path: root/net/ipv4
diff options
authorLinus Torvalds <torvalds@linux-foundation.org>2018-01-26 09:03:16 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-01-26 09:03:16 -0800
commitba804bb4b72e57374b5f567b783aa0298fba0ce6 (patch)
tree8d30198c5decc79a0666239b10babe3f9cb2e910 /net/ipv4
parentMerge tag 'drm-fixes-for-v4.15-rc10-2' of git://people.freedesktop.org/~airlied/linux (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller: 1) The per-network-namespace loopback device, and thus its namespace, can have its teardown deferred for a long time if a kernel created TCP socket closes and the namespace is exiting meanwhile. The kernel keeps trying to finish the close sequence until it times out (which takes quite some time). Fix this by forcing the socket closed in this situation, from Dan Streetman. 2) Fix regression where we're trying to invoke the update_pmtu method on route types (in this case metadata tunnel routes) that don't implement the dst_ops method. Fix from Nicolas Dichtel. 3) Fix long standing memory corruption issues in r8169 driver by performing the chip statistics DMA programming more correctly. From Francois Romieu. 4) Handle local broadcast sends over VRF routes properly, from David Ahern. 5) Don't refire the DCCP CCID2 timer endlessly, otherwise the socket can never be released. From Alexey Kodanev. 6) Set poll flags properly in VSOCK protocol layer, from Stefan Hajnoczi. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: VSOCK: set POLLOUT | POLLWRNORM for TCP_CLOSING dccp: don't restart ccid2_hc_tx_rto_expire() if sk in closed state net: vrf: Add support for sends to local broadcast address r8169: fix memory corruption on retrieval of hardware statistics. net: don't call update_pmtu unconditionally net: tcp: close sock if net namespace is exiting
Diffstat (limited to 'net/ipv4')
4 files changed, 20 insertions, 3 deletions
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 5ddb1cb52bd4..6d21068f9b55 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -520,8 +520,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
- if (skb_dst(skb))
- skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+ skb_dst_update_pmtu(skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
if (!skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 949f432a5f04..51b1669334fe 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -200,7 +200,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
mtu = dst_mtu(dst);
if (skb->len > mtu) {
- skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+ skb_dst_update_pmtu(skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f08eebe60446..8e053ad7cae2 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2298,6 +2298,9 @@ adjudge_to_death:
tcp_send_active_reset(sk, GFP_ATOMIC);
+ } else if (!check_net(sock_net(sk))) {
+ /* Not possible to send reset; just close */
+ tcp_set_state(sk, TCP_CLOSE);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 968fda198376..388158c9d9f6 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -48,11 +48,19 @@ static void tcp_write_err(struct sock *sk)
* to prevent DoS attacks. It is called when a retransmission timeout
* or zero probe timeout occurs on orphaned socket.
+ * Also close if our net namespace is exiting; in that case there is no
+ * hope of ever communicating again since all netns interfaces are already
+ * down (or about to be down), and we need to release our dst references,
+ * which have been moved to the netns loopback interface, so the namespace
+ * can finish exiting. This condition is only possible if we are a kernel
+ * socket, as those do not hold references to the namespace.
+ *
* Criteria is still not confirmed experimentally and may change.
* We kill the socket, if:
* 1. If number of orphaned sockets exceeds an administratively configured
* limit.
* 2. If we have strong memory pressure.
+ * 3. If our net namespace is exiting.
static int tcp_out_of_resources(struct sock *sk, bool do_reset)
@@ -81,6 +89,13 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
return 1;
+ if (!check_net(sock_net(sk))) {
+ /* Not possible to send reset; just close */
+ tcp_done(sk);
+ return 1;
+ }
return 0;