KVM: MMU: mmio page fault support

The idea is from Avi:

| We could cache the result of a miss in an spte by using a reserved bit, and
| checking the page fault error code (or seeing if we get an ept violation or
| ept misconfiguration), so if we get repeated mmio on a page, we don't need to
| search the slot list/tree.
| (https://lkml.org/lkml/2011/2/22/221)

When the page fault is caused by mmio, we cache the info in the shadow page
table, and also set the reserved bits in the shadow page table, so if the mmio
is caused again, we can quickly identify it and emulate it directly

Searching mmio gfn in memslots is heavy since we need to walk all memeslots, it
can be reduced by this feature, and also avoid walking guest page table for
soft mmu.

[jan: fix operator precedence issue]

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

arch/x86/kvm/paging_tmpl.h

@@ -577,6 +577,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
+	if (unlikely(error_code & PFERR_RSVD_MASK))
+		return handle_mmio_page_fault(vcpu, addr, error_code,
+					      mmu_is_nested(vcpu));
+
 	r = mmu_topup_memory_caches(vcpu);
 	if (r)
 		return r;
@@ -684,7 +688,8 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 					--vcpu->kvm->stat.lpages;
 				drop_spte(vcpu->kvm, sptep);
 				need_flush = 1;
-			}
+			} else if (is_mmio_spte(*sptep))
+				mmu_spte_clear_no_track(sptep);
 
 			break;
 		}
@@ -780,7 +785,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 		gpa_t pte_gpa;
 		gfn_t gfn;
 
-		if (!is_shadow_present_pte(sp->spt[i]))
+		if (!sp->spt[i])
 			continue;
 
 		pte_gpa = first_pte_gpa + i * sizeof(pt_element_t);
@@ -789,13 +794,18 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 					  sizeof(pt_element_t)))
 			return -EINVAL;
 
-		gfn = gpte_to_gfn(gpte);
-
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
 			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
 
+		gfn = gpte_to_gfn(gpte);
+		pte_access = sp->role.access;
+		pte_access &= FNAME(gpte_access)(vcpu, gpte, true);
+
+		if (sync_mmio_spte(&sp->spt[i], gfn, pte_access, &nr_present))
+			continue;
+
 		if (gfn != sp->gfns[i]) {
 			drop_spte(vcpu->kvm, &sp->spt[i]);
 			vcpu->kvm->tlbs_dirty++;
@@ -803,8 +813,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 		}
 
 		nr_present++;
-		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte,
-								  true);
+
 		host_writable = sp->spt[i] & SPTE_HOST_WRITEABLE;
 
 		set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,