aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/clients.h6
-rw-r--r--net/dgram.c623
-rw-r--r--net/hub.c2
-rw-r--r--net/l2tpv3.c3
-rw-r--r--net/meson.build2
-rw-r--r--net/net.c204
-rw-r--r--net/slirp.c5
-rw-r--r--net/socket.c36
-rw-r--r--net/stream.c386
-rw-r--r--net/tap-win32.c3
-rw-r--r--net/tap.c13
-rw-r--r--net/vde.c3
-rw-r--r--net/vhost-user.c3
-rw-r--r--net/vhost-vdpa.c76
14 files changed, 1213 insertions, 152 deletions
diff --git a/net/clients.h b/net/clients.h
index c9157789f2..ed8bdfff1e 100644
--- a/net/clients.h
+++ b/net/clients.h
@@ -40,6 +40,12 @@ int net_init_hubport(const Netdev *netdev, const char *name,
int net_init_socket(const Netdev *netdev, const char *name,
NetClientState *peer, Error **errp);
+int net_init_stream(const Netdev *netdev, const char *name,
+ NetClientState *peer, Error **errp);
+
+int net_init_dgram(const Netdev *netdev, const char *name,
+ NetClientState *peer, Error **errp);
+
int net_init_tap(const Netdev *netdev, const char *name,
NetClientState *peer, Error **errp);
diff --git a/net/dgram.c b/net/dgram.c
new file mode 100644
index 0000000000..9f7bf38376
--- /dev/null
+++ b/net/dgram.c
@@ -0,0 +1,623 @@
+/*
+ * QEMU System Emulator
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ * Copyright (c) 2022 Red Hat, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu/osdep.h"
+
+#include "net/net.h"
+#include "clients.h"
+#include "monitor/monitor.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/option.h"
+#include "qemu/sockets.h"
+#include "qemu/iov.h"
+#include "qemu/main-loop.h"
+#include "qemu/cutils.h"
+
+typedef struct NetDgramState {
+ NetClientState nc;
+ int fd;
+ SocketReadState rs;
+ bool read_poll; /* waiting to receive data? */
+ bool write_poll; /* waiting to transmit data? */
+ /* contains destination iff connectionless */
+ struct sockaddr *dest_addr;
+ socklen_t dest_len;
+} NetDgramState;
+
+static void net_dgram_send(void *opaque);
+static void net_dgram_writable(void *opaque);
+
+static void net_dgram_update_fd_handler(NetDgramState *s)
+{
+ qemu_set_fd_handler(s->fd,
+ s->read_poll ? net_dgram_send : NULL,
+ s->write_poll ? net_dgram_writable : NULL,
+ s);
+}
+
+static void net_dgram_read_poll(NetDgramState *s, bool enable)
+{
+ s->read_poll = enable;
+ net_dgram_update_fd_handler(s);
+}
+
+static void net_dgram_write_poll(NetDgramState *s, bool enable)
+{
+ s->write_poll = enable;
+ net_dgram_update_fd_handler(s);
+}
+
+static void net_dgram_writable(void *opaque)
+{
+ NetDgramState *s = opaque;
+
+ net_dgram_write_poll(s, false);
+
+ qemu_flush_queued_packets(&s->nc);
+}
+
+static ssize_t net_dgram_receive(NetClientState *nc,
+ const uint8_t *buf, size_t size)
+{
+ NetDgramState *s = DO_UPCAST(NetDgramState, nc, nc);
+ ssize_t ret;
+
+ do {
+ if (s->dest_addr) {
+ ret = sendto(s->fd, buf, size, 0, s->dest_addr, s->dest_len);
+ } else {
+ ret = send(s->fd, buf, size, 0);
+ }
+ } while (ret == -1 && errno == EINTR);
+
+ if (ret == -1 && errno == EAGAIN) {
+ net_dgram_write_poll(s, true);
+ return 0;
+ }
+ return ret;
+}
+
+static void net_dgram_send_completed(NetClientState *nc, ssize_t len)
+{
+ NetDgramState *s = DO_UPCAST(NetDgramState, nc, nc);
+
+ if (!s->read_poll) {
+ net_dgram_read_poll(s, true);
+ }
+}
+
+static void net_dgram_rs_finalize(SocketReadState *rs)
+{
+ NetDgramState *s = container_of(rs, NetDgramState, rs);
+
+ if (qemu_send_packet_async(&s->nc, rs->buf,
+ rs->packet_len,
+ net_dgram_send_completed) == 0) {
+ net_dgram_read_poll(s, false);
+ }
+}
+
+static void net_dgram_send(void *opaque)
+{
+ NetDgramState *s = opaque;
+ int size;
+
+ size = recv(s->fd, s->rs.buf, sizeof(s->rs.buf), 0);
+ if (size < 0) {
+ return;
+ }
+ if (size == 0) {
+ /* end of connection */
+ net_dgram_read_poll(s, false);
+ net_dgram_write_poll(s, false);
+ return;
+ }
+ if (qemu_send_packet_async(&s->nc, s->rs.buf, size,
+ net_dgram_send_completed) == 0) {
+ net_dgram_read_poll(s, false);
+ }
+}
+
+static int net_dgram_mcast_create(struct sockaddr_in *mcastaddr,
+ struct in_addr *localaddr,
+ Error **errp)
+{
+ struct ip_mreq imr;
+ int fd;
+ int val, ret;
+#ifdef __OpenBSD__
+ unsigned char loop;
+#else
+ int loop;
+#endif
+
+ if (!IN_MULTICAST(ntohl(mcastaddr->sin_addr.s_addr))) {
+ error_setg(errp, "specified mcastaddr %s (0x%08x) "
+ "does not contain a multicast address",
+ inet_ntoa(mcastaddr->sin_addr),
+ (int)ntohl(mcastaddr->sin_addr.s_addr));
+ return -1;
+ }
+
+ fd = qemu_socket(PF_INET, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ error_setg_errno(errp, errno, "can't create datagram socket");
+ return -1;
+ }
+
+ /*
+ * Allow multiple sockets to bind the same multicast ip and port by setting
+ * SO_REUSEADDR. This is the only situation where SO_REUSEADDR should be set
+ * on windows. Use socket_set_fast_reuse otherwise as it sets SO_REUSEADDR
+ * only on posix systems.
+ */
+ val = 1;
+ ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &val, sizeof(val));
+ if (ret < 0) {
+ error_setg_errno(errp, errno, "can't set socket option SO_REUSEADDR");
+ goto fail;
+ }
+
+ ret = bind(fd, (struct sockaddr *)mcastaddr, sizeof(*mcastaddr));
+ if (ret < 0) {
+ error_setg_errno(errp, errno, "can't bind ip=%s to socket",
+ inet_ntoa(mcastaddr->sin_addr));
+ goto fail;
+ }
+
+ /* Add host to multicast group */
+ imr.imr_multiaddr = mcastaddr->sin_addr;
+ if (localaddr) {
+ imr.imr_interface = *localaddr;
+ } else {
+ imr.imr_interface.s_addr = htonl(INADDR_ANY);
+ }
+
+ ret = setsockopt(fd, IPPROTO_IP, IP_ADD_MEMBERSHIP,
+ &imr, sizeof(struct ip_mreq));
+ if (ret < 0) {
+ error_setg_errno(errp, errno,
+ "can't add socket to multicast group %s",
+ inet_ntoa(imr.imr_multiaddr));
+ goto fail;
+ }
+
+ /* Force mcast msgs to loopback (eg. several QEMUs in same host */
+ loop = 1;
+ ret = setsockopt(fd, IPPROTO_IP, IP_MULTICAST_LOOP,
+ &loop, sizeof(loop));
+ if (ret < 0) {
+ error_setg_errno(errp, errno,
+ "can't force multicast message to loopback");
+ goto fail;
+ }
+
+ /* If a bind address is given, only send packets from that address */
+ if (localaddr != NULL) {
+ ret = setsockopt(fd, IPPROTO_IP, IP_MULTICAST_IF,
+ localaddr, sizeof(*localaddr));
+ if (ret < 0) {
+ error_setg_errno(errp, errno,
+ "can't set the default network send interface");
+ goto fail;
+ }
+ }
+
+ qemu_socket_set_nonblock(fd);
+ return fd;
+fail:
+ if (fd >= 0) {
+ closesocket(fd);
+ }
+ return -1;
+}
+
+static void net_dgram_cleanup(NetClientState *nc)
+{
+ NetDgramState *s = DO_UPCAST(NetDgramState, nc, nc);
+ if (s->fd != -1) {
+ net_dgram_read_poll(s, false);
+ net_dgram_write_poll(s, false);
+ close(s->fd);
+ s->fd = -1;
+ }
+ g_free(s->dest_addr);
+ s->dest_addr = NULL;
+ s->dest_len = 0;
+}
+
+static NetClientInfo net_dgram_socket_info = {
+ .type = NET_CLIENT_DRIVER_DGRAM,
+ .size = sizeof(NetDgramState),
+ .receive = net_dgram_receive,
+ .cleanup = net_dgram_cleanup,
+};
+
+static NetDgramState *net_dgram_fd_init(NetClientState *peer,
+ const char *model,
+ const char *name,
+ int fd,
+ Error **errp)
+{
+ NetClientState *nc;
+ NetDgramState *s;
+
+ nc = qemu_new_net_client(&net_dgram_socket_info, peer, model, name);
+
+ s = DO_UPCAST(NetDgramState, nc, nc);
+
+ s->fd = fd;
+ net_socket_rs_init(&s->rs, net_dgram_rs_finalize, false);
+ net_dgram_read_poll(s, true);
+
+ return s;
+}
+
+static int net_dgram_mcast_init(NetClientState *peer,
+ const char *model,
+ const char *name,
+ SocketAddress *remote,
+ SocketAddress *local,
+ Error **errp)
+{
+ NetDgramState *s;
+ int fd, ret;
+ struct sockaddr_in *saddr;
+
+ if (remote->type != SOCKET_ADDRESS_TYPE_INET) {
+ error_setg(errp, "multicast only support inet type");
+ return -1;
+ }
+
+ saddr = g_new(struct sockaddr_in, 1);
+ if (convert_host_port(saddr, remote->u.inet.host, remote->u.inet.port,
+ errp) < 0) {
+ g_free(saddr);
+ return -1;
+ }
+
+ if (!local) {
+ fd = net_dgram_mcast_create(saddr, NULL, errp);
+ if (fd < 0) {
+ g_free(saddr);
+ return -1;
+ }
+ } else {
+ switch (local->type) {
+ case SOCKET_ADDRESS_TYPE_INET: {
+ struct in_addr localaddr;
+
+ if (inet_aton(local->u.inet.host, &localaddr) == 0) {
+ g_free(saddr);
+ error_setg(errp, "localaddr '%s' is not a valid IPv4 address",
+ local->u.inet.host);
+ return -1;
+ }
+
+ fd = net_dgram_mcast_create(saddr, &localaddr, errp);
+ if (fd < 0) {
+ g_free(saddr);
+ return -1;
+ }
+ break;
+ }
+ case SOCKET_ADDRESS_TYPE_FD: {
+ int newfd;
+
+ fd = monitor_fd_param(monitor_cur(), local->u.fd.str, errp);
+ if (fd == -1) {
+ g_free(saddr);
+ return -1;
+ }
+ ret = qemu_socket_try_set_nonblock(fd);
+ if (ret < 0) {
+ g_free(saddr);
+ error_setg_errno(errp, -ret, "%s: Can't use file descriptor %d",
+ name, fd);
+ return -1;
+ }
+
+ /*
+ * fd passed: multicast: "learn" dest_addr address from bound
+ * address and save it. Because this may be "shared" socket from a
+ * "master" process, datagrams would be recv() by ONLY ONE process:
+ * we must "clone" this dgram socket --jjo
+ */
+
+ saddr = g_new(struct sockaddr_in, 1);
+
+ if (convert_host_port(saddr, local->u.inet.host, local->u.inet.port,
+ errp) < 0) {
+ g_free(saddr);
+ closesocket(fd);
+ return -1;
+ }
+
+ /* must be bound */
+ if (saddr->sin_addr.s_addr == 0) {
+ error_setg(errp, "can't setup multicast destination address");
+ g_free(saddr);
+ closesocket(fd);
+ return -1;
+ }
+ /* clone dgram socket */
+ newfd = net_dgram_mcast_create(saddr, NULL, errp);
+ if (newfd < 0) {
+ g_free(saddr);
+ closesocket(fd);
+ return -1;
+ }
+ /* clone newfd to fd, close newfd */
+ dup2(newfd, fd);
+ close(newfd);
+ break;
+ }
+ default:
+ g_free(saddr);
+ error_setg(errp, "only support inet or fd type for local");
+ return -1;
+ }
+ }
+
+ s = net_dgram_fd_init(peer, model, name, fd, errp);
+ if (!s) {
+ g_free(saddr);
+ return -1;
+ }
+
+ g_assert(s->dest_addr == NULL);
+ s->dest_addr = (struct sockaddr *)saddr;
+ s->dest_len = sizeof(*saddr);
+
+ if (!local) {
+ qemu_set_info_str(&s->nc, "mcast=%s:%d",
+ inet_ntoa(saddr->sin_addr),
+ ntohs(saddr->sin_port));
+ } else {
+ switch (local->type) {
+ case SOCKET_ADDRESS_TYPE_INET:
+ qemu_set_info_str(&s->nc, "mcast=%s:%d",
+ inet_ntoa(saddr->sin_addr),
+ ntohs(saddr->sin_port));
+ break;
+ case SOCKET_ADDRESS_TYPE_FD:
+ qemu_set_info_str(&s->nc, "fd=%d (cloned mcast=%s:%d)",
+ fd, inet_ntoa(saddr->sin_addr),
+ ntohs(saddr->sin_port));
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ }
+
+ return 0;
+
+}
+
+
+int net_init_dgram(const Netdev *netdev, const char *name,
+ NetClientState *peer, Error **errp)
+{
+ NetDgramState *s;
+ int fd, ret;
+ SocketAddress *remote, *local;
+ struct sockaddr *dest_addr;
+ struct sockaddr_in laddr_in, raddr_in;
+ struct sockaddr_un laddr_un, raddr_un;
+ socklen_t dest_len;
+
+ assert(netdev->type == NET_CLIENT_DRIVER_DGRAM);
+
+ remote = netdev->u.dgram.remote;
+ local = netdev->u.dgram.local;
+
+ /* detect multicast address */
+ if (remote && remote->type == SOCKET_ADDRESS_TYPE_INET) {
+ struct sockaddr_in mcastaddr;
+
+ if (convert_host_port(&mcastaddr, remote->u.inet.host,
+ remote->u.inet.port, errp) < 0) {
+ return -1;
+ }
+
+ if (IN_MULTICAST(ntohl(mcastaddr.sin_addr.s_addr))) {
+ return net_dgram_mcast_init(peer, "dram", name, remote, local,
+ errp);
+ }
+ }
+
+ /* unicast address */
+ if (!local) {
+ error_setg(errp, "dgram requires local= parameter");
+ return -1;
+ }
+
+ if (remote) {
+ if (local->type == SOCKET_ADDRESS_TYPE_FD) {
+ error_setg(errp, "don't set remote with local.fd");
+ return -1;
+ }
+ if (remote->type != local->type) {
+ error_setg(errp, "remote and local types must be the same");
+ return -1;
+ }
+ } else {
+ if (local->type != SOCKET_ADDRESS_TYPE_FD) {
+ error_setg(errp,
+ "type=inet or type=unix requires remote parameter");
+ return -1;
+ }
+ }
+
+ switch (local->type) {
+ case SOCKET_ADDRESS_TYPE_INET:
+ if (convert_host_port(&laddr_in, local->u.inet.host, local->u.inet.port,
+ errp) < 0) {
+ return -1;
+ }
+
+ if (convert_host_port(&raddr_in, remote->u.inet.host,
+ remote->u.inet.port, errp) < 0) {
+ return -1;
+ }
+
+ fd = qemu_socket(PF_INET, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ error_setg_errno(errp, errno, "can't create datagram socket");
+ return -1;
+ }
+
+ ret = socket_set_fast_reuse(fd);
+ if (ret < 0) {
+ error_setg_errno(errp, errno,
+ "can't set socket option SO_REUSEADDR");
+ closesocket(fd);
+ return -1;
+ }
+ ret = bind(fd, (struct sockaddr *)&laddr_in, sizeof(laddr_in));
+ if (ret < 0) {
+ error_setg_errno(errp, errno, "can't bind ip=%s to socket",
+ inet_ntoa(laddr_in.sin_addr));
+ closesocket(fd);
+ return -1;
+ }
+ qemu_socket_set_nonblock(fd);
+
+ dest_len = sizeof(raddr_in);
+ dest_addr = g_malloc(dest_len);
+ memcpy(dest_addr, &raddr_in, dest_len);
+ break;
+ case SOCKET_ADDRESS_TYPE_UNIX:
+ ret = unlink(local->u.q_unix.path);
+ if (ret < 0 && errno != ENOENT) {
+ error_setg_errno(errp, errno, "failed to unlink socket %s",
+ local->u.q_unix.path);
+ return -1;
+ }
+
+ laddr_un.sun_family = PF_UNIX;
+ ret = snprintf(laddr_un.sun_path, sizeof(laddr_un.sun_path), "%s",
+ local->u.q_unix.path);
+ if (ret < 0 || ret >= sizeof(laddr_un.sun_path)) {
+ error_setg(errp, "UNIX socket path '%s' is too long",
+ local->u.q_unix.path);
+ error_append_hint(errp, "Path must be less than %zu bytes\n",
+ sizeof(laddr_un.sun_path));
+ }
+
+ raddr_un.sun_family = PF_UNIX;
+ ret = snprintf(raddr_un.sun_path, sizeof(raddr_un.sun_path), "%s",
+ remote->u.q_unix.path);
+ if (ret < 0 || ret >= sizeof(raddr_un.sun_path)) {
+ error_setg(errp, "UNIX socket path '%s' is too long",
+ remote->u.q_unix.path);
+ error_append_hint(errp, "Path must be less than %zu bytes\n",
+ sizeof(raddr_un.sun_path));
+ }
+
+ fd = qemu_socket(PF_UNIX, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ error_setg_errno(errp, errno, "can't create datagram socket");
+ return -1;
+ }
+
+ ret = bind(fd, (struct sockaddr *)&laddr_un, sizeof(laddr_un));
+ if (ret < 0) {
+ error_setg_errno(errp, errno, "can't bind unix=%s to socket",
+ laddr_un.sun_path);
+ closesocket(fd);
+ return -1;
+ }
+ qemu_socket_set_nonblock(fd);
+
+ dest_len = sizeof(raddr_un);
+ dest_addr = g_malloc(dest_len);
+ memcpy(dest_addr, &raddr_un, dest_len);
+ break;
+ case SOCKET_ADDRESS_TYPE_FD:
+ fd = monitor_fd_param(monitor_cur(), local->u.fd.str, errp);
+ if (fd == -1) {
+ return -1;
+ }
+ ret = qemu_socket_try_set_nonblock(fd);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "%s: Can't use file descriptor %d",
+ name, fd);
+ return -1;
+ }
+ dest_addr = NULL;
+ dest_len = 0;
+ break;
+ default:
+ error_setg(errp, "only support inet or fd type for local");
+ return -1;
+ }
+
+ s = net_dgram_fd_init(peer, "dgram", name, fd, errp);
+ if (!s) {
+ return -1;
+ }
+
+ if (remote) {
+ g_assert(s->dest_addr == NULL);
+ s->dest_addr = dest_addr;
+ s->dest_len = dest_len;
+ }
+
+ switch (local->type) {
+ case SOCKET_ADDRESS_TYPE_INET:
+ qemu_set_info_str(&s->nc, "udp=%s:%d/%s:%d",
+ inet_ntoa(laddr_in.sin_addr),
+ ntohs(laddr_in.sin_port),
+ inet_ntoa(raddr_in.sin_addr),
+ ntohs(raddr_in.sin_port));
+ break;
+ case SOCKET_ADDRESS_TYPE_UNIX:
+ qemu_set_info_str(&s->nc, "udp=%s:%s",
+ laddr_un.sun_path, raddr_un.sun_path);
+ break;
+ case SOCKET_ADDRESS_TYPE_FD: {
+ SocketAddress *sa;
+ SocketAddressType sa_type;
+
+ sa = socket_local_address(fd, errp);
+ if (sa) {
+ sa_type = sa->type;
+ qapi_free_SocketAddress(sa);
+
+ qemu_set_info_str(&s->nc, "fd=%d %s", fd,
+ SocketAddressType_str(sa_type));
+ } else {
+ qemu_set_info_str(&s->nc, "fd=%d", fd);
+ }
+ break;
+ }
+ default:
+ g_assert_not_reached();
+ }
+
+ return 0;
+}
diff --git a/net/hub.c b/net/hub.c
index 1375738bf1..67ca534856 100644
--- a/net/hub.c
+++ b/net/hub.c
@@ -313,6 +313,8 @@ void net_hub_check_clients(void)
case NET_CLIENT_DRIVER_USER:
case NET_CLIENT_DRIVER_TAP:
case NET_CLIENT_DRIVER_SOCKET:
+ case NET_CLIENT_DRIVER_STREAM:
+ case NET_CLIENT_DRIVER_DGRAM:
case NET_CLIENT_DRIVER_VDE:
case NET_CLIENT_DRIVER_VHOST_USER:
has_host_dev = 1;
diff --git a/net/l2tpv3.c b/net/l2tpv3.c
index af373e5c30..350041a0d6 100644
--- a/net/l2tpv3.c
+++ b/net/l2tpv3.c
@@ -723,8 +723,7 @@ int net_init_l2tpv3(const Netdev *netdev,
l2tpv3_read_poll(s, true);
- snprintf(s->nc.info_str, sizeof(s->nc.info_str),
- "l2tpv3: connected");
+ qemu_set_info_str(&s->nc, "l2tpv3: connected");
return 0;
outerr:
qemu_del_net_client(nc);
diff --git a/net/meson.build b/net/meson.build
index d1be76daf3..6cd1e3dab3 100644
--- a/net/meson.build
+++ b/net/meson.build
@@ -13,6 +13,8 @@ softmmu_ss.add(files(
'net.c',
'queue.c',
'socket.c',
+ 'stream.c',
+ 'dgram.c',
'util.c',
))
diff --git a/net/net.c b/net/net.c
index 2db160e063..840ad9dca5 100644
--- a/net/net.c
+++ b/net/net.c
@@ -48,12 +48,14 @@
#include "qemu/qemu-print.h"
#include "qemu/main-loop.h"
#include "qemu/option.h"
+#include "qemu/keyval.h"
#include "qapi/error.h"
#include "qapi/opts-visitor.h"
#include "sysemu/runstate.h"
#include "net/colo-compare.h"
#include "net/filter.h"
#include "qapi/string-output-visitor.h"
+#include "qapi/qobject-input-visitor.h"
/* Net bridge is currently not supported for W32. */
#if !defined(_WIN32)
@@ -63,58 +65,70 @@
static VMChangeStateEntry *net_change_state_entry;
static QTAILQ_HEAD(, NetClientState) net_clients;
+typedef struct NetdevQueueEntry {
+ Netdev *nd;
+ Location loc;
+ QSIMPLEQ_ENTRY(NetdevQueueEntry) entry;
+} NetdevQueueEntry;
+
+typedef QSIMPLEQ_HEAD(, NetdevQueueEntry) NetdevQueue;
+
+static NetdevQueue nd_queue = QSIMPLEQ_HEAD_INITIALIZER(nd_queue);
+
/***********************************************************/
/* network device redirectors */
-int parse_host_port(struct sockaddr_in *saddr, const char *str,
- Error **errp)
+int convert_host_port(struct sockaddr_in *saddr, const char *host,
+ const char *port, Error **errp)
{
- gchar **substrings;
struct hostent *he;
- const char *addr, *p, *r;
- int port, ret = 0;
+ const char *r;
+ long p;
memset(saddr, 0, sizeof(*saddr));
- substrings = g_strsplit(str, ":", 2);
- if (!substrings || !substrings[0] || !substrings[1]) {
- error_setg(errp, "host address '%s' doesn't contain ':' "
- "separating host from port", str);
- ret = -1;
- goto out;
- }
-
- addr = substrings[0];
- p = substrings[1];
-
saddr->sin_family = AF_INET;
- if (addr[0] == '\0') {
+ if (host[0] == '\0') {
saddr->sin_addr.s_addr = 0;
} else {
- if (qemu_isdigit(addr[0])) {
- if (!inet_aton(addr, &saddr->sin_addr)) {
+ if (qemu_isdigit(host[0])) {
+ if (!inet_aton(host, &saddr->sin_addr)) {
error_setg(errp, "host address '%s' is not a valid "
- "IPv4 address", addr);
- ret = -1;
- goto out;
+ "IPv4 address", host);
+ return -1;
}
} else {
- he = gethostbyname(addr);
+ he = gethostbyname(host);
if (he == NULL) {
- error_setg(errp, "can't resolve host address '%s'", addr);
- ret = -1;
- goto out;
+ error_setg(errp, "can't resolve host address '%s'", host);
+ return -1;
}
saddr->sin_addr = *(struct in_addr *)he->h_addr;
}
}
- port = strtol(p, (char **)&r, 0);
- if (r == p) {
- error_setg(errp, "port number '%s' is invalid", p);
+ if (qemu_strtol(port, &r, 0, &p) != 0) {
+ error_setg(errp, "port number '%s' is invalid", port);
+ return -1;
+ }
+ saddr->sin_port = htons(p);
+ return 0;
+}
+
+int parse_host_port(struct sockaddr_in *saddr, const char *str,
+ Error **errp)
+{
+ gchar **substrings;
+ int ret;
+
+ substrings = g_strsplit(str, ":", 2);
+ if (!substrings || !substrings[0] || !substrings[1]) {
+ error_setg(errp, "host address '%s' doesn't contain ':' "
+ "separating host from port", str);
ret = -1;
goto out;
}
- saddr->sin_port = htons(port);
+
+ ret = convert_host_port(saddr, substrings[0], substrings[1], errp);
out:
g_strfreev(substrings);
@@ -128,13 +142,20 @@ char *qemu_mac_strdup_printf(const uint8_t *macaddr)
macaddr[3], macaddr[4], macaddr[5]);
}
+void qemu_set_info_str(NetClientState *nc, const char *fmt, ...)
+{
+ va_list ap;
+
+ va_start(ap, fmt);
+ vsnprintf(nc->info_str, sizeof(nc->info_str), fmt, ap);
+ va_end(ap);
+}
+
void qemu_format_nic_info_str(NetClientState *nc, uint8_t macaddr[6])
{
- snprintf(nc->info_str, sizeof(nc->info_str),
- "model=%s,macaddr=%02x:%02x:%02x:%02x:%02x:%02x",
- nc->model,
- macaddr[0], macaddr[1], macaddr[2],
- macaddr[3], macaddr[4], macaddr[5]);
+ qemu_set_info_str(nc, "model=%s,macaddr=%02x:%02x:%02x:%02x:%02x:%02x",
+ nc->model, macaddr[0], macaddr[1], macaddr[2],
+ macaddr[3], macaddr[4], macaddr[5]);
}
static int mac_table[256] = {0};
@@ -1001,6 +1022,8 @@ static int (* const net_client_init_fun[NET_CLIENT_DRIVER__MAX])(
#endif
[NET_CLIENT_DRIVER_TAP] = net_init_tap,
[NET_CLIENT_DRIVER_SOCKET] = net_init_socket,
+ [NET_CLIENT_DRIVER_STREAM] = net_init_stream,
+ [NET_CLIENT_DRIVER_DGRAM] = net_init_dgram,
#ifdef CONFIG_VDE
[NET_CLIENT_DRIVER_VDE] = net_init_vde,
#endif
@@ -1036,19 +1059,23 @@ static int net_client_init1(const Netdev *netdev, bool is_netdev, Error **errp)
if (is_netdev) {
if (netdev->type == NET_CLIENT_DRIVER_NIC ||
!net_client_init_fun[netdev->type]) {
- error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "type",
- "a netdev backend type");
+ error_setg(errp, "network backend '%s' is not compiled into this binary",
+ NetClientDriver_str(netdev->type));
return -1;
}
} else {
if (netdev->type == NET_CLIENT_DRIVER_NONE) {
return 0; /* nothing to do */
}
- if (netdev->type == NET_CLIENT_DRIVER_HUBPORT ||
- !net_client_init_fun[netdev->type]) {
- error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "type",
- "a net backend type (maybe it is not compiled "
- "into this binary)");
+ if (netdev->type == NET_CLIENT_DRIVER_HUBPORT) {
+ error_setg(errp, "network backend '%s' is only supported with -netdev/-nic",
+ NetClientDriver_str(netdev->type));
+ return -1;
+ }
+
+ if (!net_client_init_fun[netdev->type]) {
+ error_setg(errp, "network backend '%s' is not compiled into this binary",
+ NetClientDriver_str(netdev->type));
return -1;
}
@@ -1088,6 +1115,8 @@ void show_netdevs(void)
int idx;
const char *available_netdevs[] = {
"socket",
+ "stream",
+ "dgram",
"hubport",
"tap",
#ifdef CONFIG_SLIRP
@@ -1560,36 +1589,97 @@ out:
return ret;
}
-int net_init_clients(Error **errp)
+static void netdev_init_modern(void)
+{
+ while (!QSIMPLEQ_EMPTY(&nd_queue)) {
+ NetdevQueueEntry *nd = QSIMPLEQ_FIRST(&nd_queue);
+
+ QSIMPLEQ_REMOVE_HEAD(&nd_queue, entry);
+ loc_push_restore(&nd->loc);
+ net_client_init1(nd->nd, true, &error_fatal);
+ loc_pop(&nd->loc);
+ qapi_free_Netdev(nd->nd);
+ g_free(nd);
+ }
+}
+
+void net_init_clients(void)
{
net_change_state_entry =
qemu_add_vm_change_state_handler(net_vm_change_state_handler, NULL);
QTAILQ_INIT(&net_clients);
- if (qemu_opts_foreach(qemu_find_opts("netdev"),
- net_init_netdev, NULL, errp)) {
- return -1;
- }
+ netdev_init_modern();
- if (qemu_opts_foreach(qemu_find_opts("nic"), net_param_nic, NULL, errp)) {
- return -1;
- }
+ qemu_opts_foreach(qemu_find_opts("netdev"), net_init_netdev, NULL,
+ &error_fatal);
- if (qemu_opts_foreach(qemu_find_opts("net"), net_init_client, NULL, errp)) {
- return -1;
+ qemu_opts_foreach(qemu_find_opts("nic"), net_param_nic, NULL,
+ &error_fatal);
+
+ qemu_opts_foreach(qemu_find_opts("net"), net_init_client, NULL,
+ &error_fatal);
+}
+
+/*
+ * Does this -netdev argument use modern rather than traditional syntax?
+ * Modern syntax is to be parsed with netdev_parse_modern().
+ * Traditional syntax is to be parsed with net_client_parse().
+ */
+bool netdev_is_modern(const char *optarg)
+{
+ QemuOpts *opts;
+ bool is_modern;
+ const char *type;
+ static QemuOptsList dummy_opts = {
+ .name = "netdev",
+ .implied_opt_name = "type",
+ .head = QTAILQ_HEAD_INITIALIZER(dummy_opts.head),
+ .desc = { { } },
+ };
+
+ if (optarg[0] == '{') {
+ /* This is JSON, which means it's modern syntax */
+ return true;
}
- return 0;
+ opts = qemu_opts_create(&dummy_opts, NULL, false, &error_abort);
+ qemu_opts_do_parse(opts, optarg, dummy_opts.implied_opt_name,
+ &error_abort);
+ type = qemu_opt_get(opts, "type");
+ is_modern = !g_strcmp0(type, "stream") || !g_strcmp0(type, "dgram");
+
+ qemu_opts_reset(&dummy_opts);
+
+ return is_modern;
+}
+
+/*
+ * netdev_parse_modern() uses modern, more expressive syntax than
+ * net_client_parse(), but supports only the -netdev option.
+ * netdev_parse_modern() appends to @nd_queue, whereas net_client_parse()
+ * appends to @qemu_netdev_opts.
+ */
+void netdev_parse_modern(const char *optarg)
+{
+ Visitor *v;
+ NetdevQueueEntry *nd;
+
+ v = qobject_input_visitor_new_str(optarg, "type", &error_fatal);
+ nd = g_new(NetdevQueueEntry, 1);
+ visit_type_Netdev(v, NULL, &nd->nd, &error_fatal);
+ visit_free(v);
+ loc_save(&nd->loc);
+
+ QSIMPLEQ_INSERT_TAIL(&nd_queue, nd, entry);
}
-int net_client_parse(QemuOptsList *opts_list, const char *optarg)
+void net_client_parse(QemuOptsList *opts_list, const char *optarg)
{
if (!qemu_opts_parse_noisily(opts_list, optarg, true)) {
- return -1;
+ exit(1);
}
-
- return 0;
}
/* From FreeBSD */
diff --git a/net/slirp.c b/net/slirp.c
index 8679be6444..14a8d59277 100644
--- a/net/slirp.c
+++ b/net/slirp.c
@@ -611,9 +611,8 @@ static int net_slirp_init(NetClientState *peer, const char *model,
nc = qemu_new_net_client(&net_slirp_info, peer, model, name);
- snprintf(nc->info_str, sizeof(nc->info_str),
- "net=%s,restrict=%s", inet_ntoa(net),
- restricted ? "on" : "off");
+ qemu_set_info_str(nc, "net=%s,restrict=%s", inet_ntoa(net),
+ restricted ? "on" : "off");
s = DO_UPCAST(SlirpState, nc, nc);
diff --git a/net/socket.c b/net/socket.c
index bfd8596250..4944bb70d5 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -179,7 +179,7 @@ static void net_socket_send(void *opaque)
s->fd = -1;
net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
s->nc.link_down = true;
- memset(s->nc.info_str, 0, sizeof(s->nc.info_str));
+ qemu_set_info_str(&s->nc, "");
return;
}
@@ -387,16 +387,15 @@ static NetSocketState *net_socket_fd_init_dgram(NetClientState *peer,
/* mcast: save bound address as dst */
if (is_connected && mcast != NULL) {
s->dgram_dst = saddr;
- snprintf(nc->info_str, sizeof(nc->info_str),
- "socket: fd=%d (cloned mcast=%s:%d)",
- fd, inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
+ qemu_set_info_str(nc, "socket: fd=%d (cloned mcast=%s:%d)", fd,
+ inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
} else {
if (sa_type == SOCKET_ADDRESS_TYPE_UNIX) {
s->dgram_dst.sin_family = AF_UNIX;
}
- snprintf(nc->info_str, sizeof(nc->info_str),
- "socket: fd=%d %s", fd, SocketAddressType_str(sa_type));
+ qemu_set_info_str(nc, "socket: fd=%d %s", fd,
+ SocketAddressType_str(sa_type));
}
return s;
@@ -430,7 +429,7 @@ static NetSocketState *net_socket_fd_init_stream(NetClientState *peer,
nc = qemu_new_net_client(&net_socket_info, peer, model, name);
- snprintf(nc->info_str, sizeof(nc->info_str), "socket: fd=%d", fd);
+ qemu_set_info_str(nc, "socket: fd=%d", fd);
s = DO_UPCAST(NetSocketState, nc, nc);
@@ -497,9 +496,8 @@ static void net_socket_accept(void *opaque)
s->fd = fd;
s->nc.link_down = false;
net_socket_connect(s);
- snprintf(s->nc.info_str, sizeof(s->nc.info_str),
- "socket: connection from %s:%d",
- inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
+ qemu_set_info_str(&s->nc, "socket: connection from %s:%d",
+ inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
}
static int net_socket_listen_init(NetClientState *peer,
@@ -579,8 +577,7 @@ static int net_socket_connect_init(NetClientState *peer,
if (errno == EINTR || errno == EWOULDBLOCK) {
/* continue */
} else if (errno == EINPROGRESS ||
- errno == EALREADY ||
- errno == EINVAL) {
+ errno == EALREADY) {
break;
} else {
error_setg_errno(errp, errno, "can't connect socket");
@@ -597,9 +594,8 @@ static int net_socket_connect_init(NetClientState *peer,
return -1;
}
- snprintf(s->nc.info_str, sizeof(s->nc.info_str),
- "socket: connect to %s:%d",
- inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
+ qemu_set_info_str(&s->nc, "socket: connect to %s:%d",
+ inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
return 0;
}
@@ -642,9 +638,8 @@ static int net_socket_mcast_init(NetClientState *peer,
s->dgram_dst = saddr;
- snprintf(s->nc.info_str, sizeof(s->nc.info_str),
- "socket: mcast=%s:%d",
- inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
+ qemu_set_info_str(&s->nc, "socket: mcast=%s:%d",
+ inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
return 0;
}
@@ -697,9 +692,8 @@ static int net_socket_udp_init(NetClientState *peer,
s->dgram_dst = raddr;
- snprintf(s->nc.info_str, sizeof(s->nc.info_str),
- "socket: udp=%s:%d",
- inet_ntoa(raddr.sin_addr), ntohs(raddr.sin_port));
+ qemu_set_info_str(&s->nc, "socket: udp=%s:%d", inet_ntoa(raddr.sin_addr),
+ ntohs(raddr.sin_port));
return 0;
}
diff --git a/net/stream.c b/net/stream.c
new file mode 100644
index 0000000000..53b7040cc4
--- /dev/null
+++ b/net/stream.c
@@ -0,0 +1,386 @@
+/*
+ * QEMU System Emulator
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ * Copyright (c) 2022 Red Hat, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu/osdep.h"
+
+#include "net/net.h"
+#include "clients.h"
+#include "monitor/monitor.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/option.h"
+#include "qemu/sockets.h"
+#include "qemu/iov.h"
+#include "qemu/main-loop.h"
+#include "qemu/cutils.h"
+#include "io/channel.h"
+#include "io/channel-socket.h"
+#include "io/net-listener.h"
+#include "qapi/qapi-events-net.h"
+
+typedef struct NetStreamState {
+ NetClientState nc;
+ QIOChannel *listen_ioc;
+ QIONetListener *listener;
+ QIOChannel *ioc;
+ guint ioc_read_tag;
+ guint ioc_write_tag;
+ SocketReadState rs;
+ unsigned int send_index; /* number of bytes sent*/
+} NetStreamState;
+
+static void net_stream_listen(QIONetListener *listener,
+ QIOChannelSocket *cioc,
+ void *opaque);
+
+static gboolean net_stream_writable(QIOChannel *ioc,
+ GIOCondition condition,
+ gpointer data)
+{
+ NetStreamState *s = data;
+
+ s->ioc_write_tag = 0;
+
+ qemu_flush_queued_packets(&s->nc);
+
+ return G_SOURCE_REMOVE;
+}
+
+static ssize_t net_stream_receive(NetClientState *nc, const uint8_t *buf,
+ size_t size)
+{
+ NetStreamState *s = DO_UPCAST(NetStreamState, nc, nc);
+ uint32_t len = htonl(size);
+ struct iovec iov[] = {
+ {
+ .iov_base = &len,
+ .iov_len = sizeof(len),
+ }, {
+ .iov_base = (void *)buf,
+ .iov_len = size,
+ },
+ };
+ struct iovec local_iov[2];
+ unsigned int nlocal_iov;
+ size_t remaining;
+ ssize_t ret;
+
+ remaining = iov_size(iov, 2) - s->send_index;
+ nlocal_iov = iov_copy(local_iov, 2, iov, 2, s->send_index, remaining);
+ ret = qio_channel_writev(s->ioc, local_iov, nlocal_iov, NULL);
+ if (ret == QIO_CHANNEL_ERR_BLOCK) {
+ ret = 0; /* handled further down */
+ }
+ if (ret == -1) {
+ s->send_index = 0;
+ return -errno;
+ }
+ if (ret < (ssize_t)remaining) {
+ s->send_index += ret;
+ s->ioc_write_tag = qio_channel_add_watch(s->ioc, G_IO_OUT,
+ net_stream_writable, s, NULL);
+ return 0;
+ }
+ s->send_index = 0;
+ return size;
+}
+
+static gboolean net_stream_send(QIOChannel *ioc,
+ GIOCondition condition,
+ gpointer data);
+
+static void net_stream_send_completed(NetClientState *nc, ssize_t len)
+{
+ NetStreamState *s = DO_UPCAST(NetStreamState, nc, nc);
+
+ if (!s->ioc_read_tag) {
+ s->ioc_read_tag = qio_channel_add_watch(s->ioc, G_IO_IN,
+ net_stream_send, s, NULL);
+ }
+}
+
+static void net_stream_rs_finalize(SocketReadState *rs)
+{
+ NetStreamState *s = container_of(rs, NetStreamState, rs);
+
+ if (qemu_send_packet_async(&s->nc, rs->buf,
+ rs->packet_len,
+ net_stream_send_completed) == 0) {
+ if (s->ioc_read_tag) {
+ g_source_remove(s->ioc_read_tag);
+ s->ioc_read_tag = 0;
+ }
+ }
+}
+
+static gboolean net_stream_send(QIOChannel *ioc,
+ GIOCondition condition,
+ gpointer data)
+{
+ NetStreamState *s = data;
+ int size;
+ int ret;
+ char buf1[NET_BUFSIZE];
+ const char *buf;
+
+ size = qio_channel_read(s->ioc, buf1, sizeof(buf1), NULL);
+ if (size < 0) {
+ if (errno != EWOULDBLOCK) {
+ goto eoc;
+ }
+ } else if (size == 0) {
+ /* end of connection */
+ eoc:
+ s->ioc_read_tag = 0;
+ if (s->ioc_write_tag) {
+ g_source_remove(s->ioc_write_tag);
+ s->ioc_write_tag = 0;
+ }
+ if (s->listener) {
+ qio_net_listener_set_client_func(s->listener, net_stream_listen,
+ s, NULL);
+ }
+ object_unref(OBJECT(s->ioc));
+ s->ioc = NULL;
+
+ net_socket_rs_init(&s->rs, net_stream_rs_finalize, false);
+ s->nc.link_down = true;
+ qemu_set_info_str(&s->nc, "");
+
+ qapi_event_send_netdev_stream_disconnected(s->nc.name);
+
+ return G_SOURCE_REMOVE;
+ }
+ buf = buf1;
+
+ ret = net_fill_rstate(&s->rs, (const uint8_t *)buf, size);
+
+ if (ret == -1) {
+ goto eoc;
+ }
+
+ return G_SOURCE_CONTINUE;
+}
+
+static void net_stream_cleanup(NetClientState *nc)
+{
+ NetStreamState *s = DO_UPCAST(NetStreamState, nc, nc);
+ if (s->ioc) {
+ if (QIO_CHANNEL_SOCKET(s->ioc)->fd != -1) {
+ if (s->ioc_read_tag) {
+ g_source_remove(s->ioc_read_tag);
+ s->ioc_read_tag = 0;
+ }
+ if (s->ioc_write_tag) {
+ g_source_remove(s->ioc_write_tag);
+ s->ioc_write_tag = 0;
+ }
+ }
+ object_unref(OBJECT(s->ioc));
+ s->ioc = NULL;
+ }
+ if (s->listen_ioc) {
+ if (s->listener) {
+ qio_net_listener_disconnect(s->listener);
+ object_unref(OBJECT(s->listener));
+ s->listener = NULL;
+ }
+ object_unref(OBJECT(s->listen_ioc));
+ s->listen_ioc = NULL;
+ }
+}
+
+static NetClientInfo net_stream_info = {
+ .type = NET_CLIENT_DRIVER_STREAM,
+ .size = sizeof(NetStreamState),
+ .receive = net_stream_receive,
+ .cleanup = net_stream_cleanup,
+};
+
+static void net_stream_listen(QIONetListener *listener,
+ QIOChannelSocket *cioc,
+ void *opaque)
+{
+ NetStreamState *s = opaque;
+ SocketAddress *addr;
+ char *uri;
+
+ object_ref(OBJECT(cioc));
+
+ qio_net_listener_set_client_func(s->listener, NULL, s, NULL);
+
+ s->ioc = QIO_CHANNEL(cioc);
+ qio_channel_set_name(s->ioc, "stream-server");
+ s->nc.link_down = false;
+
+ s->ioc_read_tag = qio_channel_add_watch(s->ioc, G_IO_IN, net_stream_send,
+ s, NULL);
+
+ if (cioc->localAddr.ss_family == AF_UNIX) {
+ addr = qio_channel_socket_get_local_address(cioc, NULL);
+ } else {
+ addr = qio_channel_socket_get_remote_address(cioc, NULL);
+ }
+ g_assert(addr != NULL);
+ uri = socket_uri(addr);
+ qemu_set_info_str(&s->nc, uri);
+ g_free(uri);
+ qapi_event_send_netdev_stream_connected(s->nc.name, addr);
+ qapi_free_SocketAddress(addr);
+}
+
+static void net_stream_server_listening(QIOTask *task, gpointer opaque)
+{
+ NetStreamState *s = opaque;
+ QIOChannelSocket *listen_sioc = QIO_CHANNEL_SOCKET(s->listen_ioc);
+ SocketAddress *addr;
+ int ret;
+
+ if (listen_sioc->fd < 0) {
+ qemu_set_info_str(&s->nc, "connection error");
+ return;
+ }
+
+ addr = qio_channel_socket_get_local_address(listen_sioc, NULL);
+ g_assert(addr != NULL);
+ ret = qemu_socket_try_set_nonblock(listen_sioc->fd);
+ if (addr->type == SOCKET_ADDRESS_TYPE_FD && ret < 0) {
+ qemu_set_info_str(&s->nc, "can't use file descriptor %s (errno %d)",
+ addr->u.fd.str, -ret);
+ return;
+ }
+ g_assert(ret == 0);
+ qapi_free_SocketAddress(addr);
+
+ s->nc.link_down = true;
+ s->listener = qio_net_listener_new();
+
+ net_socket_rs_init(&s->rs, net_stream_rs_finalize, false);
+ qio_net_listener_set_client_func(s->listener, net_stream_listen, s, NULL);
+ qio_net_listener_add(s->listener, listen_sioc);
+}
+
+static int net_stream_server_init(NetClientState *peer,
+ const char *model,
+ const char *name,
+ SocketAddress *addr,
+ Error **errp)
+{
+ NetClientState *nc;
+ NetStreamState *s;
+ QIOChannelSocket *listen_sioc = qio_channel_socket_new();
+
+ nc = qemu_new_net_client(&net_stream_info, peer, model, name);
+ s = DO_UPCAST(NetStreamState, nc, nc);
+
+ s->listen_ioc = QIO_CHANNEL(listen_sioc);
+ qio_channel_socket_listen_async(listen_sioc, addr, 0,
+ net_stream_server_listening, s,
+ NULL, NULL);
+
+ return 0;
+}
+
+static void net_stream_client_connected(QIOTask *task, gpointer opaque)
+{
+ NetStreamState *s = opaque;
+ QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(s->ioc);
+ SocketAddress *addr;
+ gchar *uri;
+ int ret;
+
+ if (sioc->fd < 0) {
+ qemu_set_info_str(&s->nc, "connection error");
+ goto error;
+ }
+
+ addr = qio_channel_socket_get_remote_address(sioc, NULL);
+ g_assert(addr != NULL);
+ uri = socket_uri(addr);
+ qemu_set_info_str(&s->nc, uri);
+ g_free(uri);
+
+ ret = qemu_socket_try_set_nonblock(sioc->fd);
+ if (addr->type == SOCKET_ADDRESS_TYPE_FD && ret < 0) {
+ qemu_set_info_str(&s->nc, "can't use file descriptor %s (errno %d)",
+ addr->u.fd.str, -ret);
+ qapi_free_SocketAddress(addr);
+ goto error;
+ }
+ g_assert(ret == 0);
+
+ net_socket_rs_init(&s->rs, net_stream_rs_finalize, false);
+
+ /* Disable Nagle algorithm on TCP sockets to reduce latency */
+ qio_channel_set_delay(s->ioc, false);
+
+ s->ioc_read_tag = qio_channel_add_watch(s->ioc, G_IO_IN, net_stream_send,
+ s, NULL);
+ s->nc.link_down = false;
+ qapi_event_send_netdev_stream_connected(s->nc.name, addr);
+ qapi_free_SocketAddress(addr);
+
+ return;
+error:
+ object_unref(OBJECT(s->ioc));
+ s->ioc = NULL;
+}
+
+static int net_stream_client_init(NetClientState *peer,
+ const char *model,
+ const char *name,
+ SocketAddress *addr,
+ Error **errp)
+{
+ NetStreamState *s;
+ NetClientState *nc;
+ QIOChannelSocket *sioc = qio_channel_socket_new();
+
+ nc = qemu_new_net_client(&net_stream_info, peer, model, name);
+ s = DO_UPCAST(NetStreamState, nc, nc);
+
+ s->ioc = QIO_CHANNEL(sioc);
+ s->nc.link_down = true;
+
+ qio_channel_socket_connect_async(sioc, addr,
+ net_stream_client_connected, s,
+ NULL, NULL);
+
+ return 0;
+}
+
+int net_init_stream(const Netdev *netdev, const char *name,
+ NetClientState *peer, Error **errp)
+{
+ const NetdevStreamOptions *sock;
+
+ assert(netdev->type == NET_CLIENT_DRIVER_STREAM);
+ sock = &netdev->u.stream;
+
+ if (!sock->has_server || !sock->server) {
+ return net_stream_client_init(peer, "stream", name, sock->addr, errp);
+ }
+ return net_stream_server_init(peer, "stream", name, sock->addr, errp);
+}
diff --git a/net/tap-win32.c b/net/tap-win32.c
index 7466f22e77..a49c28ba5d 100644
--- a/net/tap-win32.c
+++ b/net/tap-win32.c
@@ -789,8 +789,7 @@ static int tap_win32_init(NetClientState *peer, const char *model,
s = DO_UPCAST(TAPState, nc, nc);
- snprintf(s->nc.info_str, sizeof(s->nc.info_str),
- "tap: ifname=%s", ifname);
+ qemu_set_info_str(&s->nc, "tap: ifname=%s", ifname);
s->handle = handle;
diff --git a/net/tap.c b/net/tap.c
index e203d07a12..1210a0436d 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -630,8 +630,7 @@ int net_init_bridge(const Netdev *netdev, const char *name,
}
s = net_tap_fd_init(peer, "bridge", name, fd, vnet_hdr);
- snprintf(s->nc.info_str, sizeof(s->nc.info_str), "helper=%s,br=%s", helper,
- br);
+ qemu_set_info_str(&s->nc, "helper=%s,br=%s", helper, br);
return 0;
}
@@ -690,14 +689,12 @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
}
if (tap->has_fd || tap->has_fds) {
- snprintf(s->nc.info_str, sizeof(s->nc.info_str), "fd=%d", fd);
+ qemu_set_info_str(&s->nc, "fd=%d", fd);
} else if (tap->has_helper) {
- snprintf(s->nc.info_str, sizeof(s->nc.info_str), "helper=%s",
- tap->helper);
+ qemu_set_info_str(&s->nc, "helper=%s", tap->helper);
} else {
- snprintf(s->nc.info_str, sizeof(s->nc.info_str),
- "ifname=%s,script=%s,downscript=%s", ifname, script,
- downscript);
+ qemu_set_info_str(&s->nc, "ifname=%s,script=%s,downscript=%s", ifname,
+ script, downscript);
if (strcmp(downscript, "no") != 0) {
snprintf(s->down_script, sizeof(s->down_script), "%s", downscript);
diff --git a/net/vde.c b/net/vde.c
index 1083916bcf..c0a08662cc 100644
--- a/net/vde.c
+++ b/net/vde.c
@@ -98,8 +98,7 @@ static int net_vde_init(NetClientState *peer, const char *model,
nc = qemu_new_net_client(&net_vde_info, peer, model, name);
- snprintf(nc->info_str, sizeof(nc->info_str), "sock=%s,fd=%d",
- sock, vde_datafd(vde));
+ qemu_set_info_str(nc, "sock=%s,fd=%d", sock, vde_datafd(vde));
s = DO_UPCAST(VDEState, nc, nc);
diff --git a/net/vhost-user.c b/net/vhost-user.c
index b1a0247b59..3a6b90da86 100644
--- a/net/vhost-user.c
+++ b/net/vhost-user.c
@@ -341,8 +341,7 @@ static int net_vhost_user_init(NetClientState *peer, const char *device,
user = g_new0(struct VhostUserState, 1);
for (i = 0; i < queues; i++) {
nc = qemu_new_net_client(&net_vhost_user_info, peer, device, name);
- snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user%d to %s",
- i, chr->label);
+ qemu_set_info_str(nc, "vhost-user%d to %s", i, chr->label);
nc->queue_index = i;
if (!nc0) {
nc0 = nc;
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 4bc3fd01a8..854ebd61ae 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -63,7 +63,6 @@ const int vdpa_feature_bits[] = {
VIRTIO_NET_F_CTRL_RX,
VIRTIO_NET_F_CTRL_RX_EXTRA,
VIRTIO_NET_F_CTRL_VLAN,
- VIRTIO_NET_F_GUEST_ANNOUNCE,
VIRTIO_NET_F_CTRL_MAC_ADDR,
VIRTIO_NET_F_RSS,
VIRTIO_NET_F_MQ,
@@ -463,48 +462,6 @@ static NetClientInfo net_vhost_vdpa_cvq_info = {
};
/**
- * Do not forward commands not supported by SVQ. Otherwise, the device could
- * accept it and qemu would not know how to update the device model.
- */
-static bool vhost_vdpa_net_cvq_validate_cmd(const void *out_buf, size_t len)
-{
- struct virtio_net_ctrl_hdr ctrl;
-
- if (unlikely(len < sizeof(ctrl))) {
- qemu_log_mask(LOG_GUEST_ERROR,
- "%s: invalid legnth of out buffer %zu\n", __func__, len);
- return false;
- }
-
- memcpy(&ctrl, out_buf, sizeof(ctrl));
- switch (ctrl.class) {
- case VIRTIO_NET_CTRL_MAC:
- switch (ctrl.cmd) {
- case VIRTIO_NET_CTRL_MAC_ADDR_SET:
- return true;
- default:
- qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid mac cmd %u\n",
- __func__, ctrl.cmd);
- };
- break;
- case VIRTIO_NET_CTRL_MQ:
- switch (ctrl.cmd) {
- case VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET:
- return true;
- default:
- qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid mq cmd %u\n",
- __func__, ctrl.cmd);
- };
- break;
- default:
- qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid control class %u\n",
- __func__, ctrl.class);
- };
-
- return false;
-}
-
-/**
* Validate and copy control virtqueue commands.
*
* Following QEMU guidelines, we offer a copy of the buffers to the device to
@@ -527,16 +484,10 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
.iov_len = sizeof(status),
};
ssize_t dev_written = -EINVAL;
- bool ok;
out.iov_len = iov_to_buf(elem->out_sg, elem->out_num, 0,
s->cvq_cmd_out_buffer,
vhost_vdpa_net_cvq_cmd_len());
- ok = vhost_vdpa_net_cvq_validate_cmd(s->cvq_cmd_out_buffer, out.iov_len);
- if (unlikely(!ok)) {
- goto out;
- }
-
dev_written = vhost_vdpa_net_cvq_add(s, out.iov_len, sizeof(status));
if (unlikely(dev_written < 0)) {
goto out;
@@ -593,7 +544,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
nc = qemu_new_net_control_client(&net_vhost_vdpa_cvq_info, peer,
device, name);
}
- snprintf(nc->info_str, sizeof(nc->info_str), TYPE_VHOST_VDPA);
+ qemu_set_info_str(nc, TYPE_VHOST_VDPA);
s = DO_UPCAST(VhostVDPAState, nc, nc);
s->vhost_vdpa.device_fd = vdpa_device_fd;
@@ -683,14 +634,29 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
assert(netdev->type == NET_CLIENT_DRIVER_VHOST_VDPA);
opts = &netdev->u.vhost_vdpa;
- if (!opts->vhostdev) {
- error_setg(errp, "vdpa character device not specified with vhostdev");
+ if (!opts->has_vhostdev && !opts->has_vhostfd) {
+ error_setg(errp,
+ "vhost-vdpa: neither vhostdev= nor vhostfd= was specified");
return -1;
}
- vdpa_device_fd = qemu_open(opts->vhostdev, O_RDWR, errp);
- if (vdpa_device_fd == -1) {
- return -errno;
+ if (opts->has_vhostdev && opts->has_vhostfd) {
+ error_setg(errp,
+ "vhost-vdpa: vhostdev= and vhostfd= are mutually exclusive");
+ return -1;
+ }
+
+ if (opts->has_vhostdev) {
+ vdpa_device_fd = qemu_open(opts->vhostdev, O_RDWR, errp);
+ if (vdpa_device_fd == -1) {
+ return -errno;
+ }
+ } else if (opts->has_vhostfd) {
+ vdpa_device_fd = monitor_fd_param(monitor_cur(), opts->vhostfd, errp);
+ if (vdpa_device_fd == -1) {
+ error_prepend(errp, "vhost-vdpa: unable to parse vhostfd: ");
+ return -1;
+ }
}
r = vhost_vdpa_get_features(vdpa_device_fd, &features, errp);