/*
+ * Copyright (C) 2016 Red Hat, Inc.
*
* Network Block Device Server Side
case EFBIG:
case ENOSPC:
return NBD_ENOSPC;
+ case ESHUTDOWN:
+ return NBD_ESHUTDOWN;
case EINVAL:
default:
return NBD_EINVAL;
/* Definitions for opaque data types */
-typedef struct NBDRequest NBDRequest;
+typedef struct NBDRequestData NBDRequestData;
-struct NBDRequest {
- QSIMPLEQ_ENTRY(NBDRequest) entry;
+struct NBDRequestData {
+ QSIMPLEQ_ENTRY(NBDRequestData) entry;
NBDClient *client;
uint8_t *data;
+ bool complete;
};
struct NBDExport {
BlockBackend *blk;
char *name;
+ char *description;
off_t dev_offset;
off_t size;
- uint32_t nbdflags;
+ uint16_t nbdflags;
QTAILQ_HEAD(, NBDClient) clients;
QTAILQ_ENTRY(NBDExport) next;
AioContext *ctx;
+ BlockBackend *eject_notifier_blk;
Notifier eject_notifier;
};
int refcount;
void (*close)(NBDClient *client);
+ bool no_zeroes;
NBDExport *exp;
QCryptoTLSCreds *tlscreds;
char *tlsaclname;
CoMutex send_lock;
Coroutine *send_coroutine;
- bool can_read;
-
QTAILQ_ENTRY(NBDClient) next;
int nb_requests;
bool closing;
/* That's all folks */
-static void nbd_set_handlers(NBDClient *client);
-static void nbd_unset_handlers(NBDClient *client);
-static void nbd_update_can_read(NBDClient *client);
+static void nbd_client_receive_next_request(NBDClient *client);
static gboolean nbd_negotiate_continue(QIOChannel *ioc,
GIOCondition condition,
void *opaque)
{
- qemu_coroutine_enter(opaque, NULL);
+ qemu_coroutine_enter(opaque);
return TRUE;
}
}
-static ssize_t nbd_negotiate_write(QIOChannel *ioc, void *buffer, size_t size)
+static ssize_t nbd_negotiate_write(QIOChannel *ioc, const void *buffer,
+ size_t size)
{
ssize_t ret;
guint watch;
*/
-static int nbd_negotiate_send_rep(QIOChannel *ioc, uint32_t type, uint32_t opt)
+/* Send a reply header, including length, but no payload.
+ * Return -errno on error, 0 on success. */
+static int nbd_negotiate_send_rep_len(QIOChannel *ioc, uint32_t type,
+ uint32_t opt, uint32_t len)
{
uint64_t magic;
- uint32_t len;
- TRACE("Reply opt=%x type=%x", type, opt);
+ TRACE("Reply opt=%" PRIx32 " type=%" PRIx32 " len=%" PRIu32,
+ type, opt, len);
magic = cpu_to_be64(NBD_REP_MAGIC);
if (nbd_negotiate_write(ioc, &magic, sizeof(magic)) != sizeof(magic)) {
LOG("write failed (rep type)");
return -EINVAL;
}
- len = cpu_to_be32(0);
+ len = cpu_to_be32(len);
if (nbd_negotiate_write(ioc, &len, sizeof(len)) != sizeof(len)) {
LOG("write failed (rep data length)");
return -EINVAL;
return 0;
}
-static int nbd_negotiate_send_rep_list(QIOChannel *ioc, NBDExport *exp)
+/* Send a reply header with default 0 length.
+ * Return -errno on error, 0 on success. */
+static int nbd_negotiate_send_rep(QIOChannel *ioc, uint32_t type, uint32_t opt)
{
- uint64_t magic, name_len;
- uint32_t opt, type, len;
+ return nbd_negotiate_send_rep_len(ioc, type, opt, 0);
+}
- TRACE("Advertizing export name '%s'", exp->name ? exp->name : "");
- name_len = strlen(exp->name);
- magic = cpu_to_be64(NBD_REP_MAGIC);
- if (nbd_negotiate_write(ioc, &magic, sizeof(magic)) != sizeof(magic)) {
- LOG("write failed (magic)");
- return -EINVAL;
- }
- opt = cpu_to_be32(NBD_OPT_LIST);
- if (nbd_negotiate_write(ioc, &opt, sizeof(opt)) != sizeof(opt)) {
- LOG("write failed (opt)");
- return -EINVAL;
+/* Send an error reply.
+ * Return -errno on error, 0 on success. */
+static int GCC_FMT_ATTR(4, 5)
+nbd_negotiate_send_rep_err(QIOChannel *ioc, uint32_t type,
+ uint32_t opt, const char *fmt, ...)
+{
+ va_list va;
+ char *msg;
+ int ret;
+ size_t len;
+
+ va_start(va, fmt);
+ msg = g_strdup_vprintf(fmt, va);
+ va_end(va);
+ len = strlen(msg);
+ assert(len < 4096);
+ TRACE("sending error message \"%s\"", msg);
+ ret = nbd_negotiate_send_rep_len(ioc, type, opt, len);
+ if (ret < 0) {
+ goto out;
}
- type = cpu_to_be32(NBD_REP_SERVER);
- if (nbd_negotiate_write(ioc, &type, sizeof(type)) != sizeof(type)) {
- LOG("write failed (reply type)");
- return -EINVAL;
+ if (nbd_negotiate_write(ioc, msg, len) != len) {
+ LOG("write failed (error message)");
+ ret = -EIO;
+ } else {
+ ret = 0;
}
- len = cpu_to_be32(name_len + sizeof(len));
- if (nbd_negotiate_write(ioc, &len, sizeof(len)) != sizeof(len)) {
- LOG("write failed (length)");
- return -EINVAL;
+out:
+ g_free(msg);
+ return ret;
+}
+
+/* Send a single NBD_REP_SERVER reply to NBD_OPT_LIST, including payload.
+ * Return -errno on error, 0 on success. */
+static int nbd_negotiate_send_rep_list(QIOChannel *ioc, NBDExport *exp)
+{
+ size_t name_len, desc_len;
+ uint32_t len;
+ const char *name = exp->name ? exp->name : "";
+ const char *desc = exp->description ? exp->description : "";
+ int rc;
+
+ TRACE("Advertising export name '%s' description '%s'", name, desc);
+ name_len = strlen(name);
+ desc_len = strlen(desc);
+ len = name_len + desc_len + sizeof(len);
+ rc = nbd_negotiate_send_rep_len(ioc, NBD_REP_SERVER, NBD_OPT_LIST, len);
+ if (rc < 0) {
+ return rc;
}
+
len = cpu_to_be32(name_len);
if (nbd_negotiate_write(ioc, &len, sizeof(len)) != sizeof(len)) {
- LOG("write failed (length)");
+ LOG("write failed (name length)");
+ return -EINVAL;
+ }
+ if (nbd_negotiate_write(ioc, name, name_len) != name_len) {
+ LOG("write failed (name buffer)");
return -EINVAL;
}
- if (nbd_negotiate_write(ioc, exp->name, name_len) != name_len) {
- LOG("write failed (buffer)");
+ if (nbd_negotiate_write(ioc, desc, desc_len) != desc_len) {
+ LOG("write failed (description buffer)");
return -EINVAL;
}
return 0;
}
+/* Process the NBD_OPT_LIST command, with a potential series of replies.
+ * Return -errno on error, 0 on success. */
static int nbd_negotiate_handle_list(NBDClient *client, uint32_t length)
{
NBDExport *exp;
if (nbd_negotiate_drop_sync(client->ioc, length) != length) {
return -EIO;
}
- return nbd_negotiate_send_rep(client->ioc,
- NBD_REP_ERR_INVALID, NBD_OPT_LIST);
+ return nbd_negotiate_send_rep_err(client->ioc,
+ NBD_REP_ERR_INVALID, NBD_OPT_LIST,
+ "OPT_LIST should not have length");
}
/* For each export, send a NBD_REP_SERVER reply. */
static int nbd_negotiate_handle_export_name(NBDClient *client, uint32_t length)
{
int rc = -EINVAL;
- char name[256];
+ char name[NBD_MAX_NAME_SIZE + 1];
/* Client sends:
[20 .. xx] export name (length bytes)
*/
TRACE("Checking length");
- if (length > 255) {
+ if (length >= sizeof(name)) {
LOG("Bad length received");
goto fail;
}
return rc;
}
-
+/* Handle NBD_OPT_STARTTLS. Return NULL to drop connection, or else the
+ * new channel for all further (now-encrypted) communication. */
static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client,
uint32_t length)
{
if (nbd_negotiate_drop_sync(ioc, length) != length) {
return NULL;
}
- nbd_negotiate_send_rep(ioc, NBD_REP_ERR_INVALID, NBD_OPT_STARTTLS);
+ nbd_negotiate_send_rep_err(ioc, NBD_REP_ERR_INVALID, NBD_OPT_STARTTLS,
+ "OPT_STARTTLS should not have length");
return NULL;
}
- nbd_negotiate_send_rep(client->ioc, NBD_REP_ACK, NBD_OPT_STARTTLS);
+ if (nbd_negotiate_send_rep(client->ioc, NBD_REP_ACK,
+ NBD_OPT_STARTTLS) < 0) {
+ return NULL;
+ }
tioc = qio_channel_tls_new_server(ioc,
client->tlscreds,
return NULL;
}
+ qio_channel_set_name(QIO_CHANNEL(tioc), "nbd-server-tls");
TRACE("Starting TLS handshake");
data.loop = g_main_loop_new(g_main_context_default(), FALSE);
qio_channel_tls_handshake(tioc,
}
+/* Process all NBD_OPT_* client option commands.
+ * Return -errno on error, 0 on success. */
static int nbd_negotiate_options(NBDClient *client)
{
uint32_t flags;
TRACE("Checking client flags");
be32_to_cpus(&flags);
if (flags & NBD_FLAG_C_FIXED_NEWSTYLE) {
- TRACE("Support supports fixed newstyle handshake");
+ TRACE("Client supports fixed newstyle handshake");
fixedNewstyle = true;
flags &= ~NBD_FLAG_C_FIXED_NEWSTYLE;
}
+ if (flags & NBD_FLAG_C_NO_ZEROES) {
+ TRACE("Client supports no zeroes at handshake end");
+ client->no_zeroes = true;
+ flags &= ~NBD_FLAG_C_NO_ZEROES;
+ }
if (flags != 0) {
- TRACE("Unknown client flags 0x%x received", flags);
+ TRACE("Unknown client flags 0x%" PRIx32 " received", flags);
return -EIO;
}
}
length = be32_to_cpu(length);
- TRACE("Checking option 0x%x", clientflags);
+ TRACE("Checking option 0x%" PRIx32, clientflags);
if (client->tlscreds &&
client->ioc == (QIOChannel *)client->sioc) {
QIOChannel *tioc;
if (!fixedNewstyle) {
- TRACE("Unsupported option 0x%x", clientflags);
+ TRACE("Unsupported option 0x%" PRIx32, clientflags);
return -EINVAL;
}
switch (clientflags) {
return -EINVAL;
default:
- TRACE("Option 0x%x not permitted before TLS", clientflags);
if (nbd_negotiate_drop_sync(client->ioc, length) != length) {
return -EIO;
}
- nbd_negotiate_send_rep(client->ioc, NBD_REP_ERR_TLS_REQD,
- clientflags);
+ ret = nbd_negotiate_send_rep_err(client->ioc,
+ NBD_REP_ERR_TLS_REQD,
+ clientflags,
+ "Option 0x%" PRIx32
+ "not permitted before TLS",
+ clientflags);
+ if (ret < 0) {
+ return ret;
+ }
+ /* Let the client keep trying, unless they asked to quit */
+ if (clientflags == NBD_OPT_ABORT) {
+ return -EINVAL;
+ }
break;
}
} else if (fixedNewstyle) {
break;
case NBD_OPT_ABORT:
+ /* NBD spec says we must try to reply before
+ * disconnecting, but that we must also tolerate
+ * guests that don't wait for our reply. */
+ nbd_negotiate_send_rep(client->ioc, NBD_REP_ACK, clientflags);
return -EINVAL;
case NBD_OPT_EXPORT_NAME:
return -EIO;
}
if (client->tlscreds) {
- TRACE("TLS already enabled");
- nbd_negotiate_send_rep(client->ioc, NBD_REP_ERR_INVALID,
- clientflags);
+ ret = nbd_negotiate_send_rep_err(client->ioc,
+ NBD_REP_ERR_INVALID,
+ clientflags,
+ "TLS already enabled");
} else {
- TRACE("TLS not configured");
- nbd_negotiate_send_rep(client->ioc, NBD_REP_ERR_POLICY,
- clientflags);
+ ret = nbd_negotiate_send_rep_err(client->ioc,
+ NBD_REP_ERR_POLICY,
+ clientflags,
+ "TLS not configured");
+ }
+ if (ret < 0) {
+ return ret;
}
break;
default:
- TRACE("Unsupported option 0x%x", clientflags);
if (nbd_negotiate_drop_sync(client->ioc, length) != length) {
return -EIO;
}
- nbd_negotiate_send_rep(client->ioc, NBD_REP_ERR_UNSUP,
- clientflags);
+ ret = nbd_negotiate_send_rep_err(client->ioc,
+ NBD_REP_ERR_UNSUP,
+ clientflags,
+ "Unsupported option 0x%"
+ PRIx32,
+ clientflags);
+ if (ret < 0) {
+ return ret;
+ }
break;
}
} else {
return nbd_negotiate_handle_export_name(client, length);
default:
- TRACE("Unsupported option 0x%x", clientflags);
+ TRACE("Unsupported option 0x%" PRIx32, clientflags);
return -EINVAL;
}
}
NBDClient *client = data->client;
char buf[8 + 8 + 8 + 128];
int rc;
- const int myflags = (NBD_FLAG_HAS_FLAGS | NBD_FLAG_SEND_TRIM |
- NBD_FLAG_SEND_FLUSH | NBD_FLAG_SEND_FUA);
+ const uint16_t myflags = (NBD_FLAG_HAS_FLAGS | NBD_FLAG_SEND_TRIM |
+ NBD_FLAG_SEND_FLUSH | NBD_FLAG_SEND_FUA |
+ NBD_FLAG_SEND_WRITE_ZEROES);
bool oldStyle;
+ size_t len;
/* Old style negotiation header without options
[ 0 .. 7] passwd ("NBDMAGIC")
....options sent....
[18 .. 25] size
[26 .. 27] export flags
- [28 .. 151] reserved (0)
+ [28 .. 151] reserved (0, omit if no_zeroes)
*/
qio_channel_set_blocking(client->ioc, false, NULL);
oldStyle = client->exp != NULL && !client->tlscreds;
if (oldStyle) {
- assert ((client->exp->nbdflags & ~65535) == 0);
+ TRACE("advertising size %" PRIu64 " and flags %x",
+ client->exp->size, client->exp->nbdflags | myflags);
stq_be_p(buf + 8, NBD_CLIENT_MAGIC);
stq_be_p(buf + 16, client->exp->size);
stw_be_p(buf + 26, client->exp->nbdflags | myflags);
} else {
stq_be_p(buf + 8, NBD_OPTS_MAGIC);
- stw_be_p(buf + 16, NBD_FLAG_FIXED_NEWSTYLE);
+ stw_be_p(buf + 16, NBD_FLAG_FIXED_NEWSTYLE | NBD_FLAG_NO_ZEROES);
}
if (oldStyle) {
goto fail;
}
- assert ((client->exp->nbdflags & ~65535) == 0);
+ TRACE("advertising size %" PRIu64 " and flags %x",
+ client->exp->size, client->exp->nbdflags | myflags);
stq_be_p(buf + 18, client->exp->size);
stw_be_p(buf + 26, client->exp->nbdflags | myflags);
- if (nbd_negotiate_write(client->ioc, buf + 18, sizeof(buf) - 18) !=
- sizeof(buf) - 18) {
+ len = client->no_zeroes ? 10 : sizeof(buf) - 18;
+ if (nbd_negotiate_write(client->ioc, buf + 18, len) != len) {
LOG("write failed");
goto fail;
}
return rc;
}
-#ifdef __linux__
-
-int nbd_disconnect(int fd)
-{
- ioctl(fd, NBD_CLEAR_QUE);
- ioctl(fd, NBD_DISCONNECT);
- ioctl(fd, NBD_CLEAR_SOCK);
- return 0;
-}
-
-#else
-
-int nbd_disconnect(int fd)
-{
- return -ENOTSUP;
-}
-#endif
-
-static ssize_t nbd_receive_request(QIOChannel *ioc, struct nbd_request *request)
+static ssize_t nbd_receive_request(QIOChannel *ioc, NBDRequest *request)
{
uint8_t buf[NBD_REQUEST_SIZE];
uint32_t magic;
/* Request
[ 0 .. 3] magic (NBD_REQUEST_MAGIC)
- [ 4 .. 7] type (0 == READ, 1 == WRITE)
+ [ 4 .. 5] flags (NBD_CMD_FLAG_FUA, ...)
+ [ 6 .. 7] type (NBD_CMD_READ, ...)
[ 8 .. 15] handle
[16 .. 23] from
[24 .. 27] len
*/
- magic = be32_to_cpup((uint32_t*)buf);
- request->type = be32_to_cpup((uint32_t*)(buf + 4));
- request->handle = be64_to_cpup((uint64_t*)(buf + 8));
- request->from = be64_to_cpup((uint64_t*)(buf + 16));
- request->len = be32_to_cpup((uint32_t*)(buf + 24));
+ magic = ldl_be_p(buf);
+ request->flags = lduw_be_p(buf + 4);
+ request->type = lduw_be_p(buf + 6);
+ request->handle = ldq_be_p(buf + 8);
+ request->from = ldq_be_p(buf + 16);
+ request->len = ldl_be_p(buf + 24);
- TRACE("Got request: "
- "{ magic = 0x%x, .type = %d, from = %" PRIu64" , len = %u }",
- magic, request->type, request->from, request->len);
+ TRACE("Got request: { magic = 0x%" PRIx32 ", .flags = %" PRIx16
+ ", .type = %" PRIx16 ", from = %" PRIu64 ", len = %" PRIu32 " }",
+ magic, request->flags, request->type, request->from, request->len);
if (magic != NBD_REQUEST_MAGIC) {
- LOG("invalid magic (got 0x%x)", magic);
+ LOG("invalid magic (got 0x%" PRIx32 ")", magic);
return -EINVAL;
}
return 0;
}
-static ssize_t nbd_send_reply(QIOChannel *ioc, struct nbd_reply *reply)
+static ssize_t nbd_send_reply(QIOChannel *ioc, NBDReply *reply)
{
uint8_t buf[NBD_REPLY_SIZE];
ssize_t ret;
reply->error = system_errno_to_nbd_errno(reply->error);
- TRACE("Sending response to client: { .error = %d, handle = %" PRIu64 " }",
+ TRACE("Sending response to client: { .error = %" PRId32
+ ", handle = %" PRIu64 " }",
reply->error, reply->handle);
/* Reply
*/
assert(client->closing);
- nbd_unset_handlers(client);
+ qio_channel_detach_aio_context(client->ioc);
object_unref(OBJECT(client->sioc));
object_unref(OBJECT(client->ioc));
if (client->tlscreds) {
}
}
-static NBDRequest *nbd_request_get(NBDClient *client)
+static NBDRequestData *nbd_request_get(NBDClient *client)
{
- NBDRequest *req;
+ NBDRequestData *req;
assert(client->nb_requests <= MAX_NBD_REQUESTS - 1);
client->nb_requests++;
- nbd_update_can_read(client);
- req = g_new0(NBDRequest, 1);
+ req = g_new0(NBDRequestData, 1);
nbd_client_get(client);
req->client = client;
return req;
}
-static void nbd_request_put(NBDRequest *req)
+static void nbd_request_put(NBDRequestData *req)
{
NBDClient *client = req->client;
g_free(req);
client->nb_requests--;
- nbd_update_can_read(client);
+ nbd_client_receive_next_request(client);
+
nbd_client_put(client);
}
exp->ctx = ctx;
QTAILQ_FOREACH(client, &exp->clients, next) {
- nbd_set_handlers(client);
+ qio_channel_attach_aio_context(client->ioc, ctx);
+ if (client->recv_coroutine) {
+ aio_co_schedule(ctx, client->recv_coroutine);
+ }
+ if (client->send_coroutine) {
+ aio_co_schedule(ctx, client->send_coroutine);
+ }
}
}
TRACE("Export %s: Detaching clients from AIO context %p\n", exp->name, exp->ctx);
QTAILQ_FOREACH(client, &exp->clients, next) {
- nbd_unset_handlers(client);
+ qio_channel_detach_aio_context(client->ioc);
}
exp->ctx = NULL;
nbd_export_close(exp);
}
-NBDExport *nbd_export_new(BlockBackend *blk, off_t dev_offset, off_t size,
- uint32_t nbdflags, void (*close)(NBDExport *),
+NBDExport *nbd_export_new(BlockDriverState *bs, off_t dev_offset, off_t size,
+ uint16_t nbdflags, void (*close)(NBDExport *),
+ bool writethrough, BlockBackend *on_eject_blk,
Error **errp)
{
+ BlockBackend *blk;
NBDExport *exp = g_malloc0(sizeof(NBDExport));
+ uint64_t perm;
+ int ret;
+
+ /* Don't allow resize while the NBD server is running, otherwise we don't
+ * care what happens with the node. */
+ perm = BLK_PERM_CONSISTENT_READ;
+ if ((nbdflags & NBD_FLAG_READ_ONLY) == 0) {
+ perm |= BLK_PERM_WRITE;
+ }
+ blk = blk_new(perm, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+ BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD);
+ ret = blk_insert_bs(blk, bs, errp);
+ if (ret < 0) {
+ goto fail;
+ }
+ blk_set_enable_write_cache(blk, !writethrough);
+
exp->refcount = 1;
QTAILQ_INIT(&exp->clients);
exp->blk = blk;
exp->close = close;
exp->ctx = blk_get_aio_context(blk);
- blk_ref(blk);
blk_add_aio_context_notifier(blk, blk_aio_attached, blk_aio_detach, exp);
- exp->eject_notifier.notify = nbd_eject_notifier;
- blk_add_remove_bs_notifier(blk, &exp->eject_notifier);
+ if (on_eject_blk) {
+ blk_ref(on_eject_blk);
+ exp->eject_notifier_blk = on_eject_blk;
+ exp->eject_notifier.notify = nbd_eject_notifier;
+ blk_add_remove_bs_notifier(on_eject_blk, &exp->eject_notifier);
+ }
/*
* NBD exports are used for non-shared storage migration. Make sure
return exp;
fail:
+ blk_unref(blk);
g_free(exp);
return NULL;
}
nbd_export_put(exp);
}
+void nbd_export_set_description(NBDExport *exp, const char *description)
+{
+ g_free(exp->description);
+ exp->description = g_strdup(description);
+}
+
void nbd_export_close(NBDExport *exp)
{
NBDClient *client, *next;
client_close(client);
}
nbd_export_set_name(exp, NULL);
+ nbd_export_set_description(exp, NULL);
nbd_export_put(exp);
}
if (--exp->refcount == 0) {
assert(exp->name == NULL);
+ assert(exp->description == NULL);
if (exp->close) {
exp->close(exp);
}
if (exp->blk) {
- notifier_remove(&exp->eject_notifier);
+ if (exp->eject_notifier_blk) {
+ notifier_remove(&exp->eject_notifier);
+ blk_unref(exp->eject_notifier_blk);
+ }
blk_remove_aio_context_notifier(exp->blk, blk_aio_attached,
blk_aio_detach, exp);
blk_unref(exp->blk);
}
}
-static ssize_t nbd_co_send_reply(NBDRequest *req, struct nbd_reply *reply,
+static ssize_t nbd_co_send_reply(NBDRequestData *req, NBDReply *reply,
int len)
{
NBDClient *client = req->client;
g_assert(qemu_in_coroutine());
qemu_co_mutex_lock(&client->send_lock);
client->send_coroutine = qemu_coroutine_self();
- nbd_set_handlers(client);
if (!len) {
rc = nbd_send_reply(client->ioc, reply);
}
client->send_coroutine = NULL;
- nbd_set_handlers(client);
qemu_co_mutex_unlock(&client->send_lock);
return rc;
}
-static ssize_t nbd_co_receive_request(NBDRequest *req, struct nbd_request *request)
+/* Collect a client request. Return 0 if request looks valid, -EAGAIN
+ * to keep trying the collection, -EIO to drop connection right away,
+ * and any other negative value to report an error to the client
+ * (although the caller may still need to disconnect after reporting
+ * the error). */
+static ssize_t nbd_co_receive_request(NBDRequestData *req,
+ NBDRequest *request)
{
NBDClient *client = req->client;
- uint32_t command;
ssize_t rc;
g_assert(qemu_in_coroutine());
- client->recv_coroutine = qemu_coroutine_self();
- nbd_update_can_read(client);
-
+ assert(client->recv_coroutine == qemu_coroutine_self());
rc = nbd_receive_request(client->ioc, request);
if (rc < 0) {
if (rc != -EAGAIN) {
goto out;
}
+ TRACE("Decoding type");
+
+ if (request->type != NBD_CMD_WRITE) {
+ /* No payload, we are ready to read the next request. */
+ req->complete = true;
+ }
+
+ if (request->type == NBD_CMD_DISC) {
+ /* Special case: we're going to disconnect without a reply,
+ * whether or not flags, from, or len are bogus */
+ TRACE("Request type is DISCONNECT");
+ rc = -EIO;
+ goto out;
+ }
+
+ /* Check for sanity in the parameters, part 1. Defer as many
+ * checks as possible until after reading any NBD_CMD_WRITE
+ * payload, so we can try and keep the connection alive. */
if ((request->from + request->len) < request->from) {
- LOG("integer overflow detected! "
- "you're probably being attacked");
+ LOG("integer overflow detected, you're probably being attacked");
rc = -EINVAL;
goto out;
}
- TRACE("Decoding type");
-
- command = request->type & NBD_CMD_MASK_COMMAND;
- if (command == NBD_CMD_READ || command == NBD_CMD_WRITE) {
+ if (request->type == NBD_CMD_READ || request->type == NBD_CMD_WRITE) {
if (request->len > NBD_MAX_BUFFER_SIZE) {
- LOG("len (%u) is larger than max len (%u)",
+ LOG("len (%" PRIu32" ) is larger than max len (%u)",
request->len, NBD_MAX_BUFFER_SIZE);
rc = -EINVAL;
goto out;
goto out;
}
}
- if (command == NBD_CMD_WRITE) {
- TRACE("Reading %u byte(s)", request->len);
+ if (request->type == NBD_CMD_WRITE) {
+ TRACE("Reading %" PRIu32 " byte(s)", request->len);
if (read_sync(client->ioc, req->data, request->len) != request->len) {
LOG("reading from socket failed");
rc = -EIO;
goto out;
}
+ req->complete = true;
}
+
+ /* Sanity checks, part 2. */
+ if (request->from + request->len > client->exp->size) {
+ LOG("operation past EOF; From: %" PRIu64 ", Len: %" PRIu32
+ ", Size: %" PRIu64, request->from, request->len,
+ (uint64_t)client->exp->size);
+ rc = request->type == NBD_CMD_WRITE ? -ENOSPC : -EINVAL;
+ goto out;
+ }
+ if (request->flags & ~(NBD_CMD_FLAG_FUA | NBD_CMD_FLAG_NO_HOLE)) {
+ LOG("unsupported flags (got 0x%x)", request->flags);
+ rc = -EINVAL;
+ goto out;
+ }
+ if (request->type != NBD_CMD_WRITE_ZEROES &&
+ (request->flags & NBD_CMD_FLAG_NO_HOLE)) {
+ LOG("unexpected flags (got 0x%x)", request->flags);
+ rc = -EINVAL;
+ goto out;
+ }
+
rc = 0;
out:
client->recv_coroutine = NULL;
- nbd_update_can_read(client);
+ nbd_client_receive_next_request(client);
return rc;
}
-static void nbd_trip(void *opaque)
+/* Owns a reference to the NBDClient passed as opaque. */
+static coroutine_fn void nbd_trip(void *opaque)
{
NBDClient *client = opaque;
NBDExport *exp = client->exp;
- NBDRequest *req;
- struct nbd_request request;
- struct nbd_reply reply;
+ NBDRequestData *req;
+ NBDRequest request = { 0 }; /* GCC thinks it can be used uninitialized */
+ NBDReply reply;
ssize_t ret;
- uint32_t command;
+ int flags;
TRACE("Reading request.");
if (client->closing) {
+ nbd_client_put(client);
return;
}
reply.error = -ret;
goto error_reply;
}
- command = request.type & NBD_CMD_MASK_COMMAND;
- if (command != NBD_CMD_DISC && (request.from + request.len) > exp->size) {
- LOG("From: %" PRIu64 ", Len: %u, Size: %" PRIu64
- ", Offset: %" PRIu64 "\n",
- request.from, request.len,
- (uint64_t)exp->size, (uint64_t)exp->dev_offset);
- LOG("requested operation past EOF--bad client?");
- goto invalid_request;
- }
if (client->closing) {
/*
goto done;
}
- switch (command) {
+ switch (request.type) {
case NBD_CMD_READ:
TRACE("Request type is READ");
- if (request.type & NBD_CMD_FLAG_FUA) {
+ /* XXX: NBD Protocol only documents use of FUA with WRITE */
+ if (request.flags & NBD_CMD_FLAG_FUA) {
ret = blk_co_flush(exp->blk);
if (ret < 0) {
LOG("flush failed");
}
}
- ret = blk_read(exp->blk,
- (request.from + exp->dev_offset) / BDRV_SECTOR_SIZE,
- req->data, request.len / BDRV_SECTOR_SIZE);
+ ret = blk_pread(exp->blk, request.from + exp->dev_offset,
+ req->data, request.len);
if (ret < 0) {
LOG("reading from file failed");
reply.error = -ret;
goto error_reply;
}
- TRACE("Read %u byte(s)", request.len);
+ TRACE("Read %" PRIu32" byte(s)", request.len);
if (nbd_co_send_reply(req, &reply, request.len) < 0)
goto out;
break;
TRACE("Writing to device");
- ret = blk_write(exp->blk,
- (request.from + exp->dev_offset) / BDRV_SECTOR_SIZE,
- req->data, request.len / BDRV_SECTOR_SIZE);
+ flags = 0;
+ if (request.flags & NBD_CMD_FLAG_FUA) {
+ flags |= BDRV_REQ_FUA;
+ }
+ ret = blk_pwrite(exp->blk, request.from + exp->dev_offset,
+ req->data, request.len, flags);
if (ret < 0) {
LOG("writing to file failed");
reply.error = -ret;
goto error_reply;
}
- if (request.type & NBD_CMD_FLAG_FUA) {
- ret = blk_co_flush(exp->blk);
- if (ret < 0) {
- LOG("flush failed");
- reply.error = -ret;
- goto error_reply;
- }
+ if (nbd_co_send_reply(req, &reply, 0) < 0) {
+ goto out;
+ }
+ break;
+
+ case NBD_CMD_WRITE_ZEROES:
+ TRACE("Request type is WRITE_ZEROES");
+
+ if (exp->nbdflags & NBD_FLAG_READ_ONLY) {
+ TRACE("Server is read-only, return error");
+ reply.error = EROFS;
+ goto error_reply;
+ }
+
+ TRACE("Writing to device");
+
+ flags = 0;
+ if (request.flags & NBD_CMD_FLAG_FUA) {
+ flags |= BDRV_REQ_FUA;
+ }
+ if (!(request.flags & NBD_CMD_FLAG_NO_HOLE)) {
+ flags |= BDRV_REQ_MAY_UNMAP;
+ }
+ ret = blk_pwrite_zeroes(exp->blk, request.from + exp->dev_offset,
+ request.len, flags);
+ if (ret < 0) {
+ LOG("writing to file failed");
+ reply.error = -ret;
+ goto error_reply;
}
if (nbd_co_send_reply(req, &reply, 0) < 0) {
goto out;
}
break;
+
case NBD_CMD_DISC:
- TRACE("Request type is DISCONNECT");
- errno = 0;
- goto out;
+ /* unreachable, thanks to special case in nbd_co_receive_request() */
+ abort();
+
case NBD_CMD_FLUSH:
TRACE("Request type is FLUSH");
break;
case NBD_CMD_TRIM:
TRACE("Request type is TRIM");
- ret = blk_co_discard(exp->blk, (request.from + exp->dev_offset)
- / BDRV_SECTOR_SIZE,
- request.len / BDRV_SECTOR_SIZE);
+ ret = blk_co_pdiscard(exp->blk, request.from + exp->dev_offset,
+ request.len);
if (ret < 0) {
LOG("discard failed");
reply.error = -ret;
}
break;
default:
- LOG("invalid request type (%u) received", request.type);
- invalid_request:
+ LOG("invalid request type (%" PRIu32 ") received", request.type);
reply.error = EINVAL;
error_reply:
- if (nbd_co_send_reply(req, &reply, 0) < 0) {
+ /* We must disconnect after NBD_CMD_WRITE if we did not
+ * read the payload.
+ */
+ if (nbd_co_send_reply(req, &reply, 0) < 0 || !req->complete) {
goto out;
}
break;
done:
nbd_request_put(req);
+ nbd_client_put(client);
return;
out:
nbd_request_put(req);
client_close(client);
+ nbd_client_put(client);
}
-static void nbd_read(void *opaque)
-{
- NBDClient *client = opaque;
-
- if (client->recv_coroutine) {
- qemu_coroutine_enter(client->recv_coroutine, NULL);
- } else {
- qemu_coroutine_enter(qemu_coroutine_create(nbd_trip), client);
- }
-}
-
-static void nbd_restart_write(void *opaque)
-{
- NBDClient *client = opaque;
-
- qemu_coroutine_enter(client->send_coroutine, NULL);
-}
-
-static void nbd_set_handlers(NBDClient *client)
-{
- if (client->exp && client->exp->ctx) {
- aio_set_fd_handler(client->exp->ctx, client->sioc->fd,
- true,
- client->can_read ? nbd_read : NULL,
- client->send_coroutine ? nbd_restart_write : NULL,
- client);
- }
-}
-
-static void nbd_unset_handlers(NBDClient *client)
+static void nbd_client_receive_next_request(NBDClient *client)
{
- if (client->exp && client->exp->ctx) {
- aio_set_fd_handler(client->exp->ctx, client->sioc->fd,
- true, NULL, NULL, NULL);
- }
-}
-
-static void nbd_update_can_read(NBDClient *client)
-{
- bool can_read = client->recv_coroutine ||
- client->nb_requests < MAX_NBD_REQUESTS;
-
- if (can_read != client->can_read) {
- client->can_read = can_read;
- nbd_set_handlers(client);
-
- /* There is no need to invoke aio_notify(), since aio_set_fd_handler()
- * in nbd_set_handlers() will have taken care of that */
+ if (!client->recv_coroutine && client->nb_requests < MAX_NBD_REQUESTS) {
+ nbd_client_get(client);
+ client->recv_coroutine = qemu_coroutine_create(nbd_trip, client);
+ aio_co_schedule(client->exp->ctx, client->recv_coroutine);
}
}
goto out;
}
qemu_co_mutex_init(&client->send_lock);
- nbd_set_handlers(client);
if (exp) {
QTAILQ_INSERT_TAIL(&exp->clients, client, next);
}
+
+ nbd_client_receive_next_request(client);
+
out:
g_free(data);
}
object_ref(OBJECT(client->sioc));
client->ioc = QIO_CHANNEL(sioc);
object_ref(OBJECT(client->ioc));
- client->can_read = true;
client->close = close_fn;
data->client = client;
- data->co = qemu_coroutine_create(nbd_co_client_start);
- qemu_coroutine_enter(data->co, data);
+ data->co = qemu_coroutine_create(nbd_co_client_start, data);
+ qemu_coroutine_enter(data->co);
}
projects / qemu.git / blobdiff