lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20140524080239.GA26948@azat>
Date:	Sat, 24 May 2014 12:02:39 +0400
From:	Azat Khuzhin <a3at.mail@...il.com>
To:	Miklos Szeredi <miklos@...redi.hu>
Cc:	viro@...IV.linux.org.uk, torvalds@...ux-foundation.org,
	linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
	hch@...radead.org, akpm@...ux-foundation.org, apw@...onical.com,
	nbd@...nwrt.org, neilb@...e.de, jordipujolp@...il.com,
	ezk@....cs.sunysb.edu, dhowells@...hat.com, sedat.dilek@...il.com,
	hooanon05@...oo.co.jp, mszeredi@...e.cz
Subject: Re: [PATCH 07/13] vfs: add RENAME_WHITEOUT

On Fri, May 23, 2014 at 11:43:37AM +0200, Miklos Szeredi wrote:
> From: Miklos Szeredi <mszeredi@...e.cz>
> 
> This adds a new RENAME_WHITEOUT flag.  This flag makes rename() create a
> whiteout of source.  The whiteout creation is atomic relative to the
> rename.
> 
> Signed-off-by: Miklos Szeredi <mszeredi@...e.cz>
> ---
>  fs/ext4/namei.c         | 99 ++++++++++++++++++++++++++++++++++++++++---------
>  fs/namei.c              |  8 +++-
>  include/linux/fs.h      |  7 ++++
>  include/uapi/linux/fs.h |  1 +
>  4 files changed, 95 insertions(+), 20 deletions(-)
> 
> diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
> index 1cb84f78909e..f782831b19dc 100644
> --- a/fs/ext4/namei.c
> +++ b/fs/ext4/namei.c
> @@ -3148,6 +3148,39 @@ static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent)
>  	}
>  }
>  
> +static struct inode *ext4_whiteout_for_rename(struct ext4_renament *ent,
> +					      int credits, handle_t **h)
> +{
> +	struct inode *wh;
> +	handle_t *handle;
> +	int retries = 0;
> +
> +	/*
> +	 * for inode block, sb block, group summaries,
> +	 * and inode bitmap
> +	 */
> +	credits += (EXT4_MAXQUOTAS_TRANS_BLOCKS(ent->dir->i_sb) +
> +		    EXT4_XATTR_TRANS_BLOCKS + 4);
> +retry:
> +	wh = ext4_new_inode_start_handle(ent->dir, S_IFCHR | WHITEOUT_MODE,
> +					 &ent->dentry->d_name, 0, NULL,
> +					 EXT4_HT_DIR, credits);
> +
> +	handle = ext4_journal_current_handle();
> +	if (IS_ERR(wh)) {
> +		if (handle)
> +			ext4_journal_stop(handle);
> +		if (PTR_ERR(wh) == -ENOSPC &&
> +		    ext4_should_retry_alloc(ent->dir->i_sb, &retries))
> +			goto retry;
> +	} else {
> +		*h = handle;
> +		init_special_inode(wh, wh->i_mode, WHITEOUT_DEV);
> +		wh->i_op = &ext4_special_inode_operations;
> +	}
> +	return wh;
> +}
> +
>  /*
>   * Anybody can rename anything with this: the permission checks are left to the
>   * higher-level routines.
> @@ -3156,8 +3189,9 @@ static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent)
>   * while new_{dentry,inode) refers to the destination dentry/inode
>   * This comes from rename(const char *oldpath, const char *newpath)
>   */
> -static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
> -		       struct inode *new_dir, struct dentry *new_dentry)
> +static int ext4_simple_rename(struct inode *old_dir, struct dentry *old_dentry,
> +			      struct inode *new_dir, struct dentry *new_dentry,
> +			      unsigned int flags)
>  {
>  	handle_t *handle = NULL;
>  	struct ext4_renament old = {
> @@ -3171,6 +3205,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
>  		.inode = new_dentry->d_inode,
>  	};
>  	int retval;
> +	struct inode *whiteout = NULL;
> +	int credits;
> +	u8 old_file_type;
>  
>  	dquot_initialize(old.dir);
>  	dquot_initialize(new.dir);
> @@ -3202,11 +3239,17 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
>  	if (new.inode && !test_opt(new.dir->i_sb, NO_AUTO_DA_ALLOC))
>  		ext4_alloc_da_blocks(old.inode);
>  
> -	handle = ext4_journal_start(old.dir, EXT4_HT_DIR,
> -		(2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) +
> -		 EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
> -	if (IS_ERR(handle))
> -		return PTR_ERR(handle);
> +	credits = (2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) +
> +		   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2);
> +	if (!(flags & RENAME_WHITEOUT)) {
> +		handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits);
> +		if (IS_ERR(handle))
> +			return PTR_ERR(handle);
> +	} else {
> +		whiteout = ext4_whiteout_for_rename(&old, credits, &handle);
> +		if (IS_ERR(whiteout))
> +			return PTR_ERR(whiteout);
> +	}
>  
>  	if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
>  		ext4_handle_sync(handle);
> @@ -3225,13 +3268,21 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
>  		if (retval)
>  			goto end_rename;
>  	}
> +	old_file_type = old.de->file_type;
> +	if (whiteout) {
> +		retval = ext4_setent(handle, &old, whiteout->i_ino,
> +				     EXT4_FT_CHRDEV);
> +		if (retval)
> +			goto end_rename;
> +		ext4_mark_inode_dirty(handle, whiteout);
> +	}
>  	if (!new.bh) {
>  		retval = ext4_add_entry(handle, new.dentry, old.inode);
>  		if (retval)
>  			goto end_rename;
>  	} else {
>  		retval = ext4_setent(handle, &new,
> -				     old.inode->i_ino, old.de->file_type);
> +				     old.inode->i_ino, old_file_type);
>  		if (retval)
>  			goto end_rename;
>  	}
> @@ -3243,10 +3294,12 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
>  	old.inode->i_ctime = ext4_current_time(old.inode);
>  	ext4_mark_inode_dirty(handle, old.inode);
>  
> -	/*
> -	 * ok, that's it
> -	 */
> -	ext4_rename_delete(handle, &old);
> +	if (!whiteout) {
> +		/*
> +		 * ok, that's it
> +		 */
> +		ext4_rename_delete(handle, &old);
> +	}
>  
>  	if (new.inode) {
>  		ext4_dec_count(handle, new.inode);
> @@ -3282,6 +3335,12 @@ end_rename:
>  	brelse(old.dir_bh);
>  	brelse(old.bh);
>  	brelse(new.bh);
> +	if (whiteout) {
> +		if (retval)
> +			drop_nlink(whiteout);
> +		unlock_new_inode(whiteout);
> +		iput(whiteout);
> +	}
>  	if (handle)
>  		ext4_journal_stop(handle);
>  	return retval;
> @@ -3403,22 +3462,26 @@ end_rename:
>  	return retval;
>  }
>  
> +static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
> +		       struct inode *new_dir, struct dentry *new_dentry)
> +{
> +	return ext4_simple_rename(old_dir, old_dentry, new_dir, new_dentry, 0);
> +}
> +
>  static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry,
>  			struct inode *new_dir, struct dentry *new_dentry,
>  			unsigned int flags)
>  {
> -	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
> +	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
>  		return -EINVAL;
>  
>  	if (flags & RENAME_EXCHANGE) {
>  		return ext4_cross_rename(old_dir, old_dentry,
>  					 new_dir, new_dentry);
>  	}
> -	/*
> -	 * Existence checking was done by the VFS, otherwise "RENAME_NOREPLACE"
> -	 * is equivalent to regular rename.
> -	 */
> -	return ext4_rename(old_dir, old_dentry, new_dir, new_dentry);
> +
> +	return ext4_simple_rename(old_dir, old_dentry,
> +				  new_dir, new_dentry, flags);
>  }
>  
>  /*
> diff --git a/fs/namei.c b/fs/namei.c
> index 413d7c138e95..adaa73d91173 100644
> --- a/fs/namei.c
> +++ b/fs/namei.c
> @@ -4186,12 +4186,16 @@ SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
>  	bool should_retry = false;
>  	int error;
>  
> -	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
> +	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
>  		return -EINVAL;
>  
> -	if ((flags & RENAME_NOREPLACE) && (flags & RENAME_EXCHANGE))
> +	if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) &&
> +	    (flags & RENAME_EXCHANGE))
>  		return -EINVAL;
>  
> +	if ((flags & RENAME_WHITEOUT) && !capable(CAP_MKNOD))
> +		return -EPERM;
> +
>  retry:
>  	from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags);
>  	if (IS_ERR(from)) {
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 88ec7a2878bc..48d3bd908b5d 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -228,6 +228,13 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
>  #define WHITEOUT_DEV 0
>  
>  /*
> + * Whiteout is represented by a char device.  The following constants define the
> + * mode and device number to use.
> + */
> +#define WHITEOUT_MODE 0
> +#define WHITEOUT_DEV 0

Quick note:
I suppose that there is no need in duplicating of WHITEOUT_{MODE,DEV}

Thanks.

> +
> +/*
>   * This is the Inode Attributes structure, used for notify_change().  It
>   * uses the above definitions as flags, to know which values have changed.
>   * Also, in this manner, a Filesystem can look at only the values it cares
> diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
> index ca1a11bb4443..3735fa0a6784 100644
> --- a/include/uapi/linux/fs.h
> +++ b/include/uapi/linux/fs.h
> @@ -37,6 +37,7 @@
>  
>  #define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
>  #define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
> +#define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
>  
>  struct fstrim_range {
>  	__u64 start;
> -- 
> 1.8.1.4
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

-- 
Respectfully
Azat Khuzhin
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ