qemu/include/block/nbd.h

430 lines
16 KiB
C
Raw Normal View History

/*
nbd/server: Allow MULTI_CONN for shared writable exports According to the NBD spec, a server that advertises NBD_FLAG_CAN_MULTI_CONN promises that multiple client connections will not see any cache inconsistencies: when properly separated by a single flush, actions performed by one client will be visible to another client, regardless of which client did the flush. We always satisfy these conditions in qemu - even when we support multiple clients, ALL clients go through a single point of reference into the block layer, with no local caching. The effect of one client is instantly visible to the next client. Even if our backend were a network device, we argue that any multi-path caching effects that would cause inconsistencies in back-to-back actions not seeing the effect of previous actions would be a bug in that backend, and not the fault of caching in qemu. As such, it is safe to unconditionally advertise CAN_MULTI_CONN for any qemu NBD server situation that supports parallel clients. Note, however, that we don't want to advertise CAN_MULTI_CONN when we know that a second client cannot connect (for historical reasons, qemu-nbd defaults to a single connection while nbd-server-add and QMP commands default to unlimited connections; but we already have existing means to let either style of NBD server creation alter those defaults). This is visible by no longer advertising MULTI_CONN for 'qemu-nbd -r' without -e, as in the iotest nbd-qemu-allocation. The harder part of this patch is setting up an iotest to demonstrate behavior of multiple NBD clients to a single server. It might be possible with parallel qemu-io processes, but I found it easier to do in python with the help of libnbd, and help from Nir and Vladimir in writing the test. Signed-off-by: Eric Blake <eblake@redhat.com> Suggested-by: Nir Soffer <nsoffer@redhat.com> Suggested-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru> Message-Id: <20220512004924.417153-3-eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2022-05-12 03:49:24 +03:00
* Copyright (C) 2016-2022 Red Hat, Inc.
* Copyright (C) 2005 Anthony Liguori <anthony@codemonkey.ws>
*
* Network Block Device
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; under version 2 of the License.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#ifndef NBD_H
#define NBD_H
#include "block/export.h"
#include "io/channel-socket.h"
#include "crypto/tlscreds.h"
#include "qapi/error.h"
extern const BlockExportDriver blk_exp_nbd;
/* Handshake phase structs - this struct is passed on the wire */
struct NBDOption {
uint64_t magic; /* NBD_OPTS_MAGIC */
uint32_t option; /* NBD_OPT_* */
uint32_t length;
} QEMU_PACKED;
typedef struct NBDOption NBDOption;
struct NBDOptionReply {
uint64_t magic; /* NBD_REP_MAGIC */
uint32_t option; /* NBD_OPT_* */
uint32_t type; /* NBD_REP_* */
uint32_t length;
} QEMU_PACKED;
typedef struct NBDOptionReply NBDOptionReply;
typedef struct NBDOptionReplyMetaContext {
NBDOptionReply h; /* h.type = NBD_REP_META_CONTEXT, h.length > 4 */
uint32_t context_id;
/* metadata context name follows */
} QEMU_PACKED NBDOptionReplyMetaContext;
/* Transmission phase structs
*
* Note: these are _NOT_ the same as the network representation of an NBD
* request and reply!
*/
struct NBDRequest {
uint64_t handle;
uint64_t from;
uint32_t len;
uint16_t flags; /* NBD_CMD_FLAG_* */
uint16_t type; /* NBD_CMD_* */
};
typedef struct NBDRequest NBDRequest;
typedef struct NBDSimpleReply {
uint32_t magic; /* NBD_SIMPLE_REPLY_MAGIC */
uint32_t error;
uint64_t handle;
} QEMU_PACKED NBDSimpleReply;
/* Header of all structured replies */
typedef struct NBDStructuredReplyChunk {
uint32_t magic; /* NBD_STRUCTURED_REPLY_MAGIC */
uint16_t flags; /* combination of NBD_REPLY_FLAG_* */
uint16_t type; /* NBD_REPLY_TYPE_* */
uint64_t handle; /* request handle */
uint32_t length; /* length of payload */
} QEMU_PACKED NBDStructuredReplyChunk;
typedef union NBDReply {
NBDSimpleReply simple;
NBDStructuredReplyChunk structured;
struct {
/* @magic and @handle fields have the same offset and size both in
* simple reply and structured reply chunk, so let them be accessible
* without ".simple." or ".structured." specification
*/
uint32_t magic;
uint32_t _skip;
uint64_t handle;
} QEMU_PACKED;
} NBDReply;
/* Header of chunk for NBD_REPLY_TYPE_OFFSET_DATA */
typedef struct NBDStructuredReadData {
NBDStructuredReplyChunk h; /* h.length >= 9 */
uint64_t offset;
/* At least one byte of data payload follows, calculated from h.length */
} QEMU_PACKED NBDStructuredReadData;
/* Complete chunk for NBD_REPLY_TYPE_OFFSET_HOLE */
typedef struct NBDStructuredReadHole {
NBDStructuredReplyChunk h; /* h.length == 12 */
uint64_t offset;
uint32_t length;
} QEMU_PACKED NBDStructuredReadHole;
/* Header of all NBD_REPLY_TYPE_ERROR* errors */
typedef struct NBDStructuredError {
NBDStructuredReplyChunk h; /* h.length >= 6 */
uint32_t error;
uint16_t message_length;
} QEMU_PACKED NBDStructuredError;
/* Header of NBD_REPLY_TYPE_BLOCK_STATUS */
typedef struct NBDStructuredMeta {
NBDStructuredReplyChunk h; /* h.length >= 12 (at least one extent) */
uint32_t context_id;
/* extents follows */
} QEMU_PACKED NBDStructuredMeta;
/* Extent chunk for NBD_REPLY_TYPE_BLOCK_STATUS */
typedef struct NBDExtent {
uint32_t length;
uint32_t flags; /* NBD_STATE_* */
} QEMU_PACKED NBDExtent;
/* Transmission (export) flags: sent from server to client during handshake,
but describe what will happen during transmission */
enum {
NBD_FLAG_HAS_FLAGS_BIT = 0, /* Flags are there */
NBD_FLAG_READ_ONLY_BIT = 1, /* Device is read-only */
NBD_FLAG_SEND_FLUSH_BIT = 2, /* Send FLUSH */
NBD_FLAG_SEND_FUA_BIT = 3, /* Send FUA (Force Unit Access) */
NBD_FLAG_ROTATIONAL_BIT = 4, /* Use elevator algorithm -
rotational media */
NBD_FLAG_SEND_TRIM_BIT = 5, /* Send TRIM (discard) */
NBD_FLAG_SEND_WRITE_ZEROES_BIT = 6, /* Send WRITE_ZEROES */
NBD_FLAG_SEND_DF_BIT = 7, /* Send DF (Do not Fragment) */
NBD_FLAG_CAN_MULTI_CONN_BIT = 8, /* Multi-client cache consistent */
NBD_FLAG_SEND_RESIZE_BIT = 9, /* Send resize */
NBD_FLAG_SEND_CACHE_BIT = 10, /* Send CACHE (prefetch) */
nbd: Prepare for NBD_CMD_FLAG_FAST_ZERO Commit fe0480d6 and friends added BDRV_REQ_NO_FALLBACK as a way to avoid wasting time on a preliminary write-zero request that will later be rewritten by actual data, if it is known that the write-zero request will use a slow fallback; but in doing so, could not optimize for NBD. The NBD specification is now considering an extension that will allow passing on those semantics; this patch updates the new protocol bits and 'qemu-nbd --list' output to recognize the bit, as well as the new errno value possible when using the new flag; while upcoming patches will improve the client to use the feature when present, and the server to advertise support for it. The NBD spec recommends (but not requires) that ENOTSUP be avoided for all but failures of a fast zero (the only time it is mandatory to avoid an ENOTSUP failure is when fast zero is supported but not requested during write zeroes; the questionable use is for ENOTSUP to other actions like a normal write request). However, clients that get an unexpected ENOTSUP will either already be treating it the same as EINVAL, or may appreciate the extra bit of information. We were equally loose for returning EOVERFLOW in more situations than recommended by the spec, so if it turns out to be a problem in practice, a later patch can tighten handling for both error codes. Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <20190823143726.27062-3-eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> [eblake: tweak commit message, also handle EOPNOTSUPP]
2019-08-23 17:37:23 +03:00
NBD_FLAG_SEND_FAST_ZERO_BIT = 11, /* FAST_ZERO flag for WRITE_ZEROES */
};
#define NBD_FLAG_HAS_FLAGS (1 << NBD_FLAG_HAS_FLAGS_BIT)
#define NBD_FLAG_READ_ONLY (1 << NBD_FLAG_READ_ONLY_BIT)
#define NBD_FLAG_SEND_FLUSH (1 << NBD_FLAG_SEND_FLUSH_BIT)
#define NBD_FLAG_SEND_FUA (1 << NBD_FLAG_SEND_FUA_BIT)
#define NBD_FLAG_ROTATIONAL (1 << NBD_FLAG_ROTATIONAL_BIT)
#define NBD_FLAG_SEND_TRIM (1 << NBD_FLAG_SEND_TRIM_BIT)
#define NBD_FLAG_SEND_WRITE_ZEROES (1 << NBD_FLAG_SEND_WRITE_ZEROES_BIT)
#define NBD_FLAG_SEND_DF (1 << NBD_FLAG_SEND_DF_BIT)
#define NBD_FLAG_CAN_MULTI_CONN (1 << NBD_FLAG_CAN_MULTI_CONN_BIT)
#define NBD_FLAG_SEND_RESIZE (1 << NBD_FLAG_SEND_RESIZE_BIT)
#define NBD_FLAG_SEND_CACHE (1 << NBD_FLAG_SEND_CACHE_BIT)
nbd: Prepare for NBD_CMD_FLAG_FAST_ZERO Commit fe0480d6 and friends added BDRV_REQ_NO_FALLBACK as a way to avoid wasting time on a preliminary write-zero request that will later be rewritten by actual data, if it is known that the write-zero request will use a slow fallback; but in doing so, could not optimize for NBD. The NBD specification is now considering an extension that will allow passing on those semantics; this patch updates the new protocol bits and 'qemu-nbd --list' output to recognize the bit, as well as the new errno value possible when using the new flag; while upcoming patches will improve the client to use the feature when present, and the server to advertise support for it. The NBD spec recommends (but not requires) that ENOTSUP be avoided for all but failures of a fast zero (the only time it is mandatory to avoid an ENOTSUP failure is when fast zero is supported but not requested during write zeroes; the questionable use is for ENOTSUP to other actions like a normal write request). However, clients that get an unexpected ENOTSUP will either already be treating it the same as EINVAL, or may appreciate the extra bit of information. We were equally loose for returning EOVERFLOW in more situations than recommended by the spec, so if it turns out to be a problem in practice, a later patch can tighten handling for both error codes. Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <20190823143726.27062-3-eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> [eblake: tweak commit message, also handle EOPNOTSUPP]
2019-08-23 17:37:23 +03:00
#define NBD_FLAG_SEND_FAST_ZERO (1 << NBD_FLAG_SEND_FAST_ZERO_BIT)
/* New-style handshake (global) flags, sent from server to client, and
control what will happen during handshake phase. */
#define NBD_FLAG_FIXED_NEWSTYLE (1 << 0) /* Fixed newstyle protocol. */
#define NBD_FLAG_NO_ZEROES (1 << 1) /* End handshake without zeroes. */
/* New-style client flags, sent from client to server to control what happens
during handshake phase. */
#define NBD_FLAG_C_FIXED_NEWSTYLE (1 << 0) /* Fixed newstyle protocol. */
#define NBD_FLAG_C_NO_ZEROES (1 << 1) /* End handshake without zeroes. */
/* Option requests. */
#define NBD_OPT_EXPORT_NAME (1)
#define NBD_OPT_ABORT (2)
#define NBD_OPT_LIST (3)
/* #define NBD_OPT_PEEK_EXPORT (4) not in use */
#define NBD_OPT_STARTTLS (5)
#define NBD_OPT_INFO (6)
#define NBD_OPT_GO (7)
#define NBD_OPT_STRUCTURED_REPLY (8)
#define NBD_OPT_LIST_META_CONTEXT (9)
#define NBD_OPT_SET_META_CONTEXT (10)
/* Option reply types. */
#define NBD_REP_ERR(value) ((UINT32_C(1) << 31) | (value))
#define NBD_REP_ACK (1) /* Data sending finished. */
#define NBD_REP_SERVER (2) /* Export description. */
#define NBD_REP_INFO (3) /* NBD_OPT_INFO/GO. */
#define NBD_REP_META_CONTEXT (4) /* NBD_OPT_{LIST,SET}_META_CONTEXT */
#define NBD_REP_ERR_UNSUP NBD_REP_ERR(1) /* Unknown option */
#define NBD_REP_ERR_POLICY NBD_REP_ERR(2) /* Server denied */
#define NBD_REP_ERR_INVALID NBD_REP_ERR(3) /* Invalid length */
#define NBD_REP_ERR_PLATFORM NBD_REP_ERR(4) /* Not compiled in */
#define NBD_REP_ERR_TLS_REQD NBD_REP_ERR(5) /* TLS required */
#define NBD_REP_ERR_UNKNOWN NBD_REP_ERR(6) /* Export unknown */
#define NBD_REP_ERR_SHUTDOWN NBD_REP_ERR(7) /* Server shutting down */
#define NBD_REP_ERR_BLOCK_SIZE_REQD NBD_REP_ERR(8) /* Need INFO_BLOCK_SIZE */
/* Info types, used during NBD_REP_INFO */
#define NBD_INFO_EXPORT 0
#define NBD_INFO_NAME 1
#define NBD_INFO_DESCRIPTION 2
#define NBD_INFO_BLOCK_SIZE 3
/* Request flags, sent from client to server during transmission phase */
#define NBD_CMD_FLAG_FUA (1 << 0) /* 'force unit access' during write */
#define NBD_CMD_FLAG_NO_HOLE (1 << 1) /* don't punch hole on zero run */
#define NBD_CMD_FLAG_DF (1 << 2) /* don't fragment structured read */
#define NBD_CMD_FLAG_REQ_ONE (1 << 3) /* only one extent in BLOCK_STATUS
* reply chunk */
nbd: Prepare for NBD_CMD_FLAG_FAST_ZERO Commit fe0480d6 and friends added BDRV_REQ_NO_FALLBACK as a way to avoid wasting time on a preliminary write-zero request that will later be rewritten by actual data, if it is known that the write-zero request will use a slow fallback; but in doing so, could not optimize for NBD. The NBD specification is now considering an extension that will allow passing on those semantics; this patch updates the new protocol bits and 'qemu-nbd --list' output to recognize the bit, as well as the new errno value possible when using the new flag; while upcoming patches will improve the client to use the feature when present, and the server to advertise support for it. The NBD spec recommends (but not requires) that ENOTSUP be avoided for all but failures of a fast zero (the only time it is mandatory to avoid an ENOTSUP failure is when fast zero is supported but not requested during write zeroes; the questionable use is for ENOTSUP to other actions like a normal write request). However, clients that get an unexpected ENOTSUP will either already be treating it the same as EINVAL, or may appreciate the extra bit of information. We were equally loose for returning EOVERFLOW in more situations than recommended by the spec, so if it turns out to be a problem in practice, a later patch can tighten handling for both error codes. Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <20190823143726.27062-3-eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> [eblake: tweak commit message, also handle EOPNOTSUPP]
2019-08-23 17:37:23 +03:00
#define NBD_CMD_FLAG_FAST_ZERO (1 << 4) /* fail if WRITE_ZEROES is not fast */
/* Supported request types */
enum {
NBD_CMD_READ = 0,
NBD_CMD_WRITE = 1,
NBD_CMD_DISC = 2,
NBD_CMD_FLUSH = 3,
NBD_CMD_TRIM = 4,
NBD_CMD_CACHE = 5,
NBD_CMD_WRITE_ZEROES = 6,
NBD_CMD_BLOCK_STATUS = 7,
};
#define NBD_DEFAULT_PORT 10809
/* Maximum size of a single READ/WRITE data buffer */
#define NBD_MAX_BUFFER_SIZE (32 * 1024 * 1024)
/*
* Maximum size of a protocol string (export name, metadata context name,
* etc.). Use malloc rather than stack allocation for storage of a
* string.
*/
#define NBD_MAX_STRING_SIZE 4096
/* Two types of reply structures */
#define NBD_SIMPLE_REPLY_MAGIC 0x67446698
#define NBD_STRUCTURED_REPLY_MAGIC 0x668e33ef
/* Structured reply flags */
#define NBD_REPLY_FLAG_DONE (1 << 0) /* This reply-chunk is last */
/* Structured reply types */
#define NBD_REPLY_ERR(value) ((1 << 15) | (value))
#define NBD_REPLY_TYPE_NONE 0
#define NBD_REPLY_TYPE_OFFSET_DATA 1
#define NBD_REPLY_TYPE_OFFSET_HOLE 2
#define NBD_REPLY_TYPE_BLOCK_STATUS 5
#define NBD_REPLY_TYPE_ERROR NBD_REPLY_ERR(1)
#define NBD_REPLY_TYPE_ERROR_OFFSET NBD_REPLY_ERR(2)
/* Extent flags for base:allocation in NBD_REPLY_TYPE_BLOCK_STATUS */
#define NBD_STATE_HOLE (1 << 0)
#define NBD_STATE_ZERO (1 << 1)
/* Extent flags for qemu:dirty-bitmap in NBD_REPLY_TYPE_BLOCK_STATUS */
#define NBD_STATE_DIRTY (1 << 0)
/* No flags needed for qemu:allocation-depth in NBD_REPLY_TYPE_BLOCK_STATUS */
static inline bool nbd_reply_type_is_error(int type)
{
return type & (1 << 15);
}
/* NBD errors are based on errno numbers, so there is a 1:1 mapping,
* but only a limited set of errno values is specified in the protocol.
* Everything else is squashed to EINVAL.
*/
#define NBD_SUCCESS 0
#define NBD_EPERM 1
#define NBD_EIO 5
#define NBD_ENOMEM 12
#define NBD_EINVAL 22
#define NBD_ENOSPC 28
#define NBD_EOVERFLOW 75
nbd: Prepare for NBD_CMD_FLAG_FAST_ZERO Commit fe0480d6 and friends added BDRV_REQ_NO_FALLBACK as a way to avoid wasting time on a preliminary write-zero request that will later be rewritten by actual data, if it is known that the write-zero request will use a slow fallback; but in doing so, could not optimize for NBD. The NBD specification is now considering an extension that will allow passing on those semantics; this patch updates the new protocol bits and 'qemu-nbd --list' output to recognize the bit, as well as the new errno value possible when using the new flag; while upcoming patches will improve the client to use the feature when present, and the server to advertise support for it. The NBD spec recommends (but not requires) that ENOTSUP be avoided for all but failures of a fast zero (the only time it is mandatory to avoid an ENOTSUP failure is when fast zero is supported but not requested during write zeroes; the questionable use is for ENOTSUP to other actions like a normal write request). However, clients that get an unexpected ENOTSUP will either already be treating it the same as EINVAL, or may appreciate the extra bit of information. We were equally loose for returning EOVERFLOW in more situations than recommended by the spec, so if it turns out to be a problem in practice, a later patch can tighten handling for both error codes. Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <20190823143726.27062-3-eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> [eblake: tweak commit message, also handle EOPNOTSUPP]
2019-08-23 17:37:23 +03:00
#define NBD_ENOTSUP 95
#define NBD_ESHUTDOWN 108
/* Details collected by NBD_OPT_EXPORT_NAME and NBD_OPT_GO */
struct NBDExportInfo {
/* Set by client before nbd_receive_negotiate() */
bool request_sizes;
char *x_dirty_bitmap;
nbd/client: Add nbd_receive_export_list() We want to be able to detect whether a given qemu NBD server is exposing the right export(s) and dirty bitmaps, at least for regression testing. We could use 'nbd-client -l' from the upstream NBD project to list exports, but it's annoying to rely on out-of-tree binaries; furthermore, nbd-client doesn't necessarily know about all of the qemu NBD extensions. Thus, we plan on adding a new mode to qemu-nbd that merely sniffs all possible information from the server during handshake phase, then disconnects and dumps the information. This patch adds the low-level client code for grabbing the list of exports. It benefits from the recent refactoring patches, in order to share as much code as possible when it comes to doing validation of server replies. The resulting information is stored in an array of NBDExportInfo which has been expanded to any description string, along with a convenience function for freeing the list. Note: a malicious server could exhaust memory of a client by feeding an unending loop of exports; perhaps we should place a limit on how many we are willing to receive. But note that a server could reasonably be serving an export for every file in a large directory, where an arbitrary limit in the client means we can't list anything from such a server; the same happens if we just run until the client fails to malloc() and thus dies by an abort(), where the limit is no longer arbitrary but determined by available memory. Since the client is already planning on being short-lived, it's hard to call this a denial of service attack that would starve off other uses, so it does not appear to be a security issue. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Richard W.M. Jones <rjones@redhat.com> Message-Id: <20190117193658.16413-18-eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
2019-01-17 22:36:54 +03:00
/* Set by client before nbd_receive_negotiate(), or by server results
* during nbd_receive_export_list() */
char *name; /* must be non-NULL */
/* In-out fields, set by client before nbd_receive_negotiate() and
* updated by server results during nbd_receive_negotiate() */
bool structured_reply;
bool base_allocation; /* base:allocation context for NBD_CMD_BLOCK_STATUS */
nbd/client: Add nbd_receive_export_list() We want to be able to detect whether a given qemu NBD server is exposing the right export(s) and dirty bitmaps, at least for regression testing. We could use 'nbd-client -l' from the upstream NBD project to list exports, but it's annoying to rely on out-of-tree binaries; furthermore, nbd-client doesn't necessarily know about all of the qemu NBD extensions. Thus, we plan on adding a new mode to qemu-nbd that merely sniffs all possible information from the server during handshake phase, then disconnects and dumps the information. This patch adds the low-level client code for grabbing the list of exports. It benefits from the recent refactoring patches, in order to share as much code as possible when it comes to doing validation of server replies. The resulting information is stored in an array of NBDExportInfo which has been expanded to any description string, along with a convenience function for freeing the list. Note: a malicious server could exhaust memory of a client by feeding an unending loop of exports; perhaps we should place a limit on how many we are willing to receive. But note that a server could reasonably be serving an export for every file in a large directory, where an arbitrary limit in the client means we can't list anything from such a server; the same happens if we just run until the client fails to malloc() and thus dies by an abort(), where the limit is no longer arbitrary but determined by available memory. Since the client is already planning on being short-lived, it's hard to call this a denial of service attack that would starve off other uses, so it does not appear to be a security issue. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Richard W.M. Jones <rjones@redhat.com> Message-Id: <20190117193658.16413-18-eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
2019-01-17 22:36:54 +03:00
/* Set by server results during nbd_receive_negotiate() and
* nbd_receive_export_list() */
uint64_t size;
uint16_t flags;
uint32_t min_block;
uint32_t opt_block;
uint32_t max_block;
uint32_t context_id;
nbd/client: Add nbd_receive_export_list() We want to be able to detect whether a given qemu NBD server is exposing the right export(s) and dirty bitmaps, at least for regression testing. We could use 'nbd-client -l' from the upstream NBD project to list exports, but it's annoying to rely on out-of-tree binaries; furthermore, nbd-client doesn't necessarily know about all of the qemu NBD extensions. Thus, we plan on adding a new mode to qemu-nbd that merely sniffs all possible information from the server during handshake phase, then disconnects and dumps the information. This patch adds the low-level client code for grabbing the list of exports. It benefits from the recent refactoring patches, in order to share as much code as possible when it comes to doing validation of server replies. The resulting information is stored in an array of NBDExportInfo which has been expanded to any description string, along with a convenience function for freeing the list. Note: a malicious server could exhaust memory of a client by feeding an unending loop of exports; perhaps we should place a limit on how many we are willing to receive. But note that a server could reasonably be serving an export for every file in a large directory, where an arbitrary limit in the client means we can't list anything from such a server; the same happens if we just run until the client fails to malloc() and thus dies by an abort(), where the limit is no longer arbitrary but determined by available memory. Since the client is already planning on being short-lived, it's hard to call this a denial of service attack that would starve off other uses, so it does not appear to be a security issue. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Richard W.M. Jones <rjones@redhat.com> Message-Id: <20190117193658.16413-18-eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
2019-01-17 22:36:54 +03:00
/* Set by server results during nbd_receive_export_list() */
char *description;
nbd/client: Add meta contexts to nbd_receive_export_list() We want to be able to detect whether a given qemu NBD server is exposing the right export(s) and dirty bitmaps, at least for regression testing. We could use 'nbd-client -l' from the upstream NBD project to list exports, but it's annoying to rely on out-of-tree binaries; furthermore, nbd-client doesn't necessarily know about all of the qemu NBD extensions. Thus, we plan on adding a new mode to qemu-nbd that merely sniffs all possible information from the server during handshake phase, then disconnects and dumps the information. This patch continues the work of the previous patch, by adding the ability to track the list of available meta contexts into NBDExportInfo. It benefits from the recent refactoring patches with a new nbd_list_meta_contexts() that reuses much of the same framework as setting a meta context. Note: a malicious server could exhaust memory of a client by feeding an unending loop of contexts; perhaps we could place a limit on how many we are willing to receive. But this is no different from our earlier analysis on a server sending an unending list of exports, and the death of a client due to memory exhaustion when the client was going to exit soon anyways is not really a denial of service attack. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Richard W.M. Jones <rjones@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20190117193658.16413-19-eblake@redhat.com>
2019-01-17 22:36:55 +03:00
int n_contexts;
char **contexts;
};
typedef struct NBDExportInfo NBDExportInfo;
int nbd_receive_negotiate(AioContext *aio_context, QIOChannel *ioc,
QCryptoTLSCreds *tlscreds,
const char *hostname, QIOChannel **outioc,
NBDExportInfo *info, Error **errp);
nbd/client: Add nbd_receive_export_list() We want to be able to detect whether a given qemu NBD server is exposing the right export(s) and dirty bitmaps, at least for regression testing. We could use 'nbd-client -l' from the upstream NBD project to list exports, but it's annoying to rely on out-of-tree binaries; furthermore, nbd-client doesn't necessarily know about all of the qemu NBD extensions. Thus, we plan on adding a new mode to qemu-nbd that merely sniffs all possible information from the server during handshake phase, then disconnects and dumps the information. This patch adds the low-level client code for grabbing the list of exports. It benefits from the recent refactoring patches, in order to share as much code as possible when it comes to doing validation of server replies. The resulting information is stored in an array of NBDExportInfo which has been expanded to any description string, along with a convenience function for freeing the list. Note: a malicious server could exhaust memory of a client by feeding an unending loop of exports; perhaps we should place a limit on how many we are willing to receive. But note that a server could reasonably be serving an export for every file in a large directory, where an arbitrary limit in the client means we can't list anything from such a server; the same happens if we just run until the client fails to malloc() and thus dies by an abort(), where the limit is no longer arbitrary but determined by available memory. Since the client is already planning on being short-lived, it's hard to call this a denial of service attack that would starve off other uses, so it does not appear to be a security issue. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Richard W.M. Jones <rjones@redhat.com> Message-Id: <20190117193658.16413-18-eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
2019-01-17 22:36:54 +03:00
void nbd_free_export_list(NBDExportInfo *info, int count);
int nbd_receive_export_list(QIOChannel *ioc, QCryptoTLSCreds *tlscreds,
const char *hostname, NBDExportInfo **info,
Error **errp);
int nbd_init(int fd, QIOChannelSocket *sioc, NBDExportInfo *info,
Error **errp);
int nbd_send_request(QIOChannel *ioc, NBDRequest *request);
int coroutine_fn nbd_receive_reply(BlockDriverState *bs, QIOChannel *ioc,
NBDReply *reply, Error **errp);
int nbd_client(int fd);
int nbd_disconnect(int fd);
int nbd_errno_to_system_errno(int err);
typedef struct NBDExport NBDExport;
typedef struct NBDClient NBDClient;
void nbd_export_set_on_eject_blk(BlockExport *exp, BlockBackend *blk);
AioContext *nbd_export_aio_context(NBDExport *exp);
NBDExport *nbd_export_find(const char *name);
void nbd_client_new(QIOChannelSocket *sioc,
QCryptoTLSCreds *tlscreds,
qemu-nbd: add support for authorization of TLS clients Currently any client which can complete the TLS handshake is able to use the NBD server. The server admin can turn on the 'verify-peer' option for the x509 creds to require the client to provide a x509 certificate. This means the client will have to acquire a certificate from the CA before they are permitted to use the NBD server. This is still a fairly low bar to cross. This adds a '--tls-authz OBJECT-ID' option to the qemu-nbd command which takes the ID of a previously added 'QAuthZ' object instance. This will be used to validate the client's x509 distinguished name. Clients failing the authorization check will not be permitted to use the NBD server. For example to setup authorization that only allows connection from a client whose x509 certificate distinguished name is CN=laptop.example.com,O=Example Org,L=London,ST=London,C=GB escape the commas in the name and use: qemu-nbd --object tls-creds-x509,id=tls0,dir=/home/berrange/qemutls,\ endpoint=server,verify-peer=yes \ --object 'authz-simple,id=auth0,identity=CN=laptop.example.com,,\ O=Example Org,,L=London,,ST=London,,C=GB' \ --tls-creds tls0 \ --tls-authz authz0 \ ....other qemu-nbd args... NB: a real shell command line would not have leading whitespace after the line continuation, it is just included here for clarity. Reviewed-by: Juan Quintela <quintela@redhat.com> Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Message-Id: <20190227162035.18543-2-berrange@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> [eblake: split long line in --help text, tweak 233 to show that whitespace after ,, in identity= portion is actually okay] Signed-off-by: Eric Blake <eblake@redhat.com>
2019-02-27 19:20:33 +03:00
const char *tlsauthz,
nbd: Fix regression on resiliency to port scan Back in qemu 2.5, qemu-nbd was immune to port probes (a transient server would not quit, regardless of how many probe connections came and went, until a connection actually negotiated). But we broke that in commit ee7d7aa when removing the return value to nbd_client_new(), although that patch also introduced a bug causing an assertion failure on a client that fails negotiation. We then made it worse during refactoring in commit 1a6245a (a segfault before we could even assert); the (masked) assertion was cleaned up in d3780c2 (still in 2.6), and just recently we finally fixed the segfault ("nbd: Fully intialize client in case of failed negotiation"). But that still means that ever since we added TLS support to qemu-nbd, we have been vulnerable to an ill-timed port-scan being able to cause a denial of service by taking down qemu-nbd before a real client has a chance to connect. Since negotiation is now handled asynchronously via coroutines, we no longer have a synchronous point of return by re-adding a return value to nbd_client_new(). So this patch instead wires things up to pass the negotiation status through the close_fn callback function. Simple test across two terminals: $ qemu-nbd -f raw -p 30001 file $ nmap 127.0.0.1 -p 30001 && \ qemu-io -c 'r 0 512' -f raw nbd://localhost:30001 Note that this patch does not change what constitutes successful negotiation (thus, a client must enter transmission phase before that client can be considered as a reason to terminate the server when the connection ends). Perhaps we may want to tweak things in a later patch to also treat a client that uses NBD_OPT_ABORT as being a 'successful' negotiation (the client correctly talked the NBD protocol, and informed us it was not going to use our export after all), but that's a discussion for another day. Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1451614 Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <20170608222617.20376-1-eblake@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2017-06-09 01:26:17 +03:00
void (*close_fn)(NBDClient *, bool));
void nbd_client_get(NBDClient *client);
void nbd_client_put(NBDClient *client);
void nbd_server_is_qemu_nbd(int max_connections);
bool nbd_server_is_running(void);
nbd/server: Allow MULTI_CONN for shared writable exports According to the NBD spec, a server that advertises NBD_FLAG_CAN_MULTI_CONN promises that multiple client connections will not see any cache inconsistencies: when properly separated by a single flush, actions performed by one client will be visible to another client, regardless of which client did the flush. We always satisfy these conditions in qemu - even when we support multiple clients, ALL clients go through a single point of reference into the block layer, with no local caching. The effect of one client is instantly visible to the next client. Even if our backend were a network device, we argue that any multi-path caching effects that would cause inconsistencies in back-to-back actions not seeing the effect of previous actions would be a bug in that backend, and not the fault of caching in qemu. As such, it is safe to unconditionally advertise CAN_MULTI_CONN for any qemu NBD server situation that supports parallel clients. Note, however, that we don't want to advertise CAN_MULTI_CONN when we know that a second client cannot connect (for historical reasons, qemu-nbd defaults to a single connection while nbd-server-add and QMP commands default to unlimited connections; but we already have existing means to let either style of NBD server creation alter those defaults). This is visible by no longer advertising MULTI_CONN for 'qemu-nbd -r' without -e, as in the iotest nbd-qemu-allocation. The harder part of this patch is setting up an iotest to demonstrate behavior of multiple NBD clients to a single server. It might be possible with parallel qemu-io processes, but I found it easier to do in python with the help of libnbd, and help from Nir and Vladimir in writing the test. Signed-off-by: Eric Blake <eblake@redhat.com> Suggested-by: Nir Soffer <nsoffer@redhat.com> Suggested-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru> Message-Id: <20220512004924.417153-3-eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2022-05-12 03:49:24 +03:00
int nbd_server_max_connections(void);
void nbd_server_start(SocketAddress *addr, const char *tls_creds,
const char *tls_authz, uint32_t max_connections,
Error **errp);
void nbd_server_start_options(NbdServerOptions *arg, Error **errp);
/* nbd_read
* Reads @size bytes from @ioc. Returns 0 on success.
*/
static inline int nbd_read(QIOChannel *ioc, void *buffer, size_t size,
const char *desc, Error **errp)
{
nbd: Use ERRP_GUARD() If we want to check error after errp-function call, we need to introduce local_err and then propagate it to errp. Instead, use the ERRP_GUARD() macro, benefits are: 1. No need of explicit error_propagate call 2. No need of explicit local_err variable: use errp directly 3. ERRP_GUARD() leaves errp as is if it's not NULL or &error_fatal, this means that we don't break error_abort (we'll abort on error_set, not on error_propagate) If we want to add some info to errp (by error_prepend() or error_append_hint()), we must use the ERRP_GUARD() macro. Otherwise, this info will not be added when errp == &error_fatal (the program will exit prior to the error_append_hint() or error_prepend() call). Fix several such cases, e.g. in nbd_read(). This commit is generated by command sed -n '/^Network Block Device (NBD)$/,/^$/{s/^F: //p}' \ MAINTAINERS | \ xargs git ls-files | grep '\.[hc]$' | \ xargs spatch \ --sp-file scripts/coccinelle/errp-guard.cocci \ --macro-file scripts/cocci-macro-file.h \ --in-place --no-show-diff --max-width 80 Reported-by: Kevin Wolf <kwolf@redhat.com> Reported-by: Greg Kurz <groug@kaod.org> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> [Commit message tweaked] Signed-off-by: Markus Armbruster <armbru@redhat.com> Message-Id: <20200707165037.1026246-8-armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> [ERRP_AUTO_PROPAGATE() renamed to ERRP_GUARD(), and auto-propagated-errp.cocci to errp-guard.cocci. Commit message tweaked again.]
2020-07-07 19:50:36 +03:00
ERRP_GUARD();
int ret = qio_channel_read_all(ioc, buffer, size, errp) < 0 ? -EIO : 0;
if (ret < 0) {
if (desc) {
error_prepend(errp, "Failed to read %s: ", desc);
}
return ret;
}
return 0;
}
#define DEF_NBD_READ_N(bits) \
static inline int nbd_read##bits(QIOChannel *ioc, \
uint##bits##_t *val, \
const char *desc, Error **errp) \
{ \
int ret = nbd_read(ioc, val, sizeof(*val), desc, errp); \
if (ret < 0) { \
return ret; \
} \
*val = be##bits##_to_cpu(*val); \
return 0; \
}
DEF_NBD_READ_N(16) /* Defines nbd_read16(). */
DEF_NBD_READ_N(32) /* Defines nbd_read32(). */
DEF_NBD_READ_N(64) /* Defines nbd_read64(). */
#undef DEF_NBD_READ_N
static inline bool nbd_reply_is_simple(NBDReply *reply)
{
return reply->magic == NBD_SIMPLE_REPLY_MAGIC;
}
static inline bool nbd_reply_is_structured(NBDReply *reply)
{
return reply->magic == NBD_STRUCTURED_REPLY_MAGIC;
}
const char *nbd_reply_type_lookup(uint16_t type);
const char *nbd_opt_lookup(uint32_t opt);
const char *nbd_rep_lookup(uint32_t rep);
const char *nbd_info_lookup(uint16_t info);
const char *nbd_cmd_lookup(uint16_t info);
const char *nbd_err_lookup(int err);
/* nbd/client-connection.c */
typedef struct NBDClientConnection NBDClientConnection;
void nbd_client_connection_enable_retry(NBDClientConnection *conn);
NBDClientConnection *nbd_client_connection_new(const SocketAddress *saddr,
bool do_negotiation,
const char *export_name,
const char *x_dirty_bitmap,
QCryptoTLSCreds *tlscreds,
const char *tlshostname);
void nbd_client_connection_release(NBDClientConnection *conn);
QIOChannel *coroutine_fn
nbd_co_establish_connection(NBDClientConnection *conn, NBDExportInfo *info,
bool blocking, Error **errp);
void nbd_co_establish_connection_cancel(NBDClientConnection *conn);
#endif