ops_fstype.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/blkdev.h>
#include <linux/kthread.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/gfs2_ondisk.h>
#include <linux/lm_interface.h>

#include "gfs2.h"
#include "incore.h"
#include "daemon.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "lm.h"
#include "mount.h"
#include "ops_fstype.h"
#include "ops_dentry.h"
#include "ops_super.h"
#include "recovery.h"
#include "rgrp.h"
#include "super.h"
#include "sys.h"
#include "util.h"
#include "log.h"

#define DO 0
#define UNDO 1

static struct gfs2_sbd *init_sbd(struct super_block *sb)
{
	struct gfs2_sbd *sdp;

	sdp = kzalloc(sizeof(struct gfs2_sbd), GFP_KERNEL);
	if (!sdp)
		return NULL;

	sb->s_fs_info = sdp;
	sdp->sd_vfs = sb;

	gfs2_tune_init(&sdp->sd_tune);

	INIT_LIST_HEAD(&sdp->sd_reclaim_list);
	spin_lock_init(&sdp->sd_reclaim_lock);
	init_waitqueue_head(&sdp->sd_reclaim_wq);

	mutex_init(&sdp->sd_inum_mutex);
	spin_lock_init(&sdp->sd_statfs_spin);
	mutex_init(&sdp->sd_statfs_mutex);

	spin_lock_init(&sdp->sd_rindex_spin);
	mutex_init(&sdp->sd_rindex_mutex);
	INIT_LIST_HEAD(&sdp->sd_rindex_list);
	INIT_LIST_HEAD(&sdp->sd_rindex_mru_list);
	INIT_LIST_HEAD(&sdp->sd_rindex_recent_list);

	INIT_LIST_HEAD(&sdp->sd_jindex_list);
	spin_lock_init(&sdp->sd_jindex_spin);
	mutex_init(&sdp->sd_jindex_mutex);

	INIT_LIST_HEAD(&sdp->sd_quota_list);
	spin_lock_init(&sdp->sd_quota_spin);
	mutex_init(&sdp->sd_quota_mutex);

	spin_lock_init(&sdp->sd_log_lock);

	INIT_LIST_HEAD(&sdp->sd_log_le_gl);
	INIT_LIST_HEAD(&sdp->sd_log_le_buf);
	INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
	INIT_LIST_HEAD(&sdp->sd_log_le_rg);
	INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
	INIT_LIST_HEAD(&sdp->sd_log_le_ordered);

	mutex_init(&sdp->sd_log_reserve_mutex);
	INIT_LIST_HEAD(&sdp->sd_ail1_list);
	INIT_LIST_HEAD(&sdp->sd_ail2_list);

	init_rwsem(&sdp->sd_log_flush_lock);
	atomic_set(&sdp->sd_log_in_flight, 0);
	init_waitqueue_head(&sdp->sd_log_flush_wait);

	INIT_LIST_HEAD(&sdp->sd_revoke_list);

	mutex_init(&sdp->sd_freeze_lock);

	return sdp;
}

static void init_vfs(struct super_block *sb, unsigned noatime)
{
	struct gfs2_sbd *sdp = sb->s_fs_info;

	sb->s_magic = GFS2_MAGIC;
	sb->s_op = &gfs2_super_ops;
	sb->s_export_op = &gfs2_export_ops;
	sb->s_time_gran = 1;
	sb->s_maxbytes = MAX_LFS_FILESIZE;

	if (sb->s_flags & (MS_NOATIME | MS_NODIRATIME))
		set_bit(noatime, &sdp->sd_flags);

	/* Don't let the VFS update atimes.  GFS2 handles this itself. */
	sb->s_flags |= MS_NOATIME | MS_NODIRATIME;
}

static int init_names(struct gfs2_sbd *sdp, int silent)
{
	char *proto, *table;
	int error = 0;

	proto = sdp->sd_args.ar_lockproto;
	table = sdp->sd_args.ar_locktable;

	/*  Try to autodetect  */

	if (!proto[0] || !table[0]) {
		error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
		if (error)
			return error;

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

		if (!proto[0])
			proto = sdp->sd_sb.sb_lockproto;
		if (!table[0])
			table = sdp->sd_sb.sb_locktable;
	}

	if (!table[0])
		table = sdp->sd_vfs->s_id;

	snprintf(sdp->sd_proto_name, GFS2_FSNAME_LEN, "%s", proto);
	snprintf(sdp->sd_table_name, GFS2_FSNAME_LEN, "%s", table);

	table = sdp->sd_table_name;
	while ((table = strchr(table, '/')))
		*table = '_';

out:
	return error;
}

static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
			int undo)
{
	struct task_struct *p;
	int error = 0;

	if (undo)
		goto fail_trans;

	for (sdp->sd_glockd_num = 0;
	     sdp->sd_glockd_num < sdp->sd_args.ar_num_glockd;
	     sdp->sd_glockd_num++) {
		p = kthread_run(gfs2_glockd, sdp, "gfs2_glockd");
		error = IS_ERR(p);
		if (error) {
			fs_err(sdp, "can't start glockd thread: %d\n", error);
			goto fail;
		}
		sdp->sd_glockd_process[sdp->sd_glockd_num] = p;
	}

	error = gfs2_glock_nq_num(sdp,
				  GFS2_MOUNT_LOCK, &gfs2_nondisk_glops,
				  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP | GL_NOCACHE,
				  mount_gh);
	if (error) {
		fs_err(sdp, "can't acquire mount glock: %d\n", error);
		goto fail;
	}

	error = gfs2_glock_nq_num(sdp,
				  GFS2_LIVE_LOCK, &gfs2_nondisk_glops,
				  LM_ST_SHARED,
				  LM_FLAG_NOEXP | GL_EXACT,
				  &sdp->sd_live_gh);
	if (error) {
		fs_err(sdp, "can't acquire live glock: %d\n", error);
		goto fail_mount;
	}

	error = gfs2_glock_get(sdp, GFS2_RENAME_LOCK, &gfs2_nondisk_glops,
			       CREATE, &sdp->sd_rename_gl);
	if (error) {
		fs_err(sdp, "can't create rename glock: %d\n", error);
		goto fail_live;
	}

	error = gfs2_glock_get(sdp, GFS2_TRANS_LOCK, &gfs2_trans_glops,
			       CREATE, &sdp->sd_trans_gl);
	if (error) {
		fs_err(sdp, "can't create transaction glock: %d\n", error);
		goto fail_rename;
	}
	set_bit(GLF_STICKY, &sdp->sd_trans_gl->gl_flags);

	return 0;

fail_trans:
	gfs2_glock_put(sdp->sd_trans_gl);
fail_rename:
	gfs2_glock_put(sdp->sd_rename_gl);
fail_live:
	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
fail_mount:
	gfs2_glock_dq_uninit(mount_gh);
fail:
	while (sdp->sd_glockd_num--)
		kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]);

	return error;
}

static inline struct inode *gfs2_lookup_root(struct super_block *sb,
					     u64 no_addr)
{
	return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
}

static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
{
	struct super_block *sb = sdp->sd_vfs;
	struct gfs2_holder sb_gh;
	u64 no_addr;
	struct inode *inode;
	int error = 0;

	if (undo) {
		if (sb->s_root) {
			dput(sb->s_root);
			sb->s_root = NULL;
		}
		return 0;
	}

	error = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
				 LM_ST_SHARED, 0, &sb_gh);
	if (error) {
		fs_err(sdp, "can't acquire superblock glock: %d\n", error);
		return error;
	}

	error = gfs2_read_sb(sdp, sb_gh.gh_gl, silent);
	if (error) {
		fs_err(sdp, "can't read superblock: %d\n", error);
		goto out;
	}

	/* Set up the buffer cache and SB for real */
	if (sdp->sd_sb.sb_bsize < bdev_hardsect_size(sb->s_bdev)) {
		error = -EINVAL;
		fs_err(sdp, "FS block size (%u) is too small for device "
		       "block size (%u)\n",
		       sdp->sd_sb.sb_bsize, bdev_hardsect_size(sb->s_bdev));
		goto out;
	}
	if (sdp->sd_sb.sb_bsize > PAGE_SIZE) {
		error = -EINVAL;
		fs_err(sdp, "FS block size (%u) is too big for machine "
		       "page size (%u)\n",
		       sdp->sd_sb.sb_bsize, (unsigned int)PAGE_SIZE);
		goto out;
	}
	sb_set_blocksize(sb, sdp->sd_sb.sb_bsize);

	/* Get the root inode */
	no_addr = sdp->sd_sb.sb_root_dir.no_addr;
	if (sb->s_type == &gfs2meta_fs_type)
		no_addr = sdp->sd_sb.sb_master_dir.no_addr;
	inode = gfs2_lookup_root(sb, no_addr);
	if (IS_ERR(inode)) {
		error = PTR_ERR(inode);
		fs_err(sdp, "can't read in root inode: %d\n", error);
		goto out;
	}

	sb->s_root = d_alloc_root(inode);
	if (!sb->s_root) {
		fs_err(sdp, "can't get root dentry\n");
		error = -ENOMEM;
		iput(inode);
	} else
		sb->s_root->d_op = &gfs2_dops;
	
out:
	gfs2_glock_dq_uninit(&sb_gh);
	return error;
}

static int init_journal(struct gfs2_sbd *sdp, int undo)
{
	struct gfs2_holder ji_gh;
	struct task_struct *p;
	struct gfs2_inode *ip;
	int jindex = 1;
	int error = 0;

	if (undo) {
		jindex = 0;
		goto fail_recoverd;
	}

	sdp->sd_jindex = gfs2_lookup_simple(sdp->sd_master_dir, "jindex");
	if (IS_ERR(sdp->sd_jindex)) {
		fs_err(sdp, "can't lookup journal index: %d\n", error);
		return PTR_ERR(sdp->sd_jindex);
	}
	ip = GFS2_I(sdp->sd_jindex);
	set_bit(GLF_STICKY, &ip->i_gl->gl_flags);

	/* Load in the journal index special file */

	error = gfs2_jindex_hold(sdp, &ji_gh);
	if (error) {
		fs_err(sdp, "can't read journal index: %d\n", error);
		goto fail;
	}

	error = -EINVAL;
	if (!gfs2_jindex_size(sdp)) {
		fs_err(sdp, "no journals!\n");
		goto fail_jindex;
	}

	if (sdp->sd_args.ar_spectator) {
		sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
		sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
	} else {
		if (sdp->sd_lockstruct.ls_jid >= gfs2_jindex_size(sdp)) {
			fs_err(sdp, "can't mount journal #%u\n",
			       sdp->sd_lockstruct.ls_jid);
			fs_err(sdp, "there are only %u journals (0 - %u)\n",
			       gfs2_jindex_size(sdp),
			       gfs2_jindex_size(sdp) - 1);
			goto fail_jindex;
		}
		sdp->sd_jdesc = gfs2_jdesc_find(sdp, sdp->sd_lockstruct.ls_jid);

		error = gfs2_glock_nq_num(sdp, sdp->sd_lockstruct.ls_jid,
					  &gfs2_journal_glops,
					  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP,
					  &sdp->sd_journal_gh);
		if (error) {
			fs_err(sdp, "can't acquire journal glock: %d\n", error);
			goto fail_jindex;
		}

		ip = GFS2_I(sdp->sd_jdesc->jd_inode);
		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
					   LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE,
					   &sdp->sd_jinode_gh);
		if (error) {
			fs_err(sdp, "can't acquire journal inode glock: %d\n",
			       error);
			goto fail_journal_gh;
		}

		error = gfs2_jdesc_check(sdp->sd_jdesc);
		if (error) {
			fs_err(sdp, "my journal (%u) is bad: %d\n",
			       sdp->sd_jdesc->jd_jid, error);
			goto fail_jinode_gh;
		}
		sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
	}

	if (sdp->sd_lockstruct.ls_first) {
		unsigned int x;
		for (x = 0; x < sdp->sd_journals; x++) {
			error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x));
			if (error) {
				fs_err(sdp, "error recovering journal %u: %d\n",
				       x, error);
				goto fail_jinode_gh;
			}
		}

		gfs2_lm_others_may_mount(sdp);
	} else if (!sdp->sd_args.ar_spectator) {
		error = gfs2_recover_journal(sdp->sd_jdesc);
		if (error) {
			fs_err(sdp, "error recovering my journal: %d\n", error);
			goto fail_jinode_gh;
		}
	}

	set_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags);
	gfs2_glock_dq_uninit(&ji_gh);
	jindex = 0;

	p = kthread_run(gfs2_recoverd, sdp, "gfs2_recoverd");
	error = IS_ERR(p);
	if (error) {
		fs_err(sdp, "can't start recoverd thread: %d\n", error);
		goto fail_jinode_gh;
	}
	sdp->sd_recoverd_process = p;

	return 0;

fail_recoverd:
	kthread_stop(sdp->sd_recoverd_process);
fail_jinode_gh:
	if (!sdp->sd_args.ar_spectator)
		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
fail_journal_gh:
	if (!sdp->sd_args.ar_spectator)
		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
fail_jindex:
	gfs2_jindex_free(sdp);
	if (jindex)
		gfs2_glock_dq_uninit(&ji_gh);
fail:
	iput(sdp->sd_jindex);
	return error;
}


static int init_inodes(struct gfs2_sbd *sdp, int undo)
{
	int error = 0;
	struct gfs2_inode *ip;
	struct inode *inode;

	if (undo)
		goto fail_qinode;

	inode = gfs2_lookup_root(sdp->sd_vfs, sdp->sd_sb.sb_master_dir.no_addr);
	if (IS_ERR(inode)) {
		error = PTR_ERR(inode);
		fs_err(sdp, "can't read in master directory: %d\n", error);
		goto fail;
	}
	sdp->sd_master_dir = inode;

	error = init_journal(sdp, undo);
	if (error)
		goto fail_master;

	/* Read in the master inode number inode */
	sdp->sd_inum_inode = gfs2_lookup_simple(sdp->sd_master_dir, "inum");
	if (IS_ERR(sdp->sd_inum_inode)) {
		error = PTR_ERR(sdp->sd_inum_inode);
		fs_err(sdp, "can't read in inum inode: %d\n", error);
		goto fail_journal;
	}