diff options
Diffstat (limited to 'net/ipv4')
47 files changed, 1122 insertions, 408 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 5a19aeb8609..7944df76845 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -488,7 +488,6 @@ config TCP_CONG_HTCP config TCP_CONG_HSTCP tristate "High Speed TCP" - depends on EXPERIMENTAL default n ---help--- Sally Floyd's High Speed TCP (RFC 3649) congestion control. @@ -499,7 +498,6 @@ config TCP_CONG_HSTCP config TCP_CONG_HYBLA tristate "TCP-Hybla congestion control algorithm" - depends on EXPERIMENTAL default n ---help--- TCP-Hybla is a sender-side only change that eliminates penalization of @@ -509,7 +507,6 @@ config TCP_CONG_HYBLA config TCP_CONG_VEGAS tristate "TCP Vegas" - depends on EXPERIMENTAL default n ---help--- TCP Vegas is a sender-side only change to TCP that anticipates @@ -520,7 +517,6 @@ config TCP_CONG_VEGAS config TCP_CONG_SCALABLE tristate "Scalable TCP" - depends on EXPERIMENTAL default n ---help--- Scalable TCP is a sender-side only change to TCP which uses a @@ -530,7 +526,6 @@ config TCP_CONG_SCALABLE config TCP_CONG_LP tristate "TCP Low Priority" - depends on EXPERIMENTAL default n ---help--- TCP Low Priority (TCP-LP), a distributed algorithm whose goal is @@ -540,7 +535,6 @@ config TCP_CONG_LP config TCP_CONG_VENO tristate "TCP Veno" - depends on EXPERIMENTAL default n ---help--- TCP Veno is a sender-side only enhancement of TCP to obtain better @@ -552,7 +546,6 @@ config TCP_CONG_VENO config TCP_CONG_YEAH tristate "YeAH TCP" - depends on EXPERIMENTAL select TCP_CONG_VEGAS default n ---help--- @@ -567,7 +560,6 @@ config TCP_CONG_YEAH config TCP_CONG_ILLINOIS tristate "TCP Illinois" - depends on EXPERIMENTAL default n ---help--- TCP-Illinois is a sender-side modification of TCP Reno for @@ -631,8 +623,7 @@ config DEFAULT_TCP_CONG default "cubic" config TCP_MD5SIG - bool "TCP: MD5 Signature Option support (RFC2385) (EXPERIMENTAL)" - depends on EXPERIMENTAL + bool "TCP: MD5 Signature Option support (RFC2385)" select CRYPTO select CRYPTO_MD5 ---help--- diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 24b384b7903..68f6a94f766 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -248,8 +248,12 @@ EXPORT_SYMBOL(inet_listen); u32 inet_ehash_secret __read_mostly; EXPORT_SYMBOL(inet_ehash_secret); +u32 ipv6_hash_secret __read_mostly; +EXPORT_SYMBOL(ipv6_hash_secret); + /* - * inet_ehash_secret must be set exactly once + * inet_ehash_secret must be set exactly once, and to a non nul value + * ipv6_hash_secret must be set exactly once. */ void build_ehash_secret(void) { @@ -259,25 +263,11 @@ void build_ehash_secret(void) get_random_bytes(&rnd, sizeof(rnd)); } while (rnd == 0); - cmpxchg(&inet_ehash_secret, 0, rnd); + if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) + get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); } EXPORT_SYMBOL(build_ehash_secret); -static inline int inet_netns_ok(struct net *net, __u8 protocol) -{ - const struct net_protocol *ipprot; - - if (net_eq(net, &init_net)) - return 1; - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot == NULL) { - /* raw IP is OK */ - return 1; - } - return ipprot->netns_ok; -} - /* * Create an inet socket. */ @@ -350,10 +340,6 @@ lookup_protocol: !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; - err = -EAFNOSUPPORT; - if (!inet_netns_ok(net, protocol)) - goto out_rcu_unlock; - sock->ops = answer->ops; answer_prot = answer->prot; answer_no_check = answer->no_check; @@ -1306,6 +1292,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_GRE | 0))) goto out; @@ -1333,7 +1320,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ops->callbacks.gso_segment(skb, features); rcu_read_unlock(); - if (!segs || IS_ERR(segs)) + if (IS_ERR_OR_NULL(segs)) goto out; skb = segs; @@ -1345,8 +1332,10 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (skb->next != NULL) iph->frag_off |= htons(IP_MF); offset += (skb->len - skb->mac_len - iph->ihl * 4); - } else - iph->id = htons(id++); + } else { + if (!(iph->frag_off & htons(IP_DF))) + iph->id = htons(id++); + } iph->tot_len = htons(skb->len - skb->mac_len); iph->check = 0; iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl); @@ -1590,7 +1579,7 @@ static const struct net_offload udp_offload = { static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, - .err_handler = ping_err, + .err_handler = icmp_err, .no_policy = 1, .netns_ok = 1, }; @@ -1705,12 +1694,11 @@ static struct packet_type ip_packet_type __read_mostly = { static int __init inet_init(void) { - struct sk_buff *dummy_skb; struct inet_protosw *q; struct list_head *r; int rc = -EINVAL; - BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb)); + 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) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index a0d8392491c..2e7f1948216 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -269,7 +269,11 @@ static void ah_input_done(struct crypto_async_request *base, int err) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); - skb_set_transport_header(skb, -ihl); + + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -317,8 +321,7 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) /* We are going to _remove_ AH header to keep sockets happy, * so... Later this can change. */ - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) goto out; skb->ip_summed = CHECKSUM_NONE; @@ -381,7 +384,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); - skb_set_transport_header(skb, -ihl); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); err = nexthdr; @@ -413,9 +419,12 @@ static void ah4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0); xfrm_state_put(x); } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 9547a273b9e..fea4929f620 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -928,24 +928,25 @@ static void parp_redo(struct sk_buff *skb) static int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct arphdr *arp; + const struct arphdr *arp; + + if (dev->flags & IFF_NOARP || + skb->pkt_type == PACKET_OTHERHOST || + skb->pkt_type == PACKET_LOOPBACK) + goto freeskb; + + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + goto out_of_mem; /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ if (!pskb_may_pull(skb, arp_hdr_len(dev))) goto freeskb; arp = arp_hdr(skb); - if (arp->ar_hln != dev->addr_len || - dev->flags & IFF_NOARP || - skb->pkt_type == PACKET_OTHERHOST || - skb->pkt_type == PACKET_LOOPBACK || - arp->ar_pln != 4) + if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4) goto freeskb; - skb = skb_share_check(skb, GFP_ATOMIC); - if (skb == NULL) - goto out_of_mem; - memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, skb, dev, NULL, arp_process); @@ -1404,14 +1405,14 @@ static const struct file_operations arp_seq_fops = { static int __net_init arp_net_init(struct net *net) { - if (!proc_net_fops_create(net, "arp", S_IRUGO, &arp_seq_fops)) + if (!proc_create("arp", S_IRUGO, net->proc_net, &arp_seq_fops)) return -ENOMEM; return 0; } static void __net_exit arp_net_exit(struct net *net) { - proc_net_remove(net, "arp"); + remove_proc_entry("arp", net->proc_net); } static struct pernet_operations arp_net_ops = { diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 424fafbc8cb..b28e863fe0a 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -85,3 +85,28 @@ out: return err; } EXPORT_SYMBOL(ip4_datagram_connect); + +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 flowi4 fl4; + struct rtable *rt; + + if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0)) + return; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; + rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, + 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); + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(ip4_datagram_release_cb); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a8e4f2665d5..5281314886c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -63,6 +63,7 @@ #include <net/ip_fib.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> +#include <net/addrconf.h> #include "fib_lookup.h" @@ -93,6 +94,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, + [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, }; #define IN4_ADDR_HSIZE_SHIFT 8 @@ -417,6 +419,10 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); } +static void check_lifetime(struct work_struct *work); + +static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime); + static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { @@ -462,6 +468,9 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, inet_hash_insert(dev_net(in_dev->dev), ifa); + cancel_delayed_work(&check_lifetime_work); + schedule_delayed_work(&check_lifetime_work, 0); + /* Send message first, then call notifier. Notifier will trigger FIB update, so that listeners of netlink will know about new ifaddr */ @@ -573,7 +582,107 @@ errout: return err; } -static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh) +#define INFINITY_LIFE_TIME 0xFFFFFFFF + +static void check_lifetime(struct work_struct *work) +{ + unsigned long now, next, next_sec, next_sched; + struct in_ifaddr *ifa; + struct hlist_node *node; + int i; + + now = jiffies; + next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); + + rcu_read_lock(); + for (i = 0; i < IN4_ADDR_HSIZE; i++) { + hlist_for_each_entry_rcu(ifa, node, + &inet_addr_lst[i], hash) { + unsigned long age; + + if (ifa->ifa_flags & IFA_F_PERMANENT) + continue; + + /* We try to batch several events at once. */ + age = (now - ifa->ifa_tstamp + + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + + if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && + age >= ifa->ifa_valid_lft) { + struct in_ifaddr **ifap ; + + rtnl_lock(); + for (ifap = &ifa->ifa_dev->ifa_list; + *ifap != NULL; ifap = &ifa->ifa_next) { + if (*ifap == ifa) + inet_del_ifa(ifa->ifa_dev, + ifap, 1); + } + rtnl_unlock(); + } else if (ifa->ifa_preferred_lft == + INFINITY_LIFE_TIME) { + continue; + } else if (age >= ifa->ifa_preferred_lft) { + if (time_before(ifa->ifa_tstamp + + ifa->ifa_valid_lft * HZ, next)) + next = ifa->ifa_tstamp + + ifa->ifa_valid_lft * HZ; + + if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) { + ifa->ifa_flags |= IFA_F_DEPRECATED; + rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); + } + } else if (time_before(ifa->ifa_tstamp + + ifa->ifa_preferred_lft * HZ, + next)) { + next = ifa->ifa_tstamp + + ifa->ifa_preferred_lft * HZ; + } + } + } + rcu_read_unlock(); + + next_sec = round_jiffies_up(next); + next_sched = next; + + /* If rounded timeout is accurate enough, accept it. */ + if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) + next_sched = next_sec; + + now = jiffies; + /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ + if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX)) + next_sched = now + ADDRCONF_TIMER_FUZZ_MAX; + + schedule_delayed_work(&check_lifetime_work, next_sched - now); +} + +static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, + __u32 prefered_lft) +{ + unsigned long timeout; + + ifa->ifa_flags &= ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); + + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) + ifa->ifa_valid_lft = timeout; + else + ifa->ifa_flags |= IFA_F_PERMANENT; + + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa->ifa_flags |= IFA_F_DEPRECATED; + ifa->ifa_preferred_lft = timeout; + } + ifa->ifa_tstamp = jiffies; + if (!ifa->ifa_cstamp) + ifa->ifa_cstamp = ifa->ifa_tstamp; +} + +static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, + __u32 *pvalid_lft, __u32 *pprefered_lft) { struct nlattr *tb[IFA_MAX+1]; struct in_ifaddr *ifa; @@ -633,24 +742,73 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh) else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); + if (tb[IFA_CACHEINFO]) { + struct ifa_cacheinfo *ci; + + ci = nla_data(tb[IFA_CACHEINFO]); + if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { + err = -EINVAL; + goto errout; + } + *pvalid_lft = ci->ifa_valid; + *pprefered_lft = ci->ifa_prefered; + } + return ifa; errout: return ERR_PTR(err); } +static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa) +{ + struct in_device *in_dev = ifa->ifa_dev; + struct in_ifaddr *ifa1, **ifap; + + if (!ifa->ifa_local) + return NULL; + + for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; + ifap = &ifa1->ifa_next) { + if (ifa1->ifa_mask == ifa->ifa_mask && + inet_ifa_match(ifa1->ifa_address, ifa) && + ifa1->ifa_local == ifa->ifa_local) + return ifa1; + } + return NULL; +} + static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); struct in_ifaddr *ifa; + struct in_ifaddr *ifa_existing; + __u32 valid_lft = INFINITY_LIFE_TIME; + __u32 prefered_lft = INFINITY_LIFE_TIME; ASSERT_RTNL(); - ifa = rtm_to_ifaddr(net, nlh); + ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft); if (IS_ERR(ifa)) return PTR_ERR(ifa); - return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); + 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. + */ + set_ifa_lifetime(ifa, valid_lft, prefered_lft); + return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); + } else { + inet_free_ifa(ifa); + + if (nlh->nlmsg_flags & NLM_F_EXCL || + !(nlh->nlmsg_flags & NLM_F_REPLACE)) + return -EEXIST; + + set_ifa_lifetime(ifa_existing, valid_lft, prefered_lft); + } + return 0; } /* @@ -852,6 +1010,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) ifa->ifa_prefixlen = 32; ifa->ifa_mask = inet_make_mask(32); } + set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ret = inet_set_ifa(dev, ifa); break; @@ -1190,6 +1349,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, ifa->ifa_dev = in_dev; ifa->ifa_scope = RT_SCOPE_HOST; memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); + set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, + INFINITY_LIFE_TIME); inet_insert_ifa(ifa); } } @@ -1246,11 +1407,30 @@ static size_t inet_nlmsg_size(void) + nla_total_size(IFNAMSIZ); /* IFA_LABEL */ } +static inline u32 cstamp_delta(unsigned long cstamp) +{ + return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; +} + +static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, + unsigned long tstamp, u32 preferred, u32 valid) +{ + struct ifa_cacheinfo ci; + + ci.cstamp = cstamp_delta(cstamp); + ci.tstamp = cstamp_delta(tstamp); + ci.ifa_prefered = preferred; + ci.ifa_valid = valid; + + return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); +} + static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, u32 portid, u32 seq, int event, unsigned int flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; + u32 preferred, valid; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); if (nlh == NULL) @@ -1259,10 +1439,31 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; - ifm->ifa_flags = ifa->ifa_flags|IFA_F_PERMANENT; + ifm->ifa_flags = ifa->ifa_flags; ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; + if (!(ifm->ifa_flags & IFA_F_PERMANENT)) { + preferred = ifa->ifa_preferred_lft; + valid = ifa->ifa_valid_lft; + if (preferred != INFINITY_LIFE_TIME) { + long tval = (jiffies - ifa->ifa_tstamp) / HZ; + + if (preferred > tval) + preferred -= tval; + else + preferred = 0; + if (valid != INFINITY_LIFE_TIME) { + if (valid > tval) + valid -= tval; + else + valid = 0; + } + } + } else { + preferred = INFINITY_LIFE_TIME; + valid = INFINITY_LIFE_TIME; + } if ((ifa->ifa_address && nla_put_be32(skb, IFA_ADDRESS, ifa->ifa_address)) || (ifa->ifa_local && @@ -1270,7 +1471,9 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, (ifa->ifa_broadcast && nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && - nla_put_string(skb, IFA_LABEL, ifa->ifa_label))) + nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || + put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp, + preferred, valid)) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -1988,6 +2191,8 @@ void __init devinet_init(void) register_gifconf(PF_INET, inet_gifconf); register_netdevice_notifier(&ip_netdev_notifier); + schedule_delayed_work(&check_lifetime_work, 0); + rtnl_af_register(&inet_af_ops); rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index b61e9deb7c7..3b4f0cd2e63 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -346,7 +346,10 @@ static int esp_input_done2(struct sk_buff *skb, int err) pskb_trim(skb, skb->len - alen - padlen - 2); __skb_pull(skb, hlen); - skb_set_transport_header(skb, -ihl); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); err = nexthdr[1]; @@ -499,9 +502,12 @@ static void esp4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 5cd75e2dab2..99f00d39d10 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -974,7 +974,7 @@ static void nl_fib_input(struct sk_buff *skb) nl_fib_lookup(frn, tb); - portid = NETLINK_CB(skb).portid; /* pid of sending process */ + portid = NETLINK_CB(skb).portid; /* netlink portid */ NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 31d771ca9a7..61e03da3e1f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2607,31 +2607,31 @@ static const struct file_operations fib_route_fops = { int __net_init fib_proc_init(struct net *net) { - if (!proc_net_fops_create(net, "fib_trie", S_IRUGO, &fib_trie_fops)) + if (!proc_create("fib_trie", S_IRUGO, net->proc_net, &fib_trie_fops)) goto out1; - if (!proc_net_fops_create(net, "fib_triestat", S_IRUGO, - &fib_triestat_fops)) + if (!proc_create("fib_triestat", S_IRUGO, net->proc_net, + &fib_triestat_fops)) goto out2; - if (!proc_net_fops_create(net, "route", S_IRUGO, &fib_route_fops)) + if (!proc_create("route", S_IRUGO, net->proc_net, &fib_route_fops)) goto out3; return 0; out3: - proc_net_remove(net, "fib_triestat"); + remove_proc_entry("fib_triestat", net->proc_net); out2: - proc_net_remove(net, "fib_trie"); + remove_proc_entry("fib_trie", net->proc_net); out1: return -ENOMEM; } void __net_exit fib_proc_exit(struct net *net) { - proc_net_remove(net, "fib_trie"); - proc_net_remove(net, "fib_triestat"); - proc_net_remove(net, "route"); + remove_proc_entry("fib_trie", net->proc_net); + remove_proc_entry("fib_triestat", net->proc_net); + remove_proc_entry("route", net->proc_net); } #endif /* CONFIG_PROC_FS */ diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c index 42a491055c7..7a4c710c4cd 100644 --- a/net/ipv4/gre.c +++ b/net/ipv4/gre.c @@ -19,6 +19,7 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/netdevice.h> +#include <linux/if_tunnel.h> #include <linux/spinlock.h> #include <net/protocol.h> #include <net/gre.h> @@ -26,6 +27,11 @@ static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly; static DEFINE_SPINLOCK(gre_proto_lock); +struct gre_base_hdr { + __be16 flags; + __be16 protocol; +}; +#define GRE_HEADER_SECTION 4 int gre_add_protocol(const struct gre_protocol *proto, u8 version) { @@ -112,12 +118,117 @@ static void gre_err(struct sk_buff *skb, u32 info) rcu_read_unlock(); } +static struct sk_buff *gre_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + netdev_features_t enc_features; + int ghl = GRE_HEADER_SECTION; + struct gre_base_hdr *greh; + int mac_len = skb->mac_len; + int tnl_hlen; + bool csum; + + if (unlikely(skb_shinfo(skb)->gso_type & + ~(SKB_GSO_TCPV4 | + SKB_GSO_TCPV6 | + SKB_GSO_UDP | + SKB_GSO_DODGY | + SKB_GSO_TCP_ECN | + SKB_GSO_GRE))) + goto out; + + if (unlikely(!pskb_may_pull(skb, sizeof(*greh)))) + goto out; + + greh = (struct gre_base_hdr *)skb_transport_header(skb); + + if (greh->flags & GRE_KEY) + ghl += GRE_HEADER_SECTION; + if (greh->flags & GRE_SEQ) + ghl += GRE_HEADER_SECTION; + if (greh->flags & GRE_CSUM) { + ghl += GRE_HEADER_SECTION; + csum = true; + } else + csum = false; + + /* setup inner skb. */ + if (greh->protocol == htons(ETH_P_TEB)) { + struct ethhdr *eth = eth_hdr(skb); + skb->protocol = eth->h_proto; + } else { + skb->protocol = greh->protocol; + } + + skb->encapsulation = 0; + + if (unlikely(!pskb_may_pull(skb, ghl))) + goto out; + __skb_pull(skb, ghl); + skb_reset_mac_header(skb); + skb_set_network_header(skb, skb_inner_network_offset(skb)); + skb->mac_len = skb_inner_network_offset(skb); + + /* segment inner packet. */ + enc_features = skb->dev->hw_enc_features & netif_skb_features(skb); + segs = skb_mac_gso_segment(skb, enc_features); + if (!segs || IS_ERR(segs)) + goto out; + + skb = segs; + tnl_hlen = skb_tnl_header_len(skb); + do { + __skb_push(skb, ghl); + if (csum) { + __be32 *pcsum; + + if (skb_has_shared_frag(skb)) { + int err; + + err = __skb_linearize(skb); + if (err) { + kfree_skb(segs); + segs = ERR_PTR(err); + goto out; + } + } + + greh = (struct gre_base_hdr *)(skb->data); + pcsum = (__be32 *)(greh + 1); + *pcsum = 0; + *(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0)); + } + __skb_push(skb, tnl_hlen - ghl); + + skb_reset_mac_header(skb); + skb_set_network_header(skb, mac_len); + skb->mac_len = mac_len; + } while ((skb = skb->next)); +out: + return segs; +} + +static int gre_gso_send_check(struct sk_buff *skb) +{ + if (!skb->encapsulation) + return -EINVAL; + return 0; +} + static const struct net_protocol net_gre_protocol = { .handler = gre_rcv, .err_handler = gre_err, .netns_ok = 1, }; +static const struct net_offload gre_offload = { + .callbacks = { + .gso_send_check = gre_gso_send_check, + .gso_segment = gre_gso_segment, + }, +}; + static int __init gre_init(void) { pr_info("GRE over IPv4 demultiplexor driver\n"); @@ -127,11 +238,18 @@ static int __init gre_init(void) return -EAGAIN; } + if (inet_add_offload(&gre_offload, IPPROTO_GRE)) { + pr_err("can't add protocol offload\n"); + inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); + return -EAGAIN; + } + return 0; } static void __exit gre_exit(void) { + inet_del_offload(&gre_offload, IPPROTO_GRE); inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 17ff9fd7cdd..3ac5dff7962 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -934,6 +934,29 @@ error: goto drop; } +void icmp_err(struct sk_buff *skb, u32 info) +{ + struct iphdr *iph = (struct iphdr *)skb->data; + struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2)); + int type = icmp_hdr(skb)->type; + int code = icmp_hdr(skb)->code; + struct net *net = dev_net(skb->dev); + + /* + * Use ping_err to handle all icmp errors except those + * triggered by ICMP_ECHOREPLY which sent from kernel. + */ + if (icmph->type != ICMP_ECHOREPLY) { + ping_err(skb, info); + return; + } + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ICMP, 0); + else if (type == ICMP_REDIRECT) + ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0); +} + /* * This table is the definition of how we handle ICMP. */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 736ab70fd17..d8c232794bc 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2646,24 +2646,25 @@ static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; - pde = proc_net_fops_create(net, "igmp", S_IRUGO, &igmp_mc_seq_fops); + pde = proc_create("igmp", S_IRUGO, net->proc_net, &igmp_mc_seq_fops); if (!pde) goto out_igmp; - pde = proc_net_fops_create(net, "mcfilter", S_IRUGO, &igmp_mcf_seq_fops); + pde = proc_create("mcfilter", S_IRUGO, net->proc_net, + &igmp_mcf_seq_fops); if (!pde) goto out_mcfilter; return 0; out_mcfilter: - proc_net_remove(net, "igmp"); + remove_proc_entry("igmp", net->proc_net); out_igmp: return -ENOMEM; } static void __net_exit igmp_net_exit(struct net *net) { - proc_net_remove(net, "mcfilter"); - proc_net_remove(net, "igmp"); + remove_proc_entry("mcfilter", net->proc_net); + remove_proc_entry("igmp", net->proc_net); } static struct pernet_operations igmp_net_ops = { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d0670f00d52..11cb4979a46 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -59,6 +59,8 @@ int inet_csk_bind_conflict(const struct sock *sk, struct sock *sk2; struct hlist_node *node; int reuse = sk->sk_reuse; + int reuseport = sk->sk_reuseport; + kuid_t uid = sock_i_uid((struct sock *)sk); /* * Unlike other sk lookup places we do not check @@ -73,8 +75,11 @@ int inet_csk_bind_conflict(const struct sock *sk, (!sk->sk_bound_dev_if || !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { - if (!reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) { + if ((!reuse || !sk2->sk_reuse || + sk2->sk_state == TCP_LISTEN) && + (!reuseport || !sk2->sk_reuseport || + (sk2->sk_state != TCP_TIME_WAIT && + !uid_eq(uid, sock_i_uid(sk2))))) { const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) || sk2_rcv_saddr == sk_rcv_saddr(sk)) @@ -106,6 +111,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) int ret, attempts = 5; struct net *net = sock_net(sk); int smallest_size = -1, smallest_rover; + kuid_t uid = sock_i_uid(sk); local_bh_disable(); if (!snum) { @@ -125,9 +131,12 @@ again: spin_lock(&head->lock); inet_bind_bucket_for_each(tb, node, &head->chain) if (net_eq(ib_net(tb), net) && tb->port == rover) { - if (tb->fastreuse > 0 && - sk->sk_reuse && - sk->sk_state != TCP_LISTEN && + if (((tb->fastreuse > 0 && + sk->sk_reuse && + sk->sk_state != TCP_LISTEN) || + (tb->fastreuseport > 0 && + sk->sk_reuseport && + uid_eq(tb->fastuid, uid))) && (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; smallest_rover = rover; @@ -185,14 +194,18 @@ tb_found: if (sk->sk_reuse == SK_FORCE_REUSE) goto success; - if (tb->fastreuse > 0 && - sk->sk_reuse && sk->sk_state != TCP_LISTEN && + if (((tb->fastreuse > 0 && + sk->sk_reuse && sk->sk_state != TCP_LISTEN) || + (tb->fastreuseport > 0 && + sk->sk_reuseport && uid_eq(tb->fastuid, uid))) && smallest_size == -1) { goto success; } else { ret = 1; if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) { - if (sk->sk_reuse && sk->sk_state != TCP_LISTEN && + if (((sk->sk_reuse && sk->sk_state != TCP_LISTEN) || + (tb->fastreuseport > 0 && + sk->sk_reuseport && uid_eq(tb->fastuid, uid))) && smallest_size != -1 && --attempts >= 0) { spin_unlock(&head->lock); goto again; @@ -212,9 +225,19 @@ tb_not_found: tb->fastreuse = 1; else tb->fastreuse = 0; - } else if (tb->fastreuse && - (!sk->sk_reuse || sk->sk_state == TCP_LISTEN)) - tb->fastreuse = 0; + if (sk->sk_reuseport) { + tb->fastreuseport = 1; + tb->fastuid = uid; + } else + tb->fastreuseport = 0; + } else { + if (tb->fastreuse && + (!sk->sk_reuse || sk->sk_state == TCP_LISTEN)) + tb->fastreuse = 0; + if (tb->fastreuseport && + (!sk->sk_reuseport || !uid_eq(tb->fastuid, uid))) + tb->fastreuseport = 0; + } success: if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, snum); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 4750d2b74d7..2e453bde699 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -73,8 +73,9 @@ EXPORT_SYMBOL(inet_frags_init); void inet_frags_init_net(struct netns_frags *nf) { nf->nqueues = 0; - atomic_set(&nf->mem, 0); + init_frag_mem_limit(nf); INIT_LIST_HEAD(&nf->lru_list); + spin_lock_init(&nf->lru_lock); } EXPORT_SYMBOL(inet_frags_init_net); @@ -91,6 +92,8 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f) local_bh_disable(); inet_frag_evictor(nf, f, true); local_bh_enable(); + + percpu_counter_destroy(&nf->mem); } EXPORT_SYMBOL(inet_frags_exit_net); @@ -98,9 +101,9 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) { write_lock(&f->lock); hlist_del(&fq->list); - list_del(&fq->lru_list); fq->net->nqueues--; write_unlock(&f->lock); + inet_frag_lru_del(fq); } void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) @@ -117,12 +120,8 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) EXPORT_SYMBOL(inet_frag_kill); static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f, - struct sk_buff *skb, int *work) + struct sk_buff *skb) { - if (work) - *work -= skb->truesize; - - atomic_sub(skb->truesize, &nf->mem); if (f->skb_free) f->skb_free(skb); kfree_skb(skb); @@ -133,6 +132,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, { struct sk_buff *fp; struct netns_frags *nf; + unsigned int sum, sum_truesize = 0; WARN_ON(!(q->last_in & INET_FRAG_COMPLETE)); WARN_ON(del_timer(&q->timer) != 0); @@ -143,13 +143,14 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, while (fp) { struct sk_buff *xp = fp->next; - frag_kfree_skb(nf, f, fp, work); + sum_truesize += fp->truesize; + frag_kfree_skb(nf, f, fp); fp = xp; } - + sum = sum_truesize + f->qsize; if (work) - *work -= f->qsize; - atomic_sub(f->qsize, &nf->mem); + *work -= sum; + sub_frag_mem_limit(q, sum); if (f->destructor) f->destructor(q); @@ -164,22 +165,23 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force) int work, evicted = 0; if (!force) { - if (atomic_read(&nf->mem) <= nf->high_thresh) + if (frag_mem_limit(nf) <= nf->high_thresh) return 0; } - work = atomic_read(&nf->mem) - nf->low_thresh; + work = frag_mem_limit(nf) - nf->low_thresh; while (work > 0) { - read_lock(&f->lock); + spin_lock(&nf->lru_lock); + if (list_empty(&nf->lru_list)) { - read_unlock(&f->lock); + spin_unlock(&nf->lru_lock); break; } q = list_first_entry(&nf->lru_list, struct inet_frag_queue, lru_list); atomic_inc(&q->refcnt); - read_unlock(&f->lock); + spin_unlock(&nf->lru_lock); spin_lock(&q->lock); if (!(q->last_in & INET_FRAG_COMPLETE)) @@ -233,9 +235,9 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, atomic_inc(&qp->refcnt); hlist_add_head(&qp->list, &f->hash[hash]); - list_add_tail(&qp->lru_list, &nf->lru_list); nf->nqueues++; write_unlock(&f->lock); + inet_frag_lru_add(nf, qp); return qp; } @@ -250,7 +252,8 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, q->net = nf; f->constructor(q, arg); - atomic_add(f->qsize, &nf->mem); + add_frag_mem_limit(q, f->qsize); + setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); atomic_set(&q->refcnt, 1); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index fa3ae814871..0ce0595d986 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -39,6 +39,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, write_pnet(&tb->ib_net, hold_net(net)); tb->port = snum; tb->fastreuse = 0; + tb->fastreuseport = 0; tb->num_owners = 0; INIT_HLIST_HEAD(&tb->owners); hlist_add_head(&tb->node, &head->chain); @@ -151,16 +152,16 @@ static inline int compute_score(struct sock *sk, struct net *net, if (net_eq(sock_net(sk), net) && inet->inet_num == hnum && !ipv6_only_sock(sk)) { __be32 rcv_saddr = inet->inet_rcv_saddr; - score = sk->sk_family == PF_INET ? 1 : 0; + score = sk->sk_family == PF_INET ? 2 : 1; if (rcv_saddr) { if (rcv_saddr != daddr) return -1; - score += 2; + score += 4; } if (sk->sk_bound_dev_if) { if (sk->sk_bound_dev_if != dif) return -1; - score += 2; + score += 4; } } return score; @@ -176,6 +177,7 @@ static inline int compute_score(struct sock *sk, struct net *net, struct sock *__inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, + const __be32 saddr, __be16 sport, const __be32 daddr, const unsigned short hnum, const int dif) { @@ -183,17 +185,29 @@ struct sock *__inet_lookup_listener(struct net *net, struct hlist_nulls_node *node; unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; - int score, hiscore; + int score, hiscore, matches = 0, reuseport = 0; + u32 phash = 0; rcu_read_lock(); begin: result = NULL; - hiscore = -1; + hiscore = 0; sk_nulls_for_each_rcu(sk, node, &ilb->head) { score = compute_score(sk, net, hnum, daddr, dif); if (score > hiscore) { result = sk; hiscore = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + phash = inet_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; + } + } else if (score == hiscore && reuseport) { + matches++; + if (((u64)phash * matches) >> 32 == 0) + result = sk; + phash = next_pseudo_random32(phash); } } /* @@ -501,7 +515,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, inet_bind_bucket_for_each(tb, node, &head->chain) { if (net_eq(ib_net(tb), net) && tb->port == port) { - if (tb->fastreuse >= 0) + if (tb->fastreuse >= 0 || + tb->fastreuseport >= 0) goto next_port; WARN_ON(hlist_empty(&tb->owners)); if (!check_established(death_row, sk, @@ -518,6 +533,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, break; } tb->fastreuse = -1; + tb->fastreuseport = -1; goto ok; next_port: diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index eb9d63a570c..b6d30acb600 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -122,7 +122,7 @@ int ip_frag_nqueues(struct net *net) int ip_frag_mem(struct net *net) { - return atomic_read(&net->ipv4.frags.mem); + return sum_frag_mem_limit(&net->ipv4.frags); } static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, @@ -161,13 +161,6 @@ static bool ip4_frag_match(struct inet_frag_queue *q, void *a) qp->user == arg->user; } -/* Memory Tracking Functions. */ -static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb) -{ - atomic_sub(skb->truesize, &nf->mem); - kfree_skb(skb); -} - static void ip4_frag_init(struct inet_frag_queue *q, void *a) { struct ipq *qp = container_of(q, struct ipq, q); @@ -340,6 +333,7 @@ static inline int ip_frag_too_far(struct ipq *qp) static int ip_frag_reinit(struct ipq *qp) { struct sk_buff *fp; + unsigned int sum_truesize = 0; if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) { atomic_inc(&qp->q.refcnt); @@ -349,9 +343,12 @@ static int ip_frag_reinit(struct ipq *qp) fp = qp->q.fragments; do { struct sk_buff *xp = fp->next; - frag_kfree_skb(qp->q.net, fp); + + sum_truesize += fp->truesize; + kfree_skb(fp); fp = xp; } while (fp); + sub_frag_mem_limit(&qp->q, sum_truesize); qp->q.last_in = 0; qp->q.len = 0; @@ -496,7 +493,8 @@ found: qp->q.fragments = next; qp->q.meat -= free_it->len; - frag_kfree_skb(qp->q.net, free_it); + sub_frag_mem_limit(&qp->q, free_it->truesize); + kfree_skb(free_it); } } @@ -519,7 +517,7 @@ found: qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; qp->ecn |= ecn; - atomic_add(skb->truesize, &qp->q.net->mem); + add_frag_mem_limit(&qp->q, skb->truesize); if (offset == 0) qp->q.last_in |= INET_FRAG_FIRST_IN; @@ -531,9 +529,7 @@ found: qp->q.meat == qp->q.len) return ip_frag_reasm(qp, prev, dev); - write_lock(&ip4_frags.lock); - list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list); - write_unlock(&ip4_frags.lock); + inet_frag_lru_move(&qp->q); return -EINPROGRESS; err: @@ -594,7 +590,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, goto out_oversize; /* Head of list must not be cloned. */ - if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC)) + if (skb_unclone(head, GFP_ATOMIC)) goto out_nomem; /* If the first fragment is fragmented itself, we split @@ -617,7 +613,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, head->len -= clone->len; clone->csum = 0; clone->ip_summed = head->ip_summed; - atomic_add(clone->truesize, &qp->q.net->mem); + add_frag_mem_limit(&qp->q, clone->truesize); } skb_push(head, head->data - skb_network_header(head)); @@ -645,7 +641,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, } fp = next; } - atomic_sub(sum_truesize, &qp->q.net->mem); + sub_frag_mem_limit(&qp->q, sum_truesize); head->next = NULL; head->dev = dev; @@ -851,14 +847,22 @@ static inline void ip4_frags_ctl_register(void) static int __net_init ipv4_frags_init_net(struct net *net) { - /* - * Fragment cache limits. We will commit 256K at one time. Should we - * cross that limit we will prune down to 192K. This should cope with - * even the most extreme cases without allowing an attacker to - * measurably harm machine performance. + /* Fragment cache limits. + * + * The fragment memory accounting code, (tries to) account for + * the real memory usage, by measuring both the size of frag + * queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue)) + * and the SKB's truesize. + * + * A 64K fragment consumes 129736 bytes (44*2944)+200 + * (1500 truesize == 2944, sizeof(struct ipq) == 200) + * + * We will commit 4MB at one time. Should we cross that limit + * we will prune down to 3MB, making room for approx 8 big 64K + * fragments 8x128k. */ - net->ipv4.frags.high_thresh = 256 * 1024; - net->ipv4.frags.low_thresh = 192 * 1024; + net->ipv4.frags.high_thresh = 4 * 1024 * 1024; + net->ipv4.frags.low_thresh = 3 * 1024 * 1024; /* * Important NOTE! Fragment queue must be destroyed before MSL expires. * RFC791 is wrong proposing to prolongate timer each fragment arrival diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 303012adf9e..d0ef0e674ec 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -735,10 +735,36 @@ drop: return 0; } +static struct sk_buff *handle_offloads(struct ip_tunnel *tunnel, struct sk_buff *skb) +{ + int err; + + if (skb_is_gso(skb)) { + err = skb_unclone(skb, GFP_ATOMIC); + if (unlikely(err)) + goto error; + skb_shinfo(skb)->gso_type |= SKB_GSO_GRE; + return skb; + } else if (skb->ip_summed == CHECKSUM_PARTIAL && + tunnel->parms.o_flags&GRE_CSUM) { + err = skb_checksum_help(skb); + if (unlikely(err)) + goto error; + } else if (skb->ip_summed != CHECKSUM_PARTIAL) + skb->ip_summed = CHECKSUM_NONE; + + return skb; + +error: + kfree_skb(skb); + return ERR_PTR(err); +} + static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats); struct ip_tunnel *tunnel = netdev_priv(dev); - const struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph; const struct iphdr *tiph; struct flowi4 fl4; u8 tos; @@ -751,10 +777,21 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev __be32 dst; int mtu; u8 ttl; + int err; + int pkt_len; - if (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(skb)) - goto tx_error; + skb = handle_offloads(tunnel, skb); + if (IS_ERR(skb)) { + dev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + + if (!skb->encapsulation) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } + + old_iph = ip_hdr(skb); if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -818,8 +855,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev ttl = tiph->ttl; tos = tiph->tos; - if (tos == 1) { - tos = 0; + if (tos & 0x1) { + tos &= ~0x1; if (skb->protocol == htons(ETH_P_IP)) tos = old_iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) @@ -853,7 +890,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb->protocol == htons(ETH_P_IP)) { df |= (old_iph->frag_off&htons(IP_DF)); - if ((old_iph->frag_off&htons(IP_DF)) && + if (!skb_is_gso(skb) && + (old_iph->frag_off&htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); ip_rt_put(rt); @@ -873,7 +911,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } } - if (mtu >= IPV6_MIN_MTU && mtu < skb->len - tunnel->hlen + gre_hlen) { + if (!skb_is_gso(skb) && + mtu >= IPV6_MIN_MTU && + mtu < skb->len - tunnel->hlen + gre_hlen) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; @@ -935,6 +975,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev iph->saddr = fl4.saddr; iph->ttl = ttl; + tunnel_ip_select_ident(skb, old_iph, &rt->dst); + if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) iph->ttl = old_iph->ttl; @@ -962,13 +1004,37 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev *ptr = tunnel->parms.o_key; ptr--; } - if (tunnel->parms.o_flags&GRE_CSUM) { + /* Skip GRE checksum if skb is getting offloaded. */ + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE) && + (tunnel->parms.o_flags&GRE_CSUM)) { + int offset = skb_transport_offset(skb); + + if (skb_has_shared_frag(skb)) { + err = __skb_linearize(skb); + if (err) + goto tx_error; + } + *ptr = 0; - *(__sum16 *)ptr = ip_compute_csum((void *)(iph+1), skb->len - sizeof(struct iphdr)); + *(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset, + skb->len - offset, + 0)); } } - iptunnel_xmit(skb, dev); + nf_reset(skb); + + pkt_len = skb->len - skb_transport_offset(skb); + err = ip_local_out(skb); + if (likely(net_xmit_eval(err) == 0)) { + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += pkt_len; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; + } return NETDEV_TX_OK; #if IS_ENABLED(CONFIG_IPV6) @@ -1038,6 +1104,11 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) mtu = 68; tunnel->hlen = addend; + /* TCP offload with GRE SEQ is not supported. */ + if (!(tunnel->parms.o_flags & GRE_SEQ)) { + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + } return mtu; } @@ -1587,6 +1658,9 @@ static void ipgre_tap_setup(struct net_device *dev) dev->iflink = 0; dev->features |= NETIF_F_NETNS_LOCAL; + + dev->features |= GRE_FEATURES; + dev->hw_features |= GRE_FEATURES; } static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index f1395a6fb35..87abd3e2bd3 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -208,13 +208,6 @@ static int ip_local_deliver_finish(struct sk_buff *skb) if (ipprot != NULL) { int ret; - if (!net_eq(net, &init_net) && !ipprot->netns_ok) { - net_info_ratelimited("%s: proto %d isn't netns-ready\n", - __func__, protocol); - kfree_skb(skb); - goto out; - } - if (!ipprot->no_policy) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { kfree_skb(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 3e98ed2bff5..5e12dca7b3d 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -598,6 +598,7 @@ slow_path: /* for offloaded checksums cleanup checksum before fragmentation */ if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb)) goto fail; + iph = ip_hdr(skb); left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index d3ab47e19a8..f01d1b1aff7 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -47,9 +47,12 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0); xfrm_state_put(x); } @@ -160,6 +163,7 @@ static const struct net_protocol ipcomp4_protocol = { .handler = xfrm4_rcv, .err_handler = ipcomp4_err, .no_policy = 1, + .netns_ok = 1, }; static int __init ipcomp4_init(void) diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index a2e50ae80b5..98cbc687701 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1394,7 +1394,7 @@ static int __init ip_auto_config(void) unsigned int i; #ifdef CONFIG_PROC_FS - proc_net_fops_create(&init_net, "pnp", S_IRUGO, &pnp_seq_fops); + proc_create("pnp", S_IRUGO, init_net.proc_net, &pnp_seq_fops); #endif /* CONFIG_PROC_FS */ if (!ic_enable) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 191fc24a745..8f024d41eef 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -472,7 +472,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ - const struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph; struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; @@ -486,6 +486,8 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb_checksum_help(skb)) goto tx_error; + old_iph = ip_hdr(skb); + if (tos & 1) tos = old_iph->tos; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a9454cbd953..5f95b3aa579 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -828,6 +828,49 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, return NULL; } +/* Look for a (*,*,oif) entry */ +static struct mfc_cache *ipmr_cache_find_any_parent(struct mr_table *mrt, + int vifi) +{ + int line = MFC_HASH(htonl(INADDR_ANY), htonl(INADDR_ANY)); + struct mfc_cache *c; + + list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) + if (c->mfc_origin == htonl(INADDR_ANY) && + c->mfc_mcastgrp == htonl(INADDR_ANY) && + c->mfc_un.res.ttls[vifi] < 255) + return c; + + return NULL; +} + +/* Look for a (*,G) entry */ +static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt, + __be32 mcastgrp, int vifi) +{ + int line = MFC_HASH(mcastgrp, htonl(INADDR_ANY)); + struct mfc_cache *c, *proxy; + + if (mcastgrp == htonl(INADDR_ANY)) + goto skip; + + list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) + if (c->mfc_origin == htonl(INADDR_ANY) && + c->mfc_mcastgrp == mcastgrp) { + if (c->mfc_un.res.ttls[vifi] < 255) + return c; + + /* It's ok if the vifi is part of the static tree */ + proxy = ipmr_cache_find_any_parent(mrt, + c->mfc_parent); + if (proxy && proxy->mfc_un.res.ttls[vifi] < 255) + return c; + } + +skip: + return ipmr_cache_find_any_parent(mrt, vifi); +} + /* * Allocate a multicast cache entry */ @@ -1053,7 +1096,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) * MFC cache manipulation by user space mroute daemon */ -static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) +static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) { int line; struct mfc_cache *c, *next; @@ -1062,7 +1105,8 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && - c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { + c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr && + (parent == -1 || parent == c->mfc_parent)) { list_del_rcu(&c->list); mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_cache_free(c); @@ -1073,7 +1117,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) } static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, - struct mfcctl *mfc, int mrtsock) + struct mfcctl *mfc, int mrtsock, int parent) { bool found = false; int line; @@ -1086,7 +1130,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, list_for_each_entry(c, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && - c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { + c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr && + (parent == -1 || parent == c->mfc_parent)) { found = true; break; } @@ -1103,7 +1148,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, return 0; } - if (!ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) + if (mfc->mfcc_mcastgrp.s_addr != htonl(INADDR_ANY) && + !ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) return -EINVAL; c = ipmr_cache_alloc(); @@ -1218,7 +1264,7 @@ static void mrtsock_destruct(struct sock *sk) int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { - int ret; + int ret, parent = 0; struct vifctl vif; struct mfcctl mfc; struct net *net = sock_net(sk); @@ -1287,16 +1333,22 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi */ case MRT_ADD_MFC: case MRT_DEL_MFC: + parent = -1; + case MRT_ADD_MFC_PROXY: + case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) return -EINVAL; if (copy_from_user(&mfc, optval, sizeof(mfc))) return -EFAULT; + if (parent == 0) + parent = mfc.mfcc_parent; rtnl_lock(); - if (optname == MRT_DEL_MFC) - ret = ipmr_mfc_delete(mrt, &mfc); + if (optname == MRT_DEL_MFC || optname == MRT_DEL_MFC_PROXY) + ret = ipmr_mfc_delete(mrt, &mfc, parent); else ret = ipmr_mfc_add(net, mrt, &mfc, - sk == rtnl_dereference(mrt->mroute_sk)); + sk == rtnl_dereference(mrt->mroute_sk), + parent); rtnl_unlock(); return ret; /* @@ -1749,17 +1801,28 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, { int psend = -1; int vif, ct; + int true_vifi = ipmr_find_vif(mrt, skb->dev); vif = cache->mfc_parent; cache->mfc_un.res.pkt++; cache->mfc_un.res.bytes += skb->len; + if (cache->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { + struct mfc_cache *cache_proxy; + + /* For an (*,G) entry, we only check that the incomming + * interface is part of the static tree. + */ + cache_proxy = ipmr_cache_find_any_parent(mrt, vif); + if (cache_proxy && + cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + goto forward; + } + /* * Wrong interface: drop packet and (maybe) send PIM assert. */ if (mrt->vif_table[vif].dev != skb->dev) { - int true_vifi; - if (rt_is_output_route(skb_rtable(skb))) { /* It is our own packet, looped back. * Very complicated situation... @@ -1776,7 +1839,6 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, } cache->mfc_un.res.wrong_if++; - true_vifi = ipmr_find_vif(mrt, skb->dev); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -1794,15 +1856,34 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, goto dont_forward; } +forward: mrt->vif_table[vif].pkt_in++; mrt->vif_table[vif].bytes_in += skb->len; /* * Forward the frame */ + if (cache->mfc_origin == htonl(INADDR_ANY) && + cache->mfc_mcastgrp == htonl(INADDR_ANY)) { + if (true_vifi >= 0 && + true_vifi != cache->mfc_parent && + ip_hdr(skb)->ttl > + cache->mfc_un.res.ttls[cache->mfc_parent]) { + /* It's an (*,*) entry and the packet is not coming from + * the upstream: forward the packet to the upstream + * only. + */ + psend = cache->mfc_parent; + goto last_forward; + } + goto dont_forward; + } for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { - if (ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { + /* For (*,G) entry, don't forward to the incoming interface */ + if ((cache->mfc_origin != htonl(INADDR_ANY) || + ct != true_vifi) && + ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); @@ -1813,6 +1894,7 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, psend = ct; } } +last_forward: if (psend != -1) { if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); @@ -1902,6 +1984,13 @@ int ip_mr_input(struct sk_buff *skb) /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); + if (cache == NULL) { + int vif = ipmr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr, + vif); + } /* * No usable cache entry @@ -2107,7 +2196,12 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, rcu_read_lock(); cache = ipmr_cache_find(mrt, saddr, daddr); + if (cache == NULL && skb->dev) { + int vif = ipmr_find_vif(mrt, skb->dev); + if (vif >= 0) + cache = ipmr_cache_find_any(mrt, daddr, vif); + } if (cache == NULL) { struct sk_buff *skb2; struct iphdr *iph; @@ -2609,16 +2703,16 @@ static int __net_init ipmr_net_init(struct net *net) #ifdef CONFIG_PROC_FS err = -ENOMEM; - if (!proc_net_fops_create(net, "ip_mr_vif", 0, &ipmr_vif_fops)) + if (!proc_create("ip_mr_vif", 0, net->proc_net, &ipmr_vif_fops)) goto proc_vif_fail; - if (!proc_net_fops_create(net, "ip_mr_cache", 0, &ipmr_mfc_fops)) + if (!proc_create("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_fops)) goto proc_cache_fail; #endif return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: - proc_net_remove(net, "ip_mr_vif"); + remove_proc_entry("ip_mr_vif", net->proc_net); proc_vif_fail: ipmr_rules_exit(net); #endif @@ -2629,8 +2723,8 @@ fail: static void __net_exit ipmr_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS - proc_net_remove(net, "ip_mr_cache"); - proc_net_remove(net, "ip_mr_vif"); + remove_proc_entry("ip_mr_cache", net->proc_net); + remove_proc_entry("ip_mr_vif", net->proc_net); #endif ipmr_rules_exit(net); } diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index d8d6f2a5bf1..ce2d43e1f09 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -241,8 +241,8 @@ config IP_NF_MANGLE To compile it as a module, choose M here. If unsure, say N. config IP_NF_TARGET_CLUSTERIP - tristate "CLUSTERIP target support (EXPERIMENTAL)" - depends on IP_NF_MANGLE && EXPERIMENTAL + tristate "CLUSTERIP target support" + depends on IP_NF_MANGLE depends on NF_CONNTRACK_IPV4 depends on NETFILTER_ADVANCED select NF_CONNTRACK_MARK diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 3ea4127404d..7dc6a974359 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -901,7 +901,7 @@ static int get_info(struct net *net, void __user *user, #endif t = try_then_request_module(xt_find_table_lock(net, NFPROTO_ARP, name), "arptable_%s", name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { struct arpt_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT @@ -958,7 +958,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, } t = xt_find_table_lock(net, NFPROTO_ARP, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", @@ -1001,7 +1001,7 @@ static int __do_replace(struct net *net, const char *name, t = try_then_request_module(xt_find_table_lock(net, NFPROTO_ARP, name), "arptable_%s", name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free_newinfo_counters_untrans; } @@ -1158,7 +1158,7 @@ static int do_add_counters(struct net *net, const void __user *user, } t = xt_find_table_lock(net, NFPROTO_ARP, name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } @@ -1646,7 +1646,7 @@ static int compat_get_entries(struct net *net, xt_compat_lock(NFPROTO_ARP); t = xt_find_table_lock(net, NFPROTO_ARP, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 17c5e06da66..3efcf87400c 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1090,7 +1090,7 @@ static int get_info(struct net *net, void __user *user, #endif t = try_then_request_module(xt_find_table_lock(net, AF_INET, name), "iptable_%s", name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { struct ipt_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT @@ -1149,7 +1149,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr, } t = xt_find_table_lock(net, AF_INET, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", private->number); if (get.size == private->size) @@ -1189,7 +1189,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, t = try_then_request_module(xt_find_table_lock(net, AF_INET, name), "iptable_%s", name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free_newinfo_counters_untrans; } @@ -1347,7 +1347,7 @@ do_add_counters(struct net *net, const void __user *user, } t = xt_find_table_lock(net, AF_INET, name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } @@ -1931,7 +1931,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr, xt_compat_lock(AF_INET); t = xt_find_table_lock(net, AF_INET, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; duprintf("t->private->number = %u\n", private->number); diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index b5ef3cba225..7d168dcbd13 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -88,10 +88,8 @@ static void ulog_send(unsigned int nlgroupnum) { ulog_buff_t *ub = &ulog_buffers[nlgroupnum]; - if (timer_pending(&ub->timer)) { - pr_debug("ulog_send: timer was pending, deleting\n"); - del_timer(&ub->timer); - } + pr_debug("ulog_send: timer is deleting\n"); + del_timer(&ub->timer); if (!ub->skb) { pr_debug("ulog_send: nothing to send\n"); @@ -426,10 +424,8 @@ static void __exit ulog_tg_exit(void) /* remove pending timers and free allocated skb's */ for (i = 0; i < ULOG_MAXNLGROUPS; i++) { ub = &ulog_buffers[i]; - if (timer_pending(&ub->timer)) { - pr_debug("timer was pending, deleting\n"); - del_timer(&ub->timer); - } + pr_debug("timer is deleting\n"); + del_timer(&ub->timer); if (ub->skb) { kfree_skb(ub->skb); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index fcdd0c2406e..2820aa18b54 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -100,7 +100,6 @@ static unsigned int ipv4_helper(unsigned int hooknum, enum ip_conntrack_info ctinfo; const struct nf_conn_help *help; const struct nf_conntrack_helper *helper; - unsigned int ret; /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(skb, &ctinfo); @@ -116,13 +115,8 @@ static unsigned int ipv4_helper(unsigned int hooknum, if (!helper) return NF_ACCEPT; - ret = helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb), - ct, ctinfo); - if (ret != NF_ACCEPT && (ret & NF_VERDICT_MASK) != NF_QUEUE) { - nf_log_packet(NFPROTO_IPV4, hooknum, skb, in, out, NULL, - "nf_ct_%s: dropping packet", helper->name); - } - return ret; + return helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb), + ct, ctinfo); } static unsigned int ipv4_confirm(unsigned int hooknum, @@ -420,54 +414,43 @@ static int ipv4_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_tcp4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_tcp4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_tcp4 :protocol register failed\n"); + pr_err("nf_conntrack_tcp4: pernet registration failed\n"); goto out_tcp; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_udp4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udp4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_udp4 :protocol register failed\n"); + pr_err("nf_conntrack_udp4: pernet registration failed\n"); goto out_udp; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_icmp); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_icmp); if (ret < 0) { - pr_err("nf_conntrack_l4proto_icmp4 :protocol register failed\n"); + pr_err("nf_conntrack_icmp4: pernet registration failed\n"); goto out_icmp; } - ret = nf_conntrack_l3proto_register(net, - &nf_conntrack_l3proto_ipv4); + ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv4); if (ret < 0) { - pr_err("nf_conntrack_l3proto_ipv4 :protocol register failed\n"); + pr_err("nf_conntrack_ipv4: pernet registration failed\n"); goto out_ipv4; } return 0; out_ipv4: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_icmp); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmp); out_icmp: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_udp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp4); out_udp: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_tcp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp4); out_tcp: return ret; } static void ipv4_net_exit(struct net *net) { - nf_conntrack_l3proto_unregister(net, - &nf_conntrack_l3proto_ipv4); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_icmp); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_udp4); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_tcp4); + nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmp); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp4); } static struct pernet_operations ipv4_net_ops = { @@ -500,16 +483,49 @@ static int __init nf_conntrack_l3proto_ipv4_init(void) pr_err("nf_conntrack_ipv4: can't register hooks.\n"); goto cleanup_pernet; } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp4); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register tcp4 proto.\n"); + goto cleanup_hooks; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp4); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register udp4 proto.\n"); + goto cleanup_tcp4; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmp); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register icmpv4 proto.\n"); + goto cleanup_udp4; + } + + ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv4); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register ipv4 proto.\n"); + goto cleanup_icmpv4; + } + #if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) ret = nf_conntrack_ipv4_compat_init(); if (ret < 0) - goto cleanup_hooks; + goto cleanup_proto; #endif return ret; #if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) + cleanup_proto: + nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4); +#endif + cleanup_icmpv4: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmp); + cleanup_udp4: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4); + cleanup_tcp4: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4); cleanup_hooks: nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); -#endif cleanup_pernet: unregister_pernet_subsys(&ipv4_net_ops); cleanup_sockopt: @@ -523,6 +539,10 @@ static void __exit nf_conntrack_l3proto_ipv4_fini(void) #if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) nf_conntrack_ipv4_compat_fini(); #endif + nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmp); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4); nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); unregister_pernet_subsys(&ipv4_net_ops); nf_unregister_sockopt(&so_getorigdst); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 9682b36df38..f2ca1279408 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -417,12 +417,12 @@ static int __net_init ip_conntrack_net_init(struct net *net) { struct proc_dir_entry *proc, *proc_exp, *proc_stat; - proc = proc_net_fops_create(net, "ip_conntrack", 0440, &ct_file_ops); + proc = proc_create("ip_conntrack", 0440, net->proc_net, &ct_file_ops); if (!proc) goto err1; - proc_exp = proc_net_fops_create(net, "ip_conntrack_expect", 0440, - &ip_exp_file_ops); + proc_exp = proc_create("ip_conntrack_expect", 0440, net->proc_net, + &ip_exp_file_ops); if (!proc_exp) goto err2; @@ -433,9 +433,9 @@ static int __net_init ip_conntrack_net_init(struct net *net) return 0; err3: - proc_net_remove(net, "ip_conntrack_expect"); + remove_proc_entry("ip_conntrack_expect", net->proc_net); err2: - proc_net_remove(net, "ip_conntrack"); + remove_proc_entry("ip_conntrack", net->proc_net); err1: return -ENOMEM; } @@ -443,8 +443,8 @@ err1: static void __net_exit ip_conntrack_net_exit(struct net *net) { remove_proc_entry("ip_conntrack", net->proc_net_stat); - proc_net_remove(net, "ip_conntrack_expect"); - proc_net_remove(net, "ip_conntrack"); + remove_proc_entry("ip_conntrack_expect", net->proc_net); + remove_proc_entry("ip_conntrack", net->proc_net); } static struct pernet_operations ip_conntrack_net_ops = { diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 8f3d05424a3..2e91006d607 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -322,8 +322,8 @@ void ping_err(struct sk_buff *skb, u32 info) struct iphdr *iph = (struct iphdr *)skb->data; struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2)); struct inet_sock *inet_sock; - int type = icmph->type; - int code = icmph->code; + int type = icmp_hdr(skb)->type; + int code = icmp_hdr(skb)->code; struct net *net = dev_net(skb->dev); struct sock *sk; int harderr; @@ -738,6 +738,7 @@ struct proto ping_prot = { .recvmsg = ping_recvmsg, .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = ping_v4_hash, .unhash = ping_v4_unhash, .get_port = ping_v4_get_port, @@ -888,7 +889,7 @@ static int ping_proc_register(struct net *net) struct proc_dir_entry *p; int rc = 0; - p = proc_net_fops_create(net, "icmp", S_IRUGO, &ping_seq_fops); + p = proc_create("icmp", S_IRUGO, net->proc_net, &ping_seq_fops); if (!p) rc = -ENOMEM; return rc; @@ -896,7 +897,7 @@ static int ping_proc_register(struct net *net) static void ping_proc_unregister(struct net *net) { - proc_net_remove(net, "icmp"); + remove_proc_entry("icmp", net->proc_net); } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 8de53e1ddd5..32030a24e77 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -471,28 +471,29 @@ static const struct file_operations netstat_seq_fops = { static __net_init int ip_proc_init_net(struct net *net) { - if (!proc_net_fops_create(net, "sockstat", S_IRUGO, &sockstat_seq_fops)) + if (!proc_create("sockstat", S_IRUGO, net->proc_net, + &sockstat_seq_fops)) goto out_sockstat; - if (!proc_net_fops_create(net, "netstat", S_IRUGO, &netstat_seq_fops)) + if (!proc_create("netstat", S_IRUGO, net->proc_net, &netstat_seq_fops)) goto out_netstat; - if (!proc_net_fops_create(net, "snmp", S_IRUGO, &snmp_seq_fops)) + if (!proc_create("snmp", S_IRUGO, net->proc_net, &snmp_seq_fops)) goto out_snmp; return 0; out_snmp: - proc_net_remove(net, "netstat"); + remove_proc_entry("netstat", net->proc_net); out_netstat: - proc_net_remove(net, "sockstat"); + remove_proc_entry("sockstat", net->proc_net); out_sockstat: return -ENOMEM; } static __net_exit void ip_proc_exit_net(struct net *net) { - proc_net_remove(net, "snmp"); - proc_net_remove(net, "netstat"); - proc_net_remove(net, "sockstat"); + remove_proc_entry("snmp", net->proc_net); + remove_proc_entry("netstat", net->proc_net); + remove_proc_entry("sockstat", net->proc_net); } static __net_initdata struct pernet_operations ip_proc_ops = { diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index 0f9d09f54bd..ce848461acb 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -37,6 +37,12 @@ const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly; int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) { + if (!prot->netns_ok) { + pr_err("Protocol %u is not namespace aware, cannot register.\n", + protocol); + return -EINVAL; + } + return !cmpxchg((const struct net_protocol **)&inet_protos[protocol], NULL, prot) ? 0 : -1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 73d1e4df4bf..53ddebc292b 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -894,6 +894,7 @@ struct proto raw_prot = { .recvmsg = raw_recvmsg, .bind = raw_bind, .backlog_rcv = raw_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw_sock), @@ -1049,7 +1050,7 @@ static const struct file_operations raw_seq_fops = { static __net_init int raw_init_net(struct net *net) { - if (!proc_net_fops_create(net, "raw", S_IRUGO, &raw_seq_fops)) + if (!proc_create("raw", S_IRUGO, net->proc_net, &raw_seq_fops)) return -ENOMEM; return 0; @@ -1057,7 +1058,7 @@ static __net_init int raw_init_net(struct net *net) static __net_exit void raw_exit_net(struct net *net) { - proc_net_remove(net, "raw"); + remove_proc_entry("raw", net->proc_net); } static __net_initdata struct pernet_operations raw_net_ops = { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 844a9ef60db..6e2851464f8 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -117,15 +117,11 @@ #define RT_GC_TIMEOUT (300*HZ) static int ip_rt_max_size; -static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; -static int ip_rt_gc_interval __read_mostly = 60 * HZ; -static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; -static int ip_rt_gc_elasticity __read_mostly = 8; static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; @@ -384,8 +380,8 @@ static int __net_init ip_rt_do_proc_init(struct net *net) { struct proc_dir_entry *pde; - pde = proc_net_fops_create(net, "rt_cache", S_IRUGO, - &rt_cache_seq_fops); + pde = proc_create("rt_cache", S_IRUGO, net->proc_net, + &rt_cache_seq_fops); if (!pde) goto err1; @@ -912,6 +908,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct dst_entry *dst = &rt->dst; struct fib_result res; + if (dst_metric_locked(dst, RTAX_MTU)) + return; + if (dst->dev->mtu < mtu) return; @@ -962,7 +961,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, } EXPORT_SYMBOL_GPL(ipv4_update_pmtu); -void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) +static 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; @@ -975,6 +974,53 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) ip_rt_put(rt); } } + +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; + bool new = false; + + bh_lock_sock(sk); + rt = (struct rtable *) __sk_dst_get(sk); + + if (sock_owned_by_user(sk) || !rt) { + __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 = ip_route_output_flow(sock_net(sk), &fl4, sk); + if (IS_ERR(rt)) + goto out; + + new = true; + } + + __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu); + + dst = dst_check(&rt->dst, 0); + if (!dst) { + if (new) + dst_release(&rt->dst); + + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); + if (IS_ERR(rt)) + goto out; + + new = true; + } + + if (new) + __sk_dst_set(sk, &rt->dst); + +out: + bh_unlock_sock(sk); +} EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, @@ -1120,7 +1166,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) if (!mtu || time_after_eq(jiffies, rt->dst.expires)) mtu = dst_metric_raw(dst, RTAX_MTU); - if (mtu && rt_is_output_route(rt)) + if (mtu) return mtu; mtu = dst->dev->mtu; @@ -2373,6 +2419,11 @@ void ip_rt_multicast_event(struct in_device *in_dev) } #ifdef CONFIG_SYSCTL +static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; +static int ip_rt_gc_interval __read_mostly = 60 * HZ; +static int ip_rt_gc_min_interval __read_mostly = HZ / 2; +static int ip_rt_gc_elasticity __read_mostly = 8; + static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index b236ef04914..ef54377fb11 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -232,7 +232,8 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, * * return false if we decode an option that should not be. */ -bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, bool *ecn_ok) +bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, + struct net *net, bool *ecn_ok) { /* echoed timestamp, lowest bits contain options */ u32 options = tcp_opt->rcv_tsecr & TSMASK; @@ -247,7 +248,7 @@ bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, bool *ecn_ok) tcp_opt->sack_ok = (options & (1 << 4)) ? TCP_SACK_SEEN : 0; *ecn_ok = (options >> 5) & 1; - if (*ecn_ok && !sysctl_tcp_ecn) + if (*ecn_ok && !net->ipv4.sysctl_tcp_ecn) return false; if (tcp_opt->sack_ok && !sysctl_tcp_sack) @@ -295,7 +296,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, memset(&tcp_opt, 0, sizeof(tcp_opt)); tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL); - if (!cookie_check_timestamp(&tcp_opt, &ecn_ok)) + if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok)) goto out; ret = NULL; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d84400b6504..960fd29d9b8 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -27,6 +27,7 @@ #include <net/tcp_memcontrol.h> static int zero; +static int one = 1; static int two = 2; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; @@ -232,8 +233,8 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, return 0; } -int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer, - size_t *lenp, loff_t *ppos) +static int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer, + size_t *lenp, loff_t *ppos) { ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; @@ -538,13 +539,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .procname = "tcp_ecn", - .data = &sysctl_tcp_ecn, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_dsack", .data = &sysctl_tcp_dsack, .maxlen = sizeof(int), @@ -556,14 +550,16 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_wmem, .maxlen = sizeof(sysctl_tcp_wmem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "tcp_rmem", .data = &sysctl_tcp_rmem, .maxlen = sizeof(sysctl_tcp_rmem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "tcp_app_win", @@ -637,13 +633,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_tcp_congestion_control, }, { - .procname = "tcp_abc", - .data = &sysctl_tcp_abc, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { .procname = "tcp_mtu_probing", .data = &sysctl_tcp_mtu_probing, .maxlen = sizeof(int), @@ -786,7 +775,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_rmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &one }, { .procname = "udp_wmem_min", @@ -794,7 +783,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_wmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &one }, { } }; @@ -850,6 +839,13 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = ipv4_ping_group_range, }, { + .procname = "tcp_ecn", + .data = &init_net.ipv4.sysctl_tcp_ecn, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "tcp_mem", .maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem), .mode = 0644, @@ -882,6 +878,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) &net->ipv4.sysctl_icmp_ratemask; table[6].data = &net->ipv4.sysctl_ping_group_range; + table[7].data = + &net->ipv4.sysctl_tcp_ecn; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2aa69c8ae60..47e854fcae2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -400,6 +400,8 @@ void tcp_init_sock(struct sock *sk) tcp_enable_early_retrans(tp); icsk->icsk_ca_ops = &tcp_init_congestion_ops; + tp->tsoffset = 0; + sk->sk_state = TCP_CLOSE; sk->sk_write_space = sk_stream_write_space; @@ -895,6 +897,7 @@ new_segment: get_page(page); skb_fill_page_desc(skb, i, page, offset, copy); } + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; skb->len += copy; skb->data_len += copy; @@ -1406,10 +1409,10 @@ static void tcp_service_net_dma(struct sock *sk, bool wait) return; last_issued = tp->ucopy.dma_cookie; - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + dma_async_issue_pending(tp->ucopy.dma_chan); do { - if (dma_async_memcpy_complete(tp->ucopy.dma_chan, + if (dma_async_is_tx_complete(tp->ucopy.dma_chan, last_issued, &done, &used) == DMA_SUCCESS) { /* Safe to free early-copied skbs now */ @@ -1751,7 +1754,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, tcp_service_net_dma(sk, true); tcp_cleanup_rbuf(sk, copied); } else - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + dma_async_issue_pending(tp->ucopy.dma_chan); } #endif if (copied >= target) { @@ -1844,7 +1847,7 @@ do_prequeue: break; } - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + dma_async_issue_pending(tp->ucopy.dma_chan); if ((offset + used) == skb->len) copied_early = true; @@ -2287,7 +2290,6 @@ int tcp_disconnect(struct sock *sk, int flags) tp->packets_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; - tp->bytes_acked = 0; tp->window_clamp = 0; tcp_set_ca_state(sk, TCP_CA_Open); tcp_clear_retrans(tp); @@ -2711,6 +2713,12 @@ static int do_tcp_setsockopt(struct sock *sk, int level, else err = -EINVAL; break; + case TCP_TIMESTAMP: + if (!tp->repair) + err = -EPERM; + else + tp->tsoffset = val - tcp_time_stamp; + break; default: err = -ENOPROTOOPT; break; @@ -2959,6 +2967,9 @@ 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_TIMESTAMP: + val = tcp_time_stamp + tp->tsoffset; + break; default: return -ENOPROTOOPT; } @@ -3032,6 +3043,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | + SKB_GSO_GRE | 0) || !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))) goto out; @@ -3243,7 +3255,7 @@ __tcp_alloc_md5sig_pool(struct sock *sk) struct crypto_hash *hash; hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (!hash || IS_ERR(hash)) + if (IS_ERR_OR_NULL(hash)) goto out_free; per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 291f2ed7cc3..019c2389a34 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -310,35 +310,24 @@ void tcp_slow_start(struct tcp_sock *tp) { int cnt; /* increase in packets */ unsigned int delta = 0; + u32 snd_cwnd = tp->snd_cwnd; - /* RFC3465: ABC Slow start - * Increase only after a full MSS of bytes is acked - * - * TCP sender SHOULD increase cwnd by the number of - * previously unacknowledged bytes ACKed by each incoming - * acknowledgment, provided the increase is not more than L - */ - if (sysctl_tcp_abc && tp->bytes_acked < tp->mss_cache) - return; + if (unlikely(!snd_cwnd)) { + pr_err_once("snd_cwnd is nul, please report this bug.\n"); + snd_cwnd = 1U; + } if (sysctl_tcp_max_ssthresh > 0 && tp->snd_cwnd > sysctl_tcp_max_ssthresh) cnt = sysctl_tcp_max_ssthresh >> 1; /* limited slow start */ else - cnt = tp->snd_cwnd; /* exponential increase */ - - /* RFC3465: ABC - * We MAY increase by 2 if discovered delayed ack - */ - if (sysctl_tcp_abc > 1 && tp->bytes_acked >= 2*tp->mss_cache) - cnt <<= 1; - tp->bytes_acked = 0; + cnt = snd_cwnd; /* exponential increase */ tp->snd_cwnd_cnt += cnt; - while (tp->snd_cwnd_cnt >= tp->snd_cwnd) { - tp->snd_cwnd_cnt -= tp->snd_cwnd; + while (tp->snd_cwnd_cnt >= snd_cwnd) { + tp->snd_cwnd_cnt -= snd_cwnd; delta++; } - tp->snd_cwnd = min(tp->snd_cwnd + delta, tp->snd_cwnd_clamp); + tp->snd_cwnd = min(snd_cwnd + delta, tp->snd_cwnd_clamp); } EXPORT_SYMBOL_GPL(tcp_slow_start); @@ -372,20 +361,9 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) /* In "safe" area, increase. */ if (tp->snd_cwnd <= tp->snd_ssthresh) tcp_slow_start(tp); - /* In dangerous area, increase slowly. */ - else if (sysctl_tcp_abc) { - /* RFC3465: Appropriate Byte Count - * increase once for each full cwnd acked - */ - if (tp->bytes_acked >= tp->snd_cwnd*tp->mss_cache) { - tp->bytes_acked -= tp->snd_cwnd*tp->mss_cache; - if (tp->snd_cwnd < tp->snd_cwnd_clamp) - tp->snd_cwnd++; - } - } else { + else tcp_cong_avoid_ai(tp, tp->snd_cwnd); - } } EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 18f97ca76b0..a759e19496d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -81,8 +81,6 @@ int sysctl_tcp_sack __read_mostly = 1; int sysctl_tcp_fack __read_mostly = 1; int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH; EXPORT_SYMBOL(sysctl_tcp_reordering); -int sysctl_tcp_ecn __read_mostly = 2; -EXPORT_SYMBOL(sysctl_tcp_ecn); int sysctl_tcp_dsack __read_mostly = 1; int sysctl_tcp_app_win __read_mostly = 31; int sysctl_tcp_adv_win_scale __read_mostly = 1; @@ -100,7 +98,6 @@ int sysctl_tcp_frto_response __read_mostly; int sysctl_tcp_thin_dupack __read_mostly; int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; -int sysctl_tcp_abc __read_mostly; int sysctl_tcp_early_retrans __read_mostly = 2; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ @@ -2009,7 +2006,6 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag) tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_time_stamp; tp->frto_counter = 0; - tp->bytes_acked = 0; tp->reordering = min_t(unsigned int, tp->reordering, sysctl_tcp_reordering); @@ -2058,7 +2054,6 @@ void tcp_enter_loss(struct sock *sk, int how) tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_time_stamp; - tp->bytes_acked = 0; tcp_clear_retrans_partial(tp); if (tcp_is_reno(tp)) @@ -2686,7 +2681,6 @@ static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh) struct tcp_sock *tp = tcp_sk(sk); tp->high_seq = tp->snd_nxt; - tp->bytes_acked = 0; tp->snd_cwnd_cnt = 0; tp->prior_cwnd = tp->snd_cwnd; tp->prr_delivered = 0; @@ -2737,7 +2731,6 @@ void tcp_enter_cwr(struct sock *sk, const int set_ssthresh) struct tcp_sock *tp = tcp_sk(sk); tp->prior_ssthresh = 0; - tp->bytes_acked = 0; if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { tp->undo_marker = 0; tcp_init_cwnd_reduction(sk, set_ssthresh); @@ -3419,7 +3412,6 @@ static void tcp_conservative_spur_to_response(struct tcp_sock *tp) { tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); tp->snd_cwnd_cnt = 0; - tp->bytes_acked = 0; TCP_ECN_queue_cwr(tp); tcp_moderate_cwnd(tp); } @@ -3504,6 +3496,11 @@ static bool tcp_process_frto(struct sock *sk, int flag) } } else { if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) { + if (!tcp_packets_in_flight(tp)) { + tcp_enter_frto_loss(sk, 2, flag); + return true; + } + /* Prevent sending of new data. */ tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)); @@ -3610,15 +3607,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, prior_snd_una)) flag |= FLAG_SND_UNA_ADVANCED; - if (sysctl_tcp_abc) { - if (icsk->icsk_ca_state < TCP_CA_CWR) - tp->bytes_acked += ack - prior_snd_una; - else if (icsk->icsk_ca_state == TCP_CA_Loss) - /* we assume just one segment left network */ - tp->bytes_acked += min(ack - prior_snd_una, - tp->mss_cache); - } - prior_fackets = tp->fackets_out; prior_in_flight = tcp_packets_in_flight(tp); @@ -3872,7 +3860,7 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr ++ptr; tp->rx_opt.rcv_tsval = ntohl(*ptr); ++ptr; - tp->rx_opt.rcv_tsecr = ntohl(*ptr); + tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset; return true; } return false; @@ -3896,7 +3884,11 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, if (tcp_parse_aligned_timestamp(tp, th)) return true; } + tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); + if (tp->rx_opt.saw_tstamp) + tp->rx_opt.rcv_tsecr -= tp->tsoffset; + return true; } @@ -5649,8 +5641,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, * the remote receives only the retransmitted (regular) SYNs: either * the original SYN-data or the corresponding SYN-ACK is lost. */ - syn_drop = (cookie->len <= 0 && data && - inet_csk(sk)->icsk_retransmits); + syn_drop = (cookie->len <= 0 && data && tp->total_retrans); tcp_fastopen_cache_set(sk, mss, cookie, syn_drop); @@ -5678,6 +5669,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, int saved_clamp = tp->rx_opt.mss_clamp; tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, &foc); + if (tp->rx_opt.saw_tstamp) + tp->rx_opt.rcv_tsecr -= tp->tsoffset; if (th->ack) { /* rfc793: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 54139fa514e..145d3bf8df8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -369,11 +369,10 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) * We do take care of PMTU discovery (RFC1191) special case : * we can receive locally generated ICMP messages while socket is held. */ - if (sock_owned_by_user(sk) && - type != ICMP_DEST_UNREACH && - code != ICMP_FRAG_NEEDED) - NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); - + if (sock_owned_by_user(sk)) { + if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) + NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); + } if (sk->sk_state == TCP_CLOSE) goto out; @@ -497,6 +496,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) * errors returned from accept(). */ inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; case TCP_SYN_SENT: @@ -657,7 +657,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) * no RST generated if md5 hash doesn't match. */ sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev), - &tcp_hashinfo, ip_hdr(skb)->daddr, + &tcp_hashinfo, ip_hdr(skb)->saddr, + th->source, ip_hdr(skb)->daddr, ntohs(th->source), inet_iif(skb)); /* don't send rst if it can't find key */ if (!sk1) @@ -725,7 +726,7 @@ release_sk1: */ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, - u32 win, u32 ts, int oif, + u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int reply_flags, u8 tos) { @@ -746,12 +747,12 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); - if (ts) { + if (tsecr) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); - rep.opt[1] = htonl(tcp_time_stamp); - rep.opt[2] = htonl(ts); + rep.opt[1] = htonl(tsval); + rep.opt[2] = htonl(tsecr); arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED; } @@ -766,7 +767,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, #ifdef CONFIG_TCP_MD5SIG if (key) { - int offset = (ts) ? 3 : 0; + int offset = (tsecr) ? 3 : 0; rep.opt[offset++] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -801,6 +802,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, + tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), @@ -820,6 +822,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, req->rcv_wnd, + tcp_time_stamp, req->ts_recent, 0, tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, @@ -1501,8 +1504,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * clogging syn queue with openreqs with exponentially increasing * timeout. */ - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; + } req = inet_reqsk_alloc(&tcp_request_sock_ops); if (!req) @@ -1568,7 +1573,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, skb); + TCP_ECN_create_request(req, skb, sock_net(sk)); if (want_cookie) { isn = cookie_v4_init_sequence(sk, skb, &req->mss); @@ -1667,6 +1672,7 @@ drop_and_release: drop_and_free: reqsk_free(req); drop: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; } EXPORT_SYMBOL(tcp_v4_conn_request); @@ -2074,6 +2080,7 @@ do_time_wait: case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, + iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); if (sk2) { @@ -2609,7 +2616,7 @@ EXPORT_SYMBOL(tcp_proc_register); void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo) { - proc_net_remove(net, afinfo->name); + remove_proc_entry(afinfo->name, net->proc_net); } EXPORT_SYMBOL(tcp_proc_unregister); @@ -2888,6 +2895,7 @@ EXPORT_SYMBOL(tcp_prot); static int __net_init tcp_sk_init(struct net *net) { + net->ipv4.sysctl_tcp_ecn = 2; return 0; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f35f2dfb640..b83a49cc381 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -102,6 +102,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); if (tmp_opt.saw_tstamp) { + tmp_opt.rcv_tsecr -= tcptw->tw_ts_offset; tmp_opt.ts_recent = tcptw->tw_ts_recent; tmp_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; paws_reject = tcp_paws_reject(&tmp_opt, th->rst); @@ -288,6 +289,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tcptw->tw_rcv_wnd = tcp_receive_window(tp); tcptw->tw_ts_recent = tp->rx_opt.ts_recent; tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp; + tcptw->tw_ts_offset = tp->tsoffset; #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == PF_INET6) { @@ -446,7 +448,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, */ newtp->snd_cwnd = TCP_INIT_CWND; newtp->snd_cwnd_cnt = 0; - newtp->bytes_acked = 0; newtp->frto_counter = 0; newtp->frto_highmark = 0; @@ -500,6 +501,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->rx_opt.ts_recent_stamp = 0; newtp->tcp_header_len = sizeof(struct tcphdr); } + newtp->tsoffset = 0; #ifdef CONFIG_TCP_MD5SIG newtp->md5sig_info = NULL; /*XXX*/ if (newtp->af_specific->md5_lookup(sk, newsk)) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5d451593ef1..e2b4461074d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -314,7 +314,7 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); tp->ecn_flags = 0; - if (sysctl_tcp_ecn == 1) { + if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; } @@ -622,7 +622,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, if (likely(sysctl_tcp_timestamps && *md5 == NULL)) { opts->options |= OPTION_TS; - opts->tsval = TCP_SKB_CB(skb)->when; + opts->tsval = TCP_SKB_CB(skb)->when + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } @@ -806,7 +806,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb if (likely(tp->rx_opt.tstamp_ok)) { opts->options |= OPTION_TS; - opts->tsval = tcb ? tcb->when : 0; + opts->tsval = tcb ? tcb->when + tp->tsoffset : 0; opts->tsecr = tp->rx_opt.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } @@ -1331,7 +1331,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) /* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { - if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; __pskb_trim_head(skb, len); @@ -1351,8 +1351,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) return 0; } -/* Calculate MSS. Not accounting for SACKs here. */ -int tcp_mtu_to_mss(struct sock *sk, int pmtu) +/* Calculate MSS not accounting any TCP options. */ +static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1381,13 +1381,17 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) /* Then reserve room for full set of TCP options and 8 bytes of data */ if (mss_now < 48) mss_now = 48; - - /* Now subtract TCP options size, not including SACKs */ - mss_now -= tp->tcp_header_len - sizeof(struct tcphdr); - return mss_now; } +/* Calculate MSS. Not accounting for SACKs here. */ +int tcp_mtu_to_mss(struct sock *sk, int pmtu) +{ + /* Subtract TCP options size, not including SACKs */ + return __tcp_mtu_to_mss(sk, pmtu) - + (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); +} + /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) { @@ -2930,7 +2934,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) */ if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp) tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; - space = tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - + 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, diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 4526fe68e60..d4943f67aff 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -234,7 +234,7 @@ static __init int tcpprobe_init(void) if (!tcp_probe.log) goto err0; - if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &tcpprobe_fops)) + if (!proc_create(procname, S_IRUSR, init_net.proc_net, &tcpprobe_fops)) goto err0; ret = register_jprobe(&tcp_jprobe); @@ -244,7 +244,7 @@ static __init int tcpprobe_init(void) pr_info("probe registered (port=%d) bufsize=%u\n", port, bufsize); return 0; err1: - proc_net_remove(&init_net, procname); + remove_proc_entry(procname, init_net.proc_net); err0: kfree(tcp_probe.log); return ret; @@ -253,7 +253,7 @@ module_init(tcpprobe_init); static __exit void tcpprobe_exit(void) { - proc_net_remove(&init_net, procname); + remove_proc_entry(procname, init_net.proc_net); unregister_jprobe(&tcp_jprobe); kfree(tcp_probe.log); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 79c8dbe59b5..265c42cf963 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -139,6 +139,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, { struct sock *sk2; struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); sk_nulls_for_each(sk2, node, &hslot->head) if (net_eq(sock_net(sk2), net) && @@ -147,6 +148,8 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (!sk2->sk_reuseport || !sk->sk_reuseport || + !uid_eq(uid, sock_i_uid(sk2))) && (*saddr_comp)(sk, sk2)) { if (bitmap) __set_bit(udp_sk(sk2)->udp_port_hash >> log, @@ -169,6 +172,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, { struct sock *sk2; struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); int res = 0; spin_lock(&hslot2->lock); @@ -179,6 +183,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (!sk2->sk_reuseport || !sk->sk_reuseport || + !uid_eq(uid, sock_i_uid(sk2))) && (*saddr_comp)(sk, sk2)) { res = 1; break; @@ -337,26 +343,26 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, !ipv6_only_sock(sk)) { struct inet_sock *inet = inet_sk(sk); - score = (sk->sk_family == PF_INET ? 1 : 0); + score = (sk->sk_family == PF_INET ? 2 : 1); if (inet->inet_rcv_saddr) { if (inet->inet_rcv_saddr != daddr) return -1; - score += 2; + score += 4; } if (inet->inet_daddr) { if (inet->inet_daddr != saddr) return -1; - score += 2; + score += 4; } if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; - score += 2; + score += 4; } if (sk->sk_bound_dev_if) { if (sk->sk_bound_dev_if != dif) return -1; - score += 2; + score += 4; } } return score; @@ -365,7 +371,6 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, /* * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num) */ -#define SCORE2_MAX (1 + 2 + 2 + 2) static inline int compute_score2(struct sock *sk, struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif) @@ -380,21 +385,21 @@ static inline int compute_score2(struct sock *sk, struct net *net, if (inet->inet_num != hnum) return -1; - score = (sk->sk_family == PF_INET ? 1 : 0); + score = (sk->sk_family == PF_INET ? 2 : 1); if (inet->inet_daddr) { if (inet->inet_daddr != saddr) return -1; - score += 2; + score += 4; } if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; - score += 2; + score += 4; } if (sk->sk_bound_dev_if) { if (sk->sk_bound_dev_if != dif) return -1; - score += 2; + score += 4; } } return score; @@ -409,19 +414,29 @@ static struct sock *udp4_lib_lookup2(struct net *net, { struct sock *sk, *result; struct hlist_nulls_node *node; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; begin: result = NULL; - badness = -1; + badness = 0; udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { score = compute_score2(sk, net, saddr, sport, daddr, hnum, dif); if (score > badness) { result = sk; badness = score; - if (score == SCORE2_MAX) - goto exact_match; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet_ehashfn(net, daddr, hnum, + saddr, htons(sport)); + matches = 1; + } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@ -431,9 +446,7 @@ begin: */ if (get_nulls_value(node) != slot2) goto begin; - if (result) { -exact_match: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, @@ -457,7 +470,8 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, unsigned short hnum = ntohs(dport); unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; rcu_read_lock(); if (hslot->count > 10) { @@ -486,13 +500,24 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, } begin: result = NULL; - badness = -1; + badness = 0; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet_ehashfn(net, daddr, hnum, + saddr, htons(sport)); + matches = 1; + } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@ -971,7 +996,7 @@ back_from_confirm: sizeof(struct udphdr), &ipc, &rt, msg->msg_flags); err = PTR_ERR(skb); - if (skb && !IS_ERR(skb)) + if (!IS_ERR_OR_NULL(skb)) err = udp_send_skb(skb, fl4); goto out; } @@ -1952,6 +1977,7 @@ struct proto udp_prot = { .recvmsg = udp_recvmsg, .sendpage = udp_sendpage, .backlog_rcv = __udp_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, @@ -2096,7 +2122,7 @@ EXPORT_SYMBOL(udp_proc_register); void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo) { - proc_net_remove(net, afinfo->name); + remove_proc_entry(afinfo->name, net->proc_net); } EXPORT_SYMBOL(udp_proc_unregister); @@ -2279,7 +2305,8 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, /* Packet is from an untrusted source, reset gso_segs. */ int type = skb_shinfo(skb)->gso_type; - if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | + SKB_GSO_GRE) || !(type & (SKB_GSO_UDP)))) goto out; diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 06814b6216d..1f12c8b4586 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -132,7 +132,7 @@ int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) * header and optional ESP marker bytes) and then modify the * protocol to ESP, and then call into the transform receiver. */ - if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) goto drop; /* Now we can update and verify the packet length... */ diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index ddee0a099a2..fe5189e2e11 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -142,8 +142,8 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) for_each_input_rcu(rcv_notify_handlers, handler) handler->handler(skb); - if (skb_cloned(skb) && - (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + err = skb_unclone(skb, GFP_ATOMIC); + if (err) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 3be0ac2c192..9a459be24af 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -262,21 +262,56 @@ static struct ctl_table xfrm4_policy_table[] = { { } }; -static struct ctl_table_header *sysctl_hdr; -#endif - -static void __init xfrm4_policy_init(void) +static int __net_init xfrm4_net_init(struct net *net) { - xfrm_policy_register_afinfo(&xfrm4_policy_afinfo); + struct ctl_table *table; + struct ctl_table_header *hdr; + + table = xfrm4_policy_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL); + if (!table) + goto err_alloc; + + table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh; + } + + hdr = register_net_sysctl(net, "net/ipv4", table); + if (!hdr) + goto err_reg; + + net->ipv4.xfrm4_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; } -static void __exit xfrm4_policy_fini(void) +static void __net_exit xfrm4_net_exit(struct net *net) { -#ifdef CONFIG_SYSCTL - if (sysctl_hdr) - unregister_net_sysctl_table(sysctl_hdr); + struct ctl_table *table; + + if (net->ipv4.xfrm4_hdr == NULL) + return; + + table = net->ipv4.xfrm4_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->ipv4.xfrm4_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct pernet_operations __net_initdata xfrm4_net_ops = { + .init = xfrm4_net_init, + .exit = xfrm4_net_exit, +}; #endif - xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo); + +static void __init xfrm4_policy_init(void) +{ + xfrm_policy_register_afinfo(&xfrm4_policy_afinfo); } void __init xfrm4_init(void) @@ -286,8 +321,7 @@ void __init xfrm4_init(void) xfrm4_state_init(); xfrm4_policy_init(); #ifdef CONFIG_SYSCTL - sysctl_hdr = register_net_sysctl(&init_net, "net/ipv4", - xfrm4_policy_table); + register_pernet_subsys(&xfrm4_net_ops); #endif } |