[PATCH v2 1/2] KVM: nVMX: enhance allocate/free_vpid to handle shadow vpid

[PATCH v2 1/2] KVM: nVMX: enhance allocate/free_vpid to handle shadow vpid

[Wanpeng Li]

Enhance allocate/free_vid to handle shadow vpid.

Suggested-by: Wincy Van <fanwenyi0529@gmail.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
 arch/x86/kvm/vmx.c | 33 +++++++++++++++++++++++++++------
 1 file changed, 27 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index da1590e..bd07d88 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -424,6 +424,8 @@ struct nested_vmx {
 	/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
 	u64 vmcs01_debugctl;
 
+	u16 vpid02;
+
 	u32 nested_vmx_procbased_ctls_low;
 	u32 nested_vmx_procbased_ctls_high;
 	u32 nested_vmx_true_procbased_ctls_low;
@@ -4155,18 +4157,29 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 	return r;
 }
 
-static void allocate_vpid(struct vcpu_vmx *vmx)
+static void allocate_vpid(struct vcpu_vmx *vmx, bool nested)
 {
 	int vpid;
 
-	vmx->vpid = 0;
 	if (!enable_vpid)
 		return;
+	if (!nested)
+		vmx->vpid = 0;
+	else
+		vmx->nested.vpid02 = 0;
 	spin_lock(&vmx_vpid_lock);
-	vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
-	if (vpid < VMX_NR_VPIDS) {
+	if (!nested) {
+		vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
+		if (vpid < VMX_NR_VPIDS) {
 		vmx->vpid = vpid;
 		__set_bit(vpid, vmx_vpid_bitmap);
+		}
+	} else {
+		vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
+		if (vpid < VMX_NR_VPIDS) {
+			vmx->nested.vpid02 = vpid;
+			__set_bit(vpid, vmx_vpid_bitmap);
+		}
 	}
 	spin_unlock(&vmx_vpid_lock);
 }
@@ -4178,6 +4191,12 @@ static void free_vpid(struct vcpu_vmx *vmx)
 	spin_lock(&vmx_vpid_lock);
 	if (vmx->vpid != 0)
 		__clear_bit(vmx->vpid, vmx_vpid_bitmap);
+	if (!nested) {
+		spin_unlock(&vmx_vpid_lock);
+		return;
+	}
+	if (vmx->nested.vpid02)
+		__clear_bit(vmx->nested.vpid02, vmx_vpid_bitmap);
 	spin_unlock(&vmx_vpid_lock);
 }
 
@@ -8509,7 +8528,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!vmx)
 		return ERR_PTR(-ENOMEM);
 
-	allocate_vpid(vmx);
+	allocate_vpid(vmx, false);
 
 	err = kvm_vcpu_init(&vmx->vcpu, kvm, id);
 	if (err)
@@ -8557,8 +8576,10 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 			goto free_vmcs;
 	}
 
-	if (nested)
+	if (nested) {
 		nested_vmx_setup_ctls_msrs(vmx);
+		allocate_vpid(vmx, true);
+	}
 
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
-- 
1.9.1

Re: [PATCH v2 1/2] KVM: nVMX: enhance allocate/free_vpid to handle shadow vpid

[Paolo Bonzini]

On 15/09/2015 12:30, Wanpeng Li wrote:
> +	if (!nested) {
> +		vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
> +		if (vpid < VMX_NR_VPIDS) {
>  		vmx->vpid = vpid;
>  		__set_bit(vpid, vmx_vpid_bitmap);
> +		}
> +	} else {
> +		vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
> +		if (vpid < VMX_NR_VPIDS) {
> +			vmx->nested.vpid02 = vpid;
> +			__set_bit(vpid, vmx_vpid_bitmap);
> +		}

Messy indentation, and a lot of duplicate code.  Can you instead have
(which I think was Jan's suggestion too):

static int allocate_vpid(void);
static void free_vpid(int vpid);

That said, I like the simple solution to the "too many VPIDs for each L1
VCPU" processor.

Paolo

Re: [PATCH v2 1/2] KVM: nVMX: enhance allocate/free_vpid to handle shadow vpid

[Wanpeng Li]

On 9/15/15 8:54 PM, Paolo Bonzini wrote:
>
> On 15/09/2015 12:30, Wanpeng Li wrote:
>> +	if (!nested) {
>> +		vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
>> +		if (vpid < VMX_NR_VPIDS) {
>>   		vmx->vpid = vpid;
>>   		__set_bit(vpid, vmx_vpid_bitmap);
>> +		}
>> +	} else {
>> +		vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
>> +		if (vpid < VMX_NR_VPIDS) {
>> +			vmx->nested.vpid02 = vpid;
>> +			__set_bit(vpid, vmx_vpid_bitmap);
>> +		}
> Messy indentation, and a lot of duplicate code.  Can you instead have
> (which I think was Jan's suggestion too):
>
> static int allocate_vpid(void);
> static void free_vpid(int vpid);

I see, done in v3.

>
> That said, I like the simple solution to the "too many VPIDs for each L1
> VCPU" processor.

Thanks. :-)

Regards,
Wanpeng Li

[PATCH v2 2/2] KVM: nVMX: nested VPID emulation

[Wanpeng Li]

VPID is used to tag address space and avoid a TLB flush. Currently L0 use 
the same VPID to run L1 and all its guests. KVM flushes VPID when switching 
between L1 and L2. 

This patch advertises VPID to the L1 hypervisor, then address space of L1 and 
L2 can be separately treated and avoid TLB flush when swithing between L1 and 
L2. For each nested vmentry, if vpid12 is changed, reuse shadow vpid w/ an 
invvpid.

Performance: 

run lmbench on L2 w/ 3.5 kernel.

Context switching - times in microseconds - smaller is better
-------------------------------------------------------------------------
Host                 OS  2p/0K 2p/16K 2p/64K 8p/16K 8p/64K 16p/16K 16p/64K
                         ctxsw  ctxsw  ctxsw ctxsw  ctxsw   ctxsw   ctxsw
--------- ------------- ------ ------ ------ ------ ------ ------- -------
kernel    Linux 3.5.0-1 1.2200 1.3700 1.4500 4.7800 2.3300 5.60000 2.88000  nested VPID 
kernel    Linux 3.5.0-1 1.2600 1.4300 1.5600   12.7   12.9 3.49000 7.46000  vanilla

Suggested-by: Wincy Van <fanwenyi0529@gmail.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
 arch/x86/kvm/vmx.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bd07d88..6d8ec00 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -425,6 +425,7 @@ struct nested_vmx {
 	u64 vmcs01_debugctl;
 
 	u16 vpid02;
+	u16 last_vpid;
 
 	u32 nested_vmx_procbased_ctls_low;
 	u32 nested_vmx_procbased_ctls_high;
@@ -1159,6 +1160,11 @@ static inline bool nested_cpu_has_virt_x2apic_mode(struct vmcs12 *vmcs12)
 	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
 }
 
+static inline bool nested_cpu_has_vpid(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VPID);
+}
+
 static inline bool nested_cpu_has_apic_reg_virt(struct vmcs12 *vmcs12)
 {
 	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_APIC_REGISTER_VIRT);
@@ -2473,6 +2479,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 		SECONDARY_EXEC_RDTSCP |
 		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
+		SECONDARY_EXEC_ENABLE_VPID |
 		SECONDARY_EXEC_APIC_REGISTER_VIRT |
 		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 		SECONDARY_EXEC_WBINVD_EXITING |
@@ -9460,13 +9467,17 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
 
 	if (enable_vpid) {
-		/*
-		 * Trivially support vpid by letting L2s share their parent
-		 * L1's vpid. TODO: move to a more elaborate solution, giving
-		 * each L2 its own vpid and exposing the vpid feature to L1.
-		 */
-		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
-		vmx_flush_tlb(vcpu);
+		if (nested_cpu_has_vpid(vmcs12)) {
+			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
+			if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
+				vmx->nested.last_vpid = vmcs12->virtual_processor_id;
+				vmx_flush_tlb(vcpu);
+			}
+		} else {
+			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+			vmx_flush_tlb(vcpu);
+		}
+
 	}
 
 	if (nested_cpu_has_ept(vmcs12)) {
-- 
1.9.1