target-arm: Pass fp status pointer explicitly to neon fp helpers

Make the Neon helpers for various floating point operations take an
explicit pointer to the float_status they use, so they don't rely on
the global environment pointer any more. This also allows us to drop
the mul/sub/add helpers completely and just use the vfp versions.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

3 files changed, 113 insertions, 74 deletions

diff --git a/target-arm/helper.h b/target-arm/helper.h
index 40b46770d..c29efd575 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -350,17 +350,14 @@ DEF_HELPER_1(neon_qneg_s8, i32, i32)
 DEF_HELPER_1(neon_qneg_s16, i32, i32)
 DEF_HELPER_1(neon_qneg_s32, i32, i32)
 
-DEF_HELPER_2(neon_min_f32, i32, i32, i32)
-DEF_HELPER_2(neon_max_f32, i32, i32, i32)
-DEF_HELPER_2(neon_abd_f32, i32, i32, i32)
-DEF_HELPER_2(neon_add_f32, i32, i32, i32)
-DEF_HELPER_2(neon_sub_f32, i32, i32, i32)
-DEF_HELPER_2(neon_mul_f32, i32, i32, i32)
-DEF_HELPER_2(neon_ceq_f32, i32, i32, i32)
-DEF_HELPER_2(neon_cge_f32, i32, i32, i32)
-DEF_HELPER_2(neon_cgt_f32, i32, i32, i32)
-DEF_HELPER_2(neon_acge_f32, i32, i32, i32)
-DEF_HELPER_2(neon_acgt_f32, i32, i32, i32)
+DEF_HELPER_3(neon_min_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_max_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_abd_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_ceq_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_cge_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_cgt_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_acge_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_acgt_f32, i32, i32, i32, ptr)
 
 /* iwmmxt_helper.c */
 DEF_HELPER_2(iwmmxt_maddsq, i64, i64, i64)
diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c
index 916551923..fda4021a5 100644
--- a/target-arm/neon_helper.c
+++ b/target-arm/neon_helper.c
@@ -18,8 +18,6 @@
 
 #define SET_QC() env->vfp.xregs[ARM_VFP_FPSCR] = CPSR_Q
 
-#define NFS (&env->vfp.standard_fp_status)
-
 #define NEON_TYPE1(name, type) \
 typedef struct \
 { \
@@ -1770,69 +1768,62 @@ uint32_t HELPER(neon_qneg_s32)(uint32_t x)
 }
 
 /* NEON Float helpers.  */
-uint32_t HELPER(neon_min_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_min_f32)(uint32_t a, uint32_t b, void *fpstp)
 {
-    return float32_val(float32_min(make_float32(a), make_float32(b), NFS));
+    float_status *fpst = fpstp;
+    return float32_val(float32_min(make_float32(a), make_float32(b), fpst));
 }
 
-uint32_t HELPER(neon_max_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_max_f32)(uint32_t a, uint32_t b, void *fpstp)
 {
-    return float32_val(float32_max(make_float32(a), make_float32(b), NFS));
+    float_status *fpst = fpstp;
+    return float32_val(float32_max(make_float32(a), make_float32(b), fpst));
 }
 
-uint32_t HELPER(neon_abd_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_abd_f32)(uint32_t a, uint32_t b, void *fpstp)
 {
+    float_status *fpst = fpstp;
     float32 f0 = make_float32(a);
     float32 f1 = make_float32(b);
-    return float32_val(float32_abs(float32_sub(f0, f1, NFS)));
-}
-
-uint32_t HELPER(neon_add_f32)(uint32_t a, uint32_t b)
-{
-    return float32_val(float32_add(make_float32(a), make_float32(b), NFS));
-}
-
-uint32_t HELPER(neon_sub_f32)(uint32_t a, uint32_t b)
-{
-    return float32_val(float32_sub(make_float32(a), make_float32(b), NFS));
-}
-
-uint32_t HELPER(neon_mul_f32)(uint32_t a, uint32_t b)
-{
-    return float32_val(float32_mul(make_float32(a), make_float32(b), NFS));
+    return float32_val(float32_abs(float32_sub(f0, f1, fpst)));
 }
 
 /* Floating point comparisons produce an integer result.
  * Note that EQ doesn't signal InvalidOp for QNaNs but GE and GT do.
  * Softfloat routines return 0/1, which we convert to the 0/-1 Neon requires.
  */
-uint32_t HELPER(neon_ceq_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_ceq_f32)(uint32_t a, uint32_t b, void *fpstp)
 {
-    return -float32_eq_quiet(make_float32(a), make_float32(b), NFS);
+    float_status *fpst = fpstp;
+    return -float32_eq_quiet(make_float32(a), make_float32(b), fpst);
 }
 
-uint32_t HELPER(neon_cge_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_cge_f32)(uint32_t a, uint32_t b, void *fpstp)
 {
-    return -float32_le(make_float32(b), make_float32(a), NFS);
+    float_status *fpst = fpstp;
+    return -float32_le(make_float32(b), make_float32(a), fpst);
 }
 
-uint32_t HELPER(neon_cgt_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_cgt_f32)(uint32_t a, uint32_t b, void *fpstp)
 {
-    return -float32_lt(make_float32(b), make_float32(a), NFS);
+    float_status *fpst = fpstp;
+    return -float32_lt(make_float32(b), make_float32(a), fpst);
 }
 
-uint32_t HELPER(neon_acge_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_acge_f32)(uint32_t a, uint32_t b, void *fpstp)
 {
+    float_status *fpst = fpstp;
     float32 f0 = float32_abs(make_float32(a));
     float32 f1 = float32_abs(make_float32(b));
-    return -float32_le(f1, f0, NFS);
+    return -float32_le(f1, f0, fpst);
 }
 
-uint32_t HELPER(neon_acgt_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_acgt_f32)(uint32_t a, uint32_t b, void *fpstp)
 {
+    float_status *fpst = fpstp;
     float32 f0 = float32_abs(make_float32(a));
     float32 f1 = float32_abs(make_float32(b));
-    return -float32_lt(f1, f0, NFS);
+    return -float32_lt(f1, f0, fpst);
 }
 
 #define ELEM(V, N, SIZE) (((V) >> ((N) * (SIZE))) & ((1ull << (SIZE)) - 1))
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 9ed747f36..27d988733 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -4857,57 +4857,78 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
             }
             break;
         case NEON_3R_FLOAT_ARITH: /* Floating point arithmetic. */
+        {
+            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
             switch ((u << 2) | size) {
             case 0: /* VADD */
-                gen_helper_neon_add_f32(tmp, tmp, tmp2);
+            case 4: /* VPADD */
+                gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus);
                 break;
             case 2: /* VSUB */
-                gen_helper_neon_sub_f32(tmp, tmp, tmp2);
-                break;
-            case 4: /* VPADD */
-                gen_helper_neon_add_f32(tmp, tmp, tmp2);
+                gen_helper_vfp_subs(tmp, tmp, tmp2, fpstatus);
                 break;
             case 6: /* VABD */
-                gen_helper_neon_abd_f32(tmp, tmp, tmp2);
+                gen_helper_neon_abd_f32(tmp, tmp, tmp2, fpstatus);
                 break;
             default:
                 abort();
             }
+            tcg_temp_free_ptr(fpstatus);
             break;
+        }
         case NEON_3R_FLOAT_MULTIPLY:
-            gen_helper_neon_mul_f32(tmp, tmp, tmp2);
+        {
+            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+            gen_helper_vfp_muls(tmp, tmp, tmp2, fpstatus);
             if (!u) {
                 tcg_temp_free_i32(tmp2);
                 tmp2 = neon_load_reg(rd, pass);
                 if (size == 0) {
-                    gen_helper_neon_add_f32(tmp, tmp, tmp2);
+                    gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus);
                 } else {
-                    gen_helper_neon_sub_f32(tmp, tmp2, tmp);
+                    gen_helper_vfp_subs(tmp, tmp2, tmp, fpstatus);
                 }
             }
+            tcg_temp_free_ptr(fpstatus);
             break;
+        }
         case NEON_3R_FLOAT_CMP:
+        {
+            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
             if (!u) {
-                gen_helper_neon_ceq_f32(tmp, tmp, tmp2);
+                gen_helper_neon_ceq_f32(tmp, tmp, tmp2, fpstatus);
             } else {
-                if (size == 0)
-                    gen_helper_neon_cge_f32(tmp, tmp, tmp2);
-                else
-                    gen_helper_neon_cgt_f32(tmp, tmp, tmp2);
+                if (size == 0) {
+                    gen_helper_neon_cge_f32(tmp, tmp, tmp2, fpstatus);
+                } else {
+                    gen_helper_neon_cgt_f32(tmp, tmp, tmp2, fpstatus);
+                }
             }
+            tcg_temp_free_ptr(fpstatus);
             break;
+        }
         case NEON_3R_FLOAT_ACMP:
-            if (size == 0)
-                gen_helper_neon_acge_f32(tmp, tmp, tmp2);
-            else
-                gen_helper_neon_acgt_f32(tmp, tmp, tmp2);
+        {
+            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+            if (size == 0) {
+                gen_helper_neon_acge_f32(tmp, tmp, tmp2, fpstatus);
+            } else {
+                gen_helper_neon_acgt_f32(tmp, tmp, tmp2, fpstatus);
+            }
+            tcg_temp_free_ptr(fpstatus);
             break;
+        }
         case NEON_3R_FLOAT_MINMAX:
-            if (size == 0)
-                gen_helper_neon_max_f32(tmp, tmp, tmp2);
-            else
-                gen_helper_neon_min_f32(tmp, tmp, tmp2);
+        {
+            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+            if (size == 0) {
+                gen_helper_neon_max_f32(tmp, tmp, tmp2, fpstatus);
+            } else {
+                gen_helper_neon_min_f32(tmp, tmp, tmp2, fpstatus);
+            }
+            tcg_temp_free_ptr(fpstatus);
             break;
+        }
         case NEON_3R_VRECPS_VRSQRTS:
             if (size == 0)
                 gen_helper_recps_f32(tmp, tmp, tmp2, cpu_env);
@@ -5606,7 +5627,9 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                                 gen_helper_neon_qrdmulh_s32(tmp, tmp, tmp2);
                             }
                         } else if (op & 1) {
-                            gen_helper_neon_mul_f32(tmp, tmp, tmp2);
+                            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+                            gen_helper_vfp_muls(tmp, tmp, tmp2, fpstatus);
+                            tcg_temp_free_ptr(fpstatus);
                         } else {
                             switch (size) {
                             case 0: gen_helper_neon_mul_u8(tmp, tmp, tmp2); break;
@@ -5624,14 +5647,22 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                                 gen_neon_add(size, tmp, tmp2);
                                 break;
                             case 1:
-                                gen_helper_neon_add_f32(tmp, tmp, tmp2);
+                            {
+                                TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+                                gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus);
+                                tcg_temp_free_ptr(fpstatus);
                                 break;
+                            }
                             case 4:
                                 gen_neon_rsb(size, tmp, tmp2);
                                 break;
                             case 5:
-                                gen_helper_neon_sub_f32(tmp, tmp2, tmp);
+                            {
+                                TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+                                gen_helper_vfp_subs(tmp, tmp2, tmp, fpstatus);
+                                tcg_temp_free_ptr(fpstatus);
                                 break;
+                            }
                             default:
                                 abort();
                             }
@@ -6029,30 +6060,50 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                             tcg_temp_free(tmp2);
                             break;
                         case NEON_2RM_VCGT0_F:
+                        {
+                            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
                             tmp2 = tcg_const_i32(0);
-                            gen_helper_neon_cgt_f32(tmp, tmp, tmp2);
+                            gen_helper_neon_cgt_f32(tmp, tmp, tmp2, fpstatus);
                             tcg_temp_free(tmp2);
+                            tcg_temp_free_ptr(fpstatus);
                             break;
+                        }
                         case NEON_2RM_VCGE0_F:
+                        {
+                            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
                             tmp2 = tcg_const_i32(0);
-                            gen_helper_neon_cge_f32(tmp, tmp, tmp2);
+                            gen_helper_neon_cge_f32(tmp, tmp, tmp2, fpstatus);
                             tcg_temp_free(tmp2);
+                            tcg_temp_free_ptr(fpstatus);
                             break;
+                        }
                         case NEON_2RM_VCEQ0_F:
+                        {
+                            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
                             tmp2 = tcg_const_i32(0);
-                            gen_helper_neon_ceq_f32(tmp, tmp, tmp2);
+                            gen_helper_neon_ceq_f32(tmp, tmp, tmp2, fpstatus);
                             tcg_temp_free(tmp2);
+                            tcg_temp_free_ptr(fpstatus);
                             break;
+                        }
                         case NEON_2RM_VCLE0_F:
+                        {
+                            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
                             tmp2 = tcg_const_i32(0);
-                            gen_helper_neon_cge_f32(tmp, tmp2, tmp);
+                            gen_helper_neon_cge_f32(tmp, tmp2, tmp, fpstatus);
                             tcg_temp_free(tmp2);
+                            tcg_temp_free_ptr(fpstatus);
                             break;
+                        }
                         case NEON_2RM_VCLT0_F:
+                        {
+                            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
                             tmp2 = tcg_const_i32(0);
-                            gen_helper_neon_cgt_f32(tmp, tmp2, tmp);
+                            gen_helper_neon_cgt_f32(tmp, tmp2, tmp, fpstatus);
                             tcg_temp_free(tmp2);
+                            tcg_temp_free_ptr(fpstatus);
                             break;
+                        }
                         case NEON_2RM_VABS_F:
                             gen_vfp_abs(0);
                             break;