Illumos #3956, #3957, #3958, #3959, #3960, #3961, #3962

3956 ::vdev -r should work with pipelines
3957 ztest should update the cachefile before killing itself
3958 multiple scans can lead to partial resilvering
3959 ddt entries are not always resilvered
3960 dsl_scan can skip over dedup-ed blocks if physical birth != logical birth
3961 freed gang blocks are not resilvered and can cause pool to suspend
3962 ztest should print out zfs debug buffer before exiting
Reviewed by: Matthew Ahrens <[email protected]>
Reviewed by: Adam Leventhal <[email protected]>
Approved by: Richard Lowe <[email protected]>

References:
  https://www.illumos.org/issues/3956
  https://www.illumos.org/issues/3957
  https://www.illumos.org/issues/3958
  https://www.illumos.org/issues/3959
  https://www.illumos.org/issues/3960
  https://www.illumos.org/issues/3961
  https://www.illumos.org/issues/3962
  illumos/illumos-gate@b4952e17e8858d3225793b28788278de9fe6038d

Ported-by: Richard Yao <[email protected]>
Signed-off-by: Brian Behlendorf <[email protected]>

Porting notes:

1. zfs_dbgmsg_print() is only used in userland. Since we do not have
   mdb on Linux, it does not make sense to make it available in the
   kernel. This means that a build failure will occur if any future
   kernel patch depends on it. However, that is unlikely given that
   this functionality was added to support zdb.

2. zfs_dbgmsg_print() is only invoked for -VVV or greater log levels.
   This preserves the existing behavior of minimal noise when running
   with -V, and -VV.

3. In vdev_config_generate() the call to nvlist_alloc() was not
   changed to fnvlist_alloc() because we must pass KM_PUSHPAGE in
   the txg_sync context.

1 files changed, 16 insertions, 5 deletions

diff --git a/module/zfs/dsl_scan.c b/module/zfs/dsl_scan.c
index 6cc08ab47..eef509bda 100644
--- a/module/zfs/dsl_scan.c
+++ b/module/zfs/dsl_scan.c
@@ -190,6 +190,7 @@ dsl_scan_setup_sync(void *arg, dmu_tx_t *tx)
 	scn->scn_phys.scn_errors = 0;
 	scn->scn_phys.scn_to_examine = spa->spa_root_vdev->vdev_stat.vs_alloc;
 	scn->scn_restart_txg = 0;
+	scn->scn_done_txg = 0;
 	spa_scan_stat_init(spa);
 
 	if (DSL_SCAN_IS_SCRUB_RESILVER(scn)) {
@@ -776,7 +777,7 @@ dsl_scan_visitbp(blkptr_t *bp, const zbookmark_t *zb,
 	 * Don't scan it now unless we need to because something
 	 * under it was modified.
 	 */
-	if (bp->blk_birth <= scn->scn_phys.scn_cur_max_txg) {
+	if (BP_PHYSICAL_BIRTH(bp) <= scn->scn_phys.scn_cur_max_txg) {
 		scan_funcs[scn->scn_phys.scn_func](dp, bp, zb);
 	}
 	if (buf)
@@ -1227,7 +1228,7 @@ dsl_scan_ddt_entry(dsl_scan_t *scn, enum zio_checksum checksum,
 
 	for (p = 0; p < DDT_PHYS_TYPES; p++, ddp++) {
 		if (ddp->ddp_phys_birth == 0 ||
-		    ddp->ddp_phys_birth > scn->scn_phys.scn_cur_max_txg)
+		    ddp->ddp_phys_birth > scn->scn_phys.scn_max_txg)
 			continue;
 		ddt_bp_create(checksum, ddk, ddp, &bp);
 
@@ -1475,6 +1476,16 @@ dsl_scan_sync(dsl_pool_t *dp, dmu_tx_t *tx)
 	if (scn->scn_phys.scn_state != DSS_SCANNING)
 		return;
 
+	if (scn->scn_done_txg == tx->tx_txg) {
+		ASSERT(!scn->scn_pausing);
+		/* finished with scan. */
+		zfs_dbgmsg("txg %llu scan complete", tx->tx_txg);
+		dsl_scan_done(scn, B_TRUE, tx);
+		ASSERT3U(spa->spa_scrub_inflight, ==, 0);
+		dsl_scan_sync_state(scn, tx);
+		return;
+	}
+
 	if (scn->scn_phys.scn_ddt_bookmark.ddb_class <=
 	    scn->scn_phys.scn_ddt_class_max) {
 		zfs_dbgmsg("doing scan sync txg %llu; "
@@ -1510,9 +1521,9 @@ dsl_scan_sync(dsl_pool_t *dp, dmu_tx_t *tx)
 	    (longlong_t)NSEC2MSEC(gethrtime() - scn->scn_sync_start_time));
 
 	if (!scn->scn_pausing) {
-		/* finished with scan. */
-		zfs_dbgmsg("finished scan txg %llu", (longlong_t)tx->tx_txg);
-		dsl_scan_done(scn, B_TRUE, tx);
+		scn->scn_done_txg = tx->tx_txg + 1;
+		zfs_dbgmsg("txg %llu traversal complete, waiting till txg %llu",
+		    tx->tx_txg, scn->scn_done_txg);
 	}
 
 	if (DSL_SCAN_IS_SCRUB_RESILVER(scn)) {