net: track pfmemalloc drops via SKB_DROP_REASON_PFMEMALLOC

Add a new SKB drop reason (SKB_DROP_REASON_PFMEMALLOC) to track packets
dropped due to memory pressure. In production environments, we've observed
memory exhaustion reported by memory layer stack traces, but these drops
were not properly tracked in the SKB drop reason infrastructure.

While most network code paths now properly report pfmemalloc drops, some
protocol-specific socket implementations still use sk_filter() without
drop reason tracking:
- Bluetooth L2CAP sockets
- CAIF sockets
- IUCV sockets
- Netlink sockets
- SCTP sockets
- Unix domain sockets

These remaining cases represent less common paths and could be converted
in a follow-up patch if needed. The current implementation provides
significantly improved observability into memory pressure events in the
network stack, especially for key protocols like TCP and UDP, helping to
diagnose problems in production environments.

Reported-by: Matt Fleming <[email protected]>
Signed-off-by: Jesper Dangaard Brouer <[email protected]>
Link: https://patch.msgid.link/175268316579.2407873.11634752355644843509.stgit@firesoul
Signed-off-by: Jakub Kicinski <[email protected]>

1 files changed, 13 insertions, 7 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 8b7623c7d547..7c26ec8dce63 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -526,11 +526,10 @@ int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb,
 	enum skb_drop_reason drop_reason;
 	int err;
 
-	err = sk_filter(sk, skb);
-	if (err) {
-		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+	err = sk_filter_reason(sk, skb, &drop_reason);
+	if (err)
 		goto out;
-	}
+
 	err = __sock_queue_rcv_skb(sk, skb);
 	switch (err) {
 	case -ENOMEM:
@@ -553,15 +552,18 @@ EXPORT_SYMBOL(sock_queue_rcv_skb_reason);
 int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 		     const int nested, unsigned int trim_cap, bool refcounted)
 {
+	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	int rc = NET_RX_SUCCESS;
+	int err;
 
-	if (sk_filter_trim_cap(sk, skb, trim_cap))
+	if (sk_filter_trim_cap(sk, skb, trim_cap, &reason))
 		goto discard_and_relse;
 
 	skb->dev = NULL;
 
 	if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) {
 		atomic_inc(&sk->sk_drops);
+		reason = SKB_DROP_REASON_SOCKET_RCVBUFF;
 		goto discard_and_relse;
 	}
 	if (nested)
@@ -577,8 +579,12 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 		rc = sk_backlog_rcv(sk, skb);
 
 		mutex_release(&sk->sk_lock.dep_map, _RET_IP_);
-	} else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) {
+	} else if ((err = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))) {
 		bh_unlock_sock(sk);
+		if (err == -ENOMEM)
+			reason = SKB_DROP_REASON_PFMEMALLOC;
+		if (err == -ENOBUFS)
+			reason = SKB_DROP_REASON_SOCKET_BACKLOG;
 		atomic_inc(&sk->sk_drops);
 		goto discard_and_relse;
 	}
@@ -589,7 +595,7 @@ out:
 		sock_put(sk);
 	return rc;
 discard_and_relse:
-	kfree_skb(skb);
+	sk_skb_reason_drop(sk, skb, reason);
 	goto out;
 }
 EXPORT_SYMBOL(__sk_receive_skb);