[PATCH net-next v2] netlink: split up copies in the ack construction

[Jakub Kicinski <kuba@kernel.org>]

Clean up the use of unsafe_memcpy() by adding a flexible array
at the end of netlink message header and splitting up the header
and data copies.

Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
v2: change the argument name in the kdoc as well :S
---
 include/net/netlink.h        | 21 +++++++++++++++++++++
 include/uapi/linux/netlink.h |  2 ++
 net/netlink/af_netlink.c     | 29 ++++++++++++++++++++---------
 3 files changed, 43 insertions(+), 9 deletions(-)

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 7db13b3261fc..d948cd30f11e 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -936,6 +936,27 @@ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 se
 	return __nlmsg_put(skb, portid, seq, type, payload, flags);
 }
 
+/**
+ * nlmsg_append - Add more data to a nlmsg in a skb
+ * @skb: socket buffer to store message in
+ * @size: length of message payload
+ *
+ * Append data to an existing nlmsg, used when constructing a message
+ * with multiple fixed-format headers (which is rare).
+ * Returns NULL if the tailroom of the skb is insufficient to store
+ * the extra payload.
+ */
+static inline void *nlmsg_append(struct sk_buff *skb, u32 size)
+{
+	if (unlikely(skb_tailroom(skb) < NLMSG_ALIGN(size)))
+		return NULL;
+
+	if (NLMSG_ALIGN(size) - size)
+		memset(skb_tail_pointer(skb) + size, 0,
+		       NLMSG_ALIGN(size) - size);
+	return __skb_put(skb, NLMSG_ALIGN(size));
+}
+
 /**
  * nlmsg_put_answer - Add a new callback based netlink message to an skb
  * @skb: socket buffer to store message in
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index e2ae82e3f9f7..5da0da59bf01 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -48,6 +48,7 @@ struct sockaddr_nl {
  * @nlmsg_flags: Additional flags
  * @nlmsg_seq:   Sequence number
  * @nlmsg_pid:   Sending process port ID
+ * @nlmsg_data:  Message payload
  */
 struct nlmsghdr {
 	__u32		nlmsg_len;
@@ -55,6 +56,7 @@ struct nlmsghdr {
 	__u16		nlmsg_flags;
 	__u32		nlmsg_seq;
 	__u32		nlmsg_pid;
+	__u8		nlmsg_data[];
 };
 
 /* Flags values */
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index f0c94d394ab1..b10d5e50b99d 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2499,19 +2499,24 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 		flags |= NLM_F_ACK_TLVS;
 
 	skb = nlmsg_new(payload + tlvlen, GFP_KERNEL);
-	if (!skb) {
-		NETLINK_CB(in_skb).sk->sk_err = ENOBUFS;
-		sk_error_report(NETLINK_CB(in_skb).sk);
-		return;
-	}
+	if (!skb)
+		goto err_bad_put;
 
 	rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
-			NLMSG_ERROR, payload, flags);
+			NLMSG_ERROR, sizeof(*errmsg), flags);
+	if (!rep)
+		goto err_bad_put;
 	errmsg = nlmsg_data(rep);
 	errmsg->error = err;
-	unsafe_memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg)
-					 ? nlh->nlmsg_len : sizeof(*nlh),
-		      /* Bounds checked by the skb layer. */);
+	errmsg->msg = *nlh;
+
+	if (!(flags & NLM_F_CAPPED)) {
+		if (!nlmsg_append(skb, nlmsg_len(nlh)))
+			goto err_bad_put;
+
+		memcpy(errmsg->msg.nlmsg_data, nlh->nlmsg_data,
+		       nlmsg_len(nlh));
+	}
 
 	if (tlvlen)
 		netlink_ack_tlv_fill(in_skb, skb, nlh, err, extack);
@@ -2519,6 +2524,12 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 	nlmsg_end(skb, rep);
 
 	nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid);
+
+	return;
+
+err_bad_put:
+	NETLINK_CB(in_skb).sk->sk_err = ENOBUFS;
+	sk_error_report(NETLINK_CB(in_skb).sk);
 }
 EXPORT_SYMBOL(netlink_ack);
 
-- 
2.37.3