fix a screw up in r258371

Pointyhat to:	avg

uts/common/fs/zfs/space_reftree.c

@@ -0,0 +1,159 @@
+/*
+ * 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
+ */
+/*
+ * Copyright 2009 Sun Microsystems, Inc.  All rights reserved.
+ * Use is subject to license terms.
+ */
+/*
+ * Copyright (c) 2013 by Delphix. All rights reserved.
+ */
+
+#include <sys/zfs_context.h>
+#include <sys/range_tree.h>
+#include <sys/space_reftree.h>
+
+/*
+ * Space reference trees.
+ *
+ * A range tree is a collection of integers.  Every integer is either
+ * in the tree, or it's not.  A space reference tree generalizes
+ * the idea: it allows its members to have arbitrary reference counts,
+ * as opposed to the implicit reference count of 0 or 1 in a range tree.
+ * This representation comes in handy when computing the union or
+ * intersection of multiple space maps.  For example, the union of
+ * N range trees is the subset of the reference tree with refcnt >= 1.
+ * The intersection of N range trees is the subset with refcnt >= N.
+ *
+ * [It's very much like a Fourier transform.  Unions and intersections
+ * are hard to perform in the 'range tree domain', so we convert the trees
+ * into the 'reference count domain', where it's trivial, then invert.]
+ *
+ * vdev_dtl_reassess() uses computations of this form to determine
+ * DTL_MISSING and DTL_OUTAGE for interior vdevs -- e.g. a RAID-Z vdev
+ * has an outage wherever refcnt >= vdev_nparity + 1, and a mirror vdev
+ * has an outage wherever refcnt >= vdev_children.
+ */
+static int
+space_reftree_compare(const void *x1, const void *x2)
+{
+	const space_ref_t *sr1 = x1;
+	const space_ref_t *sr2 = x2;
+
+	if (sr1->sr_offset < sr2->sr_offset)
+		return (-1);
+	if (sr1->sr_offset > sr2->sr_offset)
+		return (1);
+
+	if (sr1 < sr2)
+		return (-1);
+	if (sr1 > sr2)
+		return (1);
+
+	return (0);
+}
+
+void
+space_reftree_create(avl_tree_t *t)
+{
+	avl_create(t, space_reftree_compare,
+	    sizeof (space_ref_t), offsetof(space_ref_t, sr_node));
+}
+
+void
+space_reftree_destroy(avl_tree_t *t)
+{
+	space_ref_t *sr;
+	void *cookie = NULL;
+
+	while ((sr = avl_destroy_nodes(t, &cookie)) != NULL)
+		kmem_free(sr, sizeof (*sr));
+
+	avl_destroy(t);
+}
+
+static void
+space_reftree_add_node(avl_tree_t *t, uint64_t offset, int64_t refcnt)
+{
+	space_ref_t *sr;
+
+	sr = kmem_alloc(sizeof (*sr), KM_SLEEP);
+	sr->sr_offset = offset;
+	sr->sr_refcnt = refcnt;
+
+	avl_add(t, sr);
+}
+
+void
+space_reftree_add_seg(avl_tree_t *t, uint64_t start, uint64_t end,
+	int64_t refcnt)
+{
+	space_reftree_add_node(t, start, refcnt);
+	space_reftree_add_node(t, end, -refcnt);
+}
+
+/*
+ * Convert (or add) a range tree into a reference tree.
+ */
+void
+space_reftree_add_map(avl_tree_t *t, range_tree_t *rt, int64_t refcnt)
+{
+	range_seg_t *rs;
+
+	ASSERT(MUTEX_HELD(rt->rt_lock));
+
+	for (rs = avl_first(&rt->rt_root); rs; rs = AVL_NEXT(&rt->rt_root, rs))
+		space_reftree_add_seg(t, rs->rs_start, rs->rs_end, refcnt);
+}
+
+/*
+ * Convert a reference tree into a range tree.  The range tree will contain
+ * all members of the reference tree for which refcnt >= minref.
+ */
+void
+space_reftree_generate_map(avl_tree_t *t, range_tree_t *rt, int64_t minref)
+{
+	uint64_t start = -1ULL;
+	int64_t refcnt = 0;
+	space_ref_t *sr;
+
+	ASSERT(MUTEX_HELD(rt->rt_lock));
+
+	range_tree_vacate(rt, NULL, NULL);
+
+	for (sr = avl_first(t); sr != NULL; sr = AVL_NEXT(t, sr)) {
+		refcnt += sr->sr_refcnt;
+		if (refcnt >= minref) {
+			if (start == -1ULL) {
+				start = sr->sr_offset;
+			}
+		} else {
+			if (start != -1ULL) {
+				uint64_t end = sr->sr_offset;
+				ASSERT(start <= end);
+				if (end > start)
+					range_tree_add(rt, start, end - start);
+				start = -1ULL;
+			}
+		}
+	}
+	ASSERT(refcnt == 0);
+	ASSERT(start == -1ULL);
+}

uts/common/fs/zfs/sys/range_tree.h

@@ -0,0 +1,96 @@
+/*
+ * 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
+ */
+/*
+ * Copyright 2009 Sun Microsystems, Inc.  All rights reserved.
+ * Use is subject to license terms.
+ */
+
+/*
+ * Copyright (c) 2013 by Delphix. All rights reserved.
+ */
+
+#ifndef _SYS_RANGE_TREE_H
+#define	_SYS_RANGE_TREE_H
+
+#include <sys/avl.h>
+#include <sys/dmu.h>
+
+#ifdef	__cplusplus
+extern "C" {
+#endif
+
+#define	RANGE_TREE_HISTOGRAM_SIZE	64
+
+typedef struct range_tree_ops range_tree_ops_t;
+
+typedef struct range_tree {
+	avl_tree_t	rt_root;	/* offset-ordered segment AVL tree */
+	uint64_t	rt_space;	/* sum of all segments in the map */
+	range_tree_ops_t *rt_ops;
+	void		*rt_arg;
+
+	/*
+	 * The rt_histogram maintains a histogram of ranges. Each bucket,
+	 * rt_histogram[i], contains the number of ranges whose size is:
+	 * 2^i <= size of range in bytes < 2^(i+1)
+	 */
+	uint64_t	rt_histogram[RANGE_TREE_HISTOGRAM_SIZE];
+	kmutex_t	*rt_lock;	/* pointer to lock that protects map */
+} range_tree_t;
+
+typedef struct range_seg {
+	avl_node_t	rs_node;	/* AVL node */
+	avl_node_t	rs_pp_node;	/* AVL picker-private node */
+	uint64_t	rs_start;	/* starting offset of this segment */
+	uint64_t	rs_end;		/* ending offset (non-inclusive) */
+} range_seg_t;
+
+struct range_tree_ops {
+	void    (*rtop_create)(range_tree_t *rt, void *arg);
+	void    (*rtop_destroy)(range_tree_t *rt, void *arg);
+	void	(*rtop_add)(range_tree_t *rt, range_seg_t *rs, void *arg);
+	void    (*rtop_remove)(range_tree_t *rt, range_seg_t *rs, void *arg);
+	void	(*rtop_vacate)(range_tree_t *rt, void *arg);
+};
+
+typedef void range_tree_func_t(void *arg, uint64_t start, uint64_t size);
+
+void range_tree_init(void);
+void range_tree_fini(void);
+range_tree_t *range_tree_create(range_tree_ops_t *ops, void *arg, kmutex_t *lp);
+void range_tree_destroy(range_tree_t *rt);
+boolean_t range_tree_contains(range_tree_t *rt, uint64_t start, uint64_t size);
+uint64_t range_tree_space(range_tree_t *rt);
+void range_tree_verify(range_tree_t *rt, uint64_t start, uint64_t size);
+void range_tree_swap(range_tree_t **rtsrc, range_tree_t **rtdst);
+void range_tree_stat_verify(range_tree_t *rt);
+
+void range_tree_add(void *arg, uint64_t start, uint64_t size);
+void range_tree_remove(void *arg, uint64_t start, uint64_t size);
+
+void range_tree_vacate(range_tree_t *rt, range_tree_func_t *func, void *arg);
+void range_tree_walk(range_tree_t *rt, range_tree_func_t *func, void *arg);
+
+#ifdef	__cplusplus
+}
+#endif
+
+#endif	/* _SYS_RANGE_TREE_H */