/*
* 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
}
/*
* 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);
}
/*
* 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(void *arg1, void *arg2, boolean_t byteswap)
{
zfsvfs_t *zfsvfs = arg1;
lr_acl_t *lr = arg2;
ace_t *ace = (ace_t *)(lr + 1);
vsecattr_t vsa;
znode_t *zp;
vnode_t *vp;
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);
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);
}
vp = ZTOV(zp);
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
error = zfs_setsecattr(vp, &vsa, 0, kcred, NULL);
VOP_UNLOCK(vp, 0);
if (zfsvfs->z_fuid_replay)
zfs_fuid_info_free(zfsvfs->z_fuid_replay);
zfsvfs->z_fuid_replay = NULL;
VN_RELE(vp);
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 *zsb, 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(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_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);
zsb->z_fuid_replay =
zfs_replay_fuids(fuidstart, &fuidstart,
lr->lr_fuidcnt, lr->lr_domcnt, 0, 0);
}
error = zfs_setsecattr(ZTOV(zp), &vsa, 0, kcred, NULL);
if (zsb->z_fuid_replay)
zfs_fuid_info_free(zsb->z_fuid_replay);
zsb->z_fuid_replay = NULL;
vnode_put(ZTOV(zp));
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);
}
/* ARGSUSED */
void
zfs_acl_byteswap(void *buf, size_t size)
{
zfs_ace_byteswap(buf, size, B_TRUE);
}
/*
* 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);
}