/*
* Handles TX_SYMLINK transactions.
*/
void
zfs_log_symlink(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
znode_t *dzp, znode_t *zp, char *name, char *link)
{
itx_t *itx;
lr_create_t *lr;
size_t namesize = strlen(name) + 1;
size_t linksize = strlen(link) + 1;
if (zil_replaying(zilog, tx))
return;
itx = zil_itx_create(txtype, sizeof (*lr) + namesize + linksize);
lr = (lr_create_t *)&itx->itx_lr;
lr->lr_doid = dzp->z_id;
lr->lr_foid = zp->z_id;
lr->lr_uid = zp->z_uid;
lr->lr_gid = zp->z_gid;
lr->lr_mode = zp->z_mode;
(void) sa_lookup(zp->z_sa_hdl, SA_ZPL_GEN(ZTOZSB(zp)), &lr->lr_gen,
sizeof (uint64_t));
(void) sa_lookup(zp->z_sa_hdl, SA_ZPL_CRTIME(ZTOZSB(zp)),
lr->lr_crtime, sizeof (uint64_t) * 2);
bcopy(name, (char *)(lr + 1), namesize);
bcopy(link, (char *)(lr + 1) + namesize, linksize);
zil_itx_assign(zilog, itx, tx);
}
/*
* zfs_log_create() is used to handle TX_CREATE, TX_MKDIR and TX_MKXATTR
* transactions.
*/
void
zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, int txtype,
znode_t *dzp, znode_t *zp, char *name)
{
itx_t *itx;
uint64_t seq;
lr_create_t *lr;
size_t namesize = strlen(name) + 1;
if (zilog == NULL)
return;
itx = zil_itx_create(txtype, sizeof (*lr) + namesize);
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;
lr->lr_uid = zp->z_phys->zp_uid;
lr->lr_gid = zp->z_phys->zp_gid;
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;
bcopy(name, (char *)(lr + 1), namesize);
seq = zil_itx_assign(zilog, itx, tx);
dzp->z_last_itx = seq;
zp->z_last_itx = seq;
}
/*
* zfs_log_rename() handles TX_RENAME transactions.
*/
void
zfs_log_rename(zilog_t *zilog, dmu_tx_t *tx, int txtype,
znode_t *sdzp, char *sname, znode_t *tdzp, char *dname, znode_t *szp)
{
itx_t *itx;
uint64_t seq;
lr_rename_t *lr;
size_t snamesize = strlen(sname) + 1;
size_t dnamesize = strlen(dname) + 1;
if (zilog == NULL)
return;
itx = zil_itx_create(txtype, sizeof (*lr) + snamesize + dnamesize);
lr = (lr_rename_t *)&itx->itx_lr;
lr->lr_sdoid = sdzp->z_id;
lr->lr_tdoid = tdzp->z_id;
bcopy(sname, (char *)(lr + 1), snamesize);
bcopy(dname, (char *)(lr + 1) + snamesize, dnamesize);
seq = zil_itx_assign(zilog, itx, tx);
sdzp->z_last_itx = seq;
tdzp->z_last_itx = seq;
szp->z_last_itx = seq;
}
/*
* zfs_log_symlink() handles TX_SYMLINK transactions.
*/
void
zfs_log_symlink(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
znode_t *dzp, znode_t *zp, char *name, char *link)
{
itx_t *itx;
uint64_t seq;
lr_create_t *lr;
size_t namesize = strlen(name) + 1;
size_t linksize = strlen(link) + 1;
if (zil_replaying(zilog, tx))
return;
itx = zil_itx_create(txtype, sizeof (*lr) + namesize + linksize);
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;
lr->lr_uid = zp->z_phys->zp_uid;
lr->lr_gid = zp->z_phys->zp_gid;
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];
bcopy(name, (char *)(lr + 1), namesize);
bcopy(link, (char *)(lr + 1) + namesize, linksize);
seq = zil_itx_assign(zilog, itx, tx);
dzp->z_last_itx = seq;
zp->z_last_itx = seq;
}
/*
* Handles TX_SETATTR transactions.
*/
void
zfs_log_setattr(zilog_t *zilog, dmu_tx_t *tx, int txtype,
znode_t *zp, vattr_t *vap, uint_t mask_applied, zfs_fuid_info_t *fuidp)
{
itx_t *itx;
lr_setattr_t *lr;
xvattr_t *xvap = (xvattr_t *)vap;
size_t recsize = sizeof (lr_setattr_t);
void *start;
if (zil_replaying(zilog, tx) || zp->z_unlinked)
return;
/*
* If XVATTR set, then log record size needs to allow
* for lr_attr_t + xvattr mask, mapsize and create time
* plus actual attribute values
*/
if (vap->va_mask & AT_XVATTR)
recsize = sizeof (*lr) + ZIL_XVAT_SIZE(xvap->xva_mapsize);
if (fuidp)
recsize += fuidp->z_domain_str_sz;
itx = zil_itx_create(txtype, recsize);
lr = (lr_setattr_t *)&itx->itx_lr;
lr->lr_foid = zp->z_id;
lr->lr_mask = (uint64_t)mask_applied;
lr->lr_mode = (uint64_t)vap->va_mode;
if ((mask_applied & AT_UID) && IS_EPHEMERAL(vap->va_uid))
lr->lr_uid = fuidp->z_fuid_owner;
else
lr->lr_uid = (uint64_t)vap->va_uid;
if ((mask_applied & AT_GID) && IS_EPHEMERAL(vap->va_gid))
lr->lr_gid = fuidp->z_fuid_group;
else
lr->lr_gid = (uint64_t)vap->va_gid;
lr->lr_size = (uint64_t)vap->va_size;
ZFS_TIME_ENCODE(&vap->va_atime, lr->lr_atime);
ZFS_TIME_ENCODE(&vap->va_mtime, lr->lr_mtime);
start = (lr_setattr_t *)(lr + 1);
if (vap->va_mask & AT_XVATTR) {
zfs_log_xvattr((lr_attr_t *)start, xvap);
start = (caddr_t)start + ZIL_XVAT_SIZE(xvap->xva_mapsize);
}
/*
* Now stick on domain information if any on end
*/
if (fuidp)
(void) zfs_log_fuid_domains(fuidp, start);
itx->itx_sync = (zp->z_sync_cnt != 0);
zil_itx_assign(zilog, itx, tx);
}
/*
* Handles TX_TRUNCATE transactions.
*/
void
zfs_log_truncate(zilog_t *zilog, dmu_tx_t *tx, int txtype,
znode_t *zp, uint64_t off, uint64_t len)
{
itx_t *itx;
lr_truncate_t *lr;
if (zil_replaying(zilog, tx) || zp->z_unlinked)
return;
itx = zil_itx_create(txtype, sizeof (*lr));
lr = (lr_truncate_t *)&itx->itx_lr;
lr->lr_foid = zp->z_id;
lr->lr_offset = off;
lr->lr_length = len;
itx->itx_sync = (zp->z_sync_cnt != 0);
zil_itx_assign(zilog, itx, tx);
}
/*
* Handles TX_LINK transactions.
*/
void
zfs_log_link(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
znode_t *dzp, znode_t *zp, char *name)
{
itx_t *itx;
lr_link_t *lr;
size_t namesize = strlen(name) + 1;
if (zil_replaying(zilog, tx))
return;
itx = zil_itx_create(txtype, sizeof (*lr) + namesize);
lr = (lr_link_t *)&itx->itx_lr;
lr->lr_doid = dzp->z_id;
lr->lr_link_obj = zp->z_id;
bcopy(name, (char *)(lr + 1), namesize);
zil_itx_assign(zilog, itx, tx);
}
/*
* Log a DKIOCFREE/free-long-range to the ZIL with TX_TRUNCATE.
*/
static void
zvol_log_truncate(zvol_state_t *zv, dmu_tx_t *tx, uint64_t off, uint64_t len,
boolean_t sync)
{
itx_t *itx;
lr_truncate_t *lr;
zilog_t *zilog = zv->zv_zilog;
if (zil_replaying(zilog, tx))
return;
itx = zil_itx_create(TX_TRUNCATE, sizeof (*lr));
lr = (lr_truncate_t *)&itx->itx_lr;
lr->lr_foid = ZVOL_OBJ;
lr->lr_offset = off;
lr->lr_length = len;
itx->itx_sync = sync;
zil_itx_assign(zilog, itx, tx);
}
/*
* Handles both TX_REMOVE and TX_RMDIR transactions.
*/
void
zfs_log_remove(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
znode_t *dzp, char *name, uint64_t foid)
{
itx_t *itx;
lr_remove_t *lr;
size_t namesize = strlen(name) + 1;
if (zil_replaying(zilog, tx) || zfs_xattr_owner_unlinked(dzp))
return;
itx = zil_itx_create(txtype, sizeof (*lr) + namesize);
lr = (lr_remove_t *)&itx->itx_lr;
lr->lr_doid = dzp->z_id;
bcopy(name, (char *)(lr + 1), namesize);
itx->itx_oid = foid;
zil_itx_assign(zilog, itx, tx);
}
/*
* zfs_log_remove() handles both TX_REMOVE and TX_RMDIR transactions.
*/
void
zfs_log_remove(zilog_t *zilog, dmu_tx_t *tx, int txtype,
znode_t *dzp, char *name)
{
itx_t *itx;
uint64_t seq;
lr_remove_t *lr;
size_t namesize = strlen(name) + 1;
if (zilog == NULL)
return;
itx = zil_itx_create(txtype, sizeof (*lr) + namesize);
lr = (lr_remove_t *)&itx->itx_lr;
lr->lr_doid = dzp->z_id;
bcopy(name, (char *)(lr + 1), namesize);
seq = zil_itx_assign(zilog, itx, tx);
dzp->z_last_itx = seq;
}
/*
* zfs_log_link() handles TX_LINK transactions.
*/
void
zfs_log_link(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
znode_t *dzp, znode_t *zp, char *name)
{
itx_t *itx;
uint64_t seq;
lr_link_t *lr;
size_t namesize = strlen(name) + 1;
if (zilog == NULL)
return;
ZFS_HANDLE_REPLAY(zilog, tx); /* exits if replay */
itx = zil_itx_create(txtype, sizeof (*lr) + namesize);
lr = (lr_link_t *)&itx->itx_lr;
lr->lr_doid = dzp->z_id;
lr->lr_link_obj = zp->z_id;
bcopy(name, (char *)(lr + 1), namesize);
seq = zil_itx_assign(zilog, itx, tx);
dzp->z_last_itx = seq;
zp->z_last_itx = seq;
}
static void
zvol_log_write(zvol_state_t *zv, dmu_tx_t *tx, uint64_t offset,
uint64_t size, int sync)
{
uint32_t blocksize = zv->zv_volblocksize;
zilog_t *zilog = zv->zv_zilog;
boolean_t slogging;
ssize_t immediate_write_sz;
if (zil_replaying(zilog, tx))
return;
immediate_write_sz = (zilog->zl_logbias == ZFS_LOGBIAS_THROUGHPUT)
? 0 : zvol_immediate_write_sz;
slogging = spa_has_slogs(zilog->zl_spa) &&
(zilog->zl_logbias == ZFS_LOGBIAS_LATENCY);
while (size) {
itx_t *itx;
lr_write_t *lr;
ssize_t len;
itx_wr_state_t write_state;
/*
* Unlike zfs_log_write() we can be called with
* up to DMU_MAX_ACCESS/2 (5MB) writes.
*/
if (blocksize > immediate_write_sz && !slogging &&
size >= blocksize && offset % blocksize == 0) {
write_state = WR_INDIRECT; /* uses dmu_sync */
len = blocksize;
} else if (sync) {
write_state = WR_COPIED;
len = MIN(ZIL_MAX_LOG_DATA, size);
} else {
write_state = WR_NEED_COPY;
len = MIN(ZIL_MAX_LOG_DATA, size);
}
itx = zil_itx_create(TX_WRITE, sizeof (*lr) +
(write_state == WR_COPIED ? len : 0));
lr = (lr_write_t *)&itx->itx_lr;
if (write_state == WR_COPIED && dmu_read(zv->zv_objset,
ZVOL_OBJ, offset, len, lr+1, DMU_READ_NO_PREFETCH) != 0) {
zil_itx_destroy(itx);
itx = zil_itx_create(TX_WRITE, sizeof (*lr));
lr = (lr_write_t *)&itx->itx_lr;
write_state = WR_NEED_COPY;
}
itx->itx_wr_state = write_state;
if (write_state == WR_NEED_COPY)
itx->itx_sod += len;
lr->lr_foid = ZVOL_OBJ;
lr->lr_offset = offset;
lr->lr_length = len;
lr->lr_blkoff = 0;
BP_ZERO(&lr->lr_blkptr);
itx->itx_private = zv;
itx->itx_sync = sync;
(void) zil_itx_assign(zilog, itx, tx);
offset += len;
size -= len;
}
}
/*
* Handles TX_ACL transactions.
*/
void
zfs_log_acl(zilog_t *zilog, dmu_tx_t *tx, znode_t *zp,
vsecattr_t *vsecp, zfs_fuid_info_t *fuidp)
{
itx_t *itx;
lr_acl_v0_t *lrv0;
lr_acl_t *lr;
int txtype;
int lrsize;
size_t txsize;
size_t aclbytes = vsecp->vsa_aclentsz;
if (zil_replaying(zilog, tx) || zp->z_unlinked)
return;
txtype = (zp->z_zfsvfs->z_version < ZPL_VERSION_FUID) ?
TX_ACL_V0 : TX_ACL;
if (txtype == TX_ACL)
lrsize = sizeof (*lr);
else
lrsize = sizeof (*lrv0);
txsize = lrsize +
((txtype == TX_ACL) ? ZIL_ACE_LENGTH(aclbytes) : aclbytes) +
(fuidp ? fuidp->z_domain_str_sz : 0) +
sizeof (uint64_t) * (fuidp ? fuidp->z_fuid_cnt : 0);
itx = zil_itx_create(txtype, txsize);
lr = (lr_acl_t *)&itx->itx_lr;
lr->lr_foid = zp->z_id;
if (txtype == TX_ACL) {
lr->lr_acl_bytes = aclbytes;
lr->lr_domcnt = fuidp ? fuidp->z_domain_cnt : 0;
lr->lr_fuidcnt = fuidp ? fuidp->z_fuid_cnt : 0;
if (vsecp->vsa_mask & VSA_ACE_ACLFLAGS)
lr->lr_acl_flags = (uint64_t)vsecp->vsa_aclflags;
else
lr->lr_acl_flags = 0;
}
lr->lr_aclcnt = (uint64_t)vsecp->vsa_aclcnt;
if (txtype == TX_ACL_V0) {
lrv0 = (lr_acl_v0_t *)lr;
bcopy(vsecp->vsa_aclentp, (ace_t *)(lrv0 + 1), aclbytes);
} else {
void *start = (ace_t *)(lr + 1);
bcopy(vsecp->vsa_aclentp, start, aclbytes);
start = (caddr_t)start + ZIL_ACE_LENGTH(aclbytes);
if (fuidp) {
start = zfs_log_fuid_ids(fuidp, start);
(void) zfs_log_fuid_domains(fuidp, start);
}
}
itx->itx_sync = (zp->z_sync_cnt != 0);
zil_itx_assign(zilog, itx, tx);
}
void
zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
znode_t *zp, offset_t off, ssize_t resid, int ioflag)
{
itx_wr_state_t write_state;
boolean_t slogging;
uintptr_t fsync_cnt;
if (zilog == NULL || zp->z_unlinked)
return;
/*
* Writes are handled in three different ways:
*
* WR_INDIRECT:
* If the write is greater than zfs_immediate_write_sz and there are
* no separate logs in this pool then later *if* we need to log the
* write then dmu_sync() is used to immediately write the block and
* its block pointer is put in the log record.
* WR_COPIED:
* If we know we'll immediately be committing the
* transaction (FDSYNC (O_DSYNC)), the we allocate a larger
* log record here for the data and copy the data in.
* WR_NEED_COPY:
* Otherwise we don't allocate a buffer, and *if* we need to
* flush the write later then a buffer is allocated and
* we retrieve the data using the dmu.
*/
slogging = spa_has_slogs(zilog->zl_spa);
if (resid > zfs_immediate_write_sz && !slogging)
write_state = WR_INDIRECT;
else if (ioflag & FDSYNC)
write_state = WR_COPIED;
else
write_state = WR_NEED_COPY;
#ifndef __APPLE__
if ((fsync_cnt = (uintptr_t)tsd_get(zfs_fsyncer_key)) != 0) {
(void) tsd_set(zfs_fsyncer_key, (void *)(fsync_cnt - 1));
}
#endif
while (resid) {
itx_t *itx;
lr_write_t *lr;
ssize_t len;
/*
* If there are slogs and the write would overflow the largest
* block, then because we don't want to use the main pool
* to dmu_sync, we have to split the write.
*/
if (slogging && resid > ZIL_MAX_LOG_DATA)
len = SPA_MAXBLOCKSIZE >> 1;
else
len = resid;
itx = zil_itx_create(txtype, sizeof (*lr) +
(write_state == WR_COPIED ? len : 0));
lr = (lr_write_t *)&itx->itx_lr;
if (write_state == WR_COPIED && dmu_read(zp->z_zfsvfs->z_os,
zp->z_id, off, len, lr + 1) != 0) {
kmem_free(itx, offsetof(itx_t, itx_lr) +
itx->itx_lr.lrc_reclen);
itx = zil_itx_create(txtype, sizeof (*lr));
lr = (lr_write_t *)&itx->itx_lr;
write_state = WR_NEED_COPY;
}
itx->itx_wr_state = write_state;
lr->lr_foid = zp->z_id;
lr->lr_offset = off;
lr->lr_length = len;
lr->lr_blkoff = 0;
BP_ZERO(&lr->lr_blkptr);
itx->itx_private = zp->z_zfsvfs;
if ((zp->z_sync_cnt != 0) || (fsync_cnt != 0))
itx->itx_sync = B_TRUE;
else
itx->itx_sync = B_FALSE;
zp->z_last_itx = zil_itx_assign(zilog, itx, tx);
off += len;
resid -= len;
}
void
zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
znode_t *zp, offset_t off, ssize_t resid, int ioflag)
{
itx_wr_state_t write_state;
boolean_t slogging;
uintptr_t fsync_cnt;
if (zilog == NULL || zp->z_unlinked)
return;
ZFS_HANDLE_REPLAY(zilog, tx); /* exits if replay */
slogging = spa_has_slogs(zilog->zl_spa);
if (resid > zfs_immediate_write_sz && !slogging && resid <= zp->z_blksz)
write_state = WR_INDIRECT;
else if (ioflag & (FSYNC | FDSYNC))
write_state = WR_COPIED;
else
write_state = WR_NEED_COPY;
if ((fsync_cnt = (uintptr_t)tsd_get(zfs_fsyncer_key)) != 0) {
(void) tsd_set(zfs_fsyncer_key, (void *)(fsync_cnt - 1));
}
while (resid) {
itx_t *itx;
lr_write_t *lr;
ssize_t len;
/*
* If the write would overflow the largest block then split it.
*/
if (write_state != WR_INDIRECT && resid > ZIL_MAX_LOG_DATA)
len = SPA_MAXBLOCKSIZE >> 1;
else
len = resid;
itx = zil_itx_create(txtype, sizeof (*lr) +
(write_state == WR_COPIED ? len : 0));
lr = (lr_write_t *)&itx->itx_lr;
if (write_state == WR_COPIED && dmu_read(zp->z_zfsvfs->z_os,
zp->z_id, off, len, lr + 1, DMU_READ_NO_PREFETCH) != 0) {
kmem_free(itx, offsetof(itx_t, itx_lr) +
itx->itx_lr.lrc_reclen);
itx = zil_itx_create(txtype, sizeof (*lr));
lr = (lr_write_t *)&itx->itx_lr;
write_state = WR_NEED_COPY;
}
itx->itx_wr_state = write_state;
if (write_state == WR_NEED_COPY)
itx->itx_sod += len;
lr->lr_foid = zp->z_id;
lr->lr_offset = off;
lr->lr_length = len;
lr->lr_blkoff = 0;
BP_ZERO(&lr->lr_blkptr);
itx->itx_private = zp->z_zfsvfs;
if ((zp->z_sync_cnt != 0) || (fsync_cnt != 0) ||
(ioflag & (FSYNC | FDSYNC)))
itx->itx_sync = B_TRUE;
else
itx->itx_sync = B_FALSE;
zp->z_last_itx = zil_itx_assign(zilog, itx, tx);
off += len;
resid -= len;
}
/*
* Handles TX_CREATE, TX_CREATE_ATTR, TX_MKDIR, TX_MKDIR_ATTR and
* TK_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;
lr_create_t *lr;
lr_acl_create_t *lracl;
size_t aclsize = 0;
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 (zil_replaying(zilog, tx))
return;
/*
* 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 & ATTR_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 {
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_mode;
if (!IS_EPHEMERAL(zp->z_uid)) {
lr->lr_uid = (uint64_t)zp->z_uid;
} else {
lr->lr_uid = fuidp->z_fuid_owner;
}
if (!IS_EPHEMERAL(zp->z_gid)) {
lr->lr_gid = (uint64_t)zp->z_gid;
} else {
lr->lr_gid = fuidp->z_fuid_group;
}
(void) sa_lookup(zp->z_sa_hdl, SA_ZPL_GEN(ZTOZSB(zp)), &lr->lr_gen,
sizeof (uint64_t));
(void) sa_lookup(zp->z_sa_hdl, SA_ZPL_CRTIME(ZTOZSB(zp)),
lr->lr_crtime, sizeof (uint64_t) * 2);
if (sa_lookup(zp->z_sa_hdl, SA_ZPL_RDEV(ZTOZSB(zp)), &lr->lr_rdev,
sizeof (lr->lr_rdev)) != 0)
lr->lr_rdev = 0;
/*
* Fill in xvattr info if any
*/
if (vap->va_mask & ATTR_XVATTR) {
zfs_log_xvattr((lr_attr_t *)((caddr_t)lr + lrsize), xvap);
end = (caddr_t)lr + lrsize + xvatsize;
} else {
end = (caddr_t)lr + lrsize;
}
/* Now fill in any ACL info */
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);
}
/*
* Now place file name in log record
*/
bcopy(name, end, namesize);
zil_itx_assign(zilog, itx, tx);
}
int
zvol_log_write(zvol_state_t *zv, dmu_tx_t *tx, offset_t off, ssize_t len,
char *addr)
{
dmu_object_info_t doi;
ssize_t nbytes;
itx_t *itx;
lr_write_t *lr;
objset_t *os;
dmu_buf_t *db;
uint64_t txg;
uint64_t boff;
int error;
uint32_t blocksize;
/* handle common case */
if (len <= zvol_immediate_write_sz) {
itx = zvol_immediate_itx(off, len, addr);
(void) zil_itx_assign(zv->zv_zilog, itx, tx);
return (0);
}
txg = dmu_tx_get_txg(tx);
os = zv->zv_objset;
/*
* We need to dmu_sync() each block in the range.
* For this we need the blocksize.
*/
error = dmu_object_info(os, ZVOL_OBJ, &doi);
if (error)
return (error);
blocksize = doi.doi_data_block_size;
/*
* We need to immediate write or dmu_sync() each block in the range.
*/
while (len) {
nbytes = MIN(len, blocksize - P2PHASE(off, blocksize));
if (nbytes <= zvol_immediate_write_sz) {
itx = zvol_immediate_itx(off, nbytes, addr);
} else {
boff = P2ALIGN_TYPED(off, blocksize, uint64_t);
itx = zil_itx_create(TX_WRITE, sizeof (*lr));
lr = (lr_write_t *)&itx->itx_lr;
lr->lr_foid = ZVOL_OBJ;
lr->lr_offset = off;
lr->lr_length = nbytes;
lr->lr_blkoff = off - boff;
BP_ZERO(&lr->lr_blkptr);
/* XXX - we should do these IOs in parallel */
VERIFY(0 == dmu_buf_hold(os, ZVOL_OBJ, boff,
FTAG, &db));
ASSERT(boff == db->db_offset);
error = dmu_sync(NULL, db, &lr->lr_blkptr,
txg, NULL, NULL);
dmu_buf_rele(db, FTAG);
if (error) {
kmem_free(itx, offsetof(itx_t, itx_lr));
return (error);
}
itx->itx_wr_state = WR_COPIED;
}
(void) zil_itx_assign(zv->zv_zilog, itx, tx);
len -= nbytes;
off += nbytes;
}
return (0);
}
void
zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
znode_t *zp, offset_t off, ssize_t resid, int ioflag)
{
uint32_t blocksize = zp->z_blksz;
itx_wr_state_t write_state;
uintptr_t fsync_cnt;
if (zil_replaying(zilog, tx) || zp->z_unlinked)
return;
if (zilog->zl_logbias == ZFS_LOGBIAS_THROUGHPUT)
write_state = WR_INDIRECT;
else if (!spa_has_slogs(zilog->zl_spa) &&
resid >= zfs_immediate_write_sz)
write_state = WR_INDIRECT;
else if (ioflag & (FSYNC | FDSYNC))
write_state = WR_COPIED;
else
write_state = WR_NEED_COPY;
if ((fsync_cnt = (uintptr_t)tsd_get(zfs_fsyncer_key)) != 0) {
(void) tsd_set(zfs_fsyncer_key, (void *)(fsync_cnt - 1));
}
while (resid) {
itx_t *itx;
lr_write_t *lr;
itx_wr_state_t wr_state = write_state;
ssize_t len = resid;
if (wr_state == WR_COPIED && resid > ZIL_MAX_COPIED_DATA)
wr_state = WR_NEED_COPY;
else if (wr_state == WR_INDIRECT)
len = MIN(blocksize - P2PHASE(off, blocksize), resid);
itx = zil_itx_create(txtype, sizeof (*lr) +
(wr_state == WR_COPIED ? len : 0));
lr = (lr_write_t *)&itx->itx_lr;
if (wr_state == WR_COPIED && dmu_read(zp->z_zfsvfs->z_os,
zp->z_id, off, len, lr + 1, DMU_READ_NO_PREFETCH) != 0) {
zil_itx_destroy(itx);
itx = zil_itx_create(txtype, sizeof (*lr));
lr = (lr_write_t *)&itx->itx_lr;
wr_state = WR_NEED_COPY;
}
itx->itx_wr_state = wr_state;
lr->lr_foid = zp->z_id;
lr->lr_offset = off;
lr->lr_length = len;
lr->lr_blkoff = 0;
BP_ZERO(&lr->lr_blkptr);
itx->itx_private = zp->z_zfsvfs;
if (!(ioflag & (FSYNC | FDSYNC)) && (zp->z_sync_cnt == 0) &&
(fsync_cnt == 0))
itx->itx_sync = B_FALSE;
zil_itx_assign(zilog, itx, tx);
off += len;
resid -= len;
}
}
void
zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
znode_t *zp, offset_t off, ssize_t resid, int ioflag,
zil_callback_t callback, void *callback_data)
{
itx_wr_state_t write_state;
boolean_t slogging;
uintptr_t fsync_cnt;
ssize_t immediate_write_sz;
if (zil_replaying(zilog, tx) || zp->z_unlinked) {
if (callback != NULL)
callback(callback_data);
return;
}
immediate_write_sz = (zilog->zl_logbias == ZFS_LOGBIAS_THROUGHPUT)
? 0 : (ssize_t)zfs_immediate_write_sz;
slogging = spa_has_slogs(zilog->zl_spa) &&
(zilog->zl_logbias == ZFS_LOGBIAS_LATENCY);
if (resid > immediate_write_sz && !slogging && resid <= zp->z_blksz)
write_state = WR_INDIRECT;
else if (ioflag & (FSYNC | FDSYNC))
write_state = WR_COPIED;
else
write_state = WR_NEED_COPY;
if ((fsync_cnt = (uintptr_t)tsd_get(zfs_fsyncer_key)) != 0) {
(void) tsd_set(zfs_fsyncer_key, (void *)(fsync_cnt - 1));
}
while (resid) {
itx_t *itx;
lr_write_t *lr;
ssize_t len;
/*
* If the write would overflow the largest block then split it.
*/
if (write_state != WR_INDIRECT && resid > ZIL_MAX_LOG_DATA)
len = SPA_MAXBLOCKSIZE >> 1;
else
len = resid;
itx = zil_itx_create(txtype, sizeof (*lr) +
(write_state == WR_COPIED ? len : 0));
lr = (lr_write_t *)&itx->itx_lr;
if (write_state == WR_COPIED && dmu_read(ZTOZSB(zp)->z_os,
zp->z_id, off, len, lr + 1, DMU_READ_NO_PREFETCH) != 0) {
zil_itx_destroy(itx);
itx = zil_itx_create(txtype, sizeof (*lr));
lr = (lr_write_t *)&itx->itx_lr;
write_state = WR_NEED_COPY;
}
itx->itx_wr_state = write_state;
if (write_state == WR_NEED_COPY)
itx->itx_sod += len;
lr->lr_foid = zp->z_id;
lr->lr_offset = off;
lr->lr_length = len;
lr->lr_blkoff = 0;
BP_ZERO(&lr->lr_blkptr);
itx->itx_private = ZTOZSB(zp);
if (!(ioflag & (FSYNC | FDSYNC)) && (zp->z_sync_cnt == 0) &&
(fsync_cnt == 0))
itx->itx_sync = B_FALSE;
itx->itx_callback = callback;
itx->itx_callback_data = callback_data;
zil_itx_assign(zilog, itx, tx);
off += len;
resid -= len;
}
/*
* 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;
}
