static void
zfs_znode_dmu_init(zfsvfs_t *zfsvfs, znode_t *zp, dmu_buf_t *db)
{
znode_t *nzp;
ASSERT(!POINTER_IS_VALID(zp->z_zfsvfs) || (zfsvfs == zp->z_zfsvfs));
ASSERT(MUTEX_HELD(ZFS_OBJ_MUTEX(zfsvfs, zp->z_id)));
mutex_enter(&zp->z_lock);
ASSERT(zp->z_dbuf == NULL);
zp->z_dbuf = db;
nzp = dmu_buf_set_user_ie(db, zp, &zp->z_phys, znode_evict_error);
/*
* there should be no
* concurrent zgets on this object.
*/
if (nzp != NULL)
panic("existing znode %p for dbuf %p", (void *)nzp, (void *)db);
/*
* Slap on VROOT if we are the root znode
*/
if (zp->z_id == zfsvfs->z_root)
ZTOV(zp)->v_flag |= VROOT;
mutex_exit(&zp->z_lock);
vn_exists(ZTOV(zp));
}
static int
zfs_replay_acl_v0(zfsvfs_t *zfsvfs, lr_acl_v0_t *lr, boolean_t byteswap)
{
ace_t *ace = (ace_t *)(lr + 1); /* ace array follows lr_acl_t */
vsecattr_t vsa;
znode_t *zp;
int error;
if (byteswap) {
byteswap_uint64_array(lr, sizeof (*lr));
zfs_oldace_byteswap(ace, lr->lr_aclcnt);
}
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0)
return (error);
bzero(&vsa, sizeof (vsa));
vsa.vsa_mask = VSA_ACE | VSA_ACECNT;
vsa.vsa_aclcnt = lr->lr_aclcnt;
vsa.vsa_aclentsz = sizeof (ace_t) * vsa.vsa_aclcnt;
vsa.vsa_aclflags = 0;
vsa.vsa_aclentp = ace;
#ifdef TODO
error = VOP_SETSECATTR(ZTOV(zp), &vsa, 0, kcred, NULL);
#else
panic("%s:%u: unsupported condition", __func__, __LINE__);
#endif
VN_RELE(ZTOV(zp));
return (error);
}
static int
zfs_replay_remove(void *arg1, char *arg2, boolean_t byteswap)
{
zfsvfs_t *zfsvfs = (zfsvfs_t *)arg1;
lr_remove_t *lr = (lr_remove_t *)arg2;
char *name = (char *)(lr + 1); /* name follows lr_remove_t */
znode_t *dzp;
int error;
int vflg = 0;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zfsvfs, lr->lr_doid, &dzp)) != 0)
return (error);
if (lr->lr_common.lrc_txtype & TX_CI)
vflg |= FIGNORECASE;
switch ((int)lr->lr_common.lrc_txtype) {
case TX_REMOVE:
error = VOP_REMOVE(ZTOV(dzp), name, kcred, NULL, vflg);
break;
case TX_RMDIR:
error = VOP_RMDIR(ZTOV(dzp), name, NULL, kcred, NULL, vflg);
break;
default:
error = ENOTSUP;
}
VN_RELE(ZTOV(dzp));
return (error);
}
static int
zfs_replay_write(zfsvfs_t *zfsvfs, lr_write_t *lr, boolean_t byteswap)
{
char *data = (char *)(lr + 1); /* data follows lr_write_t */
znode_t *zp;
int error;
ssize_t resid;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) {
/*
* As we can log writes out of order, it's possible the
* file has been removed. In this case just drop the write
* and return success.
*/
if (error == ENOENT)
error = 0;
return (error);
}
error = vn_rdwr(UIO_WRITE, ZTOV(zp), data, lr->lr_length,
lr->lr_offset, UIO_SYSSPACE, 0, RLIM64_INFINITY, kcred, &resid);
VN_RELE(ZTOV(zp));
return (error);
}
static int
zfs_replay_remove(zfsvfs_t *zsb, lr_remove_t *lr, boolean_t byteswap)
{
char *name = (char *)(lr + 1); /* name follows lr_remove_t */
znode_t *dzp;
int error;
int vflg = 0;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zsb, lr->lr_doid, &dzp)) != 0)
return (error);
zfs_znode_wait_vnode(dzp);
if (lr->lr_common.lrc_txtype & TX_CI)
vflg |= FIGNORECASE;
switch ((int)lr->lr_common.lrc_txtype) {
case TX_REMOVE:
error = zfs_remove(ZTOV(dzp), name, kcred, NULL, vflg);
break;
case TX_RMDIR:
error = zfs_rmdir(ZTOV(dzp), name, NULL, kcred, NULL, vflg);
break;
default:
error = SET_ERROR(ENOTSUP);
}
vnode_put(ZTOV(dzp));
return (error);
}
static int
zfs_replay_rename(void *arg1, char *arg2, boolean_t byteswap)
{
zfsvfs_t *zfsvfs = (zfsvfs_t *)arg1;
lr_rename_t *lr = (lr_rename_t *)arg2;
char *sname = (char *)(lr + 1); /* sname and tname follow lr_rename_t */
char *tname = sname + strlen(sname) + 1;
znode_t *sdzp, *tdzp;
int error;
int vflg = 0;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zfsvfs, lr->lr_sdoid, &sdzp)) != 0)
return (error);
if ((error = zfs_zget(zfsvfs, lr->lr_tdoid, &tdzp)) != 0) {
VN_RELE(ZTOV(sdzp));
return (error);
}
if (lr->lr_common.lrc_txtype & TX_CI)
vflg |= FIGNORECASE;
error = VOP_RENAME(ZTOV(sdzp), sname, ZTOV(tdzp), tname, kcred,
NULL, vflg);
VN_RELE(ZTOV(tdzp));
VN_RELE(ZTOV(sdzp));
return (error);
}
static int
zfs_replay_truncate(zfsvfs_t *zfsvfs, lr_truncate_t *lr, boolean_t byteswap)
{
znode_t *zp;
flock64_t fl;
int error;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) {
/*
* As we can log truncates out of order, it's possible the
* file has been removed. In this case just drop the truncate
* and return success.
*/
if (error == ENOENT)
error = 0;
return (error);
}
bzero(&fl, sizeof (fl));
fl.l_type = F_WRLCK;
fl.l_whence = 0;
fl.l_start = lr->lr_offset;
fl.l_len = lr->lr_length;
error = VOP_SPACE(ZTOV(zp), F_FREESP, &fl, FWRITE | FOFFMAX,
lr->lr_offset, kcred, NULL);
VN_RELE(ZTOV(zp));
return (error);
}
static int
zfs_replay_acl_v0(zfsvfs_t *zfsvfs, lr_acl_v0_t *lr, boolean_t byteswap)
{
ace_t *ace = (ace_t *)(lr + 1); /* ace array follows lr_acl_t */
vsecattr_t vsa;
znode_t *zp;
int error;
if (byteswap) {
byteswap_uint64_array(lr, sizeof (*lr));
zfs_oldace_byteswap(ace, lr->lr_aclcnt);
}
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) {
/*
* As we can log acls out of order, it's possible the
* file has been removed. In this case just drop the acl
* and return success.
*/
if (error == ENOENT)
error = 0;
return (error);
}
bzero(&vsa, sizeof (vsa));
vsa.vsa_mask = VSA_ACE | VSA_ACECNT;
vsa.vsa_aclcnt = lr->lr_aclcnt;
vsa.vsa_aclentp = ace;
error = VOP_SETSECATTR(ZTOV(zp), &vsa, 0, kcred, NULL);
VN_RELE(ZTOV(zp));
return (error);
}
/* ARGSUSED */
static int
zfsctl_shares_readdir(vnode_t *vp, uio_t *uiop, cred_t *cr, int *eofp,
caller_context_t *ct, int flags)
{
zfsvfs_t *zfsvfs = vp->v_vfsp->vfs_data;
znode_t *dzp;
int error;
ZFS_ENTER(zfsvfs);
if (zfsvfs->z_shares_dir == 0) {
ZFS_EXIT(zfsvfs);
return (ENOTSUP);
}
if ((error = zfs_zget(zfsvfs, zfsvfs->z_shares_dir, &dzp)) == 0) {
error = VOP_READDIR(ZTOV(dzp), uiop, cr, eofp, ct, flags);
VN_RELE(ZTOV(dzp));
} else {
*eofp = 1;
error = ENOENT;
}
ZFS_EXIT(zfsvfs);
return (error);
}
/* ARGSUSED */
static int
zfsctl_shares_lookup(vnode_t *dvp, char *nm, vnode_t **vpp, pathname_t *pnp,
int flags, vnode_t *rdir, cred_t *cr, caller_context_t *ct,
int *direntflags, pathname_t *realpnp)
{
zfsvfs_t *zfsvfs = dvp->v_vfsp->vfs_data;
znode_t *dzp;
int error;
ZFS_ENTER(zfsvfs);
if (gfs_lookup_dot(vpp, dvp, zfsvfs->z_ctldir, nm) == 0) {
ZFS_EXIT(zfsvfs);
return (0);
}
if (zfsvfs->z_shares_dir == 0) {
ZFS_EXIT(zfsvfs);
return (ENOTSUP);
}
if ((error = zfs_zget(zfsvfs, zfsvfs->z_shares_dir, &dzp)) == 0)
error = VOP_LOOKUP(ZTOV(dzp), nm, vpp, pnp,
flags, rdir, cr, ct, direntflags, realpnp);
VN_RELE(ZTOV(dzp));
ZFS_EXIT(zfsvfs);
return (error);
}
static int
zfs_replay_truncate(zfsvfs_t *zfsvfs, lr_truncate_t *lr, boolean_t byteswap)
{
#ifdef sun
znode_t *zp;
flock64_t fl;
int error;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0)
return (error);
bzero(&fl, sizeof (fl));
fl.l_type = F_WRLCK;
fl.l_whence = 0;
fl.l_start = lr->lr_offset;
fl.l_len = lr->lr_length;
error = VOP_SPACE(ZTOV(zp), F_FREESP, &fl, FWRITE | FOFFMAX,
lr->lr_offset, kcred, NULL);
VN_RELE(ZTOV(zp));
return (error);
#else /* !sun */
ZFS_LOG(0, "Unexpected code path, report to [email protected]");
return (EOPNOTSUPP);
#endif /* !sun */
}
void
zfs_rmnode(znode_t *zp)
{
zfsvfs_t *zfsvfs = zp->z_zfsvfs;
objset_t *os = zfsvfs->z_os;
znode_t *xzp = NULL;
dmu_tx_t *tx;
uint64_t acl_obj;
uint64_t xattr_obj;
int error;
ASSERT(zp->z_links == 0);
ASSERT_VOP_ELOCKED(ZTOV(zp), __func__);
/*
* If this is an attribute directory, purge its contents.
*/
if (ZTOV(zp) != NULL && ZTOV(zp)->v_type == VDIR &&
(zp->z_pflags & ZFS_XATTR)) {
if (zfs_purgedir(zp) != 0) {
/*
* Not enough space to delete some xattrs.
* Leave it in the unlinked set.
*/
zfs_znode_dmu_fini(zp);
zfs_znode_free(zp);
return;
}
} else {
/*
* Free up all the data in the file. We don't do this for
* XATTR directories because we need truncate and remove to be
* in the same tx, like in zfs_znode_delete(). Otherwise, if
* we crash here we'll end up with an inconsistent truncated
* zap object in the delete queue. Note a truncated file is
* harmless since it only contains user data.
*/
error = dmu_free_long_range(os, zp->z_id, 0, DMU_OBJECT_END);
if (error) {
/*
* Not enough space. Leave the file in the unlinked
* set.
*/
zfs_znode_dmu_fini(zp);
zfs_znode_free(zp);
return;
}
}
/*
* If the file has extended attributes, we're going to unlink
* the xattr dir.
*/
error = sa_lookup(zp->z_sa_hdl, SA_ZPL_XATTR(zfsvfs),
&xattr_obj, sizeof (xattr_obj));
if (error == 0 && xattr_obj) {
error = zfs_zget(zfsvfs, xattr_obj, &xzp);
ASSERT3S(error, ==, 0);
vn_lock(ZTOV(xzp), LK_EXCLUSIVE | LK_RETRY);
}
static int
zfs_replay_truncate(zfsvfs_t *zsb, lr_truncate_t *lr, boolean_t byteswap)
{
znode_t *zp;
struct flock fl;
int error;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zsb, lr->lr_foid, &zp)) != 0)
return (error);
zfs_znode_wait_vnode(zp);
bzero(&fl, sizeof (fl));
fl.l_type = F_WRLCK;
fl.l_whence = 0;
fl.l_start = lr->lr_offset;
fl.l_len = lr->lr_length;
error = zfs_space(ZTOV(zp), F_FREESP, &fl, FWRITE | FOFFMAX,
lr->lr_offset, kcred, NULL);
vnode_put(ZTOV(zp));
return (error);
}
static int
zfs_replay_acl_v0(zfsvfs_t *zsb, lr_acl_v0_t *lr, boolean_t byteswap)
{
ace_t *ace = (ace_t *)(lr + 1); /* ace array follows lr_acl_t */
vsecattr_t vsa;
znode_t *zp;
int error;
if (byteswap) {
byteswap_uint64_array(lr, sizeof (*lr));
zfs_oldace_byteswap(ace, lr->lr_aclcnt);
}
if ((error = zfs_zget(zsb, lr->lr_foid, &zp)) != 0)
return (error);
zfs_znode_wait_vnode(zp);
bzero(&vsa, sizeof (vsa));
vsa.vsa_mask = VSA_ACE | VSA_ACECNT;
vsa.vsa_aclcnt = lr->lr_aclcnt;
vsa.vsa_aclentsz = sizeof (ace_t) * vsa.vsa_aclcnt;
vsa.vsa_aclflags = 0;
vsa.vsa_aclentp = ace;
error = zfs_setsecattr(ZTOV(zp), &vsa, 0, kcred, NULL);
vnode_put(ZTOV(zp));
return (error);
}
static int
zfs_replay_write(zfsvfs_t *zsb, lr_write_t *lr, boolean_t byteswap)
{
char *data = (char *)(lr + 1); /* data follows lr_write_t */
znode_t *zp;
int error;
uint64_t eod, offset, length;
ssize_t resid;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zsb, lr->lr_foid, &zp)) != 0) {
/*
* As we can log writes out of order, it's possible the
* file has been removed. In this case just drop the write
* and return success.
*/
if (error == ENOENT)
error = 0;
return (error);
}
zfs_znode_wait_vnode(zp);
offset = lr->lr_offset;
length = lr->lr_length;
eod = offset + length; /* end of data for this write */
/*
* This may be a write from a dmu_sync() for a whole block,
* and may extend beyond the current end of the file.
* We can't just replay what was written for this TX_WRITE as
* a future TX_WRITE2 may extend the eof and the data for that
* write needs to be there. So we write the whole block and
* reduce the eof. This needs to be done within the single dmu
* transaction created within vn_rdwr -> zfs_write. So a possible
* new end of file is passed through in zsb->z_replay_eof
*/
zsb->z_replay_eof = 0; /* 0 means don't change end of file */
/* If it's a dmu_sync() block, write the whole block */
if (lr->lr_common.lrc_reclen == sizeof (lr_write_t)) {
uint64_t blocksize = BP_GET_LSIZE(&lr->lr_blkptr);
if (length < blocksize) {
offset -= offset % blocksize;
length = blocksize;
}
if (zp->z_size < eod)
zsb->z_replay_eof = eod;
}
error = vn_rdwr(UIO_WRITE, ZTOV(zp), data, length, offset,
UIO_SYSSPACE, 0, RLIM64_INFINITY, kcred, &resid);
VN_RELE(ZTOV(zp));
zsb->z_replay_eof = 0; /* safety */
return (error);
}
static int
zfs_replay_rename(zfsvfs_t *zsb, lr_rename_t *lr, boolean_t byteswap)
{
char *sname = (char *)(lr + 1); /* sname and tname follow lr_rename_t */
char *tname = sname + strlen(sname) + 1;
znode_t *sdzp, *tdzp;
int error;
int vflg = 0;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zsb, lr->lr_sdoid, &sdzp)) != 0)
return (error);
zfs_znode_wait_vnode(sdzp);
if ((error = zfs_zget(zsb, lr->lr_tdoid, &tdzp)) != 0) {
vnode_put(ZTOV(sdzp));
return (error);
}
zfs_znode_wait_vnode(tdzp);
if (lr->lr_common.lrc_txtype & TX_CI)
vflg |= FIGNORECASE;
error = zfs_rename(ZTOV(sdzp), sname, ZTOV(tdzp), tname, kcred, NULL,vflg);
vnode_put(ZTOV(tdzp));
vnode_put(ZTOV(sdzp));
return (error);
}
static int
zfs_replay_link(zfsvfs_t *zsb, lr_link_t *lr, boolean_t byteswap)
{
char *name = (char *)(lr + 1); /* name follows lr_link_t */
znode_t *dzp, *zp;
int error;
int vflg = 0;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zsb, lr->lr_doid, &dzp)) != 0)
return (error);
zfs_znode_wait_vnode(dzp);
if ((error = zfs_zget(zsb, lr->lr_link_obj, &zp)) != 0) {
vnode_put(ZTOV(dzp));
return (error);
}
zfs_znode_wait_vnode(zp);
if (lr->lr_common.lrc_txtype & TX_CI)
vflg |= FIGNORECASE;
error = zfs_link(ZTOV(dzp), ZTOV(zp), name, kcred, NULL, vflg);
vnode_put(ZTOV(zp));
vnode_put(ZTOV(dzp));
return (error);
}
static int
zfs_replay_truncate(void *arg1, char *arg2, boolean_t byteswap)
{
zfsvfs_t *zfsvfs = (zfsvfs_t *)arg1;
lr_truncate_t *lr = (lr_truncate_t *)arg2;
znode_t *zp;
flock64_t fl;
int error;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0)
return (error);
bzero(&fl, sizeof (fl));
fl.l_type = F_WRLCK;
fl.l_whence = 0;
fl.l_start = lr->lr_offset;
fl.l_len = lr->lr_length;
error = VOP_SPACE(ZTOV(zp), F_FREESP, &fl, FWRITE | FOFFMAX,
lr->lr_offset, kcred, NULL);
VN_RELE(ZTOV(zp));
return (error);
}
static int
zfs_replay_link(void *arg1, char *arg2, boolean_t byteswap)
{
zfsvfs_t *zfsvfs = (zfsvfs_t *)arg1;
lr_link_t *lr = (lr_link_t *)arg2;
char *name = (char *)(lr + 1); /* name follows lr_link_t */
znode_t *dzp, *zp;
int error;
int vflg = 0;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zfsvfs, lr->lr_doid, &dzp)) != 0)
return (error);
if ((error = zfs_zget(zfsvfs, lr->lr_link_obj, &zp)) != 0) {
VN_RELE(ZTOV(dzp));
return (error);
}
if (lr->lr_common.lrc_txtype & TX_CI)
vflg |= FIGNORECASE;
error = VOP_LINK(ZTOV(dzp), ZTOV(zp), name, kcred, NULL, vflg);
VN_RELE(ZTOV(zp));
VN_RELE(ZTOV(dzp));
return (error);
}
static int
zfs_replay_setattr(zfsvfs_t *zfsvfs, lr_setattr_t *lr, boolean_t byteswap)
{
znode_t *zp;
xvattr_t xva;
vattr_t *vap = &xva.xva_vattr;
int error;
void *start;
xva_init(&xva);
if (byteswap) {
byteswap_uint64_array(lr, sizeof (*lr));
if ((lr->lr_mask & AT_XVATTR) &&
zfsvfs->z_version >= ZPL_VERSION_INITIAL)
zfs_replay_swap_attrs((lr_attr_t *)(lr + 1));
}
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) {
/*
* As we can log setattrs out of order, it's possible the
* file has been removed. In this case just drop the setattr
* and return success.
*/
if (error == ENOENT)
error = 0;
return (error);
}
zfs_init_vattr(vap, lr->lr_mask, lr->lr_mode,
lr->lr_uid, lr->lr_gid, 0, lr->lr_foid);
vap->va_size = lr->lr_size;
ZFS_TIME_DECODE(&vap->va_atime, lr->lr_atime);
ZFS_TIME_DECODE(&vap->va_mtime, lr->lr_mtime);
/*
* Fill in xvattr_t portions if necessary.
*/
start = (lr_setattr_t *)(lr + 1);
if (vap->va_mask & AT_XVATTR) {
zfs_replay_xvattr((lr_attr_t *)start, &xva);
start = (caddr_t)start +
ZIL_XVAT_SIZE(((lr_attr_t *)start)->lr_attr_masksize);
} else
xva.xva_vattr.va_mask &= ~AT_XVATTR;
zfsvfs->z_fuid_replay = zfs_replay_fuid_domain(start, &start,
lr->lr_uid, lr->lr_gid);
error = VOP_SETATTR(ZTOV(zp), vap, 0, kcred, NULL);
zfs_fuid_info_free(zfsvfs->z_fuid_replay);
zfsvfs->z_fuid_replay = NULL;
VN_RELE(ZTOV(zp));
return (error);
}
/*
* Delete the entire contents of a directory. Return a count
* of the number of entries that could not be deleted. If we encounter
* an error, return a count of at least one so that the directory stays
* in the unlinked set.
*
* NOTE: this function assumes that the directory is inactive,
* so there is no need to lock its entries before deletion.
* Also, it assumes the directory contents is *only* regular
* files.
*/
static int
zfs_purgedir(znode_t *dzp)
{
zap_cursor_t zc;
zap_attribute_t zap;
znode_t *xzp;
dmu_tx_t *tx;
zfsvfs_t *zfsvfs = dzp->z_zfsvfs;
zfs_dirlock_t dl;
int skipped = 0;
int error;
for (zap_cursor_init(&zc, zfsvfs->z_os, dzp->z_id);
(error = zap_cursor_retrieve(&zc, &zap)) == 0;
zap_cursor_advance(&zc)) {
error = zfs_zget(zfsvfs,
ZFS_DIRENT_OBJ(zap.za_first_integer), &xzp);
if (error) {
skipped += 1;
continue;
}
/*
ASSERT((ZTOV(xzp)->v_type == VREG) ||
(ZTOV(xzp)->v_type == VLNK));
*/
tx = dmu_tx_create(zfsvfs->z_os);
dmu_tx_hold_sa(tx, dzp->z_sa_hdl, B_FALSE);
dmu_tx_hold_zap(tx, dzp->z_id, FALSE, zap.za_name);
dmu_tx_hold_sa(tx, xzp->z_sa_hdl, B_FALSE);
dmu_tx_hold_zap(tx, zfsvfs->z_unlinkedobj, FALSE, NULL);
/* Is this really needed ? */
zfs_sa_upgrade_txholds(tx, xzp);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
dmu_tx_abort(tx);
//VN_RELE(ZTOV(xzp)); // async
VN_RELE_ASYNC(ZTOV(xzp), dsl_pool_vnrele_taskq(dmu_objset_pool(zfsvfs->z_os)));
skipped += 1;
continue;
}
bzero(&dl, sizeof (dl));
dl.dl_dzp = dzp;
dl.dl_name = zap.za_name;
error = zfs_link_destroy(&dl, xzp, tx, 0, NULL);
if (error)
skipped += 1;
dmu_tx_commit(tx);
//VN_RELE(ZTOV(xzp)); // async
VN_RELE_ASYNC(ZTOV(xzp), dsl_pool_vnrele_taskq(dmu_objset_pool(zfsvfs->z_os)));
}
zap_cursor_fini(&zc);
if (error != ENOENT)
skipped += 1;
return (skipped);
}
/*
* Unlink zp from dl, and mark zp for reaping if this was the last link.
* Can fail if zp is a mount point (EBUSY) or a non-empty directory (EEXIST).
* If 'reaped_ptr' is NULL, we put reaped znodes on the delete queue.
* If it's non-NULL, we use it to indicate whether the znode needs reaping,
* and it's the caller's job to do it.
*/
int
zfs_link_destroy(zfs_dirlock_t *dl, znode_t *zp, dmu_tx_t *tx, int flag,
int *reaped_ptr)
{
znode_t *dzp = dl->dl_dzp;
vnode_t *vp = ZTOV(zp);
int zp_is_dir = (vp->v_type == VDIR);
int reaped = 0;
int error;
dnlc_remove(ZTOV(dzp), dl->dl_name);
if (!(flag & ZRENAMING)) {
dmu_buf_will_dirty(zp->z_dbuf, tx);
if (vn_vfswlock(vp)) /* prevent new mounts on zp */
return (EBUSY);
if (vn_ismntpt(vp)) { /* don't remove mount point */
vn_vfsunlock(vp);
return (EBUSY);
}
mutex_enter(&zp->z_lock);
if (zp_is_dir && !zfs_dirempty(zp)) { /* dir not empty */
mutex_exit(&zp->z_lock);
vn_vfsunlock(vp);
return (EEXIST);
}
ASSERT(zp->z_phys->zp_links > zp_is_dir);
if (--zp->z_phys->zp_links == zp_is_dir) {
zp->z_reap = 1;
zp->z_phys->zp_links = 0;
reaped = 1;
} else {
zfs_time_stamper_locked(zp, STATE_CHANGED, tx);
}
mutex_exit(&zp->z_lock);
vn_vfsunlock(vp);
}
dmu_buf_will_dirty(dzp->z_dbuf, tx);
mutex_enter(&dzp->z_lock);
dzp->z_phys->zp_size--; /* one dirent removed */
dzp->z_phys->zp_links -= zp_is_dir; /* ".." link from zp */
zfs_time_stamper_locked(dzp, CONTENT_MODIFIED, tx);
mutex_exit(&dzp->z_lock);
error = zap_remove(zp->z_zfsvfs->z_os, dzp->z_id, dl->dl_name, tx);
ASSERT(error == 0);
if (reaped_ptr != NULL)
*reaped_ptr = reaped;
else if (reaped)
zfs_dq_add(zp, tx);
return (0);
}
/*
* Replaying ACLs is complicated by FUID support.
* The log record may contain some optional data
* to be used for replaying FUID's. These pieces
* are the actual FUIDs that were created initially.
* The FUID table index may no longer be valid and
* during zfs_create() a new index may be assigned.
* Because of this the log will contain the original
* doman+rid in order to create a new FUID.
*
* The individual ACEs may contain an ephemeral uid/gid which is no
* longer valid and will need to be replaced with an actual FUID.
*
*/
static int
zfs_replay_acl(zfsvfs_t *zfsvfs, void *data, boolean_t byteswap)
{
#ifdef __OSV__
kprintf("TX_ACL_V0 not supported on OSv\n");
return EOPNOTSUPP;
#else
lr_acl_t *lr = data;
ace_t *ace = (ace_t *)(lr + 1);
vsecattr_t vsa;
znode_t *zp;
int error;
if (byteswap) {
byteswap_uint64_array(lr, sizeof (*lr));
zfs_ace_byteswap(ace, lr->lr_acl_bytes, B_FALSE);
if (lr->lr_fuidcnt) {
byteswap_uint64_array((caddr_t)ace +
ZIL_ACE_LENGTH(lr->lr_acl_bytes),
lr->lr_fuidcnt * sizeof (uint64_t));
}
}
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0)
return (error);
#ifdef TODO
bzero(&vsa, sizeof (vsa));
vsa.vsa_mask = VSA_ACE | VSA_ACECNT | VSA_ACE_ACLFLAGS;
vsa.vsa_aclcnt = lr->lr_aclcnt;
vsa.vsa_aclentp = ace;
vsa.vsa_aclentsz = lr->lr_acl_bytes;
vsa.vsa_aclflags = lr->lr_acl_flags;
if (lr->lr_fuidcnt) {
void *fuidstart = (caddr_t)ace +
ZIL_ACE_LENGTH(lr->lr_acl_bytes);
zfsvfs->z_fuid_replay =
zfs_replay_fuids(fuidstart, &fuidstart,
lr->lr_fuidcnt, lr->lr_domcnt, 0, 0);
}
error = VOP_SETSECATTR(ZTOV(zp), &vsa, 0, kcred, NULL);
if (zfsvfs->z_fuid_replay)
zfs_fuid_info_free(zfsvfs->z_fuid_replay);
#else
error = EOPNOTSUPP;
#endif
zfsvfs->z_fuid_replay = NULL;
VN_RELE(ZTOV(zp));
return (error);
#endif
}
static int
zfs_replay_write(zfsvfs_t *zfsvfs, lr_write_t *lr, boolean_t byteswap)
{
char *data = (char *)(lr + 1); /* data follows lr_write_t */
znode_t *zp;
int error;
ssize_t resid;
uint64_t orig_eof, eod, offset, length;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) {
/*
* As we can log writes out of order, it's possible the
* file has been removed. In this case just drop the write
* and return success.
*/
if (error == ENOENT)
error = 0;
return (error);
}
offset = lr->lr_offset;
length = lr->lr_length;
eod = offset + length; /* end of data for this write */
orig_eof = zp->z_phys->zp_size;
/* If it's a dmu_sync() block, write the whole block */
if (lr->lr_common.lrc_reclen == sizeof (lr_write_t)) {
uint64_t blocksize = BP_GET_LSIZE(&lr->lr_blkptr);
if (length < blocksize) {
offset -= offset % blocksize;
length = blocksize;
}
}
error = vn_rdwr(UIO_WRITE, ZTOV(zp), data, length, offset,
UIO_SYSSPACE, 0, RLIM64_INFINITY, kcred, &resid);
/*
* This may be a write from a dmu_sync() for a whole block,
* and may extend beyond the current end of the file.
* We can't just replay what was written for this TX_WRITE as
* a future TX_WRITE2 may extend the eof and the data for that
* write needs to be there. So we write the whole block and
* reduce the eof.
*/
if (orig_eof < zp->z_phys->zp_size) /* file length grew ? */
zp->z_phys->zp_size = eod;
VN_RELE(ZTOV(zp));
return (error);
}
/*
* Look up an entry in a directory.
*
* NOTE: '.' and '..' are handled as special cases because
* no directory entries are actually stored for them. If this is
* the root of a filesystem, then '.zfs' is also treated as a
* special pseudo-directory.
*/
int
zfs_dirlook(znode_t *dzp, char *name, vnode_t **vpp, int flags,
int *deflg, pathname_t *rpnp)
{
zfs_dirlock_t *dl;
znode_t *zp;
int error = 0;
uint64_t parent;
if (name[0] == 0 || (name[0] == '.' && name[1] == 0)) {
*vpp = ZTOV(dzp);
VN_HOLD(*vpp);
} else if (name[0] == '.' && name[1] == '.' && name[2] == 0) {
zfsvfs_t *zfsvfs = dzp->z_zfsvfs;
/*
* If we are a snapshot mounted under .zfs, return
* the vp for the snapshot directory.
*/
if ((error = sa_lookup(dzp->z_sa_hdl,
SA_ZPL_PARENT(zfsvfs), &parent, sizeof (parent))) != 0)
return (error);
if (parent == dzp->z_id && zfsvfs->z_parent != zfsvfs) {
error = zfsctl_root_lookup(zfsvfs->z_parent->z_ctldir,
"snapshot", vpp, NULL, 0, NULL, kcred,
NULL, NULL, NULL);
return (error);
}
rw_enter(&dzp->z_parent_lock, RW_READER);
error = zfs_zget(zfsvfs, parent, &zp);
if (error == 0)
*vpp = ZTOV(zp);
rw_exit(&dzp->z_parent_lock);
} else if (zfs_has_ctldir(dzp) && strcmp(name, ZFS_CTLDIR_NAME) == 0) {
*vpp = zfsctl_root(dzp);
} else {
int zf;
zf = ZEXISTS | ZSHARED;
if (flags & FIGNORECASE)
zf |= ZCILOOK;
error = zfs_dirent_lock(&dl, dzp, name, &zp, zf, deflg, rpnp);
if (error == 0) {
*vpp = ZTOV(zp);
zfs_dirent_unlock(dl);
dzp->z_zn_prefetch = B_TRUE; /* enable prefetching */
}
rpnp = NULL;
}
if ((flags & FIGNORECASE) && rpnp && !error)
(void) strlcpy(rpnp->pn_buf, name, rpnp->pn_bufsize);
return (error);
}
/*
* Replaying ACLs is complicated by FUID support.
* The log record may contain some optional data
* to be used for replaying FUID's. These pieces
* are the actual FUIDs that were created initially.
* The FUID table index may no longer be valid and
* during zfs_create() a new index may be assigned.
* Because of this the log will contain the original
* doman+rid in order to create a new FUID.
*
* The individual ACEs may contain an ephemeral uid/gid which is no
* longer valid and will need to be replaced with an actual FUID.
*
*/
static int
zfs_replay_acl(zfsvfs_t *zfsvfs, lr_acl_t *lr, boolean_t byteswap)
{
ace_t *ace = (ace_t *)(lr + 1);
vsecattr_t vsa;
znode_t *zp;
int error;
if (byteswap) {
byteswap_uint64_array(lr, sizeof (*lr));
zfs_ace_byteswap(ace, lr->lr_acl_bytes, B_FALSE);
if (lr->lr_fuidcnt) {
byteswap_uint64_array((caddr_t)ace +
ZIL_ACE_LENGTH(lr->lr_acl_bytes),
lr->lr_fuidcnt * sizeof (uint64_t));
}
}
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) {
/*
* As we can log acls out of order, it's possible the
* file has been removed. In this case just drop the acl
* and return success.
*/
if (error == ENOENT)
error = 0;
return (error);
}
bzero(&vsa, sizeof (vsa));
vsa.vsa_mask = VSA_ACE | VSA_ACECNT | VSA_ACE_ACLFLAGS;
vsa.vsa_aclcnt = lr->lr_aclcnt;
vsa.vsa_aclentp = ace;
vsa.vsa_aclentsz = lr->lr_acl_bytes;
vsa.vsa_aclflags = lr->lr_acl_flags;
if (lr->lr_fuidcnt) {
void *fuidstart = (caddr_t)ace +
ZIL_ACE_LENGTH(lr->lr_acl_bytes);
zfsvfs->z_fuid_replay =
zfs_replay_fuids(fuidstart, &fuidstart,
lr->lr_fuidcnt, lr->lr_domcnt, 0, 0);
}
error = VOP_SETSECATTR(ZTOV(zp), &vsa, 0, kcred, NULL);
if (zfsvfs->z_fuid_replay)
zfs_fuid_info_free(zfsvfs->z_fuid_replay);
zfsvfs->z_fuid_replay = NULL;
VN_RELE(ZTOV(zp));
return (error);
}
static int
zfs_replay_setattr(void *arg1, char *arg2, boolean_t byteswap)
{
zfsvfs_t *zfsvfs = (zfsvfs_t *)arg1;
lr_setattr_t *lr = (lr_setattr_t *)arg2;
znode_t *zp;
xvattr_t xva;
vattr_t *vap = &xva.xva_vattr;
int error;
void *start;
xva_init(&xva);
if (byteswap) {
byteswap_uint64_array(lr, sizeof (*lr));
if ((lr->lr_mask & AT_XVATTR) &&
zfsvfs->z_version >= ZPL_VERSION_INITIAL)
zfs_replay_swap_attrs((lr_attr_t *)(lr + 1));
}
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0)
return (error);
zfs_init_vattr(vap, lr->lr_mask, lr->lr_mode,
lr->lr_uid, lr->lr_gid, 0, lr->lr_foid);
vap->va_size = lr->lr_size;
ZFS_TIME_DECODE(&vap->va_atime, lr->lr_atime);
ZFS_TIME_DECODE(&vap->va_mtime, lr->lr_mtime);
/*
* Fill in xvattr_t portions if necessary.
*/
start = (lr_setattr_t *)(lr + 1);
#ifdef HAVE_ZPL
if (vap->va_mask & AT_XVATTR) {
zfs_replay_xvattr((lr_attr_t *)start, &xva);
start = (caddr_t)start +
ZIL_XVAT_SIZE(((lr_attr_t *)start)->lr_attr_masksize);
} else
xva.xva_vattr.va_mask &= ~AT_XVATTR;
#endif /* HAVE_ZPL */
zfsvfs->z_fuid_replay = zfs_replay_fuid_domain(start, &start,
lr->lr_uid, lr->lr_gid);
error = VOP_SETATTR(ZTOV(zp), vap, 0, kcred, NULL);
zfs_fuid_info_free(zfsvfs->z_fuid_replay);
zfsvfs->z_fuid_replay = NULL;
VN_RELE(ZTOV(zp));
return (error);
}
/*
* Delete the entire contents of a directory. Return a count
* of the number of entries that could not be deleted. If we encounter
* an error, return a count of at least one so that the directory stays
* in the unlinked set.
*
* NOTE: this function assumes that the directory is inactive,
* so there is no need to lock its entries before deletion.
* Also, it assumes the directory contents is *only* regular
* files.
*/
static int
zfs_purgedir(znode_t *dzp)
{
zap_cursor_t zc;
zap_attribute_t zap;
znode_t *xzp;
dmu_tx_t *tx;
zfsvfs_t *zfsvfs = dzp->z_zfsvfs;
int skipped = 0;
int error;
for (zap_cursor_init(&zc, zfsvfs->z_os, dzp->z_id);
(error = zap_cursor_retrieve(&zc, &zap)) == 0;
zap_cursor_advance(&zc)) {
error = zfs_zget(zfsvfs,
ZFS_DIRENT_OBJ(zap.za_first_integer), &xzp);
if (error) {
skipped += 1;
continue;
}
vn_lock(ZTOV(xzp), LK_EXCLUSIVE | LK_RETRY);
ASSERT((ZTOV(xzp)->v_type == VREG) ||
(ZTOV(xzp)->v_type == VLNK));
tx = dmu_tx_create(zfsvfs->z_os);
dmu_tx_hold_sa(tx, dzp->z_sa_hdl, B_FALSE);
dmu_tx_hold_zap(tx, dzp->z_id, FALSE, zap.za_name);
dmu_tx_hold_sa(tx, xzp->z_sa_hdl, B_FALSE);
dmu_tx_hold_zap(tx, zfsvfs->z_unlinkedobj, FALSE, NULL);
/* Is this really needed ? */
zfs_sa_upgrade_txholds(tx, xzp);
dmu_tx_mark_netfree(tx);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
dmu_tx_abort(tx);
vput(ZTOV(xzp));
skipped += 1;
continue;
}
error = zfs_link_destroy(dzp, zap.za_name, xzp, tx, 0, NULL);
if (error)
skipped += 1;
dmu_tx_commit(tx);
vput(ZTOV(xzp));
}
zap_cursor_fini(&zc);
if (error != ENOENT)
skipped += 1;
return (skipped);
}
/*
* Delete the entire contents of a directory. Return a count
* of the number of entries that could not be deleted. If we encounter
* an error, return a count of at least one so that the directory stays
* in the unlinked set.
*
* NOTE: this function assumes that the directory is inactive,
* so there is no need to lock its entries before deletion.
* Also, it assumes the directory contents is *only* regular
* files.
*/
static int
zfs_purgedir(znode_t *dzp)
{
zap_cursor_t zc;
zap_attribute_t zap;
znode_t *xzp;
dmu_tx_t *tx;
zfsvfs_t *zfsvfs = dzp->z_zfsvfs;
zfs_dirlock_t dl;
int skipped = 0;
int error;
for (zap_cursor_init(&zc, zfsvfs->z_os, dzp->z_id);
(error = zap_cursor_retrieve(&zc, &zap)) == 0;
zap_cursor_advance(&zc)) {
error = zfs_zget(zfsvfs,
ZFS_DIRENT_OBJ(zap.za_first_integer), &xzp);
if (error) {
skipped += 1;
continue;
}
ASSERT((ZTOV(xzp)->v_type == VREG) ||
(ZTOV(xzp)->v_type == VLNK));
tx = dmu_tx_create(zfsvfs->z_os);
dmu_tx_hold_bonus(tx, dzp->z_id);
dmu_tx_hold_zap(tx, dzp->z_id, FALSE, zap.za_name);
dmu_tx_hold_bonus(tx, xzp->z_id);
dmu_tx_hold_zap(tx, zfsvfs->z_unlinkedobj, FALSE, NULL);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
dmu_tx_abort(tx);
VN_RELE(ZTOV(xzp));
skipped += 1;
continue;
}
bzero(&dl, sizeof (dl));
dl.dl_dzp = dzp;
dl.dl_name = zap.za_name;
error = zfs_link_destroy(&dl, xzp, tx, 0, NULL);
if (error)
skipped += 1;
dmu_tx_commit(tx);
VN_RELE(ZTOV(xzp));
}
zap_cursor_fini(&zc);
if (error != ENOENT)
skipped += 1;
return (skipped);
}
zfs_dirlook(znode_t *dzp, char *name, vnode_t **vpp)
#endif
{
zfs_dirlock_t *dl;
znode_t *zp;
int error = 0;
uint64_t parent;
#ifdef __APPLE__
char *name = cnp->cn_nameptr;
#endif
if (name[0] == 0 || (name[0] == '.' && name[1] == 0)) {
*vpp = ZTOV(dzp);
VN_HOLD(*vpp);
} else if (name[0] == '.' && name[1] == '.' && name[2] == 0) {
zfsvfs_t *zfsvfs = dzp->z_zfsvfs;
/*
* If we are a snapshot mounted under .zfs, return
* the vp for the snapshot directory.
*/
if ((error = sa_lookup(dzp->z_sa_hdl,
SA_ZPL_PARENT(zfsvfs), &parent, sizeof (parent))) != 0)
return (error);
if (parent == dzp->z_id && zfsvfs->z_parent != zfsvfs) {
error = zfsctl_root_lookup(zfsvfs->z_parent->z_ctldir,
"snapshot", vpp, NULL, 0, NULL, kcred
/*, NULL, NULL, NULL*/);
return (error);
}
rw_enter(&dzp->z_parent_lock, RW_READER);
error = zfs_zget(zfsvfs, parent, &zp);
if (error == 0)
*vpp = ZTOV(zp);
rw_exit(&dzp->z_parent_lock);
} else if (zfs_has_ctldir(dzp) && strcmp(name, ZFS_CTLDIR_NAME) == 0) {
*vpp = zfsctl_root(dzp);
} else {
#ifdef __APPLE__
error = zfs_dirent_lock(&dl, dzp, cnp, &zp, ZEXISTS | ZSHARED);
#else
error = zfs_dirent_lock(&dl, dzp, name, &zp, ZEXISTS | ZSHARED);
#endif
if (error == 0) {
*vpp = ZTOV(zp);
zfs_dirent_unlock(dl);
dzp->z_zn_prefetch = B_TRUE; /* enable prefetching */
}
}
return (error);
}
