to_jiffies(tp->srtt_us >> 5), + msecs_to_jiffies(2)); + if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay))) return false; @@ -2237,7 +2241,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) break; mss = skb_shinfo(skb)->gso_size; - err = tcp_fragment(sk, skb, (packets - oldcnt) * mss, mss); + err = tcp_fragment(sk, skb, (packets - oldcnt) * mss, + mss, GFP_ATOMIC); if (err < 0) break; cnt = packets; @@ -2660,7 +2665,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) tp->prior_ssthresh = 0; tp->undo_marker = tp->snd_una; - tp->undo_retrans = tp->retrans_out; + tp->undo_retrans = tp->retrans_out ? : -1; if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { if (!ece_ack) @@ -2680,13 +2685,12 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) bool recovered = !before(tp->snd_una, tp->high_seq); if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ - if (flag & FLAG_ORIG_SACK_ACKED) { - /* Step 3.b. A timeout is spurious if not all data are - * lost, i.e., never-retransmitted data are (s)acked. - */ - tcp_try_undo_loss(sk, true); + /* Step 3.b. A timeout is spurious if not all data are + * lost, i.e., never-retransmitted data are (s)acked. + */ + if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED)) return; - } + if (after(tp->snd_nxt, tp->high_seq) && (flag & FLAG_DATA_SACKED || is_dupack)) { tp->frto = 0; /* Loss was real: 2nd part of step 3.a */ @@ -2882,7 +2886,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, } static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, - s32 seq_rtt, s32 sack_rtt) + long seq_rtt_us, long sack_rtt_us) { const struct tcp_sock *tp = tcp_sk(sk); @@ -2892,10 +2896,10 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * is acked (RFC6298). */ if (flag & FLAG_RETRANS_DATA_ACKED) - seq_rtt = -1; + seq_rtt_us = -1L; - if (seq_rtt < 0) - seq_rtt = sack_rtt; + if (seq_rtt_us < 0) + seq_rtt_us = sack_rtt_us; /* RTTM Rule: A TSecr value received in a segment is used to * update the averaged RTT measurement only if the segment @@ -2903,14 +2907,14 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * left edge of the send window. * See draft-ietf-tcplw-high-performance-00, section 3.3. */ - if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && + if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) - seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr; + seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - tp->rx_opt.rcv_tsecr); - if (seq_rtt < 0) + if (seq_rtt_us < 0) return false; - tcp_rtt_estimator(sk, seq_rtt); + tcp_rtt_estimator(sk, seq_rtt_us); tcp_set_rto(sk); /* RFC6298: only reset backoff on valid RTT measurement. */ @@ -2922,22 +2926,23 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp) { struct tcp_sock *tp = tcp_sk(sk); - s32 seq_rtt = -1; + long seq_rtt_us = -1L; if (synack_stamp && !tp->total_retrans) - seq_rtt = tcp_time_stamp - synack_stamp; + seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - synack_stamp); /* If the ACK acks both the SYNACK and the (Fast Open'd) data packets * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack() */ - if (!tp->srtt) - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); + if (!tp->srtt_us) + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L); } -static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight) +static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { const struct inet_connection_sock *icsk = inet_csk(sk); - icsk->icsk_ca_ops->cong_avoid(sk, ack, acked, in_flight); + + icsk->icsk_ca_ops->cong_avoid(sk, ack, acked); tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp; } @@ -3020,26 +3025,27 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) * arrived at the other end. */ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, - u32 prior_snd_una, s32 sack_rtt) + u32 prior_snd_una, long sack_rtt_us) { - struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - struct sk_buff *skb; - u32 now = tcp_time_stamp; + struct skb_mstamp first_ackt, last_ackt, now; + struct tcp_sock *tp = tcp_sk(sk); + u32 prior_sacked = tp->sacked_out; + u32 reord = tp->packets_out; bool fully_acked = true; - int flag = 0; + long ca_seq_rtt_us = -1L; + long seq_rtt_us = -1L; + struct sk_buff *skb; u32 pkts_acked = 0; - u32 reord = tp->packets_out; - u32 prior_sacked = tp->sacked_out; - s32 seq_rtt = -1; - s32 ca_seq_rtt = -1; - ktime_t last_ackt = net_invalid_timestamp(); bool rtt_update; + int flag = 0; + + first_ackt.v64 = 0; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); - u32 acked_pcount; u8 sacked = scb->sacked; + u32 acked_pcount; /* Determine how many packets and what bytes were acked, tso and else */ if (after(scb->end_seq, tp->snd_una)) { @@ -3061,11 +3067,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->retrans_out -= acked_pcount; flag |= FLAG_RETRANS_DATA_ACKED; } else { - ca_seq_rtt = now - scb->when; - last_ackt = skb->tstamp; - if (seq_rtt < 0) { - seq_rtt = ca_seq_rtt; - } + last_ackt = skb->skb_mstamp; + WARN_ON_ONCE(last_ackt.v64 == 0); + if (!first_ackt.v64) + first_ackt = last_ackt; + if (!(sacked & TCPCB_SACKED_ACKED)) reord = min(pkts_acked, reord); if (!after(scb->end_seq, tp->high_seq)) @@ -3111,7 +3117,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt); + skb_mstamp_get(&now); + if (first_ackt.v64) { + seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt); + ca_seq_rtt_us = skb_mstamp_us_delta(&now, &last_ackt); + } + + rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us); if (flag & FLAG_ACKED) { const struct tcp_congestion_ops *ca_ops @@ -3139,25 +3151,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); - if (ca_ops->pkts_acked) { - s32 rtt_us = -1; - - /* Is the ACK triggering packet unambiguous? */ - if (!(flag & FLAG_RETRANS_DATA_ACKED)) { - /* High resolution needed and available? */ - if (ca_ops->flags & TCP_CONG_RTT_STAMP && - !ktime_equal(last_ackt, - net_invalid_timestamp())) - rtt_us = ktime_us_delta(ktime_get_real(), - last_ackt); - else if (ca_seq_rtt >= 0) - rtt_us = jiffies_to_usecs(ca_seq_rtt); - } + if (ca_ops->pkts_acked) + ca_ops->pkts_acked(sk, pkts_acked, ca_seq_rtt_us); - ca_ops->pkts_acked(sk, pkts_acked, rtt_us); - } - } else if (skb && rtt_update && sack_rtt >= 0 && - sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) { + } else if (skb && rtt_update && sack_rtt_us >= 0 && + sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -3367,12 +3365,11 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; - u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt; u32 prior_fackets; int prior_packets = tp->packets_out; const int prior_unsacked = tp->packets_out - tp->sacked_out; int acked = 0; /* Number of packets newly acked */ - s32 sack_rtt = -1; + long sack_rtt_us = -1L; /* If the ack is older than previous acks * then we can probably ignore it. @@ -3400,7 +3397,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= FLAG_SND_UNA_ADVANCED; prior_fackets = tp->fackets_out; - prior_in_flight = tcp_packets_in_flight(tp); /* ts_recent update must be made after we are sure that the packet * is in window. @@ -3430,7 +3426,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (TCP_SKB_CB(skb)->sacked) flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, - &sack_rtt); + &sack_rtt_us); if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb))) flag |= FLAG_ECE; @@ -3449,12 +3445,13 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ acked = tp->packets_out; - flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt); + flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, + sack_rtt_us); acked -= tp->packets_out; /* Advance cwnd if state allows */ if (tcp_may_raise_cwnd(sk, flag)) - tcp_cong_avoid(sk, ack, acked, prior_in_flight); + tcp_cong_avoid(sk, ack, acked); if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); @@ -3472,8 +3469,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (icsk->icsk_pending == ICSK_TIME_RETRANS) tcp_schedule_loss_probe(sk); - if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd) - tcp_update_pacing_rate(sk); + tcp_update_pacing_rate(sk); return 1; no_queue: @@ -3502,7 +3498,7 @@ old_ack: */ if (TCP_SKB_CB(skb)->sacked) { flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, - &sack_rtt); + &sack_rtt_us); tcp_fastretrans_alert(sk, acked, prior_unsacked, is_dupack, flag); } @@ -4416,7 +4412,7 @@ queue_and_out: if (eaten > 0) kfree_skb_partial(skb, fragstolen); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); return; } @@ -4706,28 +4702,6 @@ static int tcp_prune_queue(struct sock *sk) return -1; } -/* RFC2861, slow part. Adjust cwnd, after it was not full during one rto. - * As additional protections, we do not touch cwnd in retransmission phases, - * and if application hit its sndbuf limit recently. - */ -void tcp_cwnd_application_limited(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open && - sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { - /* Limited by application or receiver window. */ - u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk)); - u32 win_used = max(tp->snd_cwnd_used, init_win); - if (win_used < tp->snd_cwnd) { - tp->snd_ssthresh = tcp_current_ssthresh(sk); - tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1; - } - tp->snd_cwnd_used = 0; - } - tp->snd_cwnd_stamp = tcp_time_stamp; -} - static bool tcp_should_expand_sndbuf(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); @@ -4917,7 +4891,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t BUG(); tp->urg_data = TCP_URG_VALID | tmp; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } } } @@ -5003,11 +4977,11 @@ static bool tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb, (tcp_flag_word(tcp_hdr(skb)) & TCP_FLAG_PSH) || (atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1))) { tp->ucopy.wakeup = 1; - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } } else if (chunk > 0) { tp->ucopy.wakeup = 1; - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } out: return copied_early; @@ -5278,7 +5252,7 @@ no_ack: #endif if (eaten) kfree_skb_partial(skb, fragstolen); - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); return; } } @@ -5398,9 +5372,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, break; } tcp_rearm_rto(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; } tp->syn_data_acked = tp->syn_data; + if (tp->syn_data_acked) + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); return false; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3cf97651049..77cccda1ad0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -336,8 +336,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) const int code = icmp_hdr(icmp_skb)->code; struct sock *sk; struct sk_buff *skb; - struct request_sock *req; - __u32 seq; + struct request_sock *fastopen; + __u32 seq, snd_una; __u32 remaining; int err; struct net *net = dev_net(icmp_skb->dev); @@ -378,12 +378,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) icsk = inet_csk(sk); tp = tcp_sk(sk); - req = tp->fastopen_rsk; seq = ntohl(th->seq); + /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ + fastopen = tp->fastopen_rsk; + snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && - !between(seq, tp->snd_una, tp->snd_nxt) && - (req == NULL || seq != tcp_rsk(req)->snt_isn)) { - /* For a Fast Open socket, allow seq to be snt_isn. */ + !between(seq, snd_una, tp->snd_nxt)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -426,16 +426,14 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH) break; if (seq != tp->snd_una || !icsk->icsk_retransmits || - !icsk->icsk_backoff) + !icsk->icsk_backoff || fastopen) break; - /* XXX (TFO) - revisit the following logic for TFO */ - if (sock_owned_by_user(sk)) break; icsk->icsk_backoff--; - inet_csk(sk)->icsk_rto = (tp->srtt ? __tcp_set_rto(tp) : + inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT) << icsk->icsk_backoff; tcp_bound_rto(sk); @@ -462,14 +460,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) goto out; } - /* XXX (TFO) - if it's a TFO socket and has been accepted, rather - * than following the TCP_SYN_RECV case and closing the socket, - * we ignore the ICMP error and keep trying like a fully established - * socket. Is this the right thing to do? - */ - if (req && req->sk == NULL) - goto out; - switch (sk->sk_state) { struct request_sock *req, **prev; case TCP_LISTEN: @@ -502,10 +492,13 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) goto out; case TCP_SYN_SENT: - case TCP_SYN_RECV: /* Cannot happen. - It can f.e. if SYNs crossed, - or Fast Open. - */ + case TCP_SYN_RECV: + /* Only in fast or simultaneous open. If a fast open socket is + * is already accepted it is treated as a connected one below. + */ + if (fastopen && fastopen->sk == NULL) + break; + if (!sock_owned_by_user(sk)) { sk->sk_err = err; @@ -822,7 +815,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, */ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, - u16 queue_mapping) + u16 queue_mapping, + struct tcp_fastopen_cookie *foc) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; @@ -833,7 +827,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; - skb = tcp_make_synack(sk, dst, req, NULL); + skb = tcp_make_synack(sk, dst, req, foc); if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); @@ -852,10 +846,12 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req) { - int res = tcp_v4_send_synack(sk, NULL, req, 0); + int res = tcp_v4_send_synack(sk, NULL, req, 0, NULL); - if (!res) + if (!res) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + } return res; } @@ -878,8 +874,6 @@ bool tcp_syn_flood_action(struct sock *sk, bool want_cookie = false; struct listen_sock *lopt; - - #ifdef CONFIG_SYN_COOKIES if (sysctl_tcp_syncookies) { msg = "Sending cookies"; @@ -1260,187 +1254,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { }; #endif -static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct tcp_fastopen_cookie *foc, - struct tcp_fastopen_cookie *valid_foc) -{ - bool skip_cookie = false; - struct fastopen_queue *fastopenq; - - if (likely(!fastopen_cookie_present(foc))) { - /* See include/net/tcp.h for the meaning of these knobs */ - if ((sysctl_tcp_fastopen & TFO_SERVER_ALWAYS) || - ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD) && - (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1))) - skip_cookie = true; /* no cookie to validate */ - else - return false; - } - fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq; - /* A FO option is present; bump the counter. */ - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE); - - /* Make sure the listener has enabled fastopen, and we don't - * exceed the max # of pending TFO requests allowed before trying - * to validating the cookie in order to avoid burning CPU cycles - * unnecessarily. - * - * XXX (TFO) - The implication of checking the max_qlen before - * processing a cookie request is that clients can't differentiate - * between qlen overflow causing Fast Open to be disabled - * temporarily vs a server not supporting Fast Open at all. - */ - if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) == 0 || - fastopenq == NULL || fastopenq->max_qlen == 0) - return false; - - if (fastopenq->qlen >= fastopenq->max_qlen) { - struct request_sock *req1; - spin_lock(&fastopenq->lock); - req1 = fastopenq->rskq_rst_head; - if ((req1 == NULL) || time_after(req1->expires, jiffies)) { - spin_unlock(&fastopenq->lock); - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPFASTOPENLISTENOVERFLOW); - /* Avoid bumping LINUX_MIB_TCPFASTOPENPASSIVEFAIL*/ - foc->len = -1; - return false; - } - fastopenq->rskq_rst_head = req1->dl_next; - fastopenq->qlen--; - spin_unlock(&fastopenq->lock); - reqsk_free(req1); - } - if (skip_cookie) { - tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq; - return true; - } - - if (foc->len == TCP_FASTOPEN_COOKIE_SIZE) { - if ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_CHKED) == 0) { - tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, valid_foc); - if ((valid_foc->len != TCP_FASTOPEN_COOKIE_SIZE) || - memcmp(&foc->val[0], &valid_foc->val[0], - TCP_FASTOPEN_COOKIE_SIZE) != 0) - return false; - valid_foc->len = -1; - } - /* Acknowledge the data received from the peer. */ - tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq; - return true; - } else if (foc->len == 0) { /* Client requesting a cookie */ - tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, valid_foc); - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPFASTOPENCOOKIEREQD); - } else { - /* Client sent a cookie with wrong size. Treat it - * the same as invalid and return a valid one. - */ - tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, valid_foc); - } - return false; -} - -static int tcp_v4_conn_req_fastopen(struct sock *sk, - struct sk_buff *skb, - struct sk_buff *skb_synack, - struct request_sock *req) -{ - struct tcp_sock *tp = tcp_sk(sk); - struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; - const struct inet_request_sock *ireq = inet_rsk(req); - struct sock *child; - int err; - - req->num_retrans = 0; - req->num_timeout = 0; - req->sk = NULL; - - child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); - if (child == NULL) { - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPFASTOPENPASSIVEFAIL); - kfree_skb(skb_synack); - return -1; - } - err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr, - ireq->ir_rmt_addr, ireq->opt); - err = net_xmit_eval(err); - if (!err) - tcp_rsk(req)->snt_synack = tcp_time_stamp; - /* XXX (TFO) - is it ok to ignore error and continue? */ - - spin_lock(&queue->fastopenq->lock); - queue->fastopenq->qlen++; - spin_unlock(&queue->fastopenq->lock); - - /* Initialize the child socket. Have to fix some values to take - * into account the child is a Fast Open socket and is created - * only out of the bits carried in the SYN packet. - */ - tp = tcp_sk(child); - - tp->fastopen_rsk = req; - /* Do a hold on the listner sk so that if the listener is being - * closed, the child that has been accepted can live on and still - * access listen_lock. - */ - sock_hold(sk); - tcp_rsk(req)->listener = sk; - - /* RFC1323: The window in SYN & SYN/ACK segments is never - * scaled. So correct it appropriately. - */ - tp->snd_wnd = ntohs(tcp_hdr(skb)->window); - - /* Activate the retrans timer so that SYNACK can be retransmitted. - * The request socket is not added to the SYN table of the parent - * because it's been added to the accept queue directly. - */ - inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, - TCP_TIMEOUT_INIT, TCP_RTO_MAX); - - /* Add the child socket directly into the accept queue */ - inet_csk_reqsk_queue_add(sk, req, child); - - /* Now finish processing the fastopen child socket. */ - inet_csk(child)->icsk_af_ops->rebuild_header(child); - tcp_init_congestion_control(child); - tcp_mtup_init(child); - tcp_init_metrics(child); - tcp_init_buffer_space(child); - - /* Queue the data carried in the SYN packet. We need to first - * bump skb's refcnt because the caller will attempt to free it. - * - * XXX (TFO) - we honor a zero-payload TFO request for now. - * (Any reason not to?) - */ - if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq + 1) { - /* Don't queue the skb if there is no payload in SYN. - * XXX (TFO) - How about SYN+FIN? - */ - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; - } else { - skb = skb_get(skb); - skb_dst_drop(skb); - __skb_pull(skb, tcp_hdr(skb)->doff * 4); - skb_set_owner_r(skb, child); - __skb_queue_tail(&child->sk_receive_queue, skb); - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; - tp->syn_data_acked = 1; - } - sk->sk_data_ready(sk, 0); - bh_unlock_sock(child); - sock_put(child); - WARN_ON(req->sk == NULL); - return 0; -} - int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct tcp_options_received tmp_opt; @@ -1451,12 +1264,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) __be32 saddr = ip_hdr(skb)->saddr; __be32 daddr = ip_hdr(skb)->daddr; __u32 isn = TCP_SKB_CB(skb)->when; - bool want_cookie = false; + bool want_cookie = false, fastopen; struct flowi4 fl4; struct tcp_fastopen_cookie foc = { .len = -1 }; - struct tcp_fastopen_cookie valid_foc = { .len = -1 }; - struct sk_buff *skb_synack; - int do_fastopen; + int err; /* Never answer to SYNs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -1507,6 +1318,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq->ir_rmt_addr = saddr; ireq->no_srccheck = inet_sk(sk)->transparent; ireq->opt = tcp_v4_save_options(skb); + ireq->ir_mark = inet_request_mark(sk, skb); if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; @@ -1555,52 +1367,24 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) isn = tcp_v4_init_sequence(skb); } - tcp_rsk(req)->snt_isn = isn; - - if (dst == NULL) { - dst = inet_csk_route_req(sk, &fl4, req); - if (dst == NULL) - goto drop_and_free; - } - do_fastopen = tcp_fastopen_check(sk, skb, req, &foc, &valid_foc); - - /* We don't call tcp_v4_send_synack() directly because we need - * to make sure a child socket can be created successfully before - * sending back synack! - * - * XXX (TFO) - Ideally one would simply call tcp_v4_send_synack() - * (or better yet, call tcp_send_synack() in the child context - * directly, but will have to fix bunch of other code first) - * after syn_recv_sock() except one will need to first fix the - * latter to remove its dependency on the current implementation - * of tcp_v4_send_synack()->tcp_select_initial_window(). - */ - skb_synack = tcp_make_synack(sk, dst, req, - fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL); - - if (skb_synack) { - __tcp_v4_send_check(skb_synack, ireq->ir_loc_addr, ireq->ir_rmt_addr); - skb_set_queue_mapping(skb_synack, skb_get_queue_mapping(skb)); - } else + if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) goto drop_and_free; - if (likely(!do_fastopen)) { - int err; - err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr, - ireq->ir_rmt_addr, ireq->opt); - err = net_xmit_eval(err); + tcp_rsk(req)->snt_isn = isn; + tcp_rsk(req)->snt_synack = tcp_time_stamp; + tcp_openreq_init_rwin(req, sk, dst); + fastopen = !want_cookie && + tcp_try_fastopen(sk, skb, req, &foc, dst); + err = tcp_v4_send_synack(sk, dst, req, + skb_get_queue_mapping(skb), &foc); + if (!fastopen) { if (err || want_cookie) goto drop_and_free; tcp_rsk(req)->snt_synack = tcp_time_stamp; tcp_rsk(req)->listener = NULL; - /* Add the request_sock to the SYN table */ inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); - if (fastopen_cookie_present(&foc) && foc.len != 0) - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPFASTOPENPASSIVEFAIL); - } else if (tcp_v4_conn_req_fastopen(sk, skb, skb_synack, req)) - goto drop_and_free; + } return 0; @@ -1744,28 +1528,6 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) return sk; } -static __sum16 tcp_v4_checksum_init(struct sk_buff *skb) -{ - const struct iphdr *iph = ip_hdr(skb); - - if (skb->ip_summed == CHECKSUM_COMPLETE) { - if (!tcp_v4_check(skb->len, iph->saddr, - iph->daddr, skb->csum)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - return 0; - } - } - - skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb->len, IPPROTO_TCP, 0); - - if (skb->len <= 76) { - return __skb_checksum_complete(skb); - } - return 0; -} - - /* The socket must have it's spinlock held when we get * here. * @@ -1960,7 +1722,8 @@ int tcp_v4_rcv(struct sk_buff *skb) * Packet length and doff are validated by header prediction, * provided case of th->doff==0 is eliminated. * So, we defer the checks. */ - if (!skb_csum_unnecessary(skb) && tcp_v4_checksum_init(skb)) + + if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo)) goto csum_error; th = tcp_hdr(skb); @@ -2628,7 +2391,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw, { __be32 dest, src; __u16 destp, srcp; - long delta = tw->tw_ttd - jiffies; + s32 delta = tw->tw_ttd - inet_tw_time_stamp(); dest = tw->tw_daddr; src = tw->tw_rcv_saddr; diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 991d62a2f9b..1e70fa8fa79 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -115,13 +115,12 @@ static void tcp_lp_init(struct sock *sk) * Will only call newReno CA when away from inference. * From TCP-LP's paper, this will be handled in additive increasement. */ -static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 acked, - u32 in_flight) +static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct lp *lp = inet_csk_ca(sk); if (!(lp->flag & LP_WITHIN_INF)) - tcp_reno_cong_avoid(sk, ack, acked, in_flight); + tcp_reno_cong_avoid(sk, ack, acked); } /** @@ -315,11 +314,9 @@ static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, s32 rtt_us) } static struct tcp_congestion_ops tcp_lp __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_lp_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_lp_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .pkts_acked = tcp_lp_pkts_acked, .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index f7e522c558b..f7a2ec3ac58 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -102,17 +102,19 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) return 0; } -static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, - const char *buffer) +static ssize_t tcp_cgroup_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); unsigned long long val; int ret = 0; - switch (cft->private) { + buf = strstrip(buf); + + switch (of_cft(of)->private) { case RES_LIMIT: /* see memcontrol.c */ - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; ret = tcp_update_limit(memcg, val); @@ -121,7 +123,7 @@ static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, ret = -EINVAL; break; } - return ret; + return ret ?: nbytes; } static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val) @@ -168,17 +170,18 @@ static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft) return val; } -static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event) +static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg; struct cg_proto *cg_proto; - memcg = mem_cgroup_from_css(css); + memcg = mem_cgroup_from_css(of_css(of)); cg_proto = tcp_prot.proto_cgroup(memcg); if (!cg_proto) - return 0; + return nbytes; - switch (event) { + switch (of_cft(of)->private) { case RES_MAX_USAGE: res_counter_reset_max(&cg_proto->memory_allocated); break; @@ -187,13 +190,13 @@ static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event) break; } - return 0; + return nbytes; } static struct cftype tcp_files[] = { { .name = "kmem.tcp.limit_in_bytes", - .write_string = tcp_cgroup_write, + .write = tcp_cgroup_write, .read_u64 = tcp_cgroup_read, .private = RES_LIMIT, }, @@ -205,13 +208,13 @@ static struct cftype tcp_files[] = { { .name = "kmem.tcp.failcnt", .private = RES_FAILCNT, - .trigger = tcp_cgroup_reset, + .write = tcp_cgroup_reset, .read_u64 = tcp_cgroup_read, }, { .name = "kmem.tcp.max_usage_in_bytes", .private = RES_MAX_USAGE, - .trigger = tcp_cgroup_reset, + .write = tcp_cgroup_reset, .read_u64 = tcp_cgroup_read, }, { } /* terminate */ @@ -219,7 +222,7 @@ static struct cftype tcp_files[] = { static int __init tcp_memcontrol_init(void) { - WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, tcp_files)); + WARN_ON(cgroup_add_cftypes(&memory_cgrp_subsys, tcp_files)); return 0; } __initcall(tcp_memcontrol_init); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index d547075d830..4fe04180598 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -33,6 +33,11 @@ struct tcp_fastopen_metrics { struct tcp_fastopen_cookie cookie; }; +/* TCP_METRIC_MAX includes 2 extra fields for userspace compatibility + * Kernel only stores RTT and RTTVAR in usec resolution + */ +#define TCP_METRIC_MAX_KERNEL (TCP_METRIC_MAX - 2) + struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; struct inetpeer_addr tcpm_saddr; @@ -41,7 +46,7 @@ struct tcp_metrics_block { u32 tcpm_ts; u32 tcpm_ts_stamp; u32 tcpm_lock; - u32 tcpm_vals[TCP_METRIC_MAX + 1]; + u32 tcpm_vals[TCP_METRIC_MAX_KERNEL + 1]; struct tcp_fastopen_metrics tcpm_fastopen; struct rcu_head rcu_head; @@ -59,12 +64,6 @@ static u32 tcp_metric_get(struct tcp_metrics_block *tm, return tm->tcpm_vals[idx]; } -static u32 tcp_metric_get_jiffies(struct tcp_metrics_block *tm, - enum tcp_metric_index idx) -{ - return msecs_to_jiffies(tm->tcpm_vals[idx]); -} - static void tcp_metric_set(struct tcp_metrics_block *tm, enum tcp_metric_index idx, u32 val) @@ -72,13 +71,6 @@ static void tcp_metric_set(struct tcp_metrics_block *tm, tm->tcpm_vals[idx] = val; } -static void tcp_metric_set_msecs(struct tcp_metrics_block *tm, - enum tcp_metric_index idx, - u32 val) -{ - tm->tcpm_vals[idx] = jiffies_to_msecs(val); -} - static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { @@ -101,9 +93,11 @@ struct tcpm_hash_bucket { static DEFINE_SPINLOCK(tcp_metrics_lock); -static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst, +static void tcpm_suck_dst(struct tcp_metrics_block *tm, + const struct dst_entry *dst, bool fastopen_clear) { + u32 msval; u32 val; tm->tcpm_stamp = jiffies; @@ -121,8 +115,11 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst, val |= 1 << TCP_METRIC_REORDERING; tm->tcpm_lock = val; - tm->tcpm_vals[TCP_METRIC_RTT] = dst_metric_raw(dst, RTAX_RTT); - tm->tcpm_vals[TCP_METRIC_RTTVAR] = dst_metric_raw(dst, RTAX_RTTVAR); + msval = dst_metric_raw(dst, RTAX_RTT); + tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC; + + msval = dst_metric_raw(dst, RTAX_RTTVAR); + tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC; tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); @@ -384,7 +381,7 @@ void tcp_update_metrics(struct sock *sk) dst_confirm(dst); rcu_read_lock(); - if (icsk->icsk_backoff || !tp->srtt) { + if (icsk->icsk_backoff || !tp->srtt_us) { /* This session failed to estimate rtt. Why? * Probably, no packets returned in time. Reset our * results. @@ -399,8 +396,8 @@ void tcp_update_metrics(struct sock *sk) if (!tm) goto out_unlock; - rtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT); - m = rtt - tp->srtt; + rtt = tcp_metric_get(tm, TCP_METRIC_RTT); + m = rtt - tp->srtt_us; /* If newly calculated rtt larger than stored one, store new * one. Otherwise, use EWMA. Remember, rtt overestimation is @@ -408,10 +405,10 @@ void tcp_update_metrics(struct sock *sk) */ if (!tcp_metric_locked(tm, TCP_METRIC_RTT)) { if (m <= 0) - rtt = tp->srtt; + rtt = tp->srtt_us; else rtt -= (m >> 3); - tcp_metric_set_msecs(tm, TCP_METRIC_RTT, rtt); + tcp_metric_set(tm, TCP_METRIC_RTT, rtt); } if (!tcp_metric_locked(tm, TCP_METRIC_RTTVAR)) { @@ -422,16 +419,16 @@ void tcp_update_metrics(struct sock *sk) /* Scale deviation to rttvar fixed point */ m >>= 1; - if (m < tp->mdev) - m = tp->mdev; + if (m < tp->mdev_us) + m = tp->mdev_us; - var = tcp_metric_get_jiffies(tm, TCP_METRIC_RTTVAR); + var = tcp_metric_get(tm, TCP_METRIC_RTTVAR); if (m >= var) var = m; else var -= (var - m) >> 2; - tcp_metric_set_msecs(tm, TCP_METRIC_RTTVAR, var); + tcp_metric_set(tm, TCP_METRIC_RTTVAR, var); } if (tcp_in_initial_slowstart(tp)) { @@ -528,7 +525,7 @@ void tcp_init_metrics(struct sock *sk) tp->reordering = val; } - crtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT); + crtt = tcp_metric_get(tm, TCP_METRIC_RTT); rcu_read_unlock(); reset: /* The initial RTT measurement from the SYN/SYN-ACK is not ideal @@ -551,18 +548,20 @@ reset: * to low value, and then abruptly stops to do it and starts to delay * ACKs, wait for troubles. */ - if (crtt > tp->srtt) { + if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt >>= 3; + crtt /= 8 * USEC_PER_MSEC; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); - } else if (tp->srtt == 0) { + } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from * 3WHS. This is most likely due to retransmission, * including spurious one. Reset the RTO back to 3secs * from the more aggressive 1sec to avoid more spurious * retransmission. */ - tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK; + tp->rttvar_us = jiffies_to_usecs(TCP_TIMEOUT_FALLBACK); + tp->mdev_us = tp->mdev_max_us = tp->rttvar_us; + inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK; } /* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been @@ -809,10 +808,26 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS); if (!nest) goto nla_put_failure; - for (i = 0; i < TCP_METRIC_MAX + 1; i++) { - if (!tm->tcpm_vals[i]) + for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) { + u32 val = tm->tcpm_vals[i]; + + if (!val) continue; - if (nla_put_u32(msg, i + 1, tm->tcpm_vals[i]) < 0) + if (i == TCP_METRIC_RTT) { + if (nla_put_u32(msg, TCP_METRIC_RTT_US + 1, + val) < 0) + goto nla_put_failure; + n++; + val = max(val / 1000, 1U); + } + if (i == TCP_METRIC_RTTVAR) { + if (nla_put_u32(msg, TCP_METRIC_RTTVAR_US + 1, + val) < 0) + goto nla_put_failure; + n++; + val = max(val / 1000, 1U); + } + if (nla_put_u32(msg, i + 1, val) < 0) goto nla_put_failure; n++; } @@ -1144,10 +1159,7 @@ static void __net_exit tcp_net_metrics_exit(struct net *net) tm = next; } } - if (is_vmalloc_addr(net->ipv4.tcp_metrics_hash)) - vfree(net->ipv4.tcp_metrics_hash); - else - kfree(net->ipv4.tcp_metrics_hash); + kvfree(net->ipv4.tcp_metrics_hash); } static __net_initdata struct pernet_operations tcp_net_metrics_ops = { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7a436c517e4..e68e0d4af6c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -362,6 +362,37 @@ void tcp_twsk_destructor(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); +void tcp_openreq_init_rwin(struct request_sock *req, + struct sock *sk, struct dst_entry *dst) +{ + struct inet_request_sock *ireq = inet_rsk(req); + struct tcp_sock *tp = tcp_sk(sk); + __u8 rcv_wscale; + int mss = dst_metric_advmss(dst); + + if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) + mss = tp->rx_opt.user_mss; + + /* Set this up on the first call only */ + req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW); + + /* limit the window selection if the user enforce a smaller rx buffer */ + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0)) + req->window_clamp = tcp_full_space(sk); + + /* tcp_full_space because it is guaranteed to be the first packet */ + tcp_select_initial_window(tcp_full_space(sk), + mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), + &req->rcv_wnd, + &req->window_clamp, + ireq->wscale_ok, + &rcv_wscale, + dst_metric(dst, RTAX_INITRWND)); + ireq->rcv_wscale = rcv_wscale; +} +EXPORT_SYMBOL(tcp_openreq_init_rwin); + static inline void TCP_ECN_openreq_child(struct tcp_sock *tp, struct request_sock *req) { @@ -398,8 +429,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, tcp_init_wl(newtp, treq->rcv_isn); - newtp->srtt = 0; - newtp->mdev = TCP_TIMEOUT_INIT; + newtp->srtt_us = 0; + newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); newicsk->icsk_rto = TCP_TIMEOUT_INIT; newtp->packets_out = 0; @@ -745,7 +776,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, skb->len); /* Wakeup parent, send SIGIO */ if (state == TCP_SYN_RECV && child->sk_state != state) - parent->sk_data_ready(parent, 0); + parent->sk_data_ready(parent); } else { /* Alas, it is possible again, because we do lookup * in main socket hash table and lock on listening diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index b92b81718ca..55046ecd083 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -57,10 +57,12 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | SKB_GSO_GRE | + SKB_GSO_GRE_CSUM | SKB_GSO_IPIP | SKB_GSO_SIT | SKB_GSO_MPLS | SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM | 0) || !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))) goto out; @@ -97,9 +99,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, th->check = newcheck; if (skb->ip_summed != CHECKSUM_PARTIAL) - th->check = - csum_fold(csum_partial(skb_transport_header(skb), - thlen, skb->csum)); + th->check = gso_make_checksum(skb, ~th->check); seq += mss; if (copy_destructor) { @@ -133,8 +133,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, th->check = ~csum_fold((__force __wsum)((__force u32)th->check + (__force u32)delta)); if (skb->ip_summed != CHECKSUM_PARTIAL) - th->check = csum_fold(csum_partial(skb_transport_header(skb), - thlen, skb->csum)); + th->check = gso_make_checksum(skb, ~th->check); out: return segs; } @@ -310,7 +309,7 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff) th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; return tcp_gro_complete(skb); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 03d26b85eab..179b51e6bda 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -86,6 +86,9 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { tcp_rearm_rto(sk); } + + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, + tcp_skb_pcount(skb)); } /* SND.NXT, if window was not shrunk. @@ -269,6 +272,7 @@ EXPORT_SYMBOL(tcp_select_initial_window); static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 old_win = tp->rcv_wnd; u32 cur_win = tcp_receive_window(tp); u32 new_win = __tcp_select_window(sk); @@ -281,6 +285,9 @@ static u16 tcp_select_window(struct sock *sk) * * Relax Will Robinson. */ + if (new_win == 0) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPWANTZEROWINDOWADV); new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } tp->rcv_wnd = new_win; @@ -298,8 +305,14 @@ static u16 tcp_select_window(struct sock *sk) new_win >>= tp->rx_opt.rcv_wscale; /* If we advertise zero window, disable fast path. */ - if (new_win == 0) + if (new_win == 0) { tp->pred_flags = 0; + if (old_win) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPTOZEROWINDOWADV); + } else if (old_win == 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV); + } return new_win; } @@ -614,7 +627,7 @@ static unsigned int tcp_synack_options(struct sock *sk, if (unlikely(!ireq->tstamp_ok)) remaining -= TCPOLEN_SACKPERM_ALIGNED; } - if (foc != NULL) { + if (foc != NULL && foc->len >= 0) { u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { @@ -698,7 +711,8 @@ static void tcp_tsq_handler(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) - tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC); + tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle, + 0, GFP_ATOMIC); } /* * One tasklet per cpu tries to send more skbs. @@ -766,6 +780,17 @@ void tcp_release_cb(struct sock *sk) if (flags & (1UL << TCP_TSQ_DEFERRED)) tcp_tsq_handler(sk); + /* Here begins the tricky part : + * We are called from release_sock() with : + * 1) BH disabled + * 2) sk_lock.slock spinlock held + * 3) socket owned by us (sk->sk_lock.owned == 1) + * + * But following code is meant to be called from BH handlers, + * so we should keep BH disabled, but early release socket ownership + */ + sock_release_ownership(sk); + if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) { tcp_write_timer_handler(sk); __sock_put(sk); @@ -853,18 +878,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, BUG_ON(!skb || !tcp_skb_pcount(skb)); if (clone_it) { - const struct sk_buff *fclone = skb + 1; - - /* If congestion control is doing timestamping, we must - * take such a timestamp before we potentially clone/copy. - */ - if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP) - __net_timestamp(skb); - - if (unlikely(skb->fclone == SKB_FCLONE_ORIG && - fclone->fclone == SKB_FCLONE_CLONE)) - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); + skb_mstamp_get(&skb->skb_mstamp); if (unlikely(skb_cloned(skb))) skb = pskb_copy(skb, gfp_mask); @@ -872,6 +886,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb = skb_clone(skb, gfp_mask); if (unlikely(!skb)) return -ENOBUFS; + /* Our usage of tstamp should remain private */ + skb->tstamp.tv64 = 0; } inet = inet_sk(sk); @@ -958,7 +974,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); - err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl); + err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl); if (likely(err <= 0)) return err; @@ -1058,7 +1074,7 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de * Remember, these are still headerless SKBs at this point. */ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, - unsigned int mss_now) + unsigned int mss_now, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; @@ -1073,11 +1089,11 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, if (nsize < 0) nsize = 0; - if (skb_unclone(skb, GFP_ATOMIC)) + if (skb_unclone(skb, gfp)) return -ENOMEM; /* Get a new skb... force flag on. */ - buff = sk_stream_alloc_skb(sk, nsize, GFP_ATOMIC); + buff = sk_stream_alloc_skb(sk, nsize, gfp); if (buff == NULL) return -ENOMEM; /* We'll just try again later. */ @@ -1364,12 +1380,43 @@ unsigned int tcp_current_mss(struct sock *sk) return mss_now; } -/* Congestion window validation. (RFC2861) */ -static void tcp_cwnd_validate(struct sock *sk) +/* RFC2861, slow part. Adjust cwnd, after it was not full during one rto. + * As additional protections, we do not touch cwnd in retransmission phases, + * and if application hit its sndbuf limit recently. + */ +static void tcp_cwnd_application_limited(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open && + sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + /* Limited by application or receiver window. */ + u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk)); + u32 win_used = max(tp->snd_cwnd_used, init_win); + if (win_used < tp->snd_cwnd) { + tp->snd_ssthresh = tcp_current_ssthresh(sk); + tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1; + } + tp->snd_cwnd_used = 0; + } + tp->snd_cwnd_stamp = tcp_time_stamp; +} + +static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) { struct tcp_sock *tp = tcp_sk(sk); - if (tp->packets_out >= tp->snd_cwnd) { + /* Track the maximum number of outstanding packets in each + * window, and remember whether we were cwnd-limited then. + */ + if (!before(tp->snd_una, tp->max_packets_seq) || + tp->packets_out > tp->max_packets_out) { + tp->max_packets_out = tp->packets_out; + tp->max_packets_seq = tp->snd_nxt; + tp->is_cwnd_limited = is_cwnd_limited; + } + + if (tcp_is_cwnd_limited(sk)) { /* Network is feed fully. */ tp->snd_cwnd_used = 0; tp->snd_cwnd_stamp = tcp_time_stamp; @@ -1414,7 +1461,7 @@ static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now, * With Minshall's modification: all sent small packets are ACKed. */ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, - unsigned int mss_now, int nonagle) + int nonagle) { return partial && ((nonagle & TCP_NAGLE_CORK) || @@ -1446,7 +1493,7 @@ static unsigned int tcp_mss_split_point(const struct sock *sk, * to include this last segment in this skb. * Otherwise, we'll split the skb at last MSS boundary */ - if (tcp_nagle_check(partial != 0, tp, mss_now, nonagle)) + if (tcp_nagle_check(partial != 0, tp, nonagle)) return needed - partial; return needed; @@ -1509,7 +1556,7 @@ static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buf if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) return true; - if (!tcp_nagle_check(skb->len < cur_mss, tp, cur_mss, nonagle)) + if (!tcp_nagle_check(skb->len < cur_mss, tp, nonagle)) return true; return false; @@ -1578,7 +1625,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* All of a TSO frame must be composed of paged data. */ if (skb->len != skb->data_len) - return tcp_fragment(sk, skb, len, mss_now); + return tcp_fragment(sk, skb, len, mss_now, gfp); buff = sk_stream_alloc_skb(sk, 0, gfp); if (unlikely(buff == NULL)) @@ -1621,7 +1668,8 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, * * This algorithm is from John Heffner. */ -static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) +static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, + bool *is_cwnd_limited) { struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1685,6 +1733,9 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) if (!tp->tso_deferred) tp->tso_deferred = 1 | (jiffies << 1); + if (cong_win < send_win && cong_win < skb->len) + *is_cwnd_limited = true; + return true; send_now: @@ -1845,6 +1896,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, unsigned int tso_segs, sent_pkts; int cwnd_quota; int result; + bool is_cwnd_limited = false; sent_pkts = 0; @@ -1869,6 +1921,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) { + is_cwnd_limited = true; if (push_one == 2) /* Force out a loss probe pkt. */ cwnd_quota = 1; @@ -1885,7 +1938,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, nonagle : TCP_NAGLE_PUSH)))) break; } else { - if (!push_one && tcp_tso_should_defer(sk, skb)) + if (!push_one && + tcp_tso_should_defer(sk, skb, &is_cwnd_limited)) break; } @@ -1904,7 +1958,13 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (atomic_read(&sk->sk_wmem_alloc) > limit) { set_bit(TSQ_THROTTLED, &tp->tsq_flags); - break; + /* It is possible TX completion already happened + * before we set TSQ_THROTTLED, so we must + * test again the condition. + */ + smp_mb__after_atomic(); + if (atomic_read(&sk->sk_wmem_alloc) > limit) + break; } limit = mss_now; @@ -1944,7 +2004,7 @@ repair: /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk); - tcp_cwnd_validate(sk); + tcp_cwnd_validate(sk, is_cwnd_limited); return false; } return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk)); @@ -1955,7 +2015,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 timeout, tlp_time_stamp, rto_time_stamp; - u32 rtt = tp->srtt >> 3; + u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3); if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS)) return false; @@ -1977,7 +2037,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) /* Schedule a loss probe in 2*RTT for SACK capable connections * in Open state, that are either limited by cwnd or application. */ - if (sysctl_tcp_early_retrans < 3 || !rtt || !tp->packets_out || + if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out || !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open) return false; @@ -2008,6 +2068,25 @@ bool tcp_schedule_loss_probe(struct sock *sk) return true; } +/* Thanks to skb fast clones, we can detect if a prior transmit of + * a packet is still in a qdisc or driver queue. + * In this case, there is very little point doing a retransmit ! + * Note: This is called from BH context only. + */ +static bool skb_still_in_host_queue(const struct sock *sk, + const struct sk_buff *skb) +{ + const struct sk_buff *fclone = skb + 1; + + if (unlikely(skb->fclone == SKB_FCLONE_ORIG && + fclone->fclone == SKB_FCLONE_CLONE)) { + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); + return true; + } + return false; +} + /* When probe timeout (PTO) fires, send a new segment if one exists, else * retransmit the last segment. */ @@ -2033,12 +2112,16 @@ void tcp_send_loss_probe(struct sock *sk) if (WARN_ON(!skb)) goto rearm_timer; + if (skb_still_in_host_queue(sk, skb)) + goto rearm_timer; + pcount = tcp_skb_pcount(skb); if (WARN_ON(!pcount)) goto rearm_timer; if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) { - if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss))) + if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss, + GFP_ATOMIC))) goto rearm_timer; skb = tcp_write_queue_tail(sk); } @@ -2046,9 +2129,7 @@ void tcp_send_loss_probe(struct sock *sk) if (WARN_ON(!skb || !tcp_skb_pcount(skb))) goto rearm_timer; - /* Probe with zero data doesn't trigger fast recovery. */ - if (skb->len > 0) - err = __tcp_retransmit_skb(sk, skb); + err = __tcp_retransmit_skb(sk, skb); /* Record snd_nxt for loss detection. */ if (likely(!err)) @@ -2062,7 +2143,6 @@ rearm_timer: if (likely(!err)) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); - return; } /* Push out any pending frames which were held back due to @@ -2160,7 +2240,8 @@ u32 __tcp_select_window(struct sock *sk) */ int mss = icsk->icsk_ack.rcv_mss; int free_space = tcp_space(sk); - int full_space = min_t(int, tp->window_clamp, tcp_full_space(sk)); + int allowed_space = tcp_full_space(sk); + int full_space = min_t(int, tp->window_clamp, allowed_space); int window; if (mss > full_space) @@ -2173,7 +2254,19 @@ u32 __tcp_select_window(struct sock *sk) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); - if (free_space < mss) + /* free_space might become our new window, make sure we don't + * increase it due to wscale. + */ + free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale); + + /* if free space is less than mss estimate, or is below 1/16th + * of the maximum allowed, try to move to zero-window, else + * tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and + * new incoming data is dropped due to memory limits. + * With large window, mss test triggers way too late in order + * to announce zero window in time before rmem limit kicks in. + */ + if (free_space < (allowed_space >> 4) || free_space < mss) return 0; } @@ -2328,6 +2421,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); unsigned int cur_mss; + int err; /* Inconslusive MTU probe */ if (icsk->icsk_mtup.probe_size) { @@ -2341,6 +2435,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) return -EAGAIN; + if (skb_still_in_host_queue(sk, skb)) + return -EBUSY; + if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) BUG(); @@ -2363,7 +2460,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) return -EAGAIN; if (skb->len > cur_mss) { - if (tcp_fragment(sk, skb, cur_mss, cur_mss)) + if (tcp_fragment(sk, skb, cur_mss, cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ } else { int oldpcount = tcp_skb_pcount(skb); @@ -2391,11 +2488,21 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; } else { - return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + } + + if (likely(!err)) { + TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + /* Update global TCP statistics. */ + TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + tp->total_retrans++; } + return err; } int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) @@ -2404,11 +2511,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) int err = __tcp_retransmit_skb(sk, skb); if (err == 0) { - /* Update global TCP statistics. */ - TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); - - tp->total_retrans++; - #if FASTRETRANS_DEBUG > 0 if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { net_dbg_ratelimited("retrans_out leaked\n"); @@ -2423,15 +2525,17 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (!tp->retrans_stamp) tp->retrans_stamp = TCP_SKB_CB(skb)->when; - tp->undo_retrans += tcp_skb_pcount(skb); - /* snd_nxt is stored to detect loss of retransmitted segment, * see tcp_input.c tcp_sacktag_write_queue(). */ TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt; - } else { + } else if (err != -EBUSY) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); } + + if (tp->undo_retrans < 0) + tp->undo_retrans = 0; + tp->undo_retrans += tcp_skb_pcount(skb); return err; } @@ -2692,7 +2796,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, int tcp_header_size; int mss; - skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC); + skb = sock_wmalloc(sk, MAX_TCP_HEADER, 1, GFP_ATOMIC); if (unlikely(!skb)) { dst_release(dst); return NULL; @@ -2707,27 +2811,6 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) mss = tp->rx_opt.user_mss; - if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */ - __u8 rcv_wscale; - /* Set this up on the first call only */ - req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW); - - /* limit the window selection if the user enforce a smaller rx buffer */ - if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && - (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0)) - req->window_clamp = tcp_full_space(sk); - - /* tcp_full_space because it is guaranteed to be the first packet */ - tcp_select_initial_window(tcp_full_space(sk), - mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), - &req->rcv_wnd, - &req->window_clamp, - ireq->wscale_ok, - &rcv_wscale, - dst_metric(dst, RTAX_INITRWND)); - ireq->rcv_wscale = rcv_wscale; - } - memset(&opts, 0, sizeof(opts)); #ifdef CONFIG_SYN_COOKIES if (unlikely(req->cookie_ts)) @@ -2762,7 +2845,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, th->window = htons(min(req->rcv_wnd, 65535U)); tcp_options_write((__be32 *)(th + 1), tp, &opts); th->doff = (tcp_header_size >> 2); - TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ @@ -2899,7 +2982,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; - syn_data = skb_copy_expand(syn, skb_headroom(syn), space, + space = min_t(size_t, space, fo->size); + + /* limit to order-0 allocations */ + space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); + + syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space, sk->sk_allocation); if (syn_data == NULL) goto fallback; @@ -2929,9 +3017,15 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) tcp_connect_queue_skb(sk, data); fo->copied = data->len; + /* syn_data is about to be sent, we need to take current time stamps + * for the packets that are in write queue : SYN packet and DATA + */ + skb_mstamp_get(&syn->skb_mstamp); + data->skb_mstamp = syn->skb_mstamp; + if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { tp->syn_data = (fo->copied > 0); - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } syn_data = NULL; @@ -3019,8 +3113,9 @@ void tcp_send_delayed_ack(struct sock *sk) * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements * directly. */ - if (tp->srtt) { - int rtt = max(tp->srtt >> 3, TCP_DELACK_MIN); + if (tp->srtt_us) { + int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3), + TCP_DELACK_MIN); if (rtt < max_ato) max_ato = rtt; @@ -3148,7 +3243,7 @@ int tcp_write_wakeup(struct sock *sk) skb->len > mss) { seg_size = min(seg_size, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; - if (tcp_fragment(sk, skb, seg_size, mss)) + if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC)) return -1; } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(sk, skb, mss); diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 1f2d37613c9..3b66610d415 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -154,7 +154,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, p->snd_wnd = tp->snd_wnd; p->rcv_wnd = tp->rcv_wnd; p->ssthresh = tcp_current_ssthresh(sk); - p->srtt = tp->srtt >> 3; + p->srtt = tp->srtt_us >> 3; tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1); } diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 19ea6c2951f..8250949b885 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -15,12 +15,11 @@ #define TCP_SCALABLE_AI_CNT 50U #define TCP_SCALABLE_MD_SCALE 3 -static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked, - u32 in_flight) +static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); - if (!tcp_is_cwnd_limited(sk, in_flight)) + if (!tcp_is_cwnd_limited(sk)) return; if (tp->snd_cwnd <= tp->snd_ssthresh) @@ -39,7 +38,6 @@ static u32 tcp_scalable_ssthresh(struct sock *sk) static struct tcp_congestion_ops tcp_scalable __read_mostly = { .ssthresh = tcp_scalable_ssthresh, .cong_avoid = tcp_scalable_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .owner = THIS_MODULE, .name = "scalable", diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 64f0354c84c..286227abed1 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -165,6 +165,9 @@ static int tcp_write_timeout(struct sock *sk) dst_negative_advice(sk); if (tp->syn_fastopen || tp->syn_data) tcp_fastopen_cache_set(sk, 0, NULL, true); + if (tp->syn_data) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENACTIVEFAIL); } retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; syn_set = true; diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 06cae62bf20..9a5e05f27f4 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -163,14 +163,13 @@ static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp) return min(tp->snd_ssthresh, tp->snd_cwnd-1); } -static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked, - u32 in_flight) +static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct vegas *vegas = inet_csk_ca(sk); if (!vegas->doing_vegas_now) { - tcp_reno_cong_avoid(sk, ack, acked, in_flight); + tcp_reno_cong_avoid(sk, ack, acked); return; } @@ -195,7 +194,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked, /* We don't have enough RTT samples to do the Vegas * calculation, so we'll behave like Reno. */ - tcp_reno_cong_avoid(sk, ack, acked, in_flight); + tcp_reno_cong_avoid(sk, ack, acked); } else { u32 rtt, diff; u64 target_cwnd; @@ -306,11 +305,9 @@ void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) EXPORT_SYMBOL_GPL(tcp_vegas_get_info); static struct tcp_congestion_ops tcp_vegas __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_vegas_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_vegas_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .pkts_acked = tcp_vegas_pkts_acked, .set_state = tcp_vegas_state, .cwnd_event = tcp_vegas_cwnd_event, diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 326475a9486..27b9825753d 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -114,19 +114,18 @@ static void tcp_veno_cwnd_event(struct sock *sk, enum tcp_ca_event event) tcp_veno_init(sk); } -static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked, - u32 in_flight) +static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct veno *veno = inet_csk_ca(sk); if (!veno->doing_veno_now) { - tcp_reno_cong_avoid(sk, ack, acked, in_flight); + tcp_reno_cong_avoid(sk, ack, acked); return; } /* limited by applications */ - if (!tcp_is_cwnd_limited(sk, in_flight)) + if (!tcp_is_cwnd_limited(sk)) return; /* We do the Veno calculations only if we got enough rtt samples */ @@ -134,7 +133,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked, /* We don't have enough rtt samples to do the Veno * calculation, so we'll behave like Reno. */ - tcp_reno_cong_avoid(sk, ack, acked, in_flight); + tcp_reno_cong_avoid(sk, ack, acked); } else { u64 target_cwnd; u32 rtt; @@ -203,7 +202,6 @@ static u32 tcp_veno_ssthresh(struct sock *sk) } static struct tcp_congestion_ops tcp_veno __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_veno_init, .ssthresh = tcp_veno_ssthresh, .cong_avoid = tcp_veno_cong_avoid, diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index 76a1e23259e..b94a04ae2ed 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -276,7 +276,6 @@ static struct tcp_congestion_ops tcp_westwood __read_mostly = { .init = tcp_westwood_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, - .min_cwnd = tcp_westwood_bw_rttmin, .cwnd_event = tcp_westwood_event, .get_info = tcp_westwood_info, .pkts_acked = tcp_westwood_pkts_acked, diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 1a8d271f994..599b79b8eac 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -69,13 +69,12 @@ static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, s32 rtt_us) tcp_vegas_pkts_acked(sk, pkts_acked, rtt_us); } -static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked, - u32 in_flight) +static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct yeah *yeah = inet_csk_ca(sk); - if (!tcp_is_cwnd_limited(sk, in_flight)) + if (!tcp_is_cwnd_limited(sk)) return; if (tp->snd_cwnd <= tp->snd_ssthresh) @@ -227,11 +226,9 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) { } static struct tcp_congestion_ops tcp_yeah __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_yeah_init, .ssthresh = tcp_yeah_ssthresh, .cong_avoid = tcp_yeah_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .set_state = tcp_vegas_state, .cwnd_event = tcp_vegas_cwnd_event, .get_info = tcp_vegas_get_info, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 77bd16fa9f3..7d5a8661df7 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -246,7 +246,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, do { if (low <= snum && snum <= high && !test_bit(snum >> udptable->log, bitmap) && - !inet_is_reserved_local_port(snum)) + !inet_is_local_reserved_port(net, snum)) goto found; snum += rand; } while (snum != first); @@ -727,13 +727,12 @@ EXPORT_SYMBOL(udp_flush_pending_frames); void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) { struct udphdr *uh = udp_hdr(skb); - struct sk_buff *frags = skb_shinfo(skb)->frag_list; int offset = skb_transport_offset(skb); int len = skb->len - offset; int hlen = len; __wsum csum = 0; - if (!frags) { + if (!skb_has_frag_list(skb)) { /* * Only one fragment on the socket. */ @@ -742,15 +741,17 @@ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0); } else { + struct sk_buff *frags; + /* * HW-checksum won't work as there are two or more * fragments on the socket so that all csums of sk_buffs * should be together */ - do { + skb_walk_frags(skb, frags) { csum = csum_add(csum, frags->csum); hlen -= frags->len; - } while ((frags = frags->next)); + } csum = skb_checksum(skb, offset, hlen, csum); skb->ip_summed = CHECKSUM_NONE; @@ -762,6 +763,43 @@ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) } EXPORT_SYMBOL_GPL(udp4_hwcsum); +/* Function to set UDP checksum for an IPv4 UDP packet. This is intended + * for the simple case like when setting the checksum for a UDP tunnel. + */ +void udp_set_csum(bool nocheck, struct sk_buff *skb, + __be32 saddr, __be32 daddr, int len) +{ + struct udphdr *uh = udp_hdr(skb); + + if (nocheck) + uh->check = 0; + else if (skb_is_gso(skb)) + uh->check = ~udp_v4_check(len, saddr, daddr, 0); + else if (skb_dst(skb) && skb_dst(skb)->dev && + (skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) { + + BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); + + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + uh->check = ~udp_v4_check(len, saddr, daddr, 0); + } else { + __wsum csum; + + BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); + + uh->check = 0; + csum = skb_checksum(skb, 0, len, 0); + uh->check = udp_v4_check(len, saddr, daddr, csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + } +} +EXPORT_SYMBOL(udp_set_csum); + static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) { struct sock *sk = skb->sk; @@ -785,7 +823,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) if (is_udplite) /* UDP-Lite */ csum = udplite_csum(skb); - else if (sk->sk_no_check == UDP_CSUM_NOXMIT) { /* UDP csum disabled */ + else if (sk->sk_no_check_tx) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; @@ -931,7 +969,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sock_tx_timestamp(sk, &ipc.tx_flags); if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, + sk->sk_family == AF_INET6); if (err) return err; if (ipc.opt) @@ -1494,6 +1533,10 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) { int ret; + /* Verify checksum before giving to encap */ + if (udp_lib_checksum_complete(skb)) + goto csum_error; + ret = encap_rcv(sk, skb); if (ret <= 0) { UDP_INC_STATS_BH(sock_net(sk), @@ -1545,8 +1588,11 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto csum_error; - if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) + if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) { + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, + is_udplite); goto drop; + } rc = 0; @@ -1671,7 +1717,6 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) { - const struct iphdr *iph; int err; UDP_SKB_CB(skb)->partial_cov = 0; @@ -1683,22 +1728,8 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, return err; } - iph = ip_hdr(skb); - if (uh->check == 0) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - } else if (skb->ip_summed == CHECKSUM_COMPLETE) { - if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len, - proto, skb->csum)) - skb->ip_summed = CHECKSUM_UNNECESSARY; - } - if (!skb_csum_unnecessary(skb)) - skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb->len, proto, 0); - /* Probably, we should checksum udp header (it should be in cache - * in any case) and data in tiny packets (< rx copybreak). - */ - - return 0; + return skb_checksum_init_zero_check(skb, proto, uh->check, + inet_compute_pseudo); } /* @@ -1833,6 +1864,10 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask); struct udp_hslot *hslot = &udp_table.hash[slot]; + /* Do not bother scanning a too big list */ + if (hslot->count > 10) + return NULL; + rcu_read_lock(); begin: count = 0; @@ -1885,7 +1920,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum); unsigned int slot2 = hash2 & udp_table.mask; struct udp_hslot *hslot2 = &udp_table.hash2[slot2]; - INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr) + INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr); const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum); rcu_read_lock(); @@ -1978,7 +2013,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, int (*push_pending_frames)(struct sock *)) { struct udp_sock *up = udp_sk(sk); - int val; + int val, valbool; int err = 0; int is_udplite = IS_UDPLITE(sk); @@ -1988,6 +2023,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, if (get_user(val, (int __user *)optval)) return -EFAULT; + valbool = val ? 1 : 0; + switch (optname) { case UDP_CORK: if (val != 0) { @@ -2017,6 +2054,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, } break; + case UDP_NO_CHECK6_TX: + up->no_check6_tx = valbool; + break; + + case UDP_NO_CHECK6_RX: + up->no_check6_rx = valbool; + break; + /* * UDP-Lite's partial checksum coverage (RFC 3828). */ @@ -2099,6 +2144,14 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, val = up->encap_type; break; + case UDP_NO_CHECK6_TX: + val = up->no_check6_tx; + break; + + case UDP_NO_CHECK6_RX: + val = up->no_check6_rx; + break; + /* The following two cannot be changed on UDP sockets, the return is * always 0 (which corresponds to the full checksum coverage of UDP). */ case UDPLITE_SEND_CSCOV: @@ -2483,7 +2536,11 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); __be16 protocol = skb->protocol; netdev_features_t enc_features; - int outer_hlen; + int udp_offset, outer_hlen; + unsigned int oldlen; + bool need_csum; + + oldlen = (u16)~skb->len; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; @@ -2495,6 +2552,10 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, skb->mac_len = skb_inner_network_offset(skb); skb->protocol = htons(ETH_P_TEB); + need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); + if (need_csum) + skb->encap_hdr_csum = 1; + /* segment inner packet. */ enc_features = skb->dev->hw_enc_features & netif_skb_features(skb); segs = skb_mac_gso_segment(skb, enc_features); @@ -2505,10 +2566,11 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, } outer_hlen = skb_tnl_header_len(skb); + udp_offset = outer_hlen - tnl_hlen; skb = segs; do { struct udphdr *uh; - int udp_offset = outer_hlen - tnl_hlen; + int len; skb_reset_inner_headers(skb); skb->encapsulation = 1; @@ -2519,31 +2581,20 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_set_transport_header(skb, udp_offset); + len = skb->len - udp_offset; uh = udp_hdr(skb); - uh->len = htons(skb->len - udp_offset); - - /* csum segment if tunnel sets skb with csum. */ - if (protocol == htons(ETH_P_IP) && unlikely(uh->check)) { - struct iphdr *iph = ip_hdr(skb); + uh->len = htons(len); - uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - udp_offset, - IPPROTO_UDP, 0); - uh->check = csum_fold(skb_checksum(skb, udp_offset, - skb->len - udp_offset, 0)); - if (uh->check == 0) - uh->check = CSUM_MANGLED_0; + if (need_csum) { + __be32 delta = htonl(oldlen + len); - } else if (protocol == htons(ETH_P_IPV6)) { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); - u32 len = skb->len - udp_offset; + uh->check = ~csum_fold((__force __wsum) + ((__force u32)uh->check + + (__force u32)delta)); + uh->check = gso_make_checksum(skb, ~uh->check); - uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, - len, IPPROTO_UDP, 0); - uh->check = csum_fold(skb_checksum(skb, udp_offset, len, 0)); if (uh->check == 0) uh->check = CSUM_MANGLED_0; - skb->ip_summed = CHECKSUM_NONE; } skb->protocol = protocol; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 25f5cee3a08..546d2d439dd 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -17,6 +17,8 @@ static DEFINE_SPINLOCK(udp_offload_lock); static struct udp_offload_priv __rcu *udp_offload_base __read_mostly; +#define udp_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&udp_offload_lock)) + struct udp_offload_priv { struct udp_offload *offload; struct rcu_head rcu; @@ -54,7 +56,8 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, __wsum csum; if (skb->encapsulation && - skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) { + (skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) { segs = skb_udp_tunnel_segment(skb, features); goto out; } @@ -69,8 +72,10 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM | SKB_GSO_IPIP | - SKB_GSO_GRE | SKB_GSO_MPLS) || + SKB_GSO_GRE | SKB_GSO_GRE_CSUM | + SKB_GSO_MPLS) || !(type & (SKB_GSO_UDP)))) goto out; @@ -100,8 +105,7 @@ out: int udp_add_offload(struct udp_offload *uo) { - struct udp_offload_priv __rcu **head = &udp_offload_base; - struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_KERNEL); + struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_ATOMIC); if (!new_offload) return -ENOMEM; @@ -109,8 +113,8 @@ int udp_add_offload(struct udp_offload *uo) new_offload->offload = uo; spin_lock(&udp_offload_lock); - rcu_assign_pointer(new_offload->next, rcu_dereference(*head)); - rcu_assign_pointer(*head, new_offload); + new_offload->next = udp_offload_base; + rcu_assign_pointer(udp_offload_base, new_offload); spin_unlock(&udp_offload_lock); return 0; @@ -130,12 +134,12 @@ void udp_del_offload(struct udp_offload *uo) spin_lock(&udp_offload_lock); - uo_priv = rcu_dereference(*head); + uo_priv = udp_deref_protected(*head); for (; uo_priv != NULL; - uo_priv = rcu_dereference(*head)) { - + uo_priv = udp_deref_protected(*head)) { if (uo_priv->offload == uo) { - rcu_assign_pointer(*head, rcu_dereference(uo_priv->next)); + rcu_assign_pointer(*head, + udp_deref_protected(uo_priv->next)); goto unlock; } head = &uo_priv->next; @@ -196,6 +200,7 @@ unflush: } skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ + skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); pp = uo_priv->offload->callbacks.gro_receive(head, skb); out_unlock: diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 2c46acd4cc3..3b3efbda48e 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -70,7 +70,6 @@ static struct inet_protosw udplite4_protosw = { .protocol = IPPROTO_UDPLITE, .prot = &udplite_prot, .ops = &inet_dgram_ops, - .no_check = 0, /* must checksum (RFC 3828) */ .flags = INET_PROTOSW_PERMANENT, }; diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 1f12c8b4586..aac6197b7a7 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -37,15 +37,6 @@ drop: return NET_RX_DROP; } -int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, - int encap_type) -{ - XFRM_SPI_SKB_CB(skb)->family = AF_INET; - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); - return xfrm_input(skb, nexthdr, spi, encap_type); -} -EXPORT_SYMBOL(xfrm4_rcv_encap); - int xfrm4_transport_finish(struct sk_buff *skb, int async) { struct iphdr *iph = ip_hdr(skb); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 31b18152528..91771a7c802 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -15,65 +15,6 @@ #include <net/ip.h> #include <net/xfrm.h> -/* Informational hook. The decap is still done here. */ -static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly; -static DEFINE_MUTEX(xfrm4_mode_tunnel_input_mutex); - -int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -EEXIST; - int priority = handler->priority; - - mutex_lock(&xfrm4_mode_tunnel_input_mutex); - - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t->priority > priority) - break; - if (t->priority == priority) - goto err; - - } - - handler->next = *pprev; - rcu_assign_pointer(*pprev, handler); - - ret = 0; - -err: - mutex_unlock(&xfrm4_mode_tunnel_input_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_register); - -int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -ENOENT; - - mutex_lock(&xfrm4_mode_tunnel_input_mutex); - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t == handler) { - *pprev = handler->next; - ret = 0; - break; - } - } - mutex_unlock(&xfrm4_mode_tunnel_input_mutex); - synchronize_net(); - - return ret; -} -EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_deregister); - static inline void ipip_ecn_decapsulate(struct sk_buff *skb) { struct iphdr *inner_iph = ipip_hdr(skb); @@ -117,24 +58,18 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); - ip_select_ident(skb, dst->child, NULL); top_iph->ttl = ip4_dst_hoplimit(dst->child); top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; + ip_select_ident(skb, NULL); return 0; } -#define for_each_input_rcu(head, handler) \ - for (handler = rcu_dereference(head); \ - handler != NULL; \ - handler = rcu_dereference(handler->next)) - static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - struct xfrm_tunnel_notifier *handler; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) @@ -143,9 +78,6 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; - for_each_input_rcu(rcv_notify_handlers, handler) - handler->handler(skb); - err = skb_unclone(skb, GFP_ATOMIC); if (err) goto out; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index baa0f63731f..d5f6bd9a210 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -25,7 +25,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE) goto out; - if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->local_df) + if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->ignore_df) goto out; mtu = dst_mtu(skb_dst(skb)); @@ -62,10 +62,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) if (err) return err; - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED; - - skb->protocol = htons(ETH_P_IP); + IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE; return x->outer_mode->output2(x, skb); } @@ -73,27 +70,34 @@ EXPORT_SYMBOL(xfrm4_prepare_output); int xfrm4_output_finish(struct sk_buff *skb) { -#ifdef CONFIG_NETFILTER - if (!skb_dst(skb)->xfrm) { - IPCB(skb)->flags |= IPSKB_REROUTED; - return dst_output(skb); - } + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + skb->protocol = htons(ETH_P_IP); +#ifdef CONFIG_NETFILTER IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; #endif - skb->protocol = htons(ETH_P_IP); return xfrm_output(skb); } -int xfrm4_output(struct sk_buff *skb) +static int __xfrm4_output(struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); - struct xfrm_state *x = dst->xfrm; + struct xfrm_state *x = skb_dst(skb)->xfrm; + +#ifdef CONFIG_NETFILTER + if (!x) { + IPCB(skb)->flags |= IPSKB_REROUTED; + return dst_output(skb); + } +#endif + return x->outer_mode->afinfo->output_finish(skb); +} + +int xfrm4_output(struct sock *sk, struct sk_buff *skb) +{ return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, - NULL, dst->dev, - x->outer_mode->afinfo->output_finish, + NULL, skb_dst(skb)->dev, __xfrm4_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index e1a63930a96..6156f68a1e9 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -325,6 +325,7 @@ void __init xfrm4_init(void) xfrm4_state_init(); xfrm4_policy_init(); + xfrm4_protocol_init(); #ifdef CONFIG_SYSCTL register_pernet_subsys(&xfrm4_net_ops); #endif diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c new file mode 100644 index 00000000000..a2ce0101eaa --- /dev/null +++ b/net/ipv4/xfrm4_protocol.c @@ -0,0 +1,301 @@ +/* xfrm4_protocol.c - Generic xfrm protocol multiplexer. + * + * Copyright (C) 2013 secunet Security Networks AG + * + * Author: + * Steffen Klassert <steffen.klassert@secunet.com> + * + * Based on: + * net/ipv4/tunnel4.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/skbuff.h> +#include <net/icmp.h> +#include <net/ip.h> +#include <net/protocol.h> +#include <net/xfrm.h> + +static struct xfrm4_protocol __rcu *esp4_handlers __read_mostly; +static struct xfrm4_protocol __rcu *ah4_handlers __read_mostly; +static struct xfrm4_protocol __rcu *ipcomp4_handlers __read_mostly; +static DEFINE_MUTEX(xfrm4_protocol_mutex); + +static inline struct xfrm4_protocol __rcu **proto_handlers(u8 protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp4_handlers; + case IPPROTO_AH: + return &ah4_handlers; + case IPPROTO_COMP: + return &ipcomp4_handlers; + } + + return NULL; +} + +#define for_each_protocol_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) \ + +int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err) +{ + int ret; + struct xfrm4_protocol *handler; + struct xfrm4_protocol __rcu **head = proto_handlers(protocol); + + if (!head) + return 0; + + for_each_protocol_rcu(*head, handler) + if ((ret = handler->cb_handler(skb, err)) <= 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(xfrm4_rcv_cb); + +int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) +{ + int ret; + struct xfrm4_protocol *handler; + struct xfrm4_protocol __rcu **head = proto_handlers(nexthdr); + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + if (!head) + goto out; + + for_each_protocol_rcu(*head, handler) + if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) + return ret; + +out: + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} +EXPORT_SYMBOL(xfrm4_rcv_encap); + +static int xfrm4_esp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(esp4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_esp_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(esp4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static int xfrm4_ah_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(ah4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret;; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_ah_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(ah4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static int xfrm4_ipcomp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(ipcomp4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_ipcomp_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(ipcomp4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static const struct net_protocol esp4_protocol = { + .handler = xfrm4_esp_rcv, + .err_handler = xfrm4_esp_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static const struct net_protocol ah4_protocol = { + .handler = xfrm4_ah_rcv, + .err_handler = xfrm4_ah_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static const struct net_protocol ipcomp4_protocol = { + .handler = xfrm4_ipcomp_rcv, + .err_handler = xfrm4_ipcomp_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static struct xfrm_input_afinfo xfrm4_input_afinfo = { + .family = AF_INET, + .owner = THIS_MODULE, + .callback = xfrm4_rcv_cb, +}; + +static inline const struct net_protocol *netproto(unsigned char protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp4_protocol; + case IPPROTO_AH: + return &ah4_protocol; + case IPPROTO_COMP: + return &ipcomp4_protocol; + } + + return NULL; +} + +int xfrm4_protocol_register(struct xfrm4_protocol *handler, + unsigned char protocol) +{ + struct xfrm4_protocol __rcu **pprev; + struct xfrm4_protocol *t; + bool add_netproto = false; + int ret = -EEXIST; + int priority = handler->priority; + + if (!proto_handlers(protocol) || !netproto(protocol)) + return -EINVAL; + + mutex_lock(&xfrm4_protocol_mutex); + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm4_protocol_mutex))) + add_netproto = true; + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm4_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t->priority < priority) + break; + if (t->priority == priority) + goto err; + } + + handler->next = *pprev; + rcu_assign_pointer(*pprev, handler); + + ret = 0; + +err: + mutex_unlock(&xfrm4_protocol_mutex); + + if (add_netproto) { + if (inet_add_protocol(netproto(protocol), protocol)) { + pr_err("%s: can't add protocol\n", __func__); + ret = -EAGAIN; + } + } + + return ret; +} +EXPORT_SYMBOL(xfrm4_protocol_register); + +int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, + unsigned char protocol) +{ + struct xfrm4_protocol __rcu **pprev; + struct xfrm4_protocol *t; + int ret = -ENOENT; + + if (!proto_handlers(protocol) || !netproto(protocol)) + return -EINVAL; + + mutex_lock(&xfrm4_protocol_mutex); + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm4_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { + *pprev = handler->next; + ret = 0; + break; + } + } + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm4_protocol_mutex))) { + if (inet_del_protocol(netproto(protocol), protocol) < 0) { + pr_err("%s: can't remove protocol\n", __func__); + ret = -EAGAIN; + } + } + + mutex_unlock(&xfrm4_protocol_mutex); + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(xfrm4_protocol_deregister); + +void __init xfrm4_protocol_init(void) +{ + xfrm_input_register_afinfo(&xfrm4_input_afinfo); +} +EXPORT_SYMBOL(xfrm4_protocol_init); |