KVM: APIC: avoid instruction emulation for EOI writes

Instruction emulation for EOI writes can be skipped, since sane
guest simply uses MOV instead of string operations. This is a nice
improvement when guest doesn't support x2apic or hyper-V EOI
support.

a single VM bandwidth is observed with ~8% bandwidth improvement
(7.4Gbps->8Gbps), by saving ~5% cycles from EOI emulation.

Signed-off-by: Kevin Tian <kevin.tian@intel.com>
<Based on earlier work from>:
Signed-off-by: Eddie Dong <eddie.dong@intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

4 files changed, 43 insertions, 0 deletions

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 2caf290..31f180c 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -350,6 +350,18 @@ enum vmcs_field {
 #define DEBUG_REG_ACCESS_REG(eq)        (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */
 
 
+/*
+ * Exit Qualifications for APIC-Access
+ */
+#define APIC_ACCESS_OFFSET              0xfff   /* 11:0, offset within the APIC page */
+#define APIC_ACCESS_TYPE                0xf000  /* 15:12, access type */
+#define TYPE_LINEAR_APIC_INST_READ      (0 << 12)
+#define TYPE_LINEAR_APIC_INST_WRITE     (1 << 12)
+#define TYPE_LINEAR_APIC_INST_FETCH     (2 << 12)
+#define TYPE_LINEAR_APIC_EVENT          (3 << 12)
+#define TYPE_PHYSICAL_APIC_EVENT        (10 << 12)
+#define TYPE_PHYSICAL_APIC_INST         (15 << 12)
+
 /* segment AR */
 #define SEGMENT_AR_L_MASK (1 << 13)
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 57dcbd4..52645f2 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -864,6 +864,15 @@ static int apic_mmio_write(struct kvm_io_device *this,
 	return 0;
 }
 
+void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	if (apic)
+		apic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
+}
+EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
+
 void kvm_free_lapic(struct kvm_vcpu *vcpu)
 {
 	if (!vcpu->arch.apic)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 52c9e6b..8287243 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -26,6 +26,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu);
 void kvm_lapic_reset(struct kvm_vcpu *vcpu);
 u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
 void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
+void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu);
 void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value);
 u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu);
 void kvm_apic_set_version(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5e8d411..47419d6 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -71,6 +71,9 @@ module_param(vmm_exclusive, bool, S_IRUGO);
 static int __read_mostly yield_on_hlt = 1;
 module_param(yield_on_hlt, bool, S_IRUGO);
 
+static int __read_mostly fasteoi = 1;
+module_param(fasteoi, bool, S_IRUGO);
+
 /*
  * If nested=1, nested virtualization is supported, i.e., guests may use
  * VMX and be a hypervisor for its own guests. If nested=0, guests may not
@@ -4540,6 +4543,24 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu)
 
 static int handle_apic_access(struct kvm_vcpu *vcpu)
 {
+	if (likely(fasteoi)) {
+		unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+		int access_type, offset;
+
+		access_type = exit_qualification & APIC_ACCESS_TYPE;
+		offset = exit_qualification & APIC_ACCESS_OFFSET;
+		/*
+		 * Sane guest uses MOV to write EOI, with written value
+		 * not cared. So make a short-circuit here by avoiding
+		 * heavy instruction emulation.
+		 */
+		if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) &&
+		    (offset == APIC_EOI)) {
+			kvm_lapic_set_eoi(vcpu);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+	}
 	return emulate_instruction(vcpu, 0) == EMULATE_DONE;
 }