[Devel] [PATCH RHEL COMMIT] ve/net: ip_vti: skip per net init in ve

[Konstantin Khorenko]

The commit is pushed to "branch-rh9-5.14.vz9.1.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after ark-5.14
------>
commit d278b36ce34a61d786acb2cf5f61ba47a230b0c5
Author: Vladimir Davydov <vdavydov.dev at gmail.com>
Date:   Fri Sep 24 14:50:19 2021 +0300

    ve/net: ip_vti: skip per net init in ve
    
    ip_vti devices lack NETIF_F_VIRTUAL, so they can't be created inside a
    container. Problem is a device of this kind is created on net ns init if
    the module is loaded, as a result a container start fails with EPERM.
    
    We could allow ip_vti inside container (as well as other net devices,
    which I would really like to do), but this is insecure and might break
    migration, so let's keep it disabled and fix the issue by silently
    skipping ip_vti per net init if running inside a ve.
    
    https://jira.sw.ru/browse/PSBM-48698
    
    Signed-off-by: Vladimir Davydov <vdavydov at virtuozzo.com>
    
    Rebased to RHEL8 beta kernel:
    Signed-off-by: Konstantin Khorenko <khorenko at virtuozzo.com>
    
    https://jira.sw.ru/browse/PSBM-133986
    
    (cherry picked from commit d2fc3d088444fff6c12b27b3754de2ace1ffaff2)
    Signed-off-by: Alexander Mikhalitsyn <alexander.mikhalitsyn at virtuozzo.com>
---
 net/ipv4/ip_vti.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index eb560eecee08..f9642e4ebda3 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -39,6 +39,8 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
+#include <linux/ve.h>
+
 static struct rtnl_link_ops vti_link_ops __read_mostly;
 
 static unsigned int vti_net_id __read_mostly;
@@ -52,6 +54,9 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
 	struct net *net = dev_net(skb->dev);
 	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
 
+	if (itn == NULL)
+		return -EINVAL;
+
 	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 				  iph->saddr, iph->daddr, 0);
 	if (tunnel) {
@@ -323,6 +328,9 @@ static int vti4_err(struct sk_buff *skb, u32 info)
 	int protocol = iph->protocol;
 	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
 
+	if (itn == NULL)
+		return -1;
+
 	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 				  iph->daddr, iph->saddr, 0);
 	if (!tunnel)
@@ -501,6 +509,11 @@ static int __net_init vti_init_net(struct net *net)
 	int err;
 	struct ip_tunnel_net *itn;
 
+	if (!ve_is_super(net->owner_ve)) {
+		net_generic_free(net, vti_net_id);
+		return 0;
+	}
+
 	err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0");
 	if (err)
 		return err;
@@ -567,6 +580,9 @@ static int vti_newlink(struct net *src_net, struct net_device *dev,
 	struct ip_tunnel_parm parms;
 	__u32 fwmark = 0;
 
+	if (net_generic(dev_net(dev), vti_net_id) == NULL)
+		return -EACCES;
+
 	vti_netlink_parms(data, &parms, &fwmark);
 	return ip_tunnel_newlink(dev, tb, &parms, fwmark);
 }