[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Thu, 1 Jan 2015 22:23:42 +0100
From: Ingo Molnar <mingo@...nel.org>
To: Andy Lutomirski <luto@...capital.net>
Cc: Ingo Molnar <mingo@...hat.com>, X86 ML <x86@...nel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
Paolo Bonzini <pbonzini@...hat.com>,
Marcelo Tosatti <mtosatti@...hat.com>,
Linus Torvalds <torvalds@...ux-foundation.org>
Subject: Re: [GIT PULL] One more vdso fix for 3.19
* Andy Lutomirski <luto@...capital.net> wrote:
> Hi Ingo et al,
>
> Please consider pulling for x86/urgent.
>
> Thanks,
> Andy
>
>
> The following changes since commit 394f56fe480140877304d342dec46d50dc823d46:
>
> x86_64, vdso: Fix the vdso address randomization algorithm
> (2014-12-20 16:56:57 -0800)
>
> are available in the git repository at:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/luto/linux.git
> tags/pr-20141223-x86-vdso
>
> for you to fetch changes up to 1ddf0b1b11aa8a90cef6706e935fc31c75c406ba:
>
> x86, vdso: Use asm volatile in __getcpu (2014-12-23 13:05:30 -0800)
>
> ----------------------------------------------------------------
> This is hopefully the last vdso fix for 3.19. It should be very
> safe (it just adds a volatile).
>
> I don't think it fixes an actual bug (the __getcpu calls in the
> pvclock code may not have been needed in the first place), but
> discussion on that point is ongoing.
>
> It also fixes a big performance issue in 3.18 and earlier in which
> the lsl instructions in vclock_gettime got hoisted so far up the
> function that they happened even when the function they were in was
> never called. n 3.19, the performance issue seems to be gone due to
> the whims of my compiler and some interaction with a branch that's
> now gone.
>
> I'll hopefully have a much bigger overhaul of the pvclock code
> for 3.20, but it needs careful review.
>
> ----------------------------------------------------------------
> Andy Lutomirski (1):
> x86, vdso: Use asm volatile in __getcpu
>
> arch/x86/include/asm/vgtod.h | 6 ++++--
> 1 file changed, 4 insertions(+), 2 deletions(-)
Pulled into tip:x86/urgent, thanks Andy!
I've attached the full commit below - I'm not sure it was sent to
lkml.
Thanks,
Ingo
====================>
>From 1ddf0b1b11aa8a90cef6706e935fc31c75c406ba Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@...capital.net>
Date: Sun, 21 Dec 2014 08:57:46 -0800
Subject: [PATCH] x86, vdso: Use asm volatile in __getcpu
In Linux 3.18 and below, GCC hoists the lsl instructions in the
pvclock code all the way to the beginning of __vdso_clock_gettime,
slowing the non-paravirt case significantly. For unknown reasons,
presumably related to the removal of a branch, the performance issue
is gone as of
e76b027e6408 x86,vdso: Use LSL unconditionally for vgetcpu
but I don't trust GCC enough to expect the problem to stay fixed.
There should be no correctness issue, because the __getcpu calls in
__vdso_vlock_gettime were never necessary in the first place.
Note to stable maintainers: In 3.18 and below, depending on
configuration, gcc 4.9.2 generates code like this:
9c3: 44 0f 03 e8 lsl %ax,%r13d
9c7: 45 89 eb mov %r13d,%r11d
9ca: 0f 03 d8 lsl %ax,%ebx
This patch won't apply as is to any released kernel, but I'll send a
trivial backported version if needed.
Fixes: 51c19b4f5927 x86: vdso: pvclock gettime support
Cc: stable@...r.kernel.org # 3.8+
Cc: Marcelo Tosatti <mtosatti@...hat.com>
Acked-by: Paolo Bonzini <pbonzini@...hat.com>
Signed-off-by: Andy Lutomirski <luto@...capital.net>
---
arch/x86/include/asm/vgtod.h | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index e7e9682a33e9..f556c4843aa1 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -80,9 +80,11 @@ static inline unsigned int __getcpu(void)
/*
* Load per CPU data from GDT. LSL is faster than RDTSCP and
- * works on all CPUs.
+ * works on all CPUs. This is volatile so that it orders
+ * correctly wrt barrier() and to keep gcc from cleverly
+ * hoisting it out of the calling function.
*/
- asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+ asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
return p;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists