Merge https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 74 insertions, 13 deletions

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 654182ecf87b..25cdbb20f3a0 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -170,10 +170,12 @@ static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i,
 	struct scatterlist *sge = sk_msg_elem(msg, i);
 	u32 len = sge->length;
 
-	if (charge)
-		sk_mem_uncharge(sk, len);
-	if (!msg->skb)
+	/* When the skb owns the memory we free it from consume_skb path. */
+	if (!msg->skb) {
+		if (charge)
+			sk_mem_uncharge(sk, len);
 		put_page(sg_page(sge));
+	}
 	memset(sge, 0, sizeof(*sge));
 	return len;
 }
@@ -397,28 +399,45 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
 
-static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
+static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
+						  struct sk_buff *skb)
 {
-	struct sock *sk = psock->sk;
-	int copied = 0, num_sge;
 	struct sk_msg *msg;
 
+	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
+		return NULL;
+
+	if (!sk_rmem_schedule(sk, skb, skb->truesize))
+		return NULL;
+
 	msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
 	if (unlikely(!msg))
-		return -EAGAIN;
-	if (!sk_rmem_schedule(sk, skb, skb->len)) {
-		kfree(msg);
-		return -EAGAIN;
-	}
+		return NULL;
 
 	sk_msg_init(msg);
+	return msg;
+}
+
+static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
+					struct sk_psock *psock,
+					struct sock *sk,
+					struct sk_msg *msg)
+{
+	int num_sge, copied;
+
+	/* 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.
+	 */
+	if (skb_linearize(skb))
+		return -EAGAIN;
 	num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len);
 	if (unlikely(num_sge < 0)) {
 		kfree(msg);
 		return num_sge;
 	}
 
-	sk_mem_charge(sk, skb->len);
 	copied = skb->len;
 	msg->sg.start = 0;
 	msg->sg.size = copied;
@@ -430,6 +449,48 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
 	return copied;
 }
 
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb);
+
+static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
+{
+	struct sock *sk = psock->sk;
+	struct sk_msg *msg;
+
+	/* If we are receiving on the same sock skb->sk is already assigned,
+	 * skip memory accounting and owner transition seeing it already set
+	 * correctly.
+	 */
+	if (unlikely(skb->sk == sk))
+		return sk_psock_skb_ingress_self(psock, skb);
+	msg = sk_psock_create_ingress_msg(sk, skb);
+	if (!msg)
+		return -EAGAIN;
+
+	/* This will transition ownership of the data from the socket where
+	 * the BPF program was run initiating the redirect to the socket
+	 * we will eventually receive this data on. The data will be released
+	 * from skb_consume found in __tcp_bpf_recvmsg() after its been copied
+	 * into user buffers.
+	 */
+	skb_set_owner_r(skb, sk);
+	return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+}
+
+/* Puts an skb on the ingress queue of the socket already assigned to the
+ * skb. In this case we do not need to check memory limits or skb_set_owner_r
+ * because the skb is already accounted for here.
+ */
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb)
+{
+	struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
+	struct sock *sk = psock->sk;
+
+	if (unlikely(!msg))
+		return -EAGAIN;
+	sk_msg_init(msg);
+	return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+}
+
 static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
 			       u32 off, u32 len, bool ingress)
 {
@@ -789,7 +850,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 		 * retrying later from workqueue.
 		 */
 		if (skb_queue_empty(&psock->ingress_skb)) {
-			err = sk_psock_skb_ingress(psock, skb);
+			err = sk_psock_skb_ingress_self(psock, skb);
 		}
 		if (err < 0) {
 			skb_queue_tail(&psock->ingress_skb, skb);