[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Thu, 3 Sep 2020 14:45:54 -0700
From: Kees Cook <keescook@...omium.org>
To: Sami Tolvanen <samitolvanen@...gle.com>
Cc: Masahiro Yamada <masahiroy@...nel.org>, Will Deacon <will@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
Steven Rostedt <rostedt@...dmis.org>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
"Paul E. McKenney" <paulmck@...nel.org>,
Nick Desaulniers <ndesaulniers@...gle.com>,
clang-built-linux@...glegroups.com,
kernel-hardening@...ts.openwall.com, linux-arch@...r.kernel.org,
linux-arm-kernel@...ts.infradead.org, linux-kbuild@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-pci@...r.kernel.org,
x86@...nel.org, Arvind Sankar <nivedita@...m.mit.edu>
Subject: Re: [PATCH v2 02/28] x86/asm: Replace __force_order with memory
clobber
On Thu, Sep 03, 2020 at 01:30:27PM -0700, Sami Tolvanen wrote:
> From: Arvind Sankar <nivedita@...m.mit.edu>
>
> 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.
>
> Signed-off-by: Arvind Sankar <nivedita@...m.mit.edu>
In the primary thread for this patch I sent a Reviewed tag, but for good
measure, here it is again:
Reviewed-by: Kees Cook <keescook@...omium.org>
--
Kees Cook
Powered by blists - more mailing lists
Confused about mailing lists and their use?
Read about mailing lists on Wikipedia
and check out these
guidelines on proper formatting of your messages.
