ipv6: make ipv6_renew_options() interrupt/kernel safe

At present the ipv6_renew_options_kern() function ends up calling into
access_ok() which is problematic if done from inside an interrupt as
access_ok() calls WARN_ON_IN_IRQ() on some (all?) architectures
(x86-64 is affected).  Example warning/backtrace is shown below:

 WARNING: CPU: 1 PID: 3144 at lib/usercopy.c:11 _copy_from_user+0x85/0x90
 ...
 Call Trace:
  <IRQ>
  ipv6_renew_option+0xb2/0xf0
  ipv6_renew_options+0x26a/0x340
  ipv6_renew_options_kern+0x2c/0x40
  calipso_req_setattr+0x72/0xe0
  netlbl_req_setattr+0x126/0x1b0
  selinux_netlbl_inet_conn_request+0x80/0x100
  selinux_inet_conn_request+0x6d/0xb0
  security_inet_conn_request+0x32/0x50
  tcp_conn_request+0x35f/0xe00
  ? __lock_acquire+0x250/0x16c0
  ? selinux_socket_sock_rcv_skb+0x1ae/0x210
  ? tcp_rcv_state_process+0x289/0x106b
  tcp_rcv_state_process+0x289/0x106b
  ? tcp_v6_do_rcv+0x1a7/0x3c0
  tcp_v6_do_rcv+0x1a7/0x3c0
  tcp_v6_rcv+0xc82/0xcf0
  ip6_input_finish+0x10d/0x690
  ip6_input+0x45/0x1e0
  ? ip6_rcv_finish+0x1d0/0x1d0
  ipv6_rcv+0x32b/0x880
  ? ip6_make_skb+0x1e0/0x1e0
  __netif_receive_skb_core+0x6f2/0xdf0
  ? process_backlog+0x85/0x250
  ? process_backlog+0x85/0x250
  ? process_backlog+0xec/0x250
  process_backlog+0xec/0x250
  net_rx_action+0x153/0x480
  __do_softirq+0xd9/0x4f7
  do_softirq_own_stack+0x2a/0x40
  </IRQ>
  ...

While not present in the backtrace, ipv6_renew_option() ends up calling
access_ok() via the following chain:

  access_ok()
  _copy_from_user()
  copy_from_user()
  ipv6_renew_option()

The fix presented in this patch is to perform the userspace copy
earlier in the call chain such that it is only called when the option
data is actually coming from userspace; that place is
do_ipv6_setsockopt().  Not only does this solve the problem seen in
the backtrace above, it also allows us to simplify the code quite a
bit by removing ipv6_renew_options_kern() completely.  We also take
this opportunity to cleanup ipv6_renew_options()/ipv6_renew_option()
a small amount as well.

This patch is heavily based on a rough patch by Al Viro.  I've taken
his original patch, converted a kmemdup() call in do_ipv6_setsockopt()
to a memdup_user() call, made better use of the e_inval jump target in
the same function, and cleaned up the use ipv6_renew_option() by
ipv6_renew_options().

CC: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 19 insertions, 8 deletions

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 4d780c7f0130..c95c3486d904 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -398,6 +398,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 	case IPV6_DSTOPTS:
 	{
 		struct ipv6_txoptions *opt;
+		struct ipv6_opt_hdr *new = NULL;
+
+		/* hop-by-hop / destination options are privileged option */
+		retv = -EPERM;
+		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
+			break;
 
 		/* remove any sticky options header with a zero option
 		 * length, per RFC3542.
@@ -409,17 +415,22 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		else if (optlen < sizeof(struct ipv6_opt_hdr) ||
 			 optlen & 0x7 || optlen > 8 * 255)
 			goto e_inval;
-
-		/* hop-by-hop / destination options are privileged option */
-		retv = -EPERM;
-		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
-			break;
+		else {
+			new = memdup_user(optval, optlen);
+			if (IS_ERR(new)) {
+				retv = PTR_ERR(new);
+				break;
+			}
+			if (unlikely(ipv6_optlen(new) > optlen)) {
+				kfree(new);
+				goto e_inval;
+			}
+		}
 
 		opt = rcu_dereference_protected(np->opt,
 						lockdep_sock_is_held(sk));
-		opt = ipv6_renew_options(sk, opt, optname,
-					 (struct ipv6_opt_hdr __user *)optval,
-					 optlen);
+		opt = ipv6_renew_options(sk, opt, optname, new);
+		kfree(new);
 		if (IS_ERR(opt)) {
 			retv = PTR_ERR(opt);
 			break;