KVM: x86: improve reexecute_instruction

The current reexecute_instruction can not well detect the failed instruction
emulation. It allows guest to retry all the instructions except it accesses
on error pfn

For example, some cases are nested-write-protect - if the page we want to
write is used as PDE but it chains to itself. Under this case, we should
stop the emulation and report the case to userspace

Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

1 files changed, 18 insertions, 4 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6f9cab071eca..e00dd0515a84 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4751,7 +4751,8 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
         return r;
 }
 
-static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2)
+static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
+                                  bool write_fault_to_shadow_pgtable)
 {
         gpa_t gpa = cr2;
         pfn_t pfn;
@@ -4808,7 +4809,13 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2)
          * guest to let CPU execute the instruction.
          */
         kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
-        return true;
+
+        /*
+         * If the access faults on its page table, it can not
+         * be fixed by unprotecting shadow page and it should
+         * be reported to userspace.
+         */
+        return !write_fault_to_shadow_pgtable;
 }
 
 static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
@@ -4867,7 +4874,13 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
         int r;
         struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
         bool writeback = true;
+        bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
 
+        /*
+         * Clear write_fault_to_shadow_pgtable here to ensure it is
+         * never reused.
+         */
+        vcpu->arch.write_fault_to_shadow_pgtable = false;
         kvm_clear_exception_queue(vcpu);
 
         if (!(emulation_type & EMULTYPE_NO_DECODE)) {
@@ -4886,7 +4899,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
                 if (r != EMULATION_OK)  {
                         if (emulation_type & EMULTYPE_TRAP_UD)
                                 return EMULATE_FAIL;
-                        if (reexecute_instruction(vcpu, cr2))
+                        if (reexecute_instruction(vcpu, cr2,
+                                                  write_fault_to_spt))
                                 return EMULATE_DONE;
                         if (emulation_type & EMULTYPE_SKIP)
                                 return EMULATE_FAIL;
@@ -4916,7 +4930,7 @@ restart:
                 return EMULATE_DONE;
 
         if (r == EMULATION_FAILED) {
-                if (reexecute_instruction(vcpu, cr2))
+                if (reexecute_instruction(vcpu, cr2, write_fault_to_spt))
                         return EMULATE_DONE;
 
                 return handle_emulation_failure(vcpu);