diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/inet_diag.c | 18 | ||||
-rw-r--r-- | net/ipv4/ip_forward.c | 3 | ||||
-rw-r--r-- | net/ipv4/ip_fragment.c | 11 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 35 | ||||
-rw-r--r-- | net/ipv4/ip_sockglue.c | 8 | ||||
-rw-r--r-- | net/ipv4/ping.c | 5 | ||||
-rw-r--r-- | net/ipv4/route.c | 9 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 37 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 68 | ||||
-rw-r--r-- | net/ipv4/udp_diag.c | 4 |
10 files changed, 103 insertions, 95 deletions
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 45dbdab915e2..14a1ed611b05 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -71,6 +71,20 @@ static inline void inet_diag_unlock_handler( mutex_unlock(&inet_diag_table_mutex); } +static size_t inet_sk_attr_size(void) +{ + return nla_total_size(sizeof(struct tcp_info)) + + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + + nla_total_size(1) /* INET_DIAG_TOS */ + + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(sizeof(struct inet_diag_meminfo)) + + nla_total_size(sizeof(struct inet_diag_msg)) + + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + + nla_total_size(TCP_CA_NAME_MAX) + + nla_total_size(sizeof(struct tcpvegas_info)) + + 64; +} + int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, struct inet_diag_req_v2 *req, struct user_namespace *user_ns, @@ -326,9 +340,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s if (err) goto out; - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + - sizeof(struct tcp_info) + 64, GFP_KERNEL); + rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL); if (!rep) { err = -ENOMEM; goto out; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index bd1c5baf69be..31ee5c6033df 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -175,7 +175,8 @@ int ip_forward(struct sk_buff *skb) * We now generate an ICMP HOST REDIRECT giving the route * we calculated. */ - if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb)) + if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr && + !skb_sec_path(skb)) ip_rt_send_redirect(skb); skb->priority = rt_tos2priority(iph->tos); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b66910aaef4d..4c1884fed548 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -678,27 +678,30 @@ EXPORT_SYMBOL(ip_defrag); struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) { struct iphdr iph; + int netoff; u32 len; if (skb->protocol != htons(ETH_P_IP)) return skb; - if (!skb_copy_bits(skb, 0, &iph, sizeof(iph))) + netoff = skb_network_offset(skb); + + if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0) return skb; if (iph.ihl < 5 || iph.version != 4) return skb; len = ntohs(iph.tot_len); - if (skb->len < len || len < (iph.ihl * 4)) + if (skb->len < netoff + len || len < (iph.ihl * 4)) return skb; if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { - if (!pskb_may_pull(skb, iph.ihl*4)) + if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) return skb; - if (pskb_trim_rcsum(skb, len)) + if (pskb_trim_rcsum(skb, netoff + len)) return skb; memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(skb, user)) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9f3230f42a5e..85c15eb4d7ec 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -846,7 +846,8 @@ static int __ip_append_data(struct sock *sk, cork->length += length; if (((length > mtu) || (skb && skb_has_frags(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) { + (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && + (sk->sk_type == SOCK_DGRAM)) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, maxfraglen, flags); @@ -1455,26 +1456,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, /* * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. - * - * Use a fake percpu inet socket to avoid false sharing and contention. */ -static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = { - .sk = { - .__sk_common = { - .skc_refcnt = ATOMIC_INIT(1), - }, - .sk_wmem_alloc = ATOMIC_INIT(1), - .sk_allocation = GFP_ATOMIC, - .sk_flags = (1UL << SOCK_USE_WRITE_QUEUE), - }, - .pmtudisc = IP_PMTUDISC_WANT, - .uc_ttl = -1, -}; - -/* serialize concurrent calls on the same CPU to ip_send_unicast_reply */ -static DEFINE_LOCAL_IRQ_LOCK(unicast_lock); - -void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, +void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len) { @@ -1482,9 +1465,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); + struct net *net = sock_net(sk); struct sk_buff *nskb; - struct sock *sk; - struct inet_sock *inet; int err; if (ip_options_echo(&replyopts.opt.opt, skb)) @@ -1512,15 +1494,11 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, if (IS_ERR(rt)) return; - inet = &get_locked_var(unicast_lock, unicast_sock); + inet_sk(sk)->tos = arg->tos; - inet->tos = arg->tos; - sk = &inet->sk; sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; - sock_net_set(sk, net); - __skb_queue_head_init(&sk->sk_write_queue); sk->sk_sndbuf = sysctl_wmem_default; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); @@ -1536,14 +1514,11 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; - skb_orphan(nskb); skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb)); ip_push_pending_frames(sk, &fl4); } out: - put_locked_var(unicast_lock, unicast_sock); - ip_rt_put(rt); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 23e6ab0a2dc0..f6603142cb33 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -410,15 +410,11 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; - sin->sin_family = AF_UNSPEC; + memset(sin, 0, sizeof(*sin)); if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { - struct inet_sock *inet = inet_sk(sk); - sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; - sin->sin_port = 0; - memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); - if (inet->cmsg_flags) + if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index aa857a4a06a8..698f3a2ac5ae 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -720,8 +720,11 @@ void ping_rcv(struct sk_buff *skb) sk = ping_v4_lookup(net, saddr, daddr, ntohs(icmph->un.echo.id), skb->dev->ifindex); if (sk != NULL) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + pr_debug("rcv on socket %p\n", sk); - ping_queue_rcv_skb(sk, skb_get(skb)); + if (skb2) + ping_queue_rcv_skb(sk, skb2); sock_put(sk); return; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d4d162eac4df..e23c5f64286b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1514,11 +1514,10 @@ static int __mkroute_input(struct sk_buff *skb, do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && + skb->protocol == htons(ETH_P_IP) && (IN_DEV_SHARED_MEDIA(out_dev) || - inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) { - flags |= RTCF_DOREDIRECT; - do_cache = false; - } + inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) + IPCB(skb)->flags |= IPSKB_DOREDIRECT; if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is @@ -2255,6 +2254,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; + if (IPCB(skb)->flags & IPSKB_DOREDIRECT) + r->rtm_flags |= RTCF_DOREDIRECT; if (nla_put_be32(skb, RTA_DST, dst)) goto nla_put_failure; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e025c1c788a1..cce35e5a7ee6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -707,7 +707,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) net = dev_net(skb_dst(skb)->dev); arg.tos = ip_hdr(skb)->tos; - ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -790,7 +791,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, if (oif) arg.bound_dev_if = oif; arg.tos = tos; - ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -2898,14 +2900,39 @@ struct proto tcp_prot = { }; EXPORT_SYMBOL(tcp_prot); +static void __net_exit tcp_sk_exit(struct net *net) +{ + int cpu; + + for_each_possible_cpu(cpu) + inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); + free_percpu(net->ipv4.tcp_sk); +} + static int __net_init tcp_sk_init(struct net *net) { + int res, cpu; + + net->ipv4.tcp_sk = alloc_percpu(struct sock *); + if (!net->ipv4.tcp_sk) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct sock *sk; + + res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, + IPPROTO_TCP, net); + if (res) + goto fail; + *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; + } net->ipv4.sysctl_tcp_ecn = 2; return 0; -} -static void __net_exit tcp_sk_exit(struct net *net) -{ +fail: + tcp_sk_exit(net); + + return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 923146c4f007..913dc4f49b10 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2593,15 +2593,11 @@ void tcp_send_fin(struct sock *sk) } else { /* Socket is locked, keep trying until memory is available. */ for (;;) { - skb = alloc_skb_fclone(MAX_TCP_HEADER, - sk->sk_allocation); + skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); if (skb) break; yield(); } - - /* Reserve space for headers and prepare control bits. */ - skb_reserve(skb, MAX_TCP_HEADER); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); @@ -2875,9 +2871,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; - int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen; - struct sk_buff *syn_data = NULL, *data; + int syn_loss = 0, space, err = 0; unsigned long last_syn_loss = 0; + struct sk_buff *syn_data; tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie, @@ -2908,42 +2904,38 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) /* 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) + syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation); + if (!syn_data) goto fallback; + syn_data->ip_summed = CHECKSUM_PARTIAL; + memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); + if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space), + fo->data->msg_iov, 0, space))) { + kfree_skb(syn_data); + goto fallback; + } - for (i = 0; i < iovlen && syn_data->len < space; ++i) { - struct iovec *iov = &fo->data->msg_iov[i]; - unsigned char __user *from = iov->iov_base; - int len = iov->iov_len; - - if (syn_data->len + len > space) - len = space - syn_data->len; - else if (i + 1 == iovlen) - /* No more data pending in inet_wait_for_connect() */ - fo->data = NULL; + /* No more data pending in inet_wait_for_connect() */ + if (space == fo->size) + fo->data = NULL; + fo->copied = space; - if (skb_add_data(syn_data, from, len)) - goto fallback; - } + tcp_connect_queue_skb(sk, syn_data); - /* Queue a data-only packet after the regular SYN for retransmission */ - data = pskb_copy(syn_data, sk->sk_allocation); - if (data == NULL) - goto fallback; - TCP_SKB_CB(data)->seq++; - TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN; - TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH); - tcp_connect_queue_skb(sk, data); - fo->copied = data->len; + err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); - if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { + /* Now full SYN+DATA was cloned and sent (or not), + * remove the SYN from the original skb (syn_data) + * we keep in write queue in case of a retransmit, as we + * also have the SYN packet (with no data) in the same queue. + */ + TCP_SKB_CB(syn_data)->seq++; + TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; + if (!err) { tp->syn_data = (fo->copied > 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); goto done; } - syn_data = NULL; fallback: /* Send a regular SYN with Fast Open cookie request option */ @@ -2952,7 +2944,6 @@ fallback: err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation); if (err) tp->syn_fastopen = 0; - kfree_skb(syn_data); done: fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */ return err; @@ -2972,13 +2963,10 @@ int tcp_connect(struct sock *sk) return 0; } - buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation); - if (unlikely(buff == NULL)) + buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); + if (unlikely(!buff)) return -ENOBUFS; - /* Reserve space for headers. */ - skb_reserve(buff, MAX_TCP_HEADER); - tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp; tcp_connect_queue_skb(sk, buff); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 7927db0a9279..4a000f1dd757 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -99,11 +99,13 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin s_slot = cb->args[0]; num = s_num = cb->args[1]; - for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) { + for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) { struct sock *sk; struct hlist_nulls_node *node; struct udp_hslot *hslot = &table->hash[slot]; + num = 0; + if (hlist_nulls_empty(&hslot->head)) continue; |