aboutsummaryrefslogtreecommitdiff
path: root/nbd/client.c
diff options
context:
space:
mode:
Diffstat (limited to 'nbd/client.c')
-rw-r--r--nbd/client.c1131
1 files changed, 768 insertions, 363 deletions
diff --git a/nbd/client.c b/nbd/client.c
index b4d457a19a..29ffc609a4 100644
--- a/nbd/client.c
+++ b/nbd/client.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2016-2018 Red Hat, Inc.
+ * Copyright Red Hat
* Copyright (C) 2005 Anthony Liguori <anthony@codemonkey.ws>
*
* Network Block Device Client Side
@@ -19,8 +19,10 @@
#include "qemu/osdep.h"
#include "qapi/error.h"
+#include "qemu/queue.h"
#include "trace.h"
#include "nbd-internal.h"
+#include "qemu/cutils.h"
/* Definitions for opaque data types */
@@ -66,6 +68,7 @@ static int nbd_send_option_request(QIOChannel *ioc, uint32_t opt,
uint32_t len, const char *data,
Error **errp)
{
+ ERRP_GUARD();
NBDOption req;
QEMU_BUILD_BUG_ON(sizeof(req) != 16);
@@ -112,8 +115,7 @@ static int nbd_receive_option_reply(QIOChannel *ioc, uint32_t opt,
NBDOptionReply *reply, Error **errp)
{
QEMU_BUILD_BUG_ON(sizeof(*reply) != 20);
- if (nbd_read(ioc, reply, sizeof(*reply), errp) < 0) {
- error_prepend(errp, "failed to read option reply: ");
+ if (nbd_read(ioc, reply, sizeof(*reply), "option reply", errp) < 0) {
nbd_send_opt_abort(ioc);
return -1;
}
@@ -132,25 +134,28 @@ static int nbd_receive_option_reply(QIOChannel *ioc, uint32_t opt,
return -1;
}
if (reply->option != opt) {
- error_setg(errp, "Unexpected option type %x expected %x",
- reply->option, opt);
+ error_setg(errp, "Unexpected option type %u (%s), expected %u (%s)",
+ reply->option, nbd_opt_lookup(reply->option),
+ opt, nbd_opt_lookup(opt));
nbd_send_opt_abort(ioc);
return -1;
}
return 0;
}
-/* If reply represents success, return 1 without further action.
- * If reply represents an error, consume the optional payload of
- * the packet on ioc. Then return 0 for unsupported (so the client
- * can fall back to other approaches), or -1 with errp set for other
- * errors.
+/*
+ * If reply represents success, return 1 without further action. If
+ * reply represents an error, consume the optional payload of the
+ * packet on ioc. Then return 0 for unsupported (so the client can
+ * fall back to other approaches), where @strict determines if only
+ * ERR_UNSUP or all errors fit that category, or -1 with errp set for
+ * other errors.
*/
static int nbd_handle_reply_err(QIOChannel *ioc, NBDOptionReply *reply,
- Error **errp)
+ bool strict, Error **errp)
{
- char *msg = NULL;
- int result = -1;
+ ERRP_GUARD();
+ g_autofree char *msg = NULL;
if (!(reply->type & (1 << 31))) {
return 1;
@@ -161,24 +166,28 @@ static int nbd_handle_reply_err(QIOChannel *ioc, NBDOptionReply *reply,
error_setg(errp, "server error %" PRIu32
" (%s) message is too long",
reply->type, nbd_rep_lookup(reply->type));
- goto cleanup;
+ goto err;
}
msg = g_malloc(reply->length + 1);
- if (nbd_read(ioc, msg, reply->length, errp) < 0) {
- error_prepend(errp, "failed to read option error %" PRIu32
+ if (nbd_read(ioc, msg, reply->length, NULL, errp) < 0) {
+ error_prepend(errp, "Failed to read option error %" PRIu32
" (%s) message: ",
reply->type, nbd_rep_lookup(reply->type));
- goto cleanup;
+ goto err;
}
msg[reply->length] = '\0';
+ trace_nbd_server_error_msg(reply->type,
+ nbd_reply_type_lookup(reply->type), msg);
}
- switch (reply->type) {
- case NBD_REP_ERR_UNSUP:
- trace_nbd_reply_err_unsup(reply->option, nbd_opt_lookup(reply->option));
- result = 0;
- goto cleanup;
+ if (reply->type == NBD_REP_ERR_UNSUP || !strict) {
+ trace_nbd_reply_err_ignored(reply->option,
+ nbd_opt_lookup(reply->option),
+ reply->type, nbd_rep_lookup(reply->type));
+ return 0;
+ }
+ switch (reply->type) {
case NBD_REP_ERR_POLICY:
error_setg(errp, "Denied by server for option %" PRIu32 " (%s)",
reply->option, nbd_opt_lookup(reply->option));
@@ -197,6 +206,7 @@ static int nbd_handle_reply_err(QIOChannel *ioc, NBDOptionReply *reply,
case NBD_REP_ERR_TLS_REQD:
error_setg(errp, "TLS negotiation required before option %" PRIu32
" (%s)", reply->option, nbd_opt_lookup(reply->option));
+ error_append_hint(errp, "Did you forget a valid tls-creds?\n");
break;
case NBD_REP_ERR_UNKNOWN:
@@ -223,36 +233,35 @@ static int nbd_handle_reply_err(QIOChannel *ioc, NBDOptionReply *reply,
error_append_hint(errp, "server reported: %s\n", msg);
}
- cleanup:
- g_free(msg);
- if (result < 0) {
- nbd_send_opt_abort(ioc);
- }
- return result;
+ err:
+ nbd_send_opt_abort(ioc);
+ return -1;
}
-/* Process another portion of the NBD_OPT_LIST reply. Set *@match if
- * the current reply matches @want or if the server does not support
- * NBD_OPT_LIST, otherwise leave @match alone. Return 0 if iteration
- * is complete, positive if more replies are expected, or negative
- * with @errp set if an unrecoverable error occurred. */
-static int nbd_receive_list(QIOChannel *ioc, const char *want, bool *match,
+/* nbd_receive_list:
+ * Process another portion of the NBD_OPT_LIST reply, populating any
+ * name received into *@name. If @description is non-NULL, and the
+ * server provided a description, that is also populated. The caller
+ * must eventually call g_free() on success.
+ * Returns 1 if name and description were set and iteration must continue,
+ * 0 if iteration is complete (including if OPT_LIST unsupported),
+ * -1 with @errp set if an unrecoverable error occurred.
+ */
+static int nbd_receive_list(QIOChannel *ioc, char **name, char **description,
Error **errp)
{
NBDOptionReply reply;
uint32_t len;
uint32_t namelen;
- char name[NBD_MAX_NAME_SIZE + 1];
+ g_autofree char *local_name = NULL;
+ g_autofree char *local_desc = NULL;
int error;
if (nbd_receive_option_reply(ioc, NBD_OPT_LIST, &reply, errp) < 0) {
return -1;
}
- error = nbd_handle_reply_err(ioc, &reply, errp);
+ error = nbd_handle_reply_err(ioc, &reply, true, errp);
if (error <= 0) {
- /* The server did not support NBD_OPT_LIST, so set *match on
- * the assumption that any name will be accepted. */
- *match = true;
return error;
}
len = reply.length;
@@ -265,8 +274,9 @@ static int nbd_receive_list(QIOChannel *ioc, const char *want, bool *match,
}
return 0;
} else if (reply.type != NBD_REP_SERVER) {
- error_setg(errp, "Unexpected reply type %" PRIx32 " expected %x",
- reply.type, NBD_REP_SERVER);
+ error_setg(errp, "Unexpected reply type %u (%s), expected %u (%s)",
+ reply.type, nbd_rep_lookup(reply.type),
+ NBD_REP_SERVER, nbd_rep_lookup(NBD_REP_SERVER));
nbd_send_opt_abort(ioc);
return -1;
}
@@ -276,57 +286,62 @@ static int nbd_receive_list(QIOChannel *ioc, const char *want, bool *match,
nbd_send_opt_abort(ioc);
return -1;
}
- if (nbd_read(ioc, &namelen, sizeof(namelen), errp) < 0) {
- error_prepend(errp, "failed to read option name length: ");
+ if (nbd_read32(ioc, &namelen, "option name length", errp) < 0) {
nbd_send_opt_abort(ioc);
return -1;
}
- namelen = be32_to_cpu(namelen);
len -= sizeof(namelen);
- if (len < namelen) {
- error_setg(errp, "incorrect option name length");
+ if (len < namelen || namelen > NBD_MAX_STRING_SIZE) {
+ error_setg(errp, "incorrect name length in server's list response");
nbd_send_opt_abort(ioc);
return -1;
}
- if (namelen != strlen(want)) {
- if (nbd_drop(ioc, len, errp) < 0) {
- error_prepend(errp,
- "failed to skip export name with wrong length: ");
- nbd_send_opt_abort(ioc);
- return -1;
- }
- return 1;
- }
- assert(namelen < sizeof(name));
- if (nbd_read(ioc, name, namelen, errp) < 0) {
- error_prepend(errp, "failed to read export name: ");
+ local_name = g_malloc(namelen + 1);
+ if (nbd_read(ioc, local_name, namelen, "export name", errp) < 0) {
nbd_send_opt_abort(ioc);
return -1;
}
- name[namelen] = '\0';
+ local_name[namelen] = '\0';
len -= namelen;
- if (nbd_drop(ioc, len, errp) < 0) {
- error_prepend(errp, "failed to read export description: ");
- nbd_send_opt_abort(ioc);
- return -1;
+ if (len) {
+ if (len > NBD_MAX_STRING_SIZE) {
+ error_setg(errp, "incorrect description length in server's "
+ "list response");
+ nbd_send_opt_abort(ioc);
+ return -1;
+ }
+ local_desc = g_malloc(len + 1);
+ if (nbd_read(ioc, local_desc, len, "export description", errp) < 0) {
+ nbd_send_opt_abort(ioc);
+ return -1;
+ }
+ local_desc[len] = '\0';
}
- if (!strcmp(name, want)) {
- *match = true;
+
+ trace_nbd_receive_list(local_name, local_desc ?: "");
+ *name = g_steal_pointer(&local_name);
+ if (description) {
+ *description = g_steal_pointer(&local_desc);
}
return 1;
}
-/* Returns -1 if NBD_OPT_GO proves the export @wantname cannot be
- * used, 0 if NBD_OPT_GO is unsupported (fall back to NBD_OPT_LIST and
+/*
+ * nbd_opt_info_or_go:
+ * Send option for NBD_OPT_INFO or NBD_OPT_GO and parse the reply.
+ * Returns -1 if the option proves the export @info->name cannot be
+ * used, 0 if the option is unsupported (fall back to NBD_OPT_LIST and
* NBD_OPT_EXPORT_NAME in that case), and > 0 if the export is good to
- * go (with @info populated). */
-static int nbd_opt_go(QIOChannel *ioc, const char *wantname,
- NBDExportInfo *info, Error **errp)
+ * go (with the rest of @info populated).
+ */
+static int nbd_opt_info_or_go(QIOChannel *ioc, uint32_t opt,
+ NBDExportInfo *info, Error **errp)
{
+ ERRP_GUARD();
NBDOptionReply reply;
- uint32_t len = strlen(wantname);
+ uint32_t len = strlen(info->name);
uint16_t type;
int error;
char *buf;
@@ -336,16 +351,17 @@ static int nbd_opt_go(QIOChannel *ioc, const char *wantname,
* flags still 0 is a witness of a broken server. */
info->flags = 0;
- trace_nbd_opt_go_start(wantname);
+ assert(opt == NBD_OPT_GO || opt == NBD_OPT_INFO);
+ trace_nbd_opt_info_go_start(nbd_opt_lookup(opt), info->name);
buf = g_malloc(4 + len + 2 + 2 * info->request_sizes + 1);
stl_be_p(buf, len);
- memcpy(buf + 4, wantname, len);
+ memcpy(buf + 4, info->name, len);
/* At most one request, everything else up to server */
stw_be_p(buf + 4 + len, info->request_sizes);
if (info->request_sizes) {
stw_be_p(buf + 4 + len + 2, NBD_INFO_BLOCK_SIZE);
}
- error = nbd_send_option_request(ioc, NBD_OPT_GO,
+ error = nbd_send_option_request(ioc, opt,
4 + len + 2 + 2 * info->request_sizes,
buf, errp);
g_free(buf);
@@ -354,18 +370,20 @@ static int nbd_opt_go(QIOChannel *ioc, const char *wantname,
}
while (1) {
- if (nbd_receive_option_reply(ioc, NBD_OPT_GO, &reply, errp) < 0) {
+ if (nbd_receive_option_reply(ioc, opt, &reply, errp) < 0) {
return -1;
}
- error = nbd_handle_reply_err(ioc, &reply, errp);
+ error = nbd_handle_reply_err(ioc, &reply, true, errp);
if (error <= 0) {
return error;
}
len = reply.length;
if (reply.type == NBD_REP_ACK) {
- /* Server is done sending info and moved into transmission
- phase, but make sure it sent flags */
+ /*
+ * Server is done sending info, and moved into transmission
+ * phase for NBD_OPT_GO, but make sure it sent flags
+ */
if (len) {
error_setg(errp, "server sent invalid NBD_REP_ACK");
return -1;
@@ -374,13 +392,13 @@ static int nbd_opt_go(QIOChannel *ioc, const char *wantname,
error_setg(errp, "broken server omitted NBD_INFO_EXPORT");
return -1;
}
- trace_nbd_opt_go_success();
+ trace_nbd_opt_info_go_success(nbd_opt_lookup(opt));
return 1;
}
if (reply.type != NBD_REP_INFO) {
- error_setg(errp, "unexpected reply type %" PRIu32
- " (%s), expected %u",
- reply.type, nbd_rep_lookup(reply.type), NBD_REP_INFO);
+ error_setg(errp, "unexpected reply type %u (%s), expected %u (%s)",
+ reply.type, nbd_rep_lookup(reply.type),
+ NBD_REP_INFO, nbd_rep_lookup(NBD_REP_INFO));
nbd_send_opt_abort(ioc);
return -1;
}
@@ -390,13 +408,11 @@ static int nbd_opt_go(QIOChannel *ioc, const char *wantname,
nbd_send_opt_abort(ioc);
return -1;
}
- if (nbd_read(ioc, &type, sizeof(type), errp) < 0) {
- error_prepend(errp, "failed to read info type: ");
+ if (nbd_read16(ioc, &type, "info type", errp) < 0) {
nbd_send_opt_abort(ioc);
return -1;
}
len -= sizeof(type);
- type = be16_to_cpu(type);
switch (type) {
case NBD_INFO_EXPORT:
if (len != sizeof(info->size) + sizeof(info->flags)) {
@@ -405,18 +421,22 @@ static int nbd_opt_go(QIOChannel *ioc, const char *wantname,
nbd_send_opt_abort(ioc);
return -1;
}
- if (nbd_read(ioc, &info->size, sizeof(info->size), errp) < 0) {
- error_prepend(errp, "failed to read info size: ");
+ if (nbd_read64(ioc, &info->size, "info size", errp) < 0) {
+ nbd_send_opt_abort(ioc);
+ return -1;
+ }
+ if (nbd_read16(ioc, &info->flags, "info flags", errp) < 0) {
nbd_send_opt_abort(ioc);
return -1;
}
- info->size = be64_to_cpu(info->size);
- if (nbd_read(ioc, &info->flags, sizeof(info->flags), errp) < 0) {
- error_prepend(errp, "failed to read info flags: ");
+ if (info->min_block &&
+ !QEMU_IS_ALIGNED(info->size, info->min_block)) {
+ error_setg(errp, "export size %" PRIu64 " is not multiple of "
+ "minimum block size %" PRIu32, info->size,
+ info->min_block);
nbd_send_opt_abort(ioc);
return -1;
}
- info->flags = be16_to_cpu(info->flags);
trace_nbd_receive_negotiate_size_flags(info->size, info->flags);
break;
@@ -427,27 +447,23 @@ static int nbd_opt_go(QIOChannel *ioc, const char *wantname,
nbd_send_opt_abort(ioc);
return -1;
}
- if (nbd_read(ioc, &info->min_block, sizeof(info->min_block),
- errp) < 0) {
- error_prepend(errp, "failed to read info minimum block size: ");
+ if (nbd_read32(ioc, &info->min_block, "info minimum block size",
+ errp) < 0) {
nbd_send_opt_abort(ioc);
return -1;
}
- info->min_block = be32_to_cpu(info->min_block);
if (!is_power_of_2(info->min_block)) {
error_setg(errp, "server minimum block size %" PRIu32
" is not a power of two", info->min_block);
nbd_send_opt_abort(ioc);
return -1;
}
- if (nbd_read(ioc, &info->opt_block, sizeof(info->opt_block),
- errp) < 0) {
- error_prepend(errp,
- "failed to read info preferred block size: ");
+ if (nbd_read32(ioc, &info->opt_block, "info preferred block size",
+ errp) < 0)
+ {
nbd_send_opt_abort(ioc);
return -1;
}
- info->opt_block = be32_to_cpu(info->opt_block);
if (!is_power_of_2(info->opt_block) ||
info->opt_block < info->min_block) {
error_setg(errp, "server preferred block size %" PRIu32
@@ -455,25 +471,28 @@ static int nbd_opt_go(QIOChannel *ioc, const char *wantname,
nbd_send_opt_abort(ioc);
return -1;
}
- if (nbd_read(ioc, &info->max_block, sizeof(info->max_block),
- errp) < 0) {
- error_prepend(errp, "failed to read info maximum block size: ");
+ if (nbd_read32(ioc, &info->max_block, "info maximum block size",
+ errp) < 0)
+ {
nbd_send_opt_abort(ioc);
return -1;
}
- info->max_block = be32_to_cpu(info->max_block);
if (info->max_block < info->min_block) {
error_setg(errp, "server maximum block size %" PRIu32
" is not valid", info->max_block);
nbd_send_opt_abort(ioc);
return -1;
}
- trace_nbd_opt_go_info_block_size(info->min_block, info->opt_block,
- info->max_block);
+ trace_nbd_opt_info_block_size(info->min_block, info->opt_block,
+ info->max_block);
break;
default:
- trace_nbd_opt_go_info_unknown(type, nbd_info_lookup(type));
+ /*
+ * Not worth the bother to check if NBD_INFO_NAME or
+ * NBD_INFO_DESCRIPTION exceed NBD_MAX_STRING_SIZE.
+ */
+ trace_nbd_opt_info_unknown(type, nbd_info_lookup(type));
if (nbd_drop(ioc, len, errp) < 0) {
error_prepend(errp, "Failed to read info payload: ");
nbd_send_opt_abort(ioc);
@@ -489,7 +508,8 @@ static int nbd_receive_query_exports(QIOChannel *ioc,
const char *wantname,
Error **errp)
{
- bool foundExport = false;
+ bool list_empty = true;
+ bool found_export = false;
trace_nbd_receive_query_exports_start(wantname);
if (nbd_send_option_request(ioc, NBD_OPT_LIST, 0, NULL, errp) < 0) {
@@ -497,14 +517,25 @@ static int nbd_receive_query_exports(QIOChannel *ioc,
}
while (1) {
- int ret = nbd_receive_list(ioc, wantname, &foundExport, errp);
+ char *name;
+ int ret = nbd_receive_list(ioc, &name, NULL, errp);
if (ret < 0) {
/* Server gave unexpected reply */
return -1;
} else if (ret == 0) {
/* Done iterating. */
- if (!foundExport) {
+ if (list_empty) {
+ /*
+ * We don't have enough context to tell a server that
+ * sent an empty list apart from a server that does
+ * not support the list command; but as this function
+ * is just used to trigger a nicer error message
+ * before trying NBD_OPT_EXPORT_NAME, assume the
+ * export is available.
+ */
+ return 0;
+ } else if (!found_export) {
error_setg(errp, "No export with name '%s' available",
wantname);
nbd_send_opt_abort(ioc);
@@ -513,15 +544,23 @@ static int nbd_receive_query_exports(QIOChannel *ioc,
trace_nbd_receive_query_exports_success(wantname);
return 0;
}
+ list_empty = false;
+ if (!strcmp(name, wantname)) {
+ found_export = true;
+ }
+ g_free(name);
}
}
-/* nbd_request_simple_option: Send an option request, and parse the reply
+/*
+ * nbd_request_simple_option: Send an option request, and parse the reply.
+ * @strict controls whether ERR_UNSUP or all errors produce 0 status.
* return 1 for successful negotiation,
* 0 if operation is unsupported,
* -1 with errp set for any other error
*/
-static int nbd_request_simple_option(QIOChannel *ioc, int opt, Error **errp)
+static int nbd_request_simple_option(QIOChannel *ioc, int opt, bool strict,
+ Error **errp)
{
NBDOptionReply reply;
int error;
@@ -533,7 +572,7 @@ static int nbd_request_simple_option(QIOChannel *ioc, int opt, Error **errp)
if (nbd_receive_option_reply(ioc, opt, &reply, errp) < 0) {
return -1;
}
- error = nbd_handle_reply_err(ioc, &reply, errp);
+ error = nbd_handle_reply_err(ioc, &reply, strict, errp);
if (error <= 0) {
return error;
}
@@ -565,7 +604,7 @@ static QIOChannel *nbd_receive_starttls(QIOChannel *ioc,
QIOChannelTLS *tioc;
struct NBDTLSHandshakeData data = { 0 };
- ret = nbd_request_simple_option(ioc, NBD_OPT_STARTTLS, errp);
+ ret = nbd_request_simple_option(ioc, NBD_OPT_STARTTLS, true, errp);
if (ret <= 0) {
if (ret == 0) {
error_setg(errp, "Server don't support STARTTLS option");
@@ -601,82 +640,163 @@ static QIOChannel *nbd_receive_starttls(QIOChannel *ioc,
return QIO_CHANNEL(tioc);
}
-/* nbd_negotiate_simple_meta_context:
- * Set one meta context. Simple means that reply must contain zero (not
- * negotiated) or one (negotiated) contexts. More contexts would be considered
- * as a protocol error. It's also implied that meta-data query equals queried
- * context name, so, if server replies with something different than @context,
- * it is considered an error too.
- * return 1 for successful negotiation, context_id is set
- * 0 if operation is unsupported,
- * -1 with errp set for any other error
+/*
+ * nbd_send_meta_query:
+ * Send 0 or 1 set/list meta context queries.
+ * Return 0 on success, -1 with errp set for any error
*/
-static int nbd_negotiate_simple_meta_context(QIOChannel *ioc,
- const char *export,
- const char *context,
- uint32_t *context_id,
- Error **errp)
+static int nbd_send_meta_query(QIOChannel *ioc, uint32_t opt,
+ const char *export, const char *query,
+ Error **errp)
{
int ret;
- NBDOptionReply reply;
- uint32_t received_id = 0;
- bool received = false;
- uint32_t export_len = strlen(export);
- uint32_t context_len = strlen(context);
- uint32_t data_len = sizeof(export_len) + export_len +
- sizeof(uint32_t) + /* number of queries */
- sizeof(context_len) + context_len;
- char *data = g_malloc(data_len);
- char *p = data;
-
- trace_nbd_opt_meta_request(context, export);
+ uint32_t export_len;
+ uint32_t queries = !!query;
+ uint32_t query_len = 0;
+ uint32_t data_len;
+ char *data;
+ char *p;
+
+ assert(strnlen(export, NBD_MAX_STRING_SIZE + 1) <= NBD_MAX_STRING_SIZE);
+ export_len = strlen(export);
+ data_len = sizeof(export_len) + export_len + sizeof(queries);
+ if (query) {
+ assert(strnlen(query, NBD_MAX_STRING_SIZE + 1) <= NBD_MAX_STRING_SIZE);
+ query_len = strlen(query);
+ data_len += sizeof(query_len) + query_len;
+ } else {
+ assert(opt == NBD_OPT_LIST_META_CONTEXT);
+ }
+ p = data = g_malloc(data_len);
+
+ trace_nbd_opt_meta_request(nbd_opt_lookup(opt), query ?: "(all)", export);
stl_be_p(p, export_len);
memcpy(p += sizeof(export_len), export, export_len);
- stl_be_p(p += export_len, 1);
- stl_be_p(p += sizeof(uint32_t), context_len);
- memcpy(p += sizeof(context_len), context, context_len);
+ stl_be_p(p += export_len, queries);
+ if (query) {
+ stl_be_p(p += sizeof(queries), query_len);
+ memcpy(p += sizeof(query_len), query, query_len);
+ }
- ret = nbd_send_option_request(ioc, NBD_OPT_SET_META_CONTEXT, data_len, data,
- errp);
+ ret = nbd_send_option_request(ioc, opt, data_len, data, errp);
g_free(data);
- if (ret < 0) {
- return ret;
- }
+ return ret;
+}
+
+/*
+ * nbd_receive_one_meta_context:
+ * Called in a loop to receive and trace one set/list meta context reply.
+ * Pass non-NULL @name or @id to collect results back to the caller, which
+ * must eventually call g_free().
+ * return 1 if name is set and iteration must continue,
+ * 0 if iteration is complete (including if option is unsupported),
+ * -1 with errp set for any error
+ */
+static int nbd_receive_one_meta_context(QIOChannel *ioc,
+ uint32_t opt,
+ char **name,
+ uint32_t *id,
+ Error **errp)
+{
+ int ret;
+ NBDOptionReply reply;
+ char *local_name = NULL;
+ uint32_t local_id;
- if (nbd_receive_option_reply(ioc, NBD_OPT_SET_META_CONTEXT, &reply,
- errp) < 0)
- {
+ if (nbd_receive_option_reply(ioc, opt, &reply, errp) < 0) {
return -1;
}
- ret = nbd_handle_reply_err(ioc, &reply, errp);
+ ret = nbd_handle_reply_err(ioc, &reply, false, errp);
if (ret <= 0) {
return ret;
}
- if (reply.type == NBD_REP_META_CONTEXT) {
- char *name;
-
- if (reply.length != sizeof(received_id) + context_len) {
- error_setg(errp, "Failed to negotiate meta context '%s', server "
- "answered with unexpected length %" PRIu32, context,
- reply.length);
+ if (reply.type == NBD_REP_ACK) {
+ if (reply.length != 0) {
+ error_setg(errp, "Unexpected length to ACK response");
nbd_send_opt_abort(ioc);
return -1;
}
+ return 0;
+ } else if (reply.type != NBD_REP_META_CONTEXT) {
+ error_setg(errp, "Unexpected reply type %u (%s), expected %u (%s)",
+ reply.type, nbd_rep_lookup(reply.type),
+ NBD_REP_META_CONTEXT, nbd_rep_lookup(NBD_REP_META_CONTEXT));
+ nbd_send_opt_abort(ioc);
+ return -1;
+ }
- if (nbd_read(ioc, &received_id, sizeof(received_id), errp) < 0) {
- return -1;
- }
- received_id = be32_to_cpu(received_id);
+ if (reply.length <= sizeof(local_id) ||
+ reply.length > NBD_MAX_BUFFER_SIZE) {
+ error_setg(errp, "Failed to negotiate meta context, server "
+ "answered with unexpected length %" PRIu32,
+ reply.length);
+ nbd_send_opt_abort(ioc);
+ return -1;
+ }
- reply.length -= sizeof(received_id);
- name = g_malloc(reply.length + 1);
- if (nbd_read(ioc, name, reply.length, errp) < 0) {
- g_free(name);
- return -1;
- }
- name[reply.length] = '\0';
+ if (nbd_read32(ioc, &local_id, "context id", errp) < 0) {
+ return -1;
+ }
+
+ reply.length -= sizeof(local_id);
+ local_name = g_malloc(reply.length + 1);
+ if (nbd_read(ioc, local_name, reply.length, "context name", errp) < 0) {
+ g_free(local_name);
+ return -1;
+ }
+ local_name[reply.length] = '\0';
+ trace_nbd_opt_meta_reply(nbd_opt_lookup(opt), local_name, local_id);
+
+ if (name) {
+ *name = local_name;
+ } else {
+ g_free(local_name);
+ }
+ if (id) {
+ *id = local_id;
+ }
+ return 1;
+}
+
+/*
+ * nbd_negotiate_simple_meta_context:
+ * Request the server to set the meta context for export @info->name
+ * using @info->x_dirty_bitmap with a fallback to "base:allocation",
+ * setting @info->context_id to the resulting id. Fail if the server
+ * responds with more than one context or with a context different
+ * than the query.
+ * return 1 for successful negotiation,
+ * 0 if operation is unsupported,
+ * -1 with errp set for any other error
+ */
+static int nbd_negotiate_simple_meta_context(QIOChannel *ioc,
+ NBDExportInfo *info,
+ Error **errp)
+{
+ /*
+ * TODO: Removing the x_dirty_bitmap hack will mean refactoring
+ * this function to request and store ids for multiple contexts
+ * (both base:allocation and a dirty bitmap), at which point this
+ * function should lose the term _simple.
+ */
+ int ret;
+ const char *context = info->x_dirty_bitmap ?: "base:allocation";
+ bool received = false;
+ char *name = NULL;
+
+ if (nbd_send_meta_query(ioc, NBD_OPT_SET_META_CONTEXT,
+ info->name, context, errp) < 0) {
+ return -1;
+ }
+
+ ret = nbd_receive_one_meta_context(ioc, NBD_OPT_SET_META_CONTEXT,
+ &name, &info->context_id, errp);
+ if (ret < 0) {
+ return -1;
+ }
+ if (ret == 1) {
if (strcmp(context, name)) {
error_setg(errp, "Failed to negotiate meta context '%s', server "
"answered with different context '%s'", context,
@@ -686,93 +806,111 @@ static int nbd_negotiate_simple_meta_context(QIOChannel *ioc,
return -1;
}
g_free(name);
-
- trace_nbd_opt_meta_reply(context, received_id);
received = true;
- /* receive NBD_REP_ACK */
- if (nbd_receive_option_reply(ioc, NBD_OPT_SET_META_CONTEXT, &reply,
- errp) < 0)
- {
+ ret = nbd_receive_one_meta_context(ioc, NBD_OPT_SET_META_CONTEXT,
+ NULL, NULL, errp);
+ if (ret < 0) {
return -1;
}
-
- ret = nbd_handle_reply_err(ioc, &reply, errp);
- if (ret <= 0) {
- return ret;
- }
}
-
- if (reply.type != NBD_REP_ACK) {
- error_setg(errp, "Unexpected reply type %" PRIx32 " expected %x",
- reply.type, NBD_REP_ACK);
+ if (ret != 0) {
+ error_setg(errp, "Server answered with more than one context");
nbd_send_opt_abort(ioc);
return -1;
}
- if (reply.length) {
- error_setg(errp, "Unexpected length to ACK response");
- nbd_send_opt_abort(ioc);
+ return received;
+}
+
+/*
+ * nbd_list_meta_contexts:
+ * Request the server to list all meta contexts for export @info->name.
+ * return 0 if list is complete (even if empty),
+ * -1 with errp set for any error
+ */
+static int nbd_list_meta_contexts(QIOChannel *ioc,
+ NBDExportInfo *info,
+ Error **errp)
+{
+ int ret;
+ int seen_any = false;
+ int seen_qemu = false;
+
+ if (nbd_send_meta_query(ioc, NBD_OPT_LIST_META_CONTEXT,
+ info->name, NULL, errp) < 0) {
return -1;
}
- if (received) {
- *context_id = received_id;
- return 1;
+ while (1) {
+ char *context;
+
+ ret = nbd_receive_one_meta_context(ioc, NBD_OPT_LIST_META_CONTEXT,
+ &context, NULL, errp);
+ if (ret == 0 && seen_any && !seen_qemu) {
+ /*
+ * Work around qemu 3.0 bug: the server forgot to send
+ * "qemu:" replies to 0 queries. If we saw at least one
+ * reply (probably base:allocation), but none of them were
+ * qemu:, then run a more specific query to make sure.
+ */
+ seen_qemu = true;
+ if (nbd_send_meta_query(ioc, NBD_OPT_LIST_META_CONTEXT,
+ info->name, "qemu:", errp) < 0) {
+ return -1;
+ }
+ continue;
+ }
+ if (ret <= 0) {
+ return ret;
+ }
+ seen_any = true;
+ seen_qemu |= strstart(context, "qemu:", NULL);
+ info->contexts = g_renew(char *, info->contexts, ++info->n_contexts);
+ info->contexts[info->n_contexts - 1] = context;
}
-
- return 0;
}
-int nbd_receive_negotiate(QIOChannel *ioc, const char *name,
- QCryptoTLSCreds *tlscreds, const char *hostname,
- QIOChannel **outioc, NBDExportInfo *info,
- Error **errp)
+/*
+ * nbd_start_negotiate:
+ * Start the handshake to the server. After a positive return, the server
+ * is ready to accept additional NBD_OPT requests.
+ * Returns: negative errno: failure talking to server
+ * non-negative: enum NBDMode describing server abilities
+ */
+static int nbd_start_negotiate(QIOChannel *ioc, QCryptoTLSCreds *tlscreds,
+ const char *hostname, QIOChannel **outioc,
+ NBDMode max_mode, bool *zeroes,
+ Error **errp)
{
- char buf[256];
+ ERRP_GUARD();
uint64_t magic;
- int rc;
- bool zeroes = true;
- bool structured_reply = info->structured_reply;
- bool base_allocation = info->base_allocation;
- trace_nbd_receive_negotiate(tlscreds, hostname ? hostname : "<null>");
-
- info->structured_reply = false;
- info->base_allocation = false;
- rc = -EINVAL;
+ trace_nbd_start_negotiate(tlscreds, hostname ? hostname : "<null>");
+ if (zeroes) {
+ *zeroes = true;
+ }
if (outioc) {
*outioc = NULL;
}
if (tlscreds && !outioc) {
error_setg(errp, "Output I/O channel required for TLS");
- goto fail;
- }
-
- if (nbd_read(ioc, buf, 8, errp) < 0) {
- error_prepend(errp, "Failed to read data: ");
- goto fail;
+ return -EINVAL;
}
- buf[8] = '\0';
- if (strlen(buf) == 0) {
- error_setg(errp, "Server connection closed unexpectedly");
- goto fail;
+ if (nbd_read64(ioc, &magic, "initial magic", errp) < 0) {
+ return -EINVAL;
}
-
- magic = ldq_be_p(buf);
trace_nbd_receive_negotiate_magic(magic);
- if (memcmp(buf, "NBDMAGIC", 8) != 0) {
- error_setg(errp, "Invalid magic received");
- goto fail;
+ if (magic != NBD_INIT_MAGIC) {
+ error_setg(errp, "Bad initial magic received: 0x%" PRIx64, magic);
+ return -EINVAL;
}
- if (nbd_read(ioc, &magic, sizeof(magic), errp) < 0) {
- error_prepend(errp, "Failed to read magic: ");
- goto fail;
+ if (nbd_read64(ioc, &magic, "server magic", errp) < 0) {
+ return -EINVAL;
}
- magic = be64_to_cpu(magic);
trace_nbd_receive_negotiate_magic(magic);
if (magic == NBD_OPTS_MAGIC) {
@@ -780,147 +918,335 @@ int nbd_receive_negotiate(QIOChannel *ioc, const char *name,
uint16_t globalflags;
bool fixedNewStyle = false;
- if (nbd_read(ioc, &globalflags, sizeof(globalflags), errp) < 0) {
- error_prepend(errp, "Failed to read server flags: ");
- goto fail;
+ if (nbd_read16(ioc, &globalflags, "server flags", errp) < 0) {
+ return -EINVAL;
}
- globalflags = be16_to_cpu(globalflags);
trace_nbd_receive_negotiate_server_flags(globalflags);
if (globalflags & NBD_FLAG_FIXED_NEWSTYLE) {
fixedNewStyle = true;
clientflags |= NBD_FLAG_C_FIXED_NEWSTYLE;
}
if (globalflags & NBD_FLAG_NO_ZEROES) {
- zeroes = false;
+ if (zeroes) {
+ *zeroes = false;
+ }
clientflags |= NBD_FLAG_C_NO_ZEROES;
}
/* client requested flags */
clientflags = cpu_to_be32(clientflags);
if (nbd_write(ioc, &clientflags, sizeof(clientflags), errp) < 0) {
error_prepend(errp, "Failed to send clientflags field: ");
- goto fail;
+ return -EINVAL;
}
if (tlscreds) {
if (fixedNewStyle) {
*outioc = nbd_receive_starttls(ioc, tlscreds, hostname, errp);
if (!*outioc) {
- goto fail;
+ return -EINVAL;
}
ioc = *outioc;
} else {
error_setg(errp, "Server does not support STARTTLS");
- goto fail;
+ return -EINVAL;
}
}
- if (!name) {
- trace_nbd_receive_negotiate_default_name();
- name = "";
- }
if (fixedNewStyle) {
- int result;
+ int result = 0;
- if (structured_reply) {
+ if (max_mode >= NBD_MODE_EXTENDED) {
result = nbd_request_simple_option(ioc,
- NBD_OPT_STRUCTURED_REPLY,
- errp);
- if (result < 0) {
- goto fail;
+ NBD_OPT_EXTENDED_HEADERS,
+ false, errp);
+ if (result) {
+ return result < 0 ? -EINVAL : NBD_MODE_EXTENDED;
}
- info->structured_reply = result == 1;
}
-
- if (info->structured_reply && base_allocation) {
- result = nbd_negotiate_simple_meta_context(
- ioc, name, info->x_dirty_bitmap ?: "base:allocation",
- &info->meta_base_allocation_id, errp);
- if (result < 0) {
- goto fail;
+ if (max_mode >= NBD_MODE_STRUCTURED) {
+ result = nbd_request_simple_option(ioc,
+ NBD_OPT_STRUCTURED_REPLY,
+ false, errp);
+ if (result) {
+ return result < 0 ? -EINVAL : NBD_MODE_STRUCTURED;
}
- info->base_allocation = result == 1;
}
+ return NBD_MODE_SIMPLE;
+ } else {
+ return NBD_MODE_EXPORT_NAME;
+ }
+ } else if (magic == NBD_CLIENT_MAGIC) {
+ if (tlscreds) {
+ error_setg(errp, "Server does not support STARTTLS");
+ return -EINVAL;
+ }
+ return NBD_MODE_OLDSTYLE;
+ } else {
+ error_setg(errp, "Bad server magic received: 0x%" PRIx64, magic);
+ return -EINVAL;
+ }
+}
+
+/*
+ * nbd_negotiate_finish_oldstyle:
+ * Populate @info with the size and export flags from an oldstyle server,
+ * but does not consume 124 bytes of reserved zero padding.
+ * Returns 0 on success, -1 with @errp set on failure
+ */
+static int nbd_negotiate_finish_oldstyle(QIOChannel *ioc, NBDExportInfo *info,
+ Error **errp)
+{
+ uint32_t oldflags;
+
+ if (nbd_read64(ioc, &info->size, "export length", errp) < 0) {
+ return -EINVAL;
+ }
+
+ if (nbd_read32(ioc, &oldflags, "export flags", errp) < 0) {
+ return -EINVAL;
+ }
+ if (oldflags & ~0xffff) {
+ error_setg(errp, "Unexpected export flags %0x" PRIx32, oldflags);
+ return -EINVAL;
+ }
+ info->flags = oldflags;
+ return 0;
+}
+
+/*
+ * nbd_receive_negotiate:
+ * Connect to server, complete negotiation, and move into transmission phase.
+ * Returns: negative errno: failure talking to server
+ * 0: server is connected
+ */
+int nbd_receive_negotiate(QIOChannel *ioc, QCryptoTLSCreds *tlscreds,
+ const char *hostname, QIOChannel **outioc,
+ NBDExportInfo *info, Error **errp)
+{
+ ERRP_GUARD();
+ int result;
+ bool zeroes;
+ bool base_allocation = info->base_allocation;
+
+ assert(info->name && strlen(info->name) <= NBD_MAX_STRING_SIZE);
+ trace_nbd_receive_negotiate_name(info->name);
- /* Try NBD_OPT_GO first - if it works, we are done (it
- * also gives us a good message if the server requires
- * TLS). If it is not available, fall back to
- * NBD_OPT_LIST for nicer error messages about a missing
- * export, then use NBD_OPT_EXPORT_NAME. */
- result = nbd_opt_go(ioc, name, info, errp);
+ result = nbd_start_negotiate(ioc, tlscreds, hostname, outioc,
+ info->mode, &zeroes, errp);
+ if (result < 0) {
+ return result;
+ }
+
+ info->mode = result;
+ info->base_allocation = false;
+ if (tlscreds && *outioc) {
+ ioc = *outioc;
+ }
+
+ switch (info->mode) {
+ case NBD_MODE_EXTENDED:
+ case NBD_MODE_STRUCTURED:
+ if (base_allocation) {
+ result = nbd_negotiate_simple_meta_context(ioc, info, errp);
if (result < 0) {
- goto fail;
- }
- if (result > 0) {
- return 0;
- }
- /* Check our desired export is present in the
- * server export list. Since NBD_OPT_EXPORT_NAME
- * cannot return an error message, running this
- * query gives us better error reporting if the
- * export name is not available.
- */
- if (nbd_receive_query_exports(ioc, name, errp) < 0) {
- goto fail;
+ return -EINVAL;
}
+ info->base_allocation = result == 1;
+ }
+ /* fall through */
+ case NBD_MODE_SIMPLE:
+ /* Try NBD_OPT_GO first - if it works, we are done (it
+ * also gives us a good message if the server requires
+ * TLS). If it is not available, fall back to
+ * NBD_OPT_LIST for nicer error messages about a missing
+ * export, then use NBD_OPT_EXPORT_NAME. */
+ result = nbd_opt_info_or_go(ioc, NBD_OPT_GO, info, errp);
+ if (result < 0) {
+ return -EINVAL;
}
+ if (result > 0) {
+ return 0;
+ }
+ /* Check our desired export is present in the
+ * server export list. Since NBD_OPT_EXPORT_NAME
+ * cannot return an error message, running this
+ * query gives us better error reporting if the
+ * export name is not available.
+ */
+ if (nbd_receive_query_exports(ioc, info->name, errp) < 0) {
+ return -EINVAL;
+ }
+ /* fall through */
+ case NBD_MODE_EXPORT_NAME:
/* write the export name request */
- if (nbd_send_option_request(ioc, NBD_OPT_EXPORT_NAME, -1, name,
+ if (nbd_send_option_request(ioc, NBD_OPT_EXPORT_NAME, -1, info->name,
errp) < 0) {
- goto fail;
+ return -EINVAL;
}
/* Read the response */
- if (nbd_read(ioc, &info->size, sizeof(info->size), errp) < 0) {
- error_prepend(errp, "Failed to read export length: ");
- goto fail;
+ if (nbd_read64(ioc, &info->size, "export length", errp) < 0) {
+ return -EINVAL;
}
- info->size = be64_to_cpu(info->size);
- if (nbd_read(ioc, &info->flags, sizeof(info->flags), errp) < 0) {
- error_prepend(errp, "Failed to read export flags: ");
- goto fail;
+ if (nbd_read16(ioc, &info->flags, "export flags", errp) < 0) {
+ return -EINVAL;
}
- info->flags = be16_to_cpu(info->flags);
- } else if (magic == NBD_CLIENT_MAGIC) {
- uint32_t oldflags;
+ break;
+ case NBD_MODE_OLDSTYLE:
+ if (*info->name) {
+ error_setg(errp, "Server does not support non-empty export names");
+ return -EINVAL;
+ }
+ if (nbd_negotiate_finish_oldstyle(ioc, info, errp) < 0) {
+ return -EINVAL;
+ }
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ trace_nbd_receive_negotiate_size_flags(info->size, info->flags);
+ if (zeroes && nbd_drop(ioc, 124, errp) < 0) {
+ error_prepend(errp, "Failed to read reserved block: ");
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/* Clean up result of nbd_receive_export_list */
+void nbd_free_export_list(NBDExportInfo *info, int count)
+{
+ int i, j;
- if (name) {
- error_setg(errp, "Server does not support export names");
- goto fail;
+ if (!info) {
+ return;
+ }
+
+ for (i = 0; i < count; i++) {
+ g_free(info[i].name);
+ g_free(info[i].description);
+ for (j = 0; j < info[i].n_contexts; j++) {
+ g_free(info[i].contexts[j]);
}
- if (tlscreds) {
- error_setg(errp, "Server does not support STARTTLS");
- goto fail;
+ g_free(info[i].contexts);
+ }
+ g_free(info);
+}
+
+/*
+ * nbd_receive_export_list:
+ * Query details about a server's exports, then disconnect without
+ * going into transmission phase. Return a count of the exports listed
+ * in @info by the server, or -1 on error. Caller must free @info using
+ * nbd_free_export_list().
+ */
+int nbd_receive_export_list(QIOChannel *ioc, QCryptoTLSCreds *tlscreds,
+ const char *hostname, NBDExportInfo **info,
+ Error **errp)
+{
+ int result;
+ int count = 0;
+ int i;
+ int rc;
+ int ret = -1;
+ NBDExportInfo *array = NULL;
+ QIOChannel *sioc = NULL;
+
+ *info = NULL;
+ result = nbd_start_negotiate(ioc, tlscreds, hostname, &sioc,
+ NBD_MODE_EXTENDED, NULL, errp);
+ if (tlscreds && sioc) {
+ ioc = sioc;
+ }
+ if (result < 0) {
+ goto out;
+ }
+
+ switch ((NBDMode)result) {
+ case NBD_MODE_SIMPLE:
+ case NBD_MODE_STRUCTURED:
+ case NBD_MODE_EXTENDED:
+ /* newstyle - use NBD_OPT_LIST to populate array, then try
+ * NBD_OPT_INFO on each array member. If structured replies
+ * are enabled, also try NBD_OPT_LIST_META_CONTEXT. */
+ if (nbd_send_option_request(ioc, NBD_OPT_LIST, 0, NULL, errp) < 0) {
+ goto out;
+ }
+ while (1) {
+ char *name;
+ char *desc;
+
+ rc = nbd_receive_list(ioc, &name, &desc, errp);
+ if (rc < 0) {
+ goto out;
+ } else if (rc == 0) {
+ break;
+ }
+ array = g_renew(NBDExportInfo, array, ++count);
+ memset(&array[count - 1], 0, sizeof(*array));
+ array[count - 1].name = name;
+ array[count - 1].description = desc;
+ array[count - 1].mode = result;
}
- if (nbd_read(ioc, &info->size, sizeof(info->size), errp) < 0) {
- error_prepend(errp, "Failed to read export length: ");
- goto fail;
+ for (i = 0; i < count; i++) {
+ array[i].request_sizes = true;
+ rc = nbd_opt_info_or_go(ioc, NBD_OPT_INFO, &array[i], errp);
+ if (rc < 0) {
+ goto out;
+ } else if (rc == 0) {
+ /*
+ * Pointless to try rest of loop. If OPT_INFO doesn't work,
+ * it's unlikely that meta contexts work either
+ */
+ break;
+ }
+
+ if (result >= NBD_MODE_STRUCTURED &&
+ nbd_list_meta_contexts(ioc, &array[i], errp) < 0) {
+ goto out;
+ }
}
- info->size = be64_to_cpu(info->size);
- if (nbd_read(ioc, &oldflags, sizeof(oldflags), errp) < 0) {
- error_prepend(errp, "Failed to read export flags: ");
- goto fail;
+ /* Send NBD_OPT_ABORT as a courtesy before hanging up */
+ nbd_send_opt_abort(ioc);
+ break;
+ case NBD_MODE_EXPORT_NAME:
+ error_setg(errp, "Server does not support export lists");
+ /* We can't even send NBD_OPT_ABORT, so merely hang up */
+ goto out;
+ case NBD_MODE_OLDSTYLE:
+ /* Lone export name is implied, but we can parse length and flags */
+ array = g_new0(NBDExportInfo, 1);
+ array->name = g_strdup("");
+ array->mode = NBD_MODE_OLDSTYLE;
+ count = 1;
+
+ if (nbd_negotiate_finish_oldstyle(ioc, array, errp) < 0) {
+ goto out;
}
- oldflags = be32_to_cpu(oldflags);
- if (oldflags & ~0xffff) {
- error_setg(errp, "Unexpected export flags %0x" PRIx32, oldflags);
- goto fail;
+
+ /* Send NBD_CMD_DISC as a courtesy to the server, but ignore all
+ * errors now that we have the information we wanted. */
+ if (nbd_drop(ioc, 124, NULL) == 0) {
+ NBDRequest request = { .type = NBD_CMD_DISC, .mode = result };
+
+ nbd_send_request(ioc, &request);
}
- info->flags = oldflags;
- } else {
- error_setg(errp, "Bad magic received");
- goto fail;
+ break;
+ default:
+ g_assert_not_reached();
}
- trace_nbd_receive_negotiate_size_flags(info->size, info->flags);
- if (zeroes && nbd_drop(ioc, 124, errp) < 0) {
- error_prepend(errp, "Failed to read reserved block: ");
- goto fail;
- }
- rc = 0;
+ *info = array;
+ array = NULL;
+ ret = count;
-fail:
- return rc;
+ out:
+ qio_channel_shutdown(ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
+ qio_channel_close(ioc, NULL);
+ object_unref(OBJECT(sioc));
+ nbd_free_export_list(array, count);
+ return ret;
}
#ifdef __linux__
@@ -1026,40 +1352,33 @@ int nbd_disconnect(int fd)
return 0;
}
-#else
-int nbd_init(int fd, QIOChannelSocket *ioc, NBDExportInfo *info,
- Error **errp)
-{
- error_setg(errp, "nbd_init is only supported on Linux");
- return -ENOTSUP;
-}
-
-int nbd_client(int fd)
-{
- return -ENOTSUP;
-}
-int nbd_disconnect(int fd)
-{
- return -ENOTSUP;
-}
-#endif
+#endif /* __linux__ */
int nbd_send_request(QIOChannel *ioc, NBDRequest *request)
{
- uint8_t buf[NBD_REQUEST_SIZE];
+ uint8_t buf[NBD_EXTENDED_REQUEST_SIZE];
+ size_t len;
- trace_nbd_send_request(request->from, request->len, request->handle,
+ trace_nbd_send_request(request->from, request->len, request->cookie,
request->flags, request->type,
nbd_cmd_lookup(request->type));
- stl_be_p(buf, NBD_REQUEST_MAGIC);
stw_be_p(buf + 4, request->flags);
stw_be_p(buf + 6, request->type);
- stq_be_p(buf + 8, request->handle);
+ stq_be_p(buf + 8, request->cookie);
stq_be_p(buf + 16, request->from);
- stl_be_p(buf + 24, request->len);
+ if (request->mode >= NBD_MODE_EXTENDED) {
+ stl_be_p(buf, NBD_EXTENDED_REQUEST_MAGIC);
+ stq_be_p(buf + 24, request->len);
+ len = NBD_EXTENDED_REQUEST_SIZE;
+ } else {
+ assert(request->len <= UINT32_MAX);
+ stl_be_p(buf, NBD_REQUEST_MAGIC);
+ stl_be_p(buf + 24, request->len);
+ len = NBD_REQUEST_SIZE;
+ }
- return nbd_write(ioc, buf, sizeof(buf), NULL);
+ return nbd_write(ioc, buf, len, NULL);
}
/* nbd_receive_simple_reply
@@ -1075,89 +1394,175 @@ static int nbd_receive_simple_reply(QIOChannel *ioc, NBDSimpleReply *reply,
assert(reply->magic == NBD_SIMPLE_REPLY_MAGIC);
ret = nbd_read(ioc, (uint8_t *)reply + sizeof(reply->magic),
- sizeof(*reply) - sizeof(reply->magic), errp);
+ sizeof(*reply) - sizeof(reply->magic), "reply", errp);
if (ret < 0) {
return ret;
}
reply->error = be32_to_cpu(reply->error);
- reply->handle = be64_to_cpu(reply->handle);
+ reply->cookie = be64_to_cpu(reply->cookie);
return 0;
}
-/* nbd_receive_structured_reply_chunk
+/* nbd_receive_reply_chunk_header
* Read structured reply chunk except magic field (which should be already
- * read).
+ * read). Normalize into the compact form.
* Payload is not read.
*/
-static int nbd_receive_structured_reply_chunk(QIOChannel *ioc,
- NBDStructuredReplyChunk *chunk,
- Error **errp)
+static int nbd_receive_reply_chunk_header(QIOChannel *ioc, NBDReply *chunk,
+ Error **errp)
{
int ret;
+ size_t len;
+ uint64_t payload_len;
- assert(chunk->magic == NBD_STRUCTURED_REPLY_MAGIC);
+ if (chunk->magic == NBD_STRUCTURED_REPLY_MAGIC) {
+ len = sizeof(chunk->structured);
+ } else {
+ assert(chunk->magic == NBD_EXTENDED_REPLY_MAGIC);
+ len = sizeof(chunk->extended);
+ }
ret = nbd_read(ioc, (uint8_t *)chunk + sizeof(chunk->magic),
- sizeof(*chunk) - sizeof(chunk->magic), errp);
+ len - sizeof(chunk->magic), "structured chunk",
+ errp);
if (ret < 0) {
return ret;
}
- chunk->flags = be16_to_cpu(chunk->flags);
- chunk->type = be16_to_cpu(chunk->type);
- chunk->handle = be64_to_cpu(chunk->handle);
- chunk->length = be32_to_cpu(chunk->length);
+ /* flags, type, and cookie occupy same space between forms */
+ chunk->structured.flags = be16_to_cpu(chunk->structured.flags);
+ chunk->structured.type = be16_to_cpu(chunk->structured.type);
+ chunk->structured.cookie = be64_to_cpu(chunk->structured.cookie);
+
+ /*
+ * Because we use BLOCK_STATUS with REQ_ONE, and cap READ requests
+ * at 32M, no valid server should send us payload larger than
+ * this. Even if we stopped using REQ_ONE, sane servers will cap
+ * the number of extents they return for block status.
+ */
+ if (chunk->magic == NBD_STRUCTURED_REPLY_MAGIC) {
+ payload_len = be32_to_cpu(chunk->structured.length);
+ } else {
+ /* For now, we are ignoring the extended header offset. */
+ payload_len = be64_to_cpu(chunk->extended.length);
+ chunk->magic = NBD_STRUCTURED_REPLY_MAGIC;
+ }
+ if (payload_len > NBD_MAX_BUFFER_SIZE + sizeof(NBDStructuredReadData)) {
+ error_setg(errp, "server chunk %" PRIu32 " (%s) payload is too long",
+ chunk->structured.type,
+ nbd_rep_lookup(chunk->structured.type));
+ return -EINVAL;
+ }
+ chunk->structured.length = payload_len;
return 0;
}
-/* nbd_receive_reply
+/* nbd_read_eof
+ * Tries to read @size bytes from @ioc.
* Returns 1 on success
* 0 on eof, when no data was read (errp is not set)
* negative errno on failure (errp is set)
*/
-int nbd_receive_reply(QIOChannel *ioc, NBDReply *reply, Error **errp)
+static inline int coroutine_fn
+nbd_read_eof(BlockDriverState *bs, QIOChannel *ioc, void *buffer, size_t size,
+ Error **errp)
+{
+ bool partial = false;
+
+ assert(size);
+ while (size > 0) {
+ struct iovec iov = { .iov_base = buffer, .iov_len = size };
+ ssize_t len;
+
+ len = qio_channel_readv(ioc, &iov, 1, errp);
+ if (len == QIO_CHANNEL_ERR_BLOCK) {
+ qio_channel_yield(ioc, G_IO_IN);
+ continue;
+ } else if (len < 0) {
+ return -EIO;
+ } else if (len == 0) {
+ if (partial) {
+ error_setg(errp,
+ "Unexpected end-of-file before all bytes were read");
+ return -EIO;
+ } else {
+ return 0;
+ }
+ }
+
+ partial = true;
+ size -= len;
+ buffer = (uint8_t*) buffer + len;
+ }
+ return 1;
+}
+
+/* nbd_receive_reply
+ *
+ * Wait for a new reply. If this yields, the coroutine must be able to be
+ * safely reentered for nbd_client_attach_aio_context(). @mode determines
+ * which reply magic we are expecting, although this normalizes the result
+ * so that the caller only has to work with compact headers.
+ *
+ * Returns 1 on success
+ * 0 on eof, when no data was read
+ * negative errno on failure
+ */
+int coroutine_fn nbd_receive_reply(BlockDriverState *bs, QIOChannel *ioc,
+ NBDReply *reply, NBDMode mode, Error **errp)
{
int ret;
const char *type;
+ uint32_t expected;
- ret = nbd_read_eof(ioc, &reply->magic, sizeof(reply->magic), errp);
+ ret = nbd_read_eof(bs, ioc, &reply->magic, sizeof(reply->magic), errp);
if (ret <= 0) {
return ret;
}
reply->magic = be32_to_cpu(reply->magic);
+ /* Diagnose but accept wrong-width header */
switch (reply->magic) {
case NBD_SIMPLE_REPLY_MAGIC:
+ if (mode >= NBD_MODE_EXTENDED) {
+ trace_nbd_receive_wrong_header(reply->magic,
+ nbd_mode_lookup(mode));
+ }
ret = nbd_receive_simple_reply(ioc, &reply->simple, errp);
if (ret < 0) {
- break;
+ return ret;
}
trace_nbd_receive_simple_reply(reply->simple.error,
nbd_err_lookup(reply->simple.error),
- reply->handle);
+ reply->cookie);
break;
case NBD_STRUCTURED_REPLY_MAGIC:
- ret = nbd_receive_structured_reply_chunk(ioc, &reply->structured, errp);
+ case NBD_EXTENDED_REPLY_MAGIC:
+ expected = mode >= NBD_MODE_EXTENDED ? NBD_EXTENDED_REPLY_MAGIC
+ : NBD_STRUCTURED_REPLY_MAGIC;
+ if (reply->magic != expected) {
+ trace_nbd_receive_wrong_header(reply->magic,
+ nbd_mode_lookup(mode));
+ }
+ ret = nbd_receive_reply_chunk_header(ioc, reply, errp);
if (ret < 0) {
- break;
+ return ret;
}
type = nbd_reply_type_lookup(reply->structured.type);
- trace_nbd_receive_structured_reply_chunk(reply->structured.flags,
- reply->structured.type, type,
- reply->structured.handle,
- reply->structured.length);
+ trace_nbd_receive_reply_chunk_header(reply->structured.flags,
+ reply->structured.type, type,
+ reply->structured.cookie,
+ reply->structured.length);
break;
default:
+ trace_nbd_receive_wrong_header(reply->magic, nbd_mode_lookup(mode));
error_setg(errp, "invalid magic (got 0x%" PRIx32 ")", reply->magic);
return -EINVAL;
}
- if (ret < 0) {
- return ret;
- }
return 1;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-25 01:53:51 +0000