/*
* zfs_log_create() is used to handle TX_CREATE, TX_CREATE_ATTR, TX_MKDIR,
* TX_MKDIR_ATTR and TX_MKXATTR
* transactions.
*
* TX_CREATE and TX_MKDIR are standard creates, but they may have FUID
* domain information appended prior to the name. In this case the
* uid/gid in the log record will be a log centric FUID.
*
* TX_CREATE_ACL_ATTR and TX_MKDIR_ACL_ATTR handle special creates that
* may contain attributes, ACL and optional fuid information.
*
* TX_CREATE_ACL and TX_MKDIR_ACL handle special creates that specify
* and ACL and normal users/groups in the ACEs.
*
* There may be an optional xvattr attribute information similar
* to zfs_log_setattr.
*
* Also, after the file name "domain" strings may be appended.
*/
void
zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
znode_t *dzp, znode_t *zp, char *name, vsecattr_t *vsecp,
zfs_fuid_info_t *fuidp, vattr_t *vap)
{
itx_t *itx;
uint64_t seq;
lr_create_t *lr;
#ifdef HAVE_ZPL
lr_acl_create_t *lracl;
#endif
size_t aclsize;
size_t xvatsize = 0;
size_t txsize;
xvattr_t *xvap = (xvattr_t *)vap;
void *end;
size_t lrsize;
size_t namesize = strlen(name) + 1;
size_t fuidsz = 0;
if (zilog == NULL)
return;
ZFS_HANDLE_REPLAY(zilog, tx); /* exits if replay */
/*
* If we have FUIDs present then add in space for
* domains and ACE fuid's if any.
*/
if (fuidp) {
fuidsz += fuidp->z_domain_str_sz;
fuidsz += fuidp->z_fuid_cnt * sizeof (uint64_t);
}
if (vap->va_mask & AT_XVATTR)
xvatsize = ZIL_XVAT_SIZE(xvap->xva_mapsize);
if ((int)txtype == TX_CREATE_ATTR || (int)txtype == TX_MKDIR_ATTR ||
(int)txtype == TX_CREATE || (int)txtype == TX_MKDIR ||
(int)txtype == TX_MKXATTR) {
txsize = sizeof (*lr) + namesize + fuidsz + xvatsize;
lrsize = sizeof (*lr);
} else {
aclsize = (vsecp) ? vsecp->vsa_aclentsz : 0;
txsize =
sizeof (lr_acl_create_t) + namesize + fuidsz +
ZIL_ACE_LENGTH(aclsize) + xvatsize;
lrsize = sizeof (lr_acl_create_t);
}
itx = zil_itx_create(txtype, txsize);
lr = (lr_create_t *)&itx->itx_lr;
lr->lr_doid = dzp->z_id;
lr->lr_foid = zp->z_id;
lr->lr_mode = zp->z_phys->zp_mode;
if (!IS_EPHEMERAL(zp->z_phys->zp_uid)) {
lr->lr_uid = (uint64_t)zp->z_phys->zp_uid;
} else {
lr->lr_uid = fuidp->z_fuid_owner;
}
if (!IS_EPHEMERAL(zp->z_phys->zp_gid)) {
lr->lr_gid = (uint64_t)zp->z_phys->zp_gid;
} else {
lr->lr_gid = fuidp->z_fuid_group;
}
lr->lr_gen = zp->z_phys->zp_gen;
lr->lr_crtime[0] = zp->z_phys->zp_crtime[0];
lr->lr_crtime[1] = zp->z_phys->zp_crtime[1];
lr->lr_rdev = zp->z_phys->zp_rdev;
/*
* Fill in xvattr info if any
*/
#ifdef HAVE_ZPL
if (vap->va_mask & AT_XVATTR) {
zfs_log_xvattr((lr_attr_t *)((caddr_t)lr + lrsize), xvap);
end = (caddr_t)lr + lrsize + xvatsize;
} else {
end = (caddr_t)lr + lrsize;
}
#else
end = (caddr_t)lr + lrsize;
#endif /* HAVE_ZPL */
/* Now fill in any ACL info */
#ifdef HAVE_ZPL
if (vsecp) {
lracl = (lr_acl_create_t *)&itx->itx_lr;
lracl->lr_aclcnt = vsecp->vsa_aclcnt;
lracl->lr_acl_bytes = aclsize;
lracl->lr_domcnt = fuidp ? fuidp->z_domain_cnt : 0;
lracl->lr_fuidcnt = fuidp ? fuidp->z_fuid_cnt : 0;
if (vsecp->vsa_aclflags & VSA_ACE_ACLFLAGS)
lracl->lr_acl_flags = (uint64_t)vsecp->vsa_aclflags;
else
lracl->lr_acl_flags = 0;
bcopy(vsecp->vsa_aclentp, end, aclsize);
end = (caddr_t)end + ZIL_ACE_LENGTH(aclsize);
}
/* drop in FUID info */
if (fuidp) {
end = zfs_log_fuid_ids(fuidp, end);
end = zfs_log_fuid_domains(fuidp, end);
}
#endif
/*
* Now place file name in log record
*/
bcopy(name, end, namesize);
seq = zil_itx_assign(zilog, itx, tx);
dzp->z_last_itx = seq;
zp->z_last_itx = seq;
}
/*
* 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);
}
error = VOP_CREATE(ZTOV(dzp), name, &xva.xva_vattr,
0, 0, &vp, kcred, vflg, NULL, &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 = VOP_MKDIR(ZTOV(dzp), name, &xva.xva_vattr,
&vp, kcred, NULL, vflg, &vsec);
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);
}
/*
* Replay file create with optional ACL, xvattr information as well
* as option FUID information.
*/
static int
zfs_replay_create_acl(zfs_sb_t *zsb, 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(zsb, 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(zsb->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);
zsb->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 (zsb->z_fuid_replay == NULL) {
fuidstart = (caddr_t)(lracl + 1) + xvatlen +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
zsb->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);
zsb->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 (zsb->z_fuid_replay == NULL) {
fuidstart = (caddr_t)(lracl + 1) + xvatlen +
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
zsb->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 (zsb->z_fuid_replay)
zfs_fuid_info_free(zsb->z_fuid_replay);
zsb->z_fuid_replay = NULL;
return (error);
}