diff options
Diffstat (limited to 'net/ipv4')
35 files changed, 955 insertions, 435 deletions
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index f8c49ce..f032688 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -55,4 +55,4 @@ obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ - xfrm4_output.o + xfrm4_output.o xfrm4_protocol.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ecd2c3f..8c54870 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1296,8 +1296,11 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); - /* Note : following gso_segment() might change skb->encapsulation */ - udpfrag = !skb->encapsulation && proto == IPPROTO_UDP; + if (skb->encapsulation && + skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP)) + udpfrag = proto == IPPROTO_UDP && encap; + else + udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) @@ -1502,9 +1505,9 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset) bhptr = per_cpu_ptr(mib[0], cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { - start = u64_stats_fetch_begin_bh(syncp); + start = u64_stats_fetch_begin_irq(syncp); v = *(((u64 *) bhptr) + offt); - } while (u64_stats_fetch_retry_bh(syncp, start)); + } while (u64_stats_fetch_retry_irq(syncp, start)); res += v; } diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 7179026..a2afa89 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -155,6 +155,10 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) struct iphdr *iph, *top_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; ahp = x->data; ahash = ahp->ahash; @@ -167,14 +171,19 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah = ip_auth_hdr(skb); ihl = ip_hdrlen(skb); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } err = -ENOMEM; - iph = ah_alloc_tmp(ahash, nfrags, ihl); + iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + seqhi_len); if (!iph) goto out; - - icv = ah_tmp_icv(ahash, iph, ihl); + seqhi = (__be32 *)((char *)iph + ihl); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memset(ah->auth_data, 0, ahp->icv_trunc_len); @@ -210,10 +219,15 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah_output_done, skb); AH_SKB_CB(skb)->tmp = iph; @@ -295,6 +309,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) struct ip_auth_hdr *ah; struct ah_data *ahp; int err = -ENOMEM; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; if (!pskb_may_pull(skb, sizeof(*ah))) goto out; @@ -335,14 +353,22 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) iph = ip_hdr(skb); ihl = ip_hdrlen(skb); - work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } + + work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + + ahp->icv_trunc_len + seqhi_len); if (!work_iph) goto out; - auth_data = ah_tmp_auth(work_iph, ihl); + seqhi = (__be32 *)((char *)work_iph + ihl); + auth_data = ah_tmp_auth(seqhi, seqhi_len); icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memcpy(work_iph, iph, ihl); memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); @@ -361,10 +387,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, ihl); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah_input_done, skb); AH_SKB_CB(skb)->tmp = work_iph; @@ -397,7 +428,7 @@ out: return err; } -static void ah4_err(struct sk_buff *skb, u32 info) +static int ah4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; @@ -407,23 +438,25 @@ static void ah4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0); xfrm_state_put(x); + + return 0; } static int ah_init_state(struct xfrm_state *x) @@ -505,6 +538,10 @@ static void ah_destroy(struct xfrm_state *x) kfree(ahp); } +static int ah4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} static const struct xfrm_type ah_type = { @@ -518,11 +555,12 @@ static const struct xfrm_type ah_type = .output = ah_output }; -static const struct net_protocol ah4_protocol = { +static struct xfrm4_protocol ah4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = ah4_rcv_cb, .err_handler = ah4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init ah4_init(void) @@ -531,7 +569,7 @@ static int __init ah4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&ah4_protocol, IPPROTO_AH) < 0) { + if (xfrm4_protocol_register(&ah4_protocol, IPPROTO_AH) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ah_type, AF_INET); return -EAGAIN; @@ -541,7 +579,7 @@ static int __init ah4_init(void) static void __exit ah4_fini(void) { - if (inet_del_protocol(&ah4_protocol, IPPROTO_AH) < 0) + if (xfrm4_protocol_deregister(&ah4_protocol, IPPROTO_AH) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ah_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 7785b28..360b565 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -473,7 +473,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu) net_adj) & ~(blksize - 1)) + net_adj - 2; } -static void esp4_err(struct sk_buff *skb, u32 info) +static int esp4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; @@ -483,23 +483,25 @@ static void esp4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0); xfrm_state_put(x); + + return 0; } static void esp_destroy(struct xfrm_state *x) @@ -672,6 +674,11 @@ error: return err; } +static int esp4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type esp_type = { .description = "ESP4", @@ -685,11 +692,12 @@ static const struct xfrm_type esp_type = .output = esp_output }; -static const struct net_protocol esp4_protocol = { +static struct xfrm4_protocol esp4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = esp4_rcv_cb, .err_handler = esp4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init esp4_init(void) @@ -698,7 +706,7 @@ static int __init esp4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&esp4_protocol, IPPROTO_ESP) < 0) { + if (xfrm4_protocol_register(&esp4_protocol, IPPROTO_ESP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&esp_type, AF_INET); return -EAGAIN; @@ -708,7 +716,7 @@ static int __init esp4_init(void) static void __exit esp4_fini(void) { - if (inet_del_protocol(&esp4_protocol, IPPROTO_ESP) < 0) + if (xfrm4_protocol_deregister(&esp4_protocol, IPPROTO_ESP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&esp_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index bb075fc..3b01959 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -208,7 +208,7 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force) } work = frag_mem_limit(nf) - nf->low_thresh; - while (work > 0) { + while (work > 0 || force) { spin_lock(&nf->lru_lock); if (list_empty(&nf->lru_list)) { @@ -278,9 +278,10 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, atomic_inc(&qp->refcnt); hlist_add_head(&qp->list, &hb->chain); + inet_frag_lru_add(nf, qp); spin_unlock(&hb->chain_lock); read_unlock(&f->lock); - inet_frag_lru_add(nf, qp); + return qp; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8971780..1a0755f 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -422,9 +422,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) to->ipvs_property = from->ipvs_property; #endif @@ -449,7 +446,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) __be16 not_last_frag; struct rtable *rt = skb_rtable(skb); int err = 0; - bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; dev = rt->dst.dev; @@ -459,7 +455,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) iph = ip_hdr(skb); - mtu = ip_dst_mtu_maybe_forward(&rt->dst, forwarding); + mtu = ip_skb_dst_mtu(skb); if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { @@ -825,8 +821,7 @@ static int __ip_append_data(struct sock *sk, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ? - mtu : 0xFFFF; + maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -1149,8 +1144,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ? - mtu : 0xFFFF; + maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu; if (cork->length + size > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -1311,8 +1305,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * to fragment the frame generated here. No matter, what transforms * how transforms change size of the packet, it will come out. */ - if (inet->pmtudisc < IP_PMTUDISC_DO) - skb->local_df = 1; + skb->local_df = ip_sk_local_df(sk); /* DF bit is set when we want to see DF on outgoing frames. * If local_df is set too, we still allow to fragment this frame diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 580dd96..64741b9 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -186,7 +186,8 @@ void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) } EXPORT_SYMBOL(ip_cmsg_recv); -int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) +int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, + bool allow_ipv6) { int err, val; struct cmsghdr *cmsg; @@ -194,6 +195,22 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; +#if defined(CONFIG_IPV6) + if (allow_ipv6 && + cmsg->cmsg_level == SOL_IPV6 && + cmsg->cmsg_type == IPV6_PKTINFO) { + struct in6_pktinfo *src_info; + + if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info))) + return -EINVAL; + src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); + if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) + return -EINVAL; + ipc->oif = src_info->ipi6_ifindex; + ipc->addr = src_info->ipi6_addr.s6_addr32[3]; + continue; + } +#endif if (cmsg->cmsg_level != SOL_IP) continue; switch (cmsg->cmsg_type) { @@ -626,7 +643,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, inet->nodefrag = val ? 1 : 0; break; case IP_MTU_DISCOVER: - if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_INTERFACE) + if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) goto e_inval; inet->pmtudisc = val; break; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 6d430ff..66aaf50 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -93,13 +93,14 @@ static void tunnel_dst_reset(struct ip_tunnel *t) tunnel_dst_set(t, NULL); } -static void tunnel_dst_reset_all(struct ip_tunnel *t) +void ip_tunnel_dst_reset_all(struct ip_tunnel *t) { int i; for_each_possible_cpu(i) __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); } +EXPORT_SYMBOL(ip_tunnel_dst_reset_all); static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) { @@ -119,52 +120,6 @@ static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) return (struct rtable *)dst; } -/* Often modified stats are per cpu, other are shared (netdev->stats) */ -struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *tot) -{ - int i; - - for_each_possible_cpu(i) { - const struct pcpu_sw_netstats *tstats = - per_cpu_ptr(dev->tstats, i); - u64 rx_packets, rx_bytes, tx_packets, tx_bytes; - unsigned int start; - - do { - start = u64_stats_fetch_begin_bh(&tstats->syncp); - rx_packets = tstats->rx_packets; - tx_packets = tstats->tx_packets; - rx_bytes = tstats->rx_bytes; - tx_bytes = tstats->tx_bytes; - } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); - - tot->rx_packets += rx_packets; - tot->tx_packets += tx_packets; - tot->rx_bytes += rx_bytes; - tot->tx_bytes += tx_bytes; - } - - tot->multicast = dev->stats.multicast; - - tot->rx_crc_errors = dev->stats.rx_crc_errors; - tot->rx_fifo_errors = dev->stats.rx_fifo_errors; - tot->rx_length_errors = dev->stats.rx_length_errors; - tot->rx_frame_errors = dev->stats.rx_frame_errors; - tot->rx_errors = dev->stats.rx_errors; - - tot->tx_fifo_errors = dev->stats.tx_fifo_errors; - tot->tx_carrier_errors = dev->stats.tx_carrier_errors; - tot->tx_dropped = dev->stats.tx_dropped; - tot->tx_aborted_errors = dev->stats.tx_aborted_errors; - tot->tx_errors = dev->stats.tx_errors; - - tot->collisions = dev->stats.collisions; - - return tot; -} -EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); - static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, __be16 flags, __be32 key) { @@ -280,13 +235,17 @@ static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, { unsigned int h; __be32 remote; + __be32 i_key = parms->i_key; if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr)) remote = parms->iph.daddr; else remote = 0; - h = ip_tunnel_hash(parms->i_key, remote); + if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI)) + i_key = 0; + + h = ip_tunnel_hash(i_key, remote); return &itn->tunnels[h]; } @@ -759,7 +718,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, if (set_mtu) dev->mtu = mtu; } - tunnel_dst_reset_all(t); + ip_tunnel_dst_reset_all(t); netdev_state_change(dev); } @@ -1087,7 +1046,7 @@ void ip_tunnel_uninit(struct net_device *dev) if (itn->fb_tunnel_dev != dev) ip_tunnel_del(netdev_priv(dev)); - tunnel_dst_reset_all(tunnel); + ip_tunnel_dst_reset_all(tunnel); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 6156f4e..b86f0a3 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -108,7 +108,6 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) nf_reset(skb); secpath_reset(skb); skb_clear_hash_if_not_l4(skb); - skb_dst_drop(skb); skb->vlan_tci = 0; skb_set_queue_mapping(skb, 0); skb->pkt_type = PACKET_HOST; @@ -148,3 +147,49 @@ error: return ERR_PTR(err); } EXPORT_SYMBOL_GPL(iptunnel_handle_offloads); + +/* Often modified stats are per cpu, other are shared (netdev->stats) */ +struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) +{ + int i; + + for_each_possible_cpu(i) { + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_irq(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; + } + + tot->multicast = dev->stats.multicast; + + tot->rx_crc_errors = dev->stats.rx_crc_errors; + tot->rx_fifo_errors = dev->stats.rx_fifo_errors; + tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_frame_errors = dev->stats.rx_frame_errors; + tot->rx_errors = dev->stats.rx_errors; + + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + + tot->collisions = dev->stats.collisions; + + return tot; +} +EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 48eafae..687ddef 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -34,6 +34,7 @@ #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> +#include <linux/icmpv6.h> #include <net/sock.h> #include <net/ip.h> @@ -49,8 +50,8 @@ static struct rtnl_link_ops vti_link_ops __read_mostly; static int vti_net_id __read_mostly; static int vti_tunnel_init(struct net_device *dev); -/* We dont digest the packet therefore let the packet pass */ -static int vti_rcv(struct sk_buff *skb) +static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) { struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); @@ -60,79 +61,120 @@ static int vti_rcv(struct sk_buff *skb) tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); if (tunnel != NULL) { - struct pcpu_sw_netstats *tstats; - u32 oldmark = skb->mark; - int ret; - - - /* temporarily mark the skb with the tunnel o_key, to - * only match policies with this mark. - */ - skb->mark = be32_to_cpu(tunnel->parms.o_key); - ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb); - skb->mark = oldmark; - if (!ret) - return -1; - - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); - - secpath_reset(skb); - skb->dev = tunnel->dev; + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; + skb->mark = be32_to_cpu(tunnel->parms.i_key); + + return xfrm_input(skb, nexthdr, spi, encap_type); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; +} + +static int vti_rcv(struct sk_buff *skb) +{ + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + return vti_input(skb, ip_hdr(skb)->protocol, 0, 0); +} + +static int vti_rcv_cb(struct sk_buff *skb, int err) +{ + unsigned short family; + struct net_device *dev; + struct pcpu_sw_netstats *tstats; + struct xfrm_state *x; + struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; + + if (!tunnel) return 1; + + dev = tunnel->dev; + + if (err) { + dev->stats.rx_errors++; + dev->stats.rx_dropped++; + + return 0; } - return -1; + x = xfrm_input_state(skb); + family = x->inner_mode->afinfo->family; + + if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + return -EPERM; + + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev))); + skb->dev = dev; + + tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + return 0; } -/* This function assumes it is being called from dev_queue_xmit() - * and that skb is filled properly by that function. - */ +static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src) +{ + xfrm_address_t *daddr = (xfrm_address_t *)&dst; + xfrm_address_t *saddr = (xfrm_address_t *)&src; -static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) + /* if there is no transform then this tunnel is not functional. + * Or if the xfrm is not mode tunnel. + */ + if (!x || x->props.mode != XFRM_MODE_TUNNEL || + x->props.family != AF_INET) + return false; + + if (!dst) + return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET); + + if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET)) + return false; + + return true; +} + +static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, + struct flowi *fl) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct iphdr *tiph = &tunnel->parms.iph; - u8 tos; - struct rtable *rt; /* Route to the other host */ + struct ip_tunnel_parm *parms = &tunnel->parms; + struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ - struct iphdr *old_iph = ip_hdr(skb); - __be32 dst = tiph->daddr; - struct flowi4 fl4; int err; - if (skb->protocol != htons(ETH_P_IP)) - goto tx_error; - - tos = old_iph->tos; + if (!dst) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } - memset(&fl4, 0, sizeof(fl4)); - flowi4_init_output(&fl4, tunnel->parms.link, - be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos), - RT_SCOPE_UNIVERSE, - IPPROTO_IPIP, 0, - dst, tiph->saddr, 0, 0); - rt = ip_route_output_key(dev_net(dev), &fl4); - if (IS_ERR(rt)) { + dst_hold(dst); + dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0); + if (IS_ERR(dst)) { dev->stats.tx_carrier_errors++; goto tx_error_icmp; } - /* if there is no transform then this tunnel is not functional. - * Or if the xfrm is not mode tunnel. - */ - if (!rt->dst.xfrm || - rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) { + + if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { dev->stats.tx_carrier_errors++; - ip_rt_put(rt); + dst_release(dst); goto tx_error_icmp; } - tdev = rt->dst.dev; + + tdev = dst->dev; if (tdev == dev) { - ip_rt_put(rt); + dst_release(dst); dev->stats.collisions++; goto tx_error; } @@ -146,10 +188,8 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) tunnel->err_count = 0; } - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - nf_reset(skb); + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); + skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; err = dst_output(skb); @@ -166,6 +206,95 @@ tx_error: return NETDEV_TX_OK; } +/* This function assumes it is being called from dev_queue_xmit() + * and that skb is filled properly by that function. + */ +static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct flowi fl; + + memset(&fl, 0, sizeof(fl)); + + skb->mark = be32_to_cpu(tunnel->parms.o_key); + + switch (skb->protocol) { + case htons(ETH_P_IP): + xfrm_decode_session(skb, &fl, AF_INET); + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + break; + case htons(ETH_P_IPV6): + xfrm_decode_session(skb, &fl, AF_INET6); + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + break; + default: + dev->stats.tx_errors++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + + return vti_xmit(skb, dev, &fl); +} + +static int vti4_err(struct sk_buff *skb, u32 info) +{ + __be32 spi; + struct xfrm_state *x; + struct ip_tunnel *tunnel; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah ; + struct ip_comp_hdr *ipch; + struct net *net = dev_net(skb->dev); + const struct iphdr *iph = (const struct iphdr *)skb->data; + int protocol = iph->protocol; + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->daddr, iph->saddr, 0); + if (!tunnel) + return -1; + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return 0; + case ICMP_REDIRECT: + break; + default: + return 0; + } + + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET); + if (!x) + return 0; + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0); + else + ipv4_redirect(skb, net, 0, 0, protocol, 0); + xfrm_state_put(x); + + return 0; +} + static int vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -181,12 +310,13 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EINVAL; } + p.i_flags |= VTI_ISVTI; err = ip_tunnel_ioctl(dev, &p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { - p.i_flags |= GRE_KEY | VTI_ISVTI; + p.i_flags |= GRE_KEY; p.o_flags |= GRE_KEY; } @@ -224,7 +354,6 @@ static int vti_tunnel_init(struct net_device *dev) dev->flags = IFF_NOARP; dev->iflink = 0; dev->addr_len = 4; - dev->features |= NETIF_F_NETNS_LOCAL; dev->features |= NETIF_F_LLTX; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; @@ -241,9 +370,28 @@ static void __net_init vti_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; } -static struct xfrm_tunnel_notifier vti_handler __read_mostly = { +static struct xfrm4_protocol vti_esp4_protocol __read_mostly = { .handler = vti_rcv, - .priority = 1, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, +}; + +static struct xfrm4_protocol vti_ah4_protocol __read_mostly = { + .handler = vti_rcv, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, +}; + +static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { + .handler = vti_rcv, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, }; static int __net_init vti_init_net(struct net *net) @@ -287,6 +435,8 @@ static void vti_netlink_parms(struct nlattr *data[], if (!data) return; + parms->i_flags = VTI_ISVTI; + if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); @@ -382,10 +532,31 @@ static int __init vti_init(void) err = register_pernet_device(&vti_net_ops); if (err < 0) return err; - err = xfrm4_mode_tunnel_input_register(&vti_handler); + err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP); + if (err < 0) { + unregister_pernet_device(&vti_net_ops); + pr_info("vti init: can't register tunnel\n"); + + return err; + } + + err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH); + if (err < 0) { + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); + unregister_pernet_device(&vti_net_ops); + pr_info("vti init: can't register tunnel\n"); + + return err; + } + + err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP); if (err < 0) { + xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); pr_info("vti init: can't register tunnel\n"); + + return err; } err = rtnl_link_register(&vti_link_ops); @@ -395,7 +566,9 @@ static int __init vti_init(void) return err; rtnl_link_failed: - xfrm4_mode_tunnel_input_deregister(&vti_handler); + xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); + xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); return err; } @@ -403,8 +576,13 @@ rtnl_link_failed: static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); - if (xfrm4_mode_tunnel_input_deregister(&vti_handler)) + if (xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP)) pr_info("vti close: can't deregister tunnel\n"); + if (xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH)) + pr_info("vti close: can't deregister tunnel\n"); + if (xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP)) + pr_info("vti close: can't deregister tunnel\n"); + unregister_pernet_device(&vti_net_ops); } diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 826be4c..c0855d5 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -23,7 +23,7 @@ #include <net/protocol.h> #include <net/sock.h> -static void ipcomp4_err(struct sk_buff *skb, u32 info) +static int ipcomp4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); __be32 spi; @@ -34,24 +34,26 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } spi = htonl(ntohs(ipch->cpi)); x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0); xfrm_state_put(x); + + return 0; } /* We always hold one tunnel user reference to indicate a tunnel */ @@ -147,6 +149,11 @@ out: return err; } +static int ipcomp4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type ipcomp_type = { .description = "IPCOMP4", .owner = THIS_MODULE, @@ -157,11 +164,12 @@ static const struct xfrm_type ipcomp_type = { .output = ipcomp_output }; -static const struct net_protocol ipcomp4_protocol = { +static struct xfrm4_protocol ipcomp4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = ipcomp4_rcv_cb, .err_handler = ipcomp4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init ipcomp4_init(void) @@ -170,7 +178,7 @@ static int __init ipcomp4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) { + if (xfrm4_protocol_register(&ipcomp4_protocol, IPPROTO_COMP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ipcomp_type, AF_INET); return -EAGAIN; @@ -180,7 +188,7 @@ static int __init ipcomp4_init(void) static void __exit ipcomp4_fini(void) { - if (inet_del_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) + if (xfrm4_protocol_deregister(&ipcomp4_protocol, IPPROTO_COMP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ipcomp_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index d551e31..7c67667 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1198,8 +1198,8 @@ static int snmp_translate(struct nf_conn *ct, map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); } else { /* DNAT replies */ - map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip); - map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); + map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip); + map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip); } if (map.from == map.to) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 2d11c09..f4b19e5 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -727,7 +727,7 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m sock_tx_timestamp(sk, &ipc.tx_flags); if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); if (err) return err; if (ipc.opt) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index a6c8a80..ad737fa 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -273,6 +273,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK), SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE), SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE), + SNMP_MIB_ITEM("TCPFastOpenActiveFail", LINUX_MIB_TCPFASTOPENACTIVEFAIL), SNMP_MIB_ITEM("TCPFastOpenPassive", LINUX_MIB_TCPFASTOPENPASSIVE), SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL), SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW), @@ -280,6 +281,11 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES), SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS), SNMP_MIB_ITEM("TCPAutoCorking", LINUX_MIB_TCPAUTOCORKING), + SNMP_MIB_ITEM("TCPFromZeroWindowAdv", LINUX_MIB_TCPFROMZEROWINDOWADV), + SNMP_MIB_ITEM("TCPToZeroWindowAdv", LINUX_MIB_TCPTOZEROWINDOWADV), + SNMP_MIB_ITEM("TCPWantZeroWindowAdv", LINUX_MIB_TCPWANTZEROWINDOWADV), + SNMP_MIB_ITEM("TCPSynRetrans", LINUX_MIB_TCPSYNRETRANS), + SNMP_MIB_ITEM("TCPOrigDataSent", LINUX_MIB_TCPORIGDATASENT), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index c04518f..a9dbe58 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -524,7 +524,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); if (err) goto out; if (ipc.opt) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bed379c..4bd6d52 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -387,7 +387,7 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsq_node); icsk->icsk_rto = TCP_TIMEOUT_INIT; - tp->mdev = TCP_TIMEOUT_INIT; + tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -1044,7 +1044,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp) } } -static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) +static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, + int *copied, size_t size) { struct tcp_sock *tp = tcp_sk(sk); int err, flags; @@ -1059,11 +1060,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) if (unlikely(tp->fastopen_req == NULL)) return -ENOBUFS; tp->fastopen_req->data = msg; + tp->fastopen_req->size = size; flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, flags); - *size = tp->fastopen_req->copied; + *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); return err; } @@ -1083,7 +1085,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flags = msg->msg_flags; if (flags & MSG_FASTOPEN) { - err = tcp_sendmsg_fastopen(sk, msg, &copied_syn); + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) @@ -2339,7 +2341,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); - tp->srtt = 0; + tp->srtt_us = 0; if ((tp->write_seq += tp->max_window + 2) == 0) tp->write_seq = 1; icsk->icsk_backoff = 0; @@ -2783,8 +2785,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) info->tcpi_pmtu = icsk->icsk_pmtu_cookie; info->tcpi_rcv_ssthresh = tp->rcv_ssthresh; - info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3; - info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2; + info->tcpi_rtt = tp->srtt_us >> 3; + info->tcpi_rttvar = tp->mdev_us >> 2; info->tcpi_snd_ssthresh = tp->snd_ssthresh; info->tcpi_snd_cwnd = tp->snd_cwnd; info->tcpi_advmss = tp->advmss; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index f49351e..2b9464c 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -290,8 +290,7 @@ bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) left = tp->snd_cwnd - in_flight; if (sk_can_gso(sk) && left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd && - left * tp->mss_cache < sk->sk_gso_max_size && - left < sk->sk_gso_max_segs) + left < tp->xmit_size_goal_segs) return true; return left <= tcp_max_tso_deferred_mss(tp); } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 828e4c3..8bf2245 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -476,10 +476,6 @@ static int __init cubictcp_register(void) /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); - /* hystart needs ms clock resolution */ - if (hystart && HZ < 1000) - cubictcp.flags |= TCP_CONG_RTT_STAMP; - return tcp_register_congestion_control(&cubictcp); } diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index 2a1a9e2..a15a799 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -21,7 +21,7 @@ struct hybla { u32 rho2; /* Rho * Rho, integer part */ u32 rho_3ls; /* Rho parameter, <<3 */ u32 rho2_7ls; /* Rho^2, <<7 */ - u32 minrtt; /* Minimum smoothed round trip time value seen */ + u32 minrtt_us; /* Minimum smoothed round trip time value seen */ }; /* Hybla reference round trip time (default= 1/40 sec = 25 ms), in ms */ @@ -35,7 +35,9 @@ static inline void hybla_recalc_param (struct sock *sk) { struct hybla *ca = inet_csk_ca(sk); - ca->rho_3ls = max_t(u32, tcp_sk(sk)->srtt / msecs_to_jiffies(rtt0), 8); + ca->rho_3ls = max_t(u32, + tcp_sk(sk)->srtt_us / (rtt0 * USEC_PER_MSEC), + 8U); ca->rho = ca->rho_3ls >> 3; ca->rho2_7ls = (ca->rho_3ls * ca->rho_3ls) << 1; ca->rho2 = ca->rho2_7ls >> 7; @@ -59,7 +61,7 @@ static void hybla_init(struct sock *sk) hybla_recalc_param(sk); /* set minimum rtt as this is the 1st ever seen */ - ca->minrtt = tp->srtt; + ca->minrtt_us = tp->srtt_us; tp->snd_cwnd = ca->rho; } @@ -94,9 +96,9 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked, int is_slowstart = 0; /* Recalculate rho only if this srtt is the lowest */ - if (tp->srtt < ca->minrtt){ + if (tp->srtt_us < ca->minrtt_us) { hybla_recalc_param(sk); - ca->minrtt = tp->srtt; + ca->minrtt_us = tp->srtt_us; } if (!tcp_is_cwnd_limited(sk, in_flight)) diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index be047c6..863d105 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -325,7 +325,6 @@ static void tcp_illinois_info(struct sock *sk, u32 ext, } static struct tcp_congestion_ops tcp_illinois __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_illinois_init, .ssthresh = tcp_illinois_ssthresh, .cong_avoid = tcp_illinois_cong_avoid, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 227cba7..e1661f4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -667,11 +667,11 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) * To save cycles in the RFC 1323 implementation it was better to break * it up into three procedures. -- erics */ -static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) +static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) { struct tcp_sock *tp = tcp_sk(sk); - long m = mrtt; /* RTT */ - u32 srtt = tp->srtt; + long m = mrtt_us; /* RTT */ + u32 srtt = tp->srtt_us; /* The following amusing code comes from Jacobson's * article in SIGCOMM '88. Note that rtt and mdev @@ -694,7 +694,7 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) { m = -m; /* m is now abs(error) */ - m -= (tp->mdev >> 2); /* similar update on mdev */ + m -= (tp->mdev_us >> 2); /* similar update on mdev */ /* This is similar to one of Eifel findings. * Eifel blocks mdev updates when rtt decreases. * This solution is a bit different: we use finer gain @@ -706,28 +706,29 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) if (m > 0) m >>= 3; } else { - m -= (tp->mdev >> 2); /* similar update on mdev */ + m -= (tp->mdev_us >> 2); /* similar update on mdev */ } - tp->mdev += m; /* mdev = 3/4 mdev + 1/4 new */ - if (tp->mdev > tp->mdev_max) { - tp->mdev_max = tp->mdev; - if (tp->mdev_max > tp->rttvar) - tp->rttvar = tp->mdev_max; + tp->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ + if (tp->mdev_us > tp->mdev_max_us) { + tp->mdev_max_us = tp->mdev_us; + if (tp->mdev_max_us > tp->rttvar_us) + tp->rttvar_us = tp->mdev_max_us; } if (after(tp->snd_una, tp->rtt_seq)) { - if (tp->mdev_max < tp->rttvar) - tp->rttvar -= (tp->rttvar - tp->mdev_max) >> 2; + if (tp->mdev_max_us < tp->rttvar_us) + tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2; tp->rtt_seq = tp->snd_nxt; - tp->mdev_max = tcp_rto_min(sk); + tp->mdev_max_us = tcp_rto_min_us(sk); } } else { /* no previous measure. */ srtt = m << 3; /* take the measured time to be rtt */ - tp->mdev = m << 1; /* make sure rto = 3*rtt */ - tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); + tp->mdev_us = m << 1; /* make sure rto = 3*rtt */ + tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk)); + tp->mdev_max_us = tp->rttvar_us; tp->rtt_seq = tp->snd_nxt; } - tp->srtt = max(1U, srtt); + tp->srtt_us = max(1U, srtt); } /* Set the sk_pacing_rate to allow proper sizing of TSO packets. @@ -742,20 +743,12 @@ static void tcp_update_pacing_rate(struct sock *sk) u64 rate; /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */ - rate = (u64)tp->mss_cache * 2 * (HZ << 3); + rate = (u64)tp->mss_cache * 2 * (USEC_PER_SEC << 3); rate *= max(tp->snd_cwnd, tp->packets_out); - /* Correction for small srtt and scheduling constraints. - * For small rtt, consider noise is too high, and use - * the minimal value (srtt = 1 -> 125 us for HZ=1000) - * - * We probably need usec resolution in the future. - * Note: This also takes care of possible srtt=0 case, - * when tcp_rtt_estimator() was not yet called. - */ - if (tp->srtt > 8 + 2) - do_div(rate, tp->srtt); + if (likely(tp->srtt_us)) + do_div(rate, tp->srtt_us); /* ACCESS_ONCE() is needed because sch_fq fetches sk_pacing_rate * without any lock. We want to make sure compiler wont store @@ -1122,10 +1115,10 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, } struct tcp_sacktag_state { - int reord; - int fack_count; - int flag; - s32 rtt; /* RTT measured by SACKing never-retransmitted data */ + int reord; + int fack_count; + long rtt_us; /* RTT measured by SACKing never-retransmitted data */ + int flag; }; /* Check if skb is fully within the SACK block. In presence of GSO skbs, @@ -1186,7 +1179,8 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, - int dup_sack, int pcount, u32 xmit_time) + int dup_sack, int pcount, + const struct skb_mstamp *xmit_time) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; @@ -1227,8 +1221,13 @@ static u8 tcp_sacktag_one(struct sock *sk, if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; /* Pick the earliest sequence sacked for RTT */ - if (state->rtt < 0) - state->rtt = tcp_time_stamp - xmit_time; + if (state->rtt_us < 0) { + struct skb_mstamp now; + + skb_mstamp_get(&now); + state->rtt_us = skb_mstamp_us_delta(&now, + xmit_time); + } } if (sacked & TCPCB_LOST) { @@ -1287,7 +1286,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, - TCP_SKB_CB(skb)->when); + &skb->skb_mstamp); if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; @@ -1565,7 +1564,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->end_seq, dup_sack, tcp_skb_pcount(skb), - TCP_SKB_CB(skb)->when); + &skb->skb_mstamp); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -1622,7 +1621,7 @@ static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_bl static int tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, - u32 prior_snd_una, s32 *sack_rtt) + u32 prior_snd_una, long *sack_rtt_us) { struct tcp_sock *tp = tcp_sk(sk); const unsigned char *ptr = (skb_transport_header(ack_skb) + @@ -1640,7 +1639,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, state.flag = 0; state.reord = tp->packets_out; - state.rtt = -1; + state.rtt_us = -1L; if (!tp->sacked_out) { if (WARN_ON(tp->fackets_out)) @@ -1824,7 +1823,7 @@ out: WARN_ON((int)tp->retrans_out < 0); WARN_ON((int)tcp_packets_in_flight(tp) < 0); #endif - *sack_rtt = state.rtt; + *sack_rtt_us = state.rtt_us; return state.flag; } @@ -1945,8 +1944,9 @@ void tcp_enter_loss(struct sock *sk, int how) if (skb == tcp_send_head(sk)) break; - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) tp->undo_marker = 0; + TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; @@ -2034,10 +2034,12 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag) * available, or RTO is scheduled to fire first. */ if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 || - (flag & FLAG_ECE) || !tp->srtt) + (flag & FLAG_ECE) || !tp->srtt_us) return false; - delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2)); + delay = max(usecs_to_jiffies(tp->srtt_us >> 5), + msecs_to_jiffies(2)); + if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay))) return false; @@ -2884,7 +2886,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, } static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, - s32 seq_rtt, s32 sack_rtt) + long seq_rtt_us, long sack_rtt_us) { const struct tcp_sock *tp = tcp_sk(sk); @@ -2894,10 +2896,10 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * is acked (RFC6298). */ if (flag & FLAG_RETRANS_DATA_ACKED) - seq_rtt = -1; + seq_rtt_us = -1L; - if (seq_rtt < 0) - seq_rtt = sack_rtt; + if (seq_rtt_us < 0) + seq_rtt_us = sack_rtt_us; /* RTTM Rule: A TSecr value received in a segment is used to * update the averaged RTT measurement only if the segment @@ -2905,14 +2907,14 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * left edge of the send window. * See draft-ietf-tcplw-high-performance-00, section 3.3. */ - if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && + if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) - seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr; + seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - tp->rx_opt.rcv_tsecr); - if (seq_rtt < 0) + if (seq_rtt_us < 0) return false; - tcp_rtt_estimator(sk, seq_rtt); + tcp_rtt_estimator(sk, seq_rtt_us); tcp_set_rto(sk); /* RFC6298: only reset backoff on valid RTT measurement. */ @@ -2924,16 +2926,16 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp) { struct tcp_sock *tp = tcp_sk(sk); - s32 seq_rtt = -1; + long seq_rtt_us = -1L; if (synack_stamp && !tp->total_retrans) - seq_rtt = tcp_time_stamp - synack_stamp; + seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - synack_stamp); /* If the ACK acks both the SYNACK and the (Fast Open'd) data packets * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack() */ - if (!tp->srtt) - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); + if (!tp->srtt_us) + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L); } static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight) @@ -3022,26 +3024,27 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) * arrived at the other end. */ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, - u32 prior_snd_una, s32 sack_rtt) + u32 prior_snd_una, long sack_rtt_us) { - struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - struct sk_buff *skb; - u32 now = tcp_time_stamp; + struct skb_mstamp first_ackt, last_ackt, now; + struct tcp_sock *tp = tcp_sk(sk); + u32 prior_sacked = tp->sacked_out; + u32 reord = tp->packets_out; bool fully_acked = true; - int flag = 0; + long ca_seq_rtt_us = -1L; + long seq_rtt_us = -1L; + struct sk_buff *skb; u32 pkts_acked = 0; - u32 reord = tp->packets_out; - u32 prior_sacked = tp->sacked_out; - s32 seq_rtt = -1; - s32 ca_seq_rtt = -1; - ktime_t last_ackt = net_invalid_timestamp(); bool rtt_update; + int flag = 0; + + first_ackt.v64 = 0; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); - u32 acked_pcount; u8 sacked = scb->sacked; + u32 acked_pcount; /* Determine how many packets and what bytes were acked, tso and else */ if (after(scb->end_seq, tp->snd_una)) { @@ -3063,11 +3066,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->retrans_out -= acked_pcount; flag |= FLAG_RETRANS_DATA_ACKED; } else { - ca_seq_rtt = now - scb->when; - last_ackt = skb->tstamp; - if (seq_rtt < 0) { - seq_rtt = ca_seq_rtt; - } + last_ackt = skb->skb_mstamp; + WARN_ON_ONCE(last_ackt.v64 == 0); + if (!first_ackt.v64) + first_ackt = last_ackt; + if (!(sacked & TCPCB_SACKED_ACKED)) reord = min(pkts_acked, reord); if (!after(scb->end_seq, tp->high_seq)) @@ -3113,7 +3116,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt); + skb_mstamp_get(&now); + if (first_ackt.v64) { + seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt); + ca_seq_rtt_us = skb_mstamp_us_delta(&now, &last_ackt); + } + + rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us); if (flag & FLAG_ACKED) { const struct tcp_congestion_ops *ca_ops @@ -3141,25 +3150,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); - if (ca_ops->pkts_acked) { - s32 rtt_us = -1; - - /* Is the ACK triggering packet unambiguous? */ - if (!(flag & FLAG_RETRANS_DATA_ACKED)) { - /* High resolution needed and available? */ - if (ca_ops->flags & TCP_CONG_RTT_STAMP && - !ktime_equal(last_ackt, - net_invalid_timestamp())) - rtt_us = ktime_us_delta(ktime_get_real(), - last_ackt); - else if (ca_seq_rtt >= 0) - rtt_us = jiffies_to_usecs(ca_seq_rtt); - } + if (ca_ops->pkts_acked) + ca_ops->pkts_acked(sk, pkts_acked, ca_seq_rtt_us); - ca_ops->pkts_acked(sk, pkts_acked, rtt_us); - } - } else if (skb && rtt_update && sack_rtt >= 0 && - sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) { + } else if (skb && rtt_update && sack_rtt_us >= 0 && + sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -3369,12 +3364,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; - u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt; + u32 prior_in_flight; u32 prior_fackets; int prior_packets = tp->packets_out; const int prior_unsacked = tp->packets_out - tp->sacked_out; int acked = 0; /* Number of packets newly acked */ - s32 sack_rtt = -1; + long sack_rtt_us = -1L; /* If the ack is older than previous acks * then we can probably ignore it. @@ -3432,7 +3427,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (TCP_SKB_CB(skb)->sacked) flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, - &sack_rtt); + &sack_rtt_us); if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb))) flag |= FLAG_ECE; @@ -3451,7 +3446,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ acked = tp->packets_out; - flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt); + flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, + sack_rtt_us); acked -= tp->packets_out; /* Advance cwnd if state allows */ @@ -3474,8 +3470,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (icsk->icsk_pending == ICSK_TIME_RETRANS) tcp_schedule_loss_probe(sk); - if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd) - tcp_update_pacing_rate(sk); + tcp_update_pacing_rate(sk); return 1; no_queue: @@ -3504,7 +3499,7 @@ old_ack: */ if (TCP_SKB_CB(skb)->sacked) { flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, - &sack_rtt); + &sack_rtt_us); tcp_fastretrans_alert(sk, acked, prior_unsacked, is_dupack, flag); } @@ -5400,9 +5395,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, break; } tcp_rearm_rto(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; } tp->syn_data_acked = tp->syn_data; + if (tp->syn_data_acked) + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); return false; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3cf9765..c4f1d9a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -435,7 +435,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) break; icsk->icsk_backoff--; - inet_csk(sk)->icsk_rto = (tp->srtt ? __tcp_set_rto(tp) : + inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT) << icsk->icsk_backoff; tcp_bound_rto(sk); @@ -854,8 +854,10 @@ static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req) { int res = tcp_v4_send_synack(sk, NULL, req, 0); - if (!res) + if (!res) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + } return res; } diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 503798f..c9aecae 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -315,7 +315,6 @@ static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, s32 rtt_us) } static struct tcp_congestion_ops tcp_lp __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_lp_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_lp_cong_avoid, diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index d547075..dcaf72f 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -33,6 +33,11 @@ struct tcp_fastopen_metrics { struct tcp_fastopen_cookie cookie; }; +/* TCP_METRIC_MAX includes 2 extra fields for userspace compatibility + * Kernel only stores RTT and RTTVAR in usec resolution + */ +#define TCP_METRIC_MAX_KERNEL (TCP_METRIC_MAX - 2) + struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; struct inetpeer_addr tcpm_saddr; @@ -41,7 +46,7 @@ struct tcp_metrics_block { u32 tcpm_ts; u32 tcpm_ts_stamp; u32 tcpm_lock; - u32 tcpm_vals[TCP_METRIC_MAX + 1]; + u32 tcpm_vals[TCP_METRIC_MAX_KERNEL + 1]; struct tcp_fastopen_metrics tcpm_fastopen; struct rcu_head rcu_head; @@ -59,12 +64,6 @@ static u32 tcp_metric_get(struct tcp_metrics_block *tm, return tm->tcpm_vals[idx]; } -static u32 tcp_metric_get_jiffies(struct tcp_metrics_block *tm, - enum tcp_metric_index idx) -{ - return msecs_to_jiffies(tm->tcpm_vals[idx]); -} - static void tcp_metric_set(struct tcp_metrics_block *tm, enum tcp_metric_index idx, u32 val) @@ -72,13 +71,6 @@ static void tcp_metric_set(struct tcp_metrics_block *tm, tm->tcpm_vals[idx] = val; } -static void tcp_metric_set_msecs(struct tcp_metrics_block *tm, - enum tcp_metric_index idx, - u32 val) -{ - tm->tcpm_vals[idx] = jiffies_to_msecs(val); -} - static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { @@ -101,9 +93,11 @@ struct tcpm_hash_bucket { static DEFINE_SPINLOCK(tcp_metrics_lock); -static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst, +static void tcpm_suck_dst(struct tcp_metrics_block *tm, + const struct dst_entry *dst, bool fastopen_clear) { + u32 msval; u32 val; tm->tcpm_stamp = jiffies; @@ -121,8 +115,11 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst, val |= 1 << TCP_METRIC_REORDERING; tm->tcpm_lock = val; - tm->tcpm_vals[TCP_METRIC_RTT] = dst_metric_raw(dst, RTAX_RTT); - tm->tcpm_vals[TCP_METRIC_RTTVAR] = dst_metric_raw(dst, RTAX_RTTVAR); + msval = dst_metric_raw(dst, RTAX_RTT); + tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC; + + msval = dst_metric_raw(dst, RTAX_RTTVAR); + tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC; tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); @@ -384,7 +381,7 @@ void tcp_update_metrics(struct sock *sk) dst_confirm(dst); rcu_read_lock(); - if (icsk->icsk_backoff || !tp->srtt) { + if (icsk->icsk_backoff || !tp->srtt_us) { /* This session failed to estimate rtt. Why? * Probably, no packets returned in time. Reset our * results. @@ -399,8 +396,8 @@ void tcp_update_metrics(struct sock *sk) if (!tm) goto out_unlock; - rtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT); - m = rtt - tp->srtt; + rtt = tcp_metric_get(tm, TCP_METRIC_RTT); + m = rtt - tp->srtt_us; /* If newly calculated rtt larger than stored one, store new * one. Otherwise, use EWMA. Remember, rtt overestimation is @@ -408,10 +405,10 @@ void tcp_update_metrics(struct sock *sk) */ if (!tcp_metric_locked(tm, TCP_METRIC_RTT)) { if (m <= 0) - rtt = tp->srtt; + rtt = tp->srtt_us; else rtt -= (m >> 3); - tcp_metric_set_msecs(tm, TCP_METRIC_RTT, rtt); + tcp_metric_set(tm, TCP_METRIC_RTT, rtt); } if (!tcp_metric_locked(tm, TCP_METRIC_RTTVAR)) { @@ -422,16 +419,16 @@ void tcp_update_metrics(struct sock *sk) /* Scale deviation to rttvar fixed point */ m >>= 1; - if (m < tp->mdev) - m = tp->mdev; + if (m < tp->mdev_us) + m = tp->mdev_us; - var = tcp_metric_get_jiffies(tm, TCP_METRIC_RTTVAR); + var = tcp_metric_get(tm, TCP_METRIC_RTTVAR); if (m >= var) var = m; else var -= (var - m) >> 2; - tcp_metric_set_msecs(tm, TCP_METRIC_RTTVAR, var); + tcp_metric_set(tm, TCP_METRIC_RTTVAR, var); } if (tcp_in_initial_slowstart(tp)) { @@ -528,7 +525,7 @@ void tcp_init_metrics(struct sock *sk) tp->reordering = val; } - crtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT); + crtt = tcp_metric_get(tm, TCP_METRIC_RTT); rcu_read_unlock(); reset: /* The initial RTT measurement from the SYN/SYN-ACK is not ideal @@ -551,18 +548,20 @@ reset: * to low value, and then abruptly stops to do it and starts to delay * ACKs, wait for troubles. */ - if (crtt > tp->srtt) { + if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt >>= 3; + crtt /= 8 * USEC_PER_MSEC; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); - } else if (tp->srtt == 0) { + } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from * 3WHS. This is most likely due to retransmission, * including spurious one. Reset the RTO back to 3secs * from the more aggressive 1sec to avoid more spurious * retransmission. */ - tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK; + tp->rttvar_us = jiffies_to_usecs(TCP_TIMEOUT_FALLBACK); + tp->mdev_us = tp->mdev_max_us = tp->rttvar_us; + inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK; } /* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been @@ -809,10 +808,26 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS); if (!nest) goto nla_put_failure; - for (i = 0; i < TCP_METRIC_MAX + 1; i++) { - if (!tm->tcpm_vals[i]) + for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) { + u32 val = tm->tcpm_vals[i]; + + if (!val) continue; - if (nla_put_u32(msg, i + 1, tm->tcpm_vals[i]) < 0) + if (i == TCP_METRIC_RTT) { + if (nla_put_u32(msg, TCP_METRIC_RTT_US + 1, + val) < 0) + goto nla_put_failure; + n++; + val = max(val / 1000, 1U); + } + if (i == TCP_METRIC_RTTVAR) { + if (nla_put_u32(msg, TCP_METRIC_RTTVAR_US + 1, + val) < 0) + goto nla_put_failure; + n++; + val = max(val / 1000, 1U); + } + if (nla_put_u32(msg, i + 1, val) < 0) goto nla_put_failure; n++; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7a436c5..ca788ad 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -398,8 +398,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, tcp_init_wl(newtp, treq->rcv_isn); - newtp->srtt = 0; - newtp->mdev = TCP_TIMEOUT_INIT; + newtp->srtt_us = 0; + newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); newicsk->icsk_rto = TCP_TIMEOUT_INIT; newtp->packets_out = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 48414fc..e0a7b33 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -86,6 +86,9 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { tcp_rearm_rto(sk); } + + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, + tcp_skb_pcount(skb)); } /* SND.NXT, if window was not shrunk. @@ -269,6 +272,7 @@ EXPORT_SYMBOL(tcp_select_initial_window); static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 old_win = tp->rcv_wnd; u32 cur_win = tcp_receive_window(tp); u32 new_win = __tcp_select_window(sk); @@ -281,6 +285,9 @@ static u16 tcp_select_window(struct sock *sk) * * Relax Will Robinson. */ + if (new_win == 0) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPWANTZEROWINDOWADV); new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } tp->rcv_wnd = new_win; @@ -298,8 +305,14 @@ static u16 tcp_select_window(struct sock *sk) new_win >>= tp->rx_opt.rcv_wscale; /* If we advertise zero window, disable fast path. */ - if (new_win == 0) + if (new_win == 0) { tp->pred_flags = 0; + if (old_win) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPTOZEROWINDOWADV); + } else if (old_win == 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV); + } return new_win; } @@ -767,6 +780,17 @@ void tcp_release_cb(struct sock *sk) if (flags & (1UL << TCP_TSQ_DEFERRED)) tcp_tsq_handler(sk); + /* Here begins the tricky part : + * We are called from release_sock() with : + * 1) BH disabled + * 2) sk_lock.slock spinlock held + * 3) socket owned by us (sk->sk_lock.owned == 1) + * + * But following code is meant to be called from BH handlers, + * so we should keep BH disabled, but early release socket ownership + */ + sock_release_ownership(sk); + if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) { tcp_write_timer_handler(sk); __sock_put(sk); @@ -856,16 +880,12 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (clone_it) { const struct sk_buff *fclone = skb + 1; - /* If congestion control is doing timestamping, we must - * take such a timestamp before we potentially clone/copy. - */ - if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP) - __net_timestamp(skb); + skb_mstamp_get(&skb->skb_mstamp); if (unlikely(skb->fclone == SKB_FCLONE_ORIG && fclone->fclone == SKB_FCLONE_CLONE)) - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); if (unlikely(skb_cloned(skb))) skb = pskb_copy(skb, gfp_mask); @@ -873,6 +893,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb = skb_clone(skb, gfp_mask); if (unlikely(!skb)) return -ENOBUFS; + /* Our usage of tstamp should remain private */ + skb->tstamp.tv64 = 0; } inet = inet_sk(sk); @@ -1964,7 +1986,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 timeout, tlp_time_stamp, rto_time_stamp; - u32 rtt = tp->srtt >> 3; + u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3); if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS)) return false; @@ -1986,7 +2008,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) /* Schedule a loss probe in 2*RTT for SACK capable connections * in Open state, that are either limited by cwnd or application. */ - if (sysctl_tcp_early_retrans < 3 || !tp->srtt || !tp->packets_out || + if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out || !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open) return false; @@ -2168,7 +2190,8 @@ u32 __tcp_select_window(struct sock *sk) */ int mss = icsk->icsk_ack.rcv_mss; int free_space = tcp_space(sk); - int full_space = min_t(int, tp->window_clamp, tcp_full_space(sk)); + int allowed_space = tcp_full_space(sk); + int full_space = min_t(int, tp->window_clamp, allowed_space); int window; if (mss > full_space) @@ -2181,7 +2204,19 @@ u32 __tcp_select_window(struct sock *sk) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); - if (free_space < mss) + /* free_space might become our new window, make sure we don't + * increase it due to wscale. + */ + free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale); + + /* if free space is less than mss estimate, or is below 1/16th + * of the maximum allowed, try to move to zero-window, else + * tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and + * new incoming data is dropped due to memory limits. + * With large window, mss test triggers way too late in order + * to announce zero window in time before rmem limit kicks in. + */ + if (free_space < (allowed_space >> 4) || free_space < mss) return 0; } @@ -2336,6 +2371,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); unsigned int cur_mss; + int err; /* Inconslusive MTU probe */ if (icsk->icsk_mtup.probe_size) { @@ -2399,11 +2435,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; } else { - return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } + + if (likely(!err)) + TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + return err; } int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) @@ -2414,7 +2454,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (err == 0) { /* Update global TCP statistics. */ TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); - + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); tp->total_retrans++; #if FASTRETRANS_DEBUG > 0 @@ -2907,7 +2948,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; - syn_data = skb_copy_expand(syn, skb_headroom(syn), space, + space = min_t(size_t, space, fo->size); + + /* limit to order-0 allocations */ + space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); + + syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space, sk->sk_allocation); if (syn_data == NULL) goto fallback; @@ -2937,9 +2983,15 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) tcp_connect_queue_skb(sk, data); fo->copied = data->len; + /* syn_data is about to be sent, we need to take current time stamps + * for the packets that are in write queue : SYN packet and DATA + */ + skb_mstamp_get(&syn->skb_mstamp); + data->skb_mstamp = syn->skb_mstamp; + if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { tp->syn_data = (fo->copied > 0); - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } syn_data = NULL; @@ -3027,8 +3079,9 @@ void tcp_send_delayed_ack(struct sock *sk) * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements * directly. */ - if (tp->srtt) { - int rtt = max(tp->srtt >> 3, TCP_DELACK_MIN); + if (tp->srtt_us) { + int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3), + TCP_DELACK_MIN); if (rtt < max_ato) max_ato = rtt; diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 1f2d376..3b66610 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -154,7 +154,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, p->snd_wnd = tp->snd_wnd; p->rcv_wnd = tp->rcv_wnd; p->ssthresh = tcp_current_ssthresh(sk); - p->srtt = tp->srtt >> 3; + p->srtt = tp->srtt_us >> 3; tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 64f0354..286227a 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -165,6 +165,9 @@ static int tcp_write_timeout(struct sock *sk) dst_negative_advice(sk); if (tp->syn_fastopen || tp->syn_data) tcp_fastopen_cache_set(sk, 0, NULL, true); + if (tp->syn_data) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENACTIVEFAIL); } retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; syn_set = true; diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index a022c17..48539ff 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -306,7 +306,6 @@ void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) EXPORT_SYMBOL_GPL(tcp_vegas_get_info); static struct tcp_congestion_ops tcp_vegas __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_vegas_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_vegas_cong_avoid, diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 326475a..1b8e28f 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -203,7 +203,6 @@ static u32 tcp_veno_ssthresh(struct sock *sk) } static struct tcp_congestion_ops tcp_veno __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_veno_init, .ssthresh = tcp_veno_ssthresh, .cong_avoid = tcp_veno_cong_avoid, diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 8eab0203..5ede0e7 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -227,7 +227,6 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) { } static struct tcp_congestion_ops tcp_yeah __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_yeah_init, .ssthresh = tcp_yeah_ssthresh, .cong_avoid = tcp_yeah_cong_avoid, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 77bd16f..4468e1a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -931,7 +931,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sock_tx_timestamp(sk, &ipc.tx_flags); if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, + sk->sk_family == AF_INET6); if (err) return err; if (ipc.opt) diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 1f12c8b..aac6197 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -37,15 +37,6 @@ drop: return NET_RX_DROP; } -int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, - int encap_type) -{ - XFRM_SPI_SKB_CB(skb)->family = AF_INET; - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); - return xfrm_input(skb, nexthdr, spi, encap_type); -} -EXPORT_SYMBOL(xfrm4_rcv_encap); - int xfrm4_transport_finish(struct sk_buff *skb, int async) { struct iphdr *iph = ip_hdr(skb); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 31b1815..05f2b48 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -15,65 +15,6 @@ #include <net/ip.h> #include <net/xfrm.h> -/* Informational hook. The decap is still done here. */ -static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly; -static DEFINE_MUTEX(xfrm4_mode_tunnel_input_mutex); - -int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -EEXIST; - int priority = handler->priority; - - mutex_lock(&xfrm4_mode_tunnel_input_mutex); - - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t->priority > priority) - break; - if (t->priority == priority) - goto err; - - } - - handler->next = *pprev; - rcu_assign_pointer(*pprev, handler); - - ret = 0; - -err: - mutex_unlock(&xfrm4_mode_tunnel_input_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_register); - -int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -ENOENT; - - mutex_lock(&xfrm4_mode_tunnel_input_mutex); - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t == handler) { - *pprev = handler->next; - ret = 0; - break; - } - } - mutex_unlock(&xfrm4_mode_tunnel_input_mutex); - synchronize_net(); - - return ret; -} -EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_deregister); - static inline void ipip_ecn_decapsulate(struct sk_buff *skb) { struct iphdr *inner_iph = ipip_hdr(skb); @@ -127,14 +68,8 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) return 0; } -#define for_each_input_rcu(head, handler) \ - for (handler = rcu_dereference(head); \ - handler != NULL; \ - handler = rcu_dereference(handler->next)) - static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - struct xfrm_tunnel_notifier *handler; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) @@ -143,9 +78,6 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; - for_each_input_rcu(rcv_notify_handlers, handler) - handler->handler(skb); - err = skb_unclone(skb, GFP_ATOMIC); if (err) goto out; diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c new file mode 100644 index 0000000..cdc09ef --- /dev/null +++ b/net/ipv4/xfrm4_protocol.c @@ -0,0 +1,275 @@ +/* xfrm4_protocol.c - Generic xfrm protocol multiplexer. + * + * Copyright (C) 2013 secunet Security Networks AG + * + * Author: + * Steffen Klassert <steffen.klassert@secunet.com> + * + * Based on: + * net/ipv4/tunnel4.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/skbuff.h> +#include <net/icmp.h> +#include <net/ip.h> +#include <net/protocol.h> +#include <net/xfrm.h> + +static struct xfrm4_protocol __rcu *esp4_handlers __read_mostly; +static struct xfrm4_protocol __rcu *ah4_handlers __read_mostly; +static struct xfrm4_protocol __rcu *ipcomp4_handlers __read_mostly; +static DEFINE_MUTEX(xfrm4_protocol_mutex); + +static inline struct xfrm4_protocol __rcu **proto_handlers(u8 protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp4_handlers; + case IPPROTO_AH: + return &ah4_handlers; + case IPPROTO_COMP: + return &ipcomp4_handlers; + } + + return NULL; +} + +#define for_each_protocol_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) \ + +int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err) +{ + int ret; + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(*proto_handlers(protocol), handler) + if ((ret = handler->cb_handler(skb, err)) <= 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(xfrm4_rcv_cb); + +int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + for_each_protocol_rcu(*proto_handlers(nexthdr), handler) + if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) + return ret; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} +EXPORT_SYMBOL(xfrm4_rcv_encap); + +static int xfrm4_esp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(esp4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_esp_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(esp4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static int xfrm4_ah_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(ah4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret;; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_ah_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(ah4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static int xfrm4_ipcomp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(ipcomp4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_ipcomp_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(ipcomp4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static const struct net_protocol esp4_protocol = { + .handler = xfrm4_esp_rcv, + .err_handler = xfrm4_esp_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static const struct net_protocol ah4_protocol = { + .handler = xfrm4_ah_rcv, + .err_handler = xfrm4_ah_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static const struct net_protocol ipcomp4_protocol = { + .handler = xfrm4_ipcomp_rcv, + .err_handler = xfrm4_ipcomp_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static inline const struct net_protocol *netproto(unsigned char protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp4_protocol; + case IPPROTO_AH: + return &ah4_protocol; + case IPPROTO_COMP: + return &ipcomp4_protocol; + } + + return NULL; +} + +int xfrm4_protocol_register(struct xfrm4_protocol *handler, + unsigned char protocol) +{ + struct xfrm4_protocol __rcu **pprev; + struct xfrm4_protocol *t; + bool add_netproto = false; + + int ret = -EEXIST; + int priority = handler->priority; + + mutex_lock(&xfrm4_protocol_mutex); + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm4_protocol_mutex))) + add_netproto = true; + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm4_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t->priority < priority) + break; + if (t->priority == priority) + goto err; + } + + handler->next = *pprev; + rcu_assign_pointer(*pprev, handler); + + ret = 0; + +err: + mutex_unlock(&xfrm4_protocol_mutex); + + if (add_netproto) { + if (inet_add_protocol(netproto(protocol), protocol)) { + pr_err("%s: can't add protocol\n", __func__); + ret = -EAGAIN; + } + } + + return ret; +} +EXPORT_SYMBOL(xfrm4_protocol_register); + +int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, + unsigned char protocol) +{ + struct xfrm4_protocol __rcu **pprev; + struct xfrm4_protocol *t; + int ret = -ENOENT; + + mutex_lock(&xfrm4_protocol_mutex); + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm4_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { + *pprev = handler->next; + ret = 0; + break; + } + } + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm4_protocol_mutex))) { + if (inet_del_protocol(netproto(protocol), protocol) < 0) { + pr_err("%s: can't remove protocol\n", __func__); + ret = -EAGAIN; + } + } + + mutex_unlock(&xfrm4_protocol_mutex); + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(xfrm4_protocol_deregister); |
