[PATCH] netlink, audit: prevent false ENOBUFS on timeout expiry

[PATCH] netlink, audit: prevent false ENOBUFS on timeout expiry

[Ricardo Robaina]

When auditd is bottlenecked (e.g., by slow disk I/O), kauditd blocks on
the netlink socket. If the wait timeout fully expires (timeo == 0),
netlink mistakenly interprets the zeroed timeout as a non-blocking
request. It then triggers netlink_overrun that drops the event,
completely bypassing the audit subsystem's internal retry queue, and
falsely returns ENOBUFS to user-space, resulting in the following error:

 auditd[]: Error receiving audit netlink packet (No buffer space available)

Convert the `nonblock` argument in netlink_unicast() into a `flags`
bitmask and introduce NETLINK_UNICAST_TIMED. When a caller specifies
this flag and exhausts its timeout budget, netlink intercepts the
zeroed timeo state. Instead of defaulting to an overrun condition, it
safely frees the skb and returns -EAGAIN, allowing the audit subsystem
to gracefully enqueue the pending event into its internal backlog.

Suggested-by: Steve Grubb <sgrubb@redhat.com>
Signed-off-by: Ricardo Robaina <rrobaina@redhat.com>
---
 include/linux/netlink.h  |  5 ++++-
 kernel/audit.c           |  8 ++++----
 net/netlink/af_netlink.c | 17 +++++++++++++++--
 3 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 882e9c1b6c1d..1888c8ee416a 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -226,7 +226,10 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 int netlink_has_listeners(struct sock *sk, unsigned int group);
 bool netlink_strict_get_check(struct sk_buff *skb);
 
-int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
+/* Internal flags for netlink_unicast (do not overlap with MSG_* flags) */
+#define NETLINK_UNICAST_TIMED 0x80000
+
+int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int flags);
 int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid,
 		      __u32 group, gfp_t allocation);
 
diff --git a/kernel/audit.c b/kernel/audit.c
index e1d489bc2dff..005bfd9dc7a4 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -753,7 +753,7 @@ static int auditd_send_unicast_skb(struct sk_buff *skb)
 	portid = ac->portid;
 	rcu_read_unlock();
 
-	rc = netlink_unicast(sk, skb, portid, 0);
+	rc = netlink_unicast(sk, skb, portid, NETLINK_UNICAST_TIMED);
 	put_net(net);
 	if (rc < 0)
 		goto err;
@@ -811,7 +811,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid,
 retry:
 		/* grab an extra skb reference in case of error */
 		skb_get(skb);
-		rc = netlink_unicast(sk, skb, portid, 0);
+		rc = netlink_unicast(sk, skb, portid, NETLINK_UNICAST_TIMED);
 		if (rc < 0) {
 			/* send failed - try a few times unless fatal error */
 			if (++failed >= retry_limit ||
@@ -967,7 +967,7 @@ int audit_send_list_thread(void *_dest)
 	audit_ctl_unlock();
 
 	while ((skb = __skb_dequeue(&dest->q)) != NULL)
-		netlink_unicast(sk, skb, dest->portid, 0);
+		netlink_unicast(sk, skb, dest->portid, NETLINK_UNICAST_TIMED);
 
 	put_net(dest->net);
 	kfree(dest);
@@ -1020,7 +1020,7 @@ static int audit_send_reply_thread(void *arg)
 
 	/* Ignore failure. It'll only happen if the sender goes away,
 	   because our timeout is set to infinite. */
-	netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, 0);
+	netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, NETLINK_UNICAST_TIMED);
 	reply->skb = NULL;
 	audit_free_reply(reply);
 	return 0;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 2aeb0680807d..acaa96695981 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1325,14 +1325,17 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb,
 }
 
 int netlink_unicast(struct sock *ssk, struct sk_buff *skb,
-		    u32 portid, int nonblock)
+		    u32 portid, int flags)
 {
 	struct sock *sk;
 	int err;
 	long timeo;
+	int nonblock;
 
 	skb = netlink_trim(skb, gfp_any());
 
+	/* Extract blocking mode: strip internal flags, preserve MSG_DONTWAIT */
+	nonblock = flags & ~NETLINK_UNICAST_TIMED;
 	timeo = sock_sndtimeo(ssk, nonblock);
 retry:
 	sk = netlink_getsockbyportid(ssk, portid);
@@ -1351,8 +1354,18 @@ int netlink_unicast(struct sock *ssk, struct sk_buff *skb,
 	}
 
 	err = netlink_attachskb(sk, skb, &timeo, ssk);
-	if (err == 1)
+	if (err == 1) {
+		/* timeo may have been zeroed by schedule_timeout inside
+		 * netlink_attachskb. If the caller is a timed-blocking sender
+		 * (not genuinely nonblocking), don't re-enter with timeo=0 as
+		 * that would misfire netlink_overrun on the next iteration.
+		 */
+		if (!timeo && (flags & NETLINK_UNICAST_TIMED)) {
+			kfree_skb(skb);
+			return -EAGAIN;
+		}
 		goto retry;
+	}
 	if (err)
 		return err;
 
-- 
2.53.0