xattr.c

linux 内核源代码

/*
 * linux/fs/ext4/xattr.c
 *
 * Copyright (C) 2001-2003 Andreas Gruenbacher, <[e-mail]>
 *
 * Fix by Harrison Xing <[e-mail]>.
 * Ext4 code with a lot of help from Eric Jarman <[e-mail]>.
 * Extended attributes for symlinks and special files added per
 *  suggestion of Luka Renko <[e-mail]>.
 * xattr consolidation Copyright (c) 2004 James Morris <[e-mail]>,
 *  Red Hat Inc.
 * ea-in-inode support by Alex Tomas <[e-mail]> aka bzzz
 *  and Andreas Gruenbacher <[e-mail]>.
 */

/*
 * Extended attributes are stored directly in inodes (on file systems with
 * inodes bigger than 128 bytes) and on additional disk blocks. The i_file_acl
 * field contains the block number if an inode uses an additional block. All
 * attributes must fit in the inode and one additional block. Blocks that
 * contain the identical set of attributes may be shared among several inodes.
 * Identical blocks are detected by keeping a cache of blocks that have
 * recently been accessed.
 *
 * The attributes in inodes and on blocks have a different header; the entries
 * are stored in the same format:
 *
 *   +------------------+
 *   | header           |
 *   | entry 1          | |
 *   | entry 2          | | growing downwards
 *   | entry 3          | v
 *   | four null bytes  |
 *   | . . .            |
 *   | value 1          | ^
 *   | value 3          | | growing upwards
 *   | value 2          | |
 *   +------------------+
 *
 * The header is followed by multiple entry descriptors. In disk blocks, the
 * entry descriptors are kept sorted. In inodes, they are unsorted. The
 * attribute values are aligned to the end of the block in no specific order.
 *
 * Locking strategy
 * ----------------
 * EXT4_I(inode)->i_file_acl is protected by EXT4_I(inode)->xattr_sem.
 * EA blocks are only changed if they are exclusive to an inode, so
 * holding xattr_sem also means that nothing but the EA block's reference
 * count can change. Multiple writers to the same block are synchronized
 * by the buffer lock.
 */

#include <linux/init.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/ext4_jbd2.h>
#include <linux/ext4_fs.h>
#include <linux/mbcache.h>
#include <linux/quotaops.h>
#include <linux/rwsem.h>
#include "xattr.h"
#include "acl.h"

#define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data))
#define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr))
#define BFIRST(bh) ENTRY(BHDR(bh)+1)
#define IS_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0)

#ifdef EXT4_XATTR_DEBUG
# define ea_idebug(inode, f...) do { \
		printk(KERN_DEBUG "inode %s:%lu: ", \
			inode->i_sb->s_id, inode->i_ino); \
		printk(f); \
		printk("\n"); \
	} while (0)
# define ea_bdebug(bh, f...) do { \
		char b[BDEVNAME_SIZE]; \
		printk(KERN_DEBUG "block %s:%lu: ", \
			bdevname(bh->b_bdev, b), \
			(unsigned long) bh->b_blocknr); \
		printk(f); \
		printk("\n"); \
	} while (0)
#else
# define ea_idebug(f...)
# define ea_bdebug(f...)
#endif

static void ext4_xattr_cache_insert(struct buffer_head *);
static struct buffer_head *ext4_xattr_cache_find(struct inode *,
						 struct ext4_xattr_header *,
						 struct mb_cache_entry **);
static void ext4_xattr_rehash(struct ext4_xattr_header *,
			      struct ext4_xattr_entry *);

static struct mb_cache *ext4_xattr_cache;

static struct xattr_handler *ext4_xattr_handler_map[] = {
	[EXT4_XATTR_INDEX_USER]		     = &ext4_xattr_user_handler,
#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
	[EXT4_XATTR_INDEX_POSIX_ACL_ACCESS]  = &ext4_xattr_acl_access_handler,
	[EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &ext4_xattr_acl_default_handler,
#endif
	[EXT4_XATTR_INDEX_TRUSTED]	     = &ext4_xattr_trusted_handler,
#ifdef CONFIG_EXT4DEV_FS_SECURITY
	[EXT4_XATTR_INDEX_SECURITY]	     = &ext4_xattr_security_handler,
#endif
};

struct xattr_handler *ext4_xattr_handlers[] = {
	&ext4_xattr_user_handler,
	&ext4_xattr_trusted_handler,
#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
	&ext4_xattr_acl_access_handler,
	&ext4_xattr_acl_default_handler,
#endif
#ifdef CONFIG_EXT4DEV_FS_SECURITY
	&ext4_xattr_security_handler,
#endif
	NULL
};

static inline struct xattr_handler *
ext4_xattr_handler(int name_index)
{
	struct xattr_handler *handler = NULL;

	if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map))
		handler = ext4_xattr_handler_map[name_index];
	return handler;
}

/*
 * Inode operation listxattr()
 *
 * dentry->d_inode->i_mutex: don't care
 */
ssize_t
ext4_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
	return ext4_xattr_list(dentry->d_inode, buffer, size);
}

static int
ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end)
{
	while (!IS_LAST_ENTRY(entry)) {
		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry);
		if ((void *)next >= end)
			return -EIO;
		entry = next;
	}
	return 0;
}

static inline int
ext4_xattr_check_block(struct buffer_head *bh)
{
	int error;

	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
	    BHDR(bh)->h_blocks != cpu_to_le32(1))
		return -EIO;
	error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size);
	return error;
}

static inline int
ext4_xattr_check_entry(struct ext4_xattr_entry *entry, size_t size)
{
	size_t value_size = le32_to_cpu(entry->e_value_size);

	if (entry->e_value_block != 0 || value_size > size ||
	    le16_to_cpu(entry->e_value_offs) + value_size > size)
		return -EIO;
	return 0;
}

static int
ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index,
		      const char *name, size_t size, int sorted)
{
	struct ext4_xattr_entry *entry;
	size_t name_len;
	int cmp = 1;

	if (name == NULL)
		return -EINVAL;
	name_len = strlen(name);
	entry = *pentry;
	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
		cmp = name_index - entry->e_name_index;
		if (!cmp)
			cmp = name_len - entry->e_name_len;
		if (!cmp)
			cmp = memcmp(name, entry->e_name, name_len);
		if (cmp <= 0 && (sorted || cmp == 0))
			break;
	}
	*pentry = entry;
	if (!cmp && ext4_xattr_check_entry(entry, size))
			return -EIO;
	return cmp ? -ENODATA : 0;
}

static int
ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
		     void *buffer, size_t buffer_size)
{
	struct buffer_head *bh = NULL;
	struct ext4_xattr_entry *entry;
	size_t size;
	int error;

	ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
		  name_index, name, buffer, (long)buffer_size);

	error = -ENODATA;
	if (!EXT4_I(inode)->i_file_acl)
		goto cleanup;
	ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl);
	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
	if (!bh)
		goto cleanup;
	ea_bdebug(bh, "b_count=%d, refcount=%d",
		atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
	if (ext4_xattr_check_block(bh)) {
bad_block:	ext4_error(inode->i_sb, __FUNCTION__,
			   "inode %lu: bad block %llu", inode->i_ino,
			   EXT4_I(inode)->i_file_acl);
		error = -EIO;
		goto cleanup;
	}
	ext4_xattr_cache_insert(bh);
	entry = BFIRST(bh);
	error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1);
	if (error == -EIO)
		goto bad_block;
	if (error)
		goto cleanup;
	size = le32_to_cpu(entry->e_value_size);
	if (buffer) {
		error = -ERANGE;
		if (size > buffer_size)
			goto cleanup;
		memcpy(buffer, bh->b_data + le16_to_cpu(entry->e_value_offs),
		       size);
	}
	error = size;

cleanup:
	brelse(bh);
	return error;
}

static int
ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
		     void *buffer, size_t buffer_size)
{
	struct ext4_xattr_ibody_header *header;
	struct ext4_xattr_entry *entry;
	struct ext4_inode *raw_inode;
	struct ext4_iloc iloc;
	size_t size;
	void *end;
	int error;

	if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR))
		return -ENODATA;
	error = ext4_get_inode_loc(inode, &iloc);
	if (error)
		return error;
	raw_inode = ext4_raw_inode(&iloc);
	header = IHDR(inode, raw_inode);
	entry = IFIRST(header);
	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
	error = ext4_xattr_check_names(entry, end);
	if (error)
		goto cleanup;
	error = ext4_xattr_find_entry(&entry, name_index, name,
				      end - (void *)entry, 0);
	if (error)
		goto cleanup;
	size = le32_to_cpu(entry->e_value_size);
	if (buffer) {
		error = -ERANGE;
		if (size > buffer_size)
			goto cleanup;
		memcpy(buffer, (void *)IFIRST(header) +
		       le16_to_cpu(entry->e_value_offs), size);
	}
	error = size;

cleanup:
	brelse(iloc.bh);
	return error;
}

/*
 * ext4_xattr_get()
 *
 * Copy an extended attribute into the buffer
 * provided, or compute the buffer size required.
 * Buffer is NULL to compute the size of the buffer required.
 *
 * Returns a negative error number on failure, or the number of bytes
 * used / required on success.
 */
int
ext4_xattr_get(struct inode *inode, int name_index, const char *name,
	       void *buffer, size_t buffer_size)
{
	int error;

	down_read(&EXT4_I(inode)->xattr_sem);
	error = ext4_xattr_ibody_get(inode, name_index, name, buffer,
				     buffer_size);
	if (error == -ENODATA)
		error = ext4_xattr_block_get(inode, name_index, name, buffer,
					     buffer_size);
	up_read(&EXT4_I(inode)->xattr_sem);
	return error;
}

static int
ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry,
			char *buffer, size_t buffer_size)
{
	size_t rest = buffer_size;

	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
		struct xattr_handler *handler =
			ext4_xattr_handler(entry->e_name_index);

		if (handler) {
			size_t size = handler->list(inode, buffer, rest,
						    entry->e_name,
						    entry->e_name_len);
			if (buffer) {
				if (size > rest)
					return -ERANGE;
				buffer += size;
			}
			rest -= size;
		}
	}
	return buffer_size - rest;
}

static int
ext4_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size)
{
	struct buffer_head *bh = NULL;
	int error;

	ea_idebug(inode, "buffer=%p, buffer_size=%ld",
		  buffer, (long)buffer_size);

	error = 0;
	if (!EXT4_I(inode)->i_file_acl)
		goto cleanup;
	ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl);
	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
	error = -EIO;
	if (!bh)
		goto cleanup;
	ea_bdebug(bh, "b_count=%d, refcount=%d",
		atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
	if (ext4_xattr_check_block(bh)) {
		ext4_error(inode->i_sb, __FUNCTION__,
			   "inode %lu: bad block %llu", inode->i_ino,
			   EXT4_I(inode)->i_file_acl);
		error = -EIO;
		goto cleanup;
	}
	ext4_xattr_cache_insert(bh);
	error = ext4_xattr_list_entries(inode, BFIRST(bh), buffer, buffer_size);

cleanup:
	brelse(bh);

	return error;
}

static int
ext4_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
{
	struct ext4_xattr_ibody_header *header;
	struct ext4_inode *raw_inode;
	struct ext4_iloc iloc;
	void *end;
	int error;

	if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR))
		return 0;
	error = ext4_get_inode_loc(inode, &iloc);
	if (error)
		return error;
	raw_inode = ext4_raw_inode(&iloc);
	header = IHDR(inode, raw_inode);
	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
	error = ext4_xattr_check_names(IFIRST(header), end);
	if (error)
		goto cleanup;
	error = ext4_xattr_list_entries(inode, IFIRST(header),
					buffer, buffer_size);

cleanup:
	brelse(iloc.bh);
	return error;
}

/*
 * ext4_xattr_list()
 *
 * Copy a list of attribute names into the buffer
 * provided, or compute the buffer size required.
 * Buffer is NULL to compute the size of the buffer required.
 *
 * Returns a negative error number on failure, or the number of bytes
 * used / required on success.
 */
int
ext4_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
{
	int i_error, b_error;

	down_read(&EXT4_I(inode)->xattr_sem);
	i_error = ext4_xattr_ibody_list(inode, buffer, buffer_size);
	if (i_error < 0) {
		b_error = 0;
	} else {
		if (buffer) {
			buffer += i_error;
			buffer_size -= i_error;
		}
		b_error = ext4_xattr_block_list(inode, buffer, buffer_size);
		if (b_error < 0)
			i_error = 0;
	}
	up_read(&EXT4_I(inode)->xattr_sem);
	return i_error + b_error;
}

/*
 * If the EXT4_FEATURE_COMPAT_EXT_ATTR feature of this file system is
 * not set, set it.
 */
static void ext4_xattr_update_super_block(handle_t *handle,
					  struct super_block *sb)
{
	if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR))
		return;

	if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
		EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR);
		sb->s_dirt = 1;
		ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
	}
}

/*
 * Release the xattr block BH: If the reference count is > 1, decrement
 * it; otherwise free the block.
 */
static void
ext4_xattr_release_block(handle_t *handle, struct inode *inode,
			 struct buffer_head *bh)
{
	struct mb_cache_entry *ce = NULL;
	int error = 0;

	ce = mb_cache_entry_get(ext4_xattr_cache, bh->b_bdev, bh->b_blocknr);
	error = ext4_journal_get_write_access(handle, bh);
	if (error)
		goto out;

	lock_buffer(bh);
	if (BHDR(bh)->h_refcount == cpu_to_le32(1)) {
		ea_bdebug(bh, "refcount now=0; freeing");
		if (ce)
			mb_cache_entry_free(ce);
		ext4_free_blocks(handle, inode, bh->b_blocknr, 1);
		get_bh(bh);
		ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
	} else {
		BHDR(bh)->h_refcount = cpu_to_le32(
				le32_to_cpu(BHDR(bh)->h_refcount) - 1);
		error = ext4_journal_dirty_metadata(handle, bh);
		if (IS_SYNC(inode))
			handle->h_sync = 1;
		DQUOT_FREE_BLOCK(inode, 1);
		ea_bdebug(bh, "refcount now=%d; releasing",
			  le32_to_cpu(BHDR(bh)->h_refcount));
		if (ce)
			mb_cache_entry_release(ce);
	}
	unlock_buffer(bh);
out:
	ext4_std_error(inode->i_sb, error);
	return;
}

/*
 * Find the available free space for EAs. This also returns the total number of
 * bytes used by EA entries.
 */
static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last,
				    size_t *min_offs, void *base, int *total)
{
	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
		*total += EXT4_XATTR_LEN(last->e_name_len);
		if (!last->e_value_block && last->e_value_size) {
			size_t offs = le16_to_cpu(last->e_value_offs);
			if (offs < *min_offs)
				*min_offs = offs;
		}
	}
	return (*min_offs - ((void *)last - base) - sizeof(__u32));
}

struct ext4_xattr_info {
	int name_index;
	const char *name;
	const void *value;
	size_t value_len;
};