RE: [Patch bpf-next v5 04/11] skmsg: avoid lock_sock() in sk_psock_backlog()

From: Cong Wang <redacted>

We do not have to lock the sock to avoid losing sk_socket,
instead we can purge all the ingress queues when we close
the socket. Sending or receiving packets after orphaning
socket makes no sense.

We do purge these queues when psock refcnt reaches zero but
here we want to purge them explicitly in sock_map_close().
There are also some nasty race conditions on testing bit
SK_PSOCK_TX_ENABLED and queuing/canceling the psock work,
we can expand psock->ingress_lock a bit to protect them too.

Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Lorenz Bauer <redacted>
Signed-off-by: Cong Wang <redacted>
---
 include/linux/skmsg.h |  1 +
 net/core/skmsg.c      | 50 +++++++++++++++++++++++++++++++------------
 net/core/sock_map.c   |  1 +
 3 files changed, 38 insertions(+), 14 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index f2d45a73b2b2..0f5e663f6c7f 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h

@@ -347,6 +347,7 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err)
 }

 
 #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
 int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock);

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 305dddc51857..d0a227b0f672 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c

@@ -497,7 +497,7 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
 	if (!ingress) {
 		if (!sock_writeable(psock->sk))
 			return -EAGAIN;
-		return skb_send_sock_locked(psock->sk, skb, off, len);
+		return skb_send_sock(psock->sk, skb, off, len);
 	}
 	return sk_psock_skb_ingress(psock, skb);
 }

@@ -511,8 +511,6 @@ static void sk_psock_backlog(struct work_struct *work)
 	u32 len, off;
 	int ret;
 
-	/* Lock sock to avoid losing sk_socket during loop. */
-	lock_sock(psock->sk);
 	if (state->skb) {
 		skb = state->skb;
 		len = state->len;

@@ -529,7 +527,7 @@ static void sk_psock_backlog(struct work_struct *work)
 		skb_bpf_redirect_clear(skb);
 		do {
 			ret = -EIO;
-			if (likely(psock->sk->sk_socket))
+			if (!sock_flag(psock->sk, SOCK_DEAD))
 				ret = sk_psock_handle_skb(psock, skb, off,
 							  len, ingress);
 			if (ret <= 0) {

@@ -537,13 +535,13 @@ static void sk_psock_backlog(struct work_struct *work)
 					state->skb = skb;
 					state->len = len;
 					state->off = off;
-					goto end;
+					return;

 				}
 				/* Hard errors break pipe and stop xmit. */
 				sk_psock_report_error(psock, ret ? -ret : EPIPE);
 				sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
 				kfree_skb(skb);
-				goto end;
+				return;
 			}
 			off += ret;
 			len -= ret;

@@ -552,8 +550,6 @@ static void sk_psock_backlog(struct work_struct *work)
 		if (!ingress)
 			kfree_skb(skb);
 	}
-end:
-	release_sock(psock->sk);
 }
 
 struct sk_psock *sk_psock_init(struct sock *sk, int node)

@@ -631,7 +627,7 @@ static void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
 	}
 }
 
-static void sk_psock_zap_ingress(struct sk_psock *psock)
+static void __sk_psock_zap_ingress(struct sk_psock *psock)
 {
 	struct sk_buff *skb;
 

@@ -639,8 +635,13 @@ static void sk_psock_zap_ingress(struct sk_psock *psock)
 		skb_bpf_redirect_clear(skb);
 		kfree_skb(skb);
 	}
-	spin_lock_bh(&psock->ingress_lock);
 	__sk_psock_purge_ingress_msg(psock);
+}
+
+static void sk_psock_zap_ingress(struct sk_psock *psock)
+{
+	spin_lock_bh(&psock->ingress_lock);
+	__sk_psock_zap_ingress(psock);
 	spin_unlock_bh(&psock->ingress_lock);

 }
 

@@ -654,6 +655,17 @@ static void sk_psock_link_destroy(struct sk_psock *psock)
 	}
 }
 
+void sk_psock_stop(struct sk_psock *psock)
+{
+	spin_lock_bh(&psock->ingress_lock);
+	sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
+	sk_psock_cork_free(psock);
+	__sk_psock_zap_ingress(psock);
+	spin_unlock_bh(&psock->ingress_lock);
+
+	cancel_work_sync(&psock->work);
+}
+
 static void sk_psock_done_strp(struct sk_psock *psock);