From: Omar Sandoval <osandov@osandov.com>
To: linux-fsdevel@vger.kernel.org, linux-btrfs@vger.kernel.org,
Al Viro <viro@zeniv.linux.org.uk>,
Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>, Jann Horn <jannh@google.com>,
Amir Goldstein <amir73il@gmail.com>,
Aleksa Sarai <cyphar@cyphar.com>,
linux-api@vger.kernel.org, kernel-team@fb.com
Subject: [PATCH v6 02/11] fs: add O_ALLOW_ENCODED open flag
Date: Wed, 18 Nov 2020 11:18:09 -0800 [thread overview]
Message-ID: <977fd16687d8b0474fd9c442f79c23f53783e403.1605723568.git.osandov@fb.com> (raw)
In-Reply-To: <cover.1605723568.git.osandov@fb.com>
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 must be
combined with O_CLOEXEC when opening to avoid accidental leaks (if
needed, it may be set without O_CLOEXEC by using fnctl()).
Note that the usual issue that unknown open flags are ignored doesn't
really matter for O_ALLOW_ENCODED; if the kernel doesn't support
O_ALLOW_ENCODED, then it doesn't support RWF_ENCODED, either.
Signed-off-by: Omar Sandoval <osandov@fb.com>
---
arch/alpha/include/uapi/asm/fcntl.h | 1 +
arch/parisc/include/uapi/asm/fcntl.h | 1 +
arch/sparc/include/uapi/asm/fcntl.h | 1 +
fs/fcntl.c | 10 ++++++++--
fs/namei.c | 4 ++++
fs/open.c | 7 +++++++
include/linux/fcntl.h | 2 +-
include/uapi/asm-generic/fcntl.h | 4 ++++
8 files changed, 27 insertions(+), 3 deletions(-)
diff --git a/arch/alpha/include/uapi/asm/fcntl.h b/arch/alpha/include/uapi/asm/fcntl.h
index 50bdc8e8a271..391e0d112e41 100644
--- a/arch/alpha/include/uapi/asm/fcntl.h
+++ b/arch/alpha/include/uapi/asm/fcntl.h
@@ -34,6 +34,7 @@
#define O_PATH 040000000
#define __O_TMPFILE 0100000000
+#define O_ALLOW_ENCODED 0200000000
#define F_GETLK 7
#define F_SETLK 8
diff --git a/arch/parisc/include/uapi/asm/fcntl.h b/arch/parisc/include/uapi/asm/fcntl.h
index 03dee816cb13..72ea9bdf5f04 100644
--- a/arch/parisc/include/uapi/asm/fcntl.h
+++ b/arch/parisc/include/uapi/asm/fcntl.h
@@ -19,6 +19,7 @@
#define O_PATH 020000000
#define __O_TMPFILE 040000000
+#define O_ALLOW_ENCODED 100000000
#define F_GETLK64 8
#define F_SETLK64 9
diff --git a/arch/sparc/include/uapi/asm/fcntl.h b/arch/sparc/include/uapi/asm/fcntl.h
index 67dae75e5274..ac3e8c9cb32c 100644
--- a/arch/sparc/include/uapi/asm/fcntl.h
+++ b/arch/sparc/include/uapi/asm/fcntl.h
@@ -37,6 +37,7 @@
#define O_PATH 0x1000000
#define __O_TMPFILE 0x2000000
+#define O_ALLOW_ENCODED 0x8000000
#define F_GETOWN 5 /* for sockets. */
#define F_SETOWN 6 /* for sockets. */
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 19ac5baad50f..9302f68fe698 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_ALLOW_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_ALLOW_ENCODED can only be set by superuser */
+ if ((arg & O_ALLOW_ENCODED) && !(filp->f_flags & O_ALLOW_ENCODED) &&
+ !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
/* required for strict SunOS emulation */
if (O_NONBLOCK != O_NDELAY)
if (arg & O_NDELAY)
@@ -1033,7 +1039,7 @@ 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 d4a6dd772303..fbf64ce61088 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2890,6 +2890,10 @@ 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_ALLOW_ENCODED can only be set by superuser */
+ if ((flag & O_ALLOW_ENCODED) && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
return 0;
}
diff --git a/fs/open.c b/fs/open.c
index 9af548fb841b..f2863aaf78e7 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1040,6 +1040,13 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op)
acc_mode = 0;
}
+ /*
+ * O_ALLOW_ENCODED must be combined with O_CLOEXEC to avoid accidentally
+ * leaking encoded I/O privileges.
+ */
+ if ((how->flags & (O_ALLOW_ENCODED | O_CLOEXEC)) == O_ALLOW_ENCODED)
+ return -EINVAL;
+
/*
* O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
* check for O_DSYNC if the need any syncing at all we enforce it's
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index 921e750843e6..dc66c557b7d0 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -10,7 +10,7 @@
(O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \
O_APPEND | O_NDELAY | O_NONBLOCK | __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_ALLOW_ENCODED)
/* List of all valid flags for the how->upgrade_mask argument: */
#define VALID_UPGRADE_FLAGS \
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index 9dc0bf0c5a6e..75321c7a66ac 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -89,6 +89,10 @@
#define __O_TMPFILE 020000000
#endif
+#ifndef O_ALLOW_ENCODED
+#define O_ALLOW_ENCODED 040000000
+#endif
+
/* a horrid kludge trying to make sure that this will fail on old kernels */
#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)
--
2.29.2
next prev parent reply other threads:[~2020-11-18 19:18 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-18 19:18 [PATCH v6 00/11] fs: interface for directly reading/writing compressed data Omar Sandoval
2020-11-18 19:18 ` [PATCH man-pages v6] Document encoded I/O Omar Sandoval
2020-11-19 23:29 ` Alejandro Colomar (mailing lists; readonly)
2020-11-20 14:06 ` Alejandro Colomar (man-pages)
2020-11-20 15:03 ` Alejandro Colomar (man-pages)
2020-11-30 19:35 ` Omar Sandoval
2020-12-01 14:36 ` Ping: " Alejandro Colomar (man-pages)
2020-12-01 20:12 ` Michael Kerrisk (man-pages)
2020-12-01 20:20 ` Michael Kerrisk (man-pages)
2020-12-01 21:35 ` Alejandro Colomar (man-pages)
2020-12-01 21:56 ` Michael Kerrisk (man-pages)
2020-12-18 10:32 ` Ping: " Alejandro Colomar (man-pages)
2021-01-12 1:12 ` Omar Sandoval
2020-12-01 20:21 ` G. Branden Robinson
2020-12-01 21:34 ` Alejandro Colomar (man-pages)
2020-12-01 21:58 ` Michael Kerrisk (man-pages)
2020-11-18 19:18 ` [PATCH v6 01/11] iov_iter: add copy_struct_from_iter() Omar Sandoval
2020-11-18 19:18 ` Omar Sandoval [this message]
2020-11-19 7:02 ` [PATCH v6 02/11] fs: add O_ALLOW_ENCODED open flag Amir Goldstein
2020-11-20 23:41 ` Jann Horn
2020-11-30 19:26 ` Omar Sandoval
2020-12-01 8:15 ` Amir Goldstein
2020-12-01 20:31 ` Omar Sandoval
2020-11-18 19:18 ` [PATCH v6 03/11] fs: add RWF_ENCODED for reading/writing compressed data Omar Sandoval
2020-11-19 7:38 ` Amir Goldstein
2021-01-11 23:06 ` Omar Sandoval
2020-11-18 19:18 ` [PATCH v6 04/11] btrfs: fix btrfs_write_check() Omar Sandoval
2020-11-23 17:08 ` David Sterba
2020-11-30 19:18 ` Omar Sandoval
2020-11-18 19:18 ` [PATCH v6 05/11] btrfs: fix check_data_csum() error message for direct I/O Omar Sandoval
2020-11-23 17:09 ` David Sterba
2020-11-30 19:20 ` Omar Sandoval
2020-11-18 19:18 ` [PATCH v6 06/11] btrfs: don't advance offset for compressed bios in btrfs_csum_one_bio() Omar Sandoval
2020-11-18 19:18 ` [PATCH v6 07/11] btrfs: add ram_bytes and offset to btrfs_ordered_extent Omar Sandoval
2020-11-18 19:18 ` [PATCH v6 08/11] btrfs: support different disk extent size for delalloc Omar Sandoval
2020-11-18 19:18 ` [PATCH v6 09/11] btrfs: optionally extend i_size in cow_file_range_inline() Omar Sandoval
2020-11-18 19:18 ` [PATCH v6 10/11] btrfs: implement RWF_ENCODED reads Omar Sandoval
2020-12-03 14:32 ` Josef Bacik
2021-01-11 20:21 ` Omar Sandoval
2021-01-11 20:35 ` Josef Bacik
2021-01-11 20:58 ` Omar Sandoval
2020-11-18 19:18 ` [PATCH v6 11/11] btrfs: implement RWF_ENCODED writes Omar Sandoval
2020-12-02 22:03 ` Josef Bacik
2020-12-03 14:37 ` Josef Bacik
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=977fd16687d8b0474fd9c442f79c23f53783e403.1605723568.git.osandov@fb.com \
--to=osandov@osandov.com \
--cc=amir73il@gmail.com \
--cc=cyphar@cyphar.com \
--cc=david@fromorbit.com \
--cc=hch@infradead.org \
--cc=jannh@google.com \
--cc=kernel-team@fb.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=viro@zeniv.linux.org.uk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).