static int packet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sockaddr_ll *saddr=(struct sockaddr_ll *)msg->msg_name; struct sk_buff *skb; struct net_device *dev; unsigned short proto; unsigned char *addr; int ifindex, err, reserve = 0; /* * Get and verify the address. */ if (saddr == NULL) { struct packet_opt *po = pkt_sk(sk); ifindex = po->ifindex; proto = po->num; addr = NULL; } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; ifindex = saddr->sll_ifindex; proto = saddr->sll_protocol; addr = saddr->sll_addr; } dev = dev_get_by_index(ifindex); err = -ENXIO; if (dev == NULL) goto out_unlock; if (sock->type == SOCK_RAW) reserve = dev->hard_header_len; err = -EMSGSIZE; if (len > dev->mtu+reserve) goto out_unlock; skb = sock_alloc_send_skb(sk, len + LL_RESERVED_SPACE(dev), msg->msg_flags & MSG_DONTWAIT, &err); if (skb==NULL) goto out_unlock; skb_reserve(skb, LL_RESERVED_SPACE(dev)); skb->nh.raw = skb->data; if (dev->hard_header) { int res; err = -EINVAL; res = dev->hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (sock->type != SOCK_DGRAM) { skb->tail = skb->data; skb->len = 0; } else if (res < 0) goto out_free; } /* Returns -EFAULT on error */ err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len); if (err) goto out_free; skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; err = -ENETDOWN; if (!(dev->flags & IFF_UP)) goto out_free; /* * Now send it */ /*add by p44980 2008.07.30 将dhcp交互报文的优先级设置为中*/ { if (skb->protocol == __constant_htons(ETH_P_IP)) { struct iphdr *iph = skb->nh.iph; if (iph->protocol == __constant_htons(IPPROTO_UDP)) { struct udphdr *udph = (void *)iph + iph->ihl*4; if (udph->dest == 67 || udph->dest == 68) { u_int16_t diffs[2]; //优先级设置为中 skb->nfmark = (skb->nfmark & 0xFFFFFF00) | 0x00000022; diffs[0] = htons(iph->tos) ^ 0xFFFF; //dscp标记为100010 (AF41) iph->tos = 0x88; //重新计算校验和 diffs[1] = htons(iph->tos); iph->check = csum_fold(csum_partial((char *)diffs, sizeof(diffs), iph->check^0xFFFF)); } } } } /*end by p44980 2008.07.30 将dhcp交互报文的优先级设置为中*/ err = dev_queue_xmit(skb); if (err > 0 && (err = net_xmit_errno(err)) != 0) goto out_unlock; dev_put(dev); return(len); out_free: kfree_skb(skb); out_unlock: if (dev) dev_put(dev); out: return err; }
int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { struct rt6_info *rt; /* Route to the other host */ struct in6_addr saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ __u8 next_protocol = 0; __u32 payload_len = 0; __u8 dsfield = 0; __u8 ttl = 0; struct ipv6hdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int ret, local; EnterFunction(10); rcu_read_lock(); local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6, &saddr, ipvsh, 1, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_TUNNEL); if (local < 0) goto tx_error; if (local) { rcu_read_unlock(); return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1); } rt = (struct rt6_info *) skb_dst(skb); tdev = rt->dst.dev; /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr); skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom, &next_protocol, &payload_len, &dsfield, &ttl, NULL); if (IS_ERR(skb)) goto tx_error; skb = iptunnel_handle_offloads( skb, false, __tun_gso_type_mask(AF_INET6, cp->af)); if (IS_ERR(skb)) goto tx_error; skb->transport_header = skb->network_header; skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* * Push down and install the IPIP header. */ iph = ipv6_hdr(skb); iph->version = 6; iph->nexthdr = next_protocol; iph->payload_len = htons(payload_len); memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl)); ipv6_change_dsfield(iph, 0, dsfield); iph->daddr = cp->daddr.in6; iph->saddr = saddr; iph->hop_limit = ttl; /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; ret = ip_vs_tunnel_xmit_prepare(skb, cp); if (ret == NF_ACCEPT) ip6_local_out(skb); else if (ret == NF_DROP) kfree_skb(skb); rcu_read_unlock(); LeaveFunction(10); return NF_STOLEN; tx_error: if (!IS_ERR(skb)) kfree_skb(skb); rcu_read_unlock(); LeaveFunction(10); return NF_STOLEN; }
static void send_hsr_supervision_frame(struct hsr_port *master, u8 type, u8 hsrVer) { struct sk_buff *skb; int hlen, tlen; struct hsr_tag *hsr_tag; struct hsr_sup_tag *hsr_stag; struct hsr_sup_payload *hsr_sp; unsigned long irqflags; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; skb = dev_alloc_skb( sizeof(struct hsr_tag) + sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload) + hlen + tlen); if (skb == NULL) return; skb_reserve(skb, hlen); skb->dev = master->dev; skb->protocol = htons(hsrVer ? ETH_P_HSR : ETH_P_PRP); skb->priority = TC_PRIO_CONTROL; if (dev_hard_header(skb, skb->dev, (hsrVer ? ETH_P_HSR : ETH_P_PRP), master->hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); if (hsrVer > 0) { hsr_tag = (typeof(hsr_tag)) skb_put(skb, sizeof(struct hsr_tag)); hsr_tag->encap_proto = htons(ETH_P_PRP); set_hsr_tag_LSDU_size(hsr_tag, HSR_V1_SUP_LSDUSIZE); } hsr_stag = (typeof(hsr_stag)) skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsrVer ? 0x0 : 0xf)); set_hsr_stag_HSR_Ver(hsr_stag, hsrVer); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_irqsave(&master->hsr->seqnr_lock, irqflags); if (hsrVer > 0) { hsr_stag->sequence_nr = htons(master->hsr->sup_sequence_nr); hsr_tag->sequence_nr = htons(master->hsr->sequence_nr); master->hsr->sup_sequence_nr++; master->hsr->sequence_nr++; } else { hsr_stag->sequence_nr = htons(master->hsr->sequence_nr); master->hsr->sequence_nr++; } spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); hsr_stag->HSR_TLV_Type = type; /* TODO: Why 12 in HSRv0? */ hsr_stag->HSR_TLV_Length = hsrVer ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA */ hsr_sp = (typeof(hsr_sp)) skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->MacAddressA, master->dev->dev_addr); skb_put_padto(skb, ETH_ZLEN + HSR_HLEN); hsr_forward_skb(skb, master); return; out: WARN_ONCE(1, "HSR: Could not send supervision frame\n"); kfree_skb(skb); }
static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct net_device_stats *stats = &tunnel->stat; struct iphdr *tiph = &tunnel->parms.iph; struct ipv6hdr *iph6 = skb->nh.ipv6h; u8 tos = tunnel->parms.iph.tos; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ struct iphdr *iph; /* Our new IP header */ int max_headroom; /* The extra header space needed */ u32 dst = tiph->daddr; int mtu; struct in6_addr *addr6; int addr_type; if (tunnel->recursion++) { tunnel->stat.collisions++; goto tx_error; } if (skb->protocol != htons(ETH_P_IPV6)) goto tx_error; if (!dst) dst = try_6to4(&iph6->daddr); if (!dst) { struct neighbour *neigh = NULL; if (skb->dst) neigh = skb->dst->neighbour; if (neigh == NULL) { if (net_ratelimit()) printk(KERN_DEBUG "sit: nexthop == NULL\n"); goto tx_error; } addr6 = (struct in6_addr*)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { addr6 = &skb->nh.ipv6h->daddr; addr_type = ipv6_addr_type(addr6); } if ((addr_type & IPV6_ADDR_COMPATv4) == 0) goto tx_error_icmp; dst = addr6->s6_addr32[3]; } { struct flowi fl = { .nl_u = { .ip4_u = { .daddr = dst, .saddr = tiph->saddr, .tos = RT_TOS(tos) } }, .oif = tunnel->parms.link, .proto = IPPROTO_IPV6 }; if (ip_route_output_key(&rt, &fl)) { tunnel->stat.tx_carrier_errors++; goto tx_error_icmp; } } if (rt->rt_type != RTN_UNICAST) { ip_rt_put(rt); tunnel->stat.tx_carrier_errors++; goto tx_error_icmp; } tdev = rt->u.dst.dev; if (tdev == dev) { ip_rt_put(rt); tunnel->stat.collisions++; goto tx_error; } if (tiph->frag_off) mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); else mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu; if (mtu < 68) { tunnel->stat.collisions++; ip_rt_put(rt); goto tx_error; } if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (tunnel->parms.iph.daddr && skb->dst) skb->dst->ops->update_pmtu(skb->dst, mtu); if (skb->len > mtu) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev); ip_rt_put(rt); goto tx_error; } if (tunnel->err_count > 0) { if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) { tunnel->err_count--; dst_link_failure(skb); } else tunnel->err_count = 0; } /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr); if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); stats->tx_dropped++; dev_kfree_skb(skb); tunnel->recursion--; return 0; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); dev_kfree_skb(skb); skb = new_skb; iph6 = skb->nh.ipv6h; } skb->h.raw = skb->nh.raw; skb->nh.raw = skb_push(skb, sizeof(struct iphdr)); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags = 0; dst_release(skb->dst); skb->dst = &rt->u.dst; /* * Push down and install the IPIP header. */ iph = skb->nh.iph; iph->version = 4; iph->ihl = sizeof(struct iphdr)>>2; if (mtu > IPV6_MIN_MTU) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; iph->protocol = IPPROTO_IPV6; iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); iph->daddr = rt->rt_dst; iph->saddr = rt->rt_src; if ((iph->ttl = tiph->ttl) == 0) iph->ttl = iph6->hop_limit; nf_reset(skb); IPTUNNEL_XMIT(); tunnel->recursion--; return 0; tx_error_icmp: dst_link_failure(skb); tx_error: stats->tx_errors++; dev_kfree_skb(skb); tunnel->recursion--; return 0; }
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct ipv6_txoptions *opt) { struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl->fl6_dst; struct dst_entry *dst = skb->dst; struct ipv6hdr *hdr; u8 proto = fl->proto; int seg_len = skb->len; int hlimit, tclass; u32 mtu; if (opt) { unsigned int head_room; /* First: exthdrs may take lots of space (~8K for now) MAX_HEADER is not enough. */ head_room = opt->opt_nflen + opt->opt_flen; seg_len += head_room; head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev); if (skb_headroom(skb) < head_room) { struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); if (skb2 == NULL) { IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -ENOBUFS; } kfree_skb(skb); skb = skb2; skb_set_owner_w(skb, sk); } if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop); } hdr = skb->nh.ipv6h = (struct ipv6hdr*)skb_push(skb, sizeof(struct ipv6hdr)); /* * Fill in the IPv6 header */ hlimit = -1; if (np) hlimit = np->hop_limit; if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); tclass = -1; if (np) tclass = np->tclass; if (tclass < 0) tclass = 0; *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->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->daddr, first_hop); skb->protocol = htons(ETH_P_IPV6); skb->priority = sk->sk_priority; mtu = ip6_skb_dst_mtu(skb); if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_OUTREQUESTS); #if defined (CONFIG_RA_HW_NAT_IPV6) #if defined(CONFIG_RA_HW_NAT) || defined(CONFIG_RA_HW_NAT_MODULE) FOE_MAGIC_TAG(skb) = 0; FOE_AI_UNHIT(skb); #endif #endif return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, dst_output); } skb->dev = dst->dev; ipv6_local_error(sk, EMSGSIZE, fl, mtu); IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; }
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 flowi6 *fl6, struct rt6_info *rt, unsigned int flags, int dontfrag) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct inet_cork *cork; struct sk_buff *skb, *skb_prev = NULL; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu; int exthdrlen; int dst_exthdrlen; int hh_len; int copy; int err; int offset = 0; __u8 tx_flags = 0; if (flags&MSG_PROBE) return 0; cork = &inet->cork.base; if (skb_queue_empty(&sk->sk_write_queue)) { /* * setup for corking */ if (opt) { if (WARN_ON(np->cork.opt)) return -EINVAL; np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation); if (unlikely(np->cork.opt == NULL)) return -ENOBUFS; np->cork.opt->tot_len = opt->tot_len; np->cork.opt->opt_flen = opt->opt_flen; np->cork.opt->opt_nflen = opt->opt_nflen; np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt, sk->sk_allocation); if (opt->dst0opt && !np->cork.opt->dst0opt) return -ENOBUFS; np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt, sk->sk_allocation); if (opt->dst1opt && !np->cork.opt->dst1opt) return -ENOBUFS; np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt, sk->sk_allocation); if (opt->hopopt && !np->cork.opt->hopopt) return -ENOBUFS; np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt, sk->sk_allocation); if (opt->srcrt && !np->cork.opt->srcrt) return -ENOBUFS; /* need source address above miyazawa*/ } dst_hold(&rt->dst); cork->dst = &rt->dst; inet->cork.fl.u.ip6 = *fl6; np->cork.hop_limit = hlimit; np->cork.tclass = tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? rt->dst.dev->mtu : dst_mtu(&rt->dst); else mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? rt->dst.dev->mtu : dst_mtu(rt->dst.path); if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } cork->fragsize = mtu; if (dst_allfrag(rt->dst.path)) cork->flags |= IPCORK_ALLFRAG; cork->length = 0; exthdrlen = (opt ? opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } else { rt = (struct rt6_info *)cork->dst; fl6 = &inet->cork.fl.u.ip6; opt = np->cork.opt; transhdrlen = 0; exthdrlen = 0; dst_exthdrlen = 0; mtu = cork->fragsize; } orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) { if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) { ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen); return -EMSGSIZE; } } /* For UDP, check if TX timestamp is enabled */ if (sk->sk_type == SOCK_DGRAM) sock_tx_timestamp(sk, &tx_flags); /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. * Otherwise, we need to reserve fragment header and * fragment alignment (= 8-15 octects, in total). * * Note that we may need to "move" the data from the tail of * of the buffer to the new fragment when we split * the message. * * FIXME: It may be fragmented into multiple chunks * at once if non-fragmentable extension headers * are too large. * --yoshfuji */ if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_RAW)) { ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); return -EMSGSIZE; } skb = skb_peek_tail(&sk->sk_write_queue); cork->length += length; if (((length > mtu) || (skb && skb_has_frags(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags, rt); if (err) goto error; return 0; } if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; alloc_new_skb: /* There's no room in the current skb */ if (skb) fraggap = skb->len - maxfraglen; else fraggap = 0; /* update mtu and maxfraglen if necessary */ if (skb == NULL || skb_prev == NULL) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, orig_mtu); skb_prev = skb; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else alloclen = datalen + fragheaderlen; alloclen += dst_exthdrlen; if (datalen != length + fraggap) { /* * this is not the last fragment, the trailer * space is regarded as data space. */ datalen += rt->dst.trailer_len; } alloclen += rt->dst.trailer_len; fraglen = datalen + fragheaderlen; /* * We just reserve space for fragment header. * Note: this may be overallocation if the message * (without MSG_MORE) fits into the MTU. */ alloclen += sizeof(struct frag_hdr); if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen + hh_len, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (atomic_read(&sk->sk_wmem_alloc) <= 2 * sk->sk_sndbuf) skb = sock_wmalloc(sk, alloclen + hh_len, 1, 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; /* * Fill in the control structures */ skb->ip_summed = CHECKSUM_NONE; skb->csum = 0; /* reserve for fragmentation and ipsec header */ skb_reserve(skb, hh_len + sizeof(struct frag_hdr) + dst_exthdrlen); if (sk->sk_type == SOCK_DGRAM) skb_shinfo(skb)->tx_flags = tx_flags; /* * Find where to start putting bytes */ data = skb_put(skb, fraglen); skb_set_network_header(skb, exthdrlen); data += fragheaderlen; skb->transport_header = (skb->network_header + fragheaderlen); if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap, 0); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } copy = datalen - transhdrlen - fraggap; if (copy < 0) { err = -EINVAL; kfree_skb(skb); goto error; } else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } offset += copy; length -= datalen - fraggap; transhdrlen = 0; exthdrlen = 0; dst_exthdrlen = 0; /* * Put the packet on the pending queue */ __skb_queue_tail(&sk->sk_write_queue, skb); continue; } if (copy > length) copy = length; if (!(rt->dst.dev->features&NETIF_F_SG)) { unsigned int off; off = skb->len; if (getfrag(from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else { int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; if (i == MAX_SKB_FRAGS) goto error; __skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, 0); skb_shinfo(skb)->nr_frags = ++i; get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (getfrag(from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; atomic_add(copy, &sk->sk_wmem_alloc); } offset += copy; length -= copy; } return 0; error_efault: err = -EFAULT; error: cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); return err; }
int ip_forward(struct sk_buff *skb) { struct iphdr *iph; struct rtable *rt; struct ip_options * opt = &(IPCB(skb)->opt); if (skb_warn_if_lro(skb)) goto drop; if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb)) goto drop; if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb)) return NET_RX_SUCCESS; if (skb->pkt_type != PACKET_HOST) goto drop; skb_forward_csum(skb); if (ip_hdr(skb)->ttl <= 1) goto too_many_hops; if (!xfrm4_route_forward(skb)) goto drop; rt = skb_rtable(skb); if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->u.dst) && !skb_is_gso(skb) && (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { IP_INC_STATS(dev_net(rt->u.dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(dst_mtu(&rt->u.dst))); goto drop; } if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len)) goto drop; iph = ip_hdr(skb); ip_decrease_ttl(iph); if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb)) ip_rt_send_redirect(skb); skb->priority = rt_tos2priority(iph->tos); return NF_HOOK(PF_INET, NF_INET_FORWARD, skb, skb->dev, rt->u.dst.dev, ip_forward_finish); sr_failed: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0); goto drop; too_many_hops: IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS); icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); drop: kfree_skb(skb); return NET_RX_DROP; }
static int __ip6_append_data(struct sock *sk, struct flowi6 *fl6, struct sk_buff_head *queue, struct inet_cork *cork, struct inet6_cork *v6_cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, unsigned int flags, int dontfrag) { struct sk_buff *skb, *skb_prev = NULL; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu; int exthdrlen = 0; int dst_exthdrlen = 0; int hh_len; int copy; int err; int offset = 0; __u8 tx_flags = 0; u32 tskey = 0; struct rt6_info *rt = (struct rt6_info *)cork->dst; struct ipv6_txoptions *opt = v6_cork->opt; int csummode = CHECKSUM_NONE; skb = skb_peek_tail(queue); if (!skb) { exthdrlen = opt ? opt->opt_flen : 0; dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } mtu = cork->fragsize; orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) { unsigned int maxnonfragsize, headersize; headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + (dst_allfrag(&rt->dst) ? sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; if (ip6_sk_ignore_df(sk)) maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN; else maxnonfragsize = mtu; /* dontfrag active */ if ((cork->length + length > mtu - headersize) && dontfrag && (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_RAW)) { ipv6_local_rxpmtu(sk, fl6, mtu - headersize + sizeof(struct ipv6hdr)); goto emsgsize; } if (cork->length + length > maxnonfragsize - headersize) { emsgsize: ipv6_local_error(sk, EMSGSIZE, fl6, mtu - headersize + sizeof(struct ipv6hdr)); return -EMSGSIZE; } } if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) { sock_tx_timestamp(sk, &tx_flags); if (tx_flags & SKBTX_ANY_SW_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) tskey = sk->sk_tskey++; } /* If this is the first and only packet and device * supports checksum offloading, let's use it. */ if (!skb && sk->sk_protocol == IPPROTO_UDP && length + fragheaderlen < mtu && rt->dst.dev->features & NETIF_F_V6_CSUM && !exthdrlen) csummode = CHECKSUM_PARTIAL; /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. * Otherwise, we need to reserve fragment header and * fragment alignment (= 8-15 octects, in total). * * Note that we may need to "move" the data from the tail of * of the buffer to the new fragment when we split * the message. * * FIXME: It may be fragmented into multiple chunks * at once if non-fragmentable extension headers * are too large. * --yoshfuji */ cork->length += length; if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags, rt); if (err) goto error; return 0; } if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; alloc_new_skb: /* There's no room in the current skb */ if (skb) fraggap = skb->len - maxfraglen; else fraggap = 0; /* update mtu and maxfraglen if necessary */ if (skb == NULL || skb_prev == NULL) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, orig_mtu); skb_prev = skb; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else alloclen = datalen + fragheaderlen; alloclen += dst_exthdrlen; if (datalen != length + fraggap) { /* * this is not the last fragment, the trailer * space is regarded as data space. */ datalen += rt->dst.trailer_len; } alloclen += rt->dst.trailer_len; fraglen = datalen + fragheaderlen; /* * We just reserve space for fragment header. * Note: this may be overallocation if the message * (without MSG_MORE) fits into the MTU. */ alloclen += sizeof(struct frag_hdr); if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen + hh_len, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (atomic_read(&sk->sk_wmem_alloc) <= 2 * sk->sk_sndbuf) skb = sock_wmalloc(sk, alloclen + hh_len, 1, sk->sk_allocation); if (unlikely(skb == NULL)) err = -ENOBUFS; } if (skb == NULL) goto error; /* * Fill in the control structures */ skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = csummode; skb->csum = 0; /* reserve for fragmentation and ipsec header */ skb_reserve(skb, hh_len + sizeof(struct frag_hdr) + dst_exthdrlen); /* Only the initial fragment is time stamped */ skb_shinfo(skb)->tx_flags = tx_flags; tx_flags = 0; skb_shinfo(skb)->tskey = tskey; tskey = 0; /* * Find where to start putting bytes */ data = skb_put(skb, fraglen); skb_set_network_header(skb, exthdrlen); data += fragheaderlen; skb->transport_header = (skb->network_header + fragheaderlen); if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap, 0); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } copy = datalen - transhdrlen - fraggap; if (copy < 0) { err = -EINVAL; kfree_skb(skb); goto error; } else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } offset += copy; length -= datalen - fraggap; transhdrlen = 0; exthdrlen = 0; dst_exthdrlen = 0; /* * Put the packet on the pending queue */ __skb_queue_tail(queue, skb); continue; } if (copy > length) copy = length; if (!(rt->dst.dev->features&NETIF_F_SG)) { unsigned int off; off = skb->len; if (getfrag(from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; if (i == MAX_SKB_FRAGS) goto error; __skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, 0); skb_shinfo(skb)->nr_frags = ++i; get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (getfrag(from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; atomic_add(copy, &sk->sk_wmem_alloc); } offset += copy; length -= copy; } return 0; error_efault: err = -EFAULT; error: cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); return err; }
static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sockaddr_pkt *saddr=(struct sockaddr_pkt *)msg->msg_name; struct sk_buff *skb; struct net_device *dev; unsigned short proto=0; int err; /* * Get and verify the address. */ if (saddr) { if (msg->msg_namelen < sizeof(struct sockaddr)) return(-EINVAL); if (msg->msg_namelen==sizeof(struct sockaddr_pkt)) proto=saddr->spkt_protocol; } else return(-ENOTCONN); /* SOCK_PACKET must be sent giving an address */ /* * Find the device first to size check it */ saddr->spkt_device[13] = 0; dev = dev_get_by_name(saddr->spkt_device); err = -ENODEV; if (dev == NULL) goto out_unlock; /* * You may not queue a frame bigger than the mtu. This is the lowest level * raw protocol and you must do your own fragmentation at this level. */ err = -EMSGSIZE; if(len>dev->mtu+dev->hard_header_len) goto out_unlock; err = -ENOBUFS; skb = sock_wmalloc(sk, len + LL_RESERVED_SPACE(dev), 0, GFP_KERNEL); /* * If the write buffer is full, then tough. At this level the user gets to * deal with the problem - do your own algorithmic backoffs. That's far * more flexible. */ if (skb == NULL) goto out_unlock; /* * Fill it in */ /* FIXME: Save some space for broken drivers that write a * hard header at transmission time by themselves. PPP is the * notable one here. This should really be fixed at the driver level. */ skb_reserve(skb, LL_RESERVED_SPACE(dev)); skb->nh.raw = skb->data; /* Try to align data part correctly */ if (dev->hard_header) { skb->data -= dev->hard_header_len; skb->tail -= dev->hard_header_len; if (len < dev->hard_header_len) skb->nh.raw = skb->data; } /* Returns -EFAULT on error */ err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len); skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; if (err) goto out_free; err = -ENETDOWN; if (!(dev->flags & IFF_UP)) goto out_free; /* * Now send it */ dev_queue_xmit(skb); dev_put(dev); return(len); out_free: kfree_skb(skb); out_unlock: if (dev) dev_put(dev); return err; }
static void __ndisc_send(struct net_device *dev, struct neighbour *neigh, struct in6_addr *daddr, struct in6_addr *saddr, struct icmp6hdr *icmp6h, struct in6_addr *target, int llinfo, int icmp6_mib_outnd) { struct flowi fl; struct dst_entry *dst; struct sock *sk = ndisc_socket->sk; struct sk_buff *skb; struct icmp6hdr *hdr; struct inet6_dev *idev; int len; int err; u8 *opt; ndisc_flow_init(&fl, icmp6h->icmp6_type, saddr, daddr, dev->ifindex); dst = ndisc_dst_alloc(dev, neigh, daddr, ip6_output); if (!dst) return; err = xfrm_lookup(&dst, &fl, NULL, 0); if (err < 0) return; if (!dev->addr_len) llinfo = 0; len = sizeof(struct icmp6hdr) + (target ? sizeof(*target) : 0); if (llinfo) len += ndisc_opt_addr_space(dev); skb = sock_alloc_send_skb(sk, (MAX_HEADER + sizeof(struct ipv6hdr) + len + LL_RESERVED_SPACE(dev)), 1, &err); if (!skb) { ND_PRINTK0(KERN_ERR "ICMPv6 ND: %s() failed to allocate an skb.\n", __FUNCTION__); dst_release(dst); return; } skb_reserve(skb, LL_RESERVED_SPACE(dev)); ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len); skb->transport_header = skb->tail; skb_put(skb, len); hdr = (struct icmp6hdr *)skb_transport_header(skb); memcpy(hdr, icmp6h, sizeof(*hdr)); opt = skb_transport_header(skb) + sizeof(struct icmp6hdr); if (target) { ipv6_addr_copy((struct in6_addr *)opt, target); opt += sizeof(*target); } if (llinfo) ndisc_fill_addr_option(opt, llinfo, dev->dev_addr, dev->addr_len, dev->type); hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len, IPPROTO_ICMPV6, csum_partial((__u8 *) hdr, len, 0)); skb->dst = dst; idev = in6_dev_get(dst->dev); IP6_INC_STATS(idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, dst_output); if (!err) { ICMP6_INC_STATS(idev, icmp6_mib_outnd); ICMP6_INC_STATS(idev, ICMP6_MIB_OUTMSGS); } if (likely(idev != NULL)) in6_dev_put(idev); }
static int raw_send_hdrinc(struct sock *sk, void *from, int length, struct rtable *rt, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); int hh_len; struct iphdr *iph; struct sk_buff *skb; int err; if (length > rt->u.dst.dev->mtu) { ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, rt->u.dst.dev->mtu); return -EMSGSIZE; } if (flags&MSG_PROBE) goto out; hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); skb = sock_alloc_send_skb(sk, length+hh_len+15, flags&MSG_DONTWAIT, &err); if (skb == NULL) goto error; skb_reserve(skb, hh_len); skb->priority = sk->sk_priority; skb->dst = dst_clone(&rt->u.dst); skb->nh.iph = iph = (struct iphdr *)skb_put(skb, length); skb->ip_summed = CHECKSUM_NONE; skb->h.raw = skb->nh.raw; err = memcpy_fromiovecend((void *)iph, from, 0, length); if (err) goto error_fault; /* We don't modify invalid header */ if (length >= sizeof(*iph) && iph->ihl * 4 <= length) { if (!iph->saddr) iph->saddr = rt->rt_src; iph->check = 0; iph->tot_len = htons(length); if (!iph->id) ip_select_ident(iph, &rt->u.dst, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } err = NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev, dst_output); if (err > 0) err = inet->recverr ? net_xmit_errno(err) : 0; if (err) goto error; out: return 0; error_fault: err = -EFAULT; kfree_skb(skb); error: IP_INC_STATS(IPSTATS_MIB_OUTDISCARDS); return err; }
static int ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->stat; struct ipv6hdr *ipv6h = skb->nh.ipv6h; int encap_limit = -1; struct ipv6_tel_txoption opt; __u16 offset; struct flowi fl; struct dst_entry *dst; struct net_device *tdev; int mtu; int max_headroom = sizeof(struct ipv6hdr); u8 proto; int err; int pkt_len; int dsfield; if (t->recursion++) { stats->collisions++; goto tx_err; } if (skb->protocol != htons(ETH_P_IPV6) || !ip6_tnl_xmit_ctl(t) || ip6ip6_tnl_addr_conflict(t, ipv6h)) goto tx_err; if ((offset = parse_tlv_tnl_enc_lim(skb, skb->nh.raw)) > 0) { struct ipv6_tlv_tnl_enc_lim *tel; tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->nh.raw[offset]; if (tel->encap_limit == 0) { icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offset + 2, skb->dev); goto tx_err; } encap_limit = tel->encap_limit - 1; } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; memcpy(&fl, &t->fl, sizeof (fl)); proto = fl.proto; dsfield = ipv6_get_dsfield(ipv6h); if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)) fl.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); if ((dst = ip6_tnl_dst_check(t)) != NULL) dst_hold(dst); else { dst = ip6_route_output(NULL, &fl); if (dst->error || xfrm_lookup(&dst, &fl, NULL, 0) < 0) goto tx_err_link_failure; } tdev = dst->dev; if (tdev == dev) { stats->collisions++; if (net_ratelimit()) printk(KERN_WARNING "%s: Local routing loop detected!\n", t->parms.name); goto tx_err_dst_release; } mtu = dst_mtu(dst) - sizeof (*ipv6h); if (encap_limit >= 0) { max_headroom += 8; mtu -= 8; } if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (skb->dst) skb->dst->ops->update_pmtu(skb->dst, mtu); if (skb->len > mtu) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev); goto tx_err_dst_release; } /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom += LL_RESERVED_SPACE(tdev); if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { struct sk_buff *new_skb; if (!(new_skb = skb_realloc_headroom(skb, max_headroom))) goto tx_err_dst_release; if (skb->sk) skb_set_owner_w(new_skb, skb->sk); kfree_skb(skb); skb = new_skb; } dst_release(skb->dst); skb->dst = dst_clone(dst); skb->h.raw = skb->nh.raw; if (encap_limit >= 0) { init_tel_txopt(&opt, encap_limit); ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL); } skb->nh.raw = skb_push(skb, sizeof(struct ipv6hdr)); ipv6h = skb->nh.ipv6h; *(__be32*)ipv6h = fl.fl6_flowlabel | htonl(0x60000000); dsfield = INET_ECN_encapsulate(0, dsfield); ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield); ipv6h->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); 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); nf_reset(skb); pkt_len = skb->len; err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, skb->dst->dev, dst_output); if (net_xmit_eval(err) == 0) { stats->tx_bytes += pkt_len; stats->tx_packets++; } else { stats->tx_errors++; stats->tx_aborted_errors++; } ip6_tnl_dst_store(t, dst); t->recursion--; return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: dst_release(dst); tx_err: stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); t->recursion--; return 0; }
/* * Create an arp packet. If (dest_hw == NULL), we create a broadcast * message. */ struct sk_buff *arp_create(int type, int ptype, u32 dest_ip, struct net_device *dev, u32 src_ip, unsigned char *dest_hw, unsigned char *src_hw, unsigned char *target_hw) { struct sk_buff *skb; struct arphdr *arp; unsigned char *arp_ptr; /* * Allocate a buffer */ skb = alloc_skb(sizeof(struct arphdr)+ 2*(dev->addr_len+4) + LL_RESERVED_SPACE(dev), GFP_ATOMIC); if (skb == NULL) return NULL; skb_reserve(skb, LL_RESERVED_SPACE(dev)); skb->nh.raw = skb->data; arp = (struct arphdr *) skb_put(skb,sizeof(struct arphdr) + 2*(dev->addr_len+4)); skb->dev = dev; skb->protocol = htons(ETH_P_ARP); if (src_hw == NULL) src_hw = dev->dev_addr; if (dest_hw == NULL) dest_hw = dev->broadcast; /* * Fill the device header for the ARP frame */ if (dev->hard_header && dev->hard_header(skb,dev,ptype,dest_hw,src_hw,skb->len) < 0) goto out; /* * Fill out the arp protocol part. * * The arp hardware type should match the device type, except for FDDI, * which (according to RFC 1390) should always equal 1 (Ethernet). */ /* * Exceptions everywhere. AX.25 uses the AX.25 PID value not the * DIX code for the protocol. Make these device structure fields. */ switch (dev->type) { default: arp->ar_hrd = htons(dev->type); arp->ar_pro = htons(ETH_P_IP); break; #if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) case ARPHRD_AX25: arp->ar_hrd = htons(ARPHRD_AX25); arp->ar_pro = htons(AX25_P_IP); break; #if defined(CONFIG_NETROM) || defined(CONFIG_NETROM_MODULE) case ARPHRD_NETROM: arp->ar_hrd = htons(ARPHRD_NETROM); arp->ar_pro = htons(AX25_P_IP); break; #endif #endif #ifdef CONFIG_FDDI case ARPHRD_FDDI: arp->ar_hrd = htons(ARPHRD_ETHER); arp->ar_pro = htons(ETH_P_IP); break; #endif #ifdef CONFIG_TR case ARPHRD_IEEE802_TR: arp->ar_hrd = htons(ARPHRD_IEEE802); arp->ar_pro = htons(ETH_P_IP); break; #endif } arp->ar_hln = dev->addr_len; arp->ar_pln = 4; arp->ar_op = htons(type); arp_ptr=(unsigned char *)(arp+1); memcpy(arp_ptr, src_hw, dev->addr_len); arp_ptr+=dev->addr_len; memcpy(arp_ptr, &src_ip,4); arp_ptr+=4; if (target_hw != NULL) memcpy(arp_ptr, target_hw, dev->addr_len); else memset(arp_ptr, 0, dev->addr_len); arp_ptr+=dev->addr_len; memcpy(arp_ptr, &dest_ip, 4); return skb; out: kfree_skb(skb); return NULL; }
int ip_forward(struct sk_buff *skb) { struct iphdr *iph; /* Our header */ struct rtable *rt; /* Route we use */ struct ip_options * opt = &(IPCB(skb)->opt); #ifdef CONFIG_USE_POLICY_FWD if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb)) goto drop; #else if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; #endif if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb)) return NET_RX_SUCCESS; if (skb->pkt_type != PACKET_HOST) goto drop; skb->ip_summed = CHECKSUM_NONE; /* * According to the RFC, we must first decrease the TTL field. If * that reaches zero, we must reply an ICMP control message telling * that the packet's lifetime expired. */ if (skb->nh.iph->ttl <= 1) goto too_many_hops; if (!xfrm4_route_forward(skb)) goto drop; rt = (struct rtable*)skb->dst; if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway) goto sr_failed; /* We are about to mangle packet. Copy it! */ if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len)) goto drop; iph = skb->nh.iph; /* Decrease ttl after skb cow done */ ip_decrease_ttl(iph); /* * We now generate an ICMP HOST REDIRECT giving the route * we calculated. */ if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr) ip_rt_send_redirect(skb); if (!skb->priority) skb->priority = rt_dscp2priority(iph->tos); return NF_HOOK(PF_INET, NF_IP_FORWARD, skb, skb->dev, rt->u.dst.dev, ip_forward_finish); sr_failed: /* * Strict routing permits no gatewaying */ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0); goto drop; too_many_hops: /* Tell the sender its packet died... */ icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); drop: kfree_skb(skb); return NET_RX_DROP; }
/* * Create an arp packet. If (dest_hw == NULL), we create a broadcast * message. */ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw) { struct sk_buff *skb; struct arphdr *arp; unsigned char *arp_ptr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; /* * Allocate a buffer */ skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC); if (skb == NULL) return NULL; skb_reserve(skb, hlen); skb_reset_network_header(skb); arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; skb->protocol = htons(ETH_P_ARP); if (src_hw == NULL) src_hw = dev->dev_addr; if (dest_hw == NULL) dest_hw = dev->broadcast; /* * Fill the device header for the ARP frame */ if (dev_hard_header(skb, dev, ptype, dest_hw, src_hw, skb->len) < 0) goto out; /* * Fill out the arp protocol part. * * The arp hardware type should match the device type, except for FDDI, * which (according to RFC 1390) should always equal 1 (Ethernet). */ /* * Exceptions everywhere. AX.25 uses the AX.25 PID value not the * DIX code for the protocol. Make these device structure fields. */ switch (dev->type) { default: arp->ar_hrd = htons(dev->type); arp->ar_pro = htons(ETH_P_IP); break; #if IS_ENABLED(CONFIG_AX25) case ARPHRD_AX25: arp->ar_hrd = htons(ARPHRD_AX25); arp->ar_pro = htons(AX25_P_IP); break; #if IS_ENABLED(CONFIG_NETROM) case ARPHRD_NETROM: arp->ar_hrd = htons(ARPHRD_NETROM); arp->ar_pro = htons(AX25_P_IP); break; #endif #endif #if IS_ENABLED(CONFIG_FDDI) case ARPHRD_FDDI: arp->ar_hrd = htons(ARPHRD_ETHER); arp->ar_pro = htons(ETH_P_IP); break; #endif } arp->ar_hln = dev->addr_len; arp->ar_pln = 4; arp->ar_op = htons(type); arp_ptr = (unsigned char *)(arp + 1); memcpy(arp_ptr, src_hw, dev->addr_len); arp_ptr += dev->addr_len; memcpy(arp_ptr, &src_ip, 4); arp_ptr += 4; switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: break; #endif default: if (target_hw != NULL) memcpy(arp_ptr, target_hw, dev->addr_len); else memset(arp_ptr, 0, dev->addr_len); arp_ptr += dev->addr_len; } memcpy(arp_ptr, &dest_ip, 4); return skb; out: kfree_skb(skb); return NULL; }
static int packet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sockaddr_ll *saddr=(struct sockaddr_ll *)msg->msg_name; struct sk_buff *skb; struct net_device *dev; unsigned short proto; unsigned char *addr; int ifindex, err, reserve = 0; /* * Get and verify the address. */ if (saddr == NULL) { struct packet_sock *po = pkt_sk(sk); ifindex = po->ifindex; proto = po->num; addr = NULL; } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; ifindex = saddr->sll_ifindex; proto = saddr->sll_protocol; addr = saddr->sll_addr; } dev = dev_get_by_index(ifindex); err = -ENXIO; if (dev == NULL) goto out_unlock; if (sock->type == SOCK_RAW) reserve = dev->hard_header_len; err = -EMSGSIZE; if (len > dev->mtu+reserve) goto out_unlock; skb = sock_alloc_send_skb(sk, len + LL_RESERVED_SPACE(dev), msg->msg_flags & MSG_DONTWAIT, &err); if (skb==NULL) goto out_unlock; skb_reserve(skb, LL_RESERVED_SPACE(dev)); skb->nh.raw = skb->data; if (dev->hard_header) { int res; err = -EINVAL; res = dev->hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (sock->type != SOCK_DGRAM) { skb->tail = skb->data; skb->len = 0; } else if (res < 0) goto out_free; } /* Returns -EFAULT on error */ err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len); if (err) goto out_free; skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; err = -ENETDOWN; if (!(dev->flags & IFF_UP)) goto out_free; /* * Now send it */ err = dev_queue_xmit(skb); if (err > 0 && (err = net_xmit_errno(err)) != 0) goto out_unlock; dev_put(dev); return(len); out_free: kfree_skb(skb); out_unlock: if (dev) dev_put(dev); out: return err; }
int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info*)skb_dst(skb); struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; unsigned int mtu, hlen, left, len; int hroom, troom; __be32 frag_id = 0; int ptr, offset = 0, err=0; u8 *prevhdr, nexthdr = 0; struct net *net = dev_net(skb_dst(skb)->dev); hlen = ip6_find_1stfragopt(skb, &prevhdr); nexthdr = *prevhdr; mtu = ip6_skb_dst_mtu(skb); /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ if (unlikely(!skb->ignore_df && skb->len > mtu) || (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) { if (skb->sk && dst_allfrag(skb_dst(skb))) sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK); skb->dev = skb_dst(skb)->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } if (np && np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } mtu -= hlen + sizeof(struct frag_hdr); if (skb_has_frag_list(skb)) { int first_len = skb_pagelen(skb); struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || skb_cloned(skb)) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } err = 0; offset = 0; frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); /* BUILD HEADER */ *prevhdr = NEXTHDR_FRAGMENT; tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!tmp_hdr) { IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); return -ENOMEM; } __skb_pull(skb, hlen); fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr)); __skb_push(skb, hlen); skb_reset_network_header(skb); memcpy(skb_network_header(skb), tmp_hdr, hlen); ipv6_select_ident(fh, rt); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); frag_id = fh->identification; first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); dst_hold(&rt->dst); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (frag) { frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); fh = (struct frag_hdr*)__skb_push(frag, sizeof(struct frag_hdr)); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), tmp_hdr, hlen); offset += skb->len - hlen - sizeof(struct frag_hdr); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(offset); if (frag->next != NULL) fh->frag_off |= htons(IP6_MF); fh->identification = frag_id; ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); ip6_copy_metadata(frag, skb); } err = output(skb); if(!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGCREATES); if (err || !frag) break; skb = frag; frag = skb->next; skb->next = NULL; } kfree(tmp_hdr); if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); ip6_rt_put(rt); return 0; } while (frag) { skb = frag->next; kfree_skb(frag); frag = skb; } IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); ip6_rt_put(rt); return err; slow_path_clean: skb_walk_frags(skb, frag2) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb)) goto fail; left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ /* * Fragment the datagram. */ *prevhdr = NEXTHDR_FRAGMENT; hroom = LL_RESERVED_SPACE(rt->dst.dev); troom = rt->dst.dev->needed_tailroom; /* * Keep copying data until we run out. */ while(left > 0) { len = left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) len = mtu; /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < left) { len &= ~7; } /* * Allocate buffer. */ if ((frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) + hroom + troom, GFP_ATOMIC)) == NULL) { NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n"); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; } /* * Set up data on packet */ ip6_copy_metadata(frag, skb); skb_reserve(frag, hroom); skb_put(frag, len + hlen + sizeof(struct frag_hdr)); skb_reset_network_header(frag); fh = (struct frag_hdr *)(skb_network_header(frag) + hlen); frag->transport_header = (frag->network_header + hlen + sizeof(struct frag_hdr)); /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(frag, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(frag), hlen); /* * Build fragment header. */ fh->nexthdr = nexthdr; fh->reserved = 0; if (!frag_id) { ipv6_select_ident(fh, rt); frag_id = fh->identification; } else fh->identification = frag_id; /* * Copy a block of the IP datagram. */ if (skb_copy_bits(skb, ptr, skb_transport_header(frag), len)) BUG(); left -= len; fh->frag_off = htons(offset); if (left > 0) fh->frag_off |= htons(IP6_MF); ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); ptr += len; offset += len; /* * Put this fragment into the sending queue. */ err = output(frag); if (err) goto fail; IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGCREATES); } IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGOKS); consume_skb(skb); return err; fail: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return err; }
static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, void *from, size_t length, struct rtable **rtp, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct iphdr *iph; struct sk_buff *skb; unsigned int iphlen; int err; struct rtable *rt = *rtp; int hlen, tlen; if (length > rt->dst.dev->mtu) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, rt->dst.dev->mtu); return -EMSGSIZE; } if (flags&MSG_PROBE) goto out; hlen = LL_RESERVED_SPACE(rt->dst.dev); tlen = rt->dst.dev->needed_tailroom; skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto error; skb_reserve(skb, hlen); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; skb_dst_set(skb, &rt->dst); *rtp = NULL; skb_reset_network_header(skb); iph = ip_hdr(skb); skb_put(skb, length); skb->ip_summed = CHECKSUM_NONE; skb->transport_header = skb->network_header; err = -EFAULT; if (memcpy_fromiovecend((void *)iph, from, 0, length)) goto error_free; iphlen = iph->ihl * 4; /* * We don't want to modify the ip header, but we do need to * be sure that it won't cause problems later along the network * stack. Specifically we want to make sure that iph->ihl is a * sane value. If ihl points beyond the length of the buffer passed * in, reject the frame as invalid */ err = -EINVAL; if (iphlen > length) goto error_free; if (iphlen >= sizeof(*iph)) { if (!iph->saddr) iph->saddr = fl4->saddr; iph->check = 0; iph->tot_len = htons(length); if (!iph->id) ip_select_ident(skb, &rt->dst, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } if (iph->protocol == IPPROTO_ICMP) icmp_out_count(net, ((struct icmphdr *) skb_transport_header(skb))->type); err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) goto error; out: return 0; error_free: kfree_skb(skb); error: IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); if (err == -ENOBUFS && !inet->recverr) err = 0; return err; }
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, struct ipv6_txoptions *opt, int tclass) { struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr; u8 proto = fl6->flowi6_proto; int seg_len = skb->len; int hlimit = -1; u32 mtu; if (opt) { unsigned int head_room; /* First: exthdrs may take lots of space (~8K for now) MAX_HEADER is not enough. */ head_room = opt->opt_nflen + opt->opt_flen; seg_len += head_room; head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev); if (skb_headroom(skb) < head_room) { struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); if (skb2 == NULL) { IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -ENOBUFS; } consume_skb(skb); skb = skb2; skb_set_owner_w(skb, sk); } if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop); } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); /* * Fill in the IPv6 header */ if (np) hlimit = np->hop_limit; if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); ip6_flow_hdr(hdr, tclass, fl6->flowlabel); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; hdr->hop_limit = hlimit; hdr->saddr = fl6->saddr; hdr->daddr = *first_hop; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) { IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUT, skb->len); return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, dst_output); } skb->dev = dst->dev; ipv6_local_error(sk, EMSGSIZE, fl6, mtu); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; }
/* * IP Tunneling transmitter * * This function encapsulates the packet in a new IP packet, its * destination will be set to cp->daddr. Most code of this function * is taken from ipip.c. * * It is used in VS/TUN cluster. The load balancer selects a real * server from a cluster based on a scheduling algorithm, * encapsulates the request packet and forwards it to the selected * server. For example, all real servers are configured with * "ifconfig tunl0 <Virtual IP Address> up". When the server receives * the encapsulated packet, it will decapsulate the packet, processe * the request and return the response packets directly to the client * without passing the load balancer. This can greatly increase the * scalability of virtual server. * * Used for ANY protocol */ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { struct rtable *rt; /* Route to the other host */ __be32 saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ struct iphdr *old_iph = ip_hdr(skb); u8 tos = old_iph->tos; __be16 df = old_iph->frag_off; struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int mtu; int ret; EnterFunction(10); if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(tos), IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL, &saddr))) goto tx_error_icmp; if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1); } tdev = rt->dst.dev; mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (mtu < 68) { IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__); goto tx_error_put; } if (skb_dst(skb)) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); df |= (old_iph->frag_off & htons(IP_DF)); if ((old_iph->frag_off & htons(IP_DF) && mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; } /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr); if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); kfree_skb(skb); IP_VS_ERR_RL("%s(): no memory\n", __func__); return NF_STOLEN; } kfree_skb(skb); skb = new_skb; old_iph = ip_hdr(skb); } skb->transport_header = skb->network_header; /* fix old IP header checksum */ ip_send_check(old_iph); skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* drop old route */ skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); /* * Push down and install the IPIP header. */ iph = ip_hdr(skb); iph->version = 4; iph->ihl = sizeof(struct iphdr)>>2; iph->frag_off = df; iph->protocol = IPPROTO_IPIP; iph->tos = tos; iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = old_iph->ttl; ip_select_ident(iph, &rt->dst, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; ret = IP_VS_XMIT_TUNNEL(skb, cp); if (ret == NF_ACCEPT) ip_local_out(skb); else if (ret == NF_DROP) kfree_skb(skb); LeaveFunction(10); return NF_STOLEN; tx_error_icmp: dst_link_failure(skb); tx_error: kfree_skb(skb); LeaveFunction(10); return NF_STOLEN; tx_error_put: ip_rt_put(rt); goto tx_error; }
struct sk_buff *ndisc_build_skb(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *saddr, struct icmp6hdr *icmp6h, const struct in6_addr *target, int llinfo) { struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; struct sk_buff *skb; struct icmp6hdr *hdr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; int len; int err; u8 *opt; if (!dev->addr_len) llinfo = 0; len = sizeof(struct icmp6hdr) + (target ? sizeof(*target) : 0); if (llinfo) len += ndisc_opt_addr_space(dev); skb = sock_alloc_send_skb(sk, (MAX_HEADER + sizeof(struct ipv6hdr) + len + hlen + tlen), 1, &err); if (!skb) { ND_PRINTK0(KERN_ERR "ICMPv6 ND: %s() failed to allocate an skb, err=%d.\n", __func__, err); return NULL; } skb_reserve(skb, hlen); ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len); skb->transport_header = skb->tail; skb_put(skb, len); hdr = (struct icmp6hdr *)skb_transport_header(skb); memcpy(hdr, icmp6h, sizeof(*hdr)); opt = skb_transport_header(skb) + sizeof(struct icmp6hdr); if (target) { *(struct in6_addr *)opt = *target; opt += sizeof(*target); } if (llinfo) ndisc_fill_addr_option(opt, llinfo, dev->dev_addr, dev->addr_len, dev->type); hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len, IPPROTO_ICMPV6, csum_partial(hdr, len, 0)); return skb; }
int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { struct rt6_info *rt; /* Route to the other host */ struct in6_addr saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ struct ipv6hdr *old_iph = ipv6_hdr(skb); struct ipv6hdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int mtu; int ret; EnterFunction(10); if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, &saddr, 1, (IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL)))) goto tx_error_icmp; if (__ip_vs_is_local_route6(rt)) { dst_release(&rt->dst); IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1); } tdev = rt->dst.dev; mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr); if (mtu < IPV6_MIN_MTU) { IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__, IPV6_MIN_MTU); goto tx_error_put; } if (skb_dst(skb)) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) && !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); skb->dev = net->loopback_dev; } icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; } /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr); if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { dst_release(&rt->dst); kfree_skb(skb); IP_VS_ERR_RL("%s(): no memory\n", __func__); return NF_STOLEN; } kfree_skb(skb); skb = new_skb; old_iph = ipv6_hdr(skb); } skb->transport_header = skb->network_header; skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* drop old route */ skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); /* * Push down and install the IPIP header. */ iph = ipv6_hdr(skb); iph->version = 6; iph->nexthdr = IPPROTO_IPV6; iph->payload_len = old_iph->payload_len; be16_add_cpu(&iph->payload_len, sizeof(*old_iph)); iph->priority = old_iph->priority; memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl)); iph->daddr = cp->daddr.in6; iph->saddr = saddr; iph->hop_limit = old_iph->hop_limit; /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; ret = IP_VS_XMIT_TUNNEL(skb, cp); if (ret == NF_ACCEPT) ip6_local_out(skb); else if (ret == NF_DROP) kfree_skb(skb); LeaveFunction(10); return NF_STOLEN; tx_error_icmp: dst_link_failure(skb); tx_error: kfree_skb(skb); LeaveFunction(10); return NF_STOLEN; tx_error_put: dst_release(&rt->dst); goto tx_error; }
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, struct rt6_info *rt, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; unsigned int maxfraglen, fragheaderlen; int exthdrlen; int hh_len; int mtu; int copy; int err; int offset = 0; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) { /* * setup for corking */ if (opt) { if (np->cork.opt == NULL) { np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation); if (unlikely(np->cork.opt == NULL)) return -ENOBUFS; } else if (np->cork.opt->tot_len < opt->tot_len) { printk(KERN_DEBUG "ip6_append_data: invalid option length\n"); return -EINVAL; } memcpy(np->cork.opt, opt, opt->tot_len); inet->cork.flags |= IPCORK_OPT; /* need source address above miyazawa*/ } dst_hold(&rt->u.dst); np->cork.rt = rt; inet->cork.fl = *fl; np->cork.hop_limit = hlimit; np->cork.tclass = tclass; mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? rt->u.dst.dev->mtu : dst_mtu(rt->u.dst.path); if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } inet->cork.fragsize = mtu; if (dst_allfrag(rt->u.dst.path)) inet->cork.flags |= IPCORK_ALLFRAG; inet->cork.length = 0; sk->sk_sndmsg_page = NULL; sk->sk_sndmsg_off = 0; exthdrlen = rt->u.dst.header_len + (opt ? opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; } else { rt = np->cork.rt; fl = &inet->cork.fl; if (inet->cork.flags & IPCORK_OPT) opt = np->cork.opt; transhdrlen = 0; exthdrlen = 0; mtu = inet->cork.fragsize; } hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->u.dst.nfheader_len + (opt ? opt->opt_nflen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); 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); return -EMSGSIZE; } } /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. * Otherwise, we need to reserve fragment header and * fragment alignment (= 8-15 octects, in total). * * Note that we may need to "move" the data from the tail of * of the buffer to the new fragment when we split * the message. * * FIXME: It may be fragmented into multiple chunks * at once if non-fragmentable extension headers * are too large. * --yoshfuji */ skb = skb_peek_tail(&sk->sk_write_queue); inet->cork.length += length; if (((length > mtu) || (skb && skb_has_frags(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->u.dst.dev->features & NETIF_F_UFO)) { err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags); if (err) goto error; return 0; } if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; struct sk_buff *skb_prev; alloc_new_skb: skb_prev = skb; /* There's no room in the current skb */ if (skb_prev) fraggap = skb_prev->len - maxfraglen; else fraggap = 0; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen; fraglen = datalen + fragheaderlen; if ((flags & MSG_MORE) && !(rt->u.dst.dev->features&NETIF_F_SG)) alloclen = mtu; else alloclen = datalen + fragheaderlen; /* * The last fragment gets additional space at tail. * Note: we overallocate on fragments with MSG_MODE * because we have no idea if we're the last one. */ if (datalen == length + fraggap) alloclen += rt->u.dst.trailer_len; /* * We just reserve space for fragment header. * Note: this may be overallocation if the message * (without MSG_MORE) fits into the MTU. */ alloclen += sizeof(struct frag_hdr); if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen + hh_len, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (atomic_read(&sk->sk_wmem_alloc) <= 2 * sk->sk_sndbuf) skb = sock_wmalloc(sk, alloclen + hh_len, 1, sk->sk_allocation); if (unlikely(skb == NULL)) err = -ENOBUFS; } if (skb == NULL) goto error; /* * Fill in the control structures */ skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = CHECKSUM_NONE; skb->csum = 0; /* reserve for fragmentation */ skb_reserve(skb, hh_len+sizeof(struct frag_hdr)); /* * Find where to start putting bytes */ data = skb_put(skb, fraglen); skb_set_network_header(skb, exthdrlen); data += fragheaderlen; skb->h.raw = skb->nh.raw + fragheaderlen; if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap, 0); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } copy = datalen - transhdrlen - fraggap; if (copy < 0) { err = -EINVAL; kfree_skb(skb); goto error; } else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } offset += copy; length -= datalen - fraggap; transhdrlen = 0; exthdrlen = 0; /* * Put the packet on the pending queue */ __skb_queue_tail(&sk->sk_write_queue, skb); continue; } if (copy > length) copy = length; if (!(rt->u.dst.dev->features&NETIF_F_SG)) { unsigned int off; off = skb->len; if (getfrag(from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else { int i = skb_shinfo(skb)->nr_frags; skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1]; struct page *page = sk->sk_sndmsg_page; int off = sk->sk_sndmsg_off; unsigned int left; if (page && (left = PAGE_SIZE - off) > 0) { if (copy >= left) copy = left; if (page != frag->page) { if (i == MAX_SKB_FRAGS) { err = -EMSGSIZE; goto error; } get_page(page); skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0); frag = &skb_shinfo(skb)->frags[i]; } } else if(i < MAX_SKB_FRAGS) { if (copy > PAGE_SIZE) copy = PAGE_SIZE; page = alloc_pages(sk->sk_allocation, 0); if (page == NULL) { err = -ENOMEM; goto error; } sk->sk_sndmsg_page = page; sk->sk_sndmsg_off = 0; skb_fill_page_desc(skb, i, page, 0, 0); frag = &skb_shinfo(skb)->frags[i]; } else { err = -EMSGSIZE; goto error; } if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) { err = -EFAULT; goto error; } sk->sk_sndmsg_off += copy; frag->size += copy; skb->len += copy; skb->data_len += copy; skb->truesize += copy; atomic_add(copy, &sk->sk_wmem_alloc); } offset += copy; length -= copy; } return 0; error: inet->cork.length -= length; IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); return err; }
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *inner_iph; struct flowi4 fl4; u8 tos, ttl; __be16 df; struct rtable *rt; /* Route to the other host */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst; int err; bool connected = true; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ if (skb_dst(skb) == NULL) { dev->stats.tx_fifo_errors++; goto tx_error; } if (skb->protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); dst = rt_nexthop(rt, inner_iph->daddr); } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { const struct in6_addr *addr6; struct neighbour *neigh; bool do_tx_error_icmp; int addr_type; neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (neigh == NULL) goto tx_error; addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { addr6 = &ipv6_hdr(skb)->daddr; addr_type = ipv6_addr_type(addr6); } if ((addr_type & IPV6_ADDR_COMPATv4) == 0) do_tx_error_icmp = true; else { do_tx_error_icmp = false; dst = addr6->s6_addr32[3]; } neigh_release(neigh); if (do_tx_error_icmp) goto tx_error_icmp; } #endif else goto tx_error; connected = false; } tos = tnl_params->tos; if (tos & 0x1) { tos &= ~0x1; if (skb->protocol == htons(ETH_P_IP)) { tos = inner_iph->tos; connected = false; } else if (skb->protocol == htons(ETH_P_IPV6)) { tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); connected = false; } } init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link); rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL; if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { dev->stats.tx_carrier_errors++; goto tx_error; } if (connected) tunnel_dst_set(tunnel, &rt->dst); } if (rt->dst.dev == dev) { ip_rt_put(rt); dev->stats.collisions++; goto tx_error; } if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) { ip_rt_put(rt); goto tx_error; } if (tunnel->err_count > 0) { if (time_before(jiffies, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; memset(IPCB(skb), 0, sizeof(*IPCB(skb))); dst_link_failure(skb); } else tunnel->err_count = 0; } tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = tnl_params->ttl; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) ttl = inner_iph->ttl; #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; #endif else ttl = ip4_dst_hoplimit(&rt->dst); } df = tnl_params->frag_off; if (skb->protocol == htons(ETH_P_IP)) df |= (inner_iph->frag_off&htons(IP_DF)); max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len; if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; if (skb_cow_head(skb, dev->needed_headroom)) { dev->stats.tx_dropped++; kfree_skb(skb); return; } err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return; #if IS_ENABLED(CONFIG_IPV6) tx_error_icmp: dst_link_failure(skb); #endif tx_error: dev->stats.tx_errors++; kfree_skb(skb); }
static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info*)skb->dst; struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; unsigned int mtu, hlen, left, len; __be32 frag_id = 0; int ptr, offset = 0, err=0; u8 *prevhdr, nexthdr = 0; hlen = ip6_find_1stfragopt(skb, &prevhdr); nexthdr = *prevhdr; mtu = ip6_skb_dst_mtu(skb); if (np && np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } mtu -= hlen + sizeof(struct frag_hdr); if (skb_shinfo(skb)->frag_list) { int first_len = skb_pagelen(skb); struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || skb_cloned(skb)) goto slow_path; for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } err = 0; offset = 0; frag = skb_shinfo(skb)->frag_list; skb_shinfo(skb)->frag_list = NULL; /* BUILD HEADER */ *prevhdr = NEXTHDR_FRAGMENT; tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!tmp_hdr) { IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS); return -ENOMEM; } __skb_pull(skb, hlen); fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr)); skb->nh.raw = __skb_push(skb, hlen); memcpy(skb_network_header(skb), tmp_hdr, hlen); ipv6_select_ident(skb, fh); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); frag_id = fh->identification; first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; skb->nh.ipv6h->payload_len = htons(first_len - sizeof(struct ipv6hdr)); dst_hold(&rt->u.dst); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (frag) { frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); fh = (struct frag_hdr*)__skb_push(frag, sizeof(struct frag_hdr)); frag->nh.raw = __skb_push(frag, hlen); memcpy(skb_network_header(frag), tmp_hdr, hlen); offset += skb->len - hlen - sizeof(struct frag_hdr); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(offset); if (frag->next != NULL) fh->frag_off |= htons(IP6_MF); fh->identification = frag_id; frag->nh.ipv6h->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); ip6_copy_metadata(frag, skb); } err = output(skb); if(!err) IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGCREATES); if (err || !frag) break; skb = frag; frag = skb->next; skb->next = NULL; } kfree(tmp_hdr); if (err == 0) { IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGOKS); dst_release(&rt->u.dst); return 0; } while (frag) { skb = frag->next; kfree_skb(frag); frag = skb; } IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGFAILS); dst_release(&rt->u.dst); return err; slow_path_clean: for (frag2 = skb_shinfo(skb)->frag_list; frag2; frag2 = frag2->next) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb)) goto fail; left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ /* * Fragment the datagram. */ *prevhdr = NEXTHDR_FRAGMENT; /* * Keep copying data until we run out. */ while(left > 0) { len = left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) len = mtu; /* IF: we are not sending upto and including the packet end then align the next start on an eight byte boundary */ if (len < left) { len &= ~7; } /* * Allocate buffer. */ if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) { NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n"); IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; } /* * Set up data on packet */ ip6_copy_metadata(frag, skb); skb_reserve(frag, LL_RESERVED_SPACE(rt->u.dst.dev)); skb_put(frag, len + hlen + sizeof(struct frag_hdr)); skb_reset_network_header(frag); fh = (struct frag_hdr *)(skb_network_header(frag) + hlen); frag->h.raw = frag->nh.raw + hlen + sizeof(struct frag_hdr); /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(frag, skb->sk); /* * Copy the packet header into the new buffer. */ memcpy(skb_network_header(frag), skb->data, hlen); /* * Build fragment header. */ fh->nexthdr = nexthdr; fh->reserved = 0; if (!frag_id) { ipv6_select_ident(skb, fh); frag_id = fh->identification; } else fh->identification = frag_id; /* * Copy a block of the IP datagram. */ if (skb_copy_bits(skb, ptr, frag->h.raw, len)) BUG(); left -= len; fh->frag_off = htons(offset); if (left > 0) fh->frag_off |= htons(IP6_MF); frag->nh.ipv6h->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); ptr += len; offset += len; /* * Put this fragment into the sending queue. */ err = output(frag); if (err) goto fail; IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGCREATES); } IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGOKS); kfree_skb(skb); return err; fail: IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return err; }
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct ipv6_txoptions *opt, int ipfragok) { struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl->fl6_dst; struct dst_entry *dst = skb->dst; struct ipv6hdr *hdr; u8 proto = fl->proto; int seg_len = skb->len; int hlimit, tclass; u32 mtu; if (opt) { int head_room; /* First: exthdrs may take lots of space (~8K for now) MAX_HEADER is not enough. */ head_room = opt->opt_nflen + opt->opt_flen; seg_len += head_room; head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev); if (skb_headroom(skb) < head_room) { struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); if (skb2 == NULL) { IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -ENOBUFS; } kfree_skb(skb); skb = skb2; if (sk) skb_set_owner_w(skb, sk); } if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop); } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); /* * Fill in the IPv6 header */ hlimit = -1; if (np) hlimit = np->hop_limit; if (hlimit < 0) hlimit = dst_metric(dst, RTAX_HOPLIMIT); if (hlimit < 0) hlimit = ipv6_get_hoplimit(dst->dev); tclass = -1; if (np) tclass = np->tclass; if (tclass < 0) tclass = 0; *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->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->daddr, first_hop); skb->priority = sk->sk_priority; mtu = dst_mtu(dst); if ((skb->len <= mtu) || ipfragok || skb_is_gso(skb)) { IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_OUTREQUESTS); return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, dst_output); } if (net_ratelimit()) printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n"); skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; }
/* * IP Tunneling transmitter * * This function encapsulates the packet in a new IP packet, its * destination will be set to cp->daddr. Most code of this function * is taken from ipip.c. * * It is used in VS/TUN cluster. The load balancer selects a real * server from a cluster based on a scheduling algorithm, * encapsulates the request packet and forwards it to the selected * server. For example, all real servers are configured with * "ifconfig tunl0 <Virtual IP Address> up". When the server receives * the encapsulated packet, it will decapsulate the packet, processe * the request and return the response packets directly to the client * without passing the load balancer. This can greatly increase the * scalability of virtual server. * * Used for ANY protocol */ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { struct net *net = skb_net(skb); struct netns_ipvs *ipvs = net_ipvs(net); struct rtable *rt; /* Route to the other host */ __be32 saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ __u8 next_protocol = 0; __u8 dsfield = 0; __u8 ttl = 0; __be16 df = 0; __be16 *dfp = NULL; struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int ret, local; EnterFunction(10); rcu_read_lock(); local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_CONNECT | IP_VS_RT_MODE_TUNNEL, &saddr, ipvsh); if (local < 0) goto tx_error; if (local) { rcu_read_unlock(); return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1); } rt = skb_rtable(skb); tdev = rt->dst.dev; /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr); /* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */ dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL; skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom, &next_protocol, NULL, &dsfield, &ttl, dfp); if (IS_ERR(skb)) goto tx_error; skb = iptunnel_handle_offloads( skb, false, __tun_gso_type_mask(AF_INET, cp->af)); if (IS_ERR(skb)) goto tx_error; skb->transport_header = skb->network_header; skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* * Push down and install the IPIP header. */ iph = ip_hdr(skb); iph->version = 4; iph->ihl = sizeof(struct iphdr)>>2; iph->frag_off = df; iph->protocol = next_protocol; iph->tos = dsfield; iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = ttl; ip_select_ident(net, skb, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; ret = ip_vs_tunnel_xmit_prepare(skb, cp); if (ret == NF_ACCEPT) ip_local_out(skb); else if (ret == NF_DROP) kfree_skb(skb); rcu_read_unlock(); LeaveFunction(10); return NF_STOLEN; tx_error: if (!IS_ERR(skb)) kfree_skb(skb); rcu_read_unlock(); LeaveFunction(10); return NF_STOLEN; }
static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, struct rtable *rt, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct iphdr *iph; struct sk_buff *skb; unsigned int iphlen; int err; if (length > rt->u.dst.dev->mtu) { ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, rt->u.dst.dev->mtu); return -EMSGSIZE; } if (flags&MSG_PROBE) goto out; skb = sock_alloc_send_skb(sk, length + LL_ALLOCATED_SPACE(rt->u.dst.dev) + 15, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto error; skb_reserve(skb, LL_RESERVED_SPACE(rt->u.dst.dev)); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; skb_dst_set(skb, dst_clone(&rt->u.dst)); skb_reset_network_header(skb); iph = ip_hdr(skb); skb_put(skb, length); skb->ip_summed = CHECKSUM_NONE; skb->transport_header = skb->network_header; err = memcpy_fromiovecend((void *)iph, from, 0, length); if (err) goto error_fault; /* We don't modify invalid header */ iphlen = iph->ihl * 4; if (iphlen >= sizeof(*iph) && iphlen <= length) { if (!iph->saddr) iph->saddr = rt->rt_src; iph->check = 0; iph->tot_len = htons(length); if (!iph->id) ip_select_ident(iph, &rt->u.dst, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } if (iph->protocol == IPPROTO_ICMP) icmp_out_count(net, ((struct icmphdr *) skb_transport_header(skb))->type); err = NF_HOOK(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) goto error; out: return 0; error_fault: err = -EFAULT; kfree_skb(skb); error: IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); if (err == -ENOBUFS && !inet->recverr) err = 0; return err; }
int ip_forward(struct sk_buff *skb) { struct iphdr *iph; /* Our header */ struct rtable *rt; /* Route we use */ struct ip_options * opt = &(IPCB(skb)->opt); if (unlikely(skb->sk)) goto drop; if (skb_warn_if_lro(skb)) goto drop; if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb)) goto drop; if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb)) return NET_RX_SUCCESS; if (skb->pkt_type != PACKET_HOST) goto drop; skb_forward_csum(skb); /* * According to the RFC, we must first decrease the TTL field. If * that reaches zero, we must reply an ICMP control message telling * that the packet's lifetime expired. */ if (ip_hdr(skb)->ttl <= 1) goto too_many_hops; if (!xfrm4_route_forward(skb)) goto drop; rt = skb_rtable(skb); if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->u.dst) && !skb_is_gso(skb) && (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { IP_INC_STATS(dev_net(rt->u.dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(dst_mtu(&rt->u.dst))); goto drop; } /* We are about to mangle packet. Copy it! */ if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len)) goto drop; iph = ip_hdr(skb); /* Decrease ttl after skb cow done */ ip_decrease_ttl(iph); /* * We now generate an ICMP HOST REDIRECT giving the route * we calculated. */ if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb)) ip_rt_send_redirect(skb); skb->priority = rt_tos2priority(iph->tos); return NF_HOOK(PF_INET, NF_INET_FORWARD, skb, skb->dev, rt->u.dst.dev, ip_forward_finish); sr_failed: /* * Strict routing permits no gatewaying */ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0); goto drop; too_many_hops: /* Tell the sender its packet died... */ IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS); icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); drop: kfree_skb(skb); return NET_RX_DROP; }
static int mpls_forward(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct net *net = dev_net(dev); struct mpls_shim_hdr *hdr; struct mpls_route *rt; struct mpls_entry_decoded dec; struct net_device *out_dev; struct mpls_dev *mdev; unsigned int hh_len; unsigned int new_header_size; unsigned int mtu; int err; /* Careful this entire function runs inside of an rcu critical section */ mdev = mpls_dev_get(dev); if (!mdev || !mdev->input_enabled) goto drop; if (skb->pkt_type != PACKET_HOST) goto drop; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) goto drop; if (!pskb_may_pull(skb, sizeof(*hdr))) goto drop; /* Read and decode the label */ hdr = mpls_hdr(skb); dec = mpls_entry_decode(hdr); /* Pop the label */ skb_pull(skb, sizeof(*hdr)); skb_reset_network_header(skb); skb_orphan(skb); rt = mpls_route_input_rcu(net, dec.label); if (!rt) goto drop; /* Find the output device */ out_dev = rcu_dereference(rt->rt_dev); if (!mpls_output_possible(out_dev)) goto drop; if (skb_warn_if_lro(skb)) goto drop; skb_forward_csum(skb); /* Verify ttl is valid */ if (dec.ttl <= 1) goto drop; dec.ttl -= 1; /* Verify the destination can hold the packet */ new_header_size = mpls_rt_header_size(rt); mtu = mpls_dev_mtu(out_dev); if (mpls_pkt_too_big(skb, mtu - new_header_size)) goto drop; hh_len = LL_RESERVED_SPACE(out_dev); if (!out_dev->header_ops) hh_len = 0; /* Ensure there is enough space for the headers in the skb */ if (skb_cow(skb, hh_len + new_header_size)) goto drop; skb->dev = out_dev; skb->protocol = htons(ETH_P_MPLS_UC); if (unlikely(!new_header_size && dec.bos)) { /* Penultimate hop popping */ if (!mpls_egress(rt, skb, dec)) goto drop; } else { bool bos; int i; skb_push(skb, new_header_size); skb_reset_network_header(skb); /* Push the new labels */ hdr = mpls_hdr(skb); bos = dec.bos; for (i = rt->rt_labels - 1; i >= 0; i--) { hdr[i] = mpls_entry_encode(rt->rt_label[i], dec.ttl, 0, bos); bos = false; } } err = neigh_xmit(rt->rt_via_table, out_dev, rt->rt_via, skb); if (err) net_dbg_ratelimited("%s: packet transmission failed: %d\n", __func__, err); return 0; drop: kfree_skb(skb); return NET_RX_DROP; }