diff options
Diffstat (limited to 'net/ipv6')
32 files changed, 953 insertions, 801 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index fd6782e3a038..3daaf3c7703c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -718,12 +718,9 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) struct inet6_ifaddr *ifa, *ifn; struct inet6_dev *idev = ifp->idev; int state; - int hash; int deleted = 0, onlink = 0; unsigned long expires = jiffies; - hash = ipv6_addr_hash(&ifp->addr); - spin_lock_bh(&ifp->state_lock); state = ifp->state; ifp->state = INET6_IFADDR_STATE_DEAD; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 978e80e2c4a8..4b13d5d8890e 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -644,41 +644,34 @@ EXPORT_SYMBOL(inet6_unregister_protosw); int inet6_sk_rebuild_header(struct sock *sk) { - int err; - struct dst_entry *dst; struct ipv6_pinfo *np = inet6_sk(sk); + struct dst_entry *dst; dst = __sk_dst_check(sk, np->dst_cookie); if (dst == NULL) { struct inet_sock *inet = inet_sk(sk); struct in6_addr *final_p, final; - struct flowi fl; - - memset(&fl, 0, sizeof(fl)); - fl.proto = sk->sk_protocol; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.fl6_flowlabel = np->flow_label; - fl.oif = sk->sk_bound_dev_if; - fl.mark = sk->sk_mark; - fl.fl_ip_dport = inet->inet_dport; - fl.fl_ip_sport = inet->inet_sport; - security_sk_classify_flow(sk, &fl); - - final_p = fl6_update_dst(&fl, np->opt, &final); - - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) { + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = sk->sk_protocol; + ipv6_addr_copy(&fl6.daddr, &np->daddr); + ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.flowlabel = np->flow_label; + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_mark = sk->sk_mark; + fl6.fl6_dport = inet->inet_dport; + fl6.fl6_sport = inet->inet_sport; + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + + final_p = fl6_update_dst(&fl6, np->opt, &final); + + dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + if (IS_ERR(dst)) { sk->sk_route_caps = 0; - return err; - } - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) { - sk->sk_err_soft = -err; - return err; + sk->sk_err_soft = -PTR_ERR(dst); + return PTR_ERR(dst); } __ip6_dst_store(sk, dst, NULL, NULL); @@ -772,7 +765,7 @@ out: return err; } -static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) +static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 1aba54ae53c4..2195ae651923 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -409,7 +409,7 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) ah->reserved = 0; ah->spi = x->id.spi; - ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output); + ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); sg_init_table(sg, nfrags); skb_to_sgvec(skb, sg, 0, skb->len); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 320bdb877eed..16560336eb72 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -40,7 +40,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *daddr, *final_p, final; struct dst_entry *dst; - struct flowi fl; + struct flowi6 fl6; struct ip6_flowlabel *flowlabel = NULL; struct ipv6_txoptions *opt; int addr_type; @@ -59,11 +59,11 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; - memset(&fl, 0, sizeof(fl)); + memset(&fl6, 0, sizeof(fl6)); if (np->sndflow) { - fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; - if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); @@ -137,7 +137,7 @@ ipv4_connected: } ipv6_addr_copy(&np->daddr, daddr); - np->flow_label = fl.fl6_flowlabel; + np->flow_label = fl6.flowlabel; inet->inet_dport = usin->sin6_port; @@ -146,53 +146,46 @@ ipv4_connected: * destination cache for it. */ - fl.proto = sk->sk_protocol; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.oif = sk->sk_bound_dev_if; - fl.mark = sk->sk_mark; - fl.fl_ip_dport = inet->inet_dport; - fl.fl_ip_sport = inet->inet_sport; + fl6.flowi6_proto = sk->sk_protocol; + ipv6_addr_copy(&fl6.daddr, &np->daddr); + ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_mark = sk->sk_mark; + fl6.fl6_dport = inet->inet_dport; + fl6.fl6_sport = inet->inet_sport; - if (!fl.oif && (addr_type&IPV6_ADDR_MULTICAST)) - fl.oif = np->mcast_oif; + if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST)) + fl6.flowi6_oif = np->mcast_oif; - security_sk_classify_flow(sk, &fl); + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); opt = flowlabel ? flowlabel->opt : np->opt; - final_p = fl6_update_dst(&fl, opt, &final); + final_p = fl6_update_dst(&fl6, opt, &final); - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) + dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); + err = 0; + if (IS_ERR(dst)) { + err = PTR_ERR(dst); goto out; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); - if (err < 0) { - if (err == -EREMOTE) - err = ip6_dst_blackhole(sk, &dst, &fl); - if (err < 0) - goto out; } /* source address lookup done in ip6_dst_lookup */ if (ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&np->saddr, &fl.fl6_src); + ipv6_addr_copy(&np->saddr, &fl6.saddr); if (ipv6_addr_any(&np->rcv_saddr)) { - ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src); + ipv6_addr_copy(&np->rcv_saddr, &fl6.saddr); inet->inet_rcv_saddr = LOOPBACK4_IPV6; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ? + ipv6_addr_equal(&fl6.daddr, &np->daddr) ? &np->daddr : NULL, #ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_equal(&fl.fl6_src, &np->saddr) ? + ipv6_addr_equal(&fl6.saddr, &np->saddr) ? &np->saddr : #endif NULL); @@ -238,7 +231,7 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, kfree_skb(skb); } -void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info) +void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; @@ -257,7 +250,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info) skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); - ipv6_addr_copy(&iph->daddr, &fl->fl6_dst); + ipv6_addr_copy(&iph->daddr, &fl6->daddr); serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; @@ -268,7 +261,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info) serr->ee.ee_info = info; serr->ee.ee_data = 0; serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb); - serr->port = fl->fl_ip_dport; + serr->port = fl6->fl6_dport; __skb_pull(skb, skb_tail_pointer(skb) - skb->data); skb_reset_transport_header(skb); @@ -277,7 +270,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info) kfree_skb(skb); } -void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu) +void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6hdr *iph; @@ -294,7 +287,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu) skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); - ipv6_addr_copy(&iph->daddr, &fl->fl6_dst); + ipv6_addr_copy(&iph->daddr, &fl6->daddr); mtu_info = IP6CBMTU(skb); if (!mtu_info) { @@ -306,7 +299,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu) mtu_info->ip6m_addr.sin6_family = AF_INET6; mtu_info->ip6m_addr.sin6_port = 0; mtu_info->ip6m_addr.sin6_flowinfo = 0; - mtu_info->ip6m_addr.sin6_scope_id = fl->oif; + mtu_info->ip6m_addr.sin6_scope_id = fl6->flowi6_oif; ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr); __skb_pull(skb, skb_tail_pointer(skb) - skb->data); @@ -600,7 +593,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) } int datagram_send_ctl(struct net *net, - struct msghdr *msg, struct flowi *fl, + struct msghdr *msg, struct flowi6 *fl6, struct ipv6_txoptions *opt, int *hlimit, int *tclass, int *dontfrag) { @@ -636,16 +629,17 @@ int datagram_send_ctl(struct net *net, src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); if (src_info->ipi6_ifindex) { - if (fl->oif && src_info->ipi6_ifindex != fl->oif) + if (fl6->flowi6_oif && + src_info->ipi6_ifindex != fl6->flowi6_oif) return -EINVAL; - fl->oif = src_info->ipi6_ifindex; + fl6->flowi6_oif = src_info->ipi6_ifindex; } addr_type = __ipv6_addr_type(&src_info->ipi6_addr); rcu_read_lock(); - if (fl->oif) { - dev = dev_get_by_index_rcu(net, fl->oif); + if (fl6->flowi6_oif) { + dev = dev_get_by_index_rcu(net, fl6->flowi6_oif); if (!dev) { rcu_read_unlock(); return -ENODEV; @@ -661,7 +655,7 @@ int datagram_send_ctl(struct net *net, strict ? dev : NULL, 0)) err = -EINVAL; else - ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr); + ipv6_addr_copy(&fl6->saddr, &src_info->ipi6_addr); } rcu_read_unlock(); @@ -678,13 +672,13 @@ int datagram_send_ctl(struct net *net, goto exit_f; } - if (fl->fl6_flowlabel&IPV6_FLOWINFO_MASK) { - if ((fl->fl6_flowlabel^*(__be32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) { + if (fl6->flowlabel&IPV6_FLOWINFO_MASK) { + if ((fl6->flowlabel^*(__be32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) { err = -EINVAL; goto exit_f; } } - fl->fl6_flowlabel = IPV6_FLOWINFO_MASK & *(__be32 *)CMSG_DATA(cmsg); + fl6->flowlabel = IPV6_FLOWINFO_MASK & *(__be32 *)CMSG_DATA(cmsg); break; case IPV6_2292HOPOPTS: diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 1b5c9825743b..5aa8ec88f194 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -54,16 +54,20 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu); /* * Allocate an AEAD request structure with extra space for SG and IV. * - * For alignment considerations the IV is placed at the front, followed - * by the request and finally the SG list. + * For alignment considerations the upper 32 bits of the sequence number are + * placed at the front, if present. Followed by the IV, the request and finally + * the SG list. * * TODO: Use spare space in skb for this where possible. */ -static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags) +static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqihlen) { unsigned int len; - len = crypto_aead_ivsize(aead); + len = seqihlen; + + len += crypto_aead_ivsize(aead); + if (len) { len += crypto_aead_alignmask(aead) & ~(crypto_tfm_ctx_alignment() - 1); @@ -78,10 +82,16 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags) return kmalloc(len, GFP_ATOMIC); } -static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp) +static inline __be32 *esp_tmp_seqhi(void *tmp) +{ + return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32)); +} + +static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen) { return crypto_aead_ivsize(aead) ? - PTR_ALIGN((u8 *)tmp, crypto_aead_alignmask(aead) + 1) : tmp; + PTR_ALIGN((u8 *)tmp + seqhilen, + crypto_aead_alignmask(aead) + 1) : tmp + seqhilen; } static inline struct aead_givcrypt_request *esp_tmp_givreq( @@ -145,8 +155,12 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) int plen; int tfclen; int nfrags; + int assoclen; + int sglists; + int seqhilen; u8 *iv; u8 *tail; + __be32 *seqhi; struct esp_data *esp = x->data; /* skb is pure payload to encrypt */ @@ -175,14 +189,25 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) goto error; nfrags = err; - tmp = esp_alloc_tmp(aead, nfrags + 1); + assoclen = sizeof(*esph); + sglists = 1; + seqhilen = 0; + + if (x->props.flags & XFRM_STATE_ESN) { + sglists += 2; + seqhilen += sizeof(__be32); + assoclen += seqhilen; + } + + tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); if (!tmp) goto error; - iv = esp_tmp_iv(aead, tmp); + seqhi = esp_tmp_seqhi(tmp); + iv = esp_tmp_iv(aead, tmp, seqhilen); req = esp_tmp_givreq(aead, iv); asg = esp_givreq_sg(aead, req); - sg = asg + 1; + sg = asg + sglists; /* Fill padding... */ tail = skb_tail_pointer(trailer); @@ -204,19 +229,27 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) *skb_mac_header(skb) = IPPROTO_ESP; esph->spi = x->id.spi; - esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output); + esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); sg_init_table(sg, nfrags); skb_to_sgvec(skb, sg, esph->enc_data + crypto_aead_ivsize(aead) - skb->data, clen + alen); - sg_init_one(asg, esph, sizeof(*esph)); + + if ((x->props.flags & XFRM_STATE_ESN)) { + sg_init_table(asg, 3); + sg_set_buf(asg, &esph->spi, sizeof(__be32)); + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(asg + 1, seqhi, seqhilen); + sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32)); + } else + sg_init_one(asg, esph, sizeof(*esph)); aead_givcrypt_set_callback(req, 0, esp_output_done, skb); aead_givcrypt_set_crypt(req, sg, sg, clen, iv); - aead_givcrypt_set_assoc(req, asg, sizeof(*esph)); + aead_givcrypt_set_assoc(req, asg, assoclen); aead_givcrypt_set_giv(req, esph->enc_data, - XFRM_SKB_CB(skb)->seq.output); + XFRM_SKB_CB(skb)->seq.output.low); ESP_SKB_CB(skb)->tmp = tmp; err = crypto_aead_givencrypt(req); @@ -292,8 +325,12 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) struct sk_buff *trailer; int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead); int nfrags; + int assoclen; + int sglists; + int seqhilen; int ret = 0; void *tmp; + __be32 *seqhi; u8 *iv; struct scatterlist *sg; struct scatterlist *asg; @@ -314,12 +351,24 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) } ret = -ENOMEM; - tmp = esp_alloc_tmp(aead, nfrags + 1); + + assoclen = sizeof(*esph); + sglists = 1; + seqhilen = 0; + + if (x->props.flags & XFRM_STATE_ESN) { + sglists += 2; + seqhilen += sizeof(__be32); + assoclen += seqhilen; + } + + tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); if (!tmp) goto out; ESP_SKB_CB(skb)->tmp = tmp; - iv = esp_tmp_iv(aead, tmp); + seqhi = esp_tmp_seqhi(tmp); + iv = esp_tmp_iv(aead, tmp, seqhilen); req = esp_tmp_req(aead, iv); asg = esp_req_sg(aead, req); sg = asg + 1; @@ -333,11 +382,19 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) sg_init_table(sg, nfrags); skb_to_sgvec(skb, sg, sizeof(*esph) + crypto_aead_ivsize(aead), elen); - sg_init_one(asg, esph, sizeof(*esph)); + + if ((x->props.flags & XFRM_STATE_ESN)) { + sg_init_table(asg, 3); + sg_set_buf(asg, &esph->spi, sizeof(__be32)); + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(asg + 1, seqhi, seqhilen); + sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32)); + } else + sg_init_one(asg, esph, sizeof(*esph)); aead_request_set_callback(req, 0, esp_input_done, skb); aead_request_set_crypt(req, sg, sg, elen, iv); - aead_request_set_assoc(req, asg, sizeof(*esph)); + aead_request_set_assoc(req, asg, assoclen); ret = crypto_aead_decrypt(req); if (ret == -EINPROGRESS) @@ -443,10 +500,20 @@ static int esp_init_authenc(struct xfrm_state *x) goto error; err = -ENAMETOOLONG; - if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, "authenc(%s,%s)", - x->aalg ? x->aalg->alg_name : "digest_null", - x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME) - goto error; + + if ((x->props.flags & XFRM_STATE_ESN)) { + if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, + "authencesn(%s,%s)", + x->aalg ? x->aalg->alg_name : "digest_null", + x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME) + goto error; + } else { + if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, + "authenc(%s,%s)", + x->aalg ? x->aalg->alg_name : "digest_null", + x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME) + goto error; + } aead = crypto_alloc_aead(authenc_name, 0, 0); err = PTR_ERR(aead); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 262f105d23b9..79a485e8a700 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -876,22 +876,22 @@ struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, * fl6_update_dst - update flowi destination address with info given * by srcrt option, if any. * - * @fl: flowi for which fl6_dst is to be updated + * @fl6: flowi6 for which daddr is to be updated * @opt: struct ipv6_txoptions in which to look for srcrt opt - * @orig: copy of original fl6_dst address if modified + * @orig: copy of original daddr address if modified * * Returns NULL if no txoptions or no srcrt, otherwise returns orig - * and initial value of fl->fl6_dst set in orig + * and initial value of fl6->daddr set in orig */ -struct in6_addr *fl6_update_dst(struct flowi *fl, +struct in6_addr *fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig) { if (!opt || !opt->srcrt) return NULL; - ipv6_addr_copy(orig, &fl->fl6_dst); - ipv6_addr_copy(&fl->fl6_dst, ((struct rt0_hdr *)opt->srcrt)->addr); + ipv6_addr_copy(orig, &fl6->daddr); + ipv6_addr_copy(&fl6->daddr, ((struct rt0_hdr *)opt->srcrt)->addr); return orig; } diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index d829874d8946..34d244df907d 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -29,7 +29,7 @@ struct fib6_rule u8 tclass; }; -struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl, +struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, int flags, pol_lookup_t lookup) { struct fib_lookup_arg arg = { @@ -37,7 +37,8 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl, .flags = FIB_LOOKUP_NOREF, }; - fib_rules_lookup(net->ipv6.fib6_rules_ops, fl, flags, &arg); + fib_rules_lookup(net->ipv6.fib6_rules_ops, + flowi6_to_flowi(fl6), flags, &arg); if (arg.result) return arg.result; @@ -49,6 +50,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl, static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { + struct flowi6 *flp6 = &flp->u.ip6; struct rt6_info *rt = NULL; struct fib6_table *table; struct net *net = rule->fr_net; @@ -71,7 +73,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, table = fib6_get_table(net, rule->table); if (table) - rt = lookup(net, table, flp, flags); + rt = lookup(net, table, flp6, flags); if (rt != net->ipv6.ip6_null_entry) { struct fib6_rule *r = (struct fib6_rule *)rule; @@ -86,14 +88,14 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, if (ipv6_dev_get_saddr(net, ip6_dst_idev(&rt->dst)->dev, - &flp->fl6_dst, + &flp6->daddr, rt6_flags2srcprefs(flags), &saddr)) goto again; if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen)) goto again; - ipv6_addr_copy(&flp->fl6_src, &saddr); + ipv6_addr_copy(&flp6->saddr, &saddr); } goto out; } @@ -113,9 +115,10 @@ out: static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { struct fib6_rule *r = (struct fib6_rule *) rule; + struct flowi6 *fl6 = &fl->u.ip6; if (r->dst.plen && - !ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen)) + !ipv6_prefix_equal(&fl6->daddr, &r->dst.addr, r->dst.plen)) return 0; /* @@ -125,14 +128,14 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) */ if (r->src.plen) { if (flags & RT6_LOOKUP_F_HAS_SADDR) { - if (!ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, + if (!ipv6_prefix_equal(&fl6->saddr, &r->src.addr, r->src.plen)) return 0; } else if (!(r->common.flags & FIB_RULE_FIND_SADDR)) return 0; } - if (r->tclass && r->tclass != ((ntohl(fl->fl6_flowlabel) >> 20) & 0xff)) + if (r->tclass && r->tclass != ((ntohl(fl6->flowlabel) >> 20) & 0xff)) return 0; return 1; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 03e62f94ff8e..83cb4f9add81 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -157,32 +157,32 @@ static int is_ineligible(struct sk_buff *skb) /* * Check the ICMP output rate limit */ -static inline int icmpv6_xrlim_allow(struct sock *sk, u8 type, - struct flowi *fl) +static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type, + struct flowi6 *fl6) { struct dst_entry *dst; struct net *net = sock_net(sk); - int res = 0; + bool res = false; /* Informational messages are not limited. */ if (type & ICMPV6_INFOMSG_MASK) - return 1; + return true; /* Do not limit pmtu discovery, it would break it. */ if (type == ICMPV6_PKT_TOOBIG) - return 1; + return true; /* * Look up the output route. * XXX: perhaps the expire for routing entries cloned by * this lookup should be more aggressive (not longer than timeout). */ - dst = ip6_route_output(net, sk, fl); + dst = ip6_route_output(net, sk, fl6); if (dst->error) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); } else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) { - res = 1; + res = true; } else { struct rt6_info *rt = (struct rt6_info *)dst; int tmo = net->ipv6.sysctl.icmpv6_time; @@ -191,7 +191,9 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, u8 type, if (rt->rt6i_dst.plen < 128) tmo >>= ((128 - rt->rt6i_dst.plen)>>5); - res = xrlim_allow(dst, tmo); + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 1); + res = inet_peer_xrlim_allow(rt->rt6i_peer, tmo); } dst_release(dst); return res; @@ -215,7 +217,7 @@ static __inline__ int opt_unrec(struct sk_buff *skb, __u32 offset) return (*op & 0xC0) == 0x80; } -static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct icmp6hdr *thdr, int len) +static int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len) { struct sk_buff *skb; struct icmp6hdr *icmp6h; @@ -231,9 +233,9 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct if (skb_queue_len(&sk->sk_write_queue) == 1) { skb->csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), skb->csum); - icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src, - &fl->fl6_dst, - len, fl->proto, + icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr, + &fl6->daddr, + len, fl6->flowi6_proto, skb->csum); } else { __wsum tmp_csum = 0; @@ -244,9 +246,9 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct tmp_csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), tmp_csum); - icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src, - &fl->fl6_dst, - len, fl->proto, + icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr, + &fl6->daddr, + len, fl6->flowi6_proto, tmp_csum); } ip6_push_pending_frames(sk); @@ -298,6 +300,68 @@ static void mip6_addr_swap(struct sk_buff *skb) static inline void mip6_addr_swap(struct sk_buff *skb) {} #endif +static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb, + struct sock *sk, struct flowi6 *fl6) +{ + struct dst_entry *dst, *dst2; + struct flowi6 fl2; + int err; + + err = ip6_dst_lookup(sk, &dst, fl6); + if (err) + return ERR_PTR(err); + + /* + * We won't send icmp if the destination is known + * anycast. + */ + if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) { + LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: acast source\n"); + dst_release(dst); + return ERR_PTR(-EINVAL); + } + + /* No need to clone since we're just using its address. */ + dst2 = dst; + + dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), sk, 0); + if (!IS_ERR(dst)) { + if (dst != dst2) + return dst; + } else { + if (PTR_ERR(dst) == -EPERM) + dst = NULL; + else + return dst; + } + + err = xfrm_decode_session_reverse(skb, flowi6_to_flowi(&fl2), AF_INET6); + if (err) + goto relookup_failed; + + err = ip6_dst_lookup(sk, &dst2, &fl2); + if (err) + goto relookup_failed; + + dst2 = xfrm_lookup(net, dst2, flowi6_to_flowi(&fl2), sk, XFRM_LOOKUP_ICMP); + if (!IS_ERR(dst2)) { + dst_release(dst); + dst = dst2; + } else { + err = PTR_ERR(dst2); + if (err == -EPERM) { + dst_release(dst); + return dst2; + } else + goto relookup_failed; + } + +relookup_failed: + if (dst) + return dst; + return ERR_PTR(err); +} + /* * Send an ICMP message in response to a packet in error */ @@ -310,10 +374,8 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) struct ipv6_pinfo *np; struct in6_addr *saddr = NULL; struct dst_entry *dst; - struct dst_entry *dst2; struct icmp6hdr tmp_hdr; - struct flowi fl; - struct flowi fl2; + struct flowi6 fl6; struct icmpv6_msg msg; int iif = 0; int addr_type = 0; @@ -380,22 +442,22 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) mip6_addr_swap(skb); - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_ICMPV6; - ipv6_addr_copy(&fl.fl6_dst, &hdr->saddr); + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_ICMPV6; + ipv6_addr_copy(&fl6.daddr, &hdr->saddr); if (saddr) - ipv6_addr_copy(&fl.fl6_src, saddr); - fl.oif = iif; - fl.fl_icmp_type = type; - fl.fl_icmp_code = code; - security_skb_classify_flow(skb, &fl); + ipv6_addr_copy(&fl6.saddr, saddr); + fl6.flowi6_oif = iif; + fl6.fl6_icmp_type = type; + fl6.fl6_icmp_code = code; + security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); sk = icmpv6_xmit_lock(net); if (sk == NULL) return; np = inet6_sk(sk); - if (!icmpv6_xrlim_allow(sk, type, &fl)) + if (!icmpv6_xrlim_allow(sk, type, &fl6)) goto out; tmp_hdr.icmp6_type = type; @@ -403,61 +465,14 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) tmp_hdr.icmp6_cksum = 0; tmp_hdr.icmp6_pointer = htonl(info); - if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) - fl.oif = np->mcast_oif; + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) + dst = icmpv6_route_lookup(net, skb, sk, &fl6); + if (IS_ERR(dst)) goto out; - /* - * We won't send icmp if the destination is known - * anycast. - */ - if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) { - LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: acast source\n"); - goto out_dst_release; - } - - /* No need to clone since we're just using its address. */ - dst2 = dst; - - err = xfrm_lookup(net, &dst, &fl, sk, 0); - switch (err) { - case 0: - if (dst != dst2) - goto route_done; - break; - case -EPERM: - dst = NULL; - break; - default: - goto out; - } - - if (xfrm_decode_session_reverse(skb, &fl2, AF_INET6)) - goto relookup_failed; - - if (ip6_dst_lookup(sk, &dst2, &fl2)) - goto relookup_failed; - - err = xfrm_lookup(net, &dst2, &fl2, sk, XFRM_LOOKUP_ICMP); - switch (err) { - case 0: - dst_release(dst); - dst = dst2; - break; - case -EPERM: - goto out_dst_release; - default: -relookup_failed: - if (!dst) - goto out; - break; - } - -route_done: - if (ipv6_addr_is_multicast(&fl.fl6_dst)) + if (ipv6_addr_is_multicast(&fl6.daddr)) hlimit = np->mcast_hops; else hlimit = np->hop_limit; @@ -480,14 +495,14 @@ route_done: err = ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), hlimit, - np->tclass, NULL, &fl, (struct rt6_info*)dst, + np->tclass, NULL, &fl6, (struct rt6_info*)dst, MSG_DONTWAIT, np->dontfrag); if (err) { ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); goto out_put; } - err = icmpv6_push_pending_frames(sk, &fl, &tmp_hdr, len + sizeof(struct icmp6hdr)); + err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, len + sizeof(struct icmp6hdr)); out_put: if (likely(idev != NULL)) @@ -509,7 +524,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct in6_addr *saddr = NULL; struct icmp6hdr *icmph = icmp6_hdr(skb); struct icmp6hdr tmp_hdr; - struct flowi fl; + struct flowi6 fl6; struct icmpv6_msg msg; struct dst_entry *dst; int err = 0; @@ -523,30 +538,31 @@ static void icmpv6_echo_reply(struct sk_buff *skb) memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr)); tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY; - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_ICMPV6; - ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr); + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_ICMPV6; + ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr); if (saddr) - ipv6_addr_copy(&fl.fl6_src, saddr); - fl.oif = skb->dev->ifindex; - fl.fl_icmp_type = ICMPV6_ECHO_REPLY; - security_skb_classify_flow(skb, &fl); + ipv6_addr_copy(&fl6.saddr, saddr); + fl6.flowi6_oif = skb->dev->ifindex; + fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY; + security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); sk = icmpv6_xmit_lock(net); if (sk == NULL) return; np = inet6_sk(sk); - if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) - fl.oif = np->mcast_oif; + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; - err = ip6_dst_lookup(sk, &dst, &fl); + err = ip6_dst_lookup(sk, &dst, &fl6); if (err) goto out; - if ((err = xfrm_lookup(net, &dst, &fl, sk, 0)) < 0) + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); + if (IS_ERR(dst)) goto out; - if (ipv6_addr_is_multicast(&fl.fl6_dst)) + if (ipv6_addr_is_multicast(&fl6.daddr)) hlimit = np->mcast_hops; else hlimit = np->hop_limit; @@ -560,7 +576,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) msg.type = ICMPV6_ECHO_REPLY; err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl, + sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl6, (struct rt6_info*)dst, MSG_DONTWAIT, np->dontfrag); @@ -569,7 +585,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) ip6_flush_pending_frames(sk); goto out_put; } - err = icmpv6_push_pending_frames(sk, &fl, &tmp_hdr, skb->len + sizeof(struct icmp6hdr)); + err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, skb->len + sizeof(struct icmp6hdr)); out_put: if (likely(idev != NULL)) @@ -768,20 +784,20 @@ drop_no_count: return 0; } -void icmpv6_flow_init(struct sock *sk, struct flowi *fl, +void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6, u8 type, const struct in6_addr *saddr, const struct in6_addr *daddr, int oif) { - memset(fl, 0, sizeof(*fl)); - ipv6_addr_copy(&fl->fl6_src, saddr); - ipv6_addr_copy(&fl->fl6_dst, daddr); - fl->proto = IPPROTO_ICMPV6; - fl->fl_icmp_type = type; - fl->fl_icmp_code = 0; - fl->oif = oif; - security_sk_classify_flow(sk, fl); + memset(fl6, 0, sizeof(*fl6)); + ipv6_addr_copy(&fl6->saddr, saddr); + ipv6_addr_copy(&fl6->daddr, daddr); + fl6->flowi6_proto = IPPROTO_ICMPV6; + fl6->fl6_icmp_type = type; + fl6->fl6_icmp_code = 0; + fl6->flowi6_oif = oif; + security_sk_classify_flow(sk, flowi6_to_flowi(fl6)); } /* diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index d144e629d2b4..166054650466 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -61,26 +61,21 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *final_p, final; struct dst_entry *dst; - struct flowi fl; - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - final_p = fl6_update_dst(&fl, np->opt, &final); - ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); - fl.oif = sk->sk_bound_dev_if; - fl.mark = sk->sk_mark; - fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_rsk(req)->loc_port; - security_req_classify_flow(req, &fl); - - if (ip6_dst_lookup(sk, &dst, &fl)) - return NULL; - - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_TCP; + ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); + final_p = fl6_update_dst(&fl6, np->opt, &final); + ipv6_addr_copy(&fl6.saddr, &treq->loc_addr); + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_mark = sk->sk_mark; + fl6.fl6_dport = inet_rsk(req)->rmt_port; + fl6.fl6_sport = inet_rsk(req)->loc_port; + security_req_classify_flow(req, flowi6_to_flowi(&fl6)); + + dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + if (IS_ERR(dst)) return NULL; return dst; @@ -213,42 +208,34 @@ int inet6_csk_xmit(struct sk_buff *skb) struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct flowi fl; + struct flowi6 fl6; struct dst_entry *dst; struct in6_addr *final_p, final; - memset(&fl, 0, sizeof(fl)); - fl.proto = sk->sk_protocol; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.fl6_flowlabel = np->flow_label; - IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel); - fl.oif = sk->sk_bound_dev_if; - fl.mark = sk->sk_mark; - fl.fl_ip_sport = inet->inet_sport; - fl.fl_ip_dport = inet->inet_dport; - security_sk_classify_flow(sk, &fl); + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = sk->sk_protocol; + ipv6_addr_copy(&fl6.daddr, &np->daddr); + ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.flowlabel = np->flow_label; + IP6_ECN_flow_xmit(sk, fl6.flowlabel); + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_mark = sk->sk_mark; + fl6.fl6_sport = inet->inet_sport; + fl6.fl6_dport = inet->inet_dport; + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - final_p = fl6_update_dst(&fl, np->opt, &final); + final_p = fl6_update_dst(&fl6, np->opt, &final); dst = __inet6_csk_dst_check(sk, np->dst_cookie); if (dst == NULL) { - int err = ip6_dst_lookup(sk, &dst, &fl); - - if (err) { - sk->sk_err_soft = -err; - kfree_skb(skb); - return err; - } - - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); + dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); - if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) { + if (IS_ERR(dst)) { + sk->sk_err_soft = -PTR_ERR(dst); sk->sk_route_caps = 0; kfree_skb(skb); - return err; + return PTR_ERR(dst); } __inet6_csk_dst_store(sk, dst, NULL, NULL); @@ -257,9 +244,9 @@ int inet6_csk_xmit(struct sk_buff *skb) skb_dst_set(skb, dst_clone(dst)); /* Restore final destination back after routing done */ - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); + ipv6_addr_copy(&fl6.daddr, &np->daddr); - return ip6_xmit(sk, skb, &fl, np->opt); + return ip6_xmit(sk, skb, &fl6, np->opt); } EXPORT_SYMBOL_GPL(inet6_csk_xmit); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 633a6c266136..b53197233709 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -124,7 +124,7 @@ out: } EXPORT_SYMBOL(__inet6_lookup_established); -static int inline compute_score(struct sock *sk, struct net *net, +static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const struct in6_addr *daddr, const int dif) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index de382114609b..7548905e79e1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -260,10 +260,10 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) return net->ipv6.fib6_main_tbl; } -struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl, +struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, int flags, pol_lookup_t lookup) { - return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl, flags); + return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); } static void __net_init fib6_tables_init(struct net *net) diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 13654686aeab..f3caf1b8d572 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -342,7 +342,7 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, if (olen > 0) { struct msghdr msg; - struct flowi flowi; + struct flowi6 flowi6; int junk; err = -ENOMEM; @@ -358,9 +358,9 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, msg.msg_controllen = olen; msg.msg_control = (void*)(fl->opt+1); - flowi.oif = 0; + memset(&flowi6, 0, sizeof(flowi6)); - err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, + err = datagram_send_ctl(net, &msg, &flowi6, fl->opt, &junk, &junk, &junk); if (err) goto done; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5f8d242be3f3..18208876aa8a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -174,15 +174,15 @@ int ip6_output(struct sk_buff *skb) * xmit an sk_buff (used by TCP, SCTP and DCCP) */ -int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, +int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, struct ipv6_txoptions *opt) { struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct in6_addr *first_hop = &fl->fl6_dst; + struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr; - u8 proto = fl->proto; + u8 proto = fl6->flowi6_proto; int seg_len = skb->len; int hlimit = -1; int tclass = 0; @@ -230,13 +230,13 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel; + *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl6->flowlabel; hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; hdr->hop_limit = hlimit; - ipv6_addr_copy(&hdr->saddr, &fl->fl6_src); + ipv6_addr_copy(&hdr->saddr, &fl6->saddr); ipv6_addr_copy(&hdr->daddr, first_hop); skb->priority = sk->sk_priority; @@ -274,13 +274,10 @@ int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev, { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6hdr *hdr; - int totlen; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; - totlen = len + sizeof(struct ipv6hdr); - skb_reset_network_header(skb); skb_put(skb, sizeof(struct ipv6hdr)); hdr = ipv6_hdr(skb); @@ -479,10 +476,13 @@ int ip6_forward(struct sk_buff *skb) else target = &hdr->daddr; + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 1); + /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ - if (xrlim_allow(dst, 1*HZ)) + if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) ndisc_send_redirect(skb, n, target); } else { int addrtype = ipv6_addr_type(&hdr->saddr); @@ -879,7 +879,7 @@ static inline int ip6_rt_check(struct rt6key *rt_key, static struct dst_entry *ip6_sk_dst_check(struct sock *sk, struct dst_entry *dst, - struct flowi *fl) + struct flowi6 *fl6) { struct ipv6_pinfo *np = inet6_sk(sk); struct rt6_info *rt = (struct rt6_info *)dst; @@ -904,11 +904,11 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, * sockets. * 2. oif also should be the same. */ - if (ip6_rt_check(&rt->rt6i_dst, &fl->fl6_dst, np->daddr_cache) || + if (ip6_rt_check(&rt->rt6i_dst, &fl6->daddr, np->daddr_cache) || #ifdef CONFIG_IPV6_SUBTREES - ip6_rt_check(&rt->rt6i_src, &fl->fl6_src, np->saddr_cache) || + ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) || #endif - (fl->oif && fl->oif != dst->dev->ifindex)) { + (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) { dst_release(dst); dst = NULL; } @@ -918,22 +918,22 @@ out: } static int ip6_dst_lookup_tail(struct sock *sk, - struct dst_entry **dst, struct flowi *fl) + struct dst_entry **dst, struct flowi6 *fl6) { int err; struct net *net = sock_net(sk); if (*dst == NULL) - *dst = ip6_route_output(net, sk, fl); + *dst = ip6_route_output(net, sk, fl6); if ((err = (*dst)->error)) goto out_err_release; - if (ipv6_addr_any(&fl->fl6_src)) { + if (ipv6_addr_any(&fl6->saddr)) { err = ipv6_dev_get_saddr(net, ip6_dst_idev(*dst)->dev, - &fl->fl6_dst, + &fl6->daddr, sk ? inet6_sk(sk)->srcprefs : 0, - &fl->fl6_src); + &fl6->saddr); if (err) goto out_err_release; } @@ -949,10 +949,10 @@ static int ip6_dst_lookup_tail(struct sock *sk, */ if ((*dst)->neighbour && !((*dst)->neighbour->nud_state & NUD_VALID)) { struct inet6_ifaddr *ifp; - struct flowi fl_gw; + struct flowi6 fl_gw6; int redirect; - ifp = ipv6_get_ifaddr(net, &fl->fl6_src, + ifp = ipv6_get_ifaddr(net, &fl6->saddr, (*dst)->dev, 1); redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC); @@ -965,9 +965,9 @@ static int ip6_dst_lookup_tail(struct sock *sk, * default router instead */ dst_release(*dst); - memcpy(&fl_gw, fl, sizeof(struct flowi)); - memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr)); - *dst = ip6_route_output(net, sk, &fl_gw); + memcpy(&fl_gw6, fl6, sizeof(struct flowi6)); + memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr)); + *dst = ip6_route_output(net, sk, &fl_gw6); if ((err = (*dst)->error)) goto out_err_release; } @@ -988,43 +988,85 @@ out_err_release: * ip6_dst_lookup - perform route lookup on flow * @sk: socket which provides route info * @dst: pointer to dst_entry * for result - * @fl: flow to lookup + * @fl6: flow to lookup * * This function performs a route lookup on the given flow. * * It returns zero on success, or a standard errno code on error. */ -int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl) +int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { *dst = NULL; - return ip6_dst_lookup_tail(sk, dst, fl); + return ip6_dst_lookup_tail(sk, dst, fl6); } EXPORT_SYMBOL_GPL(ip6_dst_lookup); /** - * ip6_sk_dst_lookup - perform socket cached route lookup on flow + * ip6_dst_lookup_flow - perform route lookup on flow with ipsec + * @sk: socket which provides route info + * @fl6: flow to lookup + * @final_dst: final destination address for ipsec lookup + * @can_sleep: we are in a sleepable context + * + * This function performs a route lookup on the given flow. + * + * It returns a valid dst pointer on success, or a pointer encoded + * error code. + */ +struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, + const struct in6_addr *final_dst, + bool can_sleep) +{ + struct dst_entry *dst = NULL; + int err; + + err = ip6_dst_lookup_tail(sk, &dst, fl6); + if (err) + return ERR_PTR(err); + if (final_dst) + ipv6_addr_copy(&fl6->daddr, final_dst); + if (can_sleep) + fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP; + + return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); +} +EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); + +/** + * ip6_sk_dst_lookup_flow - perform socket cached route lookup on flow * @sk: socket which provides the dst cache and route info - * @dst: pointer to dst_entry * for result - * @fl: flow to lookup + * @fl6: flow to lookup + * @final_dst: final destination address for ipsec lookup + * @can_sleep: we are in a sleepable context * * This function performs a route lookup on the given flow with the * possibility of using the cached route in the socket if it is valid. * It will take the socket dst lock when operating on the dst cache. * As a result, this function can only be used in process context. * - * It returns zero on success, or a standard errno code on error. + * It returns a valid dst pointer on success, or a pointer encoded + * error code. */ -int ip6_sk_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl) +struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, + const struct in6_addr *final_dst, + bool can_sleep) { - *dst = NULL; - if (sk) { - *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie); - *dst = ip6_sk_dst_check(sk, *dst, fl); - } + struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie); + int err; + + dst = ip6_sk_dst_check(sk, dst, fl6); + + err = ip6_dst_lookup_tail(sk, &dst, fl6); + if (err) + return ERR_PTR(err); + if (final_dst) + ipv6_addr_copy(&fl6->daddr, final_dst); + if (can_sleep) + fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP; - return ip6_dst_lookup_tail(sk, dst, fl); + return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } -EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup); +EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); static inline int ip6_ufo_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, @@ -1061,7 +1103,6 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - sk->sk_sndmsg_off = 0; } err = skb_append_datato_frags(sk,skb, getfrag, from, @@ -1104,7 +1145,7 @@ static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src, int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl, + int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags, int dontfrag) { struct inet_sock *inet = inet_sk(sk); @@ -1118,6 +1159,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int err; int offset = 0; int csummode = CHECKSUM_NONE; + __u8 tx_flags = 0; if (flags&MSG_PROBE) return 0; @@ -1161,7 +1203,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, } dst_hold(&rt->dst); inet->cork.dst = &rt->dst; - inet->cork.fl = *fl; + inet->cork.fl.u.ip6 = *fl6; np->cork.hop_limit = hlimit; np->cork.tclass = tclass; mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? @@ -1182,7 +1224,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, transhdrlen += exthdrlen; } else { rt = (struct rt6_info *)inet->cork.dst; - fl = &inet->cork.fl; + fl6 = &inet->cork.fl.u.ip6; opt = np->cork.opt; transhdrlen = 0; exthdrlen = 0; @@ -1197,11 +1239,18 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) { if (inet->cork.length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) { - ipv6_local_error(sk, EMSGSIZE, fl, mtu-exthdrlen); + ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen); return -EMSGSIZE; } } + /* For UDP, check if TX timestamp is enabled */ + if (sk->sk_type == SOCK_DGRAM) { + err = sock_tx_timestamp(sk, &tx_flags); + if (err) + goto error; + } + /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. @@ -1222,7 +1271,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, if (length > mtu) { int proto = sk->sk_protocol; if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){ - ipv6_local_rxpmtu(sk, fl, mtu-exthdrlen); + ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); return -EMSGSIZE; } @@ -1306,6 +1355,12 @@ alloc_new_skb: sk->sk_allocation); if (unlikely(skb == NULL)) err = -ENOBUFS; + else { + /* Only the initial fragment + * is time stamped. + */ + tx_flags = 0; + } } if (skb == NULL) goto error; @@ -1317,6 +1372,9 @@ alloc_new_skb: /* reserve for fragmentation */ skb_reserve(skb, hh_len+sizeof(struct frag_hdr)); + if (sk->sk_type == SOCK_DGRAM) + skb_shinfo(skb)->tx_flags = tx_flags; + /* * Find where to start putting bytes */ @@ -1458,8 +1516,8 @@ int ip6_push_pending_frames(struct sock *sk) struct ipv6hdr *hdr; struct ipv6_txoptions *opt = np->cork.opt; struct rt6_info *rt = (struct rt6_info *)inet->cork.dst; - struct flowi *fl = &inet->cork.fl; - unsigned char proto = fl->proto; + struct flowi6 *fl6 = &inet->cork.fl.u.ip6; + unsigned char proto = fl6->flowi6_proto; int err = 0; if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL) @@ -1484,7 +1542,7 @@ int ip6_push_pending_frames(struct sock *sk) if (np->pmtudisc < IPV6_PMTUDISC_DO) skb->local_df = 1; - ipv6_addr_copy(final_dst, &fl->fl6_dst); + ipv6_addr_copy(final_dst, &fl6->daddr); __skb_pull(skb, skb_network_header_len(skb)); if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); @@ -1495,12 +1553,12 @@ int ip6_push_pending_frames(struct sock *sk) skb_reset_network_header(skb); hdr = ipv6_hdr(skb); - *(__be32*)hdr = fl->fl6_flowlabel | + *(__be32*)hdr = fl6->flowlabel | htonl(0x60000000 | ((int)np->cork.tclass << 20)); hdr->hop_limit = np->cork.hop_limit; hdr->nexthdr = proto; - ipv6_addr_copy(&hdr->saddr, &fl->fl6_src); + ipv6_addr_copy(&hdr->saddr, &fl6->saddr); ipv6_addr_copy(&hdr->daddr, final_dst); skb->priority = sk->sk_priority; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 4f4483e697bd..c1b1bd312df2 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -57,6 +57,7 @@ MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_NETDEV("ip6tnl0"); #ifdef IP6_TNL_DEBUG #define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __func__) @@ -535,7 +536,6 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int err; struct sk_buff *skb2; struct iphdr *eiph; - struct flowi fl; struct rtable *rt; err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code, @@ -577,11 +577,11 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, eiph = ip_hdr(skb2); /* Try to guess incoming interface */ - memset(&fl, 0, sizeof(fl)); - fl.fl4_dst = eiph->saddr; - fl.fl4_tos = RT_TOS(eiph->tos); - fl.proto = IPPROTO_IPIP; - if (ip_route_output_key(dev_net(skb->dev), &rt, &fl)) + rt = ip_route_output_ports(dev_net(skb->dev), NULL, + eiph->saddr, 0, + 0, 0, + IPPROTO_IPIP, RT_TOS(eiph->tos), 0); + if (IS_ERR(rt)) goto out; skb2->dev = rt->dst.dev; @@ -590,15 +590,18 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); rt = NULL; - fl.fl4_dst = eiph->daddr; - fl.fl4_src = eiph->saddr; - fl.fl4_tos = eiph->tos; - if (ip_route_output_key(dev_net(skb->dev), &rt, &fl) || + rt = ip_route_output_ports(dev_net(skb->dev), NULL, + eiph->daddr, eiph->saddr, + 0, 0, + IPPROTO_IPIP, + RT_TOS(eiph->tos), 0); + if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) { - ip_rt_put(rt); + if (!IS_ERR(rt)) + ip_rt_put(rt); goto out; } - skb_dst_set(skb2, (struct dst_entry *)rt); + skb_dst_set(skb2, &rt->dst); } else { ip_rt_put(rt); if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, @@ -881,7 +884,7 @@ static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t) static int ip6_tnl_xmit2(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, - struct flowi *fl, + struct flowi6 *fl6, int encap_limit, __u32 *pmtu) { @@ -901,10 +904,16 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, if ((dst = ip6_tnl_dst_check(t)) != NULL) dst_hold(dst); else { - dst = ip6_route_output(net, NULL, fl); + dst = ip6_route_output(net, NULL, fl6); - if (dst->error || xfrm_lookup(net, &dst, fl, NULL, 0) < 0) + if (dst->error) goto tx_err_link_failure; + dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; + goto tx_err_link_failure; + } } tdev = dst->dev; @@ -954,7 +963,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, skb->transport_header = skb->network_header; - proto = fl->proto; + proto = fl6->flowi6_proto; if (encap_limit >= 0) { init_tel_txopt(&opt, encap_limit); ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL); @@ -962,13 +971,13 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); - *(__be32*)ipv6h = fl->fl6_flowlabel | htonl(0x60000000); + *(__be32*)ipv6h = fl6->flowlabel | htonl(0x60000000); dsfield = INET_ECN_encapsulate(0, dsfield); ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; - ipv6_addr_copy(&ipv6h->saddr, &fl->fl6_src); - ipv6_addr_copy(&ipv6h->daddr, &fl->fl6_dst); + ipv6_addr_copy(&ipv6h->saddr, &fl6->saddr); + ipv6_addr_copy(&ipv6h->daddr, &fl6->daddr); nf_reset(skb); pkt_len = skb->len; err = ip6_local_out(skb); @@ -998,7 +1007,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); struct iphdr *iph = ip_hdr(skb); int encap_limit = -1; - struct flowi fl; + struct flowi6 fl6; __u8 dsfield; __u32 mtu; int err; @@ -1010,16 +1019,16 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; - memcpy(&fl, &t->fl, sizeof (fl)); - fl.proto = IPPROTO_IPIP; + memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6)); + fl6.flowi6_proto = IPPROTO_IPIP; dsfield = ipv4_get_dsfield(iph); if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)) - fl.fl6_flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT) + fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT) & IPV6_TCLASS_MASK; - err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu); + err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); if (err != 0) { /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) @@ -1038,7 +1047,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) struct ipv6hdr *ipv6h = ipv6_hdr(skb); int encap_limit = -1; __u16 offset; - struct flowi fl; + struct flowi6 fl6; __u8 dsfield; __u32 mtu; int err; @@ -1060,16 +1069,16 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; - memcpy(&fl, &t->fl, sizeof (fl)); - fl.proto = IPPROTO_IPV6; + memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6)); + fl6.flowi6_proto = IPPROTO_IPV6; dsfield = ipv6_get_dsfield(ipv6h); if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)) - fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK); + fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK); if ((t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)) - fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK); + fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK); - err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu); + err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); if (err != 0) { if (err == -EMSGSIZE) icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); @@ -1132,21 +1141,21 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) { struct net_device *dev = t->dev; struct ip6_tnl_parm *p = &t->parms; - struct flowi *fl = &t->fl; + struct flowi6 *fl6 = &t->fl.u.ip6; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ - ipv6_addr_copy(&fl->fl6_src, &p->laddr); - ipv6_addr_copy(&fl->fl6_dst, &p->raddr); - fl->oif = p->link; - fl->fl6_flowlabel = 0; + ipv6_addr_copy(&fl6->saddr, &p->laddr); + ipv6_addr_copy(&fl6->daddr, &p->raddr); + fl6->flowi6_oif = p->link; + fl6->flowlabel = 0; if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS)) - fl->fl6_flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; + fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) - fl->fl6_flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; + fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; ip6_tnl_set_cap(t); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 0e1d53bcf1e0..7ff0343e05c7 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -135,14 +135,15 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) return NULL; } -static int ip6mr_fib_lookup(struct net *net, struct flowi *flp, +static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, struct mr6_table **mrt) { struct ip6mr_result res; struct fib_lookup_arg arg = { .result = &res, }; int err; - err = fib_rules_lookup(net->ipv6.mr6_rules_ops, flp, 0, &arg); + err = fib_rules_lookup(net->ipv6.mr6_rules_ops, + flowi6_to_flowi(flp6), 0, &arg); if (err < 0) return err; *mrt = res.mrt; @@ -270,7 +271,7 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) return net->ipv6.mrt6; } -static int ip6mr_fib_lookup(struct net *net, struct flowi *flp, +static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, struct mr6_table **mrt) { *mrt = net->ipv6.mrt6; @@ -617,9 +618,9 @@ static int pim6_rcv(struct sk_buff *skb) struct net_device *reg_dev = NULL; struct net *net = dev_net(skb->dev); struct mr6_table *mrt; - struct flowi fl = { - .iif = skb->dev->ifindex, - .mark = skb->mark, + struct flowi6 fl6 = { + .flowi6_iif = skb->dev->ifindex, + .flowi6_mark = skb->mark, }; int reg_vif_num; @@ -644,7 +645,7 @@ static int pim6_rcv(struct sk_buff *skb) ntohs(encap->payload_len) + sizeof(*pim) > skb->len) goto drop; - if (ip6mr_fib_lookup(net, &fl, &mrt) < 0) + if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) goto drop; reg_vif_num = mrt->mroute_reg_vif_num; @@ -687,14 +688,14 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, { struct net *net = dev_net(dev); struct mr6_table *mrt; - struct flowi fl = { - .oif = dev->ifindex, - .iif = skb->skb_iif, - .mark = skb->mark, + struct flowi6 fl6 = { + .flowi6_oif = dev->ifindex, + .flowi6_iif = skb->skb_iif, + .flowi6_mark = skb->mark, }; int err; - err = ip6mr_fib_lookup(net, &fl, &mrt); + err = ip6mr_fib_lookup(net, &fl6, &mrt); if (err < 0) return err; @@ -1039,7 +1040,6 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, while((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { if (ipv6_hdr(skb)->version == 0) { - int err; struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); if (__ip6mr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) { @@ -1050,7 +1050,7 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -EMSGSIZE; } - err = rtnl_unicast(skb, net, NETLINK_CB(skb).pid); + rtnl_unicast(skb, net, NETLINK_CB(skb).pid); } else ip6_mr_forward(net, mrt, skb, c); } @@ -1548,13 +1548,13 @@ int ip6mr_sk_done(struct sock *sk) struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) { struct mr6_table *mrt; - struct flowi fl = { - .iif = skb->skb_iif, - .oif = skb->dev->ifindex, - .mark = skb->mark, + struct flowi6 fl6 = { + .flowi6_iif = skb->skb_iif, + .flowi6_oif = skb->dev->ifindex, + .flowi6_mark = skb->mark, }; - if (ip6mr_fib_lookup(net, &fl, &mrt) < 0) + if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) return NULL; return mrt->mroute6_sk; @@ -1898,7 +1898,7 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, struct mif_device *vif = &mrt->vif6_table[vifi]; struct net_device *dev; struct dst_entry *dst; - struct flowi fl; + struct flowi6 fl6; if (vif->dev == NULL) goto out_free; @@ -1916,12 +1916,12 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, ipv6h = ipv6_hdr(skb); - fl = (struct flowi) { - .oif = vif->link, - .fl6_dst = ipv6h->daddr, + fl6 = (struct flowi6) { + .flowi6_oif = vif->link, + .daddr = ipv6h->daddr, }; - dst = ip6_route_output(net, NULL, &fl); + dst = ip6_route_output(net, NULL, &fl6); if (!dst) goto out_free; @@ -2044,13 +2044,13 @@ int ip6_mr_input(struct sk_buff *skb) struct mfc6_cache *cache; struct net *net = dev_net(skb->dev); struct mr6_table *mrt; - struct flowi fl = { - .iif = skb->dev->ifindex, - .mark = skb->mark, + struct flowi6 fl6 = { + .flowi6_iif = skb->dev->ifindex, + .flowi6_mark = skb->mark, }; int err; - err = ip6mr_fib_lookup(net, &fl, &mrt); + err = ip6mr_fib_lookup(net, &fl6, &mrt); if (err < 0) return err; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index d1770e061c08..9cb191ecaba8 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -444,12 +444,12 @@ sticky_done: { struct ipv6_txoptions *opt = NULL; struct msghdr msg; - struct flowi fl; + struct flowi6 fl6; int junk; - fl.fl6_flowlabel = 0; - fl.oif = sk->sk_bound_dev_if; - fl.mark = sk->sk_mark; + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_mark = sk->sk_mark; if (optlen == 0) goto update; @@ -475,7 +475,7 @@ sticky_done: msg.msg_controllen = optlen; msg.msg_control = (void*)(opt+1); - retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk, + retv = datagram_send_ctl(net, &msg, &fl6, opt, &junk, &junk, &junk); if (retv) goto done; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 49f986d626a0..76b893771e6e 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -319,7 +319,6 @@ int ip6_mc_source(int add, int omode, struct sock *sk, { struct in6_addr *source, *group; struct ipv6_mc_socklist *pmc; - struct net_device *dev; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *psl; @@ -341,7 +340,6 @@ int ip6_mc_source(int add, int omode, struct sock *sk, rcu_read_unlock(); return -ENODEV; } - dev = idev->dev; err = -EADDRNOTAVAIL; @@ -455,7 +453,6 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) { struct in6_addr *group; struct ipv6_mc_socklist *pmc; - struct net_device *dev; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *newpsl, *psl; @@ -478,7 +475,6 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) rcu_read_unlock(); return -ENODEV; } - dev = idev->dev; err = 0; @@ -549,7 +545,6 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; - struct net_device *dev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *psl; struct net *net = sock_net(sk); @@ -566,7 +561,6 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, rcu_read_unlock(); return -ENODEV; } - dev = idev->dev; err = -EADDRNOTAVAIL; /* @@ -1402,7 +1396,7 @@ static void mld_sendpack(struct sk_buff *skb) struct inet6_dev *idev; struct net *net = dev_net(skb->dev); int err; - struct flowi fl; + struct flowi6 fl6; struct dst_entry *dst; rcu_read_lock(); @@ -1425,11 +1419,16 @@ static void mld_sendpack(struct sk_buff *skb) goto err_out; } - icmpv6_flow_init(net->ipv6.igmp_sk, &fl, ICMPV6_MLD2_REPORT, + icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - err = xfrm_lookup(net, &dst, &fl, NULL, 0); + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); + err = 0; + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; + } skb_dst_set(skb, dst); if (err) goto err_out; @@ -1732,7 +1731,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; - struct flowi fl; + struct flowi6 fl6; struct dst_entry *dst; if (type == ICMPV6_MGM_REDUCTION) @@ -1792,13 +1791,15 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) goto err_out; } - icmpv6_flow_init(sk, &fl, type, + icmpv6_flow_init(sk, &fl6, type, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - err = xfrm_lookup(net, &dst, &fl, NULL, 0); - if (err) + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); goto err_out; + } skb_dst_set(skb, dst); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index d6e9599d0705..9b210482fb05 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -203,18 +203,20 @@ static inline int mip6_report_rl_allow(struct timeval *stamp, return allow; } -static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct flowi *fl) +static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, + const struct flowi *fl) { struct net *net = xs_net(x); struct inet6_skb_parm *opt = (struct inet6_skb_parm *)skb->cb; + const struct flowi6 *fl6 = &fl->u.ip6; struct ipv6_destopt_hao *hao = NULL; struct xfrm_selector sel; int offset; struct timeval stamp; int err = 0; - if (unlikely(fl->proto == IPPROTO_MH && - fl->fl_mh_type <= IP6_MH_TYPE_MAX)) + if (unlikely(fl6->flowi6_proto == IPPROTO_MH && + fl6->fl6_mh_type <= IP6_MH_TYPE_MAX)) goto out; if (likely(opt->dsthao)) { @@ -239,14 +241,14 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct sizeof(sel.saddr)); sel.prefixlen_s = 128; sel.family = AF_INET6; - sel.proto = fl->proto; - sel.dport = xfrm_flowi_dport(fl); + sel.proto = fl6->flowi6_proto; + sel.dport = xfrm_flowi_dport(fl, &fl6->uli); if (sel.dport) sel.dport_mask = htons(~0); - sel.sport = xfrm_flowi_sport(fl); + sel.sport = xfrm_flowi_sport(fl, &fl6->uli); if (sel.sport) sel.sport_mask = htons(~0); - sel.ifindex = fl->oif; + sel.ifindex = fl6->flowi6_oif; err = km_report(net, IPPROTO_DSTOPTS, &sel, (hao ? (xfrm_address_t *)&hao->addr : NULL)); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 2342545a5ee9..0e49c9db3c98 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -511,7 +511,7 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *saddr, struct icmp6hdr *icmp6h) { - struct flowi fl; + struct flowi6 fl6; struct dst_entry *dst; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; @@ -521,7 +521,7 @@ void ndisc_send_skb(struct sk_buff *skb, type = icmp6h->icmp6_type; - icmpv6_flow_init(sk, &fl, type, saddr, daddr, dev->ifindex); + icmpv6_flow_init(sk, &fl6, type, saddr, daddr, dev->ifindex); dst = icmp6_dst_alloc(dev, neigh, daddr); if (!dst) { @@ -529,8 +529,8 @@ void ndisc_send_skb(struct sk_buff *skb, return; } - err = xfrm_lookup(net, &dst, &fl, NULL, 0); - if (err < 0) { + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); + if (IS_ERR(dst)) { kfree_skb(skb); return; } @@ -1515,7 +1515,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, struct rt6_info *rt; struct dst_entry *dst; struct inet6_dev *idev; - struct flowi fl; + struct flowi6 fl6; u8 *opt; int rd_len; int err; @@ -1535,15 +1535,15 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, return; } - icmpv6_flow_init(sk, &fl, NDISC_REDIRECT, + icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT, &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); - dst = ip6_route_output(net, NULL, &fl); + dst = ip6_route_output(net, NULL, &fl6); if (dst == NULL) return; - err = xfrm_lookup(net, &dst, &fl, NULL, 0); - if (err) + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); + if (IS_ERR(dst)) return; rt = (struct rt6_info *) dst; @@ -1553,7 +1553,9 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, "ICMPv6 Redirect: destination is not a neighbour.\n"); goto release; } - if (!xrlim_allow(dst, 1*HZ)) + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 1); + if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) goto release; if (dev->addr_len) { diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 35915e8617f0..39aaca2b4fd2 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -15,14 +15,14 @@ int ip6_route_me_harder(struct sk_buff *skb) struct net *net = dev_net(skb_dst(skb)->dev); struct ipv6hdr *iph = ipv6_hdr(skb); struct dst_entry *dst; - struct flowi fl = { - .oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, - .mark = skb->mark, - .fl6_dst = iph->daddr, - .fl6_src = iph->saddr, + struct flowi6 fl6 = { + .flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, + .flowi6_mark = skb->mark, + .daddr = iph->daddr, + .saddr = iph->saddr, }; - dst = ip6_route_output(net, skb->sk, &fl); + dst = ip6_route_output(net, skb->sk, &fl6); if (dst->error) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n"); @@ -37,9 +37,10 @@ int ip6_route_me_harder(struct sk_buff *skb) #ifdef CONFIG_XFRM if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && - xfrm_decode_session(skb, &fl, AF_INET6) == 0) { + xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) { skb_dst_set(skb, NULL); - if (xfrm_lookup(net, &dst, &fl, skb->sk, 0)) + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0); + if (IS_ERR(dst)) return -1; skb_dst_set(skb, dst); } @@ -91,7 +92,7 @@ static int nf_ip6_reroute(struct sk_buff *skb, static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl) { - *dst = ip6_route_output(&init_net, NULL, fl); + *dst = ip6_route_output(&init_net, NULL, &fl->u.ip6); return (*dst)->error; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 7d227c644f72..c9598a9067d7 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1076,6 +1076,7 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries[raw_smp_processor_id()]; + xt_compat_init_offsets(AF_INET6, info->number); xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) @@ -1274,6 +1275,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len) /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) @@ -1679,6 +1681,7 @@ translate_compat_table(struct net *net, duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(AF_INET6); + xt_compat_init_offsets(AF_INET6, number); /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, total_size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, @@ -1820,6 +1823,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) @@ -2049,6 +2053,7 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) ret = -EFAULT; break; } + rev.name[sizeof(rev.name)-1] = 0; if (cmd == IP6T_SO_GET_REVISION_TARGET) target = 1; diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 09c88891a753..e6af8d72f26b 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -410,7 +410,7 @@ fallback: if (p != NULL) { sb_add(m, "%02x", *p++); for (i = 1; i < len; i++) - sb_add(m, ":%02x", p[i]); + sb_add(m, ":%02x", *p++); } sb_add(m, " "); @@ -452,8 +452,7 @@ ip6t_log_packet(u_int8_t pf, in ? in->name : "", out ? out->name : ""); - /* MAC logging for input path only. */ - if (in && !out) + if (in != NULL) dump_mac_header(m, loginfo, skb); dump_packet(m, loginfo, skb, skb_network_offset(skb), 1); diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index bf998feac14e..28e74488a329 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -47,7 +47,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) struct ipv6hdr *ip6h; struct dst_entry *dst = NULL; u8 proto; - struct flowi fl; + struct flowi6 fl6; if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) || (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) { @@ -89,19 +89,20 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) return; } - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_src, &oip6h->daddr); - ipv6_addr_copy(&fl.fl6_dst, &oip6h->saddr); - fl.fl_ip_sport = otcph.dest; - fl.fl_ip_dport = otcph.source; - security_skb_classify_flow(oldskb, &fl); - dst = ip6_route_output(net, NULL, &fl); + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_TCP; + ipv6_addr_copy(&fl6.saddr, &oip6h->daddr); + ipv6_addr_copy(&fl6.daddr, &oip6h->saddr); + fl6.fl6_sport = otcph.dest; + fl6.fl6_dport = otcph.source; + security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); + dst = ip6_route_output(net, NULL, &fl6); if (dst == NULL || dst->error) { dst_release(dst); return; } - if (xfrm_lookup(net, &dst, &fl, NULL, 0)) + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); + if (IS_ERR(dst)) return; hh_len = (dst->dev->hard_header_len + 15)&~15; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 79d43aa8fa8d..085727263812 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -45,6 +45,7 @@ #include <linux/netfilter_ipv6.h> #include <linux/kernel.h> #include <linux/module.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> struct nf_ct_frag6_skb_cb @@ -73,7 +74,7 @@ static struct inet_frags nf_frags; static struct netns_frags nf_init_frags; #ifdef CONFIG_SYSCTL -struct ctl_table nf_ct_frag6_sysctl_table[] = { +static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", .data = &nf_init_frags.timeout, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index c5b0915d106b..4a1c3b46c56b 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -124,18 +124,18 @@ static __inline__ int icmpv6_filter(struct sock *sk, struct sk_buff *skb) } #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) -static int (*mh_filter)(struct sock *sock, struct sk_buff *skb); +typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); -int rawv6_mh_filter_register(int (*filter)(struct sock *sock, - struct sk_buff *skb)) +static mh_filter_t __rcu *mh_filter __read_mostly; + +int rawv6_mh_filter_register(mh_filter_t filter) { rcu_assign_pointer(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); -int rawv6_mh_filter_unregister(int (*filter)(struct sock *sock, - struct sk_buff *skb)) +int rawv6_mh_filter_unregister(mh_filter_t filter) { rcu_assign_pointer(mh_filter, NULL); synchronize_rcu(); @@ -193,10 +193,10 @@ static int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) * policy is placed in rawv6_rcv() because it is * required for each socket. */ - int (*filter)(struct sock *sock, struct sk_buff *skb); + mh_filter_t *filter; filter = rcu_dereference(mh_filter); - filtered = filter ? filter(sk, skb) : 0; + filtered = filter ? (*filter)(sk, skb) : 0; break; } #endif @@ -524,7 +524,7 @@ csum_copy_err: goto out; } -static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, +static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { struct sk_buff *skb; @@ -586,11 +586,10 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, if (unlikely(csum)) tmp_csum = csum_sub(tmp_csum, csum_unfold(csum)); - csum = csum_ipv6_magic(&fl->fl6_src, - &fl->fl6_dst, - total_len, fl->proto, tmp_csum); + csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, + total_len, fl6->flowi6_proto, tmp_csum); - if (csum == 0 && fl->proto == IPPROTO_UDP) + if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP) csum = CSUM_MANGLED_0; if (skb_store_bits(skb, offset, &csum, 2)) @@ -603,7 +602,7 @@ out: } static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, - struct flowi *fl, struct dst_entry **dstp, + struct flowi6 *fl6, struct dst_entry **dstp, unsigned int flags) { struct ipv6_pinfo *np = inet6_sk(sk); @@ -613,7 +612,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, struct rt6_info *rt = (struct rt6_info *)*dstp; if (length > rt->dst.dev->mtu) { - ipv6_local_error(sk, EMSGSIZE, fl, rt->dst.dev->mtu); + ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); return -EMSGSIZE; } if (flags&MSG_PROBE) @@ -662,7 +661,7 @@ error: return err; } -static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) +static int rawv6_probe_proto_opt(struct flowi6 *fl6, struct msghdr *msg) { struct iovec *iov; u8 __user *type = NULL; @@ -679,7 +678,7 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) if (!iov) continue; - switch (fl->proto) { + switch (fl6->flowi6_proto) { case IPPROTO_ICMPV6: /* check if one-byte field is readable or not. */ if (iov->iov_base && iov->iov_len < 1) @@ -694,8 +693,8 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) code = iov->iov_base; if (type && code) { - if (get_user(fl->fl_icmp_type, type) || - get_user(fl->fl_icmp_code, code)) + if (get_user(fl6->fl6_icmp_type, type) || + get_user(fl6->fl6_icmp_code, code)) return -EFAULT; probed = 1; } @@ -706,7 +705,7 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) /* check if type field is readable or not. */ if (iov->iov_len > 2 - len) { u8 __user *p = iov->iov_base; - if (get_user(fl->fl_mh_type, &p[2 - len])) + if (get_user(fl6->fl6_mh_type, &p[2 - len])) return -EFAULT; probed = 1; } else @@ -735,7 +734,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; - struct flowi fl; + struct flowi6 fl6; int addr_len = msg->msg_namelen; int hlimit = -1; int tclass = -1; @@ -756,9 +755,9 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, /* * Get and verify the address. */ - memset(&fl, 0, sizeof(fl)); + memset(&fl6, 0, sizeof(fl6)); - fl.mark = sk->sk_mark; + fl6.flowi6_mark = sk->sk_mark; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) @@ -780,9 +779,9 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, 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); + fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; daddr = &flowlabel->dst; @@ -800,32 +799,32 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL) - fl.oif = sin6->sin6_scope_id; + fl6.flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; proto = inet->inet_num; daddr = &np->daddr; - fl.fl6_flowlabel = np->flow_label; + fl6.flowlabel = np->flow_label; } - if (fl.oif == 0) - fl.oif = sk->sk_bound_dev_if; + if (fl6.flowi6_oif == 0) + fl6.flowi6_oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, + err = datagram_send_ctl(sock_net(sk), msg, &fl6, opt, &hlimit, &tclass, &dontfrag); 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 ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; } @@ -838,40 +837,31 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); - fl.proto = proto; - err = rawv6_probe_proto_opt(&fl, msg); + fl6.flowi6_proto = proto; + err = rawv6_probe_proto_opt(&fl6, msg); if (err) goto out; if (!ipv6_addr_any(daddr)) - ipv6_addr_copy(&fl.fl6_dst, daddr); + ipv6_addr_copy(&fl6.daddr, daddr); else - fl.fl6_dst.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ - if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&fl.fl6_src, &np->saddr); + fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) + ipv6_addr_copy(&fl6.saddr, &np->saddr); - final_p = fl6_update_dst(&fl, opt, &final); + final_p = fl6_update_dst(&fl6, opt, &final); - if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) - fl.oif = np->mcast_oif; - security_sk_classify_flow(sk, &fl); + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) + dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); goto out; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); - if (err < 0) { - if (err == -EREMOTE) - err = ip6_dst_blackhole(sk, &dst, &fl); - if (err < 0) - goto out; } - if (hlimit < 0) { - if (ipv6_addr_is_multicast(&fl.fl6_dst)) + if (ipv6_addr_is_multicast(&fl6.daddr)) hlimit = np->mcast_hops; else hlimit = np->hop_limit; @@ -890,17 +880,17 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, back_from_confirm: if (inet->hdrincl) - err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl, &dst, msg->msg_flags); + err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl6, &dst, msg->msg_flags); else { lock_sock(sk); err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, - len, 0, hlimit, tclass, opt, &fl, (struct rt6_info*)dst, + len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info*)dst, msg->msg_flags, dontfrag); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) - err = rawv6_push_pending_frames(sk, &fl, rp); + err = rawv6_push_pending_frames(sk, &fl6, rp); release_sock(sk); } done: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1c29f95695de..6814c8722fa7 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -97,6 +97,36 @@ static struct rt6_info *rt6_get_route_info(struct net *net, struct in6_addr *gwaddr, int ifindex); #endif +static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) +{ + struct rt6_info *rt = (struct rt6_info *) dst; + struct inet_peer *peer; + u32 *p = NULL; + + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 1); + + peer = rt->rt6i_peer; + if (peer) { + u32 *old_p = __DST_METRICS_PTR(old); + unsigned long prev, new; + + p = peer->metrics; + if (inet_metrics_new(peer)) + memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + p = __DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; + } + } + return p; +} + static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .protocol = cpu_to_be16(ETH_P_IPV6), @@ -105,6 +135,7 @@ static struct dst_ops ip6_dst_ops_template = { .check = ip6_dst_check, .default_advmss = ip6_default_advmss, .default_mtu = ip6_default_mtu, + .cow_metrics = ipv6_cow_metrics, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, @@ -128,9 +159,14 @@ static struct dst_ops ip6_dst_blackhole_ops = { .destroy = ip6_dst_destroy, .check = ip6_dst_check, .default_mtu = ip6_blackhole_default_mtu, + .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, }; +static const u32 ip6_template_metrics[RTAX_MAX] = { + [RTAX_HOPLIMIT - 1] = 255, +}; + static struct rt6_info ip6_null_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), @@ -186,7 +222,7 @@ static struct rt6_info ip6_blk_hole_entry_template = { /* allocate dst with ip6_dst_ops */ static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops) { - return (struct rt6_info *)dst_alloc(ops); + return (struct rt6_info *)dst_alloc(ops, 0); } static void ip6_dst_destroy(struct dst_entry *dst) @@ -205,6 +241,13 @@ static void ip6_dst_destroy(struct dst_entry *dst) } } +static atomic_t __rt6_peer_genid = ATOMIC_INIT(0); + +static u32 rt6_peer_genid(void) +{ + return atomic_read(&__rt6_peer_genid); +} + void rt6_bind_peer(struct rt6_info *rt, int create) { struct inet_peer *peer; @@ -212,6 +255,8 @@ void rt6_bind_peer(struct rt6_info *rt, int create) peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create); if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL) inet_putpeer(peer); + else + rt->rt6i_peer_genid = rt6_peer_genid(); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -554,17 +599,17 @@ do { \ static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, - struct flowi *fl, int flags) + struct flowi6 *fl6, int flags) { struct fib6_node *fn; struct rt6_info *rt; read_lock_bh(&table->tb6_lock); - fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); + fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: rt = fn->leaf; - rt = rt6_device_match(net, rt, &fl->fl6_src, fl->oif, flags); - BACKTRACK(net, &fl->fl6_src); + rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags); + BACKTRACK(net, &fl6->saddr); out: dst_use(&rt->dst, jiffies); read_unlock_bh(&table->tb6_lock); @@ -575,19 +620,19 @@ out: struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, int strict) { - struct flowi fl = { - .oif = oif, - .fl6_dst = *daddr, + struct flowi6 fl6 = { + .flowi6_oif = oif, + .daddr = *daddr, }; struct dst_entry *dst; int flags = strict ? RT6_LOOKUP_F_IFACE : 0; if (saddr) { - memcpy(&fl.fl6_src, saddr, sizeof(*saddr)); + memcpy(&fl6.saddr, saddr, sizeof(*saddr)); flags |= RT6_LOOKUP_F_HAS_SADDR; } - dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_lookup); + dst = fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_lookup); if (dst->error == 0) return (struct rt6_info *) dst; @@ -708,7 +753,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *d } static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, - struct flowi *fl, int flags) + struct flowi6 *fl6, int flags) { struct fib6_node *fn; struct rt6_info *rt, *nrt; @@ -723,12 +768,12 @@ relookup: read_lock_bh(&table->tb6_lock); restart_2: - fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); + fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: rt = rt6_select(fn, oif, strict | reachable); - BACKTRACK(net, &fl->fl6_src); + BACKTRACK(net, &fl6->saddr); if (rt == net->ipv6.ip6_null_entry || rt->rt6i_flags & RTF_CACHE) goto out; @@ -737,9 +782,11 @@ restart: read_unlock_bh(&table->tb6_lock); if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) - nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src); + nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); + else if (!(rt->dst.flags & DST_HOST)) + nrt = rt6_alloc_clone(rt, &fl6->daddr); else - nrt = rt6_alloc_clone(rt, &fl->fl6_dst); + goto out2; dst_release(&rt->dst); rt = nrt ? : net->ipv6.ip6_null_entry; @@ -776,9 +823,9 @@ out2: } static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, - struct flowi *fl, int flags) + struct flowi6 *fl6, int flags) { - return ip6_pol_route(net, table, fl->iif, fl, flags); + return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags); } void ip6_route_input(struct sk_buff *skb) @@ -786,56 +833,54 @@ void ip6_route_input(struct sk_buff *skb) struct ipv6hdr *iph = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); int flags = RT6_LOOKUP_F_HAS_SADDR; - struct flowi fl = { - .iif = skb->dev->ifindex, - .fl6_dst = iph->daddr, - .fl6_src = iph->saddr, - .fl6_flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK, - .mark = skb->mark, - .proto = iph->nexthdr, + struct flowi6 fl6 = { + .flowi6_iif = skb->dev->ifindex, + .daddr = iph->daddr, + .saddr = iph->saddr, + .flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK, + .flowi6_mark = skb->mark, + .flowi6_proto = iph->nexthdr, }; if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; - skb_dst_set(skb, fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input)); + skb_dst_set(skb, fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_input)); } static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, - struct flowi *fl, int flags) + struct flowi6 *fl6, int flags) { - return ip6_pol_route(net, table, fl->oif, fl, flags); + return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags); } struct dst_entry * ip6_route_output(struct net *net, struct sock *sk, - struct flowi *fl) + struct flowi6 *fl6) { int flags = 0; - if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl->fl6_dst)) + if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr)) flags |= RT6_LOOKUP_F_IFACE; - if (!ipv6_addr_any(&fl->fl6_src)) + if (!ipv6_addr_any(&fl6->saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; else if (sk) flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs); - return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output); + return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output); } EXPORT_SYMBOL(ip6_route_output); -int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl) +struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { - struct rt6_info *ort = (struct rt6_info *) *dstp; - struct rt6_info *rt = (struct rt6_info *) - dst_alloc(&ip6_dst_blackhole_ops); + struct rt6_info *rt = dst_alloc(&ip6_dst_blackhole_ops, 1); + struct rt6_info *ort = (struct rt6_info *) dst_orig; struct dst_entry *new = NULL; if (rt) { new = &rt->dst; - atomic_set(&new->__refcnt, 1); new->__use = 1; new->input = dst_discard; new->output = dst_discard; @@ -861,11 +906,9 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl dst_free(new); } - dst_release(*dstp); - *dstp = new; - return new ? 0 : -ENOMEM; + dst_release(dst_orig); + return new ? new : ERR_PTR(-ENOMEM); } -EXPORT_SYMBOL_GPL(ip6_dst_blackhole); /* * Destination cache support functions @@ -877,9 +920,14 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = (struct rt6_info *) dst; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) + if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { + if (rt->rt6i_peer_genid != rt6_peer_genid()) { + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 0); + rt->rt6i_peer_genid = rt6_peer_genid(); + } return dst; - + } return NULL; } @@ -930,7 +978,6 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) dst_metric_set(dst, RTAX_FEATURES, features); } dst_metric_set(dst, RTAX_MTU, mtu); - call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst); } } @@ -1027,11 +1074,9 @@ out: int icmp6_dst_gc(void) { - struct dst_entry *dst, *next, **pprev; + struct dst_entry *dst, **pprev; int more = 0; - next = NULL; - spin_lock_bh(&icmp6_dst_lock); pprev = &icmp6_dst_gc_list; @@ -1399,16 +1444,16 @@ static int ip6_route_del(struct fib6_config *cfg) * Handle redirects */ struct ip6rd_flowi { - struct flowi fl; + struct flowi6 fl6; struct in6_addr gateway; }; static struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, - struct flowi *fl, + struct flowi6 *fl6, int flags) { - struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl; + struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; struct rt6_info *rt; struct fib6_node *fn; @@ -1424,7 +1469,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, */ read_lock_bh(&table->tb6_lock); - fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); + fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { /* @@ -1439,7 +1484,7 @@ restart: continue; if (!(rt->rt6i_flags & RTF_GATEWAY)) continue; - if (fl->oif != rt->rt6i_dev->ifindex) + if (fl6->flowi6_oif != rt->rt6i_dev->ifindex) continue; if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) continue; @@ -1448,7 +1493,7 @@ restart: if (!rt) rt = net->ipv6.ip6_null_entry; - BACKTRACK(net, &fl->fl6_src); + BACKTRACK(net, &fl6->saddr); out: dst_hold(&rt->dst); @@ -1465,10 +1510,10 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, int flags = RT6_LOOKUP_F_HAS_SADDR; struct net *net = dev_net(dev); struct ip6rd_flowi rdfl = { - .fl = { - .oif = dev->ifindex, - .fl6_dst = *dest, - .fl6_src = *src, + .fl6 = { + .flowi6_oif = dev->ifindex, + .daddr = *dest, + .saddr = *src, }, }; @@ -1477,7 +1522,7 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, if (rt6_need_strict(dest)) flags |= RT6_LOOKUP_F_IFACE; - return (struct rt6_info *)fib6_rule_lookup(net, (struct flowi *)&rdfl, + return (struct rt6_info *)fib6_rule_lookup(net, &rdfl.fl6, flags, __ip6_route_redirect); } @@ -1979,12 +2024,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, if (IS_ERR(neigh)) { dst_free(&rt->dst); - /* We are casting this because that is the return - * value type. But an errno encoded pointer is the - * same regardless of the underlying pointer type, - * and that's what we are returning. So this is OK. - */ - return (struct rt6_info *) neigh; + return ERR_CAST(neigh); } rt->rt6i_nexthop = neigh; @@ -2345,7 +2385,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void struct rt6_info *rt; struct sk_buff *skb; struct rtmsg *rtm; - struct flowi fl; + struct flowi6 fl6; int err, iif = 0; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy); @@ -2353,27 +2393,27 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void goto errout; err = -EINVAL; - memset(&fl, 0, sizeof(fl)); + memset(&fl6, 0, sizeof(fl6)); if (tb[RTA_SRC]) { if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) goto errout; - ipv6_addr_copy(&fl.fl6_src, nla_data(tb[RTA_SRC])); + ipv6_addr_copy(&fl6.saddr, nla_data(tb[RTA_SRC])); } if (tb[RTA_DST]) { if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr)) goto errout; - ipv6_addr_copy(&fl.fl6_dst, nla_data(tb[RTA_DST])); + ipv6_addr_copy(&fl6.daddr, nla_data(tb[RTA_DST])); } if (tb[RTA_IIF]) iif = nla_get_u32(tb[RTA_IIF]); if (tb[RTA_OIF]) - fl.oif = nla_get_u32(tb[RTA_OIF]); + fl6.flowi6_oif = nla_get_u32(tb[RTA_OIF]); if (iif) { struct net_device *dev; @@ -2396,10 +2436,10 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void skb_reset_mac_header(skb); skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr)); - rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl); + rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl6); skb_dst_set(skb, &rt->dst); - err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif, + err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, 0, 0, 0); if (err < 0) { @@ -2556,14 +2596,16 @@ static int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; - int delay = net->ipv6.sysctl.flush_delay; - if (write) { - proc_dointvec(ctl, write, buffer, lenp, ppos); - fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); - return 0; - } else + struct net *net; + int delay; + if (!write) return -EINVAL; + + net = (struct net *)ctl->extra1; + delay = net->ipv6.sysctl.flush_delay; + proc_dointvec(ctl, write, buffer, lenp, ppos); + fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); + return 0; } ctl_table ipv6_route_table_template[] = { @@ -2650,6 +2692,7 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) if (table) { table[0].data = &net->ipv6.sysctl.flush_delay; + table[0].extra1 = net; table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; table[2].data = &net->ipv6.sysctl.ip6_rt_max_size; table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; @@ -2683,7 +2726,8 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_null_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; - dst_metric_set(&net->ipv6.ip6_null_entry->dst, RTAX_HOPLIMIT, 255); + dst_init_metrics(&net->ipv6.ip6_null_entry->dst, + ip6_template_metrics, true); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, @@ -2694,7 +2738,8 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_prohibit_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_prohibit_entry; net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; - dst_metric_set(&net->ipv6.ip6_prohibit_entry->dst, RTAX_HOPLIMIT, 255); + dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst, + ip6_template_metrics, true); net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), @@ -2704,7 +2749,8 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_blk_hole_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_blk_hole_entry; net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; - dst_metric_set(&net->ipv6.ip6_blk_hole_entry->dst, RTAX_HOPLIMIT, 255); + dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst, + ip6_template_metrics, true); #endif net->ipv6.sysctl.flush_delay = 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 8ce38f10a547..43b33373adb2 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -412,7 +412,7 @@ static void prl_list_destroy_rcu(struct rcu_head *head) p = container_of(head, struct ip_tunnel_prl_entry, rcu_head); do { - n = p->next; + n = rcu_dereference_protected(p->next, 1); kfree(p); p = n; } while (p); @@ -421,15 +421,17 @@ static void prl_list_destroy_rcu(struct rcu_head *head) static int ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) { - struct ip_tunnel_prl_entry *x, **p; + struct ip_tunnel_prl_entry *x; + struct ip_tunnel_prl_entry __rcu **p; int err = 0; ASSERT_RTNL(); if (a && a->addr != htonl(INADDR_ANY)) { - for (p = &t->prl; *p; p = &(*p)->next) { - if ((*p)->addr == a->addr) { - x = *p; + for (p = &t->prl; + (x = rtnl_dereference(*p)) != NULL; + p = &x->next) { + if (x->addr == a->addr) { *p = x->next; call_rcu(&x->rcu_head, prl_entry_destroy_rcu); t->prl_count--; @@ -438,9 +440,9 @@ ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) } err = -ENXIO; } else { - if (t->prl) { + x = rtnl_dereference(t->prl); + if (x) { t->prl_count = 0; - x = t->prl; call_rcu(&x->rcu_head, prl_list_destroy_rcu); t->prl = NULL; } @@ -730,16 +732,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, dst = addr6->s6_addr32[3]; } - { - struct flowi fl = { .fl4_dst = dst, - .fl4_src = tiph->saddr, - .fl4_tos = RT_TOS(tos), - .oif = tunnel->parms.link, - .proto = IPPROTO_IPV6 }; - if (ip_route_output_key(dev_net(dev), &rt, &fl)) { - dev->stats.tx_carrier_errors++; - goto tx_error_icmp; - } + rt = ip_route_output_ports(dev_net(dev), NULL, + dst, tiph->saddr, + 0, 0, + IPPROTO_IPV6, RT_TOS(tos), + tunnel->parms.link); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; } if (rt->rt_type != RTN_UNICAST) { ip_rt_put(rt); @@ -855,13 +855,14 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) iph = &tunnel->parms.iph; if (iph->daddr) { - struct flowi fl = { .fl4_dst = iph->daddr, - .fl4_src = iph->saddr, - .fl4_tos = RT_TOS(iph->tos), - .oif = tunnel->parms.link, - .proto = IPPROTO_IPV6 }; - struct rtable *rt; - if (!ip_route_output_key(dev_net(dev), &rt, &fl)) { + struct rtable *rt = ip_route_output_ports(dev_net(dev), NULL, + iph->daddr, iph->saddr, + 0, 0, + IPPROTO_IPV6, + RT_TOS(iph->tos), + tunnel->parms.link); + + if (!IS_ERR(rt)) { tdev = rt->dst.dev; ip_rt_put(rt); } @@ -1179,7 +1180,7 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; dev_hold(dev); - sitn->tunnels_wc[0] = tunnel; + rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); return 0; } @@ -1196,11 +1197,12 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea for (prio = 1; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t = sitn->tunnels[prio][h]; + struct ip_tunnel *t; + t = rtnl_dereference(sitn->tunnels[prio][h]); while (t != NULL) { unregister_netdevice_queue(t->dev, head); - t = t->next; + t = rtnl_dereference(t->next); } } } @@ -1290,4 +1292,4 @@ static int __init sit_init(void) module_init(sit_init); module_exit(sit_cleanup); MODULE_LICENSE("GPL"); -MODULE_ALIAS("sit0"); +MODULE_ALIAS_NETDEV("sit0"); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 09fd34f0dbf2..352c26081f5d 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -232,23 +232,20 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) */ { struct in6_addr *final_p, final; - struct flowi fl; - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); - final_p = fl6_update_dst(&fl, np->opt, &final); - ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr); - fl.oif = sk->sk_bound_dev_if; - fl.mark = sk->sk_mark; - fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_sk(sk)->inet_sport; - security_req_classify_flow(req, &fl); - if (ip6_dst_lookup(sk, &dst, &fl)) - goto out_free; - - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) + struct flowi6 fl6; + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_TCP; + ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr); + final_p = fl6_update_dst(&fl6, np->opt, &final); + ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr); + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_mark = sk->sk_mark; + fl6.fl6_dport = inet_rsk(req)->rmt_port; + fl6.fl6_sport = inet_sk(sk)->inet_sport; + security_req_classify_flow(req, flowi6_to_flowi(&fl6)); + + dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + if (IS_ERR(dst)) goto out_free; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 20aa95e37359..2b0c186862c8 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -131,7 +131,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct tcp_sock *tp = tcp_sk(sk); struct in6_addr *saddr = NULL, *final_p, final; struct rt6_info *rt; - struct flowi fl; + struct flowi6 fl6; struct dst_entry *dst; int addr_type; int err; @@ -142,14 +142,14 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; - memset(&fl, 0, sizeof(fl)); + memset(&fl6, 0, sizeof(fl6)); if (np->sndflow) { - fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; - IP6_ECN_flow_init(fl.fl6_flowlabel); - if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) { + fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; + IP6_ECN_flow_init(fl6.flowlabel); + if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; - flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); @@ -195,7 +195,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } ipv6_addr_copy(&np->daddr, &usin->sin6_addr); - np->flow_label = fl.fl6_flowlabel; + np->flow_label = fl6.flowlabel; /* * TCP over IPv4 @@ -242,35 +242,27 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (!ipv6_addr_any(&np->rcv_saddr)) saddr = &np->rcv_saddr; - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, + fl6.flowi6_proto = IPPROTO_TCP; + ipv6_addr_copy(&fl6.daddr, &np->daddr); + ipv6_addr_copy(&fl6.saddr, (saddr ? saddr : &np->saddr)); - fl.oif = sk->sk_bound_dev_if; - fl.mark = sk->sk_mark; - fl.fl_ip_dport = usin->sin6_port; - fl.fl_ip_sport = inet->inet_sport; + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_mark = sk->sk_mark; + fl6.fl6_dport = usin->sin6_port; + fl6.fl6_sport = inet->inet_sport; - final_p = fl6_update_dst(&fl, np->opt, &final); + final_p = fl6_update_dst(&fl6, np->opt, &final); - security_sk_classify_flow(sk, &fl); + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) + dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); goto failure; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); - if (err < 0) { - if (err == -EREMOTE) - err = ip6_dst_blackhole(sk, &dst, &fl); - if (err < 0) - goto failure; } if (saddr == NULL) { - saddr = &fl.fl6_src; + saddr = &fl6.saddr; ipv6_addr_copy(&np->rcv_saddr, saddr); } @@ -385,7 +377,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); if (type == ICMPV6_PKT_TOOBIG) { - struct dst_entry *dst = NULL; + struct dst_entry *dst; if (sock_owned_by_user(sk)) goto out; @@ -397,29 +389,25 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (dst == NULL) { struct inet_sock *inet = inet_sk(sk); - struct flowi fl; + struct flowi6 fl6; /* BUGGG_FUTURE: Again, it is not clear how to handle rthdr case. Ignore this complexity for now. */ - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.oif = sk->sk_bound_dev_if; - fl.mark = sk->sk_mark; - fl.fl_ip_dport = inet->inet_dport; - fl.fl_ip_sport = inet->inet_sport; - security_skb_classify_flow(skb, &fl); - - if ((err = ip6_dst_lookup(sk, &dst, &fl))) { - sk->sk_err_soft = -err; - goto out; - } - - if ((err = xfrm_lookup(net, &dst, &fl, sk, 0)) < 0) { - sk->sk_err_soft = -err; + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_TCP; + ipv6_addr_copy(&fl6.daddr, &np->daddr); + ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_mark = sk->sk_mark; + fl6.fl6_dport = inet->inet_dport; + fl6.fl6_sport = inet->inet_sport; + security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); + + dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false); + if (IS_ERR(dst)) { + sk->sk_err_soft = -PTR_ERR(dst); goto out; } @@ -494,38 +482,36 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, struct sk_buff * skb; struct ipv6_txoptions *opt = NULL; struct in6_addr * final_p, final; - struct flowi fl; + struct flowi6 fl6; struct dst_entry *dst; - int err = -1; - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); - fl.fl6_flowlabel = 0; - fl.oif = treq->iif; - fl.mark = sk->sk_mark; - fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_rsk(req)->loc_port; - security_req_classify_flow(req, &fl); + int err; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_TCP; + ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); + ipv6_addr_copy(&fl6.saddr, &treq->loc_addr); + fl6.flowlabel = 0; + fl6.flowi6_oif = treq->iif; + fl6.flowi6_mark = sk->sk_mark; + fl6.fl6_dport = inet_rsk(req)->rmt_port; + fl6.fl6_sport = inet_rsk(req)->loc_port; + security_req_classify_flow(req, flowi6_to_flowi(&fl6)); opt = np->opt; - final_p = fl6_update_dst(&fl, opt, &final); + final_p = fl6_update_dst(&fl6, opt, &final); - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) - goto done; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) + dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); goto done; - + } skb = tcp_make_synack(sk, dst, req, rvp); + err = -ENOMEM; if (skb) { __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); - ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - err = ip6_xmit(sk, skb, &fl, opt); + ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); + err = ip6_xmit(sk, skb, &fl6, opt); err = net_xmit_eval(err); } @@ -1006,7 +992,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, { struct tcphdr *th = tcp_hdr(skb), *t1; struct sk_buff *buff; - struct flowi fl; + struct flowi6 fl6; struct net *net = dev_net(skb_dst(skb)->dev); struct sock *ctl_sk = net->ipv6.tcp_sk; unsigned int tot_len = sizeof(struct tcphdr); @@ -1060,34 +1046,33 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, } #endif - memset(&fl, 0, sizeof(fl)); - ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&fl.fl6_src, &ipv6_hdr(skb)->daddr); + memset(&fl6, 0, sizeof(fl6)); + ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr); + ipv6_addr_copy(&fl6.saddr, &ipv6_hdr(skb)->daddr); buff->ip_summed = CHECKSUM_PARTIAL; buff->csum = 0; - __tcp_v6_send_check(buff, &fl.fl6_src, &fl.fl6_dst); + __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr); - fl.proto = IPPROTO_TCP; - fl.oif = inet6_iif(skb); - fl.fl_ip_dport = t1->dest; - fl.fl_ip_sport = t1->source; - security_skb_classify_flow(skb, &fl); + fl6.flowi6_proto = IPPROTO_TCP; + fl6.flowi6_oif = inet6_iif(skb); + fl6.fl6_dport = t1->dest; + fl6.fl6_sport = t1->source; + security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); /* Pass a socket to ip6_dst_lookup either it is for RST * Underlying function will use this to retrieve the network * namespace */ - if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) { - if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) { - skb_dst_set(buff, dst); - ip6_xmit(ctl_sk, buff, &fl, NULL); - TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); - if (rst) - TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); - return; - } + dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false); + if (!IS_ERR(dst)) { + skb_dst_set(buff, dst); + ip6_xmit(ctl_sk, buff, &fl6, NULL); + TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); + if (rst) + TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); + return; } kfree_skb(buff); @@ -1323,7 +1308,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_death_row.sysctl_tw_recycle && (dst = inet6_csk_route_req(sk, req)) != NULL && (peer = rt6_get_peer((struct rt6_info *)dst)) != NULL && - ipv6_addr_equal((struct in6_addr *)peer->daddr.a6, + ipv6_addr_equal((struct in6_addr *)peer->daddr.addr.a6, &treq->rmt_addr)) { inet_peer_refcheck(peer); if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && @@ -1636,10 +1621,8 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) opt_skb = skb_clone(skb, GFP_ATOMIC); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - TCP_CHECK_TIMER(sk); if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) goto reset; - TCP_CHECK_TIMER(sk); if (opt_skb) goto ipv6_pktoptions; return 0; @@ -1667,10 +1650,8 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) } } - TCP_CHECK_TIMER(sk); if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) goto reset; - TCP_CHECK_TIMER(sk); if (opt_skb) goto ipv6_pktoptions; return 0; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9a009c66c8a3..d7037c006e13 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -886,7 +886,7 @@ static int udp_v6_push_pending_frames(struct sock *sk) struct udphdr *uh; struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); - struct flowi *fl = &inet->cork.fl; + struct flowi6 *fl6 = &inet->cork.fl.u.ip6; int err = 0; int is_udplite = IS_UDPLITE(sk); __wsum csum = 0; @@ -899,23 +899,23 @@ static int udp_v6_push_pending_frames(struct sock *sk) * Create a UDP header */ uh = udp_hdr(skb); - uh->source = fl->fl_ip_sport; - uh->dest = fl->fl_ip_dport; + uh->source = fl6->fl6_sport; + uh->dest = fl6->fl6_dport; uh->len = htons(up->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, &fl->fl6_src, &fl->fl6_dst, + udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, up->len); goto send; } else csum = udp_csum_outgoing(sk, skb); /* add protocol-dependent pseudo-header */ - uh->check = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst, - up->len, fl->proto, csum ); + uh->check = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, + up->len, fl6->flowi6_proto, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; @@ -947,7 +947,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct in6_addr *daddr, *final_p, final; struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; - struct flowi fl; + struct flowi6 fl6; struct dst_entry *dst; int addr_len = msg->msg_namelen; int ulen = len; @@ -1030,19 +1030,19 @@ do_udp_sendmsg: } ulen += sizeof(struct udphdr); - memset(&fl, 0, sizeof(fl)); + memset(&fl6, 0, sizeof(fl6)); if (sin6) { if (sin6->sin6_port == 0) return -EINVAL; - fl.fl_ip_dport = sin6->sin6_port; + fl6.fl6_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); + fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; daddr = &flowlabel->dst; @@ -1060,38 +1060,38 @@ 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; + fl6.flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - fl.fl_ip_dport = inet->inet_dport; + fl6.fl6_dport = inet->inet_dport; daddr = &np->daddr; - fl.fl6_flowlabel = np->flow_label; + fl6.flowlabel = np->flow_label; connected = 1; } - if (!fl.oif) - fl.oif = sk->sk_bound_dev_if; + if (!fl6.flowi6_oif) + fl6.flowi6_oif = sk->sk_bound_dev_if; - if (!fl.oif) - fl.oif = np->sticky_pktinfo.ipi6_ifindex; + if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; - fl.mark = sk->sk_mark; + fl6.flowi6_mark = sk->sk_mark; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, + err = datagram_send_ctl(sock_net(sk), msg, &fl6, opt, &hlimit, &tclass, &dontfrag); 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 ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; } @@ -1105,42 +1105,35 @@ do_udp_sendmsg: opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); - fl.proto = sk->sk_protocol; + fl6.flowi6_proto = sk->sk_protocol; if (!ipv6_addr_any(daddr)) - ipv6_addr_copy(&fl.fl6_dst, daddr); + ipv6_addr_copy(&fl6.daddr, daddr); else - fl.fl6_dst.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ - 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->inet_sport; + fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) + ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.fl6_sport = inet->inet_sport; - final_p = fl6_update_dst(&fl, opt, &final); + final_p = fl6_update_dst(&fl6, opt, &final); if (final_p) connected = 0; - if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) { - fl.oif = np->mcast_oif; + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) { + fl6.flowi6_oif = np->mcast_oif; connected = 0; } - security_sk_classify_flow(sk, &fl); + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - err = ip6_sk_dst_lookup(sk, &dst, &fl); - if (err) + dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, true); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; goto out; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); - if (err < 0) { - if (err == -EREMOTE) - err = ip6_dst_blackhole(sk, &dst, &fl); - if (err < 0) - goto out; } if (hlimit < 0) { - if (ipv6_addr_is_multicast(&fl.fl6_dst)) + if (ipv6_addr_is_multicast(&fl6.daddr)) hlimit = np->mcast_hops; else hlimit = np->hop_limit; @@ -1175,7 +1168,7 @@ do_append_data: up->len += ulen; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, - sizeof(struct udphdr), hlimit, tclass, opt, &fl, + sizeof(struct udphdr), hlimit, tclass, opt, &fl6, (struct rt6_info*)dst, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag); if (err) @@ -1188,10 +1181,10 @@ do_append_data: if (dst) { if (connected) { ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ? + ipv6_addr_equal(&fl6.daddr, &np->daddr) ? &np->daddr : NULL, #ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_equal(&fl.fl6_src, &np->saddr) ? + ipv6_addr_equal(&fl6.saddr, &np->saddr) ? &np->saddr : #endif NULL); @@ -1299,7 +1292,7 @@ static int udp6_ufo_send_check(struct sk_buff *skb) return 0; } -static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, int features) +static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index da87428681cc..05e34c8ec913 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -27,18 +27,19 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo; static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, - xfrm_address_t *saddr, - xfrm_address_t *daddr) + const xfrm_address_t *saddr, + const xfrm_address_t *daddr) { - struct flowi fl = {}; + struct flowi6 fl6; struct dst_entry *dst; int err; - memcpy(&fl.fl6_dst, daddr, sizeof(fl.fl6_dst)); + memset(&fl6, 0, sizeof(fl6)); + memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr)); if (saddr) - memcpy(&fl.fl6_src, saddr, sizeof(fl.fl6_src)); + memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr)); - dst = ip6_route_output(net, NULL, &fl); + dst = ip6_route_output(net, NULL, &fl6); err = dst->error; if (dst->error) { @@ -67,7 +68,7 @@ static int xfrm6_get_saddr(struct net *net, return 0; } -static int xfrm6_get_tos(struct flowi *fl) +static int xfrm6_get_tos(const struct flowi *fl) { return 0; } @@ -87,7 +88,7 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst, } static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, - struct flowi *fl) + const struct flowi *fl) { struct rt6_info *rt = (struct rt6_info*)xdst->route; @@ -120,6 +121,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, static inline void _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) { + struct flowi6 *fl6 = &fl->u.ip6; int onlyproto = 0; u16 offset = skb_network_header_len(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -127,11 +129,11 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) const unsigned char *nh = skb_network_header(skb); u8 nexthdr = nh[IP6CB(skb)->nhoff]; - memset(fl, 0, sizeof(struct flowi)); - fl->mark = skb->mark; + memset(fl6, 0, sizeof(struct flowi6)); + fl6->flowi6_mark = skb->mark; - ipv6_addr_copy(&fl->fl6_dst, reverse ? &hdr->saddr : &hdr->daddr); - ipv6_addr_copy(&fl->fl6_src, reverse ? &hdr->daddr : &hdr->saddr); + ipv6_addr_copy(&fl6->daddr, reverse ? &hdr->saddr : &hdr->daddr); + ipv6_addr_copy(&fl6->saddr, reverse ? &hdr->daddr : &hdr->saddr); while (nh + offset + 1 < skb->data || pskb_may_pull(skb, nh + offset + 1 - skb->data)) { @@ -158,20 +160,20 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, nh + offset + 4 - skb->data))) { __be16 *ports = (__be16 *)exthdr; - fl->fl_ip_sport = ports[!!reverse]; - fl->fl_ip_dport = ports[!reverse]; + fl6->fl6_sport = ports[!!reverse]; + fl6->fl6_dport = ports[!reverse]; } - fl->proto = nexthdr; + fl6->flowi6_proto = nexthdr; return; case IPPROTO_ICMPV6: if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) { u8 *icmp = (u8 *)exthdr; - fl->fl_icmp_type = icmp[0]; - fl->fl_icmp_code = icmp[1]; + fl6->fl6_icmp_type = icmp[0]; + fl6->fl6_icmp_code = icmp[1]; } - fl->proto = nexthdr; + fl6->flowi6_proto = nexthdr; return; #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) @@ -180,9 +182,9 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) struct ip6_mh *mh; mh = (struct ip6_mh *)exthdr; - fl->fl_mh_type = mh->ip6mh_type; + fl6->fl6_mh_type = mh->ip6mh_type; } - fl->proto = nexthdr; + fl6->flowi6_proto = nexthdr; return; #endif @@ -191,8 +193,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) case IPPROTO_ESP: case IPPROTO_COMP: default: - fl->fl_ipsec_spi = 0; - fl->proto = nexthdr; + fl6->fl6_ipsec_spi = 0; + fl6->flowi6_proto = nexthdr; return; } } @@ -220,6 +222,7 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); + dst_destroy_metrics_generic(dst); if (likely(xdst->u.rt6.rt6i_peer)) inet_putpeer(xdst->u.rt6.rt6i_peer); xfrm_dst_destroy(xdst); @@ -257,6 +260,7 @@ static struct dst_ops xfrm6_dst_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, + .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, @@ -272,6 +276,7 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .get_tos = xfrm6_get_tos, .init_path = xfrm6_init_path, .fill_dst = xfrm6_fill_dst, + .blackhole_route = ip6_blackhole_route, }; static int __init xfrm6_policy_init(void) diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index a67575d472a3..afe941e9415c 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -20,26 +20,28 @@ #include <net/addrconf.h> static void -__xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) +__xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { + const struct flowi6 *fl6 = &fl->u.ip6; + /* Initialize temporary selector matching only * to current session. */ - ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst); - ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src); - sel->dport = xfrm_flowi_dport(fl); + ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl6->daddr); + ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl6->saddr); + sel->dport = xfrm_flowi_dport(fl, &fl6->uli); sel->dport_mask = htons(0xffff); - sel->sport = xfrm_flowi_sport(fl); + sel->sport = xfrm_flowi_sport(fl, &fl6->uli); sel->sport_mask = htons(0xffff); sel->family = AF_INET6; sel->prefixlen_d = 128; sel->prefixlen_s = 128; - sel->proto = fl->proto; - sel->ifindex = fl->oif; + sel->proto = fl6->flowi6_proto; + sel->ifindex = fl6->flowi6_oif; } static void -xfrm6_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +xfrm6_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl, + const xfrm_address_t *daddr, const xfrm_address_t *saddr) { x->id = tmpl->id; if (ipv6_addr_any((struct in6_addr*)&x->id.daddr)) |