Merge tag 'mm-nonmm-stable-2024-05-19-11-56' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-mm updates from Andrew Morton:
 "Mainly singleton patches, documented in their respective changelogs.
  Notable series include:

   - Some maintenance and performance work for ocfs2 in Heming Zhao's
     series "improve write IO performance when fragmentation is high".

   - Some ocfs2 bugfixes from Su Yue in the series "ocfs2 bugs fixes
     exposed by fstests".

   - kfifo header rework from Andy Shevchenko in the series "kfifo:
     Clean up kfifo.h".

   - GDB script fixes from Florian Rommel in the series "scripts/gdb:
     Fixes for $lx_current and $lx_per_cpu".

   - After much discussion, a coding-style update from Barry Song
     explaining one reason why inline functions are preferred over
     macros. The series is "codingstyle: avoid unused parameters for a
     function-like macro""

* tag 'mm-nonmm-stable-2024-05-19-11-56' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (62 commits)
  fs/proc: fix softlockup in __read_vmcore
  nilfs2: convert BUG_ON() in nilfs_finish_roll_forward() to WARN_ON()
  scripts: checkpatch: check unused parameters for function-like macro
  Documentation: coding-style: ask function-like macros to evaluate parameters
  nilfs2: use __field_struct() for a bitwise field
  selftests/kcmp: remove unused open mode
  nilfs2: remove calls to folio_set_error() and folio_clear_error()
  kernel/watchdog_perf.c: tidy up kerneldoc
  watchdog: allow nmi watchdog to use raw perf event
  watchdog: handle comma separated nmi_watchdog command line
  nilfs2: make superblock data array index computation sparse friendly
  squashfs: remove calls to set the folio error flag
  squashfs: convert squashfs_symlink_read_folio to use folio APIs
  scripts/gdb: fix detection of current CPU in KGDB
  scripts/gdb: make get_thread_info accept pointers
  scripts/gdb: fix parameter handling in $lx_per_cpu
  scripts/gdb: fix failing KGDB detection during probe
  kfifo: don't use "proxy" headers
  media: stih-cec: add missing io.h
  media: rc: add missing io.h
  ...

15 files changed, 148 insertions, 61 deletions

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index b82185075de7..f0467d3b3c88 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2283,8 +2283,6 @@ unlock:
 	ocfs2_inode_unlock(inode, 1);
 	brelse(di_bh);
 out:
-	if (ret < 0)
-		ret = -EIO;
 	return ret;
 }
 
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 5c04dde99981..2018501b2249 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1274,7 +1274,7 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len,
 {
 	struct dlm_query_nodeinfo *qn;
 	struct dlm_ctxt *dlm = NULL;
-	int locked = 0, status = -EINVAL;
+	int status = -EINVAL;
 
 	qn = (struct dlm_query_nodeinfo *) msg->buf;
 
@@ -1290,12 +1290,11 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len,
 	}
 
 	spin_lock(&dlm->spinlock);
-	locked = 1;
 	if (dlm->joining_node != qn->qn_nodenum) {
 		mlog(ML_ERROR, "Node %d queried nodes on domain %s but "
 		     "joining node is %d\n", qn->qn_nodenum, qn->qn_domain,
 		     dlm->joining_node);
-		goto bail;
+		goto unlock;
 	}
 
 	/* Support for node query was added in 1.1 */
@@ -1305,14 +1304,14 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len,
 		     "but active dlm protocol is %d.%d\n", qn->qn_nodenum,
 		     qn->qn_domain, dlm->dlm_locking_proto.pv_major,
 		     dlm->dlm_locking_proto.pv_minor);
-		goto bail;
+		goto unlock;
 	}
 
 	status = dlm_match_nodes(dlm, qn);
 
+unlock:
+	spin_unlock(&dlm->spinlock);
 bail:
-	if (locked)
-		spin_unlock(&dlm->spinlock);
 	spin_unlock(&dlm_domain_lock);
 
 	return status;
@@ -1528,7 +1527,6 @@ static void dlm_send_join_asserts(struct dlm_ctxt *dlm,
 {
 	int status, node, live;
 
-	status = 0;
 	node = -1;
 	while ((node = find_next_bit(node_map, O2NM_MAX_NODES,
 				     node + 1)) < O2NM_MAX_NODES) {
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index b8b6a191b5cb..96b684763b39 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -255,9 +255,9 @@ static struct dentry *ocfs2_fh_to_dentry(struct super_block *sb,
 	if (fh_len < 3 || fh_type > 2)
 		return NULL;
 
-	handle.ih_blkno = (u64)le32_to_cpu(fid->raw[0]) << 32;
-	handle.ih_blkno |= (u64)le32_to_cpu(fid->raw[1]);
-	handle.ih_generation = le32_to_cpu(fid->raw[2]);
+	handle.ih_blkno = (u64)le32_to_cpu((__force __le32)fid->raw[0]) << 32;
+	handle.ih_blkno |= (u64)le32_to_cpu((__force __le32)fid->raw[1]);
+	handle.ih_generation = le32_to_cpu((__force __le32)fid->raw[2]);
 	return ocfs2_get_dentry(sb, &handle);
 }
 
@@ -269,9 +269,9 @@ static struct dentry *ocfs2_fh_to_parent(struct super_block *sb,
 	if (fh_type != 2 || fh_len < 6)
 		return NULL;
 
-	parent.ih_blkno = (u64)le32_to_cpu(fid->raw[3]) << 32;
-	parent.ih_blkno |= (u64)le32_to_cpu(fid->raw[4]);
-	parent.ih_generation = le32_to_cpu(fid->raw[5]);
+	parent.ih_blkno = (u64)le32_to_cpu((__force __le32)fid->raw[3]) << 32;
+	parent.ih_blkno |= (u64)le32_to_cpu((__force __le32)fid->raw[4]);
+	parent.ih_generation = le32_to_cpu((__force __le32)fid->raw[5]);
 	return ocfs2_get_dentry(sb, &parent);
 }
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 0da8e7bd3261..ccc57038a977 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1936,6 +1936,8 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
 
 	inode_lock(inode);
 
+	/* Wait all existing dio workers, newcomers will block on i_rwsem */
+	inode_dio_wait(inode);
 	/*
 	 * This prevents concurrent writes on other nodes
 	 */
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 999111bfc271..2cc5c99fe941 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1621,6 +1621,7 @@ static struct super_block *ocfs2_inode_cache_get_super(struct ocfs2_caching_info
 }
 
 static void ocfs2_inode_cache_lock(struct ocfs2_caching_info *ci)
+__acquires(&oi->ip_lock)
 {
 	struct ocfs2_inode_info *oi = cache_info_to_inode(ci);
 
@@ -1628,6 +1629,7 @@ static void ocfs2_inode_cache_lock(struct ocfs2_caching_info *ci)
 }
 
 static void ocfs2_inode_cache_unlock(struct ocfs2_caching_info *ci)
+__releases(&oi->ip_lock)
 {
 	struct ocfs2_inode_info *oi = cache_info_to_inode(ci);
 
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index b1550ba73f96..71beef7f8a60 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -125,6 +125,7 @@ int ocfs2_fileattr_set(struct mnt_idmap *idmap,
 
 	ocfs2_inode->ip_attr = flags;
 	ocfs2_set_inode_flags(inode);
+	inode_set_ctime_current(inode);
 
 	status = ocfs2_mark_inode_dirty(handle, inode, bh);
 	if (status < 0)
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index c803c10dd97e..5df34561c551 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -212,14 +212,15 @@ static inline int ocfs2_la_state_enabled(struct ocfs2_super *osb)
 void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb,
 				      unsigned int num_clusters)
 {
-	spin_lock(&osb->osb_lock);
-	if (osb->local_alloc_state == OCFS2_LA_DISABLED ||
-	    osb->local_alloc_state == OCFS2_LA_THROTTLED)
-		if (num_clusters >= osb->local_alloc_default_bits) {
+	if (num_clusters >= osb->local_alloc_default_bits) {
+		spin_lock(&osb->osb_lock);
+		if (osb->local_alloc_state == OCFS2_LA_DISABLED ||
+		    osb->local_alloc_state == OCFS2_LA_THROTTLED) {
 			cancel_delayed_work(&osb->la_enable_wq);
 			osb->local_alloc_state = OCFS2_LA_ENABLED;
 		}
-	spin_unlock(&osb->osb_lock);
+		spin_unlock(&osb->osb_lock);
+	}
 }
 
 void ocfs2_la_enable_worker(struct work_struct *work)
@@ -335,7 +336,7 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb)
 		     "found = %u, set = %u, taken = %u, off = %u\n",
 		     num_used, le32_to_cpu(alloc->id1.bitmap1.i_used),
 		     le32_to_cpu(alloc->id1.bitmap1.i_total),
-		     OCFS2_LOCAL_ALLOC(alloc)->la_bm_off);
+		     le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off));
 
 		status = -EINVAL;
 		goto bail;
@@ -863,14 +864,8 @@ static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb,
 
 	numfound = bitoff = startoff = 0;
 	left = le32_to_cpu(alloc->id1.bitmap1.i_total);
-	while ((bitoff = ocfs2_find_next_zero_bit(bitmap, left, startoff)) != -1) {
-		if (bitoff == left) {
-			/* mlog(0, "bitoff (%d) == left", bitoff); */
-			break;
-		}
-		/* mlog(0, "Found a zero: bitoff = %d, startoff = %d, "
-		   "numfound = %d\n", bitoff, startoff, numfound);*/
-
+	while ((bitoff = ocfs2_find_next_zero_bit(bitmap, left, startoff)) <
+	       left) {
 		/* Ok, we found a zero bit... is it contig. or do we
 		 * start over?*/
 		if (bitoff == startoff) {
@@ -976,9 +971,9 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb,
 	start = count = 0;
 	left = le32_to_cpu(alloc->id1.bitmap1.i_total);
 
-	while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start))
-	       != -1) {
-		if ((bit_off < left) && (bit_off == start)) {
+	while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) <
+	       left) {
+		if (bit_off == start) {
 			count++;
 			start++;
 			continue;
@@ -1002,8 +997,7 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb,
 				goto bail;
 			}
 		}
-		if (bit_off >= left)
-			break;
+
 		count = 1;
 		start = bit_off + 1;
 	}
@@ -1220,7 +1214,7 @@ retry_enospc:
 			     OCFS2_LOCAL_ALLOC(alloc)->la_bitmap);
 
 	trace_ocfs2_local_alloc_new_window_result(
-		OCFS2_LOCAL_ALLOC(alloc)->la_bm_off,
+		le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off),
 		le32_to_cpu(alloc->id1.bitmap1.i_total));
 
 bail:
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 1f9ed117e78b..f9d6a4f9ca92 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -685,7 +685,7 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
 	}
 
 	ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh,
-					 goal_bit, len);
+					 goal_bit, len, 0, 0);
 	if (ret) {
 		ocfs2_rollback_alloc_dinode_counts(gb_inode, gb_bh, len,
 					       le16_to_cpu(gd->bg_chain));
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 9221a33f917b..4d1ea8703fcd 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -566,7 +566,7 @@ static int __ocfs2_mknod_locked(struct inode *dir,
 	fe->i_last_eb_blk = 0;
 	strcpy(fe->i_signature, OCFS2_INODE_SIGNATURE);
 	fe->i_flags |= cpu_to_le32(OCFS2_VALID_FL);
-	ktime_get_real_ts64(&ts);
+	ktime_get_coarse_real_ts64(&ts);
 	fe->i_atime = fe->i_ctime = fe->i_mtime =
 		cpu_to_le64(ts.tv_sec);
 	fe->i_mtime_nsec = fe->i_ctime_nsec = fe->i_atime_nsec =
@@ -797,6 +797,7 @@ static int ocfs2_link(struct dentry *old_dentry,
 	ocfs2_set_links_count(fe, inode->i_nlink);
 	fe->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode));
 	fe->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode));
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 	ocfs2_journal_dirty(handle, fe_bh);
 
 	err = ocfs2_add_entry(handle, dentry, inode,
@@ -993,6 +994,7 @@ static int ocfs2_unlink(struct inode *dir,
 		drop_nlink(inode);
 	drop_nlink(inode);
 	ocfs2_set_links_count(fe, inode->i_nlink);
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 	ocfs2_journal_dirty(handle, fe_bh);
 
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 7aebdbf5cc0a..c93689b568fe 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -883,7 +883,8 @@ struct ocfs2_group_desc
 	__le16	bg_free_bits_count;     /* Free bits count */
 	__le16   bg_chain;               /* What chain I am in. */
 /*10*/	__le32   bg_generation;
-	__le32	bg_reserved1;
+	__le16   bg_contig_free_bits;   /* max contig free bits length */
+	__le16   bg_reserved1;
 	__le64   bg_next_group;          /* Next group in my list, in
 					   blocks */
 /*20*/	__le64   bg_parent_dinode;       /* dinode which owns me, in
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 3f80a56d0d60..1f303b1adf1a 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -630,7 +630,7 @@ static int ocfs2_create_refcount_tree(struct inode *inode,
 	rb->rf_records.rl_count =
 			cpu_to_le16(ocfs2_refcount_recs_per_rb(osb->sb));
 	spin_lock(&osb->osb_lock);
-	rb->rf_generation = osb->s_next_generation++;
+	rb->rf_generation = cpu_to_le32(osb->s_next_generation++);
 	spin_unlock(&osb->osb_lock);
 
 	ocfs2_journal_dirty(handle, new_bh);
diff --git a/fs/ocfs2/reservations.c b/fs/ocfs2/reservations.c
index a9d1296d736d..1fe61974d9f0 100644
--- a/fs/ocfs2/reservations.c
+++ b/fs/ocfs2/reservations.c
@@ -414,7 +414,7 @@ static int ocfs2_resmap_find_free_bits(struct ocfs2_reservation_map *resmap,
 
 	start = search_start;
 	while ((offset = ocfs2_find_next_zero_bit(bitmap, resmap->m_bitmap_len,
-						 start)) != -1) {
+					start)) < resmap->m_bitmap_len) {
 		/* Search reached end of the region */
 		if (offset >= (search_start + search_len))
 			break;
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index d65d43c61857..c4a4016d3866 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -91,6 +91,8 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 	u16 cl_bpc = le16_to_cpu(cl->cl_bpc);
 	u16 cl_cpg = le16_to_cpu(cl->cl_cpg);
 	u16 old_bg_clusters;
+	u16 contig_bits;
+	__le16 old_bg_contig_free_bits;
 
 	trace_ocfs2_update_last_group_and_inode(new_clusters,
 						first_new_cluster);
@@ -122,6 +124,11 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 		le16_add_cpu(&group->bg_free_bits_count, -1 * backups);
 	}
 
+	contig_bits = ocfs2_find_max_contig_free_bits(group->bg_bitmap,
+					le16_to_cpu(group->bg_bits), 0);
+	old_bg_contig_free_bits = group->bg_contig_free_bits;
+	group->bg_contig_free_bits = cpu_to_le16(contig_bits);
+
 	ocfs2_journal_dirty(handle, group_bh);
 
 	/* update the inode accordingly. */
@@ -160,6 +167,7 @@ out_rollback:
 		le16_add_cpu(&group->bg_free_bits_count, backups);
 		le16_add_cpu(&group->bg_bits, -1 * num_bits);
 		le16_add_cpu(&group->bg_free_bits_count, -1 * num_bits);
+		group->bg_contig_free_bits = old_bg_contig_free_bits;
 	}
 out:
 	if (ret)
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 166c8918c825..f7b483f0de2a 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -50,6 +50,10 @@ struct ocfs2_suballoc_result {
 	u64		sr_blkno;	/* The first allocated block */
 	unsigned int	sr_bit_offset;	/* The bit in the bg */
 	unsigned int	sr_bits;	/* How many bits we claimed */
+	unsigned int	sr_max_contig_bits; /* The length for contiguous
+					     * free bits, only available
+					     * for cluster group
+					     */
 };
 
 static u64 ocfs2_group_from_res(struct ocfs2_suballoc_result *res)
@@ -1272,6 +1276,26 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
 	return ret;
 }
 
+u16 ocfs2_find_max_contig_free_bits(void *bitmap,
+			 u16 total_bits, u16 start)
+{
+	u16 offset, free_bits;
+	u16 contig_bits = 0;
+
+	while (start < total_bits) {
+		offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start);
+		if (offset == total_bits)
+			break;
+
+		start = ocfs2_find_next_bit(bitmap, total_bits, offset);
+		free_bits = start - offset;
+		if (contig_bits < free_bits)
+			contig_bits = free_bits;
+	}
+
+	return contig_bits;
+}
+
 static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 					     struct buffer_head *bg_bh,
 					     unsigned int bits_wanted,
@@ -1280,6 +1304,7 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 {
 	void *bitmap;
 	u16 best_offset, best_size;
+	u16 prev_best_size = 0;
 	int offset, start, found, status = 0;
 	struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
 
@@ -1290,10 +1315,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 	found = start = best_offset = best_size = 0;
 	bitmap = bg->bg_bitmap;
 
-	while((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) != -1) {
-		if (offset == total_bits)
-			break;
-
+	while ((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) <
+	       total_bits) {
 		if (!ocfs2_test_bg_bit_allocatable(bg_bh, offset)) {
 			/* We found a zero, but we can't use it as it
 			 * hasn't been put to disk yet! */
@@ -1308,6 +1331,7 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 			/* got a zero after some ones */
 			found = 1;
 			start = offset + 1;
+			prev_best_size = best_size;
 		}
 		if (found > best_size) {
 			best_size = found;
@@ -1320,6 +1344,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 		}
 	}
 
+	/* best_size will be allocated, we save prev_best_size */
+	res->sr_max_contig_bits = prev_best_size;
 	if (best_size) {
 		res->sr_bit_offset = best_offset;
 		res->sr_bits = best_size;
@@ -1337,11 +1363,16 @@ int ocfs2_block_group_set_bits(handle_t *handle,
 					     struct ocfs2_group_desc *bg,
 					     struct buffer_head *group_bh,
 					     unsigned int bit_off,
-					     unsigned int num_bits)
+					     unsigned int num_bits,
+					     unsigned int max_contig_bits,
+					     int fastpath)
 {
 	int status;
 	void *bitmap = bg->bg_bitmap;
 	int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
+	unsigned int start = bit_off + num_bits;
+	u16 contig_bits;
+	struct ocfs2_super *osb = OCFS2_SB(alloc_inode->i_sb);
 
 	/* All callers get the descriptor via
 	 * ocfs2_read_group_descriptor().  Any corruption is a code bug. */
@@ -1373,6 +1404,29 @@ int ocfs2_block_group_set_bits(handle_t *handle,
 	while(num_bits--)
 		ocfs2_set_bit(bit_off++, bitmap);
 
+	/*
+	 * this is optimize path, caller set old contig value
+	 * in max_contig_bits to bypass finding action.
+	 */
+	if (fastpath) {
+		bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits);
+	} else if (ocfs2_is_cluster_bitmap(alloc_inode)) {
+		/*
+		 * Usually, the block group bitmap allocates only 1 bit
+		 * at a time, while the cluster group allocates n bits
+		 * each time. Therefore, we only save the contig bits for
+		 * the cluster group.
+		 */
+		contig_bits = ocfs2_find_max_contig_free_bits(bitmap,
+				    le16_to_cpu(bg->bg_bits), start);
+		if (contig_bits > max_contig_bits)
+			max_contig_bits = contig_bits;
+		bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits);
+		ocfs2_local_alloc_seen_free_bits(osb, max_contig_bits);
+	} else {
+		bg->bg_contig_free_bits = 0;
+	}
+
 	ocfs2_journal_dirty(handle, group_bh);
 
 bail:
@@ -1486,7 +1540,12 @@ static int ocfs2_cluster_group_search(struct inode *inode,
 
 	BUG_ON(!ocfs2_is_cluster_bitmap(inode));
 
-	if (gd->bg_free_bits_count) {
+	if (le16_to_cpu(gd->bg_contig_free_bits) &&
+	    le16_to_cpu(gd->bg_contig_free_bits) < bits_wanted)
+		return -ENOSPC;
+
+	/* ->bg_contig_free_bits may un-initialized, so compare again */
+	if (le16_to_cpu(gd->bg_free_bits_count) >= bits_wanted) {
 		max_bits = le16_to_cpu(gd->bg_bits);
 
 		/* Tail groups in cluster bitmaps which aren't cpg
@@ -1530,13 +1589,6 @@ static int ocfs2_cluster_group_search(struct inode *inode,
 		 * of bits. */
 		if (min_bits <= res->sr_bits)
 			search = 0; /* success */
-		else if (res->sr_bits) {
-			/*
-			 * Don't show bits which we'll be returning
-			 * for allocation to the local alloc bitmap.
-			 */
-			ocfs2_local_alloc_seen_free_bits(osb, res->sr_bits);
-		}
 	}
 
 	return search;
@@ -1555,7 +1607,7 @@ static int ocfs2_block_group_search(struct inode *inode,
 	BUG_ON(min_bits != 1);
 	BUG_ON(ocfs2_is_cluster_bitmap(inode));
 
-	if (bg->bg_free_bits_count) {
+	if (le16_to_cpu(bg->bg_free_bits_count) >= bits_wanted) {
 		ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
 							group_bh, bits_wanted,
 							le16_to_cpu(bg->bg_bits),
@@ -1715,7 +1767,8 @@ static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac,
 	}
 
 	ret = ocfs2_block_group_set_bits(handle, alloc_inode, gd, group_bh,
-					 res->sr_bit_offset, res->sr_bits);
+					 res->sr_bit_offset, res->sr_bits,
+					 res->sr_max_contig_bits, 0);
 	if (ret < 0) {
 		ocfs2_rollback_alloc_dinode_counts(alloc_inode, ac->ac_bh,
 					       res->sr_bits,
@@ -1849,7 +1902,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 					    bg,
 					    group_bh,
 					    res->sr_bit_offset,
-					    res->sr_bits);
+					    res->sr_bits,
+					    res->sr_max_contig_bits,
+					    0);
 	if (status < 0) {
 		ocfs2_rollback_alloc_dinode_counts(alloc_inode,
 					ac->ac_bh, res->sr_bits, chain);
@@ -1951,7 +2006,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 	for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i ++) {
 		if (i == victim)
 			continue;
-		if (!cl->cl_recs[i].c_free)
+		if (le32_to_cpu(cl->cl_recs[i].c_free) < bits_wanted)
 			continue;
 
 		ac->ac_chain = i;
@@ -2163,7 +2218,9 @@ int ocfs2_claim_new_inode_at_loc(handle_t *handle,
 					 bg,
 					 bg_bh,
 					 res->sr_bit_offset,
-					 res->sr_bits);
+					 res->sr_bits,
+					 res->sr_max_contig_bits,
+					 0);
 	if (ret < 0) {
 		ocfs2_rollback_alloc_dinode_counts(ac->ac_inode,
 					       ac->ac_bh, res->sr_bits, chain);
@@ -2382,11 +2439,13 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
 					struct buffer_head *group_bh,
 					unsigned int bit_off,
 					unsigned int num_bits,
+					unsigned int max_contig_bits,
 					void (*undo_fn)(unsigned int bit,
 							unsigned long *bmap))
 {
 	int status;
 	unsigned int tmp;
+	u16 contig_bits;
 	struct ocfs2_group_desc *undo_bg = NULL;
 	struct journal_head *jh;
 
@@ -2433,6 +2492,20 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
 				   num_bits);
 	}
 
+	/*
+	 * TODO: even 'num_bits == 1' (the worst case, release 1 cluster),
+	 * we still need to rescan whole bitmap.
+	 */
+	if (ocfs2_is_cluster_bitmap(alloc_inode)) {
+		contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap,
+				    le16_to_cpu(bg->bg_bits), 0);
+		if (contig_bits > max_contig_bits)
+			max_contig_bits = contig_bits;
+		bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits);
+	} else {
+		bg->bg_contig_free_bits = 0;
+	}
+
 	if (undo_fn)
 		spin_unlock(&jh->b_state_lock);
 
@@ -2459,6 +2532,7 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle,
 	struct ocfs2_chain_list *cl = &fe->id2.i_chain;
 	struct buffer_head *group_bh = NULL;
 	struct ocfs2_group_desc *group;
+	__le16 old_bg_contig_free_bits = 0;
 
 	/* The alloc_bh comes from ocfs2_free_dinode() or
 	 * ocfs2_free_clusters().  The callers have all locked the
@@ -2483,9 +2557,11 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle,
 
 	BUG_ON((count + start_bit) > le16_to_cpu(group->bg_bits));
 
+	if (ocfs2_is_cluster_bitmap(alloc_inode))
+		old_bg_contig_free_bits = group->bg_contig_free_bits;
 	status = ocfs2_block_group_clear_bits(handle, alloc_inode,
 					      group, group_bh,
-					      start_bit, count, undo_fn);
+					      start_bit, count, 0, undo_fn);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -2496,7 +2572,8 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle,
 	if (status < 0) {
 		mlog_errno(status);
 		ocfs2_block_group_set_bits(handle, alloc_inode, group, group_bh,
-				start_bit, count);
+				start_bit, count,
+				le16_to_cpu(old_bg_contig_free_bits), 1);
 		goto bail;
 	}
 
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index 9c74eace3adc..b481b834857d 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -79,12 +79,16 @@ void ocfs2_rollback_alloc_dinode_counts(struct inode *inode,
 			 struct buffer_head *di_bh,
 			 u32 num_bits,
 			 u16 chain);
+u16 ocfs2_find_max_contig_free_bits(void *bitmap,
+			 u16 total_bits, u16 start);
 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);
+			 unsigned int num_bits,
+			 unsigned int max_contig_bits,
+			 int fastpath);
 
 int ocfs2_claim_metadata(handle_t *handle,
 			 struct ocfs2_alloc_context *ac,