target/arm: Introduce neon_full_reg_offset

This function makes it clear that we're talking about the whole
register, and not the 32-bit piece at index 0.  This fixes a bug
when running on a big-endian host.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20201030022618.785675-2-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

3 files changed, 31 insertions, 23 deletions

diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index 4d1a292..e259e24 100644
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -76,7 +76,7 @@ neon_element_offset(int reg, int element, MemOp size)
         ofs ^= 8 - element_size;
     }
 #endif
-    return neon_reg_offset(reg, 0) + ofs;
+    return neon_full_reg_offset(reg) + ofs;
 }
 
 static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop)
@@ -585,12 +585,12 @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a)
              * We cannot write 16 bytes at once because the
              * destination is unaligned.
              */
-            tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0),
+            tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(vd),
                                  8, 8, tmp);
-            tcg_gen_gvec_mov(0, neon_reg_offset(vd + 1, 0),
-                             neon_reg_offset(vd, 0), 8, 8);
+            tcg_gen_gvec_mov(0, neon_full_reg_offset(vd + 1),
+                             neon_full_reg_offset(vd), 8, 8);
         } else {
-            tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0),
+            tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(vd),
                                  vec_size, vec_size, tmp);
         }
         tcg_gen_addi_i32(addr, addr, 1 << size);
@@ -691,9 +691,9 @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a)
 static bool do_3same(DisasContext *s, arg_3same *a, GVecGen3Fn fn)
 {
     int vec_size = a->q ? 16 : 8;
-    int rd_ofs = neon_reg_offset(a->vd, 0);
-    int rn_ofs = neon_reg_offset(a->vn, 0);
-    int rm_ofs = neon_reg_offset(a->vm, 0);
+    int rd_ofs = neon_full_reg_offset(a->vd);
+    int rn_ofs = neon_full_reg_offset(a->vn);
+    int rm_ofs = neon_full_reg_offset(a->vm);
 
     if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
         return false;
@@ -1177,8 +1177,8 @@ static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn)
 {
     /* Handle a 2-reg-shift insn which can be vectorized. */
     int vec_size = a->q ? 16 : 8;
-    int rd_ofs = neon_reg_offset(a->vd, 0);
-    int rm_ofs = neon_reg_offset(a->vm, 0);
+    int rd_ofs = neon_full_reg_offset(a->vd);
+    int rm_ofs = neon_full_reg_offset(a->vm);
 
     if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
         return false;
@@ -1620,8 +1620,8 @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a,
 {
     /* FP operations in 2-reg-and-shift group */
     int vec_size = a->q ? 16 : 8;
-    int rd_ofs = neon_reg_offset(a->vd, 0);
-    int rm_ofs = neon_reg_offset(a->vm, 0);
+    int rd_ofs = neon_full_reg_offset(a->vd);
+    int rm_ofs = neon_full_reg_offset(a->vm);
     TCGv_ptr fpst;
 
     if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
@@ -1756,7 +1756,7 @@ static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a,
         return true;
     }
 
-    reg_ofs = neon_reg_offset(a->vd, 0);
+    reg_ofs = neon_full_reg_offset(a->vd);
     vec_size = a->q ? 16 : 8;
     imm = asimd_imm_const(a->imm, a->cmode, a->op);
 
@@ -2300,9 +2300,9 @@ static bool trans_VMULL_P_3d(DisasContext *s, arg_3diff *a)
         return true;
     }
 
-    tcg_gen_gvec_3_ool(neon_reg_offset(a->vd, 0),
-                       neon_reg_offset(a->vn, 0),
-                       neon_reg_offset(a->vm, 0),
+    tcg_gen_gvec_3_ool(neon_full_reg_offset(a->vd),
+                       neon_full_reg_offset(a->vn),
+                       neon_full_reg_offset(a->vm),
                        16, 16, 0, fn_gvec);
     return true;
 }
@@ -2445,8 +2445,8 @@ static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a,
 {
     /* Two registers and a scalar, using gvec */
     int vec_size = a->q ? 16 : 8;
-    int rd_ofs = neon_reg_offset(a->vd, 0);
-    int rn_ofs = neon_reg_offset(a->vn, 0);
+    int rd_ofs = neon_full_reg_offset(a->vd);
+    int rn_ofs = neon_full_reg_offset(a->vn);
     int rm_ofs;
     int idx;
     TCGv_ptr fpstatus;
@@ -2477,7 +2477,7 @@ static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a,
     /* a->vm is M:Vm, which encodes both register and index */
     idx = extract32(a->vm, a->size + 2, 2);
     a->vm = extract32(a->vm, 0, a->size + 2);
-    rm_ofs = neon_reg_offset(a->vm, 0);
+    rm_ofs = neon_full_reg_offset(a->vm);
 
     fpstatus = fpstatus_ptr(a->size == 1 ? FPST_STD_F16 : FPST_STD);
     tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpstatus,
@@ -2923,7 +2923,7 @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a)
         return true;
     }
 
-    tcg_gen_gvec_dup_mem(a->size, neon_reg_offset(a->vd, 0),
+    tcg_gen_gvec_dup_mem(a->size, neon_full_reg_offset(a->vd),
                          neon_element_offset(a->vm, a->index, a->size),
                          a->q ? 16 : 8, a->q ? 16 : 8);
     return true;
@@ -3412,8 +3412,8 @@ static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a)
 static bool do_2misc_vec(DisasContext *s, arg_2misc *a, GVecGen2Fn *fn)
 {
     int vec_size = a->q ? 16 : 8;
-    int rd_ofs = neon_reg_offset(a->vd, 0);
-    int rm_ofs = neon_reg_offset(a->vm, 0);
+    int rd_ofs = neon_full_reg_offset(a->vd);
+    int rm_ofs = neon_full_reg_offset(a->vm);
 
     if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
         return false;
diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc
index a7ed9bc..368bae0 100644
--- a/target/arm/translate-vfp.c.inc
+++ b/target/arm/translate-vfp.c.inc
@@ -653,7 +653,7 @@ static bool trans_VDUP(DisasContext *s, arg_VDUP *a)
     }
 
     tmp = load_reg(s, a->rt);
-    tcg_gen_gvec_dup_i32(size, neon_reg_offset(a->vn, 0),
+    tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(a->vn),
                          vec_size, vec_size, tmp);
     tcg_temp_free_i32(tmp);
 
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 38371db..1b61e50 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -1094,6 +1094,14 @@ static inline void gen_hlt(DisasContext *s, int imm)
     unallocated_encoding(s);
 }
 
+/*
+ * Return the offset of a "full" NEON Dreg.
+ */
+static long neon_full_reg_offset(unsigned reg)
+{
+    return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]);
+}
+
 static inline long vfp_reg_offset(bool dp, unsigned reg)
 {
     if (dp) {