1 files changed, 33 insertions, 20 deletions

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index f76cbf49c68c..a8d238dd982a 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -529,16 +529,22 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 					u32 off, u32 len,
 					struct sk_psock *psock,
 					struct sock *sk,
-					struct sk_msg *msg)
+					struct sk_msg *msg,
+					bool take_ref)
 {
 	int num_sge, copied;
 
+	/* skb_to_sgvec will fail when the total number of fragments in
+	 * frag_list and frags exceeds MAX_MSG_FRAGS. For example, the
+	 * caller may aggregate multiple skbs.
+	 */
 	num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
 	if (num_sge < 0) {
 		/* skb linearize may fail with ENOMEM, but lets simply try again
 		 * later if this happens. Under memory pressure we don't want to
 		 * drop the skb. We need to linearize the skb so that the mapping
 		 * in skb_to_sgvec can not error.
+		 * Note that skb_linearize requires the skb not to be shared.
 		 */
 		if (skb_linearize(skb))
 			return -EAGAIN;
@@ -555,7 +561,7 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 	msg->sg.start = 0;
 	msg->sg.size = copied;
 	msg->sg.end = num_sge;
-	msg->skb = skb;
+	msg->skb = take_ref ? skb_get(skb) : skb;
 
 	sk_psock_queue_msg(psock, msg);
 	sk_psock_data_ready(sk, psock);
@@ -563,7 +569,7 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 }
 
 static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
-				     u32 off, u32 len);
+				     u32 off, u32 len, bool take_ref);
 
 static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 				u32 off, u32 len)
@@ -577,7 +583,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 	 * correctly.
 	 */
 	if (unlikely(skb->sk == sk))
-		return sk_psock_skb_ingress_self(psock, skb, off, len);
+		return sk_psock_skb_ingress_self(psock, skb, off, len, true);
 	msg = sk_psock_create_ingress_msg(sk, skb);
 	if (!msg)
 		return -EAGAIN;
@@ -589,7 +595,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 	 * into user buffers.
 	 */
 	skb_set_owner_r(skb, sk);
-	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
+	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, true);
 	if (err < 0)
 		kfree(msg);
 	return err;
@@ -600,7 +606,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
  * because the skb is already accounted for here.
  */
 static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
-				     u32 off, u32 len)
+				     u32 off, u32 len, bool take_ref)
 {
 	struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC);
 	struct sock *sk = psock->sk;
@@ -609,7 +615,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 	if (unlikely(!msg))
 		return -EAGAIN;
 	skb_set_owner_r(skb, sk);
-	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
+	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, take_ref);
 	if (err < 0)
 		kfree(msg);
 	return err;
@@ -618,18 +624,13 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
 			       u32 off, u32 len, bool ingress)
 {
-	int err = 0;
-
 	if (!ingress) {
 		if (!sock_writeable(psock->sk))
 			return -EAGAIN;
 		return skb_send_sock(psock->sk, skb, off, len);
 	}
-	skb_get(skb);
-	err = sk_psock_skb_ingress(psock, skb, off, len);
-	if (err < 0)
-		kfree_skb(skb);
-	return err;
+
+	return sk_psock_skb_ingress(psock, skb, off, len);
 }
 
 static void sk_psock_skb_state(struct sk_psock *psock,
@@ -654,12 +655,14 @@ static void sk_psock_backlog(struct work_struct *work)
 	bool ingress;
 	int ret;
 
+	/* Increment the psock refcnt to synchronize with close(fd) path in
+	 * sock_map_close(), ensuring we wait for backlog thread completion
+	 * before sk_socket freed. If refcnt increment fails, it indicates
+	 * sock_map_close() completed with sk_socket potentially already freed.
+	 */
+	if (!sk_psock_get(psock->sk))
+		return;
 	mutex_lock(&psock->work_mutex);
-	if (unlikely(state->len)) {
-		len = state->len;
-		off = state->off;
-	}
-
 	while ((skb = skb_peek(&psock->ingress_skb))) {
 		len = skb->len;
 		off = 0;
@@ -669,6 +672,13 @@ static void sk_psock_backlog(struct work_struct *work)
 			off = stm->offset;
 			len = stm->full_len;
 		}
+
+		/* Resume processing from previous partial state */
+		if (unlikely(state->len)) {
+			len = state->len;
+			off = state->off;
+		}
+
 		ingress = skb_bpf_ingress(skb);
 		skb_bpf_redirect_clear(skb);
 		do {
@@ -696,11 +706,14 @@ static void sk_psock_backlog(struct work_struct *work)
 			len -= ret;
 		} while (len);
 
+		/* The entire skb sent, clear state */
+		sk_psock_skb_state(psock, state, 0, 0);
 		skb = skb_dequeue(&psock->ingress_skb);
 		kfree_skb(skb);
 	}
 end:
 	mutex_unlock(&psock->work_mutex);
+	sk_psock_put(psock->sk, psock);
 }
 
 struct sk_psock *sk_psock_init(struct sock *sk, int node)
@@ -1013,7 +1026,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 				off = stm->offset;
 				len = stm->full_len;
 			}
-			err = sk_psock_skb_ingress_self(psock, skb, off, len);
+			err = sk_psock_skb_ingress_self(psock, skb, off, len, false);
 		}
 		if (err < 0) {
 			spin_lock_bh(&psock->ingress_lock);