KVM: VMX: Enable acknowledge interupt on vmexit

The "acknowledge interrupt on exit" feature controls processor behavior
for external interrupt acknowledgement. When this control is set, the
processor acknowledges the interrupt controller to acquire the
interrupt vector on VM exit.

After enabling this feature, an interrupt which arrived when target cpu is
running in vmx non-root mode will be handled by vmx handler instead of handler
in idt. Currently, vmx handler only fakes an interrupt stack and jump to idt
table to let real handler to handle it. Further, we will recognize the interrupt
and only delivery the interrupt which not belong to current vcpu through idt table.
The interrupt which belonged to current vcpu will be handled inside vmx handler.
This will reduce the interrupt handle cost of KVM.

Also, interrupt enable logic is changed if this feature is turnning on:
Before this patch, hypervior call local_irq_enable() to enable it directly.
Now IF bit is set on interrupt stack frame, and will be enabled on a return from
interrupt handler if exterrupt interrupt exists. If no external interrupt, still
call local_irq_enable() to enable it.

Refer to Intel SDM volum 3, chapter 33.2.

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

arch/x86/include/asm/kvm_host.h

@@ -727,6 +727,7 @@ struct kvm_x86_ops {
 	int (*check_intercept)(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
 			       enum x86_intercept_stage stage);
+	void (*handle_external_intr)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_arch_async_pf {

arch/x86/kvm/svm.c

@@ -4233,6 +4233,11 @@ out:
 	return ret;
 }
 
+static void svm_handle_external_intr(struct kvm_vcpu *vcpu)
+{
+	local_irq_enable();
+}
+
 static struct kvm_x86_ops svm_x86_ops = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -4328,6 +4333,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.set_tdp_cr3 = set_tdp_cr3,
 
 	.check_intercept = svm_check_intercept,
+	.handle_external_intr = svm_handle_external_intr,
 };
 
 static int __init svm_init(void)

arch/x86/kvm/vmx.c

@@ -378,6 +378,7 @@ struct vcpu_vmx {
 	struct shared_msr_entry *guest_msrs;
 	int                   nmsrs;
 	int                   save_nmsrs;
+	unsigned long	      host_idt_base;
 #ifdef CONFIG_X86_64
 	u64 		      msr_host_kernel_gs_base;
 	u64 		      msr_guest_kernel_gs_base;
@@ -2627,7 +2628,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 #ifdef CONFIG_X86_64
 	min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
 #endif
-	opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT;
+	opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT |
+		VM_EXIT_ACK_INTR_ON_EXIT;
 	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
 				&_vmexit_control) < 0)
 		return -EIO;
@@ -3879,7 +3881,7 @@ static void vmx_disable_intercept_msr_write_x2apic(u32 msr)
  * Note that host-state that does change is set elsewhere. E.g., host-state
  * that is set differently for each CPU is set in vmx_vcpu_load(), not here.
  */
-static void vmx_set_constant_host_state(void)
+static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 {
 	u32 low32, high32;
 	unsigned long tmpl;
@@ -3907,6 +3909,7 @@ static void vmx_set_constant_host_state(void)
 
 	native_store_idt(&dt);
 	vmcs_writel(HOST_IDTR_BASE, dt.address);   /* 22.2.4 */
+	vmx->host_idt_base = dt.address;
 
 	vmcs_writel(HOST_RIP, vmx_return); /* 22.2.5 */
 
@@ -4039,7 +4042,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	vmcs_write16(HOST_FS_SELECTOR, 0);            /* 22.2.4 */
 	vmcs_write16(HOST_GS_SELECTOR, 0);            /* 22.2.4 */
-	vmx_set_constant_host_state();
+	vmx_set_constant_host_state(vmx);
 #ifdef CONFIG_X86_64
 	rdmsrl(MSR_FS_BASE, a);
 	vmcs_writel(HOST_FS_BASE, a); /* 22.2.4 */
@@ -6399,6 +6402,52 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 	}
 }
 
+static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
+{
+	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+
+	/*
+	 * If external interrupt exists, IF bit is set in rflags/eflags on the
+	 * interrupt stack frame, and interrupt will be enabled on a return
+	 * from interrupt handler.
+	 */
+	if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
+			== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) {
+		unsigned int vector;
+		unsigned long entry;
+		gate_desc *desc;
+		struct vcpu_vmx *vmx = to_vmx(vcpu);
+#ifdef CONFIG_X86_64
+		unsigned long tmp;
+#endif
+
+		vector =  exit_intr_info & INTR_INFO_VECTOR_MASK;
+		desc = (gate_desc *)vmx->host_idt_base + vector;
+		entry = gate_offset(*desc);
+		asm volatile(
+#ifdef CONFIG_X86_64
+			"mov %%" _ASM_SP ", %[sp]\n\t"
+			"and $0xfffffffffffffff0, %%" _ASM_SP "\n\t"
+			"push $%c[ss]\n\t"
+			"push %[sp]\n\t"
+#endif
+			"pushf\n\t"
+			"orl $0x200, (%%" _ASM_SP ")\n\t"
+			__ASM_SIZE(push) " $%c[cs]\n\t"
+			"call *%[entry]\n\t"
+			:
+#ifdef CONFIG_X86_64
+			[sp]"=&r"(tmp)
+#endif
+			:
+			[entry]"r"(entry),
+			[ss]"i"(__KERNEL_DS),
+			[cs]"i"(__KERNEL_CS)
+			);
+	} else
+		local_irq_enable();
+}
+
 static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;
@@ -7041,7 +7090,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	 * Other fields are different per CPU, and will be set later when
 	 * vmx_vcpu_load() is called, and when vmx_save_host_state() is called.
 	 */
-	vmx_set_constant_host_state();
+	vmx_set_constant_host_state(vmx);
 
 	/*
 	 * HOST_RSP is normally set correctly in vmx_vcpu_run() just before
@@ -7718,6 +7767,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.set_tdp_cr3 = vmx_set_cr3,
 
 	.check_intercept = vmx_check_intercept,
+	.handle_external_intr = vmx_handle_external_intr,
 };
 
 static int __init vmx_init(void)

arch/x86/kvm/x86.c

@@ -5820,7 +5820,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
-	local_irq_enable();
+
+	/* Interrupt is enabled by handle_external_intr() */
+	kvm_x86_ops->handle_external_intr(vcpu);
 
 	++vcpu->stat.exits;