[PATCH] kvm/vmx: EPTP switching test

[PATCH] kvm/vmx: EPTP switching test

[Michael S. Tsirkin]

This patch adds a new parameter: eptp_switching_test, which enables
testing EPT switching on VMX if supported by hardware.  All EPT entries
are initialized to the same value so this adds no useful functionality
by itself, but can be used to test VMFUNC performance, and serve as a
basis for future features based on EPTP switching.

Support for nested virt is not enabled.

This was tested using the following code within guest:
	#define VMX_VMFUNC ".byte 0x0f,0x01,0xd4"
	static void vmfunc(unsigned int nr, unsigned int ept)
	{
		asm volatile(VMX_VMFUNC
			     :
			     : "a"(nr), "c"(ept)
			     : "memory");
	}

VMFUNC instruction cost was measured at ~122 cycles.
(Note: recent versions of gnu toolchain support
 the vmfunc instruction - removing the need for writing
 the bytecode manually).

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---

I think I'd like to put this upstream so future eptp switching work can
be implemented on top. Comments?

 arch/x86/include/asm/vmx.h |  7 ++++
 arch/x86/kvm/vmx.c         | 84 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 91 insertions(+)

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 448b7ca..ceb68d9 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -69,10 +69,13 @@
 #define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY    0x00000200
 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
 #define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
+#define SECONDARY_EXEC_ENABLE_VM_FUNCTIONS	0x00002000
 #define SECONDARY_EXEC_SHADOW_VMCS              0x00004000
 #define SECONDARY_EXEC_ENABLE_PML               0x00020000
 #define SECONDARY_EXEC_XSAVES			0x00100000
 
+/* Definitions for VM-function controls */
+#define VM_FUNCTION_EPTP_SWITCHING		0x00000001
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
 #define PIN_BASED_NMI_EXITING                   0x00000008
@@ -153,6 +156,8 @@ enum vmcs_field {
 	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
 	POSTED_INTR_DESC_ADDR           = 0x00002016,
 	POSTED_INTR_DESC_ADDR_HIGH      = 0x00002017,
+	VM_FUNCTION_CTRL                = 0x00002018,
+	VM_FUNCTION_CTRL_HIGH           = 0x00002019,
 	EPT_POINTER                     = 0x0000201a,
 	EPT_POINTER_HIGH                = 0x0000201b,
 	EOI_EXIT_BITMAP0                = 0x0000201c,
@@ -163,6 +168,8 @@ enum vmcs_field {
 	EOI_EXIT_BITMAP2_HIGH           = 0x00002021,
 	EOI_EXIT_BITMAP3                = 0x00002022,
 	EOI_EXIT_BITMAP3_HIGH           = 0x00002023,
+	EPTP_LIST_ADDRESS               = 0x00002024,
+	EPTP_LIST_ADDRESS_HIGH          = 0x00002025,
 	VMREAD_BITMAP                   = 0x00002026,
 	VMWRITE_BITMAP                  = 0x00002028,
 	XSS_EXIT_BITMAP                 = 0x0000202C,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6a8bc64..3d1f613 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -45,6 +45,7 @@
 #include <asm/debugreg.h>
 #include <asm/kexec.h>
 #include <asm/apic.h>
+#include <asm/page.h>
 
 #include "trace.h"
 #include "pmu.h"
@@ -105,6 +106,9 @@ static u64 __read_mostly host_xss;
 static bool __read_mostly enable_pml = 1;
 module_param_named(pml, enable_pml, bool, S_IRUGO);
 
+static bool __read_mostly enable_eptp_switching = 0;
+module_param_named(eptp_switching_test, enable_eptp_switching, bool, S_IRUGO);
+
 #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
 #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE)
 #define KVM_VM_CR0_ALWAYS_ON						\
@@ -547,6 +551,10 @@ struct vcpu_vmx {
 	/* Support for PML */
 #define PML_ENTITY_NUM		512
 	struct page *pml_pg;
+
+	/* Support for EPTP switching */
+#define EPTP_LIST_NUM		512
+	struct page *eptp_list_pg;
 };
 
 enum segment_cache_field {
@@ -1113,6 +1121,22 @@ static inline bool cpu_has_vmx_pml(void)
 	return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_PML;
 }
 
+static inline bool cpu_has_vmx_vm_functions(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_ENABLE_VM_FUNCTIONS;
+}
+
+/* check if the cpu supports writing EPTP switching */
+static inline bool cpu_has_vmx_eptp_switching(void)
+{
+	u64 vmx_msr;
+
+	rdmsrl(MSR_IA32_VMX_VMFUNC, vmx_msr);
+	/* This MSR has same format as VM-function controls */
+	return vmx_msr & VM_FUNCTION_EPTP_SWITCHING;
+}
+
 static inline bool report_flexpriority(void)
 {
 	return flexpriority_enabled;
@@ -3011,6 +3035,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 			SECONDARY_EXEC_PAUSE_LOOP_EXITING |
 			SECONDARY_EXEC_RDTSCP |
 			SECONDARY_EXEC_ENABLE_INVPCID |
+			SECONDARY_EXEC_ENABLE_VM_FUNCTIONS |
 			SECONDARY_EXEC_APIC_REGISTER_VIRT |
 			SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 			SECONDARY_EXEC_SHADOW_VMCS |
@@ -3600,6 +3625,13 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	guest_cr3 = cr3;
 	if (enable_ept) {
 		eptp = construct_eptp(cr3);
+		if (to_vmx(vcpu)->eptp_list_pg) {
+			u64 *eptp_list = phys_to_virt(page_to_phys(to_vmx(vcpu)->eptp_list_pg));
+			int i;
+
+			for (i = 0; i < EPTP_LIST_NUM; ++i)
+				eptp_list[i] = eptp;
+		}
 		vmcs_write64(EPT_POINTER, eptp);
 		if (is_paging(vcpu) || is_guest_mode(vcpu))
 			guest_cr3 = kvm_read_cr3(vcpu);
@@ -6089,6 +6121,13 @@ static __init int hardware_setup(void)
 	if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml())
 		enable_pml = 0;
 
+	/*
+	 * Only enable EPT switching when hardware supports EPT switching, and EPT
+	 * and VM functions are enabled -- EPT switching depends on these to work.
+	 */
+	if (!enable_ept || !cpu_has_vmx_vm_functions() || !cpu_has_vmx_eptp_switching())
+		enable_eptp_switching = 0;
+
 	if (!enable_pml) {
 		kvm_x86_ops->slot_enable_log_dirty = NULL;
 		kvm_x86_ops->slot_disable_log_dirty = NULL;
@@ -7590,6 +7629,26 @@ static int vmx_enable_pml(struct vcpu_vmx *vmx)
 	return 0;
 }
 
+static int vmx_enable_ept_switching(struct vcpu_vmx *vmx)
+{
+	struct page *eptp_list_pg;
+	u64 vm_function_control;
+
+	eptp_list_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	if (!eptp_list_pg)
+		return -ENOMEM;
+
+	vmx->eptp_list_pg = eptp_list_pg;
+
+	vmcs_write64(EPTP_LIST_ADDRESS, page_to_phys(vmx->eptp_list_pg));
+
+	vm_function_control = vmcs_read64(VM_FUNCTION_CTRL);
+	vm_function_control |= VM_FUNCTION_EPTP_SWITCHING;
+	vmcs_write64(VM_FUNCTION_CTRL, vm_function_control);
+
+	return 0;
+}
+
 static void vmx_disable_pml(struct vcpu_vmx *vmx)
 {
 	u32 exec_control;
@@ -7603,6 +7662,21 @@ static void vmx_disable_pml(struct vcpu_vmx *vmx)
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
 }
 
+static void vmx_disable_ept_switching(struct vcpu_vmx *vmx)
+{
+	u64 vm_function_control;
+
+	ASSERT(vmx->eptp_list_pg);
+	__free_page(vmx->eptp_list_pg);
+	vmx->eptp_list_pg = NULL;
+
+	vmcs_write64(EPTP_LIST_ADDRESS, 0);
+
+	vm_function_control = vmcs_read64(VM_FUNCTION_CTRL);
+	vm_function_control &= ~VM_FUNCTION_EPTP_SWITCHING;
+	vmcs_write64(VM_FUNCTION_CTRL, vm_function_control);
+}
+
 static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8476,6 +8550,8 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	if (enable_eptp_switching)
+		vmx_disable_ept_switching(vmx);
 	if (enable_pml)
 		vmx_disable_pml(vmx);
 	free_vpid(vmx);
@@ -8564,8 +8640,16 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 			goto free_vmcs;
 	}
 
+	if (enable_eptp_switching) {
+		err = vmx_enable_ept_switching(vmx);
+		if (err)
+			goto disable_pml;
+	}
+
 	return &vmx->vcpu;
 
+disable_pml:
+	vmx_disable_pml(vmx);
 free_vmcs:
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
-- 
MST

Re: [PATCH] kvm/vmx: EPTP switching test

[=?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?=]

2015-11-15 18:00+0200, Michael S. Tsirkin:
> This patch adds a new parameter: eptp_switching_test, which enables
> 
> testing EPT switching on VMX if supported by hardware.  All EPT entries
> are initialized to the same value so this adds no useful functionality
> by itself, but can be used to test VMFUNC performance, and serve as a
> basis for future features based on EPTP switching.
> 
> Support for nested virt is not enabled.
> 
> This was tested using the following code within guest:
> 	#define VMX_VMFUNC ".byte 0x0f,0x01,0xd4"
> 	static void vmfunc(unsigned int nr, unsigned int ept)
> 	{
> 		asm volatile(VMX_VMFUNC
> 			     :
> 			     : "a"(nr), "c"(ept)
> 			     : "memory");
> 	}
> 
> VMFUNC instruction cost was measured at ~122 cycles.
> (Note: recent versions of gnu toolchain support
>  the vmfunc instruction - removing the need for writing
>  the bytecode manually).
> 
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> ---
> 
> I think I'd like to put this upstream so future eptp switching work can
> be implemented on top. Comments?

I'd wait for the future.  Patch is already on the list so people
interested in benchmarking VMFUNC can quickly compile a kernel and
developers will need to overwrite the code anyway.

(And I think that eptp switching is expected to be used in conjuction
 with #VE, so it'd then make sense to implement a nop for it as well.)

> diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
> @@ -3011,6 +3035,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
>  			SECONDARY_EXEC_PAUSE_LOOP_EXITING |
>  			SECONDARY_EXEC_RDTSCP |
>  			SECONDARY_EXEC_ENABLE_INVPCID |
> +			SECONDARY_EXEC_ENABLE_VM_FUNCTIONS |

The VMFUNC vmexit should be handled to prevent guests from triggering a
WARN_ON on the host.  (VMFUNC did just #UD before this patch.)

After that, it's ok for KVM.

Re: [PATCH] kvm/vmx: EPTP switching test

[Michael S. Tsirkin]

On Mon, Nov 16, 2015 at 06:51:06PM +0100, =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= wrote:
> 2015-11-15 18:00+0200, Michael S. Tsirkin:
> > This patch adds a new parameter: eptp_switching_test, which enables
> > 
> > testing EPT switching on VMX if supported by hardware.  All EPT entries
> > are initialized to the same value so this adds no useful functionality
> > by itself, but can be used to test VMFUNC performance, and serve as a
> > basis for future features based on EPTP switching.
> > 
> > Support for nested virt is not enabled.
> > 
> > This was tested using the following code within guest:
> > 	#define VMX_VMFUNC ".byte 0x0f,0x01,0xd4"
> > 	static void vmfunc(unsigned int nr, unsigned int ept)
> > 	{
> > 		asm volatile(VMX_VMFUNC
> > 			     :
> > 			     : "a"(nr), "c"(ept)
> > 			     : "memory");
> > 	}
> > 
> > VMFUNC instruction cost was measured at ~122 cycles.
> > (Note: recent versions of gnu toolchain support
> >  the vmfunc instruction - removing the need for writing
> >  the bytecode manually).
> > 
> > Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> > ---
> > 
> > I think I'd like to put this upstream so future eptp switching work can
> > be implemented on top. Comments?
> 
> I'd wait for the future.  Patch is already on the list so people
> interested in benchmarking VMFUNC can quickly compile a kernel and
> developers will need to overwrite the code anyway.

It'll bitrot though.  But I'll let Paolo decide that.

> (And I think that eptp switching is expected to be used in conjuction
>  with #VE, so it'd then make sense to implement a nop for it as well.)

No idea how would I even test it, so I'm not interested in #VE at this
point.  If you are - go ahead and post a patch for that on top though,
why not.

> > diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
> > @@ -3011,6 +3035,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
> >  			SECONDARY_EXEC_PAUSE_LOOP_EXITING |
> >  			SECONDARY_EXEC_RDTSCP |
> >  			SECONDARY_EXEC_ENABLE_INVPCID |
> > +			SECONDARY_EXEC_ENABLE_VM_FUNCTIONS |
> 
> The VMFUNC vmexit should be handled to prevent guests from triggering a
> WARN_ON on the host.  (VMFUNC did just #UD before this patch.)

Do you mean VMFUNC other than EPTP switch 0?  True, thanks!

> 
> After that, it's ok for KVM.

Re: [PATCH] kvm/vmx: EPTP switching test

[=?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?=]

2015-11-16 19:59+0200, Michael S. Tsirkin:
> On Mon, Nov 16, 2015 at 06:51:06PM +0100, =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= wrote:
>> 2015-11-15 18:00+0200, Michael S. Tsirkin:
>> (And I think that eptp switching is expected to be used in conjuction
>>  with #VE, so it'd then make sense to implement a nop for it as well.)
> 
> No idea how would I even test it, so I'm not interested in #VE at this
> point.  If you are - go ahead and post a patch for that on top though,
> why not.

I thought that it's going to be simpler to provide functionality (that
utilizes eptp switching) to the guest through #VE, which probably isn't
true as I think more about it.  (Not interested in implementing it :])

Re: [PATCH] kvm/vmx: EPTP switching test

[Andy Lutomirski]

On Mon, Nov 16, 2015 at 10:18 AM,
=?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= <rkrcmar@redhat.com> wrote:
> 2015-11-16 19:59+0200, Michael S. Tsirkin:
>> On Mon, Nov 16, 2015 at 06:51:06PM +0100, =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= wrote:
>>> 2015-11-15 18:00+0200, Michael S. Tsirkin:
>>> (And I think that eptp switching is expected to be used in conjuction
>>>  with #VE, so it'd then make sense to implement a nop for it as well.)
>>
>> No idea how would I even test it, so I'm not interested in #VE at this
>> point.  If you are - go ahead and post a patch for that on top though,
>> why not.
>
> I thought that it's going to be simpler to provide functionality (that
> utilizes eptp switching) to the guest through #VE, which probably isn't
> true as I think more about it.  (Not interested in implementing it :])

I'm willing to review a #VE stub.  I'm not likely to implement it.

--Andy

Re: [PATCH] kvm/vmx: EPTP switching test

[Paolo Bonzini]

On 16/11/2015 19:18, =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= wrote:
>> > No idea how would I even test it, so I'm not interested in #VE at this
>> > point.  If you are - go ahead and post a patch for that on top though,
>> > why not.
> I thought that it's going to be simpler to provide functionality (that
> utilizes eptp switching) to the guest through #VE, which probably isn't
> true as I think more about it.  (Not interested in implementing it :])

#VE and EPTP switching are distinct features, one does not imply the other.

Unfortunately, EPTP switching is designed for a very specific use case
where the hypervisor is effectively part of the kernel, and the kernel
is trusted to some extent.  Examples include antivirus software and
virtual machines.  Antiviruses do use VMFUNC, that's as far as I know
the only current use case of it
(https://embedded.communities.intel.com/community/en/applications/blog/2013/06/13/roving-reporter-enhancing-retail-security-and-manageability-with-4th-generation-intel-core-processors).

So I'm against this patch, but only because I'm not sure why KVM would
ever use EPTP switching in its current incarnation.  The guest kernel is
absolutely not trusted by KVM.

Paolo

RE: [PATCH] kvm/vmx: EPTP switching test

[Zhang, Yang Z]

Michael S. Tsirkin wrote on 2015-11-16:
> This patch adds a new parameter: eptp_switching_test, which enables
> testing EPT switching on VMX if supported by hardware.  All EPT
> entries are initialized to the same value so this adds no useful
> functionality by itself, but can be used to test VMFUNC performance,
> and serve as a basis for future features based on EPTP switching.
> 
> Support for nested virt is not enabled.
> 
> This was tested using the following code within guest:
> 	#define VMX_VMFUNC ".byte 0x0f,0x01,0xd4"
> 	static void vmfunc(unsigned int nr, unsigned int ept)
> 	{
> 		asm volatile(VMX_VMFUNC
> 			     :
> 			     : "a"(nr), "c"(ept)
> 			     : "memory");
> 	}
> 
> VMFUNC instruction cost was measured at ~122 cycles.
> (Note: recent versions of gnu toolchain support  the vmfunc
> instruction - removing the need for writing  the bytecode manually).
> 
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> ---
> 
> I think I'd like to put this upstream so future eptp switching work
> can be implemented on top. Comments?

We have a different version in hand which is using separate EPTP. As you known, the patch will be more complex if using separate EPTP. And there are still lots of thing need to do in our version. We will send out for comments soon.

Best regards,
Yang

Re: [PATCH] kvm/vmx: EPTP switching test

[Paolo Bonzini]

On 17/11/2015 02:45, Zhang, Yang Z wrote:
> We have a different version in hand which is using separate EPTP.

Can you say in advance what you are using EPTP switching for?  Offlist
if necessary.

Paolo

RE: [PATCH] kvm/vmx: EPTP switching test

[Wang, Wei W]

On 17/11/2015 18:18,  Paolo Bonzini wrote:
> On 17/11/2015 02:45, Zhang, Yang Z wrote:
> > We have a different version in hand which is using separate EPTP.
> 
> Can you say in advance what you are using EPTP switching for?  Offlist if
> necessary.

Hi Paolo,

We are using EPTP switching for a protected inter-VM communication design, as shown in the slides (#23) here: http://events.linuxfoundation.org/sites/events/files/slides/Jun_Nakajima_NFV_KVM%202015_final.pdf


Best,
Wei

Re: [PATCH] kvm/vmx: EPTP switching test

[Paolo Bonzini]

On 17/11/2015 11:44, Wang, Wei W wrote:
> On 17/11/2015 18:18,  Paolo Bonzini wrote:
>> On 17/11/2015 02:45, Zhang, Yang Z wrote:
>>> We have a different version in hand which is using separate
>>> EPTP.
>> 
>> Can you say in advance what you are using EPTP switching for?
>> Offlist if necessary.
> 
> Hi Paolo,
> 
> We are using EPTP switching for a protected inter-VM communication
> design, as shown in the slides (#23) here:
> http://events.linuxfoundation.org/sites/events/files/slides/Jun_Nakajima_NFV_KVM%202015_final.pdf

[offlist, adding virt-intel-list@redhat.com]

If the EPTP switch is only adding extra data pages (e.g. mapping another
guest's memory inside a PCI BAR), this can work.

However, slides 24 and 25 suggest that the executable pages change
between the two EPTP views, similar to Jun's KVM Forum 2014
presentation.  Michael and I explained in Seattle that this only works
if the guest is trusted.  I am a bit disappointed that Intel continued
developing this feature without contacting us or without urging us to
present our issues more formally.

I think I should make this very clear: I am not going to accept in KVM a
feature that requires the guest to be trusted.  A trusted guest kernel
may make sense for other applications of VMFUNC (e.g. McAfee memory
scan) but not for virtualization; if the guest is trusted, you don't
have virtualization anymore.

Michael and I are going to present our findings to Intel soon.  This
will hopefully clarify why the guest has to be trusted.  We will also
present possible extensions to VMFUNC that enable its usage with
untrusted guests, albeit only at CPL=0.

Asit Mallick is going to contact Jun about this so we can organize the
meeting.  Unfortunately it is going to be hard for everyone to attend
since we have people in Europe, US and China, but we will share the slides.

Thanks,

Paolo