diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/fib_trie.c | 2 | ||||
-rw-r--r-- | net/ipv4/icmp.c | 10 | ||||
-rw-r--r-- | net/ipv4/igmp.c | 4 | ||||
-rw-r--r-- | net/ipv4/inet_fragment.c | 41 | ||||
-rw-r--r-- | net/ipv4/ip_fragment.c | 8 | ||||
-rw-r--r-- | net/ipv4/ipip.c | 3 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_CLUSTERIP.c | 4 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_SYNPROXY.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_rpfilter.c | 1 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_nat_h323.c | 12 | ||||
-rw-r--r-- | net/ipv4/route.c | 17 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 33 | ||||
-rw-r--r-- | net/ipv4/tcp_bpf.c | 6 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 19 | ||||
-rw-r--r-- | net/ipv4/tcp_ulp.c | 13 |
15 files changed, 128 insertions, 47 deletions
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2b2b3d291ab0..1ab2fb6bb37d 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2145,7 +2145,7 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, if (filter->dump_exceptions) { err = fib_dump_info_fnhe(skb, cb, tb->tb_id, fi, - &i_fa, s_fa); + &i_fa, s_fa, flags); if (err < 0) goto stop; } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1510e951f451..4298aae74e0e 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -582,7 +582,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, if (!rt) goto out; - net = dev_net(rt->dst.dev); + + if (rt->dst.dev) + net = dev_net(rt->dst.dev); + else if (skb_in->dev) + net = dev_net(skb_in->dev); + else + goto out; /* * Find the original header. It is expected to be valid, of course. @@ -902,7 +908,7 @@ static bool icmp_redirect(struct sk_buff *skb) return false; } - icmp_socket_deliver(skb, icmp_hdr(skb)->un.gateway); + icmp_socket_deliver(skb, ntohl(icmp_hdr(skb)->un.gateway)); return true; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 180f6896b98b..480d0b22db1a 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1475,7 +1475,7 @@ EXPORT_SYMBOL(__ip_mc_inc_group); void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { - __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE); + __ip_mc_inc_group(in_dev, addr, GFP_KERNEL); } EXPORT_SYMBOL(ip_mc_inc_group); @@ -2197,7 +2197,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, iml->sflist = NULL; iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); - __ip_mc_inc_group(in_dev, addr, mode); + ____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL); err = 0; done: return err; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index d666756be5f1..10d31733297d 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -331,7 +331,7 @@ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key) prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params); if (!prev) fq = inet_frag_create(fqdir, key, &prev); - if (prev && !IS_ERR(prev)) { + if (!IS_ERR_OR_NULL(prev)) { fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; @@ -475,11 +475,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, - void *reasm_data) + void *reasm_data, bool try_coalesce) { struct sk_buff **nextp = (struct sk_buff **)reasm_data; struct rb_node *rbn; struct sk_buff *fp; + int sum_truesize; skb_push(head, head->data - skb_network_header(head)); @@ -487,25 +488,41 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, fp = FRAG_CB(head)->next_frag; rbn = rb_next(&head->rbnode); rb_erase(&head->rbnode, &q->rb_fragments); + + sum_truesize = head->truesize; while (rbn || fp) { /* fp points to the next sk_buff in the current run; * rbn points to the next run. */ /* Go through the current run. */ while (fp) { - *nextp = fp; - nextp = &fp->next; - fp->prev = NULL; - memset(&fp->rbnode, 0, sizeof(fp->rbnode)); - fp->sk = NULL; - head->data_len += fp->len; - head->len += fp->len; + struct sk_buff *next_frag = FRAG_CB(fp)->next_frag; + bool stolen; + int delta; + + sum_truesize += fp->truesize; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp = FRAG_CB(fp)->next_frag; + + if (try_coalesce && skb_try_coalesce(head, fp, &stolen, + &delta)) { + kfree_skb_partial(fp, stolen); + } else { + fp->prev = NULL; + memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; + + head->data_len += fp->len; + head->len += fp->len; + head->truesize += fp->truesize; + + *nextp = fp; + nextp = &fp->next; + } + + fp = next_frag; } /* Move to the next run. */ if (rbn) { @@ -516,7 +533,7 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, rbn = rbnext; } } - sub_frag_mem_limit(q->fqdir, head->truesize); + sub_frag_mem_limit(q->fqdir, sum_truesize); *nextp = NULL; skb_mark_not_on_list(head); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 4385eb9e781f..cfeb8890f94e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -393,6 +393,11 @@ err: return err; } +static bool ip_frag_coalesce_ok(const struct ipq *qp) +{ + return qp->q.key.v4.user == IP_DEFRAG_LOCAL_DELIVER; +} + /* Build a new IP datagram from all its fragments. */ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev) @@ -421,7 +426,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, if (len > 65535) goto out_oversize; - inet_frag_reasm_finish(&qp->q, skb, reasm_data); + inet_frag_reasm_finish(&qp->q, skb, reasm_data, + ip_frag_coalesce_ok(qp)); skb->dev = dev; IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 43adfc1641ba..2f01cf6fa0de 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -275,6 +275,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, const struct iphdr *tiph = &tunnel->parms.iph; u8 ipproto; + if (!pskb_inet_may_pull(skb)) + goto tx_error; + switch (skb->protocol) { case htons(ETH_P_IP): ipproto = IPPROTO_IPIP; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 4d6bf7ac0792..6bdb1ab8af61 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -416,8 +416,8 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) ctinfo == IP_CT_RELATED_REPLY)) return XT_CONTINUE; - /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO, - * TIMESTAMP, INFO_REQUEST or ADDRESS type icmp packets from here + /* nf_conntrack_proto_icmp guarantees us that we only have ICMP_ECHO, + * TIMESTAMP, INFO_REQUEST or ICMP_ADDRESS type icmp packets from here * on, which all have an ID field [relevant for hashing]. */ hash = clusterip_hashfn(skb, cipinfo->config); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 8e7f84ec783d..0e70f3f65f6f 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -36,6 +36,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) opts.options |= XT_SYNPROXY_OPT_ECN; opts.options &= info->options; + opts.mss_encode = opts.mss; + opts.mss = info->mss; if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, &opts); else diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 59031670b16a..cc23f1ce239c 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -78,6 +78,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; flow.flowi4_tos = RT_TOS(iph->tos); flow.flowi4_scope = RT_SCOPE_UNIVERSE; + flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par)); return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert; } diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 87b711fd5a44..3e2685c120c7 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -221,11 +221,11 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, int ret; rtp_exp->tuple.dst.u.udp.port = htons(nated_port); - ret = nf_ct_expect_related(rtp_exp); + ret = nf_ct_expect_related(rtp_exp, 0); if (ret == 0) { rtcp_exp->tuple.dst.u.udp.port = htons(nated_port + 1); - ret = nf_ct_expect_related(rtcp_exp); + ret = nf_ct_expect_related(rtcp_exp, 0); if (ret == 0) break; else if (ret == -EBUSY) { @@ -296,7 +296,7 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -352,7 +352,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -444,7 +444,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -537,7 +537,7 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 517300d587a7..b6a6f18c3dd1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2728,7 +2728,8 @@ EXPORT_SYMBOL_GPL(ip_route_output_flow); /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, struct flowi4 *fl4, - struct sk_buff *skb, u32 portid, u32 seq) + struct sk_buff *skb, u32 portid, u32 seq, + unsigned int flags) { struct rtmsg *r; struct nlmsghdr *nlh; @@ -2736,7 +2737,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 error; u32 metrics[RTAX_MAX]; - nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), 0); + nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), flags); if (!nlh) return -EMSGSIZE; @@ -2860,7 +2861,7 @@ nla_put_failure: static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fnhe_hash_bucket *bucket, int genid, - int *fa_index, int fa_start) + int *fa_index, int fa_start, unsigned int flags) { int i; @@ -2891,7 +2892,7 @@ static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, table_id, NULL, skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); + cb->nlh->nlmsg_seq, flags); if (err) return err; next: @@ -2904,7 +2905,7 @@ next: int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, - int *fa_index, int fa_start) + int *fa_index, int fa_start, unsigned int flags) { struct net *net = sock_net(cb->skb->sk); int nhsel, genid = fnhe_genid(net); @@ -2922,7 +2923,8 @@ int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, err = 0; if (bucket) err = fnhe_dump_bucket(net, skb, cb, table_id, bucket, - genid, fa_index, fa_start); + genid, fa_index, fa_start, + flags); rcu_read_unlock(); if (err) return err; @@ -3183,7 +3185,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_tos, res.fi, 0); } else { err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq); + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); } if (err < 0) goto errout_rcu; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 776905899ac0..61082065b26a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -935,6 +935,22 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } +/* In some cases, both sendpage() and sendmsg() could have added + * an skb to the write queue, but failed adding payload on it. + * We need to remove it to consume less memory, but more + * importantly be able to generate EPOLLOUT for Edge Trigger epoll() + * users. + */ +static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb) +{ + if (skb && !skb->len) { + tcp_unlink_write_queue(skb, sk); + if (tcp_write_queue_empty(sk)) + tcp_chrono_stop(sk, TCP_CHRONO_BUSY); + sk_wmem_free_skb(sk, skb); + } +} + ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -984,6 +1000,9 @@ new_segment: if (!skb) goto wait_for_memory; +#ifdef CONFIG_TLS_DEVICE + skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); +#endif skb_entail(sk, skb); copy = size_goal; } @@ -1061,6 +1080,7 @@ out: return copied; do_error: + tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk)); if (copied) goto out; out_err: @@ -1385,18 +1405,11 @@ out_nopush: sock_zerocopy_put(uarg); return copied + copied_syn; +do_error: + skb = tcp_write_queue_tail(sk); do_fault: - if (!skb->len) { - tcp_unlink_write_queue(skb, sk); - /* It is the one place in all of TCP, except connection - * reset, where we can be unlinking the send_head. - */ - if (tcp_write_queue_empty(sk)) - tcp_chrono_stop(sk, TCP_CHRONO_BUSY); - sk_wmem_free_skb(sk, skb); - } + tcp_remove_empty_skb(sk, skb); -do_error: if (copied + copied_syn) goto out; out_err: diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 3d1e15401384..8a56e09cfb0e 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -398,10 +398,14 @@ more_data: static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct sk_msg tmp, *msg_tx = NULL; - int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS; int copied = 0, err = 0; struct sk_psock *psock; long timeo; + int flags; + + /* Don't let internal do_tcp_sendpages() flags through */ + flags = (msg->msg_flags & ~MSG_SENDPAGE_DECRYPTED); + flags |= MSG_NO_SHARED_FRAGS; psock = sk_psock_get(sk); if (unlikely(!psock)) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4af1f5dae9d3..8a645f304e6c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1288,6 +1288,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int nsize, old_factor; + long limit; int nlen; u8 flags; @@ -1298,8 +1299,16 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, if (nsize < 0) nsize = 0; - if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf && - tcp_queue != TCP_FRAG_IN_WRITE_QUEUE)) { + /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb. + * We need some allowance to not penalize applications setting small + * SO_SNDBUF values. + * Also allow first and last skb in retransmit queue to be split. + */ + limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE); + if (unlikely((sk->sk_wmem_queued >> 1) > limit && + tcp_queue != TCP_FRAG_IN_WRITE_QUEUE && + skb != tcp_rtx_queue_head(sk) && + skb != tcp_rtx_queue_tail(sk))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG); return -ENOMEM; } @@ -1311,6 +1320,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, buff = sk_stream_alloc_skb(sk, nsize, gfp, true); if (!buff) return -ENOMEM; /* We'll just try again later. */ + skb_copy_decrypted(buff, skb); sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); @@ -1865,6 +1875,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, buff = sk_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) return -ENOMEM; + skb_copy_decrypted(buff, skb); sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); @@ -2042,7 +2053,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (len <= skb->len) break; - if (unlikely(TCP_SKB_CB(skb)->eor)) + if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) return false; len -= skb->len; @@ -2134,6 +2145,7 @@ static int tcp_mtu_probe(struct sock *sk) sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); + skb_copy_decrypted(nskb, skb); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq; TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size; @@ -2158,6 +2170,7 @@ static int tcp_mtu_probe(struct sock *sk) * we need to propagate it to the new skb. */ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; + tcp_skb_collapse_tstamp(nskb, skb); tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else { diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 3d8a1d835471..4849edb62d52 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -96,6 +96,19 @@ void tcp_get_available_ulp(char *buf, size_t maxlen) rcu_read_unlock(); } +void tcp_update_ulp(struct sock *sk, struct proto *proto) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (!icsk->icsk_ulp_ops) { + sk->sk_prot = proto; + return; + } + + if (icsk->icsk_ulp_ops->update) + icsk->icsk_ulp_ops->update(sk, proto); +} + void tcp_cleanup_ulp(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); |