Merge branch 'move_extents' of git://oss.oracle.com/git/tye/linux-2.6 into ocfs2-merge-window

Conflicts:
	fs/ocfs2/ioctl.c

7 files changed, 1725 insertions, 56 deletions

diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index d8a0313e99e..f17e58b3298 100644
--- a/fs/ocfs2/Makefile
+++ b/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 		\
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 312a28f433a..bc91072b721 100644
--- a/fs/ocfs2/ioctl.c
+++ b/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;
@@ -565,6 +975,8 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 		return 0;
 	}
+	case OCFS2_IOC_MOVE_EXT:
+		return ocfs2_ioctl_move_extents(filp, (void __user *)arg);
 	default:
 		return -ENOTTY;
 	}
@@ -608,6 +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;
 	}
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
new file mode 100644
index 00000000000..4c5488468c1
--- /dev/null
+++ b/fs/ocfs2/move_extents.c
@@ -0,0 +1,1153 @@
+/* -*- 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 <
+								rang