x86, apicv: add virtual interrupt delivery support

Virtual interrupt delivery avoids KVM to inject vAPIC interrupts
manually, which is fully taken care of by the hardware. This needs
some special awareness into existing interrupr injection path:

- for pending interrupt, instead of direct injection, we may need
  update architecture specific indicators before resuming to guest.

- A pending interrupt, which is masked by ISR, should be also
  considered in above update action, since hardware will decide
  when to inject it at right time. Current has_interrupt and
  get_interrupt only returns a valid vector from injection p.o.v.

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, 109 insertions, 10 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3ce8a16..0cf74a6 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -84,8 +84,8 @@ module_param(vmm_exclusive, bool, S_IRUGO);
 static bool __read_mostly fasteoi = 1;
 module_param(fasteoi, bool, S_IRUGO);
 
-static bool __read_mostly enable_apicv_reg = 1;
-module_param(enable_apicv_reg, bool, S_IRUGO);
+static bool __read_mostly enable_apicv_reg_vid = 1;
+module_param(enable_apicv_reg_vid, bool, S_IRUGO);
 
 /*
  * If nested=1, nested virtualization is supported, i.e., guests may use
@@ -781,6 +781,12 @@ static inline bool cpu_has_vmx_apic_register_virt(void)
 		SECONDARY_EXEC_APIC_REGISTER_VIRT;
 }
 
+static inline bool cpu_has_vmx_virtual_intr_delivery(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
+}
+
 static inline bool cpu_has_vmx_flexpriority(void)
 {
 	return cpu_has_vmx_tpr_shadow() &&
@@ -2571,7 +2577,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 			SECONDARY_EXEC_PAUSE_LOOP_EXITING |
 			SECONDARY_EXEC_RDTSCP |
 			SECONDARY_EXEC_ENABLE_INVPCID |
-			SECONDARY_EXEC_APIC_REGISTER_VIRT;
+			SECONDARY_EXEC_APIC_REGISTER_VIRT |
+			SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
 		if (adjust_vmx_controls(min2, opt2,
 					MSR_IA32_VMX_PROCBASED_CTLS2,
 					&_cpu_based_2nd_exec_control) < 0)
@@ -2586,7 +2593,8 @@ 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_VIRTUALIZE_X2APIC_MODE);
+				SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
+				SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
 
 	if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) {
 		/* CR3 accesses and invlpg don't need to cause VM Exits when EPT
@@ -2785,8 +2793,14 @@ static __init int hardware_setup(void)
 	if (!cpu_has_vmx_ple())
 		ple_gap = 0;
 
-	if (!cpu_has_vmx_apic_register_virt())
-		enable_apicv_reg = 0;
+	if (!cpu_has_vmx_apic_register_virt() ||
+				!cpu_has_vmx_virtual_intr_delivery())
+		enable_apicv_reg_vid = 0;
+
+	if (enable_apicv_reg_vid)
+		kvm_x86_ops->update_cr8_intercept = NULL;
+	else
+		kvm_x86_ops->hwapic_irr_update = NULL;
 
 	if (nested)
 		nested_vmx_setup_ctls_msrs();
@@ -3928,6 +3942,11 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
 	return exec_control;
 }
 
+static int vmx_vm_has_apicv(struct kvm *kvm)
+{
+	return enable_apicv_reg_vid && irqchip_in_kernel(kvm);
+}
+
 static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 {
 	u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
@@ -3945,8 +3964,9 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 		exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
 	if (!ple_gap)
 		exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
-	if (!enable_apicv_reg || !irqchip_in_kernel(vmx->vcpu.kvm))
-		exec_control &= ~SECONDARY_EXEC_APIC_REGISTER_VIRT;
+	if (!vmx_vm_has_apicv(vmx->vcpu.kvm))
+		exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
 	exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 	return exec_control;
 }
@@ -3992,6 +4012,15 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 				vmx_secondary_exec_control(vmx));
 	}
 
+	if (enable_apicv_reg_vid) {
+		vmcs_write64(EOI_EXIT_BITMAP0, 0);
+		vmcs_write64(EOI_EXIT_BITMAP1, 0);
+		vmcs_write64(EOI_EXIT_BITMAP2, 0);
+		vmcs_write64(EOI_EXIT_BITMAP3, 0);
+
+		vmcs_write16(GUEST_INTR_STATUS, 0);
+	}
+
 	if (ple_gap) {
 		vmcs_write32(PLE_GAP, ple_gap);
 		vmcs_write32(PLE_WINDOW, ple_window);
@@ -4906,6 +4935,16 @@ static int handle_apic_access(struct kvm_vcpu *vcpu)
 	return emulate_instruction(vcpu, 0) == EMULATE_DONE;
 }
 
+static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	int vector = exit_qualification & 0xff;
+
+	/* EOI-induced VM exit is trap-like and thus no need to adjust IP */
+	kvm_apic_set_eoi_accelerated(vcpu, vector);
+	return 1;
+}
+
 static int handle_apic_write(struct kvm_vcpu *vcpu)
 {
 	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
@@ -5851,6 +5890,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_TPR_BELOW_THRESHOLD]     = handle_tpr_below_threshold,
 	[EXIT_REASON_APIC_ACCESS]             = handle_apic_access,
 	[EXIT_REASON_APIC_WRITE]              = handle_apic_write,
+	[EXIT_REASON_EOI_INDUCED]             = handle_apic_eoi_induced,
 	[EXIT_REASON_WBINVD]                  = handle_wbinvd,
 	[EXIT_REASON_XSETBV]                  = handle_xsetbv,
 	[EXIT_REASON_TASK_SWITCH]             = handle_task_switch,
@@ -6208,7 +6248,8 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	 * There is not point to enable virtualize x2apic without enable
 	 * apicv
 	 */
-	if (!cpu_has_vmx_virtualize_x2apic_mode() || !enable_apicv_reg)
+	if (!cpu_has_vmx_virtualize_x2apic_mode() ||
+				!vmx_vm_has_apicv(vcpu->kvm))
 		return;
 
 	if (!vm_need_tpr_shadow(vcpu->kvm))
@@ -6228,6 +6269,56 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	vmx_set_msr_bitmap(vcpu);
 }
 
+static void vmx_hwapic_isr_update(struct kvm *kvm, int isr)
+{
+	u16 status;
+	u8 old;
+
+	if (!vmx_vm_has_apicv(kvm))
+		return;
+
+	if (isr == -1)
+		isr = 0;
+
+	status = vmcs_read16(GUEST_INTR_STATUS);
+	old = status >> 8;
+	if (isr != old) {
+		status &= 0xff;
+		status |= isr << 8;
+		vmcs_write16(GUEST_INTR_STATUS, status);
+	}
+}
+
+static void vmx_set_rvi(int vector)
+{
+	u16 status;
+	u8 old;
+
+	status = vmcs_read16(GUEST_INTR_STATUS);
+	old = (u8)status & 0xff;
+	if ((u8)vector != old) {
+		status &= ~0xff;
+		status |= (u8)vector;
+		vmcs_write16(GUEST_INTR_STATUS, status);
+	}
+}
+
+static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
+{
+	if (max_irr == -1)
+		return;
+
+	vmx_set_rvi(max_irr);
+}
+
+static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+{
+	vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]);
+	vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]);
+	vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]);
+	vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]);
+}
+
 static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;
@@ -7492,6 +7583,10 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
 	.set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
+	.vm_has_apicv = vmx_vm_has_apicv,
+	.load_eoi_exitmap = vmx_load_eoi_exitmap,
+	.hwapic_irr_update = vmx_hwapic_irr_update,
+	.hwapic_isr_update = vmx_hwapic_isr_update,
 
 	.set_tss_addr = vmx_set_tss_addr,
 	.get_tdp_level = get_ept_level,
@@ -7594,7 +7689,7 @@ static int __init vmx_init(void)
 	memcpy(vmx_msr_bitmap_longmode_x2apic,
 			vmx_msr_bitmap_longmode, PAGE_SIZE);
 
-	if (enable_apicv_reg) {
+	if (enable_apicv_reg_vid) {
 		for (msr = 0x800; msr <= 0x8ff; msr++)
 			vmx_disable_intercept_msr_read_x2apic(msr);
 
@@ -7606,6 +7701,10 @@ static int __init vmx_init(void)
 		vmx_enable_intercept_msr_read_x2apic(0x839);
 		/* TPR */
 		vmx_disable_intercept_msr_write_x2apic(0x808);
+		/* EOI */
+		vmx_disable_intercept_msr_write_x2apic(0x80b);
+		/* SELF-IPI */
+		vmx_disable_intercept_msr_write_x2apic(0x83f);
 	}
 
 	if (enable_ept) {