Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
In-Reply-To: <CA+55aFxMDAaQ-d3ktWCjcob8OQARcE=OWFXNJtQnW62rF-XY0g@mail.gmail.com>
References: <503224b776b9513885453756e44bab235221124e.1516644136.git.luto@kernel.org>
 <CA+55aFwcU_hHz+S9ZDphBDRQLw6pMsd+6Yp_=mQA8kTcmTzWcQ@mail.gmail.com>
 <CA+55aFyONQeyHit6LcQz_JM5+C9pr61fcWFSpdn=7K_2mZN+oA@mail.gmail.com> <CA+55aFxMDAaQ-d3ktWCjcob8OQARcE=OWFXNJtQnW62rF-XY0g@mail.gmail.com>
From:   Brian Gerst <brgerst@gmail.com>
Date:   Thu, 25 Jan 2018 15:04:27 -0500
Message-ID: <CAMzpN2h5_4yMQaKhvLw+eNuifVafpqRPcwzq81O4KvYGrcXFKg@mail.gmail.com>
Subject: Re: [PATCH] x86/retpoline/entry: Disable the entire SYSCALL64 fast
 path with retpolines on
To:     Linus Torvalds <torvalds@linux-foundation.org>
Cc:     Andy Lutomirski <luto@kernel.org>,
        "the arch/x86 maintainers" <x86@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Alan Cox <alan@linux.intel.com>, Jann Horn <jannh@google.com>,
        Samuel Neves <samuel.c.p.neves@gmail.com>,
        Dan Williams <dan.j.williams@intel.com>,
        Kernel Hardening <kernel-hardening@lists.openwall.com>,
        Borislav Petkov <bp@alien8.de>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

In Thu, Jan 25, 2018 at 2:16 PM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
> On Thu, Jan 25, 2018 at 10:48 AM, Linus Torvalds
> <torvalds@linux-foundation.org> wrote:
>>
>> So the biggest impact of this is the extra register saves
>
> Actually, the other noticeable part is the reloading of the argument
> registers from ptregs. Together with just the extra level of
> 'call/ret' and the stack setup, I'm guessing we're talking maybe 20
> cycles or so.
>
> So there's the extra register saves, and simply the fact that the
> fastpath had a flatter calling structure.
>
> It still feels worth it. And if we do decide that we want to do the
> register clearing on kernel entry for some paranoid mode, we'd pretty
> much have to do this anyway.
>
>                  Linus

Another extra step the slow path does is checking to see if ptregs is
safe for SYSRET.  I think that can be mitigated by moving the check to
the places that do modify ptregs (ptrace, sigreturn, and exec) which
would set a flag to force return with IRET if the modified regs do not
satisfy the criteria for SYSRET.

--
Brian Gerst