shmem.c

最新最稳定的Linux内存管理模块源代码

}

static const struct inode_operations shmem_symlink_inline_operations = {
	.readlink	= generic_readlink,
	.follow_link	= shmem_follow_link_inline,
};

static const struct inode_operations shmem_symlink_inode_operations = {
	.truncate	= shmem_truncate,
	.readlink	= generic_readlink,
	.follow_link	= shmem_follow_link,
	.put_link	= shmem_put_link,
};

#ifdef CONFIG_TMPFS_POSIX_ACL
/*
 * Superblocks without xattr inode operations will get security.* xattr
 * support from the VFS "for free". As soon as we have any other xattrs
 * like ACLs, we also need to implement the security.* handlers at
 * filesystem level, though.
 */

static size_t shmem_xattr_security_list(struct inode *inode, char *list,
					size_t list_len, const char *name,
					size_t name_len)
{
	return security_inode_listsecurity(inode, list, list_len);
}

static int shmem_xattr_security_get(struct inode *inode, const char *name,
				    void *buffer, size_t size)
{
	if (strcmp(name, "") == 0)
		return -EINVAL;
	return xattr_getsecurity(inode, name, buffer, size);
}

static int shmem_xattr_security_set(struct inode *inode, const char *name,
				    const void *value, size_t size, int flags)
{
	if (strcmp(name, "") == 0)
		return -EINVAL;
	return security_inode_setsecurity(inode, name, value, size, flags);
}

static struct xattr_handler shmem_xattr_security_handler = {
	.prefix = XATTR_SECURITY_PREFIX,
	.list   = shmem_xattr_security_list,
	.get    = shmem_xattr_security_get,
	.set    = shmem_xattr_security_set,
};

static struct xattr_handler *shmem_xattr_handlers[] = {
	&shmem_xattr_acl_access_handler,
	&shmem_xattr_acl_default_handler,
	&shmem_xattr_security_handler,
	NULL
};
#endif

static struct dentry *shmem_get_parent(struct dentry *child)
{
	return ERR_PTR(-ESTALE);
}

static int shmem_match(struct inode *ino, void *vfh)
{
	__u32 *fh = vfh;
	__u64 inum = fh[2];
	inum = (inum << 32) | fh[1];
	return ino->i_ino == inum && fh[0] == ino->i_generation;
}

static struct dentry *shmem_fh_to_dentry(struct super_block *sb,
		struct fid *fid, int fh_len, int fh_type)
{
	struct inode *inode;
	struct dentry *dentry = NULL;
	u64 inum = fid->raw[2];
	inum = (inum << 32) | fid->raw[1];

	if (fh_len < 3)
		return NULL;

	inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]),
			shmem_match, fid->raw);
	if (inode) {
		dentry = d_find_alias(inode);
		iput(inode);
	}

	return dentry;
}

static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
				int connectable)
{
	struct inode *inode = dentry->d_inode;

	if (*len < 3)
		return 255;

	if (hlist_unhashed(&inode->i_hash)) {
		/* Unfortunately insert_inode_hash is not idempotent,
		 * so as we hash inodes here rather than at creation
		 * time, we need a lock to ensure we only try
		 * to do it once
		 */
		static DEFINE_SPINLOCK(lock);
		spin_lock(&lock);
		if (hlist_unhashed(&inode->i_hash))
			__insert_inode_hash(inode,
					    inode->i_ino + inode->i_generation);
		spin_unlock(&lock);
	}

	fh[0] = inode->i_generation;
	fh[1] = inode->i_ino;
	fh[2] = ((__u64)inode->i_ino) >> 32;

	*len = 3;
	return 1;
}

static const struct export_operations shmem_export_ops = {
	.get_parent     = shmem_get_parent,
	.encode_fh      = shmem_encode_fh,
	.fh_to_dentry	= shmem_fh_to_dentry,
};

static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
			       bool remount)
{
	char *this_char, *value, *rest;

	while (options != NULL) {
		this_char = options;
		for (;;) {
			/*
			 * NUL-terminate this option: unfortunately,
			 * mount options form a comma-separated list,
			 * but mpol's nodelist may also contain commas.
			 */
			options = strchr(options, ',');
			if (options == NULL)
				break;
			options++;
			if (!isdigit(*options)) {
				options[-1] = '\0';
				break;
			}
		}
		if (!*this_char)
			continue;
		if ((value = strchr(this_char,'=')) != NULL) {
			*value++ = 0;
		} else {
			printk(KERN_ERR
			    "tmpfs: No value for mount option '%s'\n",
			    this_char);
			return 1;
		}

		if (!strcmp(this_char,"size")) {
			unsigned long long size;
			size = memparse(value,&rest);
			if (*rest == '%') {
				size <<= PAGE_SHIFT;
				size *= totalram_pages;
				do_div(size, 100);
				rest++;
			}
			if (*rest)
				goto bad_val;
			sbinfo->max_blocks =
				DIV_ROUND_UP(size, PAGE_CACHE_SIZE);
		} else if (!strcmp(this_char,"nr_blocks")) {
			sbinfo->max_blocks = memparse(value, &rest);
			if (*rest)
				goto bad_val;
		} else if (!strcmp(this_char,"nr_inodes")) {
			sbinfo->max_inodes = memparse(value, &rest);
			if (*rest)
				goto bad_val;
		} else if (!strcmp(this_char,"mode")) {
			if (remount)
				continue;
			sbinfo->mode = simple_strtoul(value, &rest, 8) & 07777;
			if (*rest)
				goto bad_val;
		} else if (!strcmp(this_char,"uid")) {
			if (remount)
				continue;
			sbinfo->uid = simple_strtoul(value, &rest, 0);
			if (*rest)
				goto bad_val;
		} else if (!strcmp(this_char,"gid")) {
			if (remount)
				continue;
			sbinfo->gid = simple_strtoul(value, &rest, 0);
			if (*rest)
				goto bad_val;
		} else if (!strcmp(this_char,"mpol")) {
			if (mpol_parse_str(value, &sbinfo->mpol, 1))
				goto bad_val;
		} else {
			printk(KERN_ERR "tmpfs: Bad mount option %s\n",
			       this_char);
			return 1;
		}
	}
	return 0;

bad_val:
	printk(KERN_ERR "tmpfs: Bad value '%s' for mount option '%s'\n",
	       value, this_char);
	return 1;

}

static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
{
	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
	struct shmem_sb_info config = *sbinfo;
	unsigned long blocks;
	unsigned long inodes;
	int error = -EINVAL;

	if (shmem_parse_options(data, &config, true))
		return error;

	spin_lock(&sbinfo->stat_lock);
	blocks = sbinfo->max_blocks - sbinfo->free_blocks;
	inodes = sbinfo->max_inodes - sbinfo->free_inodes;
	if (config.max_blocks < blocks)
		goto out;
	if (config.max_inodes < inodes)
		goto out;
	/*
	 * Those tests also disallow limited->unlimited while any are in
	 * use, so i_blocks will always be zero when max_blocks is zero;
	 * but we must separately disallow unlimited->limited, because
	 * in that case we have no record of how much is already in use.
	 */
	if (config.max_blocks && !sbinfo->max_blocks)
		goto out;
	if (config.max_inodes && !sbinfo->max_inodes)
		goto out;

	error = 0;
	sbinfo->max_blocks  = config.max_blocks;
	sbinfo->free_blocks = config.max_blocks - blocks;
	sbinfo->max_inodes  = config.max_inodes;
	sbinfo->free_inodes = config.max_inodes - inodes;

	mpol_put(sbinfo->mpol);
	sbinfo->mpol        = config.mpol;	/* transfers initial ref */
out:
	spin_unlock(&sbinfo->stat_lock);
	return error;
}

static int shmem_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
	struct shmem_sb_info *sbinfo = SHMEM_SB(vfs->mnt_sb);

	if (sbinfo->max_blocks != shmem_default_max_blocks())
		seq_printf(seq, ",size=%luk",
			sbinfo->max_blocks << (PAGE_CACHE_SHIFT - 10));
	if (sbinfo->max_inodes != shmem_default_max_inodes())
		seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes);
	if (sbinfo->mode != (S_IRWXUGO | S_ISVTX))
		seq_printf(seq, ",mode=%03o", sbinfo->mode);
	if (sbinfo->uid != 0)
		seq_printf(seq, ",uid=%u", sbinfo->uid);
	if (sbinfo->gid != 0)
		seq_printf(seq, ",gid=%u", sbinfo->gid);
	shmem_show_mpol(seq, sbinfo->mpol);
	return 0;
}
#endif /* CONFIG_TMPFS */

static void shmem_put_super(struct super_block *sb)
{
	kfree(sb->s_fs_info);
	sb->s_fs_info = NULL;
}

static int shmem_fill_super(struct super_block *sb,
			    void *data, int silent)
{
	struct inode *inode;
	struct dentry *root;
	struct shmem_sb_info *sbinfo;
	int err = -ENOMEM;

	/* Round up to L1_CACHE_BYTES to resist false sharing */
	sbinfo = kmalloc(max((int)sizeof(struct shmem_sb_info),
				L1_CACHE_BYTES), GFP_KERNEL);
	if (!sbinfo)
		return -ENOMEM;

	sbinfo->max_blocks = 0;
	sbinfo->max_inodes = 0;
	sbinfo->mode = S_IRWXUGO | S_ISVTX;
	sbinfo->uid = current_fsuid();
	sbinfo->gid = current_fsgid();
	sbinfo->mpol = NULL;
	sb->s_fs_info = sbinfo;

#ifdef CONFIG_TMPFS
	/*
	 * Per default we only allow half of the physical ram per
	 * tmpfs instance, limiting inodes to one per page of lowmem;
	 * but the internal instance is left unlimited.
	 */
	if (!(sb->s_flags & MS_NOUSER)) {
		sbinfo->max_blocks = shmem_default_max_blocks();
		sbinfo->max_inodes = shmem_default_max_inodes();
		if (shmem_parse_options(data, sbinfo, false)) {
			err = -EINVAL;
			goto failed;
		}
	}
	sb->s_export_op = &shmem_export_ops;
#else
	sb->s_flags |= MS_NOUSER;
#endif

	spin_lock_init(&sbinfo->stat_lock);
	sbinfo->free_blocks = sbinfo->max_blocks;
	sbinfo->free_inodes = sbinfo->max_inodes;

	sb->s_maxbytes = SHMEM_MAX_BYTES;
	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = TMPFS_MAGIC;
	sb->s_op = &shmem_ops;
	sb->s_time_gran = 1;
#ifdef CONFIG_TMPFS_POSIX_ACL
	sb->s_xattr = shmem_xattr_handlers;
	sb->s_flags |= MS_POSIXACL;
#endif

	inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE);
	if (!inode)
		goto failed;
	inode->i_uid = sbinfo->uid;
	inode->i_gid = sbinfo->gid;
	root = d_alloc_root(inode);
	if (!root)
		goto failed_iput;
	sb->s_root = root;
	return 0;

failed_iput:
	iput(inode);
failed:
	shmem_put_super(sb);
	return err;
}

static struct kmem_cache *shmem_inode_cachep;

static struct inode *shmem_alloc_inode(struct super_block *sb)
{
	struct shmem_inode_info *p;
	p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL);
	if (!p)
		return NULL;
	return &p->vfs_inode;
}

static void shmem_destroy_inode(struct inode *inode)
{
	if ((inode->i_mode & S_IFMT) == S_IFREG) {
		/* only struct inode is valid if it's an inline symlink */
		mpol_free_shared_policy(&SHMEM_I(inode)->policy);
	}
	shmem_acl_destroy_inode(inode);
	kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
}

static void init_once(void *foo)
{
	struct shmem_inode_info *p = (struct shmem_inode_info *) foo;

	inode_init_once(&p->vfs_inode);
#ifdef CONFIG_TMPFS_POSIX_ACL
	p->i_acl = NULL;
	p->i_default_acl = NULL;
#endif
}

static int init_inodecache(void)
{
	shmem_inode_cachep = kmem_cache_create("shmem_inode_cache",
				sizeof(struct shmem_inode_info),
				0, SLAB_PANIC, init_once);
	return 0;
}

static void destroy_inodecache(void)
{
	kmem_cache_destroy(shmem_inode_cachep);
}

static const struct address_space_operations shmem_aops = {
	.writepage	= shmem_writepage,
	.set_page_dirty	= __set_page_dirty_no_writeback,
#ifdef CONFIG_TMPFS
	.readpage	= shmem_readpage,
	.write_begin	= shmem_write_begin,
	.write_end	= shmem_write_end,
#endif
	.migratepage	= migrate_page,
};

static const struct file_operations shmem_file_operations = {
	.mmap		= shmem_mmap,
#ifdef CONFIG_TMPFS
	.llseek		= generic_file_llseek,
	.read		= do_sync_read,
	.write		= do_sync_write,
	.aio_read	= shmem_file_aio_read,
	.aio_write	= generic_file_aio_write,
	.fsync		= simple_sync_file,
	.splice_read	= generic_file_splice_read,
	.splice_write	= generic_file_splice_write,
#endif
};

static const struct inode_operations shmem_inode_operations = {
	.truncate	= shmem_truncate,
	.setattr	= shmem_notify_change,
	.truncate_range	= shmem_truncate_range,
#ifdef CONFIG_TMPFS_POSIX_ACL
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= generic_listxattr,
	.removexattr	= generic_removexattr,
	.permission	= shmem_permission,
#endif

};

static const struct inode_operations shmem_dir_inode_operations = {
#ifdef CONFIG_TMPFS
	.create		= shmem_create,
	.lookup		= simple_lookup,
	.link		= shmem_link,
	.unlink		= shmem_unlink,
	.symlink	= shmem_symlink,
	.mkdir		= shmem_mkdir,
	.rmdir		= shmem_rmdir,
	.mknod		= shmem_mknod,
	.rename		= shmem_rename,
#endif
#ifdef CONFIG_TMPFS_POSIX_ACL
	.setattr	= shmem_notify_change,
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= generic_listxattr,
	.removexattr	= generic_removexattr,
	.permission	= shmem_permission,
#endif
};

static const struct inode_operations shmem_special_inode_operations = {
#ifdef CONFIG_TMPFS_POSIX_ACL
	.setattr	= shmem_notify_change,
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= generic_listxattr,
	.removexattr	= generic_removexattr,
	.permission	= shmem_permission,
#endif
};

static const struct super_operations shmem_ops = {
	.alloc_inode	= shmem_alloc_inode,
	.destroy_inode	= shmem_destroy_inode,
#ifdef CONFIG_TMPFS
	.statfs		= shmem_statfs,
	.remount_fs	= shmem_remount_fs,
	.show_options	= shmem_show_options,
#endif
	.delete_inode	= shmem_delete_inode,
	.drop_inode	= generic_delete_inode,
	.put_super	= shmem_put_super,
};

static struct vm_operations_struct shmem_vm_ops = {
	.fault		= shmem_fault,
#ifdef CONFIG_NUMA
	.set_policy