MIME-Version: 1.0
In-Reply-To: <CAK1hOcOZiLSG00uoAm_z0qxefLWiqD_WCsAWmtLB1VSvzPz-jg@mail.gmail.com>
References: <5d120f358612d73fc909f5bfa47e7bd082db0af0.1429841474.git.luto@kernel.org>
 <CALCETrU1X4=GHmCcBfoHYDqUKAB-ybhgYpEHEGQVK+0_wwCJBA@mail.gmail.com>
 <CAK1hOcP0_cMbrhYnwapQE5wK5NTJUXbK64rq7xkSq-HEBXmdDQ@mail.gmail.com>
 <CALCETrVjcw9TAKm+GGzJtzUUPpovJYZMn4vXc=cYG+s5B57h5Q@mail.gmail.com> <CAK1hOcOZiLSG00uoAm_z0qxefLWiqD_WCsAWmtLB1VSvzPz-jg@mail.gmail.com>
From: Andy Lutomirski <luto@amacapital.net>
Date: Sun, 26 Apr 2015 16:36:37 -0700
Message-ID: <CALCETrWsACBdKsZBx29M7O8BGvOhSs=VfNUD3bWDhjR7kY5_hA@mail.gmail.com>
Subject: Re: [PATCH] x86_64, asm: Work around AMD SYSRET SS descriptor
 attribute issue
To: Denys Vlasenko <vda.linux@googlemail.com>
Cc: Andy Lutomirski <luto@kernel.org>, X86 ML <x86@kernel.org>,
        "H. Peter Anvin" <hpa@zytor.com>, Borislav Petkov <bp@alien8.de>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Brian Gerst <brgerst@gmail.com>, Denys Vlasenko <dvlasenk@redhat.com>,
        Ingo Molnar <mingo@kernel.org>, Steven Rostedt <rostedt@goodmis.org>,
        Oleg Nesterov <oleg@redhat.com>,
        Frederic Weisbecker <fweisbec@gmail.com>,
        Alexei Starovoitov <ast@plumgrid.com>, Will Drewry <wad@chromium.org>,
        Kees Cook <keescook@chromium.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset=UTF-8
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1450
Lines: 36

On Fri, Apr 24, 2015 at 7:17 PM, Denys Vlasenko
<vda.linux@googlemail.com> wrote:
> On Fri, Apr 24, 2015 at 10:50 PM, Andy Lutomirski <luto@amacapital.net> wrote:
>> On Fri, Apr 24, 2015 at 1:46 PM, Denys Vlasenko
>>>> This might be way more trouble than it's worth.
>>>
>>> Exactly my feeling. What are you trying to save? About four CPU
>>> cycles of checking %ss != __KERNEL_DS on each switch_to?
>>> That's not worth bothering about. Your last patch seems to be perfect.
>>
>> We'll have to do the write to ss almost every time an AMD CPU sleeps
>> in a syscall.
>
> Why do you think so?
> Scheduling from a syscall which decided to block won't require
> writing to %ss, since in this case %ss isn't NULL.
>
> Writing to %ss will happen every time we schedule from an interrupt.
> With timer interrupt every 1 ms it means scheduling at most ~1000
> times per second, if _every_ such interrupt causes task switch.
> This is still not often enough to worry.

OK, you've convinced me.  I still think it can happen much more than
~1k times per second due to hrtimers (see my test case) or things like
page faults, but those are all slow paths.

v2 coming.

-- 
Andy Lutomirski
AMA Capital Management, LLC
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/