rgrp.c

/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
 *
 * This copyrighted material is made available to anyone wishing to use,
 * modify, copy, or redistribute it subject to the terms and conditions
 * of the GNU General Public License version 2.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/fs.h>
#include <linux/gfs2_ondisk.h>
#include <linux/prefetch.h>
#include <linux/blkdev.h>
#include <linux/rbtree.h>
#include <linux/random.h>

#include "gfs2.h"
#include "incore.h"
#include "glock.h"
#include "glops.h"
#include "lops.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "super.h"
#include "trans.h"
#include "util.h"
#include "log.h"
#include "inode.h"
#include "trace_gfs2.h"

#define BFITNOENT ((u32)~0)
#define NO_BLOCK ((u64)~0)

#if BITS_PER_LONG == 32
#define LBITMASK   (0x55555555UL)
#define LBITSKIP55 (0x55555555UL)
#define LBITSKIP00 (0x00000000UL)
#else
#define LBITMASK   (0x5555555555555555UL)
#define LBITSKIP55 (0x5555555555555555UL)
#define LBITSKIP00 (0x0000000000000000UL)
#endif

/*
 * These routines are used by the resource group routines (rgrp.c)
 * to keep track of block allocation.  Each block is represented by two
 * bits.  So, each byte represents GFS2_NBBY (i.e. 4) blocks.
 *
 * 0 = Free
 * 1 = Used (not metadata)
 * 2 = Unlinked (still in use) inode
 * 3 = Used (metadata)
 */

struct gfs2_extent {
	struct gfs2_rbm rbm;
	u32 len;
};

static const char valid_change[16] = {
	        /* current */
	/* n */ 0, 1, 1, 1,
	/* e */ 1, 0, 0, 0,
	/* w */ 0, 0, 0, 1,
	        1, 0, 0, 0
};

static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
			 const struct gfs2_inode *ip, bool nowrap,
			 const struct gfs2_alloc_parms *ap);


/**
 * gfs2_setbit - Set a bit in the bitmaps
 * @rbm: The position of the bit to set
 * @do_clone: Also set the clone bitmap, if it exists
 * @new_state: the new state of the block
 *
 */

static inline void gfs2_setbit(const struct gfs2_rbm *rbm, bool do_clone,
			       unsigned char new_state)
{
	unsigned char *byte1, *byte2, *end, cur_state;
	struct gfs2_bitmap *bi = rbm_bi(rbm);
	unsigned int buflen = bi->bi_len;
	const unsigned int bit = (rbm->offset % GFS2_NBBY) * GFS2_BIT_SIZE;

	byte1 = bi->bi_bh->b_data + bi->bi_offset + (rbm->offset / GFS2_NBBY);
	end = bi->bi_bh->b_data + bi->bi_offset + buflen;

	BUG_ON(byte1 >= end);

	cur_state = (*byte1 >> bit) & GFS2_BIT_MASK;

	if (unlikely(!valid_change[new_state * 4 + cur_state])) {
		pr_warn("buf_blk = 0x%x old_state=%d, new_state=%d\n",
			rbm->offset, cur_state, new_state);
		pr_warn("rgrp=0x%llx bi_start=0x%x\n",
			(unsigned long long)rbm->rgd->rd_addr, bi->bi_start);
		pr_warn("bi_offset=0x%x bi_len=0x%x\n",
			bi->bi_offset, bi->bi_len);
		dump_stack();
		gfs2_consist_rgrpd(rbm->rgd);
		return;
	}
	*byte1 ^= (cur_state ^ new_state) << bit;

	if (do_clone && bi->bi_clone) {
		byte2 = bi->bi_clone + bi->bi_offset + (rbm->offset / GFS2_NBBY);
		cur_state = (*byte2 >> bit) & GFS2_BIT_MASK;
		*byte2 ^= (cur_state ^ new_state) << bit;
	}
}

/**
 * gfs2_testbit - test a bit in the bitmaps
 * @rbm: The bit to test
 *
 * Returns: The two bit block state of the requested bit
 */

static inline u8 gfs2_testbit(const struct gfs2_rbm *rbm)
{
	struct gfs2_bitmap *bi = rbm_bi(rbm);
	const u8 *buffer = bi->bi_bh->b_data + bi->bi_offset;
	const u8 *byte;
	unsigned int bit;

	byte = buffer + (rbm->offset / GFS2_NBBY);
	bit = (rbm->offset % GFS2_NBBY) * GFS2_BIT_SIZE;

	return (*byte >> bit) & GFS2_BIT_MASK;
}

/**
 * gfs2_bit_search
 * @ptr: Pointer to bitmap data
 * @mask: Mask to use (normally 0x55555.... but adjusted for search start)
 * @state: The state we are searching for
 *
 * We xor the bitmap data with a patter which is the bitwise opposite
 * of what we are looking for, this gives rise to a pattern of ones
 * wherever there is a match. Since we have two bits per entry, we
 * take this pattern, shift it down by one place and then and it with
 * the original. All the even bit positions (0,2,4, etc) then represent
 * successful matches, so we mask with 0x55555..... to remove the unwanted
 * odd bit positions.
 *
 * This allows searching of a whole u64 at once (32 blocks) with a
 * single test (on 64 bit arches).
 */

static inline u64 gfs2_bit_search(const __le64 *ptr, u64 mask, u8 state)
{
	u64 tmp;
	static const u64 search[] = {
		[0] = 0xffffffffffffffffULL,
		[1] = 0xaaaaaaaaaaaaaaaaULL,
		[2] = 0x5555555555555555ULL,
		[3] = 0x0000000000000000ULL,
	};
	tmp = le64_to_cpu(*ptr) ^ search[state];
	tmp &= (tmp >> 1);
	tmp &= mask;
	return tmp;
}

/**
 * rs_cmp - multi-block reservation range compare
 * @blk: absolute file system block number of the new reservation
 * @len: number of blocks in the new reservation
 * @rs: existing reservation to compare against
 *
 * returns: 1 if the block range is beyond the reach of the reservation
 *         -1 if the block range is before the start of the reservation
 *          0 if the block range overlaps with the reservation
 */
static inline int rs_cmp(u64 blk, u32 len, struct gfs2_blkreserv *rs)
{
	u64 startblk = gfs2_rbm_to_block(&rs->rs_rbm);

	if (blk >= startblk + rs->rs_free)
		return 1;
	if (blk + len - 1 < startblk)
		return -1;
	return 0;
}

/**
 * gfs2_bitfit - Search an rgrp's bitmap buffer to find a bit-pair representing
 *       a block in a given allocation state.
 * @buf: the buffer that holds the bitmaps
 * @len: the length (in bytes) of the buffer
 * @goal: start search at this block's bit-pair (within @buffer)
 * @state: GFS2_BLKST_XXX the state of the block we're looking for.
 *
 * Scope of @goal and returned block number is only within this bitmap buffer,
 * not entire rgrp or filesystem.  @buffer will be offset from the actual
 * beginning of a bitmap block buffer, skipping any header structures, but
 * headers are always a multiple of 64 bits long so that the buffer is
 * always aligned to a 64 bit boundary.
 *
 * The size of the buffer is in bytes, but is it assumed that it is
 * always ok to read a complete multiple of 64 bits at the end
 * of the block in case the end is no aligned to a natural boundary.
 *
 * Return: the block number (bitmap buffer scope) that was found
 */

static u32 gfs2_bitfit(const u8 *buf, const unsigned int len,
		       u32 goal, u8 state)
{
	u32 spoint = (goal << 1) & ((8*sizeof(u64)) - 1);
	const __le64 *ptr = ((__le64 *)buf) + (goal >> 5);
	const __le64 *end = (__le64 *)(buf + ALIGN(len, sizeof(u64)));
	u64 tmp;
	u64 mask = 0x5555555555555555ULL;
	u32 bit;

	/* Mask off bits we don't care about at the start of the search */
	mask <<= spoint;
	tmp = gfs2_bit_search(ptr, mask, state);
	ptr++;
	while(tmp == 0 && ptr < end) {
		tmp = gfs2_bit_search(ptr, 0x5555555555555555ULL, state);
		ptr++;
	}
	/* Mask off any bits which are more than len bytes from the start */
	if (ptr == end && (len & (sizeof(u64) - 1)))
		tmp &= (((u64)~0) >> (64 - 8*(len & (sizeof(u64) - 1))));
	/* Didn't find anything, so return */
	if (tmp == 0)
		return BFITNOENT;
	ptr--;
	bit = __ffs64(tmp);
	bit /= 2;	/* two bits per entry in the bitmap */
	return (((const unsigned char *)ptr - buf) * GFS2_NBBY) + bit;
}

/**
 * gfs2_rbm_from_block - Set the rbm based upon rgd and block number
 * @rbm: The rbm with rgd already set correctly
 * @block: The block number (filesystem relative)
 *
 * This sets the bi and offset members of an rbm based on a
 * resource group and a filesystem relative block number. The
 * resource group must be set in the rbm on entry, the bi and
 * offset members will be set by this function.
 *
 * Returns: 0 on success, or an error code
 */

static int gfs2_rbm_from_block(struct gfs2_rbm *rbm, u64 block)
{
	u64 rblock = block - rbm->rgd->rd_data0;

	if (WARN_ON_ONCE(rblock > UINT_MAX))
		return -EINVAL;
	if (block >= rbm->rgd->rd_data0 + rbm->rgd->rd_data)
		return -E2BIG;

	rbm->bii = 0;
	rbm->offset = (u32)(rblock);
	/* Check if the block is within the first block */
	if (rbm->offset < rbm_bi(rbm)->bi_blocks)
		return 0;

	/* Adjust for the size diff between gfs2_meta_header and gfs2_rgrp */
	rbm->offset += (sizeof(struct gfs2_rgrp) -
			sizeof(struct gfs2_meta_header)) * GFS2_NBBY;
	rbm->bii = rbm->offset / rbm->rgd->rd_sbd->sd_blocks_per_bitmap;
	rbm->offset -= rbm->bii * rbm->rgd->rd_sbd->sd_blocks_per_bitmap;
	return 0;
}

/**
 * gfs2_rbm_incr - increment an rbm structure
 * @rbm: The rbm with rgd already set correctly
 *
 * This function takes an existing rbm structure and increments it to the next
 * viable block offset.
 *
 * Returns: If incrementing the offset would cause the rbm to go past the
 *          end of the rgrp, true is returned, otherwise false.
 *
 */

static bool gfs2_rbm_incr(struct gfs2_rbm *rbm)
{
	if (rbm->offset + 1 < rbm_bi(rbm)->bi_blocks) { /* in the same bitmap */
		rbm->offset++;
		return false;
	}
	if (rbm->bii == rbm->rgd->rd_length - 1) /* at the last bitmap */
		return true;

	rbm->offset = 0;
	rbm->bii++;
	return false;
}

/**
 * gfs2_unaligned_extlen - Look for free blocks which are not byte aligned
 * @rbm: Position to search (value/result)
 * @n_unaligned: Number of unaligned blocks to check
 * @len: Decremented for each block found (terminate on zero)
 *
 * Returns: true if a non-free block is encountered
 */

static bool gfs2_unaligned_extlen(struct gfs2_rbm *rbm, u32 n_unaligned, u32 *len)
{
	u32 n;
	u8 res;

	for (n = 0; n < n_unaligned; n++) {
		res = gfs2_testbit(rbm);
		if (res != GFS2_BLKST_FREE)
			return true;
		(*len)--;
		if (*len == 0)
			return true;
		if (gfs2_rbm_incr(rbm))
			return true;
	}

	return false;
}

/**
 * gfs2_free_extlen - Return extent length of free blocks
 * @rrbm: Starting position
 * @len: Max length to check
 *
 * Starting at the block specified by the rbm, see how many free blocks
 * there are, not reading more than len blocks ahead. This can be done
 * using memchr_inv when the blocks are byte aligned, but has to be done
 * on a block by block basis in case of unaligned blocks. Also this
 * function can cope with bitmap boundaries (although it must stop on
 * a resource group boundary)
 *
 * Returns: Number of free blocks in the extent
 */

static u32 gfs2_free_extlen(const struct gfs2_rbm *rrbm, u32 len)
{
	struct gfs2_rbm rbm = *rrbm;
	u32 n_unaligned = rbm.offset & 3;
	u32 size = len;
	u32 bytes;
	u32 chunk_size;
	u8 *ptr, *start, *end;
	u64 block;
	struct gfs2_bitmap *bi;

	if (n_unaligned &&
	    gfs2_unaligned_extlen(&rbm, 4 - n_unaligned, &len))
		goto out;

	n_unaligned = len & 3;
	/* Start is now byte aligned */
	while (len > 3) {
		bi = rbm_bi(&rbm);
		start = bi->bi_bh->b_data;
		if (bi->bi_clone)
			start = bi->bi_clone;
		end = start + bi->bi_bh->b_size;
		start += bi->bi_offset;
		BUG_ON(rbm.offset & 3);
		start += (rbm.offset / GFS2_NBBY);
		bytes = min_t(u32, len / GFS2_NBBY, (end - start));
		ptr = memchr_inv(start, 0, bytes);
		chunk_size = ((ptr == NULL) ? bytes : (ptr - start));
		chunk_size *= GFS2_NBBY;
		BUG_ON(len < chunk_size);
		len -= chunk_size;
		block = gfs2_rbm_to_block(&rbm);
		if (gfs2_rbm_from_block(&rbm, block + chunk_size)) {
			n_unaligned = 0;
			break;
		}
		if (ptr) {
			n_unaligned = 3;
			break;
		}
		n_unaligned = len & 3;
	}

	/* Deal with any bits left over at the end */
	if (n_unaligned)
		gfs2_unaligned_extlen(&rbm, n_unaligned, &len);
out:
	return size - len;
}

/**
 * gfs2_bitcount - count the number of bits in a certain state
 * @rgd: the resource group descriptor
 * @buffer: the buffer that holds the bitmaps
 * @buflen: the length (in bytes) of the buffer
 * @state: the state of the block we're looking for
 *
 * Returns: The number of bits
 */

static u32 gfs2_bitcount(struct gfs2_rgrpd *rgd, const u8 *buffer,
			 unsigned int buflen, u8 state)
{
	const u8 *byte = buffer;
	const u8 *end = buffer + buflen;
	const u8 state1 = state << 2;
	const u8 state2 = state << 4;
	const u8 state3 = state << 6;
	u32 count = 0;

	for (; byte < end; byte++) {
		if (((*byte) & 0x03) == state)
			count++;
		if (((*byte) & 0x0C) == state1)
			count++;
		if (((*byte) & 0x30) == state2)
			count++;
		if (((*byte) & 0xC0) == state3)
			count++;
	}

	return count;
}

/**
 * gfs2_rgrp_verify - Verify that a resource group is consistent
 * @rgd: the rgrp
 *
 */

void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	struct gfs2_bitmap *bi = NULL;
	u32 length = rgd->rd_length;
	u32 count[4], tmp;
	int buf, x;

	memset(count, 0, 4 * sizeof(u32));

	/* Count # blocks in each of 4 possible allocation states */
	for (buf = 0; buf < length; buf++) {
		bi = rgd->rd_bits + buf;
		for (x = 0; x < 4; x++)
			count[x] += gfs2_bitcount(rgd,
						  bi->bi_bh->b_data +
						  bi->bi_offset,
						  bi->bi_len, x);
	}

	if (count[0] != rgd->rd_free) {
		if (gfs2_consist_rgrpd(rgd))
			fs_err(sdp, "free data mismatch:  %u != %u\n",
			       count[0], rgd->rd_free);
		return;
	}

	tmp = rgd->rd_data - rgd->rd_free - rgd->rd_dinodes;
	if (count[1] != tmp) {
		if (gfs2_consist_rgrpd(rgd))
			fs_err(sdp, "used data mismatch:  %u != %u\n",
			       count[1], tmp);
		return;
	}

	if (count[2] + count[3] != rgd->rd_dinodes) {
		if (gfs2_consist_rgrpd(rgd))
			fs_err(sdp, "used metadata mismatch:  %u != %u\n",
			       count[2] + count[3], rgd->rd_dinodes);
		return;
	}
}

static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
{
	u64 first = rgd->rd_data0;
	u64 last = first + rgd->rd_data;
	return first <= block && block < last;
}

/**
 * gfs2_blk2rgrpd - Find resource group for a given data/meta block number
 * @sdp: The GFS2 superblock
 * @blk: The data block number
 * @exact: True if this needs to be an exact match
 *
 * Returns: The resource group, or NULL if not found
 */

struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk, bool exact)
{
	struct rb_node *n, *next;
	struct gfs2_rgrpd *cur;

	spin_lock(&sdp->sd_rindex_spin);
	n = sdp->sd_rindex_tree.rb_node;
	while (n) {
		cur = rb_entry(n, struct gfs2_rgrpd, rd_node);
		next = NULL;
		if (blk < cur->rd_addr)
			next = n->rb_left;
		else if (blk >= cur->rd_data0 + cur->rd_data)
			next = n->rb_right;
		if (next == NULL) {
			spin_unlock(&sdp->sd_rindex_spin);
			if (exact) {
				if (blk < cur->rd_addr)
					return NULL;
				if (blk >= cur->rd_data0 + cur->rd_data)
					return NULL;
			}
			return cur;
		}
		n = next;
	}
	spin_unlock(&sdp->sd_rindex_spin);

	return NULL;
}

/**
 * gfs2_rgrpd_get_first - get the first Resource Group in the filesystem
 * @sdp: The GFS2 superblock
 *
 * Returns: The first rgrp in the filesystem
 */

struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp)
{
	const struct rb_node *n;
	struct gfs2_rgrpd *rgd;

	spin_lock(&sdp->sd_rindex_spin);
	n = rb_first(&sdp->sd_rindex_tree);
	rgd = rb_entry(n, struct gfs2_rgrpd, rd_node);
	spin_unlock(&sdp->sd_rindex_spin);

	return rgd;
}

/**
 * gfs2_rgrpd_get_next - get the next RG
 * @rgd: the resource group descriptor
 *
 * Returns: The next rgrp
 */

struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	const struct rb_node *n;

	spin_lock(&sdp->sd_rindex_spin);
	n = rb_next(&rgd->rd_node);
	if (n == NULL)
		n = rb_first(&sdp->sd_rindex_tree);

	if (unlikely(&rgd->rd_node == n)) {
		spin_unlock(&sdp->sd_rindex_spin);
		return NULL;
	}
	rgd = rb_entry(n, struct gfs2_rgrpd, rd_node);
	spin_unlock(&sdp->sd_rindex_spin);
	return rgd;
}

void check_and_update_goal(struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	if (!ip->i_goal || gfs2_blk2rgrpd(sdp, ip->i_goal, 1) == NULL)
		ip->i_goal = ip->i_no_addr;
}

void gfs2_free_clones(struct gfs2_rgrpd *rgd)
{
	int x;

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

/**
 * gfs2_rs_alloc - make sure we have a reservation assigned to the inode
 * @ip: the inode for this reservation
 */
int gfs2_rs_alloc(struct gfs2_inode *ip)
{
	int error = 0;

	down_write(&ip->i_rw_mutex);
	if (ip->i_res)
		goto out;

	ip->i_res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS);
	if (!ip->i_res) {
		error = -ENOMEM;
		goto out;
	}

	RB_CLEAR_NODE(&ip->i_res->rs_node);
out:
	up_write(&ip->i_rw_mutex);
	return error;
}

static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs)
{
	gfs2_print_dbg(seq, "  B: n:%llu s:%llu b:%u f:%u\n",
		       (unsigned long long)rs->rs_inum,
		       (unsigned long long)gfs2_rbm_to_block(&rs->rs_rbm),
		       rs->rs_rbm.offset, rs->rs_free);
}

/**
 * __rs_deltree - remove a multi-block reservation from the rgd tree
 * @rs: The reservation to remove
 *
 */
static void __rs_deltree(struct gfs2_blkreserv *rs)
{
	struct gfs2_rgrpd *rgd;

	if (!gfs2_rs_active(rs))
		return;

	rgd = rs->rs_rbm.rgd;
	trace_gfs2_rs(rs, TRACE_RS_TREEDEL);
	rb_erase(&rs->rs_node, &rgd->rd_rstree);
	RB_CLEAR_NODE(&rs->rs_node);

	if (rs->rs_free) {
		struct gfs2_bitmap *bi = rbm_bi(&rs->rs_rbm);

		/* return reserved blocks to the rgrp */
		BUG_ON(rs->rs_rbm.rgd->rd_reserved < rs->rs_free);
		rs->rs_rbm.rgd->rd_reserved -= rs->rs_free;
		/* The rgrp extent failure point is likely not to increase;
		   it will only do so if the freed blocks are somehow
		   contiguous with a span of free blocks that follows. Still,
		   it will force the number to be recalculated later. */
		rgd->rd_extfail_pt += rs->rs_free;
		rs->rs_free = 0;
		clear_bit(GBF_FULL, &bi->bi_flags);
	}
}

/**
 * gfs2_rs_deltree - remove a multi-block reservation from the rgd tree
 * @rs: The reservation to remove
 *
 */
void gfs2_rs_deltree(struct gfs2_blkreserv *rs)
{
	struct gfs2_rgrpd *rgd;

	rgd = rs->rs_rbm.rgd;
	if (rgd) {
		spin_lock(&rgd->rd_rsspin);
		__rs_deltree(rs);
		spin_unlock(&rgd->rd_rsspin);
	}
}

/**
 * gfs2_rs_delete - delete a multi-block reservation
 * @ip: The inode for this reservation
 * @wcount: The inode's write count, or NULL
 *
 */
void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount)
{
	down_write(&ip->i_rw_mutex);
	if (ip->i_res && ((wcount == NULL) || (atomic_read(wcount) <= 1))) {
		gfs2_rs_deltree(ip->i_res);
		BUG_ON(ip->i_res->rs_free);
		kmem_cache_free(gfs2_rsrv_cachep, ip->i_res);
		ip->i_res = NULL;
	}
	up_write(&ip->i_rw_mutex);
}

/**
 * return_all_reservations - return all reserved blocks back to the rgrp.
 * @rgd: the rgrp that needs its space back
 *
 * We previously reserved a bunch of blocks for allocation. Now we need to
 * give them back. This leave the reservation structures in tact, but removes
 * all of their corresponding "no-fly zones".
 */
static void return_all_reservations(struct gfs2_rgrpd *rgd)
{
	struct rb_node *n;
	struct gfs2_blkreserv *rs;

	spin_lock(&rgd->rd_rsspin);
	while ((n = rb_first(&rgd->rd_rstree))) {
		rs = rb_entry(n, struct gfs2_blkreserv, rs_node);
		__rs_deltree(rs);
	}
	spin_unlock(&rgd->rd_rsspin);
}

void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
{
	struct rb_node *n;
	struct gfs2_rgrpd *rgd;
	struct gfs2_glock *gl;

	while ((n = rb_first(&sdp->sd_rindex_tree))) {
		rgd = rb_entry(n, struct gfs2_rgrpd, rd_node);
		gl = rgd->rd_gl;

		rb_erase(n, &sdp->sd_rindex_tree);

		if (gl) {
			spin_lock(&gl->gl_spin);
			gl->gl_object = NULL;
			spin_unlock(&gl->gl_spin);
			gfs2_glock_add_to_lru(gl);
			gfs2_glock_put(gl);
		}

		gfs2_free_clones(rgd);
		kfree(rgd->rd_bits);
		return_all_reservations(rgd);
		kmem_cache_free(gfs2_rgrpd_cachep, rgd);
	}
}

static void gfs2_rindex_print(const struct gfs2_rgrpd *rgd)
{
	pr_info("ri_addr = %llu\n", (unsigned long long)rgd->rd_addr);
	pr_info("ri_length = %u\n", rgd->rd_length);
	pr_info("ri_data0 = %llu\n", (unsigned long long)rgd->rd_data0);
	pr_info("ri_data = %u\n", rgd->rd_data);
	pr_info("ri_bitbytes = %u\n", rgd->rd_bitbytes);
}

/**
 * gfs2_compute_bitstructs - Compute the bitmap sizes
 * @rgd: The resource group descriptor
 *
 * Calculates bitmap descriptors, one for each block that contains bitmap data
 *
 * Returns: errno
 */

static int compute_bitstructs(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	struct gfs2_bitmap *bi;
	u32 length = rgd->rd_length; /* # blocks in hdr & bitmap */
	u32 bytes_left, bytes;
	int x;

	if (!length)
		return -EINVAL;

	rgd->rd_bits = kcalloc(length, sizeof(struct gfs2_bitmap), GFP_NOFS);
	if (!rgd->rd_bits)
		return -ENOMEM;

	bytes_left = rgd->rd_bitbytes;

	for (x = 0; x < length; x++) {
		bi = rgd->rd_bits + x;

		bi->bi_flags = 0;
		/* small rgrp; bitmap stored completely in header block */
		if (length == 1) {
			bytes = bytes_left;
			bi->bi_offset = sizeof(struct gfs2_rgrp);
			bi->bi_start = 0;
			bi->bi_len = bytes;
			bi->bi_blocks = bytes * GFS2_NBBY;
		/* header block */
		} else if (x == 0) {
			bytes = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_rgrp);
			bi->bi_offset = sizeof(struct gfs2_rgrp);
			bi->bi_start = 0;
			bi->bi_len = bytes;
			bi->bi_blocks = bytes * GFS2_NBBY;
		/* last block */
		} else if (x + 1 == length) {
			bytes = bytes_left;
			bi->bi_offset = sizeof(struct gfs2_meta_header);
			bi->bi_start = rgd->rd_bitbytes - bytes_left;
			bi->bi_len = bytes;
			bi->bi_blocks = bytes * GFS2_NBBY;
		/* other blocks */
		} else {
			bytes = sdp->sd_sb.sb_bsize -
				sizeof(struct gfs2_meta_header);
			bi->bi_offset = sizeof(struct gfs2_meta_header);
			bi->bi_start = rgd->rd_bitbytes - bytes_left;
			bi->bi_len = bytes;
			bi->bi_blocks = bytes * GFS2_NBBY;
		}

		bytes_left -= bytes;
	}

	if (bytes_left) {
		gfs2_consist_rgrpd(rgd);
		return -EIO;
	}
	bi = rgd->rd_bits + (length - 1);
	if ((bi->bi_start + bi->bi_len) * GFS2_NBBY != rgd->rd_data) {
		if (gfs2_consist_rgrpd(rgd)) {
			gfs2_rindex_print(rgd);
			fs_err(sdp, "start=%u len=%u offset=%u\n",
			       bi->bi_start, bi->bi_len, bi->bi_offset);
		}
		return -EIO;
	}

	return 0;
}

/**
 * gfs2_ri_total - Total up the file system space, according to the rindex.
 * @sdp: the filesystem
 *
 */
u64 gfs2_ri_total(struct gfs2_sbd *sdp)
{
	u64 total_data = 0;	
	struct inode *inode = sdp->sd_rindex;
	struct gfs2_inode *ip = GFS2_I(inode);
	char buf[sizeof(struct gfs2_rindex)];
	int error, rgrps;

	for (rgrps = 0;; rgrps++) {
		loff_t pos = rgrps * sizeof(struct gfs2_rindex);

		if (pos + sizeof(struct gfs2_rindex) > i_size_read(inode))
			break;
		error = gfs2_internal_read(ip, buf, &pos,
					   sizeof(struct gfs2_rindex));
		if (error != sizeof(struct gfs2_rindex))
			break;
		total_data += be32_to_cpu(((struct gfs2_rindex *)buf)->ri_data);
	}
	return total_data;
}

static int rgd_insert(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	struct rb_node **newn = &sdp->sd_rindex_tree.rb_node, *parent = NULL;

	/* Figure out where to put new node */
	while (*newn) {
		struct gfs2_rgrpd *cur = rb_entry(*newn, struct gfs2_rgrpd,
						  rd_node);

		parent = *newn;
		if (rgd->rd_addr < cur->rd_addr)
			newn = &((*newn)->rb_left);
		else if (rgd->rd_addr > cur->rd_addr)
			newn = &((*newn)->rb_right);
		else
			return -EEXIST;
	}

	rb_link_node(&rgd->rd_node, parent, newn);
	rb_insert_color(&rgd->rd_node, &sdp->sd_rindex_tree);
	sdp->sd_rgrps++;
	return 0;
}

/**
 * read_rindex_entry - Pull in a new resource index entry from the disk
 * @ip: Pointer to the rindex inode
 *
 * Returns: 0 on success, > 0 on EOF, error code otherwise
 */

static int read_rindex_entry(struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	const unsigned bsize = sdp->sd_sb.sb_bsize;
	loff_t pos = sdp->sd_rgrps * sizeof(struct gfs2_rindex);
	struct gfs2_rindex buf;
	int error;
	struct gfs2_rgrpd *rgd;

	if (pos >= i_size_read(&ip->i_inode))
		return 1;

	error = gfs2_internal_read(ip, (char *)&buf, &pos,
				   sizeof(struct gfs2_rindex));

	if (error != sizeof(struct gfs2_rindex))
		return (error == 0) ? 1 : error;

	rgd = kmem_cache_zalloc(gfs2_rgrpd_cachep, GFP_NOFS);
	error = -ENOMEM;
	if (!rgd)
		return error;

	rgd->rd_sbd = sdp;
	rgd->rd_addr = be64_to_cpu(buf.ri_addr);
	rgd->rd_length = be32_to_cpu(buf.ri_length);
	rgd->rd_data0 = be64_to_cpu(buf.ri_data0);
	rgd->rd_data = be32_to_cpu(buf.ri_data);
	rgd->rd_bitbytes = be32_to_cpu(buf.ri_bitbytes);
	spin_lock_init(&rgd->rd_rsspin);

	error = compute_bitstructs(rgd);
	if (error)
		goto fail;

	error = gfs2_glock_get(sdp, rgd->rd_addr,
			       &gfs2_rgrp_glops, CREATE, &rgd->rd_gl);
	if (error)
		goto fail;

	rgd->rd_gl->gl_object = rgd;
	rgd->rd_gl->gl_vm.start = rgd->rd_addr * bsize;
	rgd->rd_gl->gl_vm.end = rgd->rd_gl->gl_vm.start + (rgd->rd_length * bsize) - 1;
	rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr;
	rgd->rd_flags &= ~(GFS2_RDF_UPTODATE | GFS2_RDF_PREFERRED);
	if (rgd->rd_data > sdp->sd_max_rg_data)
		sdp->sd_max_rg_data = rgd->rd_data;
	spin_lock(&sdp->sd_rindex_spin);
	error = rgd_insert(rgd);
	spin_unlock(&sdp->sd_rindex_spin);
	if (!error)
		return 0;

	error = 0; /* someone else read in the rgrp; free it and ignore it */
	gfs2_glock_put(rgd->rd_gl);

fail:
	kfree(rgd->rd_bits);
	kmem_cache_free(gfs2_rgrpd_cachep, rgd);
	return error;
}

/**
 * set_rgrp_preferences - Run all the rgrps, selecting some we prefer to use
 * @sdp: the GFS2 superblock
 *
 * The purpose of this function is to select a subset of the resource groups
 * and mark them as PREFERRED. We do it in such a way that each node prefers
 * to use a unique set of rgrps to minimize glock contention.
 */
static void set_rgrp_preferences(struct gfs2_sbd *sdp)
{
	struct gfs2_rgrpd *rgd, *first;
	int i;

	/* Skip an initial number of rgrps, based on this node's journal ID.
	   That should start each node out on its own set. */
	rgd = gfs2_rgrpd_get_first(sdp);
	for (i = 0; i < sdp->sd_lockstruct.ls_jid; i++)
		rgd = gfs2_rgrpd_get_next(rgd);
	first = rgd;

	do {
		rgd->rd_flags |= GFS2_RDF_PREFERRED;
		for (i = 0; i < sdp->sd_journals; i++) {
			rgd = gfs2_rgrpd_get_next(rgd);
			if (!rgd || rgd == first)
				break;
		}
	} while (rgd && rgd != first);
}

/**
 * gfs2_ri_update - Pull in a new resource index from the disk
 * @ip: pointer to the rindex inode
 *
 * Returns: 0 on successful update, error code otherwise
 */

static int gfs2_ri_update(struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	int error;

	do {
		error = read_rindex_entry(ip);
	} while (error == 0);

	if (error < 0)
		return error;

	set_rgrp_preferences(sdp);

	sdp->sd_rindex_uptodate = 1;
	return 0;
}

/**
 * gfs2_rindex_update - Update the rindex if required
 * @sdp: The GFS2 superblock
 *
 * 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 succeess, error code otherwise
 */

int gfs2_rindex_update(struct gfs2_sbd *sdp)
{
	struct gfs2_inode *ip = GFS2_I(sdp->sd_rindex);
	struct gfs2_glock *gl = ip->i_gl;
	struct gfs2_holder ri_gh;
	int error = 0;
	int unlock_required = 0;

	/* Read new copy from disk if we don't have the latest */
	if (!sdp->sd_rindex_uptodate) {
		if (!gfs2_glock_is_locked_by_me(gl)) {
			error = gfs2_glock_nq_init(gl, LM_ST_SHARED, 0, &ri_gh);
			if (error)
				return error;
			unlock_required = 1;
		}
		if (!sdp->sd_rindex_uptodate)
			error = gfs2_ri_update(ip);
		if (unlock_required)
			gfs2_glock_dq_uninit(&ri_gh);
	}

	return error;
}

static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf)
{
	const struct gfs2_rgrp *str = buf;
	u32 rg_flags;

	rg_flags = be32_to_cpu(str->rg_flags);
	rg_flags &= ~GFS2_RDF_MASK;
	rgd->rd_flags &= GFS2_RDF_MASK;
	rgd->rd_flags |= rg_flags;
	rgd->rd_free = be32_to_cpu(str->rg_free);
	rgd->rd_dinodes = be32_to_cpu(str->rg_dinodes);
	rgd->rd_igeneration = be64_to_cpu(str->rg_igeneration);
}

static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
{
	struct gfs2_rgrp *str = buf;

	str->rg_flags = cpu_to_be32(rgd->rd_flags & ~GFS2_RDF_MASK);
	str->rg_free = cpu_to_be32(rgd->rd_free);
	str->rg_dinodes = cpu_to_be32(rgd->rd_dinodes);
	str->__pad = cpu_to_be32(0);
	str->rg_igeneration = cpu_to_be64(rgd->rd_igeneration);
	memset(&str->rg_reserved, 0, sizeof(str->rg_reserved));
}

static int gfs2_rgrp_lvb_valid(struct gfs2_rgrpd *rgd)
{
	struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;
	struct gfs2_rgrp *str = (struct gfs2_rgrp *)rgd->rd_bits[0].bi_bh->b_data;

	if (rgl->rl_flags != str->rg_flags || rgl->rl_free != str->rg_free ||
	    rgl->rl_dinodes != str->rg_dinodes ||
	    rgl->rl_igeneration != str->rg_igeneration)
		return 0;
	return 1;
}

static void gfs2_rgrp_ondisk2lvb(struct gfs2_rgrp_lvb *rgl, const void *buf)
{
	const struct gfs2_rgrp *str = buf;

	rgl->rl_magic = cpu_to_be32(GFS2_MAGIC);
	rgl->rl_flags = str->rg_flags;
	rgl->rl_free = str->rg_free;
	rgl->rl_dinodes = str->rg_dinodes;
	rgl->rl_igeneration = str->rg_igeneration;
	rgl->__pad = 0UL;
}

static void update_rgrp_lvb_unlinked(struct gfs2_rgrpd *rgd, u32 change)
{
	struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;
	u32 unlinked = be32_to_cpu(rgl->rl_unlinked) + change;
	rgl->rl_unlinked = cpu_to_be32(unlinked);
}

static u32 count_unlinked(struct gfs2_rgrpd *rgd)
{
	struct gfs2_bitmap *bi;
	const u32 length = rgd->rd_length;
	const u8 *buffer = NULL;
	u32 i, goal, count = 0;

	for (i = 0, bi = rgd->rd_bits; i < length; i++, bi++) {
		goal = 0;
		buffer = bi->bi_bh->b_data + bi->bi_offset;
		WARN_ON(!buffer_uptodate(bi->bi_bh));
		while (goal < bi->bi_len * GFS2_NBBY) {
			goal = gfs2_bitfit(buffer, bi->bi_len, goal,
					   GFS2_BLKST_UNLINKED);
			if (goal == BFITNOENT)
				break;
			count++;
			goal++;
		}
	}

	return count;
}


/**
 * 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
 */

static 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;

	if (rgd->rd_bits[0].bi_bh != NULL)
		return 0;

	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;