diff options
Diffstat (limited to 'net')
| -rw-r--r-- | net/can/can_core.c | 4 | ||||
| -rw-r--r-- | net/can/can_host.c | 4 | ||||
| -rw-r--r-- | net/can/can_socketcan.c | 2 | ||||
| -rw-r--r-- | net/checksum.c | 4 | ||||
| -rw-r--r-- | net/colo-compare.c | 11 | ||||
| -rw-r--r-- | net/dump.c | 7 | ||||
| -rw-r--r-- | net/filter-buffer.c | 2 | ||||
| -rw-r--r-- | net/filter-mirror.c | 4 | ||||
| -rw-r--r-- | net/filter-replay.c | 4 | ||||
| -rw-r--r-- | net/filter-rewriter.c | 2 | ||||
| -rw-r--r-- | net/filter.c | 4 | ||||
| -rw-r--r-- | net/hub.c | 27 | ||||
| -rw-r--r-- | net/meson.build | 2 | ||||
| -rw-r--r-- | net/net-hmp-cmds.c | 2 | ||||
| -rw-r--r-- | net/net.c | 65 | ||||
| -rw-r--r-- | net/queue.c | 11 | ||||
| -rw-r--r-- | net/slirp.c | 29 | ||||
| -rw-r--r-- | net/socket.c | 2 | ||||
| -rw-r--r-- | net/stream.c | 36 | ||||
| -rw-r--r-- | net/tap-linux.c | 17 | ||||
| -rw-r--r-- | net/tap-win32.c | 15 | ||||
| -rw-r--r-- | net/tap.c | 36 | ||||
| -rw-r--r-- | net/vhost-user.c | 3 | ||||
| -rw-r--r-- | net/vhost-vdpa.c | 71 | ||||
| -rw-r--r-- | net/vmnet-common.m | 27 |
25 files changed, 204 insertions, 187 deletions
diff --git a/net/can/can_core.c b/net/can/can_core.c index 0115d78..77fe2b8 100644 --- a/net/can/can_core.c +++ b/net/can/can_core.c @@ -149,7 +149,7 @@ static bool can_bus_can_be_deleted(UserCreatable *uc) } static void can_bus_class_init(ObjectClass *klass, - void *class_data G_GNUC_UNUSED) + const void *class_data G_GNUC_UNUSED) { UserCreatableClass *uc_klass = USER_CREATABLE_CLASS(klass); @@ -162,7 +162,7 @@ static const TypeInfo can_bus_info = { .instance_size = sizeof(CanBusState), .instance_init = can_bus_instance_init, .class_init = can_bus_class_init, - .interfaces = (InterfaceInfo[]) { + .interfaces = (const InterfaceInfo[]) { { TYPE_USER_CREATABLE }, { } } diff --git a/net/can/can_host.c b/net/can/can_host.c index b2fe553..3f9bb33 100644 --- a/net/can/can_host.c +++ b/net/can/can_host.c @@ -72,7 +72,7 @@ static void can_host_complete(UserCreatable *uc, Error **errp) } static void can_host_class_init(ObjectClass *klass, - void *class_data G_GNUC_UNUSED) + const void *class_data G_GNUC_UNUSED) { UserCreatableClass *uc_klass = USER_CREATABLE_CLASS(klass); @@ -92,7 +92,7 @@ static const TypeInfo can_host_info = { .class_size = sizeof(CanHostClass), .abstract = true, .class_init = can_host_class_init, - .interfaces = (InterfaceInfo[]) { + .interfaces = (const InterfaceInfo[]) { { TYPE_USER_CREATABLE }, { } } diff --git a/net/can/can_socketcan.c b/net/can/can_socketcan.c index c1a1ad0..8a57ae0 100644 --- a/net/can/can_socketcan.c +++ b/net/can/can_socketcan.c @@ -308,7 +308,7 @@ static void can_host_socketcan_instance_init(Object *obj) } static void can_host_socketcan_class_init(ObjectClass *klass, - void *class_data G_GNUC_UNUSED) + const void *class_data G_GNUC_UNUSED) { CanHostClass *chc = CAN_HOST_CLASS(klass); diff --git a/net/checksum.c b/net/checksum.c index 1a957e4..537457d 100644 --- a/net/checksum.c +++ b/net/checksum.c @@ -57,7 +57,7 @@ uint16_t net_checksum_tcpudp(uint16_t length, uint16_t proto, return net_checksum_finish(sum); } -void net_checksum_calculate(uint8_t *data, int length, int csum_flag) +void net_checksum_calculate(void *data, int length, int csum_flag) { int mac_hdr_len, ip_len; struct ip_header *ip; @@ -101,7 +101,7 @@ void net_checksum_calculate(uint8_t *data, int length, int csum_flag) return; } - ip = (struct ip_header *)(data + mac_hdr_len); + ip = (struct ip_header *)((uint8_t *)data + mac_hdr_len); if (IP_HEADER_VERSION(ip) != IP_HEADER_VERSION_4) { return; /* not IPv4 */ diff --git a/net/colo-compare.c b/net/colo-compare.c index c4ad0ab..0e1844e 100644 --- a/net/colo-compare.c +++ b/net/colo-compare.c @@ -25,7 +25,7 @@ #include "chardev/char-fe.h" #include "qemu/sockets.h" #include "colo.h" -#include "sysemu/iothread.h" +#include "system/iothread.h" #include "net/colo-compare.h" #include "migration/colo.h" #include "util.h" @@ -412,8 +412,7 @@ static void colo_compare_tcp(CompareState *s, Connection *conn) * can ensure that the packet's payload is acknowledged by * primary and secondary. */ - uint32_t min_ack = conn->pack - conn->sack > 0 ? - conn->sack : conn->pack; + uint32_t min_ack = MIN(conn->pack, conn->sack); pri: if (g_queue_is_empty(&conn->primary_list)) { @@ -1329,8 +1328,6 @@ static void colo_compare_complete(UserCreatable *uc, Error **errp) } QTAILQ_INSERT_TAIL(&net_compares, s, next); qemu_mutex_unlock(&colo_compare_mutex); - - return; } static void colo_flush_packets(void *opaque, void *user_data) @@ -1355,7 +1352,7 @@ static void colo_flush_packets(void *opaque, void *user_data) } } -static void colo_compare_class_init(ObjectClass *oc, void *data) +static void colo_compare_class_init(ObjectClass *oc, const void *data) { UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc); @@ -1479,7 +1476,7 @@ static const TypeInfo colo_compare_info = { .instance_finalize = colo_compare_finalize, .class_size = sizeof(CompareClass), .class_init = colo_compare_class_init, - .interfaces = (InterfaceInfo[]) { + .interfaces = (const InterfaceInfo[]) { { TYPE_USER_CREATABLE }, { } } @@ -32,7 +32,7 @@ #include "qapi/visitor.h" #include "net/filter.h" #include "qom/object.h" -#include "sysemu/rtc.h" +#include "system/rtc.h" typedef struct DumpState { int64_t start_ts; @@ -155,7 +155,8 @@ static ssize_t filter_dump_receive_iov(NetFilterState *nf, NetClientState *sndr, { NetFilterDumpState *nfds = FILTER_DUMP(nf); - dump_receive_iov(&nfds->ds, iov, iovcnt, qemu_get_vnet_hdr_len(nf->netdev)); + dump_receive_iov(&nfds->ds, iov, iovcnt, flags & QEMU_NET_PACKET_FLAG_RAW ? + 0 : qemu_get_vnet_hdr_len(nf->netdev)); return 0; } @@ -233,7 +234,7 @@ static void filter_dump_instance_finalize(Object *obj) g_free(nfds->filename); } -static void filter_dump_class_init(ObjectClass *oc, void *data) +static void filter_dump_class_init(ObjectClass *oc, const void *data) { NetFilterClass *nfc = NETFILTER_CLASS(oc); diff --git a/net/filter-buffer.c b/net/filter-buffer.c index 283dc9c..a36be31 100644 --- a/net/filter-buffer.c +++ b/net/filter-buffer.c @@ -172,7 +172,7 @@ static void filter_buffer_set_interval(Object *obj, Visitor *v, s->interval = value; } -static void filter_buffer_class_init(ObjectClass *oc, void *data) +static void filter_buffer_class_init(ObjectClass *oc, const void *data) { NetFilterClass *nfc = NETFILTER_CLASS(oc); diff --git a/net/filter-mirror.c b/net/filter-mirror.c index 34a63b5..27734c9 100644 --- a/net/filter-mirror.c +++ b/net/filter-mirror.c @@ -410,7 +410,7 @@ static void filter_redirector_set_vnet_hdr(Object *obj, s->vnet_hdr = value; } -static void filter_mirror_class_init(ObjectClass *oc, void *data) +static void filter_mirror_class_init(ObjectClass *oc, const void *data) { NetFilterClass *nfc = NETFILTER_CLASS(oc); @@ -425,7 +425,7 @@ static void filter_mirror_class_init(ObjectClass *oc, void *data) nfc->receive_iov = filter_mirror_receive_iov; } -static void filter_redirector_class_init(ObjectClass *oc, void *data) +static void filter_redirector_class_init(ObjectClass *oc, const void *data) { NetFilterClass *nfc = NETFILTER_CLASS(oc); diff --git a/net/filter-replay.c b/net/filter-replay.c index 5469067..451663c 100644 --- a/net/filter-replay.c +++ b/net/filter-replay.c @@ -17,7 +17,7 @@ #include "qemu/timer.h" #include "qapi/visitor.h" #include "net/filter.h" -#include "sysemu/replay.h" +#include "system/replay.h" #include "qom/object.h" #define TYPE_FILTER_REPLAY "filter-replay" @@ -65,7 +65,7 @@ static void filter_replay_instance_finalize(Object *obj) replay_unregister_net(nfrs->rns); } -static void filter_replay_class_init(ObjectClass *oc, void *data) +static void filter_replay_class_init(ObjectClass *oc, const void *data) { NetFilterClass *nfc = NETFILTER_CLASS(oc); diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c index c18c4c2..cdf85aa 100644 --- a/net/filter-rewriter.c +++ b/net/filter-rewriter.c @@ -411,7 +411,7 @@ static void filter_rewriter_init(Object *obj) s->failover_mode = FAILOVER_MODE_OFF; } -static void colo_rewriter_class_init(ObjectClass *oc, void *data) +static void colo_rewriter_class_init(ObjectClass *oc, const void *data) { NetFilterClass *nfc = NETFILTER_CLASS(oc); diff --git a/net/filter.c b/net/filter.c index 3335908..c7cc661 100644 --- a/net/filter.c +++ b/net/filter.c @@ -333,7 +333,7 @@ static void default_handle_event(NetFilterState *nf, int event, Error **errp) } } -static void netfilter_class_init(ObjectClass *oc, void *data) +static void netfilter_class_init(ObjectClass *oc, const void *data) { UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc); NetFilterClass *nfc = NETFILTER_CLASS(oc); @@ -363,7 +363,7 @@ static const TypeInfo netfilter_info = { .instance_size = sizeof(NetFilterState), .instance_init = netfilter_init, .instance_finalize = netfilter_finalize, - .interfaces = (InterfaceInfo[]) { + .interfaces = (const InterfaceInfo[]) { { TYPE_USER_CREATABLE }, { } } @@ -20,7 +20,7 @@ #include "hub.h" #include "qemu/iov.h" #include "qemu/error-report.h" -#include "sysemu/qtest.h" +#include "system/qtest.h" /* * A hub broadcasts incoming packets to all its ports except the source port. @@ -194,31 +194,6 @@ NetClientState *net_hub_add_port(int hub_id, const char *name, } /** - * Find a available port on a hub; otherwise create one new port - */ -NetClientState *net_hub_port_find(int hub_id) -{ - NetHub *hub; - NetHubPort *port; - NetClientState *nc; - - QLIST_FOREACH(hub, &hubs, next) { - if (hub->id == hub_id) { - QLIST_FOREACH(port, &hub->ports, next) { - nc = port->nc.peer; - if (!nc) { - return &(port->nc); - } - } - break; - } - } - - nc = net_hub_add_port(hub_id, NULL, NULL); - return nc; -} - -/** * Print hub configuration */ void net_hub_info(Monitor *mon) diff --git a/net/meson.build b/net/meson.build index e0cd714..bb97b4d 100644 --- a/net/meson.build +++ b/net/meson.build @@ -39,7 +39,7 @@ if have_netmap system_ss.add(files('netmap.c')) endif -system_ss.add(when: libxdp, if_true: files('af-xdp.c')) +system_ss.add(when: [libxdp, libbpf], if_true: files('af-xdp.c')) if have_vhost_net_user system_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('vhost-user.c'), if_false: files('vhost-user-stub.c')) diff --git a/net/net-hmp-cmds.c b/net/net-hmp-cmds.c index 41d326b..e7c55d2 100644 --- a/net/net-hmp-cmds.c +++ b/net/net-hmp-cmds.c @@ -22,7 +22,7 @@ #include "qapi/clone-visitor.h" #include "qapi/qapi-commands-net.h" #include "qapi/qapi-visit-net.h" -#include "qapi/qmp/qdict.h" +#include "qobject/qdict.h" #include "qemu/config-file.h" #include "qemu/help_option.h" #include "qemu/option.h" @@ -36,7 +36,7 @@ #include "qemu/help_option.h" #include "qapi/qapi-commands-net.h" #include "qapi/qapi-visit-net.h" -#include "qapi/qmp/qdict.h" +#include "qobject/qdict.h" #include "qapi/qmp/qerror.h" #include "qemu/error-report.h" #include "qemu/sockets.h" @@ -51,7 +51,7 @@ #include "qemu/keyval.h" #include "qapi/error.h" #include "qapi/opts-visitor.h" -#include "sysemu/runstate.h" +#include "system/runstate.h" #include "net/colo-compare.h" #include "net/filter.h" #include "qapi/string-output-visitor.h" @@ -381,9 +381,12 @@ NetClientState *qemu_get_peer(NetClientState *nc, int queue_index) return ncs->peer; } -static void qemu_cleanup_net_client(NetClientState *nc) +static void qemu_cleanup_net_client(NetClientState *nc, + bool remove_from_net_clients) { - QTAILQ_REMOVE(&net_clients, nc, next); + if (remove_from_net_clients) { + QTAILQ_REMOVE(&net_clients, nc, next); + } if (nc->info->cleanup) { nc->info->cleanup(nc); @@ -425,7 +428,13 @@ void qemu_del_net_client(NetClientState *nc) object_unparent(OBJECT(nf)); } - /* If there is a peer NIC, delete and cleanup client, but do not free. */ + /* + * If there is a peer NIC, transfer ownership to it. Delete the client + * from net_client list but do not cleanup nor free. This way NIC can + * still access to members of the backend. + * + * The cleanup and free will be done when the NIC is free. + */ if (nc->peer && nc->peer->info->type == NET_CLIENT_DRIVER_NIC) { NICState *nic = qemu_get_nic(nc->peer); if (nic->peer_deleted) { @@ -435,21 +444,18 @@ void qemu_del_net_client(NetClientState *nc) for (i = 0; i < queues; i++) { ncs[i]->peer->link_down = true; + QTAILQ_REMOVE(&net_clients, ncs[i], next); } if (nc->peer->info->link_status_changed) { nc->peer->info->link_status_changed(nc->peer); } - for (i = 0; i < queues; i++) { - qemu_cleanup_net_client(ncs[i]); - } - return; } for (i = 0; i < queues; i++) { - qemu_cleanup_net_client(ncs[i]); + qemu_cleanup_net_client(ncs[i], true); qemu_free_net_client(ncs[i]); } } @@ -462,8 +468,12 @@ void qemu_del_nic(NICState *nic) for (i = 0; i < queues; i++) { NetClientState *nc = qemu_get_subqueue(nic, i); - /* If this is a peer NIC and peer has already been deleted, free it now. */ + /* + * If this is a peer NIC and peer has already been deleted, clean it up + * and free it now. + */ if (nic->peer_deleted) { + qemu_cleanup_net_client(nc->peer, false); qemu_free_net_client(nc->peer); } else if (nc->peer) { /* if there are RX packets pending, complete them */ @@ -474,7 +484,7 @@ void qemu_del_nic(NICState *nic) for (i = queues - 1; i >= 0; i--) { NetClientState *nc = qemu_get_subqueue(nic, i); - qemu_cleanup_net_client(nc); + qemu_cleanup_net_client(nc, true); qemu_free_net_client(nc); } @@ -542,6 +552,10 @@ void qemu_set_offload(NetClientState *nc, int csum, int tso4, int tso6, int qemu_get_vnet_hdr_len(NetClientState *nc) { + if (!nc) { + return 0; + } + return nc->vnet_hdr_len; } @@ -750,16 +764,6 @@ ssize_t qemu_receive_packet(NetClientState *nc, const uint8_t *buf, int size) return qemu_net_queue_receive(nc->incoming_queue, buf, size); } -ssize_t qemu_receive_packet_iov(NetClientState *nc, const struct iovec *iov, - int iovcnt) -{ - if (!qemu_can_receive_packet(nc)) { - return 0; - } - - return qemu_net_queue_receive_iov(nc->incoming_queue, iov, iovcnt); -} - ssize_t qemu_send_packet_raw(NetClientState *nc, const uint8_t *buf, int size) { return qemu_send_packet_async_with_flags(nc, QEMU_NET_PACKET_FLAG_RAW, @@ -828,6 +832,7 @@ static ssize_t qemu_deliver_packet_iov(NetClientState *sender, iov_copy[0].iov_len = nc->vnet_hdr_len; memcpy(&iov_copy[1], iov, iovcnt * sizeof(*iov)); iov = iov_copy; + iovcnt++; } if (nc->info->receive_iov) { @@ -1683,6 +1688,9 @@ void net_cleanup(void) * of the latest NET_CLIENT_DRIVER_NIC, and operate on *p as we walk * the list. * + * However, the NIC may have peers that trust to be clean beyond this + * point. For example, if they have been removed with device_del. + * * The 'nc' variable isn't part of the list traversal; it's purely * for convenience as too much '(*p)->' has a tendency to make the * readers' eyes bleed. @@ -1690,6 +1698,17 @@ void net_cleanup(void) while (*p) { nc = *p; if (nc->info->type == NET_CLIENT_DRIVER_NIC) { + NICState *nic = qemu_get_nic(nc); + + if (nic->peer_deleted) { + int queues = MAX(nic->conf->peers.queues, 1); + + for (int i = 0; i < queues; i++) { + nc = qemu_get_subqueue(nic, i); + qemu_cleanup_net_client(nc->peer, false); + } + } + /* Skip NET_CLIENT_DRIVER_NIC entries */ p = &QTAILQ_NEXT(nc, next); } else { @@ -1737,7 +1756,7 @@ void net_check_clients(void) static int net_init_client(void *dummy, QemuOpts *opts, Error **errp) { - const char *model = qemu_opt_get_del(opts, "model"); + const char *model = qemu_opt_get(opts, "model"); if (is_nic_model_help_option(model)) { return 0; diff --git a/net/queue.c b/net/queue.c index c872d51..fb33856 100644 --- a/net/queue.c +++ b/net/queue.c @@ -193,17 +193,6 @@ ssize_t qemu_net_queue_receive(NetQueue *queue, return qemu_net_queue_deliver(queue, NULL, 0, data, size); } -ssize_t qemu_net_queue_receive_iov(NetQueue *queue, - const struct iovec *iov, - int iovcnt) -{ - if (queue->delivering) { - return 0; - } - - return qemu_net_queue_deliver_iov(queue, NULL, 0, iov, iovcnt); -} - ssize_t qemu_net_queue_send(NetQueue *queue, NetClientState *sender, unsigned flags, diff --git a/net/slirp.c b/net/slirp.c index eb9a456..9657e86 100644 --- a/net/slirp.c +++ b/net/slirp.c @@ -40,10 +40,10 @@ #include "qemu/sockets.h" #include <libslirp.h> #include "chardev/char-fe.h" -#include "sysemu/sysemu.h" +#include "system/system.h" #include "qemu/cutils.h" #include "qapi/error.h" -#include "qapi/qmp/qdict.h" +#include "qobject/qdict.h" #include "util.h" #include "migration/register.h" #include "migration/vmstate.h" @@ -247,7 +247,14 @@ static void net_slirp_timer_mod(void *timer, int64_t expire_timer, timer_mod(&t->timer, expire_timer); } -static void net_slirp_register_poll_fd(int fd, void *opaque) +#if !SLIRP_CHECK_VERSION(4, 9, 0) +# define slirp_os_socket int +# define slirp_pollfds_fill_socket slirp_pollfds_fill +# define register_poll_socket register_poll_fd +# define unregister_poll_socket unregister_poll_fd +#endif + +static void net_slirp_register_poll_sock(slirp_os_socket fd, void *opaque) { #ifdef WIN32 AioContext *ctxt = qemu_get_aio_context(); @@ -260,7 +267,7 @@ static void net_slirp_register_poll_fd(int fd, void *opaque) #endif } -static void net_slirp_unregister_poll_fd(int fd, void *opaque) +static void net_slirp_unregister_poll_sock(slirp_os_socket fd, void *opaque) { #ifdef WIN32 if (WSAEventSelect(fd, NULL, 0) != 0) { @@ -286,8 +293,8 @@ static const SlirpCb slirp_cb = { #endif .timer_free = net_slirp_timer_free, .timer_mod = net_slirp_timer_mod, - .register_poll_fd = net_slirp_register_poll_fd, - .unregister_poll_fd = net_slirp_unregister_poll_fd, + .register_poll_socket = net_slirp_register_poll_sock, + .unregister_poll_socket = net_slirp_unregister_poll_sock, .notify = net_slirp_notify, }; @@ -314,7 +321,7 @@ static int slirp_poll_to_gio(int events) return ret; } -static int net_slirp_add_poll(int fd, int events, void *opaque) +static int net_slirp_add_poll(slirp_os_socket fd, int events, void *opaque) { GArray *pollfds = opaque; GPollFD pfd = { @@ -363,8 +370,8 @@ static void net_slirp_poll_notify(Notifier *notifier, void *data) switch (poll->state) { case MAIN_LOOP_POLL_FILL: - slirp_pollfds_fill(s->slirp, &poll->timeout, - net_slirp_add_poll, poll->pollfds); + slirp_pollfds_fill_socket(s->slirp, &poll->timeout, + net_slirp_add_poll, poll->pollfds); break; case MAIN_LOOP_POLL_OK: case MAIN_LOOP_POLL_ERR: @@ -629,7 +636,9 @@ static int net_slirp_init(NetClientState *peer, const char *model, s = DO_UPCAST(SlirpState, nc, nc); - cfg.version = SLIRP_CHECK_VERSION(4,7,0) ? 4 : 1; + cfg.version = + SLIRP_CHECK_VERSION(4, 9, 0) ? 6 : + SLIRP_CHECK_VERSION(4, 7, 0) ? 4 : 1; cfg.restricted = restricted; cfg.in_enabled = ipv4; cfg.vnetwork = net; diff --git a/net/socket.c b/net/socket.c index 8e3702e..784dda6 100644 --- a/net/socket.c +++ b/net/socket.c @@ -157,7 +157,7 @@ static void net_socket_send(void *opaque) NetSocketState *s = opaque; int size; int ret; - uint8_t buf1[NET_BUFSIZE]; + QEMU_UNINITIALIZED uint8_t buf1[NET_BUFSIZE]; const uint8_t *buf; size = recv(s->fd, buf1, sizeof(buf1), 0); diff --git a/net/stream.c b/net/stream.c index 97e6ec6..6152d2a 100644 --- a/net/stream.c +++ b/net/stream.c @@ -51,7 +51,7 @@ typedef struct NetStreamState { guint ioc_write_tag; SocketReadState rs; unsigned int send_index; /* number of bytes sent*/ - uint32_t reconnect; + uint32_t reconnect_ms; guint timer_tag; SocketAddress *addr; } NetStreamState; @@ -148,7 +148,7 @@ static gboolean net_stream_send(QIOChannel *ioc, NetStreamState *s = data; int size; int ret; - char buf1[NET_BUFSIZE]; + QEMU_UNINITIALIZED char buf1[NET_BUFSIZE]; const char *buf; size = qio_channel_read(s->ioc, buf1, sizeof(buf1), NULL); @@ -387,10 +387,9 @@ static gboolean net_stream_reconnect(gpointer data) static void net_stream_arm_reconnect(NetStreamState *s) { - if (s->reconnect && s->timer_tag == 0) { + if (s->reconnect_ms && s->timer_tag == 0) { qemu_set_info_str(&s->nc, "connecting"); - s->timer_tag = g_timeout_add_seconds(s->reconnect, - net_stream_reconnect, s); + s->timer_tag = g_timeout_add(s->reconnect_ms, net_stream_reconnect, s); } } @@ -398,7 +397,7 @@ static int net_stream_client_init(NetClientState *peer, const char *model, const char *name, SocketAddress *addr, - uint32_t reconnect, + uint32_t reconnect_ms, Error **errp) { NetStreamState *s; @@ -412,8 +411,8 @@ static int net_stream_client_init(NetClientState *peer, s->ioc = QIO_CHANNEL(sioc); s->nc.link_down = true; - s->reconnect = reconnect; - if (reconnect) { + s->reconnect_ms = reconnect_ms; + if (reconnect_ms) { s->addr = QAPI_CLONE(SocketAddress, addr); } qio_channel_socket_connect_async(sioc, addr, @@ -432,13 +431,24 @@ int net_init_stream(const Netdev *netdev, const char *name, sock = &netdev->u.stream; if (!sock->has_server || !sock->server) { + uint32_t reconnect_ms = 0; + + if (sock->has_reconnect && sock->has_reconnect_ms) { + error_setg(errp, "'reconnect' and 'reconnect-ms' are mutually " + "exclusive"); + return -1; + } else if (sock->has_reconnect_ms) { + reconnect_ms = sock->reconnect_ms; + } else if (sock->has_reconnect) { + reconnect_ms = sock->reconnect * 1000u; + } + return net_stream_client_init(peer, "stream", name, sock->addr, - sock->has_reconnect ? sock->reconnect : 0, - errp); + reconnect_ms, errp); } - if (sock->has_reconnect) { - error_setg(errp, "'reconnect' option is incompatible with " - "socket in server mode"); + if (sock->has_reconnect || sock->has_reconnect_ms) { + error_setg(errp, "'reconnect' and 'reconnect-ms' options are " + "incompatible with socket in server mode"); return -1; } return net_stream_server_init(peer, "stream", name, sock->addr, errp); diff --git a/net/tap-linux.c b/net/tap-linux.c index 1226d5f..22ec2f4 100644 --- a/net/tap-linux.c +++ b/net/tap-linux.c @@ -45,10 +45,21 @@ int tap_open(char *ifname, int ifname_size, int *vnet_hdr, int len = sizeof(struct virtio_net_hdr); unsigned int features; - fd = RETRY_ON_EINTR(open(PATH_NET_TUN, O_RDWR)); + + ret = if_nametoindex(ifname); + if (ret) { + g_autofree char *file = g_strdup_printf("/dev/tap%d", ret); + fd = open(file, O_RDWR); + } else { + fd = -1; + } + if (fd < 0) { - error_setg_errno(errp, errno, "could not open %s", PATH_NET_TUN); - return -1; + fd = RETRY_ON_EINTR(open(PATH_NET_TUN, O_RDWR)); + if (fd < 0) { + error_setg_errno(errp, errno, "could not open %s", PATH_NET_TUN); + return -1; + } } memset(&ifr, 0, sizeof(ifr)); ifr.ifr_flags = IFF_TAP | IFF_NO_PI; diff --git a/net/tap-win32.c b/net/tap-win32.c index 7edbd71..671dee9 100644 --- a/net/tap-win32.c +++ b/net/tap-win32.c @@ -214,7 +214,7 @@ static int is_tap_win32_dev(const char *guid) for (;;) { char enum_name[256]; - char unit_string[256]; + g_autofree char *unit_string = NULL; HKEY unit_key; char component_id_string[] = "ComponentId"; char component_id[256]; @@ -239,8 +239,7 @@ static int is_tap_win32_dev(const char *guid) return FALSE; } - snprintf (unit_string, sizeof(unit_string), "%s\\%s", - ADAPTER_KEY, enum_name); + unit_string = g_strdup_printf("%s\\%s", ADAPTER_KEY, enum_name); status = RegOpenKeyEx( HKEY_LOCAL_MACHINE, @@ -315,7 +314,7 @@ static int get_device_guid( while (!stop) { char enum_name[256]; - char connection_string[256]; + g_autofree char *connection_string = NULL; HKEY connection_key; char name_data[256]; DWORD name_type; @@ -338,9 +337,7 @@ static int get_device_guid( return -1; } - snprintf(connection_string, - sizeof(connection_string), - "%s\\%s\\Connection", + connection_string = g_strdup_printf("%s\\%s\\Connection", NETWORK_CONNECTIONS_KEY, enum_name); status = RegOpenKeyEx( @@ -595,7 +592,7 @@ static void tap_win32_free_buffer(tap_win32_overlapped_t *overlapped, static int tap_win32_open(tap_win32_overlapped_t **phandle, const char *preferred_name) { - char device_path[256]; + g_autofree char *device_path = NULL; char device_guid[0x100]; int rc; HANDLE handle; @@ -617,7 +614,7 @@ static int tap_win32_open(tap_win32_overlapped_t **phandle, if (rc) return -1; - snprintf (device_path, sizeof(device_path), "%s%s%s", + device_path = g_strdup_printf("%s%s%s", USERMODEDEVICEDIR, device_guid, TAPSUFFIX); @@ -36,7 +36,7 @@ #include "net/net.h" #include "clients.h" #include "monitor/monitor.h" -#include "sysemu/sysemu.h" +#include "system/system.h" #include "qapi/error.h" #include "qemu/cutils.h" #include "qemu/error-report.h" @@ -385,6 +385,24 @@ static TAPState *net_tap_fd_init(NetClientState *peer, return s; } +static void close_all_fds_after_fork(int excluded_fd) +{ + const int skip_fd[] = {STDIN_FILENO, STDOUT_FILENO, STDERR_FILENO, + excluded_fd}; + unsigned int nskip = ARRAY_SIZE(skip_fd); + + /* + * skip_fd must be an ordered array of distinct fds, exclude + * excluded_fd if already included in the [STDIN_FILENO - STDERR_FILENO] + * range + */ + if (excluded_fd <= STDERR_FILENO) { + nskip--; + } + + qemu_close_all_open_fd(skip_fd, nskip); +} + static void launch_script(const char *setup_script, const char *ifname, int fd, Error **errp) { @@ -400,13 +418,7 @@ static void launch_script(const char *setup_script, const char *ifname, return; } if (pid == 0) { - int open_max = sysconf(_SC_OPEN_MAX), i; - - for (i = 3; i < open_max; i++) { - if (i != fd) { - close(i); - } - } + close_all_fds_after_fork(fd); parg = args; *parg++ = (char *)setup_script; *parg++ = (char *)ifname; @@ -490,17 +502,11 @@ static int net_bridge_run_helper(const char *helper, const char *bridge, return -1; } if (pid == 0) { - int open_max = sysconf(_SC_OPEN_MAX), i; char *fd_buf = NULL; char *br_buf = NULL; char *helper_cmd = NULL; - for (i = 3; i < open_max; i++) { - if (i != sv[1]) { - close(i); - } - } - + close_all_fds_after_fork(sv[1]); fd_buf = g_strdup_printf("%s%d", "--fd=", sv[1]); if (strrchr(helper, ' ') || strrchr(helper, '\t')) { diff --git a/net/vhost-user.c b/net/vhost-user.c index 1255551..0b235e5 100644 --- a/net/vhost-user.c +++ b/net/vhost-user.c @@ -16,6 +16,7 @@ #include "chardev/char-fe.h" #include "qapi/error.h" #include "qapi/qapi-commands-net.h" +#include "qapi/qapi-events-net.h" #include "qemu/config-file.h" #include "qemu/error-report.h" #include "qemu/option.h" @@ -271,6 +272,7 @@ static void chr_closed_bh(void *opaque) if (err) { error_report_err(err); } + qapi_event_send_netdev_vhost_user_disconnected(name); } static void net_vhost_user_event(void *opaque, QEMUChrEvent event) @@ -300,6 +302,7 @@ static void net_vhost_user_event(void *opaque, QEMUChrEvent event) net_vhost_user_watch, s); qmp_set_link(name, true, &err); s->started = true; + qapi_event_send_netdev_vhost_user_connected(name, chr->label); break; case CHR_EVENT_CLOSED: /* a close event may happen during a read/write, but vhost diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c index 03457ea..58d7389 100644 --- a/net/vhost-vdpa.c +++ b/net/vhost-vdpa.c @@ -88,6 +88,7 @@ const int vdpa_feature_bits[] = { VIRTIO_NET_F_MQ, VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_MTU, + VIRTIO_NET_F_RSC_EXT, VIRTIO_NET_F_RSS, VIRTIO_NET_F_STATUS, VIRTIO_RING_F_EVENT_IDX, @@ -223,14 +224,6 @@ static void vhost_vdpa_cleanup(NetClientState *nc) { VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc); - /* - * If a peer NIC is attached, do not cleanup anything. - * Cleanup will happen as a part of qemu_cleanup() -> net_cleanup() - * when the guest is shutting down. - */ - if (nc->peer && nc->peer->info->type == NET_CLIENT_DRIVER_NIC) { - return; - } munmap(s->cvq_cmd_out_buffer, vhost_vdpa_net_cvq_cmd_page_len()); munmap(s->status, vhost_vdpa_net_cvq_cmd_page_len()); if (s->vhost_net) { @@ -242,6 +235,7 @@ static void vhost_vdpa_cleanup(NetClientState *nc) return; } qemu_close(s->vhost_vdpa.shared->device_fd); + g_clear_pointer(&s->vhost_vdpa.shared->iova_tree, vhost_iova_tree_delete); g_free(s->vhost_vdpa.shared); } @@ -269,6 +263,18 @@ static bool vhost_vdpa_has_ufo(NetClientState *nc) } +/* + * FIXME: vhost_vdpa doesn't have an API to "set h/w endianness". But it's + * reasonable to assume that h/w is LE by default, because LE is what + * virtio 1.0 and later ask for. So, this function just says "yes, the h/w is + * LE". Otherwise, on a BE machine, higher-level code would mistakely think + * the h/w is BE and can't support VDPA for a virtio 1.0 client. + */ +static int vhost_vdpa_set_vnet_le(NetClientState *nc, bool enable) +{ + return 0; +} + static bool vhost_vdpa_check_peer_type(NetClientState *nc, ObjectClass *oc, Error **errp) { @@ -357,14 +363,8 @@ static int vdpa_net_migration_state_notifier(NotifierWithReturn *notifier, static void vhost_vdpa_net_data_start_first(VhostVDPAState *s) { - struct vhost_vdpa *v = &s->vhost_vdpa; - migration_add_notifier(&s->migration_state, vdpa_net_migration_state_notifier); - if (v->shadow_vqs_enabled) { - v->shared->iova_tree = vhost_iova_tree_new(v->shared->iova_range.first, - v->shared->iova_range.last); - } } static int vhost_vdpa_net_data_start(NetClientState *nc) @@ -374,8 +374,7 @@ static int vhost_vdpa_net_data_start(NetClientState *nc) assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA); - if (s->always_svq || - migration_is_setup_or_active()) { + if (s->always_svq || migration_is_running()) { v->shadow_vqs_enabled = true; } else { v->shadow_vqs_enabled = false; @@ -412,19 +411,12 @@ static int vhost_vdpa_net_data_load(NetClientState *nc) static void vhost_vdpa_net_client_stop(NetClientState *nc) { VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc); - struct vhost_dev *dev; assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA); if (s->vhost_vdpa.index == 0) { migration_remove_notifier(&s->migration_state); } - - dev = s->vhost_vdpa.dev; - if (dev->vq_index + dev->nvqs == dev->vq_index_end) { - g_clear_pointer(&s->vhost_vdpa.shared->iova_tree, - vhost_iova_tree_delete); - } } static NetClientInfo net_vhost_vdpa_info = { @@ -437,6 +429,7 @@ static NetClientInfo net_vhost_vdpa_info = { .cleanup = vhost_vdpa_cleanup, .has_vnet_hdr = vhost_vdpa_has_vnet_hdr, .has_ufo = vhost_vdpa_has_ufo, + .set_vnet_le = vhost_vdpa_set_vnet_le, .check_peer_type = vhost_vdpa_check_peer_type, .set_steering_ebpf = vhost_vdpa_set_steering_ebpf, }; @@ -510,14 +503,20 @@ static int vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, void *buf, size_t size, bool write) { DMAMap map = {}; + hwaddr taddr = (hwaddr)(uintptr_t)buf; int r; - map.translated_addr = (hwaddr)(uintptr_t)buf; map.size = size - 1; map.perm = write ? IOMMU_RW : IOMMU_RO, - r = vhost_iova_tree_map_alloc(v->shared->iova_tree, &map); + r = vhost_iova_tree_map_alloc(v->shared->iova_tree, &map, taddr); if (unlikely(r != IOVA_OK)) { error_report("Cannot map injected element"); + + if (map.translated_addr == taddr) { + error_report("Insertion to IOVA->HVA tree failed"); + /* Remove the mapping from the IOVA-only tree */ + goto dma_map_err; + } return r; } @@ -589,24 +588,6 @@ out: return 0; } - /* - * If other vhost_vdpa already have an iova_tree, reuse it for simplicity, - * whether CVQ shares ASID with guest or not, because: - * - Memory listener need access to guest's memory addresses allocated in - * the IOVA tree. - * - There should be plenty of IOVA address space for both ASID not to - * worry about collisions between them. Guest's translations are still - * validated with virtio virtqueue_pop so there is no risk for the guest - * to access memory that it shouldn't. - * - * To allocate a iova tree per ASID is doable but it complicates the code - * and it is not worth it for the moment. - */ - if (!v->shared->iova_tree) { - v->shared->iova_tree = vhost_iova_tree_new(v->shared->iova_range.first, - v->shared->iova_range.last); - } - r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer, vhost_vdpa_net_cvq_cmd_page_len(), false); if (unlikely(r < 0)) { @@ -643,7 +624,7 @@ static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, VhostShadowVirtqueue *svq = g_ptr_array_index(s->vhost_vdpa.shadow_vqs, 0); int r; - r = vhost_svq_add(svq, out_sg, out_num, in_sg, in_num, NULL); + r = vhost_svq_add(svq, out_sg, out_num, NULL, in_sg, in_num, NULL, NULL); if (unlikely(r != 0)) { if (unlikely(r == -ENOSPC)) { qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n", @@ -1715,6 +1696,8 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, s->vhost_vdpa.shared->device_fd = vdpa_device_fd; s->vhost_vdpa.shared->iova_range = iova_range; s->vhost_vdpa.shared->shadow_data = svq; + s->vhost_vdpa.shared->iova_tree = vhost_iova_tree_new(iova_range.first, + iova_range.last); } else if (!is_datapath) { s->cvq_cmd_out_buffer = mmap(NULL, vhost_vdpa_net_cvq_cmd_page_len(), PROT_READ | PROT_WRITE, diff --git a/net/vmnet-common.m b/net/vmnet-common.m index 30c4e53..ab33ce2 100644 --- a/net/vmnet-common.m +++ b/net/vmnet-common.m @@ -17,7 +17,8 @@ #include "clients.h" #include "qemu/error-report.h" #include "qapi/error.h" -#include "sysemu/runstate.h" +#include "system/runstate.h" +#include "net/eth.h" #include <vmnet/vmnet.h> #include <dispatch/dispatch.h> @@ -93,7 +94,7 @@ ssize_t vmnet_receive_common(NetClientState *nc, if_status = vmnet_write(s->vmnet_if, &packet, &pkt_cnt); if (if_status != VMNET_SUCCESS) { - error_report("vmnet: write error: %s\n", + error_report("vmnet: write error: %s", vmnet_status_map_str(if_status)); return -1; } @@ -147,10 +148,26 @@ static int vmnet_read_packets(VmnetState *s) */ static void vmnet_write_packets_to_qemu(VmnetState *s) { + uint8_t *pkt; + size_t pktsz; + uint8_t min_pkt[ETH_ZLEN]; + size_t min_pktsz; + ssize_t size; + while (s->packets_send_current_pos < s->packets_send_end_pos) { - ssize_t size = qemu_send_packet_async(&s->nc, - s->iov_buf[s->packets_send_current_pos].iov_base, - s->packets_buf[s->packets_send_current_pos].vm_pkt_size, + pkt = s->iov_buf[s->packets_send_current_pos].iov_base; + pktsz = s->packets_buf[s->packets_send_current_pos].vm_pkt_size; + + if (net_peer_needs_padding(&s->nc)) { + min_pktsz = sizeof(min_pkt); + + if (eth_pad_short_frame(min_pkt, &min_pktsz, pkt, pktsz)) { + pkt = min_pkt; + pktsz = min_pktsz; + } + } + + size = qemu_send_packet_async(&s->nc, pkt, pktsz, vmnet_send_completed); if (size == 0) { |