Merge branch 'vsock-credit-update'

Arseniy Krasnov says:

====================
send credit update during setting SO_RCVLOWAT

                               DESCRIPTION

This patchset fixes old problem with hungup of both rx/tx sides and adds
test for it. This happens due to non-default SO_RCVLOWAT value and
deferred credit update in virtio/vsock. Link to previous old patchset:
https://lore.kernel.org/netdev/39b2e9fd-601b-189d-39a9-914e5574524c@sberdevices.ru/

Here is what happens step by step:

                                  TEST

                            INITIAL CONDITIONS

1) Vsock buffer size is 128KB.
2) Maximum packet size is also 64KB as defined in header (yes it is
   hardcoded, just to remind about that value).
3) SO_RCVLOWAT is default, e.g. 1 byte.

                                 STEPS

            SENDER                              RECEIVER
1) sends 128KB + 1 byte in a
   single buffer. 128KB will
   be sent, but for 1 byte
   sender will wait for free
   space at peer. Sender goes
   to sleep.

2)                                     reads 64KB, credit update not sent
3)                                     sets SO_RCVLOWAT to 64KB + 1
4)                                     poll() -> wait forever, there is
                                       only 64KB available to read.

So in step 4) receiver also goes to sleep, waiting for enough data or
connection shutdown message from the sender. Idea to fix it is that rx
kicks tx side to continue transmission (and may be close connection)
when rx changes number of bytes to be woken up (e.g. SO_RCVLOWAT) and
this value is bigger than number of available bytes to read.

I've added small test for this, but not sure as it uses hardcoded value
for maximum packet length, this value is defined in kernel header and
used to control deferred credit update. And as this is not available to
userspace, I can't control test parameters correctly (if one day this
define will be changed - test may become useless).

Head for this patchset is:
https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit/?id=9bab51bd662be4c3ebb18a28879981d69f3ef15a

Link to v1:
https://lore.kernel.org/netdev/20231108072004.1045669-1-avkrasnov@salutedevices.com/
Link to v2:
https://lore.kernel.org/netdev/20231119204922.2251912-1-avkrasnov@salutedevices.com/
Link to v3:
https://lore.kernel.org/netdev/20231122180510.2297075-1-avkrasnov@salutedevices.com/
Link to v4:
https://lore.kernel.org/netdev/20231129212519.2938875-1-avkrasnov@salutedevices.com/
Link to v5:
https://lore.kernel.org/netdev/20231130130840.253733-1-avkrasnov@salutedevices.com/
Link to v6:
https://lore.kernel.org/netdev/20231205064806.2851305-1-avkrasnov@salutedevices.com/
Link to v7:
https://lore.kernel.org/netdev/20231206211849.2707151-1-avkrasnov@salutedevices.com/
Link to v8:
https://lore.kernel.org/netdev/20231211211658.2904268-1-avkrasnov@salutedevices.com/
Link to v9:
https://lore.kernel.org/netdev/20231214091947.395892-1-avkrasnov@salutedevices.com/

Changelog:
v1 -> v2:
 * Patchset rebased and tested on new HEAD of net-next (see hash above).
 * New patch is added as 0001 - it removes return from SO_RCVLOWAT set
   callback in 'af_vsock.c' when transport callback is set - with that
   we can set 'sk_rcvlowat' only once in 'af_vsock.c' and in future do
   not copy-paste it to every transport. It was discussed in v1.
 * See per-patch changelog after ---.
v2 -> v3:
 * See changelog after --- in 0003 only (0001 and 0002 still same).
v3 -> v4:
 * Patchset rebased and tested on new HEAD of net-next (see hash above).
 * See per-patch changelog after ---.
v4 -> v5:
 * Change patchset tag 'RFC' -> 'net-next'.
 * See per-patch changelog after ---.
v5 -> v6:
 * New patch 0003 which sends credit update during reading bytes from
   socket.
 * See per-patch changelog after ---.
v6 -> v7:
 * Patchset rebased and tested on new HEAD of net-next (see hash above).
 * See per-patch changelog after ---.
v7 -> v8:
 * See per-patch changelog after ---.
v8 -> v9:
 * Patchset rebased and tested on new HEAD of net-next (see hash above).
 * Add 'Fixes' tag for the current 0002.
 * Reorder patches by moving two fixes first.
v9 -> v10:
 * Squash 0002 and 0003 and update commit message in result.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/vhost/vsock.c

@@ -449,6 +449,7 @@ static struct virtio_transport vhost_transport = {
 		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
 		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
+		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
 		.read_skb = virtio_transport_read_skb,
 	},

include/linux/virtio_vsock.h

@@ -256,4 +256,5 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit);
 void virtio_transport_deliver_tap_pkt(struct sk_buff *skb);
 int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list);
 int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t read_actor);
+int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val);
 #endif /* _LINUX_VIRTIO_VSOCK_H */

include/net/af_vsock.h

@@ -137,7 +137,6 @@ struct vsock_transport {
 	u64 (*stream_rcvhiwat)(struct vsock_sock *);
 	bool (*stream_is_active)(struct vsock_sock *);
 	bool (*stream_allow)(u32 cid, u32 port);
-	int (*set_rcvlowat)(struct vsock_sock *vsk, int val);
 
 	/* SEQ_PACKET. */
 	ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
@@ -168,6 +167,7 @@ struct vsock_transport {
 		struct vsock_transport_send_notify_data *);
 	/* sk_lock held by the caller */
 	void (*notify_buffer_size)(struct vsock_sock *, u64 *);
+	int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val);
 
 	/* Shutdown. */
 	int (*shutdown)(struct vsock_sock *, int);

net/vmw_vsock/af_vsock.c

@@ -2264,8 +2264,13 @@ static int vsock_set_rcvlowat(struct sock *sk, int val)
 
 	transport = vsk->transport;
 
-	if (transport && transport->set_rcvlowat)
-		return transport->set_rcvlowat(vsk, val);
+	if (transport && transport->notify_set_rcvlowat) {
+		int err;
+
+		err = transport->notify_set_rcvlowat(vsk, val);
+		if (err)
+			return err;
+	}
 
 	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 	return 0;

net/vmw_vsock/hyperv_transport.c

@@ -816,7 +816,7 @@ int hvs_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written,
 }
 
 static
-int hvs_set_rcvlowat(struct vsock_sock *vsk, int val)
+int hvs_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
 {
 	return -EOPNOTSUPP;
 }
@@ -856,7 +856,7 @@ static struct vsock_transport hvs_transport = {
 	.notify_send_pre_enqueue  = hvs_notify_send_pre_enqueue,
 	.notify_send_post_enqueue = hvs_notify_send_post_enqueue,
 
-	.set_rcvlowat             = hvs_set_rcvlowat
+	.notify_set_rcvlowat      = hvs_notify_set_rcvlowat
 };
 
 static bool hvs_check_transport(struct vsock_sock *vsk)

net/vmw_vsock/virtio_transport.c

@@ -537,6 +537,7 @@ static struct virtio_transport virtio_transport = {
 		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
 		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
+		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
 		.read_skb = virtio_transport_read_skb,
 	},

net/vmw_vsock/virtio_transport_common.c

@@ -557,6 +557,8 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
 	struct virtio_vsock_sock *vvs = vsk->trans;
 	size_t bytes, total = 0;
 	struct sk_buff *skb;
+	u32 fwd_cnt_delta;
+	bool low_rx_bytes;
 	int err = -EFAULT;
 	u32 free_space;
 
@@ -600,7 +602,10 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
 		}
 	}
 
-	free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt);
+	fwd_cnt_delta = vvs->fwd_cnt - vvs->last_fwd_cnt;
+	free_space = vvs->buf_alloc - fwd_cnt_delta;
+	low_rx_bytes = (vvs->rx_bytes <
+			sock_rcvlowat(sk_vsock(vsk), 0, INT_MAX));
 
 	spin_unlock_bh(&vvs->rx_lock);
 
@@ -610,9 +615,11 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
 	 * too high causes extra messages. Too low causes transmitter
 	 * stalls. As stalls are in theory more expensive than extra
 	 * messages, we set the limit to a high value. TODO: experiment
-	 * with different values.
+	 * with different values. Also send credit update message when
+	 * number of bytes in rx queue is not enough to wake up reader.
 	 */
-	if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE)
+	if (fwd_cnt_delta &&
+	    (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE || low_rx_bytes))
 		virtio_transport_send_credit_update(vsk);
 
 	return total;
@@ -1683,6 +1690,36 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto
 }
 EXPORT_SYMBOL_GPL(virtio_transport_read_skb);
 
+int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	bool send_update;
+
+	spin_lock_bh(&vvs->rx_lock);
+
+	/* If number of available bytes is less than new SO_RCVLOWAT value,
+	 * kick sender to send more data, because sender may sleep in its
+	 * 'send()' syscall waiting for enough space at our side. Also
+	 * don't send credit update when peer already knows actual value -
+	 * such transmission will be useless.
+	 */
+	send_update = (vvs->rx_bytes < val) &&
+		      (vvs->fwd_cnt != vvs->last_fwd_cnt);
+
+	spin_unlock_bh(&vvs->rx_lock);
+
+	if (send_update) {
+		int err;
+
+		err = virtio_transport_send_credit_update(vsk);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_set_rcvlowat);
+
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Asias He");
 MODULE_DESCRIPTION("common code for virtio vsock");

net/vmw_vsock/vsock_loopback.c

@@ -96,6 +96,7 @@ static struct virtio_transport loopback_transport = {
 		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
 		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
+		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
 		.read_skb = virtio_transport_read_skb,
 	},

tools/testing/vsock/vsock_test.c

@@ -1232,6 +1232,171 @@ static void test_double_bind_connect_client(const struct test_opts *opts)
 	}
 }
 
+#define RCVLOWAT_CREDIT_UPD_BUF_SIZE	(1024 * 128)
+/* This define is the same as in 'include/linux/virtio_vsock.h':
+ * it is used to decide when to send credit update message during
+ * reading from rx queue of a socket. Value and its usage in
+ * kernel is important for this test.
+ */
+#define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE	(1024 * 64)
+
+static void test_stream_rcvlowat_def_cred_upd_client(const struct test_opts *opts)
+{
+	size_t buf_size;
+	void *buf;
+	int fd;
+
+	fd = vsock_stream_connect(opts->peer_cid, 1234);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Send 1 byte more than peer's buffer size. */
+	buf_size = RCVLOWAT_CREDIT_UPD_BUF_SIZE + 1;
+
+	buf = malloc(buf_size);
+	if (!buf) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Wait until peer sets needed buffer size. */
+	recv_byte(fd, 1, 0);
+
+	if (send(fd, buf, buf_size, 0) != buf_size) {
+		perror("send failed");
+		exit(EXIT_FAILURE);
+	}
+
+	free(buf);
+	close(fd);
+}
+
+static void test_stream_credit_update_test(const struct test_opts *opts,
+					   bool low_rx_bytes_test)
+{
+	size_t recv_buf_size;
+	struct pollfd fds;
+	size_t buf_size;
+	void *buf;
+	int fd;
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	buf_size = RCVLOWAT_CREDIT_UPD_BUF_SIZE;
+
+	if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE,
+		       &buf_size, sizeof(buf_size))) {
+		perror("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)");
+		exit(EXIT_FAILURE);
+	}
+
+	if (low_rx_bytes_test) {
+		/* Set new SO_RCVLOWAT here. This enables sending credit
+		 * update when number of bytes if our rx queue become <
+		 * SO_RCVLOWAT value.
+		 */
+		recv_buf_size = 1 + VIRTIO_VSOCK_MAX_PKT_BUF_SIZE;
+
+		if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT,
+			       &recv_buf_size, sizeof(recv_buf_size))) {
+			perror("setsockopt(SO_RCVLOWAT)");
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	/* Send one dummy byte here, because 'setsockopt()' above also
+	 * sends special packet which tells sender to update our buffer
+	 * size. This 'send_byte()' will serialize such packet with data
+	 * reads in a loop below. Sender starts transmission only when
+	 * it receives this single byte.
+	 */
+	send_byte(fd, 1, 0);
+
+	buf = malloc(buf_size);
+	if (!buf) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Wait until there will be 128KB of data in rx queue. */
+	while (1) {
+		ssize_t res;
+
+		res = recv(fd, buf, buf_size, MSG_PEEK);
+		if (res == buf_size)
+			break;
+
+		if (res <= 0) {
+			fprintf(stderr, "unexpected 'recv()' return: %zi\n", res);
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	/* There is 128KB of data in the socket's rx queue, dequeue first
+	 * 64KB, credit update is sent if 'low_rx_bytes_test' == true.
+	 * Otherwise, credit update is sent in 'if (!low_rx_bytes_test)'.
+	 */
+	recv_buf_size = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE;
+	recv_buf(fd, buf, recv_buf_size, 0, recv_buf_size);
+
+	if (!low_rx_bytes_test) {
+		recv_buf_size++;
+
+		/* Updating SO_RCVLOWAT will send credit update. */
+		if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT,
+			       &recv_buf_size, sizeof(recv_buf_size))) {
+			perror("setsockopt(SO_RCVLOWAT)");
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	fds.fd = fd;
+	fds.events = POLLIN | POLLRDNORM | POLLERR |
+		     POLLRDHUP | POLLHUP;
+
+	/* This 'poll()' will return once we receive last byte
+	 * sent by client.
+	 */
+	if (poll(&fds, 1, -1) < 0) {
+		perror("poll");
+		exit(EXIT_FAILURE);
+	}
+
+	if (fds.revents & POLLERR) {
+		fprintf(stderr, "'poll()' error\n");
+		exit(EXIT_FAILURE);
+	}
+
+	if (fds.revents & (POLLIN | POLLRDNORM)) {
+		recv_buf(fd, buf, recv_buf_size, MSG_DONTWAIT, recv_buf_size);
+	} else {
+		/* These flags must be set, as there is at
+		 * least 64KB of data ready to read.
+		 */
+		fprintf(stderr, "POLLIN | POLLRDNORM expected\n");
+		exit(EXIT_FAILURE);
+	}
+
+	free(buf);
+	close(fd);
+}
+
+static void test_stream_cred_upd_on_low_rx_bytes(const struct test_opts *opts)
+{
+	test_stream_credit_update_test(opts, true);
+}
+
+static void test_stream_cred_upd_on_set_rcvlowat(const struct test_opts *opts)
+{
+	test_stream_credit_update_test(opts, false);
+}
+
 static struct test_case test_cases[] = {
 	{
 		.name = "SOCK_STREAM connection reset",
@@ -1342,6 +1507,16 @@ static struct test_case test_cases[] = {
 		.run_client = test_double_bind_connect_client,
 		.run_server = test_double_bind_connect_server,
 	},
+	{
+		.name = "SOCK_STREAM virtio credit update + SO_RCVLOWAT",
+		.run_client = test_stream_rcvlowat_def_cred_upd_client,
+		.run_server = test_stream_cred_upd_on_set_rcvlowat,
+	},
+	{
+		.name = "SOCK_STREAM virtio credit update + low rx_bytes",
+		.run_client = test_stream_rcvlowat_def_cred_upd_client,
+		.run_server = test_stream_cred_upd_on_low_rx_bytes,
+	},
 	{},
 };