KVM: x86: retry non-page-table writing instructions

If the emulation is caused by #PF and it is non-page_table writing instruction,
it means the VM-EXIT is caused by shadow page protected, we can zap the shadow
page and retry this instruction directly

The idea is from Avi

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

1 files changed, 19 insertions, 6 deletions

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 232c5a30ddc8..7a22eb81b4ca 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1998,7 +1998,7 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
         kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages;
 }
 
-static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
+int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 {
         struct kvm_mmu_page *sp;
         struct hlist_node *node;
@@ -2007,7 +2007,7 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 
         pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
         r = 0;
-
+        spin_lock(&kvm->mmu_lock);
         for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) {
                 pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
                          sp->role.word);
@@ -2015,8 +2015,11 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
                 kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
         }
         kvm_mmu_commit_zap_page(kvm, &invalid_list);
+        spin_unlock(&kvm->mmu_lock);
+
         return r;
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
 
 static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
 {
@@ -3698,9 +3701,8 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
 
         gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
 
-        spin_lock(&vcpu->kvm->mmu_lock);
         r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
-        spin_unlock(&vcpu->kvm->mmu_lock);
+
         return r;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt);
@@ -3721,10 +3723,18 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
         kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
 }
 
+static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr)
+{
+        if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu))
+                return vcpu_match_mmio_gpa(vcpu, addr);
+
+        return vcpu_match_mmio_gva(vcpu, addr);
+}
+
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
                        void *insn, int insn_len)
 {
-        int r;
+        int r, emulation_type = EMULTYPE_RETRY;
         enum emulation_result er;
 
         r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false);
@@ -3736,7 +3746,10 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
                 goto out;
         }
 
-        er = x86_emulate_instruction(vcpu, cr2, 0, insn, insn_len);
+        if (is_mmio_page_fault(vcpu, cr2))
+                emulation_type = 0;
+
+        er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
 
         switch (er) {
         case EMULATE_DONE: