summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c12
-rw-r--r--net/ipv4/fib_frontend.c3
-rw-r--r--net/ipv4/inet_connection_sock.c2
-rw-r--r--net/ipv4/ip_fragment.c25
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_sockglue.c10
-rw-r--r--net/ipv4/ipconfig.c2
-rw-r--r--net/ipv4/ipmr.c11
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c2
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c4
-rw-r--r--net/ipv4/netfilter/nf_nat_l3proto_ipv4.c5
-rw-r--r--net/ipv4/netfilter/nf_nat_snmp_basic.c20
-rw-r--r--net/ipv4/netfilter/nft_masq_ipv4.c8
-rw-r--r--net/ipv4/netfilter/nft_redir_ipv4.c8
-rw-r--r--net/ipv4/ping.c5
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv4/route.c5
-rw-r--r--net/ipv4/tcp.c4
-rw-r--r--net/ipv4/tcp_cong.c11
-rw-r--r--net/ipv4/tcp_input.c63
-rw-r--r--net/ipv4/tcp_ipv4.c10
-rw-r--r--net/ipv4/tcp_minisocks.c1
-rw-r--r--net/ipv4/tcp_output.c23
-rw-r--r--net/ipv4/tcp_recovery.c3
-rw-r--r--net/ipv4/tcp_timer.c6
-rw-r--r--net/ipv4/udp_offload.c3
26 files changed, 134 insertions, 116 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 602d40f43687..13a9a3297eae 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -689,11 +689,12 @@ EXPORT_SYMBOL(inet_stream_connect);
* Accept a pending connection. The TCP layer now gives BSD semantics.
*/
-int inet_accept(struct socket *sock, struct socket *newsock, int flags)
+int inet_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk1 = sock->sk;
int err = -EINVAL;
- struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err);
+ struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern);
if (!sk2)
goto do_err;
@@ -1342,6 +1343,9 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
if (*(u8 *)iph != 0x45)
goto out_unlock;
+ if (ip_is_fragment(iph))
+ goto out_unlock;
+
if (unlikely(ip_fast_csum((u8 *)iph, 5)))
goto out_unlock;
@@ -1487,8 +1491,10 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)
int proto = iph->protocol;
int err = -ENOSYS;
- if (skb->encapsulation)
+ if (skb->encapsulation) {
+ skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP));
skb_set_inner_network_header(skb, nhoff);
+ }
csum_replace2(&iph->check, iph->tot_len, newlen);
iph->tot_len = newlen;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 42bfd08109dd..8f2133ffc2ff 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1083,7 +1083,8 @@ static void nl_fib_input(struct sk_buff *skb)
net = sock_net(skb->sk);
nlh = nlmsg_hdr(skb);
- if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
+ if (skb->len < nlmsg_total_size(sizeof(*frn)) ||
+ skb->len < nlh->nlmsg_len ||
nlmsg_len(nlh) < sizeof(*frn))
return;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b4d5980ade3b..5e313c1ac94f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -424,7 +424,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
/*
* This will accept the next outstanding connection.
*/
-struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct request_sock_queue *queue = &icsk->icsk_accept_queue;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index bbe7f72db9c1..b3cdeec85f1f 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -198,6 +198,7 @@ static void ip_expire(unsigned long arg)
qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
+ rcu_read_lock();
spin_lock(&qp->q.lock);
if (qp->q.flags & INET_FRAG_COMPLETE)
@@ -207,7 +208,7 @@ static void ip_expire(unsigned long arg)
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
if (!inet_frag_evicting(&qp->q)) {
- struct sk_buff *head = qp->q.fragments;
+ struct sk_buff *clone, *head = qp->q.fragments;
const struct iphdr *iph;
int err;
@@ -216,32 +217,40 @@ static void ip_expire(unsigned long arg)
if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
goto out;
- rcu_read_lock();
head->dev = dev_get_by_index_rcu(net, qp->iif);
if (!head->dev)
- goto out_rcu_unlock;
+ goto out;
+
/* skb has no dst, perform route lookup again */
iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
if (err)
- goto out_rcu_unlock;
+ goto out;
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
if (frag_expire_skip_icmp(qp->user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
- goto out_rcu_unlock;
+ goto out;
+
+ clone = skb_clone(head, GFP_ATOMIC);
/* Send an ICMP "Fragment Reassembly Timeout" message. */
- icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
-out_rcu_unlock:
- rcu_read_unlock();
+ if (clone) {
+ spin_unlock(&qp->q.lock);
+ icmp_send(clone, ICMP_TIME_EXCEEDED,
+ ICMP_EXC_FRAGTIME, 0);
+ consume_skb(clone);
+ goto out_rcu_unlock;
+ }
}
out:
spin_unlock(&qp->q.lock);
+out_rcu_unlock:
+ rcu_read_unlock();
ipq_put(qp);
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 737ce826d7ec..7a3fd25e8913 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -966,7 +966,7 @@ static int __ip_append_data(struct sock *sk,
cork->length += length;
if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
- (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+ (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
(sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
err = ip_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen, transhdrlen,
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index ebd953bc5607..1d46d05efb0f 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -488,16 +488,15 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk,
return false;
/* Support IP_PKTINFO on tstamp packets if requested, to correlate
- * timestamp with egress dev. Not possible for packets without dev
+ * timestamp with egress dev. Not possible for packets without iif
* or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
*/
- if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
- (!skb->dev))
+ info = PKTINFO_SKB_CB(skb);
+ if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) ||
+ !info->ipi_ifindex)
return false;
- info = PKTINFO_SKB_CB(skb);
info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
- info->ipi_ifindex = skb->dev->ifindex;
return true;
}
@@ -591,6 +590,7 @@ static bool setsockopt_needs_rtnl(int optname)
case MCAST_LEAVE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_UNBLOCK_SOURCE:
+ case IP_ROUTER_ALERT:
return true;
}
return false;
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index fd9f34bbd740..dfb2ab2dd3c8 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -306,7 +306,7 @@ static void __init ic_close_devs(void)
while ((d = next)) {
next = d->next;
dev = d->dev;
- if ((!ic_dev || dev != ic_dev->dev) && !netdev_uses_dsa(dev)) {
+ if (d != ic_dev && !netdev_uses_dsa(dev)) {
pr_debug("IP-Config: Downing %s\n", dev->name);
dev_change_flags(dev, d->flags);
}
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c0317c940bcd..b036e85e093b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1278,7 +1278,7 @@ static void mrtsock_destruct(struct sock *sk)
struct net *net = sock_net(sk);
struct mr_table *mrt;
- rtnl_lock();
+ ASSERT_RTNL();
ipmr_for_each_table(mrt, net) {
if (sk == rtnl_dereference(mrt->mroute_sk)) {
IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
@@ -1289,7 +1289,6 @@ static void mrtsock_destruct(struct sock *sk)
mroute_clean_tables(mrt, false);
}
}
- rtnl_unlock();
}
/* Socket options and virtual interface manipulation. The whole
@@ -1353,13 +1352,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
if (sk != rcu_access_pointer(mrt->mroute_sk)) {
ret = -EACCES;
} else {
- /* We need to unlock here because mrtsock_destruct takes
- * care of rtnl itself and we can't change that due to
- * the IP_ROUTER_ALERT setsockopt which runs without it.
- */
- rtnl_unlock();
ret = ip_ra_control(sk, 0, NULL);
- goto out;
+ goto out_unlock;
}
break;
case MRT_ADD_VIF:
@@ -1470,7 +1464,6 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
}
out_unlock:
rtnl_unlock();
-out:
return ret;
}
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 52f26459efc3..9b8841316e7b 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -461,7 +461,7 @@ static void clusterip_tg_destroy(const struct xt_tgdtor_param *par)
clusterip_config_put(cipinfo->config);
- nf_ct_netns_get(par->net, par->family);
+ nf_ct_netns_put(par->net, par->family);
}
#ifdef CONFIG_COMPAT
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index bc1486f2c064..2e14ed11a35c 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -165,6 +165,10 @@ static unsigned int ipv4_conntrack_local(void *priv,
if (skb->len < sizeof(struct iphdr) ||
ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
+
+ if (ip_is_fragment(ip_hdr(skb))) /* IP_NODEFRAG setsockopt set */
+ return NF_ACCEPT;
+
return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
}
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index f8aad03d674b..6f5e8d01b876 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -255,11 +255,6 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
/* maniptype == SRC for postrouting. */
enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook);
- /* We never see fragments: conntrack defrags on pre-routing
- * and local-out, and nf_nat_out protects post-routing.
- */
- NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb)));
-
ct = nf_ct_get(skb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
* have dropped it. Hence it's the user's responsibilty to
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index c9b52c361da2..53e49f5011d3 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -1260,16 +1260,6 @@ static const struct nf_conntrack_expect_policy snmp_exp_policy = {
.timeout = 180,
};
-static struct nf_conntrack_helper snmp_helper __read_mostly = {
- .me = THIS_MODULE,
- .help = help,
- .expect_policy = &snmp_exp_policy,
- .name = "snmp",
- .tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = cpu_to_be16(SNMP_PORT),
- .tuple.dst.protonum = IPPROTO_UDP,
-};
-
static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
.me = THIS_MODULE,
.help = help,
@@ -1288,22 +1278,16 @@ static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
static int __init nf_nat_snmp_basic_init(void)
{
- int ret = 0;
-
BUG_ON(nf_nat_snmp_hook != NULL);
RCU_INIT_POINTER(nf_nat_snmp_hook, help);
- ret = nf_conntrack_helper_register(&snmp_trap_helper);
- if (ret < 0) {
- nf_conntrack_helper_unregister(&snmp_helper);
- return ret;
- }
- return ret;
+ return nf_conntrack_helper_register(&snmp_trap_helper);
}
static void __exit nf_nat_snmp_basic_fini(void)
{
RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
+ synchronize_rcu();
nf_conntrack_helper_unregister(&snmp_trap_helper);
}
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index a0ea8aad1bf1..f18677277119 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -26,10 +26,10 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr,
memset(&range, 0, sizeof(range));
range.flags = priv->flags;
if (priv->sreg_proto_min) {
- range.min_proto.all =
- *(__be16 *)&regs->data[priv->sreg_proto_min];
- range.max_proto.all =
- *(__be16 *)&regs->data[priv->sreg_proto_max];
+ range.min_proto.all = (__force __be16)nft_reg_load16(
+ &regs->data[priv->sreg_proto_min]);
+ range.max_proto.all = (__force __be16)nft_reg_load16(
+ &regs->data[priv->sreg_proto_max]);
}
regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt),
&range, nft_out(pkt));
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
index 1650ed23c15d..5120be1d3118 100644
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -26,10 +26,10 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr,
memset(&mr, 0, sizeof(mr));
if (priv->sreg_proto_min) {
- mr.range[0].min.all =
- *(__be16 *)&regs->data[priv->sreg_proto_min];
- mr.range[0].max.all =
- *(__be16 *)&regs->data[priv->sreg_proto_max];
+ mr.range[0].min.all = (__force __be16)nft_reg_load16(
+ &regs->data[priv->sreg_proto_min]);
+ mr.range[0].max.all = (__force __be16)nft_reg_load16(
+ &regs->data[priv->sreg_proto_max]);
mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 2af6244b83e2..ccfbce13a633 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -156,17 +156,18 @@ int ping_hash(struct sock *sk)
void ping_unhash(struct sock *sk)
{
struct inet_sock *isk = inet_sk(sk);
+
pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+ write_lock_bh(&ping_table.lock);
if (sk_hashed(sk)) {
- write_lock_bh(&ping_table.lock);
hlist_nulls_del(&sk->sk_nulls_node);
sk_nulls_node_init(&sk->sk_nulls_node);
sock_put(sk);
isk->inet_num = 0;
isk->inet_sport = 0;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
- write_unlock_bh(&ping_table.lock);
}
+ write_unlock_bh(&ping_table.lock);
}
EXPORT_SYMBOL_GPL(ping_unhash);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8119e1f66e03..9d943974de2b 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -682,7 +682,9 @@ static void raw_close(struct sock *sk, long timeout)
/*
* Raw sockets may have direct kernel references. Kill them.
*/
+ rtnl_lock();
ip_ra_control(sk, 0, NULL);
+ rtnl_unlock();
sk_common_release(sk);
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8471dd116771..d9724889ff09 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2359,7 +2359,8 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
}
/* L3 master device is the loopback for that domain */
- dev_out = l3mdev_master_dev_rcu(dev_out) ? : net->loopback_dev;
+ dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
+ net->loopback_dev;
fl4->flowi4_oif = dev_out->ifindex;
flags |= RTCF_LOCAL;
goto make_route;
@@ -2620,7 +2621,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
skb_reset_network_header(skb);
/* Bugfix: need to give ip_route_input enough of an IP header to not gag. */
- ip_hdr(skb)->protocol = IPPROTO_ICMP;
+ ip_hdr(skb)->protocol = IPPROTO_UDP;
skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cf4555581282..40ba4249a586 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2322,6 +2322,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tcp_init_send_head(sk);
memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
__sk_dst_reset(sk);
+ tcp_saved_syn_free(tp);
/* Clean up fastopen related fields */
tcp_free_fastopen_req(tp);
@@ -2770,7 +2771,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
{
const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */
const struct inet_connection_sock *icsk = inet_csk(sk);
- u32 now = tcp_time_stamp, intv;
+ u32 now, intv;
u64 rate64;
bool slow;
u32 rate;
@@ -2839,6 +2840,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_retrans = tp->retrans_out;
info->tcpi_fackets = tp->fackets_out;
+ now = tcp_time_stamp;
info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime);
info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime);
info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 79c4817abc94..6e3c512054a6 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -168,12 +168,8 @@ void tcp_assign_congestion_control(struct sock *sk)
}
out:
rcu_read_unlock();
+ memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
- /* Clear out private data before diag gets it and
- * the ca has not been initialized.
- */
- if (ca->get_info)
- memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
if (ca->flags & TCP_CONG_NEEDS_ECN)
INET_ECN_xmit(sk);
else
@@ -200,11 +196,10 @@ static void tcp_reinit_congestion_control(struct sock *sk,
tcp_cleanup_congestion_control(sk);
icsk->icsk_ca_ops = ca;
icsk->icsk_ca_setsockopt = 1;
+ memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
- if (sk->sk_state != TCP_CLOSE) {
- memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+ if (sk->sk_state != TCP_CLOSE)
tcp_init_congestion_control(sk);
- }
}
/* Manage refcounts on socket close. */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 39c393cc0fd3..659d1baefb2b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -126,7 +126,8 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
#define REXMIT_LOST 1 /* retransmit packets marked lost */
#define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */
-static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
+static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
+ unsigned int len)
{
static bool __once __read_mostly;
@@ -137,8 +138,9 @@ static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
rcu_read_lock();
dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
- pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
- dev ? dev->name : "Unknown driver");
+ if (!dev || len >= dev->mtu)
+ pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
+ dev ? dev->name : "Unknown driver");
rcu_read_unlock();
}
}
@@ -161,8 +163,10 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
if (len >= icsk->icsk_ack.rcv_mss) {
icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
tcp_sk(sk)->advmss);
- if (unlikely(icsk->icsk_ack.rcv_mss != len))
- tcp_gro_dev_warn(sk, skb);
+ /* Account for possibly-removed options */
+ if (unlikely(len > icsk->icsk_ack.rcv_mss +
+ MAX_TCP_OPTION_SPACE))
+ tcp_gro_dev_warn(sk, skb, len);
} else {
/* Otherwise, we make more careful check taking into account,
* that SACKs block is variable.
@@ -874,22 +878,11 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
const int ts)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (metric > tp->reordering) {
- int mib_idx;
+ int mib_idx;
+ if (metric > tp->reordering) {
tp->reordering = min(sysctl_tcp_max_reordering, metric);
- /* This exciting event is worth to be remembered. 8) */
- if (ts)
- mib_idx = LINUX_MIB_TCPTSREORDER;
- else if (tcp_is_reno(tp))
- mib_idx = LINUX_MIB_TCPRENOREORDER;
- else if (tcp_is_fack(tp))
- mib_idx = LINUX_MIB_TCPFACKREORDER;
- else
- mib_idx = LINUX_MIB_TCPSACKREORDER;
-
- NET_INC_STATS(sock_net(sk), mib_idx);
#if FASTRETRANS_DEBUG > 1
pr_debug("Disorder%d %d %u f%u s%u rr%d\n",
tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
@@ -902,6 +895,18 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
}
tp->rack.reord = 1;
+
+ /* This exciting event is worth to be remembered. 8) */
+ if (ts)
+ mib_idx = LINUX_MIB_TCPTSREORDER;
+ else if (tcp_is_reno(tp))
+ mib_idx = LINUX_MIB_TCPRENOREORDER;
+ else if (tcp_is_fack(tp))
+ mib_idx = LINUX_MIB_TCPFACKREORDER;
+ else
+ mib_idx = LINUX_MIB_TCPSACKREORDER;
+
+ NET_INC_STATS(sock_net(sk), mib_idx);
}
/* This must be called before lost_out is incremented */
@@ -1930,6 +1935,7 @@ void tcp_enter_loss(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
struct sk_buff *skb;
+ bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
bool is_reneg; /* is receiver reneging on SACKs? */
bool mark_lost;
@@ -1989,15 +1995,18 @@ void tcp_enter_loss(struct sock *sk)
tp->high_seq = tp->snd_nxt;
tcp_ecn_queue_cwr(tp);
- /* F-RTO RFC5682 sec 3.1 step 1 mandates to disable F-RTO
- * if a previous recovery is underway, otherwise it may incorrectly
- * call a timeout spurious if some previously retransmitted packets
- * are s/acked (sec 3.2). We do not apply that retriction since
- * retransmitted skbs are permanently tagged with TCPCB_EVER_RETRANS
- * so FLAG_ORIG_SACK_ACKED is always correct. But we do disable F-RTO
- * on PTMU discovery to avoid sending new data.
+ /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
+ * loss recovery is underway except recurring timeout(s) on
+ * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
+ *
+ * In theory F-RTO can be used repeatedly during loss recovery.
+ * In practice this interacts badly with broken middle-boxes that
+ * falsely raise the receive window, which results in repeated
+ * timeouts and stop-and-go behavior.
*/
- tp->frto = sysctl_tcp_frto && !inet_csk(sk)->icsk_mtup.probe_size;
+ tp->frto = sysctl_tcp_frto &&
+ (new_recovery || icsk->icsk_retransmits) &&
+ !inet_csk(sk)->icsk_mtup.probe_size;
}
/* If ACK arrived pointing to a remembered SACK, it means that our
@@ -5541,6 +5550,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
struct inet_connection_sock *icsk = inet_csk(sk);
tcp_set_state(sk, TCP_ESTABLISHED);
+ icsk->icsk_ack.lrcvtime = tcp_time_stamp;
if (skb) {
icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
@@ -5759,7 +5769,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
* to stand against the temptation 8) --ANK
*/
inet_csk_schedule_ack(sk);
- icsk->icsk_ack.lrcvtime = tcp_time_stamp;
tcp_enter_quickack_mode(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
TCP_DELACK_MAX, TCP_RTO_MAX);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9a89b8deafae..575e19dcc017 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -279,10 +279,13 @@ EXPORT_SYMBOL(tcp_v4_connect);
*/
void tcp_v4_mtu_reduced(struct sock *sk)
{
- struct dst_entry *dst;
struct inet_sock *inet = inet_sk(sk);
- u32 mtu = tcp_sk(sk)->mtu_info;
+ struct dst_entry *dst;
+ u32 mtu;
+ if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+ return;
+ mtu = tcp_sk(sk)->mtu_info;
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
@@ -428,7 +431,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
switch (type) {
case ICMP_REDIRECT:
- do_redirect(icmp_skb, sk);
+ if (!sock_owned_by_user(sk))
+ do_redirect(icmp_skb, sk);
goto out;
case ICMP_SOURCE_QUENCH:
/* Just silently ignore these. */
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7e16243cdb58..65c0f3d13eca 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -460,6 +460,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U);
newicsk->icsk_rto = TCP_TIMEOUT_INIT;
+ newicsk->icsk_ack.lrcvtime = tcp_time_stamp;
newtp->packets_out = 0;
newtp->retrans_out = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 22548b5f05cb..a85d863c4419 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1267,7 +1267,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
* eventually). The difference is that pulled data not copied, but
* immediately discarded.
*/
-static void __pskb_trim_head(struct sk_buff *skb, int len)
+static int __pskb_trim_head(struct sk_buff *skb, int len)
{
struct skb_shared_info *shinfo;
int i, k, eat;
@@ -1277,7 +1277,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
__skb_pull(skb, eat);
len -= eat;
if (!len)
- return;
+ return 0;
}
eat = len;
k = 0;
@@ -1303,23 +1303,28 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
skb_reset_tail_pointer(skb);
skb->data_len -= len;
skb->len = skb->data_len;
+ return len;
}
/* Remove acked data from a packet in the transmit queue. */
int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
{
+ u32 delta_truesize;
+
if (skb_unclone(skb, GFP_ATOMIC))
return -ENOMEM;
- __pskb_trim_head(skb, len);
+ delta_truesize = __pskb_trim_head(skb, len);
TCP_SKB_CB(skb)->seq += len;
skb->ip_summed = CHECKSUM_PARTIAL;
- skb->truesize -= len;
- sk->sk_wmem_queued -= len;
- sk_mem_uncharge(sk, len);
- sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+ if (delta_truesize) {
+ skb->truesize -= delta_truesize;
+ sk->sk_wmem_queued -= delta_truesize;
+ sk_mem_uncharge(sk, delta_truesize);
+ sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+ }
/* Any change of skb->len requires recalculation of tso factor. */
if (tcp_skb_pcount(skb) > 1)
@@ -2999,6 +3004,8 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
{
struct sk_buff *skb;
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
+
/* NOTE: No TCP options attached and we never retransmit this. */
skb = alloc_skb(MAX_TCP_HEADER, priority);
if (!skb) {
@@ -3014,8 +3021,6 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
/* Send it off. */
if (tcp_transmit_skb(sk, skb, 0, priority))
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
-
- TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
}
/* Send a crossed SYN-ACK during socket establishment.
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 4ecb38ae8504..d8acbd9f477a 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -12,7 +12,8 @@ static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
/* Account for retransmits that are lost again */
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT);
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
+ tcp_skb_pcount(skb));
}
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 40d893556e67..b2ab411c6d37 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -249,7 +249,8 @@ void tcp_delack_timer_handler(struct sock *sk)
sk_mem_reclaim_partial(sk);
- if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+ if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+ !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
goto out;
if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -552,7 +553,8 @@ void tcp_write_timer_handler(struct sock *sk)
struct inet_connection_sock *icsk = inet_csk(sk);
int event;
- if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
+ if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+ !icsk->icsk_pending)
goto out;
if (time_after(icsk->icsk_timeout, jiffies)) {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index b2be1d9757ef..781250151d40 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -29,6 +29,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
u16 mac_len = skb->mac_len;
int udp_offset, outer_hlen;
__wsum partial;
+ bool need_ipsec;
if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
goto out;
@@ -62,8 +63,10 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
ufo = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
+ need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
/* Try to offload checksum if possible */
offload_csum = !!(need_csum &&
+ !need_ipsec &&
(skb->dev->features &
(is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) :
(NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-16 19:21:39 +0300