diff options
author | Peter Maydell <peter.maydell@linaro.org> | 2021-07-10 19:55:20 +0100 |
---|---|---|
committer | Peter Maydell <peter.maydell@linaro.org> | 2021-07-10 19:55:21 +0100 |
commit | 42e1d798a6a01817bdcf722ac27eea01531e21cd (patch) | |
tree | 9c97b2ca0318c43e62c99753a57236b4fab788d6 /block | |
parent | fc32b91a88cc9cd560da5488bdca4d69f2bac620 (diff) | |
parent | e60edf69e2f64e818466019313517a2e6d6b63f4 (diff) | |
download | qemu-42e1d798a6a01817bdcf722ac27eea01531e21cd.zip |
Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging
Block layer patches
- Make blockdev-reopen stable
- Remove deprecated qemu-img backing file without format
- rbd: Convert to coroutines and add write zeroes support
- rbd: Updated MAINTAINERS
- export/fuse: Allow other users access to the export
- vhost-user: Fix backends without multiqueue support
- Fix drive-backup transaction endless drained section
# gpg: Signature made Fri 09 Jul 2021 13:49:22 BST
# gpg: using RSA key DC3DEB159A9AF95D3D7456FE7F09B272C88F2FD6
# gpg: issuer "kwolf@redhat.com"
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>" [full]
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74 56FE 7F09 B272 C88F 2FD6
* remotes/kevin/tags/for-upstream: (28 commits)
block: Make blockdev-reopen stable API
iotests: Test reopening multiple devices at the same time
block: Support multiple reopening with x-blockdev-reopen
block: Acquire AioContexts during bdrv_reopen_multiple()
block: Add bdrv_reopen_queue_free()
qcow2: Fix dangling pointer after reopen for 'file'
qemu-img: Improve error for rebase without backing format
qemu-img: Require -F with -b backing image
qcow2: Prohibit backing file changes in 'qemu-img amend'
blockdev: fix drive-backup transaction endless drained section
vhost-user: Fix backends without multiqueue support
MAINTAINERS: add block/rbd.c reviewer
block/rbd: fix type of task->complete
iotests/fuse-allow-other: Test allow-other
iotests/308: Test +w on read-only FUSE exports
export/fuse: Let permissions be adjustable
export/fuse: Give SET_ATTR_SIZE its own branch
export/fuse: Add allow-other option
export/fuse: Pass default_permissions for mount
util/uri: do not check argument of uri_free()
...
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Diffstat (limited to 'block')
-rw-r--r-- | block/export/fuse.c | 121 | ||||
-rw-r--r-- | block/nfs.c | 4 | ||||
-rw-r--r-- | block/qcow2.c | 42 | ||||
-rw-r--r-- | block/rbd.c | 749 | ||||
-rw-r--r-- | block/replication.c | 7 | ||||
-rw-r--r-- | block/ssh.c | 4 |
6 files changed, 611 insertions, 316 deletions
diff --git a/block/export/fuse.c b/block/export/fuse.c index 38f74c94da..ada9e263eb 100644 --- a/block/export/fuse.c +++ b/block/export/fuse.c @@ -46,6 +46,12 @@ typedef struct FuseExport { char *mountpoint; bool writable; bool growable; + /* Whether allow_other was used as a mount option or not */ + bool allow_other; + + mode_t st_mode; + uid_t st_uid; + gid_t st_gid; } FuseExport; static GHashTable *exports; @@ -57,7 +63,7 @@ static void fuse_export_delete(BlockExport *exp); static void init_exports_table(void); static int setup_fuse_export(FuseExport *exp, const char *mountpoint, - Error **errp); + bool allow_other, Error **errp); static void read_from_fuse_export(void *opaque); static bool is_regular_file(const char *path, Error **errp); @@ -118,7 +124,29 @@ static int fuse_export_create(BlockExport *blk_exp, exp->writable = blk_exp_args->writable; exp->growable = args->growable; - ret = setup_fuse_export(exp, args->mountpoint, errp); + /* set default */ + if (!args->has_allow_other) { + args->allow_other = FUSE_EXPORT_ALLOW_OTHER_AUTO; + } + + exp->st_mode = S_IFREG | S_IRUSR; + if (exp->writable) { + exp->st_mode |= S_IWUSR; + } + exp->st_uid = getuid(); + exp->st_gid = getgid(); + + if (args->allow_other == FUSE_EXPORT_ALLOW_OTHER_AUTO) { + /* Ignore errors on our first attempt */ + ret = setup_fuse_export(exp, args->mountpoint, true, NULL); + exp->allow_other = ret == 0; + if (ret < 0) { + ret = setup_fuse_export(exp, args->mountpoint, false, errp); + } + } else { + exp->allow_other = args->allow_other == FUSE_EXPORT_ALLOW_OTHER_ON; + ret = setup_fuse_export(exp, args->mountpoint, exp->allow_other, errp); + } if (ret < 0) { goto fail; } @@ -146,15 +174,20 @@ static void init_exports_table(void) * Create exp->fuse_session and mount it. */ static int setup_fuse_export(FuseExport *exp, const char *mountpoint, - Error **errp) + bool allow_other, Error **errp) { const char *fuse_argv[4]; char *mount_opts; struct fuse_args fuse_args; int ret; - /* Needs to match what fuse_init() sets. Only max_read must be supplied. */ - mount_opts = g_strdup_printf("max_read=%zu", FUSE_MAX_BOUNCE_BYTES); + /* + * max_read needs to match what fuse_init() sets. + * max_write need not be supplied. + */ + mount_opts = g_strdup_printf("max_read=%zu,default_permissions%s", + FUSE_MAX_BOUNCE_BYTES, + allow_other ? ",allow_other" : ""); fuse_argv[0] = ""; /* Dummy program name */ fuse_argv[1] = "-o"; @@ -316,7 +349,6 @@ static void fuse_getattr(fuse_req_t req, fuse_ino_t inode, int64_t length, allocated_blocks; time_t now = time(NULL); FuseExport *exp = fuse_req_userdata(req); - mode_t mode; length = blk_getlength(exp->common.blk); if (length < 0) { @@ -331,17 +363,12 @@ static void fuse_getattr(fuse_req_t req, fuse_ino_t inode, allocated_blocks = DIV_ROUND_UP(allocated_blocks, 512); } - mode = S_IFREG | S_IRUSR; - if (exp->writable) { - mode |= S_IWUSR; - } - statbuf = (struct stat) { .st_ino = inode, - .st_mode = mode, + .st_mode = exp->st_mode, .st_nlink = 1, - .st_uid = getuid(), - .st_gid = getgid(), + .st_uid = exp->st_uid, + .st_gid = exp->st_gid, .st_size = length, .st_blksize = blk_bs(exp->common.blk)->bl.request_alignment, .st_blocks = allocated_blocks, @@ -387,28 +414,76 @@ static int fuse_do_truncate(const FuseExport *exp, int64_t size, } /** - * Let clients set file attributes. Only resizing is supported. + * Let clients set file attributes. Only resizing and changing + * permissions (st_mode, st_uid, st_gid) is allowed. + * Changing permissions is only allowed as far as it will actually + * permit access: Read-only exports cannot be given +w, and exports + * without allow_other cannot be given a different UID or GID, and + * they cannot be given non-owner access. */ static void fuse_setattr(fuse_req_t req, fuse_ino_t inode, struct stat *statbuf, int to_set, struct fuse_file_info *fi) { FuseExport *exp = fuse_req_userdata(req); + int supported_attrs; int ret; - if (!exp->writable) { - fuse_reply_err(req, EACCES); - return; + supported_attrs = FUSE_SET_ATTR_SIZE | FUSE_SET_ATTR_MODE; + if (exp->allow_other) { + supported_attrs |= FUSE_SET_ATTR_UID | FUSE_SET_ATTR_GID; } - if (to_set & ~FUSE_SET_ATTR_SIZE) { + if (to_set & ~supported_attrs) { fuse_reply_err(req, ENOTSUP); return; } - ret = fuse_do_truncate(exp, statbuf->st_size, true, PREALLOC_MODE_OFF); - if (ret < 0) { - fuse_reply_err(req, -ret); - return; + /* Do some argument checks first before committing to anything */ + if (to_set & FUSE_SET_ATTR_MODE) { + /* + * Without allow_other, non-owners can never access the export, so do + * not allow setting permissions for them + */ + if (!exp->allow_other && + (statbuf->st_mode & (S_IRWXG | S_IRWXO)) != 0) + { + fuse_reply_err(req, EPERM); + return; + } + + /* +w for read-only exports makes no sense, disallow it */ + if (!exp->writable && + (statbuf->st_mode & (S_IWUSR | S_IWGRP | S_IWOTH)) != 0) + { + fuse_reply_err(req, EROFS); + return; + } + } + + if (to_set & FUSE_SET_ATTR_SIZE) { + if (!exp->writable) { + fuse_reply_err(req, EACCES); + return; + } + + ret = fuse_do_truncate(exp, statbuf->st_size, true, PREALLOC_MODE_OFF); + if (ret < 0) { + fuse_reply_err(req, -ret); + return; + } + } + + if (to_set & FUSE_SET_ATTR_MODE) { + /* Ignore FUSE-supplied file type, only change the mode */ + exp->st_mode = (statbuf->st_mode & 07777) | S_IFREG; + } + + if (to_set & FUSE_SET_ATTR_UID) { + exp->st_uid = statbuf->st_uid; + } + + if (to_set & FUSE_SET_ATTR_GID) { + exp->st_gid = statbuf->st_gid; } fuse_getattr(req, inode, fi); diff --git a/block/nfs.c b/block/nfs.c index 7dff64f489..9aeaefb364 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -147,9 +147,7 @@ out: if (qp) { query_params_free(qp); } - if (uri) { - uri_free(uri); - } + uri_free(uri); return ret; } diff --git a/block/qcow2.c b/block/qcow2.c index ee4530cdbd..9f1b6461c8 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -1926,6 +1926,7 @@ static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp) static int qcow2_reopen_prepare(BDRVReopenState *state, BlockReopenQueue *queue, Error **errp) { + BDRVQcow2State *s = state->bs->opaque; Qcow2ReopenState *r; int ret; @@ -1956,6 +1957,16 @@ static int qcow2_reopen_prepare(BDRVReopenState *state, } } + /* + * Without an external data file, s->data_file points to the same BdrvChild + * as bs->file. It needs to be resynced after reopen because bs->file may + * be changed. We can't use it in the meantime. + */ + if (!has_data_file(state->bs)) { + assert(s->data_file == state->bs->file); + s->data_file = NULL; + } + return 0; fail: @@ -1966,7 +1977,16 @@ fail: static void qcow2_reopen_commit(BDRVReopenState *state) { + BDRVQcow2State *s = state->bs->opaque; + qcow2_update_options_commit(state->bs, state->opaque); + if (!s->data_file) { + /* + * If we don't have an external data file, s->data_file was cleared by + * qcow2_reopen_prepare() and needs to be updated. + */ + s->data_file = state->bs->file; + } g_free(state->opaque); } @@ -1990,6 +2010,15 @@ static void qcow2_reopen_commit_post(BDRVReopenState *state) static void qcow2_reopen_abort(BDRVReopenState *state) { + BDRVQcow2State *s = state->bs->opaque; + + if (!s->data_file) { + /* + * If we don't have an external data file, s->data_file was cleared by + * qcow2_reopen_prepare() and needs to be restored. + */ + s->data_file = state->bs->file; + } qcow2_update_options_abort(state->bs, state->opaque); g_free(state->opaque); } @@ -5620,15 +5649,10 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, if (backing_file || backing_format) { if (g_strcmp0(backing_file, s->image_backing_file) || g_strcmp0(backing_format, s->image_backing_format)) { - warn_report("Deprecated use of amend to alter the backing file; " - "use qemu-img rebase instead"); - } - ret = qcow2_change_backing_file(bs, - backing_file ?: s->image_backing_file, - backing_format ?: s->image_backing_format); - if (ret < 0) { - error_setg_errno(errp, -ret, "Failed to change the backing file"); - return ret; + error_setg(errp, "Cannot amend the backing file"); + error_append_hint(errp, + "You can use 'qemu-img rebase' instead.\n"); + return -EINVAL; } } diff --git a/block/rbd.c b/block/rbd.c index 26f64cce7c..dcf82b15b8 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -55,49 +55,30 @@ * leading "\". */ -/* rbd_aio_discard added in 0.1.2 */ -#if LIBRBD_VERSION_CODE >= LIBRBD_VERSION(0, 1, 2) -#define LIBRBD_SUPPORTS_DISCARD -#else -#undef LIBRBD_SUPPORTS_DISCARD -#endif - #define OBJ_MAX_SIZE (1UL << OBJ_DEFAULT_OBJ_ORDER) #define RBD_MAX_SNAPS 100 -/* The LIBRBD_SUPPORTS_IOVEC is defined in librbd.h */ -#ifdef LIBRBD_SUPPORTS_IOVEC -#define LIBRBD_USE_IOVEC 1 -#else -#define LIBRBD_USE_IOVEC 0 -#endif +#define RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN 8 + +static const char rbd_luks_header_verification[ + RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN] = { + 'L', 'U', 'K', 'S', 0xBA, 0xBE, 0, 1 +}; + +static const char rbd_luks2_header_verification[ + RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN] = { + 'L', 'U', 'K', 'S', 0xBA, 0xBE, 0, 2 +}; typedef enum { RBD_AIO_READ, RBD_AIO_WRITE, RBD_AIO_DISCARD, - RBD_AIO_FLUSH + RBD_AIO_FLUSH, + RBD_AIO_WRITE_ZEROES } RBDAIOCmd; -typedef struct RBDAIOCB { - BlockAIOCB common; - int64_t ret; - QEMUIOVector *qiov; - char *bounce; - RBDAIOCmd cmd; - int error; - struct BDRVRBDState *s; -} RBDAIOCB; - -typedef struct RADOSCB { - RBDAIOCB *acb; - struct BDRVRBDState *s; - int64_t size; - char *buf; - int64_t ret; -} RADOSCB; - typedef struct BDRVRBDState { rados_t cluster; rados_ioctx_t io_ctx; @@ -106,8 +87,16 @@ typedef struct BDRVRBDState { char *snap; char *namespace; uint64_t image_size; + uint64_t object_size; } BDRVRBDState; +typedef struct RBDTask { + BlockDriverState *bs; + Coroutine *co; + bool complete; + int64_t ret; +} RBDTask; + static int qemu_rbd_connect(rados_t *cluster, rados_ioctx_t *io_ctx, BlockdevOptionsRbd *opts, bool cache, const char *keypairs, const char *secretid, @@ -251,14 +240,6 @@ done: return; } - -static void qemu_rbd_refresh_limits(BlockDriverState *bs, Error **errp) -{ - /* XXX Does RBD support AIO on less than 512-byte alignment? */ - bs->bl.request_alignment = 512; -} - - static int qemu_rbd_set_auth(rados_t cluster, BlockdevOptionsRbd *opts, Error **errp) { @@ -340,16 +321,202 @@ static int qemu_rbd_set_keypairs(rados_t cluster, const char *keypairs_json, return ret; } -static void qemu_rbd_memset(RADOSCB *rcb, int64_t offs) +#ifdef LIBRBD_SUPPORTS_ENCRYPTION +static int qemu_rbd_convert_luks_options( + RbdEncryptionOptionsLUKSBase *luks_opts, + char **passphrase, + size_t *passphrase_len, + Error **errp) +{ + return qcrypto_secret_lookup(luks_opts->key_secret, (uint8_t **)passphrase, + passphrase_len, errp); +} + +static int qemu_rbd_convert_luks_create_options( + RbdEncryptionCreateOptionsLUKSBase *luks_opts, + rbd_encryption_algorithm_t *alg, + char **passphrase, + size_t *passphrase_len, + Error **errp) { - if (LIBRBD_USE_IOVEC) { - RBDAIOCB *acb = rcb->acb; - iov_memset(acb->qiov->iov, acb->qiov->niov, offs, 0, - acb->qiov->size - offs); + int r = 0; + + r = qemu_rbd_convert_luks_options( + qapi_RbdEncryptionCreateOptionsLUKSBase_base(luks_opts), + passphrase, passphrase_len, errp); + if (r < 0) { + return r; + } + + if (luks_opts->has_cipher_alg) { + switch (luks_opts->cipher_alg) { + case QCRYPTO_CIPHER_ALG_AES_128: { + *alg = RBD_ENCRYPTION_ALGORITHM_AES128; + break; + } + case QCRYPTO_CIPHER_ALG_AES_256: { + *alg = RBD_ENCRYPTION_ALGORITHM_AES256; + break; + } + default: { + r = -ENOTSUP; + error_setg_errno(errp, -r, "unknown encryption algorithm: %u", + luks_opts->cipher_alg); + return r; + } + } } else { - memset(rcb->buf + offs, 0, rcb->size - offs); + /* default alg */ + *alg = RBD_ENCRYPTION_ALGORITHM_AES256; + } + + return 0; +} + +static int qemu_rbd_encryption_format(rbd_image_t image, + RbdEncryptionCreateOptions *encrypt, + Error **errp) +{ + int r = 0; + g_autofree char *passphrase = NULL; + size_t passphrase_len; + rbd_encryption_format_t format; + rbd_encryption_options_t opts; + rbd_encryption_luks1_format_options_t luks_opts; + rbd_encryption_luks2_format_options_t luks2_opts; + size_t opts_size; + uint64_t raw_size, effective_size; + + r = rbd_get_size(image, &raw_size); + if (r < 0) { + error_setg_errno(errp, -r, "cannot get raw image size"); + return r; + } + + switch (encrypt->format) { + case RBD_IMAGE_ENCRYPTION_FORMAT_LUKS: { + memset(&luks_opts, 0, sizeof(luks_opts)); + format = RBD_ENCRYPTION_FORMAT_LUKS1; + opts = &luks_opts; + opts_size = sizeof(luks_opts); + r = qemu_rbd_convert_luks_create_options( + qapi_RbdEncryptionCreateOptionsLUKS_base(&encrypt->u.luks), + &luks_opts.alg, &passphrase, &passphrase_len, errp); + if (r < 0) { + return r; + } + luks_opts.passphrase = passphrase; + luks_opts.passphrase_size = passphrase_len; + break; + } + case RBD_IMAGE_ENCRYPTION_FORMAT_LUKS2: { + memset(&luks2_opts, 0, sizeof(luks2_opts)); + format = RBD_ENCRYPTION_FORMAT_LUKS2; + opts = &luks2_opts; + opts_size = sizeof(luks2_opts); + r = qemu_rbd_convert_luks_create_options( + qapi_RbdEncryptionCreateOptionsLUKS2_base( + &encrypt->u.luks2), + &luks2_opts.alg, &passphrase, &passphrase_len, errp); + if (r < 0) { + return r; + } + luks2_opts.passphrase = passphrase; + luks2_opts.passphrase_size = passphrase_len; + break; + } + default: { + r = -ENOTSUP; + error_setg_errno( + errp, -r, "unknown image encryption format: %u", + encrypt->format); + return r; + } + } + + r = rbd_encryption_format(image, format, opts, opts_size); + if (r < 0) { + error_setg_errno(errp, -r, "encryption format fail"); + return r; + } + + r = rbd_get_size(image, &effective_size); + if (r < 0) { + error_setg_errno(errp, -r, "cannot get effective image size"); + return r; + } + + r = rbd_resize(image, raw_size + (raw_size - effective_size)); + if (r < 0) { + error_setg_errno(errp, -r, "cannot resize image after format"); + return r; + } + + return 0; +} + +static int qemu_rbd_encryption_load(rbd_image_t image, + RbdEncryptionOptions *encrypt, + Error **errp) +{ + int r = 0; + g_autofree char *passphrase = NULL; + size_t passphrase_len; + rbd_encryption_luks1_format_options_t luks_opts; + rbd_encryption_luks2_format_options_t luks2_opts; + rbd_encryption_format_t format; + rbd_encryption_options_t opts; + size_t opts_size; + + switch (encrypt->format) { + case RBD_IMAGE_ENCRYPTION_FORMAT_LUKS: { + memset(&luks_opts, 0, sizeof(luks_opts)); + format = RBD_ENCRYPTION_FORMAT_LUKS1; + opts = &luks_opts; + opts_size = sizeof(luks_opts); + r = qemu_rbd_convert_luks_options( + qapi_RbdEncryptionOptionsLUKS_base(&encrypt->u.luks), + &passphrase, &passphrase_len, errp); + if (r < 0) { + return r; + } + luks_opts.passphrase = passphrase; + luks_opts.passphrase_size = passphrase_len; + break; + } + case RBD_IMAGE_ENCRYPTION_FORMAT_LUKS2: { + memset(&luks2_opts, 0, sizeof(luks2_opts)); + format = RBD_ENCRYPTION_FORMAT_LUKS2; + opts = &luks2_opts; + opts_size = sizeof(luks2_opts); + r = qemu_rbd_convert_luks_options( + qapi_RbdEncryptionOptionsLUKS2_base(&encrypt->u.luks2), + &passphrase, &passphrase_len, errp); + if (r < 0) { + return r; + } + luks2_opts.passphrase = passphrase; + luks2_opts.passphrase_size = passphrase_len; + break; + } + default: { + r = -ENOTSUP; + error_setg_errno( + errp, -r, "unknown image encryption format: %u", + encrypt->format); + return r; + } } + + r = rbd_encryption_load(image, format, opts, opts_size); + if (r < 0) { + error_setg_errno(errp, -r, "encryption load fail"); + return r; + } + + return 0; } +#endif /* FIXME Deprecate and remove keypairs or make it available in QMP. */ static int qemu_rbd_do_create(BlockdevCreateOptions *options, @@ -368,6 +535,13 @@ static int qemu_rbd_do_create(BlockdevCreateOptions *options, return -EINVAL; } +#ifndef LIBRBD_SUPPORTS_ENCRYPTION + if (opts->has_encrypt) { + error_setg(errp, "RBD library does not support image encryption"); + return -ENOTSUP; + } +#endif + if (opts->has_cluster_size) { int64_t objsize = opts->cluster_size; if ((objsize - 1) & objsize) { /* not a power of 2? */ @@ -393,6 +567,28 @@ static int qemu_rbd_do_create(BlockdevCreateOptions *options, goto out; } +#ifdef LIBRBD_SUPPORTS_ENCRYPTION + if (opts->has_encrypt) { + rbd_image_t image; + + ret = rbd_open(io_ctx, opts->location->image, &image, NULL); + if (ret < 0) { + error_setg_errno(errp, -ret, + "error opening image '%s' for encryption format", + opts->location->image); + goto out; + } + + ret = qemu_rbd_encryption_format(image, opts->encrypt, errp); + rbd_close(image); + if (ret < 0) { + /* encryption format fail, try removing the image */ + rbd_remove(io_ctx, opts->location->image); + goto out; + } + } +#endif + ret = 0; out: rados_ioctx_destroy(io_ctx); @@ -405,6 +601,43 @@ static int qemu_rbd_co_create(BlockdevCreateOptions *options, Error **errp) return qemu_rbd_do_create(options, NULL, NULL, errp); } +static int qemu_rbd_extract_encryption_create_options( + QemuOpts *opts, + RbdEncryptionCreateOptions **spec, + Error **errp) +{ + QDict *opts_qdict; + QDict *encrypt_qdict; + Visitor *v; + int ret = 0; + + opts_qdict = qemu_opts_to_qdict(opts, NULL); + qdict_extract_subqdict(opts_qdict, &encrypt_qdict, "encrypt."); + qobject_unref(opts_qdict); + if (!qdict_size(encrypt_qdict)) { + *spec = NULL; + goto exit; + } + + /* Convert options into a QAPI object */ + v = qobject_input_visitor_new_flat_confused(encrypt_qdict, errp); + if (!v) { + ret = -EINVAL; + goto exit; + } + + visit_type_RbdEncryptionCreateOptions(v, NULL, spec, errp); + visit_free(v); + if (!*spec) { + ret = -EINVAL; + goto exit; + } + +exit: + qobject_unref(encrypt_qdict); + return ret; +} + static int coroutine_fn qemu_rbd_co_create_opts(BlockDriver *drv, const char *filename, QemuOpts *opts, @@ -413,6 +646,7 @@ static int coroutine_fn qemu_rbd_co_create_opts(BlockDriver *drv, BlockdevCreateOptions *create_options; BlockdevCreateOptionsRbd *rbd_opts; BlockdevOptionsRbd *loc; + RbdEncryptionCreateOptions *encrypt = NULL; Error *local_err = NULL; const char *keypairs, *password_secret; QDict *options = NULL; @@ -441,6 +675,13 @@ static int coroutine_fn qemu_rbd_co_create_opts(BlockDriver *drv, goto exit; } + ret = qemu_rbd_extract_encryption_create_options(opts, &encrypt, errp); + if (ret < 0) { + goto exit; + } + rbd_opts->encrypt = encrypt; + rbd_opts->has_encrypt = !!encrypt; + /* * Caution: while qdict_get_try_str() is fine, getting non-string * types would require more care. When @options come from -blockdev @@ -469,53 +710,6 @@ exit: return ret; } -/* - * This aio completion is being called from rbd_finish_bh() and runs in qemu - * BH context. - */ -static void qemu_rbd_complete_aio(RADOSCB *rcb) -{ - RBDAIOCB *acb = rcb->acb; - int64_t r; - - r = rcb->ret; - - if (acb->cmd != RBD_AIO_READ) { - if (r < 0) { - acb->ret = r; - acb->error = 1; - } else if (!acb->error) { - acb->ret = rcb->size; - } - } else { - if (r < 0) { - qemu_rbd_memset(rcb, 0); - acb->ret = r; - acb->error = 1; - } else if (r < rcb->size) { - qemu_rbd_memset(rcb, r); - if (!acb->error) { - acb->ret = rcb->size; - } - } else if (!acb->error) { - acb->ret = r; - } - } - - g_free(rcb); - - if (!LIBRBD_USE_IOVEC) { - if (acb->cmd == RBD_AIO_READ) { - qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size); - } - qemu_vfree(acb->bounce); - } - - acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret)); - - qemu_aio_unref(acb); -} - static char *qemu_rbd_mon_host(BlockdevOptionsRbd *opts, Error **errp) { const char **vals; @@ -702,6 +896,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags, const QDictEntry *e; Error *local_err = NULL; char *keypairs, *secretid; + rbd_image_info_t info; int r; keypairs = g_strdup(qdict_get_try_str(options, "=keyvalue-pairs")); @@ -766,30 +961,49 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags, goto failed_open; } - r = rbd_get_size(s->image, &s->image_size); + if (opts->has_encrypt) { +#ifdef LIBRBD_SUPPORTS_ENCRYPTION + r = qemu_rbd_encryption_load(s->image, opts->encrypt, errp); + if (r < 0) { + goto failed_post_open; + } +#else + r = -ENOTSUP; + error_setg(errp, "RBD library does not support image encryption"); + goto failed_post_open; +#endif + } + + r = rbd_stat(s->image, &info, sizeof(info)); if (r < 0) { - error_setg_errno(errp, -r, "error getting image size from %s", + error_setg_errno(errp, -r, "error getting image info from %s", s->image_name); - rbd_close(s->image); - goto failed_open; + goto failed_post_open; } + s->image_size = info.size; + s->object_size = info.obj_size; /* If we are using an rbd snapshot, we must be r/o, otherwise * leave as-is */ if (s->snap != NULL) { r = bdrv_apply_auto_read_only(bs, "rbd snapshots are read-only", errp); if (r < 0) { - rbd_close(s->image); - goto failed_open; + goto failed_post_open; } } +#ifdef LIBRBD_SUPPORTS_WRITE_ZEROES + bs->supported_zero_flags = BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK; +#endif + /* When extending regular files, we get zeros from the OS */ bs->supported_truncate_flags = BDRV_REQ_ZERO_WRITE; r = 0; goto out; +failed_post_open: + rbd_close(s->image); failed_open: rados_ioctx_destroy(s->io_ctx); g_free(s->snap); @@ -849,229 +1063,213 @@ static int qemu_rbd_resize(BlockDriverState *bs, uint64_t size) return 0; } -static const AIOCBInfo rbd_aiocb_info = { - .aiocb_size = sizeof(RBDAIOCB), -}; - -static void rbd_finish_bh(void *opaque) +static void qemu_rbd_finish_bh(void *opaque) { - RADOSCB *rcb = opaque; - qemu_rbd_complete_aio(rcb); + RBDTask *task = opaque; + task->complete = true; + aio_co_wake(task->co); } /* - * This is the callback function for rbd_aio_read and _write + * This is the completion callback function for all rbd aio calls + * started from qemu_rbd_start_co(). * * Note: this function is being called from a non qemu thread so * we need to be careful about what we do here. Generally we only * schedule a BH, and do the rest of the io completion handling - * from rbd_finish_bh() which runs in a qemu context. + * from qemu_rbd_finish_bh() which runs in a qemu context. */ -static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb) +static void qemu_rbd_completion_cb(rbd_completion_t c, RBDTask *task) { - RBDAIOCB *acb = rcb->acb; - - rcb->ret = rbd_aio_get_return_value(c); + task->ret = rbd_aio_get_return_value(c); rbd_aio_release(c); - - replay_bh_schedule_oneshot_event(bdrv_get_aio_context(acb->common.bs), - rbd_finish_bh, rcb); -} - -static int rbd_aio_discard_wrapper(rbd_image_t image, - uint64_t off, - uint64_t len, - rbd_completion_t comp) -{ -#ifdef LIBRBD_SUPPORTS_DISCARD - return rbd_aio_discard(image, off, len, comp); -#else - return -ENOTSUP; -#endif -} - -static int rbd_aio_flush_wrapper(rbd_image_t image, - rbd_completion_t comp) -{ -#ifdef LIBRBD_SUPPORTS_AIO_FLUSH - return rbd_aio_flush(image, comp); -#else - return -ENOTSUP; -#endif + aio_bh_schedule_oneshot(bdrv_get_aio_context(task->bs), + qemu_rbd_finish_bh, task); } -static BlockAIOCB *rbd_start_aio(BlockDriverState *bs, - int64_t off, - QEMUIOVector *qiov, - int64_t size, - BlockCompletionFunc *cb, - void *opaque, - RBDAIOCmd cmd) +static int coroutine_fn qemu_rbd_start_co(BlockDriverState *bs, + uint64_t offset, + uint64_t bytes, + QEMUIOVector *qiov, + int flags, + RBDAIOCmd cmd) { - RBDAIOCB *acb; - RADOSCB *rcb = NULL; + BDRVRBDState *s = bs->opaque; + RBDTask task = { .bs = bs, .co = qemu_coroutine_self() }; rbd_completion_t c; int r; - BDRVRBDState *s = bs->opaque; - - acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque); - acb->cmd = cmd; - acb->qiov = qiov; - assert(!qiov || qiov->size == size); - - rcb = g_new(RADOSCB, 1); - - if (!LIBRBD_USE_IOVEC) { - if (cmd == RBD_AIO_DISCARD || cmd == RBD_AIO_FLUSH) { - acb->bounce = NULL; - } else { - acb->bounce = qemu_try_blockalign(bs, qiov->size); - if (acb->bounce == NULL) { - goto failed; - } - } - if (cmd == RBD_AIO_WRITE) { - qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size); - } - rcb->buf = acb->bounce; - } - - acb->ret = 0; - acb->error = 0; - acb->s = s; + assert(!qiov || qiov->size == bytes); - rcb->acb = acb; - rcb->s = acb->s; - rcb->size = size; - r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c); + r = rbd_aio_create_completion(&task, + (rbd_callback_t) qemu_rbd_completion_cb, &c); if (r < 0) { - goto failed; + return r; } switch (cmd) { - case RBD_AIO_WRITE: { - /* - * RBD APIs don't allow us to write more than actual size, so in order - * to support growing images, we resize the image before write - * operations that exceed the current size. - */ - if (off + size > s->image_size) { - r = qemu_rbd_resize(bs, off + size); - if (r < 0) { - goto failed_completion; - } - } -#ifdef LIBRBD_SUPPORTS_IOVEC - r = rbd_aio_writev(s->image, qiov->iov, qiov->niov, off, c); -#else - r = rbd_aio_write(s->image, off, size, rcb->buf, c); -#endif - break; - } case RBD_AIO_READ: -#ifdef LIBRBD_SUPPORTS_IOVEC - r = rbd_aio_readv(s->image, qiov->iov, qiov->niov, off, c); -#else - r = rbd_aio_read(s->image, off, size, rcb->buf, c); -#endif + r = rbd_aio_readv(s->image, qiov->iov, qiov->niov, offset, c); + break; + case RBD_AIO_WRITE: + r = rbd_aio_writev(s->image, qiov->iov, qiov->niov, offset, c); break; case RBD_AIO_DISCARD: - r = rbd_aio_discard_wrapper(s->image, off, size, c); + r = rbd_aio_discard(s->image, offset, bytes, c); break; case RBD_AIO_FLUSH: - r = rbd_aio_flush_wrapper(s->image, c); + r = rbd_aio_flush(s->image, c); break; +#ifdef LIBRBD_SUPPORTS_WRITE_ZEROES + case RBD_AIO_WRITE_ZEROES: { + int zero_flags = 0; +#ifdef RBD_WRITE_ZEROES_FLAG_THICK_PROVISION + if (!(flags & BDRV_REQ_MAY_UNMAP)) { + zero_flags = RBD_WRITE_ZEROES_FLAG_THICK_PROVISION; + } +#endif + r = rbd_aio_write_zeroes(s->image, offset, bytes, c, zero_flags, 0); + break; + } +#endif default: r = -EINVAL; } if (r < 0) { - goto failed_completion; + error_report("rbd request failed early: cmd %d offset %" PRIu64 + " bytes %" PRIu64 " flags %d r %d (%s)", cmd, offset, + bytes, flags, r, strerror(-r)); + rbd_aio_release(c); + return r; } - return &acb->common; -failed_completion: - rbd_aio_release(c); -failed: - g_free(rcb); - if (!LIBRBD_USE_IOVEC) { - qemu_vfree(acb->bounce); + while (!task.complete) { + qemu_coroutine_yield(); } - qemu_aio_unref(acb); - return NULL; + if (task.ret < 0) { + error_report("rbd request failed: cmd %d offset %" PRIu64 " bytes %" + PRIu64 " flags %d task.ret %" PRIi64 " (%s)", cmd, offset, + bytes, flags, task.ret, strerror(-task.ret)); + return task.ret; + } + + /* zero pad short reads */ + if (cmd == RBD_AIO_READ && task.ret < qiov->size) { + qemu_iovec_memset(qiov, task.ret, 0, qiov->size - task.ret); + } + + return 0; } -static BlockAIOCB *qemu_rbd_aio_preadv(BlockDriverState *bs, - uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags, - BlockCompletionFunc *cb, - void *opaque) +static int +coroutine_fn qemu_rbd_co_preadv(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, + int flags) { - return rbd_start_aio(bs, offset, qiov, bytes, cb, opaque, - RBD_AIO_READ); + return qemu_rbd_start_co(bs, offset, bytes, qiov, flags, RBD_AIO_READ); } -static BlockAIOCB *qemu_rbd_aio_pwritev(BlockDriverState *bs, - uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags, - BlockCompletionFunc *cb, - void *opaque) +static int +coroutine_fn qemu_rbd_co_pwritev(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, + int flags) { - return rbd_start_aio(bs, offset, qiov, bytes, cb, opaque, - RBD_AIO_WRITE); + BDRVRBDState *s = bs->opaque; + /* + * RBD APIs don't allow us to write more than actual size, so in order + * to support growing images, we resize the image before write + * operations that exceed the current size. + */ + if (offset + bytes > s->image_size) { + int r = qemu_rbd_resize(bs, offset + bytes); + if (r < 0) { + return r; + } + } + return qemu_rbd_start_co(bs, offset, bytes, qiov, flags, RBD_AIO_WRITE); } -#ifdef LIBRBD_SUPPORTS_AIO_FLUSH -static BlockAIOCB *qemu_rbd_aio_flush(BlockDriverState *bs, - BlockCompletionFunc *cb, - void *opaque) +static int coroutine_fn qemu_rbd_co_flush(BlockDriverState *bs) { - return rbd_start_aio(bs, 0, NULL, 0, cb, opaque, RBD_AIO_FLUSH); + return qemu_rbd_start_co(bs, 0, 0, NULL, 0, RBD_AIO_FLUSH); } -#else +static int coroutine_fn qemu_rbd_co_pdiscard(BlockDriverState *bs, + int64_t offset, int count) +{ + return qemu_rbd_start_co(bs, offset, count, NULL, 0, RBD_AIO_DISCARD); +} -static int qemu_rbd_co_flush(BlockDriverState *bs) +#ifdef LIBRBD_SUPPORTS_WRITE_ZEROES +static int +coroutine_fn qemu_rbd_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, + int count, BdrvRequestFlags flags) { -#if LIBRBD_VERSION_CODE >= LIBRBD_VERSION(0, 1, 1) - /* rbd_flush added in 0.1.1 */ - BDRVRBDState *s = bs->opaque; - return rbd_flush(s->image); -#else - return 0; -#endif + return qemu_rbd_start_co(bs, offset, count, NULL, flags, + RBD_AIO_WRITE_ZEROES); } #endif static int qemu_rbd_getinfo(BlockDriverState *bs, BlockDriverInfo *bdi) { BDRVRBDState *s = bs->opaque; - rbd_image_info_t info; + bdi->cluster_size = s->object_size; + return 0; +} + +static ImageInfoSpecific *qemu_rbd_get_specific_info(BlockDriverState *bs, + Error **errp) +{ + BDRVRBDState *s = bs->opaque; + ImageInfoSpecific *spec_info; + char buf[RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN] = {0}; int r; - r = rbd_stat(s->image, &info, sizeof(info)); - if (r < 0) { - return r; + if (s->image_size >= RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN) { + r = rbd_read(s->image, 0, + RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN, buf); + if (r < 0) { + error_setg_errno(errp, -r, "cannot read image start for probe"); + return NULL; + } } - bdi->cluster_size = info.obj_size; - return 0; + spec_info = g_new(ImageInfoSpecific, 1); + *spec_info = (ImageInfoSpecific){ + .type = IMAGE_INFO_SPECIFIC_KIND_RBD, + .u.rbd.data = g_new0(ImageInfoSpecificRbd, 1), + }; + + if (memcmp(buf, rbd_luks_header_verification, + RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN) == 0) { + spec_info->u.rbd.data->encryption_format = + RBD_IMAGE_ENCRYPTION_FORMAT_LUKS; + spec_info->u.rbd.data->has_encryption_format = true; + } else if (memcmp(buf, rbd_luks2_header_verification, + RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN) == 0) { + spec_info->u.rbd.data->encryption_format = + RBD_IMAGE_ENCRYPTION_FORMAT_LUKS2; + spec_info->u.rbd.data->has_encryption_format = true; + } else { + spec_info->u.rbd.data->has_encryption_format = false; + } + + return spec_info; } static int64_t qemu_rbd_getlength(BlockDriverState *bs) { BDRVRBDState *s = bs->opaque; - rbd_image_info_t info; int r; - r = rbd_stat(s->image, &info, sizeof(info)); + r = rbd_get_size(s->image, &s->image_size); if (r < 0) { return r; } - return info.size; + return s->image_size; } static int coroutine_fn qemu_rbd_co_truncate(BlockDriverState *bs, @@ -1210,19 +1408,6 @@ static int qemu_rbd_snap_list(BlockDriverState *bs, return snap_count; } -#ifdef LIBRBD_SUPPORTS_DISCARD -static BlockAIOCB *qemu_rbd_aio_pdiscard(BlockDriverState *bs, - int64_t offset, - int bytes, - BlockCompletionFunc *cb, - void *opaque) -{ - return rbd_start_aio(bs, offset, NULL, bytes, cb, opaque, - RBD_AIO_DISCARD); -} -#endif - -#ifdef LIBRBD_SUPPORTS_INVALIDATE static void coroutine_fn qemu_rbd_co_invalidate_cache(BlockDriverState *bs, Error **errp) { @@ -1232,7 +1417,6 @@ static void coroutine_fn qemu_rbd_co_invalidate_cache(BlockDriverState *bs, error_setg_errno(errp, -r, "Failed to invalidate the cache"); } } -#endif static QemuOptsList qemu_rbd_create_opts = { .name = "rbd-create-opts", @@ -1253,6 +1437,22 @@ static QemuOptsList qemu_rbd_create_opts = { .type = QEMU_OPT_STRING, .help = "ID of secret providing the password", }, + { + .name = "encrypt.format", + .type = QEMU_OPT_STRING, + .help = "Encrypt the image, format choices: 'luks', 'luks2'", + }, + { + .name = "encrypt.cipher-alg", + .type = QEMU_OPT_STRING, + .help = "Name of encryption cipher algorithm" + " (allowed values: aes-128, aes-256)", + }, + { + .name = "encrypt.key-secret", + .type = QEMU_OPT_STRING, + .help = "ID of secret providing LUKS passphrase", + }, { /* end of list */ } } }; @@ -1274,7 +1474,6 @@ static BlockDriver bdrv_rbd = { .format_name = "rbd", .instance_size = sizeof(BDRVRBDState), .bdrv_parse_filename = qemu_rbd_parse_filename, - .bdrv_refresh_limits = qemu_rbd_refresh_limits, .bdrv_file_open = qemu_rbd_open, .bdrv_close = qemu_rbd_close, .bdrv_reopen_prepare = qemu_rbd_reopen_prepare, @@ -1282,31 +1481,25 @@ static BlockDriver bdrv_rbd = { .bdrv_co_create_opts = qemu_rbd_co_create_opts, .bdrv_has_zero_init = bdrv_has_zero_init_1, .bdrv_get_info = qemu_rbd_getinfo, + .bdrv_get_specific_info = qemu_rbd_get_specific_info, .create_opts = &qemu_rbd_create_opts, .bdrv_getlength = qemu_rbd_getlength, .bdrv_co_truncate = qemu_rbd_co_truncate, .protocol_name = "rbd", - .bdrv_aio_preadv = qemu_rbd_aio_preadv, - .bdrv_aio_pwritev = qemu_rbd_aio_pwritev, - -#ifdef LIBRBD_SUPPORTS_AIO_FLUSH - .bdrv_aio_flush = qemu_rbd_aio_flush, -#else + .bdrv_co_preadv = qemu_rbd_co_preadv, + .bdrv_co_pwritev = qemu_rbd_co_pwritev, .bdrv_co_flush_to_disk = qemu_rbd_co_flush, -#endif - -#ifdef LIBRBD_SUPPORTS_DISCARD - .bdrv_aio_pdiscard = qemu_rbd_aio_pdiscard, + .bdrv_co_pdiscard = qemu_rbd_co_pdiscard, +#ifdef LIBRBD_SUPPORTS_WRITE_ZEROES + .bdrv_co_pwrite_zeroes = qemu_rbd_co_pwrite_zeroes, #endif .bdrv_snapshot_create = qemu_rbd_snap_create, .bdrv_snapshot_delete = qemu_rbd_snap_remove, .bdrv_snapshot_list = qemu_rbd_snap_list, .bdrv_snapshot_goto = qemu_rbd_snap_rollback, -#ifdef LIBRBD_SUPPORTS_INVALIDATE .bdrv_co_invalidate_cache = qemu_rbd_co_invalidate_cache, -#endif .strong_runtime_opts = qemu_rbd_strong_runtime_opts, }; diff --git a/block/replication.c b/block/replication.c index 52163f2d1f..774e15df16 100644 --- a/block/replication.c +++ b/block/replication.c @@ -390,7 +390,14 @@ static void reopen_backing_file(BlockDriverState *bs, bool writable, } if (reopen_queue) { + AioContext *ctx = bdrv_get_aio_context(bs); + if (ctx != qemu_get_aio_context()) { + aio_context_release(ctx); + } bdrv_reopen_multiple(reopen_queue, errp); + if (ctx != qemu_get_aio_context()) { + aio_context_acquire(ctx); + } } bdrv_subtree_drained_end(s->hidden_disk->bs); diff --git a/block/ssh.c b/block/ssh.c index d008caf059..e0fbb4934b 100644 --- a/block/ssh.c +++ b/block/ssh.c @@ -237,9 +237,7 @@ static int parse_uri(const char *filename, QDict *options, Error **errp) return 0; err: - if (uri) { - uri_free(uri); - } + uri_free(uri); return -EINVAL; } |