[PATCH 3/7] tcg/ppc: Use prefixed instructions in tcg_out_mem_long

[Richard Henderson]

When the offset is out of range of the non-prefixed insn, but
fits the 34-bit immediate of the prefixed insn, use that.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/ppc/tcg-target.c.inc | 66 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc
index 7fa2a2500b..d41c499b7d 100644
--- a/tcg/ppc/tcg-target.c.inc
+++ b/tcg/ppc/tcg-target.c.inc
@@ -323,6 +323,15 @@ static bool tcg_target_const_match(int64_t val, TCGType 
type, int ct)
 #define STDX   XO31(149)
 #define STQ    XO62(  2)
 
+#define PLWA   OPCD( 41)
+#define PLD    OPCD( 57)
+#define PLXSD  OPCD( 42)
+#define PLXV   OPCD(25 * 2 + 1)  /* force tx=1 */
+
+#define PSTD   OPCD( 61)
+#define PSTXSD OPCD( 46)
+#define PSTXV  OPCD(27 * 2 + 1)  /* force tx=1 */
+
 #define ADDIC  OPCD( 12)
 #define ADDI   OPCD( 14)
 #define ADDIS  OPCD( 15)
@@ -720,6 +729,20 @@ static void tcg_out_prefix_align(TCGContext *s)
     }
 }
 
+/* Output Type 00 Prefix - 8-Byte Load/Store Form (8LS:D) */
+static void tcg_out_8ls_d(TCGContext *s, tcg_insn_unit opc, unsigned rt,
+                          unsigned ra, tcg_target_long imm, bool r)
+{
+    tcg_insn_unit p, i;
+
+    p = OPCD(1) | (r << 20) | ((imm >> 16) & 0x3ffff);
+    i = opc | TAI(rt, ra, imm);
+
+    tcg_out_prefix_align(s);
+    tcg_out32(s, p);
+    tcg_out32(s, i);
+}
+
 /* Output Type 10 Prefix - Modified Load/Store Form (MLS:D) */
 static void tcg_out_mls_d(TCGContext *s, tcg_insn_unit opc, unsigned rt,
                           unsigned ra, tcg_target_long imm, bool r)
@@ -1364,6 +1387,49 @@ static void tcg_out_mem_long(TCGContext *s, int opi, int 
opx, TCGReg rt,
         break;
     }
 
+    /* For unaligned or large offsets, use the prefixed form. */
+    if (have_isa_3_10
+        && (offset != (int16_t)offset || (offset & align))
+        && offset == sextract64(offset, 0, 34)) {
+        /*
+         * Note that the MLS:D insns retain their un-prefixed opcode,
+         * while the 8LS:D insns use a different opcode space.
+         */
+        switch (opi) {
+        case LBZ:
+        case LHZ:
+        case LHA:
+        case LWZ:
+        case STB:
+        case STH:
+        case STW:
+        case ADDI:
+            tcg_out_mls_d(s, opi, rt, base, offset, 0);
+            return;
+        case LWA:
+            tcg_out_8ls_d(s, PLWA, rt, base, offset, 0);
+            return;
+        case LD:
+            tcg_out_8ls_d(s, PLD, rt, base, offset, 0);
+            return;
+        case STD:
+            tcg_out_8ls_d(s, PSTD, rt, base, offset, 0);
+            return;
+        case LXSD:
+            tcg_out_8ls_d(s, PLXSD, rt & 31, base, offset, 0);
+            return;
+        case STXSD:
+            tcg_out_8ls_d(s, PSTXSD, rt & 31, base, offset, 0);
+            return;
+        case LXV:
+            tcg_out_8ls_d(s, PLXV, rt & 31, base, offset, 0);
+            return;
+        case STXV:
+            tcg_out_8ls_d(s, PSTXV, rt & 31, base, offset, 0);
+            return;
+        }
+    }
+
     /* For unaligned, or very large offsets, use the indexed form.  */
     if (offset & align || offset != (int32_t)offset || opi == 0) {
         if (rs == base) {
-- 
2.34.1