KVM: Implement perf callbacks for guest sampling

Below patch implements the perf_guest_info_callbacks on kvm.

Signed-off-by: Zhang Yanmin <yanmin_zhang@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 686492e..82be6da 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3654,8 +3654,11 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
 
        /* We need to handle NMIs before interrupts are enabled */
        if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
-           (exit_intr_info & INTR_INFO_VALID_MASK))
+           (exit_intr_info & INTR_INFO_VALID_MASK)) {
+               kvm_before_handle_nmi(&vmx->vcpu);
                asm("int $2");
+               kvm_after_handle_nmi(&vmx->vcpu);
+       }
 
        idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
 

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 24cd0ee..c3a33b2 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -40,6 +40,7 @@
 #include <linux/user-return-notifier.h>
 #include <linux/srcu.h>
 #include <linux/slab.h>
+#include <linux/perf_event.h>
 #include <trace/events/kvm.h>
 #undef TRACE_INCLUDE_FILE
 #define CREATE_TRACE_POINTS
@@ -3765,6 +3766,47 @@ static void kvm_timer_init(void)
        }
 }
 
+static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
+
+static int kvm_is_in_guest(void)
+{
+       return percpu_read(current_vcpu) != NULL;
+}
+
+static int kvm_is_user_mode(void)
+{
+       int user_mode = 3;
+       if (percpu_read(current_vcpu))
+               user_mode = kvm_x86_ops->get_cpl(percpu_read(current_vcpu));
+       return user_mode != 0;
+}
+
+static unsigned long kvm_get_guest_ip(void)
+{
+       unsigned long ip = 0;
+       if (percpu_read(current_vcpu))
+               ip = kvm_rip_read(percpu_read(current_vcpu));
+       return ip;
+}
+
+static struct perf_guest_info_callbacks kvm_guest_cbs = {
+       .is_in_guest            = kvm_is_in_guest,
+       .is_user_mode           = kvm_is_user_mode,
+       .get_guest_ip           = kvm_get_guest_ip,
+};
+
+void kvm_before_handle_nmi(struct kvm_vcpu *vcpu)
+{
+       percpu_write(current_vcpu, vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_before_handle_nmi);
+
+void kvm_after_handle_nmi(struct kvm_vcpu *vcpu)
+{
+       percpu_write(current_vcpu, NULL);
+}
+EXPORT_SYMBOL_GPL(kvm_after_handle_nmi);
+
 int kvm_arch_init(void *opaque)
 {
        int r;
@@ -3801,6 +3843,8 @@ int kvm_arch_init(void *opaque)
 
        kvm_timer_init();
 
+       perf_register_guest_info_callbacks(&kvm_guest_cbs);
+
        return 0;
 
 out:
@@ -3809,6 +3853,8 @@ out:
 
 void kvm_arch_exit(void)
 {
+       perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
+
        if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
                cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
                                            CPUFREQ_TRANSITION_NOTIFIER);

diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 2d10163..b7a4047 100644 (file)
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -65,4 +65,7 @@ static inline int is_paging(struct kvm_vcpu *vcpu)
        return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
 }
 
+void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
+void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
+
 #endif