[PATCH v4] KVM: nVMX: nested TPR shadow/threshold emulation

[Wanpeng Li]

This patch fix bug https://bugzilla.kernel.org/show_bug.cgi?id=61411

TPR shadow/threshold feature is important to speed up the Windows guest.
Besides, it is a must feature for certain VMM.

We map virtual APIC page address and TPR threshold from L1 VMCS. If
TPR_BELOW_THRESHOLD VM exit is triggered by L2 guest and L1 interested
in, we inject it into L1 VMM for handling.

Reviewed-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxxxxxx>
---
v3 -> v4:
 * add Paolo's Reviewed-by
 * unconditionally fail the vmentry, with a comment  
 * setup the TPR_SHADOW/virtual_apic_page of vmcs02 based on vmcs01 if L2 owns the APIC
v2 -> v3:
 * nested vm entry failure if both tpr shadow and cr8 exiting bits are not set
v1 -> v2:
 * don't take L0's "virtualize APIC accesses" setting into account
 * virtual_apic_page do exactly the same thing that is done for apic_access_page
 * add the tpr threshold field to the read-write fields for shadow VMCS

 arch/x86/kvm/vmx.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 47 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bfe11cf..c8d8e9a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -379,6 +379,7 @@ struct nested_vmx {
 	 * we must keep them pinned while L2 runs.
 	 */
 	struct page *apic_access_page;
+	struct page *virtual_apic_page;
 	u64 msr_ia32_feature_control;
 
 	struct hrtimer preemption_timer;
@@ -533,6 +534,7 @@ static int max_shadow_read_only_fields =
 	ARRAY_SIZE(shadow_read_only_fields);
 
 static unsigned long shadow_read_write_fields[] = {
+	TPR_THRESHOLD,
 	GUEST_RIP,
 	GUEST_RSP,
 	GUEST_CR0,
@@ -2330,7 +2332,7 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 		CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
 		CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING |
 		CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING |
-		CPU_BASED_PAUSE_EXITING |
+		CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW |
 		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
 	/*
 	 * We can allow some features even when not supported by the
@@ -6148,6 +6150,10 @@ static void free_nested(struct vcpu_vmx *vmx)
 		nested_release_page(vmx->nested.apic_access_page);
 		vmx->nested.apic_access_page = 0;
 	}
+	if (vmx->nested.virtual_apic_page) {
+		nested_release_page(vmx->nested.virtual_apic_page);
+		vmx->nested.virtual_apic_page = 0;
+	}
 
 	nested_free_all_saved_vmcss(vmx);
 }
@@ -6936,7 +6942,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	case EXIT_REASON_MCE_DURING_VMENTRY:
 		return 0;
 	case EXIT_REASON_TPR_BELOW_THRESHOLD:
-		return 1;
+		return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
 	case EXIT_REASON_APIC_ACCESS:
 		return nested_cpu_has2(vmcs12,
 			SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
@@ -7057,6 +7063,12 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	if (is_guest_mode(vcpu) &&
+		nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
+		return;
+
 	if (irr == -1 || tpr < irr) {
 		vmcs_write32(TPR_THRESHOLD, 0);
 		return;
@@ -8024,6 +8036,35 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
 	exec_control &= ~CPU_BASED_TPR_SHADOW;
 	exec_control |= vmcs12->cpu_based_vm_exec_control;
+
+	if (exec_control & CPU_BASED_TPR_SHADOW) {
+		if (vmx->nested.virtual_apic_page)
+			nested_release_page(vmx->nested.virtual_apic_page);
+		vmx->nested.virtual_apic_page =
+		   nested_get_page(vcpu, vmcs12->virtual_apic_page_addr);
+		if (!vmx->nested.virtual_apic_page)
+			exec_control &=
+				~CPU_BASED_TPR_SHADOW;
+		else
+			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
+				page_to_phys(vmx->nested.virtual_apic_page));
+
+		/*
+		 * If CR8 load exits are enabled, CR8 store exits are enabled,
+		 * and virtualize APIC access is disabled, the processor would
+		 * never notice. Doing it unconditionally is not correct, but
+		 * it is the simplest thing.
+		 */
+		if (!(exec_control & CPU_BASED_TPR_SHADOW) &&
+			!((exec_control & CPU_BASED_CR8_LOAD_EXITING) &&
+				(exec_control & CPU_BASED_CR8_STORE_EXITING)))
+			nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+
+		vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+	} else if (vm_need_tpr_shadow(vmx->vcpu.kvm))
+		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
+				__pa(vmx->vcpu.arch.apic->regs));
+
 	/*
 	 * Merging of IO and MSR bitmaps not currently supported.
 	 * Rather, exit every time.
@@ -8792,6 +8833,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 		nested_release_page(vmx->nested.apic_access_page);
 		vmx->nested.apic_access_page = 0;
 	}
+	if (vmx->nested.virtual_apic_page) {
+		nested_release_page(vmx->nested.virtual_apic_page);
+		vmx->nested.virtual_apic_page = 0;
+	}
 
 	/*
 	 * Exiting from L2 to L1, we're now back to L1 which thinks it just
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/