static int nbd_co_send_request(NbdClientSession *s,
struct nbd_request *request,
QEMUIOVector *qiov, int offset)
{
int rc, ret;
qemu_co_mutex_lock(&s->send_mutex);
s->send_coroutine = qemu_coroutine_self();
qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write, s);
if (qiov) {
if (!s->is_unix) {
socket_set_cork(s->sock, 1);
}
rc = nbd_send_request(s->sock, request);
if (rc >= 0) {
ret = qemu_co_sendv(s->sock, qiov->iov, qiov->niov,
offset, request->len);
if (ret != request->len) {
rc = -EIO;
}
}
if (!s->is_unix) {
socket_set_cork(s->sock, 0);
}
} else {
rc = nbd_send_request(s->sock, request);
}
qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL, s);
s->send_coroutine = NULL;
qemu_co_mutex_unlock(&s->send_mutex);
return rc;
}
static void nbd_teardown_connection(NbdClientSession *client)
{
struct nbd_request request = {
.type = NBD_CMD_DISC,
.from = 0,
.len = 0
};
nbd_send_request(client->sock, &request);
/* finish any pending coroutines */
shutdown(client->sock, 2);
nbd_recv_coroutines_enter_all(client);
qemu_aio_set_fd_handler(client->sock, NULL, NULL, NULL);
closesocket(client->sock);
client->sock = -1;
}
void nbd_client_session_close(NbdClientSession *client)
{
if (!client->bs) {
return;
}
nbd_teardown_connection(client);
client->bs = NULL;
}
int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
int sock, const char *export)
{
int ret;
/* NBD handshake */
logout("session init %s\n", export);
qemu_set_block(sock);
ret = nbd_receive_negotiate(sock, export,
&client->nbdflags, &client->size,
&client->blocksize);
if (ret < 0) {
logout("Failed to negotiate with the NBD server\n");
closesocket(sock);
return ret;
}
qemu_co_mutex_init(&client->send_mutex);
qemu_co_mutex_init(&client->free_sema);
client->bs = bs;
client->sock = sock;
/* Now that we're connected, set the socket to be non-blocking and
* kick the reply mechanism. */
qemu_set_nonblock(sock);
qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL, client);
logout("Established connection with NBD server\n");
return 0;
}
static void prep_fetchline(void *opaque)
{
int *fetchable = opaque;
qemu_aio_set_fd_handler(STDIN_FILENO, NULL, NULL, NULL, NULL, NULL);
*fetchable= 1;
}
static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
{
GlusterAIOCB *acb = (GlusterAIOCB *)arg;
BlockDriverState *bs = acb->common.bs;
BDRVGlusterState *s = bs->opaque;
int retval;
acb->ret = ret;
retval = qemu_write_full(s->fds[GLUSTER_FD_WRITE], &acb, sizeof(acb));
if (retval != sizeof(acb)) {
/*
* Gluster AIO callback thread failed to notify the waiting
* QEMU thread about IO completion.
*
* Complete this IO request and make the disk inaccessible for
* subsequent reads and writes.
*/
error_report("Gluster failed to notify QEMU about IO completion");
qemu_mutex_lock_iothread(); /* We are in gluster thread context */
acb->common.cb(acb->common.opaque, -EIO);
qemu_aio_release(acb);
s->qemu_aio_count--;
close(s->fds[GLUSTER_FD_READ]);
close(s->fds[GLUSTER_FD_WRITE]);
qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ], NULL, NULL, NULL,
NULL);
bs->drv = NULL; /* Make the disk inaccessible */
qemu_mutex_unlock_iothread();
}
}
static void iscsi_close(BlockDriverState *bs)
{
IscsiLun *iscsilun = bs->opaque;
struct iscsi_context *iscsi = iscsilun->iscsi;
qemu_aio_set_fd_handler(iscsi_get_fd(iscsi), NULL, NULL, NULL, NULL);
iscsi_destroy_context(iscsi);
memset(iscsilun, 0, sizeof(IscsiLun));
}
static void
iscsi_set_events(IscsiLun *iscsilun)
{
struct iscsi_context *iscsi = iscsilun->iscsi;
qemu_aio_set_fd_handler(iscsi_get_fd(iscsi), iscsi_process_read,
(iscsi_which_events(iscsi) & POLLOUT)
? iscsi_process_write : NULL,
iscsi_process_flush, iscsilun);
}
static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
void *s, void *sp)
{
DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, fd);
switch (action) {
case CURL_POLL_IN:
qemu_aio_set_fd_handler(fd, curl_multi_do, NULL, s);
break;
case CURL_POLL_OUT:
qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, s);
break;
case CURL_POLL_INOUT:
qemu_aio_set_fd_handler(fd, curl_multi_do, curl_multi_do, s);
break;
case CURL_POLL_REMOVE:
qemu_aio_set_fd_handler(fd, NULL, NULL, NULL);
break;
}
return 0;
}
static int qemu_gluster_open(BlockDriverState *bs, const char *filename,
QDict *options, int bdrv_flags)
{
BDRVGlusterState *s = bs->opaque;
int open_flags = O_BINARY;
int ret = 0;
GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
s->glfs = qemu_gluster_init(gconf, filename);
if (!s->glfs) {
ret = -errno;
goto out;
}
if (bdrv_flags & BDRV_O_RDWR) {
open_flags |= O_RDWR;
} else {
open_flags |= O_RDONLY;
}
if ((bdrv_flags & BDRV_O_NOCACHE)) {
open_flags |= O_DIRECT;
}
s->fd = glfs_open(s->glfs, gconf->image, open_flags);
if (!s->fd) {
ret = -errno;
goto out;
}
ret = qemu_pipe(s->fds);
if (ret < 0) {
ret = -errno;
goto out;
}
fcntl(s->fds[GLUSTER_FD_READ], F_SETFL, O_NONBLOCK);
qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ],
qemu_gluster_aio_event_reader, NULL, qemu_gluster_aio_flush_cb, s);
out:
qemu_gluster_gconf_free(gconf);
if (!ret) {
return ret;
}
if (s->fd) {
glfs_close(s->fd);
}
if (s->glfs) {
glfs_fini(s->glfs);
}
return ret;
}
static void nbd_teardown_connection(BlockDriverState *bs)
{
BDRVNBDState *s = bs->opaque;
struct nbd_request request;
request.type = NBD_CMD_DISC;
request.from = 0;
request.len = 0;
nbd_send_request(s->sock, &request);
qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL, NULL);
closesocket(s->sock);
}
static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
struct iovec *iov, int offset)
{
int rc, ret;
qemu_co_mutex_lock(&s->send_mutex);
s->send_coroutine = qemu_coroutine_self();
qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write,
nbd_have_request, s);
rc = nbd_send_request(s->sock, request);
if (rc >= 0 && iov) {
ret = qemu_co_sendv(s->sock, iov, request->len, offset);
if (ret != request->len) {
return -EIO;
}
}
qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL,
nbd_have_request, s);
s->send_coroutine = NULL;
qemu_co_mutex_unlock(&s->send_mutex);
return rc;
}
static void qemu_rbd_close(BlockDriverState *bs)
{
BDRVRBDState *s = bs->opaque;
close(s->fds[0]);
close(s->fds[1]);
qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], NULL, NULL, NULL, NULL);
rbd_close(s->image);
rados_ioctx_destroy(s->io_ctx);
g_free(s->snap);
rados_shutdown(s->cluster);
}
static void qemu_gluster_close(BlockDriverState *bs)
{
BDRVGlusterState *s = bs->opaque;
close(s->fds[GLUSTER_FD_READ]);
close(s->fds[GLUSTER_FD_WRITE]);
qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ], NULL, NULL, NULL);
if (s->fd) {
glfs_close(s->fd);
s->fd = NULL;
}
glfs_fini(s->glfs);
}
static void
iscsi_set_events(IscsiLun *iscsilun)
{
struct iscsi_context *iscsi = iscsilun->iscsi;
int ev;
/* We always register a read handler. */
ev = POLLIN;
ev |= iscsi_which_events(iscsi);
if (ev != iscsilun->events) {
qemu_aio_set_fd_handler(iscsi_get_fd(iscsi),
iscsi_process_read,
(ev & POLLOUT) ? iscsi_process_write : NULL,
iscsilun);
}
iscsilun->events = ev;
}
static int nbd_establish_connection(BlockDriverState *bs)
{
BDRVNBDState *s = bs->opaque;
int sock;
int ret;
off_t size;
size_t blocksize;
if (s->host_spec[0] == '/') {
sock = unix_socket_outgoing(s->host_spec);
} else {
sock = tcp_socket_outgoing_spec(s->host_spec);
}
/* Failed to establish connection */
if (sock < 0) {
logout("Failed to establish connection to NBD server\n");
return -errno;
}
/* NBD handshake */
ret = nbd_receive_negotiate(sock, s->export_name, &s->nbdflags, &size,
&blocksize);
if (ret < 0) {
logout("Failed to negotiate with the NBD server\n");
closesocket(sock);
return ret;
}
/* Now that we're connected, set the socket to be non-blocking and
* kick the reply mechanism. */
socket_set_nonblock(sock);
qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL,
nbd_have_request, s);
s->sock = sock;
s->size = size;
s->blocksize = blocksize;
logout("Established connection with NBD server\n");
return 0;
}
static coroutine_fn void set_fd_handler(BDRVSSHState *s)
{
int r;
IOHandler *rd_handler = NULL, *wr_handler = NULL;
Coroutine *co = qemu_coroutine_self();
r = libssh2_session_block_directions(s->session);
if (r & LIBSSH2_SESSION_BLOCK_INBOUND) {
rd_handler = restart_coroutine;
}
if (r & LIBSSH2_SESSION_BLOCK_OUTBOUND) {
wr_handler = restart_coroutine;
}
DPRINTF("s->sock=%d rd_handler=%p wr_handler=%p", s->sock,
rd_handler, wr_handler);
qemu_aio_set_fd_handler(s->sock, rd_handler, wr_handler, return_true, co);
}
static int posix_aio_init(void)
{
struct sigaction act;
PosixAioState *s;
int fds[2];
struct qemu_paioinit ai;
if (posix_aio_state)
return 0;
s = qemu_malloc(sizeof(PosixAioState));
sigfillset(&act.sa_mask);
act.sa_flags = 0; /* do not restart syscalls to interrupt select() */
act.sa_handler = aio_signal_handler;
sigaction(SIGUSR2, &act, NULL);
s->first_aio = NULL;
if (pipe(fds) == -1) {
fprintf(stderr, "failed to create pipe\n");
return -errno;
}
s->rfd = fds[0];
s->wfd = fds[1];
fcntl(s->rfd, F_SETFL, O_NONBLOCK);
fcntl(s->wfd, F_SETFL, O_NONBLOCK);
qemu_aio_set_fd_handler(s->rfd, posix_aio_read, NULL, posix_aio_flush, s);
memset(&ai, 0, sizeof(ai));
ai.aio_threads = 64;
ai.aio_num = 64;
qemu_paio_init(&ai);
posix_aio_state = s;
return 0;
}
static int posix_aio_init(void)
{
sigset_t mask;
PosixAioState *s;
struct qemu_paioinit ai;
if (posix_aio_state)
return 0;
s = qemu_malloc(sizeof(PosixAioState));
/* Make sure to block AIO signal */
sigemptyset(&mask);
sigaddset(&mask, SIGUSR2);
sigprocmask(SIG_BLOCK, &mask, NULL);
s->first_aio = NULL;
s->fd = qemu_signalfd(&mask);
if (s->fd == -1) {
fprintf(stderr, "failed to create signalfd\n");
return -errno;
}
fcntl(s->fd, F_SETFL, O_NONBLOCK);
qemu_aio_set_fd_handler(s->fd, posix_aio_read, NULL, posix_aio_flush, s);
memset(&ai, 0, sizeof(ai));
ai.aio_threads = 64;
ai.aio_num = 64;
qemu_paio_init(&ai);
posix_aio_state = s;
return 0;
}
void *laio_init(void)
{
struct qemu_laio_state *s;
s = g_malloc0(sizeof(*s));
s->efd = eventfd(0, 0);
if (s->efd == -1)
goto out_free_state;
fcntl(s->efd, F_SETFL, O_NONBLOCK);
if (io_setup(MAX_EVENTS, &s->ctx) != 0)
goto out_close_efd;
qemu_aio_set_fd_handler(s->efd, qemu_laio_completion_cb, NULL,
qemu_laio_flush_cb, NULL, s);
return s;
out_close_efd:
close(s->efd);
out_free_state:
g_free(s);
return NULL;
}
static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags)
{
BDRVRBDState *s = bs->opaque;
char pool[RBD_MAX_POOL_NAME_SIZE];
char snap_buf[RBD_MAX_SNAP_NAME_SIZE];
char conf[RBD_MAX_CONF_SIZE];
char clientname_buf[RBD_MAX_CONF_SIZE];
char *clientname;
int r;
if (qemu_rbd_parsename(filename, pool, sizeof(pool),
snap_buf, sizeof(snap_buf),
s->name, sizeof(s->name),
conf, sizeof(conf)) < 0) {
return -EINVAL;
}
clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
r = rados_create(&s->cluster, clientname);
if (r < 0) {
error_report("error initializing");
return r;
}
s->snap = NULL;
if (snap_buf[0] != '\0') {
s->snap = g_strdup(snap_buf);
}
if (strstr(conf, "conf=") == NULL) {
/* try default location, but ignore failure */
rados_conf_read_file(s->cluster, NULL);
}
if (conf[0] != '\0') {
r = qemu_rbd_set_conf(s->cluster, conf);
if (r < 0) {
error_report("error setting config options");
goto failed_shutdown;
}
}
r = rados_connect(s->cluster);
if (r < 0) {
error_report("error connecting");
goto failed_shutdown;
}
r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
if (r < 0) {
error_report("error opening pool %s", pool);
goto failed_shutdown;
}
r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
if (r < 0) {
error_report("error reading header from %s", s->name);
goto failed_open;
}
bs->read_only = (s->snap != NULL);
s->event_reader_pos = 0;
r = qemu_pipe(s->fds);
if (r < 0) {
error_report("error opening eventfd");
goto failed;
}
fcntl(s->fds[0], F_SETFL, O_NONBLOCK);
fcntl(s->fds[1], F_SETFL, O_NONBLOCK);
qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], qemu_rbd_aio_event_reader,
NULL, qemu_rbd_aio_flush_cb, NULL, s);
return 0;
failed:
rbd_close(s->image);
failed_open:
rados_ioctx_destroy(s->io_ctx);
failed_shutdown:
rados_shutdown(s->cluster);
g_free(s->snap);
return r;
}
static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags)
{
BDRVRBDState *s = bs->opaque;
char pool[RBD_MAX_POOL_NAME_SIZE];
char snap_buf[RBD_MAX_SNAP_NAME_SIZE];
char conf[RBD_MAX_CONF_SIZE];
char clientname_buf[RBD_MAX_CONF_SIZE];
char *clientname;
int r;
if (qemu_rbd_parsename(filename, pool, sizeof(pool),
snap_buf, sizeof(snap_buf),
s->name, sizeof(s->name),
conf, sizeof(conf)) < 0) {
return -EINVAL;
}
clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
r = rados_create(&s->cluster, clientname);
if (r < 0) {
error_report("error initializing");
return r;
}
s->snap = NULL;
if (snap_buf[0] != '\0') {
s->snap = g_strdup(snap_buf);
}
/*
* Fallback to more conservative semantics if setting cache
* options fails. Ignore errors from setting rbd_cache because the
* only possible error is that the option does not exist, and
* librbd defaults to no caching. If write through caching cannot
* be set up, fall back to no caching.
*/
if (flags & BDRV_O_NOCACHE) {
rados_conf_set(s->cluster, "rbd_cache", "false");
} else {
rados_conf_set(s->cluster, "rbd_cache", "true");
}
if (strstr(conf, "conf=") == NULL) {
/* try default location, but ignore failure */
rados_conf_read_file(s->cluster, NULL);
}
if (conf[0] != '\0') {
r = qemu_rbd_set_conf(s->cluster, conf);
if (r < 0) {
error_report("error setting config options");
goto failed_shutdown;
}
}
r = rados_connect(s->cluster);
if (r < 0) {
error_report("error connecting");
goto failed_shutdown;
}
r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
if (r < 0) {
error_report("error opening pool %s", pool);
goto failed_shutdown;
}
r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
if (r < 0) {
error_report("error reading header from %s", s->name);
goto failed_open;
}
bs->read_only = (s->snap != NULL);
s->event_reader_pos = 0;
r = qemu_pipe(s->fds);
if (r < 0) {
error_report("error opening eventfd");
goto failed;
}
fcntl(s->fds[0], F_SETFL, O_NONBLOCK);
fcntl(s->fds[1], F_SETFL, O_NONBLOCK);
qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], qemu_rbd_aio_event_reader,
NULL, qemu_rbd_aio_flush_cb, s);
return 0;
failed:
rbd_close(s->image);
failed_open:
rados_ioctx_destroy(s->io_ctx);
failed_shutdown:
rados_shutdown(s->cluster);
g_free(s->snap);
return r;
}
void command_loop(void)
{
int c, i, j = 0, done = 0, fetchable = 0, prompted = 0;
char *input;
char **v;
const cmdinfo_t *ct;
for (i = 0; !done && i < ncmdline; i++) {
input = strdup(cmdline[i]);
if (!input) {
fprintf(stderr, _("cannot strdup command '%s': %s\n"),
cmdline[i], strerror(errno));
exit(1);
}
v = breakline(input, &c);
if (c) {
ct = find_command(v[0]);
if (ct) {
if (ct->flags & CMD_FLAG_GLOBAL) {
done = command(ct, c, v);
} else {
j = 0;
while (!done && (j = args_command(j))) {
done = command(ct, c, v);
}
}
} else {
fprintf(stderr, _("command \"%s\" not found\n"), v[0]);
}
}
doneline(input, v);
}
if (cmdline) {
g_free(cmdline);
return;
}
while (!done) {
if (!prompted) {
printf("%s", get_prompt());
fflush(stdout);
qemu_aio_set_fd_handler(STDIN_FILENO, prep_fetchline, NULL, NULL,
NULL, &fetchable);
prompted = 1;
}
qemu_aio_wait();
if (!fetchable) {
continue;
}
input = fetchline();
if (input == NULL) {
break;
}
v = breakline(input, &c);
if (c) {
ct = find_command(v[0]);
if (ct) {
done = command(ct, c, v);
} else {
fprintf(stderr, _("command \"%s\" not found\n"), v[0]);
}
}
doneline(input, v);
prompted = 0;
fetchable = 0;
}
qemu_aio_set_fd_handler(STDIN_FILENO, NULL, NULL, NULL, NULL, NULL);
}
static int qemu_gluster_open(BlockDriverState *bs, QDict *options,
int bdrv_flags)
{
BDRVGlusterState *s = bs->opaque;
int open_flags = O_BINARY;
int ret = 0;
GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
QemuOpts *opts;
Error *local_err = NULL;
const char *filename;
opts = qemu_opts_create_nofail(&runtime_opts);
qemu_opts_absorb_qdict(opts, options, &local_err);
if (error_is_set(&local_err)) {
qerror_report_err(local_err);
error_free(local_err);
ret = -EINVAL;
goto out;
}
filename = qemu_opt_get(opts, "filename");
s->glfs = qemu_gluster_init(gconf, filename);
if (!s->glfs) {
ret = -errno;
goto out;
}
if (bdrv_flags & BDRV_O_RDWR) {
open_flags |= O_RDWR;
} else {
open_flags |= O_RDONLY;
}
if ((bdrv_flags & BDRV_O_NOCACHE)) {
open_flags |= O_DIRECT;
}
s->fd = glfs_open(s->glfs, gconf->image, open_flags);
if (!s->fd) {
ret = -errno;
goto out;
}
ret = qemu_pipe(s->fds);
if (ret < 0) {
ret = -errno;
goto out;
}
fcntl(s->fds[GLUSTER_FD_READ], F_SETFL, O_NONBLOCK);
qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ],
qemu_gluster_aio_event_reader, NULL, s);
out:
qemu_opts_del(opts);
qemu_gluster_gconf_free(gconf);
if (!ret) {
return ret;
}
if (s->fd) {
glfs_close(s->fd);
}
if (s->glfs) {
glfs_fini(s->glfs);
}
return ret;
}
static coroutine_fn void clear_fd_handler(BDRVSSHState *s)
{
DPRINTF("s->sock=%d", s->sock);
qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL, NULL);
}
