KVM: inject #UD if instruction emulation fails and exit to userspace

Do not kill VM when instruction emulation fails. Inject #UD and report
failure to userspace instead. Userspace may choose to reenter guest if
vcpu is in userspace (cpl == 3) in which case guest OS will kill
offending process and continue running.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2ca1867ed97aa8f8821b6cd8473561d6e0a5cf29..0c06148fa3b1d4433a7e0d3966793a3495fdff43 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -576,7 +576,6 @@ enum emulation_result {
 #define EMULTYPE_SKIP              (1 << 2)
 int emulate_instruction(struct kvm_vcpu *vcpu,
                        unsigned long cr2, u16 error_code, int emulation_type);
-void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
 void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
 void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
 

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index be981b1f188113476f6d7dbc5680b17aa34c3cfc..4a02dee1f2b56286ecd113b0b9c89e034902ee39 100644 (file)
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2814,11 +2814,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
                return 1;
        case EMULATE_DO_MMIO:
                ++vcpu->stat.mmio_exits;
-               return 0;
+               /* fall through */
        case EMULATE_FAIL:
-               vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-               vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-               vcpu->run->internal.ndata = 0;
                return 0;
        default:
                BUG();

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 41fe0381a1ae55cb96f221106a444287121c7df2..134260c36ce2911c241544feeba464fb3159f33b 100644 (file)
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1535,7 +1535,7 @@ static int io_interception(struct vcpu_svm *svm)
        string = (io_info & SVM_IOIO_STR_MASK) != 0;
        in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
        if (string || in)
-               return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
+               return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
 
        port = io_info >> 16;
        size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
@@ -2386,16 +2386,12 @@ static int iret_interception(struct vcpu_svm *svm)
 
 static int invlpg_interception(struct vcpu_svm *svm)
 {
-       if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
-               pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
-       return 1;
+       return emulate_instruction(&svm->vcpu, 0, 0, 0) == EMULATE_DONE;
 }
 
 static int emulate_on_interception(struct vcpu_svm *svm)
 {
-       if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
-               pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
-       return 1;
+       return emulate_instruction(&svm->vcpu, 0, 0, 0) == EMULATE_DONE;
 }
 
 static int cr8_write_interception(struct vcpu_svm *svm)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 59893173425107289599fb472503d6a78157f1e5..a82cfa1e2a4054ae9b09d679e13e71ce9617f802 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3070,7 +3070,7 @@ static int handle_io(struct kvm_vcpu *vcpu)
        ++vcpu->stat.io_exits;
 
        if (string || in)
-               return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
+               return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
 
        port = exit_qualification >> 16;
        size = (exit_qualification & 7) + 1;
@@ -3327,22 +3327,7 @@ static int handle_wbinvd(struct kvm_vcpu *vcpu)
 
 static int handle_apic_access(struct kvm_vcpu *vcpu)
 {
-       unsigned long exit_qualification;
-       enum emulation_result er;
-       unsigned long offset;
-
-       exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-       offset = exit_qualification & 0xffful;
-
-       er = emulate_instruction(vcpu, 0, 0, 0);
-
-       if (er !=  EMULATE_DONE) {
-               printk(KERN_ERR
-                      "Fail to handle apic access vmexit! Offset is 0x%lx\n",
-                      offset);
-               return -ENOEXEC;
-       }
-       return 1;
+       return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
 }
 
 static int handle_task_switch(struct kvm_vcpu *vcpu)
@@ -3554,13 +3539,8 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
                        goto out;
                }
 
-               if (err != EMULATE_DONE) {
-                       vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-                       vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-                       vcpu->run->internal.ndata = 0;
-                       ret = 0;
-                       goto out;
-               }
+               if (err != EMULATE_DONE)
+                       return 0;
 
                if (signal_pending(current))
                        goto out;

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fc5611b4007f3594ffe757bf4d6a1f3e99156939..ae9d6f3e5d0d616a9e241ec5959f65e8f8dc0559 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3639,24 +3639,6 @@ int emulator_set_dr(int dr, unsigned long value, struct kvm_vcpu *vcpu)
        return __kvm_set_dr(vcpu, dr, value);
 }
 
-void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
-{
-       u8 opcodes[4];
-       unsigned long rip = kvm_rip_read(vcpu);
-       unsigned long rip_linear;
-
-       if (!printk_ratelimit())
-               return;
-
-       rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS);
-
-       kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu, NULL);
-
-       printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n",
-              context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]);
-}
-EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
-
 static u64 mk_cr_64(u64 curr_cr, u32 new_val)
 {
        return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
@@ -3863,6 +3845,19 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu)
                kvm_queue_exception(vcpu, ctxt->exception);
 }
 
+static int handle_emulation_failure(struct kvm_vcpu *vcpu)
+{
+       struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
+
+       ++vcpu->stat.insn_emulation_fail;
+       trace_kvm_emulate_insn_failed(vcpu);
+       vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+       vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+       vcpu->run->internal.ndata = 0;
+       kvm_queue_exception(vcpu, UD_VECTOR);
+       return EMULATE_FAIL;
+}
+
 int emulate_instruction(struct kvm_vcpu *vcpu,
                        unsigned long cr2,
                        u16 error_code,
@@ -3931,11 +3926,11 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 
                ++vcpu->stat.insn_emulation;
                if (r)  {
-                       ++vcpu->stat.insn_emulation_fail;
-                       trace_kvm_emulate_insn_failed(vcpu);
                        if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
                                return EMULATE_DONE;
-                       return EMULATE_FAIL;
+                       if (emulation_type & EMULTYPE_SKIP)
+                               return EMULATE_FAIL;
+                       return handle_emulation_failure(vcpu);
                }
        }
 
@@ -3960,9 +3955,7 @@ restart:
                if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
                        return EMULATE_DONE;
 
-               trace_kvm_emulate_insn_failed(vcpu);
-               kvm_report_emulation_failure(vcpu, "mmio");
-               return EMULATE_FAIL;
+               return handle_emulation_failure(vcpu);
        }
 
        toggle_interruptibility(vcpu, vcpu->arch.emulate_ctxt.interruptibility);
@@ -4798,7 +4791,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
                vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
                r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
                srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-               if (r == EMULATE_DO_MMIO) {
+               if (r != EMULATE_DONE) {
                        r = 0;
                        goto out;
                }