Re: [PATCH v2] x86/paravirt: Don't make vcpu_is_preempted() a callee-save function

[Peter Zijlstra]

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.
  */