From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932415AbeCLODP (ORCPT ); Mon, 12 Mar 2018 10:03:15 -0400 Received: from mx3-rdu2.redhat.com ([66.187.233.73]:37056 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S932332AbeCLODI (ORCPT ); Mon, 12 Mar 2018 10:03:08 -0400 From: Vitaly Kuznetsov To: kvm@vger.kernel.org, x86@kernel.org Cc: linux-kernel@vger.kernel.org, Paolo Bonzini , =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= , Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , Andy Lutomirski Subject: [PATCH 3/3] x86/kvm/vmx: avoid expensive rdmsr for MSR_GS_BASE Date: Mon, 12 Mar 2018 15:03:00 +0100 Message-Id: <20180312140300.6166-4-vkuznets@redhat.com> In-Reply-To: <20180312140300.6166-1-vkuznets@redhat.com> References: <20180312140300.6166-1-vkuznets@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org vmx_save_host_state() is only called from kvm_arch_vcpu_ioctl_run() so the context is pretty well defined and as we're past 'swapgs' MSR_GS_BASE should contain kernel's GS base which we point to irq_stack_union. Add new kernelmode_gs_base() API, irq_stack_union needs to be exported as KVM can be build as module. Signed-off-by: Vitaly Kuznetsov --- arch/x86/include/asm/processor.h | 5 +++++ arch/x86/kernel/cpu/common.c | 3 ++- arch/x86/kvm/vmx.c | 3 ++- 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 006352b85ba3..ab3d3e426a41 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -407,6 +407,11 @@ union irq_stack_union { DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible; DECLARE_INIT_PER_CPU(irq_stack_union); +static inline unsigned long cpu_kernelmode_gs_base(int cpu) +{ + return (unsigned long)per_cpu(irq_stack_union.gs_base, cpu); +} + DECLARE_PER_CPU(char *, irq_stack_ptr); DECLARE_PER_CPU(unsigned int, irq_count); extern asmlinkage void ignore_sysret(void); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 348cf4821240..4702fbd98f92 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -487,7 +487,7 @@ void load_percpu_segment(int cpu) loadsegment(fs, __KERNEL_PERCPU); #else __loadsegment_simple(gs, 0); - wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu)); + wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu)); #endif load_stack_canary_segment(); } @@ -1398,6 +1398,7 @@ __setup("clearcpuid=", setup_clearcpuid); #ifdef CONFIG_X86_64 DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE) __visible; +EXPORT_PER_CPU_SYMBOL_GPL(irq_stack_union); /* * The following percpu variables are hot. Align current_task to diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index d4d9bb2fd91e..36cb14a121ca 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2123,6 +2123,7 @@ static unsigned long segment_base(u16 selector) static void vmx_save_host_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + int cpu = raw_smp_processor_id(); int i; if (vmx->host_state.loaded) @@ -2160,7 +2161,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) /* Synchronize FS and GS bases to current->thread first */ save_current_fsgs(); vmcs_writel(HOST_FS_BASE, current->thread.fsbase); - vmcs_writel(HOST_GS_BASE, read_msr(MSR_GS_BASE)); + vmcs_writel(HOST_GS_BASE, cpu_kernelmode_gs_base(cpu)); #else vmcs_writel(HOST_FS_BASE, segment_base(vmx->host_state.fs_sel)); vmcs_writel(HOST_GS_BASE, segment_base(vmx->host_state.gs_sel)); -- 2.14.3