diff options
Diffstat (limited to 'net/ipv6/udp.c')
| -rw-r--r-- | net/ipv6/udp.c | 1970 |
1 files changed, 1228 insertions, 742 deletions
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f4058150262b..794c13674e8a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * UDP over IPv6 * Linux INET6 implementation @@ -14,13 +15,9 @@ * a single port at the same time. * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data * YOSHIFUJI Hideaki @USAGI: convert /proc/net/udp6 to seq_file. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ +#include <linux/bpf-cgroup.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> @@ -35,300 +32,376 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/slab.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> +#include <linux/indirect_call_wrapper.h> +#include <trace/events/udp.h> +#include <net/addrconf.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/raw.h> +#include <net/seg6.h> #include <net/tcp_states.h> #include <net/ip6_checksum.h> +#include <net/ip6_tunnel.h> +#include <net/udp_tunnel.h> #include <net/xfrm.h> +#include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/busy_poll.h> +#include <net/sock_reuseport.h> +#include <net/gro.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <trace/events/skb.h> #include "udp_impl.h" -int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) +static void udpv6_destruct_sock(struct sock *sk) { - const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; - const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); - __be32 sk1_rcv_saddr = sk_rcv_saddr(sk); - __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); - int sk_ipv6only = ipv6_only_sock(sk); - int sk2_ipv6only = inet_v6_ipv6only(sk2); - int addr_type = ipv6_addr_type(sk_rcv_saddr6); - int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; - - /* if both are mapped, treat as IPv4 */ - if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) - return (!sk2_ipv6only && - (!sk1_rcv_saddr || !sk2_rcv_saddr || - sk1_rcv_saddr == sk2_rcv_saddr)); - - if (addr_type2 == IPV6_ADDR_ANY && - !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) - return 1; - - if (addr_type == IPV6_ADDR_ANY && - !(sk_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) - return 1; - - if (sk2_rcv_saddr6 && - ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6)) - return 1; + udp_destruct_common(sk); + inet6_sock_destruct(sk); +} - return 0; +int udpv6_init_sock(struct sock *sk) +{ + int res = udp_lib_init_sock(sk); + + sk->sk_destruct = udpv6_destruct_sock; + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); + return res; } -static unsigned int udp6_portaddr_hash(struct net *net, - const struct in6_addr *addr6, - unsigned int port) +INDIRECT_CALLABLE_SCOPE +u32 udp6_ehashfn(const struct net *net, + const struct in6_addr *laddr, + const u16 lport, + const struct in6_addr *faddr, + const __be16 fport) { - unsigned int hash, mix = net_hash_mix(net); + u32 lhash, fhash; - if (ipv6_addr_any(addr6)) - hash = jhash_1word(0, mix); - else if (ipv6_addr_v4mapped(addr6)) - hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix); - else - hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix); + net_get_random_once(&udp6_ehash_secret, + sizeof(udp6_ehash_secret)); + net_get_random_once(&udp_ipv6_hash_secret, + sizeof(udp_ipv6_hash_secret)); - return hash ^ port; -} + lhash = (__force u32)laddr->s6_addr32[3]; + fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); + return __inet6_ehashfn(lhash, lport, fhash, fport, + udp6_ehash_secret + net_hash_mix(net)); +} int udp_v6_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = - udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum); + ipv6_portaddr_hash(sock_net(sk), &in6addr_any, snum); unsigned int hash2_partial = - udp6_portaddr_hash(sock_net(sk), &inet6_sk(sk)->rcv_saddr, 0); + ipv6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0); /* precompute partial secondary hash */ udp_sk(sk)->udp_portaddr_hash = hash2_partial; - return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr); + return udp_lib_get_port(sk, snum, hash2_nulladdr); } -static void udp_v6_rehash(struct sock *sk) +void udp_v6_rehash(struct sock *sk) { - u16 new_hash = udp6_portaddr_hash(sock_net(sk), - &inet6_sk(sk)->rcv_saddr, + u16 new_hash = ipv6_portaddr_hash(sock_net(sk), + &sk->sk_v6_rcv_saddr, inet_sk(sk)->inet_num); + u16 new_hash4; - udp_lib_rehash(sk, new_hash); -} - -static inline int compute_score(struct sock *sk, struct net *net, - unsigned short hnum, - const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, __be16 dport, - int dif) -{ - int score = -1; - - if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && - sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - struct inet_sock *inet = inet_sk(sk); - - score = 0; - if (inet->inet_dport) { - if (inet->inet_dport != sport) - return -1; - score++; - } - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) - return -1; - score++; - } - if (!ipv6_addr_any(&np->daddr)) { - if (!ipv6_addr_equal(&np->daddr, saddr)) - return -1; - score++; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - return -1; - score++; - } + if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) { + new_hash4 = udp_ehashfn(sock_net(sk), + sk->sk_rcv_saddr, sk->sk_num, + sk->sk_daddr, sk->sk_dport); + } else { + new_hash4 = udp6_ehashfn(sock_net(sk), + &sk->sk_v6_rcv_saddr, sk->sk_num, + &sk->sk_v6_daddr, sk->sk_dport); } - return score; + + udp_lib_rehash(sk, new_hash, new_hash4); } -#define SCORE2_MAX (1 + 1 + 1) -static inline int compute_score2(struct sock *sk, struct net *net, - const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, unsigned short hnum, - int dif) +static int compute_score(struct sock *sk, const struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, unsigned short hnum, + int dif, int sdif) { - int score = -1; + int bound_dev_if, score; + struct inet_sock *inet; + bool dev_match; + + if (!net_eq(sock_net(sk), net) || + udp_sk(sk)->udp_port_hash != hnum || + sk->sk_family != PF_INET6) + return -1; + + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) + return -1; - if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && - sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - struct inet_sock *inet = inet_sk(sk); + score = 0; + inet = inet_sk(sk); - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + if (inet->inet_dport) { + if (inet->inet_dport != sport) return -1; - score = 0; - if (inet->inet_dport) { - if (inet->inet_dport != sport) - return -1; - score++; - } - if (!ipv6_addr_any(&np->daddr)) { - if (!ipv6_addr_equal(&np->daddr, saddr)) - return -1; - score++; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - return -1; - score++; - } + score++; + } + + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr)) + return -1; + score++; } + + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + dev_match = udp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif); + if (!dev_match) + return -1; + if (bound_dev_if) + score++; + + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) + score++; + return score; } - -/* called with read_rcu_lock() */ -static struct sock *udp6_lib_lookup2(struct net *net, - const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, unsigned int hnum, int dif, - struct udp_hslot *hslot2, unsigned int slot2) +/** + * udp6_lib_lookup1() - Simplified lookup using primary hash (destination port) + * @net: Network namespace + * @saddr: Source address, network order + * @sport: Source port, network order + * @daddr: Destination address, network order + * @hnum: Destination port, host order + * @dif: Destination interface index + * @sdif: Destination bridge port index, if relevant + * @udptable: Set of UDP hash tables + * + * Simplified lookup to be used as fallback if no sockets are found due to a + * potential race between (receive) address change, and lookup happening before + * the rehash operation. This function ignores SO_REUSEPORT groups while scoring + * result sockets, because if we have one, we don't need the fallback at all. + * + * Called under rcu_read_lock(). + * + * Return: socket with highest matching score if any, NULL if none + */ +static struct sock *udp6_lib_lookup1(const struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, + unsigned int hnum, int dif, int sdif, + const struct udp_table *udptable) { - struct sock *sk, *result; - struct hlist_nulls_node *node; - int score, badness, matches = 0, reuseport = 0; - u32 hash = 0; - -begin: - result = NULL; - badness = -1; - udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { - score = compute_score2(sk, net, saddr, sport, - daddr, hnum, dif); + unsigned int slot = udp_hashfn(net, hnum, udptable->mask); + struct udp_hslot *hslot = &udptable->hash[slot]; + struct sock *sk, *result = NULL; + int score, badness = 0; + + sk_for_each_rcu(sk, &hslot->head) { + score = compute_score(sk, net, + saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { result = sk; badness = score; - reuseport = sk->sk_reuseport; - if (reuseport) { - hash = inet6_ehashfn(net, daddr, hnum, - saddr, sport); - matches = 1; - } else if (score == SCORE2_MAX) - goto exact_match; - } else if (score == badness && reuseport) { - matches++; - if (((u64)hash * matches) >> 32 == 0) - result = sk; - hash = next_pseudo_random32(hash); } } - /* - * if the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. - */ - 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, - daddr, hnum, dif) < badness)) { - sock_put(result); - goto begin; - } - } return result; } -struct sock *__udp6_lib_lookup(struct net *net, - const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, __be16 dport, - int dif, struct udp_table *udptable) +/* called with rcu_read_lock() */ +static struct sock *udp6_lib_lookup2(const struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, unsigned int hnum, + int dif, int sdif, struct udp_hslot *hslot2, + struct sk_buff *skb) { struct sock *sk, *result; - struct hlist_nulls_node *node; - 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, matches = 0, reuseport = 0; - u32 hash = 0; - - rcu_read_lock(); - if (hslot->count > 10) { - hash2 = udp6_portaddr_hash(net, daddr, hnum); - slot2 = hash2 & udptable->mask; - hslot2 = &udptable->hash2[slot2]; - if (hslot->count < hslot2->count) - goto begin; - - result = udp6_lib_lookup2(net, saddr, sport, - daddr, hnum, dif, - hslot2, slot2); - if (!result) { - hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum); - slot2 = hash2 & udptable->mask; - hslot2 = &udptable->hash2[slot2]; - if (hslot->count < hslot2->count) - goto begin; - - result = udp6_lib_lookup2(net, saddr, sport, - &in6addr_any, hnum, dif, - hslot2, slot2); - } - rcu_read_unlock(); - return result; - } -begin: + int score, badness; + bool need_rescore; + result = NULL; badness = -1; - sk_nulls_for_each_rcu(sk, node, &hslot->head) { - score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif); + udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { + need_rescore = false; +rescore: + score = compute_score(need_rescore ? result : sk, net, saddr, + sport, daddr, hnum, dif, sdif); if (score > badness) { - result = sk; badness = score; - reuseport = sk->sk_reuseport; - if (reuseport) { - hash = inet6_ehashfn(net, daddr, hnum, - saddr, sport); - matches = 1; + + if (need_rescore) + continue; + + if (sk->sk_state == TCP_ESTABLISHED) { + result = sk; + continue; } - } else if (score == badness && reuseport) { - matches++; - if (((u64)hash * matches) >> 32 == 0) + + result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, udp6_ehashfn); + if (!result) { result = sk; - hash = next_pseudo_random32(hash); + continue; + } + + /* Fall back to scoring if group has connections */ + if (!reuseport_has_conns(sk)) + return result; + + /* Reuseport logic returned an error, keep original score. */ + if (IS_ERR(result)) + continue; + + /* compute_score is too long of a function to be + * inlined, and calling it again here yields + * measurable overhead for some + * workloads. Work around it by jumping + * backwards to rescore 'result'. + */ + need_rescore = true; + goto rescore; } } - /* - * if the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. + return result; +} + +#if IS_ENABLED(CONFIG_BASE_SMALL) +static struct sock *udp6_lib_lookup4(const struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, + unsigned int hnum, int dif, int sdif, + struct udp_table *udptable) +{ + return NULL; +} + +static void udp6_hash4(struct sock *sk) +{ +} +#else /* !CONFIG_BASE_SMALL */ +static struct sock *udp6_lib_lookup4(const struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, + unsigned int hnum, int dif, int sdif, + struct udp_table *udptable) +{ + const __portpair ports = INET_COMBINED_PORTS(sport, hnum); + const struct hlist_nulls_node *node; + struct udp_hslot *hslot4; + unsigned int hash4, slot; + struct udp_sock *up; + struct sock *sk; + + hash4 = udp6_ehashfn(net, daddr, hnum, saddr, sport); + slot = hash4 & udptable->mask; + hslot4 = &udptable->hash4[slot]; + +begin: + udp_lrpa_for_each_entry_rcu(up, node, &hslot4->nulls_head) { + sk = (struct sock *)up; + if (inet6_match(net, sk, saddr, daddr, ports, dif, sdif)) + return sk; + } + + /* if the nulls value we got at the end of this lookup is not the + * expected one, we must restart lookup. We probably met an item that + * was moved to another chain due to rehash. */ if (get_nulls_value(node) != slot) goto begin; - if (result) { - if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) - result = NULL; - else if (unlikely(compute_score(result, net, hnum, saddr, sport, - daddr, dport, dif) < badness)) { - sock_put(result); - goto begin; + return NULL; +} + +static void udp6_hash4(struct sock *sk) +{ + struct net *net = sock_net(sk); + unsigned int hash; + + if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) { + udp4_hash4(sk); + return; + } + + if (sk_unhashed(sk) || ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + return; + + hash = udp6_ehashfn(net, &sk->sk_v6_rcv_saddr, sk->sk_num, + &sk->sk_v6_daddr, sk->sk_dport); + + udp_lib_hash4(sk, hash); +} +#endif /* CONFIG_BASE_SMALL */ + +/* rcu_read_lock() must be held */ +struct sock *__udp6_lib_lookup(const struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, + int dif, int sdif, struct udp_table *udptable, + struct sk_buff *skb) +{ + unsigned short hnum = ntohs(dport); + struct udp_hslot *hslot2; + struct sock *result, *sk; + unsigned int hash2; + + hash2 = ipv6_portaddr_hash(net, daddr, hnum); + hslot2 = udp_hashslot2(udptable, hash2); + + if (udp_has_hash4(hslot2)) { + result = udp6_lib_lookup4(net, saddr, sport, daddr, hnum, + dif, sdif, udptable); + if (result) /* udp6_lib_lookup4 return sk or NULL */ + return result; + } + + /* Lookup connected or non-wildcard sockets */ + result = udp6_lib_lookup2(net, saddr, sport, + daddr, hnum, dif, sdif, + hslot2, skb); + if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED) + goto done; + + /* Lookup redirect from BPF */ + if (static_branch_unlikely(&bpf_sk_lookup_enabled) && + udptable == net->ipv4.udp_table) { + sk = inet6_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, dif, + udp6_ehashfn); + if (sk) { + result = sk; + goto done; } } - rcu_read_unlock(); + + /* Got non-wildcard socket or error on first lookup */ + if (result) + goto done; + + /* Lookup wildcard sockets */ + hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum); + hslot2 = udp_hashslot2(udptable, hash2); + + result = udp6_lib_lookup2(net, saddr, sport, + &in6addr_any, hnum, dif, sdif, + hslot2, skb); + if (!IS_ERR_OR_NULL(result)) + goto done; + + /* Cover address change/lookup/rehash race: see __udp4_lib_lookup() */ + result = udp6_lib_lookup1(net, saddr, sport, daddr, hnum, dif, sdif, + udptable); + +done: + if (IS_ERR(result)) + return NULL; return result; } EXPORT_SYMBOL_GPL(__udp6_lib_lookup); @@ -337,66 +410,94 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, struct udp_table *udptable) { - struct sock *sk; const struct ipv6hdr *iph = ipv6_hdr(skb); - if (unlikely(sk = skb_steal_sock(skb))) - return sk; - return __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport, + return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), - udptable); + inet6_sdif(skb), udptable, skb); } -struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, +struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, + __be16 sport, __be16 dport) +{ + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset); + struct net *net = dev_net(skb->dev); + int iif, sdif; + + inet6_get_iif_sdif(skb, &iif, &sdif); + + return __udp6_lib_lookup(net, &iph->saddr, sport, + &iph->daddr, dport, iif, + sdif, net->ipv4.udp_table, NULL); +} + +/* Must be called under rcu_read_lock(). + * Does increment socket refcount. + */ +#if IS_ENABLED(CONFIG_NF_TPROXY_IPV6) || IS_ENABLED(CONFIG_NF_SOCKET_IPV6) +struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif) { - return __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table); + struct sock *sk; + + sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport, + dif, 0, net->ipv4.udp_table, NULL); + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + return sk; } EXPORT_SYMBOL_GPL(udp6_lib_lookup); +#endif +/* do not use the scratch area len for jumbogram: their length exceeds the + * scratch area space; note that the IP6CB flags is still in the first + * cacheline, so checking for jumbograms is cheap + */ +static int udp6_skb_len(struct sk_buff *skb) +{ + return unlikely(inet6_is_jumbogram(skb)) ? skb->len : udp_skb_len(skb); +} /* - * This should be easy, if there is something there we - * return it, otherwise we block. + * This should be easy, if there is something there we + * return it, otherwise we block. */ -int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, - int noblock, int flags, int *addr_len) +int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; unsigned int ulen, copied; - int peeked, off = 0; - int err; + int off, err, peeking = flags & MSG_PEEK; int is_udplite = IS_UDPLITE(sk); + struct udp_mib __percpu *mib; + bool checksum_valid = false; int is_udp4; - bool slow; - - if (addr_len) - *addr_len = sizeof(struct sockaddr_in6); if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); - if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + if (np->rxopt.bits.rxpmtu && READ_ONCE(np->rxpmtu)) + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: - skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), - &peeked, &off, &err); + off = sk_peek_offset(sk, flags); + skb = __skb_recv_udp(sk, flags, &off, &err); if (!skb) - goto out; + return err; - ulen = skb->len - sizeof(struct udphdr); + ulen = udp6_skb_len(skb); copied = len; - if (copied > ulen) - copied = ulen; + if (copied > ulen - off) + copied = ulen - off; else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; is_udp4 = (skb->protocol == htons(ETH_P_IP)); + mib = __UDPX_MIB(sk, is_udp4); /* * If checksum is needed at all, try to do it while copying the @@ -404,50 +505,40 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { - if (udp_lib_checksum_complete(skb)) + if (copied < ulen || peeking || + (is_udplite && UDP_SKB_CB(skb)->partial_cov)) { + checksum_valid = udp_skb_csum_unnecessary(skb) || + !__udp_lib_checksum_complete(skb); + if (!checksum_valid) goto csum_copy_err; } - if (skb_csum_unnecessary(skb)) - err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, copied); - else { - err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); + if (checksum_valid || udp_skb_csum_unnecessary(skb)) { + if (udp_skb_is_linear(skb)) + err = copy_linear_skb(skb, copied, off, &msg->msg_iter); + else + err = skb_copy_datagram_msg(skb, off, msg, copied); + } else { + err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) goto csum_copy_err; } if (unlikely(err)) { - trace_kfree_skb(skb, udpv6_recvmsg); - if (!peeked) { - atomic_inc(&sk->sk_drops); - if (is_udp4) - UDP_INC_STATS_USER(sock_net(sk), - UDP_MIB_INERRORS, - is_udplite); - else - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_INERRORS, - is_udplite); + if (!peeking) { + udp_drops_inc(sk); + SNMP_INC_STATS(mib, UDP_MIB_INERRORS); } - goto out_free; - } - if (!peeked) { - if (is_udp4) - UDP_INC_STATS_USER(sock_net(sk), - UDP_MIB_INDATAGRAMS, is_udplite); - else - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_INDATAGRAMS, is_udplite); + kfree_skb(skb); + return err; } + if (!peeking) + SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS); - sock_recv_ts_and_drops(msg, sk, skb); + sock_recv_cmsgs(msg, sk, skb); /* Copy the address. */ if (msg->msg_name) { - struct sockaddr_in6 *sin6; - - sin6 = (struct sockaddr_in6 *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); sin6->sin6_family = AF_INET6; sin6->sin6_port = udp_hdr(skb)->source; sin6->sin6_flowinfo = 0; @@ -460,138 +551,293 @@ try_again: sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, - IP6CB(skb)->iif); + inet6_iif(skb)); } + *addr_len = sizeof(*sin6); + BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, + (struct sockaddr *)sin6, + addr_len); } + + if (udp_test_bit(GRO_ENABLED, sk)) + udp_cmsg_recv(msg, sk, skb); + + if (np->rxopt.all) + ip6_datagram_recv_common_ctl(sk, msg, skb); + if (is_udp4) { - if (inet->cmsg_flags) - ip_cmsg_recv(msg, skb); + if (inet_cmsg_flags(inet)) + ip_cmsg_recv_offset(msg, sk, skb, + sizeof(struct udphdr), off); } else { if (np->rxopt.all) - ip6_datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_specific_ctl(sk, msg, skb); } err = copied; if (flags & MSG_TRUNC) err = ulen; -out_free: - skb_free_datagram_locked(sk, skb); -out: + skb_consume_udp(sk, skb, peeking ? -err : err); return err; csum_copy_err: - slow = lock_sock_fast(sk); - if (!skb_kill_datagram(sk, skb, flags)) { - if (is_udp4) { - UDP_INC_STATS_USER(sock_net(sk), - UDP_MIB_CSUMERRORS, is_udplite); - UDP_INC_STATS_USER(sock_net(sk), - UDP_MIB_INERRORS, is_udplite); - } else { - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_CSUMERRORS, is_udplite); - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_INERRORS, is_udplite); - } + if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, + udp_skb_destructor)) { + SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS); + SNMP_INC_STATS(mib, UDP_MIB_INERRORS); } - unlock_sock_fast(sk, slow); + kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM); - if (noblock) - return -EAGAIN; - - /* starting over for a new packet */ + /* starting over for a new packet, but check if we need to yield */ + cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } -void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info, - struct udp_table *udptable) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +void udpv6_encap_enable(void) +{ + static_branch_inc(&udpv6_encap_needed_key); +} +EXPORT_SYMBOL(udpv6_encap_enable); + +/* Handler for tunnels with arbitrary destination ports: no socket lookup, go + * through error handlers in encapsulations looking for a match. + */ +static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb, + struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + int i; + + for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { + int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info); + const struct ip6_tnl_encap_ops *encap; + + encap = rcu_dereference(ip6tun_encaps[i]); + if (!encap) + continue; + handler = encap->err_handler; + if (handler && !handler(skb, opt, type, code, offset, info)) + return 0; + } + + return -ENOENT; +} + +/* Try to match ICMP errors to UDP tunnels by looking up a socket without + * reversing source and destination port: this will match tunnels that force the + * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that + * lwtunnels might actually break this assumption by being configured with + * different destination ports on endpoints, in this case we won't be able to + * trace ICMP messages back to them. + * + * If this doesn't match any socket, probe tunnels with arbitrary destination + * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port + * we've sent packets to won't necessarily match the local destination port. + * + * Then ask the tunnel implementation to match the error against a valid + * association. + * + * Return an error if we can't find a match, the socket if we need further + * processing, zero otherwise. + */ +static struct sock *__udp6_lib_err_encap(struct net *net, + const struct ipv6hdr *hdr, int offset, + struct udphdr *uh, + struct udp_table *udptable, + struct sock *sk, + struct sk_buff *skb, + struct inet6_skb_parm *opt, + u8 type, u8 code, __be32 info) +{ + int (*lookup)(struct sock *sk, struct sk_buff *skb); + int network_offset, transport_offset; + struct udp_sock *up; + + network_offset = skb_network_offset(skb); + transport_offset = skb_transport_offset(skb); + + /* Network header needs to point to the outer IPv6 header inside ICMP */ + skb_reset_network_header(skb); + + /* Transport header needs to point to the UDP header */ + skb_set_transport_header(skb, offset); + + if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (lookup && lookup(sk, skb)) + sk = NULL; + + goto out; + } + + sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source, + &hdr->saddr, uh->dest, + inet6_iif(skb), 0, udptable, skb); + if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (!lookup || lookup(sk, skb)) + sk = NULL; + } + +out: + if (!sk) { + sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code, + offset, info)); + } + + skb_set_transport_header(skb, transport_offset); + skb_set_network_header(skb, network_offset); + + return sk; +} + +int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info, + struct udp_table *udptable) { struct ipv6_pinfo *np; const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct in6_addr *saddr = &hdr->saddr; - const struct in6_addr *daddr = &hdr->daddr; - struct udphdr *uh = (struct udphdr*)(skb->data+offset); + const struct in6_addr *daddr = seg6_get_daddr(skb, opt) ? : &hdr->daddr; + struct udphdr *uh = (struct udphdr *)(skb->data+offset); + bool tunnel = false; struct sock *sk; + int harderr; int err; + struct net *net = dev_net(skb->dev); - sk = __udp6_lib_lookup(dev_net(skb->dev), daddr, uh->dest, - saddr, uh->source, inet6_iif(skb), udptable); - if (sk == NULL) - return; + sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, + inet6_iif(skb), inet6_sdif(skb), udptable, NULL); - if (type == ICMPV6_PKT_TOOBIG) - ip6_sk_update_pmtu(skb, sk, info); - if (type == NDISC_REDIRECT) - ip6_sk_redirect(skb, sk); + if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) { + /* No socket for error: try tunnels before discarding */ + if (static_branch_unlikely(&udpv6_encap_needed_key)) { + sk = __udp6_lib_err_encap(net, hdr, offset, uh, + udptable, sk, skb, + opt, type, code, info); + if (!sk) + return 0; + } else + sk = ERR_PTR(-ENOENT); + + if (IS_ERR(sk)) { + __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), + ICMP6_MIB_INERRORS); + return PTR_ERR(sk); + } + tunnel = true; + } + + harderr = icmpv6_err_convert(type, code, &err); np = inet6_sk(sk); - if (!icmpv6_err_convert(type, code, &err) && !np->recverr) + if (type == ICMPV6_PKT_TOOBIG) { + if (!ip6_sk_accept_pmtu(sk)) + goto out; + ip6_sk_update_pmtu(skb, sk, info); + if (READ_ONCE(np->pmtudisc) != IPV6_PMTUDISC_DONT) + harderr = 1; + } + if (type == NDISC_REDIRECT) { + if (tunnel) { + ip6_redirect(skb, sock_net(sk), inet6_iif(skb), + READ_ONCE(sk->sk_mark), + sk_uid(sk)); + } else { + ip6_sk_redirect(skb, sk); + } goto out; + } - if (sk->sk_state != TCP_ESTABLISHED && !np->recverr) + /* Tunnels don't have an application socket: don't pass errors back */ + if (tunnel) { + if (udp_sk(sk)->encap_err_rcv) + udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, + ntohl(info), (u8 *)(uh+1)); goto out; + } - if (np->recverr) + if (!inet6_test_bit(RECVERR6, sk)) { + if (!harderr || sk->sk_state != TCP_ESTABLISHED) + goto out; + } else { ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1)); + } sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: - sock_put(sk); + return 0; } static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; - if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { sock_rps_save_rxhash(sk, skb); + sk_mark_napi_id(sk, skb); + sk_incoming_cpu_update(sk); + } else { + sk_mark_napi_id_once(sk, skb); + } - rc = sock_queue_rcv_skb(sk, skb); + rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); + enum skb_drop_reason drop_reason; /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) - UDP6_INC_STATS_BH(sock_net(sk), - UDP_MIB_RCVBUFERRORS, is_udplite); - UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - kfree_skb(skb); + if (rc == -ENOMEM) { + UDP6_INC_STATS(sock_net(sk), + UDP_MIB_RCVBUFERRORS, is_udplite); + drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF; + } else { + UDP6_INC_STATS(sock_net(sk), + UDP_MIB_MEMERRORS, is_udplite); + drop_reason = SKB_DROP_REASON_PROTO_MEM; + } + UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + trace_udp_fail_queue_rcv_skb(rc, sk, skb); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } - return 0; -} -static __inline__ void udpv6_err(struct sk_buff *skb, - struct inet6_skb_parm *opt, u8 type, - u8 code, int offset, __be32 info ) -{ - __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); + return 0; } -static struct static_key udpv6_encap_needed __read_mostly; -void udpv6_encap_enable(void) +static __inline__ int udpv6_err(struct sk_buff *skb, + struct inet6_skb_parm *opt, u8 type, + u8 code, int offset, __be32 info) { - if (!static_key_enabled(&udpv6_encap_needed)) - static_key_slow_inc(&udpv6_encap_needed); + return __udp6_lib_err(skb, opt, type, code, offset, info, + dev_net(skb->dev)->ipv4.udp_table); } -EXPORT_SYMBOL(udpv6_encap_enable); -int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct udp_sock *up = udp_sk(sk); - int rc; int is_udplite = IS_UDPLITE(sk); - if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { + drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; + } + nf_reset_ct(skb); - if (static_key_false(&udpv6_encap_needed) && up->encap_type) { + if (static_branch_unlikely(&udpv6_encap_needed_key) && + READ_ONCE(up->encap_type)) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -606,13 +852,17 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ /* if we're overly short, let UDP handle it */ - encap_rcv = ACCESS_ONCE(up->encap_rcv); - if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) { + encap_rcv = READ_ONCE(up->encap_rcv); + if (encap_rcv) { int ret; + /* Verify checksum before giving to encap */ + if (udp_lib_checksum_complete(skb)) + goto csum_error; + ret = encap_rcv(sk, skb); if (ret <= 0) { - UDP_INC_STATS_BH(sock_net(sk), + __UDP6_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS, is_udplite); return -ret; @@ -625,173 +875,208 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if (udp_test_bit(UDPLITE_RECV_CC, sk) && UDP_SKB_CB(skb)->partial_cov) { + u16 pcrlen = READ_ONCE(up->pcrlen); - if (up->pcrlen == 0) { /* full coverage was set */ - LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: partial coverage" - " %d while full coverage %d requested\n", - UDP_SKB_CB(skb)->cscov, skb->len); + if (pcrlen == 0) { /* full coverage was set */ + net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n", + UDP_SKB_CB(skb)->cscov, skb->len); goto drop; } - if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { - LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: coverage %d " - "too small, need min %d\n", - UDP_SKB_CB(skb)->cscov, up->pcrlen); + if (UDP_SKB_CB(skb)->cscov < pcrlen) { + net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n", + UDP_SKB_CB(skb)->cscov, pcrlen); goto drop; } } - if (rcu_access_pointer(sk->sk_filter)) { - if (udp_lib_checksum_complete(skb)) - goto csum_error; - } + prefetch(&sk->sk_rmem_alloc); + if (rcu_access_pointer(sk->sk_filter) && + udp_lib_checksum_complete(skb)) + goto csum_error; - if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) + if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr), &drop_reason)) goto drop; + udp_csum_pull_header(skb); + skb_dst_drop(skb); - bh_lock_sock(sk); - rc = 0; - if (!sock_owned_by_user(sk)) - rc = __udpv6_queue_rcv_skb(sk, skb); - else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { - bh_unlock_sock(sk); - goto drop; - } - bh_unlock_sock(sk); + return __udpv6_queue_rcv_skb(sk, skb); - return rc; csum_error: - UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); + drop_reason = SKB_DROP_REASON_UDP_CSUM; + __UDP6_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: - UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - atomic_inc(&sk->sk_drops); - kfree_skb(skb); + __UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + udp_drops_inc(sk); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } -static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, - __be16 loc_port, const struct in6_addr *loc_addr, - __be16 rmt_port, const struct in6_addr *rmt_addr, - int dif) +static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - struct hlist_nulls_node *node; - struct sock *s = sk; - unsigned short num = ntohs(loc_port); - - sk_nulls_for_each_from(s, node) { - struct inet_sock *inet = inet_sk(s); + struct sk_buff *next, *segs; + int ret; - if (!net_eq(sock_net(s), net)) - continue; + if (likely(!udp_unexpected_gso(sk, skb))) + return udpv6_queue_rcv_one_skb(sk, skb); - if (udp_sk(s)->udp_port_hash == num && - s->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(s); - if (inet->inet_dport) { - if (inet->inet_dport != rmt_port) - continue; - } - if (!ipv6_addr_any(&np->daddr) && - !ipv6_addr_equal(&np->daddr, rmt_addr)) - continue; + __skb_push(skb, -skb_mac_offset(skb)); + segs = udp_rcv_segment(sk, skb, false); + skb_list_walk_safe(segs, skb, next) { + __skb_pull(skb, skb_transport_offset(skb)); - if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif) - continue; - - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr)) - continue; - } - if (!inet6_mc_check(s, loc_addr, rmt_addr)) - continue; - return s; - } + udp_post_segment_fix_csum(skb); + ret = udpv6_queue_rcv_one_skb(sk, skb); + if (ret > 0) + ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret, + true); } - return NULL; + return 0; } -static void flush_stack(struct sock **stack, unsigned int count, - struct sk_buff *skb, unsigned int final) +static bool __udp_v6_is_mcast_sock(struct net *net, const struct sock *sk, + __be16 loc_port, const struct in6_addr *loc_addr, + __be16 rmt_port, const struct in6_addr *rmt_addr, + int dif, int sdif, unsigned short hnum) { - struct sk_buff *skb1 = NULL; - struct sock *sk; - unsigned int i; - - for (i = 0; i < count; i++) { - sk = stack[i]; - if (likely(skb1 == NULL)) - skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); - if (!skb1) { - atomic_inc(&sk->sk_drops); - UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, - IS_UDPLITE(sk)); - UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, - IS_UDPLITE(sk)); - } + const struct inet_sock *inet = inet_sk(sk); + + if (!net_eq(sock_net(sk), net)) + return false; + + if (udp_sk(sk)->udp_port_hash != hnum || + sk->sk_family != PF_INET6 || + (inet->inet_dport && inet->inet_dport != rmt_port) || + (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || + !udp_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif, sdif) || + (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && + !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))) + return false; + if (!inet6_mc_check(sk, loc_addr, rmt_addr)) + return false; + return true; +} - if (skb1 && udpv6_queue_rcv_skb(sk, skb1) <= 0) - skb1 = NULL; - } - if (unlikely(skb1)) - kfree_skb(skb1); +static void udp6_csum_zero_error(struct sk_buff *skb) +{ + /* RFC 2460 section 8.1 says that we SHOULD log + * this error. Well, it is reasonable. + */ + net_dbg_ratelimited("IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n", + &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source), + &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest)); } + /* * Note: called only from the BH handler context, * so we don't need to lock the hashes. */ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, - struct udp_table *udptable) + struct udp_table *udptable, int proto) { - struct sock *sk, *stack[256 / sizeof(struct sock *)]; + struct sock *sk, *first = NULL; const struct udphdr *uh = udp_hdr(skb); - struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); - int dif; - unsigned int i, count = 0; - - spin_lock(&hslot->lock); - sk = sk_nulls_head(&hslot->head); - dif = inet6_iif(skb); - sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); - while (sk) { - stack[count++] = sk; - sk = udp_v6_mcast_next(net, sk_nulls_next(sk), uh->dest, daddr, - uh->source, saddr, dif); - if (unlikely(count == ARRAY_SIZE(stack))) { - if (!sk) - break; - flush_stack(stack, count, skb, ~0); - count = 0; - } + unsigned short hnum = ntohs(uh->dest); + struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); + unsigned int offset = offsetof(typeof(*sk), sk_node); + unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); + int dif = inet6_iif(skb); + int sdif = inet6_sdif(skb); + struct hlist_node *node; + struct sk_buff *nskb; + + if (use_hash2) { + hash2_any = ipv6_portaddr_hash(net, &in6addr_any, hnum) & + udptable->mask; + hash2 = ipv6_portaddr_hash(net, daddr, hnum) & udptable->mask; +start_lookup: + hslot = &udptable->hash2[hash2].hslot; + offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } - /* - * before releasing the lock, we must take reference on sockets - */ - for (i = 0; i < count; i++) - sock_hold(stack[i]); - spin_unlock(&hslot->lock); + sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) { + if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr, + uh->source, saddr, dif, sdif, + hnum)) + continue; + /* If zero checksum and no_check is not on for + * the socket then skip it. + */ + if (!uh->check && !udp_get_no_check6_rx(sk)) + continue; + if (!first) { + first = sk; + continue; + } + nskb = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!nskb)) { + udp_drops_inc(sk); + __UDP6_INC_STATS(net, UDP_MIB_RCVBUFERRORS, + IS_UDPLITE(sk)); + __UDP6_INC_STATS(net, UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + continue; + } + + if (udpv6_queue_rcv_skb(sk, nskb) > 0) + consume_skb(nskb); + } - if (count) { - flush_stack(stack, count, skb, count - 1); + /* Also lookup *:port if we are using hash2 and haven't done so yet. */ + if (use_hash2 && hash2 != hash2_any) { + hash2 = hash2_any; + goto start_lookup; + } - for (i = 0; i < count; i++) - sock_put(stack[i]); + if (first) { + if (udpv6_queue_rcv_skb(first, skb) > 0) + consume_skb(skb); } else { kfree_skb(skb); + __UDP6_INC_STATS(net, UDP_MIB_IGNOREDMULTI, + proto == IPPROTO_UDPLITE); } return 0; } +static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) +{ + if (udp_sk_rx_dst_set(sk, dst)) + sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); +} + +/* wrapper for udp_queue_rcv_skb taking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, ip6_compute_pseudo); + + ret = udpv6_queue_rcv_skb(sk, skb); + + /* a return value > 0 means to resubmit the input */ + if (ret > 0) + return ret; + return 0; +} + int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; + const struct in6_addr *saddr, *daddr; struct net *net = dev_net(skb->dev); - struct sock *sk; + struct sock *sk = NULL; struct udphdr *uh; - const struct in6_addr *saddr, *daddr; + bool refcounted; u32 ulen = 0; if (!pskb_may_pull(skb, sizeof(struct udphdr))) @@ -827,69 +1112,158 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp6_csum_init(skb, uh, proto)) goto csum_error; + /* Check if the socket is already available, e.g. due to early demux */ + sk = inet6_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest, + &refcounted, udp6_ehashfn); + if (IS_ERR(sk)) + goto no_sk; + + if (sk) { + struct dst_entry *dst = skb_dst(skb); + int ret; + + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) + udp6_sk_rx_dst_set(sk, dst); + + if (!uh->check && !udp_get_no_check6_rx(sk)) { + if (refcounted) + sock_put(sk); + goto report_csum_error; + } + + ret = udp6_unicast_rcv_skb(sk, skb, uh); + if (refcounted) + sock_put(sk); + return ret; + } + /* * Multicast receive code */ if (ipv6_addr_is_multicast(daddr)) return __udp6_lib_mcast_deliver(net, skb, - saddr, daddr, udptable); + saddr, daddr, udptable, proto); /* Unicast */ - - /* - * check socket cache ... must talk to Alan about his plans - * for sock caches... i'll skip this for now. - */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); - if (sk != NULL) { - int ret; - - sk_mark_napi_id(sk, skb); - ret = udpv6_queue_rcv_skb(sk, skb); - sock_put(sk); - - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - - return 0; + if (sk) { + if (!uh->check && !udp_get_no_check6_rx(sk)) + goto report_csum_error; + return udp6_unicast_rcv_skb(sk, skb, uh); } +no_sk: + reason = SKB_DROP_REASON_NO_SOCKET; + + if (!uh->check) + goto report_csum_error; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; + nf_reset_ct(skb); if (udp_lib_checksum_complete(skb)) goto csum_error; - UDP6_INC_STATS_BH(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); + __UDP6_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); - kfree_skb(skb); + sk_skb_reason_drop(sk, skb, reason); return 0; short_packet: - LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n", - proto == IPPROTO_UDPLITE ? "-Lite" : "", - saddr, - ntohs(uh->source), - ulen, - skb->len, - daddr, - ntohs(uh->dest)); + if (reason == SKB_DROP_REASON_NOT_SPECIFIED) + reason = SKB_DROP_REASON_PKT_TOO_SMALL; + net_dbg_ratelimited("UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n", + proto == IPPROTO_UDPLITE ? "-Lite" : "", + saddr, ntohs(uh->source), + ulen, skb->len, + daddr, ntohs(uh->dest)); goto discard; + +report_csum_error: + udp6_csum_zero_error(skb); csum_error: - UDP6_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); + if (reason == SKB_DROP_REASON_NOT_SPECIFIED) + reason = SKB_DROP_REASON_UDP_CSUM; + __UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: - UDP6_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); - kfree_skb(skb); + __UDP6_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); + sk_skb_reason_drop(sk, skb, reason); return 0; } -static __inline__ int udpv6_rcv(struct sk_buff *skb) + +static struct sock *__udp6_lib_demux_lookup(struct net *net, + __be16 loc_port, const struct in6_addr *loc_addr, + __be16 rmt_port, const struct in6_addr *rmt_addr, + int dif, int sdif) +{ + struct udp_table *udptable = net->ipv4.udp_table; + unsigned short hnum = ntohs(loc_port); + struct udp_hslot *hslot2; + unsigned int hash2; + __portpair ports; + struct sock *sk; + + hash2 = ipv6_portaddr_hash(net, loc_addr, hnum); + hslot2 = udp_hashslot2(udptable, hash2); + ports = INET_COMBINED_PORTS(rmt_port, hnum); + + udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { + if (sk->sk_state == TCP_ESTABLISHED && + inet6_match(net, sk, rmt_addr, loc_addr, ports, dif, sdif)) + return sk; + /* Only check first socket in chain */ + break; + } + return NULL; +} + +void udp_v6_early_demux(struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + const struct udphdr *uh; + struct sock *sk; + struct dst_entry *dst; + int dif = skb->dev->ifindex; + int sdif = inet6_sdif(skb); + + if (!pskb_may_pull(skb, skb_transport_offset(skb) + + sizeof(struct udphdr))) + return; + + uh = udp_hdr(skb); + + if (skb->pkt_type == PACKET_HOST) + sk = __udp6_lib_demux_lookup(net, uh->dest, + &ipv6_hdr(skb)->daddr, + uh->source, &ipv6_hdr(skb)->saddr, + dif, sdif); + else + return; + + if (!sk) + return; + + skb->sk = sk; + DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk)); + skb->destructor = sock_pfree; + dst = rcu_dereference(sk->sk_rx_dst); + + if (dst) + dst = dst_check(dst, sk->sk_rx_dst_cookie); + if (dst) { + /* set noref for now. + * any place which wants to hold dst has to call + * dst_hold_safe() + */ + skb_dst_set_noref(skb, dst); + } +} + +INDIRECT_CALLABLE_SCOPE int udpv6_rcv(struct sk_buff *skb) { - return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP); + return __udp6_lib_rcv(skb, dev_net(skb->dev)->ipv4.udp_table, IPPROTO_UDP); } /* @@ -903,16 +1277,53 @@ static void udp_v6_flush_pending_frames(struct sock *sk) udp_flush_pending_frames(sk); else if (up->pending) { up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); ip6_flush_pending_frames(sk); } } +static int udpv6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) +{ + if (addr_len < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; + /* The following checks are replicated from __ip6_datagram_connect() + * and intended to prevent BPF program called below from accessing + * bytes that are out of the bound specified by user in addr_len. + */ + if (uaddr->sa_family == AF_INET) { + if (ipv6_only_sock(sk)) + return -EAFNOSUPPORT; + return udp_pre_connect(sk, uaddr, addr_len); + } + + if (addr_len < SIN6_LEN_RFC2133) + return -EINVAL; + + return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len); +} + +static int udpv6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) +{ + int res; + + lock_sock(sk); + res = __ip6_datagram_connect(sk, uaddr, addr_len); + if (!res) + udp6_hash4(sk); + release_sock(sk); + return res; +} + /** - * udp6_hwcsum_outgoing - handle outgoing HW checksumming - * @sk: socket we are sending on - * @skb: sk_buff containing the filled-in UDP header - * (checksum field must be zeroed out) + * udp6_hwcsum_outgoing - handle outgoing HW checksumming + * @sk: socket we are sending on + * @skb: sk_buff containing the filled-in UDP header + * (checksum field must be zeroed out) + * @saddr: source address + * @daddr: destination address + * @len: length of packet */ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, const struct in6_addr *saddr, @@ -920,9 +1331,10 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, { unsigned int offset; struct udphdr *uh = udp_hdr(skb); + struct sk_buff *frags = skb_shinfo(skb)->frag_list; __wsum csum = 0; - if (skb_queue_len(&sk->sk_write_queue) == 1) { + if (!frags) { /* Only one fragment on the socket. */ skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); @@ -935,12 +1347,13 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, */ offset = skb_transport_offset(skb); skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); + csum = skb->csum; skb->ip_summed = CHECKSUM_NONE; - skb_queue_walk(&sk->sk_write_queue, skb) { - csum = csum_add(csum, skb->csum); - } + do { + csum = csum_add(csum, frags->csum); + } while ((frags = frags->next)); uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, csum); @@ -953,25 +1366,17 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, * Sending */ -static int udp_v6_push_pending_frames(struct sock *sk) +static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, + struct inet_cork *cork) { - struct sk_buff *skb; + struct sock *sk = skb->sk; struct udphdr *uh; - struct udp_sock *up = udp_sk(sk); - struct inet_sock *inet = inet_sk(sk); - struct flowi6 *fl6; int err = 0; int is_udplite = IS_UDPLITE(sk); __wsum csum = 0; - - if (up->pending == AF_INET) - return udp_push_pending_frames(sk); - - fl6 = &inet->cork.fl.u.ip6; - - /* Grab the skbuff where UDP header space exists. */ - if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) - goto out; + int offset = skb_transport_offset(skb); + int len = skb->len - offset; + int datalen = len - sizeof(*uh); /* * Create a UDP header @@ -979,65 +1384,121 @@ static int udp_v6_push_pending_frames(struct sock *sk) uh = udp_hdr(skb); uh->source = fl6->fl6_sport; uh->dest = fl6->fl6_dport; - uh->len = htons(up->len); + uh->len = htons(len); uh->check = 0; + if (cork->gso_size) { + const int hlen = skb_network_header_len(skb) + + sizeof(struct udphdr); + + if (hlen + min(datalen, cork->gso_size) > cork->fragsize) { + kfree_skb(skb); + return -EMSGSIZE; + } + if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { + kfree_skb(skb); + return -EINVAL; + } + if (udp_get_no_check6_tx(sk)) { + kfree_skb(skb); + return -EINVAL; + } + if (is_udplite || dst_xfrm(skb_dst(skb))) { + kfree_skb(skb); + return -EIO; + } + + if (datalen > cork->gso_size) { + skb_shinfo(skb)->gso_size = cork->gso_size; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen, + cork->gso_size); + + /* Don't checksum the payload, skb will get segmented */ + goto csum_partial; + } + } + if (is_udplite) - csum = udplite_csum_outgoing(sk, skb); - else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ - udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, - up->len); + csum = udplite_csum(skb); + else if (udp_get_no_check6_tx(sk)) { /* UDP csum disabled */ + skb->ip_summed = CHECKSUM_NONE; + goto send; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ +csum_partial: + udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, len); goto send; } else - csum = udp_csum_outgoing(sk, skb); + csum = udp_csum(skb); /* add protocol-dependent pseudo-header */ uh->check = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, - up->len, fl6->flowi6_proto, csum); + len, fl6->flowi6_proto, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; send: - err = ip6_push_pending_frames(sk); + err = ip6_send_skb(skb); if (err) { - if (err == -ENOBUFS && !inet6_sk(sk)->recverr) { - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_SNDBUFERRORS, is_udplite); + if (err == -ENOBUFS && !inet6_test_bit(RECVERR6, sk)) { + UDP6_INC_STATS(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); err = 0; } - } else - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_OUTDATAGRAMS, is_udplite); + } else { + UDP6_INC_STATS(sock_net(sk), + UDP_MIB_OUTDATAGRAMS, is_udplite); + } + return err; +} + +static int udp_v6_push_pending_frames(struct sock *sk) +{ + struct sk_buff *skb; + struct udp_sock *up = udp_sk(sk); + int err = 0; + + if (up->pending == AF_INET) + return udp_push_pending_frames(sk); + + skb = ip6_finish_skb(sk); + if (!skb) + goto out; + + err = udp_v6_send_skb(skb, &inet_sk(sk)->cork.fl.u.ip6, + &inet_sk(sk)->cork.base); out: up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); return err; } -int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len) +int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct ipv6_txoptions *opt = NULL; + struct ipv6_txoptions *opt_to_free = NULL; struct ip6_flowlabel *flowlabel = NULL; - struct flowi6 fl6; + struct inet_cork_full cork; + struct flowi6 *fl6 = &cork.fl.u.ip6; struct dst_entry *dst; + struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; + bool connected = false; int ulen = len; - int hlimit = -1; - int tclass = -1; - int dontfrag = -1; - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE; int err; - int connected = 0; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); + ipcm6_init_sk(&ipc6, sk); + ipc6.gso_size = READ_ONCE(up->gso_size); + /* destination address check */ if (sin6) { if (addr_len < offsetof(struct sockaddr, sa_data)) @@ -1048,6 +1509,10 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; daddr = &sin6->sin6_addr; + if (ipv6_addr_any(daddr) && + ipv6_addr_v4mapped(&np->saddr)) + ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), + daddr); break; case AF_INET: goto do_udp_sendmsg; @@ -1059,10 +1524,10 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, default: return -EINVAL; } - } else if (!up->pending) { + } else if (!READ_ONCE(up->pending)) { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - daddr = &np->daddr; + daddr = &sk->sk_v6_daddr; } else daddr = NULL; @@ -1075,22 +1540,24 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: - if (__ipv6_only_sock(sk)) - return -ENETUNREACH; - return udp_sendmsg(iocb, sk, msg, len); + err = ipv6_only_sock(sk) ? + -ENETUNREACH : udp_sendmsg(sk, msg, len); + msg->msg_name = sin6; + msg->msg_namelen = addr_len; + return err; } } - if (up->pending == AF_INET) - return udp_sendmsg(iocb, sk, msg, len); - /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ if (len > INT_MAX - sizeof(struct udphdr)) return -EMSGSIZE; - if (up->pending) { + getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; + if (READ_ONCE(up->pending)) { + if (READ_ONCE(up->pending) == AF_INET) + return udp_sendmsg(sk, msg, len); /* * There are pending frames. * The socket lock must be held while it's corked. @@ -1108,22 +1575,21 @@ do_udp_sendmsg: } ulen += sizeof(struct udphdr); - memset(&fl6, 0, sizeof(fl6)); + memset(fl6, 0, sizeof(*fl6)); if (sin6) { if (sin6->sin6_port == 0) return -EINVAL; - fl6.fl6_dport = sin6->sin6_port; + fl6->fl6_dport = sin6->sin6_port; daddr = &sin6->sin6_addr; - if (np->sndflow) { - fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; - if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); - if (flowlabel == NULL) + if (inet6_test_bit(SNDFLOW, sk)) { + fl6->flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl6->flowlabel & IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); + if (IS_ERR(flowlabel)) return -EINVAL; - daddr = &flowlabel->dst; } } @@ -1132,153 +1598,176 @@ do_udp_sendmsg: * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && - ipv6_addr_equal(daddr, &np->daddr)) - daddr = &np->daddr; + ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) + daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) - fl6.flowi6_oif = sin6->sin6_scope_id; + fl6->flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - fl6.fl6_dport = inet->inet_dport; - daddr = &np->daddr; - fl6.flowlabel = np->flow_label; - connected = 1; + fl6->fl6_dport = inet->inet_dport; + daddr = &sk->sk_v6_daddr; + fl6->flowlabel = np->flow_label; + connected = true; } - if (!fl6.flowi6_oif) - fl6.flowi6_oif = sk->sk_bound_dev_if; + if (!fl6->flowi6_oif) + fl6->flowi6_oif = READ_ONCE(sk->sk_bound_dev_if); - if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; + if (!fl6->flowi6_oif) + fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; - fl6.flowi6_mark = sk->sk_mark; + fl6->flowi6_uid = sk_uid(sk); if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); + ipc6.opt = opt; - err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + err = udp_cmsg_send(sk, msg, &ipc6.gso_size); + if (err > 0) { + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, fl6, + &ipc6); + connected = false; + } if (err < 0) { fl6_sock_release(flowlabel); return err; } - if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { - flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); - if (flowlabel == NULL) + if ((fl6->flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { + flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); + if (IS_ERR(flowlabel)) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; - connected = 0; } - if (opt == NULL) - opt = np->opt; + if (!opt) { + opt = txopt_get(np); + opt_to_free = opt; + } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); + ipc6.opt = opt; + + fl6->flowi6_proto = sk->sk_protocol; + fl6->flowi6_mark = ipc6.sockc.mark; + fl6->daddr = *daddr; + if (ipv6_addr_any(&fl6->saddr) && !ipv6_addr_any(&np->saddr)) + fl6->saddr = np->saddr; + fl6->fl6_sport = inet->inet_sport; + + if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) { + err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, + (struct sockaddr *)sin6, + &addr_len, + &fl6->saddr); + if (err) + goto out_no_dst; + if (sin6) { + if (ipv6_addr_v4mapped(&sin6->sin6_addr)) { + /* BPF program rewrote IPv6-only by IPv4-mapped + * IPv6. It's currently unsupported. + */ + err = -ENOTSUPP; + goto out_no_dst; + } + if (sin6->sin6_port == 0) { + /* BPF program set invalid port. Reject it. */ + err = -EINVAL; + goto out_no_dst; + } + fl6->fl6_dport = sin6->sin6_port; + fl6->daddr = sin6->sin6_addr; + } + } - fl6.flowi6_proto = sk->sk_protocol; - if (!ipv6_addr_any(daddr)) - fl6.daddr = *daddr; - else - fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ - if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) - fl6.saddr = np->saddr; - fl6.fl6_sport = inet->inet_sport; + if (ipv6_addr_any(&fl6->daddr)) + fl6->daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ - final_p = fl6_update_dst(&fl6, opt, &final); + final_p = fl6_update_dst(fl6, opt, &final); if (final_p) - connected = 0; + connected = false; - if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) { - fl6.flowi6_oif = np->mcast_oif; - connected = 0; - } else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; + if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr)) { + fl6->flowi6_oif = READ_ONCE(np->mcast_oif); + connected = false; + } else if (!fl6->flowi6_oif) + fl6->flowi6_oif = READ_ONCE(np->ucast_oif); - security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); - dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, true); + fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel); + + dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto out; } - if (hlimit < 0) { - if (ipv6_addr_is_multicast(&fl6.daddr)) - hlimit = np->mcast_hops; - else - hlimit = np->hop_limit; - if (hlimit < 0) - hlimit = ip6_dst_hoplimit(dst); - } - - if (tclass < 0) - tclass = np->tclass; - - if (dontfrag < 0) - dontfrag = np->dontfrag; + if (ipc6.hlimit < 0) + ipc6.hlimit = ip6_sk_dst_hoplimit(np, fl6, dst); if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: + /* Lockless fast path for the non-corking case */ + if (!corkreq) { + struct sk_buff *skb; + + skb = ip6_make_skb(sk, getfrag, msg, ulen, + sizeof(struct udphdr), &ipc6, + dst_rt6_info(dst), + msg->msg_flags, &cork); + err = PTR_ERR(skb); + if (!IS_ERR_OR_NULL(skb)) + err = udp_v6_send_skb(skb, fl6, &cork.base); + /* ip6_make_skb steals dst reference */ + goto out_no_dst; + } + lock_sock(sk); if (unlikely(up->pending)) { /* The socket is already corked while preparing it. */ /* ... which is an evident application bug. --ANK */ release_sock(sk); - LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n"); + net_dbg_ratelimited("udp cork app bug 2\n"); err = -EINVAL; goto out; } - up->pending = AF_INET6; + WRITE_ONCE(up->pending, AF_INET6); do_append_data: up->len += ulen; - getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; - err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, - sizeof(struct udphdr), hlimit, tclass, opt, &fl6, - (struct rt6_info*)dst, - corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag); + err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), + &ipc6, fl6, dst_rt6_info(dst), + corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_v6_flush_pending_frames(sk); else if (!corkreq) err = udp_v6_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) - up->pending = 0; - - if (dst) { - if (connected) { - ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl6.daddr, &np->daddr) ? - &np->daddr : NULL, -#ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_equal(&fl6.saddr, &np->saddr) ? - &np->saddr : -#endif - NULL); - } else { - dst_release(dst); - } - dst = NULL; - } + WRITE_ONCE(up->pending, 0); if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; + err = inet6_test_bit(RECVERR6, sk) ? net_xmit_errno(err) : 0; release_sock(sk); + out: dst_release(dst); +out_no_dst: fl6_sock_release(flowlabel); + txopt_put(opt_to_free); if (!err) return len; /* @@ -1289,59 +1778,73 @@ out: * seems like overkill. */ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_SNDBUFERRORS, is_udplite); + UDP6_INC_STATS(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); } return err; do_confirm: - dst_confirm(dst); + if (msg->msg_flags & MSG_PROBE) + dst_confirm_neigh(dst, &fl6->daddr); if (!(msg->msg_flags&MSG_PROBE) || len) goto back_from_confirm; err = 0; goto out; } +EXPORT_SYMBOL(udpv6_sendmsg); + +static void udpv6_splice_eof(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct udp_sock *up = udp_sk(sk); + + if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk)) + return; + + lock_sock(sk); + if (up->pending && !udp_test_bit(CORK, sk)) + udp_v6_push_pending_frames(sk); + release_sock(sk); +} void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); lock_sock(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_v6_flush_pending_frames(sk); release_sock(sk); - if (static_key_false(&udpv6_encap_needed) && up->encap_type) { - void (*encap_destroy)(struct sock *sk); - encap_destroy = ACCESS_ONCE(up->encap_destroy); - if (encap_destroy) - encap_destroy(sk); + if (static_branch_unlikely(&udpv6_encap_needed_key)) { + if (up->encap_type) { + void (*encap_destroy)(struct sock *sk); + encap_destroy = READ_ONCE(up->encap_destroy); + if (encap_destroy) + encap_destroy(sk); + } + if (udp_test_bit(ENCAP_ENABLED, sk)) { + static_branch_dec(&udpv6_encap_needed_key); + udp_encap_disable(); + udp_tunnel_cleanup_gro(sk); + } } - - inet6_destroy_sock(sk); } /* * Socket option code for UDP */ -int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) +int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, + unsigned int optlen) { - if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, + if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET) + return udp_lib_setsockopt(sk, level, optname, + optval, optlen, udp_v6_push_pending_frames); return ipv6_setsockopt(sk, level, optname, optval, optlen); } -#ifdef CONFIG_COMPAT -int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) -{ - if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, - udp_v6_push_pending_frames); - return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); -} -#endif - int udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -1350,21 +1853,6 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname, return ipv6_getsockopt(sk, level, optname, optval, optlen); } -#ifdef CONFIG_COMPAT -int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_getsockopt(sk, level, optname, optval, optlen); - return compat_ipv6_getsockopt(sk, level, optname, optval, optlen); -} -#endif - -static const struct inet6_protocol udpv6_protocol = { - .handler = udpv6_rcv, - .err_handler = udpv6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS @@ -1374,84 +1862,79 @@ int udp6_seq_show(struct seq_file *seq, void *v) seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { int bucket = ((struct udp_iter_state *)seq->private)->bucket; - struct inet_sock *inet = inet_sk(v); + const struct inet_sock *inet = inet_sk((const struct sock *)v); __u16 srcp = ntohs(inet->inet_sport); __u16 destp = ntohs(inet->inet_dport); - ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); + __ip6_dgram_sock_seq_show(seq, v, srcp, destp, + udp_rqueue_get(v), bucket); } return 0; } -static const struct file_operations udp6_afinfo_seq_fops = { - .owner = THIS_MODULE, - .open = udp_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net +const struct seq_operations udp6_seq_ops = { + .start = udp_seq_start, + .next = udp_seq_next, + .stop = udp_seq_stop, + .show = udp6_seq_show, }; +EXPORT_SYMBOL(udp6_seq_ops); static struct udp_seq_afinfo udp6_seq_afinfo = { - .name = "udp6", .family = AF_INET6, - .udp_table = &udp_table, - .seq_fops = &udp6_afinfo_seq_fops, - .seq_ops = { - .show = udp6_seq_show, - }, + .udp_table = NULL, }; int __net_init udp6_proc_init(struct net *net) { - return udp_proc_register(net, &udp6_seq_afinfo); -} - -void udp6_proc_exit(struct net *net) { - udp_proc_unregister(net, &udp6_seq_afinfo); + if (!proc_create_net_data("udp6", 0444, net->proc_net, &udp6_seq_ops, + sizeof(struct udp_iter_state), &udp6_seq_afinfo)) + return -ENOMEM; + return 0; } -#endif /* CONFIG_PROC_FS */ -void udp_v6_clear_sk(struct sock *sk, int size) +void udp6_proc_exit(struct net *net) { - struct inet_sock *inet = inet_sk(sk); - - /* we do not want to clear pinet6 field, because of RCU lookups */ - sk_prot_clear_portaddr_nulls(sk, offsetof(struct inet_sock, pinet6)); - - size -= offsetof(struct inet_sock, pinet6) + sizeof(inet->pinet6); - memset(&inet->pinet6 + 1, 0, size); + remove_proc_entry("udp6", net->proc_net); } +#endif /* CONFIG_PROC_FS */ /* ------------------------------------------------------------------------ */ struct proto udpv6_prot = { - .name = "UDPv6", - .owner = THIS_MODULE, - .close = udp_lib_close, - .connect = ip6_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = udp_ioctl, - .destroy = udpv6_destroy_sock, - .setsockopt = udpv6_setsockopt, - .getsockopt = udpv6_getsockopt, - .sendmsg = udpv6_sendmsg, - .recvmsg = udpv6_recvmsg, - .backlog_rcv = __udpv6_queue_rcv_skb, - .hash = udp_lib_hash, - .unhash = udp_lib_unhash, - .rehash = udp_v6_rehash, - .get_port = udp_v6_get_port, - .memory_allocated = &udp_memory_allocated, - .sysctl_mem = sysctl_udp_mem, - .sysctl_wmem = &sysctl_udp_wmem_min, - .sysctl_rmem = &sysctl_udp_rmem_min, - .obj_size = sizeof(struct udp6_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, - .h.udp_table = &udp_table, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udpv6_setsockopt, - .compat_getsockopt = compat_udpv6_getsockopt, + .name = "UDPv6", + .owner = THIS_MODULE, + .close = udp_lib_close, + .pre_connect = udpv6_pre_connect, + .connect = udpv6_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .init = udpv6_init_sock, + .destroy = udpv6_destroy_sock, + .setsockopt = udpv6_setsockopt, + .getsockopt = udpv6_getsockopt, + .sendmsg = udpv6_sendmsg, + .recvmsg = udpv6_recvmsg, + .splice_eof = udpv6_splice_eof, + .release_cb = ip6_datagram_release_cb, + .hash = udp_lib_hash, + .unhash = udp_lib_unhash, + .rehash = udp_v6_rehash, + .get_port = udp_v6_get_port, + .put_port = udp_lib_unhash, +#ifdef CONFIG_BPF_SYSCALL + .psock_update_sk_prot = udp_bpf_update_proto, #endif - .clear_sk = udp_v6_clear_sk, + + .memory_allocated = &net_aligned_data.udp_memory_allocated, + .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, + + .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), + .obj_size = sizeof(struct udp6_sock), + .ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6), + .h.udp_table = NULL, + .diag_destroy = udp_abort, }; static struct inet_protosw udpv6_protosw = { @@ -1459,16 +1942,19 @@ static struct inet_protosw udpv6_protosw = { .protocol = IPPROTO_UDP, .prot = &udpv6_prot, .ops = &inet6_dgram_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_PERMANENT, }; - int __init udpv6_init(void) { int ret; - ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP); + net_hotdata.udpv6_protocol = (struct inet6_protocol) { + .handler = udpv6_rcv, + .err_handler = udpv6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, + }; + ret = inet6_add_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); if (ret) goto out; @@ -1479,12 +1965,12 @@ out: return ret; out_udpv6_protocol: - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); goto out; } void udpv6_exit(void) { inet6_unregister_protosw(&udpv6_protosw); - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); } |