net: ioctl: Use kernel memory on protocol ioctl callbacks

Most of the ioctls to net protocols operates directly on userspace
argument (arg). Usually doing get_user()/put_user() directly in the
ioctl callback.  This is not flexible, because it is hard to reuse these
functions without passing userspace buffers.

Change the "struct proto" ioctls to avoid touching userspace memory and
operate on kernel buffers, i.e., all protocol's ioctl callbacks is
adapted to operate on a kernel memory other than on userspace (so, no
more {put,get}_user() and friends being called in the ioctl callback).

This changes the "struct proto" ioctl format in the following way:

    int                     (*ioctl)(struct sock *sk, int cmd,
-                                        unsigned long arg);
+                                        int *karg);

(Important to say that this patch does not touch the "struct proto_ops"
protocols)

So, the "karg" argument, which is passed to the ioctl callback, is a
pointer allocated to kernel space memory (inside a function wrapper).
This buffer (karg) may contain input argument (copied from userspace in
a prep function) and it might return a value/buffer, which is copied
back to userspace if necessary. There is not one-size-fits-all format
(that is I am using 'may' above), but basically, there are three type of
ioctls:

1) Do not read from userspace, returns a result to userspace
2) Read an input parameter from userspace, and does not return anything
  to userspace
3) Read an input from userspace, and return a buffer to userspace.

The default case (1) (where no input parameter is given, and an "int" is
returned to userspace) encompasses more than 90% of the cases, but there
are two other exceptions. Here is a list of exceptions:

* Protocol RAW:
   * cmd = SIOCGETVIFCNT:
     * input and output = struct sioc_vif_req
   * cmd = SIOCGETSGCNT
     * input and output = struct sioc_sg_req
   * Explanation: for the SIOCGETVIFCNT case, userspace passes the input
     argument, which is struct sioc_vif_req. Then the callback populates
     the struct, which is copied back to userspace.

* Protocol RAW6:
   * cmd = SIOCGETMIFCNT_IN6
     * input and output = struct sioc_mif_req6
   * cmd = SIOCGETSGCNT_IN6
     * input and output = struct sioc_sg_req6

* Protocol PHONET:
  * cmd == SIOCPNADDRESOURCE | SIOCPNDELRESOURCE
     * input int (4 bytes)
  * Nothing is copied back to userspace.

For the exception cases, functions sock_sk_ioctl_inout() will
copy the userspace input, and copy it back to kernel space.

The wrapper that prepare the buffer and put the buffer back to user is
sk_ioctl(), so, instead of calling sk->sk_prot->ioctl(), the callee now
calls sk_ioctl(), which will handle all cases.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230609152800.830401-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 56 insertions, 42 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 0e16ac8282c5..38e649fb4474 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -998,7 +998,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		break;
 	default:
 		if (sk->sk_prot->ioctl)
-			err = sk->sk_prot->ioctl(sk, cmd, arg);
+			err = sk_ioctl(sk, cmd, (void __user *)arg);
 		else
 			err = -ENOIOCTLCMD;
 		break;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index eec1f6df80d8..3f0c6d602fb7 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1547,6 +1547,28 @@ out:
 	return ret;
 }
 
+/* Execute if this ioctl is a special mroute ioctl */
+int ipmr_sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
+{
+	switch (cmd) {
+	/* These userspace buffers will be consumed by ipmr_ioctl() */
+	case SIOCGETVIFCNT: {
+		struct sioc_vif_req buffer;
+
+		return sock_ioctl_inout(sk, cmd, arg, &buffer,
+				      sizeof(buffer));
+		}
+	case SIOCGETSGCNT: {
+		struct sioc_sg_req buffer;
+
+		return sock_ioctl_inout(sk, cmd, arg, &buffer,
+				      sizeof(buffer));
+		}
+	}
+	/* return code > 0 means that the ioctl was not executed */
+	return 1;
+}
+
 /* Getsock opt support for the multicast routing system. */
 int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
 			 sockptr_t optlen)
@@ -1593,13 +1615,13 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
 }
 
 /* The IP multicast ioctl support routines. */
-int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
+int ipmr_ioctl(struct sock *sk, int cmd, void *arg)
 {
-	struct sioc_sg_req sr;
-	struct sioc_vif_req vr;
 	struct vif_device *vif;
 	struct mfc_cache *c;
 	struct net *net = sock_net(sk);
+	struct sioc_vif_req *vr;
+	struct sioc_sg_req *sr;
 	struct mr_table *mrt;
 
 	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
@@ -1608,40 +1630,33 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
 
 	switch (cmd) {
 	case SIOCGETVIFCNT:
-		if (copy_from_user(&vr, arg, sizeof(vr)))
-			return -EFAULT;
-		if (vr.vifi >= mrt->maxvif)
+		vr = (struct sioc_vif_req *)arg;
+		if (vr->vifi >= mrt->maxvif)
 			return -EINVAL;
-		vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif);
+		vr->vifi = array_index_nospec(vr->vifi, mrt->maxvif);
 		rcu_read_lock();
-		vif = &mrt->vif_table[vr.vifi];
-		if (VIF_EXISTS(mrt, vr.vifi)) {
-			vr.icount = READ_ONCE(vif->pkt_in);
-			vr.ocount = READ_ONCE(vif->pkt_out);
-			vr.ibytes = READ_ONCE(vif->bytes_in);
-			vr.obytes = READ_ONCE(vif->bytes_out);
+		vif = &mrt->vif_table[vr->vifi];
+		if (VIF_EXISTS(mrt, vr->vifi)) {
+			vr->icount = READ_ONCE(vif->pkt_in);
+			vr->ocount = READ_ONCE(vif->pkt_out);
+			vr->ibytes = READ_ONCE(vif->bytes_in);
+			vr->obytes = READ_ONCE(vif->bytes_out);
 			rcu_read_unlock();
 
-			if (copy_to_user(arg, &vr, sizeof(vr)))
-				return -EFAULT;
 			return 0;
 		}
 		rcu_read_unlock();
 		return -EADDRNOTAVAIL;
 	case SIOCGETSGCNT:
-		if (copy_from_user(&sr, arg, sizeof(sr)))
-			return -EFAULT;
+		sr = (struct sioc_sg_req *)arg;
 
 		rcu_read_lock();
-		c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr);
+		c = ipmr_cache_find(mrt, sr->src.s_addr, sr->grp.s_addr);
 		if (c) {
-			sr.pktcnt = c->_c.mfc_un.res.pkt;
-			sr.bytecnt = c->_c.mfc_un.res.bytes;
-			sr.wrong_if = c->_c.mfc_un.res.wrong_if;
+			sr->pktcnt = c->_c.mfc_un.res.pkt;
+			sr->bytecnt = c->_c.mfc_un.res.bytes;
+			sr->wrong_if = c->_c.mfc_un.res.wrong_if;
 			rcu_read_unlock();
-
-			if (copy_to_user(arg, &sr, sizeof(sr)))
-				return -EFAULT;
 			return 0;
 		}
 		rcu_read_unlock();
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 9aacce9db7b9..7782ff5e6539 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -856,29 +856,29 @@ static int raw_getsockopt(struct sock *sk, int level, int optname,
 	return do_raw_getsockopt(sk, level, optname, optval, optlen);
 }
 
-static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
+static int raw_ioctl(struct sock *sk, int cmd, int *karg)
 {
 	switch (cmd) {
 	case SIOCOUTQ: {
-		int amount = sk_wmem_alloc_get(sk);
-
-		return put_user(amount, (int __user *)arg);
+		*karg = sk_wmem_alloc_get(sk);
+		return 0;
 	}
 	case SIOCINQ: {
 		struct sk_buff *skb;
-		int amount = 0;
 
 		spin_lock_bh(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)
-			amount = skb->len;
+			*karg = skb->len;
+		else
+			*karg = 0;
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
-		return put_user(amount, (int __user *)arg);
+		return 0;
 	}
 
 	default:
 #ifdef CONFIG_IP_MROUTE
-		return ipmr_ioctl(sk, cmd, (void __user *)arg);
+		return ipmr_ioctl(sk, cmd, karg);
 #else
 		return -ENOIOCTLCMD;
 #endif
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fba6578bc98f..0e21ea92dc1d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -599,7 +599,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 }
 EXPORT_SYMBOL(tcp_poll);
 
-int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+int tcp_ioctl(struct sock *sk, int cmd, int *karg)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int answ;
@@ -641,7 +641,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		return -ENOIOCTLCMD;
 	}
 
-	return put_user(answ, (int __user *)arg);
+	*karg = answ;
+	return 0;
 }
 EXPORT_SYMBOL(tcp_ioctl);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7e0542c10471..48fdcd3cad9c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1692,21 +1692,19 @@ static int first_packet_length(struct sock *sk)
  *	IOCTL requests applicable to the UDP protocol
  */
 
-int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+int udp_ioctl(struct sock *sk, int cmd, int *karg)
 {
 	switch (cmd) {
 	case SIOCOUTQ:
 	{
-		int amount = sk_wmem_alloc_get(sk);
-
-		return put_user(amount, (int __user *)arg);
+		*karg = sk_wmem_alloc_get(sk);
+		return 0;
 	}
 
 	case SIOCINQ:
 	{
-		int amount = max_t(int, 0, first_packet_length(sk));
-
-		return put_user(amount, (int __user *)arg);
+		*karg = max_t(int, 0, first_packet_length(sk));
+		return 0;
 	}
 
 	default: