tcg/optimize: optimize TSTNE using smask and zmask

Generalize the existing optimization of "TSTNE x,sign" and "TSTNE x,-1".
This can be useful for example in the i386 frontend, which will generate
tests of zero-extended registers against 0xffffffff.

Ironically, on x86 hosts this is a very slight pessimization in the very
case it's meant to optimize because

 brcond_i64 cc_dst,$0xffffffff,tsteq,$L1

(test %ebx, %ebx) is 1 byte smaller than

 brcond_i64 cc_dst,$0x0,eq,$L1

(test %rbx, %rbx).  However, in general it is an improvement, especially
if it avoids placing a large immediate in the constant pool.

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

tcg/optimize.c

@@ -766,6 +766,7 @@ static int do_constant_folding_cond1(OptContext *ctx, TCGOp *op, TCGArg dest,
                                      TCGArg *p1, TCGArg *p2, TCGArg *pcond)
 {
     TCGCond cond;
+    TempOptInfo *i1;
     bool swap;
     int r;
 
@@ -783,19 +784,21 @@ static int do_constant_folding_cond1(OptContext *ctx, TCGOp *op, TCGArg dest,
         return -1;
     }
 
+    i1 = arg_info(*p1);
+
     /*
      * TSTNE x,x -> NE x,0
-     * TSTNE x,-1 -> NE x,0
+     * TSTNE x,i -> NE x,0 if i includes all nonzero bits of x
      */
-    if (args_are_copies(*p1, *p2) || arg_is_const_val(*p2, -1)) {
+    if (args_are_copies(*p1, *p2) ||
+        (arg_is_const(*p2) && (i1->z_mask & ~arg_info(*p2)->val) == 0)) {
         *p2 = arg_new_constant(ctx, 0);
         *pcond = tcg_tst_eqne_cond(cond);
         return -1;
     }
 
-    /* TSTNE x,sign -> LT x,0 */
-    if (arg_is_const_val(*p2, (ctx->type == TCG_TYPE_I32
-                               ? INT32_MIN : INT64_MIN))) {
+    /* TSTNE x,i -> LT x,0 if i only includes sign bit copies */
+    if (arg_is_const(*p2) && (arg_info(*p2)->val & ~i1->s_mask) == 0) {
         *p2 = arg_new_constant(ctx, 0);
         *pcond = tcg_tst_ltge_cond(cond);
         return -1;