diff options
author | pjd <pjd@FreeBSD.org> | 2008-11-17 20:49:29 +0000 |
---|---|---|
committer | pjd <pjd@FreeBSD.org> | 2008-11-17 20:49:29 +0000 |
commit | bbe899b96e388a8b82439f81ed3707e0d9c6070d (patch) | |
tree | 81b89fa4ac6467771d5aa291a97f4665981a6108 /sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_replay.c | |
parent | d2f579595c362ce27b4d87e2c40e1c4e09b929e3 (diff) | |
download | FreeBSD-src-bbe899b96e388a8b82439f81ed3707e0d9c6070d.zip FreeBSD-src-bbe899b96e388a8b82439f81ed3707e0d9c6070d.tar.gz |
Update ZFS from version 6 to 13 and bring some FreeBSD-specific changes.
This bring huge amount of changes, I'll enumerate only user-visible changes:
- Delegated Administration
Allows regular users to perform ZFS operations, like file system
creation, snapshot creation, etc.
- L2ARC
Level 2 cache for ZFS - allows to use additional disks for cache.
Huge performance improvements mostly for random read of mostly
static content.
- slog
Allow to use additional disks for ZFS Intent Log to speed up
operations like fsync(2).
- vfs.zfs.super_owner
Allows regular users to perform privileged operations on files stored
on ZFS file systems owned by him. Very careful with this one.
- chflags(2)
Not all the flags are supported. This still needs work.
- ZFSBoot
Support to boot off of ZFS pool. Not finished, AFAIK.
Submitted by: dfr
- Snapshot properties
- New failure modes
Before if write requested failed, system paniced. Now one
can select from one of three failure modes:
- panic - panic on write error
- wait - wait for disk to reappear
- continue - serve read requests if possible, block write requests
- Refquota, refreservation properties
Just quota and reservation properties, but don't count space consumed
by children file systems, clones and snapshots.
- Sparse volumes
ZVOLs that don't reserve space in the pool.
- External attributes
Compatible with extattr(2).
- NFSv4-ACLs
Not sure about the status, might not be complete yet.
Submitted by: trasz
- Creation-time properties
- Regression tests for zpool(8) command.
Obtained from: OpenSolaris
Diffstat (limited to 'sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_replay.c')
-rw-r--r-- | sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_replay.c | 579 |
1 files changed, 546 insertions, 33 deletions
diff --git a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_replay.c b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_replay.c index eb3215d..573a82c 100644 --- a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_replay.c +++ b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_replay.c @@ -19,7 +19,7 @@ * CDDL HEADER END */ /* - * Copyright 2006 Sun Microsystems, Inc. All rights reserved. + * Copyright 2008 Sun Microsystems, Inc. All rights reserved. * Use is subject to license terms. */ @@ -38,6 +38,7 @@ #include <sys/zfs_znode.h> #include <sys/zfs_dir.h> #include <sys/zfs_acl.h> +#include <sys/zfs_fuid.h> #include <sys/spa.h> #include <sys/zil.h> #include <sys/byteorder.h> @@ -61,8 +62,8 @@ zfs_init_vattr(vattr_t *vap, uint64_t mask, uint64_t mode, vap->va_mask = (uint_t)mask; vap->va_type = IFTOVT(mode); vap->va_mode = mode & MODEMASK; - vap->va_uid = (uid_t)uid; - vap->va_gid = (gid_t)gid; + vap->va_uid = (uid_t)(IS_EPHEMERAL(uid)) ? -1 : uid; + vap->va_gid = (gid_t)(IS_EPHEMERAL(gid)) ? -1 : gid; vap->va_rdev = zfs_cmpldev(rdev); vap->va_nodeid = nodeid; } @@ -74,24 +75,365 @@ zfs_replay_error(zfsvfs_t *zfsvfs, lr_t *lr, boolean_t byteswap) return (ENOTSUP); } +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; + + xvap->xva_vattr.va_mask |= AT_XVATTR; + if ((xoap = xva_getxoptattr(xvap)) == NULL) { + xvap->xva_vattr.va_mask &= ~AT_XVATTR; /* shouldn't happen */ + 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); +} + +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 +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; + + if (byteswap) { + byteswap_uint64_array(lracl, sizeof (*lracl)); + txtype = (int)lr->lr_common.lrc_txtype; + 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 ((int)lr->lr_common.lrc_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)); + + zfs_fuid_info_free(zfsvfs->z_fuid_replay); + zfsvfs->z_fuid_replay = NULL; + + return (error); +} + static int zfs_replay_create(zfsvfs_t *zfsvfs, lr_create_t *lr, boolean_t byteswap) { - char *name = (char *)(lr + 1); /* name follows lr_create_t */ + char *name = NULL; /* location determined later */ char *link; /* symlink content follows name */ znode_t *dzp; vnode_t *vp = NULL; - vattr_t va; + 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; - if (byteswap) + if (byteswap) { byteswap_uint64_array(lr, sizeof (*lr)); + txtype = (int)lr->lr_common.lrc_txtype; + 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); - zfs_init_vattr(&va, AT_TYPE | AT_MODE | AT_UID | AT_GID, + 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); /* @@ -101,34 +443,89 @@ zfs_replay_create(zfsvfs_t *zfsvfs, lr_create_t *lr, boolean_t byteswap) * 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(&va.va_ctime, lr->lr_crtime); - va.va_nblocks = lr->lr_gen; + 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_nameptr = name; cn.cn_cred = kcred; cn.cn_thread = curthread; cn.cn_flags = SAVENAME; vn_lock(ZTOV(dzp), LK_EXCLUSIVE | LK_RETRY); switch ((int)lr->lr_common.lrc_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: - error = VOP_CREATE(ZTOV(dzp), &vp, &cn, &va); + 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: - error = VOP_MKDIR(ZTOV(dzp), &vp, &cn, &va); + 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, &va, &vp, kcred); + name = (char *)(lr + 1); + error = zfs_make_xattrdir(dzp, &xva.xva_vattr, &vp, kcred); break; case TX_SYMLINK: + name = (char *)(lr + 1); link = name + strlen(name) + 1; - error = VOP_SYMLINK(ZTOV(dzp), &vp, &cn, &va, link); + 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) { VOP_UNLOCK(vp, 0); VN_RELE(vp); @@ -136,6 +533,9 @@ zfs_replay_create(zfsvfs_t *zfsvfs, lr_create_t *lr, boolean_t byteswap) VN_RELE(ZTOV(dzp)); + if (zfsvfs->z_fuid_replay) + zfs_fuid_info_free(zfsvfs->z_fuid_replay); + zfsvfs->z_fuid_replay = NULL; return (error); } @@ -147,6 +547,7 @@ zfs_replay_remove(zfsvfs_t *zfsvfs, lr_remove_t *lr, boolean_t byteswap) struct componentname cn; vnode_t *vp; int error; + int vflg = 0; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); @@ -154,7 +555,8 @@ zfs_replay_remove(zfsvfs_t *zfsvfs, lr_remove_t *lr, boolean_t byteswap) if ((error = zfs_zget(zfsvfs, lr->lr_doid, &dzp)) != 0) return (error); - bzero(&cn, sizeof(cn)); + if (lr->lr_common.lrc_txtype & TX_CI) + vflg |= FIGNORECASE; cn.cn_nameptr = name; cn.cn_namelen = strlen(name); cn.cn_nameiop = DELETE; @@ -171,10 +573,10 @@ zfs_replay_remove(zfsvfs_t *zfsvfs, lr_remove_t *lr, boolean_t byteswap) switch ((int)lr->lr_common.lrc_txtype) { case TX_REMOVE: - error = VOP_REMOVE(ZTOV(dzp), vp, &cn); + error = VOP_REMOVE(ZTOV(dzp), vp, &cn /*,vflg*/); break; case TX_RMDIR: - error = VOP_RMDIR(ZTOV(dzp), vp, &cn); + error = VOP_RMDIR(ZTOV(dzp), vp, &cn /*,vflg*/); break; default: error = ENOTSUP; @@ -194,6 +596,7 @@ zfs_replay_link(zfsvfs_t *zfsvfs, lr_link_t *lr, boolean_t byteswap) znode_t *dzp, *zp; struct componentname cn; int error; + int vflg = 0; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); @@ -206,6 +609,8 @@ zfs_replay_link(zfsvfs_t *zfsvfs, lr_link_t *lr, boolean_t byteswap) return (error); } + if (lr->lr_common.lrc_txtype & TX_CI) + vflg |= FIGNORECASE; cn.cn_nameptr = name; cn.cn_cred = kcred; cn.cn_thread = curthread; @@ -213,7 +618,7 @@ zfs_replay_link(zfsvfs_t *zfsvfs, lr_link_t *lr, boolean_t byteswap) vn_lock(ZTOV(dzp), LK_EXCLUSIVE | LK_RETRY); vn_lock(ZTOV(zp), LK_EXCLUSIVE | LK_RETRY); - error = VOP_LINK(ZTOV(dzp), ZTOV(zp), &cn); + error = VOP_LINK(ZTOV(dzp), ZTOV(zp), &cn /*,vflg*/); VOP_UNLOCK(ZTOV(zp), 0); VOP_UNLOCK(ZTOV(dzp), 0); @@ -233,6 +638,7 @@ zfs_replay_rename(zfsvfs_t *zfsvfs, lr_rename_t *lr, boolean_t byteswap) vnode_t *svp, *tvp; kthread_t *td = curthread; int error; + int vflg = 0; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); @@ -245,9 +651,10 @@ zfs_replay_rename(zfsvfs_t *zfsvfs, lr_rename_t *lr, boolean_t byteswap) return (error); } + if (lr->lr_common.lrc_txtype & TX_CI) + vflg |= FIGNORECASE; svp = tvp = NULL; - bzero(&scn, sizeof(scn)); scn.cn_nameptr = sname; scn.cn_namelen = strlen(sname); scn.cn_nameiop = DELETE; @@ -262,7 +669,6 @@ zfs_replay_rename(zfsvfs_t *zfsvfs, lr_rename_t *lr, boolean_t byteswap) goto fail; VOP_UNLOCK(svp, 0); - bzero(&tcn, sizeof(tcn)); tcn.cn_nameptr = tname; tcn.cn_namelen = strlen(tname); tcn.cn_nameiop = RENAME; @@ -279,7 +685,7 @@ zfs_replay_rename(zfsvfs_t *zfsvfs, lr_rename_t *lr, boolean_t byteswap) goto fail; } - error = VOP_RENAME(ZTOV(sdzp), svp, &scn, ZTOV(tdzp), tvp, &tcn); + error = VOP_RENAME(ZTOV(sdzp), svp, &scn, ZTOV(tdzp), tvp, &tcn /*,vflg*/); return (error); fail: if (svp != NULL) @@ -334,13 +740,21 @@ static int zfs_replay_setattr(zfsvfs_t *zfsvfs, lr_setattr_t *lr, boolean_t byteswap) { znode_t *zp; - vattr_t va; + xvattr_t xva; + vattr_t *vap = &xva.xva_vattr; vnode_t *vp; int error; + void *start; - if (byteswap) + 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) { /* * As we can log setattrs out of order, it's possible the @@ -352,35 +766,112 @@ zfs_replay_setattr(zfsvfs_t *zfsvfs, lr_setattr_t *lr, boolean_t byteswap) return (error); } - zfs_init_vattr(&va, lr->lr_mask, lr->lr_mode, + zfs_init_vattr(vap, lr->lr_mask, lr->lr_mode, lr->lr_uid, lr->lr_gid, 0, lr->lr_foid); - va.va_size = lr->lr_size; - ZFS_TIME_DECODE(&va.va_atime, lr->lr_atime); - ZFS_TIME_DECODE(&va.va_mtime, lr->lr_mtime); + 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, &va, kcred); + 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); } static int -zfs_replay_acl(zfsvfs_t *zfsvfs, lr_acl_t *lr, boolean_t byteswap) +zfs_replay_acl_v0(zfsvfs_t *zfsvfs, lr_acl_v0_t *lr, boolean_t byteswap) { ace_t *ace = (ace_t *)(lr + 1); /* ace array follows lr_acl_t */ -#ifdef TODO 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) { + /* + * As we can log acls out of order, it's possible the + * file has been removed. In this case just drop the acl + * and return success. + */ + if (error == ENOENT) + error = 0; + return (error); + } + + bzero(&vsa, sizeof (vsa)); + vsa.vsa_mask = VSA_ACE | VSA_ACECNT; + vsa.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); +} + +/* + * Replaying ACLs is complicated by FUID support. + * The log record may contain some optional data + * to be used for replaying FUID's. These pieces + * are the actual FUIDs that were created initially. + * The FUID table index may no longer be valid and + * during zfs_create() a new index may be assigned. + * Because of this the log will contain the original + * doman+rid in order to create a new FUID. + * + * The individual ACEs may contain an ephemeral uid/gid which is no + * longer valid and will need to be replaced with an actual FUID. + * + */ +static int +zfs_replay_acl(zfsvfs_t *zfsvfs, lr_acl_t *lr, boolean_t byteswap) +{ + ace_t *ace = (ace_t *)(lr + 1); + vsecattr_t vsa; znode_t *zp; int error; if (byteswap) { byteswap_uint64_array(lr, sizeof (*lr)); - zfs_ace_byteswap(ace, lr->lr_aclcnt); + zfs_ace_byteswap(ace, lr->lr_acl_bytes, B_FALSE); + if (lr->lr_fuidcnt) { + byteswap_uint64_array((caddr_t)ace + + ZIL_ACE_LENGTH(lr->lr_acl_bytes), + lr->lr_fuidcnt * sizeof (uint64_t)); + } } if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) { @@ -396,15 +887,30 @@ zfs_replay_acl(zfsvfs_t *zfsvfs, lr_acl_t *lr, boolean_t byteswap) #ifdef TODO bzero(&vsa, sizeof (vsa)); - vsa.vsa_mask = VSA_ACE | VSA_ACECNT; + vsa.vsa_mask = VSA_ACE | VSA_ACECNT | VSA_ACE_ACLFLAGS; vsa.vsa_aclcnt = lr->lr_aclcnt; vsa.vsa_aclentp = ace; + vsa.vsa_aclentsz = lr->lr_acl_bytes; + vsa.vsa_aclflags = lr->lr_acl_flags; + + if (lr->lr_fuidcnt) { + void *fuidstart = (caddr_t)ace + + ZIL_ACE_LENGTH(lr->lr_acl_bytes); + + zfsvfs->z_fuid_replay = + zfs_replay_fuids(fuidstart, &fuidstart, + lr->lr_fuidcnt, lr->lr_domcnt, 0, 0); + } + + error = VOP_SETSECATTR(ZTOV(zp), &vsa, 0, kcred, NULL); - error = VOP_SETSECATTR(ZTOV(zp), &vsa, 0, kcred); + if (zfsvfs->z_fuid_replay) + zfs_fuid_info_free(zfsvfs->z_fuid_replay); #else error = EOPNOTSUPP; #endif + zfsvfs->z_fuid_replay = NULL; VN_RELE(ZTOV(zp)); return (error); @@ -426,5 +932,12 @@ zil_replay_func_t *zfs_replay_vector[TX_MAX_TYPE] = { zfs_replay_write, /* TX_WRITE */ zfs_replay_truncate, /* TX_TRUNCATE */ zfs_replay_setattr, /* TX_SETATTR */ + zfs_replay_acl_v0, /* TX_ACL_V0 */ zfs_replay_acl, /* TX_ACL */ + zfs_replay_create_acl, /* TX_CREATE_ACL */ + zfs_replay_create, /* TX_CREATE_ATTR */ + zfs_replay_create_acl, /* TX_CREATE_ACL_ATTR */ + zfs_replay_create_acl, /* TX_MKDIR_ACL */ + zfs_replay_create, /* TX_MKDIR_ATTR */ + zfs_replay_create_acl, /* TX_MKDIR_ACL_ATTR */ }; |