[PATCH net v4] af_unix: Read with MSG_PEEK loops if the first unread byte is OOB

[PATCH net v4] af_unix: Read with MSG_PEEK loops if the first unread byte is OOB

[Rao Shoaib]

Read with MSG_PEEK flag loops if the first byte to read is an OOB byte.
commit 22dd70eb2c3d ("af_unix: Don't peek OOB data without MSG_OOB.")
addresses the loop issue but does not address the issue that no data
beyond OOB byte can be read.

>>> from socket import *
>>> c1, c2 = socketpair(AF_UNIX, SOCK_STREAM)
>>> c1.send(b'a', MSG_OOB)
1
>>> c1.send(b'b')
1
>>> c2.recv(1, MSG_PEEK | MSG_DONTWAIT)
b'b'

Fixes: 314001f0bf92 ("af_unix: Add OOB support")
Signed-off-by: Rao Shoaib <Rao.Shoaib@oracle.com>
---
 net/unix/af_unix.c | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 9a6ad5974dff..e88ec8744329 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2658,19 +2658,19 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 		if (skb == u->oob_skb) {
 			if (copied) {
 				skb = NULL;
-			} else if (sock_flag(sk, SOCK_URGINLINE)) {
-				if (!(flags & MSG_PEEK)) {
+			} else if (!(flags & MSG_PEEK)) {
+				if (sock_flag(sk, SOCK_URGINLINE)) {
 					WRITE_ONCE(u->oob_skb, NULL);
 					consume_skb(skb);
+				} else {
+					skb_unlink(skb, &sk->sk_receive_queue);
+					WRITE_ONCE(u->oob_skb, NULL);
+					if (!WARN_ON_ONCE(skb_unref(skb)))
+						kfree_skb(skb);
+					skb = skb_peek(&sk->sk_receive_queue);
 				}
-			} else if (flags & MSG_PEEK) {
-				skb = NULL;
-			} else {
-				skb_unlink(skb, &sk->sk_receive_queue);
-				WRITE_ONCE(u->oob_skb, NULL);
-				if (!WARN_ON_ONCE(skb_unref(skb)))
-					kfree_skb(skb);
-				skb = skb_peek(&sk->sk_receive_queue);
+			} else if (!sock_flag(sk, SOCK_URGINLINE)) {
+				skb = skb_peek_next(skb, &sk->sk_receive_queue);
 			}
 		}
 	}
@@ -2747,9 +2747,10 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
 		if (skb) {
 			skb = manage_oob(skb, sk, flags, copied);
-			if (!skb && copied) {
+			if (!skb) {
 				unix_state_unlock(sk);
-				break;
+				if (copied || (flags & MSG_PEEK))
+					break;
 			}
 		}
 #endif
-- 
2.39.3

Re: [PATCH net v4] af_unix: Read with MSG_PEEK loops if the first unread byte is OOB

[Kuniyuki Iwashima]

From: Rao Shoaib <Rao.Shoaib@oracle.com>
Date: Tue, 30 Apr 2024 01:16:13 -0700
> Read with MSG_PEEK flag loops if the first byte to read is an OOB byte.
> commit 22dd70eb2c3d ("af_unix: Don't peek OOB data without MSG_OOB.")
> addresses the loop issue but does not address the issue that no data
> beyond OOB byte can be read.
> 
> >>> from socket import *
> >>> c1, c2 = socketpair(AF_UNIX, SOCK_STREAM)
> >>> c1.send(b'a', MSG_OOB)
> 1
> >>> c1.send(b'b')
> 1
> >>> c2.recv(1, MSG_PEEK | MSG_DONTWAIT)
> b'b'
> 
> Fixes: 314001f0bf92 ("af_unix: Add OOB support")
> Signed-off-by: Rao Shoaib <Rao.Shoaib@oracle.com>
> ---
>  net/unix/af_unix.c | 25 +++++++++++++------------
>  1 file changed, 13 insertions(+), 12 deletions(-)
> 
> diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
> index 9a6ad5974dff..e88ec8744329 100644
> --- a/net/unix/af_unix.c
> +++ b/net/unix/af_unix.c
> @@ -2658,19 +2658,19 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
>  		if (skb == u->oob_skb) {
>  			if (copied) {
>  				skb = NULL;
> -			} else if (sock_flag(sk, SOCK_URGINLINE)) {
> -				if (!(flags & MSG_PEEK)) {
> +			} else if (!(flags & MSG_PEEK)) {
> +				if (sock_flag(sk, SOCK_URGINLINE)) {
>  					WRITE_ONCE(u->oob_skb, NULL);
>  					consume_skb(skb);
> +				} else {
> +					skb_unlink(skb, &sk->sk_receive_queue);
> +					WRITE_ONCE(u->oob_skb, NULL);
> +					if (!WARN_ON_ONCE(skb_unref(skb)))
> +						kfree_skb(skb);
> +					skb = skb_peek(&sk->sk_receive_queue);
>  				}
> -			} else if (flags & MSG_PEEK) {
> -				skb = NULL;
> -			} else {
> -				skb_unlink(skb, &sk->sk_receive_queue);
> -				WRITE_ONCE(u->oob_skb, NULL);
> -				if (!WARN_ON_ONCE(skb_unref(skb)))
> -					kfree_skb(skb);
> -				skb = skb_peek(&sk->sk_receive_queue);
> +			} else if (!sock_flag(sk, SOCK_URGINLINE)) {
> +				skb = skb_peek_next(skb, &sk->sk_receive_queue);

My last comment for v3 was about this line.
https://lore.kernel.org/netdev/20240424013921.16819-1-kuniyu@amazon.com/

Here, (flags & MSG_PEEK) is true, and if skb_peek_next() returns NULL,


>  			}
>  		}
>  	}
> @@ -2747,9 +2747,10 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
>  #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
>  		if (skb) {
>  			skb = manage_oob(skb, sk, flags, copied);
> -			if (!skb && copied) {
> +			if (!skb) {
>  				unix_state_unlock(sk);
> -				break;
> +				if (copied || (flags & MSG_PEEK))
> +					break;

we will bail out the loop due to this change.

However, no data is copied here, so whether we break or not
should depend on MSG_DONTWAIT, which is handled in the following
`if (skb == NULL)` block.

In the example below, TCP socket is blocked because there is
no data to receive and MSG_DONTWAIT is not specified.  And this
is unblocked when normal data arrives.

  ---8<---
  >>> from socket import *
  >>> 
  >>> s = socket()
  >>> s.listen()
  >>> 
  >>> c1 = socket()
  >>> c1.connect(s.getsockname())
  >>> 
  >>> c2, _ = s.accept()
  >>> 
  >>> c1.send(b'a', MSG_OOB)
  1
  >>> c2.recv(1, MSG_PEEK)
  ^C
  ---8<---

But with your patch, AF_UNIX socket is not blocked even without
MSG_DONTWAIT.

  ---8<---
  >>> from socket import *
  >>> 
  >>> c1, c2 = socketpair(AF_UNIX, SOCK_STREAM, 0)
  >>> c1.send(b'a', MSG_OOB)
  1
  >>> c2.recv(1, MSG_PEEK)
  b''
  ---8<---

That's why I said the change in unix_stream_read_generic() is not
needed.