super.c

ReactOS是一些高手根据Windows XP的内核编写出的类XP。内核实现机理和API函数调用几乎相同。甚至可以兼容XP的程序。喜欢研究系统内核的人可以看一看。

	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
		if (!IS_ERR(tmp_ino))
			iput(tmp_ino);
		ntfs_error(sb, "Failed to load $LogFile.");
		// FIMXE: We only want to empty the thing so pointless bailing
		// out. Can recover/ignore.
		goto iput_vol_err_out;
	}
	// FIXME: Empty the logfile, but only if not read-only.
	// FIXME: What happens if someone remounts rw? We need to empty the file
	// then. We need a flag to tell us whether we have done it already.
	iput(tmp_ino);
	/*
	 * Get the inode for the attribute definitions file and parse the
	 * attribute definitions.
	 */
	tmp_ino = ntfs_iget(sb, FILE_AttrDef);
	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
		if (!IS_ERR(tmp_ino))
			iput(tmp_ino);
		ntfs_error(sb, "Failed to load $AttrDef.");
		goto iput_vol_err_out;
	}
	// FIXME: Parse the attribute definitions.
	iput(tmp_ino);
	/* Get the root directory inode. */
	vol->root_ino = ntfs_iget(sb, FILE_root);
	if (IS_ERR(vol->root_ino) || is_bad_inode(vol->root_ino)) {
		if (!IS_ERR(vol->root_ino))
			iput(vol->root_ino);
		ntfs_error(sb, "Failed to load root directory.");
		goto iput_vol_err_out;
	}
	/* If on NTFS versions before 3.0, we are done. */
	if (vol->major_ver < 3)
		return TRUE;
	/* NTFS 3.0+ specific initialization. */
	/* Get the security descriptors inode. */
	vol->secure_ino = ntfs_iget(sb, FILE_Secure);
	if (IS_ERR(vol->secure_ino) || is_bad_inode(vol->secure_ino)) {
		if (!IS_ERR(vol->secure_ino))
			iput(vol->secure_ino);
		ntfs_error(sb, "Failed to load $Secure.");
		goto iput_root_err_out;
	}
	// FIXME: Initialize security.
	/* Get the extended system files' directory inode. */
	tmp_ino = ntfs_iget(sb, FILE_Extend);
	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
		if (!IS_ERR(tmp_ino))
			iput(tmp_ino);
		ntfs_error(sb, "Failed to load $Extend.");
		goto iput_sec_err_out;
	}
	// FIXME: Do something. E.g. want to delete the $UsnJrnl if exists.
	// Note we might be doing this at the wrong level; we might want to
	// d_alloc_root() and then do a "normal" open(2) of $Extend\$UsnJrnl
	// rather than using ntfs_iget here, as we don't know the inode number
	// for the files in $Extend directory.
	iput(tmp_ino);
	return TRUE;
iput_sec_err_out:
	iput(vol->secure_ino);
iput_root_err_out:
	iput(vol->root_ino);
iput_vol_err_out:
	iput(vol->vol_ino);
iput_lcnbmp_err_out:
	iput(vol->lcnbmp_ino);
iput_mirr_err_out:
	iput(vol->mftmirr_ino);
iput_mftbmp_err_out:
	iput(vol->mftbmp_ino);
	return FALSE;
}

/**
 * ntfs_put_super - called by the vfs to unmount a volume
 * @vfs_sb:	vfs superblock of volume to unmount
 *
 * ntfs_put_super() is called by the VFS (from fs/super.c::do_umount()) when
 * the volume is being unmounted (umount system call has been invoked) and it
 * releases all inodes and memory belonging to the NTFS specific part of the
 * super block.
 */
static void ntfs_put_super(struct super_block *vfs_sb)
{
	ntfs_volume *vol = NTFS_SB(vfs_sb);

	ntfs_debug("Entering.");

	iput(vol->vol_ino);
	vol->vol_ino = NULL;

	/* NTFS 3.0+ specific clean up. */
	if (vol->major_ver >= 3) {
		if (vol->secure_ino) {
			iput(vol->secure_ino);
			vol->secure_ino = NULL;
		}
	}

	iput(vol->root_ino);
	vol->root_ino = NULL;

	down_write(&vol->lcnbmp_lock);
	iput(vol->lcnbmp_ino);
	vol->lcnbmp_ino = NULL;
	up_write(&vol->lcnbmp_lock);

	iput(vol->mftmirr_ino);
	vol->mftmirr_ino = NULL;

	down_write(&vol->mftbmp_lock);
	iput(vol->mftbmp_ino);
	vol->mftbmp_ino = NULL;
	up_write(&vol->mftbmp_lock);

	iput(vol->mft_ino);
	vol->mft_ino = NULL;

	vol->upcase_len = 0;
	/*
	 * Decrease the number of mounts and destroy the global default upcase
	 * table if necessary. Also decrease the number of upcase users if we
	 * are a user.
	 */
	down(&ntfs_lock);
	ntfs_nr_mounts--;
	if (vol->upcase == default_upcase) {
		ntfs_nr_upcase_users--;
		vol->upcase = NULL;
	}
	if (!ntfs_nr_upcase_users && default_upcase) {
		ntfs_free(default_upcase);
		default_upcase = NULL;
	}
	if (vol->cluster_size <= 4096 && !--ntfs_nr_compression_users)
		free_compression_buffers();
	up(&ntfs_lock);
	if (vol->upcase) {
		ntfs_free(vol->upcase);
		vol->upcase = NULL;
	}
	if (vol->nls_map) {
		unload_nls(vol->nls_map);
		vol->nls_map = NULL;
	}
	vfs_sb->s_fs_info = NULL;
	kfree(vol);
	return;
}

/**
 * get_nr_free_clusters - return the number of free clusters on a volume
 * @vol:	ntfs volume for which to obtain free cluster count
 *
 * Calculate the number of free clusters on the mounted NTFS volume @vol. We
 * actually calculate the number of clusters in use instead because this
 * allows us to not care about partial pages as these will be just zero filled
 * and hence not be counted as allocated clusters.
 *
 * The only particularity is that clusters beyond the end of the logical ntfs
 * volume will be marked as allocated to prevent errors which means we have to
 * discount those at the end. This is important as the cluster bitmap always
 * has a size in multiples of 8 bytes, i.e. up to 63 clusters could be outside
 * the logical volume and marked in use when they are not as they do not exist.
 *
 * If any pages cannot be read we assume all clusters in the erroring pages are
 * in use. This means we return an underestimate on errors which is better than
 * an overestimate.
 */
static s64 get_nr_free_clusters(ntfs_volume *vol)
{
	s64 nr_free = vol->nr_clusters;
	u32 *kaddr;
	struct address_space *mapping = vol->lcnbmp_ino->i_mapping;
	filler_t *readpage = (filler_t*)mapping->a_ops->readpage;
	struct page *page;
	unsigned long index, max_index;
	unsigned int max_size;

	ntfs_debug("Entering.");
	/* Serialize accesses to the cluster bitmap. */
	down_read(&vol->lcnbmp_lock);
	/*
	 * Convert the number of bits into bytes rounded up, then convert into
	 * multiples of PAGE_CACHE_SIZE, rounding up so that if we have one
	 * full and one partial page max_index = 2.
	 */
	max_index = (((vol->nr_clusters + 7) >> 3) + PAGE_CACHE_SIZE - 1) >>
			PAGE_CACHE_SHIFT;
	/* Use multiples of 4 bytes. */
	max_size = PAGE_CACHE_SIZE >> 2;
	ntfs_debug("Reading $Bitmap, max_index = 0x%lx, max_size = 0x%x.",
			max_index, max_size);
	for (index = 0UL; index < max_index; index++) {
		unsigned int i;
		/*
		 * Read the page from page cache, getting it from backing store
		 * if necessary, and increment the use count.
		 */
		page = read_cache_page(mapping, index, (filler_t*)readpage,
				NULL);
		/* Ignore pages which errored synchronously. */
		if (IS_ERR(page)) {
			ntfs_debug("Sync read_cache_page() error. Skipping "
					"page (index 0x%lx).", index);
			nr_free -= PAGE_CACHE_SIZE * 8;
			continue;
		}
		wait_on_page_locked(page);
		/* Ignore pages which errored asynchronously. */
		if (!PageUptodate(page)) {
			ntfs_debug("Async read_cache_page() error. Skipping "
					"page (index 0x%lx).", index);
			page_cache_release(page);
			nr_free -= PAGE_CACHE_SIZE * 8;
			continue;
		}
		kaddr = (u32*)kmap_atomic(page, KM_USER0);
		/*
		 * For each 4 bytes, subtract the number of set bits. If this
		 * is the last page and it is partial we don't really care as
		 * it just means we do a little extra work but it won't affect
		 * the result as all out of range bytes are set to zero by
		 * ntfs_readpage().
		 */
	  	for (i = 0; i < max_size; i++)
			nr_free -= (s64)hweight32(kaddr[i]);
		kunmap_atomic(kaddr, KM_USER0);
		page_cache_release(page);
	}
	ntfs_debug("Finished reading $Bitmap, last index = 0x%lx.", index - 1);
	/*
	 * Fixup for eventual bits outside logical ntfs volume (see function
	 * description above).
	 */
	if (vol->nr_clusters & 63)
		nr_free += 64 - (vol->nr_clusters & 63);
	up_read(&vol->lcnbmp_lock);
	/* If errors occured we may well have gone below zero, fix this. */
	if (nr_free < 0)
		nr_free = 0;
	ntfs_debug("Exiting.");
	return nr_free;
}

/**
 * __get_nr_free_mft_records - return the number of free inodes on a volume
 * @vol:	ntfs volume for which to obtain free inode count
 *
 * Calculate the number of free mft records (inodes) on the mounted NTFS
 * volume @vol. We actually calculate the number of mft records in use instead
 * because this allows us to not care about partial pages as these will be just
 * zero filled and hence not be counted as allocated mft record.
 *
 * If any pages cannot be read we assume all mft records in the erroring pages
 * are in use. This means we return an underestimate on errors which is better
 * than an overestimate.
 *
 * NOTE: Caller must hold mftbmp_lock rw_semaphore for reading or writing.
 */
static unsigned long __get_nr_free_mft_records(ntfs_volume *vol)
{
	s64 nr_free = vol->nr_mft_records;
	u32 *kaddr;
	struct address_space *mapping = vol->mftbmp_ino->i_mapping;
	filler_t *readpage = (filler_t*)mapping->a_ops->readpage;
	struct page *page;
	unsigned long index, max_index;
	unsigned int max_size;

	ntfs_debug("Entering.");
	/*
	 * Convert the number of bits into bytes rounded up, then convert into
	 * multiples of PAGE_CACHE_SIZE, rounding up so that if we have one
	 * full and one partial page max_index = 2.
	 */
	max_index = (((vol->nr_mft_records + 7) >> 3) + PAGE_CACHE_SIZE - 1) >>
			PAGE_CACHE_SHIFT;
	/* Use multiples of 4 bytes. */
	max_size = PAGE_CACHE_SIZE >> 2;
	ntfs_debug("Reading $MFT/$BITMAP, max_index = 0x%lx, max_size = "
			"0x%x.", max_index, max_size);
	for (index = 0UL; index < max_index; index++) {
		unsigned int i;
		/*
		 * Read the page from page cache, getting it from backing store
		 * if necessary, and increment the use count.
		 */
		page = read_cache_page(mapping, index, (filler_t*)readpage,
				NULL);
		/* Ignore pages which errored synchronously. */
		if (IS_ERR(page)) {
			ntfs_debug("Sync read_cache_page() error. Skipping "
					"page (index 0x%lx).", index);
			nr_free -= PAGE_CACHE_SIZE * 8;
			continue;
		}
		wait_on_page_locked(page);
		/* Ignore pages which errored asynchronously. */
		if (!PageUptodate(page)) {
			ntfs_debug("Async read_cache_page() error. Skipping "
					"page (index 0x%lx).", index);
			page_cache_release(page);
			nr_free -= PAGE_CACHE_SIZE * 8;
			continue;
		}
		kaddr = (u32*)kmap_atomic(page, KM_USER0);
		/*
		 * For each 4 bytes, subtract the number of set bits. If this
		 * is the last page and it is partial we don't really care as
		 * it just means we do a little extra work but it won't affect
		 * the result as all out of range bytes are set to zero by
		 * ntfs_readpage().
		 */
	  	for (i = 0; i < max_size; i++)
			nr_free -= (s64)hweight32(kaddr[i]);
		kunmap_atomic(kaddr, KM_USER0);
		page_cache_release(page);
	}
	ntfs_debug("Finished reading $MFT/$BITMAP, last index = 0x%lx.",
			index - 1);
	/* If errors occured we may well have gone below zero, fix this. */
	if (nr_free < 0)
		nr_free = 0;
	ntfs_debug("Exiting.");
	return nr_free;
}

/**
 * ntfs_statfs - return information about mounted NTFS volume
 * @sb:		super block of mounted volume
 * @sfs:	statfs structure in which to return the information
 *
 * Return information about the mounted NTFS volume @sb in the statfs structure
 * pointed to by @sfs (this is initialized with zeros before ntfs_statfs is
 * called). We interpret the values to be correct of the moment in time at
 * which we are called. Most values are variable otherwise and this isn't just
 * the free values but the totals as well. For example we can increase the
 * total number of file nodes if we run out and we can keep doing this until
 * there is no more space on the volume left at all.
 *
 * Called from vfs_statfs which is used to handle the statfs, fstatfs, and
 * ustat system calls.
 *
 * Return 0 on success or -errno on error.
 */
static int ntfs_statfs(struct super_block *sb, struct kstatfs *sfs)
{
	ntfs_volume *vol = NTFS_SB(sb);
	s64 size;

	ntfs_debug("Entering.");
	/* Type of filesystem. */
	sfs->f_type   = NTFS_SB_MAGIC;
	/* Optimal transfer block size. */
	sfs->f_bsize  = PAGE_CACHE_SIZE;
	/*
	 * Total data blocks in file system in units of f_bsize and since
	 * inodes are also stored in data blocs ($MFT is a file) this is just
	 * the total clusters.
	 */
	sfs->f_blocks = vol->nr_clusters << vol->cluster_size_bits >>
				PAGE_CACHE_SHIFT;
	/* Free data blocks in file system in units of f_bsize. */
	size	      = get_nr_free_clusters(vol) << vol->cluster_size_bits >>
				PAGE_CACHE_SHIFT;
	if (size < 0LL)
		size = 0LL;
	/* Free blocks avail to non-superuser, same as above on NTFS. */
	sfs->f_bavail = sfs->f_bfree = size;
	/* Serialize accesses to the inode bitmap. */
	down_read(&vol->mftbmp_lock);
	/* Total file nodes in file system (at this moment in time). */
	sfs->f_files  = vol->mft_ino->i_size >> vol->mft_record_size_bits;
	/* Free file nodes in fs (based on current total count). */
	sfs->f_ffree = __get_nr_free_mft_records(vol);
	up_read(&vol->mftbmp_lock);
	/*
	 * File system id. This is extremely *nix flavour dependent and even
	 * within Linux itself all fs do their own thing. I interpret this to
	 * mean a unique id associated with the mounted fs and not the id
	 * associated with the file system driver, the latter is already given
	 * by the file system type in sfs->f_type. Thus we use the 64-bit
	 * volume serial number splitting it into two 32-bit parts. We enter
	 * the least significant 32-bits in f_fsid[0] and the most significant
	 * 32-bits in f_fsid[1].
	 */
	sfs->f_fsid.val[0] = vol->serial_no & 0xffffffff;
	sfs->f_fsid.val[1] = (vol->serial_no >> 32) & 0xffffffff;
	/* Maximum length of filenames. */
	sfs->f_namelen	   = NTFS_MAX_NAME_LEN;
	return 0;
}

/**
 * Super operations for mount time when we don't have enough setup to use the
 * proper functions.
 */
struct super_operations ntfs_mount_sops = {
	.alloc_inode	= ntfs_alloc_big_inode,	  /* VFS: Allocate new inode. */
	.destroy_inode	= ntfs_destroy_big_inode, /* VFS: Deallocate inode. */
	.read_inode	= ntfs_read_inode_mount,  /* VFS: Load inode from disk,
						     called from iget(). */
	.clear_inode	= ntfs_clear_big_inode,	  /* VFS: Called when inode is
						     removed from memory. */
};

/**
 * The complete super operations.
 */
struct super_operations ntfs_sops = {
	.alloc_inode	= ntfs_alloc_big_inode,	  /* VFS: Allocate new inode. */
	.destroy_inode	= ntfs_destroy_big_inode, /* VFS: Deallocate inode. */
	//.dirty_inode	= ntfs_dirty_inode,	  /* VFS: Called from
	//					     __mark_inode_dirty(). */
	//.write_inode	= NULL,		  /* VFS: Write dirty inode to disk. */
	.put_inode	= ntfs_put_inode, /* VFS: Called just before the inode
					     reference count is decreased. */
	//.delete_inode	= NULL,		  /* VFS: Delete inode from disk. Called
	//				     when i_count becomes 0 and i_nlink
	//				     is also 0. */
	.put_super	= ntfs_put_super, /* Syscall: umount. */
	//write_super	= NULL,		  /* Flush dirty super block to disk. */
	//write_super_lockfs	= NULL,	  /* ? */
	//unlockfs	= NULL,		  /* ? */
	.statfs		= ntfs_statfs,	  /* Syscall: statfs */
	.remount_fs	= ntfs_remount,	  /* Syscall: mount -o remount. */
	.clear_inode	= ntfs_clear_big_inode,	/* VFS: Called when an inode is
						   removed from memory. */
	//.umount_begin	= NULL,		     /* Forced umount. */
	.show_options	= ntfs_show_options, /* Show mount options in proc. */
};

/**
 * ntfs_fill_super - mount an ntfs files system
 * @sb:		super block of ntfs file system to mount
 * @opt:	string containing the mount options
 * @silent:	silence error output
 *
 * ntfs_fill_super() is called by the VFS to mount the device described by @sb
 * with the mount otions in @data with the NTFS file system.
 *
 * If @silent is true, remain silent even if errors are detected. This is used
 * during bootup, when the kernel tries to mount the root file system with all
 * registered file systems one after the other until one succeeds. This implies
 * that all file systems except the correct one will quite correctly and
 * expectedly return an error, but nobody wants to see error messages when in
 * fact this is what is supposed to happen.
 *