Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2021-06-23

The following pull-request contains BPF updates for your *net* tree.

We've added 14 non-merge commits during the last 6 day(s) which contain
a total of 13 files changed, 137 insertions(+), 64 deletions(-).

Note that when you merge net into net-next, there is a small merge conflict
between 9f2470fbc4cb ("skmsg: Improve udp_bpf_recvmsg() accuracy") from bpf
with c49661aa6f70 ("skmsg: Remove unused parameters of sk_msg_wait_data()")
from net-next. Resolution is to: i) net/ipv4/udp_bpf.c: take udp_msg_wait_data()
and remove err parameter from the function, ii) net/ipv4/tcp_bpf.c: take
tcp_msg_wait_data() and remove err parameter from the function, iii) for
net/core/skmsg.c and include/linux/skmsg.h: remove the sk_msg_wait_data()
implementation and its prototype in header.

The main changes are:

1) Fix BPF poke descriptor adjustments after insn rewrite, from John Fastabend.

2) Fix regression when using BPF_OBJ_GET with non-O_RDWR flags, from Maciej Żenczykowski.

3) Various bug and error handling fixes for UDP-related sock_map, from Cong Wang.

4) Fix patching of vmlinux BTF IDs with correct endianness, from Tony Ambardar.

5) Two fixes for TX descriptor validation in AF_XDP, from Magnus Karlsson.

6) Fix overflow in size calculation for bpf_map_area_alloc(), from Bui Quang Minh.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 67 insertions, 6 deletions

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index ad9d17923fc5..bb49b52d7be8 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -163,6 +163,28 @@ static bool tcp_bpf_stream_read(const struct sock *sk)
 	return !empty;
 }
 
+static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
+			     long timeo, int *err)
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	int ret = 0;
+
+	if (sk->sk_shutdown & RCV_SHUTDOWN)
+		return 1;
+
+	if (!timeo)
+		return ret;
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	ret = sk_wait_event(sk, &timeo,
+			    !list_empty(&psock->ingress_msg) ||
+			    !skb_queue_empty(&sk->sk_receive_queue), &wait);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	remove_wait_queue(sk_sleep(sk), &wait);
+	return ret;
+}
+
 static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		    int nonblock, int flags, int *addr_len)
 {
@@ -188,7 +210,7 @@ msg_bytes_ready:
 		long timeo;
 
 		timeo = sock_rcvtimeo(sk, nonblock);
-		data = sk_msg_wait_data(sk, psock, flags, timeo, &err);
+		data = tcp_msg_wait_data(sk, psock, flags, timeo, &err);
 		if (data) {
 			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1307ad0d3b9e..8091276cb85b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1798,11 +1798,13 @@ int udp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		if (used <= 0) {
 			if (!copied)
 				copied = used;
+			kfree_skb(skb);
 			break;
 		} else if (used <= skb->len) {
 			copied += used;
 		}
 
+		kfree_skb(skb);
 		if (!desc->count)
 			break;
 	}
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 954c4591a6fd..565a70040c57 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -21,6 +21,45 @@ static int sk_udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	return udp_prot.recvmsg(sk, msg, len, noblock, flags, addr_len);
 }
 
+static bool udp_sk_has_data(struct sock *sk)
+{
+	return !skb_queue_empty(&udp_sk(sk)->reader_queue) ||
+	       !skb_queue_empty(&sk->sk_receive_queue);
+}
+
+static bool psock_has_data(struct sk_psock *psock)
+{
+	return !skb_queue_empty(&psock->ingress_skb) ||
+	       !sk_psock_queue_empty(psock);
+}
+
+#define udp_msg_has_data(__sk, __psock)	\
+		({ udp_sk_has_data(__sk) || psock_has_data(__psock); })
+
+static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
+			     long timeo, int *err)
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	int ret = 0;
+
+	if (sk->sk_shutdown & RCV_SHUTDOWN)
+		return 1;
+
+	if (!timeo)
+		return ret;
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	ret = udp_msg_has_data(sk, psock);
+	if (!ret) {
+		wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
+		ret = udp_msg_has_data(sk, psock);
+	}
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	remove_wait_queue(sk_sleep(sk), &wait);
+	return ret;
+}
+
 static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			   int nonblock, int flags, int *addr_len)
 {
@@ -34,8 +73,7 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (unlikely(!psock))
 		return sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
-	lock_sock(sk);
-	if (sk_psock_queue_empty(psock)) {
+	if (!psock_has_data(psock)) {
 		ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 		goto out;
 	}
@@ -47,9 +85,9 @@ msg_bytes_ready:
 		long timeo;
 
 		timeo = sock_rcvtimeo(sk, nonblock);
-		data = sk_msg_wait_data(sk, psock, flags, timeo, &err);
+		data = udp_msg_wait_data(sk, psock, flags, timeo, &err);
 		if (data) {
-			if (!sk_psock_queue_empty(psock))
+			if (psock_has_data(psock))
 				goto msg_bytes_ready;
 			ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 			goto out;
@@ -62,7 +100,6 @@ msg_bytes_ready:
 	}
 	ret = copied;
 out:
-	release_sock(sk);
 	sk_psock_put(sk, psock);
 	return ret;
 }