/*
* TX_WRITE2 are only generated when dmu_sync() returns EALREADY
* meaning the pool block is already being synced. So now that we always write
* out full blocks, all we have to do is expand the eof if
* the file is grown.
*/
static int
zfs_replay_write2(zfsvfs_t *zfsvfs, lr_write_t *lr, boolean_t byteswap)
{
znode_t *zp;
int error;
uint64_t end;
if (byteswap)
byteswap_uint64_array(lr, sizeof (*lr));
if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0)
return (error);
top:
end = lr->lr_offset + lr->lr_length;
if (end > zp->z_size) {
dmu_tx_t *tx = dmu_tx_create(zfsvfs->z_os);
zp->z_size = end;
dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE);
error = dmu_tx_assign(tx, TXG_WAIT);
if (error) {
VN_RELE(ZTOV(zp));
if (error == ERESTART) {
dmu_tx_wait(tx);
dmu_tx_abort(tx);
goto top;
}
dmu_tx_abort(tx);
return (error);
}
(void) sa_update(zp->z_sa_hdl, SA_ZPL_SIZE(zfsvfs),
(void *)&zp->z_size, sizeof (uint64_t), tx);
/* Ensure the replayed seq is updated */
(void) zil_replaying(zfsvfs->z_log, tx);
dmu_tx_commit(tx);
}
VN_RELE(ZTOV(zp));
return (error);
}
static int
zfs_replay_link(void *arg1, void *arg2, boolean_t byteswap)
{
zfsvfs_t *zfsvfs = arg1;
lr_link_t *lr = arg2;
char *name = (char *)(lr + 1); /* name follows lr_link_t */
znode_t *dzp, *zp;
struct componentname cn;
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;
cn.cn_nameptr = name;
cn.cn_cred = kcred;
cn.cn_thread = curthread;
cn.cn_flags = SAVENAME;
vn_lock(ZTOV(dzp), LK_EXCLUSIVE | LK_RETRY);
vn_lock(ZTOV(zp), LK_EXCLUSIVE | LK_RETRY);
error = VOP_LINK(ZTOV(dzp), ZTOV(zp), &cn /*,vflg*/);
VOP_UNLOCK(ZTOV(zp), 0);
VOP_UNLOCK(ZTOV(dzp), 0);
VN_RELE(ZTOV(zp));
VN_RELE(ZTOV(dzp));
return (error);
}
static int
zfs_replay_acl_v0(zfsvfs_t *zfsvfs, void *data, boolean_t byteswap)
{
#ifdef __OSV__
kprintf("TX_ACL_V0 not supported on OSv\n");
return EOPNOTSUPP;
#else
lr_acl_v0_t *lr = data;
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);
#endif
}
/*
* 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);
}
static int
zfs_replay_setattr(zfsvfs_t *zfsvfs, void *data, boolean_t byteswap)
{
#ifdef __OSV__
kprintf("TX_SETATTR not supported on OSv\n");
return EOPNOTSUPP;
#else
lr_setattr_t *lr = data;
znode_t *zp;
xvattr_t xva;
vattr_t *vap = &xva.xva_vattr;
vnode_t *vp;
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);
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);
vp = ZTOV(zp);
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
error = VOP_SETATTR(vp, vap, kcred);
VOP_UNLOCK(vp, 0);
zfs_fuid_info_free(zfsvfs->z_fuid_replay);
zfsvfs->z_fuid_replay = NULL;
VN_RELE(vp);
return (error);
#endif
}
static int
zfs_replay_write(zfsvfs_t *zfsvfs, void *_data, boolean_t byteswap)
{
#ifndef TODO_OSV
kprintf("TX_WRITE\n");
return EOPNOTSUPP;
#else
lr_write_t *lr = _data;
char *data = (char *)(lr + 1); /* data follows lr_write_t */
znode_t *zp;
int error;
ssize_t resid;
uint64_t 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 */
/*
* 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 zfsvfs->z_replay_eof
*/
zfsvfs->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)
zfsvfs->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));
zfsvfs->z_replay_eof = 0; /* safety */
return (error);
#endif
}
int
zio_checksum_error(zio_t *zio, zio_bad_cksum_t *info)
{
blkptr_t *bp = zio->io_bp;
uint_t checksum = (bp == NULL ? zio->io_prop.zp_checksum :
(BP_IS_GANG(bp) ? ZIO_CHECKSUM_GANG_HEADER : BP_GET_CHECKSUM(bp)));
int byteswap;
int error;
uint64_t size = (bp == NULL ? zio->io_size :
(BP_IS_GANG(bp) ? SPA_GANGBLOCKSIZE : BP_GET_PSIZE(bp)));
uint64_t offset = zio->io_offset;
void *data = zio->io_data;
zio_checksum_info_t *ci = &zio_checksum_table[checksum];
zio_cksum_t actual_cksum, expected_cksum, verifier;
if (checksum >= ZIO_CHECKSUM_FUNCTIONS || ci->ci_func[0] == NULL)
return (EINVAL);
if (ci->ci_eck) {
zio_eck_t *eck;
if (checksum == ZIO_CHECKSUM_ZILOG2) {
zil_chain_t *zilc = data;
uint64_t nused;
eck = &zilc->zc_eck;
if (eck->zec_magic == ZEC_MAGIC)
nused = zilc->zc_nused;
else if (eck->zec_magic == BSWAP_64(ZEC_MAGIC))
nused = BSWAP_64(zilc->zc_nused);
else
return (ECKSUM);
if (nused > size)
return (ECKSUM);
size = P2ROUNDUP_TYPED(nused, ZIL_MIN_BLKSZ, uint64_t);
} else {
eck = (zio_eck_t *)((char *)data + size) - 1;
}
if (checksum == ZIO_CHECKSUM_GANG_HEADER)
zio_checksum_gang_verifier(&verifier, bp);
else if (checksum == ZIO_CHECKSUM_LABEL)
zio_checksum_label_verifier(&verifier, offset);
else
verifier = bp->blk_cksum;
byteswap = (eck->zec_magic == BSWAP_64(ZEC_MAGIC));
if (byteswap)
byteswap_uint64_array(&verifier, sizeof (zio_cksum_t));
expected_cksum = eck->zec_cksum;
eck->zec_cksum = verifier;
ci->ci_func[byteswap](data, size, &actual_cksum);
eck->zec_cksum = expected_cksum;
if (byteswap)
byteswap_uint64_array(&expected_cksum,
sizeof (zio_cksum_t));
} else {
ASSERT(!BP_IS_GANG(bp));
byteswap = BP_SHOULD_BYTESWAP(bp);
expected_cksum = bp->blk_cksum;
ci->ci_func[byteswap](data, size, &actual_cksum);
}
info->zbc_expected = expected_cksum;
info->zbc_actual = actual_cksum;
info->zbc_checksum_name = ci->ci_name;
info->zbc_byteswapped = byteswap;
info->zbc_injected = 0;
info->zbc_has_cksum = 1;
if (!ZIO_CHECKSUM_EQUAL(actual_cksum, expected_cksum)) {
return (ECKSUM);
}
if (zio_injection_enabled && !zio->io_error &&
(error = zio_handle_fault_injection(zio, ECKSUM)) != 0) {
info->zbc_injected = 1;
return (error);
}
return (0);
}
static void
zil_replay_log_record(zilog_t *zilog, lr_t *lr, void *zra, uint64_t claim_txg)
{
zil_replay_arg_t *zr = zra;
const zil_header_t *zh = zilog->zl_header;
uint64_t reclen = lr->lrc_reclen;
uint64_t txtype = lr->lrc_txtype;
char *name;
int pass, error;
if (!zilog->zl_replay) /* giving up */
return;
if (lr->lrc_txg < claim_txg) /* already committed */
return;
if (lr->lrc_seq <= zh->zh_replay_seq) /* already replayed */
return;
/* Strip case-insensitive bit, still present in log record */
txtype &= ~TX_CI;
if (txtype == 0 || txtype >= TX_MAX_TYPE) {
error = EINVAL;
goto bad;
}
/*
* Make a copy of the data so we can revise and extend it.
*/
bcopy(lr, zr->zr_lrbuf, reclen);
/*
* The log block containing this lr may have been byteswapped
* so that we can easily examine common fields like lrc_txtype.
* However, the log is a mix of different data types, and only the
* replay vectors know how to byteswap their records. Therefore, if
* the lr was byteswapped, undo it before invoking the replay vector.
*/
if (zr->zr_byteswap)
byteswap_uint64_array(zr->zr_lrbuf, reclen);
/*
* We must now do two things atomically: replay this log record,
* and update the log header sequence number to reflect the fact that
* we did so. At the end of each replay function the sequence number
* is updated if we are in replay mode.
*/
for (pass = 1; pass <= 2; pass++) {
zilog->zl_replaying_seq = lr->lrc_seq;
/* Only byteswap (if needed) on the 1st pass. */
error = zr->zr_replay[txtype](zr->zr_arg, zr->zr_lrbuf,
zr->zr_byteswap && pass == 1);
if (!error)
return;
/*
* The DMU's dnode layer doesn't see removes until the txg
* commits, so a subsequent claim can spuriously fail with
* EEXIST. So if we receive any error we try syncing out
* any removes then retry the transaction.
*/
if (pass == 1)
txg_wait_synced(spa_get_dsl(zilog->zl_spa), 0);
}
bad:
ASSERT(error);
name = kmem_alloc(MAXNAMELEN, KM_SLEEP);
dmu_objset_name(zr->zr_os, name);
cmn_err(CE_WARN, "ZFS replay transaction error %d, "
"dataset %s, seq 0x%llx, txtype %llu %s\n",
error, name, (u_longlong_t)lr->lrc_seq, (u_longlong_t)txtype,
(lr->lrc_txtype & TX_CI) ? "CI" : "");
zilog->zl_replay = B_FALSE;
kmem_free(name, MAXNAMELEN);
}
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);
}
static int
zfs_replay_write(void *arg1, void *arg2, boolean_t byteswap)
{
zfsvfs_t *zfsvfs = arg1;
lr_write_t *lr = arg2;
char *data = (char *)(lr + 1); /* data follows lr_write_t */
znode_t *zp;
int error, written;
uint64_t 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 */
/*
* 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 zfsvfs->z_replay_eof
*/
zfsvfs->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)
zfsvfs->z_replay_eof = eod;
}
written = zpl_write_common(ZTOI(zp), data, length, &offset,
UIO_SYSSPACE, 0, kcred);
if (written < 0)
error = -written;
else if (written < length)
error = SET_ERROR(EIO); /* short write */
iput(ZTOI(zp));
zfsvfs->z_replay_eof = 0; /* safety */
return (error);
}
int
zio_checksum_error_impl(spa_t *spa, const blkptr_t *bp,
enum zio_checksum checksum, abd_t *abd, uint64_t size, uint64_t offset,
zio_bad_cksum_t *info)
{
zio_checksum_info_t *ci = &zio_checksum_table[checksum];
zio_cksum_t actual_cksum, expected_cksum;
zio_eck_t eck;
int byteswap;
if (checksum >= ZIO_CHECKSUM_FUNCTIONS || ci->ci_func[0] == NULL)
return (SET_ERROR(EINVAL));
zio_checksum_template_init(checksum, spa);
if (ci->ci_flags & ZCHECKSUM_FLAG_EMBEDDED) {
zio_cksum_t verifier;
size_t eck_offset;
if (checksum == ZIO_CHECKSUM_ZILOG2) {
zil_chain_t zilc;
uint64_t nused;
abd_copy_to_buf(&zilc, abd, sizeof (zil_chain_t));
eck = zilc.zc_eck;
eck_offset = offsetof(zil_chain_t, zc_eck) +
offsetof(zio_eck_t, zec_cksum);
if (eck.zec_magic == ZEC_MAGIC) {
nused = zilc.zc_nused;
} else if (eck.zec_magic == BSWAP_64(ZEC_MAGIC)) {
nused = BSWAP_64(zilc.zc_nused);
} else {
return (SET_ERROR(ECKSUM));
}
if (nused > size) {
return (SET_ERROR(ECKSUM));
}
size = P2ROUNDUP_TYPED(nused, ZIL_MIN_BLKSZ, uint64_t);
} else {
eck_offset = size - sizeof (zio_eck_t);
abd_copy_to_buf_off(&eck, abd, eck_offset,
sizeof (zio_eck_t));
eck_offset += offsetof(zio_eck_t, zec_cksum);
}
if (checksum == ZIO_CHECKSUM_GANG_HEADER)
zio_checksum_gang_verifier(&verifier, bp);
else if (checksum == ZIO_CHECKSUM_LABEL)
zio_checksum_label_verifier(&verifier, offset);
else
verifier = bp->blk_cksum;
byteswap = (eck.zec_magic == BSWAP_64(ZEC_MAGIC));
if (byteswap)
byteswap_uint64_array(&verifier, sizeof (zio_cksum_t));
expected_cksum = eck.zec_cksum;
abd_copy_from_buf_off(abd, &verifier, eck_offset,
sizeof (zio_cksum_t));
ci->ci_func[byteswap](abd, size,
spa->spa_cksum_tmpls[checksum], &actual_cksum);
abd_copy_from_buf_off(abd, &expected_cksum, eck_offset,
sizeof (zio_cksum_t));
if (byteswap) {
byteswap_uint64_array(&expected_cksum,
sizeof (zio_cksum_t));
}
} else {
byteswap = BP_SHOULD_BYTESWAP(bp);
expected_cksum = bp->blk_cksum;
ci->ci_func[byteswap](abd, size,
spa->spa_cksum_tmpls[checksum], &actual_cksum);
}
/*
* MAC checksums are a special case since half of this checksum will
* actually be the encryption MAC. This will be verified by the
* decryption process, so we just check the truncated checksum now.
* Objset blocks use embedded MACs so we don't truncate the checksum
* for them.
*/
if (bp != NULL && BP_USES_CRYPT(bp) &&
BP_GET_TYPE(bp) != DMU_OT_OBJSET) {
if (!(ci->ci_flags & ZCHECKSUM_FLAG_DEDUP)) {
actual_cksum.zc_word[0] ^= actual_cksum.zc_word[2];
actual_cksum.zc_word[1] ^= actual_cksum.zc_word[3];
}
actual_cksum.zc_word[2] = 0;
actual_cksum.zc_word[3] = 0;
expected_cksum.zc_word[2] = 0;
expected_cksum.zc_word[3] = 0;
}
if (info != NULL) {
info->zbc_expected = expected_cksum;
info->zbc_actual = actual_cksum;
info->zbc_checksum_name = ci->ci_name;
info->zbc_byteswapped = byteswap;
info->zbc_injected = 0;
info->zbc_has_cksum = 1;
}
if (!ZIO_CHECKSUM_EQUAL(actual_cksum, expected_cksum))
return (SET_ERROR(ECKSUM));
return (0);
}
int
zio_checksum_error_impl(spa_t *spa, blkptr_t *bp, enum zio_checksum checksum,
abd_t *abd, uint64_t size, uint64_t offset, zio_bad_cksum_t *info)
{
zio_checksum_info_t *ci = &zio_checksum_table[checksum];
int byteswap;
zio_cksum_t actual_cksum, expected_cksum;
if (checksum >= ZIO_CHECKSUM_FUNCTIONS || ci->ci_func[0] == NULL)
return (SET_ERROR(EINVAL));
zio_checksum_template_init(checksum, spa);
if (ci->ci_flags & ZCHECKSUM_FLAG_EMBEDDED) {
zio_eck_t *eck;
zio_cksum_t verifier;
size_t eck_offset;
uint64_t data_size = size;
void *data = abd_borrow_buf_copy(abd, data_size);
if (checksum == ZIO_CHECKSUM_ZILOG2) {
zil_chain_t *zilc = data;
uint64_t nused;
eck = &zilc->zc_eck;
if (eck->zec_magic == ZEC_MAGIC) {
nused = zilc->zc_nused;
} else if (eck->zec_magic == BSWAP_64(ZEC_MAGIC)) {
nused = BSWAP_64(zilc->zc_nused);
} else {
abd_return_buf(abd, data, data_size);
return (SET_ERROR(ECKSUM));
}
if (nused > data_size) {
abd_return_buf(abd, data, data_size);
return (SET_ERROR(ECKSUM));
}
size = P2ROUNDUP_TYPED(nused, ZIL_MIN_BLKSZ, uint64_t);
} else {
eck = (zio_eck_t *)((char *)data + data_size) - 1;
}
if (checksum == ZIO_CHECKSUM_GANG_HEADER)
zio_checksum_gang_verifier(&verifier, bp);
else if (checksum == ZIO_CHECKSUM_LABEL)
zio_checksum_label_verifier(&verifier, offset);
else
verifier = bp->blk_cksum;
byteswap = (eck->zec_magic == BSWAP_64(ZEC_MAGIC));
if (byteswap)
byteswap_uint64_array(&verifier, sizeof (zio_cksum_t));
eck_offset = (size_t)(&eck->zec_cksum) - (size_t)data;
expected_cksum = eck->zec_cksum;
eck->zec_cksum = verifier;
abd_return_buf_copy(abd, data, data_size);
ci->ci_func[byteswap](abd, size,
spa->spa_cksum_tmpls[checksum], &actual_cksum);
abd_copy_from_buf_off(abd, &expected_cksum,
eck_offset, sizeof (zio_cksum_t));
if (byteswap) {
byteswap_uint64_array(&expected_cksum,
sizeof (zio_cksum_t));
}
} else {
byteswap = BP_SHOULD_BYTESWAP(bp);
expected_cksum = bp->blk_cksum;
ci->ci_func[byteswap](abd, size,
spa->spa_cksum_tmpls[checksum], &actual_cksum);
}
if (info != NULL) {
info->zbc_expected = expected_cksum;
info->zbc_actual = actual_cksum;
info->zbc_checksum_name = ci->ci_name;
info->zbc_byteswapped = byteswap;
info->zbc_injected = 0;
info->zbc_has_cksum = 1;
}
if (!ZIO_CHECKSUM_EQUAL(actual_cksum, expected_cksum))
return (SET_ERROR(ECKSUM));
return (0);
}
int
zio_checksum_error(zio_t *zio, zio_bad_cksum_t *info)
{
blkptr_t *bp = zio->io_bp;
uint_t checksum = (bp == NULL ? zio->io_prop.zp_checksum :
(BP_IS_GANG(bp) ? ZIO_CHECKSUM_GANG_HEADER : BP_GET_CHECKSUM(bp)));
int byteswap;
int error;
uint64_t size = (bp == NULL ? zio->io_size :
(BP_IS_GANG(bp) ? SPA_GANGBLOCKSIZE : BP_GET_PSIZE(bp)));
uint64_t offset = zio->io_offset;
void *data = zio->io_data;
zio_checksum_info_t *ci = &zio_checksum_table[checksum];
zio_cksum_t actual_cksum, expected_cksum, verifier;
if (checksum >= ZIO_CHECKSUM_FUNCTIONS || ci->ci_func[0] == NULL)
return (SET_ERROR(EINVAL));
if (ci->ci_eck) {
zio_eck_t *eck;
if (checksum == ZIO_CHECKSUM_ZILOG2) {
zil_chain_t *zilc = data;
uint64_t nused;
eck = &zilc->zc_eck;
if (eck->zec_magic == ZEC_MAGIC)
nused = zilc->zc_nused;
else if (eck->zec_magic == BSWAP_64(ZEC_MAGIC))
nused = BSWAP_64(zilc->zc_nused);
else
return (SET_ERROR(ECKSUM));
if (nused > size)
return (SET_ERROR(ECKSUM));
size = P2ROUNDUP_TYPED(nused, ZIL_MIN_BLKSZ, uint64_t);
} else {
eck = (zio_eck_t *)((char *)data + size) - 1;
}
if (checksum == ZIO_CHECKSUM_GANG_HEADER)
zio_checksum_gang_verifier(&verifier, bp);
else if (checksum == ZIO_CHECKSUM_LABEL)
zio_checksum_label_verifier(&verifier, offset);
else
verifier = bp->blk_cksum;
byteswap = (eck->zec_magic == BSWAP_64(ZEC_MAGIC));
if (byteswap)
byteswap_uint64_array(&verifier, sizeof (zio_cksum_t));
expected_cksum = eck->zec_cksum;
eck->zec_cksum = verifier;
ci->ci_func[byteswap](data, size, &actual_cksum);
eck->zec_cksum = expected_cksum;
if (byteswap)
byteswap_uint64_array(&expected_cksum,
sizeof (zio_cksum_t));
} else {
ASSERT(!BP_IS_GANG(bp));
byteswap = BP_SHOULD_BYTESWAP(bp);
expected_cksum = bp->blk_cksum;
ci->ci_func[byteswap](data, size, &actual_cksum);
}
info->zbc_expected = expected_cksum;
info->zbc_actual = actual_cksum;
info->zbc_checksum_name = ci->ci_name;
info->zbc_byteswapped = byteswap;
info->zbc_injected = 0;
info->zbc_has_cksum = 1;
/*
* Special case for truncated checksums with crypto MAC
* This may not be the best place to deal with this but it is here now.
*
* Words 0 and 1 and 32 bits of word 2 of the checksum are the
* first 160 bytes of SHA256 hash.
* The rest of words 2 and all of word 3 are the crypto MAC so
* ignore those because we can't check them until we do the decryption
* later, nor could we do them if the key wasn't present
*/
if (ci->ci_trunc) {
if (!(0 == (
(actual_cksum.zc_word[0] - expected_cksum.zc_word[0]) |
(actual_cksum.zc_word[1] - expected_cksum.zc_word[1]) |
(BF64_GET(actual_cksum.zc_word[2], 0, 32) -
BF64_GET(expected_cksum.zc_word[2], 0, 32))))) {
return (ECKSUM);
}
} else if (!ZIO_CHECKSUM_EQUAL(actual_cksum, expected_cksum)) {
return (SET_ERROR(ECKSUM));
}
if (zio_injection_enabled && !zio->io_error &&
(error = zio_handle_fault_injection(zio, ECKSUM)) != 0) {
info->zbc_injected = 1;
return (error);
}
return (0);
}
static void
zil_replay_log_record(zilog_t *zilog, lr_t *lr, void *zra, uint64_t claim_txg)
{
zil_replay_arg_t *zr = zra;
const zil_header_t *zh = zilog->zl_header;
uint64_t reclen = lr->lrc_reclen;
uint64_t txtype = lr->lrc_txtype;
char *name;
int pass, error;
if (!zilog->zl_replay) /* giving up */
return;
if (lr->lrc_txg < claim_txg) /* already committed */
return;
if (lr->lrc_seq <= zh->zh_replay_seq) /* already replayed */
return;
/* Strip case-insensitive bit, still present in log record */
txtype &= ~TX_CI;
if (txtype == 0 || txtype >= TX_MAX_TYPE) {
error = EINVAL;
goto bad;
}
/*
* Make a copy of the data so we can revise and extend it.
*/
bcopy(lr, zr->zr_lrbuf, reclen);
/*
* The log block containing this lr may have been byteswapped
* so that we can easily examine common fields like lrc_txtype.
* However, the log is a mix of different data types, and only the
* replay vectors know how to byteswap their records. Therefore, if
* the lr was byteswapped, undo it before invoking the replay vector.
*/
if (zr->zr_byteswap)
byteswap_uint64_array(zr->zr_lrbuf, reclen);
/*
* If this is a TX_WRITE with a blkptr, suck in the data.
*/
if (txtype == TX_WRITE && reclen == sizeof (lr_write_t)) {
lr_write_t *lrw = (lr_write_t *)lr;
blkptr_t *wbp = &lrw->lr_blkptr;
uint64_t wlen = lrw->lr_length;
char *wbuf = zr->zr_lrbuf + reclen;
if (BP_IS_HOLE(wbp)) { /* compressed to a hole */
bzero(wbuf, wlen);
} else {
/*
* A subsequent write may have overwritten this block,
* in which case wbp may have been been freed and
* reallocated, and our read of wbp may fail with a
* checksum error. We can safely ignore this because
* the later write will provide the correct data.
*/
zbookmark_t zb;
zb.zb_objset = dmu_objset_id(zilog->zl_os);
zb.zb_object = lrw->lr_foid;
zb.zb_level = -1;
zb.zb_blkid = lrw->lr_offset / BP_GET_LSIZE(wbp);
(void) zio_wait(zio_read(NULL, zilog->zl_spa,
wbp, wbuf, BP_GET_LSIZE(wbp), NULL, NULL,
ZIO_PRIORITY_SYNC_READ,
ZIO_FLAG_CANFAIL | ZIO_FLAG_SPECULATIVE, &zb));
(void) memmove(wbuf, wbuf + lrw->lr_blkoff, wlen);
}
}
/*
* We must now do two things atomically: replay this log record,
* and update the log header sequence number to reflect the fact that
* we did so. At the end of each replay function the sequence number
* is updated if we are in replay mode.
*/
for (pass = 1; pass <= 2; pass++) {
zilog->zl_replaying_seq = lr->lrc_seq;
/* Only byteswap (if needed) on the 1st pass. */
error = zr->zr_replay[txtype](zr->zr_arg, zr->zr_lrbuf,
zr->zr_byteswap && pass == 1);
if (!error)
return;
/*
* The DMU's dnode layer doesn't see removes until the txg
* commits, so a subsequent claim can spuriously fail with
* EEXIST. So if we receive any error we try syncing out
* any removes then retry the transaction.
*/
if (pass == 1)
txg_wait_synced(spa_get_dsl(zilog->zl_spa), 0);
}
bad:
ASSERT(error);
name = kmem_alloc(MAXNAMELEN, KM_SLEEP);
dmu_objset_name(zr->zr_os, name);
cmn_err(CE_WARN, "ZFS replay transaction error %d, "
"dataset %s, seq 0x%llx, txtype %llu %s\n",
error, name, (u_longlong_t)lr->lrc_seq, (u_longlong_t)txtype,
(lr->lrc_txtype & TX_CI) ? "CI" : "");
zilog->zl_replay = B_FALSE;
kmem_free(name, MAXNAMELEN);
}
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);
}
static int
zfs_replay_rename(zfsvfs_t *zfsvfs, 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;
struct componentname scn, tcn;
vnode_t *svp, *tvp;
kthread_t *td = curthread;
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;
svp = tvp = NULL;
scn.cn_nameptr = sname;
scn.cn_namelen = strlen(sname);
scn.cn_nameiop = DELETE;
scn.cn_flags = ISLASTCN | SAVENAME;
scn.cn_lkflags = LK_EXCLUSIVE | LK_RETRY;
scn.cn_cred = kcred;
scn.cn_thread = td;
vn_lock(ZTOV(sdzp), LK_EXCLUSIVE | LK_RETRY);
error = VOP_LOOKUP(ZTOV(sdzp), &svp, &scn);
VOP_UNLOCK(ZTOV(sdzp), 0);
if (error != 0)
goto fail;
VOP_UNLOCK(svp, 0);
tcn.cn_nameptr = tname;
tcn.cn_namelen = strlen(tname);
tcn.cn_nameiop = RENAME;
tcn.cn_flags = ISLASTCN | SAVENAME;
tcn.cn_lkflags = LK_EXCLUSIVE | LK_RETRY;
tcn.cn_cred = kcred;
tcn.cn_thread = td;
vn_lock(ZTOV(tdzp), LK_EXCLUSIVE | LK_RETRY);
error = VOP_LOOKUP(ZTOV(tdzp), &tvp, &tcn);
if (error == EJUSTRETURN)
tvp = NULL;
else if (error != 0) {
VOP_UNLOCK(ZTOV(tdzp), 0);
goto fail;
}
error = VOP_RENAME(ZTOV(sdzp), svp, &scn, ZTOV(tdzp), tvp, &tcn /*,vflg*/);
return (error);
fail:
if (svp != NULL)
vrele(svp);
if (tvp != NULL)
vrele(tvp);
VN_RELE(ZTOV(tdzp));
VN_RELE(ZTOV(sdzp));
return (error);
}
static int
zfs_replay_write(void *arg1, char *arg2, boolean_t byteswap)
{
zfsvfs_t *zfsvfs = (zfsvfs_t *)arg1;
lr_write_t *lr = (lr_write_t *)arg2;
char *data = (char *)(lr + 1); /* data follows lr_write_t */
znode_t *zp;
int error;
#ifndef LINUX_PORT
ssize_t resid;
#else
uio_t uio;
int vflg = 0;
struct iovec iov;
#endif
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);
}
#ifndef LINUX_PORT
offset = lr->lr_offset;
length = lr->lr_length;
iov.iov_base = (void *) data;
iov.iov_len = lr->lr_length;
/* 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 zfsvfs->z_replay_eof
*/
zfsvfs->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)
zfsvfs->z_replay_eof = eod;
}
error = vn_rdwr(UIO_WRITE, ZTOV(zp), data, length, offset,
UIO_SYSSPACE, 0, RLIM64_INFINITY, kcred, &resid);
#else
iov.iov_base = (void *) data;
iov.iov_len = lr->lr_length;
uio.uio_iov = &iov;
uio.uio_resid = lr->lr_length;
uio.uio_iovcnt = 1;
uio.uio_loffset = (offset_t)lr->lr_offset;
uio.uio_limit = MAXOFFSET_T;
uio.uio_segflg = UIO_SYSSPACE;
error = VOP_WRITE(ZTOV(zp), &uio, vflg, NULL , NULL);
#endif
VN_RELE(ZTOV(zp));
zfsvfs->z_replay_eof = 0; /* safety */
return (error);
}
