From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1753488AbdBJQUk (ORCPT <rfc822;w@1wt.eu>);
        Fri, 10 Feb 2017 11:20:40 -0500
Received: from bombadil.infradead.org ([65.50.211.133]:36221 "EHLO
        bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1751767AbdBJQUf (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Fri, 10 Feb 2017 11:20:35 -0500
Date: Fri, 10 Feb 2017 17:19:28 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Waiman Long <longman@redhat.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>,
        Chris Wright <chrisw@sous-sol.org>, Alok Kataria <akataria@vmware.com>,
        Rusty Russell <rusty@rustcorp.com.au>, Ingo Molnar <mingo@redhat.com>,
        Thomas Gleixner <tglx@linutronix.de>, "H. Peter Anvin" <hpa@zytor.com>,
        linux-arch@vger.kernel.org, x86@kernel.org,
        linux-kernel@vger.kernel.org,
        virtualization@lists.linux-foundation.org,
        xen-devel@lists.xenproject.org, kvm@vger.kernel.org,
        Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Radim =?utf-8?B?S3LEjW3DocWZ?= <rkrcmar@redhat.com>,
        Boris Ostrovsky <boris.ostrovsky@oracle.com>,
        Juergen Gross <jgross@suse.com>
Subject: Re: [PATCH v2] x86/paravirt: Don't make vcpu_is_preempted() a
 callee-save function
Message-ID: <20170210161928.GI6515@twins.programming.kicks-ass.net>
References: <1486741389-8513-1-git-send-email-longman@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1486741389-8513-1-git-send-email-longman@redhat.com>
User-Agent: Mutt/1.5.23.1 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Fri, Feb 10, 2017 at 10:43:09AM -0500, Waiman Long wrote:
> It was found when running fio sequential write test with a XFS ramdisk
> on a VM running on a 2-socket x86-64 system, the %CPU times as reported
> by perf were as follows:
> 
>  69.75%  0.59%  fio  [k] down_write
>  69.15%  0.01%  fio  [k] call_rwsem_down_write_failed
>  67.12%  1.12%  fio  [k] rwsem_down_write_failed
>  63.48% 52.77%  fio  [k] osq_lock
>   9.46%  7.88%  fio  [k] __raw_callee_save___kvm_vcpu_is_preempt
>   3.93%  3.93%  fio  [k] __kvm_vcpu_is_preempted
> 

Thinking about this again, wouldn't something like the below also work?


diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 099fcba4981d..6aa33702c15c 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -589,6 +589,7 @@ static void kvm_wait(u8 *ptr, u8 val)
 	local_irq_restore(flags);
 }
 
+#ifdef CONFIG_X86_32
 __visible bool __kvm_vcpu_is_preempted(int cpu)
 {
 	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
@@ -597,6 +598,31 @@ __visible bool __kvm_vcpu_is_preempted(int cpu)
 }
 PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
 
+#else
+
+extern bool __raw_callee_save___kvm_vcpu_is_preempted(int);
+
+asm(
+".pushsection .text;"
+".global __raw_callee_save___kvm_vcpu_is_preempted;"
+".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
+"__raw_callee_save___kvm_vcpu_is_preempted:"
+FRAME_BEGIN
+"push %rdi;"
+"push %rdx;"
+"movslq  %edi, %rdi;"
+"movq    $steal_time+16, %rax;"
+"movq    __per_cpu_offset(,%rdi,8), %rdx;"
+"cmpb    $0, (%rdx,%rax);"
+"setne   %al;"
+"pop %rdx;"
+"pop %rdi;"
+FRAME_END
+"ret;"
+".popsection");
+
+#endif
+
 /*
  * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
  */