3.16.57-rc1 review patch. If anyone has any objections, please let me know. ------------------ From: Paolo Bonzini <pbonzini@xxxxxxxxxx> commit 946fbbc13dce68902f64515b610eeb2a6c3d7a64 upstream. vmx_vcpu_run() and svm_vcpu_run() are large functions, and giving branch hints to the compiler can actually make a substantial cycle difference by keeping the fast path contiguous in memory. With this optimization, the retpoline-guest/retpoline-host case is about 50 cycles faster. Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx> Reviewed-by: Jim Mattson <jmattson@xxxxxxxxxx> Cc: David Woodhouse <dwmw@xxxxxxxxxxxx> Cc: KarimAllah Ahmed <karahmed@xxxxxxxxx> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: Radim Krčmář <rkrcmar@xxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: kvm@xxxxxxxxxxxxxxx Link: http://lkml.kernel.org/r/20180222154318.20361-3-pbonzini@xxxxxxxxxx Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx> [bwh: Backported to 3.16: adjust context] Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx> --- arch/x86/kvm/svm.c | 2 +- arch/x86/kvm/vmx.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -4077,7 +4077,7 @@ static void svm_vcpu_run(struct kvm_vcpu * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (svm->spec_ctrl) --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -7673,7 +7673,7 @@ static void __noclone vmx_vcpu_run(struc * If the L01 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (!msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL)) + if (unlikely(!msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL))) vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (vmx->spec_ctrl)
