X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=net%2Fipv6%2Fudp.c;h=b5dc5dbf186b4c09f857f57fb649d040dd017e46;hb=refs%2Fheads%2Fvserver;hp=513ed8f2ac0fc17b5b1fc8a63473e5a94cb74105;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 513ed8f2a..b5dc5dbf1 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -23,7 +23,6 @@ * 2 of the License, or (at your option) any later version. */ -#include #include #include #include @@ -39,123 +38,29 @@ #include #include -#include -#include - -#include #include #include #include #include -#include -#include -#include #include -#include #include - #include #include #include #include +#include "udp_impl.h" DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly; -/* Grrr, addr_type already calculated by caller, but I don't want - * to add some silly "cookie" argument to this method just for that. - */ -static int udp_v6_get_port(struct sock *sk, unsigned short snum) +static inline int udp_v6_get_port(struct sock *sk, unsigned short snum) { - struct sock *sk2; - struct hlist_node *node; - - write_lock_bh(&udp_hash_lock); - if (snum == 0) { - int best_size_so_far, best, result, i; - - if (udp_port_rover > sysctl_local_port_range[1] || - udp_port_rover < sysctl_local_port_range[0]) - udp_port_rover = sysctl_local_port_range[0]; - best_size_so_far = 32767; - best = result = udp_port_rover; - for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) { - int size; - struct hlist_head *list; - - list = &udp_hash[result & (UDP_HTABLE_SIZE - 1)]; - if (hlist_empty(list)) { - if (result > sysctl_local_port_range[1]) - result = sysctl_local_port_range[0] + - ((result - sysctl_local_port_range[0]) & - (UDP_HTABLE_SIZE - 1)); - goto gotit; - } - size = 0; - sk_for_each(sk2, node, list) - if (++size >= best_size_so_far) - goto next; - best_size_so_far = size; - best = result; - next:; - } - result = best; - for(i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++, result += UDP_HTABLE_SIZE) { - if (result > sysctl_local_port_range[1]) - result = sysctl_local_port_range[0] - + ((result - sysctl_local_port_range[0]) & - (UDP_HTABLE_SIZE - 1)); - if (!udp_lport_inuse(result)) - break; - } - if (i >= (1 << 16) / UDP_HTABLE_SIZE) - goto fail; -gotit: - udp_port_rover = snum = result; - } else { - sk_for_each(sk2, node, - &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]) { - if (inet_sk(sk2)->num == snum && - sk2 != sk && - (!sk2->sk_bound_dev_if || - !sk->sk_bound_dev_if || - sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && - (!sk2->sk_reuse || !sk->sk_reuse) && - ipv6_rcv_saddr_equal(sk, sk2)) - goto fail; - } - } - - inet_sk(sk)->num = snum; - if (sk_unhashed(sk)) { - sk_add_node(sk, &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]); - sock_prot_inc_use(sk->sk_prot); - } - write_unlock_bh(&udp_hash_lock); - return 0; - -fail: - write_unlock_bh(&udp_hash_lock); - return 1; + return udp_get_port(sk, snum, ipv6_rcv_saddr_equal); } -static void udp_v6_hash(struct sock *sk) -{ - BUG(); -} - -static void udp_v6_unhash(struct sock *sk) -{ - write_lock_bh(&udp_hash_lock); - if (sk_del_node_init(sk)) { - inet_sk(sk)->num = 0; - sock_prot_dec_use(sk->sk_prot); - } - write_unlock_bh(&udp_hash_lock); -} - -static struct sock *udp_v6_lookup(struct in6_addr *saddr, u16 sport, - struct in6_addr *daddr, u16 dport, int dif) +static struct sock *__udp6_lib_lookup(struct in6_addr *saddr, __be16 sport, + struct in6_addr *daddr, __be16 dport, + int dif, struct hlist_head udptable[]) { struct sock *sk, *result = NULL; struct hlist_node *node; @@ -163,7 +68,7 @@ static struct sock *udp_v6_lookup(struct in6_addr *saddr, u16 sport, int badness = -1; read_lock(&udp_hash_lock); - sk_for_each(sk, node, &udp_hash[hnum & (UDP_HTABLE_SIZE - 1)]) { + sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) { struct inet_sock *inet = inet_sk(sk); if (inet->num == hnum && sk->sk_family == PF_INET6) { @@ -204,21 +109,12 @@ static struct sock *udp_v6_lookup(struct in6_addr *saddr, u16 sport, return result; } -/* - * - */ - -static void udpv6_close(struct sock *sk, long timeout) -{ - sk_common_release(sk); -} - /* * This should be easy, if there is something there we * return it, otherwise we block. */ -static int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, +int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { @@ -226,7 +122,7 @@ static int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; size_t copied; - int err; + int err, copy_only, is_udplite = IS_UDPLITE(sk); if (addr_len) *addr_len=sizeof(struct sockaddr_in6); @@ -245,15 +141,21 @@ try_again: msg->msg_flags |= MSG_TRUNC; } - if (skb->ip_summed==CHECKSUM_UNNECESSARY) { - err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov, - copied); - } else if (msg->msg_flags&MSG_TRUNC) { - if (__skb_checksum_complete(skb)) + /* + * Decide whether to checksum and/or copy data. + */ + copy_only = (skb->ip_summed==CHECKSUM_UNNECESSARY); + + if (is_udplite || (!copy_only && msg->msg_flags&MSG_TRUNC)) { + if (__udp_lib_checksum_complete(skb)) goto csum_copy_err; - err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov, - copied); - } else { + copy_only = 1; + } + + if (copy_only) + 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 (err == -EINVAL) goto csum_copy_err; @@ -304,14 +206,15 @@ csum_copy_err: skb_kill_datagram(sk, skb, flags); if (flags & MSG_DONTWAIT) { - UDP6_INC_STATS_USER(UDP_MIB_INERRORS); + UDP6_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite); return -EAGAIN; } goto try_again; } -static void udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) +void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + int type, int code, int offset, __be32 info, + struct hlist_head udptable[] ) { struct ipv6_pinfo *np; struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; @@ -321,8 +224,8 @@ static void udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct sock *sk; int err; - sk = udp_v6_lookup(daddr, uh->dest, saddr, uh->source, inet6_iif(skb)); - + sk = __udp6_lib_lookup(daddr, uh->dest, + saddr, uh->source, inet6_iif(skb), udptable); if (sk == NULL) return; @@ -343,31 +246,60 @@ out: sock_put(sk); } -static inline int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) +static __inline__ void udpv6_err(struct sk_buff *skb, + struct inet6_skb_parm *opt, int type, + int code, int offset, __be32 info ) { - if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { - kfree_skb(skb); - return -1; - } + return __udp6_lib_err(skb, opt, type, code, offset, info, udp_hash); +} - if (skb_checksum_complete(skb)) { - UDP6_INC_STATS_BH(UDP_MIB_INERRORS); - kfree_skb(skb); - return 0; +int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) +{ + struct udp_sock *up = udp_sk(sk); + int rc; + + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) + goto drop; + + /* + * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). + */ + if ((up->pcflag & 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); + 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); + goto drop; + } } - if (sock_queue_rcv_skb(sk,skb)<0) { - UDP6_INC_STATS_BH(UDP_MIB_INERRORS); - kfree_skb(skb); - return 0; + if (udp_lib_checksum_complete(skb)) + goto drop; + + if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { + /* Note that an ENOMEM error is charged twice */ + if (rc == -ENOMEM) + UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, up->pcflag); + goto drop; } - UDP6_INC_STATS_BH(UDP_MIB_INDATAGRAMS); + UDP6_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag); return 0; +drop: + UDP6_INC_STATS_BH(UDP_MIB_INERRORS, up->pcflag); + kfree_skb(skb); + return -1; } static struct sock *udp_v6_mcast_next(struct sock *sk, - u16 loc_port, struct in6_addr *loc_addr, - u16 rmt_port, struct in6_addr *rmt_addr, + __be16 loc_port, struct in6_addr *loc_addr, + __be16 rmt_port, struct in6_addr *rmt_addr, int dif) { struct hlist_node *node; @@ -406,15 +338,15 @@ static struct sock *udp_v6_mcast_next(struct sock *sk, * Note: called only from the BH handler context, * so we don't need to lock the hashes. */ -static void udpv6_mcast_deliver(struct udphdr *uh, - struct in6_addr *saddr, struct in6_addr *daddr, - struct sk_buff *skb) +static int __udp6_lib_mcast_deliver(struct sk_buff *skb, struct in6_addr *saddr, + struct in6_addr *daddr, struct hlist_head udptable[]) { struct sock *sk, *sk2; + const struct udphdr *uh = skb->h.uh; int dif; read_lock(&udp_hash_lock); - sk = sk_head(&udp_hash[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]); + sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]); dif = inet6_iif(skb); sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); if (!sk) { @@ -432,9 +364,35 @@ static void udpv6_mcast_deliver(struct udphdr *uh, udpv6_queue_rcv_skb(sk, skb); out: read_unlock(&udp_hash_lock); + return 0; +} + +static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh) + +{ + if (uh->check == 0) { + /* RFC 2460 section 8.1 says that we SHOULD log + this error. Well, it is reasonable. + */ + LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); + return 1; + } + if (skb->ip_summed == CHECKSUM_COMPLETE && + !csum_ipv6_magic(&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr, + skb->len, IPPROTO_UDP, skb->csum )) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (skb->ip_summed != CHECKSUM_UNNECESSARY) + skb->csum = ~csum_unfold(csum_ipv6_magic(&skb->nh.ipv6h->saddr, + &skb->nh.ipv6h->daddr, + skb->len, IPPROTO_UDP, + 0)); + + return (UDP_SKB_CB(skb)->partial_cov = 0); } -static int udpv6_rcv(struct sk_buff **pskb) +int __udp6_lib_rcv(struct sk_buff **pskb, struct hlist_head udptable[], + int is_udplite) { struct sk_buff *skb = *pskb; struct sock *sk; @@ -451,44 +409,39 @@ static int udpv6_rcv(struct sk_buff **pskb) uh = skb->h.uh; ulen = ntohs(uh->len); + if (ulen > skb->len) + goto short_packet; - /* Check for jumbo payload */ - if (ulen == 0) - ulen = skb->len; + if(! is_udplite ) { /* UDP validates ulen. */ - if (ulen > skb->len || ulen < sizeof(*uh)) - goto short_packet; + /* Check for jumbo payload */ + if (ulen == 0) + ulen = skb->len; - if (uh->check == 0) { - /* RFC 2460 section 8.1 says that we SHOULD log - this error. Well, it is reasonable. - */ - LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); - goto discard; - } + if (ulen < sizeof(*uh)) + goto short_packet; - if (ulen < skb->len) { - if (pskb_trim_rcsum(skb, ulen)) - goto discard; - saddr = &skb->nh.ipv6h->saddr; - daddr = &skb->nh.ipv6h->daddr; - uh = skb->h.uh; - } + if (ulen < skb->len) { + if (pskb_trim_rcsum(skb, ulen)) + goto short_packet; + saddr = &skb->nh.ipv6h->saddr; + daddr = &skb->nh.ipv6h->daddr; + uh = skb->h.uh; + } - if (skb->ip_summed == CHECKSUM_HW && - !csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, skb->csum)) - skb->ip_summed = CHECKSUM_UNNECESSARY; + if (udp6_csum_init(skb, uh)) + goto discard; - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->csum = ~csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, 0); + } else { /* UDP-Lite validates cscov. */ + if (udplite6_csum_init(skb, uh)) + goto discard; + } /* * Multicast receive code */ - if (ipv6_addr_is_multicast(daddr)) { - udpv6_mcast_deliver(uh, saddr, daddr, skb); - return 0; - } + if (ipv6_addr_is_multicast(daddr)) + return __udp6_lib_mcast_deliver(skb, saddr, daddr, udptable); /* Unicast */ @@ -496,15 +449,16 @@ static int udpv6_rcv(struct sk_buff **pskb) * check socket cache ... must talk to Alan about his plans * for sock caches... i'll skip this for now. */ - sk = udp_v6_lookup(saddr, uh->source, daddr, uh->dest, inet6_iif(skb)); + sk = __udp6_lib_lookup(saddr, uh->source, + daddr, uh->dest, inet6_iif(skb), udptable); if (sk == NULL) { if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; - if (skb_checksum_complete(skb)) + if (udp_lib_checksum_complete(skb)) goto discard; - UDP6_INC_STATS_BH(UDP_MIB_NOPORTS); + UDP6_INC_STATS_BH(UDP_MIB_NOPORTS, is_udplite); icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev); @@ -519,14 +473,20 @@ static int udpv6_rcv(struct sk_buff **pskb) return(0); short_packet: - if (net_ratelimit()) - printk(KERN_DEBUG "UDP: short packet: %d/%u\n", ulen, skb->len); + LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: %d/%u\n", + is_udplite? "-Lite" : "", ulen, skb->len); discard: - UDP6_INC_STATS_BH(UDP_MIB_INERRORS); + UDP6_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); return(0); } + +static __inline__ int udpv6_rcv(struct sk_buff **pskb) +{ + return __udp6_lib_rcv(pskb, udp_hash, 0); +} + /* * Throw away all pending data and cancel the corking. Socket is locked. */ @@ -545,13 +505,15 @@ static void udp_v6_flush_pending_frames(struct sock *sk) * Sending */ -static int udp_v6_push_pending_frames(struct sock *sk, struct udp_sock *up) +static int udp_v6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; struct udphdr *uh; + struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct flowi *fl = &inet->cork.fl; int err = 0; + __wsum csum = 0; /* Grab the skbuff where UDP header space exists. */ if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) @@ -566,35 +528,17 @@ static int udp_v6_push_pending_frames(struct sock *sk, struct udp_sock *up) uh->len = htons(up->len); uh->check = 0; - if (sk->sk_no_check == UDP_CSUM_NOXMIT) { - skb->ip_summed = CHECKSUM_NONE; - goto send; - } + if (up->pcflag) + csum = udplite_csum_outgoing(sk, skb); + else + csum = udp_csum_outgoing(sk, skb); - if (skb_queue_len(&sk->sk_write_queue) == 1) { - skb->csum = csum_partial((char *)uh, - sizeof(struct udphdr), skb->csum); - uh->check = csum_ipv6_magic(&fl->fl6_src, - &fl->fl6_dst, - up->len, fl->proto, skb->csum); - } else { - u32 tmp_csum = 0; - - skb_queue_walk(&sk->sk_write_queue, skb) { - tmp_csum = csum_add(tmp_csum, skb->csum); - } - tmp_csum = csum_partial((char *)uh, - sizeof(struct udphdr), tmp_csum); - tmp_csum = csum_ipv6_magic(&fl->fl6_src, - &fl->fl6_dst, - up->len, fl->proto, tmp_csum); - uh->check = tmp_csum; - - } + /* add protocol-dependent pseudo-header */ + uh->check = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst, + up->len, fl->proto, csum ); if (uh->check == 0) - uh->check = -1; + uh->check = CSUM_MANGLED_0; -send: err = ip6_push_pending_frames(sk); out: up->len = 0; @@ -602,7 +546,7 @@ out: return err; } -static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, +int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; @@ -613,7 +557,7 @@ static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct in6_addr *daddr, *final_p = NULL, final; struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; - struct flowi *fl = &inet->cork.fl; + struct flowi fl; struct dst_entry *dst; int addr_len = msg->msg_namelen; int ulen = len; @@ -622,6 +566,8 @@ static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; int err; int connected = 0; + int is_udplite = up->pcflag; + int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); /* destination address check */ if (sin6) { @@ -670,7 +616,7 @@ do_udp_sendmsg: return udp_sendmsg(iocb, sk, msg, len); /* Rough check on arithmetic overflow, - better check is made in ip6_build_xmit + better check is made in ip6_append_data(). */ if (len > INT_MAX - sizeof(struct udphdr)) return -EMSGSIZE; @@ -693,19 +639,19 @@ do_udp_sendmsg: } ulen += sizeof(struct udphdr); - memset(fl, 0, sizeof(*fl)); + memset(&fl, 0, sizeof(fl)); if (sin6) { if (sin6->sin6_port == 0) return -EINVAL; - fl->fl_ip_dport = sin6->sin6_port; + fl.fl_ip_dport = sin6->sin6_port; daddr = &sin6->sin6_addr; if (np->sndflow) { - fl->fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; - if (fl->fl6_flowlabel&IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl->fl6_flowlabel); + fl.fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); if (flowlabel == NULL) return -EINVAL; daddr = &flowlabel->dst; @@ -723,32 +669,32 @@ do_udp_sendmsg: if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL) - fl->oif = sin6->sin6_scope_id; + fl.oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - fl->fl_ip_dport = inet->dport; + fl.fl_ip_dport = inet->dport; daddr = &np->daddr; - fl->fl6_flowlabel = np->flow_label; + fl.fl6_flowlabel = np->flow_label; connected = 1; } - if (!fl->oif) - fl->oif = sk->sk_bound_dev_if; + if (!fl.oif) + fl.oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(msg, fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); if (err < 0) { fl6_sock_release(flowlabel); return err; } - if ((fl->fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { - flowlabel = fl6_sock_lookup(sk, fl->fl6_flowlabel); + if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { + flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); if (flowlabel == NULL) return -EINVAL; } @@ -762,37 +708,39 @@ do_udp_sendmsg: opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); - fl->proto = IPPROTO_UDP; - ipv6_addr_copy(&fl->fl6_dst, daddr); - if (ipv6_addr_any(&fl->fl6_src) && !ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&fl->fl6_src, &np->saddr); - fl->fl_ip_sport = inet->sport; + fl.proto = sk->sk_protocol; + ipv6_addr_copy(&fl.fl6_dst, daddr); + if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr)) + ipv6_addr_copy(&fl.fl6_src, &np->saddr); + fl.fl_ip_sport = inet->sport; /* merge ip6_build_xmit from ip6_output */ if (opt && opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl->fl6_dst); - ipv6_addr_copy(&fl->fl6_dst, rt0->addr); + ipv6_addr_copy(&final, &fl.fl6_dst); + ipv6_addr_copy(&fl.fl6_dst, rt0->addr); final_p = &final; connected = 0; } - if (!fl->oif && ipv6_addr_is_multicast(&fl->fl6_dst)) { - fl->oif = np->mcast_oif; + if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) { + fl.oif = np->mcast_oif; connected = 0; } - err = ip6_dst_lookup(sk, &dst, fl); + security_sk_classify_flow(sk, &fl); + + err = ip6_sk_dst_lookup(sk, &dst, &fl); if (err) goto out; if (final_p) - ipv6_addr_copy(&fl->fl6_dst, final_p); + ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, fl, sk, 0)) < 0) + if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) goto out; if (hlimit < 0) { - if (ipv6_addr_is_multicast(&fl->fl6_dst)) + if (ipv6_addr_is_multicast(&fl.fl6_dst)) hlimit = np->mcast_hops; else hlimit = np->hop_limit; @@ -827,20 +775,28 @@ back_from_confirm: do_append_data: up->len += ulen; - err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen, - sizeof(struct udphdr), hlimit, tclass, opt, fl, + getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; + err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, + sizeof(struct udphdr), hlimit, tclass, opt, &fl, (struct 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, up); + 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(&fl->fl6_dst, &np->daddr) ? - &np->daddr : NULL); + ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ? + &np->daddr : NULL, +#ifdef CONFIG_IPV6_SUBTREES + ipv6_addr_equal(&fl.fl6_src, &np->saddr) ? + &np->saddr : +#endif + NULL); } else { dst_release(dst); } @@ -852,9 +808,19 @@ do_append_data: out: fl6_sock_release(flowlabel); if (!err) { - UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS); + UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite); return len; } + /* + * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting + * ENOBUFS might not be good (it's not tunable per se), but otherwise + * we don't have a good statistic (IpOutDiscards but it can be too many + * things). We could add another new stat but at least for now that + * seems like overkill. + */ + if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + UDP6_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite); + } return err; do_confirm: @@ -865,7 +831,7 @@ do_confirm: goto out; } -static int udpv6_destroy_sock(struct sock *sk) +int udpv6_destroy_sock(struct sock *sk) { lock_sock(sk); udp_v6_flush_pending_frames(sk); @@ -879,89 +845,43 @@ static int udpv6_destroy_sock(struct sock *sk) /* * Socket option code for UDP */ -static int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) +int udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) { - struct udp_sock *up = udp_sk(sk); - int val; - int err = 0; - - if (level != SOL_UDP) - return ipv6_setsockopt(sk, level, optname, optval, optlen); - - if(optlencorkflag = 1; - } else { - up->corkflag = 0; - lock_sock(sk); - udp_v6_push_pending_frames(sk, up); - release_sock(sk); - } - break; - - case UDP_ENCAP: - switch (val) { - case 0: - up->encap_type = val; - break; - default: - err = -ENOPROTOOPT; - break; - } - break; - - default: - err = -ENOPROTOOPT; - break; - }; - - return err; + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_setsockopt(sk, level, optname, optval, optlen, + udp_v6_push_pending_frames); + return ipv6_setsockopt(sk, level, optname, optval, optlen); } -static int udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) +#ifdef CONFIG_COMPAT +int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) { - struct udp_sock *up = udp_sk(sk); - int val, len; - - if (level != SOL_UDP) - return ipv6_getsockopt(sk, level, optname, optval, 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 - if(get_user(len,optlen)) - return -EFAULT; +int 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 ipv6_getsockopt(sk, level, optname, optval, optlen); +} - len = min_t(unsigned int, len, sizeof(int)); - - if(len < 0) - return -EINVAL; - - switch(optname) { - case UDP_CORK: - val = up->corkflag; - break; - - case UDP_ENCAP: - val = up->encap_type; - break; - - default: - return -ENOPROTOOPT; - }; - - if(put_user(len, optlen)) - return -EFAULT; - if(copy_to_user(optval, &val,len)) - return -EFAULT; - return 0; +#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 struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, @@ -1000,7 +920,7 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket atomic_read(&sp->sk_refcnt), sp); } -static int udp6_seq_show(struct seq_file *seq, void *v) +int udp6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, @@ -1019,6 +939,7 @@ static struct udp_seq_afinfo udp6_seq_afinfo = { .owner = THIS_MODULE, .name = "udp6", .family = AF_INET6, + .hashtable = udp_hash, .seq_show = udp6_seq_show, .seq_fops = &udp6_seq_fops, }; @@ -1036,22 +957,26 @@ void udp6_proc_exit(void) { /* ------------------------------------------------------------------------ */ struct proto udpv6_prot = { - .name = "UDPv6", - .owner = THIS_MODULE, - .close = udpv6_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_v6_hash, - .unhash = udp_v6_unhash, - .get_port = udp_v6_get_port, - .obj_size = sizeof(struct udp6_sock), + .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, + .get_port = udp_v6_get_port, + .obj_size = sizeof(struct udp6_sock), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_udpv6_setsockopt, + .compat_getsockopt = compat_udpv6_getsockopt, +#endif }; static struct inet_protosw udpv6_protosw = {