[PATCH 0/3] KVM/Hyper-V: Add Hyper-V direct tlb flush support

[PATCH 0/3] KVM/Hyper-V: Add Hyper-V direct tlb flush support

[lantianyu1986]

From: Tianyu Lan <Tianyu.Lan@microsoft.com>


This patchset is to add Hyper-V direct tlb support in KVM. Hyper-V
in L0 can delegate L1 hypervisor to handle tlb flush request from
L2 guest when direct tlb flush is enabled in L1.

Patch 2 introduces new cap KVM_CAP_HYPERV_DIRECT_TLBFLUSH to enable
feature from user space. User space should enable this feature only
when Hyper-V hypervisor capability is exposed to guest and KVM profile
is hided. There is a parameter conflict between KVM and Hyper-V hypercall.
We hope L2 guest doesn't use KVM hypercall when the feature is
enabled. Detail please see comment of new API "KVM_CAP_HYPERV_DIRECT_TLBFLUSH"

Tianyu Lan (2):
  x86/Hyper-V: Fix definition of struct hv_vp_assist_page
  KVM/Hyper-V: Add new KVM cap KVM_CAP_HYPERV_DIRECT_TLBFLUSH

Vitaly Kuznetsov (1):
  KVM/Hyper-V/VMX: Add direct tlb flush support

 Documentation/virtual/kvm/api.txt  | 10 ++++++++++
 arch/x86/include/asm/hyperv-tlfs.h | 24 +++++++++++++++++++-----
 arch/x86/include/asm/kvm_host.h    |  2 ++
 arch/x86/kvm/vmx/evmcs.h           |  2 ++
 arch/x86/kvm/vmx/vmx.c             | 38 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/x86.c                 |  8 ++++++++
 include/linux/kvm_host.h           |  1 +
 include/uapi/linux/kvm.h           |  1 +
 8 files changed, 81 insertions(+), 5 deletions(-)

-- 
2.14.2

[PATCH 1/3] x86/Hyper-V: Fix definition of struct hv_vp_assist_page

[lantianyu1986]

From: Tianyu Lan <Tianyu.Lan@microsoft.com>

The struct hv_vp_assist_page was defined incorrectly.
The "vtl_control" should be u64[3], "nested_enlightenments_control"
should be a u64 and there is 7 reserved bytes following "enlighten_vmentry".
This patch is to fix it.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 arch/x86/include/asm/hyperv-tlfs.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index af78cd72b8f3..a79703c56ebe 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -517,11 +517,11 @@ struct hv_timer_message_payload {
 /* Define virtual processor assist page structure. */
 struct hv_vp_assist_page {
 	__u32 apic_assist;
-	__u32 reserved;
-	__u64 vtl_control[2];
+	__u32 reserved1;
+	__u64 vtl_control[3];
 	__u64 nested_enlightenments_control[2];
-	__u32 enlighten_vmentry;
-	__u32 padding;
+	__u8 enlighten_vmentry;
+	__u8 reserved2[7];
 	__u64 current_nested_vmcs;
 } __packed;
 
-- 
2.14.2

[PATCH 2/3] KVM/Hyper-V: Add new KVM cap KVM_CAP_HYPERV_DIRECT_TLBFLUSH

[lantianyu1986]

From: Tianyu Lan <Tianyu.Lan@microsoft.com>

This patch adds new KVM cap KVM_CAP_HYPERV_DIRECT_TLBFLUSH and let
user space to enable direct tlb flush function when only Hyper-V
hypervsior capability is exposed to VM. This patch also adds
enable_direct_tlbflush callback in the struct kvm_x86_ops and
platforms may use it to implement direct tlb flush support.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 Documentation/virtual/kvm/api.txt | 10 ++++++++++
 arch/x86/include/asm/kvm_host.h   |  2 ++
 arch/x86/kvm/x86.c                |  8 ++++++++
 include/uapi/linux/kvm.h          |  1 +
 4 files changed, 21 insertions(+)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 2cd6250b2896..45308ed6dd75 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -5289,3 +5289,13 @@ Architectures: x86
 This capability indicates that KVM supports paravirtualized Hyper-V IPI send
 hypercalls:
 HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
+8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
+
+Architecture: x86
+
+This capability indicates that KVM supports Hyper-V direct tlb flush function.
+User space should enable this feature only when Hyper-V hypervisor capability
+is exposed to guest and KVM profile is hided. Both Hyper-V and KVM hypercalls
+use RAX and RCX registers to pass parameters. If KVM hypercall is exposed
+to L2 guest with direct tlbflush enabled, Hyper-V may mistake KVM hypercall
+for Hyper-V tlb flush Hypercall due to paremeter register overlap.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0cc5b611a113..667d154e89d4 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1205,6 +1205,8 @@ struct kvm_x86_ops {
 	uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu);
 
 	bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu);
+
+	int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_arch_async_pf {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9d7b9e6a0939..a9d8ee7f7bf0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3183,6 +3183,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = kvm_x86_ops->get_nested_state ?
 			kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
 		break;
+	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
+		r = kvm_x86_ops->enable_direct_tlbflush ? 1 : 0;
+		break;
 	default:
 		break;
 	}
@@ -3953,6 +3956,11 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 				r = -EFAULT;
 		}
 		return r;
+	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
+		if (!kvm_x86_ops->enable_direct_tlbflush)
+			return -ENOTTY;
+
+		return kvm_x86_ops->enable_direct_tlbflush(vcpu);
 
 	default:
 		return -EINVAL;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index a7c19540ce21..cb959bc925b1 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -996,6 +996,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172
 #define KVM_CAP_PMU_EVENT_FILTER 173
+#define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 174
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
2.14.2

Re: [PATCH 1/3] x86/Hyper-V: Fix definition of struct hv_vp_assist_page

[Vitaly Kuznetsov]

lantianyu1986@gmail.com writes:

> From: Tianyu Lan <Tianyu.Lan@microsoft.com>
>
> The struct hv_vp_assist_page was defined incorrectly.
> The "vtl_control" should be u64[3], "nested_enlightenments_control"
> should be a u64 and there is 7 reserved bytes following "enlighten_vmentry".
> This patch is to fix it.
>
> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
> ---
>  arch/x86/include/asm/hyperv-tlfs.h | 8 ++++----
>  1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
> index af78cd72b8f3..a79703c56ebe 100644
> --- a/arch/x86/include/asm/hyperv-tlfs.h
> +++ b/arch/x86/include/asm/hyperv-tlfs.h
> @@ -517,11 +517,11 @@ struct hv_timer_message_payload {
>  /* Define virtual processor assist page structure. */
>  struct hv_vp_assist_page {
>  	__u32 apic_assist;
> -	__u32 reserved;
> -	__u64 vtl_control[2];
> +	__u32 reserved1;
> +	__u64 vtl_control[3];
>  	__u64 nested_enlightenments_control[2];

In PATCH3 you define 'struct hv_nested_enlightenments_control' and it is
64bit long, not 128. We should change it here too as ...

> -	__u32 enlighten_vmentry;

enlighten_vmentry filed will get a very different offset breaking
Enlightened VMCS.

> -	__u32 padding;
> +	__u8 enlighten_vmentry;
> +	__u8 reserved2[7];
>  	__u64 current_nested_vmcs;
>  } __packed;

-- 
Vitaly

Re: [PATCH 2/3] KVM/Hyper-V: Add new KVM cap KVM_CAP_HYPERV_DIRECT_TLBFLUSH

[Vitaly Kuznetsov]

lantianyu1986@gmail.com writes:

> From: Tianyu Lan <Tianyu.Lan@microsoft.com>
>
> This patch adds new KVM cap KVM_CAP_HYPERV_DIRECT_TLBFLUSH and let
> user space to enable direct tlb flush function when only Hyper-V
> hypervsior capability is exposed to VM. This patch also adds
> enable_direct_tlbflush callback in the struct kvm_x86_ops and
> platforms may use it to implement direct tlb flush support.
>
> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
> ---
>  Documentation/virtual/kvm/api.txt | 10 ++++++++++
>  arch/x86/include/asm/kvm_host.h   |  2 ++
>  arch/x86/kvm/x86.c                |  8 ++++++++
>  include/uapi/linux/kvm.h          |  1 +
>  4 files changed, 21 insertions(+)
>
> diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
> index 2cd6250b2896..45308ed6dd75 100644
> --- a/Documentation/virtual/kvm/api.txt
> +++ b/Documentation/virtual/kvm/api.txt
> @@ -5289,3 +5289,13 @@ Architectures: x86
>  This capability indicates that KVM supports paravirtualized Hyper-V IPI send
>  hypercalls:
>  HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
> +8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
> +
> +Architecture: x86
> +
> +This capability indicates that KVM supports Hyper-V direct tlb flush function.
> +User space should enable this feature only when Hyper-V hypervisor capability
> +is exposed to guest and KVM profile is hided. Both Hyper-V and KVM hypercalls
> +use RAX and RCX registers to pass parameters. If KVM hypercall is exposed
> +to L2 guest with direct tlbflush enabled, Hyper-V may mistake KVM hypercall
> +for Hyper-V tlb flush Hypercall due to paremeter register overlap.

First, we need to explicitly state that this is for KVM on Hyper-V and
second, that this disables normal hypercall handling by KVM.

My take:

This capability indicates that KVM running on top of Hyper-V hypervisor
enables Direct TLB flush for its guests meaning that TLB flush
hypercalls are handled by Level 1 hypervisor (Hyper-V) bypassing KVM. 
Due to the different ABI for hypercall parameters between Hyper-V and
KVM, enabling this capability effectively disables all hypercall
handling by KVM (as some KVM hypercall may be mistakenly treated as TLB
flush hypercalls by Hyper-C) so userspace should disable KVM
identification in CPUID.

I think we should also enforce this somehow leaving only Hyper-V style
hypercalls handling (for Windows guests) in place.

> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 0cc5b611a113..667d154e89d4 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1205,6 +1205,8 @@ struct kvm_x86_ops {
>  	uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu);
>  
>  	bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu);
> +
> +	int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu);
>  };
>  
>  struct kvm_arch_async_pf {
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 9d7b9e6a0939..a9d8ee7f7bf0 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -3183,6 +3183,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>  		r = kvm_x86_ops->get_nested_state ?
>  			kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
>  		break;
> +	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
> +		r = kvm_x86_ops->enable_direct_tlbflush ? 1 : 0;
> +		break;
>  	default:
>  		break;
>  	}
> @@ -3953,6 +3956,11 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
>  				r = -EFAULT;
>  		}
>  		return r;
> +	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
> +		if (!kvm_x86_ops->enable_direct_tlbflush)
> +			return -ENOTTY;
> +
> +		return kvm_x86_ops->enable_direct_tlbflush(vcpu);
>  
>  	default:
>  		return -EINVAL;
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index a7c19540ce21..cb959bc925b1 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -996,6 +996,7 @@ struct kvm_ppc_resize_hpt {
>  #define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
>  #define KVM_CAP_ARM_PTRAUTH_GENERIC 172
>  #define KVM_CAP_PMU_EVENT_FILTER 173
> +#define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 174
>  
>  #ifdef KVM_CAP_IRQ_ROUTING

-- 
Vitaly