Merge branch 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2

* 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2: (28 commits)
  Ocfs2: Teach local-mounted ocfs2 to handle unwritten_extents correctly.
  ocfs2/dlm: Do not migrate resource to a node that is leaving the domain
  ocfs2/dlm: Add new dlm message DLM_BEGIN_EXIT_DOMAIN_MSG
  Ocfs2/move_extents: Set several trivial constraints for threshold.
  Ocfs2/move_extents: Let defrag handle partial extent moving.
  Ocfs2/move_extents: move/defrag extents within a certain range.
  Ocfs2/move_extents: helper to calculate the defraging length in one run.
  Ocfs2/move_extents: move entire/partial extent.
  Ocfs2/move_extents: helpers to update the group descriptor and global bitmap inode.
  Ocfs2/move_extents: helper to probe a proper region to move in an alloc group.
  Ocfs2/move_extents: helper to validate and adjust moving goal.
  Ocfs2/move_extents: find the victim alloc group, where the given #blk fits.
  Ocfs2/move_extents: defrag a range of extent.
  Ocfs2/move_extents: move a range of extent.
  Ocfs2/move_extents: lock allocators and reserve metadata blocks and data clusters for extents moving.
  Ocfs2/move_extents: Add basic framework and source files for extent moving.
  Ocfs2/move_extents: Adding new ioctl code 'OCFS2_IOC_MOVE_EXT' to ocfs2.
  Ocfs2/refcounttree: Publicize couple of funcs from refcounttree.c
  Ocfs2: Add a new code 'OCFS2_INFO_FREEFRAG' for o2info ioctl.
  Ocfs2: Add a new code 'OCFS2_INFO_FREEINODE' for o2info ioctl.
  ...

Documentation/ABI/obsolete/o2cb → Documentation/ABI/removed/o2cb

 What:		/sys/o2cb symlink
-Date:		Dec 2005
-KernelVersion:	2.6.16
+Date:		May 2011
+KernelVersion:	2.6.40
 Contact:	ocfs2-devel@oss.oracle.com
-Description:	This is a symlink: /sys/o2cb to /sys/fs/o2cb. The symlink will
-		be removed when new versions of ocfs2-tools which know to look
+Description:	This is a symlink: /sys/o2cb to /sys/fs/o2cb. The symlink is
+		removed when new versions of ocfs2-tools which know to look
 		in /sys/fs/o2cb are sufficiently prevalent. Don't code new
 		software to look here, it should try /sys/fs/o2cb instead.
-		See Documentation/ABI/stable/o2cb for more information on usage.
 Users:		ocfs2-tools. It's sufficient to mail proposed changes to
 		ocfs2-devel@oss.oracle.com.

Documentation/feature-removal-schedule.txt

@@ -262,16 +262,6 @@ Who:	Michael Buesch <mb@bu3sch.de>
 
 ---------------------------
 
-What:	/sys/o2cb symlink
-When:	January 2010
-Why:	/sys/fs/o2cb is the proper location for this information - /sys/o2cb
-	exists as a symlink for backwards compatibility for old versions of
-	ocfs2-tools. 2 years should be sufficient time to phase in new versions
-	which know to look in /sys/fs/o2cb.
-Who:	ocfs2-devel@oss.oracle.com
-
----------------------------
-
 What:	Ability for non root users to shm_get hugetlb pages based on mlock
 	resource limits
 When:	2.6.31

Documentation/filesystems/ocfs2.txt

@@ -46,9 +46,15 @@ errors=panic		Panic and halt the machine if an error occurs.
 intr		(*)	Allow signals to interrupt cluster operations.
 nointr			Do not allow signals to interrupt cluster
 			operations.
+noatime			Do not update access time.
+relatime(*)		Update atime if the previous atime is older than
+			mtime or ctime
+strictatime		Always update atime, but the minimum update interval
+			is specified by atime_quantum.
 atime_quantum=60(*)	OCFS2 will not update atime unless this number
 			of seconds has passed since the last update.
-			Set to zero to always update atime.
+			Set to zero to always update atime. This option need
+			work with strictatime.
 data=ordered	(*)	All data are forced directly out to the main file
 			system prior to its metadata being committed to the
 			journal.

fs/ocfs2/Makefile

@@ -30,6 +30,7 @@ ocfs2-objs := \
 	namei.o 		\
 	refcounttree.o		\
 	reservations.o		\
+	move_extents.o		\
 	resize.o		\
 	slot_map.o 		\
 	suballoc.o 		\

fs/ocfs2/alloc.c

@@ -29,6 +29,7 @@
 #include <linux/highmem.h>
 #include <linux/swap.h>
 #include <linux/quotaops.h>
+#include <linux/blkdev.h>
 
 #include <cluster/masklog.h>
 
@@ -7184,3 +7185,168 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
 out:
 	return ret;
 }
+
+static int ocfs2_trim_extent(struct super_block *sb,
+			     struct ocfs2_group_desc *gd,
+			     u32 start, u32 count)
+{
+	u64 discard, bcount;
+
+	bcount = ocfs2_clusters_to_blocks(sb, count);
+	discard = le64_to_cpu(gd->bg_blkno) +
+			ocfs2_clusters_to_blocks(sb, start);
+
+	trace_ocfs2_trim_extent(sb, (unsigned long long)discard, bcount);
+
+	return sb_issue_discard(sb, discard, bcount, GFP_NOFS, 0);
+}
+
+static int ocfs2_trim_group(struct super_block *sb,
+			    struct ocfs2_group_desc *gd,
+			    u32 start, u32 max, u32 minbits)
+{
+	int ret = 0, count = 0, next;
+	void *bitmap = gd->bg_bitmap;
+
+	if (le16_to_cpu(gd->bg_free_bits_count) < minbits)
+		return 0;
+
+	trace_ocfs2_trim_group((unsigned long long)le64_to_cpu(gd->bg_blkno),
+			       start, max, minbits);
+
+	while (start < max) {
+		start = ocfs2_find_next_zero_bit(bitmap, max, start);
+		if (start >= max)
+			break;
+		next = ocfs2_find_next_bit(bitmap, max, start);
+
+		if ((next - start) >= minbits) {
+			ret = ocfs2_trim_extent(sb, gd,
+						start, next - start);
+			if (ret < 0) {
+				mlog_errno(ret);
+				break;
+			}
+			count += next - start;
+		}
+		start = next + 1;
+
+		if (fatal_signal_pending(current)) {
+			count = -ERESTARTSYS;
+			break;
+		}
+
+		if ((le16_to_cpu(gd->bg_free_bits_count) - count) < minbits)
+			break;
+	}
+
+	if (ret < 0)
+		count = ret;
+
+	return count;
+}
+
+int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
+{
+	struct ocfs2_super *osb = OCFS2_SB(sb);
+	u64 start, len, trimmed, first_group, last_group, group;
+	int ret, cnt;
+	u32 first_bit, last_bit, minlen;
+	struct buffer_head *main_bm_bh = NULL;
+	struct inode *main_bm_inode = NULL;
+	struct buffer_head *gd_bh = NULL;
+	struct ocfs2_dinode *main_bm;
+	struct ocfs2_group_desc *gd = NULL;
+
+	start = range->start >> osb->s_clustersize_bits;
+	len = range->len >> osb->s_clustersize_bits;
+	minlen = range->minlen >> osb->s_clustersize_bits;
+	trimmed = 0;
+
+	if (!len) {
+		range->len = 0;
+		return 0;
+	}
+
+	if (minlen >= osb->bitmap_cpg)
+		return -EINVAL;
+
+	main_bm_inode = ocfs2_get_system_file_inode(osb,
+						    GLOBAL_BITMAP_SYSTEM_INODE,
+						    OCFS2_INVALID_SLOT);
+	if (!main_bm_inode) {
+		ret = -EIO;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	mutex_lock(&main_bm_inode->i_mutex);
+
+	ret = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 0);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out_mutex;
+	}
+	main_bm = (struct ocfs2_dinode *)main_bm_bh->b_data;
+
+	if (start >= le32_to_cpu(main_bm->i_clusters)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	if (start + len > le32_to_cpu(main_bm->i_clusters))
+		len = le32_to_cpu(main_bm->i_clusters) - start;
+
+	trace_ocfs2_trim_fs(start, len, minlen);
+
+	/* Determine first and last group to examine based on start and len */
+	first_group = ocfs2_which_cluster_group(main_bm_inode, start);
+	if (first_group == osb->first_cluster_group_blkno)
+		first_bit = start;
+	else
+		first_bit = start - ocfs2_blocks_to_clusters(sb, first_group);
+	last_group = ocfs2_which_cluster_group(main_bm_inode, start + len - 1);
+	last_bit = osb->bitmap_cpg;
+
+	for (group = first_group; group <= last_group;) {
+		if (first_bit + len >= osb->bitmap_cpg)
+			last_bit = osb->bitmap_cpg;
+		else
+			last_bit = first_bit + len;
+
+		ret = ocfs2_read_group_descriptor(main_bm_inode,
+						  main_bm, group,
+						  &gd_bh);
+		if (ret < 0) {
+			mlog_errno(ret);
+			break;
+		}
+
+		gd = (struct ocfs2_group_desc *)gd_bh->b_data;
+		cnt = ocfs2_trim_group(sb, gd, first_bit, last_bit, minlen);
+		brelse(gd_bh);
+		gd_bh = NULL;
+		if (cnt < 0) {
+			ret = cnt;
+			mlog_errno(ret);
+			break;
+		}
+
+		trimmed += cnt;
+		len -= osb->bitmap_cpg - first_bit;
+		first_bit = 0;
+		if (group == osb->first_cluster_group_blkno)
+			group = ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg);
+		else
+			group += ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg);
+	}
+	range->len = trimmed * sb->s_blocksize;
+out_unlock:
+	ocfs2_inode_unlock(main_bm_inode, 0);
+	brelse(main_bm_bh);
+out_mutex:
+	mutex_unlock(&main_bm_inode->i_mutex);
+	iput(main_bm_inode);
+out:
+	return ret;
+}

fs/ocfs2/alloc.h

@@ -239,6 +239,7 @@ int ocfs2_find_leaf(struct ocfs2_caching_info *ci,
 		    struct buffer_head **leaf_bh);
 int ocfs2_search_extent_list(struct ocfs2_extent_list *el, u32 v_cluster);
 
+int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range);
 /*
  * Helper function to look at the # of clusters in an extent record.
  */

fs/ocfs2/cluster/sys.c

@@ -57,7 +57,6 @@ static struct kset *o2cb_kset;
 void o2cb_sys_shutdown(void)
 {
 	mlog_sys_shutdown();
-	sysfs_remove_link(NULL, "o2cb");
 	kset_unregister(o2cb_kset);
 }
 
@@ -69,14 +68,6 @@ int o2cb_sys_init(void)
 	if (!o2cb_kset)
 		return -ENOMEM;
 
-	/*
-	 * Create this symlink for backwards compatibility with old
-	 * versions of ocfs2-tools which look for things in /sys/o2cb.
-	 */
-	ret = sysfs_create_link(NULL, &o2cb_kset->kobj, "o2cb");
-	if (ret)
-		goto error;
-
 	ret = sysfs_create_group(&o2cb_kset->kobj, &o2cb_attr_group);
 	if (ret)
 		goto error;

fs/ocfs2/dlm/dlmcommon.h

@@ -144,6 +144,7 @@ struct dlm_ctxt
 	wait_queue_head_t dlm_join_events;
 	unsigned long live_nodes_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
 	unsigned long domain_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	unsigned long exit_domain_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
 	unsigned long recovery_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
 	struct dlm_recovery_ctxt reco;
 	spinlock_t master_lock;
@@ -401,6 +402,18 @@ static inline int dlm_lvb_is_empty(char *lvb)
 	return 1;
 }
 
+static inline char *dlm_list_in_text(enum dlm_lockres_list idx)
+{
+	if (idx == DLM_GRANTED_LIST)
+		return "granted";
+	else if (idx == DLM_CONVERTING_LIST)
+		return "converting";
+	else if (idx == DLM_BLOCKED_LIST)
+		return "blocked";
+	else
+		return "unknown";
+}
+
 static inline struct list_head *
 dlm_list_idx_to_ptr(struct dlm_lock_resource *res, enum dlm_lockres_list idx)
 {
@@ -448,6 +461,7 @@ enum {
 	DLM_FINALIZE_RECO_MSG		= 518,
 	DLM_QUERY_REGION		= 519,
 	DLM_QUERY_NODEINFO		= 520,
+	DLM_BEGIN_EXIT_DOMAIN_MSG	= 521,
 };
 
 struct dlm_reco_node_data

fs/ocfs2/dlm/dlmdebug.c

@@ -756,6 +756,12 @@ static int debug_state_print(struct dlm_ctxt *dlm, char *buf, int len)
 				 buf + out, len - out);
 	out += snprintf(buf + out, len - out, "\n");
 
+	/* Exit Domain Map: xx xx xx */
+	out += snprintf(buf + out, len - out, "Exit Domain Map: ");
+	out += stringify_nodemap(dlm->exit_domain_map, O2NM_MAX_NODES,
+				 buf + out, len - out);
+	out += snprintf(buf + out, len - out, "\n");
+
 	/* Live Map: xx xx xx */
 	out += snprintf(buf + out, len - out, "Live Map: ");
 	out += stringify_nodemap(dlm->live_nodes_map, O2NM_MAX_NODES,

fs/ocfs2/dlm/dlmdomain.c

@@ -132,10 +132,12 @@ static DECLARE_WAIT_QUEUE_HEAD(dlm_domain_events);
  * New in version 1.1:
  *	- Message DLM_QUERY_REGION added to support global heartbeat
  *	- Message DLM_QUERY_NODEINFO added to allow online node removes
+ * New in version 1.2:
+ * 	- Message DLM_BEGIN_EXIT_DOMAIN_MSG added to mark start of exit domain
  */
 static const struct dlm_protocol_version dlm_protocol = {
 	.pv_major = 1,
-	.pv_minor = 1,
+	.pv_minor = 2,
 };
 
 #define DLM_DOMAIN_BACKOFF_MS 200
@@ -449,14 +451,18 @@ static int dlm_migrate_all_locks(struct dlm_ctxt *dlm)
 			dropped = dlm_empty_lockres(dlm, res);
 
 			spin_lock(&res->spinlock);
-			__dlm_lockres_calc_usage(dlm, res);
-			iter = res->hash_node.next;
+			if (dropped)
+				__dlm_lockres_calc_usage(dlm, res);
+			else
+				iter = res->hash_node.next;
 			spin_unlock(&res->spinlock);
 
 			dlm_lockres_put(res);
 
-			if (dropped)
+			if (dropped) {
+				cond_resched_lock(&dlm->spinlock);
 				goto redo_bucket;
+			}
 		}
 		cond_resched_lock(&dlm->spinlock);
 		num += n;
@@ -486,6 +492,28 @@ static int dlm_no_joining_node(struct dlm_ctxt *dlm)
 	return ret;
 }
 
+static int dlm_begin_exit_domain_handler(struct o2net_msg *msg, u32 len,
+					 void *data, void **ret_data)
+{
+	struct dlm_ctxt *dlm = data;
+	unsigned int node;
+	struct dlm_exit_domain *exit_msg = (struct dlm_exit_domain *) msg->buf;
+
+	if (!dlm_grab(dlm))
+		return 0;
+
+	node = exit_msg->node_idx;
+	mlog(0, "%s: Node %u sent a begin exit domain message\n", dlm->name, node);
+
+	spin_lock(&dlm->spinlock);
+	set_bit(node, dlm->exit_domain_map);
+	spin_unlock(&dlm->spinlock);
+
+	dlm_put(dlm);
+
+	return 0;
+}
+
 static void dlm_mark_domain_leaving(struct dlm_ctxt *dlm)
 {
 	/* Yikes, a double spinlock! I need domain_lock for the dlm
@@ -542,6 +570,7 @@ static int dlm_exit_domain_handler(struct o2net_msg *msg, u32 len, void *data,
 
 	spin_lock(&dlm->spinlock);
 	clear_bit(node, dlm->domain_map);
+	clear_bit(node, dlm->exit_domain_map);
 	__dlm_print_nodes(dlm);
 
 	/* notify anything attached to the heartbeat events */
@@ -554,29 +583,56 @@ static int dlm_exit_domain_handler(struct o2net_msg *msg, u32 len, void *data,
 	return 0;
 }
 
-static int dlm_send_one_domain_exit(struct dlm_ctxt *dlm,
+static int dlm_send_one_domain_exit(struct dlm_ctxt *dlm, u32 msg_type,
 				    unsigned int node)
 {
 	int status;
 	struct dlm_exit_domain leave_msg;
 
-	mlog(0, "Asking node %u if we can leave the domain %s me = %u\n",
-		  node, dlm->name, dlm->node_num);
+	mlog(0, "%s: Sending domain exit message %u to node %u\n", dlm->name,
+	     msg_type, node);
 
 	memset(&leave_msg, 0, sizeof(leave_msg));
 	leave_msg.node_idx = dlm->node_num;
 
-	status = o2net_send_message(DLM_EXIT_DOMAIN_MSG, dlm->key,
-				    &leave_msg, sizeof(leave_msg), node,
-				    NULL);
+	status = o2net_send_message(msg_type, dlm->key, &leave_msg,
+				    sizeof(leave_msg), node, NULL);
 	if (status < 0)
-		mlog(ML_ERROR, "Error %d when sending message %u (key 0x%x) to "
-		     "node %u\n", status, DLM_EXIT_DOMAIN_MSG, dlm->key, node);
-	mlog(0, "status return %d from o2net_send_message\n", status);
+		mlog(ML_ERROR, "Error %d sending domain exit message %u "
+		     "to node %u on domain %s\n", status, msg_type, node,
+		     dlm->name);
 
 	return status;
 }
 
+static void dlm_begin_exit_domain(struct dlm_ctxt *dlm)
+{
+	int node = -1;
+
+	/* Support for begin exit domain was added in 1.2 */
+	if (dlm->dlm_locking_proto.pv_major == 1 &&
+	    dlm->dlm_locking_proto.pv_minor < 2)
+		return;
+
+	/*
+	 * Unlike DLM_EXIT_DOMAIN_MSG, DLM_BEGIN_EXIT_DOMAIN_MSG is purely
+	 * informational. Meaning if a node does not receive the message,
+	 * so be it.
+	 */
+	spin_lock(&dlm->spinlock);
+	while (1) {
+		node = find_next_bit(dlm->domain_map, O2NM_MAX_NODES, node + 1);
+		if (node >= O2NM_MAX_NODES)
+			break;
+		if (node == dlm->node_num)
+			continue;
+
+		spin_unlock(&dlm->spinlock);
+		dlm_send_one_domain_exit(dlm, DLM_BEGIN_EXIT_DOMAIN_MSG, node);
+		spin_lock(&dlm->spinlock);
+	}
+	spin_unlock(&dlm->spinlock);
+}
 
 static void dlm_leave_domain(struct dlm_ctxt *dlm)
 {
@@ -602,7 +658,8 @@ static void dlm_leave_domain(struct dlm_ctxt *dlm)
 
 		clear_node = 1;
 
-		status = dlm_send_one_domain_exit(dlm, node);
+		status = dlm_send_one_domain_exit(dlm, DLM_EXIT_DOMAIN_MSG,
+						  node);
 		if (status < 0 &&
 		    status != -ENOPROTOOPT &&
 		    status != -ENOTCONN) {
@@ -677,6 +734,7 @@ void dlm_unregister_domain(struct dlm_ctxt *dlm)
 
 	if (leave) {
 		mlog(0, "shutting down domain %s\n", dlm->name);
+		dlm_begin_exit_domain(dlm);
 
 		/* We changed dlm state, notify the thread */
 		dlm_kick_thread(dlm, NULL);
@@ -909,6 +967,7 @@ static int dlm_assert_joined_handler(struct o2net_msg *msg, u32 len, void *data,
 		 * leftover join state. */
 		BUG_ON(dlm->joining_node != assert->node_idx);
 		set_bit(assert->node_idx, dlm->domain_map);
+		clear_bit(assert->node_idx, dlm->exit_domain_map);
 		__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
 
 		printk(KERN_NOTICE "o2dlm: Node %u joins domain %s\n",
@@ -1793,6 +1852,13 @@ static int dlm_register_domain_handlers(struct dlm_ctxt *dlm)
 	if (status)
 		goto bail;
 
+	status = o2net_register_handler(DLM_BEGIN_EXIT_DOMAIN_MSG, dlm->key,
+					sizeof(struct dlm_exit_domain),
+					dlm_begin_exit_domain_handler,
+					dlm, NULL, &dlm->dlm_domain_handlers);
+	if (status)
+		goto bail;
+
 bail:
 	if (status)
 		dlm_unregister_domain_handlers(dlm);

fs/ocfs2/dlm/dlmmaster.c

@@ -2339,65 +2339,55 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 	dlm_lockres_put(res);
 }
 
-/* Checks whether the lockres can be migrated. Returns 0 if yes, < 0
- * if not. If 0, numlocks is set to the number of locks in the lockres.
+/*
+ * A migrateable resource is one that is :
+ * 1. locally mastered, and,
+ * 2. zero local locks, and,
+ * 3. one or more non-local locks, or, one or more references
+ * Returns 1 if yes, 0 if not.
  */
 static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
-				      struct dlm_lock_resource *res,
-				      int *numlocks,
-				      int *hasrefs)
+				      struct dlm_lock_resource *res)
 {
-	int ret;
-	int i;
-	int count = 0;
+	enum dlm_lockres_list idx;
+	int nonlocal = 0, node_ref;
 	struct list_head *queue;
 	struct dlm_lock *lock;
+	u64 cookie;
 
 	assert_spin_locked(&res->spinlock);
 
-	*numlocks = 0;
-	*hasrefs = 0;
-
-	ret = -EINVAL;
-	if (res->owner == DLM_LOCK_RES_OWNER_UNKNOWN) {
-		mlog(0, "cannot migrate lockres with unknown owner!\n");
-		goto leave;
-	}
-
-	if (res->owner != dlm->node_num) {
-		mlog(0, "cannot migrate lockres this node doesn't own!\n");
-		goto leave;
-	}
+	if (res->owner != dlm->node_num)
+		return 0;
 
-	ret = 0;
-	queue = &res->granted;
-	for (i = 0; i < 3; i++) {
+        for (idx = DLM_GRANTED_LIST; idx <= DLM_BLOCKED_LIST; idx++) {
+		queue = dlm_list_idx_to_ptr(res, idx);
 		list_for_each_entry(lock, queue, list) {
-			++count;
-			if (lock->ml.node == dlm->node_num) {
-				mlog(0, "found a lock owned by this node still "
-				     "on the %s queue!  will not migrate this "
-				     "lockres\n", (i == 0 ? "granted" :
-						   (i == 1 ? "converting" :
-						    "blocked")));
-				ret = -ENOTEMPTY;
-				goto leave;
+			if (lock->ml.node != dlm->node_num) {
+				nonlocal++;
+				continue;
 			}
+			cookie = be64_to_cpu(lock->ml.cookie);
+			mlog(0, "%s: Not migrateable res %.*s, lock %u:%llu on "
+			     "%s list\n", dlm->name, res->lockname.len,
+			     res->lockname.name,
+			     dlm_get_lock_cookie_node(cookie),
+			     dlm_get_lock_cookie_seq(cookie),
+			     dlm_list_in_text(idx));
+			return 0;
 		}
-		queue++;
 	}
 
-	*numlocks = count;
-
-	count = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
-	if (count < O2NM_MAX_NODES)
-		*hasrefs = 1;
+	if (!nonlocal) {
+		node_ref = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
+		if (node_ref >= O2NM_MAX_NODES)
+			return 0;
+	}
 
-	mlog(0, "%s: res %.*s, Migrateable, locks %d, refs %d\n", dlm->name,
-	     res->lockname.len, res->lockname.name, *numlocks, *hasrefs);
+	mlog(0, "%s: res %.*s, Migrateable\n", dlm->name, res->lockname.len,
+	     res->lockname.name);
 
-leave:
-	return ret;
+	return 1;
 }
 
 /*
@@ -2406,8 +2396,7 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 
 
 static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
-			       struct dlm_lock_resource *res,
-			       u8 target)
+			       struct dlm_lock_resource *res, u8 target)
 {
 	struct dlm_master_list_entry *mle = NULL;
 	struct dlm_master_list_entry *oldmle = NULL;
@@ -2416,37 +2405,20 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
 	const char *name;
 	unsigned int namelen;
 	int mle_added = 0;
-	int numlocks, hasrefs;
 	int wake = 0;
 
 	if (!dlm_grab(dlm))
 		return -EINVAL;
 
+	BUG_ON(target == O2NM_MAX_NODES);
+
 	name = res->lockname.name;
 	namelen = res->lockname.len;
 
-	mlog(0, "%s: Migrating %.*s to %u\n", dlm->name, namelen, name, target);
-
-	/*
-	 * ensure this lockres is a proper candidate for migration
-	 */
-	spin_lock(&res->spinlock);
-	ret = dlm_is_lockres_migrateable(dlm, res, &numlocks, &hasrefs);
-	if (ret < 0) {
-		spin_unlock(&res->spinlock);
-		goto leave;
-	}
-	spin_unlock(&res->spinlock);
-
-	/* no work to do */
-	if (numlocks == 0 && !hasrefs)
-		goto leave;
-
-	/*
-	 * preallocate up front
-	 * if this fails, abort
-	 */
+	mlog(0, "%s: Migrating %.*s to node %u\n", dlm->name, namelen, name,
+	     target);
 
+	/* preallocate up front. if this fails, abort */
 	ret = -ENOMEM;
 	mres = (struct dlm_migratable_lockres *) __get_free_page(GFP_NOFS);
 	if (!mres) {
@@ -2461,36 +2433,11 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
 	}
 	ret = 0;
 
-	/*
-	 * find a node to migrate the lockres to
-	 */
-
-	spin_lock(&dlm->spinlock);
-	/* pick a new node */
-	if (!test_bit(target, dlm->domain_map) ||
-	    target >= O2NM_MAX_NODES) {
-		target = dlm_pick_migration_target(dlm, res);
-	}
-	mlog(0, "%s: res %.*s, Node %u chosen for migration\n", dlm->name,
-	     namelen, name, target);
-
-	if (target >= O2NM_MAX_NODES ||
-	    !test_bit(target, dlm->domain_map)) {
-		/* target chosen is not alive */
-		ret = -EINVAL;
-	}
-
-	if (ret) {
-		spin_unlock(&dlm->spinlock);
-		goto fail;
-	}
-
-	mlog(0, "continuing with target = %u\n", target);
-
 	/*
 	 * clear any existing master requests and
 	 * add the migration mle to the list
 	 */
+	spin_lock(&dlm->spinlock);
 	spin_lock(&dlm->master_lock);
 	ret = dlm_add_migration_mle(dlm, res, mle, &oldmle, name,
 				    namelen, target, dlm->node_num);
@@ -2531,6 +2478,7 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
 			dlm_put_mle(mle);
 		} else if (mle) {
 			kmem_cache_free(dlm_mle_cache, mle);
+			mle = NULL;
 		}
 		goto leave;
 	}
@@ -2652,69 +2600,52 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
 	if (wake)
 		wake_up(&res->wq);
 
-	/* TODO: cleanup */
 	if (mres)
 		free_page((unsigned long)mres);
 
 	dlm_put(dlm);
 
-	mlog(0, "returning %d\n", ret);
+	mlog(0, "%s: Migrating %.*s to %u, returns %d\n", dlm->name, namelen,
+	     name, target, ret);
 	return ret;
 }
 
 #define DLM_MIGRATION_RETRY_MS  100
 
-/* Should be called only after beginning the domain leave process.
+/*
+ * Should be called only after beginning the domain leave process.
  * There should not be any remaining locks on nonlocal lock resources,
  * and there should be no local locks left on locally mastered resources.
  *
  * Called with the dlm spinlock held, may drop it to do migration, but
  * will re-acquire before exit.
  *
- * Returns: 1 if dlm->spinlock was dropped/retaken, 0 if never dropped */
+ * Returns: 1 if dlm->spinlock was dropped/retaken, 0 if never dropped
+ */
 int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 {
 	int ret;
 	int lock_dropped = 0;
-	int numlocks, hasrefs;
+	u8 target = O2NM_MAX_NODES;
+
+	assert_spin_locked(&dlm->spinlock);
 
 	spin_lock(&res->spinlock);
-	if (res->owner != dlm->node_num) {
-		if (!__dlm_lockres_unused(res)) {
-			mlog(ML_ERROR, "%s:%.*s: this node is not master, "
-			     "trying to free this but locks remain\n",
-			     dlm->name, res->lockname.len, res->lockname.name);
-		}
-		spin_unlock(&res->spinlock);
-		goto leave;
-	}
+	if (dlm_is_lockres_migrateable(dlm, res))
+		target = dlm_pick_migration_target(dlm, res);
+	spin_unlock(&res->spinlock);
 
-	/* No need to migrate a lockres having no locks */
-	ret = dlm_is_lockres_migrateable(dlm, res, &numlocks, &hasrefs);
-	if (ret >= 0 && numlocks == 0 && !hasrefs) {
-		spin_unlock(&res->spinlock);
+	if (target == O2NM_MAX_NODES)
 		goto leave;
-	}
-	spin_unlock(&res->spinlock);
 
 	/* Wheee! Migrate lockres here! Will sleep so drop spinlock. */
 	spin_unlock(&dlm->spinlock);
 	lock_dropped = 1;
-	while (1) {
-		ret = dlm_migrate_lockres(dlm, res, O2NM_MAX_NODES);
-		if (ret >= 0)
-			break;
-		if (ret == -ENOTEMPTY) {
-			mlog(ML_ERROR, "lockres %.*s still has local locks!\n",
-		     		res->lockname.len, res->lockname.name);
-			BUG();
-		}
-
-		mlog(0, "lockres %.*s: migrate failed, "
-		     "retrying\n", res->lockname.len,
-		     res->lockname.name);
-		msleep(DLM_MIGRATION_RETRY_MS);
-	}
+	ret = dlm_migrate_lockres(dlm, res, target);
+	if (ret)
+		mlog(0, "%s: res %.*s, Migrate to node %u failed with %d\n",
+		     dlm->name, res->lockname.len, res->lockname.name,
+		     target, ret);
 	spin_lock(&dlm->spinlock);
 leave:
 	return lock_dropped;
@@ -2898,61 +2829,55 @@ static void dlm_remove_nonlocal_locks(struct dlm_ctxt *dlm,
 	}
 }
 
-/* for now this is not too intelligent.  we will
- * need stats to make this do the right thing.
- * this just finds the first lock on one of the
- * queues and uses that node as the target. */
+/*
+ * Pick a node to migrate the lock resource to. This function selects a
+ * potential target based first on the locks and then on refmap. It skips
+ * nodes that are in the process of exiting the domain.
+ */
 static u8 dlm_pick_migration_target(struct dlm_ctxt *dlm,
 				    struct dlm_lock_resource *res)
 {
-	int i;
+	enum dlm_lockres_list idx;
 	struct list_head *queue = &res->granted;
 	struct dlm_lock *lock;
-	int nodenum;
+	int noderef;
+	u8 nodenum = O2NM_MAX_NODES;
 
 	assert_spin_locked(&dlm->spinlock);
+	assert_spin_locked(&res->spinlock);
 
-	spin_lock(&res->spinlock);
-	for (i=0; i<3; i++) {
+	/* Go through all the locks */
+	for (idx = DLM_GRANTED_LIST; idx <= DLM_BLOCKED_LIST; idx++) {
+		queue = dlm_list_idx_to_ptr(res, idx);
 		list_for_each_entry(lock, queue, list) {
-			/* up to the caller to make sure this node
-			 * is alive */
-			if (lock->ml.node != dlm->node_num) {
-				spin_unlock(&res->spinlock);
-				return lock->ml.node;
-			}
+			if (lock->ml.node == dlm->node_num)
+				continue;
+			if (test_bit(lock->ml.node, dlm->exit_domain_map))
+				continue;
+			nodenum = lock->ml.node;
+			goto bail;
 		}
-		queue++;
-	}
-
-	nodenum = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
-	if (nodenum < O2NM_MAX_NODES) {
-		spin_unlock(&res->spinlock);
-		return nodenum;
 	}
-	spin_unlock(&res->spinlock);
-	mlog(0, "have not found a suitable target yet! checking domain map\n");
 
-	/* ok now we're getting desperate.  pick anyone alive. */
-	nodenum = -1;
+	/* Go thru the refmap */
+	noderef = -1;
 	while (1) {
-		nodenum = find_next_bit(dlm->domain_map,
-					O2NM_MAX_NODES, nodenum+1);
-		mlog(0, "found %d in domain map\n", nodenum);
-		if (nodenum >= O2NM_MAX_NODES)
+		noderef = find_next_bit(res->refmap, O2NM_MAX_NODES,
+					noderef + 1);
+		if (noderef >= O2NM_MAX_NODES)
 			break;
-		if (nodenum != dlm->node_num) {
-			mlog(0, "picking %d\n", nodenum);
-			return nodenum;
-		}
+		if (noderef == dlm->node_num)
+			continue;
+		if (test_bit(noderef, dlm->exit_domain_map))
+			continue;
+		nodenum = noderef;
+		goto bail;
 	}
 
-	mlog(0, "giving up.  no master to migrate to\n");
-	return DLM_LOCK_RES_OWNER_UNKNOWN;
+bail:
+	return nodenum;
 }
 
-
-
 /* this is called by the new master once all lockres
  * data has been received */
 static int dlm_do_migrate_request(struct dlm_ctxt *dlm,

fs/ocfs2/dlm/dlmrecovery.c

@@ -2393,6 +2393,7 @@ static void __dlm_hb_node_down(struct dlm_ctxt *dlm, int idx)
 
 	mlog(0, "node %u being removed from domain map!\n", idx);
 	clear_bit(idx, dlm->domain_map);
+	clear_bit(idx, dlm->exit_domain_map);
 	/* wake up migration waiters if a node goes down.
 	 * perhaps later we can genericize this for other waiters. */
 	wake_up(&dlm->migration_wq);

fs/ocfs2/dlmfs/dlmfs.c

@@ -88,7 +88,7 @@ struct workqueue_struct *user_dlm_worker;
  *		  signifies a bast fired on the lock.
  */
 #define DLMFS_CAPABILITIES "bast stackglue"
-extern int param_set_dlmfs_capabilities(const char *val,
+static int param_set_dlmfs_capabilities(const char *val,
 					struct kernel_param *kp)
 {
 	printk(KERN_ERR "%s: readonly parameter\n", kp->name);

fs/ocfs2/file.c

@@ -2670,6 +2670,7 @@ const struct file_operations ocfs2_fops_no_plocks = {
 	.flock		= ocfs2_flock,
 	.splice_read	= ocfs2_file_splice_read,
 	.splice_write	= ocfs2_file_splice_write,
+	.fallocate	= ocfs2_fallocate,
 };
 
 const struct file_operations ocfs2_dops_no_plocks = {

fs/ocfs2/ioctl.c

@@ -22,6 +22,11 @@
 #include "ioctl.h"
 #include "resize.h"
 #include "refcounttree.h"
+#include "sysfile.h"
+#include "dir.h"
+#include "buffer_head_io.h"
+#include "suballoc.h"
+#include "move_extents.h"
 
 #include <linux/ext2_fs.h>
 
@@ -35,31 +40,27 @@
  * be -EFAULT.  The error will be returned from the ioctl(2) call.  It's
  * just a best-effort to tell userspace that this request caused the error.
  */
-static inline void __o2info_set_request_error(struct ocfs2_info_request *kreq,
+static inline void o2info_set_request_error(struct ocfs2_info_request *kreq,
 					struct ocfs2_info_request __user *req)
 {
 	kreq->ir_flags |= OCFS2_INFO_FL_ERROR;
 	(void)put_user(kreq->ir_flags, (__u32 __user *)&(req->ir_flags));
 }
 
-#define o2info_set_request_error(a, b) \
-		__o2info_set_request_error((struct ocfs2_info_request *)&(a), b)
-
-static inline void __o2info_set_request_filled(struct ocfs2_info_request *req)
+static inline void o2info_set_request_filled(struct ocfs2_info_request *req)
 {
 	req->ir_flags |= OCFS2_INFO_FL_FILLED;
 }
 
-#define o2info_set_request_filled(a) \
-		__o2info_set_request_filled((struct ocfs2_info_request *)&(a))
-
-static inline void __o2info_clear_request_filled(struct ocfs2_info_request *req)
+static inline void o2info_clear_request_filled(struct ocfs2_info_request *req)
 {
 	req->ir_flags &= ~OCFS2_INFO_FL_FILLED;
 }
 
-#define o2info_clear_request_filled(a) \
-		__o2info_clear_request_filled((struct ocfs2_info_request *)&(a))
+static inline int o2info_coherent(struct ocfs2_info_request *req)
+{
+	return (!(req->ir_flags & OCFS2_INFO_FL_NON_COHERENT));
+}
 
 static int ocfs2_get_inode_attr(struct inode *inode, unsigned *flags)
 {
@@ -153,7 +154,7 @@ int ocfs2_info_handle_blocksize(struct inode *inode,
 
 	oib.ib_blocksize = inode->i_sb->s_blocksize;
 
-	o2info_set_request_filled(oib);
+	o2info_set_request_filled(&oib.ib_req);
 
 	if (o2info_to_user(oib, req))
 		goto bail;
@@ -161,7 +162,7 @@ int ocfs2_info_handle_blocksize(struct inode *inode,
 	status = 0;
 bail:
 	if (status)
-		o2info_set_request_error(oib, req);
+		o2info_set_request_error(&oib.ib_req, req);
 
 	return status;
 }
@@ -178,7 +179,7 @@ int ocfs2_info_handle_clustersize(struct inode *inode,
 
 	oic.ic_clustersize = osb->s_clustersize;
 
-	o2info_set_request_filled(oic);
+	o2info_set_request_filled(&oic.ic_req);
 
 	if (o2info_to_user(oic, req))
 		goto bail;
@@ -186,7 +187,7 @@ int ocfs2_info_handle_clustersize(struct inode *inode,
 	status = 0;
 bail:
 	if (status)
-		o2info_set_request_error(oic, req);
+		o2info_set_request_error(&oic.ic_req, req);
 
 	return status;
 }
@@ -203,7 +204,7 @@ int ocfs2_info_handle_maxslots(struct inode *inode,
 
 	oim.im_max_slots = osb->max_slots;
 
-	o2info_set_request_filled(oim);
+	o2info_set_request_filled(&oim.im_req);
 
 	if (o2info_to_user(oim, req))
 		goto bail;
@@ -211,7 +212,7 @@ int ocfs2_info_handle_maxslots(struct inode *inode,
 	status = 0;
 bail:
 	if (status)
-		o2info_set_request_error(oim, req);
+		o2info_set_request_error(&oim.im_req, req);
 
 	return status;
 }
@@ -228,7 +229,7 @@ int ocfs2_info_handle_label(struct inode *inode,
 
 	memcpy(oil.il_label, osb->vol_label, OCFS2_MAX_VOL_LABEL_LEN);
 
-	o2info_set_request_filled(oil);
+	o2info_set_request_filled(&oil.il_req);
 
 	if (o2info_to_user(oil, req))
 		goto bail;
@@ -236,7 +237,7 @@ int ocfs2_info_handle_label(struct inode *inode,
 	status = 0;
 bail:
 	if (status)
-		o2info_set_request_error(oil, req);
+		o2info_set_request_error(&oil.il_req, req);
 
 	return status;
 }
@@ -253,7 +254,7 @@ int ocfs2_info_handle_uuid(struct inode *inode,
 
 	memcpy(oiu.iu_uuid_str, osb->uuid_str, OCFS2_TEXT_UUID_LEN + 1);
 
-	o2info_set_request_filled(oiu);
+	o2info_set_request_filled(&oiu.iu_req);
 
 	if (o2info_to_user(oiu, req))
 		goto bail;
@@ -261,7 +262,7 @@ int ocfs2_info_handle_uuid(struct inode *inode,
 	status = 0;
 bail:
 	if (status)
-		o2info_set_request_error(oiu, req);
+		o2info_set_request_error(&oiu.iu_req, req);
 
 	return status;
 }
@@ -280,7 +281,7 @@ int ocfs2_info_handle_fs_features(struct inode *inode,
 	oif.if_incompat_features = osb->s_feature_incompat;
 	oif.if_ro_compat_features = osb->s_feature_ro_compat;
 
-	o2info_set_request_filled(oif);
+	o2info_set_request_filled(&oif.if_req);
 
 	if (o2info_to_user(oif, req))
 		goto bail;
@@ -288,7 +289,7 @@ int ocfs2_info_handle_fs_features(struct inode *inode,
 	status = 0;
 bail:
 	if (status)
-		o2info_set_request_error(oif, req);
+		o2info_set_request_error(&oif.if_req, req);
 
 	return status;
 }
@@ -305,7 +306,7 @@ int ocfs2_info_handle_journal_size(struct inode *inode,
 
 	oij.ij_journal_size = osb->journal->j_inode->i_size;
 
-	o2info_set_request_filled(oij);
+	o2info_set_request_filled(&oij.ij_req);
 
 	if (o2info_to_user(oij, req))
 		goto bail;
@@ -313,7 +314,408 @@ int ocfs2_info_handle_journal_size(struct inode *inode,
 	status = 0;
 bail:
 	if (status)
-		o2info_set_request_error(oij, req);
+		o2info_set_request_error(&oij.ij_req, req);
+
+	return status;
+}
+
+int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb,
+				struct inode *inode_alloc, u64 blkno,
+				struct ocfs2_info_freeinode *fi, u32 slot)
+{
+	int status = 0, unlock = 0;
+
+	struct buffer_head *bh = NULL;
+	struct ocfs2_dinode *dinode_alloc = NULL;
+
+	if (inode_alloc)
+		mutex_lock(&inode_alloc->i_mutex);
+
+	if (o2info_coherent(&fi->ifi_req)) {
+		status = ocfs2_inode_lock(inode_alloc, &bh, 0);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		}
+		unlock = 1;
+	} else {
+		status = ocfs2_read_blocks_sync(osb, blkno, 1, &bh);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		}
+	}
+
+	dinode_alloc = (struct ocfs2_dinode *)bh->b_data;
+
+	fi->ifi_stat[slot].lfi_total =
+		le32_to_cpu(dinode_alloc->id1.bitmap1.i_total);
+	fi->ifi_stat[slot].lfi_free =
+		le32_to_cpu(dinode_alloc->id1.bitmap1.i_total) -
+		le32_to_cpu(dinode_alloc->id1.bitmap1.i_used);
+
+bail:
+	if (unlock)
+		ocfs2_inode_unlock(inode_alloc, 0);
+
+	if (inode_alloc)
+		mutex_unlock(&inode_alloc->i_mutex);
+
+	brelse(bh);
+
+	return status;
+}
+
+int ocfs2_info_handle_freeinode(struct inode *inode,
+				struct ocfs2_info_request __user *req)
+{
+	u32 i;
+	u64 blkno = -1;
+	char namebuf[40];
+	int status = -EFAULT, type = INODE_ALLOC_SYSTEM_INODE;
+	struct ocfs2_info_freeinode *oifi = NULL;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct inode *inode_alloc = NULL;
+
+	oifi = kzalloc(sizeof(struct ocfs2_info_freeinode), GFP_KERNEL);
+	if (!oifi) {
+		status = -ENOMEM;
+		mlog_errno(status);
+		goto bail;
+	}
+
+	if (o2info_from_user(*oifi, req))
+		goto bail;
+
+	oifi->ifi_slotnum = osb->max_slots;
+
+	for (i = 0; i < oifi->ifi_slotnum; i++) {
+		if (o2info_coherent(&oifi->ifi_req)) {
+			inode_alloc = ocfs2_get_system_file_inode(osb, type, i);
+			if (!inode_alloc) {
+				mlog(ML_ERROR, "unable to get alloc inode in "
+				    "slot %u\n", i);
+				status = -EIO;
+				goto bail;
+			}
+		} else {
+			ocfs2_sprintf_system_inode_name(namebuf,
+							sizeof(namebuf),
+							type, i);
+			status = ocfs2_lookup_ino_from_name(osb->sys_root_inode,
+							    namebuf,
+							    strlen(namebuf),
+							    &blkno);
+			if (status < 0) {
+				status = -ENOENT;
+				goto bail;
+			}
+		}
+
+		status = ocfs2_info_scan_inode_alloc(osb, inode_alloc, blkno, oifi, i);
+		if (status < 0)
+			goto bail;
+
+		iput(inode_alloc);
+		inode_alloc = NULL;
+	}
+
+	o2info_set_request_filled(&oifi->ifi_req);
+
+	if (o2info_to_user(*oifi, req))
+		goto bail;
+
+	status = 0;
+bail:
+	if (status)
+		o2info_set_request_error(&oifi->ifi_req, req);
+
+	kfree(oifi);
+
+	return status;
+}
+
+static void o2ffg_update_histogram(struct ocfs2_info_free_chunk_list *hist,
+				   unsigned int chunksize)
+{
+	int index;
+
+	index = __ilog2_u32(chunksize);
+	if (index >= OCFS2_INFO_MAX_HIST)
+		index = OCFS2_INFO_MAX_HIST - 1;
+
+	hist->fc_chunks[index]++;
+	hist->fc_clusters[index] += chunksize;
+}
+
+static void o2ffg_update_stats(struct ocfs2_info_freefrag_stats *stats,
+			       unsigned int chunksize)
+{
+	if (chunksize > stats->ffs_max)
+		stats->ffs_max = chunksize;
+
+	if (chunksize < stats->ffs_min)
+		stats->ffs_min = chunksize;
+
+	stats->ffs_avg += chunksize;
+	stats->ffs_free_chunks_real++;
+}
+
+void ocfs2_info_update_ffg(struct ocfs2_info_freefrag *ffg,
+			   unsigned int chunksize)
+{
+	o2ffg_update_histogram(&(ffg->iff_ffs.ffs_fc_hist), chunksize);
+	o2ffg_update_stats(&(ffg->iff_ffs), chunksize);
+}
+
+int ocfs2_info_freefrag_scan_chain(struct ocfs2_super *osb,
+				   struct inode *gb_inode,
+				   struct ocfs2_dinode *gb_dinode,
+				   struct ocfs2_chain_rec *rec,
+				   struct ocfs2_info_freefrag *ffg,
+				   u32 chunks_in_group)
+{
+	int status = 0, used;
+	u64 blkno;
+
+	struct buffer_head *bh = NULL;
+	struct ocfs2_group_desc *bg = NULL;
+
+	unsigned int max_bits, num_clusters;
+	unsigned int offset = 0, cluster, chunk;
+	unsigned int chunk_free, last_chunksize = 0;
+
+	if (!le32_to_cpu(rec->c_free))
+		goto bail;
+
+	do {
+		if (!bg)
+			blkno = le64_to_cpu(rec->c_blkno);
+		else
+			blkno = le64_to_cpu(bg->bg_next_group);
+
+		if (bh) {
+			brelse(bh);
+			bh = NULL;
+		}
+
+		if (o2info_coherent(&ffg->iff_req))
+			status = ocfs2_read_group_descriptor(gb_inode,
+							     gb_dinode,
+							     blkno, &bh);
+		else
+			status = ocfs2_read_blocks_sync(osb, blkno, 1, &bh);
+
+		if (status < 0) {
+			mlog(ML_ERROR, "Can't read the group descriptor # "
+			     "%llu from device.", (unsigned long long)blkno);
+			status = -EIO;
+			goto bail;
+		}
+
+		bg = (struct ocfs2_group_desc *)bh->b_data;
+
+		if (!le16_to_cpu(bg->bg_free_bits_count))
+			continue;
+
+		max_bits = le16_to_cpu(bg->bg_bits);
+		offset = 0;
+
+		for (chunk = 0; chunk < chunks_in_group; chunk++) {
+			/*
+			 * last chunk may be not an entire one.
+			 */
+			if ((offset + ffg->iff_chunksize) > max_bits)
+				num_clusters = max_bits - offset;
+			else
+				num_clusters = ffg->iff_chunksize;
+
+			chunk_free = 0;
+			for (cluster = 0; cluster < num_clusters; cluster++) {
+				used = ocfs2_test_bit(offset,
+						(unsigned long *)bg->bg_bitmap);
+				/*
+				 * - chunk_free counts free clusters in #N chunk.
+				 * - last_chunksize records the size(in) clusters
+				 *   for the last real free chunk being counted.
+				 */
+				if (!used) {
+					last_chunksize++;
+					chunk_free++;
+				}
+
+				if (used && last_chunksize) {
+					ocfs2_info_update_ffg(ffg,
+							      last_chunksize);
+					last_chunksize = 0;
+				}
+
+				offset++;
+			}
+
+			if (chunk_free == ffg->iff_chunksize)
+				ffg->iff_ffs.ffs_free_chunks++;
+		}
+
+		/*
+		 * need to update the info for last free chunk.
+		 */
+		if (last_chunksize)
+			ocfs2_info_update_ffg(ffg, last_chunksize);
+
+	} while (le64_to_cpu(bg->bg_next_group));
+
+bail:
+	brelse(bh);
+
+	return status;
+}
+
+int ocfs2_info_freefrag_scan_bitmap(struct ocfs2_super *osb,
+				    struct inode *gb_inode, u64 blkno,
+				    struct ocfs2_info_freefrag *ffg)
+{
+	u32 chunks_in_group;
+	int status = 0, unlock = 0, i;
+
+	struct buffer_head *bh = NULL;
+	struct ocfs2_chain_list *cl = NULL;
+	struct ocfs2_chain_rec *rec = NULL;
+	struct ocfs2_dinode *gb_dinode = NULL;
+
+	if (gb_inode)
+		mutex_lock(&gb_inode->i_mutex);
+
+	if (o2info_coherent(&ffg->iff_req)) {
+		status = ocfs2_inode_lock(gb_inode, &bh, 0);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		}
+		unlock = 1;
+	} else {
+		status = ocfs2_read_blocks_sync(osb, blkno, 1, &bh);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		}
+	}
+
+	gb_dinode = (struct ocfs2_dinode *)bh->b_data;
+	cl = &(gb_dinode->id2.i_chain);
+
+	/*
+	 * Chunksize(in) clusters from userspace should be
+	 * less than clusters in a group.
+	 */
+	if (ffg->iff_chunksize > le16_to_cpu(cl->cl_cpg)) {
+		status = -EINVAL;
+		goto bail;
+	}
+
+	memset(&ffg->iff_ffs, 0, sizeof(struct ocfs2_info_freefrag_stats));
+
+	ffg->iff_ffs.ffs_min = ~0U;
+	ffg->iff_ffs.ffs_clusters =
+			le32_to_cpu(gb_dinode->id1.bitmap1.i_total);
+	ffg->iff_ffs.ffs_free_clusters = ffg->iff_ffs.ffs_clusters -
+			le32_to_cpu(gb_dinode->id1.bitmap1.i_used);
+
+	chunks_in_group = le16_to_cpu(cl->cl_cpg) / ffg->iff_chunksize + 1;
+
+	for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i++) {
+		rec = &(cl->cl_recs[i]);
+		status = ocfs2_info_freefrag_scan_chain(osb, gb_inode,
+							gb_dinode,
+							rec, ffg,
+							chunks_in_group);
+		if (status)
+			goto bail;
+	}
+
+	if (ffg->iff_ffs.ffs_free_chunks_real)
+		ffg->iff_ffs.ffs_avg = (ffg->iff_ffs.ffs_avg /
+					ffg->iff_ffs.ffs_free_chunks_real);
+bail:
+	if (unlock)
+		ocfs2_inode_unlock(gb_inode, 0);
+
+	if (gb_inode)
+		mutex_unlock(&gb_inode->i_mutex);
+
+	if (gb_inode)
+		iput(gb_inode);
+
+	brelse(bh);
+
+	return status;
+}
+
+int ocfs2_info_handle_freefrag(struct inode *inode,
+			       struct ocfs2_info_request __user *req)
+{
+	u64 blkno = -1;
+	char namebuf[40];
+	int status = -EFAULT, type = GLOBAL_BITMAP_SYSTEM_INODE;
+
+	struct ocfs2_info_freefrag *oiff;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct inode *gb_inode = NULL;
+
+	oiff = kzalloc(sizeof(struct ocfs2_info_freefrag), GFP_KERNEL);
+	if (!oiff) {
+		status = -ENOMEM;
+		mlog_errno(status);
+		goto bail;
+	}
+
+	if (o2info_from_user(*oiff, req))
+		goto bail;
+	/*
+	 * chunksize from userspace should be power of 2.
+	 */
+	if ((oiff->iff_chunksize & (oiff->iff_chunksize - 1)) ||
+	    (!oiff->iff_chunksize)) {
+		status = -EINVAL;
+		goto bail;
+	}
+
+	if (o2info_coherent(&oiff->iff_req)) {
+		gb_inode = ocfs2_get_system_file_inode(osb, type,
+						       OCFS2_INVALID_SLOT);
+		if (!gb_inode) {
+			mlog(ML_ERROR, "unable to get global_bitmap inode\n");
+			status = -EIO;
+			goto bail;
+		}
+	} else {
+		ocfs2_sprintf_system_inode_name(namebuf, sizeof(namebuf), type,
+						OCFS2_INVALID_SLOT);
+		status = ocfs2_lookup_ino_from_name(osb->sys_root_inode,
+						    namebuf,
+						    strlen(namebuf),
+						    &blkno);
+		if (status < 0) {
+			status = -ENOENT;
+			goto bail;
+		}
+	}
+
+	status = ocfs2_info_freefrag_scan_bitmap(osb, gb_inode, blkno, oiff);
+	if (status < 0)
+		goto bail;
+
+	o2info_set_request_filled(&oiff->iff_req);
+
+	if (o2info_to_user(*oiff, req))
+		goto bail;
+
+	status = 0;
+bail:
+	if (status)
+		o2info_set_request_error(&oiff->iff_req, req);
+
+	kfree(oiff);
 
 	return status;
 }
@@ -327,7 +729,7 @@ int ocfs2_info_handle_unknown(struct inode *inode,
 	if (o2info_from_user(oir, req))
 		goto bail;
 
-	o2info_clear_request_filled(oir);
+	o2info_clear_request_filled(&oir);
 
 	if (o2info_to_user(oir, req))
 		goto bail;
@@ -335,7 +737,7 @@ int ocfs2_info_handle_unknown(struct inode *inode,
 	status = 0;
 bail:
 	if (status)
-		o2info_set_request_error(oir, req);
+		o2info_set_request_error(&oir, req);
 
 	return status;
 }
@@ -389,6 +791,14 @@ int ocfs2_info_handle_request(struct inode *inode,
 		if (oir.ir_size == sizeof(struct ocfs2_info_journal_size))
 			status = ocfs2_info_handle_journal_size(inode, req);
 		break;
+	case OCFS2_INFO_FREEINODE:
+		if (oir.ir_size == sizeof(struct ocfs2_info_freeinode))
+			status = ocfs2_info_handle_freeinode(inode, req);
+		break;
+	case OCFS2_INFO_FREEFRAG:
+		if (oir.ir_size == sizeof(struct ocfs2_info_freefrag))
+			status = ocfs2_info_handle_freefrag(inode, req);
+		break;
 	default:
 		status = ocfs2_info_handle_unknown(inode, req);
 		break;
@@ -542,6 +952,31 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			return -EFAULT;
 
 		return ocfs2_info_handle(inode, &info, 0);
+	case FITRIM:
+	{
+		struct super_block *sb = inode->i_sb;
+		struct fstrim_range range;
+		int ret = 0;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (copy_from_user(&range, (struct fstrim_range *)arg,
+		    sizeof(range)))
+			return -EFAULT;
+
+		ret = ocfs2_trim_fs(sb, &range);
+		if (ret < 0)
+			return ret;
+
+		if (copy_to_user((struct fstrim_range *)arg, &range,
+		    sizeof(range)))
+			return -EFAULT;
+
+		return 0;
+	}
+	case OCFS2_IOC_MOVE_EXT:
+		return ocfs2_ioctl_move_extents(filp, (void __user *)arg);
 	default:
 		return -ENOTTY;
 	}
@@ -569,6 +1004,7 @@ long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case OCFS2_IOC_GROUP_EXTEND:
 	case OCFS2_IOC_GROUP_ADD:
 	case OCFS2_IOC_GROUP_ADD64:
+	case FITRIM:
 		break;
 	case OCFS2_IOC_REFLINK:
 		if (copy_from_user(&args, (struct reflink_arguments *)arg,
@@ -584,6 +1020,8 @@ long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 			return -EFAULT;
 
 		return ocfs2_info_handle(inode, &info, 1);
+	case OCFS2_IOC_MOVE_EXT:
+		break;
 	default:
 		return -ENOIOCTLCMD;
 	}

fs/ocfs2/move_extents.c

+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * move_extents.c
+ *
+ * Copyright (C) 2011 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#include <linux/fs.h>
+#include <linux/types.h>
+#include <linux/mount.h>
+#include <linux/swap.h>
+
+#include <cluster/masklog.h>
+
+#include "ocfs2.h"
+#include "ocfs2_ioctl.h"
+
+#include "alloc.h"
+#include "aops.h"
+#include "dlmglue.h"
+#include "extent_map.h"
+#include "inode.h"
+#include "journal.h"
+#include "suballoc.h"
+#include "uptodate.h"
+#include "super.h"
+#include "dir.h"
+#include "buffer_head_io.h"
+#include "sysfile.h"
+#include "suballoc.h"
+#include "refcounttree.h"
+#include "move_extents.h"
+
+struct ocfs2_move_extents_context {
+	struct inode *inode;
+	struct file *file;
+	int auto_defrag;
+	int partial;
+	int credits;
+	u32 new_phys_cpos;
+	u32 clusters_moved;
+	u64 refcount_loc;
+	struct ocfs2_move_extents *range;
+	struct ocfs2_extent_tree et;
+	struct ocfs2_alloc_context *meta_ac;
+	struct ocfs2_alloc_context *data_ac;
+	struct ocfs2_cached_dealloc_ctxt dealloc;
+};
+
+static int __ocfs2_move_extent(handle_t *handle,
+			       struct ocfs2_move_extents_context *context,
+			       u32 cpos, u32 len, u32 p_cpos, u32 new_p_cpos,
+			       int ext_flags)
+{
+	int ret = 0, index;
+	struct inode *inode = context->inode;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_extent_rec *rec, replace_rec;
+	struct ocfs2_path *path = NULL;
+	struct ocfs2_extent_list *el;
+	u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
+	u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);
+
+	ret = ocfs2_duplicate_clusters_by_page(handle, context->file, cpos,
+					       p_cpos, new_p_cpos, len);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	memset(&replace_rec, 0, sizeof(replace_rec));
+	replace_rec.e_cpos = cpu_to_le32(cpos);
+	replace_rec.e_leaf_clusters = cpu_to_le16(len);
+	replace_rec.e_blkno = cpu_to_le64(ocfs2_clusters_to_blocks(inode->i_sb,
+								   new_p_cpos));
+
+	path = ocfs2_new_path_from_et(&context->et);
+	if (!path) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_find_path(INODE_CACHE(inode), path, cpos);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	el = path_leaf_el(path);
+
+	index = ocfs2_search_extent_list(el, cpos);
+	if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
+		ocfs2_error(inode->i_sb,
+			    "Inode %llu has an extent at cpos %u which can no "
+			    "longer be found.\n",
+			    (unsigned long long)ino, cpos);
+		ret = -EROFS;
+		goto out;
+	}
+
+	rec = &el->l_recs[index];
+
+	BUG_ON(ext_flags != rec->e_flags);
+	/*
+	 * after moving/defraging to new location, the extent is not going
+	 * to be refcounted anymore.
+	 */
+	replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED;
+
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
+				      context->et.et_root_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_split_extent(handle, &context->et, path, index,
+				 &replace_rec, context->meta_ac,
+				 &context->dealloc);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ocfs2_journal_dirty(handle, context->et.et_root_bh);
+
+	context->new_phys_cpos = new_p_cpos;
+
+	/*
+	 * need I to append truncate log for old clusters?
+	 */
+	if (old_blkno) {
+		if (ext_flags & OCFS2_EXT_REFCOUNTED)
+			ret = ocfs2_decrease_refcount(inode, handle,
+					ocfs2_blocks_to_clusters(osb->sb,
+								 old_blkno),
+					len, context->meta_ac,
+					&context->dealloc, 1);
+		else
+			ret = ocfs2_truncate_log_append(osb, handle,
+							old_blkno, len);
+	}
+
+out:
+	return ret;
+}
+
+/*
+ * lock allocators, and reserving appropriate number of bits for
+ * meta blocks and data clusters.
+ *
+ * in some cases, we don't need to reserve clusters, just let data_ac
+ * be NULL.
+ */
+static int ocfs2_lock_allocators_move_extents(struct inode *inode,
+					struct ocfs2_extent_tree *et,
+					u32 clusters_to_move,
+					u32 extents_to_split,
+					struct ocfs2_alloc_context **meta_ac,
+					struct ocfs2_alloc_context **data_ac,
+					int extra_blocks,
+					int *credits)
+{
+	int ret, num_free_extents;
+	unsigned int max_recs_needed = 2 * extents_to_split + clusters_to_move;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	num_free_extents = ocfs2_num_free_extents(osb, et);
+	if (num_free_extents < 0) {
+		ret = num_free_extents;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (!num_free_extents ||
+	    (ocfs2_sparse_alloc(osb) && num_free_extents < max_recs_needed))
+		extra_blocks += ocfs2_extend_meta_needed(et->et_root_el);
+
+	ret = ocfs2_reserve_new_metadata_blocks(osb, extra_blocks, meta_ac);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (data_ac) {
+		ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el,
+					      clusters_to_move + 2);
+
+	mlog(0, "reserve metadata_blocks: %d, data_clusters: %u, credits: %d\n",
+	     extra_blocks, clusters_to_move, *credits);
+out:
+	if (ret) {
+		if (*meta_ac) {
+			ocfs2_free_alloc_context(*meta_ac);
+			*meta_ac = NULL;
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * Using one journal handle to guarantee the data consistency in case
+ * crash happens anywhere.
+ *
+ *  XXX: defrag can end up with finishing partial extent as requested,
+ * due to not enough contiguous clusters can be found in allocator.
+ */
+static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
+			       u32 cpos, u32 phys_cpos, u32 *len, int ext_flags)
+{
+	int ret, credits = 0, extra_blocks = 0, partial = context->partial;
+	handle_t *handle;
+	struct inode *inode = context->inode;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct inode *tl_inode = osb->osb_tl_inode;
+	struct ocfs2_refcount_tree *ref_tree = NULL;
+	u32 new_phys_cpos, new_len;
+	u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
+
+	if ((ext_flags & OCFS2_EXT_REFCOUNTED) && *len) {
+
+		BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
+			 OCFS2_HAS_REFCOUNT_FL));
+
+		BUG_ON(!context->refcount_loc);
+
+		ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1,
+					       &ref_tree, NULL);
+		if (ret) {
+			mlog_errno(ret);
+			return ret;
+		}
+
+		ret = ocfs2_prepare_refcount_change_for_del(inode,
+							context->refcount_loc,
+							phys_blkno,
+							*len,
+							&credits,
+							&extra_blocks);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, *len, 1,
+						 &context->meta_ac,
+						 &context->data_ac,
+						 extra_blocks, &credits);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	/*
+	 * should be using allocation reservation strategy there?
+	 *
+	 * if (context->data_ac)
+	 *	context->data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
+	 */
+
+	mutex_lock(&tl_inode->i_mutex);
+
+	if (ocfs2_truncate_log_needs_flush(osb)) {
+		ret = __ocfs2_flush_truncate_log(osb);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out_unlock_mutex;
+		}
+	}
+
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out_unlock_mutex;
+	}
+
+	ret = __ocfs2_claim_clusters(handle, context->data_ac, 1, *len,
+				     &new_phys_cpos, &new_len);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	/*
+	 * allowing partial extent moving is kind of 'pros and cons', it makes
+	 * whole defragmentation less likely to fail, on the contrary, the bad
+	 * thing is it may make the fs even more fragmented after moving, let
+	 * userspace make a good decision here.
+	 */
+	if (new_len != *len) {
+		mlog(0, "len_claimed: %u, len: %u\n", new_len, *len);
+		if (!partial) {
+			context->range->me_flags &= ~OCFS2_MOVE_EXT_FL_COMPLETE;
+			ret = -ENOSPC;
+			goto out_commit;
+		}
+	}
+
+	mlog(0, "cpos: %u, phys_cpos: %u, new_phys_cpos: %u\n", cpos,
+	     phys_cpos, new_phys_cpos);
+
+	ret = __ocfs2_move_extent(handle, context, cpos, new_len, phys_cpos,
+				  new_phys_cpos, ext_flags);
+	if (ret)
+		mlog_errno(ret);
+
+	if (partial && (new_len != *len))
+		*len = new_len;
+
+	/*
+	 * Here we should write the new page out first if we are
+	 * in write-back mode.
+	 */
+	ret = ocfs2_cow_sync_writeback(inode->i_sb, context->inode, cpos, *len);
+	if (ret)
+		mlog_errno(ret);
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+
+out_unlock_mutex:
+	mutex_unlock(&tl_inode->i_mutex);
+
+	if (context->data_ac) {
+		ocfs2_free_alloc_context(context->data_ac);
+		context->data_ac = NULL;
+	}
+
+	if (context->meta_ac) {
+		ocfs2_free_alloc_context(context->meta_ac);
+		context->meta_ac = NULL;
+	}
+
+out:
+	if (ref_tree)
+		ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
+
+	return ret;
+}
+
+/*
+ * find the victim alloc group, where #blkno fits.
+ */
+static int ocfs2_find_victim_alloc_group(struct inode *inode,
+					 u64 vict_blkno,
+					 int type, int slot,
+					 int *vict_bit,
+					 struct buffer_head **ret_bh)
+{
+	int ret, i, blocks_per_unit = 1;
+	u64 blkno;
+	char namebuf[40];
+
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct buffer_head *ac_bh = NULL, *gd_bh = NULL;
+	struct ocfs2_chain_list *cl;
+	struct ocfs2_chain_rec *rec;
+	struct ocfs2_dinode *ac_dinode;
+	struct ocfs2_group_desc *bg;
+
+	ocfs2_sprintf_system_inode_name(namebuf, sizeof(namebuf), type, slot);
+	ret = ocfs2_lookup_ino_from_name(osb->sys_root_inode, namebuf,
+					 strlen(namebuf), &blkno);
+	if (ret) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	ret = ocfs2_read_blocks_sync(osb, blkno, 1, &ac_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ac_dinode = (struct ocfs2_dinode *)ac_bh->b_data;
+	cl = &(ac_dinode->id2.i_chain);
+	rec = &(cl->cl_recs[0]);
+
+	if (type == GLOBAL_BITMAP_SYSTEM_INODE)
+		blocks_per_unit <<= (osb->s_clustersize_bits -
+						inode->i_sb->s_blocksize_bits);
+	/*
+	 * 'vict_blkno' was out of the valid range.
+	 */
+	if ((vict_blkno < le64_to_cpu(rec->c_blkno)) ||
+	    (vict_blkno >= (le32_to_cpu(ac_dinode->id1.bitmap1.i_total) *
+				blocks_per_unit))) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i++) {
+
+		rec = &(cl->cl_recs[i]);
+		if (!rec)
+			continue;
+
+		bg = NULL;
+
+		do {
+			if (!bg)
+				blkno = le64_to_cpu(rec->c_blkno);
+			else
+				blkno = le64_to_cpu(bg->bg_next_group);
+
+			if (gd_bh) {
+				brelse(gd_bh);
+				gd_bh = NULL;
+			}
+
+			ret = ocfs2_read_blocks_sync(osb, blkno, 1, &gd_bh);
+			if (ret) {
+				mlog_errno(ret);
+				goto out;
+			}
+
+			bg = (struct ocfs2_group_desc *)gd_bh->b_data;
+
+			if (vict_blkno < (le64_to_cpu(bg->bg_blkno) +
+						le16_to_cpu(bg->bg_bits))) {
+
+				*ret_bh = gd_bh;
+				*vict_bit = (vict_blkno - blkno) /
+							blocks_per_unit;
+				mlog(0, "find the victim group: #%llu, "
+				     "total_bits: %u, vict_bit: %u\n",
+				     blkno, le16_to_cpu(bg->bg_bits),
+				     *vict_bit);
+				goto out;
+			}
+
+		} while (le64_to_cpu(bg->bg_next_group));
+	}
+
+	ret = -EINVAL;
+out:
+	brelse(ac_bh);
+
+	/*
+	 * caller has to release the gd_bh properly.
+	 */
+	return ret;
+}
+
+/*
+ * XXX: helper to validate and adjust moving goal.
+ */
+static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
+					       struct ocfs2_move_extents *range)
+{
+	int ret, goal_bit = 0;
+
+	struct buffer_head *gd_bh = NULL;
+	struct ocfs2_group_desc *bg;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int c_to_b = 1 << (osb->s_clustersize_bits -
+					inode->i_sb->s_blocksize_bits);
+
+	/*
+	 * validate goal sits within global_bitmap, and return the victim
+	 * group desc
+	 */
+	ret = ocfs2_find_victim_alloc_group(inode, range->me_goal,
+					    GLOBAL_BITMAP_SYSTEM_INODE,
+					    OCFS2_INVALID_SLOT,
+					    &goal_bit, &gd_bh);
+	if (ret)
+		goto out;
+
+	bg = (struct ocfs2_group_desc *)gd_bh->b_data;
+
+	/*
+	 * make goal become cluster aligned.
+	 */
+	if (range->me_goal % c_to_b)
+		range->me_goal = range->me_goal / c_to_b * c_to_b;
+
+	/*
+	 * moving goal is not allowd to start with a group desc blok(#0 blk)
+	 * let's compromise to the latter cluster.
+	 */
+	if (range->me_goal == le64_to_cpu(bg->bg_blkno))
+		range->me_goal += c_to_b;
+
+	/*
+	 * movement is not gonna cross two groups.
+	 */
+	if ((le16_to_cpu(bg->bg_bits) - goal_bit) * osb->s_clustersize <
+								range->me_len) {
+		ret = -EINVAL;
+		goto out;
+	}
+	/*
+	 * more exact validations/adjustments will be performed later during
+	 * moving operation for each extent range.
+	 */
+	mlog(0, "extents get ready to be moved to #%llu block\n",
+	     range->me_goal);
+
+out:
+	brelse(gd_bh);
+
+	return ret;
+}
+
+static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh,
+				    int *goal_bit, u32 move_len, u32 max_hop,
+				    u32 *phys_cpos)
+{
+	int i, used, last_free_bits = 0, base_bit = *goal_bit;
+	struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
+	u32 base_cpos = ocfs2_blocks_to_clusters(inode->i_sb,
+						 le64_to_cpu(gd->bg_blkno));
+
+	for (i = base_bit; i < le16_to_cpu(gd->bg_bits); i++) {
+
+		used = ocfs2_test_bit(i, (unsigned long *)gd->bg_bitmap);
+		if (used) {
+			/*
+			 * we even tried searching the free chunk by jumping
+			 * a 'max_hop' distance, but still failed.
+			 */
+			if ((i - base_bit) > max_hop) {
+				*phys_cpos = 0;
+				break;
+			}
+
+			if (last_free_bits)
+				last_free_bits = 0;
+
+			continue;
+		} else
+			last_free_bits++;
+
+		if (last_free_bits == move_len) {
+			*goal_bit = i;
+			*phys_cpos = base_cpos + i;
+			break;
+		}
+	}
+
+	mlog(0, "found phys_cpos: %u to fit the wanted moving.\n", *phys_cpos);
+}
+
+static int ocfs2_alloc_dinode_update_counts(struct inode *inode,
+				       handle_t *handle,
+				       struct buffer_head *di_bh,
+				       u32 num_bits,
+				       u16 chain)
+{
+	int ret;
+	u32 tmp_used;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
+	struct ocfs2_chain_list *cl =
+				(struct ocfs2_chain_list *) &di->id2.i_chain;
+
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	tmp_used = le32_to_cpu(di->id1.bitmap1.i_used);
+	di->id1.bitmap1.i_used = cpu_to_le32(num_bits + tmp_used);
+	le32_add_cpu(&cl->cl_recs[chain].c_free, -num_bits);
+	ocfs2_journal_dirty(handle, di_bh);
+
+out:
+	return ret;
+}
+
+static inline int ocfs2_block_group_set_bits(handle_t *handle,
+					     struct inode *alloc_inode,
+					     struct ocfs2_group_desc *bg,
+					     struct buffer_head *group_bh,
+					     unsigned int bit_off,
+					     unsigned int num_bits)
+{
+	int status;
+	void *bitmap = bg->bg_bitmap;
+	int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
+
+	/* All callers get the descriptor via
+	 * ocfs2_read_group_descriptor().  Any corruption is a code bug. */
+	BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg));
+	BUG_ON(le16_to_cpu(bg->bg_free_bits_count) < num_bits);
+
+	mlog(0, "block_group_set_bits: off = %u, num = %u\n", bit_off,
+	     num_bits);
+
+	if (ocfs2_is_cluster_bitmap(alloc_inode))
+		journal_type = OCFS2_JOURNAL_ACCESS_UNDO;
+
+	status = ocfs2_journal_access_gd(handle,
+					 INODE_CACHE(alloc_inode),
+					 group_bh,
+					 journal_type);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
+	if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
+		ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
+			    " count %u but claims %u are freed. num_bits %d",
+			    (unsigned long long)le64_to_cpu(bg->bg_blkno),
+			    le16_to_cpu(bg->bg_bits),
+			    le16_to_cpu(bg->bg_free_bits_count), num_bits);
+		return -EROFS;
+	}
+	while (num_bits--)
+		ocfs2_set_bit(bit_off++, bitmap);
+
+	ocfs2_journal_dirty(handle, group_bh);
+
+bail:
+	return status;
+}
+
+static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
+			     u32 cpos, u32 phys_cpos, u32 *new_phys_cpos,
+			     u32 len, int ext_flags)
+{
+	int ret, credits = 0, extra_blocks = 0, goal_bit = 0;
+	handle_t *handle;
+	struct inode *inode = context->inode;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct inode *tl_inode = osb->osb_tl_inode;
+	struct inode *gb_inode = NULL;
+	struct buffer_head *gb_bh = NULL;
+	struct buffer_head *gd_bh = NULL;
+	struct ocfs2_group_desc *gd;
+	struct ocfs2_refcount_tree *ref_tree = NULL;
+	u32 move_max_hop = ocfs2_blocks_to_clusters(inode->i_sb,
+						    context->range->me_threshold);
+	u64 phys_blkno, new_phys_blkno;
+
+	phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
+
+	if ((ext_flags & OCFS2_EXT_REFCOUNTED) && len) {
+
+		BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
+			 OCFS2_HAS_REFCOUNT_FL));
+
+		BUG_ON(!context->refcount_loc);
+
+		ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1,
+					       &ref_tree, NULL);
+		if (ret) {
+			mlog_errno(ret);
+			return ret;
+		}
+
+		ret = ocfs2_prepare_refcount_change_for_del(inode,
+							context->refcount_loc,
+							phys_blkno,
+							len,
+							&credits,
+							&extra_blocks);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
+						 &context->meta_ac,
+						 NULL, extra_blocks, &credits);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	/*
+	 * need to count 2 extra credits for global_bitmap inode and
+	 * group descriptor.
+	 */
+	credits += OCFS2_INODE_UPDATE_CREDITS + 1;
+
+	/*
+	 * ocfs2_move_extent() didn't reserve any clusters in lock_allocators()
+	 * logic, while we still need to lock the global_bitmap.
+	 */
+	gb_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE,
+					       OCFS2_INVALID_SLOT);
+	if (!gb_inode) {
+		mlog(ML_ERROR, "unable to get global_bitmap inode\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	mutex_lock(&gb_inode->i_mutex);
+
+	ret = ocfs2_inode_lock(gb_inode, &gb_bh, 1);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_unlock_gb_mutex;
+	}
+
+	mutex_lock(&tl_inode->i_mutex);
+
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out_unlock_tl_inode;
+	}
+
+	new_phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *new_phys_cpos);
+	ret = ocfs2_find_victim_alloc_group(inode, new_phys_blkno,
+					    GLOBAL_BITMAP_SYSTEM_INODE,
+					    OCFS2_INVALID_SLOT,
+					    &goal_bit, &gd_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	/*
+	 * probe the victim cluster group to find a proper
+	 * region to fit wanted movement, it even will perfrom
+	 * a best-effort attempt by compromising to a threshold
+	 * around the goal.
+	 */
+	ocfs2_probe_alloc_group(inode, gd_bh, &goal_bit, len, move_max_hop,
+				new_phys_cpos);
+	if (!new_phys_cpos) {
+		ret = -ENOSPC;
+		goto out_commit;
+	}
+
+	ret = __ocfs2_move_extent(handle, context, cpos, len, phys_cpos,
+				  *new_phys_cpos, ext_flags);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	gd = (struct ocfs2_group_desc *)gd_bh->b_data;
+	ret = ocfs2_alloc_dinode_update_counts(gb_inode, handle, gb_bh, len,
+					       le16_to_cpu(gd->bg_chain));
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh,
+					 goal_bit, len);
+	if (ret)
+		mlog_errno(ret);
+
+	/*
+	 * Here we should write the new page out first if we are
+	 * in write-back mode.
+	 */
+	ret = ocfs2_cow_sync_writeback(inode->i_sb, context->inode, cpos, len);
+	if (ret)
+		mlog_errno(ret);
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+	brelse(gd_bh);
+
+out_unlock_tl_inode:
+	mutex_unlock(&tl_inode->i_mutex);
+
+	ocfs2_inode_unlock(gb_inode, 1);
+out_unlock_gb_mutex:
+	mutex_unlock(&gb_inode->i_mutex);
+	brelse(gb_bh);
+	iput(gb_inode);
+
+out:
+	if (context->meta_ac) {
+		ocfs2_free_alloc_context(context->meta_ac);
+		context->meta_ac = NULL;
+	}
+
+	if (ref_tree)
+		ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
+
+	return ret;
+}
+
+/*
+ * Helper to calculate the defraging length in one run according to threshold.
+ */
+static void ocfs2_calc_extent_defrag_len(u32 *alloc_size, u32 *len_defraged,
+					 u32 threshold, int *skip)
+{
+	if ((*alloc_size + *len_defraged) < threshold) {
+		/*
+		 * proceed defragmentation until we meet the thresh
+		 */
+		*len_defraged += *alloc_size;
+	} else if (*len_defraged == 0) {
+		/*
+		 * XXX: skip a large extent.
+		 */
+		*skip = 1;
+	} else {
+		/*
+		 * split this extent to coalesce with former pieces as
+		 * to reach the threshold.
+		 *
+		 * we're done here with one cycle of defragmentation
+		 * in a size of 'thresh', resetting 'len_defraged'
+		 * forces a new defragmentation.
+		 */
+		*alloc_size = threshold - *len_defraged;
+		*len_defraged = 0;
+	}
+}
+
+static int __ocfs2_move_extents_range(struct buffer_head *di_bh,
+				struct ocfs2_move_extents_context *context)
+{
+	int ret = 0, flags, do_defrag, skip = 0;
+	u32 cpos, phys_cpos, move_start, len_to_move, alloc_size;
+	u32 len_defraged = 0, defrag_thresh = 0, new_phys_cpos = 0;
+
+	struct inode *inode = context->inode;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+	struct ocfs2_move_extents *range = context->range;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	if ((inode->i_size == 0) || (range->me_len == 0))
+		return 0;
+
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		return 0;
+
+	context->refcount_loc = le64_to_cpu(di->i_refcount_loc);
+
+	ocfs2_init_dinode_extent_tree(&context->et, INODE_CACHE(inode), di_bh);
+	ocfs2_init_dealloc_ctxt(&context->dealloc);
+
+	/*
+	 * TO-DO XXX:
+	 *
+	 * - xattr extents.
+	 */
+
+	do_defrag = context->auto_defrag;
+
+	/*
+	 * extents moving happens in unit of clusters, for the sake
+	 * of simplicity, we may ignore two clusters where 'byte_start'
+	 * and 'byte_start + len' were within.
+	 */
+	move_start = ocfs2_clusters_for_bytes(osb->sb, range->me_start);
+	len_to_move = (range->me_start + range->me_len) >>
+						osb->s_clustersize_bits;
+	if (len_to_move >= move_start)
+		len_to_move -= move_start;
+	else
+		len_to_move = 0;
+
+	if (do_defrag) {
+		defrag_thresh = range->me_threshold >> osb->s_clustersize_bits;
+		if (defrag_thresh <= 1)
+			goto done;
+	} else
+		new_phys_cpos = ocfs2_blocks_to_clusters(inode->i_sb,
+							 range->me_goal);
+
+	mlog(0, "Inode: %llu, start: %llu, len: %llu, cstart: %u, clen: %u, "
+	     "thresh: %u\n",
+	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
+	     (unsigned long long)range->me_start,
+	     (unsigned long long)range->me_len,
+	     move_start, len_to_move, defrag_thresh);
+
+	cpos = move_start;
+	while (len_to_move) {
+		ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &alloc_size,
+					 &flags);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		if (alloc_size > len_to_move)
+			alloc_size = len_to_move;
+
+		/*
+		 * XXX: how to deal with a hole:
+		 *
+		 * - skip the hole of course
+		 * - force a new defragmentation
+		 */
+		if (!phys_cpos) {
+			if (do_defrag)
+				len_defraged = 0;
+
+			goto next;
+		}
+
+		if (do_defrag) {
+			ocfs2_calc_extent_defrag_len(&alloc_size, &len_defraged,
+						     defrag_thresh, &skip);
+			/*
+			 * skip large extents
+			 */
+			if (skip) {
+				skip = 0;
+				goto next;
+			}
+
+			mlog(0, "#Defrag: cpos: %u, phys_cpos: %u, "
+			     "alloc_size: %u, len_defraged: %u\n",
+			     cpos, phys_cpos, alloc_size, len_defraged);
+
+			ret = ocfs2_defrag_extent(context, cpos, phys_cpos,
+						  &alloc_size, flags);
+		} else {
+			ret = ocfs2_move_extent(context, cpos, phys_cpos,
+						&new_phys_cpos, alloc_size,
+						flags);
+
+			new_phys_cpos += alloc_size;
+		}
+
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		context->clusters_moved += alloc_size;
+next:
+		cpos += alloc_size;
+		len_to_move -= alloc_size;
+	}
+
+done:
+	range->me_flags |= OCFS2_MOVE_EXT_FL_COMPLETE;
+
+out:
+	range->me_moved_len = ocfs2_clusters_to_bytes(osb->sb,
+						      context->clusters_moved);
+	range->me_new_offset = ocfs2_clusters_to_bytes(osb->sb,
+						       context->new_phys_cpos);
+
+	ocfs2_schedule_truncate_log_flush(osb, 1);
+	ocfs2_run_deallocs(osb, &context->dealloc);
+
+	return ret;
+}
+
+static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
+{
+	int status;
+	handle_t *handle;
+	struct inode *inode = context->inode;
+	struct ocfs2_dinode *di;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	if (!inode)
+		return -ENOENT;
+
+	if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
+		return -EROFS;
+
+	mutex_lock(&inode->i_mutex);
+
+	/*
+	 * This prevents concurrent writes from other nodes
+	 */
+	status = ocfs2_rw_lock(inode, 1);
+	if (status) {
+		mlog_errno(status);
+		goto out;
+	}
+
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status) {
+		mlog_errno(status);
+		goto out_rw_unlock;
+	}
+
+	/*
+	 * rememer ip_xattr_sem also needs to be held if necessary
+	 */
+	down_write(&OCFS2_I(inode)->ip_alloc_sem);
+
+	status = __ocfs2_move_extents_range(di_bh, context);
+
+	up_write(&OCFS2_I(inode)->ip_alloc_sem);
+	if (status) {
+		mlog_errno(status);
+		goto out_inode_unlock;
+	}
+
+	/*
+	 * We update ctime for these changes
+	 */
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		mlog_errno(status);
+		goto out_inode_unlock;
+	}
+
+	status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+					 OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status) {
+		mlog_errno(status);
+		goto out_commit;
+	}
+
+	di = (struct ocfs2_dinode *)di_bh->b_data;
+	inode->i_ctime = CURRENT_TIME;
+	di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
+	di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+
+	ocfs2_journal_dirty(handle, di_bh);
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+
+out_inode_unlock:
+	brelse(di_bh);
+	ocfs2_inode_unlock(inode, 1);
+out_rw_unlock:
+	ocfs2_rw_unlock(inode, 1);
+out:
+	mutex_unlock(&inode->i_mutex);
+
+	return status;
+}
+
+int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp)
+{
+	int status;
+
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct ocfs2_move_extents range;
+	struct ocfs2_move_extents_context *context = NULL;
+
+	status = mnt_want_write(filp->f_path.mnt);
+	if (status)
+		return status;
+
+	if ((!S_ISREG(inode->i_mode)) || !(filp->f_mode & FMODE_WRITE))
+		goto out;
+
+	if (inode->i_flags & (S_IMMUTABLE|S_APPEND)) {
+		status = -EPERM;
+		goto out;
+	}
+
+	context = kzalloc(sizeof(struct ocfs2_move_extents_context), GFP_NOFS);
+	if (!context) {
+		status = -ENOMEM;
+		mlog_errno(status);
+		goto out;
+	}
+
+	context->inode = inode;
+	context->file = filp;
+
+	if (argp) {
+		if (copy_from_user(&range, (struct ocfs2_move_extents *)argp,
+				   sizeof(range))) {
+			status = -EFAULT;
+			goto out;
+		}
+	} else {
+		status = -EINVAL;
+		goto out;
+	}
+
+	if (range.me_start > i_size_read(inode))
+		goto out;
+
+	if (range.me_start + range.me_len > i_size_read(inode))
+			range.me_len = i_size_read(inode) - range.me_start;
+
+	context->range = &range;
+
+	if (range.me_flags & OCFS2_MOVE_EXT_FL_AUTO_DEFRAG) {
+		context->auto_defrag = 1;
+		/*
+		 * ok, the default theshold for the defragmentation
+		 * is 1M, since our maximum clustersize was 1M also.
+		 * any thought?
+		 */
+		if (!range.me_threshold)
+			range.me_threshold = 1024 * 1024;
+
+		if (range.me_threshold > i_size_read(inode))
+			range.me_threshold = i_size_read(inode);
+
+		if (range.me_flags & OCFS2_MOVE_EXT_FL_PART_DEFRAG)
+			context->partial = 1;
+	} else {
+		/*
+		 * first best-effort attempt to validate and adjust the goal
+		 * (physical address in block), while it can't guarantee later
+		 * operation can succeed all the time since global_bitmap may
+		 * change a bit over time.
+		 */
+
+		status = ocfs2_validate_and_adjust_move_goal(inode, &range);
+		if (status)
+			goto out;
+	}
+
+	status = ocfs2_move_extents(context);
+	if (status)
+		mlog_errno(status);
+out:
+	/*
+	 * movement/defragmentation may end up being partially completed,
+	 * that's the reason why we need to return userspace the finished
+	 * length and new_offset even if failure happens somewhere.
+	 */
+	if (argp) {
+		if (copy_to_user((struct ocfs2_move_extents *)argp, &range,
+				sizeof(range)))
+			status = -EFAULT;
+	}
+
+	kfree(context);
+
+	mnt_drop_write(filp->f_path.mnt);
+
+	return status;
+}

fs/ocfs2/move_extents.h

+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * move_extents.h
+ *
+ * Copyright (C) 2011 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#ifndef OCFS2_MOVE_EXTENTS_H
+#define OCFS2_MOVE_EXTENTS_H
+
+int ocfs2_ioctl_move_extents(struct file *filp,  void __user *argp);
+
+#endif /* OCFS2_MOVE_EXTENTS_H */

fs/ocfs2/ocfs2_ioctl.h

@@ -142,6 +142,38 @@ struct ocfs2_info_journal_size {
 	__u64 ij_journal_size;
 };
 
+struct ocfs2_info_freeinode {
+	struct ocfs2_info_request ifi_req;
+	struct ocfs2_info_local_freeinode {
+		__u64 lfi_total;
+		__u64 lfi_free;
+	} ifi_stat[OCFS2_MAX_SLOTS];
+	__u32 ifi_slotnum; /* out */
+	__u32 ifi_pad;
+};
+
+#define OCFS2_INFO_MAX_HIST     (32)
+
+struct ocfs2_info_freefrag {
+	struct ocfs2_info_request iff_req;
+	struct ocfs2_info_freefrag_stats { /* (out) */
+		struct ocfs2_info_free_chunk_list {
+			__u32 fc_chunks[OCFS2_INFO_MAX_HIST];
+			__u32 fc_clusters[OCFS2_INFO_MAX_HIST];
+		} ffs_fc_hist;
+		__u32 ffs_clusters;
+		__u32 ffs_free_clusters;
+		__u32 ffs_free_chunks;
+		__u32 ffs_free_chunks_real;
+		__u32 ffs_min; /* Minimum free chunksize in clusters */
+		__u32 ffs_max;
+		__u32 ffs_avg;
+		__u32 ffs_pad;
+	} iff_ffs;
+	__u32 iff_chunksize; /* chunksize in clusters(in) */
+	__u32 iff_pad;
+};
+
 /* Codes for ocfs2_info_request */
 enum ocfs2_info_type {
 	OCFS2_INFO_CLUSTERSIZE = 1,
@@ -151,6 +183,8 @@ enum ocfs2_info_type {
 	OCFS2_INFO_UUID,
 	OCFS2_INFO_FS_FEATURES,
 	OCFS2_INFO_JOURNAL_SIZE,
+	OCFS2_INFO_FREEINODE,
+	OCFS2_INFO_FREEFRAG,
 	OCFS2_INFO_NUM_TYPES
 };
 
@@ -171,4 +205,38 @@ enum ocfs2_info_type {
 
 #define OCFS2_IOC_INFO		_IOR('o', 5, struct ocfs2_info)
 
+struct ocfs2_move_extents {
+/* All values are in bytes */
+	/* in */
+	__u64 me_start;		/* Virtual start in the file to move */
+	__u64 me_len;		/* Length of the extents to be moved */
+	__u64 me_goal;		/* Physical offset of the goal,
+				   it's in block unit */
+	__u64 me_threshold;	/* Maximum distance from goal or threshold
+				   for auto defragmentation */
+	__u64 me_flags;		/* Flags for the operation:
+				 * - auto defragmentation.
+				 * - refcount,xattr cases.
+				 */
+	/* out */
+	__u64 me_moved_len;	/* Moved/defraged length */
+	__u64 me_new_offset;	/* Resulting physical location */
+	__u32 me_reserved[2];	/* Reserved for futhure */
+};
+
+#define OCFS2_MOVE_EXT_FL_AUTO_DEFRAG	(0x00000001)	/* Kernel manages to
+							   claim new clusters
+							   as the goal place
+							   for extents moving */
+#define OCFS2_MOVE_EXT_FL_PART_DEFRAG	(0x00000002)	/* Allow partial extent
+							   moving, is to make
+							   movement less likely
+							   to fail, may make fs
+							   even more fragmented */
+#define OCFS2_MOVE_EXT_FL_COMPLETE	(0x00000004)	/* Move or defragmenation
+							   completely gets done.
+							 */
+
+#define OCFS2_IOC_MOVE_EXT	_IOW('o', 6, struct ocfs2_move_extents)
+
 #endif /* OCFS2_IOCTL_H */

fs/ocfs2/ocfs2_trace.h

@@ -688,6 +688,31 @@ TRACE_EVENT(ocfs2_cache_block_dealloc,
 		  __entry->blkno, __entry->bit)
 );
 
+TRACE_EVENT(ocfs2_trim_extent,
+	TP_PROTO(struct super_block *sb, unsigned long long blk,
+		 unsigned long long count),
+	TP_ARGS(sb, blk, count),
+	TP_STRUCT__entry(
+		__field(int, dev_major)
+		__field(int, dev_minor)
+		__field(unsigned long long, blk)
+		__field(__u64,	count)
+	),
+	TP_fast_assign(
+		__entry->dev_major = MAJOR(sb->s_dev);
+		__entry->dev_minor = MINOR(sb->s_dev);
+		__entry->blk = blk;
+		__entry->count = count;
+	),
+	TP_printk("%d %d %llu %llu",
+		  __entry->dev_major, __entry->dev_minor,
+		  __entry->blk, __entry->count)
+);
+
+DEFINE_OCFS2_ULL_UINT_UINT_UINT_EVENT(ocfs2_trim_group);
+
+DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_trim_fs);
+
 /* End of trace events for fs/ocfs2/alloc.c. */
 
 /* Trace events for fs/ocfs2/localalloc.c. */

fs/ocfs2/refcounttree.c

@@ -66,7 +66,7 @@ struct ocfs2_cow_context {
 			    u32 *num_clusters,
 			    unsigned int *extent_flags);
 	int (*cow_duplicate_clusters)(handle_t *handle,
-				      struct ocfs2_cow_context *context,
+				      struct file *file,
 				      u32 cpos, u32 old_cluster,
 				      u32 new_cluster, u32 new_len);
 };
@@ -2921,20 +2921,21 @@ static int ocfs2_clear_cow_buffer(handle_t *handle, struct buffer_head *bh)
 	return 0;
 }
 
-static int ocfs2_duplicate_clusters_by_page(handle_t *handle,
-					    struct ocfs2_cow_context *context,
-					    u32 cpos, u32 old_cluster,
-					    u32 new_cluster, u32 new_len)
+int ocfs2_duplicate_clusters_by_page(handle_t *handle,
+				     struct file *file,
+				     u32 cpos, u32 old_cluster,
+				     u32 new_cluster, u32 new_len)
 {
 	int ret = 0, partial;
-	struct ocfs2_caching_info *ci = context->data_et.et_ci;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct ocfs2_caching_info *ci = INODE_CACHE(inode);
 	struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
 	u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
 	struct page *page;
 	pgoff_t page_index;
 	unsigned int from, to, readahead_pages;
 	loff_t offset, end, map_end;
-	struct address_space *mapping = context->inode->i_mapping;
+	struct address_space *mapping = inode->i_mapping;
 
 	trace_ocfs2_duplicate_clusters_by_page(cpos, old_cluster,
 					       new_cluster, new_len);
@@ -2948,8 +2949,8 @@ static int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 	 * We only duplicate pages until we reach the page contains i_size - 1.
 	 * So trim 'end' to i_size.
 	 */
-	if (end > i_size_read(context->inode))
-		end = i_size_read(context->inode);
+	if (end > i_size_read(inode))
+		end = i_size_read(inode);
 
 	while (offset < end) {
 		page_index = offset >> PAGE_CACHE_SHIFT;
@@ -2972,10 +2973,9 @@ static int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 		if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize)
 			BUG_ON(PageDirty(page));
 
-		if (PageReadahead(page) && context->file) {
+		if (PageReadahead(page)) {
 			page_cache_async_readahead(mapping,
-						   &context->file->f_ra,
-						   context->file,
+						   &file->f_ra, file,
 						   page, page_index,
 						   readahead_pages);
 		}
@@ -2999,8 +2999,7 @@ static int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 			}
 		}
 
-		ocfs2_map_and_dirty_page(context->inode,
-					 handle, from, to,
+		ocfs2_map_and_dirty_page(inode, handle, from, to,
 					 page, 0, &new_block);
 		mark_page_accessed(page);
 unlock:
@@ -3015,14 +3014,15 @@ static int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 	return ret;
 }
 
-static int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
-					   struct ocfs2_cow_context *context,
-					   u32 cpos, u32 old_cluster,
-					   u32 new_cluster, u32 new_len)
+int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
+				    struct file *file,
+				    u32 cpos, u32 old_cluster,
+				    u32 new_cluster, u32 new_len)
 {
 	int ret = 0;
-	struct super_block *sb = context->inode->i_sb;
-	struct ocfs2_caching_info *ci = context->data_et.et_ci;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	struct ocfs2_caching_info *ci = INODE_CACHE(inode);
 	int i, blocks = ocfs2_clusters_to_blocks(sb, new_len);
 	u64 old_block = ocfs2_clusters_to_blocks(sb, old_cluster);
 	u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
@@ -3145,8 +3145,8 @@ static int ocfs2_replace_clusters(handle_t *handle,
 
 	/*If the old clusters is unwritten, no need to duplicate. */
 	if (!(ext_flags & OCFS2_EXT_UNWRITTEN)) {
-		ret = context->cow_duplicate_clusters(handle, context, cpos,
-						      old, new, len);
+		ret = context->cow_duplicate_clusters(handle, context->file,
+						      cpos, old, new, len);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
@@ -3162,22 +3162,22 @@ static int ocfs2_replace_clusters(handle_t *handle,
 	return ret;
 }
 
-static int ocfs2_cow_sync_writeback(struct super_block *sb,
-				    struct ocfs2_cow_context *context,
-				    u32 cpos, u32 num_clusters)
+int ocfs2_cow_sync_writeback(struct super_block *sb,
+			     struct inode *inode,
+			     u32 cpos, u32 num_clusters)
 {
 	int ret = 0;
 	loff_t offset, end, map_end;
 	pgoff_t page_index;
 	struct page *page;
 
-	if (ocfs2_should_order_data(context->inode))
+	if (ocfs2_should_order_data(inode))
 		return 0;
 
 	offset = ((loff_t)cpos) << OCFS2_SB(sb)->s_clustersize_bits;
 	end = offset + (num_clusters << OCFS2_SB(sb)->s_clustersize_bits);
 
-	ret = filemap_fdatawrite_range(context->inode->i_mapping,
+	ret = filemap_fdatawrite_range(inode->i_mapping,
 				       offset, end - 1);
 	if (ret < 0) {
 		mlog_errno(ret);
@@ -3190,7 +3190,7 @@ static int ocfs2_cow_sync_writeback(struct super_block *sb,
 		if (map_end > end)
 			map_end = end;
 
-		page = find_or_create_page(context->inode->i_mapping,
+		page = find_or_create_page(inode->i_mapping,
 					   page_index, GFP_NOFS);
 		BUG_ON(!page);
 
@@ -3349,7 +3349,7 @@ static int ocfs2_make_clusters_writable(struct super_block *sb,
 	 * in write-back mode.
 	 */
 	if (context->get_clusters == ocfs2_di_get_clusters) {
-		ret = ocfs2_cow_sync_writeback(sb, context, cpos,
+		ret = ocfs2_cow_sync_writeback(sb, context->inode, cpos,
 					       orig_num_clusters);
 		if (ret)
 			mlog_errno(ret);

fs/ocfs2/refcounttree.h

@@ -84,6 +84,17 @@ int ocfs2_refcount_cow_xattr(struct inode *inode,
 			     struct buffer_head *ref_root_bh,
 			     u32 cpos, u32 write_len,
 			     struct ocfs2_post_refcount *post);
+int ocfs2_duplicate_clusters_by_page(handle_t *handle,
+				     struct file *file,
+				     u32 cpos, u32 old_cluster,
+				     u32 new_cluster, u32 new_len);
+int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
+				    struct file *file,
+				    u32 cpos, u32 old_cluster,
+				    u32 new_cluster, u32 new_len);
+int ocfs2_cow_sync_writeback(struct super_block *sb,
+			     struct inode *inode,
+			     u32 cpos, u32 num_clusters);
 int ocfs2_add_refcount_flag(struct inode *inode,
 			    struct ocfs2_extent_tree *data_et,
 			    struct ocfs2_caching_info *ref_ci,

fs/ocfs2/super.c

@@ -1567,7 +1567,7 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 	if (osb->preferred_slot != OCFS2_INVALID_SLOT)
 		seq_printf(s, ",preferred_slot=%d", osb->preferred_slot);
 
-	if (osb->s_atime_quantum != OCFS2_DEFAULT_ATIME_QUANTUM)
+	if (!(mnt->mnt_flags & MNT_NOATIME) && !(mnt->mnt_flags & MNT_RELATIME))
 		seq_printf(s, ",atime_quantum=%u", osb->s_atime_quantum);
 
 	if (osb->osb_commit_interval)