static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, netdev_features_t features), __be16 new_protocol, bool is_ipv6) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); bool remcsum, need_csum, offload_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); struct udphdr *uh = udp_hdr(skb); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int udp_offset, outer_hlen; __wsum partial; bool need_ipsec; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; /* Adjust partial header checksum to negate old length. * We cannot rely on the value contained in uh->len as it is * possible that the actual value exceeds the boundaries of the * 16 bit length field due to the header being added outside of an * IP or IPv6 frame that was already limited to 64K - 1. */ if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) partial = (__force __wsum)uh->len; else partial = (__force __wsum)htonl(skb->len); partial = csum_sub(csum_unfold(uh->check), partial); /* setup inner skb. */ skb->encapsulation = 0; SKB_GSO_CB(skb)->encap_level = 0; __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); skb->mac_len = skb_inner_network_offset(skb); skb->protocol = new_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); skb->encap_hdr_csum = need_csum; remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && (skb->dev->features & (is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) : (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)))); features &= skb->dev->hw_enc_features; /* The only checksum offload we care about from here on out is the * outer one so strip the existing checksum feature flags and * instead set the flag based on our outer checksum offload value. */ if (remcsum) { features &= ~NETIF_F_CSUM_MASK; if (!need_csum || offload_csum) features |= NETIF_F_HW_CSUM; } /* segment inner packet. */ segs = gso_inner_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, mac_len); goto out; } gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); outer_hlen = skb_tnl_header_len(skb); udp_offset = outer_hlen - tnl_hlen; skb = segs; do { unsigned int len; if (remcsum) skb->ip_summed = CHECKSUM_NONE; /* Set up inner headers if we are offloading inner checksum */ if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_reset_inner_headers(skb); skb->encapsulation = 1; } skb->mac_len = mac_len; skb->protocol = protocol; __skb_push(skb, outer_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_set_transport_header(skb, udp_offset); len = skb->len - udp_offset; uh = udp_hdr(skb); /* If we are only performing partial GSO the inner header * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ if (gso_partial && skb_is_gso(skb)) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); } else { uh->len = htons(len); } if (!need_csum) continue; uh->check = ~csum_fold(csum_add(partial, (__force __wsum)htonl(len))); if (skb->encapsulation || !offload_csum) { uh->check = gso_make_checksum(skb, ~uh->check); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); } } while ((skb = skb->next)); out: return segs; }
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, struct ipcm6_cookie *ipc6, const struct sockcm_cookie *sockc) { 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; unsigned int maxnonfragsize, headersize; 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); 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 (cork->length + length > mtu - headersize && ipc6->dontfrag && (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_RAW)) { ipv6_local_rxpmtu(sk, fl6, mtu - headersize + sizeof(struct ipv6hdr)); goto emsgsize; } if (ip6_sk_ignore_df(sk)) maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN; else maxnonfragsize = mtu; if (cork->length + length > maxnonfragsize - headersize) { emsgsize: ipv6_local_error(sk, EMSGSIZE, fl6, mtu - headersize + sizeof(struct ipv6hdr)); return -EMSGSIZE; } /* CHECKSUM_PARTIAL only with no extension headers and when * we are not going to fragment */ if (transhdrlen && sk->sk_protocol == IPPROTO_UDP && headersize == sizeof(struct ipv6hdr) && length <= mtu - headersize && !(flags & MSG_MORE) && rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) { sock_tx_timestamp(sk, sockc->tsflags, &tx_flags); if (tx_flags & SKBTX_ANY_SW_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) tskey = sk->sk_tskey++; } /* * 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 + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, exthdrlen, transhdrlen, mtu, flags, fl6); 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 || !skb_prev) 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)) err = -ENOBUFS; } if (!skb) 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; if ((flags & MSG_CONFIRM) && !skb_prev) skb_set_dst_pending_confirm(skb, 1); /* * 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; }