* GNU GPL, version 2 or (at your option) any later version.
*/
-#include <inttypes.h>
+#include "qemu/osdep.h"
-#include "qemu-common.h"
+#include "qapi/error.h"
#include "qemu/error-report.h"
#include "block/block_int.h"
+#include "crypto/secret.h"
+#include "qemu/cutils.h"
#include <rbd/librbd.h>
#define RBD_MAX_SNAP_NAME_SIZE 128
#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
+
typedef enum {
RBD_AIO_READ,
RBD_AIO_WRITE,
typedef struct RBDAIOCB {
BlockAIOCB common;
- QEMUBH *bh;
int64_t ret;
QEMUIOVector *qiov;
char *bounce;
RBDAIOCmd cmd;
- int64_t sector_num;
int error;
struct BDRVRBDState *s;
- int status;
} RBDAIOCB;
typedef struct RADOSCB {
- int rcbid;
RBDAIOCB *acb;
struct BDRVRBDState *s;
- int done;
int64_t size;
char *buf;
int64_t ret;
} RADOSCB;
-#define RBD_FD_READ 0
-#define RBD_FD_WRITE 1
-
typedef struct BDRVRBDState {
rados_t cluster;
rados_ioctx_t io_ctx;
char *snap;
} BDRVRBDState;
-static int qemu_rbd_next_tok(char *dst, int dst_len,
- char *src, char delim,
- const char *name,
- char **p, Error **errp)
+static char *qemu_rbd_next_tok(int max_len,
+ char *src, char delim,
+ const char *name,
+ char **p, Error **errp)
{
int l;
char *end;
}
}
l = strlen(src);
- if (l >= dst_len) {
+ if (l >= max_len) {
error_setg(errp, "%s too long", name);
- return -EINVAL;
+ return NULL;
} else if (l == 0) {
error_setg(errp, "%s too short", name);
- return -EINVAL;
+ return NULL;
}
- pstrcpy(dst, dst_len, src);
-
- return 0;
+ return src;
}
static void qemu_rbd_unescape(char *src)
{
const char *start;
char *p, *buf;
- int ret;
+ int ret = 0;
+ char *found_str;
+ Error *local_err = NULL;
if (!strstart(filename, "rbd:", &start)) {
error_setg(errp, "File name must start with 'rbd:'");
*snap = '\0';
*conf = '\0';
- ret = qemu_rbd_next_tok(pool, pool_len, p,
- '/', "pool name", &p, errp);
- if (ret < 0 || !p) {
+ found_str = qemu_rbd_next_tok(pool_len, p,
+ '/', "pool name", &p, &local_err);
+ if (local_err) {
+ goto done;
+ }
+ if (!p) {
ret = -EINVAL;
+ error_setg(errp, "Pool name is required");
goto done;
}
- qemu_rbd_unescape(pool);
+ qemu_rbd_unescape(found_str);
+ g_strlcpy(pool, found_str, pool_len);
if (strchr(p, '@')) {
- ret = qemu_rbd_next_tok(name, name_len, p,
- '@', "object name", &p, errp);
- if (ret < 0) {
+ found_str = qemu_rbd_next_tok(name_len, p,
+ '@', "object name", &p, &local_err);
+ if (local_err) {
+ goto done;
+ }
+ qemu_rbd_unescape(found_str);
+ g_strlcpy(name, found_str, name_len);
+
+ found_str = qemu_rbd_next_tok(snap_len, p,
+ ':', "snap name", &p, &local_err);
+ if (local_err) {
goto done;
}
- ret = qemu_rbd_next_tok(snap, snap_len, p,
- ':', "snap name", &p, errp);
- qemu_rbd_unescape(snap);
+ qemu_rbd_unescape(found_str);
+ g_strlcpy(snap, found_str, snap_len);
} else {
- ret = qemu_rbd_next_tok(name, name_len, p,
- ':', "object name", &p, errp);
+ found_str = qemu_rbd_next_tok(name_len, p,
+ ':', "object name", &p, &local_err);
+ if (local_err) {
+ goto done;
+ }
+ qemu_rbd_unescape(found_str);
+ g_strlcpy(name, found_str, name_len);
}
- qemu_rbd_unescape(name);
- if (ret < 0 || !p) {
+ if (!p) {
goto done;
}
- ret = qemu_rbd_next_tok(conf, conf_len, p,
- '\0', "configuration", &p, errp);
+ found_str = qemu_rbd_next_tok(conf_len, p,
+ '\0', "configuration", &p, &local_err);
+ if (local_err) {
+ goto done;
+ }
+ g_strlcpy(conf, found_str, conf_len);
done:
+ if (local_err) {
+ ret = -EINVAL;
+ error_propagate(errp, local_err);
+ }
g_free(buf);
return ret;
}
return NULL;
}
-static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
+
+static int qemu_rbd_set_auth(rados_t cluster, const char *secretid,
+ Error **errp)
+{
+ if (secretid == 0) {
+ return 0;
+ }
+
+ gchar *secret = qcrypto_secret_lookup_as_base64(secretid,
+ errp);
+ if (!secret) {
+ return -1;
+ }
+
+ rados_conf_set(cluster, "key", secret);
+ g_free(secret);
+
+ return 0;
+}
+
+
+static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
+ bool only_read_conf_file,
+ Error **errp)
{
char *p, *buf;
- char name[RBD_MAX_CONF_NAME_SIZE];
- char value[RBD_MAX_CONF_VAL_SIZE];
+ char *name;
+ char *value;
+ Error *local_err = NULL;
int ret = 0;
buf = g_strdup(conf);
p = buf;
while (p) {
- ret = qemu_rbd_next_tok(name, sizeof(name), p,
- '=', "conf option name", &p, errp);
- if (ret < 0) {
+ name = qemu_rbd_next_tok(RBD_MAX_CONF_NAME_SIZE, p,
+ '=', "conf option name", &p, &local_err);
+ if (local_err) {
break;
}
qemu_rbd_unescape(name);
break;
}
- ret = qemu_rbd_next_tok(value, sizeof(value), p,
- ':', "conf option value", &p, errp);
- if (ret < 0) {
+ value = qemu_rbd_next_tok(RBD_MAX_CONF_VAL_SIZE, p,
+ ':', "conf option value", &p, &local_err);
+ if (local_err) {
break;
}
qemu_rbd_unescape(value);
if (strcmp(name, "conf") == 0) {
- ret = rados_conf_read_file(cluster, value);
- if (ret < 0) {
- error_setg(errp, "error reading conf file %s", value);
- break;
+ /* read the conf file alone, so it doesn't override more
+ specific settings for a particular device */
+ if (only_read_conf_file) {
+ ret = rados_conf_read_file(cluster, value);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "error reading conf file %s",
+ value);
+ break;
+ }
}
} else if (strcmp(name, "id") == 0) {
/* ignore, this is parsed by qemu_rbd_parse_clientname() */
- } else {
+ } else if (!only_read_conf_file) {
ret = rados_conf_set(cluster, name, value);
if (ret < 0) {
- error_setg(errp, "invalid conf option %s", name);
+ error_setg_errno(errp, -ret, "invalid conf option %s", name);
ret = -EINVAL;
break;
}
}
}
+ if (local_err) {
+ error_propagate(errp, local_err);
+ ret = -EINVAL;
+ }
g_free(buf);
return ret;
}
+static void qemu_rbd_memset(RADOSCB *rcb, int64_t offs)
+{
+ if (LIBRBD_USE_IOVEC) {
+ RBDAIOCB *acb = rcb->acb;
+ iov_memset(acb->qiov->iov, acb->qiov->niov, offs, 0,
+ acb->qiov->size - offs);
+ } else {
+ memset(rcb->buf + offs, 0, rcb->size - offs);
+ }
+}
+
+static QemuOptsList runtime_opts = {
+ .name = "rbd",
+ .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
+ .desc = {
+ {
+ .name = "filename",
+ .type = QEMU_OPT_STRING,
+ .help = "Specification of the rbd image",
+ },
+ {
+ .name = "password-secret",
+ .type = QEMU_OPT_STRING,
+ .help = "ID of secret providing the password",
+ },
+ {
+ .name = "conf",
+ .type = QEMU_OPT_STRING,
+ .help = "Rados config file location",
+ },
+ {
+ .name = "pool",
+ .type = QEMU_OPT_STRING,
+ .help = "Rados pool name",
+ },
+ {
+ .name = "image",
+ .type = QEMU_OPT_STRING,
+ .help = "Image name in the pool",
+ },
+ {
+ .name = "snapshot",
+ .type = QEMU_OPT_STRING,
+ .help = "Ceph snapshot name",
+ },
+ {
+ /* maps to 'id' in rados_create() */
+ .name = "user",
+ .type = QEMU_OPT_STRING,
+ .help = "Rados id name",
+ },
+ {
+ .name = "keyvalue-pairs",
+ .type = QEMU_OPT_STRING,
+ .help = "Legacy rados key/value option parameters",
+ },
+ { /* end of list */ }
+ },
+};
+
static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
{
Error *local_err = NULL;
char conf[RBD_MAX_CONF_SIZE];
char clientname_buf[RBD_MAX_CONF_SIZE];
char *clientname;
+ const char *secretid;
rados_t cluster;
rados_ioctx_t io_ctx;
int ret;
+ secretid = qemu_opt_get(opts, "password-secret");
+
if (qemu_rbd_parsename(filename, pool, sizeof(pool),
snap_buf, sizeof(snap_buf),
name, sizeof(name),
error_setg(errp, "obj size too small");
return -EINVAL;
}
- obj_order = ffs(objsize) - 1;
+ obj_order = ctz32(objsize);
}
clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
- if (rados_create(&cluster, clientname) < 0) {
- error_setg(errp, "error initializing");
- return -EIO;
+ ret = rados_create(&cluster, clientname);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "error initializing");
+ return ret;
}
if (strstr(conf, "conf=") == NULL) {
/* try default location, but ignore failure */
rados_conf_read_file(cluster, NULL);
+ } else if (conf[0] != '\0' &&
+ qemu_rbd_set_conf(cluster, conf, true, &local_err) < 0) {
+ error_propagate(errp, local_err);
+ ret = -EIO;
+ goto shutdown;
}
if (conf[0] != '\0' &&
- qemu_rbd_set_conf(cluster, conf, &local_err) < 0) {
- rados_shutdown(cluster);
+ qemu_rbd_set_conf(cluster, conf, false, &local_err) < 0) {
error_propagate(errp, local_err);
- return -EIO;
+ ret = -EIO;
+ goto shutdown;
+ }
+
+ if (qemu_rbd_set_auth(cluster, secretid, errp) < 0) {
+ ret = -EIO;
+ goto shutdown;
}
- if (rados_connect(cluster) < 0) {
- error_setg(errp, "error connecting");
- rados_shutdown(cluster);
- return -EIO;
+ ret = rados_connect(cluster);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "error connecting");
+ goto shutdown;
}
- if (rados_ioctx_create(cluster, pool, &io_ctx) < 0) {
- error_setg(errp, "error opening pool %s", pool);
- rados_shutdown(cluster);
- return -EIO;
+ ret = rados_ioctx_create(cluster, pool, &io_ctx);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "error opening pool %s", pool);
+ goto shutdown;
}
ret = rbd_create(io_ctx, name, bytes, &obj_order);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "error rbd create");
+ }
+
rados_ioctx_destroy(io_ctx);
- rados_shutdown(cluster);
+shutdown:
+ rados_shutdown(cluster);
return ret;
}
}
} else {
if (r < 0) {
- memset(rcb->buf, 0, rcb->size);
+ qemu_rbd_memset(rcb, 0);
acb->ret = r;
acb->error = 1;
} else if (r < rcb->size) {
- memset(rcb->buf + r, 0, rcb->size - r);
+ qemu_rbd_memset(rcb, r);
if (!acb->error) {
acb->ret = rcb->size;
}
g_free(rcb);
- if (acb->cmd == RBD_AIO_READ) {
- qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
+ 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);
}
- qemu_vfree(acb->bounce);
+
acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
- acb->status = 0;
qemu_aio_unref(acb);
}
-/* TODO Convert to fine grained options */
-static QemuOptsList runtime_opts = {
- .name = "rbd",
- .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
- .desc = {
- {
- .name = "filename",
- .type = QEMU_OPT_STRING,
- .help = "Specification of the rbd image",
- },
- { /* end of list */ }
- },
-};
-
static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
char conf[RBD_MAX_CONF_SIZE];
char clientname_buf[RBD_MAX_CONF_SIZE];
char *clientname;
+ const char *secretid;
QemuOpts *opts;
Error *local_err = NULL;
const char *filename;
}
filename = qemu_opt_get(opts, "filename");
+ secretid = qemu_opt_get(opts, "password-secret");
if (qemu_rbd_parsename(filename, pool, sizeof(pool),
snap_buf, sizeof(snap_buf),
clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
r = rados_create(&s->cluster, clientname);
if (r < 0) {
- error_setg(&local_err, "error initializing");
+ error_setg_errno(errp, -r, "error initializing");
goto failed_opts;
}
s->snap = g_strdup(snap_buf);
}
+ if (strstr(conf, "conf=") == NULL) {
+ /* try default location, but ignore failure */
+ rados_conf_read_file(s->cluster, NULL);
+ } else if (conf[0] != '\0') {
+ r = qemu_rbd_set_conf(s->cluster, conf, true, errp);
+ if (r < 0) {
+ goto failed_shutdown;
+ }
+ }
+
+ if (conf[0] != '\0') {
+ r = qemu_rbd_set_conf(s->cluster, conf, false, errp);
+ if (r < 0) {
+ goto failed_shutdown;
+ }
+ }
+
+ if (qemu_rbd_set_auth(s->cluster, secretid, errp) < 0) {
+ r = -EIO;
+ goto failed_shutdown;
+ }
+
/*
* Fallback to more conservative semantics if setting cache
* options fails. Ignore errors from setting rbd_cache because the
rados_conf_set(s->cluster, "rbd_cache", "true");
}
- if (strstr(conf, "conf=") == NULL) {
- /* try default location, but ignore failure */
- rados_conf_read_file(s->cluster, NULL);
- }
-
- if (conf[0] != '\0') {
- r = qemu_rbd_set_conf(s->cluster, conf, errp);
- if (r < 0) {
- goto failed_shutdown;
- }
- }
-
r = rados_connect(s->cluster);
if (r < 0) {
- error_setg(&local_err, "error connecting");
+ error_setg_errno(errp, -r, "error connecting");
goto failed_shutdown;
}
r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
if (r < 0) {
- error_setg(&local_err, "error opening pool %s", pool);
+ error_setg_errno(errp, -r, "error opening pool %s", pool);
goto failed_shutdown;
}
r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
if (r < 0) {
- error_setg(&local_err, "error reading header from %s", s->name);
+ error_setg_errno(errp, -r, "error reading header from %s", s->name);
goto failed_open;
}
static void rbd_finish_bh(void *opaque)
{
RADOSCB *rcb = opaque;
- qemu_bh_delete(rcb->acb->bh);
qemu_rbd_complete_aio(rcb);
}
rcb->ret = rbd_aio_get_return_value(c);
rbd_aio_release(c);
- acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
- rbd_finish_bh, rcb);
- qemu_bh_schedule(acb->bh);
+ aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs),
+ rbd_finish_bh, rcb);
}
static int rbd_aio_discard_wrapper(rbd_image_t image,
}
static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
- int64_t sector_num,
+ int64_t off,
QEMUIOVector *qiov,
- int nb_sectors,
+ int64_t size,
BlockCompletionFunc *cb,
void *opaque,
RBDAIOCmd cmd)
RBDAIOCB *acb;
RADOSCB *rcb = NULL;
rbd_completion_t c;
- int64_t off, size;
- char *buf;
int r;
BDRVRBDState *s = bs->opaque;
acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque);
acb->cmd = cmd;
acb->qiov = qiov;
- 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;
+ 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;
- acb->bh = NULL;
- acb->status = -EINPROGRESS;
-
- if (cmd == RBD_AIO_WRITE) {
- qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
- }
-
- buf = acb->bounce;
-
- off = sector_num * BDRV_SECTOR_SIZE;
- size = nb_sectors * BDRV_SECTOR_SIZE;
- rcb = g_new(RADOSCB, 1);
- rcb->done = 0;
rcb->acb = acb;
- rcb->buf = buf;
rcb->s = acb->s;
rcb->size = size;
r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
switch (cmd) {
case RBD_AIO_WRITE:
- r = rbd_aio_write(s->image, off, size, buf, c);
+#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:
- r = rbd_aio_read(s->image, off, size, buf, c);
+#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
break;
case RBD_AIO_DISCARD:
r = rbd_aio_discard_wrapper(s->image, off, size, c);
if (r < 0) {
goto failed_completion;
}
-
return &acb->common;
failed_completion:
rbd_aio_release(c);
failed:
g_free(rcb);
- qemu_vfree(acb->bounce);
+ if (!LIBRBD_USE_IOVEC) {
+ qemu_vfree(acb->bounce);
+ }
+
qemu_aio_unref(acb);
return NULL;
}
BlockCompletionFunc *cb,
void *opaque)
{
- return rbd_start_aio(bs, sector_num, qiov, nb_sectors, cb, opaque,
+ return rbd_start_aio(bs, sector_num << BDRV_SECTOR_BITS, qiov,
+ (int64_t) nb_sectors << BDRV_SECTOR_BITS, cb, opaque,
RBD_AIO_READ);
}
BlockCompletionFunc *cb,
void *opaque)
{
- return rbd_start_aio(bs, sector_num, qiov, nb_sectors, cb, opaque,
+ return rbd_start_aio(bs, sector_num << BDRV_SECTOR_BITS, qiov,
+ (int64_t) nb_sectors << BDRV_SECTOR_BITS, cb, opaque,
RBD_AIO_WRITE);
}
const char *snapshot_name)
{
BDRVRBDState *s = bs->opaque;
- int r;
- r = rbd_snap_rollback(s->image, snapshot_name);
- return r;
+ return rbd_snap_rollback(s->image, snapshot_name);
}
static int qemu_rbd_snap_list(BlockDriverState *bs,
}
#ifdef LIBRBD_SUPPORTS_DISCARD
-static BlockAIOCB* qemu_rbd_aio_discard(BlockDriverState *bs,
- int64_t sector_num,
- int nb_sectors,
- BlockCompletionFunc *cb,
- void *opaque)
+static BlockAIOCB *qemu_rbd_aio_pdiscard(BlockDriverState *bs,
+ int64_t offset,
+ int count,
+ BlockCompletionFunc *cb,
+ void *opaque)
{
- return rbd_start_aio(bs, sector_num, NULL, nb_sectors, cb, opaque,
+ return rbd_start_aio(bs, offset, NULL, count, cb, opaque,
RBD_AIO_DISCARD);
}
#endif
+#ifdef LIBRBD_SUPPORTS_INVALIDATE
+static void qemu_rbd_invalidate_cache(BlockDriverState *bs,
+ Error **errp)
+{
+ BDRVRBDState *s = bs->opaque;
+ int r = rbd_invalidate_cache(s->image);
+ if (r < 0) {
+ error_setg_errno(errp, -r, "Failed to invalidate the cache");
+ }
+}
+#endif
+
static QemuOptsList qemu_rbd_create_opts = {
.name = "rbd-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(qemu_rbd_create_opts.head),
.type = QEMU_OPT_SIZE,
.help = "RBD object size"
},
+ {
+ .name = "password-secret",
+ .type = QEMU_OPT_STRING,
+ .help = "ID of secret providing the password",
+ },
{ /* end of list */ }
}
};
#endif
#ifdef LIBRBD_SUPPORTS_DISCARD
- .bdrv_aio_discard = qemu_rbd_aio_discard,
+ .bdrv_aio_pdiscard = qemu_rbd_aio_pdiscard,
#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_invalidate_cache = qemu_rbd_invalidate_cache,
+#endif
};
static void bdrv_rbd_init(void)
projects / qemu.git / blobdiff