*/
#include "qemu/osdep.h"
+#include "qapi/error.h"
#include "nbd-internal.h"
static int system_errno_to_nbd_errno(int err)
case 0:
return NBD_SUCCESS;
case EPERM:
+ case EROFS:
return NBD_EPERM;
case EIO:
return NBD_EIO;
QSIMPLEQ_ENTRY(NBDRequest) entry;
NBDClient *client;
uint8_t *data;
+ bool complete;
};
struct NBDExport {
char *name;
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;
};
void (*close)(NBDClient *client);
NBDExport *exp;
+ QCryptoTLSCreds *tlscreds;
+ char *tlsaclname;
QIOChannelSocket *sioc; /* The underlying data channel */
QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */
GIOCondition condition,
void *opaque)
{
- qemu_coroutine_enter(opaque, NULL);
+ qemu_coroutine_enter(opaque);
return TRUE;
}
uint64_t magic;
uint32_t len;
+ TRACE("Reply opt=%" PRIx32 " type=%" PRIx32, type, opt);
+
magic = cpu_to_be64(NBD_REP_MAGIC);
if (nbd_negotiate_write(ioc, &magic, sizeof(magic)) != sizeof(magic)) {
LOG("write failed (rep magic)");
uint64_t magic, name_len;
uint32_t opt, type, len;
+ TRACE("Advertising 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)) {
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;
}
}
name[length] = '\0';
+ TRACE("Client requested export '%s'", name);
+
client->exp = nbd_export_find(name);
if (!client->exp) {
LOG("export not found");
return rc;
}
+
+static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client,
+ uint32_t length)
+{
+ QIOChannel *ioc;
+ QIOChannelTLS *tioc;
+ struct NBDTLSHandshakeData data = { 0 };
+
+ TRACE("Setting up TLS");
+ ioc = client->ioc;
+ if (length) {
+ if (nbd_negotiate_drop_sync(ioc, length) != length) {
+ return NULL;
+ }
+ nbd_negotiate_send_rep(ioc, NBD_REP_ERR_INVALID, NBD_OPT_STARTTLS);
+ return NULL;
+ }
+
+ 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,
+ client->tlsaclname,
+ NULL);
+ if (!tioc) {
+ return NULL;
+ }
+
+ TRACE("Starting TLS handshake");
+ data.loop = g_main_loop_new(g_main_context_default(), FALSE);
+ qio_channel_tls_handshake(tioc,
+ nbd_tls_handshake,
+ &data,
+ NULL);
+
+ if (!data.complete) {
+ g_main_loop_run(data.loop);
+ }
+ g_main_loop_unref(data.loop);
+ if (data.error) {
+ object_unref(OBJECT(tioc));
+ error_free(data.error);
+ return NULL;
+ }
+
+ return QIO_CHANNEL(tioc);
+}
+
+
static int nbd_negotiate_options(NBDClient *client)
{
uint32_t flags;
+ bool fixedNewstyle = false;
/* Client sends:
[ 0 .. 3] client flags
}
TRACE("Checking client flags");
be32_to_cpus(&flags);
- if (flags != 0 && flags != NBD_FLAG_C_FIXED_NEWSTYLE) {
- LOG("Bad client flags received");
+ if (flags & NBD_FLAG_C_FIXED_NEWSTYLE) {
+ TRACE("Client supports fixed newstyle handshake");
+ fixedNewstyle = true;
+ flags &= ~NBD_FLAG_C_FIXED_NEWSTYLE;
+ }
+ if (flags != 0) {
+ TRACE("Unknown client flags 0x%" PRIx32 " received", flags);
return -EIO;
}
while (1) {
int ret;
- uint32_t tmp, length;
+ uint32_t clientflags, length;
uint64_t magic;
if (nbd_negotiate_read(client->ioc, &magic, sizeof(magic)) !=
return -EINVAL;
}
- if (nbd_negotiate_read(client->ioc, &tmp, sizeof(tmp)) != sizeof(tmp)) {
+ if (nbd_negotiate_read(client->ioc, &clientflags,
+ sizeof(clientflags)) != sizeof(clientflags)) {
LOG("read failed");
return -EINVAL;
}
+ clientflags = be32_to_cpu(clientflags);
if (nbd_negotiate_read(client->ioc, &length, sizeof(length)) !=
sizeof(length)) {
}
length = be32_to_cpu(length);
- TRACE("Checking option");
- switch (be32_to_cpu(tmp)) {
- case NBD_OPT_LIST:
- ret = nbd_negotiate_handle_list(client, length);
- if (ret < 0) {
- return ret;
+ TRACE("Checking option 0x%" PRIx32, clientflags);
+ if (client->tlscreds &&
+ client->ioc == (QIOChannel *)client->sioc) {
+ QIOChannel *tioc;
+ if (!fixedNewstyle) {
+ TRACE("Unsupported option 0x%" PRIx32, clientflags);
+ return -EINVAL;
+ }
+ switch (clientflags) {
+ case NBD_OPT_STARTTLS:
+ tioc = nbd_negotiate_handle_starttls(client, length);
+ if (!tioc) {
+ return -EIO;
+ }
+ object_unref(OBJECT(client->ioc));
+ client->ioc = QIO_CHANNEL(tioc);
+ break;
+
+ case NBD_OPT_EXPORT_NAME:
+ /* No way to return an error to client, so drop connection */
+ TRACE("Option 0x%x not permitted before TLS", clientflags);
+ return -EINVAL;
+
+ default:
+ TRACE("Option 0x%" PRIx32 " not permitted before TLS",
+ clientflags);
+ if (nbd_negotiate_drop_sync(client->ioc, length) != length) {
+ return -EIO;
+ }
+ ret = nbd_negotiate_send_rep(client->ioc, NBD_REP_ERR_TLS_REQD,
+ clientflags);
+ if (ret < 0) {
+ return ret;
+ }
+ break;
+ }
+ } else if (fixedNewstyle) {
+ switch (clientflags) {
+ case NBD_OPT_LIST:
+ ret = nbd_negotiate_handle_list(client, length);
+ if (ret < 0) {
+ return ret;
+ }
+ break;
+
+ case NBD_OPT_ABORT:
+ return -EINVAL;
+
+ case NBD_OPT_EXPORT_NAME:
+ return nbd_negotiate_handle_export_name(client, length);
+
+ case NBD_OPT_STARTTLS:
+ if (nbd_negotiate_drop_sync(client->ioc, length) != length) {
+ return -EIO;
+ }
+ if (client->tlscreds) {
+ TRACE("TLS already enabled");
+ ret = nbd_negotiate_send_rep(client->ioc,
+ NBD_REP_ERR_INVALID,
+ clientflags);
+ } else {
+ TRACE("TLS not configured");
+ ret = nbd_negotiate_send_rep(client->ioc,
+ NBD_REP_ERR_POLICY,
+ clientflags);
+ }
+ if (ret < 0) {
+ return ret;
+ }
+ break;
+ default:
+ TRACE("Unsupported option 0x%" PRIx32, clientflags);
+ if (nbd_negotiate_drop_sync(client->ioc, length) != length) {
+ return -EIO;
+ }
+ ret = nbd_negotiate_send_rep(client->ioc, NBD_REP_ERR_UNSUP,
+ clientflags);
+ if (ret < 0) {
+ return ret;
+ }
+ break;
+ }
+ } else {
+ /*
+ * If broken new-style we should drop the connection
+ * for anything except NBD_OPT_EXPORT_NAME
+ */
+ switch (clientflags) {
+ case NBD_OPT_EXPORT_NAME:
+ return nbd_negotiate_handle_export_name(client, length);
+
+ default:
+ TRACE("Unsupported option 0x%" PRIx32, clientflags);
+ return -EINVAL;
}
- break;
-
- case NBD_OPT_ABORT:
- return -EINVAL;
-
- case NBD_OPT_EXPORT_NAME:
- return nbd_negotiate_handle_export_name(client, length);
-
- default:
- tmp = be32_to_cpu(tmp);
- LOG("Unsupported option 0x%x", tmp);
- nbd_negotiate_send_rep(client->ioc, NBD_REP_ERR_UNSUP, tmp);
- 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);
+ bool oldStyle;
- /* Negotiation header without options:
+ /* Old style negotiation header without options
[ 0 .. 7] passwd ("NBDMAGIC")
[ 8 .. 15] magic (NBD_CLIENT_MAGIC)
[16 .. 23] size
[26 .. 27] export flags
[28 .. 151] reserved (0)
- Negotiation header with options, part 1:
+ New style negotiation header with options
[ 0 .. 7] passwd ("NBDMAGIC")
[ 8 .. 15] magic (NBD_OPTS_MAGIC)
[16 .. 17] server flags (0)
-
- part 2 (after options are sent):
+ ....options sent....
[18 .. 25] size
[26 .. 27] export flags
[28 .. 151] reserved (0)
TRACE("Beginning negotiation.");
memset(buf, 0, sizeof(buf));
memcpy(buf, "NBDMAGIC", 8);
- if (client->exp) {
- assert ((client->exp->nbdflags & ~65535) == 0);
+
+ oldStyle = client->exp != NULL && !client->tlscreds;
+ if (oldStyle) {
+ 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);
stw_be_p(buf + 16, NBD_FLAG_FIXED_NEWSTYLE);
}
- if (client->exp) {
+ if (oldStyle) {
+ if (client->tlscreds) {
+ TRACE("TLS cannot be enabled with oldstyle protocol");
+ goto fail;
+ }
if (nbd_negotiate_write(client->ioc, buf, sizeof(buf)) != sizeof(buf)) {
LOG("write failed");
goto fail;
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) !=
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)
{
uint8_t buf[NBD_REQUEST_SIZE];
[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->type = ldl_be_p(buf + 4);
+ 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 }",
+ TRACE("Got request: { magic = 0x%" PRIx32 ", .type = %" PRIx32
+ ", from = %" PRIu64 " , len = %" PRIu32 " }",
magic, 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;
reply->error = system_errno_to_nbd_errno(reply->error);
+ TRACE("Sending response to client: { .error = %" PRId32
+ ", handle = %" PRIu64 " }",
+ reply->error, reply->handle);
+
/* Reply
[ 0 .. 3] magic (NBD_REPLY_MAGIC)
[ 4 .. 7] error (0 == no error)
stl_be_p(buf + 4, reply->error);
stq_be_p(buf + 8, reply->handle);
- TRACE("Sending response to client");
-
ret = write_sync(ioc, buf, sizeof(buf));
if (ret < 0) {
return ret;
nbd_unset_handlers(client);
object_unref(OBJECT(client->sioc));
object_unref(OBJECT(client->ioc));
+ if (client->tlscreds) {
+ object_unref(OBJECT(client->tlscreds));
+ }
+ g_free(client->tlsaclname);
if (client->exp) {
QTAILQ_REMOVE(&client->exp->clients, client, next);
nbd_export_put(client->exp);
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));
+
+ blk = blk_new();
+ blk_insert_bs(blk, bs);
+ 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;
}
}
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);
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(NBDRequest *req,
+ struct nbd_request *request)
{
NBDClient *client = req->client;
uint32_t command;
goto out;
}
+ TRACE("Decoding type");
+
+ command = request->type & NBD_CMD_MASK_COMMAND;
+ if (command != NBD_CMD_WRITE) {
+ /* No payload, we are ready to read the next request. */
+ req->complete = true;
+ }
+
+ if (command == 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->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;
}
}
if (command == NBD_CMD_WRITE) {
- TRACE("Reading %u byte(s)", request->len);
+ 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 = command == NBD_CMD_WRITE ? -ENOSPC : -EINVAL;
+ goto out;
+ }
+ if (request->type & ~NBD_CMD_MASK_COMMAND & ~NBD_CMD_FLAG_FUA) {
+ LOG("unsupported flags (got 0x%x)",
+ request->type & ~NBD_CMD_MASK_COMMAND);
+ rc = -EINVAL;
+ goto out;
+ }
+
rc = 0;
out:
struct nbd_reply reply;
ssize_t ret;
uint32_t command;
+ int flags;
TRACE("Reading request.");
if (client->closing) {
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) {
/*
}
}
- 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.type & 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_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;
NBDClient *client = opaque;
if (client->recv_coroutine) {
- qemu_coroutine_enter(client->recv_coroutine, NULL);
+ qemu_coroutine_enter(client->recv_coroutine);
} else {
- qemu_coroutine_enter(qemu_coroutine_create(nbd_trip), client);
+ qemu_coroutine_enter(qemu_coroutine_create(nbd_trip, client));
}
}
{
NBDClient *client = opaque;
- qemu_coroutine_enter(client->send_coroutine, NULL);
+ qemu_coroutine_enter(client->send_coroutine);
}
static void nbd_set_handlers(NBDClient *client)
void nbd_client_new(NBDExport *exp,
QIOChannelSocket *sioc,
+ QCryptoTLSCreds *tlscreds,
+ const char *tlsaclname,
void (*close_fn)(NBDClient *))
{
NBDClient *client;
client = g_malloc0(sizeof(NBDClient));
client->refcount = 1;
client->exp = exp;
+ client->tlscreds = tlscreds;
+ if (tlscreds) {
+ object_ref(OBJECT(client->tlscreds));
+ }
+ client->tlsaclname = g_strdup(tlsaclname);
client->sioc = sioc;
object_ref(OBJECT(client->sioc));
client->ioc = QIO_CHANNEL(sioc);
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