KVM: x86: use kvm_read_guest_page for emulator accesses

Emulator accesses are always done a page at a time, either by the emulator
itself (for fetches) or because we need to query the MMU for address
translations.  Speed up these accesses by using kvm_read_guest_page
and, in the case of fetches, by inlining kvm_read_guest_virt_helper and
dropping the loop around kvm_read_guest_page.

This final tweak saves 30-100 more clock cycles (4-10%), bringing the
count (as measured by kvm-unit-tests) down to 720-1100 clock cycles on
a Sandy Bridge Xeon host, compared to 2300-3200 before the whole series
and 925-1700 after the first two low-hanging fruit changes.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/x86.c

@@ -4085,7 +4085,8 @@ static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
 
 		if (gpa == UNMAPPED_GVA)
 			return X86EMUL_PROPAGATE_FAULT;
-		ret = kvm_read_guest(vcpu->kvm, gpa, data, toread);
+		ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, data,
+					  offset, toread);
 		if (ret < 0) {
 			r = X86EMUL_IO_NEEDED;
 			goto out;
@@ -4106,10 +4107,24 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt,
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+	unsigned offset;
+	int ret;
 
-	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu,
-					  access | PFERR_FETCH_MASK,
-					  exception);
+	/* Inline kvm_read_guest_virt_helper for speed.  */
+	gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access|PFERR_FETCH_MASK,
+						    exception);
+	if (unlikely(gpa == UNMAPPED_GVA))
+		return X86EMUL_PROPAGATE_FAULT;
+
+	offset = addr & (PAGE_SIZE-1);
+	if (WARN_ON(offset + bytes > PAGE_SIZE))
+		bytes = (unsigned)PAGE_SIZE - offset;
+	ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, val,
+				  offset, bytes);
+	if (unlikely(ret < 0))
+		return X86EMUL_IO_NEEDED;
+
+	return X86EMUL_CONTINUE;
 }
 
 int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt,