[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20201103131328.GC5219@willie-the-truck>
Date: Tue, 3 Nov 2020 13:13:29 +0000
From: Will Deacon <will@...nel.org>
To: Mark Rutland <mark.rutland@....com>
Cc: linux-arm-kernel@...ts.infradead.org,
Kees Cook <keescook@...omium.org>,
Catalin Marinas <catalin.marinas@....com>,
Sami Tolvanen <samitolvanen@...gle.com>,
Masahiro Yamada <masahiroy@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v4 4/4] arm64: lto: Strengthen READ_ONCE() to acquire
when CONFIG_LTO=y
On Tue, Nov 03, 2020 at 12:58:45PM +0000, Mark Rutland wrote:
> On Tue, Nov 03, 2020 at 12:17:21PM +0000, Will Deacon wrote:
> > When building with LTO, there is an increased risk of the compiler
> > converting an address dependency headed by a READ_ONCE() invocation
> > into a control dependency and consequently allowing for harmful
> > reordering by the CPU.
> >
> > Ensure that such transformations are harmless by overriding the generic
> > READ_ONCE() definition with one that provides acquire semantics when
> > building with LTO.
> >
> > Acked-by: Peter Zijlstra (Intel) <peterz@...radead.org>
> > Signed-off-by: Will Deacon <will@...nel.org>
>
> [...]
>
> Could we add a note above __READ_ONCE() along the lines of the commit
> message, e.g.
>
> /*
> * With LTO a compiler might convert an address dependency headed by a
> * READ_ONCE() into a control dependency, allowing for harmful
> * reordering by the CPU.
> *
> * To prevent this, upgrade READ_OONCE() to provide acquire semantics
> * when building with LTO.
It's not halloween any moooore :)
But yes, I'll add something to that effect, cheers.
Will
Powered by blists - more mailing lists