rgrp.c

linux 内核源代码

	}

	sdp->sd_rindex_vn = ip->i_gl->gl_vn;
	return 0;
}

/**
 * gfs2_ri_update_special - Pull in a new resource index from the disk
 *
 * This is a special version that's safe to call from gfs2_inplace_reserve_i.
 * In this case we know that we don't have any resource groups in memory yet.
 *
 * @ip: pointer to the rindex inode
 *
 * Returns: 0 on successful update, error code otherwise
 */
static int gfs2_ri_update_special(struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct inode *inode = &ip->i_inode;
	struct file_ra_state ra_state;
	int error;

	file_ra_state_init(&ra_state, inode->i_mapping);
	for (sdp->sd_rgrps = 0;; sdp->sd_rgrps++) {
		/* Ignore partials */
		if ((sdp->sd_rgrps + 1) * sizeof(struct gfs2_rindex) >
		    ip->i_di.di_size)
			break;
		error = read_rindex_entry(ip, &ra_state);
		if (error) {
			clear_rgrpdi(sdp);
			return error;
		}
	}

	sdp->sd_rindex_vn = ip->i_gl->gl_vn;
	return 0;
}

/**
 * gfs2_rindex_hold - Grab a lock on the rindex
 * @sdp: The GFS2 superblock
 * @ri_gh: the glock holder
 *
 * We grab a lock on the rindex inode to make sure that it doesn't
 * change whilst we are performing an operation. We keep this lock
 * for quite long periods of time compared to other locks. This
 * doesn't matter, since it is shared and it is very, very rarely
 * accessed in the exclusive mode (i.e. only when expanding the filesystem).
 *
 * This makes sure that we're using the latest copy of the resource index
 * special file, which might have been updated if someone expanded the
 * filesystem (via gfs2_grow utility), which adds new resource groups.
 *
 * Returns: 0 on success, error code otherwise
 */

int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh)
{
	struct gfs2_inode *ip = GFS2_I(sdp->sd_rindex);
	struct gfs2_glock *gl = ip->i_gl;
	int error;

	error = gfs2_glock_nq_init(gl, LM_ST_SHARED, 0, ri_gh);
	if (error)
		return error;

	/* Read new copy from disk if we don't have the latest */
	if (sdp->sd_rindex_vn != gl->gl_vn) {
		mutex_lock(&sdp->sd_rindex_mutex);
		if (sdp->sd_rindex_vn != gl->gl_vn) {
			error = gfs2_ri_update(ip);
			if (error)
				gfs2_glock_dq_uninit(ri_gh);
		}
		mutex_unlock(&sdp->sd_rindex_mutex);
	}

	return error;
}

static void gfs2_rgrp_in(struct gfs2_rgrp_host *rg, const void *buf)
{
	const struct gfs2_rgrp *str = buf;

	rg->rg_flags = be32_to_cpu(str->rg_flags);
	rg->rg_free = be32_to_cpu(str->rg_free);
	rg->rg_dinodes = be32_to_cpu(str->rg_dinodes);
	rg->rg_igeneration = be64_to_cpu(str->rg_igeneration);
}

static void gfs2_rgrp_out(const struct gfs2_rgrp_host *rg, void *buf)
{
	struct gfs2_rgrp *str = buf;

	str->rg_flags = cpu_to_be32(rg->rg_flags);
	str->rg_free = cpu_to_be32(rg->rg_free);
	str->rg_dinodes = cpu_to_be32(rg->rg_dinodes);
	str->__pad = cpu_to_be32(0);
	str->rg_igeneration = cpu_to_be64(rg->rg_igeneration);
	memset(&str->rg_reserved, 0, sizeof(str->rg_reserved));
}

/**
 * gfs2_rgrp_bh_get - Read in a RG's header and bitmaps
 * @rgd: the struct gfs2_rgrpd describing the RG to read in
 *
 * Read in all of a Resource Group's header and bitmap blocks.
 * Caller must eventually call gfs2_rgrp_relse() to free the bitmaps.
 *
 * Returns: errno
 */

int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	struct gfs2_glock *gl = rgd->rd_gl;
	unsigned int length = rgd->rd_length;
	struct gfs2_bitmap *bi;
	unsigned int x, y;
	int error;

	mutex_lock(&rgd->rd_mutex);

	spin_lock(&sdp->sd_rindex_spin);
	if (rgd->rd_bh_count) {
		rgd->rd_bh_count++;
		spin_unlock(&sdp->sd_rindex_spin);
		mutex_unlock(&rgd->rd_mutex);
		return 0;
	}
	spin_unlock(&sdp->sd_rindex_spin);

	for (x = 0; x < length; x++) {
		bi = rgd->rd_bits + x;
		error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, &bi->bi_bh);
		if (error)
			goto fail;
	}

	for (y = length; y--;) {
		bi = rgd->rd_bits + y;
		error = gfs2_meta_wait(sdp, bi->bi_bh);
		if (error)
			goto fail;
		if (gfs2_metatype_check(sdp, bi->bi_bh, y ? GFS2_METATYPE_RB :
					      GFS2_METATYPE_RG)) {
			error = -EIO;
			goto fail;
		}
	}

	if (rgd->rd_rg_vn != gl->gl_vn) {
		gfs2_rgrp_in(&rgd->rd_rg, (rgd->rd_bits[0].bi_bh)->b_data);
		rgd->rd_rg_vn = gl->gl_vn;
	}

	spin_lock(&sdp->sd_rindex_spin);
	rgd->rd_free_clone = rgd->rd_rg.rg_free;
	rgd->rd_bh_count++;
	spin_unlock(&sdp->sd_rindex_spin);

	mutex_unlock(&rgd->rd_mutex);

	return 0;

fail:
	while (x--) {
		bi = rgd->rd_bits + x;
		brelse(bi->bi_bh);
		bi->bi_bh = NULL;
		gfs2_assert_warn(sdp, !bi->bi_clone);
	}
	mutex_unlock(&rgd->rd_mutex);

	return error;
}

void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;

	spin_lock(&sdp->sd_rindex_spin);
	gfs2_assert_warn(rgd->rd_sbd, rgd->rd_bh_count);
	rgd->rd_bh_count++;
	spin_unlock(&sdp->sd_rindex_spin);
}

/**
 * gfs2_rgrp_bh_put - Release RG bitmaps read in with gfs2_rgrp_bh_get()
 * @rgd: the struct gfs2_rgrpd describing the RG to read in
 *
 */

void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	int x, length = rgd->rd_length;

	spin_lock(&sdp->sd_rindex_spin);
	gfs2_assert_warn(rgd->rd_sbd, rgd->rd_bh_count);
	if (--rgd->rd_bh_count) {
		spin_unlock(&sdp->sd_rindex_spin);
		return;
	}

	for (x = 0; x < length; x++) {
		struct gfs2_bitmap *bi = rgd->rd_bits + x;
		kfree(bi->bi_clone);
		bi->bi_clone = NULL;
		brelse(bi->bi_bh);
		bi->bi_bh = NULL;
	}

	spin_unlock(&sdp->sd_rindex_spin);
}

void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	unsigned int length = rgd->rd_length;
	unsigned int x;

	for (x = 0; x < length; x++) {
		struct gfs2_bitmap *bi = rgd->rd_bits + x;
		if (!bi->bi_clone)
			continue;
		memcpy(bi->bi_clone + bi->bi_offset,
		       bi->bi_bh->b_data + bi->bi_offset, bi->bi_len);
	}

	spin_lock(&sdp->sd_rindex_spin);
	rgd->rd_free_clone = rgd->rd_rg.rg_free;
	spin_unlock(&sdp->sd_rindex_spin);
}

/**
 * gfs2_alloc_get - get the struct gfs2_alloc structure for an inode
 * @ip: the incore GFS2 inode structure
 *
 * Returns: the struct gfs2_alloc
 */

struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip)
{
	struct gfs2_alloc *al = &ip->i_alloc;

	/* FIXME: Should assert that the correct locks are held here... */
	memset(al, 0, sizeof(*al));
	return al;
}

/**
 * try_rgrp_fit - See if a given reservation will fit in a given RG
 * @rgd: the RG data
 * @al: the struct gfs2_alloc structure describing the reservation
 *
 * If there's room for the requested blocks to be allocated from the RG:
 *   Sets the $al_rgd field in @al.
 *
 * Returns: 1 on success (it fits), 0 on failure (it doesn't fit)
 */

static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	int ret = 0;

	if (rgd->rd_rg.rg_flags & GFS2_RGF_NOALLOC)
		return 0;

	spin_lock(&sdp->sd_rindex_spin);
	if (rgd->rd_free_clone >= al->al_requested) {
		al->al_rgd = rgd;
		ret = 1;
	}
	spin_unlock(&sdp->sd_rindex_spin);

	return ret;
}

/**
 * try_rgrp_unlink - Look for any unlinked, allocated, but unused inodes
 * @rgd: The rgrp
 *
 * Returns: The inode, if one has been found
 */

static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked)
{
	struct inode *inode;
	u32 goal = 0, block;
	u64 no_addr;
	struct gfs2_sbd *sdp = rgd->rd_sbd;

	for(;;) {
		if (goal >= rgd->rd_data)
			break;
		down_write(&sdp->sd_log_flush_lock);
		block = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
				     GFS2_BLKST_UNLINKED);
		up_write(&sdp->sd_log_flush_lock);
		if (block == BFITNOENT)
			break;
		/* rgblk_search can return a block < goal, so we need to
		   keep it marching forward. */
		no_addr = block + rgd->rd_data0;
		goal++;
		if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked)
			continue;
		*last_unlinked = no_addr;
		inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN,
					  no_addr, -1, 1);
		if (!IS_ERR(inode))
			return inode;
	}

	rgd->rd_flags &= ~GFS2_RDF_CHECK;
	return NULL;
}

/**
 * recent_rgrp_first - get first RG from "recent" list
 * @sdp: The GFS2 superblock
 * @rglast: address of the rgrp used last
 *
 * Returns: The first rgrp in the recent list
 */

static struct gfs2_rgrpd *recent_rgrp_first(struct gfs2_sbd *sdp,
					    u64 rglast)
{
	struct gfs2_rgrpd *rgd = NULL;

	spin_lock(&sdp->sd_rindex_spin);

	if (list_empty(&sdp->sd_rindex_recent_list))
		goto out;

	if (!rglast)
		goto first;

	list_for_each_entry(rgd, &sdp->sd_rindex_recent_list, rd_recent) {
		if (rgd->rd_addr == rglast)
			goto out;
	}

first:
	rgd = list_entry(sdp->sd_rindex_recent_list.next, struct gfs2_rgrpd,
			 rd_recent);
out:
	spin_unlock(&sdp->sd_rindex_spin);
	return rgd;
}

/**
 * recent_rgrp_next - get next RG from "recent" list
 * @cur_rgd: current rgrp
 * @remove:
 *
 * Returns: The next rgrp in the recent list
 */

static struct gfs2_rgrpd *recent_rgrp_next(struct gfs2_rgrpd *cur_rgd,
					   int remove)
{
	struct gfs2_sbd *sdp = cur_rgd->rd_sbd;
	struct list_head *head;
	struct gfs2_rgrpd *rgd;

	spin_lock(&sdp->sd_rindex_spin);

	head = &sdp->sd_rindex_recent_list;

	list_for_each_entry(rgd, head, rd_recent) {
		if (rgd == cur_rgd) {
			if (cur_rgd->rd_recent.next != head)
				rgd = list_entry(cur_rgd->rd_recent.next,
						 struct gfs2_rgrpd, rd_recent);
			else
				rgd = NULL;

			if (remove)
				list_del(&cur_rgd->rd_recent);

			goto out;
		}
	}

	rgd = NULL;
	if (!list_empty(head))
		rgd = list_entry(head->next, struct gfs2_rgrpd, rd_recent);

out:
	spin_unlock(&sdp->sd_rindex_spin);
	return rgd;
}

/**
 * recent_rgrp_add - add an RG to tail of "recent" list
 * @new_rgd: The rgrp to add
 *
 */

static void recent_rgrp_add(struct gfs2_rgrpd *new_rgd)
{
	struct gfs2_sbd *sdp = new_rgd->rd_sbd;
	struct gfs2_rgrpd *rgd;
	unsigned int count = 0;
	unsigned int max = sdp->sd_rgrps / gfs2_jindex_size(sdp);

	spin_lock(&sdp->sd_rindex_spin);

	list_for_each_entry(rgd, &sdp->sd_rindex_recent_list, rd_recent) {
		if (rgd == new_rgd)
			goto out;

		if (++count >= max)
			goto out;
	}
	list_add_tail(&new_rgd->rd_recent, &sdp->sd_rindex_recent_list);

out:
	spin_unlock(&sdp->sd_rindex_spin);
}

/**
 * forward_rgrp_get - get an rgrp to try next from full list
 * @sdp: The GFS2 superblock
 *
 * Returns: The rgrp to try next
 */

static struct gfs2_rgrpd *forward_rgrp_get(struct gfs2_sbd *sdp)
{
	struct gfs2_rgrpd *rgd;
	unsigned int journals = gfs2_jindex_size(sdp);
	unsigned int rg = 0, x;

	spin_lock(&sdp->sd_rindex_spin);

	rgd = sdp->sd_rindex_forward;
	if (!rgd) {
		if (sdp->sd_rgrps >= journals)
			rg = sdp->sd_rgrps * sdp->sd_jdesc->jd_jid / journals;

		for (x = 0, rgd = gfs2_rgrpd_get_first(sdp); x < rg;
		     x++, rgd = gfs2_rgrpd_get_next(rgd))
			/* Do Nothing */;

		sdp->sd_rindex_forward = rgd;
	}

	spin_unlock(&sdp->sd_rindex_spin);

	return rgd;
}

/**
 * forward_rgrp_set - set the forward rgrp pointer
 * @sdp: the filesystem
 * @rgd: The new forward rgrp
 *
 */

static void forward_rgrp_set(struct gfs2_sbd *sdp, struct gfs2_rgrpd *rgd)
{
	spin_lock(&sdp->sd_rindex_spin);
	sdp->sd_rindex_forward = rgd;
	spin_unlock(&sdp->sd_rindex_spin);
}

/**
 * get_local_rgrp - Choose and lock a rgrp for allocation
 * @ip: the inode to reserve space for
 * @rgp: the chosen and locked rgrp
 *
 * Try to acquire rgrp in way which avoids contending with others.
 *
 * Returns: errno
 */

static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
{
	struct inode *inode = NULL;
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct gfs2_rgrpd *rgd, *begin = NULL;
	struct gfs2_alloc *al = &ip->i_alloc;
	int flags = LM_FLAG_TRY;
	int skipped = 0;
	int loops = 0;
	int error;

	/* Try recently successful rgrps */

	rgd = recent_rgrp_first(sdp, ip->i_last_rg_alloc);

	while (rgd) {
		error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
					   LM_FLAG_TRY, &al->al_rgd_gh);
		switch (error) {
		case 0:
			if (try_rgrp_fit(rgd, al))
				goto out;
			if (rgd->rd_flags & GFS2_RDF_CHECK)
				inode = try_rgrp_unlink(rgd, last_unlinked);
			gfs2_glock_dq_uninit(&al->al_rgd_gh);
			if (inode)
				return inode;
			rgd = recent_rgrp_next(rgd, 1);
			break;

		case GLR_TRYFAILED:
			rgd = recent_rgrp_next(rgd, 0);
			break;

		default:
			return ERR_PTR(error);
		}
	}

	/* Go through full list of rgrps */

	begin = rgd = forward_rgrp_get(sdp);

	for (;;) {
		error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, flags,
					  &al->al_rgd_gh);
		switch (error) {
		case 0:
			if (try_rgrp_fit(rgd, al))
				goto out;
			if (rgd->rd_flags & GFS2_RDF_CHECK)
				inode = try_rgrp_unlink(rgd, last_unlinked);
			gfs2_glock_dq_uninit(&al->al_rgd_gh);
			if (inode)
				return inode;
			break;

		case GLR_TRYFAILED:
			skipped++;
			break;

		default:
			return ERR_PTR(error);
		}

		rgd = gfs2_rgrpd_get_next(rgd);
		if (!rgd)
			rgd = gfs2_rgrpd_get_first(sdp);

		if (rgd == begin) {
			if (++loops >= 3)
				return ERR_PTR(-ENOSPC);
			if (!skipped)
				loops++;
			flags = 0;
			if (loops == 2)
				gfs2_log_flush(sdp, NULL);
		}
	}

out:
	ip->i_last_rg_alloc = rgd->rd_addr;

	if (begin) {
		recent_rgrp_add(rgd);
		rgd = gfs2_rgrpd_get_next(rgd);
		if (!rgd)
			rgd = gfs2_rgrpd_get_first(sdp);
		forward_rgrp_set(sdp, rgd);
	}