On 2019-10-15, Omar Sandoval <osandov@osandov.com> wrote:
> From: Omar Sandoval <osandov@fb.com>
> 
> The upcoming RWF_ENCODED operation introduces some security concerns:
> 
> 1. Compressed writes will pass arbitrary data to decompression
>    algorithms in the kernel.
> 2. Compressed reads can leak truncated/hole punched data.
> 
> Therefore, we need to require privilege for RWF_ENCODED. It's not
> possible to do the permissions checks at the time of the read or write
> because, e.g., io_uring submits IO from a worker thread. So, add an open
> flag which requires CAP_SYS_ADMIN. It can also be set and cleared with
> fcntl(). The flag is not cleared in any way on fork or exec; it should
> probably be used with O_CLOEXEC in most cases.
> 
> Note that the usual issue that unknown open flags are ignored doesn't
> really matter for O_ENCODED; if the kernel doesn't support O_ENCODED,
> then it doesn't support RWF_ENCODED, either.
> 
> Signed-off-by: Omar Sandoval <osandov@fb.com>
> ---
>  fs/fcntl.c                       | 10 ++++++++--
>  fs/namei.c                       |  4 ++++
>  include/linux/fcntl.h            |  2 +-
>  include/uapi/asm-generic/fcntl.h |  4 ++++
>  4 files changed, 17 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/fcntl.c b/fs/fcntl.c
> index 3d40771e8e7c..45ebc6df078e 100644
> --- a/fs/fcntl.c
> +++ b/fs/fcntl.c
> @@ -30,7 +30,8 @@
>  #include <asm/siginfo.h>
>  #include <linux/uaccess.h>
>  
> -#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
> +#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME | \
> +		    O_ENCODED)
>  
>  static int setfl(int fd, struct file * filp, unsigned long arg)
>  {
> @@ -49,6 +50,11 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
>  		if (!inode_owner_or_capable(inode))
>  			return -EPERM;
>  
> +	/* O_ENCODED can only be set by superuser */
> +	if ((arg & O_ENCODED) && !(filp->f_flags & O_ENCODED) &&
> +	    !capable(CAP_SYS_ADMIN))
> +		return -EPERM;

I have a feeling the error should probably be an EACCES and not EPERM.

> +
>  	/* required for strict SunOS emulation */
>  	if (O_NONBLOCK != O_NDELAY)
>  	       if (arg & O_NDELAY)
> @@ -1031,7 +1037,7 @@ static int __init fcntl_init(void)
>  	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
>  	 * is defined as O_NONBLOCK on some platforms and not on others.
>  	 */
> -	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ !=
> +	BUILD_BUG_ON(22 - 1 /* for O_RDONLY being 0 */ !=
>  		HWEIGHT32(
>  			(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
>  			__FMODE_EXEC | __FMODE_NONOTIFY));
> diff --git a/fs/namei.c b/fs/namei.c
> index 671c3c1a3425..ae86b125888a 100644
> --- a/fs/namei.c
> +++ b/fs/namei.c
> @@ -2978,6 +2978,10 @@ static int may_open(const struct path *path, int acc_mode, int flag)
>  	if (flag & O_NOATIME && !inode_owner_or_capable(inode))
>  		return -EPERM;
>  
> +	/* O_ENCODED can only be set by superuser */
> +	if ((flag & O_ENCODED) && !capable(CAP_SYS_ADMIN))
> +		return -EPERM;

I would suggest that this check be put into build_open_flags() rather
than putting it this late in open(). Also, same nit about the error
return as above.

> +
>  	return 0;
>  }
>  
> diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
> index d019df946cb2..5fac02479639 100644
> --- a/include/linux/fcntl.h
> +++ b/include/linux/fcntl.h
> @@ -9,7 +9,7 @@
>  	(O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \
>  	 O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \
>  	 FASYNC	| O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
> -	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE)
> +	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE | O_ENCODED)
>  
>  #ifndef force_o_largefile
>  #define force_o_largefile() (!IS_ENABLED(CONFIG_ARCH_32BIT_OFF_T))
> diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
> index 9dc0bf0c5a6e..8c5cbd5942e3 100644
> --- a/include/uapi/asm-generic/fcntl.h
> +++ b/include/uapi/asm-generic/fcntl.h
> @@ -97,6 +97,10 @@
>  #define O_NDELAY	O_NONBLOCK
>  #endif
>  
> +#ifndef O_ENCODED
> +#define O_ENCODED	040000000
> +#endif

You should also define this for all of the architectures which don't use
the generic O_* flag values. On alpha, O_PATH is equal to the value you
picked (just be careful on sparc -- 0x4000000 is the next free bit, but
it's used by FMODE_NONOTIFY.)

> +
>  #define F_DUPFD		0	/* dup */
>  #define F_GETFD		1	/* get close_on_exec */
>  #define F_SETFD		2	/* set/clear close_on_exec */

-- 
Aleksa Sarai
Senior Software Engineer (Containers)
SUSE Linux GmbH
<https://www.cyphar.com/>