netlink: Add new socket option to enable strict checking on dumps

Add a new socket option, NETLINK_DUMP_STRICT_CHK, that userspace
can use via setsockopt to request strict checking of headers and
attributes on dump requests.

To get dump features such as kernel side filtering based on data in
the header or attributes appended to the dump request, userspace
must call setsockopt() for NETLINK_DUMP_STRICT_CHK and a non-zero
value. Since the netlink sock and its flags are private to the
af_netlink code, the strict checking flag is passed to dump handlers
via a flag in the netlink_callback struct.

For old userspace on new kernel there is no impact as all of the data
checks in later patches are wrapped in a check on the new strict flag.

For new userspace on old kernel, the setsockopt will fail and even if
new userspace sets data in the headers and appended attributes the
kernel will silently ignore it. Moving forward when the setsockopt
succeeds, the new userspace on old kernel means the dump request can
pass an attribute the kernel does not understand. The dump will then
fail as the older kernel does not understand it.

New userspace on new kernel setting the socket option gets the benefit
of the improved data dump.

Kernel side the NETLINK_DUMP_STRICT_CHK uapi is converted to a generic
NETLINK_F_STRICT_CHK flag which can potentially be leveraged for tighter
checking on the NEW, DEL, and SET commands.

Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Christian Brauner <christian@brauner.io>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netlink.h

@@ -179,6 +179,7 @@ struct netlink_callback {
 	struct netlink_ext_ack	*extack;
 	u16			family;
 	u16			min_dump_alloc;
+	bool			strict_check;
 	unsigned int		prev_seq, seq;
 	long			args[6];
 };

include/uapi/linux/netlink.h

@@ -155,6 +155,7 @@ enum nlmsgerr_attrs {
 #define NETLINK_LIST_MEMBERSHIPS	9
 #define NETLINK_CAP_ACK			10
 #define NETLINK_EXT_ACK			11
+#define NETLINK_DUMP_STRICT_CHK		12
 
 struct nl_pktinfo {
 	__u32	group;

net/netlink/af_netlink.c

@@ -1706,6 +1706,13 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			nlk->flags &= ~NETLINK_F_EXT_ACK;
 		err = 0;
 		break;
+	case NETLINK_DUMP_STRICT_CHK:
+		if (val)
+			nlk->flags |= NETLINK_F_STRICT_CHK;
+		else
+			nlk->flags &= ~NETLINK_F_STRICT_CHK;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -1799,6 +1806,15 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 			return -EFAULT;
 		err = 0;
 		break;
+	case NETLINK_DUMP_STRICT_CHK:
+		if (len < sizeof(int))
+			return -EINVAL;
+		len = sizeof(int);
+		val = nlk->flags & NETLINK_F_STRICT_CHK ? 1 : 0;
+		if (put_user(len, optlen) || put_user(val, optval))
+			return -EFAULT;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -2282,9 +2298,9 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 			 const struct nlmsghdr *nlh,
 			 struct netlink_dump_control *control)
 {
+	struct netlink_sock *nlk, *nlk2;
 	struct netlink_callback *cb;
 	struct sock *sk;
-	struct netlink_sock *nlk;
 	int ret;
 
 	refcount_inc(&skb->users);
@@ -2318,6 +2334,9 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	cb->min_dump_alloc = control->min_dump_alloc;
 	cb->skb = skb;
 
+	nlk2 = nlk_sk(NETLINK_CB(skb).sk);
+	cb->strict_check = !!(nlk2->flags & NETLINK_F_STRICT_CHK);
+
 	if (control->start) {
 		ret = control->start(cb);
 		if (ret)

net/netlink/af_netlink.h

@@ -15,6 +15,7 @@
 #define NETLINK_F_LISTEN_ALL_NSID	0x10
 #define NETLINK_F_CAP_ACK		0x20
 #define NETLINK_F_EXT_ACK		0x40
+#define NETLINK_F_STRICT_CHK		0x80
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
 #define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))