Merge branch 'vsock-introduce-siocinq-ioctl-support'

Xuewei Niu says:

====================
vsock: Introduce SIOCINQ ioctl support

Introduce SIOCINQ ioctl support for vsock, indicating the length of unread
bytes.

Similar with SIOCOUTQ ioctl, the information is transport-dependent.

The first patch adds SIOCINQ ioctl support in AF_VSOCK.

Thanks to @dexuan, the second patch is to fix the issue where hyper-v
`hvs_stream_has_data()` doesn't return the readable bytes.

The third patch wraps the ioctl into `ioctl_int()`, which implements a
retry mechanism to prevent immediate failure.

The last one adds two test cases to check the functionality. The changes
have been tested, and the results are as expected.
====================

Link: https://patch.msgid.link/20250708-siocinq-v6-0-3775f9a9e359@antgroup.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 137 insertions, 12 deletions

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 2e7a3034e965..bae6b89bb5fb 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1389,6 +1389,28 @@ static int vsock_do_ioctl(struct socket *sock, unsigned int cmd,
 	vsk = vsock_sk(sk);
 
 	switch (cmd) {
+	case SIOCINQ: {
+		ssize_t n_bytes;
+
+		if (!vsk->transport) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		if (sock_type_connectible(sk->sk_type) &&
+		    sk->sk_state == TCP_LISTEN) {
+			ret = -EINVAL;
+			break;
+		}
+
+		n_bytes = vsock_stream_has_data(vsk);
+		if (n_bytes < 0) {
+			ret = n_bytes;
+			break;
+		}
+		ret = put_user(n_bytes, arg);
+		break;
+	}
 	case SIOCOUTQ: {
 		ssize_t n_bytes;
 
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 31342ab502b4..432fcbbd14d4 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -694,15 +694,26 @@ out:
 static s64 hvs_stream_has_data(struct vsock_sock *vsk)
 {
 	struct hvsock *hvs = vsk->trans;
+	bool need_refill;
 	s64 ret;
 
 	if (hvs->recv_data_len > 0)
-		return 1;
+		return hvs->recv_data_len;
 
 	switch (hvs_channel_readable_payload(hvs->chan)) {
 	case 1:
-		ret = 1;
-		break;
+		need_refill = !hvs->recv_desc;
+		if (!need_refill)
+			return -EIO;
+
+		hvs->recv_desc = hv_pkt_iter_first(hvs->chan);
+		if (!hvs->recv_desc)
+			return -ENOBUFS;
+
+		ret = hvs_update_recv_data(hvs);
+		if (ret)
+			return ret;
+		return hvs->recv_data_len;
 	case 0:
 		vsk->peer_shutdown |= SEND_SHUTDOWN;
 		ret = 0;
diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 803f1e075b62..1e65c5abd85b 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -17,6 +17,7 @@
 #include <unistd.h>
 #include <assert.h>
 #include <sys/epoll.h>
+#include <sys/ioctl.h>
 #include <sys/mman.h>
 #include <linux/sockios.h>
 
@@ -101,28 +102,39 @@ void vsock_wait_remote_close(int fd)
 	close(epollfd);
 }
 
-/* Wait until transport reports no data left to be sent.
- * Return false if transport does not implement the unsent_bytes() callback.
+/* Wait until ioctl gives an expected int value.
+ * Return false if the op is not supported.
  */
-bool vsock_wait_sent(int fd)
+bool vsock_ioctl_int(int fd, unsigned long op, int expected)
 {
-	int ret, sock_bytes_unsent;
+	int actual, ret;
+	char name[32];
+
+	snprintf(name, sizeof(name), "ioctl(%lu)", op);
 
 	timeout_begin(TIMEOUT);
 	do {
-		ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
+		ret = ioctl(fd, op, &actual);
 		if (ret < 0) {
 			if (errno == EOPNOTSUPP)
 				break;
 
-			perror("ioctl(SIOCOUTQ)");
+			perror(name);
 			exit(EXIT_FAILURE);
 		}
-		timeout_check("SIOCOUTQ");
-	} while (sock_bytes_unsent != 0);
+		timeout_check(name);
+	} while (actual != expected);
 	timeout_end();
 
-	return !ret;
+	return ret >= 0;
+}
+
+/* Wait until transport reports no data left to be sent.
+ * Return false if transport does not implement the unsent_bytes() callback.
+ */
+bool vsock_wait_sent(int fd)
+{
+	return vsock_ioctl_int(fd, SIOCOUTQ, 0);
 }
 
 /* Create socket <type>, bind to <cid, port>.
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index fdd4649fe2d4..142c02a6834a 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -87,6 +87,7 @@ int vsock_stream_listen(unsigned int cid, unsigned int port);
 int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
 			   struct sockaddr_vm *clientaddrp);
 void vsock_wait_remote_close(int fd);
+bool vsock_ioctl_int(int fd, unsigned long op, int expected);
 bool vsock_wait_sent(int fd);
 void send_buf(int fd, const void *buf, size_t len, int flags,
 	      ssize_t expected_ret);
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index be6ce764f694..a66d2360133d 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -24,6 +24,7 @@
 #include <linux/time64.h>
 #include <pthread.h>
 #include <fcntl.h>
+#include <linux/sockios.h>
 
 #include "vsock_test_zerocopy.h"
 #include "timeout.h"
@@ -1307,6 +1308,54 @@ static void test_unsent_bytes_client(const struct test_opts *opts, int type)
 	close(fd);
 }
 
+static void test_unread_bytes_server(const struct test_opts *opts, int type)
+{
+	unsigned char buf[MSG_BUF_IOCTL_LEN];
+	int client_fd;
+
+	client_fd = vsock_accept(VMADDR_CID_ANY, opts->peer_port, NULL, type);
+	if (client_fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	for (int i = 0; i < sizeof(buf); i++)
+		buf[i] = rand() & 0xFF;
+
+	send_buf(client_fd, buf, sizeof(buf), 0, sizeof(buf));
+	control_writeln("SENT");
+
+	close(client_fd);
+}
+
+static void test_unread_bytes_client(const struct test_opts *opts, int type)
+{
+	unsigned char buf[MSG_BUF_IOCTL_LEN];
+	int fd;
+
+	fd = vsock_connect(opts->peer_cid, opts->peer_port, type);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	control_expectln("SENT");
+	/* The data has arrived but has not been read. The expected is
+	 * MSG_BUF_IOCTL_LEN.
+	 */
+	if (!vsock_ioctl_int(fd, SIOCINQ, MSG_BUF_IOCTL_LEN)) {
+		fprintf(stderr, "Test skipped, SIOCINQ not supported.\n");
+		goto out;
+	}
+
+	recv_buf(fd, buf, sizeof(buf), 0, sizeof(buf));
+	/* All data has been consumed, so the expected is 0. */
+	vsock_ioctl_int(fd, SIOCINQ, 0);
+
+out:
+	close(fd);
+}
+
 static void test_stream_unsent_bytes_client(const struct test_opts *opts)
 {
 	test_unsent_bytes_client(opts, SOCK_STREAM);
@@ -1327,6 +1376,26 @@ static void test_seqpacket_unsent_bytes_server(const struct test_opts *opts)
 	test_unsent_bytes_server(opts, SOCK_SEQPACKET);
 }
 
+static void test_stream_unread_bytes_client(const struct test_opts *opts)
+{
+	test_unread_bytes_client(opts, SOCK_STREAM);
+}
+
+static void test_stream_unread_bytes_server(const struct test_opts *opts)
+{
+	test_unread_bytes_server(opts, SOCK_STREAM);
+}
+
+static void test_seqpacket_unread_bytes_client(const struct test_opts *opts)
+{
+	test_unread_bytes_client(opts, SOCK_SEQPACKET);
+}
+
+static void test_seqpacket_unread_bytes_server(const struct test_opts *opts)
+{
+	test_unread_bytes_server(opts, SOCK_SEQPACKET);
+}
+
 #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
@@ -2276,6 +2345,16 @@ static struct test_case test_cases[] = {
 		.run_client = test_stream_transport_change_client,
 		.run_server = test_stream_transport_change_server,
 	},
+	{
+		.name = "SOCK_STREAM ioctl(SIOCINQ) functionality",
+		.run_client = test_stream_unread_bytes_client,
+		.run_server = test_stream_unread_bytes_server,
+	},
+	{
+		.name = "SOCK_SEQPACKET ioctl(SIOCINQ) functionality",
+		.run_client = test_seqpacket_unread_bytes_client,
+		.run_server = test_seqpacket_unread_bytes_server,
+	},
 	{},
 };