Skip to contentSkip to conversation

bpf/sockmap: read psock ingress_msg before sk_receive_queue

PATCH In review Lingpeng Chen 4 participants 11 messages Jan 7, 2020 – Jan 9, 2020 1 message not in the archive

Subsystems (6)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 bpf/sockmap: read psock ingress_msg before sk_receive_queue

Right now in tcp_bpf_recvmsg, sock read data first from sk_receive_queue if not empty than psock->ingress_msg otherwise. If a FIN packet arrives and there's also some data in psock->ingress_msg, the data in psock->ingress_msg will be purged. It is always happen when request to a HTTP1.0 server like python SimpleHTTPServer since the server send FIN packet after data is sent out.

---
 net/ipv4/tcp_bpf.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
net/ipv4/tcp_bpf.c +1 -3
index e38705165ac9..cd4b699d3d0d 100644
@@ -123,8 +123,6 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
-	if (!skb_queue_empty(&sk->sk_receive_queue))
-		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
@@ -139,7 +137,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		timeo = sock_rcvtimeo(sk, nonblock);
 		data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
 		if (data) {
-			if (skb_queue_empty(&sk->sk_receive_queue))
+			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
 			release_sock(sk);
 			sk_psock_put(sk, psock);
Signature · 1 line
2.17.1
maintainer
#1 lore raw
Quoted 8 lines · Lingpeng Chen

Right now in tcp_bpf_recvmsg, sock read data first from sk_receive_queue if not empty than psock->ingress_msg otherwise. If a FIN packet arrives and there's also some data in psock->ingress_msg, the data in psock->ingress_msg will be purged. It is always happen when request to a HTTP1.0 server like python SimpleHTTPServer since the server send FIN packet after data is sent out.

Hi, Good timing I have a very similar patch I was just about to send out on my queue as well. Also needs Fixes tag but see patch below

Quoted 9 lines
---
 net/ipv4/tcp_bpf.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
net/ipv4/tcp_bpf.c +0 -0
index e38705165ac9..cd4b699d3d0d 100644

net/ipv4/tcp_bpf.c int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, · line 127

Quoted 5 lines
net/ipv4/tcp_bpf.c +0 -2
@@ -123,8 +123,6 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
-	if (!skb_queue_empty(&sk->sk_receive_queue))
-		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);

I agree with this part.

net/ipv4/tcp_bpf.c int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, · line 140

Quoted 9 lines
net/ipv4/tcp_bpf.c +1 -1
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
@@ -139,7 +137,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		timeo = sock_rcvtimeo(sk, nonblock);
 		data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
 		if (data) {
-			if (skb_queue_empty(&sk->sk_receive_queue))
+			if (!sk_psock_queue_empty(psock))

+1

net/ipv4/tcp_bpf.c int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, · line 143

Quoted 3 lines
net/ipv4/tcp_bpf.c +0 -0
 				goto msg_bytes_ready;
 			release_sock(sk);
 			sk_psock_put(sk, psock);

I think it just misses one extra piece. We don't want to grab lock, call __tcp_bpf_recvmsg(), call tcp_bpf_wait_data(), etc. when we know the psock queue is empty. How about this patch I think it would solve your case as well. If you think this also works go ahead and add your Signed-off-by and send it. Or I'll send it later today with the upcoming series I have with a couple syzbot fixes as well.

commit 40d1c0965cda3713f444c7c0b570364220b94a8a

Author: John Fastabend <[email protected]>
Date:   Thu Dec 19 17:18:42 2019 +0000

bpf: bpf redirect should handle any received data before sk_receive_queue

Arika reported that when SOCK_DONE occurs we handle sk_receive_queue before psock->ingress_msg so we may leave data in the ingress_msg queue. Resulting in a possible error on application side.

Fix this by handling ingress_msg queue first so that data is not left in the insgress_msg queue.

Fixes 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
net/ipv4/tcp_bpf.c +5 -3
index e38705165ac9..3b235c2cbc83 100644
@@ -123,12 +123,14 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
        if (unlikely(flags & MSG_ERRQUEUE))
                return inet_recv_error(sk, msg, len, addr_len);
-       if (!skb_queue_empty(&sk->sk_receive_queue))
-               return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
        psock = sk_psock_get(sk);
        if (unlikely(!psock))
                return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+
+       if (!skb_queue_empty(&sk->sk_receive_queue) && sk_psock_queue_empty(psock))
+               return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+
        lock_sock(sk);
 msg_bytes_ready:
        copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
@@ -139,7 +141,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
                timeo = sock_rcvtimeo(sk, nonblock);
                data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
                if (data) {
-                       if (skb_queue_empty(&sk->sk_receive_queue))
+                       if (!sk_psock_queue_empty(psock))
                                goto msg_bytes_ready;
                        release_sock(sk);
                        sk_psock_put(sk, psock);

A message that is not in the archive (sent off-list or not yet received): CAH+Qyb+37gaWZzEvvXeX9ghsCYw1JyH_23S+1HW0ML-MZkcYfg@mail.gmail.com

maintainer
#3 lore raw
Quoted 1 line · Forrest Chen

Thanks John for the review.

Usually try not to top post.

Quoted 3 lines

I think you are right for the missing part. I would like to update the patch and re-send it, is it ok for you?

Yep glad to have more folks looking over sockmap code and looks like it already hit the list so that is good.

Quoted 6 lines

Since it is my first kernel patch, I'm not familiar with the process. What''s the meaning of 'add your Signed-off-by'?
I think I have add Signed-off-by in the first patch, do you mean I should add 'Signed-off-by: John Fastabend <[email protected]>' as well?

I was just saying feel free to add _your_ Signed-off-by to the patch I attached and send it. You added my signed-off-by to your patch which is also fine I don't think it matters much as long as we get the fix.

Also we should add Fixes tag and a tag to give Arika some credit. Seems we had the same fix in mind. I'll just add those now, next time for fixes please add a Fixes tag so we can track where we need to backport the fix.

Thanks for looking into this.

#4 lore raw

PATCH 1/1 bpf/sockmap: read psock ingress_msg before sk_receive_queue

Right now in tcp_bpf_recvmsg, sock read data first from sk_receive_queue if not empty than psock->ingress_msg otherwise. If a FIN packet arrives and there's also some data in psock->ingress_msg, the data in psock->ingress_msg will be purged. It is always happen when request to a HTTP1.0 server like python SimpleHTTPServer since the server send FIN packet after data is sent out.

Fixes 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
---
 net/ipv4/tcp_bpf.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
net/ipv4/tcp_bpf.c +4 -3
index e38705165ac9..f7e902868fce 100644
@@ -123,12 +123,13 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
-	if (!skb_queue_empty(&sk->sk_receive_queue))
-		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+	if (!skb_queue_empty(&sk->sk_receive_queue) &&
+	    sk_psock_queue_empty(psock))
+		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 	lock_sock(sk);
 msg_bytes_ready:
 	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
@@ -139,7 +140,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		timeo = sock_rcvtimeo(sk, nonblock);
 		data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
 		if (data) {
-			if (skb_queue_empty(&sk->sk_receive_queue))
+			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
 			release_sock(sk);
 			sk_psock_put(sk, psock);
Signature · 1 line
2.17.1
reviewer Acked-by on v1 1/1
#5 lore raw
Quoted 8 lines · Lingpeng Chen

Right now in tcp_bpf_recvmsg, sock read data first from sk_receive_queue if not empty than psock->ingress_msg otherwise. If a FIN packet arrives and there's also some data in psock->ingress_msg, the data in psock->ingress_msg will be purged. It is always happen when request to a HTTP1.0 server like python SimpleHTTPServer since the server send FIN packet after data is sent out.

Quoted 5 lines
Fixes 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
maintainer
#6 lore raw
In reply to Lingpeng Chen
Quoted 21 lines · Lingpeng Chen

Right now in tcp_bpf_recvmsg, sock read data first from sk_receive_queue if not empty than psock->ingress_msg otherwise. If a FIN packet arrives and there's also some data in psock->ingress_msg, the data in psock->ingress_msg will be purged. It is always happen when request to a HTTP1.0 server like python SimpleHTTPServer since the server send FIN packet after data is sent out.

Fixes 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
---
 net/ipv4/tcp_bpf.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
net/ipv4/tcp_bpf.c +0 -0
index e38705165ac9..f7e902868fce 100644

net/ipv4/tcp_bpf.c int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, · line 125

Quoted 3 lines
net/ipv4/tcp_bpf.c +0 -0
@@ -123,12 +123,13 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);

Shouldn't we also move the error queue handling below the psock test as well and let tcp_recvmsg() natively do it in case of !psock?

Quoted 24 lines
net/ipv4/tcp_bpf.c +4 -3
-	if (!skb_queue_empty(&sk->sk_receive_queue))
-		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+	if (!skb_queue_empty(&sk->sk_receive_queue) &&
+	    sk_psock_queue_empty(psock))
+		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 	lock_sock(sk);
 msg_bytes_ready:
 	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
@@ -139,7 +140,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		timeo = sock_rcvtimeo(sk, nonblock);
 		data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
 		if (data) {
-			if (skb_queue_empty(&sk->sk_receive_queue))
+			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
 			release_sock(sk);
 			sk_psock_put(sk, psock);
Signature · 1 line
2.17.1
maintainer
#7 lore raw
Quoted 23 lines · Daniel Borkmann
Quoted 22 lines · Lingpeng Chen

Right now in tcp_bpf_recvmsg, sock read data first from sk_receive_queue if not empty than psock->ingress_msg otherwise. If a FIN packet arrives and there's also some data in psock->ingress_msg, the data in psock->ingress_msg will be purged. It is always happen when request to a HTTP1.0 server like python SimpleHTTPServer since the server send FIN packet after data is sent out.

Fixes 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
---
 net/ipv4/tcp_bpf.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
net/ipv4/tcp_bpf.c +0 -0
index e38705165ac9..f7e902868fce 100644
@@ -123,12 +123,13 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
Quoted 6 lines

net/ipv4/tcp_bpf.c int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, · line 125

Quoted 2 lines
net/ipv4/tcp_bpf.c +0 -0
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);

Shouldn't we also move the error queue handling below the psock test as well and let tcp_recvmsg() natively do it in case of !psock?

You mean the MSG_ERRQUEUE flag handling? If the user sets MSG_ERRQUEUE they expect to receive any queued errors it would be wrong to return psock data in this case if psock is attached and has data on queue and user passes MSG_ERRQUEUE flag.

MSG_ERRQUEUE (since Linux 2.2)
This flag specifies that queued errors should be received from the socket error queue. The error is passed in an ancillary message with a type dependent on the protocol (for IPv4 IP_RECVERR). The user should supply a buffer of sufficient size. See cmsg(3) and ip(7) for more information. The payload of the original packet that caused the error is passed as normal data via msg_iovec. The original destination address of the datagram that caused the error is supplied via msg_name.

I believe it needs to be where it is.

Quoted 24 lines
Quoted 24 lines
net/ipv4/tcp_bpf.c +4 -3
-	if (!skb_queue_empty(&sk->sk_receive_queue))
-		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+	if (!skb_queue_empty(&sk->sk_receive_queue) &&
+	    sk_psock_queue_empty(psock))
+		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 	lock_sock(sk);
 msg_bytes_ready:
 	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
@@ -139,7 +140,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		timeo = sock_rcvtimeo(sk, nonblock);
 		data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
 		if (data) {
-			if (skb_queue_empty(&sk->sk_receive_queue))
+			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
 			release_sock(sk);
 			sk_psock_put(sk, psock);
Signature · 1 line
2.17.1
maintainer
#8 lore raw
Quoted 45 lines · John Fastabend
Quoted 23 lines · Daniel Borkmann
Quoted 22 lines · Lingpeng Chen

Right now in tcp_bpf_recvmsg, sock read data first from sk_receive_queue if not empty than psock->ingress_msg otherwise. If a FIN packet arrives and there's also some data in psock->ingress_msg, the data in psock->ingress_msg will be purged. It is always happen when request to a HTTP1.0 server like python SimpleHTTPServer since the server send FIN packet after data is sent out.

Fixes 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
---
  net/ipv4/tcp_bpf.c | 7 ++++---
  1 file changed, 4 insertions(+), 3 deletions(-)
net/ipv4/tcp_bpf.c +0 -0
index e38705165ac9..f7e902868fce 100644
@@ -123,12 +123,13 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
Quoted 6 lines

net/ipv4/tcp_bpf.c int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, · line 125

Quoted 2 lines
net/ipv4/tcp_bpf.c +0 -0
  	if (unlikely(flags & MSG_ERRQUEUE))
  		return inet_recv_error(sk, msg, len, addr_len);

Shouldn't we also move the error queue handling below the psock test as well and let tcp_recvmsg() natively do it in case of !psock?

You mean the MSG_ERRQUEUE flag handling? If the user sets MSG_ERRQUEUE they expect to receive any queued errors it would be wrong to return psock data in this case if psock is attached and has data on queue and user passes MSG_ERRQUEUE flag.

MSG_ERRQUEUE (since Linux 2.2)
This flag specifies that queued errors should be received from the socket error queue. The error is passed in an ancillary message with a type dependent on the protocol (for IPv4 IP_RECVERR). The user should supply a buffer of sufficient size. See cmsg(3) and ip(7) for more information. The payload of the original packet that caused the error is passed as normal data via msg_iovec. The original destination address of the datagram that caused the error is supplied via msg_name.

Quoted 1 line

I believe it needs to be where it is.

I meant that it should have looked as follows (aka moving both below the psock test) ...

        psock = sk_psock_get(sk);
        if (unlikely(!psock))
            return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
        if (unlikely(flags & MSG_ERRQUEUE))
            return inet_recv_error(sk, msg, len, addr_len);
	if (!skb_queue_empty(&sk->sk_receive_queue) && [...]

... since when detached it's handled already via tcp_recvmsg() internals.

Quoted 26 lines
Quoted 24 lines
Quoted 24 lines
net/ipv4/tcp_bpf.c +4 -3
-	if (!skb_queue_empty(&sk->sk_receive_queue))
-		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
  	psock = sk_psock_get(sk);
  	if (unlikely(!psock))
  		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+	if (!skb_queue_empty(&sk->sk_receive_queue) &&
+	    sk_psock_queue_empty(psock))
+		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
  	lock_sock(sk);
  msg_bytes_ready:
  	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
@@ -139,7 +140,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
  		timeo = sock_rcvtimeo(sk, nonblock);
  		data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
  		if (data) {
-			if (skb_queue_empty(&sk->sk_receive_queue))
+			if (!sk_psock_queue_empty(psock))
  				goto msg_bytes_ready;
  			release_sock(sk);
  			sk_psock_put(sk, psock);
Signature · 1 line
2.17.1
maintainer
#9 lore raw
Quoted 51 lines · Daniel Borkmann
Quoted 45 lines · John Fastabend
Quoted 23 lines · Daniel Borkmann
Quoted 22 lines · Lingpeng Chen

Right now in tcp_bpf_recvmsg, sock read data first from sk_receive_queue if not empty than psock->ingress_msg otherwise. If a FIN packet arrives and there's also some data in psock->ingress_msg, the data in psock->ingress_msg will be purged. It is always happen when request to a HTTP1.0 server like python SimpleHTTPServer since the server send FIN packet after data is sent out.

Fixes 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
---
  net/ipv4/tcp_bpf.c | 7 ++++---
  1 file changed, 4 insertions(+), 3 deletions(-)
net/ipv4/tcp_bpf.c +0 -0
index e38705165ac9..f7e902868fce 100644
@@ -123,12 +123,13 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
Quoted 6 lines

net/ipv4/tcp_bpf.c int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, · line 125

Quoted 2 lines
net/ipv4/tcp_bpf.c +0 -0
  	if (unlikely(flags & MSG_ERRQUEUE))
  		return inet_recv_error(sk, msg, len, addr_len);

Shouldn't we also move the error queue handling below the psock test as well and let tcp_recvmsg() natively do it in case of !psock?

You mean the MSG_ERRQUEUE flag handling? If the user sets MSG_ERRQUEUE they expect to receive any queued errors it would be wrong to return psock data in this case if psock is attached and has data on queue and user passes MSG_ERRQUEUE flag.

MSG_ERRQUEUE (since Linux 2.2)
This flag specifies that queued errors should be received from the socket error queue. The error is passed in an ancillary message with a type dependent on the protocol (for IPv4 IP_RECVERR). The user should supply a buffer of sufficient size. See cmsg(3) and ip(7) for more information. The payload of the original packet that caused the error is passed as normal data via msg_iovec. The original destination address of the datagram that caused the error is supplied via msg_name.

Quoted 1 line

I believe it needs to be where it is.

I meant that it should have looked as follows (aka moving both below the psock test) ...

Quoted 9 lines
         psock = sk_psock_get(sk);
         if (unlikely(!psock))
             return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
         if (unlikely(flags & MSG_ERRQUEUE))
             return inet_recv_error(sk, msg, len, addr_len);
	if (!skb_queue_empty(&sk->sk_receive_queue) && [...]

... since when detached it's handled already via tcp_recvmsg() internals.

Ah, OK the 'if (unlikely(!psock))' is a very rare case so I'm not sure it matters much. But, I agree it is slightly nicer.

Lingpeng, can you spin a v2 moving the MSG_ERRQUEUE check down and also keep the ACK and stable tags I don't think its a very big change the Acks can stick around IMO.

Thanks.

#10 lore raw

PATCH v2 1/1 bpf/sockmap: read psock ingress_msg before sk_receive_queue

Right now in tcp_bpf_recvmsg, sock read data first from sk_receive_queue if not empty than psock->ingress_msg otherwise. If a FIN packet arrives and there's also some data in psock->ingress_msg, the data in psock->ingress_msg will be purged. It is always happen when request to a HTTP1.0 server like python SimpleHTTPServer since the server send FIN packet after data is sent out.

Fixes 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
Cc [email protected] # v4.20+
---
 net/ipv4/tcp_bpf.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
net/ipv4/tcp_bpf.c +6 -6
index e38705165ac9..e6b08b5a0895 100644
@@ -121,14 +121,14 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	struct sk_psock *psock;
 	int copied, ret;
 
-	if (unlikely(flags & MSG_ERRQUEUE))
-		return inet_recv_error(sk, msg, len, addr_len);
-	if (!skb_queue_empty(&sk->sk_receive_queue))
-		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
-
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+	if (!skb_queue_empty(&sk->sk_receive_queue) &&
+	    sk_psock_queue_empty(psock))
+		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 	lock_sock(sk);
 msg_bytes_ready:
 	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
@@ -139,7 +139,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		timeo = sock_rcvtimeo(sk, nonblock);
 		data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
 		if (data) {
-			if (skb_queue_empty(&sk->sk_receive_queue))
+			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
 			release_sock(sk);
 			sk_psock_put(sk, psock);
Signature · 1 line
2.17.1
maintainer Applied
#11 lore raw
Quoted 7 lines · Lingpeng Chen

Right now in tcp_bpf_recvmsg, sock read data first from sk_receive_queue if not empty than psock->ingress_msg otherwise. If a FIN packet arrives and there's also some data in psock->ingress_msg, the data in psock->ingress_msg will be purged. It is always happen when request to a HTTP1.0 server like python SimpleHTTPServer since the server send FIN packet after data is sent out.

Quoted 7 lines
Fixes 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
Cc [email protected] # v4.20+

Applied to bpf, thanks!