x86, apicv: add virtual x2apic support

basically to benefit from apicv, we need to enable virtualized x2apic mode.
Currently, we only enable it when guest is really using x2apic.

Also, clear MSR bitmap for corresponding x2apic MSRs when guest enabled x2apic:
0x800 - 0x8ff: no read intercept for apicv register virtualization,
               except APIC ID and TMCCT which need software's assistance to
               get right value.

Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Yang Zhang <yang.z.zhang@Intel.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>

1 files changed, 178 insertions, 20 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5ad7c8531083..3ce8a1629330 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -643,6 +643,8 @@ static unsigned long *vmx_io_bitmap_a;
 static unsigned long *vmx_io_bitmap_b;
 static unsigned long *vmx_msr_bitmap_legacy;
 static unsigned long *vmx_msr_bitmap_longmode;
+static unsigned long *vmx_msr_bitmap_legacy_x2apic;
+static unsigned long *vmx_msr_bitmap_longmode_x2apic;
 
 static bool cpu_has_load_ia32_efer;
 static bool cpu_has_load_perf_global_ctrl;
@@ -767,6 +769,12 @@ static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
 		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
 }
 
+static inline bool cpu_has_vmx_virtualize_x2apic_mode(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+}
+
 static inline bool cpu_has_vmx_apic_register_virt(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -1830,6 +1838,25 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
 	vmx->guest_msrs[from] = tmp;
 }
 
+static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
+{
+	unsigned long *msr_bitmap;
+
+	if (irqchip_in_kernel(vcpu->kvm) && apic_x2apic_mode(vcpu->arch.apic)) {
+		if (is_long_mode(vcpu))
+			msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
+		else
+			msr_bitmap = vmx_msr_bitmap_legacy_x2apic;
+	} else {
+		if (is_long_mode(vcpu))
+			msr_bitmap = vmx_msr_bitmap_longmode;
+		else
+			msr_bitmap = vmx_msr_bitmap_legacy;
+	}
+
+	vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
+}
+
 /*
  * Set up the vmcs to automatically save and restore system
  * msrs.  Don't touch the 64-bit msrs if the guest is in legacy
@@ -1838,7 +1865,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
 static void setup_msrs(struct vcpu_vmx *vmx)
 {
 	int save_nmsrs, index;
-	unsigned long *msr_bitmap;
 
 	save_nmsrs = 0;
 #ifdef CONFIG_X86_64
@@ -1870,14 +1896,8 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 
 	vmx->save_nmsrs = save_nmsrs;
 
-	if (cpu_has_vmx_msr_bitmap()) {
-		if (is_long_mode(&vmx->vcpu))
-			msr_bitmap = vmx_msr_bitmap_longmode;
-		else
-			msr_bitmap = vmx_msr_bitmap_legacy;
-
-		vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
-	}
+	if (cpu_has_vmx_msr_bitmap())
+		vmx_set_msr_bitmap(&vmx->vcpu);
 }
 
 /*
@@ -2543,6 +2563,7 @@ 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 |
@@ -2564,7 +2585,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 
 	if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW))
 		_cpu_based_2nd_exec_control &= ~(
-				SECONDARY_EXEC_APIC_REGISTER_VIRT);
+				SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
 
 	if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) {
 		/* CR3 accesses and invlpg don't need to cause VM Exits when EPT
@@ -3725,7 +3747,10 @@ 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);
 
@@ -3738,20 +3763,93 @@ 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_enable_intercept_for_msr(unsigned long *msr_bitmap,
+						u32 msr, int type)
+{
+	int f = sizeof(unsigned long);
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return;
+
+	/*
+	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
+	 * have the write-low and read-high bitmap offsets the wrong way round.
+	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
+	 */
+	if (msr <= 0x1fff) {
+		if (type & MSR_TYPE_R)
+			/* read-low */
+			__set_bit(msr, msr_bitmap + 0x000 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-low */
+			__set_bit(msr, msr_bitmap + 0x800 / f);
+
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		if (type & MSR_TYPE_R)
+			/* read-high */
+			__set_bit(msr, msr_bitmap + 0x400 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-high */
+			__set_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_enable_intercept_msr_read_x2apic(u32 msr)
+{
+	__vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
+			msr, MSR_TYPE_R);
+	__vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
+			msr, MSR_TYPE_R);
+}
+
+static void vmx_disable_intercept_msr_read_x2apic(u32 msr)
+{
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
+			msr, MSR_TYPE_R);
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
+			msr, MSR_TYPE_R);
+}
+
+static void vmx_disable_intercept_msr_write_x2apic(u32 msr)
+{
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
+			msr, MSR_TYPE_W);
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
+			msr, MSR_TYPE_W);
 }
 
 /*
@@ -3849,6 +3947,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 		exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
 	if (!enable_apicv_reg || !irqchip_in_kernel(vmx->vcpu.kvm))
 		exec_control &= ~SECONDARY_EXEC_APIC_REGISTER_VIRT;
+	exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 	return exec_control;
 }
 
@@ -6101,6 +6200,34 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 	vmcs_write32(TPR_THRESHOLD, irr);
 }
 
+static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
+{
+	u32 sec_exec_control;
+
+	/*
+	 * There is not point to enable virtualize x2apic without enable
+	 * apicv
+	 */
+	if (!cpu_has_vmx_virtualize_x2apic_mode() || !enable_apicv_reg)
+		return;
+
+	if (!vm_need_tpr_shadow(vcpu->kvm))
+		return;
+
+	sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+
+	if (set) {
+		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+	} else {
+		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+	}
+	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
+
+	vmx_set_msr_bitmap(vcpu);
+}
+
 static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;
@@ -7364,6 +7491,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.enable_nmi_window = enable_nmi_window,
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
+	.set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
 
 	.set_tss_addr = vmx_set_tss_addr,
 	.get_tdp_level = get_ept_level,
@@ -7396,7 +7524,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 
 static int __init vmx_init(void)
 {
-	int r, i;
+	int r, i, msr;
 
 	rdmsrl_safe(MSR_EFER, &host_efer);
 
@@ -7417,11 +7545,19 @@ static int __init vmx_init(void)
 	if (!vmx_msr_bitmap_legacy)
 		goto out1;
 
+	vmx_msr_bitmap_legacy_x2apic =
+				(unsigned long *)__get_free_page(GFP_KERNEL);
+	if (!vmx_msr_bitmap_legacy_x2apic)
+		goto out2;
 
 	vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
 	if (!vmx_msr_bitmap_longmode)
-		goto out2;
+		goto out3;
 
+	vmx_msr_bitmap_longmode_x2apic =
+				(unsigned long *)__get_free_page(GFP_KERNEL);
+	if (!vmx_msr_bitmap_longmode_x2apic)
+		goto out4;
 
 	/*
 	 * Allow direct access to the PC debug port (it is often used for I/O
@@ -7453,6 +7589,24 @@ static int __init vmx_init(void)
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
+	memcpy(vmx_msr_bitmap_legacy_x2apic,
+			vmx_msr_bitmap_legacy, PAGE_SIZE);
+	memcpy(vmx_msr_bitmap_longmode_x2apic,
+			vmx_msr_bitmap_longmode, PAGE_SIZE);
+
+	if (enable_apicv_reg) {
+		for (msr = 0x800; msr <= 0x8ff; msr++)
+			vmx_disable_intercept_msr_read_x2apic(msr);
+
+		/* According SDM, in x2apic mode, the whole id reg is used.
+		 * But in KVM, it only use the highest eight bits. Need to
+		 * intercept it */
+		vmx_enable_intercept_msr_read_x2apic(0x802);
+		/* TMCCT */
+		vmx_enable_intercept_msr_read_x2apic(0x839);
+		/* TPR */
+		vmx_disable_intercept_msr_write_x2apic(0x808);
+	}
 
 	if (enable_ept) {
 		kvm_mmu_set_mask_ptes(0ull,
@@ -7466,8 +7620,10 @@ static int __init vmx_init(void)
 
 	return 0;
 
-out3:
+out4:
 	free_page((unsigned long)vmx_msr_bitmap_longmode);
+out3:
+	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
 out2:
 	free_page((unsigned long)vmx_msr_bitmap_legacy);
 out1:
@@ -7479,6 +7635,8 @@ out:
 
 static void __exit vmx_exit(void)
 {
+	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
+	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
 	free_page((unsigned long)vmx_msr_bitmap_legacy);
 	free_page((unsigned long)vmx_msr_bitmap_longmode);
 	free_page((unsigned long)vmx_io_bitmap_b);