summaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/qcow2-cluster.c2
-rw-r--r--block/qcow2-refcount.c11
-rw-r--r--block/qcow2.c7
-rw-r--r--block/qcow2.h2
-rw-r--r--block/qed.c129
-rw-r--r--block/qed.h7
-rw-r--r--block/raw-posix.c79
-rw-r--r--block/raw-win32.c12
-rw-r--r--block/rbd.c896
-rw-r--r--block/rbd_types.h71
-rw-r--r--block/sheepdog.c4
-rw-r--r--block/vdi.c6
-rw-r--r--block/vmdk.c22
13 files changed, 574 insertions, 674 deletions
diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c
index 750abe37d4..c9e7bbd9d6 100644
--- a/block/qcow2-cluster.c
+++ b/block/qcow2-cluster.c
@@ -70,7 +70,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, int min_size, bool exact_size)
ret = qcow2_cache_flush(bs, s->refcount_block_cache);
if (ret < 0) {
- return ret;
+ goto fail;
}
BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_WRITE_TABLE);
diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c
index 915d85acbf..ac95b88fe1 100644
--- a/block/qcow2-refcount.c
+++ b/block/qcow2-refcount.c
@@ -1063,7 +1063,7 @@ fail:
* Checks an image for refcount consistency.
*
* Returns 0 if no errors are found, the number of errors in case the image is
- * detected as corrupted, and -errno when an internal error occured.
+ * detected as corrupted, and -errno when an internal error occurred.
*/
int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res)
{
@@ -1086,7 +1086,7 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res)
ret = check_refcounts_l1(bs, res, refcount_table, nb_clusters,
s->l1_table_offset, s->l1_size, 1);
if (ret < 0) {
- return ret;
+ goto fail;
}
/* snapshots */
@@ -1095,7 +1095,7 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res)
ret = check_refcounts_l1(bs, res, refcount_table, nb_clusters,
sn->l1_table_offset, sn->l1_size, 0);
if (ret < 0) {
- return ret;
+ goto fail;
}
}
inc_refcounts(bs, res, refcount_table, nb_clusters,
@@ -1159,8 +1159,11 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res)
}
}
+ ret = 0;
+
+fail:
qemu_free(refcount_table);
- return 0;
+ return ret;
}
diff --git a/block/qcow2.c b/block/qcow2.c
index 75b8becc0a..8451ded9a3 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -229,7 +229,7 @@ static int qcow2_open(BlockDriverState *bs, int flags)
}
/* alloc L2 table/refcount block cache */
- writethrough = ((flags & BDRV_O_CACHE_MASK) == 0);
+ writethrough = ((flags & BDRV_O_CACHE_WB) == 0);
s->l2_table_cache = qcow2_cache_create(bs, L2_CACHE_SIZE, writethrough);
s->refcount_block_cache = qcow2_cache_create(bs, REFCOUNT_CACHE_SIZE,
writethrough);
@@ -1036,7 +1036,7 @@ static int qcow2_create(const char *filename, QEMUOptionParameter *options)
const char *backing_fmt = NULL;
uint64_t sectors = 0;
int flags = 0;
- size_t cluster_size = 65536;
+ size_t cluster_size = DEFAULT_CLUSTER_SIZE;
int prealloc = 0;
/* Read out options */
@@ -1343,7 +1343,8 @@ static QEMUOptionParameter qcow2_create_options[] = {
{
.name = BLOCK_OPT_CLUSTER_SIZE,
.type = OPT_SIZE,
- .help = "qcow2 cluster size"
+ .help = "qcow2 cluster size",
+ .value = { .n = DEFAULT_CLUSTER_SIZE },
},
{
.name = BLOCK_OPT_PREALLOC,
diff --git a/block/qcow2.h b/block/qcow2.h
index a019831838..e1ae3e8c2b 100644
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -54,6 +54,8 @@
/* Must be at least 4 to cover all cases of refcount table growth */
#define REFCOUNT_CACHE_SIZE 4
+#define DEFAULT_CLUSTER_SIZE 65536
+
typedef struct QCowHeader {
uint32_t magic;
uint32_t version;
diff --git a/block/qed.c b/block/qed.c
index c8c5930448..39703793e9 100644
--- a/block/qed.c
+++ b/block/qed.c
@@ -12,6 +12,7 @@
*
*/
+#include "qemu-timer.h"
#include "trace.h"
#include "qed.h"
#include "qerror.h"
@@ -291,6 +292,88 @@ static CachedL2Table *qed_new_l2_table(BDRVQEDState *s)
static void qed_aio_next_io(void *opaque, int ret);
+static void qed_plug_allocating_write_reqs(BDRVQEDState *s)
+{
+ assert(!s->allocating_write_reqs_plugged);
+
+ s->allocating_write_reqs_plugged = true;
+}
+
+static void qed_unplug_allocating_write_reqs(BDRVQEDState *s)
+{
+ QEDAIOCB *acb;
+
+ assert(s->allocating_write_reqs_plugged);
+
+ s->allocating_write_reqs_plugged = false;
+
+ acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs);
+ if (acb) {
+ qed_aio_next_io(acb, 0);
+ }
+}
+
+static void qed_finish_clear_need_check(void *opaque, int ret)
+{
+ /* Do nothing */
+}
+
+static void qed_flush_after_clear_need_check(void *opaque, int ret)
+{
+ BDRVQEDState *s = opaque;
+
+ bdrv_aio_flush(s->bs, qed_finish_clear_need_check, s);
+
+ /* No need to wait until flush completes */
+ qed_unplug_allocating_write_reqs(s);
+}
+
+static void qed_clear_need_check(void *opaque, int ret)
+{
+ BDRVQEDState *s = opaque;
+
+ if (ret) {
+ qed_unplug_allocating_write_reqs(s);
+ return;
+ }
+
+ s->header.features &= ~QED_F_NEED_CHECK;
+ qed_write_header(s, qed_flush_after_clear_need_check, s);
+}
+
+static void qed_need_check_timer_cb(void *opaque)
+{
+ BDRVQEDState *s = opaque;
+
+ /* The timer should only fire when allocating writes have drained */
+ assert(!QSIMPLEQ_FIRST(&s->allocating_write_reqs));
+
+ trace_qed_need_check_timer_cb(s);
+
+ qed_plug_allocating_write_reqs(s);
+
+ /* Ensure writes are on disk before clearing flag */
+ bdrv_aio_flush(s->bs, qed_clear_need_check, s);
+}
+
+static void qed_start_need_check_timer(BDRVQEDState *s)
+{
+ trace_qed_start_need_check_timer(s);
+
+ /* Use vm_clock so we don't alter the image file while suspended for
+ * migration.
+ */
+ qemu_mod_timer(s->need_check_timer, qemu_get_clock_ns(vm_clock) +
+ get_ticks_per_sec() * QED_NEED_CHECK_TIMEOUT);
+}
+
+/* It's okay to call this multiple times or when no timer is started */
+static void qed_cancel_need_check_timer(BDRVQEDState *s)
+{
+ trace_qed_cancel_need_check_timer(s);
+ qemu_del_timer(s->need_check_timer);
+}
+
static int bdrv_qed_open(BlockDriverState *bs, int flags)
{
BDRVQEDState *s = bs->opaque;
@@ -406,7 +489,10 @@ static int bdrv_qed_open(BlockDriverState *bs, int flags)
BdrvCheckResult result = {0};
ret = qed_check(s, &result, true);
- if (!ret && !result.corruptions && !result.check_errors) {
+ if (ret) {
+ goto out;
+ }
+ if (!result.corruptions && !result.check_errors) {
/* Ensure fixes reach storage before clearing check bit */
bdrv_flush(s->bs);
@@ -416,6 +502,9 @@ static int bdrv_qed_open(BlockDriverState *bs, int flags)
}
}
+ s->need_check_timer = qemu_new_timer_ns(vm_clock,
+ qed_need_check_timer_cb, s);
+
out:
if (ret) {
qed_free_l2_cache(&s->l2_cache);
@@ -428,6 +517,9 @@ static void bdrv_qed_close(BlockDriverState *bs)
{
BDRVQEDState *s = bs->opaque;
+ qed_cancel_need_check_timer(s);
+ qemu_free_timer(s->need_check_timer);
+
/* Ensure writes reach stable storage */
bdrv_flush(bs->file);
@@ -809,6 +901,8 @@ static void qed_aio_complete(QEDAIOCB *acb, int ret)
acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs);
if (acb) {
qed_aio_next_io(acb, 0);
+ } else if (s->header.features & QED_F_NEED_CHECK) {
+ qed_start_need_check_timer(s);
}
}
}
@@ -1014,11 +1108,17 @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len)
{
BDRVQEDState *s = acb_to_s(acb);
+ /* Cancel timer when the first allocating request comes in */
+ if (QSIMPLEQ_EMPTY(&s->allocating_write_reqs)) {
+ qed_cancel_need_check_timer(s);
+ }
+
/* Freeze this request if another allocating write is in progress */
if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs)) {
QSIMPLEQ_INSERT_TAIL(&s->allocating_write_reqs, acb, next);
}
- if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs)) {
+ if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs) ||
+ s->allocating_write_reqs_plugged) {
return; /* wait for existing request to finish */
}
@@ -1233,7 +1333,27 @@ static BlockDriverAIOCB *bdrv_qed_aio_flush(BlockDriverState *bs,
static int bdrv_qed_truncate(BlockDriverState *bs, int64_t offset)
{
- return -ENOTSUP;
+ BDRVQEDState *s = bs->opaque;
+ uint64_t old_image_size;
+ int ret;
+
+ if (!qed_is_image_size_valid(offset, s->header.cluster_size,
+ s->header.table_size)) {
+ return -EINVAL;
+ }
+
+ /* Shrinking is currently not supported */
+ if ((uint64_t)offset < s->header.image_size) {
+ return -ENOTSUP;
+ }
+
+ old_image_size = s->header.image_size;
+ s->header.image_size = offset;
+ ret = qed_write_header_sync(s);
+ if (ret < 0) {
+ s->header.image_size = old_image_size;
+ }
+ return ret;
}
static int64_t bdrv_qed_getlength(BlockDriverState *bs)
@@ -1344,7 +1464,8 @@ static QEMUOptionParameter qed_create_options[] = {
}, {
.name = BLOCK_OPT_CLUSTER_SIZE,
.type = OPT_SIZE,
- .help = "Cluster size (in bytes)"
+ .help = "Cluster size (in bytes)",
+ .value = { .n = QED_DEFAULT_CLUSTER_SIZE },
}, {
.name = BLOCK_OPT_TABLE_SIZE,
.type = OPT_SIZE,
diff --git a/block/qed.h b/block/qed.h
index 1d1421fee1..388fdb3760 100644
--- a/block/qed.h
+++ b/block/qed.h
@@ -78,6 +78,9 @@ enum {
QED_MIN_TABLE_SIZE = 1, /* in clusters */
QED_MAX_TABLE_SIZE = 16,
QED_DEFAULT_TABLE_SIZE = 4,
+
+ /* Delay to flush and clean image after last allocating write completes */
+ QED_NEED_CHECK_TIMEOUT = 5, /* in seconds */
};
typedef struct {
@@ -157,6 +160,10 @@ typedef struct {
/* Allocating write request queue */
QSIMPLEQ_HEAD(, QEDAIOCB) allocating_write_reqs;
+ bool allocating_write_reqs_plugged;
+
+ /* Periodic flush and clear need check flag */
+ QEMUTimer *need_check_timer;
} BDRVQEDState;
enum {
diff --git a/block/raw-posix.c b/block/raw-posix.c
index 6b72470599..4cd7d7afbb 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -43,7 +43,6 @@
#ifdef __sun__
#define _POSIX_PTHREAD_SEMANTICS 1
-#include <signal.h>
#include <sys/dkio.h>
#endif
#ifdef __linux__
@@ -53,7 +52,6 @@
#include <linux/fd.h>
#endif
#if defined (__FreeBSD__) || defined(__FreeBSD_kernel__)
-#include <signal.h>
#include <sys/disk.h>
#include <sys/cdio.h>
#endif
@@ -64,6 +62,13 @@
#include <sys/dkio.h>
#endif
+#ifdef __NetBSD__
+#include <sys/ioctl.h>
+#include <sys/disklabel.h>
+#include <sys/dkio.h>
+#include <sys/disk.h>
+#endif
+
#ifdef __DragonFly__
#include <sys/ioctl.h>
#include <sys/diskslice.h>
@@ -136,12 +141,55 @@ static int64_t raw_getlength(BlockDriverState *bs);
static int cdrom_reopen(BlockDriverState *bs);
#endif
+#if defined(__NetBSD__)
+static int raw_normalize_devicepath(const char **filename)
+{
+ static char namebuf[PATH_MAX];
+ const char *dp, *fname;
+ struct stat sb;
+
+ fname = *filename;
+ dp = strrchr(fname, '/');
+ if (lstat(fname, &sb) < 0) {
+ fprintf(stderr, "%s: stat failed: %s\n",
+ fname, strerror(errno));
+ return -errno;
+ }
+
+ if (!S_ISBLK(sb.st_mode)) {
+ return 0;
+ }
+
+ if (dp == NULL) {
+ snprintf(namebuf, PATH_MAX, "r%s", fname);
+ } else {
+ snprintf(namebuf, PATH_MAX, "%.*s/r%s",
+ (int)(dp - fname), fname, dp + 1);
+ }
+ fprintf(stderr, "%s is a block device", fname);
+ *filename = namebuf;
+ fprintf(stderr, ", using %s\n", *filename);
+
+ return 0;
+}
+#else
+static int raw_normalize_devicepath(const char **filename)
+{
+ return 0;
+}
+#endif
+
static int raw_open_common(BlockDriverState *bs, const char *filename,
int bdrv_flags, int open_flags)
{
BDRVRawState *s = bs->opaque;
int fd, ret;
+ ret = raw_normalize_devicepath(&filename);
+ if (ret != 0) {
+ return ret;
+ }
+
s->open_flags = open_flags | O_BINARY;
s->open_flags &= ~O_ACCMODE;
if (bdrv_flags & BDRV_O_RDWR) {
@@ -154,7 +202,7 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
* and O_DIRECT for no caching. */
if ((bdrv_flags & BDRV_O_NOCACHE))
s->open_flags |= O_DIRECT;
- else if (!(bdrv_flags & BDRV_O_CACHE_WB))
+ if (!(bdrv_flags & BDRV_O_CACHE_WB))
s->open_flags |= O_DSYNC;
s->fd = -1;
@@ -622,6 +670,31 @@ static int64_t raw_getlength(BlockDriverState *bs)
} else
return st.st_size;
}
+#elif defined(__NetBSD__)
+static int64_t raw_getlength(BlockDriverState *bs)
+{
+ BDRVRawState *s = bs->opaque;
+ int fd = s->fd;
+ struct stat st;
+
+ if (fstat(fd, &st))
+ return -1;
+ if (S_ISCHR(st.st_mode) || S_ISBLK(st.st_mode)) {
+ struct dkwedge_info dkw;
+
+ if (ioctl(fd, DIOCGWEDGEINFO, &dkw) != -1) {
+ return dkw.dkw_size * 512;
+ } else {
+ struct disklabel dl;
+
+ if (ioctl(fd, DIOCGDINFO, &dl))
+ return -1;
+ return (uint64_t)dl.d_secsize *
+ dl.d_partitions[DISKPART(st.st_rdev)].p_size;
+ }
+ } else
+ return st.st_size;
+}
#elif defined(__sun__)
static int64_t raw_getlength(BlockDriverState *bs)
{
diff --git a/block/raw-win32.c b/block/raw-win32.c
index c204a80d79..56bd7195a1 100644
--- a/block/raw-win32.c
+++ b/block/raw-win32.c
@@ -88,9 +88,9 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags)
}
overlapped = FILE_ATTRIBUTE_NORMAL;
- if ((flags & BDRV_O_NOCACHE))
- overlapped |= FILE_FLAG_NO_BUFFERING | FILE_FLAG_WRITE_THROUGH;
- else if (!(flags & BDRV_O_CACHE_WB))
+ if (flags & BDRV_O_NOCACHE)
+ overlapped |= FILE_FLAG_NO_BUFFERING;
+ if (!(flags & BDRV_O_CACHE_WB))
overlapped |= FILE_FLAG_WRITE_THROUGH;
s->hfile = CreateFile(filename, access_flags,
FILE_SHARE_READ, NULL,
@@ -349,9 +349,9 @@ static int hdev_open(BlockDriverState *bs, const char *filename, int flags)
create_flags = OPEN_EXISTING;
overlapped = FILE_ATTRIBUTE_NORMAL;
- if ((flags & BDRV_O_NOCACHE))
- overlapped |= FILE_FLAG_NO_BUFFERING | FILE_FLAG_WRITE_THROUGH;
- else if (!(flags & BDRV_O_CACHE_WB))
+ if (flags & BDRV_O_NOCACHE)
+ overlapped |= FILE_FLAG_NO_BUFFERING;
+ if (!(flags & BDRV_O_CACHE_WB))
overlapped |= FILE_FLAG_WRITE_THROUGH;
s->hfile = CreateFile(filename, access_flags,
FILE_SHARE_READ, NULL,
diff --git a/block/rbd.c b/block/rbd.c
index 249a590c98..bdc448aa9f 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -1,33 +1,39 @@
/*
* QEMU Block driver for RADOS (Ceph)
*
- * Copyright (C) 2010 Christian Brunner <chb@muc.de>
+ * Copyright (C) 2010-2011 Christian Brunner <chb@muc.de>,
+ * Josh Durgin <josh.durgin@dreamhost.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
+#include <inttypes.h>
+
#include "qemu-common.h"
#include "qemu-error.h"
-#include "rbd_types.h"
#include "block_int.h"
-#include <rados/librados.h>
+#include <rbd/librbd.h>
/*
* When specifying the image filename use:
*
- * rbd:poolname/devicename
+ * rbd:poolname/devicename[@snapshotname][:option1=value1[:option2=value2...]]
*
* poolname must be the name of an existing rados pool
*
* devicename is the basename for all objects used to
* emulate the raw device.
*
+ * Each option given is used to configure rados, and may be
+ * any Ceph option, or "conf". The "conf" option specifies
+ * a Ceph configuration file to read.
+ *
* Metadata information (image size, ...) is stored in an
* object with the name "devicename.rbd".
*
@@ -40,6 +46,13 @@
#define OBJ_MAX_SIZE (1UL << OBJ_DEFAULT_OBJ_ORDER)
+#define RBD_MAX_CONF_NAME_SIZE 128
+#define RBD_MAX_CONF_VAL_SIZE 512
+#define RBD_MAX_CONF_SIZE 1024
+#define RBD_MAX_POOL_NAME_SIZE 128
+#define RBD_MAX_SNAP_NAME_SIZE 128
+#define RBD_MAX_SNAPS 100
+
typedef struct RBDAIOCB {
BlockDriverAIOCB common;
QEMUBH *bh;
@@ -48,7 +61,6 @@ typedef struct RBDAIOCB {
char *bounce;
int write;
int64_t sector_num;
- int aiocnt;
int error;
struct BDRVRBDState *s;
int cancelled;
@@ -59,7 +71,7 @@ typedef struct RADOSCB {
RBDAIOCB *acb;
struct BDRVRBDState *s;
int done;
- int64_t segsize;
+ int64_t size;
char *buf;
int ret;
} RADOSCB;
@@ -69,25 +81,22 @@ typedef struct RADOSCB {
typedef struct BDRVRBDState {
int fds[2];
- rados_pool_t pool;
- rados_pool_t header_pool;
- char name[RBD_MAX_OBJ_NAME_SIZE];
- char block_name[RBD_MAX_BLOCK_NAME_SIZE];
- uint64_t size;
- uint64_t objsize;
+ rados_t cluster;
+ rados_ioctx_t io_ctx;
+ rbd_image_t image;
+ char name[RBD_MAX_IMAGE_NAME_SIZE];
int qemu_aio_count;
+ char *snap;
int event_reader_pos;
RADOSCB *event_rcb;
} BDRVRBDState;
-typedef struct rbd_obj_header_ondisk RbdHeader1;
-
static void rbd_aio_bh_cb(void *opaque);
-static int rbd_next_tok(char *dst, int dst_len,
- char *src, char delim,
- const char *name,
- char **p)
+static int qemu_rbd_next_tok(char *dst, int dst_len,
+ char *src, char delim,
+ const char *name,
+ char **p)
{
int l;
char *end;
@@ -115,10 +124,11 @@ static int rbd_next_tok(char *dst, int dst_len,
return 0;
}
-static int rbd_parsename(const char *filename,
- char *pool, int pool_len,
- char *snap, int snap_len,
- char *name, int name_len)
+static int qemu_rbd_parsename(const char *filename,
+ char *pool, int pool_len,
+ char *snap, int snap_len,
+ char *name, int name_len,
+ char *conf, int conf_len)
{
const char *start;
char *p, *buf;
@@ -130,138 +140,108 @@ static int rbd_parsename(const char *filename,
buf = qemu_strdup(start);
p = buf;
+ *snap = '\0';
+ *conf = '\0';
- ret = rbd_next_tok(pool, pool_len, p, '/', "pool name", &p);
+ ret = qemu_rbd_next_tok(pool, pool_len, p, '/', "pool name", &p);
if (ret < 0 || !p) {
ret = -EINVAL;
goto done;
}
- ret = rbd_next_tok(name, name_len, p, '@', "object name", &p);
- if (ret < 0) {
- goto done;
+
+ if (strchr(p, '@')) {
+ ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p);
+ if (ret < 0) {
+ goto done;
+ }
+ ret = qemu_rbd_next_tok(snap, snap_len, p, ':', "snap name", &p);
+ } else {
+ ret = qemu_rbd_next_tok(name, name_len, p, ':', "object name", &p);
}
- if (!p) {
- *snap = '\0';
+ if (ret < 0 || !p) {
goto done;
}
- ret = rbd_next_tok(snap, snap_len, p, '\0', "snap name", &p);
+ ret = qemu_rbd_next_tok(conf, conf_len, p, '\0', "configuration", &p);
done:
qemu_free(buf);
return ret;
}
-static int create_tmap_op(uint8_t op, const char *name, char **tmap_desc)
-{
- uint32_t len = strlen(name);
- uint32_t len_le = cpu_to_le32(len);
- /* total_len = encoding op + name + empty buffer */
- uint32_t total_len = 1 + (sizeof(uint32_t) + len) + sizeof(uint32_t);
- uint8_t *desc = NULL;
-
- desc = qemu_malloc(total_len);
-
- *tmap_desc = (char *)desc;
-
- *desc = op;
- desc++;
- memcpy(desc, &len_le, sizeof(len_le));
- desc += sizeof(len_le);
- memcpy(desc, name, len);
- desc += len;
- len = 0; /* no need for endian conversion for 0 */
- memcpy(desc, &len, sizeof(len));
- desc += sizeof(len);
-
- return (char *)desc - *tmap_desc;
-}
-
-static void free_tmap_op(char *tmap_desc)
+static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
{
- qemu_free(tmap_desc);
-}
-
-static int rbd_register_image(rados_pool_t pool, const char *name)
-{
- char *tmap_desc;
- const char *dir = RBD_DIRECTORY;
- int ret;
-
- ret = create_tmap_op(CEPH_OSD_TMAP_SET, name, &tmap_desc);
- if (ret < 0) {
- return ret;
- }
-
- ret = rados_tmap_update(pool, dir, tmap_desc, ret);
- free_tmap_op(tmap_desc);
-
- return ret;
-}
+ char *p, *buf;
+ char name[RBD_MAX_CONF_NAME_SIZE];
+ char value[RBD_MAX_CONF_VAL_SIZE];
+ int ret = 0;
-static int touch_rbd_info(rados_pool_t pool, const char *info_oid)
-{
- int r = rados_write(pool, info_oid, 0, NULL, 0);
- if (r < 0) {
- return r;
- }
- return 0;
-}
+ buf = qemu_strdup(conf);
+ p = buf;
-static int rbd_assign_bid(rados_pool_t pool, uint64_t *id)
-{
- uint64_t out[1];
- const char *info_oid = RBD_INFO;
+ while (p) {
+ ret = qemu_rbd_next_tok(name, sizeof(name), p,
+ '=', "conf option name", &p);
+ if (ret < 0) {
+ break;
+ }
- *id = 0;
+ if (!p) {
+ error_report("conf option %s has no value", name);
+ ret = -EINVAL;
+ break;
+ }
- int r = touch_rbd_info(pool, info_oid);
- if (r < 0) {
- return r;
- }
+ ret = qemu_rbd_next_tok(value, sizeof(value), p,
+ ':', "conf option value", &p);
+ if (ret < 0) {
+ break;
+ }
- r = rados_exec(pool, info_oid, "rbd", "assign_bid", NULL,
- 0, (char *)out, sizeof(out));
- if (r < 0) {
- return r;
+ if (strcmp(name, "conf")) {
+ ret = rados_conf_set(cluster, name, value);
+ if (ret < 0) {
+ error_report("invalid conf option %s", name);
+ ret = -EINVAL;
+ break;
+ }
+ } else {
+ ret = rados_conf_read_file(cluster, value);
+ if (ret < 0) {
+ error_report("error reading conf file %s", value);
+ break;
+ }
+ }
}
- le64_to_cpus(out);
- *id = out[0];
-
- return 0;
+ qemu_free(buf);
+ return ret;
}
-static int rbd_create(const char *filename, QEMUOptionParameter *options)
+static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options)
{
int64_t bytes = 0;
int64_t objsize;
- uint64_t size;
- time_t mtime;
- uint8_t obj_order = RBD_DEFAULT_OBJ_ORDER;
- char pool[RBD_MAX_SEG_NAME_SIZE];
- char n[RBD_MAX_SEG_NAME_SIZE];
- char name[RBD_MAX_OBJ_NAME_SIZE];
- char snap_buf[RBD_MAX_SEG_NAME_SIZE];
+ int obj_order = 0;
+ char pool[RBD_MAX_POOL_NAME_SIZE];
+ char name[RBD_MAX_IMAGE_NAME_SIZE];
+ char snap_buf[RBD_MAX_SNAP_NAME_SIZE];
+ char conf[RBD_MAX_CONF_SIZE];
char *snap = NULL;
- RbdHeader1 header;
- rados_pool_t p;
- uint64_t bid;
- uint32_t hi, lo;
+ rados_t cluster;
+ rados_ioctx_t io_ctx;
int ret;
- if (rbd_parsename(filename,
- pool, sizeof(pool),
- snap_buf, sizeof(snap_buf),
- name, sizeof(name)) < 0) {
+ if (qemu_rbd_parsename(filename, pool, sizeof(pool),
+ snap_buf, sizeof(snap_buf),
+ name, sizeof(name),
+ conf, sizeof(conf)) < 0) {
return -EINVAL;
}
if (snap_buf[0] != '\0') {
snap = snap_buf;
}
- snprintf(n, sizeof(n), "%s%s", name, RBD_SUFFIX);
-
/* Read out options */
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
@@ -277,82 +257,64 @@ static int rbd_create(const char *filename, QEMUOptionParameter *options)
error_report("obj size too small");
return -EINVAL;
}
- obj_order = ffs(objsize) - 1;
+ obj_order = ffs(objsize) - 1;
}
}
options++;
}
- memset(&header, 0, sizeof(header));
- pstrcpy(header.text, sizeof(header.text), RBD_HEADER_TEXT);
- pstrcpy(header.signature, sizeof(header.signature), RBD_HEADER_SIGNATURE);
- pstrcpy(header.version, sizeof(header.version), RBD_HEADER_VERSION);
- header.image_size = cpu_to_le64(bytes);
- header.options.order = obj_order;
- header.options.crypt_type = RBD_CRYPT_NONE;
- header.options.comp_type = RBD_COMP_NONE;
- header.snap_seq = 0;
- header.snap_count = 0;
-
- if (rados_initialize(0, NULL) < 0) {
+ if (rados_create(&cluster, NULL) < 0) {
error_report("error initializing");
return -EIO;
}
- if (rados_open_pool(pool, &p)) {
- error_report("error opening pool %s", pool);
- rados_deinitialize();
- return -EIO;
+ if (strstr(conf, "conf=") == NULL) {
+ if (rados_conf_read_file(cluster, NULL) < 0) {
+ error_report("error reading config file");
+ rados_shutdown(cluster);
+ return -EIO;
+ }
}
- /* check for existing rbd header file */
- ret = rados_stat(p, n, &size, &mtime);
- if (ret == 0) {
- ret=-EEXIST;
- goto done;
+ if (conf[0] != '\0' &&
+ qemu_rbd_set_conf(cluster, conf) < 0) {
+ error_report("error setting config options");
+ rados_shutdown(cluster);
+ return -EIO;
}
- ret = rbd_assign_bid(p, &bid);
- if (ret < 0) {
- error_report("failed assigning block id");
- rados_deinitialize();
+ if (rados_connect(cluster) < 0) {
+ error_report("error connecting");
+ rados_shutdown(cluster);
return -EIO;
}
- hi = bid >> 32;
- lo = bid & 0xFFFFFFFF;
- snprintf(header.block_name, sizeof(header.block_name), "rb.%x.%x", hi, lo);
- /* create header file */
- ret = rados_write(p, n, 0, (const char *)&header, sizeof(header));
- if (ret < 0) {
- goto done;
+ if (rados_ioctx_create(cluster, pool, &io_ctx) < 0) {
+ error_report("error opening pool %s", pool);
+ rados_shutdown(cluster);
+ return -EIO;
}
- ret = rbd_register_image(p, name);
-done:
- rados_close_pool(p);
- rados_deinitialize();
+ ret = rbd_create(io_ctx, name, bytes, &obj_order);
+ rados_ioctx_destroy(io_ctx);
+ rados_shutdown(cluster);
return ret;
}
/*
- * This aio completion is being called from rbd_aio_event_reader() and
- * runs in qemu context. It schedules a bh, but just in case the aio
+ * This aio completion is being called from qemu_rbd_aio_event_reader()
+ * and runs in qemu context. It schedules a bh, but just in case the aio
* was not cancelled before.
*/
-static void rbd_complete_aio(RADOSCB *rcb)
+static void qemu_rbd_complete_aio(RADOSCB *rcb)
{
RBDAIOCB *acb = rcb->acb;
int64_t r;
- acb->aiocnt--;
-
if (acb->cancelled) {
- if (!acb->aiocnt) {
- qemu_vfree(acb->bounce);
- qemu_aio_release(acb);
- }
+ qemu_vfree(acb->bounce);
+ qemu_aio_release(acb);
goto done;
}
@@ -363,32 +325,25 @@ static void rbd_complete_aio(RADOSCB *rcb)
acb->ret = r;
acb->error = 1;
} else if (!acb->error) {
- acb->ret += rcb->segsize;
+ acb->ret = rcb->size;
}
} else {
- if (r == -ENOENT) {
- memset(rcb->buf, 0, rcb->segsize);
- if (!acb->error) {
- acb->ret += rcb->segsize;
- }
- } else if (r < 0) {
- memset(rcb->buf, 0, rcb->segsize);
+ if (r < 0) {
+ memset(rcb->buf, 0, rcb->size);
acb->ret = r;
acb->error = 1;
- } else if (r < rcb->segsize) {
- memset(rcb->buf + r, 0, rcb->segsize - r);
+ } else if (r < rcb->size) {
+ memset(rcb->buf + r, 0, rcb->size - r);
if (!acb->error) {
- acb->ret += rcb->segsize;
+ acb->ret = rcb->size;
}
} else if (!acb->error) {
- acb->ret += r;
+ acb->ret = r;
}
}
/* Note that acb->bh can be NULL in case where the aio was cancelled */
- if (!acb->aiocnt) {
- acb->bh = qemu_bh_new(rbd_aio_bh_cb, acb);
- qemu_bh_schedule(acb->bh);
- }
+ acb->bh = qemu_bh_new(rbd_aio_bh_cb, acb);
+ qemu_bh_schedule(acb->bh);
done:
qemu_free(rcb);
}
@@ -397,7 +352,7 @@ done:
* aio fd read handler. It runs in the qemu context and calls the
* completion handling of completed rados aio operations.
*/
-static void rbd_aio_event_reader(void *opaque)
+static void qemu_rbd_aio_event_reader(void *opaque)
{
BDRVRBDState *s = opaque;
@@ -413,176 +368,87 @@ static void rbd_aio_event_reader(void *opaque)
s->event_reader_pos += ret;
if (s->event_reader_pos == sizeof(s->event_rcb)) {
s->event_reader_pos = 0;
- rbd_complete_aio(s->event_rcb);
- s->qemu_aio_count --;
+ qemu_rbd_complete_aio(s->event_rcb);
+ s->qemu_aio_count--;
}
}
}
} while (ret < 0 && errno == EINTR);
}
-static int rbd_aio_flush_cb(void *opaque)
+static int qemu_rbd_aio_flush_cb(void *opaque)
{
BDRVRBDState *s = opaque;
return (s->qemu_aio_count > 0);
}
-
-static int rbd_set_snapc(rados_pool_t pool, const char *snap, RbdHeader1 *header)
-{
- uint32_t snap_count = le32_to_cpu(header->snap_count);
- rados_snap_t *snaps = NULL;
- rados_snap_t seq;
- uint32_t i;
- uint64_t snap_names_len = le64_to_cpu(header->snap_names_len);
- int r;
- rados_snap_t snapid = 0;
-
- if (snap_count) {
- const char *header_snap = (const char *)&header->snaps[snap_count];
- const char *end = header_snap + snap_names_len;
- snaps = qemu_malloc(sizeof(rados_snap_t) * header->snap_count);
-
- for (i=0; i < snap_count; i++) {
- snaps[i] = le64_to_cpu(header->snaps[i].id);
-
- if (snap && strcmp(snap, header_snap) == 0) {
- snapid = snaps[i];
- }
-
- header_snap += strlen(header_snap) + 1;
- if (header_snap > end) {
- error_report("bad header, snapshot list broken");
- }
- }
- }
-
- if (snap && !snapid) {
- error_report("snapshot not found");
- qemu_free(snaps);
- return -ENOENT;
- }
- seq = le32_to_cpu(header->snap_seq);
-
- r = rados_set_snap_context(pool, seq, snaps, snap_count);
-
- rados_set_snap(pool, snapid);
-
- qemu_free(snaps);
-
- return r;
-}
-
-#define BUF_READ_START_LEN 4096
-
-static int rbd_read_header(BDRVRBDState *s, char **hbuf)
-{
- char *buf = NULL;
- char n[RBD_MAX_SEG_NAME_SIZE];
- uint64_t len = BUF_READ_START_LEN;
- int r;
-
- snprintf(n, sizeof(n), "%s%s", s->name, RBD_SUFFIX);
-
- buf = qemu_malloc(len);
-
- r = rados_read(s->header_pool, n, 0, buf, len);
- if (r < 0) {
- goto failed;
- }
-
- if (r < len) {
- goto done;
- }
-
- qemu_free(buf);
- buf = qemu_malloc(len);
-
- r = rados_stat(s->header_pool, n, &len, NULL);
- if (r < 0) {
- goto failed;
- }
-
- r = rados_read(s->header_pool, n, 0, buf, len);
- if (r < 0) {
- goto failed;
- }
-
-done:
- *hbuf = buf;
- return 0;
-
-failed:
- qemu_free(buf);
- return r;
-}
-
-static int rbd_open(BlockDriverState *bs, const char *filename, int flags)
+static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags)
{
BDRVRBDState *s = bs->opaque;
- RbdHeader1 *header;
- char pool[RBD_MAX_SEG_NAME_SIZE];
- char snap_buf[RBD_MAX_SEG_NAME_SIZE];
- char *snap = NULL;
- char *hbuf = NULL;
+ char pool[RBD_MAX_POOL_NAME_SIZE];
+ char snap_buf[RBD_MAX_SNAP_NAME_SIZE];
+ char conf[RBD_MAX_CONF_SIZE];
int r;
- if (rbd_parsename(filename, pool, sizeof(pool),
- snap_buf, sizeof(snap_buf),
- s->name, sizeof(s->name)) < 0) {
+ if (qemu_rbd_parsename(filename, pool, sizeof(pool),
+ snap_buf, sizeof(snap_buf),
+ s->name, sizeof(s->name),
+ conf, sizeof(conf)) < 0) {
return -EINVAL;
}
+ s->snap = NULL;
if (snap_buf[0] != '\0') {
- snap = snap_buf;
+ s->snap = qemu_strdup(snap_buf);
}
- if ((r = rados_initialize(0, NULL)) < 0) {
+ r = rados_create(&s->cluster, NULL);
+ if (r < 0) {
error_report("error initializing");
return r;
}
- if ((r = rados_open_pool(pool, &s->pool))) {
- error_report("error opening pool %s", pool);
- rados_deinitialize();
- return r;
- }
-
- if ((r = rados_open_pool(pool, &s->header_pool))) {
- error_report("error opening pool %s", pool);
- rados_deinitialize();
- return r;
+ if (strstr(conf, "conf=") == NULL) {
+ r = rados_conf_read_file(s->cluster, NULL);
+ if (r < 0) {
+ error_report("error reading config file");
+ rados_shutdown(s->cluster);
+ return r;
+ }
}
- if ((r = rbd_read_header(s, &hbuf)) < 0) {
- error_report("error reading header from %s", s->name);
- goto failed;
+ if (conf[0] != '\0') {
+ r = qemu_rbd_set_conf(s->cluster, conf);
+ if (r < 0) {
+ error_report("error setting config options");
+ rados_shutdown(s->cluster);
+ return r;
+ }
}
- if (memcmp(hbuf + 64, RBD_HEADER_SIGNATURE, 4)) {
- error_report("Invalid header signature");
- r = -EMEDIUMTYPE;
- goto failed;
+ r = rados_connect(s->cluster);
+ if (r < 0) {
+ error_report("error connecting");
+ rados_shutdown(s->cluster);
+ return r;
}
- if (memcmp(hbuf + 68, RBD_HEADER_VERSION, 8)) {
- error_report("Unknown image version");
- r = -EMEDIUMTYPE;
- goto failed;
+ r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
+ if (r < 0) {
+ error_report("error opening pool %s", pool);
+ rados_shutdown(s->cluster);
+ return r;
}
- header = (RbdHeader1 *) hbuf;
- s->size = le64_to_cpu(header->image_size);
- s->objsize = 1ULL << header->options.order;
- memcpy(s->block_name, header->block_name, sizeof(header->block_name));
-
- r = rbd_set_snapc(s->pool, snap, header);
+ r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
if (r < 0) {
- error_report("failed setting snap context: %s", strerror(-r));
- goto failed;
+ error_report("error reading header from %s", s->name);
+ rados_ioctx_destroy(s->io_ctx);
+ rados_shutdown(s->cluster);
+ return r;
}
- bs->read_only = (snap != NULL);
+ bs->read_only = (s->snap != NULL);
s->event_reader_pos = 0;
r = qemu_pipe(s->fds);
@@ -592,23 +458,20 @@ static int rbd_open(BlockDriverState *bs, const char *filename, int flags)
}
fcntl(s->fds[0], F_SETFL, O_NONBLOCK);
fcntl(s->fds[1], F_SETFL, O_NONBLOCK);
- qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], rbd_aio_event_reader, NULL,
- rbd_aio_flush_cb, NULL, s);
+ qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], qemu_rbd_aio_event_reader,
+ NULL, qemu_rbd_aio_flush_cb, NULL, s);
- qemu_free(hbuf);
return 0;
failed:
- qemu_free(hbuf);
-
- rados_close_pool(s->header_pool);
- rados_close_pool(s->pool);
- rados_deinitialize();
+ rbd_close(s->image);
+ rados_ioctx_destroy(s->io_ctx);
+ rados_shutdown(s->cluster);
return r;
}
-static void rbd_close(BlockDriverState *bs)
+static void qemu_rbd_close(BlockDriverState *bs)
{
BDRVRBDState *s = bs->opaque;
@@ -617,16 +480,17 @@ static void rbd_close(BlockDriverState *bs)
qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], NULL , NULL, NULL, NULL,
NULL);
- rados_close_pool(s->header_pool);
- rados_close_pool(s->pool);
- rados_deinitialize();
+ rbd_close(s->image);
+ rados_ioctx_destroy(s->io_ctx);
+ qemu_free(s->snap);
+ rados_shutdown(s->cluster);
}
/*
* Cancel aio. Since we don't reference acb in a non qemu threads,
* it is safe to access it here.
*/
-static void rbd_aio_cancel(BlockDriverAIOCB *blockacb)
+static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
{
RBDAIOCB *acb = (RBDAIOCB *) blockacb;
acb->cancelled = 1;
@@ -634,39 +498,28 @@ static void rbd_aio_cancel(BlockDriverAIOCB *blockacb)
static AIOPool rbd_aio_pool = {
.aiocb_size = sizeof(RBDAIOCB),
- .cancel = rbd_aio_cancel,
+ .cancel = qemu_rbd_aio_cancel,
};
-/*
- * This is the callback function for rados_aio_read and _write
- *
- * 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
- * write to the block notification pipe, and do the rest of the
- * io completion handling from rbd_aio_event_reader() which
- * runs in a qemu context.
- */
-static void rbd_finish_aiocb(rados_completion_t c, RADOSCB *rcb)
+static int qemu_rbd_send_pipe(BDRVRBDState *s, RADOSCB *rcb)
{
- int ret;
- rcb->ret = rados_aio_get_return_value(c);
- rados_aio_release(c);
+ int ret = 0;
while (1) {
fd_set wfd;
- int fd = rcb->s->fds[RBD_FD_WRITE];
+ int fd = s->fds[RBD_FD_WRITE];
- /* send the rcb pointer to the qemu thread that is responsible
- for the aio completion. Must do it in a qemu thread context */
+ /* send the op pointer to the qemu thread that is responsible
+ for the aio/op completion. Must do it in a qemu thread context */
ret = write(fd, (void *)&rcb, sizeof(rcb));
if (ret >= 0) {
break;
}
if (errno == EINTR) {
continue;
- }
+ }
if (errno != EAGAIN) {
break;
- }
+ }
FD_ZERO(&wfd);
FD_SET(fd, &wfd);
@@ -675,13 +528,31 @@ static void rbd_finish_aiocb(rados_completion_t c, RADOSCB *rcb)
} while (ret < 0 && errno == EINTR);
}
+ return ret;
+}
+
+/*
+ * This is the callback function for rbd_aio_read and _write
+ *
+ * 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
+ * write to the block notification pipe, and do the rest of the
+ * io completion handling from qemu_rbd_aio_event_reader() which
+ * runs in a qemu context.
+ */
+static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
+{
+ int ret;
+ rcb->ret = rbd_aio_get_return_value(c);
+ rbd_aio_release(c);
+ ret = qemu_rbd_send_pipe(rcb->s, rcb);
if (ret < 0) {
- error_report("failed writing to acb->s->fds\n");
+ error_report("failed writing to acb->s->fds");
qemu_free(rcb);
}
}
-/* Callback when all queued rados_aio requests are complete */
+/* Callback when all queued rbd_aio requests are complete */
static void rbd_aio_bh_cb(void *opaque)
{
@@ -707,19 +578,20 @@ static BlockDriverAIOCB *rbd_aio_rw_vector(BlockDriverState *bs,
{
RBDAIOCB *acb;
RADOSCB *rcb;
- rados_completion_t c;
- char n[RBD_MAX_SEG_NAME_SIZE];
- int64_t segnr, segoffs, segsize, last_segnr;
+ rbd_completion_t c;
int64_t off, size;
char *buf;
+ int r;
BDRVRBDState *s = bs->opaque;
acb = qemu_aio_get(&rbd_aio_pool, bs, cb, opaque);
+ if (!acb) {
+ return NULL;
+ }
acb->write = write;
acb->qiov = qiov;
acb->bounce = qemu_blockalign(bs, qiov->size);
- acb->aiocnt = 0;
acb->ret = 0;
acb->error = 0;
acb->s = s;
@@ -734,95 +606,106 @@ static BlockDriverAIOCB *rbd_aio_rw_vector(BlockDriverState *bs,
off = sector_num * BDRV_SECTOR_SIZE;
size = nb_sectors * BDRV_SECTOR_SIZE;
- segnr = off / s->objsize;
- segoffs = off % s->objsize;
- segsize = s->objsize - segoffs;
-
- last_segnr = ((off + size - 1) / s->objsize);
- acb->aiocnt = (last_segnr - segnr) + 1;
- s->qemu_aio_count += acb->aiocnt; /* All the RADOSCB */
+ s->qemu_aio_count++; /* All the RADOSCB */
- while (size > 0) {
- if (size < segsize) {
- segsize = size;
- }
+ rcb = qemu_malloc(sizeof(RADOSCB));
+ 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);
+ if (r < 0) {
+ goto failed;
+ }
- snprintf(n, sizeof(n), "%s.%012" PRIx64, s->block_name,
- segnr);
-
- rcb = qemu_malloc(sizeof(RADOSCB));
- rcb->done = 0;
- rcb->acb = acb;
- rcb->segsize = segsize;
- rcb->buf = buf;
- rcb->s = acb->s;
-
- if (write) {
- rados_aio_create_completion(rcb, NULL,
- (rados_callback_t) rbd_finish_aiocb,
- &c);
- rados_aio_write(s->pool, n, segoffs, buf, segsize, c);
- } else {
- rados_aio_create_completion(rcb,
- (rados_callback_t) rbd_finish_aiocb,
- NULL, &c);
- rados_aio_read(s->pool, n, segoffs, buf, segsize, c);
- }
+ if (write) {
+ r = rbd_aio_write(s->image, off, size, buf, c);
+ } else {
+ r = rbd_aio_read(s->image, off, size, buf, c);
+ }
- buf += segsize;
- size -= segsize;
- segoffs = 0;
- segsize = s->objsize;
- segnr++;
+ if (r < 0) {
+ goto failed;
}
return &acb->common;
+
+failed:
+ qemu_free(rcb);
+ s->qemu_aio_count--;
+ qemu_aio_release(acb);
+ return NULL;
}
-static BlockDriverAIOCB *rbd_aio_readv(BlockDriverState * bs,
- int64_t sector_num, QEMUIOVector * qiov,
- int nb_sectors,
- BlockDriverCompletionFunc * cb,
- void *opaque)
+static BlockDriverAIOCB *qemu_rbd_aio_readv(BlockDriverState *bs,
+ int64_t sector_num,
+ QEMUIOVector *qiov,
+ int nb_sectors,
+ BlockDriverCompletionFunc *cb,
+ void *opaque)
{
return rbd_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
}
-static BlockDriverAIOCB *rbd_aio_writev(BlockDriverState * bs,
- int64_t sector_num, QEMUIOVector * qiov,
- int nb_sectors,
- BlockDriverCompletionFunc * cb,
- void *opaque)
+static BlockDriverAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs,
+ int64_t sector_num,
+ QEMUIOVector *qiov,
+ int nb_sectors,
+ BlockDriverCompletionFunc *cb,
+ void *opaque)
{
return rbd_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
}
-static int rbd_getinfo(BlockDriverState * bs, BlockDriverInfo * bdi)
+static int qemu_rbd_getinfo(BlockDriverState *bs, BlockDriverInfo *bdi)
{
BDRVRBDState *s = bs->opaque;
- bdi->cluster_size = s->objsize;
+ rbd_image_info_t info;
+ int r;
+
+ r = rbd_stat(s->image, &info, sizeof(info));
+ if (r < 0) {
+ return r;
+ }
+
+ bdi->cluster_size = info.obj_size;
return 0;
}
-static int64_t rbd_getlength(BlockDriverState * bs)
+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));
+ if (r < 0) {
+ return r;
+ }
+
+ return info.size;
+}
+
+static int qemu_rbd_truncate(BlockDriverState *bs, int64_t offset)
{
BDRVRBDState *s = bs->opaque;
+ int r;
- return s->size;
+ r = rbd_resize(s->image, offset);
+ if (r < 0) {
+ return r;
+ }
+
+ return 0;
}
-static int rbd_snap_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
+static int qemu_rbd_snap_create(BlockDriverState *bs,
+ QEMUSnapshotInfo *sn_info)
{
BDRVRBDState *s = bs->opaque;
- char inbuf[512], outbuf[128];
- uint64_t snap_id;
int r;
- char *p = inbuf;
- char *end = inbuf + sizeof(inbuf);
- char n[RBD_MAX_SEG_NAME_SIZE];
- char *hbuf = NULL;
- RbdHeader1 *header;
if (sn_info->name[0] == '\0') {
return -EINVAL; /* we need a name for rbd snapshots */
@@ -841,185 +724,57 @@ static int rbd_snap_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
return -ERANGE;
}
- r = rados_selfmanaged_snap_create(s->header_pool, &snap_id);
- if (r < 0) {
- error_report("failed to create snap id: %s", strerror(-r));
- return r;
- }
-
- *(uint32_t *)p = strlen(sn_info->name);
- cpu_to_le32s((uint32_t *)p);
- p += sizeof(uint32_t);
- strncpy(p, sn_info->name, end - p);
- p += strlen(p);
- if (p + sizeof(snap_id) > end) {
- error_report("invalid input parameter");
- return -EINVAL;
- }
-
- *(uint64_t *)p = snap_id;
- cpu_to_le64s((uint64_t *)p);
-
- snprintf(n, sizeof(n), "%s%s", s->name, RBD_SUFFIX);
-
- r = rados_exec(s->header_pool, n, "rbd", "snap_add", inbuf,
- sizeof(inbuf), outbuf, sizeof(outbuf));
- if (r < 0) {
- error_report("rbd.snap_add execution failed failed: %s", strerror(-r));
- return r;
- }
-
- sprintf(sn_info->id_str, "%s", sn_info->name);
-
- r = rbd_read_header(s, &hbuf);
+ r = rbd_snap_create(s->image, sn_info->name);
if (r < 0) {
- error_report("failed reading header: %s", strerror(-r));
+ error_report("failed to create snap: %s", strerror(-r));
return r;
}
- header = (RbdHeader1 *) hbuf;
- r = rbd_set_snapc(s->pool, sn_info->name, header);
- if (r < 0) {
- error_report("failed setting snap context: %s", strerror(-r));
- goto failed;
- }
-
return 0;
-
-failed:
- qemu_free(header);
- return r;
}
-static int decode32(char **p, const char *end, uint32_t *v)
-{
- if (*p + 4 > end) {
- return -ERANGE;
- }
-
- *v = *(uint32_t *)(*p);
- le32_to_cpus(v);
- *p += 4;
- return 0;
-}
-
-static int decode64(char **p, const char *end, uint64_t *v)
-{
- if (*p + 8 > end) {
- return -ERANGE;
- }
-
- *v = *(uint64_t *)(*p);
- le64_to_cpus(v);
- *p += 8;
- return 0;
-}
-
-static int decode_str(char **p, const char *end, char **s)
-{
- uint32_t len;
- int r;
-
- if ((r = decode32(p, end, &len)) < 0) {
- return r;
- }
-
- *s = qemu_malloc(len + 1);
- memcpy(*s, *p, len);
- *p += len;
- (*s)[len] = '\0';
-
- return len;
-}
-
-static int rbd_snap_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
+static int qemu_rbd_snap_list(BlockDriverState *bs,
+ QEMUSnapshotInfo **psn_tab)
{
BDRVRBDState *s = bs->opaque;
- char n[RBD_MAX_SEG_NAME_SIZE];
QEMUSnapshotInfo *sn_info, *sn_tab = NULL;
- RbdHeader1 *header;
- char *hbuf = NULL;
- char *outbuf = NULL, *end, *buf;
- uint64_t len;
- uint64_t snap_seq;
- uint32_t snap_count;
- int r, i;
-
- /* read header to estimate how much space we need to read the snap
- * list */
- if ((r = rbd_read_header(s, &hbuf)) < 0) {
- goto done_err;
- }
- header = (RbdHeader1 *)hbuf;
- len = le64_to_cpu(header->snap_names_len);
- len += 1024; /* should have already been enough, but new snapshots might
- already been created since we read the header. just allocate
- a bit more, so that in most cases it'll suffice anyway */
- qemu_free(hbuf);
-
- snprintf(n, sizeof(n), "%s%s", s->name, RBD_SUFFIX);
- while (1) {
- qemu_free(outbuf);
- outbuf = qemu_malloc(len);
+ int i, snap_count;
+ rbd_snap_info_t *snaps;
+ int max_snaps = RBD_MAX_SNAPS;
- r = rados_exec(s->header_pool, n, "rbd", "snap_list", NULL, 0,
- outbuf, len);
- if (r < 0) {
- error_report("rbd.snap_list execution failed failed: %s", strerror(-r));
- goto done_err;
+ do {
+ snaps = qemu_malloc(sizeof(*snaps) * max_snaps);
+ snap_count = rbd_snap_list(s->image, snaps, &max_snaps);
+ if (snap_count < 0) {
+ qemu_free(snaps);
}
- if (r != len) {
- break;
- }
-
- /* if we're here, we probably raced with some snaps creation */
- len *= 2;
- }
- buf = outbuf;
- end = buf + len;
+ } while (snap_count == -ERANGE);
- if ((r = decode64(&buf, end, &snap_seq)) < 0) {
- goto done_err;
- }
- if ((r = decode32(&buf, end, &snap_count)) < 0) {
- goto done_err;
+ if (snap_count <= 0) {
+ return snap_count;
}
sn_tab = qemu_mallocz(snap_count * sizeof(QEMUSnapshotInfo));
- for (i = 0; i < snap_count; i++) {
- uint64_t id, image_size;
- char *snap_name;
- if ((r = decode64(&buf, end, &id)) < 0) {
- goto done_err;
- }
- if ((r = decode64(&buf, end, &image_size)) < 0) {
- goto done_err;
- }
- if ((r = decode_str(&buf, end, &snap_name)) < 0) {
- goto done_err;
- }
+ for (i = 0; i < snap_count; i++) {
+ const char *snap_name = snaps[i].name;
sn_info = sn_tab + i;
pstrcpy(sn_info->id_str, sizeof(sn_info->id_str), snap_name);
pstrcpy(sn_info->name, sizeof(sn_info->name), snap_name);
- qemu_free(snap_name);
- sn_info->vm_state_size = image_size;
+ sn_info->vm_state_size = snaps[i].size;
sn_info->date_sec = 0;
sn_info->date_nsec = 0;
sn_info->vm_clock_nsec = 0;
}
+ rbd_snap_list_end(snaps);
+
*psn_tab = sn_tab;
- qemu_free(outbuf);
return snap_count;
-done_err:
- qemu_free(sn_tab);
- qemu_free(outbuf);
- return r;
}
-static QEMUOptionParameter rbd_create_options[] = {
+static QEMUOptionParameter qemu_rbd_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
@@ -1036,19 +791,20 @@ static QEMUOptionParameter rbd_create_options[] = {
static BlockDriver bdrv_rbd = {
.format_name = "rbd",
.instance_size = sizeof(BDRVRBDState),
- .bdrv_file_open = rbd_open,
- .bdrv_close = rbd_close,
- .bdrv_create = rbd_create,
- .bdrv_get_info = rbd_getinfo,
- .create_options = rbd_create_options,
- .bdrv_getlength = rbd_getlength,
+ .bdrv_file_open = qemu_rbd_open,
+ .bdrv_close = qemu_rbd_close,
+ .bdrv_create = qemu_rbd_create,
+ .bdrv_get_info = qemu_rbd_getinfo,
+ .create_options = qemu_rbd_create_options,
+ .bdrv_getlength = qemu_rbd_getlength,
+ .bdrv_truncate = qemu_rbd_truncate,
.protocol_name = "rbd",
- .bdrv_aio_readv = rbd_aio_readv,
- .bdrv_aio_writev = rbd_aio_writev,
+ .bdrv_aio_readv = qemu_rbd_aio_readv,
+ .bdrv_aio_writev = qemu_rbd_aio_writev,
- .bdrv_snapshot_create = rbd_snap_create,
- .bdrv_snapshot_list = rbd_snap_list,
+ .bdrv_snapshot_create = qemu_rbd_snap_create,
+ .bdrv_snapshot_list = qemu_rbd_snap_list,
};
static void bdrv_rbd_init(void)
diff --git a/block/rbd_types.h b/block/rbd_types.h
deleted file mode 100644
index f4cca9970c..0000000000
--- a/block/rbd_types.h
+++ /dev/null
@@ -1,71 +0,0 @@
-/*
- * Ceph - scalable distributed file system
- *
- * Copyright (C) 2004-2010 Sage Weil <sage@newdream.net>
- *
- * This is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License version 2.1, as published by the Free Software
- * Foundation. See file COPYING.LIB.
- *
- */
-
-#ifndef CEPH_RBD_TYPES_H
-#define CEPH_RBD_TYPES_H
-
-
-/*
- * rbd image 'foo' consists of objects
- * foo.rbd - image metadata
- * foo.00000000
- * foo.00000001
- * ... - data
- */
-
-#define RBD_SUFFIX ".rbd"
-#define RBD_DIRECTORY "rbd_directory"
-#define RBD_INFO "rbd_info"
-
-#define RBD_DEFAULT_OBJ_ORDER 22 /* 4MB */
-
-#define RBD_MAX_OBJ_NAME_SIZE 96
-#define RBD_MAX_BLOCK_NAME_SIZE 24
-#define RBD_MAX_SEG_NAME_SIZE 128
-
-#define RBD_COMP_NONE 0
-#define RBD_CRYPT_NONE 0
-
-#define RBD_HEADER_TEXT "<<< Rados Block Device Image >>>\n"
-#define RBD_HEADER_SIGNATURE "RBD"
-#define RBD_HEADER_VERSION "001.005"
-
-struct rbd_info {
- uint64_t max_id;
-} __attribute__ ((packed));
-
-struct rbd_obj_snap_ondisk {
- uint64_t id;
- uint64_t image_size;
-} __attribute__((packed));
-
-struct rbd_obj_header_ondisk {
- char text[40];
- char block_name[RBD_MAX_BLOCK_NAME_SIZE];
- char signature[4];
- char version[8];
- struct {
- uint8_t order;
- uint8_t crypt_type;
- uint8_t comp_type;
- uint8_t unused;
- } __attribute__((packed)) options;
- uint64_t image_size;
- uint64_t snap_seq;
- uint32_t snap_count;
- uint32_t reserved;
- uint64_t snap_names_len;
- struct rbd_obj_snap_ondisk snaps[0];
-} __attribute__((packed));
-
-
-#endif
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 98946d72b7..0392ca8c9c 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -196,7 +196,7 @@ static inline uint64_t fnv_64a_buf(void *buf, size_t len, uint64_t hval)
return hval;
}
-static inline int is_data_obj_writeable(SheepdogInode *inode, unsigned int idx)
+static inline int is_data_obj_writable(SheepdogInode *inode, unsigned int idx)
{
return inode->vdi_id == inode->data_vdi_id[idx];
}
@@ -1577,7 +1577,7 @@ static void sd_readv_writev_bh_cb(void *p)
create = 1;
} else if (acb->aiocb_type == AIOCB_WRITE_UDATA
- && !is_data_obj_writeable(inode, idx)) {
+ && !is_data_obj_writable(inode, idx)) {
/* Copy-On-Write */
create = 1;
old_oid = oid;
diff --git a/block/vdi.c b/block/vdi.c
index 701745bf8c..4c9e201c33 100644
--- a/block/vdi.c
+++ b/block/vdi.c
@@ -87,6 +87,7 @@ void uuid_unparse(const uuid_t uu, char *out);
#define MiB (KiB * KiB)
#define SECTOR_SIZE 512
+#define DEFAULT_CLUSTER_SIZE (1 * MiB)
#if defined(CONFIG_VDI_DEBUG)
#define logout(fmt, ...) \
@@ -803,7 +804,7 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
int result = 0;
uint64_t bytes = 0;
uint32_t blocks;
- size_t block_size = 1 * MiB;
+ size_t block_size = DEFAULT_CLUSTER_SIZE;
uint32_t image_type = VDI_TYPE_DYNAMIC;
VdiHeader header;
size_t i;
@@ -921,7 +922,8 @@ static QEMUOptionParameter vdi_create_options[] = {
{
.name = BLOCK_OPT_CLUSTER_SIZE,
.type = OPT_SIZE,
- .help = "VDI cluster (block) size"
+ .help = "VDI cluster (block) size",
+ .value = { .n = DEFAULT_CLUSTER_SIZE },
},
#endif
#if defined(CONFIG_VDI_STATIC_IMAGE)
diff --git a/block/vmdk.c b/block/vmdk.c
index 8fc9d67208..922b23d8f5 100644
--- a/block/vmdk.c
+++ b/block/vmdk.c
@@ -716,11 +716,11 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
return -errno;
magic = cpu_to_be32(VMDK4_MAGIC);
memset(&header, 0, sizeof(header));
- header.version = cpu_to_le32(1);
- header.flags = cpu_to_le32(3); /* ?? */
- header.capacity = cpu_to_le64(total_size);
- header.granularity = cpu_to_le64(128);
- header.num_gtes_per_gte = cpu_to_le32(512);
+ header.version = 1;
+ header.flags = 3; /* ?? */
+ header.capacity = total_size;
+ header.granularity = 128;
+ header.num_gtes_per_gte = 512;
grains = (total_size + header.granularity - 1) / header.granularity;
gt_size = ((header.num_gtes_per_gte * sizeof(uint32_t)) + 511) >> 9;
@@ -736,6 +736,12 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
header.granularity - 1) / header.granularity) *
header.granularity;
+ /* swap endianness for all header fields */
+ header.version = cpu_to_le32(header.version);
+ header.flags = cpu_to_le32(header.flags);
+ header.capacity = cpu_to_le64(header.capacity);
+ header.granularity = cpu_to_le64(header.granularity);
+ header.num_gtes_per_gte = cpu_to_le32(header.num_gtes_per_gte);
header.desc_offset = cpu_to_le64(header.desc_offset);
header.desc_size = cpu_to_le64(header.desc_size);
header.rgd_offset = cpu_to_le64(header.rgd_offset);
@@ -759,7 +765,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
goto exit;
}
- ret = ftruncate(fd, header.grain_offset << 9);
+ ret = ftruncate(fd, le64_to_cpu(header.grain_offset) << 9);
if (ret < 0) {
ret = -errno;
goto exit;
@@ -767,7 +773,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
/* write grain directory */
lseek(fd, le64_to_cpu(header.rgd_offset) << 9, SEEK_SET);
- for (i = 0, tmp = header.rgd_offset + gd_size;
+ for (i = 0, tmp = le64_to_cpu(header.rgd_offset) + gd_size;
i < gt_count; i++, tmp += gt_size) {
ret = qemu_write_full(fd, &tmp, sizeof(tmp));
if (ret != sizeof(tmp)) {
@@ -778,7 +784,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
/* write backup grain directory */
lseek(fd, le64_to_cpu(header.gd_offset) << 9, SEEK_SET);
- for (i = 0, tmp = header.gd_offset + gd_size;
+ for (i = 0, tmp = le64_to_cpu(header.gd_offset) + gd_size;
i < gt_count; i++, tmp += gt_size) {
ret = qemu_write_full(fd, &tmp, sizeof(tmp));
if (ret != sizeof(tmp)) {
generated by cgit v1.2.1 (git 2.18.0) at 2024-07-01 06:37:51 +0000