[Qemu-devel] [PATCH 4/6] tcg-i386: Implement small forward branches.

[Richard Henderson]

There are places, like brcond2, where we know that the destination
of a forward branch will be within 127 bytes.  Add the R_386_PC8
relocation type to support this, and add a flag to tcg_out_jxx to
generate it.  Set the flag in the small forward branches in brcond2.

Signed-off-by: Richard Henderson <address@hidden>
---
 elf.h                 |    2 ++
 tcg/i386/tcg-target.c |   36 +++++++++++++++++++++++++-----------
 2 files changed, 27 insertions(+), 11 deletions(-)

diff --git a/elf.h b/elf.h
index 11674d7..c84c8ab 100644
--- a/elf.h
+++ b/elf.h
@@ -243,6 +243,8 @@ typedef struct {
 #define R_386_GOTOFF   9
 #define R_386_GOTPC    10
 #define R_386_NUM      11
+/* Not a dynamic reloc, so not included in R_386_NUM.  Used in TCG.  */
+#define R_386_PC8      23
 
 #define R_MIPS_NONE            0
 #define R_MIPS_16              1
diff --git a/tcg/i386/tcg-target.c b/tcg/i386/tcg-target.c
index 972b102..cc3d28f 100644
--- a/tcg/i386/tcg-target.c
+++ b/tcg/i386/tcg-target.c
@@ -61,6 +61,9 @@ static void patch_reloc(uint8_t *code_ptr, int type,
     case R_386_PC32:
         *(uint32_t *)code_ptr = value - (long)code_ptr;
         break;
+    case R_386_PC8:
+        *(uint8_t *)code_ptr = value - (long)code_ptr;
+        break;
     default:
         tcg_abort();
     }
@@ -305,7 +308,8 @@ static void tcg_out_addi(TCGContext *s, int reg, 
tcg_target_long val)
         tgen_arithi(s, ARITH_ADD, reg, val, 0);
 }
 
-static void tcg_out_jxx(TCGContext *s, int opc, int label_index)
+/* Use SMALL != 0 to force a short forward branch.  */
+static void tcg_out_jxx(TCGContext *s, int opc, int label_index, int small)
 {
     int32_t val, val1;
     TCGLabel *l = &s->labels[label_index];
@@ -320,6 +324,7 @@ static void tcg_out_jxx(TCGContext *s, int opc, int 
label_index)
                 tcg_out8(s, 0x70 + opc);
             tcg_out8(s, val1);
         } else {
+            assert (!small);
             if (opc == -1) {
                 tcg_out8(s, 0xe9);
                 tcg_out32(s, val - 5);
@@ -329,6 +334,15 @@ static void tcg_out_jxx(TCGContext *s, int opc, int 
label_index)
                 tcg_out32(s, val - 6);
             }
         }
+    } else if (small) {
+        if (opc == -1) {
+            tcg_out8(s, 0xeb);
+        } else {
+            tcg_out8(s, 0x0f);
+            tcg_out8(s, 0x70 + opc);
+        }
+        tcg_out_reloc(s, s->code_ptr, R_386_PC8, label_index, -1);
+        s->code_ptr += 1;
     } else {
         if (opc == -1) {
             tcg_out8(s, 0xe9);
@@ -355,7 +369,7 @@ static void tcg_out_brcond(TCGContext *s, int cond,
     } else {
         tcg_out_modrm(s, 0x01 | (ARITH_CMP << 3), arg2, arg1);
     }
-    tcg_out_jxx(s, tcg_cond_to_jcc[cond], label_index);
+    tcg_out_jxx(s, tcg_cond_to_jcc[cond], label_index, 0);
 }
 
 /* XXX: we implement it at the target level to avoid having to
@@ -376,42 +390,42 @@ static void tcg_out_brcond2(TCGContext *s,
         break;
     case TCG_COND_LT:
         tcg_out_brcond(s, TCG_COND_LT, args[1], args[3], const_args[3], 
args[5]);
-        tcg_out_jxx(s, JCC_JNE, label_next);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
         tcg_out_brcond(s, TCG_COND_LTU, args[0], args[2], const_args[2], 
args[5]);
         break;
     case TCG_COND_LE:
         tcg_out_brcond(s, TCG_COND_LT, args[1], args[3], const_args[3], 
args[5]);
-        tcg_out_jxx(s, JCC_JNE, label_next);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
         tcg_out_brcond(s, TCG_COND_LEU, args[0], args[2], const_args[2], 
args[5]);
         break;
     case TCG_COND_GT:
         tcg_out_brcond(s, TCG_COND_GT, args[1], args[3], const_args[3], 
args[5]);
-        tcg_out_jxx(s, JCC_JNE, label_next);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
         tcg_out_brcond(s, TCG_COND_GTU, args[0], args[2], const_args[2], 
args[5]);
         break;
     case TCG_COND_GE:
         tcg_out_brcond(s, TCG_COND_GT, args[1], args[3], const_args[3], 
args[5]);
-        tcg_out_jxx(s, JCC_JNE, label_next);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
         tcg_out_brcond(s, TCG_COND_GEU, args[0], args[2], const_args[2], 
args[5]);
         break;
     case TCG_COND_LTU:
         tcg_out_brcond(s, TCG_COND_LTU, args[1], args[3], const_args[3], 
args[5]);
-        tcg_out_jxx(s, JCC_JNE, label_next);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
         tcg_out_brcond(s, TCG_COND_LTU, args[0], args[2], const_args[2], 
args[5]);
         break;
     case TCG_COND_LEU:
         tcg_out_brcond(s, TCG_COND_LTU, args[1], args[3], const_args[3], 
args[5]);
-        tcg_out_jxx(s, JCC_JNE, label_next);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
         tcg_out_brcond(s, TCG_COND_LEU, args[0], args[2], const_args[2], 
args[5]);
         break;
     case TCG_COND_GTU:
         tcg_out_brcond(s, TCG_COND_GTU, args[1], args[3], const_args[3], 
args[5]);
-        tcg_out_jxx(s, JCC_JNE, label_next);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
         tcg_out_brcond(s, TCG_COND_GTU, args[0], args[2], const_args[2], 
args[5]);
         break;
     case TCG_COND_GEU:
         tcg_out_brcond(s, TCG_COND_GTU, args[1], args[3], const_args[3], 
args[5]);
-        tcg_out_jxx(s, JCC_JNE, label_next);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
         tcg_out_brcond(s, TCG_COND_GEU, args[0], args[2], const_args[2], 
args[5]);
         break;
     default:
@@ -913,7 +927,7 @@ static inline void tcg_out_op(TCGContext *s, int opc,
         }
         break;
     case INDEX_op_br:
-        tcg_out_jxx(s, JCC_JMP, args[0]);
+        tcg_out_jxx(s, JCC_JMP, args[0], 0);
         break;
     case INDEX_op_movi_i32:
         tcg_out_movi(s, TCG_TYPE_I32, args[0], args[1]);
-- 
1.6.5.2