nilfs2: segment constructor

This adds the segment constructor (also called log writer).

The segment constructor collects dirty buffers for every dirty inode,
makes summaries of the buffers, assigns disk block addresses to the
buffers, and then submits BIOs for the buffers.

Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 3577 insertions, 3 deletions

diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 7ddd42e24f77..8031086db8d5 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -73,10 +73,66 @@ nilfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	return ret;
 }
 
-static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct page *page)
+static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	if (!(vma->vm_flags & (VM_WRITE | VM_MAYWRITE)))
-		return -EPERM;
+	struct page *page = vmf->page;
+	struct inode *inode = vma->vm_file->f_dentry->d_inode;
+	struct nilfs_transaction_info ti;
+	int ret;
+
+	if (unlikely(nilfs_near_disk_full(NILFS_SB(inode->i_sb)->s_nilfs)))
+		return VM_FAULT_SIGBUS; /* -ENOSPC */
+
+	lock_page(page);
+	if (page->mapping != inode->i_mapping ||
+	    page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
+		unlock_page(page);
+		return VM_FAULT_NOPAGE; /* make the VM retry the fault */
+	}
+
+	/*
+	 * check to see if the page is mapped already (no holes)
+	 */
+	if (PageMappedToDisk(page)) {
+		unlock_page(page);
+		goto mapped;
+	}
+	if (page_has_buffers(page)) {
+		struct buffer_head *bh, *head;
+		int fully_mapped = 1;
+
+		bh = head = page_buffers(page);
+		do {
+			if (!buffer_mapped(bh)) {
+				fully_mapped = 0;
+				break;
+			}
+		} while (bh = bh->b_this_page, bh != head);
+
+		if (fully_mapped) {
+			SetPageMappedToDisk(page);
+			unlock_page(page);
+			goto mapped;
+		}
+	}
+	unlock_page(page);
+
+	/*
+	 * fill hole blocks
+	 */
+	ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
+	/* never returns -ENOMEM, but may return -ENOSPC */
+	if (unlikely(ret))
+		return VM_FAULT_SIGBUS;
+
+	ret = block_page_mkwrite(vma, vmf, nilfs_get_block);
+	if (unlikely(ret)) {
+		nilfs_transaction_abort(inode->i_sb);
+		return ret;
+	}
+	nilfs_transaction_commit(inode->i_sb);
+
+ mapped:
 	SetPageChecked(page);
 	wait_on_page_writeback(page);
 	return 0;
diff --git a/fs/nilfs2/seglist.h b/fs/nilfs2/seglist.h
new file mode 100644
index 000000000000..d39df9144e99
--- /dev/null
+++ b/fs/nilfs2/seglist.h
@@ -0,0 +1,85 @@
+/*
+ * seglist.h - expediential structure and routines to handle list of segments
+ *             (would be removed in a future release)
+ *
+ * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ *
+ * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ *
+ */
+#ifndef _NILFS_SEGLIST_H
+#define _NILFS_SEGLIST_H
+
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/nilfs2_fs.h>
+#include "sufile.h"
+
+struct nilfs_segment_entry {
+	__u64			segnum;
+
+#define NILFS_SLH_FREED		0x0001	/* The segment was freed provisonally.
+					   It must be cancelled if
+					   construction aborted */
+
+	unsigned		flags;
+	struct list_head	list;
+	struct buffer_head     *bh_su;
+	struct nilfs_segment_usage *raw_su;
+};
+
+
+void nilfs_dispose_segment_list(struct list_head *);
+
+static inline struct nilfs_segment_entry *
+nilfs_alloc_segment_entry(__u64 segnum)
+{
+	struct nilfs_segment_entry *ent = kmalloc(sizeof(*ent), GFP_NOFS);
+
+	if (likely(ent)) {
+		ent->segnum = segnum;
+		ent->flags = 0;
+		ent->bh_su = NULL;
+		ent->raw_su = NULL;
+		INIT_LIST_HEAD(&ent->list);
+	}
+	return ent;
+}
+
+static inline int nilfs_open_segment_entry(struct nilfs_segment_entry *ent,
+					   struct inode *sufile)
+{
+	return nilfs_sufile_get_segment_usage(sufile, ent->segnum,
+					      &ent->raw_su, &ent->bh_su);
+}
+
+static inline void nilfs_close_segment_entry(struct nilfs_segment_entry *ent,
+					     struct inode *sufile)
+{
+	if (!ent->bh_su)
+		return;
+	nilfs_sufile_put_segment_usage(sufile, ent->segnum, ent->bh_su);
+	ent->bh_su = NULL;
+	ent->raw_su = NULL;
+}
+
+static inline void nilfs_free_segment_entry(struct nilfs_segment_entry *ent)
+{
+	kfree(ent);
+}
+
+#endif /* _NILFS_SEGLIST_H */
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
new file mode 100644
index 000000000000..2c4c088059fd
--- /dev/null
+++ b/fs/nilfs2/segment.c
@@ -0,0 +1,3187 @@
+/*
+ * segment.c - NILFS segment constructor.
+ *
+ * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ *
+ * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ *
+ */
+
+#include <linux/pagemap.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+#include <linux/bio.h>
+#include <linux/completion.h>
+#include <linux/blkdev.h>
+#include <linux/backing-dev.h>
+#include <linux/freezer.h>
+#include <linux/kthread.h>
+#include <linux/crc32.h>
+#include <linux/pagevec.h>
+#include "nilfs.h"
+#include "btnode.h"
+#include "page.h"
+#include "segment.h"
+#include "sufile.h"
+#include "cpfile.h"
+#include "ifile.h"
+#include "seglist.h"
+#include "segbuf.h"
+
+
+/*
+ * Segment constructor
+ */
+#define SC_N_INODEVEC	16   /* Size of locally allocated inode vector */
+
+#define SC_MAX_SEGDELTA 64   /* Upper limit of the number of segments
+				appended in collection retry loop */
+
+/* Construction mode */
+enum {
+	SC_LSEG_SR = 1,	/* Make a logical segment having a super root */
+	SC_LSEG_DSYNC,	/* Flush data blocks of a given file and make
+			   a logical segment without a super root */
+	SC_FLUSH_FILE,	/* Flush data files, leads to segment writes without
+			   creating a checkpoint */
+	SC_FLUSH_DAT,	/* Flush DAT file. This also creates segments without
+			   a checkpoint */
+};
+
+/* Stage numbers of dirty block collection */
+enum {
+	NILFS_ST_INIT = 0,
+	NILFS_ST_GC,		/* Collecting dirty blocks for GC */
+	NILFS_ST_FILE,
+	NILFS_ST_SKETCH,
+	NILFS_ST_IFILE,
+	NILFS_ST_CPFILE,
+	NILFS_ST_SUFILE,
+	NILFS_ST_DAT,
+	NILFS_ST_SR,		/* Super root */
+	NILFS_ST_DSYNC,		/* Data sync blocks */
+	NILFS_ST_DONE,
+};
+
+/* State flags of collection */
+#define NILFS_CF_NODE		0x0001	/* Collecting node blocks */
+#define NILFS_CF_IFILE_STARTED	0x0002	/* IFILE stage has started */
+#define NILFS_CF_HISTORY_MASK	(NILFS_CF_IFILE_STARTED)
+
+/* Operations depending on the construction mode and file type */
+struct nilfs_sc_operations {
+	int (*collect_data)(struct nilfs_sc_info *, struct buffer_head *,
+			    struct inode *);
+	int (*collect_node)(struct nilfs_sc_info *, struct buffer_head *,
+			    struct inode *);
+	int (*collect_bmap)(struct nilfs_sc_info *, struct buffer_head *,
+			    struct inode *);
+	void (*write_data_binfo)(struct nilfs_sc_info *,
+				 struct nilfs_segsum_pointer *,
+				 union nilfs_binfo *);
+	void (*write_node_binfo)(struct nilfs_sc_info *,
+				 struct nilfs_segsum_pointer *,
+				 union nilfs_binfo *);
+};
+
+/*
+ * Other definitions
+ */
+static void nilfs_segctor_start_timer(struct nilfs_sc_info *);
+static void nilfs_segctor_do_flush(struct nilfs_sc_info *, int);
+static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *);
+static void nilfs_dispose_list(struct nilfs_sb_info *, struct list_head *,
+			       int);
+
+#define nilfs_cnt32_gt(a, b)   \
+	(typecheck(__u32, a) && typecheck(__u32, b) && \
+	 ((__s32)(b) - (__s32)(a) < 0))
+#define nilfs_cnt32_ge(a, b)   \
+	(typecheck(__u32, a) && typecheck(__u32, b) && \
+	 ((__s32)(a) - (__s32)(b) >= 0))
+#define nilfs_cnt32_lt(a, b)  nilfs_cnt32_gt(b, a)
+#define nilfs_cnt32_le(a, b)  nilfs_cnt32_ge(b, a)
+
+/*
+ * Transaction
+ */
+static struct kmem_cache *nilfs_transaction_cachep;
+
+/**
+ * nilfs_init_transaction_cache - create a cache for nilfs_transaction_info
+ *
+ * nilfs_init_transaction_cache() creates a slab cache for the struct
+ * nilfs_transaction_info.
+ *
+ * Return Value: On success, it returns 0. On error, one of the following
+ * negative error code is returned.
+ *
+ * %-ENOMEM - Insufficient memory available.
+ */
+int nilfs_init_transaction_cache(void)
+{
+	nilfs_transaction_cachep =
+		kmem_cache_create("nilfs2_transaction_cache",
+				  sizeof(struct nilfs_transaction_info),
+				  0, SLAB_RECLAIM_ACCOUNT, NULL);
+	return (nilfs_transaction_cachep == NULL) ? -ENOMEM : 0;
+}
+
+/**
+ * nilfs_detroy_transaction_cache - destroy the cache for transaction info
+ *
+ * nilfs_destroy_transaction_cache() frees the slab cache for the struct
+ * nilfs_transaction_info.
+ */
+void nilfs_destroy_transaction_cache(void)
+{
+	kmem_cache_destroy(nilfs_transaction_cachep);
+}
+
+static int nilfs_prepare_segment_lock(struct nilfs_transaction_info *ti)
+{
+	struct nilfs_transaction_info *cur_ti = current->journal_info;
+	void *save = NULL;
+
+	if (cur_ti) {
+		if (cur_ti->ti_magic == NILFS_TI_MAGIC)
+			return ++cur_ti->ti_count;
+		else {
+			/*
+			 * If journal_info field is occupied by other FS,
+			 * we save it and restore on nilfs_transaction_end().
+			 * But this should never happen.
+			 */
+			printk(KERN_WARNING
+			       "NILFS warning: journal info from a different "
+			       "FS\n");
+			save = current->journal_info;
+		}
+	}
+	if (!ti) {
+		ti = kmem_cache_alloc(nilfs_transaction_cachep, GFP_NOFS);
+		if (!ti)
+			return -ENOMEM;
+		ti->ti_flags = NILFS_TI_DYNAMIC_ALLOC;
+	} else {
+		ti->ti_flags = 0;
+	}
+	ti->ti_count = 0;
+	ti->ti_save = save;
+	ti->ti_magic = NILFS_TI_MAGIC;
+	current->journal_info = ti;
+	return 0;
+}
+
+/**
+ * nilfs_transaction_begin - start indivisible file operations.
+ * @sb: super block
+ * @ti: nilfs_transaction_info
+ * @vacancy_check: flags for vacancy rate checks
+ *
+ * nilfs_transaction_begin() acquires a reader/writer semaphore, called
+ * the segment semaphore, to make a segment construction and write tasks
+ * exclusive.  The function is used with nilfs_transaction_end() in pairs.
+ * The region enclosed by these two functions can be nested.  To avoid a
+ * deadlock, the semaphore is only acquired or released in the outermost call.
+ *
+ * This function allocates a nilfs_transaction_info struct to keep context
+ * information on it.  It is initialized and hooked onto the current task in
+ * the outermost call.  If a pre-allocated struct is given to @ti, it is used
+ * instead; othewise a new struct is assigned from a slab.
+ *
+ * When @vacancy_check flag is set, this function will check the amount of
+ * free space, and will wait for the GC to reclaim disk space if low capacity.
+ *
+ * Return Value: On success, 0 is returned. On error, one of the following
+ * negative error code is returned.
+ *
+ * %-ENOMEM - Insufficient memory available.
+ *
+ * %-ERESTARTSYS - Interrupted
+ *
+ * %-ENOSPC - No space left on device
+ */
+int nilfs_transaction_begin(struct super_block *sb,
+			    struct nilfs_transaction_info *ti,
+			    int vacancy_check)
+{
+	struct nilfs_sb_info *sbi;
+	struct the_nilfs *nilfs;
+	int ret = nilfs_prepare_segment_lock(ti);
+
+	if (unlikely(ret < 0))
+		return ret;
+	if (ret > 0)
+		return 0;
+
+	sbi = NILFS_SB(sb);
+	nilfs = sbi->s_nilfs;
+	down_read(&nilfs->ns_segctor_sem);
+	if (vacancy_check && nilfs_near_disk_full(nilfs)) {
+		up_read(&nilfs->ns_segctor_sem);
+		ret = -ENOSPC;
+		goto failed;
+	}
+	return 0;
+
+ failed:
+	ti = current->journal_info;
+	current->journal_info = ti->ti_save;
+	if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
+		kmem_cache_free(nilfs_transaction_cachep, ti);
+	return ret;
+}
+
+/**
+ * nilfs_transaction_end - end indivisible file operations.
+ * @sb: super block
+ * @commit: commit flag (0 for no change)
+ *
+ * nilfs_transaction_end() releases the read semaphore which is
+ * acquired by nilfs_transaction_begin(). Its releasing is only done
+ * in outermost call of this function. If the nilfs_transaction_info
+ * was allocated dynamically, it is given back to a slab cache.
+ */
+int nilfs_transaction_end(struct super_block *sb, int commit)
+{
+	struct nilfs_transaction_info *ti = current->journal_info;
+	struct nilfs_sb_info *sbi;
+	struct nilfs_sc_info *sci;
+	int err = 0;
+
+	BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
+
+	if (commit)
+		ti->ti_flags |= NILFS_TI_COMMIT;
+	if (ti->ti_count > 0) {
+		ti->ti_count--;
+		return 0;
+	}
+	sbi = NILFS_SB(sb);
+	sci = NILFS_SC(sbi);
+	if (sci != NULL) {
+		if (ti->ti_flags & NILFS_TI_COMMIT)
+			nilfs_segctor_start_timer(sci);
+		if (atomic_read(&sbi->s_nilfs->ns_ndirtyblks) >
+		    sci->sc_watermark)
+			nilfs_segctor_do_flush(sci, 0);
+	}
+	up_read(&sbi->s_nilfs->ns_segctor_sem);
+	current->journal_info = ti->ti_save;
+
+	if (ti->ti_flags & NILFS_TI_SYNC)
+		err = nilfs_construct_segment(sb);
+	if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
+		kmem_cache_free(nilfs_transaction_cachep, ti);
+	return err;
+}
+
+void nilfs_relax_pressure_in_lock(struct super_block *sb)
+{
+	struct nilfs_sb_info *sbi = NILFS_SB(sb);
+	struct nilfs_sc_info *sci = NILFS_SC(sbi);
+	struct the_nilfs *nilfs = sbi->s_nilfs;
+
+	if (!sci || !sci->sc_flush_request)
+		return;
+
+	set_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags);
+	up_read(&nilfs->ns_segctor_sem);
+
+	down_write(&nilfs->ns_segctor_sem);
+	if (sci->sc_flush_request &&
+	    test_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags)) {
+		struct nilfs_transaction_info *ti = current->journal_info;
+
+		ti->ti_flags |= NILFS_TI_WRITER;
+		nilfs_segctor_do_immediate_flush(sci);
+		ti->ti_flags &= ~NILFS_TI_WRITER;
+	}
+	downgrade_write(&nilfs->ns_segctor_sem);
+}
+
+static void nilfs_transaction_lock(struct nilfs_sb_info *sbi,
+				   struct nilfs_transaction_info *ti,
+				   int gcflag)
+{
+	struct nilfs_transaction_info *cur_ti = current->journal_info;
+
+	BUG_ON(cur_ti);
+	BUG_ON(!ti);
+	ti->ti_flags = NILFS_TI_WRITER;
+	ti->ti_count = 0;
+	ti->ti_save = cur_ti;
+	ti->ti_magic = NILFS_TI_MAGIC;
+	INIT_LIST_HEAD(&ti->ti_garbage);
+	current->journal_info = ti;
+
+	for (;;) {
+		down_write(&sbi->s_nilfs->ns_segctor_sem);
+		if (!test_bit(NILFS_SC_PRIOR_FLUSH, &NILFS_SC(sbi)->sc_flags))
+			break;
+
+		nilfs_segctor_do_immediate_flush(NILFS_SC(sbi));
+
+		up_write(&sbi->s_nilfs->ns_segctor_sem);
+		yield();
+	}
+	if (gcflag)
+		ti->ti_flags |= NILFS_TI_GC;
+}
+
+static void nilfs_transaction_unlock(struct nilfs_sb_info *sbi)
+{
+	struct nilfs_transaction_info *ti = current->journal_info;
+
+	BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
+	BUG_ON(ti->ti_count > 0);
+
+	up_write(&sbi->s_nilfs->ns_segctor_sem);
+	current->journal_info = ti->ti_save;
+	if (!list_empty(&ti->ti_garbage))
+		nilfs_dispose_list(sbi, &ti->ti_garbage, 0);
+}
+
+static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
+					    struct nilfs_segsum_pointer *ssp,
+					    unsigned bytes)
+{
+	struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
+	unsigned blocksize = sci->sc_super->s_blocksize;
+	void *p;
+
+	if (unlikely(ssp->offset + bytes > blocksize)) {
+		ssp->offset = 0;
+		BUG_ON(NILFS_SEGBUF_BH_IS_LAST(ssp->bh,
+					       &segbuf->sb_segsum_buffers));
+		ssp->bh = NILFS_SEGBUF_NEXT_BH(ssp->bh);
+	}
+	p = ssp->bh->b_data + ssp->offset;
+	ssp->offset += bytes;
+	return p;
+}
+
+/**
+ * nilfs_segctor_reset_segment_buffer - reset the current segment buffer
+ * @sci: nilfs_sc_info
+ */
+static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci)
+{
+	struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
+	struct buffer_head *sumbh;
+	unsigned sumbytes;
+	unsigned flags = 0;
+	int err;
+
+	if (nilfs_doing_gc())
+		flags = NILFS_SS_GC;
+	err = nilfs_segbuf_reset(segbuf, flags, sci->sc_seg_ctime);
+	if (unlikely(err))
+		return err;
+
+	sumbh = NILFS_SEGBUF_FIRST_BH(&segbuf->sb_segsum_buffers);
+	sumbytes = segbuf->sb_sum.sumbytes;
+	sci->sc_finfo_ptr.bh = sumbh;  sci->sc_finfo_ptr.offset = sumbytes;
+	sci->sc_binfo_ptr.bh = sumbh;  sci->sc_binfo_ptr.offset = sumbytes;
+	sci->sc_blk_cnt = sci->sc_datablk_cnt = 0;
+	return 0;
+}
+
+static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci)
+{
+	sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks;
+	if (NILFS_SEGBUF_IS_LAST(sci->sc_curseg, &sci->sc_segbufs))
+		return -E2BIG; /* The current segment is filled up
+				  (internal code) */
+	sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg);
+	return nilfs_segctor_reset_segment_buffer(sci);
+}
+
+static int nilfs_segctor_add_super_root(struct nilfs_sc_info *sci)
+{
+	struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
+	int err;
+
+	if (segbuf->sb_sum.nblocks >= segbuf->sb_rest_blocks) {
+		err = nilfs_segctor_feed_segment(sci);
+		if (err)
+			return err;
+		segbuf = sci->sc_curseg;
+	}
+	err = nilfs_segbuf_extend_payload(segbuf, &sci->sc_super_root);
+	if (likely(!err))
+		segbuf->sb_sum.flags |= NILFS_SS_SR;
+	return err;
+}
+
+/*
+ * Functions for making segment summary and payloads
+ */
+static int nilfs_segctor_segsum_block_required(
+	struct nilfs_sc_info *sci, const struct nilfs_segsum_pointer *ssp,
+	unsigned binfo_size)
+{
+	unsigned blocksize = sci->sc_super->s_blocksize;
+	/* Size of finfo and binfo is enough small against blocksize */
+
+	return ssp->offset + binfo_size +
+		(!sci->sc_blk_cnt ? sizeof(struct nilfs_finfo) : 0) >
+		blocksize;
+}
+
+static void nilfs_segctor_begin_finfo(struct nilfs_sc_info *sci,
+				      struct inode *inode)
+{
+	sci->sc_curseg->sb_sum.nfinfo++;
+	sci->sc_binfo_ptr = sci->sc_finfo_ptr;
+	nilfs_segctor_map_segsum_entry(
+		sci, &sci->sc_binfo_ptr, sizeof(struct nilfs_finfo));
+	/* skip finfo */
+}
+
+static void nilfs_segctor_end_finfo(struct nilfs_sc_info *sci,
+				    struct inode *inode)
+{
+	struct nilfs_finfo *finfo;
+	struct nilfs_inode_info *ii;
+	struct nilfs_segment_buffer *segbuf;
+
+	if (sci->sc_blk_cnt == 0)
+		return;
+
+	ii = NILFS_I(inode);
+	finfo = nilfs_segctor_map_segsum_entry(sci, &sci->sc_finfo_ptr,
+						 sizeof(*finfo));
+	finfo->fi_ino = cpu_to_le64(inode->i_ino);
+	finfo->fi_nblocks = cpu_to_le32(sci->sc_blk_cnt);
+	finfo->fi_ndatablk = cpu_to_le32(sci->sc_datablk_cnt);
+	finfo->fi_cno = cpu_to_le64(ii->i_cno);
+
+	segbuf = sci->sc_curseg;
+	segbuf->sb_sum.sumbytes = sci->sc_binfo_ptr.offset +
+		sci->sc_super->s_blocksize * (segbuf->sb_sum.nsumblk - 1);
+	sci->sc_finfo_ptr = sci->sc_binfo_ptr;
+	sci->sc_blk_cnt = sci->sc_datablk_cnt = 0;
+}
+
+static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci,
+					struct buffer_head *bh,
+					struct inode *inode,
+					unsigned binfo_size)
+{
+	struct nilfs_segment_buffer *segbuf;
+	int required, err = 0;
+
+ retry:
+	segbuf = sci->sc_curseg;
+	required = nilfs_segctor_segsum_block_required(
+		sci, &sci->sc_binfo_ptr, binfo_size);
+	if (segbuf->sb_sum.nblocks + required + 1 > segbuf->sb_rest_blocks) {
+		nilfs_segctor_end_finfo(sci, inode);
+		err = nilfs_segctor_feed_segment(sci);
+		if (err)
+			return err;
+		goto retry;
+	}
+	if (unlikely(required)) {
+		err = nilfs_segbuf_extend_segsum(segbuf);
+		if (unlikely(err))
+			goto failed;
+	}
+	if (sci->sc_blk_cnt == 0)
+		nilfs_segctor_begin_finfo(sci, inode);
+
+	nilfs_segctor_map_segsum_entry(sci, &sci->sc_binfo_ptr, binfo_size);
+	/* Substitution to vblocknr is delayed until update_blocknr() */
+	nilfs_segbuf_add_file_buffer(segbuf, bh);
+	sci->sc_blk_cnt++;
+ failed:
+	return err;
+}
+
+static int nilfs_handle_bmap_error(int err, const char *fname,
+				   struct inode *inode, struct super_block *sb)
+{
+	if (err == -EINVAL) {
+		nilfs_error(sb, fname, "broken bmap (inode=%lu)\n",
+			    inode->i_ino);
+		err = -EIO;
+	}
+	return err;
+}
+
+/*
+ * Callback functions that enumerate, mark, and collect dirty blocks
+ */
+static int nilfs_collect_file_data(struct nilfs_sc_info *sci,
+				   struct buffer_head *bh, struct inode *inode)
+{
+	int err;
+
+	/* BUG_ON(!buffer_dirty(bh)); */
+	/* excluded by scan_dirty_data_buffers() */
+	err = nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
+	if (unlikely(err < 0))
+		return nilfs_handle_bmap_error(err, __func__, inode,
+					       sci->sc_super);
+
+	err = nilfs_segctor_add_file_block(sci, bh, inode,
+					   sizeof(struct nilfs_binfo_v));
+	if (!err)
+		sci->sc_datablk_cnt++;
+	return err;
+}
+
+static int nilfs_collect_file_node(struct nilfs_sc_info *sci,
+				   struct buffer_head *bh,
+				   struct inode *inode)
+{
+	int err;
+
+	/* BUG_ON(!buffer_dirty(bh)); */
+	/* excluded by scan_dirty_node_buffers() */
+	err = nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
+	if (unlikely(err < 0))
+		return nilfs_handle_bmap_error(err, __func__, inode,
+					       sci->sc_super);
+	return 0;
+}
+
+static int nilfs_collect_file_bmap(struct nilfs_sc_info *sci,
+				   struct buffer_head *bh,
+				   struct inode *inode)
+{
+	BUG_ON(!buffer_dirty(bh));
+	return nilfs_segctor_add_file_block(sci, bh, inode, sizeof(__le64));
+}
+
+static void nilfs_write_file_data_binfo(struct nilfs_sc_info *sci,
+					struct nilfs_segsum_pointer *ssp,
+					union nilfs_binfo *binfo)
+{
+	struct nilfs_binfo_v *binfo_v = nilfs_segctor_map_segsum_entry(
+		sci, ssp, sizeof(*binfo_v));
+	*binfo_v = binfo->bi_v;
+}
+
+static void nilfs_write_file_node_binfo(struct nilfs_sc_info *sci,
+					struct nilfs_segsum_pointer *ssp,
+					union nilfs_binfo *binfo)
+{
+	__le64 *vblocknr = nilfs_segctor_map_segsum_entry(
+		sci, ssp, sizeof(*vblocknr));
+	*vblocknr = binfo->bi_v.bi_vblocknr;
+}
+
+struct nilfs_sc_operations nilfs_sc_file_ops = {
+	.collect_data = nilfs_collect_file_data,
+	.collect_node = nilfs_collect_file_node,
+	.collect_bmap = nilfs_collect_file_bmap,
+	.write_data_binfo = nilfs_write_file_data_binfo,
+	.write_node_binfo = nilfs_write_file_node_binfo,
+};
+
+static int nilfs_collect_dat_data(struct nilfs_sc_info *sci,
+				  struct buffer_head *bh, struct inode *inode)
+{
+	int err;
+
+	err = nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
+	if (unlikely(err < 0))
+		return nilfs_handle_bmap_error(err, __func__, inode,
+					       sci->sc_super);
+
+	err = nilfs_segctor_add_file_block(sci, bh, inode, sizeof(__le64));
+	if (!err)
+		sci->sc_datablk_cnt++;
+	return err;
+}
+
+static int nilfs_collect_dat_bmap(struct nilfs_sc_info *sci,
+				  struct buffer_head *bh, struct inode *inode)
+{
+	BUG_ON(!buffer_dirty(bh));
+	return nilfs_segctor_add_file_block(sci, bh, inode,
+					    sizeof(struct nilfs_binfo_dat));
+}
+
+static void nilfs_write_dat_data_binfo(struct nilfs_sc_info *sci,
+				       struct nilfs_segsum_pointer *ssp,
+				       union nilfs_binfo *binfo)
+{
+	__le64 *blkoff = nilfs_segctor_map_segsum_entry(sci, ssp,
+							  sizeof(*blkoff));
+	*blkoff = binfo->bi_dat.bi_blkoff;
+}
+
+static void nilfs_write_dat_node_binfo(struct nilfs_sc_info *sci,
+				       struct nilfs_segsum_pointer *ssp,
+				       union nilfs_binfo *binfo)
+{
+	struct nilfs_binfo_dat *binfo_dat =
+		nilfs_segctor_map_segsum_entry(sci, ssp, sizeof(*binfo_dat));
+	*binfo_dat = binfo->bi_dat;
+}
+
+struct nilfs_sc_operations nilfs_sc_dat_ops = {
+	.collect_data = nilfs_collect_dat_data,
+	.collect_node = nilfs_collect_file_node,
+	.collect_bmap = nilfs_collect_dat_bmap,
+	.write_data_binfo = nilfs_write_dat_data_binfo,
+	.write_node_binfo = nilfs_write_dat_node_binfo,
+};
+
+struct nilfs_sc_operations nilfs_sc_dsync_ops = {
+	.collect_data = nilfs_collect_file_data,
+	.collect_node = NULL,
+	.collect_bmap = NULL,
+	.write_data_binfo = nilfs_write_file_data_binfo,
+	.write_node_binfo = NULL,
+};
+
+static int nilfs_lookup_dirty_data_buffers(struct inode *inode,
+					   struct list_head *listp,
+					   struct nilfs_sc_info *sci)
+{
+	struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
+	struct address_space *mapping = inode->i_mapping;
+	struct pagevec pvec;
+	unsigned i, ndirties = 0, nlimit;
+	pgoff_t index = 0;
+	int err = 0;
+
+	nlimit = sci->sc_segbuf_nblocks -
+		(sci->sc_nblk_this_inc + segbuf->sb_sum.nblocks);
+	pagevec_init(&pvec, 0);
+ repeat:
+	if (!pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
+				PAGEVEC_SIZE))
+		return 0;
+
+	for (i = 0; i < pagevec_count(&pvec); i++) {
+		struct buffer_head *bh, *head;
+		struct page *page = pvec.pages[i];
+
+		if (mapping->host) {
+			lock_page(page);
+			if (!page_has_buffers(page))
+				create_empty_buffers(page,
+						     1 << inode->i_blkbits, 0);
+			unlock_page(page);
+		}
+
+		bh = head = page_buffers(page);
+		do {
+			if (buffer_dirty(bh)) {
+				if (ndirties > nlimit) {
+					err = -E2BIG;
+					break;
+				}
+				get_bh(bh);
+				list_add_tail(&bh->b_assoc_buffers, listp);
+				ndirties++;
+			}
+			bh = bh->b_this_page;
+		} while (bh != head);
+	}
+	pagevec_release(&pvec);
+	cond_resched();
+
+	if (!err)
+		goto repeat;
+	return err;
+}
+
+static void nilfs_lookup_dirty_node_buffers(struct inode *inode,
+					    struct list_head *listp)
+{
+	struct nilfs_inode_info *ii = NILFS_I(inode);
+	struct address_space *mapping = &ii->i_btnode_cache;
+	struct pagevec pvec;
+	struct buffer_head *bh, *head;
+	unsigned int i;
+	pgoff_t index = 0;
+
+	pagevec_init(&pvec, 0);
+
+	while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
+				  PAGEVEC_SIZE)) {
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			bh = head = page_buffers(pvec.pages[i]);
+			do {
+				if (buffer_dirty(bh)) {
+					get_bh(bh);
+					list_add_tail(&bh->b_assoc_buffers,
+						      listp);
+				}
+				bh = bh->b_this_page;
+			} while (bh != head);
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+}
+
+static void nilfs_dispose_list(struct nilfs_sb_info *sbi,
+			       struct list_head *head, int force)
+{
+	struct nilfs_inode_info *ii, *n;
+	struct nilfs_inode_info *ivec[SC_N_INODEVEC], **pii;
+	unsigned nv = 0;
+
+	while (!list_empty(head)) {
+		spin_lock(&sbi->s_inode_lock);
+		list_for_each_entry_safe(ii, n, head, i_dirty) {
+			list_del_init(&ii->i_dirty);
+			if (force) {
+				if (unlikely(ii->i_bh)) {
+					brelse(ii->i_bh);
+					ii->i_bh = NULL;
+				}
+			} else if (test_bit(NILFS_I_DIRTY, &ii->i_state)) {
+				set_bit(NILFS_I_QUEUED, &ii->i_state);
+				list_add_tail(&ii->i_dirty,
+					      &sbi->s_dirty_files);
+				continue;
+			}
+			ivec[nv++] = ii;
+			if (nv == SC_N_INODEVEC)
+				break;
+		}
+		spin_unlock(&sbi->s_inode_lock);
+
+		for (pii = ivec; nv > 0; pii++, nv--)
+			iput(&(*pii)->vfs_inode);
+	}
+}
+
+static int nilfs_test_metadata_dirty(struct nilfs_sb_info *sbi)
+{
+	struct the_nilfs *nilfs = sbi->s_nilfs;
+	int ret = 0;
+
+	if (nilfs_mdt_fetch_dirty(sbi->s_ifile))
+		ret++;
+	if (nilfs_mdt_fetch_dirty(nilfs->ns_cpfile))
+		ret++;
+	if (nilfs_mdt_fetch_dirty(nilfs->ns_sufile))
+		ret++;
+	if (ret || nilfs_doing_gc())
+		if (nilfs_mdt_fetch_dirty(nilfs_dat_inode(nilfs)))
+			ret++;
+	return ret;
+}
+
+static int nilfs_segctor_clean(struct nilfs_sc_info *sci)
+{
+	return list_empty(&sci->sc_dirty_files) &&
+		!test_bit(NILFS_SC_DIRTY, &sci->sc_flags) &&
+		list_empty(&sci->sc_cleaning_segments) &&
+		(!nilfs_doing_gc() || list_empty(&sci->sc_gc_inodes));
+}
+
+static int nilfs_segctor_confirm(struct nilfs_sc_info *sci)
+{
+	struct nilfs_sb_info *sbi = sci->sc_sbi;
+	int ret = 0;
+
+	if (nilfs_test_metadata_dirty(sbi))
+		set_bit(NILFS_SC_DIRTY, &sci->sc_flags);
+
+	spin_lock(&sbi->s_inode_lock);
+	if (list_empty(&sbi->s_dirty_files) && nilfs_segctor_clean(sci))
+		ret++;
+
+	spin_unlock(&sbi->s_inode_lock);
+	return ret;
+}
+
+static void nilfs_segctor_clear_metadata_dirty(struct nilfs_sc_info *sci)
+{
+	struct nilfs_sb_info *sbi = sci->sc_sbi;
+	struct the_nilfs *nilfs = sbi->s_nilfs;
+
+	nilfs_mdt_clear_dirty(sbi->s_ifile);
+	nilfs_mdt_clear_dirty(nilfs->ns_cpfile);
+	nilfs_mdt_clear_dirty(nilfs->ns_sufile);
+	nilfs_mdt_clear_dirty(nilfs_dat_inode(nilfs));
+}
+
+static int nilfs_segctor_create_checkpoint(struct nilfs_sc_info *sci)
+{
+	struct the_nilfs *nilfs = sci->sc_sbi->s_nilfs;
+	struct buffer_head *bh_cp;
+	struct nilfs_checkpoint *raw_cp;
+	int err;
+
+	/* XXX: this interface will be changed */
+	err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, 1,
+					  &raw_cp, &bh_cp);
+	if (likely(!err)) {
+		/* The following code is duplicated with cpfile.  But, it is
+		   needed to collect the checkpoint even if it was not newly
+		   created */
+		nilfs_mdt_mark_buffer_dirty(bh_cp);
+		nilfs_mdt_mark_dirty(nilfs->ns_cpfile);
+		nilfs_cpfile_put_checkpoint(
+			nilfs->ns_cpfile, nilfs->ns_cno, bh_cp);
+	} else {
+		BUG_ON(err == -EINVAL || err == -ENOENT);
+	}
+	return err;
+}
+
+static int nilfs_segctor_fill_in_checkpoint(struct nilfs_sc_info *sci)
+{
+	struct nilfs_sb_info *sbi = sci->sc_sbi;
+	struct the_nilfs *nilfs = sbi->s_nilfs;
+	struct buffer_head *bh_cp;
+	struct nilfs_checkpoint *raw_cp;
+	int err;
+
+	err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, 0,
+					  &raw_cp, &bh_cp);
+	if (unlikely(err)) {
+		BUG_ON(err == -EINVAL || err == -ENOENT);
+		goto failed_ibh;
+	}
+	raw_cp->cp_snapshot_list.ssl_next = 0;
+	raw_cp->cp_snapshot_list.ssl_prev = 0;
+	raw_cp->cp_inodes_count =
+		cpu_to_le64(atomic_read(&sbi->s_inodes_count));
+	raw_cp->cp_blocks_count =
+		cpu_to_le64(atomic_read(&sbi->s_blocks_count));
+	raw_cp->cp_nblk_inc =
+		cpu_to_le64(sci->sc_nblk_inc + sci->sc_nblk_this_inc);
+	raw_cp->cp_create = cpu_to_le64(sci->sc_seg_ctime);
+	raw_cp->cp_cno = cpu_to_le64(nilfs->ns_cno);
+	if (sci->sc_sketch_inode && i_size_read(sci->sc_sketch_inode) > 0)
+		nilfs_checkpoint_set_sketch(raw_cp);
+	nilfs_write_inode_common(sbi->s_ifile, &raw_cp->cp_ifile_inode, 1);
+	nilfs_cpfile_put_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, bh_cp);
+	return 0;
+
+ failed_ibh:
+	return err;
+}
+
+static void nilfs_fill_in_file_bmap(struct inode *ifile,
+				    struct nilfs_inode_info *ii)
+
+{
+	struct buffer_head *ibh;
+	struct nilfs_inode *raw_inode;
+
+	if (test_bit(NILFS_I_BMAP, &ii->i_state)) {
+		ibh = ii->i_bh;
+		BUG_ON(!ibh);
+		raw_inode = nilfs_ifile_map_inode(ifile, ii->vfs_inode.i_ino,
+						  ibh);
+		nilfs_bmap_write(ii->i_bmap, raw_inode);
+		nilfs_ifile_unmap_inode(ifile, ii->vfs_inode.i_ino, ibh);
+	}
+}
+
+static void nilfs_segctor_fill_in_file_bmap(struct nilfs_sc_info *sci,
+					    struct inode *ifile)
+{
+	struct nilfs_inode_info *ii;
+
+	list_for_each_entry(ii, &sci->sc_dirty_files, i_dirty) {
+		nilfs_fill_in_file_bmap(ifile, ii);
+		set_bit(NILFS_I_COLLECTED, &ii->i_state);
+	}
+	if (sci->sc_sketch_inode) {
+		ii = NILFS_I(sci->sc_sketch_inode);
+		if (test_bit(NILFS_I_DIRTY, &ii->i_state))
+			nilfs_fill_in_file_bmap(ifile, ii);
+	}
+}
+
+/*
+ * CRC calculation routines
+ */
+static void nilfs_fill_in_super_root_crc(struct buffer_head *bh_sr, u32 seed)
+{
+	struct nilfs_super_root *raw_sr =
+		(struct nilfs_super_root *)bh_sr->b_data;
+	u32 crc;
+
+	BUG_ON(NILFS_SR_BYTES > bh_sr->b_size);
+	crc = crc32_le(seed,