[v2,08/11] target/arm: Add read/write_neon_element64

diff --git a/target/arm/translate.c b/target/arm/translate.c
index 8491ab705b..4fb0a62200 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -1178,6 +1178,19 @@  static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop)
     }
 }
 
+static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop)
+{
+    long off = neon_element_offset(reg, ele, memop);
+
+    switch (memop) {
+    case MO_Q:
+        tcg_gen_ld_i64(dest, cpu_env, off);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
 static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop)
 {
     long off = neon_element_offset(reg, ele, memop);
@@ -1197,6 +1210,19 @@  static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop)
     }
 }
 
+static void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop)
+{
+    long off = neon_element_offset(reg, ele, memop);
+
+    switch (memop) {
+    case MO_64:
+        tcg_gen_st_i64(src, cpu_env, off);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
 static TCGv_ptr vfp_reg_ptr(bool dp, int reg)
 {
     TCGv_ptr ret = tcg_temp_new_ptr();
diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index 549381703e..c2d67160f9 100644
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -1265,9 +1265,9 @@  static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a,
     for (pass = 0; pass < a->q + 1; pass++) {
         TCGv_i64 tmp = tcg_temp_new_i64();
 
-        neon_load_reg64(tmp, a->vm + pass);
+        read_neon_element64(tmp, a->vm, pass, MO_64);
         fn(tmp, cpu_env, tmp, constimm);
-        neon_store_reg64(tmp, a->vd + pass);
+        write_neon_element64(tmp, a->vd, pass, MO_64);
         tcg_temp_free_i64(tmp);
     }
     tcg_temp_free_i64(constimm);
@@ -1375,8 +1375,8 @@  static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a,
     rd = tcg_temp_new_i32();
 
     /* Load both inputs first to avoid potential overwrite if rm == rd */
-    neon_load_reg64(rm1, a->vm);
-    neon_load_reg64(rm2, a->vm + 1);
+    read_neon_element64(rm1, a->vm, 0, MO_64);
+    read_neon_element64(rm2, a->vm, 1, MO_64);
 
     shiftfn(rm1, rm1, constimm);
     narrowfn(rd, cpu_env, rm1);
@@ -1579,7 +1579,7 @@  static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a,
         tcg_gen_shli_i64(tmp, tmp, a->shift);
         tcg_gen_andi_i64(tmp, tmp, ~widen_mask);
     }
-    neon_store_reg64(tmp, a->vd);
+    write_neon_element64(tmp, a->vd, 0, MO_64);
 
     widenfn(tmp, rm1);
     tcg_temp_free_i32(rm1);
@@ -1587,7 +1587,7 @@  static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a,
         tcg_gen_shli_i64(tmp, tmp, a->shift);
         tcg_gen_andi_i64(tmp, tmp, ~widen_mask);
     }
-    neon_store_reg64(tmp, a->vd + 1);
+    write_neon_element64(tmp, a->vd, 1, MO_64);
     tcg_temp_free_i64(tmp);
     return true;
 }
@@ -1822,7 +1822,7 @@  static bool do_prewiden_3d(DisasContext *s, arg_3diff *a,
     rm_64 = tcg_temp_new_i64();
 
     if (src1_wide) {
-        neon_load_reg64(rn0_64, a->vn);
+        read_neon_element64(rn0_64, a->vn, 0, MO_64);
     } else {
         TCGv_i32 tmp = tcg_temp_new_i32();
         read_neon_element32(tmp, a->vn, 0, MO_32);
@@ -1841,7 +1841,7 @@  static bool do_prewiden_3d(DisasContext *s, arg_3diff *a,
      * avoid incorrect results if a narrow input overlaps with the result.
      */
     if (src1_wide) {
-        neon_load_reg64(rn1_64, a->vn + 1);
+        read_neon_element64(rn1_64, a->vn, 1, MO_64);
     } else {
         TCGv_i32 tmp = tcg_temp_new_i32();
         read_neon_element32(tmp, a->vn, 1, MO_32);
@@ -1851,12 +1851,12 @@  static bool do_prewiden_3d(DisasContext *s, arg_3diff *a,
     rm = tcg_temp_new_i32();
     read_neon_element32(rm, a->vm, 1, MO_32);
 
-    neon_store_reg64(rn0_64, a->vd);
+    write_neon_element64(rn0_64, a->vd, 0, MO_64);
 
     widenfn(rm_64, rm);
     tcg_temp_free_i32(rm);
     opfn(rn1_64, rn1_64, rm_64);
-    neon_store_reg64(rn1_64, a->vd + 1);
+    write_neon_element64(rn1_64, a->vd, 1, MO_64);
 
     tcg_temp_free_i64(rn0_64);
     tcg_temp_free_i64(rn1_64);
@@ -1928,15 +1928,15 @@  static bool do_narrow_3d(DisasContext *s, arg_3diff *a,
     rd0 = tcg_temp_new_i32();
     rd1 = tcg_temp_new_i32();
 
-    neon_load_reg64(rn_64, a->vn);
-    neon_load_reg64(rm_64, a->vm);
+    read_neon_element64(rn_64, a->vn, 0, MO_64);
+    read_neon_element64(rm_64, a->vm, 0, MO_64);
 
     opfn(rn_64, rn_64, rm_64);
 
     narrowfn(rd0, rn_64);
 
-    neon_load_reg64(rn_64, a->vn + 1);
-    neon_load_reg64(rm_64, a->vm + 1);
+    read_neon_element64(rn_64, a->vn, 1, MO_64);
+    read_neon_element64(rm_64, a->vm, 1, MO_64);
 
     opfn(rn_64, rn_64, rm_64);
 
@@ -2036,16 +2036,16 @@  static bool do_long_3d(DisasContext *s, arg_3diff *a,
     /* Don't store results until after all loads: they might overlap */
     if (accfn) {
         tmp = tcg_temp_new_i64();
-        neon_load_reg64(tmp, a->vd);
+        read_neon_element64(tmp, a->vd, 0, MO_64);
         accfn(tmp, tmp, rd0);
-        neon_store_reg64(tmp, a->vd);
-        neon_load_reg64(tmp, a->vd + 1);
+        write_neon_element64(tmp, a->vd, 0, MO_64);
+        read_neon_element64(tmp, a->vd, 1, MO_64);
         accfn(tmp, tmp, rd1);
-        neon_store_reg64(tmp, a->vd + 1);
+        write_neon_element64(tmp, a->vd, 1, MO_64);
         tcg_temp_free_i64(tmp);
     } else {
-        neon_store_reg64(rd0, a->vd);
-        neon_store_reg64(rd1, a->vd + 1);
+        write_neon_element64(rd0, a->vd, 0, MO_64);
+        write_neon_element64(rd1, a->vd, 1, MO_64);
     }
 
     tcg_temp_free_i64(rd0);
@@ -2669,16 +2669,16 @@  static bool do_2scalar_long(DisasContext *s, arg_2scalar *a,
 
     if (accfn) {
         TCGv_i64 t64 = tcg_temp_new_i64();
-        neon_load_reg64(t64, a->vd);
+        read_neon_element64(t64, a->vd, 0, MO_64);
         accfn(t64, t64, rn0_64);
-        neon_store_reg64(t64, a->vd);
-        neon_load_reg64(t64, a->vd + 1);
+        write_neon_element64(t64, a->vd, 0, MO_64);
+        read_neon_element64(t64, a->vd, 1, MO_64);
         accfn(t64, t64, rn1_64);
-        neon_store_reg64(t64, a->vd + 1);
+        write_neon_element64(t64, a->vd, 1, MO_64);
         tcg_temp_free_i64(t64);
     } else {
-        neon_store_reg64(rn0_64, a->vd);
-        neon_store_reg64(rn1_64, a->vd + 1);
+        write_neon_element64(rn0_64, a->vd, 0, MO_64);
+        write_neon_element64(rn1_64, a->vd, 1, MO_64);
     }
     tcg_temp_free_i64(rn0_64);
     tcg_temp_free_i64(rn1_64);
@@ -2812,10 +2812,10 @@  static bool trans_VEXT(DisasContext *s, arg_VEXT *a)
         right = tcg_temp_new_i64();
         dest = tcg_temp_new_i64();
 
-        neon_load_reg64(right, a->vn);
-        neon_load_reg64(left, a->vm);
+        read_neon_element64(right, a->vn, 0, MO_64);
+        read_neon_element64(left, a->vm, 0, MO_64);
         tcg_gen_extract2_i64(dest, right, left, a->imm * 8);
-        neon_store_reg64(dest, a->vd);
+        write_neon_element64(dest, a->vd, 0, MO_64);
 
         tcg_temp_free_i64(left);
         tcg_temp_free_i64(right);
@@ -2831,21 +2831,21 @@  static bool trans_VEXT(DisasContext *s, arg_VEXT *a)
         destright = tcg_temp_new_i64();
 
         if (a->imm < 8) {
-            neon_load_reg64(right, a->vn);
-            neon_load_reg64(middle, a->vn + 1);
+            read_neon_element64(right, a->vn, 0, MO_64);
+            read_neon_element64(middle, a->vn, 1, MO_64);
             tcg_gen_extract2_i64(destright, right, middle, a->imm * 8);
-            neon_load_reg64(left, a->vm);
+            read_neon_element64(left, a->vm, 0, MO_64);
             tcg_gen_extract2_i64(destleft, middle, left, a->imm * 8);
         } else {
-            neon_load_reg64(right, a->vn + 1);
-            neon_load_reg64(middle, a->vm);
+            read_neon_element64(right, a->vn, 1, MO_64);
+            read_neon_element64(middle, a->vm, 0, MO_64);
             tcg_gen_extract2_i64(destright, right, middle, (a->imm - 8) * 8);
-            neon_load_reg64(left, a->vm + 1);
+            read_neon_element64(left, a->vm, 1, MO_64);
             tcg_gen_extract2_i64(destleft, middle, left, (a->imm - 8) * 8);
         }
 
-        neon_store_reg64(destright, a->vd);
-        neon_store_reg64(destleft, a->vd + 1);
+        write_neon_element64(destright, a->vd, 0, MO_64);
+        write_neon_element64(destleft, a->vd, 1, MO_64);
 
         tcg_temp_free_i64(destright);
         tcg_temp_free_i64(destleft);
@@ -3052,11 +3052,11 @@  static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a,
 
         if (accfn) {
             TCGv_i64 tmp64 = tcg_temp_new_i64();
-            neon_load_reg64(tmp64, a->vd + pass);
+            read_neon_element64(tmp64, a->vd, pass, MO_64);
             accfn(rd_64, tmp64, rd_64);
             tcg_temp_free_i64(tmp64);
         }
-        neon_store_reg64(rd_64, a->vd + pass);
+        write_neon_element64(rd_64, a->vd, pass, MO_64);
         tcg_temp_free_i64(rd_64);
     }
     return true;
@@ -3254,9 +3254,9 @@  static bool do_vmovn(DisasContext *s, arg_2misc *a,
     rd0 = tcg_temp_new_i32();
     rd1 = tcg_temp_new_i32();
 
-    neon_load_reg64(rm, a->vm);
+    read_neon_element64(rm, a->vm, 0, MO_64);
     narrowfn(rd0, cpu_env, rm);
-    neon_load_reg64(rm, a->vm + 1);
+    read_neon_element64(rm, a->vm, 1, MO_64);
     narrowfn(rd1, cpu_env, rm);
     write_neon_element32(rd0, a->vd, 0, MO_32);
     write_neon_element32(rd1, a->vd, 1, MO_32);
@@ -3326,10 +3326,10 @@  static bool trans_VSHLL(DisasContext *s, arg_2misc *a)
 
     widenfn(rd, rm0);
     tcg_gen_shli_i64(rd, rd, 8 << a->size);
-    neon_store_reg64(rd, a->vd);
+    write_neon_element64(rd, a->vd, 0, MO_64);
     widenfn(rd, rm1);
     tcg_gen_shli_i64(rd, rd, 8 << a->size);
-    neon_store_reg64(rd, a->vd + 1);
+    write_neon_element64(rd, a->vd, 1, MO_64);
 
     tcg_temp_free_i64(rd);
     tcg_temp_free_i32(rm0);
@@ -3847,10 +3847,10 @@  static bool trans_VSWP(DisasContext *s, arg_2misc *a)
     rm = tcg_temp_new_i64();
     rd = tcg_temp_new_i64();
     for (pass = 0; pass < (a->q ? 2 : 1); pass++) {
-        neon_load_reg64(rm, a->vm + pass);
-        neon_load_reg64(rd, a->vd + pass);
-        neon_store_reg64(rm, a->vd + pass);
-        neon_store_reg64(rd, a->vm + pass);
+        read_neon_element64(rm, a->vm, pass, MO_64);
+        read_neon_element64(rd, a->vd, pass, MO_64);
+        write_neon_element64(rm, a->vd, pass, MO_64);
+        write_neon_element64(rd, a->vm, pass, MO_64);
     }
     tcg_temp_free_i64(rm);
     tcg_temp_free_i64(rd);