static int qemu_signalfd_compat(const sigset_t *mask)
{
pthread_attr_t attr;
pthread_t tid;
struct sigfd_compat_info *info;
int fds[2];
info = malloc(sizeof(*info));
if (info == NULL) {
errno = ENOMEM;
return -1;
}
if (pipe(fds) == -1) {
free(info);
return -1;
}
qemu_set_cloexec(fds[0]);
qemu_set_cloexec(fds[1]);
memcpy(&info->mask, mask, sizeof(*mask));
info->fd = fds[1];
pthread_attr_init(&attr);
pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED);
pthread_create(&tid, &attr, sigwait_compat, info);
pthread_attr_destroy(&attr);
return fds[0];
}
/*
* Creates a pipe with FD_CLOEXEC set on both file descriptors
*/
int qemu_pipe(int pipefd[2])
{
int ret;
#ifdef CONFIG_PIPE2
ret = pipe2(pipefd, O_CLOEXEC);
if (ret != -1 || errno != ENOSYS) {
return ret;
}
#endif
ret = pipe(pipefd);
if (ret == 0) {
qemu_set_cloexec(pipefd[0]);
qemu_set_cloexec(pipefd[1]);
}
return ret;
}
static ssize_t tcp_chr_recv(Chardev *chr, char *buf, size_t len)
{
SocketChardev *s = SOCKET_CHARDEV(chr);
struct iovec iov = { .iov_base = buf, .iov_len = len };
int ret;
size_t i;
int *msgfds = NULL;
size_t msgfds_num = 0;
if (qio_channel_has_feature(s->ioc, QIO_CHANNEL_FEATURE_FD_PASS)) {
ret = qio_channel_readv_full(s->ioc, &iov, 1,
&msgfds, &msgfds_num,
NULL);
} else {
ret = qio_channel_readv_full(s->ioc, &iov, 1,
NULL, NULL,
NULL);
}
if (ret == QIO_CHANNEL_ERR_BLOCK) {
errno = EAGAIN;
ret = -1;
} else if (ret == -1) {
errno = EIO;
}
if (msgfds_num) {
/* close and clean read_msgfds */
for (i = 0; i < s->read_msgfds_num; i++) {
close(s->read_msgfds[i]);
}
if (s->read_msgfds_num) {
g_free(s->read_msgfds);
}
s->read_msgfds = msgfds;
s->read_msgfds_num = msgfds_num;
}
for (i = 0; i < s->read_msgfds_num; i++) {
int fd = s->read_msgfds[i];
if (fd < 0) {
continue;
}
/* O_NONBLOCK is preserved across SCM_RIGHTS so reset it */
qemu_set_block(fd);
#ifndef MSG_CMSG_CLOEXEC
qemu_set_cloexec(fd);
#endif
}
return ret;
}
int qemu_dup(int fd)
{
int ret;
#ifdef F_DUPFD_CLOEXEC
ret = fcntl(fd, F_DUPFD_CLOEXEC, 0);
#else
ret = dup(fd);
if (ret != -1) {
qemu_set_cloexec(ret);
}
#endif
return ret;
}
/*
* Dups an fd and sets the flags
*/
static int qemu_dup_flags(int fd, int flags)
{
int ret;
int serrno;
int dup_flags;
#ifdef F_DUPFD_CLOEXEC
ret = fcntl(fd, F_DUPFD_CLOEXEC, 0);
#else
ret = dup(fd);
if (ret != -1) {
qemu_set_cloexec(ret);
}
#endif
if (ret == -1) {
goto fail;
}
dup_flags = fcntl(ret, F_GETFL);
if (dup_flags == -1) {
goto fail;
}
if ((flags & O_SYNC) != (dup_flags & O_SYNC)) {
errno = EINVAL;
goto fail;
}
/* Set/unset flags that we can with fcntl */
if (fcntl(ret, F_SETFL, flags) == -1) {
goto fail;
}
/* Truncate the file in the cases that open() would truncate it */
if (flags & O_TRUNC ||
((flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))) {
if (ftruncate(ret, 0) == -1) {
goto fail;
}
}
return ret;
fail:
serrno = errno;
if (ret != -1) {
close(ret);
}
errno = serrno;
return -1;
}
int qemu_signalfd(const sigset_t *mask)
{
#if defined(CONFIG_SYS_SIGNALFD)
int ret;
ret = syscall(SYS_signalfd, -1, mask, _NSIG / 8);
if (ret != -1) {
qemu_set_cloexec(ret);
return ret;
}
#endif
return qemu_signalfd_compat(mask);
}
void os_daemonize(void)
{
if (daemonize) {
pid_t pid;
int fds[2];
if (pipe(fds) == -1) {
exit(1);
}
pid = fork();
if (pid > 0) {
uint8_t status;
ssize_t len;
close(fds[1]);
do {
len = read(fds[0], &status, 1);
} while (len < 0 && errno == EINTR);
/* only exit successfully if our child actually wrote
* a one-byte zero to our pipe, upon successful init */
exit(len == 1 && status == 0 ? 0 : 1);
} else if (pid < 0) {
exit(1);
}
close(fds[0]);
daemon_pipe = fds[1];
qemu_set_cloexec(daemon_pipe);
setsid();
pid = fork();
if (pid > 0) {
exit(0);
} else if (pid < 0) {
exit(1);
}
umask(027);
signal(SIGTSTP, SIG_IGN);
signal(SIGTTOU, SIG_IGN);
signal(SIGTTIN, SIG_IGN);
rcu_after_fork();
}
}
void os_daemonize(void)
{
if (daemonize) {
pid_t pid;
if (pipe(fds) == -1)
exit(1);
pid = fork();
if (pid > 0) {
uint8_t status;
ssize_t len;
close(fds[1]);
again:
len = read(fds[0], &status, 1);
LOGV("%s:%s, read(), len = %d", __FILE__, __func__, len);
if (len == -1 && (errno == EINTR))
goto again;
if (len != 1)
exit(1);
else if (status == 1) {
fprintf(stderr, "Could not acquire pidfile: %s\n", strerror(errno));
exit(1);
} else
exit(0);
} else if (pid < 0)
exit(1);
close(fds[0]);
qemu_set_cloexec(fds[1]);
setsid();
pid = fork();
if (pid > 0)
exit(0);
else if (pid < 0)
exit(1);
umask(027);
signal(SIGTSTP, SIG_IGN);
signal(SIGTTOU, SIG_IGN);
signal(SIGTTIN, SIG_IGN);
}
}
/*
* Creates an eventfd that looks like a pipe and has EFD_CLOEXEC set.
*/
int qemu_eventfd(int fds[2])
{
#ifdef CONFIG_EVENTFD
int ret;
ret = eventfd(0, 0);
if (ret >= 0) {
fds[0] = ret;
qemu_set_cloexec(ret);
if ((fds[1] = dup(ret)) == -1) {
close(ret);
return -1;
}
qemu_set_cloexec(fds[1]);
return 0;
}
if (errno != ENOSYS) {
return -1;
}
#endif
return qemu_pipe(fds);
}
static void qio_channel_socket_copy_fds(struct msghdr *msg,
int **fds, size_t *nfds)
{
struct cmsghdr *cmsg;
*nfds = 0;
*fds = NULL;
for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
int fd_size, i;
int gotfds;
if (cmsg->cmsg_len < CMSG_LEN(sizeof(int)) ||
cmsg->cmsg_level != SOL_SOCKET ||
cmsg->cmsg_type != SCM_RIGHTS) {
continue;
}
fd_size = cmsg->cmsg_len - CMSG_LEN(0);
if (!fd_size) {
continue;
}
gotfds = fd_size / sizeof(int);
*fds = g_renew(int, *fds, *nfds + gotfds);
memcpy(*fds + *nfds, CMSG_DATA(cmsg), fd_size);
for (i = 0; i < gotfds; i++) {
int fd = (*fds)[*nfds + i];
if (fd < 0) {
continue;
}
/* O_NONBLOCK is preserved across SCM_RIGHTS so reset it */
qemu_set_block(fd);
#ifndef MSG_CMSG_CLOEXEC
qemu_set_cloexec(fd);
#endif
}
*nfds += gotfds;
}
}
static void ga_log(const gchar *domain, GLogLevelFlags level,
const gchar *msg, gpointer opaque)
{
GAState *s = opaque;
GTimeVal time;
const char *level_str = ga_log_level_str(level);
if (!ga_logging_enabled(s)) {
return;
}
level &= G_LOG_LEVEL_MASK;
#ifndef _WIN32
if (g_strcmp0(domain, "syslog") == 0) {
syslog(LOG_INFO, "%s: %s", level_str, msg);
} else if (level & s->log_level) {
#else
if (level & s->log_level) {
#endif
g_get_current_time(&time);
fprintf(s->log_file,
"%lu.%lu: %s: %s\n", time.tv_sec, time.tv_usec, level_str, msg);
fflush(s->log_file);
}
}
void ga_set_response_delimited(GAState *s)
{
s->delimit_response = true;
}
static FILE *ga_open_logfile(const char *logfile)
{
FILE *f;
f = fopen(logfile, "a");
if (!f) {
return NULL;
}
qemu_set_cloexec(fileno(f));
return f;
}
static int init_socket(const char *socket_path)
{
struct sockaddr_un addr;
int sock;
int ret;
sock = socket(PF_UNIX, SOCK_STREAM, 0);
g_assert_no_errno(sock);
addr.sun_family = AF_UNIX;
snprintf(addr.sun_path, sizeof(addr.sun_path), "%s", socket_path);
qemu_set_cloexec(sock);
do {
ret = bind(sock, (struct sockaddr *)&addr, sizeof(addr));
} while (ret == -1 && errno == EINTR);
g_assert_no_errno(ret);
listen(sock, 1);
return sock;
}
static int raw_reopen_prepare(BDRVReopenState *state,
BlockReopenQueue *queue, Error **errp)
{
BDRVRawState *s;
BDRVRawReopenState *raw_s;
int ret = 0;
assert(state != NULL);
assert(state->bs != NULL);
s = state->bs->opaque;
state->opaque = g_malloc0(sizeof(BDRVRawReopenState));
raw_s = state->opaque;
#ifdef CONFIG_LINUX_AIO
raw_s->use_aio = s->use_aio;
/* we can use s->aio_ctx instead of a copy, because the use_aio flag is
* valid in the 'false' condition even if aio_ctx is set, and raw_set_aio()
* won't override aio_ctx if aio_ctx is non-NULL */
if (raw_set_aio(&s->aio_ctx, &raw_s->use_aio, state->flags)) {
return -1;
}
#endif
if (s->type == FTYPE_FD || s->type == FTYPE_CD) {
raw_s->open_flags |= O_NONBLOCK;
}
raw_parse_flags(state->flags, &raw_s->open_flags);
raw_s->fd = -1;
int fcntl_flags = O_APPEND | O_NONBLOCK;
#ifdef O_NOATIME
fcntl_flags |= O_NOATIME;
#endif
#ifdef O_ASYNC
/* Not all operating systems have O_ASYNC, and those that don't
* will not let us track the state into raw_s->open_flags (typically
* you achieve the same effect with an ioctl, for example I_SETSIG
* on Solaris). But we do not use O_ASYNC, so that's fine.
*/
assert((s->open_flags & O_ASYNC) == 0);
#endif
if ((raw_s->open_flags & ~fcntl_flags) == (s->open_flags & ~fcntl_flags)) {
/* dup the original fd */
/* TODO: use qemu fcntl wrapper */
#ifdef F_DUPFD_CLOEXEC
raw_s->fd = fcntl(s->fd, F_DUPFD_CLOEXEC, 0);
#else
raw_s->fd = dup(s->fd);
if (raw_s->fd != -1) {
qemu_set_cloexec(raw_s->fd);
}
#endif
if (raw_s->fd >= 0) {
ret = fcntl_setfl(raw_s->fd, raw_s->open_flags);
if (ret) {
qemu_close(raw_s->fd);
raw_s->fd = -1;
}
}
}
/* If we cannot use fcntl, or fcntl failed, fall back to qemu_open() */
if (raw_s->fd == -1) {
assert(!(raw_s->open_flags & O_CREAT));
raw_s->fd = qemu_open(state->bs->filename, raw_s->open_flags);
if (raw_s->fd == -1) {
ret = -1;
}
}
return ret;
}
static int xen_9pfs_connect(struct XenLegacyDevice *xendev)
{
Error *err = NULL;
int i;
Xen9pfsDev *xen_9pdev = container_of(xendev, Xen9pfsDev, xendev);
V9fsState *s = &xen_9pdev->state;
QemuOpts *fsdev;
if (xenstore_read_fe_int(&xen_9pdev->xendev, "num-rings",
&xen_9pdev->num_rings) == -1 ||
xen_9pdev->num_rings > MAX_RINGS || xen_9pdev->num_rings < 1) {
return -1;
}
xen_9pdev->rings = g_new0(Xen9pfsRing, xen_9pdev->num_rings);
for (i = 0; i < xen_9pdev->num_rings; i++) {
char *str;
int ring_order;
xen_9pdev->rings[i].priv = xen_9pdev;
xen_9pdev->rings[i].evtchn = -1;
xen_9pdev->rings[i].local_port = -1;
str = g_strdup_printf("ring-ref%u", i);
if (xenstore_read_fe_int(&xen_9pdev->xendev, str,
&xen_9pdev->rings[i].ref) == -1) {
g_free(str);
goto out;
}
g_free(str);
str = g_strdup_printf("event-channel-%u", i);
if (xenstore_read_fe_int(&xen_9pdev->xendev, str,
&xen_9pdev->rings[i].evtchn) == -1) {
g_free(str);
goto out;
}
g_free(str);
xen_9pdev->rings[i].intf =
xen_be_map_grant_ref(&xen_9pdev->xendev,
xen_9pdev->rings[i].ref,
PROT_READ | PROT_WRITE);
if (!xen_9pdev->rings[i].intf) {
goto out;
}
ring_order = xen_9pdev->rings[i].intf->ring_order;
if (ring_order > MAX_RING_ORDER) {
goto out;
}
xen_9pdev->rings[i].ring_order = ring_order;
xen_9pdev->rings[i].data =
xen_be_map_grant_refs(&xen_9pdev->xendev,
xen_9pdev->rings[i].intf->ref,
(1 << ring_order),
PROT_READ | PROT_WRITE);
if (!xen_9pdev->rings[i].data) {
goto out;
}
xen_9pdev->rings[i].ring.in = xen_9pdev->rings[i].data;
xen_9pdev->rings[i].ring.out = xen_9pdev->rings[i].data +
XEN_FLEX_RING_SIZE(ring_order);
xen_9pdev->rings[i].bh = qemu_bh_new(xen_9pfs_bh, &xen_9pdev->rings[i]);
xen_9pdev->rings[i].out_cons = 0;
xen_9pdev->rings[i].out_size = 0;
xen_9pdev->rings[i].inprogress = false;
xen_9pdev->rings[i].evtchndev = xenevtchn_open(NULL, 0);
if (xen_9pdev->rings[i].evtchndev == NULL) {
goto out;
}
qemu_set_cloexec(xenevtchn_fd(xen_9pdev->rings[i].evtchndev));
xen_9pdev->rings[i].local_port = xenevtchn_bind_interdomain
(xen_9pdev->rings[i].evtchndev,
xendev->dom,
xen_9pdev->rings[i].evtchn);
if (xen_9pdev->rings[i].local_port == -1) {
xen_pv_printf(xendev, 0,
"xenevtchn_bind_interdomain failed port=%d\n",
xen_9pdev->rings[i].evtchn);
goto out;
}
xen_pv_printf(xendev, 2, "bind evtchn port %d\n", xendev->local_port);
qemu_set_fd_handler(xenevtchn_fd(xen_9pdev->rings[i].evtchndev),
xen_9pfs_evtchn_event, NULL, &xen_9pdev->rings[i]);
}
xen_9pdev->security_model = xenstore_read_be_str(xendev, "security_model");
xen_9pdev->path = xenstore_read_be_str(xendev, "path");
xen_9pdev->id = s->fsconf.fsdev_id =
g_strdup_printf("xen9p%d", xendev->dev);
xen_9pdev->tag = s->fsconf.tag = xenstore_read_fe_str(xendev, "tag");
fsdev = qemu_opts_create(qemu_find_opts("fsdev"),
s->fsconf.tag,
1, NULL);
qemu_opt_set(fsdev, "fsdriver", "local", NULL);
qemu_opt_set(fsdev, "path", xen_9pdev->path, NULL);
qemu_opt_set(fsdev, "security_model", xen_9pdev->security_model, NULL);
qemu_opts_set_id(fsdev, s->fsconf.fsdev_id);
qemu_fsdev_add(fsdev, &err);
if (err) {
error_report_err(err);
}
v9fs_device_realize_common(s, &xen_9p_transport, NULL);
return 0;
out:
xen_9pfs_free(xendev);
return -1;
}