ialloc.c

linux 内核源代码

/*
 *  linux/fs/ext4/ialloc.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card ([e-mail])
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  BSD ufs-inspired inode and directory allocation by
 *  Stephen Tweedie ([e-mail]), 1993
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller ([e-mail]), 1995
 */

#include <linux/time.h>
#include <linux/fs.h>
#include <linux/jbd2.h>
#include <linux/ext4_fs.h>
#include <linux/ext4_jbd2.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include <linux/random.h>
#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <asm/byteorder.h>

#include "xattr.h"
#include "acl.h"
#include "group.h"

/*
 * ialloc.c contains the inodes allocation and deallocation routines
 */

/*
 * The free inodes are managed by bitmaps.  A file system contains several
 * blocks groups.  Each group contains 1 bitmap block for blocks, 1 bitmap
 * block for inodes, N blocks for the inode table and data blocks.
 *
 * The file system contains group descriptors which are located after the
 * super block.  Each descriptor contains the number of the bitmap block and
 * the free blocks count in the block.
 */

/*
 * To avoid calling the atomic setbit hundreds or thousands of times, we only
 * need to use it within a single byte (to ensure we get endianness right).
 * We can use memset for the rest of the bitmap as there are no other users.
 */
void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
{
	int i;

	if (start_bit >= end_bit)
		return;

	ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit);
	for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++)
		ext4_set_bit(i, bitmap);
	if (i < end_bit)
		memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);
}

/* Initializes an uninitialized inode bitmap */
unsigned ext4_init_inode_bitmap(struct super_block *sb,
				struct buffer_head *bh, int block_group,
				struct ext4_group_desc *gdp)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	J_ASSERT_BH(bh, buffer_locked(bh));

	/* If checksum is bad mark all blocks and inodes use to prevent
	 * allocation, essentially implementing a per-group read-only flag. */
	if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
		ext4_error(sb, __FUNCTION__, "Checksum bad for group %u\n",
			   block_group);
		gdp->bg_free_blocks_count = 0;
		gdp->bg_free_inodes_count = 0;
		gdp->bg_itable_unused = 0;
		memset(bh->b_data, 0xff, sb->s_blocksize);
		return 0;
	}

	memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
	mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), EXT4_BLOCKS_PER_GROUP(sb),
			bh->b_data);

	return EXT4_INODES_PER_GROUP(sb);
}

/*
 * Read the inode allocation bitmap for a given block_group, reading
 * into the specified slot in the superblock's bitmap cache.
 *
 * Return buffer_head of bitmap on success or NULL.
 */
static struct buffer_head *
read_inode_bitmap(struct super_block * sb, unsigned long block_group)
{
	struct ext4_group_desc *desc;
	struct buffer_head *bh = NULL;

	desc = ext4_get_group_desc(sb, block_group, NULL);
	if (!desc)
		goto error_out;
	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
		bh = sb_getblk(sb, ext4_inode_bitmap(sb, desc));
		if (!buffer_uptodate(bh)) {
			lock_buffer(bh);
			if (!buffer_uptodate(bh)) {
				ext4_init_inode_bitmap(sb, bh, block_group,
						       desc);
				set_buffer_uptodate(bh);
			}
			unlock_buffer(bh);
		}
	} else {
		bh = sb_bread(sb, ext4_inode_bitmap(sb, desc));
	}
	if (!bh)
		ext4_error(sb, "read_inode_bitmap",
			    "Cannot read inode bitmap - "
			    "block_group = %lu, inode_bitmap = %llu",
			    block_group, ext4_inode_bitmap(sb, desc));
error_out:
	return bh;
}

/*
 * NOTE! When we get the inode, we're the only people
 * that have access to it, and as such there are no
 * race conditions we have to worry about. The inode
 * is not on the hash-lists, and it cannot be reached
 * through the filesystem because the directory entry
 * has been deleted earlier.
 *
 * HOWEVER: we must make sure that we get no aliases,
 * which means that we have to call "clear_inode()"
 * _before_ we mark the inode not in use in the inode
 * bitmaps. Otherwise a newly created file might use
 * the same inode number (not actually the same pointer
 * though), and then we'd have two inodes sharing the
 * same inode number and space on the harddisk.
 */
void ext4_free_inode (handle_t *handle, struct inode * inode)
{
	struct super_block * sb = inode->i_sb;
	int is_directory;
	unsigned long ino;
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *bh2;
	unsigned long block_group;
	unsigned long bit;
	struct ext4_group_desc * gdp;
	struct ext4_super_block * es;
	struct ext4_sb_info *sbi;
	int fatal = 0, err;

	if (atomic_read(&inode->i_count) > 1) {
		printk ("ext4_free_inode: inode has count=%d\n",
					atomic_read(&inode->i_count));
		return;
	}
	if (inode->i_nlink) {
		printk ("ext4_free_inode: inode has nlink=%d\n",
			inode->i_nlink);
		return;
	}
	if (!sb) {
		printk("ext4_free_inode: inode on nonexistent device\n");
		return;
	}
	sbi = EXT4_SB(sb);

	ino = inode->i_ino;
	ext4_debug ("freeing inode %lu\n", ino);

	/*
	 * Note: we must free any quota before locking the superblock,
	 * as writing the quota to disk may need the lock as well.
	 */
	DQUOT_INIT(inode);
	ext4_xattr_delete_inode(handle, inode);
	DQUOT_FREE_INODE(inode);
	DQUOT_DROP(inode);

	is_directory = S_ISDIR(inode->i_mode);

	/* Do this BEFORE marking the inode not in use or returning an error */
	clear_inode (inode);

	es = EXT4_SB(sb)->s_es;
	if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
		ext4_error (sb, "ext4_free_inode",
			    "reserved or nonexistent inode %lu", ino);
		goto error_return;
	}
	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
	bitmap_bh = read_inode_bitmap(sb, block_group);
	if (!bitmap_bh)
		goto error_return;

	BUFFER_TRACE(bitmap_bh, "get_write_access");
	fatal = ext4_journal_get_write_access(handle, bitmap_bh);
	if (fatal)
		goto error_return;

	/* Ok, now we can actually update the inode bitmaps.. */
	if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
					bit, bitmap_bh->b_data))
		ext4_error (sb, "ext4_free_inode",
			      "bit already cleared for inode %lu", ino);
	else {
		gdp = ext4_get_group_desc (sb, block_group, &bh2);

		BUFFER_TRACE(bh2, "get_write_access");
		fatal = ext4_journal_get_write_access(handle, bh2);
		if (fatal) goto error_return;

		if (gdp) {
			spin_lock(sb_bgl_lock(sbi, block_group));
			gdp->bg_free_inodes_count = cpu_to_le16(
				le16_to_cpu(gdp->bg_free_inodes_count) + 1);
			if (is_directory)
				gdp->bg_used_dirs_count = cpu_to_le16(
				  le16_to_cpu(gdp->bg_used_dirs_count) - 1);
			gdp->bg_checksum = ext4_group_desc_csum(sbi,
							block_group, gdp);
			spin_unlock(sb_bgl_lock(sbi, block_group));
			percpu_counter_inc(&sbi->s_freeinodes_counter);
			if (is_directory)
				percpu_counter_dec(&sbi->s_dirs_counter);

		}
		BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
		err = ext4_journal_dirty_metadata(handle, bh2);
		if (!fatal) fatal = err;
	}
	BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata");
	err = ext4_journal_dirty_metadata(handle, bitmap_bh);
	if (!fatal)
		fatal = err;
	sb->s_dirt = 1;
error_return:
	brelse(bitmap_bh);
	ext4_std_error(sb, fatal);
}

/*
 * There are two policies for allocating an inode.  If the new inode is
 * a directory, then a forward search is made for a block group with both
 * free space and a low directory-to-inode ratio; if that fails, then of
 * the groups with above-average free space, that group with the fewest
 * directories already is chosen.
 *
 * For other inodes, search forward from the parent directory\'s block
 * group to find a free inode.
 */
static int find_group_dir(struct super_block *sb, struct inode *parent)
{
	int ngroups = EXT4_SB(sb)->s_groups_count;
	unsigned int freei, avefreei;
	struct ext4_group_desc *desc, *best_desc = NULL;
	int group, best_group = -1;

	freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter);
	avefreei = freei / ngroups;

	for (group = 0; group < ngroups; group++) {
		desc = ext4_get_group_desc (sb, group, NULL);
		if (!desc || !desc->bg_free_inodes_count)
			continue;
		if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
			continue;
		if (!best_desc ||
		    (le16_to_cpu(desc->bg_free_blocks_count) >
		     le16_to_cpu(best_desc->bg_free_blocks_count))) {
			best_group = group;
			best_desc = desc;
		}
	}
	return best_group;
}

/*
 * Orlov's allocator for directories.
 *
 * We always try to spread first-level directories.
 *
 * If there are blockgroups with both free inodes and free blocks counts
 * not worse than average we return one with smallest directory count.
 * Otherwise we simply return a random group.
 *
 * For the rest rules look so:
 *
 * It's OK to put directory into a group unless
 * it has too many directories already (max_dirs) or
 * it has too few free inodes left (min_inodes) or
 * it has too few free blocks left (min_blocks) or
 * it's already running too large debt (max_debt).
 * Parent's group is prefered, if it doesn't satisfy these
 * conditions we search cyclically through the rest. If none
 * of the groups look good we just look for a group with more
 * free inodes than average (starting at parent's group).
 *
 * Debt is incremented each time we allocate a directory and decremented
 * when we allocate an inode, within 0--255.
 */

#define INODE_COST 64
#define BLOCK_COST 256

static int find_group_orlov(struct super_block *sb, struct inode *parent)
{
	int parent_group = EXT4_I(parent)->i_block_group;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
	int ngroups = sbi->s_groups_count;
	int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
	unsigned int freei, avefreei;
	ext4_fsblk_t freeb, avefreeb;
	ext4_fsblk_t blocks_per_dir;
	unsigned int ndirs;
	int max_debt, max_dirs, min_inodes;
	ext4_grpblk_t min_blocks;
	int group = -1, i;
	struct ext4_group_desc *desc;

	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
	avefreei = freei / ngroups;
	freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
	avefreeb = freeb;
	do_div(avefreeb, ngroups);
	ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);

	if ((parent == sb->s_root->d_inode) ||
	    (EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL)) {
		int best_ndir = inodes_per_group;
		int best_group = -1;

		get_random_bytes(&group, sizeof(group));
		parent_group = (unsigned)group % ngroups;
		for (i = 0; i < ngroups; i++) {
			group = (parent_group + i) % ngroups;
			desc = ext4_get_group_desc (sb, group, NULL);
			if (!desc || !desc->bg_free_inodes_count)
				continue;
			if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
				continue;
			if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
				continue;
			if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
				continue;
			best_group = group;
			best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
		}
		if (best_group >= 0)
			return best_group;
		goto fallback;
	}

	blocks_per_dir = ext4_blocks_count(es) - freeb;
	do_div(blocks_per_dir, ndirs);

	max_dirs = ndirs / ngroups + inodes_per_group / 16;
	min_inodes = avefreei - inodes_per_group / 4;
	min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb) / 4;

	max_debt = EXT4_BLOCKS_PER_GROUP(sb);
	max_debt /= max_t(int, blocks_per_dir, BLOCK_COST);
	if (max_debt * INODE_COST > inodes_per_group)
		max_debt = inodes_per_group / INODE_COST;
	if (max_debt > 255)
		max_debt = 255;
	if (max_debt == 0)
		max_debt = 1;

	for (i = 0; i < ngroups; i++) {
		group = (parent_group + i) % ngroups;
		desc = ext4_get_group_desc (sb, group, NULL);
		if (!desc || !desc->bg_free_inodes_count)
			continue;
		if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
			continue;
		if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes)
			continue;
		if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
			continue;
		return group;
	}

fallback:
	for (i = 0; i < ngroups; i++) {
		group = (parent_group + i) % ngroups;
		desc = ext4_get_group_desc (sb, group, NULL);
		if (!desc || !desc->bg_free_inodes_count)
			continue;
		if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
			return group;
	}

	if (avefreei) {
		/*
		 * The free-inodes counter is approximate, and for really small
		 * filesystems the above test can fail to find any blockgroups
		 */
		avefreei = 0;
		goto fallback;
	}

	return -1;
}

static int find_group_other(struct super_block *sb, struct inode *parent)
{
	int parent_group = EXT4_I(parent)->i_block_group;
	int ngroups = EXT4_SB(sb)->s_groups_count;
	struct ext4_group_desc *desc;
	int group, i;

	/*
	 * Try to place the inode in its parent directory
	 */
	group = parent_group;
	desc = ext4_get_group_desc (sb, group, NULL);
	if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
			le16_to_cpu(desc->bg_free_blocks_count))
		return group;

	/*
	 * We're going to place this inode in a different blockgroup from its
	 * parent.  We want to cause files in a common directory to all land in
	 * the same blockgroup.  But we want files which are in a different
	 * directory which shares a blockgroup with our parent to land in a
	 * different blockgroup.
	 *
	 * So add our directory's i_ino into the starting point for the hash.
	 */
	group = (group + parent->i_ino) % ngroups;

	/*
	 * Use a quadratic hash to find a group with a free inode and some free
	 * blocks.