Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2023-05-24

We've added 19 non-merge commits during the last 10 day(s) which contain
a total of 20 files changed, 738 insertions(+), 448 deletions(-).

The main changes are:

1) Batch of BPF sockmap fixes found when running against NGINX TCP tests,
   from John Fastabend.

2) Fix a memleak in the LRU{,_PERCPU} hash map when bucket locking fails,
   from Anton Protopopov.

3) Init the BPF offload table earlier than just late_initcall,
   from Jakub Kicinski.

4) Fix ctx access mask generation for 32-bit narrow loads of 64-bit fields,
   from Will Deacon.

5) Remove a now unsupported __fallthrough in BPF samples,
   from Andrii Nakryiko.

6) Fix a typo in pkg-config call for building sign-file,
   from Jeremy Sowden.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf, sockmap: Test progs verifier error with latest clang
  bpf, sockmap: Test FIONREAD returns correct bytes in rx buffer with drops
  bpf, sockmap: Test FIONREAD returns correct bytes in rx buffer
  bpf, sockmap: Test shutdown() correctly exits epoll and recv()=0
  bpf, sockmap: Build helper to create connected socket pair
  bpf, sockmap: Pull socket helpers out of listen test for general use
  bpf, sockmap: Incorrectly handling copied_seq
  bpf, sockmap: Wake up polling after data copy
  bpf, sockmap: TCP data stall on recv before accept
  bpf, sockmap: Handle fin correctly
  bpf, sockmap: Improved check for empty queue
  bpf, sockmap: Reschedule is now done through backlog
  bpf, sockmap: Convert schedule_work into delayed_work
  bpf, sockmap: Pass skb ownership through read_skb
  bpf: fix a memory leak in the LRU and LRU_PERCPU hash maps
  bpf: Fix mask generation for 32-bit narrow loads of 64-bit fields
  samples/bpf: Drop unnecessary fallthrough
  bpf: netdev: init the offload table earlier
  selftests/bpf: Fix pkg-config call building sign-file
====================

Link: https://lore.kernel.org/r/20230524170839.13905-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 81 insertions, 16 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4d6392c16b7a..a60f6f4e7cd9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1571,7 +1571,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
  * calculation of whether or not we must ACK for the sake of
  * a window update.
  */
-static void __tcp_cleanup_rbuf(struct sock *sk, int copied)
+void __tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
@@ -1773,7 +1773,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 		WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
 		tcp_flags = TCP_SKB_CB(skb)->tcp_flags;
 		used = recv_actor(sk, skb);
-		consume_skb(skb);
 		if (used < 0) {
 			if (!copied)
 				copied = used;
@@ -1787,14 +1786,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 			break;
 		}
 	}
-	WRITE_ONCE(tp->copied_seq, seq);
-
-	tcp_rcv_space_adjust(sk);
-
-	/* Clean up data we have read: This will do ACK frames. */
-	if (copied > 0)
-		__tcp_cleanup_rbuf(sk, copied);
-
 	return copied;
 }
 EXPORT_SYMBOL(tcp_read_skb);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 2e9547467edb..5f93918c063c 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -11,6 +11,24 @@
 #include <net/inet_common.h>
 #include <net/tls.h>
 
+void tcp_eat_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tcp;
+	int copied;
+
+	if (!skb || !skb->len || !sk_is_tcp(sk))
+		return;
+
+	if (skb_bpf_strparser(skb))
+		return;
+
+	tcp = tcp_sk(sk);
+	copied = tcp->copied_seq + skb->len;
+	WRITE_ONCE(tcp->copied_seq, copied);
+	tcp_rcv_space_adjust(sk);
+	__tcp_cleanup_rbuf(sk, skb->len);
+}
+
 static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 			   struct sk_msg *msg, u32 apply_bytes, int flags)
 {
@@ -174,14 +192,34 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 	return ret;
 }
 
+static bool is_next_msg_fin(struct sk_psock *psock)
+{
+	struct scatterlist *sge;
+	struct sk_msg *msg_rx;
+	int i;
+
+	msg_rx = sk_psock_peek_msg(psock);
+	i = msg_rx->sg.start;
+	sge = sk_msg_elem(msg_rx, i);
+	if (!sge->length) {
+		struct sk_buff *skb = msg_rx->skb;
+
+		if (skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+			return true;
+	}
+	return false;
+}
+
 static int tcp_bpf_recvmsg_parser(struct sock *sk,
 				  struct msghdr *msg,
 				  size_t len,
 				  int flags,
 				  int *addr_len)
 {
+	struct tcp_sock *tcp = tcp_sk(sk);
+	u32 seq = tcp->copied_seq;
 	struct sk_psock *psock;
-	int copied;
+	int copied = 0;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
@@ -194,8 +232,43 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
 		return tcp_recvmsg(sk, msg, len, flags, addr_len);
 
 	lock_sock(sk);
+
+	/* We may have received data on the sk_receive_queue pre-accept and
+	 * then we can not use read_skb in this context because we haven't
+	 * assigned a sk_socket yet so have no link to the ops. The work-around
+	 * is to check the sk_receive_queue and in these cases read skbs off
+	 * queue again. The read_skb hook is not running at this point because
+	 * of lock_sock so we avoid having multiple runners in read_skb.
+	 */
+	if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) {
+		tcp_data_ready(sk);
+		/* This handles the ENOMEM errors if we both receive data
+		 * pre accept and are already under memory pressure. At least
+		 * let user know to retry.
+		 */
+		if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) {
+			copied = -EAGAIN;
+			goto out;
+		}
+	}
+
 msg_bytes_ready:
 	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+	/* The typical case for EFAULT is the socket was gracefully
+	 * shutdown with a FIN pkt. So check here the other case is
+	 * some error on copy_page_to_iter which would be unexpected.
+	 * On fin return correct return code to zero.
+	 */
+	if (copied == -EFAULT) {
+		bool is_fin = is_next_msg_fin(psock);
+
+		if (is_fin) {
+			copied = 0;
+			seq++;
+			goto out;
+		}
+	}
+	seq += copied;
 	if (!copied) {
 		long timeo;
 		int data;
@@ -233,6 +306,10 @@ msg_bytes_ready:
 		copied = -EAGAIN;
 	}
 out:
+	WRITE_ONCE(tcp->copied_seq, seq);
+	tcp_rcv_space_adjust(sk);
+	if (copied > 0)
+		__tcp_cleanup_rbuf(sk, copied);
 	release_sock(sk);
 	sk_psock_put(sk, psock);
 	return copied;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index aa32afd871ee..9482def1f310 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1818,7 +1818,7 @@ EXPORT_SYMBOL(__skb_recv_udp);
 int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
 	struct sk_buff *skb;
-	int err, copied;
+	int err;
 
 try_again:
 	skb = skb_recv_udp(sk, MSG_DONTWAIT, &err);
@@ -1837,10 +1837,7 @@ try_again:
 	}
 
 	WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
-	copied = recv_actor(sk, skb);
-	kfree_skb(skb);
-
-	return copied;
+	return recv_actor(sk, skb);
 }
 EXPORT_SYMBOL(udp_read_skb);