segment.c

/*
 * 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 <linux/slab.h>
#include "nilfs.h"
#include "btnode.h"
#include "page.h"
#include "segment.h"
#include "sufile.h"
#include "cpfile.h"
#include "ifile.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_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_SUFREED	0x0004	/* segment usages has been freed */
#define NILFS_CF_HISTORY_MASK	(NILFS_CF_IFILE_STARTED | NILFS_CF_SUFREED)

/* 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 the_nilfs *, 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)

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,
			 * it is saved and will be restored on
			 * nilfs_transaction_commit().
			 */
			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_commit() 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; otherwise 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.
 *
 * %-ENOSPC - No space left on device
 */
int nilfs_transaction_begin(struct super_block *sb,
			    struct nilfs_transaction_info *ti,
			    int vacancy_check)
{
	struct the_nilfs *nilfs;
	int ret = nilfs_prepare_segment_lock(ti);

	if (unlikely(ret < 0))
		return ret;
	if (ret > 0)
		return 0;

	sb_start_intwrite(sb);

	nilfs = sb->s_fs_info;
	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);
	sb_end_intwrite(sb);
	return ret;
}

/**
 * nilfs_transaction_commit - commit indivisible file operations.
 * @sb: super block
 *
 * nilfs_transaction_commit() releases the read semaphore which is
 * acquired by nilfs_transaction_begin(). This is only performed
 * in outermost call of this function.  If a commit flag is set,
 * nilfs_transaction_commit() sets a timer to start the segment
 * constructor.  If a sync flag is set, it starts construction
 * directly.
 */
int nilfs_transaction_commit(struct super_block *sb)
{
	struct nilfs_transaction_info *ti = current->journal_info;
	struct the_nilfs *nilfs = sb->s_fs_info;
	int err = 0;

	BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
	ti->ti_flags |= NILFS_TI_COMMIT;
	if (ti->ti_count > 0) {
		ti->ti_count--;
		return 0;
	}
	if (nilfs->ns_writer) {
		struct nilfs_sc_info *sci = nilfs->ns_writer;

		if (ti->ti_flags & NILFS_TI_COMMIT)
			nilfs_segctor_start_timer(sci);
		if (atomic_read(&nilfs->ns_ndirtyblks) > sci->sc_watermark)
			nilfs_segctor_do_flush(sci, 0);
	}
	up_read(&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);
	sb_end_intwrite(sb);
	return err;
}

void nilfs_transaction_abort(struct super_block *sb)
{
	struct nilfs_transaction_info *ti = current->journal_info;
	struct the_nilfs *nilfs = sb->s_fs_info;

	BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
	if (ti->ti_count > 0) {
		ti->ti_count--;
		return;
	}
	up_read(&nilfs->ns_segctor_sem);

	current->journal_info = ti->ti_save;
	if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
		kmem_cache_free(nilfs_transaction_cachep, ti);
	sb_end_intwrite(sb);
}

void nilfs_relax_pressure_in_lock(struct super_block *sb)
{
	struct the_nilfs *nilfs = sb->s_fs_info;
	struct nilfs_sc_info *sci = nilfs->ns_writer;

	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 super_block *sb,
				   struct nilfs_transaction_info *ti,
				   int gcflag)
{
	struct nilfs_transaction_info *cur_ti = current->journal_info;
	struct the_nilfs *nilfs = sb->s_fs_info;
	struct nilfs_sc_info *sci = nilfs->ns_writer;

	WARN_ON(cur_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(&nilfs->ns_segctor_sem);
		if (!test_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags))
			break;

		nilfs_segctor_do_immediate_flush(sci);

		up_write(&nilfs->ns_segctor_sem);
		yield();
	}
	if (gcflag)
		ti->ti_flags |= NILFS_TI_GC;
}

static void nilfs_transaction_unlock(struct super_block *sb)
{
	struct nilfs_transaction_info *ti = current->journal_info;
	struct the_nilfs *nilfs = sb->s_fs_info;

	BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
	BUG_ON(ti->ti_count > 0);

	up_write(&nilfs->ns_segctor_sem);
	current->journal_info = ti->ti_save;
	if (!list_empty(&ti->ti_garbage))
		nilfs_dispose_list(nilfs, &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, sci->sc_cno);
	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, &segbuf->sb_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));

	if (NILFS_I(inode)->i_root &&
	    !test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags))
		set_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags);
	/* 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;
	__u64 cno;

	if (sci->sc_blk_cnt == 0)
		return;

	ii = NILFS_I(inode);

	if (test_bit(NILFS_I_GCINODE, &ii->i_state))
		cno = ii->i_cno;
	else if (NILFS_ROOT_METADATA_FILE(inode->i_ino))
		cno = 0;
	else
		cno = sci->sc_cno;

	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(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;
}

/*
 * 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;

	err = nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
	if (err < 0)
		return err;

	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)
{
	return nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
}

static int nilfs_collect_file_bmap(struct nilfs_sc_info *sci,
				   struct buffer_head *bh,
				   struct inode *inode)
{
	WARN_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;
}

static 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 (err < 0)
		return err;

	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)
{
	WARN_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;
}

static 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,
};

static 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 size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
					      struct list_head *listp,
					      size_t nlimit,
					      loff_t start, loff_t end)
{
	struct address_space *mapping = inode->i_mapping;
	struct pagevec pvec;
	pgoff_t index = 0, last = ULONG_MAX;
	size_t ndirties = 0;
	int i;

	if (unlikely(start != 0 || end != LLONG_MAX)) {
		/*
		 * A valid range is given for sync-ing data pages. The
		 * range is rounded to per-page; extra dirty buffers
		 * may be included if blocksize < pagesize.
		 */
		index = start >> PAGE_SHIFT;
		last = end >> PAGE_SHIFT;
	}
	pagevec_init(&pvec, 0);
 repeat:
	if (unlikely(index > last) ||
	    !pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
				min_t(pgoff_t, last - index,
				      PAGEVEC_SIZE - 1) + 1))
		return ndirties;

	for (i = 0; i < pagevec_count(&pvec); i++) {
		struct buffer_head *bh, *head;
		struct page *page = pvec.pages[i];

		if (unlikely(page->index > last))
			break;

		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) || buffer_async_write(bh))
				continue;
			get_bh(bh);
			list_add_tail(&bh->b_assoc_buffers, listp);
			ndirties++;
			if (unlikely(ndirties >= nlimit)) {
				pagevec_release(&pvec);
				cond_resched();
				return ndirties;
			}
		} while (bh = bh->b_this_page, bh != head);
	}
	pagevec_release(&pvec);
	cond_resched();
	goto repeat;
}

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) &&
						!buffer_async_write(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 the_nilfs *nilfs,
			       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(&nilfs->ns_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,
					      &nilfs->ns_dirty_files);
				continue;
			}
			ivec[nv++] = ii;
			if (nv == SC_N_INODEVEC)
				break;
		}
		spin_unlock(&nilfs->ns_inode_lock);

		for (pii = ivec; nv > 0; pii++, nv--)
			iput(&(*pii)->vfs_inode);
	}
}

static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs,
				     struct nilfs_root *root)
{
	int ret = 0;

	if (nilfs_mdt_fetch_dirty(root->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()) && nilfs_mdt_fetch_dirty(nilfs->ns_dat))
		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) &&
		sci->sc_nfreesegs == 0 &&
		(!nilfs_doing_gc() || list_empty(&sci->sc_gc_inodes));
}

static int nilfs_segctor_confirm(struct nilfs_sc_info *sci)
{
	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
	int ret = 0;

	if (nilfs_test_metadata_dirty(nilfs, sci->sc_root))
		set_bit(NILFS_SC_DIRTY, &sci->sc_flags);

	spin_lock(&nilfs->ns_inode_lock);
	if (list_empty(&nilfs->ns_dirty_files) && nilfs_segctor_clean(sci))
		ret++;

	spin_unlock(&nilfs->ns_inode_lock);
	return ret;
}

static void nilfs_segctor_clear_metadata_dirty(struct nilfs_sc_info *sci)
{
	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;

	nilfs_mdt_clear_dirty(sci->sc_root->ifile);
	nilfs_mdt_clear_dirty(nilfs->ns_cpfile);
	nilfs_mdt_clear_dirty(nilfs->ns_sufile);
	nilfs_mdt_clear_dirty(nilfs->ns_dat);
}

static int nilfs_segctor_create_checkpoint(struct nilfs_sc_info *sci)
{
	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
	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 */
		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
		WARN_ON(err == -EINVAL || err == -ENOENT);

	return err;
}

static int nilfs_segctor_fill_in_checkpoint(struct nilfs_sc_info *sci)
{
	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
	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)) {
		WARN_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(atomic64_read(&sci->sc_root->inodes_count));
	raw_cp->cp_blocks_count =
		cpu_to_le64(atomic64_read(&sci->sc_root->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 (test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags))
		nilfs_checkpoint_clear_minor(raw_cp);
	else
		nilfs_checkpoint_set_minor(raw_cp);

	nilfs_write_inode_common(sci->sc_root->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 nilfs_inode_info *ii;

	list_for_each_entry(ii, &sci->sc_dirty_files, i_dirty) {
		nilfs_fill_in_file_bmap(sci->sc_root->ifile, ii);
		set_bit(NILFS_I_COLLECTED, &ii->i_state);
	}
}

static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci,
					     struct the_nilfs *nilfs)
{
	struct buffer_head *bh_sr;
	struct nilfs_super_root *raw_sr;
	unsigned isz, srsz;

	bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root;
	raw_sr = (struct nilfs_super_root *)bh_sr->b_data;
	isz = nilfs->ns_inode_size;
	srsz = NILFS_SR_BYTES(isz);

	raw_sr->sr_bytes = cpu_to_le16(srsz);
	raw_sr->sr_nongc_ctime
		= cpu_to_le64(nilfs_doing_gc() ?
			      nilfs->ns_nongc_ctime : sci->sc_seg_ctime);
	raw_sr->sr_flags = 0;

	nilfs_write_inode_common(nilfs->ns_dat, (void *)raw_sr +
				 NILFS_SR_DAT_OFFSET(isz), 1);
	nilfs_write_inode_common(nilfs->ns_cpfile, (void *)raw_sr +
				 NILFS_SR_CPFILE_OFFSET(isz), 1);
	nilfs_write_inode_common(nilfs->ns_sufile, (void *)raw_sr +
				 NILFS_SR_SUFILE_OFFSET(isz), 1);
	memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz);
}

static void nilfs_redirty_inodes(struct list_head *head)
{
	struct nilfs_inode_info *ii;

	list_for_each_entry(ii, head, i_dirty) {
		if (test_bit(NILFS_I_COLLECTED, &ii->i_state))
			clear_bit(NILFS_I_COLLECTED, &ii->i_state);
	}
}

static void nilfs_drop_collected_inodes(struct list_head *head)
{
	struct nilfs_inode_info *ii;

	list_for_each_entry(ii, head, i_dirty) {
		if (!test_and_clear_bit(NILFS_I_COLLECTED, &ii->i_state))
			continue;

		clear_bit(NILFS_I_INODE_DIRTY, &ii->i_state);
		set_bit(NILFS_I_UPDATED, &ii->i_state);
	}
}

static int nilfs_segctor_apply_buffers(struct nilfs_sc_info *sci,
				       struct inode *inode,
				       struct list_head *listp,
				       int (*collect)(struct nilfs_sc_info *,
						      struct buffer_head *,
						      struct inode *))
{
	struct buffer_head *bh, *n;
	int err = 0;

	if (collect) {
		list_for_each_entry_safe(bh, n, listp, b_assoc_buffers) {
			list_del_init(&bh->b_assoc_buffers);
			err = collect(sci, bh, inode);
			brelse(bh);
			if (unlikely(err))
				goto dispose_buffers;
		}
		return 0;
	}

 dispose_buffers:
	while (!list_empty(listp)) {
		bh = list_first_entry(listp, struct buffer_head,
				      b_assoc_buffers);
		list_del_init(&bh->b_assoc_buffers);
		brelse(bh);
	}
	return err;
}

static size_t nilfs_segctor_buffer_rest(struct nilfs_sc_info *sci)
{
	/* Remaining number of blocks within segment buffer */
	return sci->sc_segbuf_nblocks -
		(sci->sc_nblk_this_inc + sci->sc_curseg->sb_sum.nblocks);
}

static int nilfs_segctor_scan_file(struct nilfs_sc_info *sci,
				   struct inode *inode,
				   struct nilfs_sc_operations *sc_ops)
{
	LIST_HEAD(data_buffers);
	LIST_HEAD(node_buffers);
	int err;

	if (!(sci->sc_stage.flags & NILFS_CF_NODE)) {
		size_t n, rest = nilfs_segctor_buffer_rest(sci);

		n = nilfs_lookup_dirty_data_buffers(
			inode, &data_buffers, rest + 1, 0, LLONG_MAX);
		if (n > rest) {
			err = nilfs_segctor_apply_buffers(
				sci, inode, &data_buffers,
				sc_ops->collect_data);
			BUG_ON(!err); /* always receive -E2BIG or true error */
			goto break_or_fail;
		}
	}
	nilfs_lookup_dirty_node_buffers(inode, &node_buffers);

	if (!(sci->sc_stage.flags & NILFS_CF_NODE)) {
		err = nilfs_segctor_apply_buffers(