--- zzzz-none-000/linux-3.10.107/net/ipv6/udp.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/net/ipv6/udp.c 2021-02-04 17:41:59.000000000 +0000 @@ -46,47 +46,71 @@ #include #include #include +#include #include #include #include #include "udp_impl.h" +#ifdef CONFIG_AVM_PA +#include +#endif + +static u32 udp6_ehashfn(const struct net *net, + const struct in6_addr *laddr, + const u16 lport, + const struct in6_addr *faddr, + const __be16 fport) +{ + static u32 udp6_ehash_secret __read_mostly; + static u32 udp_ipv6_hash_secret __read_mostly; + + u32 lhash, fhash; + + net_get_random_once(&udp6_ehash_secret, + sizeof(udp6_ehash_secret)); + net_get_random_once(&udp_ipv6_hash_secret, + sizeof(udp_ipv6_hash_secret)); + + lhash = (__force u32)laddr->s6_addr32[3]; + fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); + + return __inet6_ehashfn(lhash, lport, fhash, fport, + udp_ipv6_hash_secret + net_hash_mix(net)); +} + int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { - 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_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); 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)); + (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr || + sk->sk_rcv_saddr == sk2->sk_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)) + !(ipv6_only_sock(sk) && addr_type2 == IPV6_ADDR_MAPPED)) return 1; if (sk2_rcv_saddr6 && - ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6)) + ipv6_addr_equal(&sk->sk_v6_rcv_saddr, sk2_rcv_saddr6)) return 1; return 0; } -static unsigned int udp6_portaddr_hash(struct net *net, - const struct in6_addr *addr6, - unsigned int port) +static u32 udp6_portaddr_hash(const struct net *net, + const struct in6_addr *addr6, + unsigned int port) { unsigned int hash, mix = net_hash_mix(net); @@ -100,13 +124,12 @@ return hash ^ port; } - int udp_v6_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum); unsigned int hash2_partial = - udp6_portaddr_hash(sock_net(sk), &inet6_sk(sk)->rcv_saddr, 0); + udp6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0); /* precompute partial secondary hash */ udp_sk(sk)->udp_portaddr_hash = hash2_partial; @@ -116,7 +139,7 @@ static void udp_v6_rehash(struct sock *sk) { u16 new_hash = udp6_portaddr_hash(sock_net(sk), - &inet6_sk(sk)->rcv_saddr, + &sk->sk_v6_rcv_saddr, inet_sk(sk)->inet_num); udp_lib_rehash(sk, new_hash); @@ -128,74 +151,90 @@ const struct in6_addr *daddr, __be16 dport, int dif) { - int score = -1; + int score; + struct inet_sock *inet; - 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 (!net_eq(sock_net(sk), net) || + udp_sk(sk)->udp_port_hash != hnum || + sk->sk_family != PF_INET6) + return -1; + + score = 0; + inet = inet_sk(sk); + + if (inet->inet_dport) { + if (inet->inet_dport != sport) + return -1; + score++; + } + + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) + return -1; + score++; } + + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr)) + return -1; + score++; + } + + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score++; + } + + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; + return score; } -#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) -{ - int score = -1; + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, + unsigned short hnum, int dif) +{ + int score; + struct inet_sock *inet; + + 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++; } + + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score++; + } + + if (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, @@ -218,14 +257,13 @@ badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - hash = inet6_ehashfn(net, daddr, hnum, - saddr, sport); + hash = udp6_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) + if (reciprocal_scale(hash, matches) == 0) result = sk; hash = next_pseudo_random32(hash); } @@ -239,7 +277,6 @@ 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, @@ -299,13 +336,13 @@ badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - hash = inet6_ehashfn(net, daddr, hnum, - saddr, sport); + hash = udp6_ehashfn(net, daddr, hnum, + saddr, sport); matches = 1; } } else if (score == badness && reuseport) { matches++; - if (((u64)hash * matches) >> 32 == 0) + if (reciprocal_scale(hash, matches) == 0) result = sk; hash = next_pseudo_random32(hash); } @@ -339,11 +376,18 @@ struct sock *sk; const struct ipv6hdr *iph = ipv6_hdr(skb); - if (unlikely(sk = skb_steal_sock(skb))) + sk = skb_steal_sock(skb); + if (unlikely(sk)) return sk; - return __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport, + + sk = __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), udptable); +#ifdef CONFIG_AVM_PA + if (sk) + avm_pa_add_local_session(skb, sk); +#endif + return sk; } struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, @@ -353,14 +397,12 @@ } EXPORT_SYMBOL_GPL(udp6_lib_lookup); - /* - * 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 udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); @@ -408,10 +450,10 @@ } if (checksum_valid || skb_csum_unnecessary(skb)) - err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, copied); + err = skb_copy_datagram_msg(skb, sizeof(struct udphdr), + msg, copied); else { - err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); + err = skb_copy_and_csum_datagram_msg(skb, sizeof(struct udphdr), msg); if (err == -EINVAL) goto csum_copy_err; } @@ -443,9 +485,7 @@ /* 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; @@ -458,16 +498,21 @@ 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); } + + if (np->rxopt.all) + ip6_datagram_recv_common_ctl(sk, msg, skb); + if (is_udp4) { if (inet->cmsg_flags) - ip_cmsg_recv(msg, skb); + ip_cmsg_recv_offset(msg, 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; @@ -510,19 +555,28 @@ 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); + struct udphdr *uh = (struct udphdr *)(skb->data+offset); struct sock *sk; int err; + struct net *net = dev_net(skb->dev); - sk = __udp6_lib_lookup(dev_net(skb->dev), daddr, uh->dest, + sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), udptable); - if (sk == NULL) + if (!sk) { + ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), + ICMP6_MIB_INERRORS); return; + } - if (type == ICMPV6_PKT_TOOBIG) + if (type == ICMPV6_PKT_TOOBIG) { + if (!ip6_sk_accept_pmtu(sk)) + goto out; ip6_sk_update_pmtu(skb, sk, info); - if (type == NDISC_REDIRECT) + } + if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); + goto out; + } np = inet6_sk(sk); @@ -545,8 +599,11 @@ { 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); + } rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) { @@ -565,7 +622,7 @@ static __inline__ void udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, - u8 code, int offset, __be32 info ) + u8 code, int offset, __be32 info) { __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); } @@ -603,9 +660,13 @@ /* 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) { + 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), @@ -624,15 +685,13 @@ if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { 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); + 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); + net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n", + UDP_SKB_CB(skb)->cscov, up->pcrlen); goto drop; } } @@ -642,8 +701,11 @@ goto csum_error; } - if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) + if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { + UDP6_INC_STATS_BH(sock_net(sk), + UDP_MIB_RCVBUFERRORS, is_udplite); goto drop; + } skb_dst_drop(skb); @@ -658,6 +720,7 @@ bh_unlock_sock(sk); return rc; + csum_error: UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: @@ -667,45 +730,28 @@ 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 bool __udp_v6_is_mcast_sock(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, unsigned short hnum) { - 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 inet_sock *inet = inet_sk(sk); - if (!net_eq(sock_net(s), net)) - continue; + if (!net_eq(sock_net(sk), net)) + return false; - 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; - - 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; - } - } - return NULL; + 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)) || + (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) || + (!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; } static void flush_stack(struct sock **stack, unsigned int count, @@ -717,7 +763,7 @@ for (i = 0; i < count; i++) { sk = stack[i]; - if (likely(skb1 == NULL)) + if (likely(!skb1)) skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); if (!skb1) { atomic_inc(&sk->sk_drops); @@ -729,54 +775,84 @@ if (skb1 && udpv6_queue_rcv_skb(sk, skb1) <= 0) skb1 = NULL; + sock_put(sk); } 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 *)]; 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; + struct hlist_nulls_node *node; + unsigned short hnum = ntohs(uh->dest); + struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); + int dif = inet6_iif(skb); + unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node); + unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); + bool inner_flushed = false; + + if (use_hash2) { + hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) & + udp_table.mask; + hash2 = udp6_portaddr_hash(net, daddr, hnum) & udp_table.mask; +start_lookup: + hslot = &udp_table.hash2[hash2]; + offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); + } 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; + sk_nulls_for_each_entry_offset(sk, node, &hslot->head, offset) { + if (__udp_v6_is_mcast_sock(net, sk, + uh->dest, daddr, + uh->source, saddr, + dif, hnum) && + /* If zero checksum and no_check is not on for + * the socket then skip it. + */ + (uh->check || udp_sk(sk)->no_check6_rx)) { + if (unlikely(count == ARRAY_SIZE(stack))) { + flush_stack(stack, count, skb, ~0); + inner_flushed = true; + count = 0; + } + stack[count++] = sk; + sock_hold(sk); } } - /* - * before releasing the lock, we must take reference on sockets - */ - for (i = 0; i < count; i++) - sock_hold(stack[i]); spin_unlock(&hslot->lock); + /* 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; + } + if (count) { flush_stack(stack, count, skb, count - 1); - - for (i = 0; i < count; i++) - sock_put(stack[i]); } else { - kfree_skb(skb); + if (!inner_flushed) + UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI, + proto == IPPROTO_UDPLITE); + consume_skb(skb); } return 0; } @@ -828,7 +904,7 @@ */ if (ipv6_addr_is_multicast(daddr)) return __udp6_lib_mcast_deliver(net, skb, - saddr, daddr, udptable); + saddr, daddr, udptable, proto); /* Unicast */ @@ -837,8 +913,20 @@ * 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 = udpv6_queue_rcv_skb(sk, skb); + if (sk) { + int ret; + + if (!uh->check && !udp_sk(sk)->no_check6_rx) { + sock_put(sk); + udp6_csum_zero_error(skb); + goto csum_error; + } + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + ip6_compute_pseudo); + + ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); /* a return value > 0 means to resubmit the input */ @@ -848,6 +936,11 @@ return 0; } + if (!uh->check) { + udp6_csum_zero_error(skb); + goto csum_error; + } + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; @@ -861,14 +954,11 @@ 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)); + 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; csum_error: UDP6_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); @@ -900,10 +990,10 @@ } /** - * 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) */ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, const struct in6_addr *saddr, @@ -911,9 +1001,10 @@ { 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); @@ -929,9 +1020,9 @@ 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); @@ -944,25 +1035,15 @@ * 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 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; /* * Create a UDP header @@ -970,26 +1051,28 @@ 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 (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_sk(sk)->no_check6_tx) { /* UDP csum disabled */ + skb->ip_summed = CHECKSUM_NONE; + goto send; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ + 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), @@ -999,22 +1082,46 @@ } else UDP6_INC_STATS_USER(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); + 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); + out: up->len = 0; 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 dst_entry *dst; @@ -1053,7 +1160,7 @@ } else if (!up->pending) { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - daddr = &np->daddr; + daddr = &sk->sk_v6_daddr; } else daddr = NULL; @@ -1068,12 +1175,12 @@ do_udp_sendmsg: if (__ipv6_only_sock(sk)) return -ENETUNREACH; - return udp_sendmsg(iocb, sk, msg, len); + return udp_sendmsg(sk, msg, len); } } if (up->pending == AF_INET) - return udp_sendmsg(iocb, sk, msg, len); + return udp_sendmsg(sk, msg, len); /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). @@ -1081,6 +1188,7 @@ if (len > INT_MAX - sizeof(struct udphdr)) return -EMSGSIZE; + getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; if (up->pending) { /* * There are pending frames. @@ -1112,9 +1220,8 @@ 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 (!flowlabel) return -EINVAL; - daddr = &flowlabel->dst; } } @@ -1123,8 +1230,8 @@ * 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 && @@ -1135,7 +1242,7 @@ return -EDESTADDRREQ; fl6.fl6_dport = inet->inet_dport; - daddr = &np->daddr; + daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; connected = 1; } @@ -1161,15 +1268,17 @@ } if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); - if (flowlabel == NULL) + if (!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); @@ -1195,39 +1304,44 @@ security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, true); + dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p); 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 (hlimit < 0) + hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (tclass < 0) tclass = np->tclass; - if (dontfrag < 0) - dontfrag = np->dontfrag; - 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), hlimit, tclass, opt, + &fl6, (struct rt6_info *)dst, + msg->msg_flags, dontfrag); + err = PTR_ERR(skb); + if (!IS_ERR_OR_NULL(skb)) + err = udp_v6_send_skb(skb, &fl6); + goto release_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; } @@ -1235,11 +1349,12 @@ up->pending = AF_INET6; do_append_data: + if (dontfrag < 0) + dontfrag = np->dontfrag; up->len += ulen; - getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; - err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, + err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), hlimit, tclass, opt, &fl6, - (struct rt6_info*)dst, + (struct rt6_info *)dst, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag); if (err) udp_v6_flush_pending_frames(sk); @@ -1248,11 +1363,16 @@ else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) up->pending = 0; + if (err > 0) + err = np->recverr ? net_xmit_errno(err) : 0; + release_sock(sk); + +release_dst: if (dst) { if (connected) { ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl6.daddr, &np->daddr) ? - &np->daddr : NULL, + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ? + &sk->sk_v6_daddr : NULL, #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_equal(&fl6.saddr, &np->saddr) ? &np->saddr : @@ -1264,12 +1384,10 @@ dst = NULL; } - if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; - release_sock(sk); out: dst_release(dst); fl6_sock_release(flowlabel); + txopt_put(opt_to_free); if (!err) return len; /* @@ -1359,48 +1477,17 @@ /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS - -static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket) -{ - struct inet_sock *inet = inet_sk(sp); - struct ipv6_pinfo *np = inet6_sk(sp); - const struct in6_addr *dest, *src; - __u16 destp, srcp; - - dest = &np->daddr; - src = &np->rcv_saddr; - destp = ntohs(inet->inet_dport); - srcp = ntohs(inet->inet_sport); - seq_printf(seq, - "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", - bucket, - src->s6_addr32[0], src->s6_addr32[1], - src->s6_addr32[2], src->s6_addr32[3], srcp, - dest->s6_addr32[0], dest->s6_addr32[1], - dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - sk_wmem_alloc_get(sp), - sk_rmem_alloc_get(sp), - 0, 0L, 0, - from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), - 0, - sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, - atomic_read(&sp->sk_drops)); -} - int udp6_seq_show(struct seq_file *seq, void *v) { - if (v == SEQ_START_TOKEN) - seq_printf(seq, - " sl " - "local_address " - "remote_address " - "st tx_queue rx_queue tr tm->when retrnsmt" - " uid timeout inode ref pointer drops\n"); - else - udp6_sock_seq_show(seq, v, ((struct udp_iter_state *)seq->private)->bucket); + if (v == SEQ_START_TOKEN) { + seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); + } else { + int bucket = ((struct udp_iter_state *)seq->private)->bucket; + struct inet_sock *inet = inet_sk(v); + __u16 srcp = ntohs(inet->inet_sport); + __u16 destp = ntohs(inet->inet_dport); + ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); + } return 0; } @@ -1427,7 +1514,8 @@ return udp_proc_register(net, &udp6_seq_afinfo); } -void udp6_proc_exit(struct net *net) { +void udp6_proc_exit(struct net *net) +{ udp_proc_unregister(net, &udp6_seq_afinfo); } #endif /* CONFIG_PROC_FS */ @@ -1481,11 +1569,9 @@ .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;