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;
}
int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset,
uint64_t bytes, QEMUIOVector *qiov, int flags)
{
NBDClientSession *client = nbd_get_client_session(bs);
NBDRequest request = {
.type = NBD_CMD_WRITE,
.from = offset,
.len = bytes,
};
NBDReply reply;
ssize_t ret;
if (flags & BDRV_REQ_FUA) {
assert(client->nbdflags & NBD_FLAG_SEND_FUA);
request.flags |= NBD_CMD_FLAG_FUA;
}
assert(bytes <= NBD_MAX_BUFFER_SIZE);
ret = nbd_co_send_request(bs, &request, qiov);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, NULL);
}
nbd_coroutine_end(bs, &request);
return -reply.error;
}
int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes)
{
NBDClientSession *client = nbd_get_client_session(bs);
NBDRequest request = {
.type = NBD_CMD_TRIM,
.from = offset,
.len = bytes,
};
NBDReply reply;
ssize_t ret;
if (!(client->nbdflags & NBD_FLAG_SEND_TRIM)) {
return 0;
}
ret = nbd_co_send_request(bs, &request, NULL);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, NULL);
}
nbd_coroutine_end(bs, &request);
return -reply.error;
}
void nbd_client_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
NBDClientSession *client = nbd_get_client_session(bs);
qio_channel_attach_aio_context(QIO_CHANNEL(client->ioc), new_context);
aio_co_schedule(new_context, client->read_reply_co);
}
static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, QEMUIOVector *qiov,
int offset)
{
NbdClientSession *client = nbd_get_client_session(bs);
struct nbd_request request = { .type = NBD_CMD_WRITE };
struct nbd_reply reply;
ssize_t ret;
if (!bdrv_enable_write_cache(bs) &&
(client->nbdflags & NBD_FLAG_SEND_FUA)) {
request.type |= NBD_CMD_FLAG_FUA;
}
request.from = sector_num * 512;
request.len = nb_sectors * 512;
nbd_coroutine_start(client, &request);
ret = nbd_co_send_request(bs, &request, qiov, offset);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, NULL, 0);
}
nbd_coroutine_end(client, &request);
return -reply.error;
}
int nbd_client_co_flush(BlockDriverState *bs)
{
NbdClientSession *client = nbd_get_client_session(bs);
struct nbd_request request = { .type = NBD_CMD_FLUSH };
struct nbd_reply reply;
ssize_t ret;
if (!(client->nbdflags & NBD_FLAG_SEND_FLUSH)) {
return 0;
}
if (client->nbdflags & NBD_FLAG_SEND_FUA) {
request.type |= NBD_CMD_FLAG_FUA;
}
request.from = 0;
request.len = 0;
nbd_coroutine_start(client, &request);
ret = nbd_co_send_request(bs, &request, NULL, 0);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, NULL, 0);
}
nbd_coroutine_end(client, &request);
return -reply.error;
}
int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
int nb_sectors)
{
NbdClientSession *client = nbd_get_client_session(bs);
struct nbd_request request = { .type = NBD_CMD_TRIM };
struct nbd_reply reply;
ssize_t ret;
if (!(client->nbdflags & NBD_FLAG_SEND_TRIM)) {
return 0;
}
request.from = sector_num * 512;
request.len = nb_sectors * 512;
nbd_coroutine_start(client, &request);
ret = nbd_co_send_request(bs, &request, NULL, 0);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, NULL, 0);
}
nbd_coroutine_end(client, &request);
return -reply.error;
}
int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset,
uint64_t bytes, QEMUIOVector *qiov, int flags)
{
NbdClientSession *client = nbd_get_client_session(bs);
struct nbd_request request = {
.type = NBD_CMD_READ,
.from = offset,
.len = bytes,
};
struct nbd_reply reply;
ssize_t ret;
assert(bytes <= NBD_MAX_BUFFER_SIZE);
assert(!flags);
nbd_coroutine_start(client, &request);
ret = nbd_co_send_request(bs, &request, NULL);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, qiov);
}
nbd_coroutine_end(client, &request);
return -reply.error;
}
int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
int bytes, BdrvRequestFlags flags)
{
ssize_t ret;
NBDClientSession *client = nbd_get_client_session(bs);
NBDRequest request = {
.type = NBD_CMD_WRITE_ZEROES,
.from = offset,
.len = bytes,
};
NBDReply reply;
if (!(client->nbdflags & NBD_FLAG_SEND_WRITE_ZEROES)) {
return -ENOTSUP;
}
if (flags & BDRV_REQ_FUA) {
assert(client->nbdflags & NBD_FLAG_SEND_FUA);
request.flags |= NBD_CMD_FLAG_FUA;
}
if (!(flags & BDRV_REQ_MAY_UNMAP)) {
request.flags |= NBD_CMD_FLAG_NO_HOLE;
}
ret = nbd_co_send_request(bs, &request, NULL);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, NULL);
}
nbd_coroutine_end(bs, &request);
return -reply.error;
}
static void nbd_teardown_connection(BlockDriverState *bs)
{
NbdClientSession *client = nbd_get_client_session(bs);
/* finish any pending coroutines */
shutdown(client->sock, 2);
nbd_recv_coroutines_enter_all(client);
nbd_client_detach_aio_context(bs);
closesocket(client->sock);
client->sock = -1;
}
static void nbd_recv_coroutines_enter_all(BlockDriverState *bs)
{
NBDClientSession *s = nbd_get_client_session(bs);
int i;
for (i = 0; i < MAX_NBD_REQUESTS; i++) {
if (s->recv_coroutine[i]) {
qemu_coroutine_enter(s->recv_coroutine[i]);
}
}
BDRV_POLL_WHILE(bs, s->read_reply_co);
}
void nbd_client_close(BlockDriverState *bs)
{
NBDClientSession *client = nbd_get_client_session(bs);
NBDRequest request = { .type = NBD_CMD_DISC };
if (client->ioc == NULL) {
return;
}
nbd_send_request(client->ioc, &request);
nbd_teardown_connection(bs);
}
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 nbd_coroutine_end(BlockDriverState *bs,
NBDRequest *request)
{
NBDClientSession *s = nbd_get_client_session(bs);
int i = HANDLE_TO_INDEX(s, request->handle);
s->recv_coroutine[i] = NULL;
s->in_flight--;
qemu_co_queue_next(&s->free_sema);
/* Kick the read_reply_co to get the next reply. */
if (s->read_reply_co) {
aio_co_wake(s->read_reply_co);
}
}
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 int nbd_co_send_request(BlockDriverState *bs,
NBDRequest *request,
QEMUIOVector *qiov)
{
NBDClientSession *s = nbd_get_client_session(bs);
int rc, ret, i;
qemu_co_mutex_lock(&s->send_mutex);
while (s->in_flight == MAX_NBD_REQUESTS) {
qemu_co_queue_wait(&s->free_sema, &s->send_mutex);
}
s->in_flight++;
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;
}
if (qiov) {
qio_channel_set_cork(s->ioc, true);
rc = nbd_send_request(s->ioc, request);
if (rc >= 0) {
ret = nbd_rwv(s->ioc, qiov->iov, qiov->niov, request->len, false,
NULL);
if (ret != request->len) {
rc = -EIO;
}
}
qio_channel_set_cork(s->ioc, false);
} else {
rc = nbd_send_request(s->ioc, request);
}
qemu_co_mutex_unlock(&s->send_mutex);
return rc;
}
static void nbd_reply_ready(void *opaque)
{
BlockDriverState *bs = opaque;
NbdClientSession *s = nbd_get_client_session(bs);
uint64_t i;
int ret;
if (!s->ioc) { /* Already closed */
return;
}
if (s->reply.handle == 0) {
/* No reply already in flight. Fetch a header. It is possible
* that another thread has done the same thing in parallel, so
* the socket is not readable anymore.
*/
ret = nbd_receive_reply(s->ioc, &s->reply);
if (ret == -EAGAIN) {
return;
}
if (ret < 0) {
s->reply.handle = 0;
goto fail;
}
}
/* There's no need for a mutex on the receive side, because the
* handler acts as a synchronization point and ensures that only
* one coroutine is called until the reply finishes. */
i = HANDLE_TO_INDEX(s, s->reply.handle);
if (i >= MAX_NBD_REQUESTS) {
goto fail;
}
if (s->recv_coroutine[i]) {
qemu_coroutine_enter(s->recv_coroutine[i], NULL);
return;
}
fail:
nbd_teardown_connection(bs);
}
static void nbd_teardown_connection(BlockDriverState *bs)
{
NBDClientSession *client = nbd_get_client_session(bs);
if (!client->ioc) { /* Already closed */
return;
}
/* finish any pending coroutines */
qio_channel_shutdown(client->ioc,
QIO_CHANNEL_SHUTDOWN_BOTH,
NULL);
BDRV_POLL_WHILE(bs, client->read_reply_co);
nbd_client_detach_aio_context(bs);
object_unref(OBJECT(client->sioc));
client->sioc = NULL;
object_unref(OBJECT(client->ioc));
client->ioc = NULL;
}
static int nbd_co_request(BlockDriverState *bs,
NBDRequest *request,
QEMUIOVector *qiov)
{
NBDClientSession *client = nbd_get_client_session(bs);
NBDReply reply;
int ret;
assert(!qiov || request->type == NBD_CMD_WRITE ||
request->type == NBD_CMD_READ);
ret = nbd_co_send_request(bs, request,
request->type == NBD_CMD_WRITE ? qiov : NULL);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, request, &reply,
request->type == NBD_CMD_READ ? qiov : NULL);
}
return -reply.error;
}
static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, QEMUIOVector *qiov,
int offset)
{
NbdClientSession *client = nbd_get_client_session(bs);
struct nbd_request request = { .type = NBD_CMD_READ };
struct nbd_reply reply;
ssize_t ret;
request.from = sector_num * 512;
request.len = nb_sectors * 512;
nbd_coroutine_start(client, &request);
ret = nbd_co_send_request(bs, &request, NULL, 0);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, qiov, offset);
}
nbd_coroutine_end(client, &request);
return -reply.error;
}
static void nbd_restart_write(void *opaque)
{
BlockDriverState *bs = opaque;
qemu_coroutine_enter(nbd_get_client_session(bs)->send_coroutine, NULL);
}
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->ioc == NULL) {
return;
}
nbd_send_request(client->ioc, &request);
nbd_teardown_connection(bs);
}
int nbd_client_init(BlockDriverState *bs,
QIOChannelSocket *sioc,
const char *export,
QCryptoTLSCreds *tlscreds,
const char *hostname,
Error **errp)
{
NbdClientSession *client = nbd_get_client_session(bs);
int ret;
/* NBD handshake */
logout("session init %s\n", export);
qio_channel_set_blocking(QIO_CHANNEL(sioc), true, NULL);
ret = nbd_receive_negotiate(QIO_CHANNEL(sioc), export,
&client->nbdflags,
tlscreds, hostname,
&client->ioc,
&client->size, errp);
if (ret < 0) {
logout("Failed to negotiate with the NBD server\n");
return ret;
}
qemu_co_mutex_init(&client->send_mutex);
qemu_co_mutex_init(&client->free_sema);
client->sioc = sioc;
object_ref(OBJECT(client->sioc));
if (!client->ioc) {
client->ioc = QIO_CHANNEL(sioc);
object_ref(OBJECT(client->ioc));
}
/* Now that we're connected, set the socket to be non-blocking and
* kick the reply mechanism. */
qio_channel_set_blocking(QIO_CHANNEL(sioc), false, NULL);
nbd_client_attach_aio_context(bs, bdrv_get_aio_context(bs));
logout("Established connection with NBD server\n");
return 0;
}
void nbd_client_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
aio_set_fd_handler(new_context, nbd_get_client_session(bs)->sock,
false, nbd_reply_ready, NULL, bs);
}
void nbd_client_detach_aio_context(BlockDriverState *bs)
{
aio_set_fd_handler(bdrv_get_aio_context(bs),
nbd_get_client_session(bs)->sock,
false, NULL, NULL, NULL);
}
static int nbd_co_send_request(BlockDriverState *bs,
NBDRequest *request,
QEMUIOVector *qiov)
{
NBDClientSession *s = nbd_get_client_session(bs);
int rc, i;
qemu_co_mutex_lock(&s->send_mutex);
while (s->in_flight == MAX_NBD_REQUESTS) {
qemu_co_queue_wait(&s->free_sema, &s->send_mutex);
}
s->in_flight++;
for (i = 0; i < MAX_NBD_REQUESTS; i++) {
if (s->requests[i].coroutine == NULL) {
break;
}
}
g_assert(qemu_in_coroutine());
assert(i < MAX_NBD_REQUESTS);
s->requests[i].coroutine = qemu_coroutine_self();
s->requests[i].receiving = false;
request->handle = INDEX_TO_HANDLE(s, i);
if (s->quit) {
rc = -EIO;
goto err;
}
if (!s->ioc) {
rc = -EPIPE;
goto err;
}
if (qiov) {
qio_channel_set_cork(s->ioc, true);
rc = nbd_send_request(s->ioc, request);
if (rc >= 0 && !s->quit) {
assert(request->len == iov_size(qiov->iov, qiov->niov));
if (qio_channel_writev_all(s->ioc, qiov->iov, qiov->niov,
NULL) < 0) {
rc = -EIO;
}
}
qio_channel_set_cork(s->ioc, false);
} else {
rc = nbd_send_request(s->ioc, request);
}
err:
if (rc < 0) {
s->quit = true;
s->requests[i].coroutine = NULL;
s->in_flight--;
qemu_co_queue_next(&s->free_sema);
}
qemu_co_mutex_unlock(&s->send_mutex);
return rc;
}
return;
}
nbd_send_request(client->ioc, &request);
nbd_teardown_connection(bs);
}
int nbd_client_init(BlockDriverState *bs,
QIOChannelSocket *sioc,
const char *export,
QCryptoTLSCreds *tlscreds,
const char *hostname,
Error **errp)
{
NBDClientSession *client = nbd_get_client_session(bs);
int ret;
/* NBD handshake */
logout("session init %s\n", export);
qio_channel_set_blocking(QIO_CHANNEL(sioc), true, NULL);
ret = nbd_receive_negotiate(QIO_CHANNEL(sioc), export,
&client->nbdflags,
tlscreds, hostname,
&client->ioc,
&client->size, errp);
if (ret < 0) {
logout("Failed to negotiate with the NBD server\n");
return ret;
}
void nbd_client_detach_aio_context(BlockDriverState *bs)
{
NBDClientSession *client = nbd_get_client_session(bs);
qio_channel_detach_aio_context(QIO_CHANNEL(client->ioc));
}