Subject: Re: [PATCH V4 11/11] KVM: x86: Implement Intel Processor Trace
 context switch
To: Luwei Kang <luwei.kang@intel.com>, kvm@vger.kernel.org
Cc: tglx@linutronix.de, mingo@redhat.com, hpa@zytor.com, x86@kernel.org,
        rkrcmar@redhat.com, linux-kernel@vger.kernel.org, joro@8bytes.org,
        Chao Peng <chao.p.peng@linux.intel.com>
References: <1512937857-10477-1-git-send-email-luwei.kang@intel.com>
 <1512937857-10477-12-git-send-email-luwei.kang@intel.com>
From: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <67f18e8e-0adb-afa6-60bf-67e3298fdebd@redhat.com>
Date: Tue, 12 Dec 2017 18:06:11 +0100
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101
 Thunderbird/52.5.0
MIME-Version: 1.0
In-Reply-To: <1512937857-10477-12-git-send-email-luwei.kang@intel.com>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 3841
Lines: 116

On 10/12/2017 21:30, Luwei Kang wrote:
> From: Chao Peng <chao.p.peng@linux.intel.com>
> 
> Load/Store Intel processor trace register in context switch.
> MSR IA32_RTIT_CTL is loaded/stored automatically from VMCS.
> In HOST mode, we just need to restore the status of IA32_RTIT_CTL.
> In HOST_GUEST mode, we need load/resore PT MSRs only when PT is
> enabled in guest.
> 
> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
> Signed-off-by: Luwei Kang <luwei.kang@intel.com>
> ---
>  arch/x86/kvm/vmx.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 61 insertions(+)
> 
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index f948231..d45cc76 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -2144,6 +2144,55 @@ static unsigned long segment_base(u16 selector)
>  }
>  #endif
>  
> +static inline void pt_load_msr(struct pt_ctx *ctx, unsigned int addr_num)
> +{
> +	u32 i;
> +
> +	wrmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
> +	wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
> +	wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
> +	wrmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
> +	for (i = 0; i < addr_num; i++)
> +		wrmsrl(MSR_IA32_RTIT_ADDR0_A + i, ctx->addrs[i]);
> +}
> +
> +static inline void pt_save_msr(struct pt_ctx *ctx, unsigned int addr_num)
> +{
> +	u32 i;
> +
> +	rdmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
> +	rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
> +	rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
> +	rdmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
> +	for (i = 0; i < addr_num; i++)
> +		rdmsrl(MSR_IA32_RTIT_ADDR0_A + i, ctx->addrs[i]);
> +}
> +
> +static void pt_guest_enter(struct vcpu_vmx *vmx)
> +{
> +	if (pt_mode == PT_MODE_HOST || PT_MODE_HOST_GUEST)

Small mistake here (missing "pt_mode == ").

Thanks,

Paolo

> +		rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
> +
> +	if (pt_mode == PT_MODE_HOST_GUEST &&
> +		vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
> +		wrmsrl(MSR_IA32_RTIT_CTL, 0);
> +		pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_num);
> +		pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_num);
> +	}
> +}
> +
> +static void pt_guest_exit(struct vcpu_vmx *vmx)
> +{
> +	if (pt_mode == PT_MODE_HOST_GUEST &&
> +		vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
> +		pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_num);
> +		pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_num);
> +	}
> +
> +	if (pt_mode == PT_MODE_HOST || pt_mode == PT_MODE_HOST_GUEST)
> +		wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
> +}
> +
>  static void vmx_save_host_state(struct kvm_vcpu *vcpu)
>  {
>  	struct vcpu_vmx *vmx = to_vmx(vcpu);
> @@ -5766,6 +5815,14 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
>  		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
>  		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
>  	}
> +
> +	if (pt_mode == PT_MODE_HOST_GUEST) {
> +		memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc));
> +		vmx->pt_desc.addr_num = kvm_get_pt_addr_cnt();
> +		/* Bit[6~0] are forced to 1, writes are ignored. */
> +		vmx->pt_desc.guest.output_mask = 0x7F;
> +		vmcs_write64(GUEST_IA32_RTIT_CTL, 0);
> +	}
>  }
>  
>  static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
> @@ -9589,6 +9646,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
>  	    vcpu->arch.pkru != vmx->host_pkru)
>  		__write_pkru(vcpu->arch.pkru);
>  
> +	pt_guest_enter(vmx);
> +
>  	atomic_switch_perf_msrs(vmx);
>  	debugctlmsr = get_debugctlmsr();
>  
> @@ -9724,6 +9783,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
>  				  | (1 << VCPU_EXREG_CR3));
>  	vcpu->arch.regs_dirty = 0;
>  
> +	pt_guest_exit(vmx);
> +
>  	/*
>  	 * eager fpu is enabled if PKEY is supported and CR4 is switched
>  	 * back on host, so it is safe to read guest PKRU from current
>