[PATCH net v4] openvswitch: cap upcall PID array size and pre-size vport replies

[Weiming Shi <bestswngs@gmail.com>]

The vport netlink reply helpers allocate a fixed-size skb with
nlmsg_new(NLMSG_DEFAULT_SIZE, ...) but serialize the full upcall PID
array via ovs_vport_get_upcall_portids().  Since
ovs_vport_set_upcall_portids() accepts any non-zero multiple of
sizeof(u32) with no upper bound, a CAP_NET_ADMIN user can install a PID
array large enough to overflow the reply buffer, causing nla_put() to
fail with -EMSGSIZE and hitting BUG_ON(err < 0).  On systems with
unprivileged user namespaces enabled (e.g., Ubuntu default), this is
reachable via unshare -Urn since OVS vport mutation operations use
GENL_UNS_ADMIN_PERM.

 kernel BUG at net/openvswitch/datapath.c:2414!
 Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI
 CPU: 1 UID: 0 PID: 65 Comm: poc Not tainted 7.0.0-rc7-00195-geb216e422044 #1
 RIP: 0010:ovs_vport_cmd_set+0x34c/0x400
 Call Trace:
  <TASK>
  genl_family_rcv_msg_doit (net/netlink/genetlink.c:1116)
  genl_rcv_msg (net/netlink/genetlink.c:1194)
  netlink_rcv_skb (net/netlink/af_netlink.c:2550)
  genl_rcv (net/netlink/genetlink.c:1219)
  netlink_unicast (net/netlink/af_netlink.c:1344)
  netlink_sendmsg (net/netlink/af_netlink.c:1894)
  __sys_sendto (net/socket.c:2206)
  __x64_sys_sendto (net/socket.c:2209)
  do_syscall_64 (arch/x86/entry/syscall_64.c:63)
  entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
  </TASK>
 Kernel panic - not syncing: Fatal exception

Reject attempts to set more PIDs than nr_cpu_ids in
ovs_vport_set_upcall_portids(), and pre-compute the worst-case reply
size in ovs_vport_cmd_msg_size() based on that bound, similar to the
existing ovs_dp_cmd_msg_size().  nr_cpu_ids matches the cap already
used by the per-CPU dispatch configuration on the datapath side
(ovs_dp_cmd_fill_info() serialises at most nr_cpu_ids PIDs), so the
two sides stay consistent.

Fixes: 5cd667b0a456 ("openvswitch: Allow each vport to have an array of 'port_id's.")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
---
v4 (per Ilya):
- Use nr_cpu_ids instead of num_possible_cpus() for consistency with
  the per-CPU dispatch on the datapath side.
- Annotate ovs_vport_cmd_msg_size() per-attribute; split nested sums.
v3: Cap at num_possible_cpus(); add ovs_vport_cmd_msg_size(); keep
    BUG_ON(); fix Fixes tag.
v2: Dynamically size reply skb; drop WARN_ON_ONCE, return plain errors.
---
 net/openvswitch/datapath.c | 33 +++++++++++++++++++++++++++++++--
 net/openvswitch/vport.c    |  3 +++
 2 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index e209099218b4..35e67e51b0d2 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -2184,9 +2184,38 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
 	return err;
 }
 
+static size_t ovs_vport_cmd_msg_size(void)
+{
+	size_t msgsize = NLMSG_ALIGN(sizeof(struct ovs_header));
+
+	msgsize += nla_total_size(sizeof(u32)); /* OVS_VPORT_ATTR_PORT_NO */
+	msgsize += nla_total_size(sizeof(u32)); /* OVS_VPORT_ATTR_TYPE */
+	msgsize += nla_total_size(IFNAMSIZ);    /* OVS_VPORT_ATTR_NAME */
+	msgsize += nla_total_size(sizeof(u32)); /* OVS_VPORT_ATTR_IFINDEX */
+	msgsize += nla_total_size(sizeof(s32)); /* OVS_VPORT_ATTR_NETNSID */
+	/* OVS_VPORT_ATTR_STATS */
+	msgsize += nla_total_size_64bit(sizeof(struct ovs_vport_stats));
+	/* OVS_VPORT_ATTR_UPCALL_STATS(OVS_VPORT_UPCALL_ATTR_SUCCESS +
+	 *                             OVS_VPORT_UPCALL_ATTR_FAIL)
+	 */
+	msgsize += nla_total_size(nla_total_size_64bit(sizeof(u64)) +
+				  nla_total_size_64bit(sizeof(u64)));
+	/* OVS_VPORT_ATTR_UPCALL_PID (capped at nr_cpu_ids by
+	 * ovs_vport_set_upcall_portids())
+	 */
+	msgsize += nla_total_size(nr_cpu_ids * sizeof(u32));
+	/* OVS_VPORT_ATTR_OPTIONS(OVS_TUNNEL_ATTR_DST_PORT +
+	 *                        OVS_TUNNEL_ATTR_EXTENSION(OVS_VXLAN_EXT_GBP))
+	 */
+	msgsize += nla_total_size(nla_total_size(sizeof(u16)) +
+				  nla_total_size(nla_total_size(0)));
+
+	return msgsize;
+}
+
 static struct sk_buff *ovs_vport_cmd_alloc_info(void)
 {
-	return nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	return genlmsg_new(ovs_vport_cmd_msg_size(), GFP_KERNEL);
 }
 
 /* Called with ovs_mutex, only via ovs_dp_notify_wq(). */
@@ -2196,7 +2225,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net,
 	struct sk_buff *skb;
 	int retval;
 
-	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	skb = ovs_vport_cmd_alloc_info();
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 23f629e94a36..56b2e2d1a749 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -406,6 +406,9 @@ int ovs_vport_set_upcall_portids(struct vport *vport, const struct nlattr *ids)
 	if (!nla_len(ids) || nla_len(ids) % sizeof(u32))
 		return -EINVAL;
 
+	if (nla_len(ids) / sizeof(u32) > nr_cpu_ids)
+		return -EINVAL;
+
 	old = ovsl_dereference(vport->upcall_portids);
 
 	vport_portids = kmalloc(sizeof(*vport_portids) + nla_len(ids),
-- 
2.43.0