static int qemu_event_init(void)
{
int err;
int fds[2];
err = pipe(fds);
if (err == -1)
return -errno;
err = fcntl_setfl(fds[0], O_NONBLOCK);
if (err < 0)
goto fail;
err = fcntl_setfl(fds[1], O_NONBLOCK);
if (err < 0)
goto fail;
qemu_set_fd_handler2(fds[0], NULL, qemu_event_read, NULL,
(void *)(unsigned long)fds[0]);
io_thread_fd = fds[1];
return 0;
fail:
close(fds[0]);
close(fds[1]);
return err;
}
static int qemu_event_init(void)
{
int err;
int fds[2];
err = qemu_eventfd(fds);
if (err == -1) {
return -errno;
}
err = fcntl_setfl(fds[0], O_NONBLOCK);
if (err < 0) {
goto fail;
}
err = fcntl_setfl(fds[1], O_NONBLOCK);
if (err < 0) {
goto fail;
}
qemu_set_fd_handler2(fds[0], NULL, qemu_event_read, NULL,
(void *)(intptr_t)fds[0]);
io_thread_fd = fds[1];
return 0;
fail:
close(fds[0]);
close(fds[1]);
return err;
}
static int qemu_signal_init(void)
{
int sigfd;
sigset_t set;
/*
* SIG_IPI must be blocked in the main thread and must not be caught
* by sigwait() in the signal thread. Otherwise, the cpu thread will
* not catch it reliably.
*/
sigemptyset(&set);
sigaddset(&set, SIG_IPI);
sigaddset(&set, SIGIO);
sigaddset(&set, SIGALRM);
sigaddset(&set, SIGBUS);
pthread_sigmask(SIG_BLOCK, &set, NULL);
sigdelset(&set, SIG_IPI);
sigfd = qemu_signalfd(&set);
if (sigfd == -1) {
fprintf(stderr, "failed to create signalfd\n");
return -errno;
}
fcntl_setfl(sigfd, O_NONBLOCK);
qemu_set_fd_handler2(sigfd, NULL, sigfd_handler, NULL,
(void *)(intptr_t)sigfd);
return 0;
}
static void process_msg_connect(IVShmemState *s, uint16_t posn, int fd,
Error **errp)
{
Peer *peer = &s->peers[posn];
int vector;
/*
* The N-th connect message for this peer comes with the file
* descriptor for vector N-1. Count messages to find the vector.
*/
if (peer->nb_eventfds >= s->vectors) {
error_setg(errp, "Too many eventfd received, device has %d vectors",
s->vectors);
close(fd);
return;
}
vector = peer->nb_eventfds++;
IVSHMEM_DPRINTF("eventfds[%d][%d] = %d\n", posn, vector, fd);
event_notifier_init_fd(&peer->eventfds[vector], fd);
fcntl_setfl(fd, O_NONBLOCK); /* msix/irqfd poll non block */
if (posn == s->vm_id) {
setup_interrupt(s, vector, errp);
/* TODO do we need to handle the error? */
}
if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
ivshmem_add_eventfd(s, posn, vector);
}
}
static int qemu_signal_init(Error **errp)
{
int sigfd;
sigset_t set;
/*
* SIG_IPI must be blocked in the main thread and must not be caught
* by sigwait() in the signal thread. Otherwise, the cpu thread will
* not catch it reliably.
*/
sigemptyset(&set);
sigaddset(&set, SIG_IPI);
sigaddset(&set, SIGIO);
sigaddset(&set, SIGALRM);
sigaddset(&set, SIGBUS);
/* SIGINT cannot be handled via signalfd, so that ^C can be used
* to interrupt QEMU when it is being run under gdb. SIGHUP and
* SIGTERM are also handled asynchronously, even though it is not
* strictly necessary, because they use the same handler as SIGINT.
*/
pthread_sigmask(SIG_BLOCK, &set, NULL);
sigdelset(&set, SIG_IPI);
sigfd = qemu_signalfd(&set);
if (sigfd == -1) {
error_setg_errno(errp, errno, "failed to create signalfd");
return -errno;
}
fcntl_setfl(sigfd, O_NONBLOCK);
qemu_set_fd_handler(sigfd, sigfd_handler, NULL, (void *)(intptr_t)sigfd);
return 0;
}
int event_notifier_init(EventNotifier *e, int active)
{
int fds[2];
int ret;
#ifdef CONFIG_EVENTFD
ret = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC);
#else
ret = -1;
errno = ENOSYS;
#endif
if (ret >= 0) {
e->rfd = e->wfd = ret;
} else {
if (errno != ENOSYS) {
return -errno;
}
if (qemu_pipe(fds) < 0) {
return -errno;
}
ret = fcntl_setfl(fds[0], O_NONBLOCK);
if (ret < 0) {
ret = -errno;
goto fail;
}
ret = fcntl_setfl(fds[1], O_NONBLOCK);
if (ret < 0) {
ret = -errno;
goto fail;
}
e->rfd = fds[0];
e->wfd = fds[1];
}
if (active) {
event_notifier_set(e);
}
return 0;
fail:
close(fds[0]);
close(fds[1]);
return ret;
}
static void enable_sigio_timer(int fd)
{
struct sigaction act;
/* timer signal */
sigfillset(&act.sa_mask);
act.sa_flags = 0;
act.sa_handler = host_alarm_handler;
sigaction(SIGIO, &act, NULL);
fcntl_setfl(fd, O_ASYNC);
fcntl(fd, F_SETOWN, getpid());
}
static int qemu_signal_init(void)
{
int sigfd;
sigset_t set;
#ifdef CONFIG_IOTHREAD
/* SIGUSR2 used by posix-aio-compat.c */
sigemptyset(&set);
sigaddset(&set, SIGUSR2);
pthread_sigmask(SIG_UNBLOCK, &set, NULL);
/*
* SIG_IPI must be blocked in the main thread and must not be caught
* by sigwait() in the signal thread. Otherwise, the cpu thread will
* not catch it reliably.
*/
sigemptyset(&set);
sigaddset(&set, SIG_IPI);
pthread_sigmask(SIG_BLOCK, &set, NULL);
sigemptyset(&set);
sigaddset(&set, SIGIO);
sigaddset(&set, SIGALRM);
sigaddset(&set, SIGBUS);
#else
sigemptyset(&set);
sigaddset(&set, SIGBUS);
if (kvm_enabled()) {
/*
* We need to process timer signals synchronously to avoid a race
* between exit_request check and KVM vcpu entry.
*/
sigaddset(&set, SIGIO);
sigaddset(&set, SIGALRM);
}
#endif
pthread_sigmask(SIG_BLOCK, &set, NULL);
sigfd = qemu_signalfd(&set);
if (sigfd == -1) {
fprintf(stderr, "failed to create signalfd\n");
return -errno;
}
fcntl_setfl(sigfd, O_NONBLOCK);
qemu_set_fd_handler2(sigfd, NULL, sigfd_handler, NULL,
(void *)(intptr_t)sigfd);
return 0;
}
static int qemu_signalfd_init(sigset_t mask)
{
int sigfd;
sigfd = qemu_signalfd(&mask);
if (sigfd == -1) {
fprintf(stderr, "failed to create signalfd\n");
return -errno;
}
fcntl_setfl(sigfd, O_NONBLOCK);
qemu_set_fd_handler2(sigfd, NULL, sigfd_handler, NULL,
(void *)(unsigned long) sigfd);
return 0;
}
int qemu_http_init(void)
{
QemuHttpState *state = (QemuHttpState *)qemu_mallocz(sizeof(QemuHttpState));
ghttp_state = state;
state->listen_fd = 0;
memset(state->clients, 0, sizeof(state->clients));
state->connections = 0;
state->listen_fd = qemu_socket(AF_INET, SOCK_STREAM, 0);
if (state->listen_fd < 0) {
return 0;
}
const int on = 1;
setsockopt(state->listen_fd, SOL_SOCKET, SO_REUSEADDR, (void*)&on, sizeof(on));
struct sockaddr_in laddr;
memset(&laddr, 0, sizeof(laddr));
laddr.sin_family = AF_INET;
laddr.sin_port = htons(DEFAULT_HTTP_PORT);
laddr.sin_addr.s_addr = INADDR_ANY;
if (bind(state->listen_fd, (struct sockaddr *)&laddr, sizeof(laddr)) == -1) {
return 0;
}
if (listen(state->listen_fd, QEMU_MAX_HTTP_CONNECTIONS) == -1) {
return 0;
}
fcntl_setfl(state->listen_fd, O_NONBLOCK);
qemu_set_fd_handler(state->listen_fd, accept_handler, NULL, (void *)state);
return 1;
}
static void accept_handler(void *opaque)
{
QemuHttpState *state = (QemuHttpState *)opaque;
if (state->connections == QEMU_MAX_HTTP_CONNECTIONS)
return;
int fd = qemu_accept(state->listen_fd, NULL, 0);
if (fd < 0)
return;
state->connections++;
int i;
int mindex = 0;
for (i = 0; i < QEMU_MAX_HTTP_CONNECTIONS; ++i) {
if (!state->clients[i].open) {
mindex = i;
break;
}
}
QemuHttpConnection *conn = &state->clients[mindex];
conn->fd = fd;
conn->open = 1;
conn->state = NEW_REQUEST;
conn->pos = 0;
conn->page_complete = 0;
conn->page_pos = -1;
conn->out_size = 0;
memset(conn->page, 0, sizeof(conn->page));
fcntl_setfl(conn->fd, O_NONBLOCK);
qemu_set_fd_handler(conn->fd, client_handler, NULL, (void *)conn);
}
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 void ivshmem_read(void *opaque, const uint8_t *buf, int size)
{
IVShmemState *s = opaque;
int incoming_fd;
int new_eventfd;
int64_t incoming_posn;
Error *err = NULL;
Peer *peer;
if (!fifo_update_and_get_i64(s, buf, size, &incoming_posn)) {
return;
}
if (incoming_posn < -1) {
IVSHMEM_DPRINTF("invalid incoming_posn %" PRId64 "\n", incoming_posn);
return;
}
/* pick off s->server_chr->msgfd and store it, posn should accompany msg */
incoming_fd = qemu_chr_fe_get_msgfd(s->server_chr);
IVSHMEM_DPRINTF("posn is %" PRId64 ", fd is %d\n",
incoming_posn, incoming_fd);
/* make sure we have enough space for this peer */
if (incoming_posn >= s->nb_peers) {
if (resize_peers(s, incoming_posn + 1) < 0) {
error_report("failed to resize peers array");
if (incoming_fd != -1) {
close(incoming_fd);
}
return;
}
}
peer = &s->peers[incoming_posn];
if (incoming_fd == -1) {
/* if posn is positive and unseen before then this is our posn*/
if (incoming_posn >= 0 && s->vm_id == -1) {
/* receive our posn */
s->vm_id = incoming_posn;
} else {
/* otherwise an fd == -1 means an existing peer has gone away */
IVSHMEM_DPRINTF("posn %" PRId64 " has gone away\n", incoming_posn);
close_peer_eventfds(s, incoming_posn);
}
return;
}
/* if the position is -1, then it's shared memory region fd */
if (incoming_posn == -1) {
void * map_ptr;
if (memory_region_is_mapped(&s->ivshmem)) {
error_report("shm already initialized");
close(incoming_fd);
return;
}
if (check_shm_size(s, incoming_fd, &err) == -1) {
error_report_err(err);
close(incoming_fd);
return;
}
/* mmap the region and map into the BAR2 */
map_ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED,
incoming_fd, 0);
if (map_ptr == MAP_FAILED) {
error_report("Failed to mmap shared memory %s", strerror(errno));
close(incoming_fd);
return;
}
memory_region_init_ram_ptr(&s->ivshmem, OBJECT(s),
"ivshmem.bar2", s->ivshmem_size, map_ptr);
qemu_set_ram_fd(s->ivshmem.ram_addr, incoming_fd);
vmstate_register_ram(&s->ivshmem, DEVICE(s));
IVSHMEM_DPRINTF("guest h/w addr = %p, size = %" PRIu64 "\n",
map_ptr, s->ivshmem_size);
memory_region_add_subregion(&s->bar, 0, &s->ivshmem);
return;
}
/* each peer has an associated array of eventfds, and we keep
* track of how many eventfds received so far */
/* get a new eventfd: */
if (peer->nb_eventfds >= s->vectors) {
error_report("Too many eventfd received, device has %d vectors",
s->vectors);
close(incoming_fd);
return;
}
new_eventfd = peer->nb_eventfds++;
/* this is an eventfd for a particular peer VM */
IVSHMEM_DPRINTF("eventfds[%" PRId64 "][%d] = %d\n", incoming_posn,
new_eventfd, incoming_fd);
event_notifier_init_fd(&peer->eventfds[new_eventfd], incoming_fd);
fcntl_setfl(incoming_fd, O_NONBLOCK); /* msix/irqfd poll non block */
if (incoming_posn == s->vm_id) {
setup_interrupt(s, new_eventfd);
}
if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
ivshmem_add_eventfd(s, incoming_posn, new_eventfd);
}
}
