From: Nadav Har'El Date: Mon, 5 Aug 2013 08:07:06 +0000 (+0300) Subject: nEPT: Support LOAD_IA32_EFER entry/exit controls for L1 X-Git-Url: http://git.cdn.openwrt.org/?a=commitdiff_plain;h=8049d651e8789b15baaf2a8b888d8919df1152a9;p=openwrt%2Fstaging%2Fblogic.git nEPT: Support LOAD_IA32_EFER entry/exit controls for L1 Recent KVM, since http://kerneltrap.org/mailarchive/linux-kvm/2010/5/2/6261577 switch the EFER MSR when EPT is used and the host and guest have different NX bits. So if we add support for nested EPT (L1 guest using EPT to run L2) and want to be able to run recent KVM as L1, we need to allow L1 to use this EFER switching feature. To do this EFER switching, KVM uses VM_ENTRY/EXIT_LOAD_IA32_EFER if available, and if it isn't, it uses the generic VM_ENTRY/EXIT_MSR_LOAD. This patch adds support for the former (the latter is still unsupported). Nested entry and exit emulation (prepare_vmcs_02 and load_vmcs12_host_state, respectively) already handled VM_ENTRY/EXIT_LOAD_IA32_EFER correctly. So all that's left to do in this patch is to properly advertise this feature to L1. Note that vmcs12's VM_ENTRY/EXIT_LOAD_IA32_EFER are emulated by L0, by using vmx_set_efer (which itself sets one of several vmcs02 fields), so we always support this feature, regardless of whether the host supports it. Reviewed-by: Orit Wasserman Signed-off-by: Nadav Har'El Signed-off-by: Jun Nakajima Signed-off-by: Xinhao Xu Signed-off-by: Yang Zhang Signed-off-by: Gleb Natapov Signed-off-by: Paolo Bonzini --- diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 30974c3efa45..25a650638305 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2198,7 +2198,8 @@ static __init void nested_vmx_setup_ctls_msrs(void) #else nested_vmx_exit_ctls_high = 0; #endif - nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; + nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | + VM_EXIT_LOAD_IA32_EFER); /* entry controls */ rdmsr(MSR_IA32_VMX_ENTRY_CTLS, @@ -2207,8 +2208,8 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; nested_vmx_entry_ctls_high &= VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_IA32E_MODE; - nested_vmx_entry_ctls_high |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; - + nested_vmx_entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | + VM_ENTRY_LOAD_IA32_EFER); /* cpu-based controls */ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high); @@ -7529,10 +7530,18 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask; vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); - /* Note: IA32_MODE, LOAD_IA32_EFER are modified by vmx_set_efer below */ - vmcs_write32(VM_EXIT_CONTROLS, - vmcs12->vm_exit_controls | vmcs_config.vmexit_ctrl); - vmcs_write32(VM_ENTRY_CONTROLS, vmcs12->vm_entry_controls | + /* L2->L1 exit controls are emulated - the hardware exit is to L0 so + * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER + * bits are further modified by vmx_set_efer() below. + */ + vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl); + + /* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are + * emulated by vmx_set_efer(), below. + */ + vmcs_write32(VM_ENTRY_CONTROLS, + (vmcs12->vm_entry_controls & ~VM_ENTRY_LOAD_IA32_EFER & + ~VM_ENTRY_IA32E_MODE) | (vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE)); if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)