KVM: PPC: Make PV mtmsrd L=1 work with r30 and r31

We had an arbitrary limitation in mtmsrd L=1 that kept us from using r30 and
r31 as input registers. Let's get rid of that and get more potential speedups!
Signed-off-by: Alexander Graf <agraf@suse.de>

arch/powerpc/kernel/kvm.c

@@ -158,6 +158,7 @@ static u32 *kvm_alloc(int len)
 
 extern u32 kvm_emulate_mtmsrd_branch_offs;
 extern u32 kvm_emulate_mtmsrd_reg_offs;
+extern u32 kvm_emulate_mtmsrd_orig_ins_offs;
 extern u32 kvm_emulate_mtmsrd_len;
 extern u32 kvm_emulate_mtmsrd[];
 
@@ -186,7 +187,21 @@ static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
 	/* Modify the chunk to fit the invocation */
 	memcpy(p, kvm_emulate_mtmsrd, kvm_emulate_mtmsrd_len * 4);
 	p[kvm_emulate_mtmsrd_branch_offs] |= distance_end & KVM_INST_B_MASK;
+	switch (get_rt(rt)) {
+	case 30:
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsrd_reg_offs],
+				 magic_var(scratch2), KVM_RT_30);
+		break;
+	case 31:
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsrd_reg_offs],
+				 magic_var(scratch1), KVM_RT_30);
+		break;
+	default:
 		p[kvm_emulate_mtmsrd_reg_offs] |= rt;
+		break;
+	}
+
+	p[kvm_emulate_mtmsrd_orig_ins_offs] = *inst;
 	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsrd_len * 4);
 
 	/* Patch the invocation */
@@ -423,8 +438,6 @@ static void kvm_check_ins(u32 *inst, u32 features)
 
 	/* Rewrites */
 	case KVM_INST_MTMSRD_L1:
-		/* We use r30 and r31 during the hook */
-		if (get_rt(inst_rt) < 30)
 		kvm_patch_ins_mtmsrd(inst, inst_rt);
 		break;
 	case KVM_INST_MTMSR:

arch/powerpc/kernel/kvm_emul.S

@@ -78,7 +78,8 @@ kvm_emulate_mtmsrd:
 
 	/* OR the register's (MSR_EE|MSR_RI) on MSR */
 kvm_emulate_mtmsrd_reg:
-	andi.	r30, r0, (MSR_EE|MSR_RI)
+	ori	r30, r0, 0
+	andi.	r30, r30, (MSR_EE|MSR_RI)
 	or	r31, r31, r30
 
 	/* Put MSR back into magic page */
@@ -96,6 +97,7 @@ kvm_emulate_mtmsrd_reg:
 	SCRATCH_RESTORE
 
 	/* Nag hypervisor */
+kvm_emulate_mtmsrd_orig_ins:
 	tlbsync
 
 	b	kvm_emulate_mtmsrd_branch
@@ -117,6 +119,10 @@ kvm_emulate_mtmsrd_branch_offs:
 kvm_emulate_mtmsrd_reg_offs:
 	.long (kvm_emulate_mtmsrd_reg - kvm_emulate_mtmsrd) / 4
 
+.global kvm_emulate_mtmsrd_orig_ins_offs
+kvm_emulate_mtmsrd_orig_ins_offs:
+	.long (kvm_emulate_mtmsrd_orig_ins - kvm_emulate_mtmsrd) / 4
+
 .global kvm_emulate_mtmsrd_len
 kvm_emulate_mtmsrd_len:
 	.long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4