/*
* Set ZFS_PROP_VOLSIZE set entry point.
*/
int
zvol_set_volsize(const char *name, uint64_t volsize)
{
zvol_state_t *zv = NULL;
objset_t *os = NULL;
int error;
dmu_object_info_t *doi;
uint64_t readonly;
boolean_t owned = B_FALSE;
error = dsl_prop_get_integer(name,
zfs_prop_to_name(ZFS_PROP_READONLY), &readonly, NULL);
if (error != 0)
return (SET_ERROR(error));
if (readonly)
return (SET_ERROR(EROFS));
mutex_enter(&zvol_state_lock);
zv = zvol_find_by_name(name);
if (zv == NULL || zv->zv_objset == NULL) {
if ((error = dmu_objset_own(name, DMU_OST_ZVOL, B_FALSE,
FTAG, &os)) != 0) {
mutex_exit(&zvol_state_lock);
return (SET_ERROR(error));
}
owned = B_TRUE;
if (zv != NULL)
zv->zv_objset = os;
} else {
os = zv->zv_objset;
}
doi = kmem_alloc(sizeof (dmu_object_info_t), KM_SLEEP);
if ((error = dmu_object_info(os, ZVOL_OBJ, doi)) ||
(error = zvol_check_volsize(volsize, doi->doi_data_block_size)))
goto out;
error = zvol_update_volsize(volsize, os);
kmem_free(doi, sizeof (dmu_object_info_t));
if (error == 0 && zv != NULL)
error = zvol_update_live_volsize(zv, volsize);
out:
if (owned) {
dmu_objset_disown(os, FTAG);
if (zv != NULL)
zv->zv_objset = NULL;
}
mutex_exit(&zvol_state_lock);
return (error);
}
/*
* Clean up any znodes that had no links when we either crashed or
* (force) umounted the file system.
*/
void
zfs_unlinked_drain(zfsvfs_t *zfsvfs)
{
zap_cursor_t zc;
zap_attribute_t zap;
dmu_object_info_t doi;
znode_t *zp;
int error;
printf("ZFS: unlinked drain\n");
/*
* Interate over the contents of the unlinked set.
*/
for (zap_cursor_init(&zc, zfsvfs->z_os, zfsvfs->z_unlinkedobj);
zap_cursor_retrieve(&zc, &zap) == 0;
zap_cursor_advance(&zc)) {
/*
* See what kind of object we have in list
*/
error = dmu_object_info(zfsvfs->z_os,
zap.za_first_integer, &doi);
if (error != 0)
continue;
ASSERT((doi.doi_type == DMU_OT_PLAIN_FILE_CONTENTS) ||
(doi.doi_type == DMU_OT_DIRECTORY_CONTENTS));
/*
* We need to re-mark these list entries for deletion,
* so we pull them back into core and set zp->z_unlinked.
*/
error = zfs_zget(zfsvfs, zap.za_first_integer, &zp);
/*
* We may pick up znodes that are already marked for deletion.
* This could happen during the purge of an extended attribute
* directory. All we need to do is skip over them, since they
* are already in the system marked z_unlinked.
*/
if (error != 0)
continue;
zp->z_unlinked = B_TRUE;
VN_RELE(ZTOV(zp));
}
zap_cursor_fini(&zc);
printf("ZFS: unlinked drain completed.\n");
}
/*
* Set ZFS_PROP_VOLSIZE set entry point.
*/
int
zvol_set_volsize(const char *name, uint64_t volsize)
{
zvol_state_t *zv;
dmu_object_info_t *doi;
objset_t *os = NULL;
uint64_t readonly;
int error;
mutex_enter(&zvol_state_lock);
zv = zvol_find_by_name(name);
if (zv == NULL) {
error = ENXIO;
goto out;
}
doi = kmem_alloc(sizeof(dmu_object_info_t), KM_SLEEP);
error = dmu_objset_hold(name, FTAG, &os);
if (error)
goto out_doi;
if ((error = dmu_object_info(os, ZVOL_OBJ, doi)) != 0 ||
(error = zvol_check_volsize(volsize,doi->doi_data_block_size)) != 0)
goto out_doi;
VERIFY(dsl_prop_get_integer(name, "readonly", &readonly, NULL) == 0);
if (readonly) {
error = EROFS;
goto out_doi;
}
if (get_disk_ro(zv->zv_disk) || (zv->zv_flags & ZVOL_RDONLY)) {
error = EROFS;
goto out_doi;
}
error = zvol_update_volsize(zv, volsize, os);
out_doi:
kmem_free(doi, sizeof(dmu_object_info_t));
out:
if (os)
dmu_objset_rele(os, FTAG);
mutex_exit(&zvol_state_lock);
return (error);
}
int
zvol_get_stats(zfs_cmd_t *zc, objset_t *os)
{
int error;
dmu_object_info_t doi;
error = zap_lookup(os, ZVOL_ZAP_OBJ, "size", 8, 1, &zc->zc_volsize);
if (error)
return (error);
error = dmu_object_info(os, ZVOL_OBJ, &doi);
if (error == 0)
zc->zc_volblocksize = doi.doi_data_block_size;
return (error);
}
int
zvol_get_stats(objset_t *os, nvlist_t *nv)
{
int error;
dmu_object_info_t doi;
uint64_t val;
error = zap_lookup(os, ZVOL_ZAP_OBJ, "size", 8, 1, &val);
if (error)
return (error);
dsl_prop_nvlist_add_uint64(nv, ZFS_PROP_VOLSIZE, val);
error = dmu_object_info(os, ZVOL_OBJ, &doi);
if (error == 0) {
dsl_prop_nvlist_add_uint64(nv, ZFS_PROP_VOLBLOCKSIZE,
doi.doi_data_block_size);
}
return (error);
}
/*
* zfs_init_fs - Initialize the zfsvfs struct and the file system
* incore "master" object. Verify version compatibility.
*/
int
zfs_init_fs(zfsvfs_t *zfsvfs, znode_t **zpp, cred_t *cr)
{
extern int zfsfstype;
objset_t *os = zfsvfs->z_os;
int i, error;
dmu_object_info_t doi;
uint64_t fsid_guid;
uint64_t zval;
*zpp = NULL;
/*
* XXX - hack to auto-create the pool root filesystem at
* the first attempted mount.
*/
if (dmu_object_info(os, MASTER_NODE_OBJ, &doi) == ENOENT) {
dmu_tx_t *tx = dmu_tx_create(os);
uint64_t zpl_version;
nvlist_t *zprops;
dmu_tx_hold_zap(tx, DMU_NEW_OBJECT, TRUE, NULL); /* master */
dmu_tx_hold_zap(tx, DMU_NEW_OBJECT, TRUE, NULL); /* del queue */
dmu_tx_hold_bonus(tx, DMU_NEW_OBJECT); /* root node */
error = dmu_tx_assign(tx, TXG_WAIT);
ASSERT3U(error, ==, 0);
if (spa_version(dmu_objset_spa(os)) >= SPA_VERSION_FUID)
zpl_version = ZPL_VERSION;
else
zpl_version = ZPL_VERSION_FUID - 1;
VERIFY(nvlist_alloc(&zprops, NV_UNIQUE_NAME, KM_SLEEP) == 0);
VERIFY(nvlist_add_uint64(zprops,
zfs_prop_to_name(ZFS_PROP_VERSION), zpl_version) == 0);
zfs_create_fs(os, cr, zprops, tx);
nvlist_free(zprops);
dmu_tx_commit(tx);
}
/*
* ZFS_IOC_OBJSET_STATS entry point.
*/
int
zvol_get_stats(objset_t *os, nvlist_t *nv)
{
int error;
dmu_object_info_t *doi;
uint64_t val;
error = zap_lookup(os, ZVOL_ZAP_OBJ, "size", 8, 1, &val);
if (error)
return (SET_ERROR(error));
dsl_prop_nvlist_add_uint64(nv, ZFS_PROP_VOLSIZE, val);
doi = kmem_alloc(sizeof (dmu_object_info_t), KM_SLEEP);
error = dmu_object_info(os, ZVOL_OBJ, doi);
if (error == 0) {
dsl_prop_nvlist_add_uint64(nv, ZFS_PROP_VOLBLOCKSIZE,
doi->doi_data_block_size);
}
kmem_free(doi, sizeof (dmu_object_info_t));
return (SET_ERROR(error));
}
static int
zfs_replay_create(zfsvfs_t *zfsvfs, lr_create_t *lr, boolean_t byteswap)
{
char *name = NULL; /* location determined later */
char *link; /* symlink content follows name */
znode_t *dzp;
vnode_t *vp = NULL;
xvattr_t xva;
int vflg = 0;
size_t lrsize = sizeof (lr_create_t);
lr_attr_t *lrattr;
void *start;
size_t xvatlen;
uint64_t txtype;
struct componentname cn;
int error;
txtype = (lr->lr_common.lrc_txtype & ~TX_CI);
if (byteswap) {
byteswap_uint64_array(lr, sizeof (*lr));
if (txtype == TX_CREATE_ATTR || txtype == TX_MKDIR_ATTR)
zfs_replay_swap_attrs((lr_attr_t *)(lr + 1));
}
if ((error = zfs_zget(zfsvfs, lr->lr_doid, &dzp)) != 0)
return (error);
xva_init(&xva);
zfs_init_vattr(&xva.xva_vattr, AT_TYPE | AT_MODE | AT_UID | AT_GID,
lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, lr->lr_foid);
/*
* All forms of zfs create (create, mkdir, mkxattrdir, symlink)
* eventually end up in zfs_mknode(), which assigns the object's
* creation time and generation number. The generic VOP_CREATE()
* doesn't have either concept, so we smuggle the values inside
* the vattr's otherwise unused va_ctime and va_nblocks fields.
*/
ZFS_TIME_DECODE(&xva.xva_vattr.va_ctime, lr->lr_crtime);
xva.xva_vattr.va_nblocks = lr->lr_gen;
error = dmu_object_info(zfsvfs->z_os, lr->lr_foid, NULL);
if (error != ENOENT)
goto out;
if (lr->lr_common.lrc_txtype & TX_CI)
vflg |= FIGNORECASE;
/*
* Symlinks don't have fuid info, and CIFS never creates
* symlinks.
*
* The _ATTR versions will grab the fuid info in their subcases.
*/
if ((int)lr->lr_common.lrc_txtype != TX_SYMLINK &&
(int)lr->lr_common.lrc_txtype != TX_MKDIR_ATTR &&
(int)lr->lr_common.lrc_txtype != TX_CREATE_ATTR) {
start = (lr + 1);
zfsvfs->z_fuid_replay =
zfs_replay_fuid_domain(start, &start,
lr->lr_uid, lr->lr_gid);
}
cn.cn_cred = kcred;
cn.cn_thread = curthread;
cn.cn_flags = SAVENAME;
vn_lock(ZTOV(dzp), LK_EXCLUSIVE | LK_RETRY);
switch (txtype) {
case TX_CREATE_ATTR:
lrattr = (lr_attr_t *)(caddr_t)(lr + 1);
xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize);
zfs_replay_xvattr((lr_attr_t *)((caddr_t)lr + lrsize), &xva);
start = (caddr_t)(lr + 1) + xvatlen;
zfsvfs->z_fuid_replay =
zfs_replay_fuid_domain(start, &start,
lr->lr_uid, lr->lr_gid);
name = (char *)start;
/*FALLTHROUGH*/
case TX_CREATE:
if (name == NULL)
name = (char *)start;
cn.cn_nameptr = name;
error = VOP_CREATE(ZTOV(dzp), &vp, &cn, &xva.xva_vattr /*,vflg*/);
break;
case TX_MKDIR_ATTR:
lrattr = (lr_attr_t *)(caddr_t)(lr + 1);
xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize);
zfs_replay_xvattr((lr_attr_t *)((caddr_t)lr + lrsize), &xva);
start = (caddr_t)(lr + 1) + xvatlen;
zfsvfs->z_fuid_replay =
zfs_replay_fuid_domain(start, &start,
lr->lr_uid, lr->lr_gid);
name = (char *)start;
/*FALLTHROUGH*/
case TX_MKDIR:
if (name == NULL)
name = (char *)(lr + 1);
cn.cn_nameptr = name;
error = VOP_MKDIR(ZTOV(dzp), &vp, &cn, &xva.xva_vattr /*,vflg*/);
break;
case TX_MKXATTR:
error = zfs_make_xattrdir(dzp, &xva.xva_vattr, &vp, kcred);
break;
case TX_SYMLINK:
name = (char *)(lr + 1);
link = name + strlen(name) + 1;
cn.cn_nameptr = name;
error = VOP_SYMLINK(ZTOV(dzp), &vp, &cn, &xva.xva_vattr, link /*,vflg*/);
break;
default:
error = ENOTSUP;
}
VOP_UNLOCK(ZTOV(dzp), 0);
out:
if (error == 0 && vp != NULL)
VN_URELE(vp);
VN_RELE(ZTOV(dzp));
if (zfsvfs->z_fuid_replay)
zfs_fuid_info_free(zfsvfs->z_fuid_replay);
zfsvfs->z_fuid_replay = NULL;
return (error);
}
/*
* Replay file create with optional ACL, xvattr information as well
* as option FUID information.
*/
static int
zfs_replay_create_acl(zfsvfs_t *zfsvfs,
lr_acl_create_t *lracl, boolean_t byteswap)
{
char *name = NULL; /* location determined later */
lr_create_t *lr = (lr_create_t *)lracl;
znode_t *dzp;
vnode_t *vp = NULL;
xvattr_t xva;
int vflg = 0;
vsecattr_t vsec = { 0 };
lr_attr_t *lrattr;
void *aclstart;
void *fuidstart;
size_t xvatlen = 0;
uint64_t txtype;
int error;
txtype = (lr->lr_common.lrc_txtype & ~TX_CI);
if (byteswap) {
byteswap_uint64_array(lracl, sizeof (*lracl));
if (txtype == TX_CREATE_ACL_ATTR ||
txtype == TX_MKDIR_ACL_ATTR) {
lrattr = (lr_attr_t *)(caddr_t)(lracl + 1);
zfs_replay_swap_attrs(lrattr);
xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize);
}
aclstart = (caddr_t)(lracl + 1) + xvatlen;
zfs_ace_byteswap(aclstart, lracl->lr_acl_bytes, B_FALSE);
/* swap fuids */
if (lracl->lr_fuidcnt) {
byteswap_uint64_array((caddr_t)aclstart +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes),
lracl->lr_fuidcnt * sizeof (uint64_t));
}
}
if ((error = zfs_zget(zfsvfs, lr->lr_doid, &dzp)) != 0)
return (error);
xva_init(&xva);
zfs_init_vattr(&xva.xva_vattr, AT_TYPE | AT_MODE | AT_UID | AT_GID,
lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, lr->lr_foid);
/*
* All forms of zfs create (create, mkdir, mkxattrdir, symlink)
* eventually end up in zfs_mknode(), which assigns the object's
* creation time and generation number. The generic VOP_CREATE()
* doesn't have either concept, so we smuggle the values inside
* the vattr's otherwise unused va_ctime and va_nblocks fields.
*/
ZFS_TIME_DECODE(&xva.xva_vattr.va_ctime, lr->lr_crtime);
xva.xva_vattr.va_nblocks = lr->lr_gen;
error = dmu_object_info(zfsvfs->z_os, lr->lr_foid, NULL);
if (error != ENOENT)
goto bail;
if (lr->lr_common.lrc_txtype & TX_CI)
vflg |= FIGNORECASE;
switch (txtype) {
case TX_CREATE_ACL:
aclstart = (caddr_t)(lracl + 1);
fuidstart = (caddr_t)aclstart +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
zfsvfs->z_fuid_replay = zfs_replay_fuids(fuidstart,
(void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt,
lr->lr_uid, lr->lr_gid);
/*FALLTHROUGH*/
case TX_CREATE_ACL_ATTR:
if (name == NULL) {
lrattr = (lr_attr_t *)(caddr_t)(lracl + 1);
xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize);
xva.xva_vattr.va_mask |= AT_XVATTR;
zfs_replay_xvattr(lrattr, &xva);
}
vsec.vsa_mask = VSA_ACE | VSA_ACE_ACLFLAGS;
vsec.vsa_aclentp = (caddr_t)(lracl + 1) + xvatlen;
vsec.vsa_aclcnt = lracl->lr_aclcnt;
vsec.vsa_aclentsz = lracl->lr_acl_bytes;
vsec.vsa_aclflags = lracl->lr_acl_flags;
if (zfsvfs->z_fuid_replay == NULL) {
fuidstart = (caddr_t)(lracl + 1) + xvatlen +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
zfsvfs->z_fuid_replay =
zfs_replay_fuids(fuidstart,
(void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt,
lr->lr_uid, lr->lr_gid);
}
#ifdef TODO
error = VOP_CREATE(ZTOV(dzp), name, &xva.xva_vattr,
0, 0, &vp, kcred, vflg, NULL, &vsec);
#else
panic("%s:%u: unsupported condition", __func__, __LINE__);
#endif
break;
case TX_MKDIR_ACL:
aclstart = (caddr_t)(lracl + 1);
fuidstart = (caddr_t)aclstart +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
zfsvfs->z_fuid_replay = zfs_replay_fuids(fuidstart,
(void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt,
lr->lr_uid, lr->lr_gid);
/*FALLTHROUGH*/
case TX_MKDIR_ACL_ATTR:
if (name == NULL) {
lrattr = (lr_attr_t *)(caddr_t)(lracl + 1);
xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize);
zfs_replay_xvattr(lrattr, &xva);
}
vsec.vsa_mask = VSA_ACE | VSA_ACE_ACLFLAGS;
vsec.vsa_aclentp = (caddr_t)(lracl + 1) + xvatlen;
vsec.vsa_aclcnt = lracl->lr_aclcnt;
vsec.vsa_aclentsz = lracl->lr_acl_bytes;
vsec.vsa_aclflags = lracl->lr_acl_flags;
if (zfsvfs->z_fuid_replay == NULL) {
fuidstart = (caddr_t)(lracl + 1) + xvatlen +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
zfsvfs->z_fuid_replay =
zfs_replay_fuids(fuidstart,
(void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt,
lr->lr_uid, lr->lr_gid);
}
#ifdef TODO
error = VOP_MKDIR(ZTOV(dzp), name, &xva.xva_vattr,
&vp, kcred, NULL, vflg, &vsec);
#else
panic("%s:%u: unsupported condition", __func__, __LINE__);
#endif
break;
default:
error = ENOTSUP;
}
bail:
if (error == 0 && vp != NULL)
VN_RELE(vp);
VN_RELE(ZTOV(dzp));
if (zfsvfs->z_fuid_replay)
zfs_fuid_info_free(zfsvfs->z_fuid_replay);
zfsvfs->z_fuid_replay = NULL;
return (error);
}
/*
* Create a block device minor node and setup the linkage between it
* and the specified volume. Once this function returns the block
* device is live and ready for use.
*/
static int
zvol_create_minor_impl(const char *name)
{
zvol_state_t *zv;
objset_t *os;
dmu_object_info_t *doi;
uint64_t volsize;
uint64_t len;
unsigned minor = 0;
int error = 0;
mutex_enter(&zvol_state_lock);
zv = zvol_find_by_name(name);
if (zv) {
error = SET_ERROR(EEXIST);
goto out;
}
doi = kmem_alloc(sizeof (dmu_object_info_t), KM_SLEEP);
error = dmu_objset_own(name, DMU_OST_ZVOL, B_TRUE, zvol_tag, &os);
if (error)
goto out_doi;
error = dmu_object_info(os, ZVOL_OBJ, doi);
if (error)
goto out_dmu_objset_disown;
error = zap_lookup(os, ZVOL_ZAP_OBJ, "size", 8, 1, &volsize);
if (error)
goto out_dmu_objset_disown;
error = zvol_find_minor(&minor);
if (error)
goto out_dmu_objset_disown;
zv = zvol_alloc(MKDEV(zvol_major, minor), name);
if (zv == NULL) {
error = SET_ERROR(EAGAIN);
goto out_dmu_objset_disown;
}
if (dmu_objset_is_snapshot(os))
zv->zv_flags |= ZVOL_RDONLY;
zv->zv_volblocksize = doi->doi_data_block_size;
zv->zv_volsize = volsize;
zv->zv_objset = os;
set_capacity(zv->zv_disk, zv->zv_volsize >> 9);
blk_queue_max_hw_sectors(zv->zv_queue, (DMU_MAX_ACCESS / 4) >> 9);
blk_queue_max_segments(zv->zv_queue, UINT16_MAX);
blk_queue_max_segment_size(zv->zv_queue, UINT_MAX);
blk_queue_physical_block_size(zv->zv_queue, zv->zv_volblocksize);
blk_queue_io_opt(zv->zv_queue, zv->zv_volblocksize);
blk_queue_max_discard_sectors(zv->zv_queue,
(zvol_max_discard_blocks * zv->zv_volblocksize) >> 9);
blk_queue_discard_granularity(zv->zv_queue, zv->zv_volblocksize);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zv->zv_queue);
#ifdef QUEUE_FLAG_NONROT
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zv->zv_queue);
#endif
#ifdef QUEUE_FLAG_ADD_RANDOM
queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, zv->zv_queue);
#endif
if (spa_writeable(dmu_objset_spa(os))) {
if (zil_replay_disable)
zil_destroy(dmu_objset_zil(os), B_FALSE);
else
zil_replay(os, zv, zvol_replay_vector);
}
/*
* When udev detects the addition of the device it will immediately
* invoke blkid(8) to determine the type of content on the device.
* Prefetching the blocks commonly scanned by blkid(8) will speed
* up this process.
*/
len = MIN(MAX(zvol_prefetch_bytes, 0), SPA_MAXBLOCKSIZE);
if (len > 0) {
dmu_prefetch(os, ZVOL_OBJ, 0, 0, len, ZIO_PRIORITY_SYNC_READ);
dmu_prefetch(os, ZVOL_OBJ, 0, volsize - len, len,
ZIO_PRIORITY_SYNC_READ);
}
zv->zv_objset = NULL;
out_dmu_objset_disown:
dmu_objset_disown(os, zvol_tag);
out_doi:
kmem_free(doi, sizeof (dmu_object_info_t));
out:
if (error == 0) {
zvol_insert(zv);
/*
* Drop the lock to prevent deadlock with sys_open() ->
* zvol_open(), which first takes bd_disk->bd_mutex and then
* takes zvol_state_lock, whereas this code path first takes
* zvol_state_lock, and then takes bd_disk->bd_mutex.
*/
mutex_exit(&zvol_state_lock);
add_disk(zv->zv_disk);
} else {
mutex_exit(&zvol_state_lock);
}
return (SET_ERROR(error));
}
static int
__zvol_create_minor(const char *name)
{
zvol_state_t *zv;
objset_t *os;
dmu_object_info_t *doi;
uint64_t volsize;
unsigned minor = 0;
int error = 0;
ASSERT(MUTEX_HELD(&zvol_state_lock));
zv = zvol_find_by_name(name);
if (zv) {
error = EEXIST;
goto out;
}
doi = kmem_alloc(sizeof(dmu_object_info_t), KM_SLEEP);
error = dmu_objset_own(name, DMU_OST_ZVOL, B_TRUE, zvol_tag, &os);
if (error)
goto out_doi;
/* Make sure we have the key loaded if we need one. */
error = dsl_crypto_key_inherit(name);
if (error != 0 && error != EEXIST)
goto out_dmu_objset_disown;
error = dmu_object_info(os, ZVOL_OBJ, doi);
if (error)
goto out_dmu_objset_disown;
error = zap_lookup(os, ZVOL_ZAP_OBJ, "size", 8, 1, &volsize);
if (error)
goto out_dmu_objset_disown;
error = zvol_find_minor(&minor);
if (error)
goto out_dmu_objset_disown;
zv = zvol_alloc(MKDEV(zvol_major, minor), name);
if (zv == NULL) {
error = EAGAIN;
goto out_dmu_objset_disown;
}
if (dmu_objset_is_snapshot(os))
zv->zv_flags |= ZVOL_RDONLY;
zv->zv_volblocksize = doi->doi_data_block_size;
zv->zv_volsize = volsize;
zv->zv_objset = os;
set_capacity(zv->zv_disk, zv->zv_volsize >> 9);
blk_queue_max_hw_sectors(zv->zv_queue, UINT_MAX);
blk_queue_max_segments(zv->zv_queue, UINT16_MAX);
blk_queue_max_segment_size(zv->zv_queue, UINT_MAX);
blk_queue_physical_block_size(zv->zv_queue, zv->zv_volblocksize);
blk_queue_io_opt(zv->zv_queue, zv->zv_volblocksize);
#ifdef HAVE_BLK_QUEUE_DISCARD
blk_queue_max_discard_sectors(zv->zv_queue,
(zvol_max_discard_blocks * zv->zv_volblocksize) >> 9);
blk_queue_discard_granularity(zv->zv_queue, zv->zv_volblocksize);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zv->zv_queue);
#endif
#ifdef HAVE_BLK_QUEUE_NONROT
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zv->zv_queue);
#endif
if (zil_replay_disable)
zil_destroy(dmu_objset_zil(os), B_FALSE);
else
zil_replay(os, zv, zvol_replay_vector);
out_dmu_objset_disown:
dmu_objset_disown(os, zvol_tag);
zv->zv_objset = NULL;
out_doi:
kmem_free(doi, sizeof(dmu_object_info_t));
out:
if (error == 0) {
zvol_insert(zv);
add_disk(zv->zv_disk);
}
return (error);
}
static int
zfs_replay_create(zfsvfs_t *zfsvfs, lr_create_t *lr, boolean_t byteswap)
{
char *name = NULL; /* location determined later */
char *link; /* symlink content follows name */
znode_t *dzp;
struct inode *ip = NULL;
xvattr_t xva;
int vflg = 0;
size_t lrsize = sizeof (lr_create_t);
lr_attr_t *lrattr;
void *start;
size_t xvatlen;
uint64_t txtype;
uint64_t objid;
uint64_t dnodesize;
int error;
txtype = (lr->lr_common.lrc_txtype & ~TX_CI);
if (byteswap) {
byteswap_uint64_array(lr, sizeof (*lr));
if (txtype == TX_CREATE_ATTR || txtype == TX_MKDIR_ATTR)
zfs_replay_swap_attrs((lr_attr_t *)(lr + 1));
}
if ((error = zfs_zget(zfsvfs, lr->lr_doid, &dzp)) != 0)
return (error);
objid = LR_FOID_GET_OBJ(lr->lr_foid);
dnodesize = LR_FOID_GET_SLOTS(lr->lr_foid) << DNODE_SHIFT;
xva_init(&xva);
zfs_init_vattr(&xva.xva_vattr, ATTR_MODE | ATTR_UID | ATTR_GID,
lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, objid);
/*
* All forms of zfs create (create, mkdir, mkxattrdir, symlink)
* eventually end up in zfs_mknode(), which assigns the object's
* creation time, generation number, and dnode slot count. The
* generic zfs_create() has no concept of these attributes, so
* we smuggle the values inside * the vattr's otherwise unused
* va_ctime, va_nblocks, and va_nlink fields.
*/
ZFS_TIME_DECODE(&xva.xva_vattr.va_ctime, lr->lr_crtime);
xva.xva_vattr.va_nblocks = lr->lr_gen;
xva.xva_vattr.va_fsid = dnodesize;
error = dmu_object_info(zfsvfs->z_os, objid, NULL);
if (error != ENOENT)
goto out;
if (lr->lr_common.lrc_txtype & TX_CI)
vflg |= FIGNORECASE;
/*
* Symlinks don't have fuid info, and CIFS never creates
* symlinks.
*
* The _ATTR versions will grab the fuid info in their subcases.
*/
if ((int)lr->lr_common.lrc_txtype != TX_SYMLINK &&
(int)lr->lr_common.lrc_txtype != TX_MKDIR_ATTR &&
(int)lr->lr_common.lrc_txtype != TX_CREATE_ATTR) {
start = (lr + 1);
zfsvfs->z_fuid_replay =
zfs_replay_fuid_domain(start, &start,
lr->lr_uid, lr->lr_gid);
}
switch (txtype) {
case TX_CREATE_ATTR:
lrattr = (lr_attr_t *)(caddr_t)(lr + 1);
xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize);
zfs_replay_xvattr((lr_attr_t *)((caddr_t)lr + lrsize), &xva);
start = (caddr_t)(lr + 1) + xvatlen;
zfsvfs->z_fuid_replay =
zfs_replay_fuid_domain(start, &start,
lr->lr_uid, lr->lr_gid);
name = (char *)start;
/*FALLTHROUGH*/
case TX_CREATE:
if (name == NULL)
name = (char *)start;
error = zfs_create(ZTOI(dzp), name, &xva.xva_vattr,
0, 0, &ip, kcred, vflg, NULL);
break;
case TX_MKDIR_ATTR:
lrattr = (lr_attr_t *)(caddr_t)(lr + 1);
xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize);
zfs_replay_xvattr((lr_attr_t *)((caddr_t)lr + lrsize), &xva);
start = (caddr_t)(lr + 1) + xvatlen;
zfsvfs->z_fuid_replay =
zfs_replay_fuid_domain(start, &start,
lr->lr_uid, lr->lr_gid);
name = (char *)start;
/*FALLTHROUGH*/
case TX_MKDIR:
if (name == NULL)
name = (char *)(lr + 1);
error = zfs_mkdir(ZTOI(dzp), name, &xva.xva_vattr,
&ip, kcred, vflg, NULL);
break;
case TX_MKXATTR:
error = zfs_make_xattrdir(dzp, &xva.xva_vattr, &ip, kcred);
break;
case TX_SYMLINK:
name = (char *)(lr + 1);
link = name + strlen(name) + 1;
error = zfs_symlink(ZTOI(dzp), name, &xva.xva_vattr,
link, &ip, kcred, vflg);
break;
default:
error = SET_ERROR(ENOTSUP);
}
out:
if (error == 0 && ip != NULL)
iput(ip);
iput(ZTOI(dzp));
if (zfsvfs->z_fuid_replay)
zfs_fuid_info_free(zfsvfs->z_fuid_replay);
zfsvfs->z_fuid_replay = NULL;
return (error);
}
/*
* Replay file create with optional ACL, xvattr information as well
* as option FUID information.
*/
static int
zfs_replay_create_acl(zfsvfs_t *zfsvfs,
lr_acl_create_t *lracl, boolean_t byteswap)
{
char *name = NULL; /* location determined later */
lr_create_t *lr = (lr_create_t *)lracl;
znode_t *dzp;
struct inode *ip = NULL;
xvattr_t xva;
int vflg = 0;
vsecattr_t vsec = { 0 };
lr_attr_t *lrattr;
void *aclstart;
void *fuidstart;
size_t xvatlen = 0;
uint64_t txtype;
uint64_t objid;
uint64_t dnodesize;
int error;
txtype = (lr->lr_common.lrc_txtype & ~TX_CI);
if (byteswap) {
byteswap_uint64_array(lracl, sizeof (*lracl));
if (txtype == TX_CREATE_ACL_ATTR ||
txtype == TX_MKDIR_ACL_ATTR) {
lrattr = (lr_attr_t *)(caddr_t)(lracl + 1);
zfs_replay_swap_attrs(lrattr);
xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize);
}
aclstart = (caddr_t)(lracl + 1) + xvatlen;
zfs_ace_byteswap(aclstart, lracl->lr_acl_bytes, B_FALSE);
/* swap fuids */
if (lracl->lr_fuidcnt) {
byteswap_uint64_array((caddr_t)aclstart +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes),
lracl->lr_fuidcnt * sizeof (uint64_t));
}
}
if ((error = zfs_zget(zfsvfs, lr->lr_doid, &dzp)) != 0)
return (error);
objid = LR_FOID_GET_OBJ(lr->lr_foid);
dnodesize = LR_FOID_GET_SLOTS(lr->lr_foid) << DNODE_SHIFT;
xva_init(&xva);
zfs_init_vattr(&xva.xva_vattr, ATTR_MODE | ATTR_UID | ATTR_GID,
lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, objid);
/*
* All forms of zfs create (create, mkdir, mkxattrdir, symlink)
* eventually end up in zfs_mknode(), which assigns the object's
* creation time, generation number, and dnode size. The generic
* zfs_create() has no concept of these attributes, so we smuggle
* the values inside the vattr's otherwise unused va_ctime,
* va_nblocks, and va_fsid fields.
*/
ZFS_TIME_DECODE(&xva.xva_vattr.va_ctime, lr->lr_crtime);
xva.xva_vattr.va_nblocks = lr->lr_gen;
xva.xva_vattr.va_fsid = dnodesize;
error = dmu_object_info(zfsvfs->z_os, lr->lr_foid, NULL);
if (error != ENOENT)
goto bail;
if (lr->lr_common.lrc_txtype & TX_CI)
vflg |= FIGNORECASE;
switch (txtype) {
case TX_CREATE_ACL:
aclstart = (caddr_t)(lracl + 1);
fuidstart = (caddr_t)aclstart +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
zfsvfs->z_fuid_replay = zfs_replay_fuids(fuidstart,
(void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt,
lr->lr_uid, lr->lr_gid);
/*FALLTHROUGH*/
case TX_CREATE_ACL_ATTR:
if (name == NULL) {
lrattr = (lr_attr_t *)(caddr_t)(lracl + 1);
xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize);
xva.xva_vattr.va_mask |= ATTR_XVATTR;
zfs_replay_xvattr(lrattr, &xva);
}
vsec.vsa_mask = VSA_ACE | VSA_ACE_ACLFLAGS;
vsec.vsa_aclentp = (caddr_t)(lracl + 1) + xvatlen;
vsec.vsa_aclcnt = lracl->lr_aclcnt;
vsec.vsa_aclentsz = lracl->lr_acl_bytes;
vsec.vsa_aclflags = lracl->lr_acl_flags;
if (zfsvfs->z_fuid_replay == NULL) {
fuidstart = (caddr_t)(lracl + 1) + xvatlen +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
zfsvfs->z_fuid_replay =
zfs_replay_fuids(fuidstart,
(void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt,
lr->lr_uid, lr->lr_gid);
}
error = zfs_create(ZTOI(dzp), name, &xva.xva_vattr,
0, 0, &ip, kcred, vflg, &vsec);
break;
case TX_MKDIR_ACL:
aclstart = (caddr_t)(lracl + 1);
fuidstart = (caddr_t)aclstart +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
zfsvfs->z_fuid_replay = zfs_replay_fuids(fuidstart,
(void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt,
lr->lr_uid, lr->lr_gid);
/*FALLTHROUGH*/
case TX_MKDIR_ACL_ATTR:
if (name == NULL) {
lrattr = (lr_attr_t *)(caddr_t)(lracl + 1);
xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize);
zfs_replay_xvattr(lrattr, &xva);
}
vsec.vsa_mask = VSA_ACE | VSA_ACE_ACLFLAGS;
vsec.vsa_aclentp = (caddr_t)(lracl + 1) + xvatlen;
vsec.vsa_aclcnt = lracl->lr_aclcnt;
vsec.vsa_aclentsz = lracl->lr_acl_bytes;
vsec.vsa_aclflags = lracl->lr_acl_flags;
if (zfsvfs->z_fuid_replay == NULL) {
fuidstart = (caddr_t)(lracl + 1) + xvatlen +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
zfsvfs->z_fuid_replay =
zfs_replay_fuids(fuidstart,
(void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt,
lr->lr_uid, lr->lr_gid);
}
error = zfs_mkdir(ZTOI(dzp), name, &xva.xva_vattr,
&ip, kcred, vflg, &vsec);
break;
default:
error = SET_ERROR(ENOTSUP);
}
bail:
if (error == 0 && ip != NULL)
iput(ip);
iput(ZTOI(dzp));
if (zfsvfs->z_fuid_replay)
zfs_fuid_info_free(zfsvfs->z_fuid_replay);
zfsvfs->z_fuid_replay = NULL;
return (error);
}
int
zvol_log_write(zvol_state_t *zv, dmu_tx_t *tx, offset_t off, ssize_t len,
char *addr)
{
dmu_object_info_t doi;
ssize_t nbytes;
itx_t *itx;
lr_write_t *lr;
objset_t *os;
dmu_buf_t *db;
uint64_t txg;
uint64_t boff;
int error;
uint32_t blocksize;
/* handle common case */
if (len <= zvol_immediate_write_sz) {
itx = zvol_immediate_itx(off, len, addr);
(void) zil_itx_assign(zv->zv_zilog, itx, tx);
return (0);
}
txg = dmu_tx_get_txg(tx);
os = zv->zv_objset;
/*
* We need to dmu_sync() each block in the range.
* For this we need the blocksize.
*/
error = dmu_object_info(os, ZVOL_OBJ, &doi);
if (error)
return (error);
blocksize = doi.doi_data_block_size;
/*
* We need to immediate write or dmu_sync() each block in the range.
*/
while (len) {
nbytes = MIN(len, blocksize - P2PHASE(off, blocksize));
if (nbytes <= zvol_immediate_write_sz) {
itx = zvol_immediate_itx(off, nbytes, addr);
} else {
boff = P2ALIGN_TYPED(off, blocksize, uint64_t);
itx = zil_itx_create(TX_WRITE, sizeof (*lr));
lr = (lr_write_t *)&itx->itx_lr;
lr->lr_foid = ZVOL_OBJ;
lr->lr_offset = off;
lr->lr_length = nbytes;
lr->lr_blkoff = off - boff;
BP_ZERO(&lr->lr_blkptr);
/* XXX - we should do these IOs in parallel */
VERIFY(0 == dmu_buf_hold(os, ZVOL_OBJ, boff,
FTAG, &db));
ASSERT(boff == db->db_offset);
error = dmu_sync(NULL, db, &lr->lr_blkptr,
txg, NULL, NULL);
dmu_buf_rele(db, FTAG);
if (error) {
kmem_free(itx, offsetof(itx_t, itx_lr));
return (error);
}
itx->itx_wr_state = WR_COPIED;
}
(void) zil_itx_assign(zv->zv_zilog, itx, tx);
len -= nbytes;
off += nbytes;
}
return (0);
}
static int
__zvol_create_minor(const char *name)
{
zvol_state_t *zv;
objset_t *os;
dmu_object_info_t *doi;
uint64_t volsize;
unsigned minor = 0;
int error = 0;
ASSERT(MUTEX_HELD(&zvol_state_lock));
zv = zvol_find_by_name(name);
if (zv) {
error = EEXIST;
goto out;
}
doi = kmem_alloc(sizeof(dmu_object_info_t), KM_SLEEP);
error = dmu_objset_own(name, DMU_OST_ZVOL, B_TRUE, zvol_tag, &os);
if (error)
goto out_doi;
error = dmu_object_info(os, ZVOL_OBJ, doi);
if (error)
goto out_dmu_objset_disown;
error = zap_lookup(os, ZVOL_ZAP_OBJ, "size", 8, 1, &volsize);
if (error)
goto out_dmu_objset_disown;
error = zvol_find_minor(&minor);
if (error)
goto out_dmu_objset_disown;
zv = zvol_alloc(MKDEV(zvol_major, minor), name);
if (zv == NULL) {
error = EAGAIN;
goto out_dmu_objset_disown;
}
if (dmu_objset_is_snapshot(os))
zv->zv_flags |= ZVOL_RDONLY;
zv->zv_volblocksize = doi->doi_data_block_size;
zv->zv_volsize = volsize;
zv->zv_objset = os;
set_capacity(zv->zv_disk, zv->zv_volsize >> 9);
if (zil_replay_disable)
zil_destroy(dmu_objset_zil(os), B_FALSE);
else
zil_replay(os, zv, zvol_replay_vector);
out_dmu_objset_disown:
dmu_objset_disown(os, zvol_tag);
zv->zv_objset = NULL;
out_doi:
kmem_free(doi, sizeof(dmu_object_info_t));
out:
if (error == 0) {
zvol_insert(zv);
add_disk(zv->zv_disk);
}
return (error);
}