fs/ocfs2/move_extents.c

/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * move_extents.c
 *
 * Copyright (C) 2011 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License version 2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 */
#include <linux/fs.h>
#include <linux/types.h>
#include <linux/mount.h>
#include <linux/swap.h>

#include <cluster/masklog.h>

#include "ocfs2.h"
#include "ocfs2_ioctl.h"

#include "alloc.h"
#include "aops.h"
#include "dlmglue.h"
#include "extent_map.h"
#include "inode.h"
#include "journal.h"
#include "suballoc.h"
#include "uptodate.h"
#include "super.h"
#include "dir.h"
#include "buffer_head_io.h"
#include "sysfile.h"
#include "suballoc.h"
#include "refcounttree.h"
#include "move_extents.h"

struct ocfs2_move_extents_context {
	struct inode *inode;
	struct file *file;
	int auto_defrag;
	int credits;
	u32 new_phys_cpos;
	u32 clusters_moved;
	u64 refcount_loc;
	struct ocfs2_move_extents *range;
	struct ocfs2_extent_tree et;
	struct ocfs2_alloc_context *meta_ac;
	struct ocfs2_alloc_context *data_ac;
	struct ocfs2_cached_dealloc_ctxt dealloc;
};

static int __ocfs2_move_extent(handle_t *handle,
			       struct ocfs2_move_extents_context *context,
			       u32 cpos, u32 len, u32 p_cpos, u32 new_p_cpos,
			       int ext_flags)
{
	int ret = 0, index;
	struct inode *inode = context->inode;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_extent_rec *rec, replace_rec;
	struct ocfs2_path *path = NULL;
	struct ocfs2_extent_list *el;
	u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
	u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);

	ret = ocfs2_duplicate_clusters_by_page(handle, context->file, cpos,
					       p_cpos, new_p_cpos, len);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	memset(&replace_rec, 0, sizeof(replace_rec));
	replace_rec.e_cpos = cpu_to_le32(cpos);
	replace_rec.e_leaf_clusters = cpu_to_le16(len);
	replace_rec.e_blkno = cpu_to_le64(ocfs2_clusters_to_blocks(inode->i_sb,
								   new_p_cpos));

	path = ocfs2_new_path_from_et(&context->et);
	if (!path) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_find_path(INODE_CACHE(inode), path, cpos);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	el = path_leaf_el(path);

	index = ocfs2_search_extent_list(el, cpos);
	if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
		ocfs2_error(inode->i_sb,
			    "Inode %llu has an extent at cpos %u which can no "
			    "longer be found.\n",
			    (unsigned long long)ino, cpos);
		ret = -EROFS;
		goto out;
	}

	rec = &el->l_recs[index];

	BUG_ON(ext_flags != rec->e_flags);
	/*
	 * after moving/defraging to new location, the extent is not going
	 * to be refcounted anymore.
	 */
	replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED;

	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
				      context->et.et_root_bh,
				      OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_split_extent(handle, &context->et, path, index,
				 &replace_rec, context->meta_ac,
				 &context->dealloc);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ocfs2_journal_dirty(handle, context->et.et_root_bh);

	context->new_phys_cpos = new_p_cpos;

	/*
	 * need I to append truncate log for old clusters?
	 */
	if (old_blkno) {
		if (ext_flags & OCFS2_EXT_REFCOUNTED)
			ret = ocfs2_decrease_refcount(inode, handle,
					ocfs2_blocks_to_clusters(osb->sb,
								 old_blkno),
					len, context->meta_ac,
					&context->dealloc, 1);
		else
			ret = ocfs2_truncate_log_append(osb, handle,
							old_blkno, len);
	}

out:
	return ret;
}

/*
 * lock allocators, and reserving appropriate number of bits for
 * meta blocks and data clusters.
 *
 * in some cases, we don't need to reserve clusters, just let data_ac
 * be NULL.
 */
static int ocfs2_lock_allocators_move_extents(struct inode *inode,
					struct ocfs2_extent_tree *et,
					u32 clusters_to_move,
					u32 extents_to_split,
					struct ocfs2_alloc_context **meta_ac,
					struct ocfs2_alloc_context **data_ac,
					int extra_blocks,
					int *credits)
{
	int ret, num_free_extents;
	unsigned int max_recs_needed = 2 * extents_to_split + clusters_to_move;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);

	num_free_extents = ocfs2_num_free_extents(osb, et);
	if (num_free_extents < 0) {
		ret = num_free_extents;
		mlog_errno(ret);
		goto out;
	}

	if (!num_free_extents ||
	    (ocfs2_sparse_alloc(osb) && num_free_extents < max_recs_needed))
		extra_blocks += ocfs2_extend_meta_needed(et->et_root_el);

	ret = ocfs2_reserve_new_metadata_blocks(osb, extra_blocks, meta_ac);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	if (data_ac) {
		ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el,
					      clusters_to_move + 2);

	mlog(0, "reserve metadata_blocks: %d, data_clusters: %u, credits: %d\n",
	     extra_blocks, clusters_to_move, *credits);
out:
	if (ret) {
		if (*meta_ac) {
			ocfs2_free_alloc_context(*meta_ac);
			*meta_ac = NULL;
		}
	}

	return ret;
}

/*
 * Using one journal handle to guarantee the data consistency in case
 * crash happens anywhere.
 */
static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
			       u32 cpos, u32 phys_cpos, u32 len, int ext_flags)
{
	int ret, credits = 0, extra_blocks = 0;
	handle_t *handle;
	struct inode *inode = context->inode;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct inode *tl_inode = osb->osb_tl_inode;
	struct ocfs2_refcount_tree *ref_tree = NULL;
	u32 new_phys_cpos, new_len;
	u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);

	if ((ext_flags & OCFS2_EXT_REFCOUNTED) && len) {

		BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
			 OCFS2_HAS_REFCOUNT_FL));

		BUG_ON(!context->refcount_loc);

		ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1,
					       &ref_tree, NULL);
		if (ret) {
			mlog_errno(ret);
			return ret;
		}

		ret = ocfs2_prepare_refcount_change_for_del(inode,
							context->refcount_loc,
							phys_blkno,
							len,
							&credits,
							&extra_blocks);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
						 &context->meta_ac,
						 &context->data_ac,
						 extra_blocks, &credits);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	/*
	 * should be using allocation reservation strategy there?
	 *
	 * if (context->data_ac)
	 *	context->data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
	 */

	mutex_lock(&tl_inode->i_mutex);

	if (ocfs2_truncate_log_needs_flush(osb)) {
		ret = __ocfs2_flush_truncate_log(osb);
		if (ret < 0) {
			mlog_errno(ret);
			goto out_unlock_mutex;
		}
	}

	handle = ocfs2_start_trans(osb, credits);
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		mlog_errno(ret);
		goto out_unlock_mutex;
	}

	ret = __ocfs2_claim_clusters(handle, context->data_ac, 1, len,
				     &new_phys_cpos, &new_len);
	if (ret) {
		mlog_errno(ret);
		goto out_commit;
	}

	/*
	 * we're not quite patient here to make multiple attempts for claiming
	 * enough clusters, failure to claim clusters per-requested is not a
	 * disaster though, it can only mean partial range of defragmentation
	 * or extent movements gets gone, users anyway is able to have another
	 * try as they wish anytime, since they're going to be returned a
	 * '-ENOSPC' and completed length of this movement.
	 */
	if (new_len != len) {
		mlog(0, "len_claimed: %u, len: %u\n", new_len, len);
		context->range->me_flags &= ~OCFS2_MOVE_EXT_FL_COMPLETE;
		ret = -ENOSPC;
		goto out_commit;
	}

	mlog(0, "cpos: %u, phys_cpos: %u, new_phys_cpos: %u\n", cpos,
	     phys_cpos, new_phys_cpos);

	ret = __ocfs2_move_extent(handle, context, cpos, len, phys_cpos,
				  new_phys_cpos, ext_flags);
	if (ret)
		mlog_errno(ret);

	/*
	 * Here we should write the new page out first if we are
	 * in write-back mode.
	 */
	ret = ocfs2_cow_sync_writeback(inode->i_sb, context->inode, cpos, len);
	if (ret)
		mlog_errno(ret);

out_commit:
	ocfs2_commit_trans(osb, handle);

out_unlock_mutex:
	mutex_unlock(&tl_inode->i_mutex);

	if (context->data_ac) {
		ocfs2_free_alloc_context(context->data_ac);
		context->data_ac = NULL;
	}

	if (context->meta_ac) {
		ocfs2_free_alloc_context(context->meta_ac);
		context->meta_ac = NULL;
	}

out:
	if (ref_tree)
		ocfs2_unlock_refcount_tree(osb, ref_tree, 1);

	return ret;
}

/*
 * find the victim alloc group, where #blkno fits.
 */
static int ocfs2_find_victim_alloc_group(struct inode *inode,
					 u64 vict_blkno,
					 int type, int slot,
					 int *vict_bit,
					 struct buffer_head **ret_bh)
{
	int ret, i, blocks_per_unit = 1;
	u64 blkno;
	char namebuf[40];

	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct buffer_head *ac_bh = NULL, *gd_bh = NULL;
	struct ocfs2_chain_list *cl;
	struct ocfs2_chain_rec *rec;
	struct ocfs2_dinode *ac_dinode;
	struct ocfs2_group_desc *bg;

	ocfs2_sprintf_system_inode_name(namebuf, sizeof(namebuf), type, slot);
	ret = ocfs2_lookup_ino_from_name(osb->sys_root_inode, namebuf,
					 strlen(namebuf), &blkno);
	if (ret) {
		ret = -ENOENT;
		goto out;
	}

	ret = ocfs2_read_blocks_sync(osb, blkno, 1, &ac_bh);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ac_dinode = (struct ocfs2_dinode *)ac_bh->b_data;
	cl = &(ac_dinode->id2.i_chain);
	rec = &(cl->cl_recs[0]);

	if (type == GLOBAL_BITMAP_SYSTEM_INODE)
		blocks_per_unit <<= (osb->s_clustersize_bits -
						inode->i_sb->s_blocksize_bits);
	/*
	 * 'vict_blkno' was out of the valid range.
	 */
	if ((vict_blkno < le64_to_cpu(rec->c_blkno)) ||
	    (vict_blkno >= (le32_to_cpu(ac_dinode->id1.bitmap1.i_total) *
				blocks_per_unit))) {
		ret = -EINVAL;
		goto out;
	}

	for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i++) {

		rec = &(cl->cl_recs[i]);
		if (!rec)
			continue;

		bg = NULL;

		do {
			if (!bg)
				blkno = le64_to_cpu(rec->c_blkno);
			else
				blkno = le64_to_cpu(bg->bg_next_group);

			if (gd_bh) {
				brelse(gd_bh);
				gd_bh = NULL;
			}

			ret = ocfs2_read_blocks_sync(osb, blkno, 1, &gd_bh);
			if (ret) {
				mlog_errno(ret);
				goto out;
			}

			bg = (struct ocfs2_group_desc *)gd_bh->b_data;

			if (vict_blkno < (le64_to_cpu(bg->bg_blkno) +
						le16_to_cpu(bg->bg_bits))) {

				*ret_bh = gd_bh;
				*vict_bit = (vict_blkno - blkno) /
							blocks_per_unit;
				mlog(0, "find the victim group: #%llu, "
				     "total_bits: %u, vict_bit: %u\n",
				     blkno, le16_to_cpu(bg->bg_bits),
				     *vict_bit);
				goto out;
			}

		} while (le64_to_cpu(bg->bg_next_group));
	}

	ret = -EINVAL;
out:
	brelse(ac_bh);

	/*
	 * caller has to release the gd_bh properly.
	 */
	return ret;
}

/*
 * XXX: helper to validate and adjust moving goal.
 */
static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
					       struct ocfs2_move_extents *range)
{
	int ret, goal_bit = 0;

	struct buffer_head *gd_bh = NULL;
	struct ocfs2_group_desc *bg;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	int c_to_b = 1 << (osb->s_clustersize_bits -
					inode->i_sb->s_blocksize_bits);

	/*
	 * validate goal sits within global_bitmap, and return the victim
	 * group desc
	 */
	ret = ocfs2_find_victim_alloc_group(inode, range->me_goal,
					    GLOBAL_BITMAP_SYSTEM_INODE,
					    OCFS2_INVALID_SLOT,
					    &goal_bit, &gd_bh);
	if (ret)
		goto out;

	bg = (struct ocfs2_group_desc *)gd_bh->b_data;

	/*
	 * make goal become cluster aligned.
	 */
	if (range->me_goal % c_to_b)
		range->me_goal = range->me_goal / c_to_b * c_to_b;

	/*
	 * moving goal is not allowd to start with a group desc blok(#0 blk)
	 * let's compromise to the latter cluster.
	 */
	if (range->me_goal == le64_to_cpu(bg->bg_blkno))
		range->me_goal += c_to_b;

	/*
	 * movement is not gonna cross two groups.
	 */
	if ((le16_to_cpu(bg->bg_bits) - goal_bit) * osb->s_clustersize <
								range->me_len) {
		ret = -EINVAL;
		goto out;
	}
	/*
	 * more exact validations/adjustments will be performed later during
	 * moving operation for each extent range.
	 */
	mlog(0, "extents get ready to be moved to #%llu block\n",
	     range->me_goal);

out:
	brelse(gd_bh);

	return ret;
}

static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh,
				    int *goal_bit, u32 move_len, u32 max_hop,
				    u32 *phys_cpos)
{
	int i, used, last_free_bits = 0, base_bit = *goal_bit;
	struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
	u32 base_cpos = ocfs2_blocks_to_clusters(inode->i_sb,
						 le64_to_cpu(gd->bg_blkno));

	for (i = base_bit; i < le16_to_cpu(gd->bg_bits); i++) {

		used = ocfs2_test_bit(i, (unsigned long *)gd->bg_bitmap);
		if (used) {
			/*
			 * we even tried searching the free chunk by jumping
			 * a 'max_hop' distance, but still failed.
			 */
			if ((i - base_bit) > max_hop) {
				*phys_cpos = 0;
				break;
			}

			if (last_free_bits)
				last_free_bits = 0;

			continue;
		} else
			last_free_bits++;

		if (last_free_bits == move_len) {
			*goal_bit = i;
			*phys_cpos = base_cpos + i;
			break;
		}
	}

	mlog(0, "found phys_cpos: %u to fit the wanted moving.\n", *phys_cpos);
}

static int ocfs2_alloc_dinode_update_counts(struct inode *inode,
				       handle_t *handle,
				       struct buffer_head *di_bh,
				       u32 num_bits,
				       u16 chain)
{
	int ret;
	u32 tmp_used;
	struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
	struct ocfs2_chain_list *cl =
				(struct ocfs2_chain_list *) &di->id2.i_chain;

	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
				      OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret < 0) {
		mlog_errno(ret);
		goto out;
	}

	tmp_used = le32_to_cpu(di->id1.bitmap1.i_used);
	di->id1.bitmap1.i_used = cpu_to_le32(num_bits + tmp_used);
	le32_add_cpu(&cl->cl_recs[chain].c_free, -num_bits);
	ocfs2_journal_dirty(handle, di_bh);

out:
	return ret;
}

static inline 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)
{
	int status;
	void *bitmap = bg->bg_bitmap;
	int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;

	/* All callers get the descriptor via
	 * ocfs2_read_group_descriptor().  Any corruption is a code bug. */
	BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg));
	BUG_ON(le16_to_cpu(bg->bg_free_bits_count) < num_bits);

	mlog(0, "block_group_set_bits: off = %u, num = %u\n", bit_off,
	     num_bits);

	if (ocfs2_is_cluster_bitmap(alloc_inode))
		journal_type = OCFS2_JOURNAL_ACCESS_UNDO;

	status = ocfs2_journal_access_gd(handle,
					 INODE_CACHE(alloc_inode),
					 group_bh,
					 journal_type);
	if (status < 0) {
		mlog_errno(status);
		goto bail;
	}

	le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
	if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
		ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
			    " count %u but claims %u are freed. num_bits %d",
			    (unsigned long long)le64_to_cpu(bg->bg_blkno),
			    le16_to_cpu(bg->bg_bits),
			    le16_to_cpu(bg->bg_free_bits_count), num_bits);
		return -EROFS;
	}
	while (num_bits--)
		ocfs2_set_bit(bit_off++, bitmap);

	ocfs2_journal_dirty(handle, group_bh);

bail:
	return status;
}