2008-11-20 20:01:55 +00:00
|
|
|
/*
|
|
|
|
* CDDL HEADER START
|
|
|
|
*
|
|
|
|
* The contents of this file are subject to the terms of the
|
|
|
|
* Common Development and Distribution License (the "License").
|
|
|
|
* You may not use this file except in compliance with the License.
|
|
|
|
*
|
|
|
|
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
|
|
|
|
* or http://www.opensolaris.org/os/licensing.
|
|
|
|
* See the License for the specific language governing permissions
|
|
|
|
* and limitations under the License.
|
|
|
|
*
|
|
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
|
|
*
|
|
|
|
* CDDL HEADER END
|
|
|
|
*/
|
|
|
|
/*
|
2010-08-26 21:24:34 +00:00
|
|
|
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
|
2012-09-13 20:25:15 +00:00
|
|
|
* Copyright (c) 2012 Cyril Plisko. All rights reserved.
|
2013-03-08 18:41:28 +00:00
|
|
|
* Copyright (c) 2013 by Delphix. All rights reserved.
|
2008-11-20 20:01:55 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
#include <sys/types.h>
|
|
|
|
#include <sys/param.h>
|
|
|
|
#include <sys/systm.h>
|
|
|
|
#include <sys/sysmacros.h>
|
|
|
|
#include <sys/cmn_err.h>
|
|
|
|
#include <sys/kmem.h>
|
|
|
|
#include <sys/thread.h>
|
|
|
|
#include <sys/file.h>
|
|
|
|
#include <sys/fcntl.h>
|
|
|
|
#include <sys/vfs.h>
|
|
|
|
#include <sys/fs/zfs.h>
|
|
|
|
#include <sys/zfs_znode.h>
|
|
|
|
#include <sys/zfs_dir.h>
|
|
|
|
#include <sys/zfs_acl.h>
|
|
|
|
#include <sys/zfs_fuid.h>
|
2011-03-01 20:24:09 +00:00
|
|
|
#include <sys/zfs_vnops.h>
|
2008-11-20 20:01:55 +00:00
|
|
|
#include <sys/spa.h>
|
|
|
|
#include <sys/zil.h>
|
|
|
|
#include <sys/byteorder.h>
|
|
|
|
#include <sys/stat.h>
|
|
|
|
#include <sys/mode.h>
|
|
|
|
#include <sys/acl.h>
|
|
|
|
#include <sys/atomic.h>
|
|
|
|
#include <sys/cred.h>
|
2011-03-01 20:24:09 +00:00
|
|
|
#include <sys/zpl.h>
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Functions to replay ZFS intent log (ZIL) records
|
|
|
|
* The functions are called through a function vector (zfs_replay_vector)
|
|
|
|
* which is indexed by the transaction type.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void
|
2011-03-01 20:24:09 +00:00
|
|
|
zfs_init_vattr(vattr_t *vap, uint64_t mask, uint64_t mode,
|
|
|
|
uint64_t uid, uint64_t gid, uint64_t rdev, uint64_t nodeid)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
2011-03-01 20:24:09 +00:00
|
|
|
bzero(vap, sizeof (*vap));
|
|
|
|
vap->va_mask = (uint_t)mask;
|
|
|
|
vap->va_type = IFTOVT(mode);
|
|
|
|
vap->va_mode = mode;
|
|
|
|
vap->va_uid = (uid_t)(IS_EPHEMERAL(uid)) ? -1 : uid;
|
|
|
|
vap->va_gid = (gid_t)(IS_EPHEMERAL(gid)) ? -1 : gid;
|
|
|
|
vap->va_rdev = rdev;
|
|
|
|
vap->va_nodeid = nodeid;
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/* ARGSUSED */
|
|
|
|
static int
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_error(zfs_sb_t *zsb, lr_t *lr, boolean_t byteswap)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
2013-03-08 18:41:28 +00:00
|
|
|
return (SET_ERROR(ENOTSUP));
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
|
|
|
zfs_replay_xvattr(lr_attr_t *lrattr, xvattr_t *xvap)
|
|
|
|
{
|
|
|
|
xoptattr_t *xoap = NULL;
|
|
|
|
uint64_t *attrs;
|
|
|
|
uint64_t *crtime;
|
|
|
|
uint32_t *bitmap;
|
|
|
|
void *scanstamp;
|
|
|
|
int i;
|
|
|
|
|
2011-03-01 20:24:09 +00:00
|
|
|
xvap->xva_vattr.va_mask |= ATTR_XVATTR;
|
2008-11-20 20:01:55 +00:00
|
|
|
if ((xoap = xva_getxoptattr(xvap)) == NULL) {
|
2011-03-01 20:24:09 +00:00
|
|
|
xvap->xva_vattr.va_mask &= ~ATTR_XVATTR; /* shouldn't happen */
|
2008-11-20 20:01:55 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
ASSERT(lrattr->lr_attr_masksize == xvap->xva_mapsize);
|
|
|
|
|
|
|
|
bitmap = &lrattr->lr_attr_bitmap;
|
|
|
|
for (i = 0; i != lrattr->lr_attr_masksize; i++, bitmap++)
|
|
|
|
xvap->xva_reqattrmap[i] = *bitmap;
|
|
|
|
|
|
|
|
attrs = (uint64_t *)(lrattr + lrattr->lr_attr_masksize - 1);
|
|
|
|
crtime = attrs + 1;
|
|
|
|
scanstamp = (caddr_t)(crtime + 2);
|
|
|
|
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_HIDDEN))
|
|
|
|
xoap->xoa_hidden = ((*attrs & XAT0_HIDDEN) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_SYSTEM))
|
|
|
|
xoap->xoa_system = ((*attrs & XAT0_SYSTEM) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_ARCHIVE))
|
|
|
|
xoap->xoa_archive = ((*attrs & XAT0_ARCHIVE) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_READONLY))
|
|
|
|
xoap->xoa_readonly = ((*attrs & XAT0_READONLY) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_IMMUTABLE))
|
|
|
|
xoap->xoa_immutable = ((*attrs & XAT0_IMMUTABLE) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_NOUNLINK))
|
|
|
|
xoap->xoa_nounlink = ((*attrs & XAT0_NOUNLINK) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_APPENDONLY))
|
|
|
|
xoap->xoa_appendonly = ((*attrs & XAT0_APPENDONLY) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_NODUMP))
|
|
|
|
xoap->xoa_nodump = ((*attrs & XAT0_NODUMP) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_OPAQUE))
|
|
|
|
xoap->xoa_opaque = ((*attrs & XAT0_OPAQUE) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_AV_MODIFIED))
|
|
|
|
xoap->xoa_av_modified = ((*attrs & XAT0_AV_MODIFIED) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_AV_QUARANTINED))
|
|
|
|
xoap->xoa_av_quarantined =
|
|
|
|
((*attrs & XAT0_AV_QUARANTINED) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_CREATETIME))
|
|
|
|
ZFS_TIME_DECODE(&xoap->xoa_createtime, crtime);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_AV_SCANSTAMP))
|
|
|
|
bcopy(scanstamp, xoap->xoa_av_scanstamp, AV_SCANSTAMP_SZ);
|
2010-05-28 20:45:14 +00:00
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_REPARSE))
|
|
|
|
xoap->xoa_reparse = ((*attrs & XAT0_REPARSE) != 0);
|
2010-08-26 21:24:34 +00:00
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_OFFLINE))
|
|
|
|
xoap->xoa_offline = ((*attrs & XAT0_OFFLINE) != 0);
|
|
|
|
if (XVA_ISSET_REQ(xvap, XAT_SPARSE))
|
|
|
|
xoap->xoa_sparse = ((*attrs & XAT0_SPARSE) != 0);
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
zfs_replay_domain_cnt(uint64_t uid, uint64_t gid)
|
|
|
|
{
|
|
|
|
uint64_t uid_idx;
|
|
|
|
uint64_t gid_idx;
|
|
|
|
int domcnt = 0;
|
|
|
|
|
|
|
|
uid_idx = FUID_INDEX(uid);
|
|
|
|
gid_idx = FUID_INDEX(gid);
|
|
|
|
if (uid_idx)
|
|
|
|
domcnt++;
|
|
|
|
if (gid_idx > 0 && gid_idx != uid_idx)
|
|
|
|
domcnt++;
|
|
|
|
|
|
|
|
return (domcnt);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void *
|
|
|
|
zfs_replay_fuid_domain_common(zfs_fuid_info_t *fuid_infop, void *start,
|
|
|
|
int domcnt)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i != domcnt; i++) {
|
|
|
|
fuid_infop->z_domain_table[i] = start;
|
|
|
|
start = (caddr_t)start + strlen(start) + 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
return (start);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Set the uid/gid in the fuid_info structure.
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
zfs_replay_fuid_ugid(zfs_fuid_info_t *fuid_infop, uint64_t uid, uint64_t gid)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* If owner or group are log specific FUIDs then slurp up
|
|
|
|
* domain information and build zfs_fuid_info_t
|
|
|
|
*/
|
|
|
|
if (IS_EPHEMERAL(uid))
|
|
|
|
fuid_infop->z_fuid_owner = uid;
|
|
|
|
|
|
|
|
if (IS_EPHEMERAL(gid))
|
|
|
|
fuid_infop->z_fuid_group = gid;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Load fuid domains into fuid_info_t
|
|
|
|
*/
|
|
|
|
static zfs_fuid_info_t *
|
|
|
|
zfs_replay_fuid_domain(void *buf, void **end, uint64_t uid, uint64_t gid)
|
|
|
|
{
|
|
|
|
int domcnt;
|
|
|
|
|
|
|
|
zfs_fuid_info_t *fuid_infop;
|
|
|
|
|
|
|
|
fuid_infop = zfs_fuid_info_alloc();
|
|
|
|
|
|
|
|
domcnt = zfs_replay_domain_cnt(uid, gid);
|
|
|
|
|
|
|
|
if (domcnt == 0)
|
|
|
|
return (fuid_infop);
|
|
|
|
|
|
|
|
fuid_infop->z_domain_table =
|
|
|
|
kmem_zalloc(domcnt * sizeof (char **), KM_SLEEP);
|
|
|
|
|
|
|
|
zfs_replay_fuid_ugid(fuid_infop, uid, gid);
|
|
|
|
|
|
|
|
fuid_infop->z_domain_cnt = domcnt;
|
|
|
|
*end = zfs_replay_fuid_domain_common(fuid_infop, buf, domcnt);
|
|
|
|
return (fuid_infop);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* load zfs_fuid_t's and fuid_domains into fuid_info_t
|
|
|
|
*/
|
|
|
|
static zfs_fuid_info_t *
|
|
|
|
zfs_replay_fuids(void *start, void **end, int idcnt, int domcnt, uint64_t uid,
|
|
|
|
uint64_t gid)
|
|
|
|
{
|
|
|
|
uint64_t *log_fuid = (uint64_t *)start;
|
|
|
|
zfs_fuid_info_t *fuid_infop;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
fuid_infop = zfs_fuid_info_alloc();
|
|
|
|
fuid_infop->z_domain_cnt = domcnt;
|
|
|
|
|
|
|
|
fuid_infop->z_domain_table =
|
|
|
|
kmem_zalloc(domcnt * sizeof (char **), KM_SLEEP);
|
|
|
|
|
|
|
|
for (i = 0; i != idcnt; i++) {
|
|
|
|
zfs_fuid_t *zfuid;
|
|
|
|
|
|
|
|
zfuid = kmem_alloc(sizeof (zfs_fuid_t), KM_SLEEP);
|
|
|
|
zfuid->z_logfuid = *log_fuid;
|
|
|
|
zfuid->z_id = -1;
|
|
|
|
zfuid->z_domidx = 0;
|
|
|
|
list_insert_tail(&fuid_infop->z_fuids, zfuid);
|
|
|
|
log_fuid++;
|
|
|
|
}
|
|
|
|
|
|
|
|
zfs_replay_fuid_ugid(fuid_infop, uid, gid);
|
|
|
|
|
|
|
|
*end = zfs_replay_fuid_domain_common(fuid_infop, log_fuid, domcnt);
|
|
|
|
return (fuid_infop);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
|
|
|
zfs_replay_swap_attrs(lr_attr_t *lrattr)
|
|
|
|
{
|
|
|
|
/* swap the lr_attr structure */
|
|
|
|
byteswap_uint32_array(lrattr, sizeof (*lrattr));
|
|
|
|
/* swap the bitmap */
|
|
|
|
byteswap_uint32_array(lrattr + 1, (lrattr->lr_attr_masksize - 1) *
|
|
|
|
sizeof (uint32_t));
|
|
|
|
/* swap the attributes, create time + 64 bit word for attributes */
|
|
|
|
byteswap_uint64_array((caddr_t)(lrattr + 1) + (sizeof (uint32_t) *
|
|
|
|
(lrattr->lr_attr_masksize - 1)), 3 * sizeof (uint64_t));
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Replay file create with optional ACL, xvattr information as well
|
|
|
|
* as option FUID information.
|
|
|
|
*/
|
|
|
|
static int
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_create_acl(zfs_sb_t *zsb, lr_acl_create_t *lracl, boolean_t byteswap)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
char *name = NULL; /* location determined later */
|
|
|
|
lr_create_t *lr = (lr_create_t *)lracl;
|
|
|
|
znode_t *dzp;
|
2011-02-08 19:33:08 +00:00
|
|
|
struct inode *ip = NULL;
|
2008-11-20 20:01:55 +00:00
|
|
|
xvattr_t xva;
|
2011-02-08 19:33:08 +00:00
|
|
|
int vflg = 0;
|
2011-03-01 20:24:09 +00:00
|
|
|
vsecattr_t vsec = { 0 };
|
2008-11-20 20:01:55 +00:00
|
|
|
lr_attr_t *lrattr;
|
|
|
|
void *aclstart;
|
|
|
|
void *fuidstart;
|
|
|
|
size_t xvatlen = 0;
|
|
|
|
uint64_t txtype;
|
|
|
|
int error;
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
txtype = (lr->lr_common.lrc_txtype & ~TX_CI);
|
2008-11-20 20:01:55 +00:00
|
|
|
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));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_doid, &dzp)) != 0)
|
2008-11-20 20:01:55 +00:00
|
|
|
return (error);
|
|
|
|
|
|
|
|
xva_init(&xva);
|
2011-03-03 19:29:15 +00:00
|
|
|
zfs_init_vattr(&xva.xva_vattr, ATTR_MODE | ATTR_UID | ATTR_GID,
|
2011-03-01 20:24:09 +00:00
|
|
|
lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, lr->lr_foid);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* All forms of zfs create (create, mkdir, mkxattrdir, symlink)
|
|
|
|
* eventually end up in zfs_mknode(), which assigns the object's
|
2010-12-22 18:07:03 +00:00
|
|
|
* creation time and generation number. The generic zfs_create()
|
2008-11-20 20:01:55 +00:00
|
|
|
* 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;
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
error = dmu_object_info(zsb->z_os, lr->lr_foid, NULL);
|
2008-11-20 20:01:55 +00:00
|
|
|
if (error != ENOENT)
|
|
|
|
goto bail;
|
|
|
|
|
|
|
|
if (lr->lr_common.lrc_txtype & TX_CI)
|
|
|
|
vflg |= FIGNORECASE;
|
2010-05-28 20:45:14 +00:00
|
|
|
switch (txtype) {
|
2008-11-20 20:01:55 +00:00
|
|
|
case TX_CREATE_ACL:
|
|
|
|
aclstart = (caddr_t)(lracl + 1);
|
|
|
|
fuidstart = (caddr_t)aclstart +
|
|
|
|
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_fuid_replay = zfs_replay_fuids(fuidstart,
|
2008-11-20 20:01:55 +00:00
|
|
|
(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);
|
2011-03-01 20:24:09 +00:00
|
|
|
xva.xva_vattr.va_mask |= ATTR_XVATTR;
|
2008-11-20 20:01:55 +00:00
|
|
|
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;
|
2011-02-08 19:33:08 +00:00
|
|
|
if (zsb->z_fuid_replay == NULL) {
|
2008-11-20 20:01:55 +00:00
|
|
|
fuidstart = (caddr_t)(lracl + 1) + xvatlen +
|
|
|
|
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_fuid_replay =
|
2008-11-20 20:01:55 +00:00
|
|
|
zfs_replay_fuids(fuidstart,
|
|
|
|
(void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt,
|
|
|
|
lr->lr_uid, lr->lr_gid);
|
|
|
|
}
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
error = zfs_create(ZTOI(dzp), name, &xva.xva_vattr,
|
2011-03-01 20:24:09 +00:00
|
|
|
0, 0, &ip, kcred, vflg, &vsec);
|
2008-11-20 20:01:55 +00:00
|
|
|
break;
|
|
|
|
case TX_MKDIR_ACL:
|
|
|
|
aclstart = (caddr_t)(lracl + 1);
|
|
|
|
fuidstart = (caddr_t)aclstart +
|
|
|
|
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_fuid_replay = zfs_replay_fuids(fuidstart,
|
2008-11-20 20:01:55 +00:00
|
|
|
(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;
|
2011-02-08 19:33:08 +00:00
|
|
|
if (zsb->z_fuid_replay == NULL) {
|
2008-11-20 20:01:55 +00:00
|
|
|
fuidstart = (caddr_t)(lracl + 1) + xvatlen +
|
|
|
|
ZIL_ACE_LENGTH(lracl->lr_acl_bytes);
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_fuid_replay =
|
2008-11-20 20:01:55 +00:00
|
|
|
zfs_replay_fuids(fuidstart,
|
|
|
|
(void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt,
|
|
|
|
lr->lr_uid, lr->lr_gid);
|
|
|
|
}
|
2011-02-08 19:33:08 +00:00
|
|
|
error = zfs_mkdir(ZTOI(dzp), name, &xva.xva_vattr,
|
2011-03-01 20:24:09 +00:00
|
|
|
&ip, kcred, vflg, &vsec);
|
2008-11-20 20:01:55 +00:00
|
|
|
break;
|
|
|
|
default:
|
2013-03-08 18:41:28 +00:00
|
|
|
error = SET_ERROR(ENOTSUP);
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
bail:
|
2011-02-08 19:33:08 +00:00
|
|
|
if (error == 0 && ip != NULL)
|
|
|
|
iput(ip);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
iput(ZTOI(dzp));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if (zsb->z_fuid_replay)
|
|
|
|
zfs_fuid_info_free(zsb->z_fuid_replay);
|
|
|
|
zsb->z_fuid_replay = NULL;
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_create(zfs_sb_t *zsb, lr_create_t *lr, boolean_t byteswap)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
char *name = NULL; /* location determined later */
|
|
|
|
char *link; /* symlink content follows name */
|
|
|
|
znode_t *dzp;
|
2011-02-08 19:33:08 +00:00
|
|
|
struct inode *ip = NULL;
|
2008-11-20 20:01:55 +00:00
|
|
|
xvattr_t xva;
|
|
|
|
int vflg = 0;
|
|
|
|
size_t lrsize = sizeof (lr_create_t);
|
|
|
|
lr_attr_t *lrattr;
|
2011-02-08 19:33:08 +00:00
|
|
|
void *start;
|
2011-03-01 20:24:09 +00:00
|
|
|
size_t xvatlen;
|
2008-11-20 20:01:55 +00:00
|
|
|
uint64_t txtype;
|
|
|
|
int error;
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
txtype = (lr->lr_common.lrc_txtype & ~TX_CI);
|
2008-11-20 20:01:55 +00:00
|
|
|
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));
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_doid, &dzp)) != 0)
|
2008-11-20 20:01:55 +00:00
|
|
|
return (error);
|
|
|
|
|
|
|
|
xva_init(&xva);
|
2011-03-03 19:29:15 +00:00
|
|
|
zfs_init_vattr(&xva.xva_vattr, ATTR_MODE | ATTR_UID | ATTR_GID,
|
2011-03-01 20:24:09 +00:00
|
|
|
lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, lr->lr_foid);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* All forms of zfs create (create, mkdir, mkxattrdir, symlink)
|
|
|
|
* eventually end up in zfs_mknode(), which assigns the object's
|
2010-12-22 18:07:03 +00:00
|
|
|
* creation time and generation number. The generic zfs_create()
|
2008-11-20 20:01:55 +00:00
|
|
|
* 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;
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
error = dmu_object_info(zsb->z_os, lr->lr_foid, NULL);
|
2008-11-20 20:01:55 +00:00
|
|
|
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);
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_fuid_replay =
|
2008-11-20 20:01:55 +00:00
|
|
|
zfs_replay_fuid_domain(start, &start,
|
|
|
|
lr->lr_uid, lr->lr_gid);
|
|
|
|
}
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
switch (txtype) {
|
2008-11-20 20:01:55 +00:00
|
|
|
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;
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_fuid_replay =
|
2008-11-20 20:01:55 +00:00
|
|
|
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;
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
error = zfs_create(ZTOI(dzp), name, &xva.xva_vattr,
|
|
|
|
0, 0, &ip, kcred, vflg, NULL);
|
2008-11-20 20:01:55 +00:00
|
|
|
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;
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_fuid_replay =
|
2008-11-20 20:01:55 +00:00
|
|
|
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);
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
error = zfs_mkdir(ZTOI(dzp), name, &xva.xva_vattr,
|
|
|
|
&ip, kcred, vflg, NULL);
|
2008-11-20 20:01:55 +00:00
|
|
|
break;
|
|
|
|
case TX_MKXATTR:
|
2011-02-08 19:33:08 +00:00
|
|
|
error = zfs_make_xattrdir(dzp, &xva.xva_vattr, &ip, kcred);
|
2008-11-20 20:01:55 +00:00
|
|
|
break;
|
|
|
|
case TX_SYMLINK:
|
|
|
|
name = (char *)(lr + 1);
|
|
|
|
link = name + strlen(name) + 1;
|
2011-02-08 19:33:08 +00:00
|
|
|
error = zfs_symlink(ZTOI(dzp), name, &xva.xva_vattr,
|
|
|
|
link, &ip, kcred, vflg);
|
2008-11-20 20:01:55 +00:00
|
|
|
break;
|
|
|
|
default:
|
2013-03-08 18:41:28 +00:00
|
|
|
error = SET_ERROR(ENOTSUP);
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
2011-02-08 19:33:08 +00:00
|
|
|
if (error == 0 && ip != NULL)
|
|
|
|
iput(ip);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
iput(ZTOI(dzp));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if (zsb->z_fuid_replay)
|
|
|
|
zfs_fuid_info_free(zsb->z_fuid_replay);
|
|
|
|
zsb->z_fuid_replay = NULL;
|
2008-11-20 20:01:55 +00:00
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_remove(zfs_sb_t *zsb, lr_remove_t *lr, boolean_t byteswap)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
char *name = (char *)(lr + 1); /* name follows lr_remove_t */
|
|
|
|
znode_t *dzp;
|
|
|
|
int error;
|
|
|
|
int vflg = 0;
|
|
|
|
|
|
|
|
if (byteswap)
|
|
|
|
byteswap_uint64_array(lr, sizeof (*lr));
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_doid, &dzp)) != 0)
|
2008-11-20 20:01:55 +00:00
|
|
|
return (error);
|
|
|
|
|
|
|
|
if (lr->lr_common.lrc_txtype & TX_CI)
|
|
|
|
vflg |= FIGNORECASE;
|
|
|
|
|
|
|
|
switch ((int)lr->lr_common.lrc_txtype) {
|
|
|
|
case TX_REMOVE:
|
2016-04-13 15:55:35 +00:00
|
|
|
error = zfs_remove(ZTOI(dzp), name, kcred, vflg);
|
2008-11-20 20:01:55 +00:00
|
|
|
break;
|
|
|
|
case TX_RMDIR:
|
2011-02-08 19:33:08 +00:00
|
|
|
error = zfs_rmdir(ZTOI(dzp), name, NULL, kcred, vflg);
|
2008-11-20 20:01:55 +00:00
|
|
|
break;
|
|
|
|
default:
|
2013-03-08 18:41:28 +00:00
|
|
|
error = SET_ERROR(ENOTSUP);
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
iput(ZTOI(dzp));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_link(zfs_sb_t *zsb, lr_link_t *lr, boolean_t byteswap)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
char *name = (char *)(lr + 1); /* name follows lr_link_t */
|
|
|
|
znode_t *dzp, *zp;
|
|
|
|
int error;
|
2011-03-01 20:24:09 +00:00
|
|
|
int vflg = 0;
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
if (byteswap)
|
|
|
|
byteswap_uint64_array(lr, sizeof (*lr));
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_doid, &dzp)) != 0)
|
2008-11-20 20:01:55 +00:00
|
|
|
return (error);
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_link_obj, &zp)) != 0) {
|
|
|
|
iput(ZTOI(dzp));
|
2008-11-20 20:01:55 +00:00
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (lr->lr_common.lrc_txtype & TX_CI)
|
|
|
|
vflg |= FIGNORECASE;
|
|
|
|
|
2016-04-13 15:55:35 +00:00
|
|
|
error = zfs_link(ZTOI(dzp), ZTOI(zp), name, kcred, vflg);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
iput(ZTOI(zp));
|
|
|
|
iput(ZTOI(dzp));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_rename(zfs_sb_t *zsb, lr_rename_t *lr, boolean_t byteswap)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
char *sname = (char *)(lr + 1); /* sname and tname follow lr_rename_t */
|
|
|
|
char *tname = sname + strlen(sname) + 1;
|
|
|
|
znode_t *sdzp, *tdzp;
|
|
|
|
int error;
|
|
|
|
int vflg = 0;
|
|
|
|
|
|
|
|
if (byteswap)
|
|
|
|
byteswap_uint64_array(lr, sizeof (*lr));
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_sdoid, &sdzp)) != 0)
|
2008-11-20 20:01:55 +00:00
|
|
|
return (error);
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_tdoid, &tdzp)) != 0) {
|
|
|
|
iput(ZTOI(sdzp));
|
2008-11-20 20:01:55 +00:00
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (lr->lr_common.lrc_txtype & TX_CI)
|
|
|
|
vflg |= FIGNORECASE;
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
error = zfs_rename(ZTOI(sdzp), sname, ZTOI(tdzp), tname, kcred, vflg);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
iput(ZTOI(tdzp));
|
|
|
|
iput(ZTOI(sdzp));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_write(zfs_sb_t *zsb, lr_write_t *lr, boolean_t byteswap)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
char *data = (char *)(lr + 1); /* data follows lr_write_t */
|
|
|
|
znode_t *zp;
|
2012-09-13 20:25:15 +00:00
|
|
|
int error, written;
|
2010-08-26 21:24:34 +00:00
|
|
|
uint64_t eod, offset, length;
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
if (byteswap)
|
|
|
|
byteswap_uint64_array(lr, sizeof (*lr));
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_foid, &zp)) != 0) {
|
2008-11-20 20:01:55 +00:00
|
|
|
/*
|
|
|
|
* 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);
|
|
|
|
}
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
offset = lr->lr_offset;
|
|
|
|
length = lr->lr_length;
|
2010-08-26 21:24:34 +00:00
|
|
|
eod = offset + length; /* end of data for this write */
|
2010-05-28 20:45:14 +00:00
|
|
|
|
2010-08-26 21:24:34 +00:00
|
|
|
/*
|
|
|
|
* 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
|
2011-02-08 19:33:08 +00:00
|
|
|
* new end of file is passed through in zsb->z_replay_eof
|
2010-08-26 21:24:34 +00:00
|
|
|
*/
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_replay_eof = 0; /* 0 means don't change end of file */
|
2010-05-28 20:45:14 +00:00
|
|
|
|
|
|
|
/* 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;
|
|
|
|
}
|
2010-08-26 21:24:34 +00:00
|
|
|
if (zp->z_size < eod)
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_replay_eof = eod;
|
2010-05-28 20:45:14 +00:00
|
|
|
}
|
|
|
|
|
Linux AIO Support
nfsd uses do_readv_writev() to implement fops->read and fops->write.
do_readv_writev() will attempt to read/write using fops->aio_read and
fops->aio_write, but it will fallback to fops->read and fops->write when
AIO is not available. However, the fallback will perform a call for each
individual data page. Since our default recordsize is 128KB, sequential
operations on NFS will generate 32 DMU transactions where only 1
transaction was needed. That was unnecessary overhead and we implement
fops->aio_read and fops->aio_write to eliminate it.
ZFS originated in OpenSolaris, where the AIO API is entirely implemented
in userland's libc by intelligently mapping them to VOP_WRITE, VOP_READ
and VOP_FSYNC. Linux implements AIO inside the kernel itself. Linux
filesystems therefore must implement their own AIO logic and nearly all
of them implement fops->aio_write synchronously. Consequently, they do
not implement aio_fsync(). However, since the ZPL works by mapping
Linux's VFS calls to the functions implementing Illumos' VFS operations,
we instead implement AIO in the kernel by mapping the operations to the
VOP_READ, VOP_WRITE and VOP_FSYNC equivalents. We therefore implement
fops->aio_fsync.
One might be inclined to make our fops->aio_write implementation
synchronous to make software that expects this behavior safe. However,
there are several reasons not to do this:
1. Other platforms do not implement aio_write() synchronously and since
the majority of userland software using AIO should be cross platform,
expectations of synchronous behavior should not be a problem.
2. We would hurt the performance of programs that use POSIX interfaces
properly while simultaneously encouraging the creation of more
non-compliant software.
3. The broader community concluded that userland software should be
patched to properly use POSIX interfaces instead of implementing hacks
in filesystems to cater to broken software. This concept is best
described as the O_PONIES debate.
4. Making an asynchronous write synchronous is non sequitur.
Any software dependent on synchronous aio_write behavior will suffer
data loss on ZFSOnLinux in a kernel panic / system failure of at most
zfs_txg_timeout seconds, which by default is 5 seconds. This seems like
a reasonable consequence of using non-compliant software.
It should be noted that this is also a problem in the kernel itself
where nfsd does not pass O_SYNC on files opened with it and instead
relies on a open()/write()/close() to enforce synchronous behavior when
the flush is only guarenteed on last close.
Exporting any filesystem that does not implement AIO via NFS risks data
loss in the event of a kernel panic / system failure when something else
is also accessing the file. Exporting any file system that implements
AIO the way this patch does bears similar risk. However, it seems
reasonable to forgo crippling our AIO implementation in favor of
developing patches to fix this problem in Linux's nfsd for the reasons
stated earlier. In the interim, the risk will remain. Failing to
implement AIO will not change the problem that nfsd created, so there is
no reason for nfsd's mistake to block our implementation of AIO.
It also should be noted that `aio_cancel()` will always return
`AIO_NOTCANCELED` under this implementation. It is possible to implement
aio_cancel by deferring work to taskqs and use `kiocb_set_cancel_fn()`
to set a callback function for cancelling work sent to taskqs, but the
simpler approach is allowed by the specification:
```
Which operations are cancelable is implementation-defined.
```
http://pubs.opengroup.org/onlinepubs/009695399/functions/aio_cancel.html
The only programs on my system that are capable of using `aio_cancel()`
are QEMU, beecrypt and fio use it according to a recursive grep of my
system's `/usr/src/debug`. That suggests that `aio_cancel()` users are
rare. Implementing aio_cancel() is left to a future date when it is
clear that there are consumers that benefit from its implementation to
justify the work.
Lastly, it is important to know that handling of the iovec updates differs
between Illumos and Linux in the implementation of read/write. On Linux,
it is the VFS' responsibility whle on Illumos, it is the filesystem's
responsibility. We take the intermediate solution of copying the iovec
so that the ZFS code can update it like on Solaris while leaving the
originals alone. This imposes some overhead. We could always revisit
this should profiling show that the allocations are a problem.
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #223
Closes #2373
2014-08-04 11:09:32 +00:00
|
|
|
written = zpl_write_common(ZTOI(zp), data, length, &offset,
|
2011-03-01 20:24:09 +00:00
|
|
|
UIO_SYSSPACE, 0, kcred);
|
2012-09-13 20:25:15 +00:00
|
|
|
if (written < 0)
|
|
|
|
error = -written;
|
|
|
|
else if (written < length)
|
2013-03-08 18:41:28 +00:00
|
|
|
error = SET_ERROR(EIO); /* short write */
|
2010-05-28 20:45:14 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
iput(ZTOI(zp));
|
|
|
|
zsb->z_replay_eof = 0; /* safety */
|
2010-05-28 20:45:14 +00:00
|
|
|
|
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_write2(zfs_sb_t *zsb, lr_write_t *lr, boolean_t byteswap)
|
2010-05-28 20:45:14 +00:00
|
|
|
{
|
|
|
|
znode_t *zp;
|
|
|
|
int error;
|
|
|
|
uint64_t end;
|
|
|
|
|
|
|
|
if (byteswap)
|
|
|
|
byteswap_uint64_array(lr, sizeof (*lr));
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_foid, &zp)) != 0)
|
2010-05-28 20:45:14 +00:00
|
|
|
return (error);
|
|
|
|
|
2010-08-26 21:24:34 +00:00
|
|
|
top:
|
2010-05-28 20:45:14 +00:00
|
|
|
end = lr->lr_offset + lr->lr_length;
|
|
|
|
if (end > zp->z_size) {
|
2011-02-08 19:33:08 +00:00
|
|
|
dmu_tx_t *tx = dmu_tx_create(zsb->z_os);
|
2010-08-26 21:24:34 +00:00
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
zp->z_size = end;
|
2010-08-26 21:24:34 +00:00
|
|
|
dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE);
|
|
|
|
error = dmu_tx_assign(tx, TXG_WAIT);
|
|
|
|
if (error) {
|
2011-02-08 19:33:08 +00:00
|
|
|
iput(ZTOI(zp));
|
2010-08-26 21:24:34 +00:00
|
|
|
if (error == ERESTART) {
|
|
|
|
dmu_tx_wait(tx);
|
|
|
|
dmu_tx_abort(tx);
|
|
|
|
goto top;
|
|
|
|
}
|
|
|
|
dmu_tx_abort(tx);
|
|
|
|
return (error);
|
|
|
|
}
|
2011-02-08 19:33:08 +00:00
|
|
|
(void) sa_update(zp->z_sa_hdl, SA_ZPL_SIZE(zsb),
|
2010-08-26 21:24:34 +00:00
|
|
|
(void *)&zp->z_size, sizeof (uint64_t), tx);
|
|
|
|
|
|
|
|
/* Ensure the replayed seq is updated */
|
2011-02-08 19:33:08 +00:00
|
|
|
(void) zil_replaying(zsb->z_log, tx);
|
2010-08-26 21:24:34 +00:00
|
|
|
|
|
|
|
dmu_tx_commit(tx);
|
2010-05-28 20:45:14 +00:00
|
|
|
}
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
iput(ZTOI(zp));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_truncate(zfs_sb_t *zsb, lr_truncate_t *lr, boolean_t byteswap)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
znode_t *zp;
|
|
|
|
flock64_t fl;
|
|
|
|
int error;
|
|
|
|
|
|
|
|
if (byteswap)
|
|
|
|
byteswap_uint64_array(lr, sizeof (*lr));
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_foid, &zp)) != 0)
|
2008-11-20 20:01:55 +00:00
|
|
|
return (error);
|
|
|
|
|
|
|
|
bzero(&fl, sizeof (fl));
|
|
|
|
fl.l_type = F_WRLCK;
|
|
|
|
fl.l_whence = 0;
|
|
|
|
fl.l_start = lr->lr_offset;
|
|
|
|
fl.l_len = lr->lr_length;
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
error = zfs_space(ZTOI(zp), F_FREESP, &fl, FWRITE | FOFFMAX,
|
|
|
|
lr->lr_offset, kcred);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
iput(ZTOI(zp));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_setattr(zfs_sb_t *zsb, lr_setattr_t *lr, boolean_t byteswap)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
znode_t *zp;
|
|
|
|
xvattr_t xva;
|
2011-03-01 20:24:09 +00:00
|
|
|
vattr_t *vap = &xva.xva_vattr;
|
2008-11-20 20:01:55 +00:00
|
|
|
int error;
|
|
|
|
void *start;
|
|
|
|
|
|
|
|
xva_init(&xva);
|
|
|
|
if (byteswap) {
|
|
|
|
byteswap_uint64_array(lr, sizeof (*lr));
|
|
|
|
|
2011-03-01 20:24:09 +00:00
|
|
|
if ((lr->lr_mask & ATTR_XVATTR) &&
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_version >= ZPL_VERSION_INITIAL)
|
2008-11-20 20:01:55 +00:00
|
|
|
zfs_replay_swap_attrs((lr_attr_t *)(lr + 1));
|
|
|
|
}
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_foid, &zp)) != 0)
|
2008-11-20 20:01:55 +00:00
|
|
|
return (error);
|
|
|
|
|
2011-03-01 20:24:09 +00:00
|
|
|
zfs_init_vattr(vap, lr->lr_mask, lr->lr_mode,
|
|
|
|
lr->lr_uid, lr->lr_gid, 0, lr->lr_foid);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-03-01 20:24:09 +00:00
|
|
|
vap->va_size = lr->lr_size;
|
|
|
|
ZFS_TIME_DECODE(&vap->va_atime, lr->lr_atime);
|
|
|
|
ZFS_TIME_DECODE(&vap->va_mtime, lr->lr_mtime);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Fill in xvattr_t portions if necessary.
|
|
|
|
*/
|
|
|
|
|
|
|
|
start = (lr_setattr_t *)(lr + 1);
|
2011-03-01 20:24:09 +00:00
|
|
|
if (vap->va_mask & ATTR_XVATTR) {
|
2008-11-20 20:01:55 +00:00
|
|
|
zfs_replay_xvattr((lr_attr_t *)start, &xva);
|
|
|
|
start = (caddr_t)start +
|
|
|
|
ZIL_XVAT_SIZE(((lr_attr_t *)start)->lr_attr_masksize);
|
|
|
|
} else
|
2011-03-01 20:24:09 +00:00
|
|
|
xva.xva_vattr.va_mask &= ~ATTR_XVATTR;
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_fuid_replay = zfs_replay_fuid_domain(start, &start,
|
2008-11-20 20:01:55 +00:00
|
|
|
lr->lr_uid, lr->lr_gid);
|
|
|
|
|
2011-03-01 20:24:09 +00:00
|
|
|
error = zfs_setattr(ZTOI(zp), vap, 0, kcred);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_fuid_info_free(zsb->z_fuid_replay);
|
|
|
|
zsb->z_fuid_replay = NULL;
|
|
|
|
iput(ZTOI(zp));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_acl_v0(zfs_sb_t *zsb, lr_acl_v0_t *lr, boolean_t byteswap)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_foid, &zp)) != 0)
|
2008-11-20 20:01:55 +00:00
|
|
|
return (error);
|
|
|
|
|
|
|
|
bzero(&vsa, sizeof (vsa));
|
|
|
|
vsa.vsa_mask = VSA_ACE | VSA_ACECNT;
|
|
|
|
vsa.vsa_aclcnt = lr->lr_aclcnt;
|
2008-12-03 20:09:06 +00:00
|
|
|
vsa.vsa_aclentsz = sizeof (ace_t) * vsa.vsa_aclcnt;
|
|
|
|
vsa.vsa_aclflags = 0;
|
2008-11-20 20:01:55 +00:00
|
|
|
vsa.vsa_aclentp = ace;
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
error = zfs_setsecattr(ZTOI(zp), &vsa, 0, kcred);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
iput(ZTOI(zp));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
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
|
2011-02-08 19:33:08 +00:00
|
|
|
zfs_replay_acl(zfs_sb_t *zsb, lr_acl_t *lr, boolean_t byteswap)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
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));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if ((error = zfs_zget(zsb, lr->lr_foid, &zp)) != 0)
|
2008-11-20 20:01:55 +00:00
|
|
|
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);
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_fuid_replay =
|
2008-11-20 20:01:55 +00:00
|
|
|
zfs_replay_fuids(fuidstart, &fuidstart,
|
|
|
|
lr->lr_fuidcnt, lr->lr_domcnt, 0, 0);
|
|
|
|
}
|
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
error = zfs_setsecattr(ZTOI(zp), &vsa, 0, kcred);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
if (zsb->z_fuid_replay)
|
|
|
|
zfs_fuid_info_free(zsb->z_fuid_replay);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2011-02-08 19:33:08 +00:00
|
|
|
zsb->z_fuid_replay = NULL;
|
|
|
|
iput(ZTOI(zp));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
return (error);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Callback vectors for replaying records
|
|
|
|
*/
|
2013-02-15 04:37:43 +00:00
|
|
|
zil_replay_func_t zfs_replay_vector[TX_MAX_TYPE] = {
|
|
|
|
(zil_replay_func_t)zfs_replay_error, /* no such type */
|
|
|
|
(zil_replay_func_t)zfs_replay_create, /* TX_CREATE */
|
|
|
|
(zil_replay_func_t)zfs_replay_create, /* TX_MKDIR */
|
|
|
|
(zil_replay_func_t)zfs_replay_create, /* TX_MKXATTR */
|
|
|
|
(zil_replay_func_t)zfs_replay_create, /* TX_SYMLINK */
|
|
|
|
(zil_replay_func_t)zfs_replay_remove, /* TX_REMOVE */
|
|
|
|
(zil_replay_func_t)zfs_replay_remove, /* TX_RMDIR */
|
|
|
|
(zil_replay_func_t)zfs_replay_link, /* TX_LINK */
|
|
|
|
(zil_replay_func_t)zfs_replay_rename, /* TX_RENAME */
|
|
|
|
(zil_replay_func_t)zfs_replay_write, /* TX_WRITE */
|
|
|
|
(zil_replay_func_t)zfs_replay_truncate, /* TX_TRUNCATE */
|
|
|
|
(zil_replay_func_t)zfs_replay_setattr, /* TX_SETATTR */
|
|
|
|
(zil_replay_func_t)zfs_replay_acl_v0, /* TX_ACL_V0 */
|
|
|
|
(zil_replay_func_t)zfs_replay_acl, /* TX_ACL */
|
|
|
|
(zil_replay_func_t)zfs_replay_create_acl, /* TX_CREATE_ACL */
|
|
|
|
(zil_replay_func_t)zfs_replay_create, /* TX_CREATE_ATTR */
|
|
|
|
(zil_replay_func_t)zfs_replay_create_acl, /* TX_CREATE_ACL_ATTR */
|
|
|
|
(zil_replay_func_t)zfs_replay_create_acl, /* TX_MKDIR_ACL */
|
|
|
|
(zil_replay_func_t)zfs_replay_create, /* TX_MKDIR_ATTR */
|
|
|
|
(zil_replay_func_t)zfs_replay_create_acl, /* TX_MKDIR_ACL_ATTR */
|
|
|
|
(zil_replay_func_t)zfs_replay_write2, /* TX_WRITE2 */
|
2008-11-20 20:01:55 +00:00
|
|
|
};
|