diff mbox

[v3,01/13] nEPT: Support LOAD_IA32_EFER entry/exit controls for L1

Message ID 1368060805-2790-1-git-send-email-jun.nakajima@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Nakajima, Jun May 9, 2013, 12:53 a.m. UTC
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.

Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Jun Nakajima <jun.nakajima@intel.com>
Signed-off-by: Xinhao Xu <xinhao.xu@intel.com>
---
 arch/x86/kvm/vmx.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

Comments

Gleb Natapov May 13, 2013, 12:25 p.m. UTC | #1
Please use --no-chain-reply-to option to "git send-email" for nicer
email threading and there is something wrong with Signed-off chain for
the patches. The first Signed-off-by: is by Nadav, but you appears to be
the author of the patches for git. AFAIK Nadav is the author, so you
need to add proper From: in your patch submission. If you'll fix the
authorship in your git "git format-patch" will do it for you. 

On Wed, May 08, 2013 at 05:53:13PM -0700, Jun Nakajima wrote:
> 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.
> 
> Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
> Signed-off-by: Jun Nakajima <jun.nakajima@intel.com>
> Signed-off-by: Xinhao Xu <xinhao.xu@intel.com>
> ---
>  arch/x86/kvm/vmx.c | 23 ++++++++++++++++-------
>  1 file changed, 16 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index e53a5f7..51b8b4f0 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -2192,7 +2192,8 @@ 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,
> @@ -2201,8 +2202,8 @@ 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);
> @@ -7486,10 +7487,18 @@ 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 IA32_MODE, 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)
> -- 
> 1.8.1.2
> 
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

--
			Gleb.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Nakajima, Jun May 19, 2013, 4:57 a.m. UTC | #2
On Mon, May 13, 2013 at 5:25 AM, Gleb Natapov <gleb@redhat.com> wrote:
> Please use --no-chain-reply-to option to "git send-email" for nicer
> email threading and there is something wrong with Signed-off chain for
> the patches. The first Signed-off-by: is by Nadav, but you appears to be
> the author of the patches for git. AFAIK Nadav is the author, so you
> need to add proper From: in your patch submission. If you'll fix the
> authorship in your git "git format-patch" will do it for you.

I have been out of town, and I just have re-submitted v3 patches,
using the options. I wrote the patches 12/13 and 13/13, so I didn't
add From: Nadav in them.

--
Jun
Intel Open Source Technology Center
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e53a5f7..51b8b4f0 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2192,7 +2192,8 @@  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,
@@ -2201,8 +2202,8 @@  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);
@@ -7486,10 +7487,18 @@  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 IA32_MODE, 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)