MFC r268858: MFV r268850:

Change the interaction between the DMU and ARC so that when the DMU is
shutting down an objset, we do not evict the data from the ARC.  Instead
we simply coordinate the destruction of the DMU's data with the ARC.

The only case where we actually need to explicitly evict from the ARC is
when dbuf_rele_and_unlock() determines that the administrator has requested
that it not be kept in memory, via the primarycache/secondarycache properties.
In this case, we evict the data from the ARC by its blkptr_t, the same way
as when a block is freed we explicitly evict it from the ARC.

Illumos issue:
    4631 zvol_get_stats triggering too many reads

1 files changed, 25 insertions, 13 deletions

diff --git a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dbuf.c b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dbuf.c
index 5ab6a65..b681ea4 100644
--- a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dbuf.c
+++ b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dbuf.c
@@ -181,8 +181,7 @@ dbuf_hash_insert(dmu_buf_impl_t *db)
 }
 
 /*
- * Remove an entry from the hash table.  This operation will
- * fail if there are any existing holds on the db.
+ * Remove an entry from the hash table.  It must be in the EVICTING state.
  */
 static void
 dbuf_hash_remove(dmu_buf_impl_t *db)
@@ -194,7 +193,7 @@ dbuf_hash_remove(dmu_buf_impl_t *db)
 	dmu_buf_impl_t *dbf, **dbp;
 
 	/*
-	 * We musn't hold db_mtx to maintin lock ordering:
+	 * We musn't hold db_mtx to maintain lock ordering:
 	 * DBUF_HASH_MUTEX > db_mtx.
 	 */
 	ASSERT(refcount_is_zero(&db->db_holds));
@@ -431,7 +430,6 @@ static void
 dbuf_set_data(dmu_buf_impl_t *db, arc_buf_t *buf)
 {
 	ASSERT(MUTEX_HELD(&db->db_mtx));
-	ASSERT(db->db_buf == NULL || !arc_has_callback(db->db_buf));
 	db->db_buf = buf;
 	if (buf != NULL) {
 		ASSERT(buf->b_data != NULL);
@@ -1544,12 +1542,15 @@ dbuf_assign_arcbuf(dmu_buf_impl_t *db, arc_buf_t *buf, dmu_tx_t *tx)
  * when we are not holding the dn_dbufs_mtx, we can't clear the
  * entry in the dn_dbufs list.  We have to wait until dbuf_destroy()
  * in this case.  For callers from the DMU we will usually see:
- *	dbuf_clear()->arc_buf_evict()->dbuf_do_evict()->dbuf_destroy()
+ *	dbuf_clear()->arc_clear_callback()->dbuf_do_evict()->dbuf_destroy()
  * For the arc callback, we will usually see:
  *	dbuf_do_evict()->dbuf_clear();dbuf_destroy()
  * Sometimes, though, we will get a mix of these two:
- *	DMU: dbuf_clear()->arc_buf_evict()
+ *	DMU: dbuf_clear()->arc_clear_callback()
  *	ARC: dbuf_do_evict()->dbuf_destroy()
+ *
+ * This routine will dissociate the dbuf from the arc, by calling
+ * arc_clear_callback(), but will not evict the data from the ARC.
  */
 void
 dbuf_clear(dmu_buf_impl_t *db)
@@ -1557,7 +1558,7 @@ dbuf_clear(dmu_buf_impl_t *db)
 	dnode_t *dn;
 	dmu_buf_impl_t *parent = db->db_parent;
 	dmu_buf_impl_t *dndb;
-	int dbuf_gone = FALSE;
+	boolean_t dbuf_gone = B_FALSE;
 
 	ASSERT(MUTEX_HELD(&db->db_mtx));
 	ASSERT(refcount_is_zero(&db->db_holds));
@@ -1603,7 +1604,7 @@ dbuf_clear(dmu_buf_impl_t *db)
 	}
 
 	if (db->db_buf)
-		dbuf_gone = arc_buf_evict(db->db_buf);
+		dbuf_gone = arc_clear_callback(db->db_buf);
 
 	if (!dbuf_gone)
 		mutex_exit(&db->db_mtx);
@@ -1771,8 +1772,7 @@ dbuf_create(dnode_t *dn, uint8_t level, uint64_t blkid,
 static int
 dbuf_do_evict(void *private)
 {
-	arc_buf_t *buf = private;
-	dmu_buf_impl_t *db = buf->b_private;
+	dmu_buf_impl_t *db = private;
 
 	if (!MUTEX_HELD(&db->db_mtx))
 		mutex_enter(&db->db_mtx);
@@ -2135,11 +2135,23 @@ dbuf_rele_and_unlock(dmu_buf_impl_t *db, void *tag)
 			 * block on-disk. If so, then we simply evict
 			 * ourselves.
 			 */
-			if (!DBUF_IS_CACHEABLE(db) ||
-			    arc_buf_eviction_needed(db->db_buf))
+			if (!DBUF_IS_CACHEABLE(db)) {
+				if (db->db_blkptr != NULL &&
+				    !BP_IS_HOLE(db->db_blkptr) &&
+				    !BP_IS_EMBEDDED(db->db_blkptr)) {
+					spa_t *spa =
+					    dmu_objset_spa(db->db_objset);
+					blkptr_t bp = *db->db_blkptr;
+					dbuf_clear(db);
+					arc_freed(spa, &bp);
+				} else {
+					dbuf_clear(db);
+				}
+			} else if (arc_buf_eviction_needed(db->db_buf)) {
 				dbuf_clear(db);
-			else
+			} else {
 				mutex_exit(&db->db_mtx);
+			}
 		}
 	} else {
 		mutex_exit(&db->db_mtx);