Re: [Qemu-devel] E5-2620v2 - emulation stop error

[Radim Krčmář]

2015-03-31 17:56+0300, Andrey Korolyov:
> > Chasing the culprit this way could take a long time, so a new tracepoint
> > that shows if 0xef is set on entry would let us guess the bug faster ...
> >
> > Please provide a failing trace with the following patch:
>
> Thanks, please see below:
> 
> http://xdel.ru/downloads/kvm-e5v2-issue/new-tracepoint-fail-with-apicv.dat.gz

 qemu-system-x86-4022  [006]  255.915978:
  kvm_entry:            vcpu 0
  kvm_emulate_insn:     f0000:d275: ea 7a d2 00 f0
  kvm_emulate_insn:     f0000:d27a: 2e 0f 01 1e f0 6c
  kvm_emulate_insn:     f0000:d280: 31 c0
  kvm_emulate_insn:     f0000:d282: 8e e0
  kvm_emulate_insn:     f0000:d284: 8e e8
  kvm_emulate_insn:     f0000:d286: 8e c0
  kvm_emulate_insn:     f0000:d288: 8e d8
  kvm_emulate_insn:     f0000:d28a: 8e d0
  kvm_entry:            vcpu 0
  kvm_0xef:             irr clear, isr clear, vmcs 0x0
  kvm_exit:             reason EPT_VIOLATION rip 0x8dd0 info 184 0
  kvm_page_fault:       address f8dd0 error_code 184
  kvm_entry:            vcpu 0
  kvm_0xef:             irr clear, isr clear, vmcs 0x0
  kvm_exit:             reason EPT_VIOLATION rip 0x76d6 info 184 0
  kvm_page_fault:       address f76d6 error_code 184
  kvm_entry:            vcpu 0
  kvm_0xef:             irr clear, isr clear, vmcs 0x0
  kvm_exit:             reason EXCEPTION_NMI rip 0xd331 info 0 80000b0d
  kvm_userspace_exit:   reason KVM_EXIT_INTERNAL_ERROR (17)

Ok, nothing obvious here either ... I've desperately added all
information I know about.  Please run it again, thanks.

(The patch has to be applied instead of the previous one.)
---
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 7c7bc8bef21f..f986636ad9d0 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -742,6 +742,41 @@ TRACE_EVENT(kvm_emulate_insn,
 #define trace_kvm_emulate_insn_start(vcpu) trace_kvm_emulate_insn(vcpu, 0)
 #define trace_kvm_emulate_insn_failed(vcpu) trace_kvm_emulate_insn(vcpu, 1)
 
+TRACE_EVENT(kvm_0xef,
+       TP_PROTO(bool irr, bool isr, u32 info, bool on, bool pir, u16 status),
+       TP_ARGS(irr, isr, info, on, pir, status),
+
+       TP_STRUCT__entry(
+               __field(bool,  irr )
+               __field(bool,  isr )
+               __field(u32,   info)
+               __field(bool,  on  )
+               __field(bool,  pir )
+               __field(u8,    rvi )
+               __field(u8,    svi )
+               ),
+
+       TP_fast_assign(
+               __entry->irr  = irr;
+               __entry->isr  = isr;
+               __entry->info = info;
+               __entry->on   = on;
+               __entry->pir  = pir;
+               __entry->rvi  = status & 0xff;
+               __entry->svi  = status >> 8;
+               ),
+
+       TP_printk("irr %s, isr %s, info 0x%x, on %s, pir %s, rvi 0x%x, svi 
0x%x",
+                 __entry->irr ? "set  " : "clear",
+                 __entry->isr ? "set  " : "clear",
+                 __entry->info,
+                 __entry->on  ? "set  " : "clear",
+                 __entry->pir ? "set  " : "clear",
+                 __entry->rvi,
+                 __entry->svi
+                )
+       );
+
 TRACE_EVENT(
        vcpu_match_mmio,
        TP_PROTO(gva_t gva, gpa_t gpa, bool write, bool gpa_match),
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index eee63dc33d89..b461edc93d53 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5047,6 +5047,25 @@ static int handle_machine_check(struct kvm_vcpu *vcpu)
        return 1;
 }
 
+#define VEC_POS(v) ((v) & (32 - 1))
+#define REG_POS(v) (((v) >> 5) << 4)
+static inline int apic_test_vector(int vec, void *bitmap)
+{
+       return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+}
+
+static inline void random_trace(struct kvm_vcpu *vcpu)
+{
+       struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+       trace_kvm_0xef(apic_test_vector(0xef, vcpu->arch.apic->regs + APIC_IRR),
+                      apic_test_vector(0xef, vcpu->arch.apic->regs + APIC_ISR),
+                      vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
+                      test_bit(POSTED_INTR_ON, (unsigned long 
*)&vmx->pi_desc.control),
+                      test_bit(0xef, (unsigned long *)vmx->pi_desc.pir),
+                      vmcs_read16(GUEST_INTR_STATUS));
+}
+
 static int handle_exception(struct kvm_vcpu *vcpu)
 {
        struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -5077,6 +5096,8 @@ static int handle_exception(struct kvm_vcpu *vcpu)
                return 1;
        }
 
+       random_trace(vcpu);
+
        error_code = 0;
        if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
                error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
@@ -8143,6 +8164,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
        if (vmx->emulation_required)
                return;
 
+       random_trace(vcpu);
+
        if (vmx->ple_window_dirty) {
                vmx->ple_window_dirty = false;
                vmcs_write32(PLE_WINDOW, vmx->ple_window);
@@ -8312,6 +8335,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
        vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
        trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX);
 
+       random_trace(vcpu);
+
        /*
         * the KVM_REQ_EVENT optimization bit is only on for one entry, and if
         * we did not inject a still-pending event to L1 now because of
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 32bf19ef3115..a45fa01bd354 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7881,3 +7881,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_0xef);