/* A non-blocking call returned EAGAIN, so yield, ensuring the
* handlers are set up so that we'll be rescheduled when there is an
* interesting event on the socket.
*/
static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs)
{
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);
aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock,
false, rd_handler, wr_handler, NULL, co);
qemu_coroutine_yield();
DPRINTF("s->sock=%d - back", s->sock);
aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, false,
NULL, NULL, NULL, NULL);
}
static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
struct virtio_blk_config blkcfg;
memcpy(&blkcfg, config, sizeof(blkcfg));
aio_context_acquire(bdrv_get_aio_context(s->bs));
bdrv_set_enable_write_cache(s->bs, blkcfg.wce != 0);
aio_context_release(bdrv_get_aio_context(s->bs));
}
BlockStatsList *qmp_query_blockstats(bool has_query_nodes,
bool query_nodes,
Error **errp)
{
BlockStatsList *head = NULL, **p_next = &head;
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
/* Just to be safe if query_nodes is not always initialized */
query_nodes = has_query_nodes && query_nodes;
while (next_query_bds(&blk, &bs, query_nodes)) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = blk ? blk_get_aio_context(blk)
: bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
info->value = bdrv_query_stats(blk, bs, !query_nodes);
aio_context_release(ctx);
*p_next = info;
p_next = &info->next;
}
return head;
}
static coroutine_fn void clear_fd_handler(BDRVSSHState *s,
BlockDriverState *bs)
{
DPRINTF("s->sock=%d", s->sock);
aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock,
false, NULL, NULL, NULL);
}
static int block_job_finish_sync(BlockJob *job,
void (*finish)(BlockJob *, Error **errp),
Error **errp)
{
struct BlockFinishData data;
BlockDriverState *bs = job->bs;
Error *local_err = NULL;
assert(bs->job == job);
/* Set up our own callback to store the result and chain to
* the original callback.
*/
data.job = job;
data.cb = job->cb;
data.opaque = job->opaque;
data.ret = -EINPROGRESS;
job->cb = block_job_finish_cb;
job->opaque = &data;
finish(job, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return -EBUSY;
}
while (data.ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(bs), true);
}
return (data.cancelled && data.ret == 0) ? -ECANCELED : data.ret;
}
int bdrv_all_create_snapshot(QEMUSnapshotInfo *sn,
BlockDriverState *vm_state_bs,
uint64_t vm_state_size,
BlockDriverState **first_bad_bs)
{
int err = 0;
BlockDriverState *bs = NULL;
while (err == 0 && (bs = bdrv_next(bs))) {
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
if (bs == vm_state_bs) {
sn->vm_state_size = vm_state_size;
err = bdrv_snapshot_create(bs, sn);
} else if (bdrv_can_snapshot(bs)) {
sn->vm_state_size = 0;
err = bdrv_snapshot_create(bs, sn);
}
aio_context_release(ctx);
}
*first_bad_bs = bs;
return err;
}
static void qemu_archipelago_aio_cancel(BlockDriverAIOCB *blockacb)
{
ArchipelagoAIOCB *aio_cb = (ArchipelagoAIOCB *) blockacb;
aio_cb->cancelled = true;
while (aio_cb->status == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(aio_cb->common.bs), true);
}
qemu_aio_release(aio_cb);
}
/*
* This is the callback function for rbd_aio_read and _write
*
* Note: this function is being called from a non qemu thread so
* we need to be careful about what we do here. Generally we only
* schedule a BH, and do the rest of the io completion handling
* from rbd_finish_bh() which runs in a qemu context.
*/
static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
{
RBDAIOCB *acb = rcb->acb;
rcb->ret = rbd_aio_get_return_value(c);
rbd_aio_release(c);
aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs),
rbd_finish_bh, rcb);
}
int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset)
{
int ret = -EINPROGRESS;
qed_read_l2_table(s, request, offset, qed_sync_cb, &ret);
while (ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(s->bs), true);
}
return ret;
}
/*
* Cancel aio. Since we don't reference acb in a non qemu threads,
* it is safe to access it here.
*/
static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
{
RBDAIOCB *acb = (RBDAIOCB *) blockacb;
acb->cancelled = 1;
while (acb->status == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(acb->common.bs), true);
}
qemu_aio_release(acb);
}
static void win32_aio_cancel(BlockDriverAIOCB *blockacb)
{
QEMUWin32AIOCB *waiocb = (QEMUWin32AIOCB *)blockacb;
/*
* CancelIoEx is only supported in Vista and newer. For now, just
* wait for completion.
*/
while (!HasOverlappedIoCompleted(&waiocb->ov)) {
aio_poll(bdrv_get_aio_context(blockacb->bs), true);
}
}
static void blkverify_aio_cancel(BlockDriverAIOCB *blockacb)
{
BlkverifyAIOCB *acb = (BlkverifyAIOCB *)blockacb;
AioContext *aio_context = bdrv_get_aio_context(blockacb->bs);
bool finished = false;
/* Wait until request completes, invokes its callback, and frees itself */
acb->finished = &finished;
while (!finished) {
aio_poll(aio_context, true);
}
}
int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
unsigned int index, unsigned int n, bool flush)
{
int ret = -EINPROGRESS;
qed_write_l2_table(s, request, index, n, flush, qed_sync_cb, &ret);
while (ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(s->bs), true);
}
return ret;
}
static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
{
QEDAIOCB *acb = (QEDAIOCB *)blockacb;
AioContext *aio_context = bdrv_get_aio_context(blockacb->bs);
bool finished = false;
/* Wait for the request to finish */
acb->finished = &finished;
while (!finished) {
aio_poll(aio_context, true);
}
}
int qed_read_l1_table_sync(BDRVQEDState *s)
{
int ret = -EINPROGRESS;
qed_read_table(s, s->header.l1_table_offset,
s->l1_table, qed_sync_cb, &ret);
while (ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(s->bs), true);
}
return ret;
}
int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
unsigned int n)
{
int ret = -EINPROGRESS;
qed_write_l1_table(s, index, n, qed_sync_cb, &ret);
while (ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(s->bs), true);
}
return ret;
}
static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
uint32_t features;
#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
if (s->dataplane && !(status & (VIRTIO_CONFIG_S_DRIVER |
VIRTIO_CONFIG_S_DRIVER_OK))) {
virtio_blk_data_plane_stop(s->dataplane);
}
#endif
if (!(status & VIRTIO_CONFIG_S_DRIVER_OK)) {
return;
}
features = vdev->guest_features;
/* A guest that supports VIRTIO_BLK_F_CONFIG_WCE must be able to send
* cache flushes. Thus, the "auto writethrough" behavior is never
* necessary for guests that support the VIRTIO_BLK_F_CONFIG_WCE feature.
* Leaving it enabled would break the following sequence:
*
* Guest started with "-drive cache=writethrough"
* Guest sets status to 0
* Guest sets DRIVER bit in status field
* Guest reads host features (WCE=0, CONFIG_WCE=1)
* Guest writes guest features (WCE=0, CONFIG_WCE=1)
* Guest writes 1 to the WCE configuration field (writeback mode)
* Guest sets DRIVER_OK bit in status field
*
* s->bs would erroneously be placed in writethrough mode.
*/
if (!(features & (1 << VIRTIO_BLK_F_CONFIG_WCE))) {
aio_context_acquire(bdrv_get_aio_context(s->bs));
bdrv_set_enable_write_cache(s->bs,
!!(features & (1 << VIRTIO_BLK_F_WCE)));
aio_context_release(bdrv_get_aio_context(s->bs));
}
}
static void archipelago_finish_aiocb(AIORequestData *reqdata)
{
if (reqdata->aio_cb->ret != reqdata->segreq->total) {
reqdata->aio_cb->ret = -EIO;
} else if (reqdata->aio_cb->ret == reqdata->segreq->total) {
reqdata->aio_cb->ret = 0;
}
reqdata->aio_cb->bh = aio_bh_new(
bdrv_get_aio_context(reqdata->aio_cb->common.bs),
qemu_archipelago_complete_aio, reqdata
);
qemu_bh_schedule(reqdata->aio_cb->bh);
}
void block_job_defer_to_main_loop(BlockJob *job,
BlockJobDeferToMainLoopFn *fn,
void *opaque)
{
BlockJobDeferToMainLoopData *data = g_malloc(sizeof(*data));
data->job = job;
data->bh = qemu_bh_new(block_job_defer_to_main_loop_bh, data);
data->aio_context = bdrv_get_aio_context(job->bs);
data->fn = fn;
data->opaque = opaque;
qemu_bh_schedule(data->bh);
}
static int nbd_co_send_request(BlockDriverState *bs,
struct nbd_request *request,
QEMUIOVector *qiov, int offset)
{
NbdClientSession *s = nbd_get_client_session(bs);
AioContext *aio_context;
int rc, ret, i;
qemu_co_mutex_lock(&s->send_mutex);
for (i = 0; i < MAX_NBD_REQUESTS; i++) {
if (s->recv_coroutine[i] == NULL) {
s->recv_coroutine[i] = qemu_coroutine_self();
break;
}
}
g_assert(qemu_in_coroutine());
assert(i < MAX_NBD_REQUESTS);
request->handle = INDEX_TO_HANDLE(s, i);
if (!s->ioc) {
qemu_co_mutex_unlock(&s->send_mutex);
return -EPIPE;
}
s->send_coroutine = qemu_coroutine_self();
aio_context = bdrv_get_aio_context(bs);
aio_set_fd_handler(aio_context, s->sioc->fd, false,
nbd_reply_ready, nbd_restart_write, bs);
if (qiov) {
qio_channel_set_cork(s->ioc, true);
rc = nbd_send_request(s->ioc, request);
if (rc >= 0) {
ret = nbd_wr_syncv(s->ioc, qiov->iov, qiov->niov,
offset, request->len, 0);
if (ret != request->len) {
rc = -EIO;
}
}
qio_channel_set_cork(s->ioc, false);
} else {
rc = nbd_send_request(s->ioc, request);
}
aio_set_fd_handler(aio_context, s->sioc->fd, false,
nbd_reply_ready, NULL, bs);
s->send_coroutine = NULL;
qemu_co_mutex_unlock(&s->send_mutex);
return rc;
}
static void mirror_complete(BlockJob *job, Error **errp)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
BlockDriverState *target;
target = blk_bs(s->target);
if (!s->synced) {
error_setg(errp, "The active block job '%s' cannot be completed",
job->id);
return;
}
if (s->backing_mode == MIRROR_OPEN_BACKING_CHAIN) {
int ret;
assert(!target->backing);
ret = bdrv_open_backing_file(target, NULL, "backing", errp);
if (ret < 0) {
return;
}
}
/* block all operations on to_replace bs */
if (s->replaces) {
AioContext *replace_aio_context;
s->to_replace = bdrv_find_node(s->replaces);
if (!s->to_replace) {
error_setg(errp, "Node name '%s' not found", s->replaces);
return;
}
replace_aio_context = bdrv_get_aio_context(s->to_replace);
aio_context_acquire(replace_aio_context);
/* TODO Translate this into permission system. Current definition of
* GRAPH_MOD would require to request it for the parents; they might
* not even be BlockDriverStates, however, so a BdrvChild can't address
* them. May need redefinition of GRAPH_MOD. */
error_setg(&s->replace_blocker,
"block device is in use by block-job-complete");
bdrv_op_block_all(s->to_replace, s->replace_blocker);
bdrv_ref(s->to_replace);
aio_context_release(replace_aio_context);
}
s->should_complete = true;
block_job_enter(&s->common);
}
BlockDriverState *bdrv_all_find_vmstate_bs(void)
{
bool not_found = true;
BlockDriverState *bs = NULL;
while (not_found && (bs = bdrv_next(bs))) {
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
not_found = !bdrv_can_snapshot(bs);
aio_context_release(ctx);
}
return bs;
}
void nbd_client_close(BlockDriverState *bs)
{
NbdClientSession *client = nbd_get_client_session(bs);
struct nbd_request request = {
.type = NBD_CMD_DISC,
.from = 0,
.len = 0
};
if (client->sock == -1) {
return;
}
nbd_send_request(client->sock, &request);
nbd_teardown_connection(bs);
}
int nbd_client_init(BlockDriverState *bs, int sock, const char *export,
Error **errp)
{
NbdClientSession *client = nbd_get_client_session(bs);
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, errp);
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->sock = sock;
/* Now that we're connected, set the socket to be non-blocking and
* kick the reply mechanism. */
qemu_set_nonblock(sock);
nbd_client_attach_aio_context(bs, bdrv_get_aio_context(bs));
logout("Established connection with NBD server\n");
return 0;
}
static int nbd_co_send_request(BlockDriverState *bs,
struct nbd_request *request,
QEMUIOVector *qiov, int offset)
{
NbdClientSession *s = nbd_get_client_session(bs);
AioContext *aio_context;
int rc, ret, i;
qemu_co_mutex_lock(&s->send_mutex);
for (i = 0; i < MAX_NBD_REQUESTS; i++) {
if (s->recv_coroutine[i] == NULL) {
s->recv_coroutine[i] = qemu_coroutine_self();
break;
}
}
assert(i < MAX_NBD_REQUESTS);
request->handle = INDEX_TO_HANDLE(s, i);
s->send_coroutine = qemu_coroutine_self();
aio_context = bdrv_get_aio_context(bs);
aio_set_fd_handler(aio_context, s->sock, AIO_CLIENT_PROTOCOL,
nbd_reply_ready, nbd_restart_write, bs);
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);
}
aio_set_fd_handler(aio_context, s->sock, AIO_CLIENT_PROTOCOL,
nbd_reply_ready, NULL, bs);
s->send_coroutine = NULL;
qemu_co_mutex_unlock(&s->send_mutex);
return rc;
}
static BlockAIOCB *curl_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
{
CURLAIOCB *acb;
acb = qemu_aio_get(&curl_aiocb_info, bs, cb, opaque);
acb->qiov = qiov;
acb->sector_num = sector_num;
acb->nb_sectors = nb_sectors;
acb->bh = aio_bh_new(bdrv_get_aio_context(bs), curl_readv_bh_cb, acb);
qemu_bh_schedule(acb->bh);
return &acb->common;
}
void block_job_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns)
{
assert(job->busy);
/* Check cancellation *before* setting busy = false, too! */
if (block_job_is_cancelled(job)) {
return;
}
job->busy = false;
if (block_job_is_paused(job)) {
qemu_coroutine_yield();
} else {
co_aio_sleep_ns(bdrv_get_aio_context(job->bs), type, ns);
}
job->busy = true;
}
/*
* Called from a libqnio thread
*/
static void vxhs_iio_callback(void *ctx, uint32_t opcode, uint32_t error)
{
VXHSAIOCB *acb = NULL;
switch (opcode) {
case IRP_READ_REQUEST:
case IRP_WRITE_REQUEST:
/*
* ctx is VXHSAIOCB*
* ctx is NULL if error is QNIOERROR_CHANNEL_HUP
*/
if (ctx) {
acb = ctx;
} else {
trace_vxhs_iio_callback(error);
goto out;
}
if (error) {
if (!acb->err) {
acb->err = error;
}
trace_vxhs_iio_callback(error);
}
aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs),
vxhs_complete_aio_bh, acb);
break;
default:
if (error == QNIOERROR_HUP) {
/*
* Channel failed, spontaneous notification,
* not in response to I/O
*/
trace_vxhs_iio_callback_chnfail(error, errno);
} else {
trace_vxhs_iio_callback_unknwn(opcode, error);
}
break;
}
out:
return;
}
int bdrv_all_goto_snapshot(const char *name, BlockDriverState **first_bad_bs)
{
int err = 0;
BlockDriverState *bs = NULL;
while (err == 0 && (bs = bdrv_next(bs))) {
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
if (bdrv_can_snapshot(bs)) {
err = bdrv_snapshot_goto(bs, name);
}
aio_context_release(ctx);
}
*first_bad_bs = bs;
return err;
}
bool bdrv_all_can_snapshot(BlockDriverState **first_bad_bs)
{
bool ok = true;
BlockDriverState *bs = NULL;
while (ok && (bs = bdrv_next(bs))) {
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
if (bdrv_is_inserted(bs) && !bdrv_is_read_only(bs)) {
ok = bdrv_can_snapshot(bs);
}
aio_context_release(ctx);
}
*first_bad_bs = bs;
return ok;
}
void iothread_stop_all(void)
{
Object *container = object_get_objects_root();
BlockDriverState *bs;
BdrvNextIterator it;
for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
AioContext *ctx = bdrv_get_aio_context(bs);
if (ctx == qemu_get_aio_context()) {
continue;
}
aio_context_acquire(ctx);
bdrv_set_aio_context(bs, qemu_get_aio_context());
aio_context_release(ctx);
}
object_child_foreach(container, iothread_stop, NULL);
}