diff options
author | Greg Kurz <groug@kaod.org> | 2021-03-12 10:22:09 +0100 |
---|---|---|
committer | Michael S. Tsirkin <mst@redhat.com> | 2021-03-22 10:17:53 -0400 |
commit | 57dc02173cb089c11d3c84a0570cb60fe7d7f0d5 (patch) | |
tree | 840618c1ec3563ea7e2a00bd9f879f3c68115a5c /hw | |
parent | de62e4946052076186428900a85d6547627e84c6 (diff) |
vhost-user: Convert slave channel to QIOChannelSocket
The slave channel is implemented with socketpair() : QEMU creates
the pair, passes one of the socket to virtiofsd and monitors the
other one with the main event loop using qemu_set_fd_handler().
In order to fix a potential deadlock between QEMU and a vhost-user
external process (e.g. virtiofsd with DAX), we want to be able to
monitor and service the slave channel while handling vhost-user
requests.
Prepare ground for this by converting the slave channel to be a
QIOChannelSocket. This will make monitoring of the slave channel
as simple as calling qio_channel_add_watch_source(). Since the
connection is already established between the two sockets, only
incoming I/O (G_IO_IN) and disconnect (G_IO_HUP) need to be
serviced.
This also allows to get rid of the ancillary data parsing since
QIOChannelSocket can do this for us. Note that the MSG_CTRUNC
check is dropped on the way because QIOChannelSocket ignores this
case. This isn't a problem since slave_read() provisions space for
8 file descriptors, but affected vhost-user slave protocol messages
generally only convey one. If for some reason a buggy implementation
passes more file descriptors, no need to break the connection, just
like we don't break it if some other type of ancillary data is
received : this isn't explicitely violating the protocol per-se so
it seems better to ignore it.
The current code errors out on short reads and writes. Use the
qio_channel_*_all() variants to address this on the way.
Signed-off-by: Greg Kurz <groug@kaod.org>
Message-Id: <20210312092212.782255-5-groug@kaod.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Diffstat (limited to 'hw')
-rw-r--r-- | hw/virtio/vhost-user.c | 99 |
1 files changed, 39 insertions, 60 deletions
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index cb0c98f30a..3c1e1611b0 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -16,6 +16,7 @@ #include "hw/virtio/virtio.h" #include "hw/virtio/virtio-net.h" #include "chardev/char-fe.h" +#include "io/channel-socket.h" #include "sysemu/kvm.h" #include "qemu/error-report.h" #include "qemu/main-loop.h" @@ -237,7 +238,8 @@ struct vhost_user { struct vhost_dev *dev; /* Shared between vhost devs of the same virtio device */ VhostUserState *user; - int slave_fd; + QIOChannel *slave_ioc; + GSource *slave_src; NotifierWithReturn postcopy_notifier; struct PostCopyFD postcopy_fd; uint64_t postcopy_client_bases[VHOST_USER_MAX_RAM_SLOTS]; @@ -1394,61 +1396,37 @@ static int vhost_user_slave_handle_vring_host_notifier(struct vhost_dev *dev, static void close_slave_channel(struct vhost_user *u) { - qemu_set_fd_handler(u->slave_fd, NULL, NULL, NULL); - close(u->slave_fd); - u->slave_fd = -1; + g_source_destroy(u->slave_src); + g_source_unref(u->slave_src); + u->slave_src = NULL; + object_unref(OBJECT(u->slave_ioc)); + u->slave_ioc = NULL; } -static void slave_read(void *opaque) +static gboolean slave_read(QIOChannel *ioc, GIOCondition condition, + gpointer opaque) { struct vhost_dev *dev = opaque; struct vhost_user *u = dev->opaque; VhostUserHeader hdr = { 0, }; VhostUserPayload payload = { 0, }; - int size, ret = 0; + Error *local_err = NULL; + gboolean rc = G_SOURCE_CONTINUE; + int ret = 0; struct iovec iov; - struct msghdr msgh; - int fd[VHOST_USER_SLAVE_MAX_FDS]; - char control[CMSG_SPACE(sizeof(fd))]; - struct cmsghdr *cmsg; - int i, fdsize = 0; - - memset(&msgh, 0, sizeof(msgh)); - msgh.msg_iov = &iov; - msgh.msg_iovlen = 1; - msgh.msg_control = control; - msgh.msg_controllen = sizeof(control); - - memset(fd, -1, sizeof(fd)); + g_autofree int *fd = NULL; + size_t fdsize = 0; + int i; /* Read header */ iov.iov_base = &hdr; iov.iov_len = VHOST_USER_HDR_SIZE; - do { - size = recvmsg(u->slave_fd, &msgh, 0); - } while (size < 0 && errno == EINTR); - - if (size != VHOST_USER_HDR_SIZE) { - error_report("Failed to read from slave."); + if (qio_channel_readv_full_all(ioc, &iov, 1, &fd, &fdsize, &local_err)) { + error_report_err(local_err); goto err; } - if (msgh.msg_flags & MSG_CTRUNC) { - error_report("Truncated message."); - goto err; - } - - for (cmsg = CMSG_FIRSTHDR(&msgh); cmsg != NULL; - cmsg = CMSG_NXTHDR(&msgh, cmsg)) { - if (cmsg->cmsg_level == SOL_SOCKET && - cmsg->cmsg_type == SCM_RIGHTS) { - fdsize = cmsg->cmsg_len - CMSG_LEN(0); - memcpy(fd, CMSG_DATA(cmsg), fdsize); - break; - } - } - if (hdr.size > VHOST_USER_PAYLOAD_SIZE) { error_report("Failed to read msg header." " Size %d exceeds the maximum %zu.", hdr.size, @@ -1457,12 +1435,8 @@ static void slave_read(void *opaque) } /* Read payload */ - do { - size = read(u->slave_fd, &payload, hdr.size); - } while (size < 0 && errno == EINTR); - - if (size != hdr.size) { - error_report("Failed to read payload from slave."); + if (qio_channel_read_all(ioc, (char *) &payload, hdr.size, &local_err)) { + error_report_err(local_err); goto err; } @@ -1475,7 +1449,7 @@ static void slave_read(void *opaque) break; case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG: ret = vhost_user_slave_handle_vring_host_notifier(dev, &payload.area, - fd[0]); + fd ? fd[0] : -1); break; default: error_report("Received unexpected msg type: %d.", hdr.request); @@ -1501,12 +1475,8 @@ static void slave_read(void *opaque) iovec[1].iov_base = &payload; iovec[1].iov_len = hdr.size; - do { - size = writev(u->slave_fd, iovec, ARRAY_SIZE(iovec)); - } while (size < 0 && errno == EINTR); - - if (size != VHOST_USER_HDR_SIZE + hdr.size) { - error_report("Failed to send msg reply to slave."); + if (qio_channel_writev_all(ioc, iovec, ARRAY_SIZE(iovec), &local_err)) { + error_report_err(local_err); goto err; } } @@ -1515,14 +1485,15 @@ static void slave_read(void *opaque) err: close_slave_channel(u); + rc = G_SOURCE_REMOVE; fdcleanup: - for (i = 0; i < fdsize; i++) { - if (fd[i] != -1) { + if (fd) { + for (i = 0; i < fdsize; i++) { close(fd[i]); } } - return; + return rc; } static int vhost_setup_slave_channel(struct vhost_dev *dev) @@ -1535,6 +1506,8 @@ static int vhost_setup_slave_channel(struct vhost_dev *dev) int sv[2], ret = 0; bool reply_supported = virtio_has_feature(dev->protocol_features, VHOST_USER_PROTOCOL_F_REPLY_ACK); + Error *local_err = NULL; + QIOChannel *ioc; if (!virtio_has_feature(dev->protocol_features, VHOST_USER_PROTOCOL_F_SLAVE_REQ)) { @@ -1546,8 +1519,15 @@ static int vhost_setup_slave_channel(struct vhost_dev *dev) return -1; } - u->slave_fd = sv[0]; - qemu_set_fd_handler(u->slave_fd, slave_read, NULL, dev); + ioc = QIO_CHANNEL(qio_channel_socket_new_fd(sv[0], &local_err)); + if (!ioc) { + error_report_err(local_err); + return -1; + } + u->slave_ioc = ioc; + u->slave_src = qio_channel_add_watch_source(u->slave_ioc, + G_IO_IN | G_IO_HUP, + slave_read, dev, NULL, NULL); if (reply_supported) { msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK; @@ -1802,7 +1782,6 @@ static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque) u = g_new0(struct vhost_user, 1); u->user = opaque; - u->slave_fd = -1; u->dev = dev; dev->opaque = u; @@ -1917,7 +1896,7 @@ static int vhost_user_backend_cleanup(struct vhost_dev *dev) close(u->postcopy_fd.fd); u->postcopy_fd.handler = NULL; } - if (u->slave_fd >= 0) { + if (u->slave_ioc) { close_slave_channel(u); } g_free(u->region_rb); |