super.c

linux 内核源代码

/*
 *  linux/fs/ext3/super.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card ([e-mail])
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/inode.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller ([e-mail]), 1995
 */

#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/jbd.h>
#include <linux/ext3_fs.h>
#include <linux/ext3_jbd.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/parser.h>
#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/vfs.h>
#include <linux/random.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
#include <linux/log2.h>

#include <asm/uaccess.h>

#include "xattr.h"
#include "acl.h"
#include "namei.h"

static int ext3_load_journal(struct super_block *, struct ext3_super_block *,
			     unsigned long journal_devnum);
static int ext3_create_journal(struct super_block *, struct ext3_super_block *,
			       unsigned int);
static void ext3_commit_super (struct super_block * sb,
			       struct ext3_super_block * es,
			       int sync);
static void ext3_mark_recovery_complete(struct super_block * sb,
					struct ext3_super_block * es);
static void ext3_clear_journal_err(struct super_block * sb,
				   struct ext3_super_block * es);
static int ext3_sync_fs(struct super_block *sb, int wait);
static const char *ext3_decode_error(struct super_block * sb, int errno,
				     char nbuf[16]);
static int ext3_remount (struct super_block * sb, int * flags, char * data);
static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf);
static void ext3_unlockfs(struct super_block *sb);
static void ext3_write_super (struct super_block * sb);
static void ext3_write_super_lockfs(struct super_block *sb);

/*
 * Wrappers for journal_start/end.
 *
 * The only special thing we need to do here is to make sure that all
 * journal_end calls result in the superblock being marked dirty, so
 * that sync() will call the filesystem's write_super callback if
 * appropriate.
 */
handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks)
{
	journal_t *journal;

	if (sb->s_flags & MS_RDONLY)
		return ERR_PTR(-EROFS);

	/* Special case here: if the journal has aborted behind our
	 * backs (eg. EIO in the commit thread), then we still need to
	 * take the FS itself readonly cleanly. */
	journal = EXT3_SB(sb)->s_journal;
	if (is_journal_aborted(journal)) {
		ext3_abort(sb, __FUNCTION__,
			   "Detected aborted journal");
		return ERR_PTR(-EROFS);
	}

	return journal_start(journal, nblocks);
}

/*
 * The only special thing we need to do here is to make sure that all
 * journal_stop calls result in the superblock being marked dirty, so
 * that sync() will call the filesystem's write_super callback if
 * appropriate.
 */
int __ext3_journal_stop(const char *where, handle_t *handle)
{
	struct super_block *sb;
	int err;
	int rc;

	sb = handle->h_transaction->t_journal->j_private;
	err = handle->h_err;
	rc = journal_stop(handle);

	if (!err)
		err = rc;
	if (err)
		__ext3_std_error(sb, where, err);
	return err;
}

void ext3_journal_abort_handle(const char *caller, const char *err_fn,
		struct buffer_head *bh, handle_t *handle, int err)
{
	char nbuf[16];
	const char *errstr = ext3_decode_error(NULL, err, nbuf);

	if (bh)
		BUFFER_TRACE(bh, "abort");

	if (!handle->h_err)
		handle->h_err = err;

	if (is_handle_aborted(handle))
		return;

	printk(KERN_ERR "%s: aborting transaction: %s in %s\n",
	       caller, errstr, err_fn);

	journal_abort_handle(handle);
}

/* Deal with the reporting of failure conditions on a filesystem such as
 * inconsistencies detected or read IO failures.
 *
 * On ext2, we can store the error state of the filesystem in the
 * superblock.  That is not possible on ext3, because we may have other
 * write ordering constraints on the superblock which prevent us from
 * writing it out straight away; and given that the journal is about to
 * be aborted, we can't rely on the current, or future, transactions to
 * write out the superblock safely.
 *
 * We'll just use the journal_abort() error code to record an error in
 * the journal instead.  On recovery, the journal will compain about
 * that error until we've noted it down and cleared it.
 */

static void ext3_handle_error(struct super_block *sb)
{
	struct ext3_super_block *es = EXT3_SB(sb)->s_es;

	EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
	es->s_state |= cpu_to_le16(EXT3_ERROR_FS);

	if (sb->s_flags & MS_RDONLY)
		return;

	if (!test_opt (sb, ERRORS_CONT)) {
		journal_t *journal = EXT3_SB(sb)->s_journal;

		EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT;
		if (journal)
			journal_abort(journal, -EIO);
	}
	if (test_opt (sb, ERRORS_RO)) {
		printk (KERN_CRIT "Remounting filesystem read-only\n");
		sb->s_flags |= MS_RDONLY;
	}
	ext3_commit_super(sb, es, 1);
	if (test_opt(sb, ERRORS_PANIC))
		panic("EXT3-fs (device %s): panic forced after error\n",
			sb->s_id);
}

void ext3_error (struct super_block * sb, const char * function,
		 const char * fmt, ...)
{
	va_list args;

	va_start(args, fmt);
	printk(KERN_CRIT "EXT3-fs error (device %s): %s: ",sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);

	ext3_handle_error(sb);
}

static const char *ext3_decode_error(struct super_block * sb, int errno,
				     char nbuf[16])
{
	char *errstr = NULL;

	switch (errno) {
	case -EIO:
		errstr = "IO failure";
		break;
	case -ENOMEM:
		errstr = "Out of memory";
		break;
	case -EROFS:
		if (!sb || EXT3_SB(sb)->s_journal->j_flags & JFS_ABORT)
			errstr = "Journal has aborted";
		else
			errstr = "Readonly filesystem";
		break;
	default:
		/* If the caller passed in an extra buffer for unknown
		 * errors, textualise them now.  Else we just return
		 * NULL. */
		if (nbuf) {
			/* Check for truncated error codes... */
			if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
				errstr = nbuf;
		}
		break;
	}

	return errstr;
}

/* __ext3_std_error decodes expected errors from journaling functions
 * automatically and invokes the appropriate error response.  */

void __ext3_std_error (struct super_block * sb, const char * function,
		       int errno)
{
	char nbuf[16];
	const char *errstr;

	/* Special case: if the error is EROFS, and we're not already
	 * inside a transaction, then there's really no point in logging
	 * an error. */
	if (errno == -EROFS && journal_current_handle() == NULL &&
	    (sb->s_flags & MS_RDONLY))
		return;

	errstr = ext3_decode_error(sb, errno, nbuf);
	printk (KERN_CRIT "EXT3-fs error (device %s) in %s: %s\n",
		sb->s_id, function, errstr);

	ext3_handle_error(sb);
}

/*
 * ext3_abort is a much stronger failure handler than ext3_error.  The
 * abort function may be used to deal with unrecoverable failures such
 * as journal IO errors or ENOMEM at a critical moment in log management.
 *
 * We unconditionally force the filesystem into an ABORT|READONLY state,
 * unless the error response on the fs has been set to panic in which
 * case we take the easy way out and panic immediately.
 */

void ext3_abort (struct super_block * sb, const char * function,
		 const char * fmt, ...)
{
	va_list args;

	printk (KERN_CRIT "ext3_abort called.\n");

	va_start(args, fmt);
	printk(KERN_CRIT "EXT3-fs error (device %s): %s: ",sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);

	if (test_opt(sb, ERRORS_PANIC))
		panic("EXT3-fs panic from previous error\n");

	if (sb->s_flags & MS_RDONLY)
		return;

	printk(KERN_CRIT "Remounting filesystem read-only\n");
	EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
	sb->s_flags |= MS_RDONLY;
	EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT;
	journal_abort(EXT3_SB(sb)->s_journal, -EIO);
}

void ext3_warning (struct super_block * sb, const char * function,
		   const char * fmt, ...)
{
	va_list args;

	va_start(args, fmt);
	printk(KERN_WARNING "EXT3-fs warning (device %s): %s: ",
	       sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);
}

void ext3_update_dynamic_rev(struct super_block *sb)
{
	struct ext3_super_block *es = EXT3_SB(sb)->s_es;

	if (le32_to_cpu(es->s_rev_level) > EXT3_GOOD_OLD_REV)
		return;

	ext3_warning(sb, __FUNCTION__,
		     "updating to rev %d because of new feature flag, "
		     "running e2fsck is recommended",
		     EXT3_DYNAMIC_REV);

	es->s_first_ino = cpu_to_le32(EXT3_GOOD_OLD_FIRST_INO);
	es->s_inode_size = cpu_to_le16(EXT3_GOOD_OLD_INODE_SIZE);
	es->s_rev_level = cpu_to_le32(EXT3_DYNAMIC_REV);
	/* leave es->s_feature_*compat flags alone */
	/* es->s_uuid will be set by e2fsck if empty */

	/*
	 * The rest of the superblock fields should be zero, and if not it
	 * means they are likely already in use, so leave them alone.  We
	 * can leave it up to e2fsck to clean up any inconsistencies there.
	 */
}

/*
 * Open the external journal device
 */
static struct block_device *ext3_blkdev_get(dev_t dev)
{
	struct block_device *bdev;
	char b[BDEVNAME_SIZE];

	bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
	if (IS_ERR(bdev))
		goto fail;
	return bdev;

fail:
	printk(KERN_ERR "EXT3: failed to open journal device %s: %ld\n",
			__bdevname(dev, b), PTR_ERR(bdev));
	return NULL;
}

/*
 * Release the journal device
 */
static int ext3_blkdev_put(struct block_device *bdev)
{
	bd_release(bdev);
	return blkdev_put(bdev);
}

static int ext3_blkdev_remove(struct ext3_sb_info *sbi)
{
	struct block_device *bdev;
	int ret = -ENODEV;

	bdev = sbi->journal_bdev;
	if (bdev) {
		ret = ext3_blkdev_put(bdev);
		sbi->journal_bdev = NULL;
	}
	return ret;
}

static inline struct inode *orphan_list_entry(struct list_head *l)
{
	return &list_entry(l, struct ext3_inode_info, i_orphan)->vfs_inode;
}

static void dump_orphan_list(struct super_block *sb, struct ext3_sb_info *sbi)
{
	struct list_head *l;

	printk(KERN_ERR "sb orphan head is %d\n",
	       le32_to_cpu(sbi->s_es->s_last_orphan));

	printk(KERN_ERR "sb_info orphan list:\n");
	list_for_each(l, &sbi->s_orphan) {
		struct inode *inode = orphan_list_entry(l);
		printk(KERN_ERR "  "
		       "inode %s:%lu at %p: mode %o, nlink %d, next %d\n",
		       inode->i_sb->s_id, inode->i_ino, inode,
		       inode->i_mode, inode->i_nlink,
		       NEXT_ORPHAN(inode));
	}
}

static void ext3_put_super (struct super_block * sb)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	struct ext3_super_block *es = sbi->s_es;
	int i;

	ext3_xattr_put_super(sb);
	journal_destroy(sbi->s_journal);
	if (!(sb->s_flags & MS_RDONLY)) {
		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
		es->s_state = cpu_to_le16(sbi->s_mount_state);
		BUFFER_TRACE(sbi->s_sbh, "marking dirty");
		mark_buffer_dirty(sbi->s_sbh);
		ext3_commit_super(sb, es, 1);
	}

	for (i = 0; i < sbi->s_gdb_count; i++)
		brelse(sbi->s_group_desc[i]);
	kfree(sbi->s_group_desc);
	percpu_counter_destroy(&sbi->s_freeblocks_counter);
	percpu_counter_destroy(&sbi->s_freeinodes_counter);
	percpu_counter_destroy(&sbi->s_dirs_counter);
	brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
	for (i = 0; i < MAXQUOTAS; i++)
		kfree(sbi->s_qf_names[i]);
#endif

	/* Debugging code just in case the in-memory inode orphan list
	 * isn't empty.  The on-disk one can be non-empty if we've
	 * detected an error and taken the fs readonly, but the
	 * in-memory list had better be clean by this point. */
	if (!list_empty(&sbi->s_orphan))
		dump_orphan_list(sb, sbi);
	J_ASSERT(list_empty(&sbi->s_orphan));

	invalidate_bdev(sb->s_bdev);
	if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
		/*
		 * Invalidate the journal device's buffers.  We don't want them
		 * floating about in memory - the physical journal device may
		 * hotswapped, and it breaks the `ro-after' testing code.
		 */
		sync_blockdev(sbi->journal_bdev);
		invalidate_bdev(sbi->journal_bdev);
		ext3_blkdev_remove(sbi);
	}
	sb->s_fs_info = NULL;
	kfree(sbi);
	return;
}

static struct kmem_cache *ext3_inode_cachep;

/*
 * Called inside transaction, so use GFP_NOFS
 */
static struct inode *ext3_alloc_inode(struct super_block *sb)
{
	struct ext3_inode_info *ei;

	ei = kmem_cache_alloc(ext3_inode_cachep, GFP_NOFS);
	if (!ei)
		return NULL;
#ifdef CONFIG_EXT3_FS_POSIX_ACL
	ei->i_acl = EXT3_ACL_NOT_CACHED;
	ei->i_default_acl = EXT3_ACL_NOT_CACHED;
#endif
	ei->i_block_alloc_info = NULL;