[Qemu-devel] [PATCH for-2.5 09/10] tcg/optimize: do not remember garbage high bits for 32-bit ops

[Aurelien Jarno]

Now that we have real size changing ops, we don't need to mark high
bits of the destination as garbage. The goal of the optimizer is to
predict the value of the temps (and not of the registers) and do
simplifications when possible. The problem there is therefore not the
fact that those bits are not counted as garbage, but that a size
changing op is replaced by a move.

This patch is basically a revert of 24666baf, including the changes that
have been made since then.

Cc: Richard Henderson <address@hidden>
Signed-off-by: Aurelien Jarno <address@hidden>
---
 tcg/optimize.c | 43 ++++++++++++-------------------------------
 1 file changed, 12 insertions(+), 31 deletions(-)

diff --git a/tcg/optimize.c b/tcg/optimize.c
index 155d5c3..15d76a0 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -209,21 +209,13 @@ static bool temps_are_copies(TCGArg arg1, TCGArg arg2)
 static void tcg_opt_gen_movi(TCGContext *s, TCGOp *op, TCGArg *args,
                              TCGArg dst, TCGArg val)
 {
-    TCGOpcode new_op = op_to_movi(op->opc);
-    tcg_target_ulong mask;
-
-    op->opc = new_op;
+    op->opc = op_to_movi(op->opc);
 
     reset_temp(dst);
-    temps[dst].is_const = true;
     temps[dst].is_copy = false;
+    temps[dst].is_const = true;
     temps[dst].val = val;
-    mask = val;
-    if (TCG_TARGET_REG_BITS > 32 && new_op == INDEX_op_movi_i32) {
-        /* High bits of the destination are now garbage.  */
-        mask |= ~0xffffffffull;
-    }
-    temps[dst].mask = mask;
+    temps[dst].mask = val;
 
     args[0] = dst;
     args[1] = val;
@@ -237,18 +229,9 @@ static void tcg_opt_gen_mov(TCGContext *s, TCGOp *op, 
TCGArg *args,
         return;
     }
 
-    TCGOpcode new_op = op_to_mov(op->opc);
-    tcg_target_ulong mask;
-
-    op->opc = new_op;
+    op->opc = op_to_mov(op->opc);
 
     reset_temp(dst);
-    mask = temps[src].mask;
-    if (TCG_TARGET_REG_BITS > 32 && new_op == INDEX_op_mov_i32) {
-        /* High bits of the destination are now garbage.  */
-        mask |= ~0xffffffffull;
-    }
-    temps[dst].mask = mask;
 
     if (s->temps[src].type == s->temps[dst].type) {
         if (!temp_is_copy(src)) {
@@ -256,15 +239,17 @@ static void tcg_opt_gen_mov(TCGContext *s, TCGOp *op, 
TCGArg *args,
             temps[src].next_copy = src;
             temps[src].prev_copy = src;
         }
-        temps[dst].is_const = temps[src].is_const;
         temps[dst].is_copy = true;
-        temps[dst].val = temps[src].val;
         temps[dst].next_copy = temps[src].next_copy;
         temps[dst].prev_copy = src;
         temps[temps[dst].next_copy].prev_copy = dst;
         temps[src].next_copy = dst;
     }
 
+    temps[dst].is_const = temps[src].is_const;
+    temps[dst].val = temps[src].val;
+    temps[dst].mask = temps[src].mask;
+
     args[0] = dst;
     args[1] = src;
 }
@@ -597,7 +582,7 @@ void tcg_optimize(TCGContext *s)
     reset_all_temps(nb_temps);
 
     for (oi = s->gen_first_op_idx; oi >= 0; oi = oi_next) {
-        tcg_target_ulong mask, partmask, affected;
+        tcg_target_ulong mask, affected;
         int nb_oargs, nb_iargs, i;
         TCGArg tmp;
 
@@ -950,17 +935,13 @@ void tcg_optimize(TCGContext *s)
             break;
         }
 
-        /* 32-bit ops generate 32-bit results.  For the result is zero test
-           below, we can ignore high bits, but for further optimizations we
-           need to record that the high bits contain garbage.  */
-        partmask = mask;
+        /* 32-bit ops generate 32-bit results.  */
         if (!(def->flags & TCG_OPF_64BIT)) {
-            mask |= ~(tcg_target_ulong)0xffffffffu;
-            partmask &= 0xffffffffu;
+            mask &= 0xffffffffu;
             affected &= 0xffffffffu;
         }
 
-        if (partmask == 0) {
+        if (mask == 0) {
             assert(nb_oargs == 1);
             tcg_opt_gen_movi(s, op, args, args[0], 0);
             continue;
-- 
2.1.4