#include "qemu/option.h"
#include "qemu/cutils.h"
#include "qemu/main-loop.h"
+#include "qemu/atomic.h"
#include "qapi/qapi-visit-sockets.h"
#include "qapi/qmp/qstring.h"
#include "block/nbd.h"
#include "block/block_int.h"
+#include "qemu/yank.h"
+
#define EN_OPTSTR ":exportname="
#define MAX_NBD_REQUESTS 16
Error *connect_err;
bool wait_in_flight;
+ QEMUTimer *reconnect_delay_timer;
+
NBDClientRequest requests[MAX_NBD_REQUESTS];
NBDReply reply;
BlockDriverState *bs;
QCryptoTLSCreds *tlscreds;
const char *hostname;
char *x_dirty_bitmap;
+ bool alloc_depth;
bool wait_connect;
NBDConnectThread *connect_thread;
} BDRVNBDState;
-static QIOChannelSocket *nbd_establish_connection(SocketAddress *saddr,
- Error **errp);
-static QIOChannelSocket *nbd_co_establish_connection(BlockDriverState *bs,
- Error **errp);
+static int nbd_establish_connection(BlockDriverState *bs, SocketAddress *saddr,
+ Error **errp);
+static int nbd_co_establish_connection(BlockDriverState *bs, Error **errp);
static void nbd_co_establish_connection_cancel(BlockDriverState *bs,
bool detach);
-static int nbd_client_handshake(BlockDriverState *bs, QIOChannelSocket *sioc,
- Error **errp);
+static int nbd_client_handshake(BlockDriverState *bs, Error **errp);
+static void nbd_yank(void *opaque);
static void nbd_clear_bdrvstate(BDRVNBDState *s)
{
static void nbd_channel_error(BDRVNBDState *s, int ret)
{
if (ret == -EIO) {
- if (s->state == NBD_CLIENT_CONNECTED) {
+ if (qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED) {
s->state = s->reconnect_delay ? NBD_CLIENT_CONNECTING_WAIT :
NBD_CLIENT_CONNECTING_NOWAIT;
}
} else {
- if (s->state == NBD_CLIENT_CONNECTED) {
+ if (qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED) {
qio_channel_shutdown(s->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
}
s->state = NBD_CLIENT_QUIT;
}
}
+static void reconnect_delay_timer_del(BDRVNBDState *s)
+{
+ if (s->reconnect_delay_timer) {
+ timer_free(s->reconnect_delay_timer);
+ s->reconnect_delay_timer = NULL;
+ }
+}
+
+static void reconnect_delay_timer_cb(void *opaque)
+{
+ BDRVNBDState *s = opaque;
+
+ if (qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTING_WAIT) {
+ s->state = NBD_CLIENT_CONNECTING_NOWAIT;
+ while (qemu_co_enter_next(&s->free_sema, NULL)) {
+ /* Resume all queued requests */
+ }
+ }
+
+ reconnect_delay_timer_del(s);
+}
+
+static void reconnect_delay_timer_init(BDRVNBDState *s, uint64_t expire_time_ns)
+{
+ if (qatomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTING_WAIT) {
+ return;
+ }
+
+ assert(!s->reconnect_delay_timer);
+ s->reconnect_delay_timer = aio_timer_new(bdrv_get_aio_context(s->bs),
+ QEMU_CLOCK_REALTIME,
+ SCALE_NS,
+ reconnect_delay_timer_cb, s);
+ timer_mod(s->reconnect_delay_timer, expire_time_ns);
+}
+
static void nbd_client_detach_aio_context(BlockDriverState *bs)
{
BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
- qio_channel_detach_aio_context(QIO_CHANNEL(s->ioc));
+ /* Timer is deleted in nbd_client_co_drain_begin() */
+ assert(!s->reconnect_delay_timer);
+ /*
+ * If reconnect is in progress we may have no ->ioc. It will be
+ * re-instantiated in the proper aio context once the connection is
+ * reestablished.
+ */
+ if (s->ioc) {
+ qio_channel_detach_aio_context(QIO_CHANNEL(s->ioc));
+ }
}
static void nbd_client_attach_aio_context_bh(void *opaque)
BlockDriverState *bs = opaque;
BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
- /*
- * The node is still drained, so we know the coroutine has yielded in
- * nbd_read_eof(), the only place where bs->in_flight can reach 0, or it is
- * entered for the first time. Both places are safe for entering the
- * coroutine.
- */
- qemu_aio_coroutine_enter(bs->aio_context, s->connection_co);
+ if (s->connection_co) {
+ /*
+ * The node is still drained, so we know the coroutine has yielded in
+ * nbd_read_eof(), the only place where bs->in_flight can reach 0, or
+ * it is entered for the first time. Both places are safe for entering
+ * the coroutine.
+ */
+ qemu_aio_coroutine_enter(bs->aio_context, s->connection_co);
+ }
bdrv_dec_in_flight(bs);
}
* s->connection_co is either yielded from nbd_receive_reply or from
* nbd_co_reconnect_loop()
*/
- if (s->state == NBD_CLIENT_CONNECTED) {
+ if (qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED) {
qio_channel_attach_aio_context(QIO_CHANNEL(s->ioc), new_context);
}
}
nbd_co_establish_connection_cancel(bs, false);
+
+ reconnect_delay_timer_del(s);
+
+ if (qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTING_WAIT) {
+ s->state = NBD_CLIENT_CONNECTING_NOWAIT;
+ qemu_co_queue_restart_all(&s->free_sema);
+ }
}
static void coroutine_fn nbd_client_co_drain_end(BlockDriverState *bs)
static bool nbd_client_connecting(BDRVNBDState *s)
{
- return s->state == NBD_CLIENT_CONNECTING_WAIT ||
- s->state == NBD_CLIENT_CONNECTING_NOWAIT;
+ NBDClientState state = qatomic_load_acquire(&s->state);
+ return state == NBD_CLIENT_CONNECTING_WAIT ||
+ state == NBD_CLIENT_CONNECTING_NOWAIT;
}
static bool nbd_client_connecting_wait(BDRVNBDState *s)
{
- return s->state == NBD_CLIENT_CONNECTING_WAIT;
+ return qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTING_WAIT;
}
static void connect_bh(void *opaque)
return NULL;
}
-static QIOChannelSocket *coroutine_fn
+static int coroutine_fn
nbd_co_establish_connection(BlockDriverState *bs, Error **errp)
{
+ int ret;
QemuThread thread;
BDRVNBDState *s = bs->opaque;
- QIOChannelSocket *res;
NBDConnectThread *thr = s->connect_thread;
qemu_mutex_lock(&thr->mutex);
case CONNECT_THREAD_SUCCESS:
/* Previous attempt finally succeeded in background */
thr->state = CONNECT_THREAD_NONE;
- res = thr->sioc;
+ s->sioc = thr->sioc;
thr->sioc = NULL;
+ yank_register_function(BLOCKDEV_YANK_INSTANCE(bs->node_name),
+ nbd_yank, bs);
qemu_mutex_unlock(&thr->mutex);
- return res;
+ return 0;
case CONNECT_THREAD_RUNNING:
/* Already running, will wait */
break;
thr->state = CONNECT_THREAD_NONE;
error_propagate(errp, thr->err);
thr->err = NULL;
- res = thr->sioc;
+ s->sioc = thr->sioc;
thr->sioc = NULL;
+ if (s->sioc) {
+ yank_register_function(BLOCKDEV_YANK_INSTANCE(bs->node_name),
+ nbd_yank, bs);
+ }
+ ret = (s->sioc ? 0 : -1);
break;
case CONNECT_THREAD_RUNNING:
case CONNECT_THREAD_RUNNING_DETACHED:
* failed. Still connect thread is executing in background, and its
* result may be used for next connection attempt.
*/
- res = NULL;
+ ret = -1;
error_setg(errp, "Connection attempt cancelled by other operation");
break;
qemu_mutex_unlock(&thr->mutex);
- return res;
+ return ret;
}
/*
{
int ret;
Error *local_err = NULL;
- QIOChannelSocket *sioc;
if (!nbd_client_connecting(s)) {
return;
/* Finalize previous connection if any */
if (s->ioc) {
- nbd_client_detach_aio_context(s->bs);
+ qio_channel_detach_aio_context(QIO_CHANNEL(s->ioc));
+ yank_unregister_function(BLOCKDEV_YANK_INSTANCE(s->bs->node_name),
+ nbd_yank, s->bs);
object_unref(OBJECT(s->sioc));
s->sioc = NULL;
object_unref(OBJECT(s->ioc));
s->ioc = NULL;
}
- sioc = nbd_co_establish_connection(s->bs, &local_err);
- if (!sioc) {
+ if (nbd_co_establish_connection(s->bs, &local_err) < 0) {
ret = -ECONNREFUSED;
goto out;
}
bdrv_dec_in_flight(s->bs);
- ret = nbd_client_handshake(s->bs, sioc, &local_err);
+ ret = nbd_client_handshake(s->bs, &local_err);
if (s->drained) {
s->wait_drained_end = true;
static coroutine_fn void nbd_co_reconnect_loop(BDRVNBDState *s)
{
- uint64_t start_time_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
- uint64_t delay_ns = s->reconnect_delay * NANOSECONDS_PER_SECOND;
uint64_t timeout = 1 * NANOSECONDS_PER_SECOND;
uint64_t max_timeout = 16 * NANOSECONDS_PER_SECOND;
+ if (qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTING_WAIT) {
+ reconnect_delay_timer_init(s, qemu_clock_get_ns(QEMU_CLOCK_REALTIME) +
+ s->reconnect_delay * NANOSECONDS_PER_SECOND);
+ }
+
nbd_reconnect_attempt(s);
while (nbd_client_connecting(s)) {
- if (s->state == NBD_CLIENT_CONNECTING_WAIT &&
- qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start_time_ns > delay_ns)
- {
- s->state = NBD_CLIENT_CONNECTING_NOWAIT;
- qemu_co_queue_restart_all(&s->free_sema);
- }
-
if (s->drained) {
bdrv_dec_in_flight(s->bs);
s->wait_drained_end = true;
} else {
qemu_co_sleep_ns_wakeable(QEMU_CLOCK_REALTIME, timeout,
&s->connection_co_sleep_ns_state);
+ if (s->drained) {
+ continue;
+ }
if (timeout < max_timeout) {
timeout *= 2;
}
nbd_reconnect_attempt(s);
}
+
+ reconnect_delay_timer_del(s);
}
static coroutine_fn void nbd_connection_entry(void *opaque)
int ret = 0;
Error *local_err = NULL;
- while (s->state != NBD_CLIENT_QUIT) {
+ while (qatomic_load_acquire(&s->state) != NBD_CLIENT_QUIT) {
/*
* The NBD client can only really be considered idle when it has
* yielded from qio_channel_readv_all_eof(), waiting for data. This is
nbd_co_reconnect_loop(s);
}
- if (s->state != NBD_CLIENT_CONNECTED) {
+ if (qatomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) {
continue;
}
s->connection_co = NULL;
if (s->ioc) {
- nbd_client_detach_aio_context(s->bs);
+ qio_channel_detach_aio_context(QIO_CHANNEL(s->ioc));
+ yank_unregister_function(BLOCKDEV_YANK_INSTANCE(s->bs->node_name),
+ nbd_yank, s->bs);
object_unref(OBJECT(s->sioc));
s->sioc = NULL;
object_unref(OBJECT(s->ioc));
qemu_co_queue_wait(&s->free_sema, &s->send_mutex);
}
- if (s->state != NBD_CLIENT_CONNECTED) {
+ if (qatomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) {
rc = -EIO;
goto err;
}
if (qiov) {
qio_channel_set_cork(s->ioc, true);
rc = nbd_send_request(s->ioc, request);
- if (rc >= 0 && s->state == NBD_CLIENT_CONNECTED) {
+ if (qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED &&
+ rc >= 0) {
if (qio_channel_writev_all(s->ioc, qiov->iov, qiov->niov,
NULL) < 0) {
rc = -EIO;
trace_nbd_parse_blockstatus_compliance("extent length too large");
}
+ /*
+ * HACK: if we are using x-dirty-bitmaps to access
+ * qemu:allocation-depth, treat all depths > 2 the same as 2,
+ * since nbd_client_co_block_status is only expecting the low two
+ * bits to be set.
+ */
+ if (s->alloc_depth && extent->flags > 2) {
+ extent->flags = 2;
+ }
+
return 0;
}
s->requests[i].receiving = true;
qemu_coroutine_yield();
s->requests[i].receiving = false;
- if (s->state != NBD_CLIENT_CONNECTED) {
+ if (qatomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) {
error_setg(errp, "Connection closed");
return -EIO;
}
NBDReply local_reply;
NBDStructuredReplyChunk *chunk;
Error *local_err = NULL;
- if (s->state != NBD_CLIENT_CONNECTED) {
+ if (qatomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) {
error_setg(&local_err, "Connection closed");
nbd_iter_channel_error(iter, -EIO, &local_err);
goto break_loop;
}
/* Do not execute the body of NBD_FOREACH_REPLY_CHUNK for simple reply. */
- if (nbd_reply_is_simple(reply) || s->state != NBD_CLIENT_CONNECTED) {
+ if (nbd_reply_is_simple(reply) ||
+ qatomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) {
goto break_loop;
}
return 0;
}
+static void nbd_yank(void *opaque)
+{
+ BlockDriverState *bs = opaque;
+ BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
+
+ qatomic_store_release(&s->state, NBD_CLIENT_QUIT);
+ qio_channel_shutdown(QIO_CHANNEL(s->sioc), QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
+}
+
static void nbd_client_close(BlockDriverState *bs)
{
BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
nbd_teardown_connection(bs);
}
-static QIOChannelSocket *nbd_establish_connection(SocketAddress *saddr,
- Error **errp)
+static int nbd_establish_connection(BlockDriverState *bs,
+ SocketAddress *saddr,
+ Error **errp)
{
ERRP_GUARD();
- QIOChannelSocket *sioc;
+ BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
- sioc = qio_channel_socket_new();
- qio_channel_set_name(QIO_CHANNEL(sioc), "nbd-client");
+ s->sioc = qio_channel_socket_new();
+ qio_channel_set_name(QIO_CHANNEL(s->sioc), "nbd-client");
- qio_channel_socket_connect_sync(sioc, saddr, errp);
+ qio_channel_socket_connect_sync(s->sioc, saddr, errp);
if (*errp) {
- object_unref(OBJECT(sioc));
- return NULL;
+ object_unref(OBJECT(s->sioc));
+ s->sioc = NULL;
+ return -1;
}
- qio_channel_set_delay(QIO_CHANNEL(sioc), false);
+ yank_register_function(BLOCKDEV_YANK_INSTANCE(bs->node_name), nbd_yank, bs);
+ qio_channel_set_delay(QIO_CHANNEL(s->sioc), false);
- return sioc;
+ return 0;
}
-/* nbd_client_handshake takes ownership on sioc. On failure it is unref'ed. */
-static int nbd_client_handshake(BlockDriverState *bs, QIOChannelSocket *sioc,
- Error **errp)
+/* nbd_client_handshake takes ownership on s->sioc. On failure it's unref'ed. */
+static int nbd_client_handshake(BlockDriverState *bs, Error **errp)
{
BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
AioContext *aio_context = bdrv_get_aio_context(bs);
int ret;
trace_nbd_client_handshake(s->export);
-
- s->sioc = sioc;
-
- qio_channel_set_blocking(QIO_CHANNEL(sioc), false, NULL);
- qio_channel_attach_aio_context(QIO_CHANNEL(sioc), aio_context);
+ qio_channel_set_blocking(QIO_CHANNEL(s->sioc), false, NULL);
+ qio_channel_attach_aio_context(QIO_CHANNEL(s->sioc), aio_context);
s->info.request_sizes = true;
s->info.structured_reply = true;
s->info.base_allocation = true;
s->info.x_dirty_bitmap = g_strdup(s->x_dirty_bitmap);
s->info.name = g_strdup(s->export ?: "");
- ret = nbd_receive_negotiate(aio_context, QIO_CHANNEL(sioc), s->tlscreds,
+ ret = nbd_receive_negotiate(aio_context, QIO_CHANNEL(s->sioc), s->tlscreds,
s->hostname, &s->ioc, &s->info, errp);
g_free(s->info.x_dirty_bitmap);
g_free(s->info.name);
if (ret < 0) {
- object_unref(OBJECT(sioc));
+ yank_unregister_function(BLOCKDEV_YANK_INSTANCE(bs->node_name),
+ nbd_yank, bs);
+ object_unref(OBJECT(s->sioc));
s->sioc = NULL;
return ret;
}
- if (s->x_dirty_bitmap && !s->info.base_allocation) {
- error_setg(errp, "requested x-dirty-bitmap %s not found",
- s->x_dirty_bitmap);
- ret = -EINVAL;
- goto fail;
+ if (s->x_dirty_bitmap) {
+ if (!s->info.base_allocation) {
+ error_setg(errp, "requested x-dirty-bitmap %s not found",
+ s->x_dirty_bitmap);
+ ret = -EINVAL;
+ goto fail;
+ }
+ if (strcmp(s->x_dirty_bitmap, "qemu:allocation-depth") == 0) {
+ s->alloc_depth = true;
+ }
}
if (s->info.flags & NBD_FLAG_READ_ONLY) {
ret = bdrv_apply_auto_read_only(bs, "NBD export is read-only", errp);
}
if (!s->ioc) {
- s->ioc = QIO_CHANNEL(sioc);
+ s->ioc = QIO_CHANNEL(s->sioc);
object_ref(OBJECT(s->ioc));
}
{
NBDRequest request = { .type = NBD_CMD_DISC };
- nbd_send_request(s->ioc ?: QIO_CHANNEL(sioc), &request);
+ nbd_send_request(s->ioc ?: QIO_CHANNEL(s->sioc), &request);
- object_unref(OBJECT(sioc));
+ yank_unregister_function(BLOCKDEV_YANK_INSTANCE(bs->node_name),
+ nbd_yank, bs);
+ object_unref(OBJECT(s->sioc));
s->sioc = NULL;
return ret;
{
int ret;
BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
- QIOChannelSocket *sioc;
ret = nbd_process_options(bs, options, errp);
if (ret < 0) {
qemu_co_mutex_init(&s->send_mutex);
qemu_co_queue_init(&s->free_sema);
+ if (!yank_register_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name), errp)) {
+ return -EEXIST;
+ }
+
/*
* establish TCP connection, return error if it fails
* TODO: Configurable retry-until-timeout behaviour.
*/
- sioc = nbd_establish_connection(s->saddr, errp);
- if (!sioc) {
+ if (nbd_establish_connection(bs, s->saddr, errp) < 0) {
+ yank_unregister_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name));
return -ECONNREFUSED;
}
- ret = nbd_client_handshake(bs, sioc, errp);
+ ret = nbd_client_handshake(bs, errp);
if (ret < 0) {
+ yank_unregister_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name));
nbd_clear_bdrvstate(s);
return ret;
}
BDRVNBDState *s = bs->opaque;
nbd_client_close(bs);
+ yank_unregister_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name));
nbd_clear_bdrvstate(s);
}
NULL
};
+static void nbd_cancel_in_flight(BlockDriverState *bs)
+{
+ BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
+
+ reconnect_delay_timer_del(s);
+
+ if (s->state == NBD_CLIENT_CONNECTING_WAIT) {
+ s->state = NBD_CLIENT_CONNECTING_NOWAIT;
+ qemu_co_queue_restart_all(&s->free_sema);
+ }
+}
+
static BlockDriver bdrv_nbd = {
.format_name = "nbd",
.protocol_name = "nbd",
.bdrv_co_block_status = nbd_client_co_block_status,
.bdrv_dirname = nbd_dirname,
.strong_runtime_opts = nbd_strong_runtime_opts,
+ .bdrv_cancel_in_flight = nbd_cancel_in_flight,
};
static BlockDriver bdrv_nbd_tcp = {
.bdrv_co_block_status = nbd_client_co_block_status,
.bdrv_dirname = nbd_dirname,
.strong_runtime_opts = nbd_strong_runtime_opts,
+ .bdrv_cancel_in_flight = nbd_cancel_in_flight,
};
static BlockDriver bdrv_nbd_unix = {
.bdrv_co_block_status = nbd_client_co_block_status,
.bdrv_dirname = nbd_dirname,
.strong_runtime_opts = nbd_strong_runtime_opts,
+ .bdrv_cancel_in_flight = nbd_cancel_in_flight,
};
static void bdrv_nbd_init(void)
projects / mirror_qemu.git / blobdiff