Finally... Import the latest open-source ZFS version - (SPA) 28.

Few new things available from now on:

- Data deduplication.
- Triple parity RAIDZ (RAIDZ3).
- zfs diff.
- zpool split.
- Snapshot holds.
- zpool import -F. Allows to rewind corrupted pool to earlier
  transaction group.
- Possibility to import pool in read-only mode.

MFC after:	1 month

1 files changed, 61 insertions, 117 deletions

diff --git a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_log.c b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_log.c
index 3105088..29378d8 100644
--- a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_log.c
+++ b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_log.c
@@ -19,8 +19,7 @@
  * CDDL HEADER END
  */
 /*
- * Copyright 2008 Sun Microsystems, Inc.  All rights reserved.
- * Use is subject to license terms.
+ * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
  */
 
 #include <sys/types.h>
@@ -44,14 +43,6 @@
 #include <sys/zfs_fuid.h>
 #include <sys/dsl_dataset.h>
 
-#define	ZFS_HANDLE_REPLAY(zilog, tx) \
-	if (zilog->zl_replay) { \
-		dsl_dataset_dirty(dmu_objset_ds(zilog->zl_os), tx); \
-		zilog->zl_replayed_seq[dmu_tx_get_txg(tx) & TXG_MASK] = \
-		    zilog->zl_replaying_seq; \
-		return; \
-	}
-
 /*
  * These zfs_log_* functions must be called within a dmu tx, in one
  * of 2 contexts depending on zilog->z_replay:
@@ -180,6 +171,15 @@ zfs_log_xvattr(lr_attr_t *lrattr, xvattr_t *xvap)
 		ZFS_TIME_ENCODE(&xoap->xoa_createtime, crtime);
 	if (XVA_ISSET_REQ(xvap, XAT_AV_SCANSTAMP))
 		bcopy(xoap->xoa_av_scanstamp, scanstamp, AV_SCANSTAMP_SZ);
+	if (XVA_ISSET_REQ(xvap, XAT_REPARSE))
+		*attrs |= (xoap->xoa_reparse == 0) ? 0 :
+		    XAT0_REPARSE;
+	if (XVA_ISSET_REQ(xvap, XAT_OFFLINE))
+		*attrs |= (xoap->xoa_offline == 0) ? 0 :
+		    XAT0_OFFLINE;
+	if (XVA_ISSET_REQ(xvap, XAT_SPARSE))
+		*attrs |= (xoap->xoa_sparse == 0) ? 0 :
+		    XAT0_SPARSE;
 }
 
 static void *
@@ -241,7 +241,6 @@ zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
     zfs_fuid_info_t *fuidp, vattr_t *vap)
 {
 	itx_t *itx;
-	uint64_t seq;
 	lr_create_t *lr;
 	lr_acl_create_t *lracl;
 	size_t aclsize;
@@ -253,11 +252,9 @@ zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
 	size_t namesize = strlen(name) + 1;
 	size_t fuidsz = 0;
 
-	if (zilog == NULL)
+	if (zil_replaying(zilog, tx))
 		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.
@@ -288,21 +285,25 @@ zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
 	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;
+	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_phys->zp_gid)) {
-		lr->lr_gid = (uint64_t)zp->z_phys->zp_gid;
+	if (!IS_EPHEMERAL(zp->z_gid)) {
+		lr->lr_gid = (uint64_t)zp->z_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;
+	(void) sa_lookup(zp->z_sa_hdl, SA_ZPL_GEN(zp->z_zfsvfs), &lr->lr_gen,
+	    sizeof (uint64_t));
+	(void) sa_lookup(zp->z_sa_hdl, SA_ZPL_CRTIME(zp->z_zfsvfs),
+	    lr->lr_crtime, sizeof (uint64_t) * 2);
+
+	if (sa_lookup(zp->z_sa_hdl, SA_ZPL_RDEV(zp->z_zfsvfs), &lr->lr_rdev,
+	    sizeof (lr->lr_rdev)) != 0)
+		lr->lr_rdev = 0;
 
 	/*
 	 * Fill in xvattr info if any
@@ -341,9 +342,7 @@ zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
 	 */
 	bcopy(name, end, namesize);
 
-	seq = zil_itx_assign(zilog, itx, tx);
-	dzp->z_last_itx = seq;
-	zp->z_last_itx = seq;
+	zil_itx_assign(zilog, itx, tx);
 }
 
 /*
@@ -351,25 +350,23 @@ zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
  */
 void
 zfs_log_remove(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
-	znode_t *dzp, char *name)
+	znode_t *dzp, char *name, uint64_t foid)
 {
 	itx_t *itx;
-	uint64_t seq;
 	lr_remove_t *lr;
 	size_t namesize = strlen(name) + 1;
 
-	if (zilog == NULL)
+	if (zil_replaying(zilog, tx))
 		return;
 
-	ZFS_HANDLE_REPLAY(zilog, tx); /* exits if replay */
-
 	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;
+	itx->itx_oid = foid;
+
+	zil_itx_assign(zilog, itx, tx);
 }
 
 /*
@@ -380,24 +377,19 @@ 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)
+	if (zil_replaying(zilog, tx))
 		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;
+	zil_itx_assign(zilog, itx, tx);
 }
 
 /*
@@ -408,32 +400,28 @@ 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 (zilog == NULL)
+	if (zil_replaying(zilog, tx))
 		return;
 
-	ZFS_HANDLE_REPLAY(zilog, tx); /* exits if replay */
-
 	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];
+	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(zp->z_zfsvfs), &lr->lr_gen,
+	    sizeof (uint64_t));
+	(void) sa_lookup(zp->z_sa_hdl, SA_ZPL_CRTIME(zp->z_zfsvfs),
+	    lr->lr_crtime, sizeof (uint64_t) * 2);
 	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;
+	zil_itx_assign(zilog, itx, tx);
 }
 
 /*
@@ -444,27 +432,22 @@ zfs_log_rename(zilog_t *zilog, dmu_tx_t *tx, uint64_t 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)
+	if (zil_replaying(zilog, tx))
 		return;
 
-	ZFS_HANDLE_REPLAY(zilog, tx); /* exits if replay */
-
 	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);
+	itx->itx_oid = szp->z_id;
 
-	seq = zil_itx_assign(zilog, itx, tx);
-	sdzp->z_last_itx = seq;
-	tdzp->z_last_itx = seq;
-	szp->z_last_itx = seq;
+	zil_itx_assign(zilog, itx, tx);
 }
 
 /*
@@ -472,9 +455,6 @@ zfs_log_rename(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
  */
 ssize_t zfs_immediate_write_sz = 32768;
 
-#define	ZIL_MAX_LOG_DATA (SPA_MAXBLOCKSIZE - sizeof (zil_trailer_t) - \
-    sizeof (lr_write_t))
-
 void
 zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
 	znode_t *zp, offset_t off, ssize_t resid, int ioflag)
@@ -482,37 +462,17 @@ zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
 	itx_wr_state_t write_state;
 	boolean_t slogging;
 	uintptr_t fsync_cnt;
+	ssize_t immediate_write_sz;
 
-	if (zilog == NULL || zp->z_unlinked)
+	if (zil_replaying(zilog, tx) || zp->z_unlinked)
 		return;
 
-	ZFS_HANDLE_REPLAY(zilog, tx); /* exits if replay */
+	immediate_write_sz = (zilog->zl_logbias == ZFS_LOGBIAS_THROUGHPUT)
+	    ? 0 : zfs_immediate_write_sz;
 
-	/*
-	 * Writes are handled in three different ways:
-	 *
-	 * WR_INDIRECT:
-	 *    In this mode, if we need to commit the write later, then the block
-	 *    is immediately written into the file system (using dmu_sync),
-	 *    and a pointer to the block is put into the log record.
-	 *    When the txg commits the block is linked in.
-	 *    This saves additionally writing the data into the log record.
-	 *    There are a few requirements for this to occur:
-	 *	- write is greater than zfs_immediate_write_sz
-	 *	- not using slogs (as slogs are assumed to always be faster
-	 *	  than writing into the main pool)
-	 *	- the write occupies only one block
-	 * WR_COPIED:
-	 *    If we know we'll immediately be committing the
-	 *    transaction (FSYNC or FDSYNC), 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 && resid <= zp->z_blksz)
+	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;
@@ -541,8 +501,7 @@ zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
 		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);
+			zil_itx_destroy(itx);
 			itx = zil_itx_create(txtype, sizeof (*lr));
 			lr = (lr_write_t *)&itx->itx_lr;
 			write_state = WR_NEED_COPY;
@@ -559,13 +518,11 @@ zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
 
 		itx->itx_private = zp->z_zfsvfs;
 
-		if ((zp->z_sync_cnt != 0) || (fsync_cnt != 0) ||
-		    (ioflag & (FSYNC | FDSYNC)))
-			itx->itx_sync = B_TRUE;
-		else
+		if (!(ioflag & (FSYNC | FDSYNC)) && (zp->z_sync_cnt == 0) &&
+		    (fsync_cnt == 0))
 			itx->itx_sync = B_FALSE;
 
-		zp->z_last_itx = zil_itx_assign(zilog, itx, tx);
+		zil_itx_assign(zilog, itx, tx);
 
 		off += len;
 		resid -= len;
@@ -580,14 +537,11 @@ zfs_log_truncate(zilog_t *zilog, dmu_tx_t *tx, int txtype,
 	znode_t *zp, uint64_t off, uint64_t len)
 {
 	itx_t *itx;
-	uint64_t seq;
 	lr_truncate_t *lr;
 
-	if (zilog == NULL || zp->z_unlinked)
+	if (zil_replaying(zilog, tx) || zp->z_unlinked)
 		return;
 
-	ZFS_HANDLE_REPLAY(zilog, tx); /* exits if replay */
-
 	itx = zil_itx_create(txtype, sizeof (*lr));
 	lr = (lr_truncate_t *)&itx->itx_lr;
 	lr->lr_foid = zp->z_id;
@@ -595,8 +549,7 @@ zfs_log_truncate(zilog_t *zilog, dmu_tx_t *tx, int txtype,
 	lr->lr_length = len;
 
 	itx->itx_sync = (zp->z_sync_cnt != 0);
-	seq = zil_itx_assign(zilog, itx, tx);
-	zp->z_last_itx = seq;
+	zil_itx_assign(zilog, itx, tx);
 }
 
 /*
@@ -607,18 +560,14 @@ 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;
-	uint64_t	seq;
 	lr_setattr_t	*lr;
 	xvattr_t	*xvap = (xvattr_t *)vap;
 	size_t		recsize = sizeof (lr_setattr_t);
 	void		*start;
 
-
-	if (zilog == NULL || zp->z_unlinked)
+	if (zil_replaying(zilog, tx) || zp->z_unlinked)
 		return;
 
-	ZFS_HANDLE_REPLAY(zilog, tx); /* exits if replay */
-
 	/*
 	 * If XVATTR set, then log record size needs to allow
 	 * for lr_attr_t + xvattr mask, mapsize and create time
@@ -662,8 +611,7 @@ zfs_log_setattr(zilog_t *zilog, dmu_tx_t *tx, int txtype,
 		(void) zfs_log_fuid_domains(fuidp, start);
 
 	itx->itx_sync = (zp->z_sync_cnt != 0);
-	seq = zil_itx_assign(zilog, itx, tx);
-	zp->z_last_itx = seq;
+	zil_itx_assign(zilog, itx, tx);
 }
 
 /*
@@ -674,7 +622,6 @@ zfs_log_acl(zilog_t *zilog, dmu_tx_t *tx, znode_t *zp,
     vsecattr_t *vsecp, zfs_fuid_info_t *fuidp)
 {
 	itx_t *itx;
-	uint64_t seq;
 	lr_acl_v0_t *lrv0;
 	lr_acl_t *lr;
 	int txtype;
@@ -682,11 +629,9 @@ zfs_log_acl(zilog_t *zilog, dmu_tx_t *tx, znode_t *zp,
 	size_t txsize;
 	size_t aclbytes = vsecp->vsa_aclentsz;
 
-	if (zilog == NULL || zp->z_unlinked)
+	if (zil_replaying(zilog, tx) || zp->z_unlinked)
 		return;
 
-	ZFS_HANDLE_REPLAY(zilog, tx); /* exits if replay */
-
 	txtype = (zp->z_zfsvfs->z_version < ZPL_VERSION_FUID) ?
 	    TX_ACL_V0 : TX_ACL;
 
@@ -732,6 +677,5 @@ zfs_log_acl(zilog_t *zilog, dmu_tx_t *tx, znode_t *zp,
 	}
 
 	itx->itx_sync = (zp->z_sync_cnt != 0);
-	seq = zil_itx_assign(zilog, itx, tx);
-	zp->z_last_itx = seq;
+	zil_itx_assign(zilog, itx, tx);
 }