From: Kees Cook <keescook@chromium.org>
To: Arvind Sankar <nivedita@alum.mit.edu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>,
Sedat Dilek <sedat.dilek@gmail.com>,
Segher Boessenkool <segher@kernel.crashing.org>,
Thomas Gleixner <tglx@linutronix.de>,
Nick Desaulniers <ndesaulniers@google.com>,
"Paul E. McKenney" <paulmck@kernel.org>,
Ingo Molnar <mingo@redhat.com>, Arnd Bergmann <arnd@arndb.de>,
Borislav Petkov <bp@alien8.de>,
"maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)"
<x86@kernel.org>, "H. Peter Anvin" <hpa@zytor.com>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Peter Zijlstra <peterz@infradead.org>,
Juergen Gross <jgross@suse.com>,
Andy Lutomirski <luto@kernel.org>,
Andrew Cooper <andrew.cooper3@citrix.com>,
LKML <linux-kernel@vger.kernel.org>,
clang-built-linux <clang-built-linux@googlegroups.com>,
Will Deacon <will@kernel.org>,
nadav.amit@gmail.com,
Nathan Chancellor <natechancellor@gmail.com>
Subject: Re: [PATCH v3] x86/asm: Replace __force_order with memory clobber
Date: Wed, 2 Sep 2020 19:17:30 -0700 [thread overview]
Message-ID: <202009021916.CD41C28A52@keescook> (raw)
In-Reply-To: <20200902232152.3709896-1-nivedita@alum.mit.edu>
On Wed, Sep 02, 2020 at 07:21:52PM -0400, Arvind Sankar wrote:
> The CRn accessor functions use __force_order as a dummy operand to
> prevent the compiler from reordering CRn reads/writes with respect to
> each other.
>
> The fact that the asm is volatile should be enough to prevent this:
> volatile asm statements should be executed in program order. However GCC
> 4.9.x and 5.x have a bug that might result in reordering. This was fixed
> in 8.1, 7.3 and 6.5. Versions prior to these, including 5.x and 4.9.x,
> may reorder volatile asm statements with respect to each other.
>
> There are some issues with __force_order as implemented:
> - It is used only as an input operand for the write functions, and hence
> doesn't do anything additional to prevent reordering writes.
> - It allows memory accesses to be cached/reordered across write
> functions, but CRn writes affect the semantics of memory accesses, so
> this could be dangerous.
> - __force_order is not actually defined in the kernel proper, but the
> LLVM toolchain can in some cases require a definition: LLVM (as well
> as GCC 4.9) requires it for PIE code, which is why the compressed
> kernel has a definition, but also the clang integrated assembler may
> consider the address of __force_order to be significant, resulting in
> a reference that requires a definition.
>
> Fix this by:
> - Using a memory clobber for the write functions to additionally prevent
> caching/reordering memory accesses across CRn writes.
> - Using a dummy input operand with an arbitrary constant address for the
> read functions, instead of a global variable. This will prevent reads
> from being reordered across writes, while allowing memory loads to be
> cached/reordered across CRn reads, which should be safe.
>
> Tested-by: Nathan Chancellor <natechancellor@gmail.com>
> Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
> Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Seems reasonable to me. As reasonable as compiler bug workarounds
go, that is. ;)
Reviewed-by: Kees Cook <keescook@chromium.org>
--
Kees Cook
next prev parent reply other threads:[~2020-09-03 2:17 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-27 13:53 [PATCH] x86: work around clang IAS bug referencing __force_order Arnd Bergmann
2020-08-01 11:50 ` Sedat Dilek
2020-08-06 22:13 ` Thomas Gleixner
2020-08-07 7:03 ` Sedat Dilek
2020-08-04 0:09 ` Nick Desaulniers
2020-08-14 17:29 ` Sedat Dilek
2020-08-14 21:19 ` Sedat Dilek
2020-08-14 22:57 ` Nick Desaulniers
2020-08-15 0:26 ` Nick Desaulniers
2020-08-15 3:28 ` Sedat Dilek
2020-08-15 8:23 ` Sedat Dilek
2020-08-15 10:46 ` Sedat Dilek
2020-08-15 14:39 ` Sedat Dilek
2020-08-16 9:37 ` Sedat Dilek
2020-08-06 22:11 ` Thomas Gleixner
2020-08-13 0:12 ` Nick Desaulniers
2020-08-13 8:49 ` David Laight
2020-08-13 17:20 ` Arvind Sankar
2020-08-13 17:28 ` Thomas Gleixner
2020-08-13 17:37 ` Paul E. McKenney
2020-08-13 18:09 ` Arvind Sankar
2020-08-13 18:20 ` Paul E. McKenney
2020-08-20 10:44 ` Thomas Gleixner
2020-08-20 13:06 ` Arvind Sankar
2020-08-21 0:37 ` Thomas Gleixner
2020-08-21 23:04 ` Arvind Sankar
2020-08-21 23:16 ` Nick Desaulniers
2020-08-21 23:25 ` Arvind Sankar
2020-08-22 0:43 ` Thomas Gleixner
2020-08-22 3:55 ` Arvind Sankar
2020-08-22 8:41 ` Segher Boessenkool
2020-08-22 9:23 ` Sedat Dilek
2020-08-22 9:51 ` Sedat Dilek
2020-08-22 10:26 ` Segher Boessenkool
2020-08-22 10:35 ` Arnd Bergmann
2020-08-22 18:17 ` Miguel Ojeda
2020-08-22 21:08 ` Linus Torvalds
2020-08-22 23:10 ` Arvind Sankar
2020-08-23 0:10 ` Linus Torvalds
2020-08-23 1:16 ` Arvind Sankar
2020-08-23 21:25 ` [PATCH] x86/asm: Replace __force_order with memory clobber Arvind Sankar
2020-08-24 17:50 ` Nathan Chancellor
2020-08-24 19:13 ` Miguel Ojeda
2020-08-25 15:19 ` Arvind Sankar
2020-08-25 15:21 ` Sedat Dilek
2020-09-02 15:33 ` [PATCH v2] " Arvind Sankar
2020-09-02 15:58 ` David Laight
2020-09-02 16:14 ` Arvind Sankar
2020-09-02 16:08 ` Arvind Sankar
2020-09-02 20:26 ` David Laight
2020-09-02 17:16 ` Segher Boessenkool
2020-09-02 17:36 ` Arvind Sankar
2020-09-02 18:19 ` Miguel Ojeda
2020-09-02 18:24 ` Arvind Sankar
2020-09-02 23:21 ` [PATCH v3] " Arvind Sankar
2020-09-03 2:17 ` Kees Cook [this message]
2020-09-03 5:34 ` Miguel Ojeda
2020-09-30 20:50 ` Kees Cook
2020-10-01 10:12 ` [tip: x86/asm] x86/asm: Replace __force_order with a " tip-bot2 for Arvind Sankar
2020-10-13 9:30 ` tip-bot2 for Arvind Sankar
2020-08-22 21:17 ` [PATCH] x86: work around clang IAS bug referencing __force_order Arvind Sankar
2020-08-23 13:31 ` David Laight
2020-09-08 22:25 ` Pavel Machek
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=202009021916.CD41C28A52@keescook \
--to=keescook@chromium.org \
--cc=andrew.cooper3@citrix.com \
--cc=arnd@arndb.de \
--cc=bp@alien8.de \
--cc=clang-built-linux@googlegroups.com \
--cc=hpa@zytor.com \
--cc=jgross@suse.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=miguel.ojeda.sandonis@gmail.com \
--cc=mingo@redhat.com \
--cc=nadav.amit@gmail.com \
--cc=natechancellor@gmail.com \
--cc=ndesaulniers@google.com \
--cc=nivedita@alum.mit.edu \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=sedat.dilek@gmail.com \
--cc=segher@kernel.crashing.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=will@kernel.org \
--cc=x86@kernel.org \
/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).