[PATCH net] ip6_gre: init dev->mtu and dev->hard_header_len correctly

[PATCH net] ip6_gre: init dev->mtu and dev->hard_header_len correctly

[Alexey Kodanev]

Commit b05229f44228 ("gre6: Cleanup GREv6 transmit path,
call common GRE functions") moved dev->mtu initialization
from ip6gre_tunnel_setup() to ip6gre_tunnel_init(), as a
result, the previously set values, before ndo_init(), are
reset in the following cases:

* rtnl_create_link() can update dev->mtu from IFLA_MTU
  parameter

* ip6gre_tnl_link_config() is invoked before ndo_init() in
  netlink and ioctl setup, so ndo_init() can reset MTU
  adjustments with the lower device MTU as well, dev->mtu
  and dev->hard_header_len.

  Not applicable for ip6gretap because it has one more call
  to ip6gre_tnl_link_config(tunnel, 1) in ip6gre_tap_init().

Since, initially net_device allocated with kvzalloc, make sure
that dev->mtu is zero, i.e. not changed, before setting default
MTU inside ndo_init(), and invoke ip6gre_tnl_link_config after
setting default values.

For ip6gretap, reset dev->mtu to zero in ip6gre_tap_setup()
after ether_setup(), in order for it to work with the new check
in ip6gre_tunnel_init_common().

Fixes: b05229f44228 ("gre6: Cleanup GREv6 transmit path, call common GRE functions")
Fixes: db2ec95d1ba4 ("ip6_gre: Fix MTU setting")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
---
 net/ipv6/ip6_gre.c |   22 ++++++++++------------
 1 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 7726959..edf65d0 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -337,7 +337,6 @@ static void ip6gre_tunnel_unlink(struct ip6gre_net *ign, struct ip6_tnl *t)
 
 	nt->dev = dev;
 	nt->net = dev_net(dev);
-	ip6gre_tnl_link_config(nt, 1);
 
 	if (register_netdevice(dev) < 0)
 		goto failed_free;
@@ -1047,6 +1046,7 @@ static void ip6gre_tnl_init_features(struct net_device *dev)
 static int ip6gre_tunnel_init_common(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
+	int set_mtu = !dev->mtu;
 	int ret;
 	int t_hlen;
 
@@ -1072,13 +1072,16 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
 	t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
 
 	dev->hard_header_len = LL_MAX_HEADER + t_hlen;
-	dev->mtu = ETH_DATA_LEN - t_hlen;
-	if (dev->type == ARPHRD_ETHER)
-		dev->mtu -= ETH_HLEN;
-	if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
-		dev->mtu -= 8;
+	if (set_mtu) {
+		dev->mtu = ETH_DATA_LEN - t_hlen;
+		if (dev->type == ARPHRD_ETHER)
+			dev->mtu -= ETH_HLEN;
+		if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+			dev->mtu -= 8;
+	}
 
 	ip6gre_tnl_init_features(dev);
+	ip6gre_tnl_link_config(tunnel, set_mtu);
 
 	return 0;
 }
@@ -1303,7 +1306,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 
 static int ip6gre_tap_init(struct net_device *dev)
 {
-	struct ip6_tnl *tunnel;
 	int ret;
 
 	ret = ip6gre_tunnel_init_common(dev);
@@ -1312,10 +1314,6 @@ static int ip6gre_tap_init(struct net_device *dev)
 
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
-	tunnel = netdev_priv(dev);
-
-	ip6gre_tnl_link_config(tunnel, 1);
-
 	return 0;
 }
 
@@ -1335,6 +1333,7 @@ static void ip6gre_tap_setup(struct net_device *dev)
 
 	ether_setup(dev);
 
+	dev->mtu = 0;
 	dev->max_mtu = 0;
 	dev->netdev_ops = &ip6gre_tap_netdev_ops;
 	dev->needs_free_netdev = true;
@@ -1408,7 +1407,6 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
 
 	nt->dev = dev;
 	nt->net = dev_net(dev);
-	ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
 
 	err = register_netdevice(dev);
 	if (err)
-- 
1.7.1

Re: [PATCH net] ip6_gre: init dev->mtu and dev->hard_header_len correctly

[David Miller]

From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Thu, 11 Jan 2018 16:02:54 +0300

> For ip6gretap, reset dev->mtu to zero in ip6gre_tap_setup()
> after ether_setup(), in order for it to work with the new check
> in ip6gre_tunnel_init_common().

This part is error prone.  Please instead add a new boolean argument
to ip6gre_tunnel_init_common: "bool set_mtu".  Set it to true when
it is invoked from ip6gre_tap_init() and false when it is invoked
from ip6gre_tunnel_init().

Thank you.

Re: [PATCH net] ip6_gre: init dev->mtu and dev->hard_header_len correctly

[Alexey Kodanev]

On 01/16/2018 07:32 PM, David Miller wrote:
> From: Alexey Kodanev <alexey.kodanev@oracle.com>
> Date: Thu, 11 Jan 2018 16:02:54 +0300
> 
>> For ip6gretap, reset dev->mtu to zero in ip6gre_tap_setup()
>> after ether_setup(), in order for it to work with the new check
>> in ip6gre_tunnel_init_common().
> 
> This part is error prone.  Please instead add a new boolean argument
> to ip6gre_tunnel_init_common: "bool set_mtu".  Set it to true when
> it is invoked from ip6gre_tap_init() and false when it is invoked
> from ip6gre_tunnel_init().

Hi David,

This way it won't fix the first regression mentioned in the patch for
ip6gretap, i.e. if a user sets a MTU manually on the device creation.

May be it would be less error prone if a MTU is adjusted again in
ip6gre_newlink with "tb[IFLA_MTU]" parameter and ip6gre_tnl_link_config()
is moved after register_netdevice()? I haven't tested the following patch
yet but it looks like it is fixing all the mentioned cases as well:

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 7726959..d12550e 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -337,11 +337,12 @@ static void ip6gre_tunnel_unlink(struct ip6gre_net *ign, struct ip6_tnl *t)

        nt->dev = dev;
        nt->net = dev_net(dev);
-       ip6gre_tnl_link_config(nt, 1);

        if (register_netdevice(dev) < 0)
                goto failed_free;

+       ip6gre_tnl_link_config(nt, 1);
+
        /* Can use a lockless transmit, unless we generate output sequences */
        if (!(nt->parms.o_flags & TUNNEL_SEQ))
                dev->features |= NETIF_F_LLTX;
@@ -1303,7 +1304,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[],

 static int ip6gre_tap_init(struct net_device *dev)
 {
-       struct ip6_tnl *tunnel;
        int ret;

        ret = ip6gre_tunnel_init_common(dev);
@@ -1312,10 +1312,6 @@ static int ip6gre_tap_init(struct net_device *dev)

        dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;

-       tunnel = netdev_priv(dev);
-
-       ip6gre_tnl_link_config(tunnel, 1);
-
        return 0;
 }

@@ -1408,12 +1404,16 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,

        nt->dev = dev;
        nt->net = dev_net(dev);
-       ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);

        err = register_netdevice(dev);
        if (err)
                goto out;

+       ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
+
+       if (tb[IFLA_MTU])
+               dev->mtu = nla_get_u32(tb[IFLA_MTU]);
+
        dev_hold(dev);
        ip6gre_tunnel_link(ign, nt);


Thanks,
Alexey