1 files changed, 242 insertions, 141 deletions

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 5def3a2e85be..43ce17a6a585 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -399,6 +399,104 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
 
+int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
+		     long timeo, int *err)
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	int ret = 0;
+
+	if (sk->sk_shutdown & RCV_SHUTDOWN)
+		return 1;
+
+	if (!timeo)
+		return ret;
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	ret = sk_wait_event(sk, &timeo,
+			    !list_empty(&psock->ingress_msg) ||
+			    !skb_queue_empty(&sk->sk_receive_queue), &wait);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	remove_wait_queue(sk_sleep(sk), &wait);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sk_msg_wait_data);
+
+/* Receive sk_msg from psock->ingress_msg to @msg. */
+int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
+		   int len, int flags)
+{
+	struct iov_iter *iter = &msg->msg_iter;
+	int peek = flags & MSG_PEEK;
+	struct sk_msg *msg_rx;
+	int i, copied = 0;
+
+	msg_rx = sk_psock_peek_msg(psock);
+	while (copied != len) {
+		struct scatterlist *sge;
+
+		if (unlikely(!msg_rx))
+			break;
+
+		i = msg_rx->sg.start;
+		do {
+			struct page *page;
+			int copy;
+
+			sge = sk_msg_elem(msg_rx, i);
+			copy = sge->length;
+			page = sg_page(sge);
+			if (copied + copy > len)
+				copy = len - copied;
+			copy = copy_page_to_iter(page, sge->offset, copy, iter);
+			if (!copy)
+				return copied ? copied : -EFAULT;
+
+			copied += copy;
+			if (likely(!peek)) {
+				sge->offset += copy;
+				sge->length -= copy;
+				if (!msg_rx->skb)
+					sk_mem_uncharge(sk, copy);
+				msg_rx->sg.size -= copy;
+
+				if (!sge->length) {
+					sk_msg_iter_var_next(i);
+					if (!msg_rx->skb)
+						put_page(page);
+				}
+			} else {
+				/* Lets not optimize peek case if copy_page_to_iter
+				 * didn't copy the entire length lets just break.
+				 */
+				if (copy != sge->length)
+					return copied;
+				sk_msg_iter_var_next(i);
+			}
+
+			if (copied == len)
+				break;
+		} while (i != msg_rx->sg.end);
+
+		if (unlikely(peek)) {
+			msg_rx = sk_psock_next_msg(psock, msg_rx);
+			if (!msg_rx)
+				break;
+			continue;
+		}
+
+		msg_rx->sg.start = i;
+		if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) {
+			msg_rx = sk_psock_dequeue_msg(psock);
+			kfree_sk_msg(msg_rx);
+		}
+		msg_rx = sk_psock_peek_msg(psock);
+	}
+
+	return copied;
+}
+EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
+
 static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
 						  struct sk_buff *skb)
 {
@@ -410,7 +508,7 @@ static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
 	if (!sk_rmem_schedule(sk, skb, skb->truesize))
 		return NULL;
 
-	msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
+	msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_KERNEL);
 	if (unlikely(!msg))
 		return NULL;
 
@@ -498,7 +596,7 @@ 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);
 }
@@ -512,8 +610,7 @@ 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);
+	mutex_lock(&psock->work_mutex);
 	if (state->skb) {
 		skb = state->skb;
 		len = state->len;
@@ -526,10 +623,11 @@ static void sk_psock_backlog(struct work_struct *work)
 		len = skb->len;
 		off = 0;
 start:
-		ingress = tcp_skb_bpf_ingress(skb);
+		ingress = skb_bpf_ingress(skb);
+		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) {
@@ -553,7 +651,7 @@ start:
 			kfree_skb(skb);
 	}
 end:
-	release_sock(psock->sk);
+	mutex_unlock(&psock->work_mutex);
 }
 
 struct sk_psock *sk_psock_init(struct sock *sk, int node)
@@ -563,11 +661,6 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 
 	write_lock_bh(&sk->sk_callback_lock);
 
-	if (inet_csk_has_ulp(sk)) {
-		psock = ERR_PTR(-EINVAL);
-		goto out;
-	}
-
 	if (sk->sk_user_data) {
 		psock = ERR_PTR(-EBUSY);
 		goto out;
@@ -591,7 +684,9 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 	spin_lock_init(&psock->link_lock);
 
 	INIT_WORK(&psock->work, sk_psock_backlog);
+	mutex_init(&psock->work_mutex);
 	INIT_LIST_HEAD(&psock->ingress_msg);
+	spin_lock_init(&psock->ingress_lock);
 	skb_queue_head_init(&psock->ingress_skb);
 
 	sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED);
@@ -619,7 +714,7 @@ struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock)
 	return link;
 }
 
-void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
+static void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
 {
 	struct sk_msg *msg, *tmp;
 
@@ -630,9 +725,14 @@ 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)
 {
-	__skb_queue_purge(&psock->ingress_skb);
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(&psock->ingress_skb)) != NULL) {
+		skb_bpf_redirect_clear(skb);
+		kfree_skb(skb);
+	}
 	__sk_psock_purge_ingress_msg(psock);
 }
 
@@ -646,23 +746,35 @@ static void sk_psock_link_destroy(struct sk_psock *psock)
 	}
 }
 
-static void sk_psock_destroy_deferred(struct work_struct *gc)
+void sk_psock_stop(struct sk_psock *psock, bool wait)
 {
-	struct sk_psock *psock = container_of(gc, struct sk_psock, gc);
+	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);
 
+	if (wait)
+		cancel_work_sync(&psock->work);
+}
+
+static void sk_psock_done_strp(struct sk_psock *psock);
+
+static void sk_psock_destroy(struct work_struct *work)
+{
+	struct sk_psock *psock = container_of(to_rcu_work(work),
+					      struct sk_psock, rwork);
 	/* No sk_callback_lock since already detached. */
 
-	/* Parser has been stopped */
-	if (psock->progs.skb_parser)
-		strp_done(&psock->parser.strp);
+	sk_psock_done_strp(psock);
 
 	cancel_work_sync(&psock->work);
+	mutex_destroy(&psock->work_mutex);
 
 	psock_progs_drop(&psock->progs);
 
 	sk_psock_link_destroy(psock);
 	sk_psock_cork_free(psock);
-	sk_psock_zap_ingress(psock);
 
 	if (psock->sk_redir)
 		sock_put(psock->sk_redir);
@@ -670,30 +782,21 @@ static void sk_psock_destroy_deferred(struct work_struct *gc)
 	kfree(psock);
 }
 
-static void sk_psock_destroy(struct rcu_head *rcu)
-{
-	struct sk_psock *psock = container_of(rcu, struct sk_psock, rcu);
-
-	INIT_WORK(&psock->gc, sk_psock_destroy_deferred);
-	schedule_work(&psock->gc);
-}
-
 void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 {
-	sk_psock_cork_free(psock);
-	sk_psock_zap_ingress(psock);
+	sk_psock_stop(psock, false);
 
 	write_lock_bh(&sk->sk_callback_lock);
 	sk_psock_restore_proto(sk, psock);
 	rcu_assign_sk_user_data(sk, NULL);
-	if (psock->progs.skb_parser)
+	if (psock->progs.stream_parser)
 		sk_psock_stop_strp(sk, psock);
-	else if (psock->progs.skb_verdict)
+	else if (psock->progs.stream_verdict || psock->progs.skb_verdict)
 		sk_psock_stop_verdict(sk, psock);
 	write_unlock_bh(&sk->sk_callback_lock);
-	sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
 
-	call_rcu(&psock->rcu, sk_psock_destroy);
+	INIT_RCU_WORK(&psock->rwork, sk_psock_destroy);
+	queue_rcu_work(system_wq, &psock->rwork);
 }
 EXPORT_SYMBOL_GPL(sk_psock_drop);
 
@@ -744,27 +847,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_psock_msg_verdict);
 
-static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog,
-			    struct sk_buff *skb)
-{
-	bpf_compute_data_end_sk_skb(skb);
-	return bpf_prog_run_pin_on_cpu(prog, skb);
-}
-
-static struct sk_psock *sk_psock_from_strp(struct strparser *strp)
-{
-	struct sk_psock_parser *parser;
-
-	parser = container_of(strp, struct sk_psock_parser, strp);
-	return container_of(parser, struct sk_psock, parser);
-}
-
 static void sk_psock_skb_redirect(struct sk_buff *skb)
 {
 	struct sk_psock *psock_other;
 	struct sock *sk_other;
 
-	sk_other = tcp_skb_bpf_redirect_fetch(skb);
+	sk_other = skb_bpf_redirect_fetch(skb);
 	/* This error is a buggy BPF program, it returned a redirect
 	 * return code, but then didn't set a redirect interface.
 	 */
@@ -777,14 +865,20 @@ static void sk_psock_skb_redirect(struct sk_buff *skb)
 	 * error that caused the pipe to break. We can't send a packet on
 	 * a socket that is in this state so we drop the skb.
 	 */
-	if (!psock_other || sock_flag(sk_other, SOCK_DEAD) ||
-	    !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) {
+	if (!psock_other || sock_flag(sk_other, SOCK_DEAD)) {
+		kfree_skb(skb);
+		return;
+	}
+	spin_lock_bh(&psock_other->ingress_lock);
+	if (!sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) {
+		spin_unlock_bh(&psock_other->ingress_lock);
 		kfree_skb(skb);
 		return;
 	}
 
 	skb_queue_tail(&psock_other->ingress_skb, skb);
 	schedule_work(&psock_other->work);
+	spin_unlock_bh(&psock_other->ingress_lock);
 }
 
 static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int verdict)
@@ -806,12 +900,13 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
 	int ret = __SK_PASS;
 
 	rcu_read_lock();
-	prog = READ_ONCE(psock->progs.skb_verdict);
+	prog = READ_ONCE(psock->progs.stream_verdict);
 	if (likely(prog)) {
 		skb->sk = psock->sk;
-		tcp_skb_bpf_redirect_clear(skb);
-		ret = sk_psock_bpf_run(psock, prog, skb);
-		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+		skb_dst_drop(skb);
+		skb_bpf_redirect_clear(skb);
+		ret = bpf_prog_run_pin_on_cpu(prog, skb);
+		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
 		skb->sk = NULL;
 	}
 	sk_psock_tls_verdict_apply(skb, psock->sk, ret);
@@ -823,7 +918,6 @@ EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
 static void sk_psock_verdict_apply(struct sk_psock *psock,
 				   struct sk_buff *skb, int verdict)
 {
-	struct tcp_skb_cb *tcp;
 	struct sock *sk_other;
 	int err = -EIO;
 
@@ -835,8 +929,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 			goto out_free;
 		}
 
-		tcp = TCP_SKB_CB(skb);
-		tcp->bpf.flags |= BPF_F_INGRESS;
+		skb_bpf_set_ingress(skb);
 
 		/* If the queue is empty then we can submit directly
 		 * into the msg queue. If its not empty we have to
@@ -848,8 +941,12 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 			err = sk_psock_skb_ingress_self(psock, skb);
 		}
 		if (err < 0) {
-			skb_queue_tail(&psock->ingress_skb, skb);
-			schedule_work(&psock->work);
+			spin_lock_bh(&psock->ingress_lock);
+			if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
+				skb_queue_tail(&psock->ingress_skb, skb);
+				schedule_work(&psock->work);
+			}
+			spin_unlock_bh(&psock->ingress_lock);
 		}
 		break;
 	case __SK_REDIRECT:
@@ -862,6 +959,24 @@ out_free:
 	}
 }
 
+static void sk_psock_write_space(struct sock *sk)
+{
+	struct sk_psock *psock;
+	void (*write_space)(struct sock *sk) = NULL;
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (likely(psock)) {
+		if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+			schedule_work(&psock->work);
+		write_space = psock->saved_write_space;
+	}
+	rcu_read_unlock();
+	if (write_space)
+		write_space(sk);
+}
+
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
 static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 {
 	struct sk_psock *psock;
@@ -876,12 +991,13 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 		kfree_skb(skb);
 		goto out;
 	}
-	prog = READ_ONCE(psock->progs.skb_verdict);
+	prog = READ_ONCE(psock->progs.stream_verdict);
 	if (likely(prog)) {
 		skb->sk = sk;
-		tcp_skb_bpf_redirect_clear(skb);
-		ret = sk_psock_bpf_run(psock, prog, skb);
-		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+		skb_dst_drop(skb);
+		skb_bpf_redirect_clear(skb);
+		ret = bpf_prog_run_pin_on_cpu(prog, skb);
+		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
 		skb->sk = NULL;
 	}
 	sk_psock_verdict_apply(psock, skb, ret);
@@ -896,15 +1012,15 @@ static int sk_psock_strp_read_done(struct strparser *strp, int err)
 
 static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb)
 {
-	struct sk_psock *psock = sk_psock_from_strp(strp);
+	struct sk_psock *psock = container_of(strp, struct sk_psock, strp);
 	struct bpf_prog *prog;
 	int ret = skb->len;
 
 	rcu_read_lock();
-	prog = READ_ONCE(psock->progs.skb_parser);
+	prog = READ_ONCE(psock->progs.stream_parser);
 	if (likely(prog)) {
 		skb->sk = psock->sk;
-		ret = sk_psock_bpf_run(psock, prog, skb);
+		ret = bpf_prog_run_pin_on_cpu(prog, skb);
 		skb->sk = NULL;
 	}
 	rcu_read_unlock();
@@ -920,16 +1036,59 @@ static void sk_psock_strp_data_ready(struct sock *sk)
 	psock = sk_psock(sk);
 	if (likely(psock)) {
 		if (tls_sw_has_ctx_rx(sk)) {
-			psock->parser.saved_data_ready(sk);
+			psock->saved_data_ready(sk);
 		} else {
 			write_lock_bh(&sk->sk_callback_lock);
-			strp_data_ready(&psock->parser.strp);
+			strp_data_ready(&psock->strp);
 			write_unlock_bh(&sk->sk_callback_lock);
 		}
 	}
 	rcu_read_unlock();
 }
 
+int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
+{
+	static const struct strp_callbacks cb = {
+		.rcv_msg	= sk_psock_strp_read,
+		.read_sock_done	= sk_psock_strp_read_done,
+		.parse_msg	= sk_psock_strp_parse,
+	};
+
+	return strp_init(&psock->strp, sk, &cb);
+}
+
+void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
+{
+	if (psock->saved_data_ready)
+		return;
+
+	psock->saved_data_ready = sk->sk_data_ready;
+	sk->sk_data_ready = sk_psock_strp_data_ready;
+	sk->sk_write_space = sk_psock_write_space;
+}
+
+void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
+{
+	if (!psock->saved_data_ready)
+		return;
+
+	sk->sk_data_ready = psock->saved_data_ready;
+	psock->saved_data_ready = NULL;
+	strp_stop(&psock->strp);
+}
+
+static void sk_psock_done_strp(struct sk_psock *psock)
+{
+	/* Parser has been stopped */
+	if (psock->progs.stream_parser)
+		strp_done(&psock->strp);
+}
+#else
+static void sk_psock_done_strp(struct sk_psock *psock)
+{
+}
+#endif /* CONFIG_BPF_STREAM_PARSER */
+
 static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
 				 unsigned int offset, size_t orig_len)
 {
@@ -953,12 +1112,15 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
 		kfree_skb(skb);
 		goto out;
 	}
-	prog = READ_ONCE(psock->progs.skb_verdict);
+	prog = READ_ONCE(psock->progs.stream_verdict);
+	if (!prog)
+		prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
 		skb->sk = sk;
-		tcp_skb_bpf_redirect_clear(skb);
-		ret = sk_psock_bpf_run(psock, prog, skb);
-		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+		skb_dst_drop(skb);
+		skb_bpf_redirect_clear(skb);
+		ret = bpf_prog_run_pin_on_cpu(prog, skb);
+		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
 		skb->sk = NULL;
 	}
 	sk_psock_verdict_apply(psock, skb, ret);
@@ -982,82 +1144,21 @@ static void sk_psock_verdict_data_ready(struct sock *sk)
 	sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv);
 }
 
-static void sk_psock_write_space(struct sock *sk)
-{
-	struct sk_psock *psock;
-	void (*write_space)(struct sock *sk) = NULL;
-
-	rcu_read_lock();
-	psock = sk_psock(sk);
-	if (likely(psock)) {
-		if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
-			schedule_work(&psock->work);
-		write_space = psock->saved_write_space;
-	}
-	rcu_read_unlock();
-	if (write_space)
-		write_space(sk);
-}
-
-int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
-{
-	static const struct strp_callbacks cb = {
-		.rcv_msg	= sk_psock_strp_read,
-		.read_sock_done	= sk_psock_strp_read_done,
-		.parse_msg	= sk_psock_strp_parse,
-	};
-
-	psock->parser.enabled = false;
-	return strp_init(&psock->parser.strp, sk, &cb);
-}
-
 void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
 {
-	struct sk_psock_parser *parser = &psock->parser;
-
-	if (parser->enabled)
+	if (psock->saved_data_ready)
 		return;
 
-	parser->saved_data_ready = sk->sk_data_ready;
+	psock->saved_data_ready = sk->sk_data_ready;
 	sk->sk_data_ready = sk_psock_verdict_data_ready;
 	sk->sk_write_space = sk_psock_write_space;
-	parser->enabled = true;
-}
-
-void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
-{
-	struct sk_psock_parser *parser = &psock->parser;
-
-	if (parser->enabled)
-		return;
-
-	parser->saved_data_ready = sk->sk_data_ready;
-	sk->sk_data_ready = sk_psock_strp_data_ready;
-	sk->sk_write_space = sk_psock_write_space;
-	parser->enabled = true;
-}
-
-void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
-{
-	struct sk_psock_parser *parser = &psock->parser;
-
-	if (!parser->enabled)
-		return;
-
-	sk->sk_data_ready = parser->saved_data_ready;
-	parser->saved_data_ready = NULL;
-	strp_stop(&parser->strp);
-	parser->enabled = false;
 }
 
 void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
 {
-	struct sk_psock_parser *parser = &psock->parser;
-
-	if (!parser->enabled)
+	if (!psock->saved_data_ready)
 		return;
 
-	sk->sk_data_ready = parser->saved_data_ready;
-	parser->saved_data_ready = NULL;
-	parser->enabled = false;
+	sk->sk_data_ready = psock->saved_data_ready;
+	psock->saved_data_ready = NULL;
 }