super.c

linux 内核源代码

/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2006 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.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/crc32.h>
#include <linux/gfs2_ondisk.h>
#include <linux/bio.h>
#include <linux/lm_interface.h>

#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "dir.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "quota.h"
#include "recovery.h"
#include "rgrp.h"
#include "super.h"
#include "trans.h"
#include "util.h"

static const u32 gfs2_old_fs_formats[] = {
        0
};

static const u32 gfs2_old_multihost_formats[] = {
        0
};

/**
 * gfs2_tune_init - Fill a gfs2_tune structure with default values
 * @gt: tune
 *
 */

void gfs2_tune_init(struct gfs2_tune *gt)
{
	spin_lock_init(&gt->gt_spin);

	gt->gt_ilimit = 100;
	gt->gt_ilimit_tries = 3;
	gt->gt_ilimit_min = 1;
	gt->gt_demote_secs = 300;
	gt->gt_incore_log_blocks = 1024;
	gt->gt_log_flush_secs = 60;
	gt->gt_jindex_refresh_secs = 60;
	gt->gt_recoverd_secs = 60;
	gt->gt_logd_secs = 1;
	gt->gt_quotad_secs = 5;
	gt->gt_quota_simul_sync = 64;
	gt->gt_quota_warn_period = 10;
	gt->gt_quota_scale_num = 1;
	gt->gt_quota_scale_den = 1;
	gt->gt_quota_cache_secs = 300;
	gt->gt_quota_quantum = 60;
	gt->gt_atime_quantum = 3600;
	gt->gt_new_files_jdata = 0;
	gt->gt_new_files_directio = 0;
	gt->gt_max_readahead = 1 << 18;
	gt->gt_lockdump_size = 131072;
	gt->gt_stall_secs = 600;
	gt->gt_complain_secs = 10;
	gt->gt_reclaim_limit = 5000;
	gt->gt_statfs_quantum = 30;
	gt->gt_statfs_slow = 0;
}

/**
 * gfs2_check_sb - Check superblock
 * @sdp: the filesystem
 * @sb: The superblock
 * @silent: Don't print a message if the check fails
 *
 * Checks the version code of the FS is one that we understand how to
 * read and that the sizes of the various on-disk structures have not
 * changed.
 */

int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
{
	unsigned int x;

	if (sb->sb_magic != GFS2_MAGIC ||
	    sb->sb_type != GFS2_METATYPE_SB) {
		if (!silent)
			printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n");
		return -EINVAL;
	}

	/*  If format numbers match exactly, we're done.  */

	if (sb->sb_fs_format == GFS2_FORMAT_FS &&
	    sb->sb_multihost_format == GFS2_FORMAT_MULTI)
		return 0;

	if (sb->sb_fs_format != GFS2_FORMAT_FS) {
		for (x = 0; gfs2_old_fs_formats[x]; x++)
			if (gfs2_old_fs_formats[x] == sb->sb_fs_format)
				break;

		if (!gfs2_old_fs_formats[x]) {
			printk(KERN_WARNING
			       "GFS2: code version (%u, %u) is incompatible "
			       "with ondisk format (%u, %u)\n",
			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
			       sb->sb_fs_format, sb->sb_multihost_format);
			printk(KERN_WARNING
			       "GFS2: I don't know how to upgrade this FS\n");
			return -EINVAL;
		}
	}

	if (sb->sb_multihost_format != GFS2_FORMAT_MULTI) {
		for (x = 0; gfs2_old_multihost_formats[x]; x++)
			if (gfs2_old_multihost_formats[x] ==
			    sb->sb_multihost_format)
				break;

		if (!gfs2_old_multihost_formats[x]) {
			printk(KERN_WARNING
			       "GFS2: code version (%u, %u) is incompatible "
			       "with ondisk format (%u, %u)\n",
			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
			       sb->sb_fs_format, sb->sb_multihost_format);
			printk(KERN_WARNING
			       "GFS2: I don't know how to upgrade this FS\n");
			return -EINVAL;
		}
	}

	if (!sdp->sd_args.ar_upgrade) {
		printk(KERN_WARNING
		       "GFS2: code version (%u, %u) is incompatible "
		       "with ondisk format (%u, %u)\n",
		       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
		       sb->sb_fs_format, sb->sb_multihost_format);
		printk(KERN_INFO
		       "GFS2: Use the \"upgrade\" mount option to upgrade "
		       "the FS\n");
		printk(KERN_INFO "GFS2: See the manual for more details\n");
		return -EINVAL;
	}

	return 0;
}


static void end_bio_io_page(struct bio *bio, int error)
{
	struct page *page = bio->bi_private;

	if (!error)
		SetPageUptodate(page);
	else
		printk(KERN_WARNING "gfs2: error %d reading superblock\n", error);
	unlock_page(page);
}

static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
{
	const struct gfs2_sb *str = buf;

	sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic);
	sb->sb_type = be32_to_cpu(str->sb_header.mh_type);
	sb->sb_format = be32_to_cpu(str->sb_header.mh_format);
	sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
	sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
	sb->sb_bsize = be32_to_cpu(str->sb_bsize);
	sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift);
	sb->sb_master_dir.no_addr = be64_to_cpu(str->sb_master_dir.no_addr);
	sb->sb_master_dir.no_formal_ino = be64_to_cpu(str->sb_master_dir.no_formal_ino);
	sb->sb_root_dir.no_addr = be64_to_cpu(str->sb_root_dir.no_addr);
	sb->sb_root_dir.no_formal_ino = be64_to_cpu(str->sb_root_dir.no_formal_ino);

	memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
	memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
}

/**
 * gfs2_read_super - Read the gfs2 super block from disk
 * @sdp: The GFS2 super block
 * @sector: The location of the super block
 * @error: The error code to return
 *
 * This uses the bio functions to read the super block from disk
 * because we want to be 100% sure that we never read cached data.
 * A super block is read twice only during each GFS2 mount and is
 * never written to by the filesystem. The first time its read no
 * locks are held, and the only details which are looked at are those
 * relating to the locking protocol. Once locking is up and working,
 * the sb is read again under the lock to establish the location of
 * the master directory (contains pointers to journals etc) and the
 * root directory.
 *
 * Returns: 0 on success or error
 */

int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
{
	struct super_block *sb = sdp->sd_vfs;
	struct gfs2_sb *p;
	struct page *page;
	struct bio *bio;

	page = alloc_page(GFP_KERNEL);
	if (unlikely(!page))
		return -ENOBUFS;

	ClearPageUptodate(page);
	ClearPageDirty(page);
	lock_page(page);

	bio = bio_alloc(GFP_KERNEL, 1);
	if (unlikely(!bio)) {
		__free_page(page);
		return -ENOBUFS;
	}

	bio->bi_sector = sector * (sb->s_blocksize >> 9);
	bio->bi_bdev = sb->s_bdev;
	bio_add_page(bio, page, PAGE_SIZE, 0);

	bio->bi_end_io = end_bio_io_page;
	bio->bi_private = page;
	submit_bio(READ_SYNC | (1 << BIO_RW_META), bio);
	wait_on_page_locked(page);
	bio_put(bio);
	if (!PageUptodate(page)) {
		__free_page(page);
		return -EIO;
	}
	p = kmap(page);
	gfs2_sb_in(&sdp->sd_sb, p);
	kunmap(page);
	__free_page(page);
	return 0;
}

/**
 * gfs2_read_sb - Read super block
 * @sdp: The GFS2 superblock
 * @gl: the glock for the superblock (assumed to be held)
 * @silent: Don't print message if mount fails
 *
 */

int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent)
{
	u32 hash_blocks, ind_blocks, leaf_blocks;
	u32 tmp_blocks;
	unsigned int x;
	int error;

	error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
	if (error) {
		if (!silent)
			fs_err(sdp, "can't read superblock\n");
		return error;
	}

	error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
	if (error)
		return error;

	sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
			       GFS2_BASIC_BLOCK_SHIFT;
	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
	sdp->sd_diptrs = (sdp->sd_sb.sb_bsize -
			  sizeof(struct gfs2_dinode)) / sizeof(u64);
	sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
			  sizeof(struct gfs2_meta_header)) / sizeof(u64);
	sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
	sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
	sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
	sdp->sd_hash_ptrs = sdp->sd_hash_bsize / sizeof(u64);
	sdp->sd_qc_per_block = (sdp->sd_sb.sb_bsize -
				sizeof(struct gfs2_meta_header)) /
			        sizeof(struct gfs2_quota_change);

	/* Compute maximum reservation required to add a entry to a directory */

	hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH),
			     sdp->sd_jbsize);

	ind_blocks = 0;
	for (tmp_blocks = hash_blocks; tmp_blocks > sdp->sd_diptrs;) {
		tmp_blocks = DIV_ROUND_UP(tmp_blocks, sdp->sd_inptrs);
		ind_blocks += tmp_blocks;
	}

	leaf_blocks = 2 + GFS2_DIR_MAX_DEPTH;

	sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;

	sdp->sd_heightsize[0] = sdp->sd_sb.sb_bsize -
				sizeof(struct gfs2_dinode);
	sdp->sd_heightsize[1] = sdp->sd_sb.sb_bsize * sdp->sd_diptrs;
	for (x = 2;; x++) {
		u64 space, d;
		u32 m;

		space = sdp->sd_heightsize[x - 1] * sdp->sd_inptrs;
		d = space;
		m = do_div(d, sdp->sd_inptrs);

		if (d != sdp->sd_heightsize[x - 1] || m)
			break;
		sdp->sd_heightsize[x] = space;
	}
	sdp->sd_max_height = x;
	gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);

	sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
				 sizeof(struct gfs2_dinode);
	sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
	for (x = 2;; x++) {
		u64 space, d;
		u32 m;

		space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
		d = space;
		m = do_div(d, sdp->sd_inptrs);

		if (d != sdp->sd_jheightsize[x - 1] || m)
			break;
		sdp->sd_jheightsize[x] = space;
	}
	sdp->sd_max_jheight = x;
	gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);

	return 0;
}

/**
 * gfs2_jindex_hold - Grab a lock on the jindex
 * @sdp: The GFS2 superblock
 * @ji_gh: the holder for the jindex glock
 *
 * This is very similar to the gfs2_rindex_hold() function, except that
 * in general we hold the jindex lock for longer periods of time and
 * we grab it far less frequently (in general) then the rgrp lock.
 *
 * Returns: errno
 */

int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
{
	struct gfs2_inode *dip = GFS2_I(sdp->sd_jindex);
	struct qstr name;
	char buf[20];
	struct gfs2_jdesc *jd;
	int error;

	name.name = buf;

	mutex_lock(&sdp->sd_jindex_mutex);

	for (;;) {
		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, ji_gh);
		if (error)
			break;

		name.len = sprintf(buf, "journal%u", sdp->sd_journals);
		name.hash = gfs2_disk_hash(name.name, name.len);

		error = gfs2_dir_check(sdp->sd_jindex, &name, NULL);
		if (error == -ENOENT) {
			error = 0;
			break;
		}

		gfs2_glock_dq_uninit(ji_gh);

		if (error)
			break;

		error = -ENOMEM;
		jd = kzalloc(sizeof(struct gfs2_jdesc), GFP_KERNEL);
		if (!jd)
			break;

		jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1, NULL);
		if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
			if (!jd->jd_inode)
				error = -ENOENT;
			else
				error = PTR_ERR(jd->jd_inode);
			kfree(jd);
			break;
		}

		spin_lock(&sdp->sd_jindex_spin);
		jd->jd_jid = sdp->sd_journals++;
		list_add_tail(&jd->jd_list, &sdp->sd_jindex_list);
		spin_unlock(&sdp->sd_jindex_spin);
	}

	mutex_unlock(&sdp->sd_jindex_mutex);

	return error;
}

/**
 * gfs2_jindex_free - Clear all the journal index information
 * @sdp: The GFS2 superblock
 *
 */

void gfs2_jindex_free(struct gfs2_sbd *sdp)
{
	struct list_head list;
	struct gfs2_jdesc *jd;

	spin_lock(&sdp->sd_jindex_spin);
	list_add(&list, &sdp->sd_jindex_list);
	list_del_init(&sdp->sd_jindex_list);
	sdp->sd_journals = 0;
	spin_unlock(&sdp->sd_jindex_spin);

	while (!list_empty(&list)) {
		jd = list_entry(list.next, struct gfs2_jdesc, jd_list);
		list_del(&jd->jd_list);
		iput(jd->jd_inode);
		kfree(jd);
	}
}

static struct gfs2_jdesc *jdesc_find_i(struct list_head *head, unsigned int jid)
{
	struct gfs2_jdesc *jd;
	int found = 0;

	list_for_each_entry(jd, head, jd_list) {
		if (jd->jd_jid == jid) {
			found = 1;
			break;
		}
	}

	if (!found)
		jd = NULL;

	return jd;
}

struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid)
{
	struct gfs2_jdesc *jd;

	spin_lock(&sdp->sd_jindex_spin);
	jd = jdesc_find_i(&sdp->sd_jindex_list, jid);
	spin_unlock(&sdp->sd_jindex_spin);

	return jd;
}

void gfs2_jdesc_make_dirty(struct gfs2_sbd *sdp, unsigned int jid)
{
	struct gfs2_jdesc *jd;

	spin_lock(&sdp->sd_jindex_spin);
	jd = jdesc_find_i(&sdp->sd_jindex_list, jid);
	if (jd)
		jd->jd_dirty = 1;
	spin_unlock(&sdp->sd_jindex_spin);
}

struct gfs2_jdesc *gfs2_jdesc_find_dirty(struct gfs2_sbd *sdp)
{
	struct gfs2_jdesc *jd;
	int found = 0;

	spin_lock(&sdp->sd_jindex_spin);

	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
		if (jd->jd_dirty) {
			jd->jd_dirty = 0;
			found = 1;
			break;
		}
	}
	spin_unlock(&sdp->sd_jindex_spin);

	if (!found)
		jd = NULL;

	return jd;
}

int gfs2_jdesc_check(struct gfs2_jdesc *jd)
{
	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
	int ar;
	int error;

	if (ip->i_di.di_size < (8 << 20) || ip->i_di.di_size > (1 << 30) ||