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/removed/o2cb

@@ -1,11 +1,10 @@
 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 @@ out_commit:
 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 @@ redo_bucket:
 			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;
+	if (res->owner != dlm->node_num)
+		return 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;
-	}
-
-	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;
+	if (!nonlocal) {
+		node_ref = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
+		if (node_ref >= O2NM_MAX_NODES)
+			return 0;
+	}
 
-	count = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
-	if (count < O2NM_MAX_NODES)
-		*hasrefs = 1;
+	mlog(0, "%s: res %.*s, Migrateable\n", dlm->name, res->lockname.len,
+	     res->lockname.name);
 
-	mlog(0, "%s: res %.*s, Migrateable, locks %d, refs %d\n", dlm->name,
-	     res->lockname.len, res->lockname.name, *numlocks, *hasrefs);
-
-leave:
-	return ret;
+	return 1;
 }
 
 /*
@@ -2406,8 +2396,7 @@ leave:
 
 
 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 @@ fail:
 			dlm_put_mle(mle);
 		} else if (mle) {
 			kmem_cache_free(dlm_mle_cache, mle);
+			mle = NULL;
 		}
 		goto leave;
 	}
@@ -2652,69 +2600,52 @@ leave:
 	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;
-	}
-
-	/* 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);
-		goto leave;
-	}
+	if (dlm_is_lockres_migrateable(dlm, res))
+		target = dlm_pick_migration_target(dlm, res);
 	spin_unlock(&res->spinlock);
 
+	if (target == O2NM_MAX_NODES)
+		goto leave;
+
 	/* 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/move_extents.h

@@ -0,0 +1,22 @@
+/* -*- 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 @@ unlock:
 	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 @@ out:
 	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);