diff options
Diffstat (limited to 'net/ipv6/udp.c')
| -rw-r--r-- | net/ipv6/udp.c | 852 |
1 files changed, 554 insertions, 298 deletions
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 2596ffdeebea..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> @@ -36,6 +33,8 @@ #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/indirect_call_wrapper.h> +#include <trace/events/udp.h> #include <net/addrconf.h> #include <net/ndisc.h> @@ -43,39 +42,45 @@ #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" -static bool udp6_lib_exact_dif_match(struct net *net, struct sk_buff *skb) +static void udpv6_destruct_sock(struct sock *sk) { -#if defined(CONFIG_NET_L3_MASTER_DEV) - if (!net->ipv4.sysctl_udp_l3mdev_accept && - skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) - return true; -#endif - return false; + udp_destruct_common(sk); + inet6_sock_destruct(sk); } -static u32 udp6_ehashfn(const struct net *net, - const struct in6_addr *laddr, - const u16 lport, - const struct in6_addr *faddr, - const __be16 fport) +int udpv6_init_sock(struct sock *sk) { - static u32 udp6_ehash_secret __read_mostly; - static u32 udp_ipv6_hash_secret __read_mostly; + int res = udp_lib_init_sock(sk); + sk->sk_destruct = udpv6_destruct_sock; + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); + return res; +} + +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) +{ u32 lhash, fhash; net_get_random_once(&udp6_ehash_secret, @@ -87,7 +92,7 @@ static u32 udp6_ehashfn(const struct net *net, fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, - udp_ipv6_hash_secret + net_hash_mix(net)); + udp6_ehash_secret + net_hash_mix(net)); } int udp_v6_get_port(struct sock *sk, unsigned short snum) @@ -107,16 +112,27 @@ void udp_v6_rehash(struct sock *sk) 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); + 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); + } + + udp_lib_rehash(sk, new_hash, new_hash4); } -static int compute_score(struct sock *sk, struct net *net, +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, bool exact_dif) + int dif, int sdif) { - int score; + int bound_dev_if, score; struct inet_sock *inet; bool dev_match; @@ -143,82 +159,248 @@ static int compute_score(struct sock *sk, struct net *net, score++; } - dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif); + 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; - score++; + if (bound_dev_if) + score++; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; } +/** + * 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) +{ + 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; + } + } + + return result; +} + /* called with rcu_read_lock() */ -static struct sock *udp6_lib_lookup2(struct net *net, +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, bool exact_dif, - struct udp_hslot *hslot2, struct sk_buff *skb) + int dif, int sdif, struct udp_hslot *hslot2, + struct sk_buff *skb) { struct sock *sk, *result; int score, badness; - u32 hash = 0; + bool need_rescore; result = NULL; badness = -1; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { - score = compute_score(sk, net, saddr, sport, - daddr, hnum, dif, sdif, exact_dif); + need_rescore = false; +rescore: + score = compute_score(need_rescore ? result : sk, net, saddr, + sport, daddr, hnum, dif, sdif); if (score > badness) { - if (sk->sk_reuseport) { - hash = udp6_ehashfn(net, daddr, hnum, - saddr, sport); - - result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (result) - return result; - } - result = sk; badness = score; + + if (need_rescore) + continue; + + if (sk->sk_state == TCP_ESTABLISHED) { + result = sk; + continue; + } + + result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, udp6_ehashfn); + if (!result) { + result = sk; + 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; } } 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; + + 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(struct net *net, +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); - unsigned int hash2, slot2; struct udp_hslot *hslot2; - struct sock *result; - bool exact_dif = udp6_lib_exact_dif_match(net, skb); + struct sock *result, *sk; + unsigned int hash2; hash2 = ipv6_portaddr_hash(net, daddr, hnum); - slot2 = hash2 & udptable->mask; - hslot2 = &udptable->hash2[slot2]; + 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, exact_dif, + daddr, hnum, dif, sdif, hslot2, skb); - if (!result) { - hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum); - slot2 = hash2 & udptable->mask; + 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; + } + } - hslot2 = &udptable->hash2[slot2]; + /* Got non-wildcard socket or error on first lookup */ + if (result) + goto done; - result = udp6_lib_lookup2(net, saddr, sport, - &in6addr_any, hnum, dif, sdif, - exact_dif, hslot2, - skb); - } - if (unlikely(IS_ERR(result))) + /* 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; } @@ -235,28 +417,32 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, inet6_sdif(skb), udptable, skb); } -struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, +struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { - const struct ipv6hdr *iph = ipv6_hdr(skb); + 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; - return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, - &iph->daddr, dport, inet6_iif(skb), - inet6_sdif(skb), &udp_table, skb); + 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); } -EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb); /* 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(struct net *net, const struct in6_addr *saddr, __be16 sport, +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) { struct sock *sk; sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport, - dif, 0, &udp_table, NULL); + dif, 0, net->ipv4.udp_table, NULL); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; @@ -264,7 +450,7 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be EXPORT_SYMBOL_GPL(udp6_lib_lookup); #endif -/* do not use the scratch area len for jumbogram: their length execeeds the +/* 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 */ @@ -279,29 +465,27 @@ static int udp6_skb_len(struct sk_buff *skb) */ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int noblock, int flags, int *addr_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, peeking, off; - int err; + int off, err, peeking = flags & MSG_PEEK; int is_udplite = IS_UDPLITE(sk); + struct udp_mib __percpu *mib; bool checksum_valid = false; - struct udp_mib *mib; int is_udp4; if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); - if (np->rxpmtu && np->rxopt.bits.rxpmtu) + if (np->rxopt.bits.rxpmtu && READ_ONCE(np->rxpmtu)) return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: - peeking = flags & MSG_PEEK; off = sk_peek_offset(sk, flags); - skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err); + skb = __skb_recv_udp(sk, flags, &off, &err); if (!skb) return err; @@ -340,17 +524,17 @@ try_again: goto csum_copy_err; } if (unlikely(err)) { - if (!peeked) { - atomic_inc(&sk->sk_drops); + if (!peeking) { + udp_drops_inc(sk); SNMP_INC_STATS(mib, UDP_MIB_INERRORS); } kfree_skb(skb); return err; } - if (!peeked) + 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) { @@ -370,16 +554,20 @@ try_again: inet6_iif(skb)); } *addr_len = sizeof(*sin6); + + BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, + (struct sockaddr *)sin6, + addr_len); } - if (udp_sk(sk)->gro_enabled) + 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) + if (inet_cmsg_flags(inet)) ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off); } else { @@ -400,7 +588,7 @@ csum_copy_err: SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS); SNMP_INC_STATS(mib, UDP_MIB_INERRORS); } - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM); /* starting over for a new packet, but check if we need to yield */ cond_resched(); @@ -408,7 +596,7 @@ csum_copy_err: goto try_again; } -DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_inc(&udpv6_encap_needed_key); @@ -420,17 +608,19 @@ EXPORT_SYMBOL(udpv6_encap_enable); */ static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info) + 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, u32 info); + u8 type, u8 code, int offset, __be32 info); + const struct ip6_tnl_encap_ops *encap; - if (!ip6tun_encaps[i]) + encap = rcu_dereference(ip6tun_encaps[i]); + if (!encap) continue; - handler = rcu_dereference(ip6tun_encaps[i]->err_handler); + handler = encap->err_handler; if (handler && !handler(skb, opt, type, code, offset, info)) return 0; } @@ -459,12 +649,14 @@ 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 sock *sk; + struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); @@ -475,18 +667,28 @@ static struct sock *__udp6_lib_err_encap(struct net *net, /* 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) { - int (*lookup)(struct sock *sk, struct sk_buff *skb); - struct udp_sock *up = udp_sk(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)); @@ -505,7 +707,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, 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; + 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; @@ -514,17 +716,18 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct net *net = dev_net(skb->dev); sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, - inet6_iif(skb), inet6_sdif(skb), udptable, skb); - if (!sk) { + inet6_iif(skb), inet6_sdif(skb), udptable, NULL); + + if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) { /* No socket for error: try tunnels before discarding */ - sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udpv6_encap_needed_key)) { sk = __udp6_lib_err_encap(net, hdr, offset, uh, - udptable, skb, + 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), @@ -542,13 +745,14 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!ip6_sk_accept_pmtu(sk)) goto out; ip6_sk_update_pmtu(skb, sk, info); - if (np->pmtudisc != IPV6_PMTUDISC_DONT) + 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), - sk->sk_mark, sk->sk_uid); + READ_ONCE(sk->sk_mark), + sk_uid(sk)); } else { ip6_sk_redirect(skb, sk); } @@ -556,10 +760,14 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } /* Tunnels don't have an application socket: don't pass errors back */ - if (tunnel) + 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 { @@ -567,7 +775,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: return 0; } @@ -587,13 +795,21 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *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) + 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); - kfree_skb(skb); + trace_udp_fail_queue_rcv_skb(rc, sk, skb); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } @@ -604,18 +820,24 @@ static __inline__ int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - return __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); + return __udp6_lib_err(skb, opt, type, code, offset, info, + dev_net(skb->dev)->ipv4.udp_table); } 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 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_branch_unlikely(&udpv6_encap_needed_key) && 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); /* @@ -640,9 +862,9 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) ret = encap_rcv(sk, skb); if (ret <= 0) { - __UDP_INC_STATS(sock_net(sk), - UDP_MIB_INDATAGRAMS, - is_udplite); + __UDP6_INC_STATS(sock_net(sk), + UDP_MIB_INDATAGRAMS, + is_udplite); return -ret; } } @@ -653,16 +875,17 @@ static int udpv6_queue_rcv_one_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 */ + 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) { + if (UDP_SKB_CB(skb)->cscov < pcrlen) { net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n", - UDP_SKB_CB(skb)->cscov, up->pcrlen); + UDP_SKB_CB(skb)->cscov, pcrlen); goto drop; } } @@ -672,7 +895,7 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) udp_lib_checksum_complete(skb)) goto csum_error; - if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) + if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr), &drop_reason)) goto drop; udp_csum_pull_header(skb); @@ -682,11 +905,12 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) return __udpv6_queue_rcv_skb(sk, skb); csum_error: + drop_reason = SKB_DROP_REASON_UDP_CSUM; __UDP6_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: __UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - atomic_inc(&sk->sk_drops); - kfree_skb(skb); + udp_drops_inc(sk); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } @@ -700,10 +924,10 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) __skb_push(skb, -skb_mac_offset(skb)); segs = udp_rcv_segment(sk, skb, false); - for (skb = segs; skb; skb = next) { - next = skb->next; + skb_list_walk_safe(segs, skb, next) { __skb_pull(skb, skb_transport_offset(skb)); + 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, @@ -712,12 +936,12 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) return 0; } -static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, +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 inet_sock *inet = inet_sk(sk); + const struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) return false; @@ -727,7 +951,7 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, (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, sk->sk_bound_dev_if, dif, sdif) || + !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; @@ -770,7 +994,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, udptable->mask; hash2 = ipv6_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: - hslot = &udptable->hash2[hash2]; + hslot = &udptable->hash2[hash2].hslot; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } @@ -782,7 +1006,7 @@ start_lookup: /* If zero checksum and no_check is not on for * the socket then skip it. */ - if (!uh->check && !udp_sk(sk)->no_check6_rx) + if (!uh->check && !udp_get_no_check6_rx(sk)) continue; if (!first) { first = sk; @@ -790,7 +1014,7 @@ start_lookup: } nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) { - atomic_inc(&sk->sk_drops); + udp_drops_inc(sk); __UDP6_INC_STATS(net, UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk)); __UDP6_INC_STATS(net, UDP_MIB_INERRORS, @@ -821,14 +1045,11 @@ start_lookup: static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { - if (udp_sk_rx_dst_set(sk, dst)) { - const struct rt6_info *rt = (const struct rt6_info *)dst; - - inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); - } + 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 tacking care of csum conversion and +/* 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, @@ -837,8 +1058,7 @@ static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, int ret; if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) - skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, - ip6_compute_pseudo); + skb_checksum_try_convert(skb, IPPROTO_UDP, ip6_compute_pseudo); ret = udpv6_queue_rcv_skb(sk, skb); @@ -851,10 +1071,12 @@ static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, 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 = NULL; struct udphdr *uh; - struct sock *sk; + bool refcounted; u32 ulen = 0; if (!pskb_may_pull(skb, sizeof(struct udphdr))) @@ -891,21 +1113,27 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, goto csum_error; /* Check if the socket is already available, e.g. due to early demux */ - sk = skb_steal_sock(skb); + 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(sk->sk_rx_dst != dst)) + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp6_sk_rx_dst_set(sk, dst); - if (!uh->check && !udp_sk(sk)->no_check6_rx) { - sock_put(sk); + 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); - sock_put(sk); + if (refcounted) + sock_put(sk); return ret; } @@ -919,16 +1147,19 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, /* Unicast */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) { - if (!uh->check && !udp_sk(sk)->no_check6_rx) + 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; @@ -936,10 +1167,12 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, __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: + 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), @@ -950,10 +1183,12 @@ short_packet: report_csum_error: udp6_csum_zero_error(skb); csum_error: + 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(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); - kfree_skb(skb); + sk_skb_reason_drop(sk, skb, reason); return 0; } @@ -963,16 +1198,20 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net, __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); - unsigned int hash2 = ipv6_portaddr_hash(net, loc_addr, hnum); - unsigned int slot2 = hash2 & udp_table.mask; - struct udp_hslot *hslot2 = &udp_table.hash2[slot2]; - const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum); + 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(sk, net, rmt_addr, loc_addr, ports, dif, sdif)) + inet6_match(net, sk, rmt_addr, loc_addr, ports, dif, sdif)) return sk; /* Only check first socket in chain */ break; @@ -980,7 +1219,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net, return NULL; } -static void udp_v6_early_demux(struct sk_buff *skb) +void udp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); const struct udphdr *uh; @@ -1003,15 +1242,16 @@ static void udp_v6_early_demux(struct sk_buff *skb) else return; - if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) + if (!sk) return; skb->sk = sk; - skb->destructor = sock_efree; - dst = READ_ONCE(sk->sk_rx_dst); + 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, inet6_sk(sk)->rx_dst_cookie); + 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 @@ -1021,9 +1261,9 @@ static void udp_v6_early_demux(struct sk_buff *skb) } } -static __inline__ int udpv6_rcv(struct sk_buff *skb) +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); } /* @@ -1037,20 +1277,22 @@ 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 *uaddr, +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)) + if (ipv6_only_sock(sk)) return -EAFNOSUPPORT; return udp_pre_connect(sk, uaddr, addr_len); } @@ -1058,7 +1300,20 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; - return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr); + 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; } /** @@ -1066,6 +1321,9 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, * @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, @@ -1118,6 +1376,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, __wsum csum = 0; int offset = skb_transport_offset(skb); int len = skb->len - offset; + int datalen = len - sizeof(*uh); /* * Create a UDP header @@ -1132,32 +1391,37 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); - if (hlen + cork->gso_size > cork->fragsize) { + if (hlen + min(datalen, cork->gso_size) > cork->fragsize) { kfree_skb(skb); - return -EINVAL; + return -EMSGSIZE; } - if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) { + if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); return -EINVAL; } - if (udp_sk(sk)->no_check6_tx) { + if (udp_get_no_check6_tx(sk)) { kfree_skb(skb); return -EINVAL; } - if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || - dst_xfrm(skb_dst(skb))) { + if (is_udplite || dst_xfrm(skb_dst(skb))) { kfree_skb(skb); return -EIO; } - skb_shinfo(skb)->gso_size = cork->gso_size; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; - goto csum_partial; + 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(skb); - else if (udp_sk(sk)->no_check6_tx) { /* UDP csum disabled */ + 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 */ @@ -1176,7 +1440,7 @@ csum_partial: send: err = ip6_send_skb(skb); if (err) { - if (err == -ENOBUFS && !inet6_sk(sk)->recverr) { + if (err == -ENOBUFS && !inet6_test_bit(RECVERR6, sk)) { UDP6_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS, is_udplite); err = 0; @@ -1192,26 +1456,20 @@ static int udp_v6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; struct udp_sock *up = udp_sk(sk); - struct flowi6 fl6; int err = 0; if (up->pending == AF_INET) return udp_push_pending_frames(sk); - /* ip6_finish_skb will release the cork, so make a copy of - * fl6 here. - */ - fl6 = inet_sk(sk)->cork.fl.u.ip6; - skb = ip6_finish_skb(sk); if (!skb) goto out; - err = udp_v6_send_skb(skb, &fl6, &inet_sk(sk)->cork.base); - + 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; } @@ -1226,20 +1484,20 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 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 corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE; int err; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); - ipcm6_init(&ipc6); - ipc6.gso_size = up->gso_size; - ipc6.sockc.tsflags = sk->sk_tsflags; + ipcm6_init_sk(&ipc6, sk); + ipc6.gso_size = READ_ONCE(up->gso_size); /* destination address check */ if (sin6) { @@ -1266,7 +1524,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) default: return -EINVAL; } - } else if (!up->pending) { + } else if (!READ_ONCE(up->pending)) { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; @@ -1282,15 +1540,14 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: - if (__ipv6_only_sock(sk)) - return -ENETUNREACH; - return udp_sendmsg(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(sk, msg, len); - /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ @@ -1298,7 +1555,9 @@ do_udp_sendmsg: return -EMSGSIZE; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; - if (up->pending) { + 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. @@ -1316,20 +1575,20 @@ 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) + 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; } } @@ -1345,25 +1604,24 @@ do_udp_sendmsg: 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; + fl6->fl6_dport = inet->inet_dport; daddr = &sk->sk_v6_daddr; - fl6.flowlabel = np->flow_label; + 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->sk_uid; + fl6->flowi6_uid = sk_uid(sk); if (msg->msg_controllen) { opt = &opt_space; @@ -1372,21 +1630,22 @@ do_udp_sendmsg: ipc6.opt = opt; err = udp_cmsg_send(sk, msg, &ipc6.gso_size); - if (err > 0) - err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, + 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) + 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 = false; } if (!opt) { opt = txopt_get(np); @@ -1397,15 +1656,18 @@ do_udp_sendmsg: opt = ipv6_fixup_options(&opt_space, opt); ipc6.opt = opt; - fl6.flowi6_proto = sk->sk_protocol; - fl6.daddr = *daddr; - if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) - fl6.saddr = np->saddr; - fl6.fl6_sport = inet->inet_sport; + 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 && !connected) { + if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, - (struct sockaddr *)sin6, &fl6.saddr); + (struct sockaddr *)sin6, + &addr_len, + &fl6->saddr); if (err) goto out_no_dst; if (sin6) { @@ -1421,32 +1683,29 @@ do_udp_sendmsg: err = -EINVAL; goto out_no_dst; } - fl6.fl6_dport = sin6->sin6_port; - fl6.daddr = sin6->sin6_addr; + fl6->fl6_dport = sin6->sin6_port; + fl6->daddr = sin6->sin6_addr; } } - if (ipv6_addr_any(&fl6.daddr)) - fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + 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 = false; - if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) { - fl6.flowi6_oif = np->mcast_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 = np->ucast_oif; - - security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + } else if (!fl6->flowi6_oif) + fl6->flowi6_oif = READ_ONCE(np->ucast_oif); - if (ipc6.tclass < 0) - ipc6.tclass = np->tclass; + security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); - fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); + fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel); - dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, connected); + dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; @@ -1454,7 +1713,7 @@ do_udp_sendmsg: } if (ipc6.hlimit < 0) - ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); + ipc6.hlimit = ip6_sk_dst_hoplimit(np, fl6, dst); if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; @@ -1462,17 +1721,17 @@ back_from_confirm: /* Lockless fast path for the non-corking case */ if (!corkreq) { - struct inet_cork_full cork; struct sk_buff *skb; skb = ip6_make_skb(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, - &fl6, (struct rt6_info *)dst, + 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); - goto out; + err = udp_v6_send_skb(skb, fl6, &cork.base); + /* ip6_make_skb steals dst reference */ + goto out_no_dst; } lock_sock(sk); @@ -1486,24 +1745,22 @@ back_from_confirm: goto out; } - up->pending = AF_INET6; + WRITE_ONCE(up->pending, AF_INET6); do_append_data: - if (ipc6.dontfrag < 0) - ipc6.dontfrag = np->dontfrag; up->len += ulen; err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), - &ipc6, &fl6, (struct rt6_info *)dst, + &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; + 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: @@ -1528,17 +1785,35 @@ out_no_dst: do_confirm: if (msg->msg_flags & MSG_PROBE) - dst_confirm_neigh(dst, &fl6.daddr); + 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); @@ -1549,36 +1824,27 @@ void udpv6_destroy_sock(struct sock *sk) if (encap_destroy) encap_destroy(sk); } - if (up->encap_enabled) + 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) { @@ -1587,26 +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 - -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct inet6_protocol udpv6_protocol = { - .early_demux = udp_v6_early_demux, - .early_demux_handler = udp_v6_early_demux, - .handler = udpv6_rcv, - .err_handler = udpv6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS @@ -1616,7 +1862,7 @@ 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, @@ -1635,7 +1881,7 @@ EXPORT_SYMBOL(udp6_seq_ops); static struct udp_seq_afinfo udp6_seq_afinfo = { .family = AF_INET6, - .udp_table = &udp_table, + .udp_table = NULL, }; int __net_init udp6_proc_init(struct net *net) @@ -1659,30 +1905,35 @@ struct proto udpv6_prot = { .owner = THIS_MODULE, .close = udp_lib_close, .pre_connect = udpv6_pre_connect, - .connect = ip6_datagram_connect, + .connect = udpv6_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, - .init = udp_init_sock, + .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, - .memory_allocated = &udp_memory_allocated, + .put_port = udp_lib_unhash, +#ifdef CONFIG_BPF_SYSCALL + .psock_update_sk_prot = udp_bpf_update_proto, +#endif + + .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), - .h.udp_table = &udp_table, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udpv6_setsockopt, - .compat_getsockopt = compat_udpv6_getsockopt, -#endif + .ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6), + .h.udp_table = NULL, .diag_destroy = udp_abort, }; @@ -1698,7 +1949,12 @@ 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; @@ -1709,12 +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); } |