[PATCH v8 3/3] x86, apicv: add virtual x2apic support

[Yang Zhang <yang.z.zhang@intel.com>]

From: Yang Zhang <yang.z.zhang@Intel.com>

basically to benefit from apicv, we need clear MSR bitmap for
corresponding x2apic MSRs when guest enabled x2apic:
    0x800 - 0x8ff: no read intercept for apicv register virtualization
    TPR,EOI,SELF-IPI: no write intercept for virtual interrupt delivery

Signed-off-by: Yang Zhang <yang.z.zhang@Intel.com>
Signed-off-by: Kevin Tian <kevin.tian@intel.com>
---
 arch/x86/include/asm/kvm_host.h |    1 +
 arch/x86/include/asm/vmx.h      |    1 +
 arch/x86/kvm/lapic.c            |    2 +
 arch/x86/kvm/svm.c              |    6 +++
 arch/x86/kvm/vmx.c              |   80 +++++++++++++++++++++++++++++++++++---
 5 files changed, 83 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 135603f..af9a8c3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -704,6 +704,7 @@ struct kvm_x86_ops {
 	void (*update_exitmap_end)(struct kvm_vcpu *vcpu);
 	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu);
 	void (*restore_rvi)(struct kvm_vcpu *vcpu);
+	void (*enable_virtual_x2apic_mode)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index d1ab331..694586c 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -140,6 +140,7 @@
 #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
 #define SECONDARY_EXEC_ENABLE_EPT               0x00000002
 #define SECONDARY_EXEC_RDTSCP			0x00000008
+#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE   0x00000010
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
 #define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e1baf37..dba5300 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1349,6 +1349,8 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		u32 id = kvm_apic_id(apic);
 		u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
 		kvm_apic_set_ldr(apic, ldr);
+		kvm_x86_ops->enable_virtual_x2apic_mode(vcpu);
+
 	}
 	apic->base_address = apic->vcpu->arch.apic_base &
 			     MSR_IA32_APICBASE_BASE;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a8a8a4e..3e34e19 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3601,6 +3601,11 @@ static void svm_restore_rvi(struct kvm_vcpu *vcpu)
 	return;
 }
 
+static void svm_enable_virtual_x2apic_mode(struct kvm_vcpu *vcpu)
+{
+	return;
+}
+
 static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -4326,6 +4331,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.update_exitmap_end = svm_update_exitmap_end,
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
 	.restore_rvi = svm_restore_rvi,
+	.enable_virtual_x2apic_mode = svm_enable_virtual_x2apic_mode,
 
 	.set_tss_addr = svm_set_tss_addr,
 	.get_tdp_level = get_npt_level,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 0c85c7e..466b05d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2551,6 +2551,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 	if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) {
 		min2 = 0;
 		opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+			SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
 			SECONDARY_EXEC_WBINVD_EXITING |
 			SECONDARY_EXEC_ENABLE_VPID |
 			SECONDARY_EXEC_ENABLE_EPT |
@@ -3739,7 +3740,10 @@ static void free_vpid(struct vcpu_vmx *vmx)
 	spin_unlock(&vmx_vpid_lock);
 }
 
-static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
+#define MSR_TYPE_R	1
+#define MSR_TYPE_W	2
+static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+						u32 msr, int type)
 {
 	int f = sizeof(unsigned long);
 
@@ -3752,20 +3756,52 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
 	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
 	 */
 	if (msr <= 0x1fff) {
-		__clear_bit(msr, msr_bitmap + 0x000 / f); /* read-low */
-		__clear_bit(msr, msr_bitmap + 0x800 / f); /* write-low */
+		if (type & MSR_TYPE_R)
+			/* read-low */
+			__clear_bit(msr, msr_bitmap + 0x000 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-low */
+			__clear_bit(msr, msr_bitmap + 0x800 / f);
+
 	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
 		msr &= 0x1fff;
-		__clear_bit(msr, msr_bitmap + 0x400 / f); /* read-high */
-		__clear_bit(msr, msr_bitmap + 0xc00 / f); /* write-high */
+		if (type & MSR_TYPE_R)
+			/* read-high */
+			__clear_bit(msr, msr_bitmap + 0x400 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-high */
+			__clear_bit(msr, msr_bitmap + 0xc00 / f);
+
 	}
 }
 
 static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only)
 {
 	if (!longmode_only)
-		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, msr);
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, msr);
+		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy,
+						msr, MSR_TYPE_R | MSR_TYPE_W);
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode,
+						msr, MSR_TYPE_R | MSR_TYPE_W);
+}
+
+static void vmx_disable_intercept_for_msr_read(u32 msr, bool longmode_only)
+{
+	if (!longmode_only)
+		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy,
+						msr, MSR_TYPE_R);
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode,
+					msr, MSR_TYPE_R);
+}
+
+static void vmx_disable_intercept_for_msr_write(u32 msr, bool longmode_only)
+{
+	if (!longmode_only)
+		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy,
+						msr, MSR_TYPE_W);
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode,
+					msr, MSR_TYPE_W);
 }
 
 /*
@@ -3864,6 +3900,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 	if (!enable_apicv_reg_vid)
 		exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
 				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+	exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 	return exec_control;
 }
 
@@ -6274,6 +6311,34 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu)
 	spin_unlock(&vmx->eoi_bitmap_lock);
 }
 
+static void vmx_enable_virtual_x2apic_mode(struct kvm_vcpu *vcpu)
+{
+	u32 exec_control;
+	int msr;
+
+	if (!enable_apicv_reg_vid)
+		return;
+
+	exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+	if (!(exec_control & CPU_BASED_TPR_SHADOW))
+		return;
+	exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+	exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+	exec_control |= SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+
+	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
+
+	for (msr = 0x800; msr <= 0x8ff; msr++)
+		vmx_disable_intercept_for_msr_read(msr, false);
+
+	/* TPR */
+	vmx_disable_intercept_for_msr_write(0x808, false);
+	/* EOI */
+	vmx_disable_intercept_for_msr_write(0x80b, false);
+	/* SELF-IPI */
+	vmx_disable_intercept_for_msr_write(0x83f, false);
+}
+
 static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;
@@ -7544,6 +7609,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.update_exitmap_end = vmx_update_exitmap_end,
 	.load_eoi_exitmap = vmx_load_eoi_exitmap,
 	.restore_rvi = vmx_restore_rvi,
+	.enable_virtual_x2apic_mode = vmx_enable_virtual_x2apic_mode,
 
 	.set_tss_addr = vmx_set_tss_addr,
 	.get_tdp_level = get_ept_level,
-- 
1.7.1