[v2,5/6] Revert "target-arm: Use global env in neon_helper.c helpers"

diff --git a/target-arm/helper.h b/target-arm/helper.h
index c29efd5..3ad1cb0 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -154,22 +154,22 @@  DEF_HELPER_2(sar_cc, i32, i32, i32)
 DEF_HELPER_2(ror_cc, i32, i32, i32)
 
 /* neon_helper.c */
-DEF_HELPER_2(neon_qadd_u8, i32, i32, i32)
-DEF_HELPER_2(neon_qadd_s8, i32, i32, i32)
-DEF_HELPER_2(neon_qadd_u16, i32, i32, i32)
-DEF_HELPER_2(neon_qadd_s16, i32, i32, i32)
-DEF_HELPER_2(neon_qadd_u32, i32, i32, i32)
-DEF_HELPER_2(neon_qadd_s32, i32, i32, i32)
-DEF_HELPER_2(neon_qsub_u8, i32, i32, i32)
-DEF_HELPER_2(neon_qsub_s8, i32, i32, i32)
-DEF_HELPER_2(neon_qsub_u16, i32, i32, i32)
-DEF_HELPER_2(neon_qsub_s16, i32, i32, i32)
-DEF_HELPER_2(neon_qsub_u32, i32, i32, i32)
-DEF_HELPER_2(neon_qsub_s32, i32, i32, i32)
-DEF_HELPER_2(neon_qadd_u64, i64, i64, i64)
-DEF_HELPER_2(neon_qadd_s64, i64, i64, i64)
-DEF_HELPER_2(neon_qsub_u64, i64, i64, i64)
-DEF_HELPER_2(neon_qsub_s64, i64, i64, i64)
+DEF_HELPER_3(neon_qadd_u8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qadd_s8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qadd_u16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qadd_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qadd_u32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qadd_s32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_u8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_s8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_u16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_u32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_s32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qadd_u64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qadd_s64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qsub_u64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qsub_s64, i64, env, i64, i64)
 
 DEF_HELPER_2(neon_hadd_s8, i32, i32, i32)
 DEF_HELPER_2(neon_hadd_u8, i32, i32, i32)
@@ -247,26 +247,26 @@  DEF_HELPER_2(neon_rshl_u32, i32, i32, i32)
 DEF_HELPER_2(neon_rshl_s32, i32, i32, i32)
 DEF_HELPER_2(neon_rshl_u64, i64, i64, i64)
 DEF_HELPER_2(neon_rshl_s64, i64, i64, i64)
-DEF_HELPER_2(neon_qshl_u8, i32, i32, i32)
-DEF_HELPER_2(neon_qshl_s8, i32, i32, i32)
-DEF_HELPER_2(neon_qshl_u16, i32, i32, i32)
-DEF_HELPER_2(neon_qshl_s16, i32, i32, i32)
-DEF_HELPER_2(neon_qshl_u32, i32, i32, i32)
-DEF_HELPER_2(neon_qshl_s32, i32, i32, i32)
-DEF_HELPER_2(neon_qshl_u64, i64, i64, i64)
-DEF_HELPER_2(neon_qshl_s64, i64, i64, i64)
-DEF_HELPER_2(neon_qshlu_s8, i32, i32, i32);
-DEF_HELPER_2(neon_qshlu_s16, i32, i32, i32);
-DEF_HELPER_2(neon_qshlu_s32, i32, i32, i32);
-DEF_HELPER_2(neon_qshlu_s64, i64, i64, i64);
-DEF_HELPER_2(neon_qrshl_u8, i32, i32, i32)
-DEF_HELPER_2(neon_qrshl_s8, i32, i32, i32)
-DEF_HELPER_2(neon_qrshl_u16, i32, i32, i32)
-DEF_HELPER_2(neon_qrshl_s16, i32, i32, i32)
-DEF_HELPER_2(neon_qrshl_u32, i32, i32, i32)
-DEF_HELPER_2(neon_qrshl_s32, i32, i32, i32)
-DEF_HELPER_2(neon_qrshl_u64, i64, i64, i64)
-DEF_HELPER_2(neon_qrshl_s64, i64, i64, i64)
+DEF_HELPER_3(neon_qshl_u8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_s8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_u16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_u32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_s32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qshl_u64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qshl_s64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qshlu_s8, i32, env, i32, i32);
+DEF_HELPER_3(neon_qshlu_s16, i32, env, i32, i32);
+DEF_HELPER_3(neon_qshlu_s32, i32, env, i32, i32);
+DEF_HELPER_3(neon_qshlu_s64, i64, env, i64, i64);
+DEF_HELPER_3(neon_qrshl_u8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_s8, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_u16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_u32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_s32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrshl_u64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qrshl_s64, i64, env, i64, i64)
 
 DEF_HELPER_2(neon_add_u8, i32, i32, i32)
 DEF_HELPER_2(neon_add_u16, i32, i32, i32)
@@ -295,22 +295,22 @@  DEF_HELPER_1(neon_cls_s16, i32, i32)
 DEF_HELPER_1(neon_cls_s32, i32, i32)
 DEF_HELPER_1(neon_cnt_u8, i32, i32)
 
-DEF_HELPER_2(neon_qdmulh_s16, i32, i32, i32)
-DEF_HELPER_2(neon_qrdmulh_s16, i32, i32, i32)
-DEF_HELPER_2(neon_qdmulh_s32, i32, i32, i32)
-DEF_HELPER_2(neon_qrdmulh_s32, i32, i32, i32)
+DEF_HELPER_3(neon_qdmulh_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrdmulh_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qdmulh_s32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qrdmulh_s32, i32, env, i32, i32)
 
 DEF_HELPER_1(neon_narrow_u8, i32, i64)
 DEF_HELPER_1(neon_narrow_u16, i32, i64)
-DEF_HELPER_1(neon_unarrow_sat8, i32, i64)
-DEF_HELPER_1(neon_narrow_sat_u8, i32, i64)
-DEF_HELPER_1(neon_narrow_sat_s8, i32, i64)
-DEF_HELPER_1(neon_unarrow_sat16, i32, i64)
-DEF_HELPER_1(neon_narrow_sat_u16, i32, i64)
-DEF_HELPER_1(neon_narrow_sat_s16, i32, i64)
-DEF_HELPER_1(neon_unarrow_sat32, i32, i64)
-DEF_HELPER_1(neon_narrow_sat_u32, i32, i64)
-DEF_HELPER_1(neon_narrow_sat_s32, i32, i64)
+DEF_HELPER_2(neon_unarrow_sat8, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_u8, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_s8, i32, env, i64)
+DEF_HELPER_2(neon_unarrow_sat16, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_u16, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_s16, i32, env, i64)
+DEF_HELPER_2(neon_unarrow_sat32, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_u32, i32, env, i64)
+DEF_HELPER_2(neon_narrow_sat_s32, i32, env, i64)
 DEF_HELPER_1(neon_narrow_high_u8, i32, i64)
 DEF_HELPER_1(neon_narrow_high_u16, i32, i64)
 DEF_HELPER_1(neon_narrow_round_high_u8, i32, i64)
@@ -326,8 +326,8 @@  DEF_HELPER_2(neon_paddl_u16, i64, i64, i64)
 DEF_HELPER_2(neon_paddl_u32, i64, i64, i64)
 DEF_HELPER_2(neon_subl_u16, i64, i64, i64)
 DEF_HELPER_2(neon_subl_u32, i64, i64, i64)
-DEF_HELPER_2(neon_addl_saturate_s32, i64, i64, i64)
-DEF_HELPER_2(neon_addl_saturate_s64, i64, i64, i64)
+DEF_HELPER_3(neon_addl_saturate_s32, i64, env, i64, i64)
+DEF_HELPER_3(neon_addl_saturate_s64, i64, env, i64, i64)
 DEF_HELPER_2(neon_abdl_u16, i64, i32, i32)
 DEF_HELPER_2(neon_abdl_s16, i64, i32, i32)
 DEF_HELPER_2(neon_abdl_u32, i64, i32, i32)
@@ -343,12 +343,12 @@  DEF_HELPER_1(neon_negl_u16, i64, i64)
 DEF_HELPER_1(neon_negl_u32, i64, i64)
 DEF_HELPER_1(neon_negl_u64, i64, i64)
 
-DEF_HELPER_1(neon_qabs_s8, i32, i32)
-DEF_HELPER_1(neon_qabs_s16, i32, i32)
-DEF_HELPER_1(neon_qabs_s32, i32, i32)
-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_qabs_s8, i32, env, i32)
+DEF_HELPER_2(neon_qabs_s16, i32, env, i32)
+DEF_HELPER_2(neon_qabs_s32, i32, env, i32)
+DEF_HELPER_2(neon_qneg_s8, i32, env, i32)
+DEF_HELPER_2(neon_qneg_s16, i32, env, i32)
+DEF_HELPER_2(neon_qneg_s32, i32, env, i32)
 
 DEF_HELPER_3(neon_min_f32, i32, i32, i32, ptr)
 DEF_HELPER_3(neon_max_f32, i32, i32, i32, ptr)
@@ -458,15 +458,15 @@  DEF_HELPER_3(iwmmxt_muladdswl, i64, i64, i32, i32)
 
 DEF_HELPER_2(set_teecr, void, env, i32)
 
-DEF_HELPER_2(neon_unzip8, void, i32, i32)
-DEF_HELPER_2(neon_unzip16, void, i32, i32)
-DEF_HELPER_2(neon_qunzip8, void, i32, i32)
-DEF_HELPER_2(neon_qunzip16, void, i32, i32)
-DEF_HELPER_2(neon_qunzip32, void, i32, i32)
-DEF_HELPER_2(neon_zip8, void, i32, i32)
-DEF_HELPER_2(neon_zip16, void, i32, i32)
-DEF_HELPER_2(neon_qzip8, void, i32, i32)
-DEF_HELPER_2(neon_qzip16, void, i32, i32)
-DEF_HELPER_2(neon_qzip32, void, i32, i32)
+DEF_HELPER_3(neon_unzip8, void, env, i32, i32)
+DEF_HELPER_3(neon_unzip16, void, env, i32, i32)
+DEF_HELPER_3(neon_qunzip8, void, env, i32, i32)
+DEF_HELPER_3(neon_qunzip16, void, env, i32, i32)
+DEF_HELPER_3(neon_qunzip32, void, env, i32, i32)
+DEF_HELPER_3(neon_zip8, void, env, i32, i32)
+DEF_HELPER_3(neon_zip16, void, env, i32, i32)
+DEF_HELPER_3(neon_qzip8, void, env, i32, i32)
+DEF_HELPER_3(neon_qzip16, void, env, i32, i32)
+DEF_HELPER_3(neon_qzip32, void, env, i32, i32)
 
 #include "def-helper.h"
diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c
index fda4021..2830627 100644
--- a/target-arm/neon_helper.c
+++ b/target-arm/neon_helper.c
@@ -10,7 +10,7 @@ 
 #include <stdio.h>
 
 #include "cpu.h"
-#include "exec.h"
+#include "exec-all.h"
 #include "helper.h"
 
 #define SIGNBIT (uint32_t)0x80000000
@@ -113,6 +113,10 @@  NEON_TYPE1(u32, uint32_t)
 uint32_t HELPER(glue(neon_,name))(uint32_t arg1, uint32_t arg2) \
 NEON_VOP_BODY(vtype, n)
 
+#define NEON_VOP_ENV(name, vtype, n) \
+uint32_t HELPER(glue(neon_,name))(CPUState *env, uint32_t arg1, uint32_t arg2) \
+NEON_VOP_BODY(vtype, n)
+
 /* Pairwise operations.  */
 /* For 32-bit elements each segment only contains a single element, so
    the elementwise and pairwise operations are the same.  */
@@ -161,14 +165,14 @@  uint32_t HELPER(glue(neon_,name))(uint32_t arg) \
         dest = tmp; \
     }} while(0)
 #define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint8_t)
-NEON_VOP(qadd_u8, neon_u8, 4)
+NEON_VOP_ENV(qadd_u8, neon_u8, 4)
 #undef NEON_FN
 #define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint16_t)
-NEON_VOP(qadd_u16, neon_u16, 2)
+NEON_VOP_ENV(qadd_u16, neon_u16, 2)
 #undef NEON_FN
 #undef NEON_USAT
 
-uint32_t HELPER(neon_qadd_u32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_qadd_u32)(CPUState *env, uint32_t a, uint32_t b)
 {
     uint32_t res = a + b;
     if (res < a) {
@@ -178,7 +182,7 @@  uint32_t HELPER(neon_qadd_u32)(uint32_t a, uint32_t b)
     return res;
 }
 
-uint64_t HELPER(neon_qadd_u64)(uint64_t src1, uint64_t src2)
+uint64_t HELPER(neon_qadd_u64)(CPUState *env, uint64_t src1, uint64_t src2)
 {
     uint64_t res;
 
@@ -203,14 +207,14 @@  uint64_t HELPER(neon_qadd_u64)(uint64_t src1, uint64_t src2)
     dest = tmp; \
     } while(0)
 #define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int8_t)
-NEON_VOP(qadd_s8, neon_s8, 4)
+NEON_VOP_ENV(qadd_s8, neon_s8, 4)
 #undef NEON_FN
 #define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int16_t)
-NEON_VOP(qadd_s16, neon_s16, 2)
+NEON_VOP_ENV(qadd_s16, neon_s16, 2)
 #undef NEON_FN
 #undef NEON_SSAT
 
-uint32_t HELPER(neon_qadd_s32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_qadd_s32)(CPUState *env, uint32_t a, uint32_t b)
 {
     uint32_t res = a + b;
     if (((res ^ a) & SIGNBIT) && !((a ^ b) & SIGNBIT)) {
@@ -220,7 +224,7 @@  uint32_t HELPER(neon_qadd_s32)(uint32_t a, uint32_t b)
     return res;
 }
 
-uint64_t HELPER(neon_qadd_s64)(uint64_t src1, uint64_t src2)
+uint64_t HELPER(neon_qadd_s64)(CPUState *env, uint64_t src1, uint64_t src2)
 {
     uint64_t res;
 
@@ -241,14 +245,14 @@  uint64_t HELPER(neon_qadd_s64)(uint64_t src1, uint64_t src2)
         dest = tmp; \
     }} while(0)
 #define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint8_t)
-NEON_VOP(qsub_u8, neon_u8, 4)
+NEON_VOP_ENV(qsub_u8, neon_u8, 4)
 #undef NEON_FN
 #define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint16_t)
-NEON_VOP(qsub_u16, neon_u16, 2)
+NEON_VOP_ENV(qsub_u16, neon_u16, 2)
 #undef NEON_FN
 #undef NEON_USAT
 
-uint32_t HELPER(neon_qsub_u32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_qsub_u32)(CPUState *env, uint32_t a, uint32_t b)
 {
     uint32_t res = a - b;
     if (res > a) {
@@ -258,7 +262,7 @@  uint32_t HELPER(neon_qsub_u32)(uint32_t a, uint32_t b)
     return res;
 }
 
-uint64_t HELPER(neon_qsub_u64)(uint64_t src1, uint64_t src2)
+uint64_t HELPER(neon_qsub_u64)(CPUState *env, uint64_t src1, uint64_t src2)
 {
     uint64_t res;
 
@@ -284,14 +288,14 @@  uint64_t HELPER(neon_qsub_u64)(uint64_t src1, uint64_t src2)
     dest = tmp; \
     } while(0)
 #define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int8_t)
-NEON_VOP(qsub_s8, neon_s8, 4)
+NEON_VOP_ENV(qsub_s8, neon_s8, 4)
 #undef NEON_FN
 #define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int16_t)
-NEON_VOP(qsub_s16, neon_s16, 2)
+NEON_VOP_ENV(qsub_s16, neon_s16, 2)
 #undef NEON_FN
 #undef NEON_SSAT
 
-uint32_t HELPER(neon_qsub_s32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_qsub_s32)(CPUState *env, uint32_t a, uint32_t b)
 {
     uint32_t res = a - b;
     if (((res ^ a) & SIGNBIT) && ((a ^ b) & SIGNBIT)) {
@@ -301,7 +305,7 @@  uint32_t HELPER(neon_qsub_s32)(uint32_t a, uint32_t b)
     return res;
 }
 
-uint64_t HELPER(neon_qsub_s64)(uint64_t src1, uint64_t src2)
+uint64_t HELPER(neon_qsub_s64)(CPUState *env, uint64_t src1, uint64_t src2)
 {
     uint64_t res;
 
@@ -652,12 +656,12 @@  uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shiftop)
             dest = ~0; \
         } \
     }} while (0)
-NEON_VOP(qshl_u8, neon_u8, 4)
-NEON_VOP(qshl_u16, neon_u16, 2)
-NEON_VOP(qshl_u32, neon_u32, 1)
+NEON_VOP_ENV(qshl_u8, neon_u8, 4)
+NEON_VOP_ENV(qshl_u16, neon_u16, 2)
+NEON_VOP_ENV(qshl_u32, neon_u32, 1)
 #undef NEON_FN
 
-uint64_t HELPER(neon_qshl_u64)(uint64_t val, uint64_t shiftop)
+uint64_t HELPER(neon_qshl_u64)(CPUState *env, uint64_t val, uint64_t shiftop)
 {
     int8_t shift = (int8_t)shiftop;
     if (shift >= 64) {
@@ -707,12 +711,12 @@  uint64_t HELPER(neon_qshl_u64)(uint64_t val, uint64_t shiftop)
             } \
         } \
     }} while (0)
-NEON_VOP(qshl_s8, neon_s8, 4)
-NEON_VOP(qshl_s16, neon_s16, 2)
-NEON_VOP(qshl_s32, neon_s32, 1)
+NEON_VOP_ENV(qshl_s8, neon_s8, 4)
+NEON_VOP_ENV(qshl_s16, neon_s16, 2)
+NEON_VOP_ENV(qshl_s32, neon_s32, 1)
 #undef NEON_FN
 
-uint64_t HELPER(neon_qshl_s64)(uint64_t valop, uint64_t shiftop)
+uint64_t HELPER(neon_qshl_s64)(CPUState *env, uint64_t valop, uint64_t shiftop)
 {
     int8_t shift = (uint8_t)shiftop;
     int64_t val = valop;
@@ -762,26 +766,26 @@  uint64_t HELPER(neon_qshl_s64)(uint64_t valop, uint64_t shiftop)
             } \
         } \
     }} while (0)
-NEON_VOP(qshlu_s8, neon_u8, 4)
-NEON_VOP(qshlu_s16, neon_u16, 2)
+NEON_VOP_ENV(qshlu_s8, neon_u8, 4)
+NEON_VOP_ENV(qshlu_s16, neon_u16, 2)
 #undef NEON_FN
 
-uint32_t HELPER(neon_qshlu_s32)(uint32_t valop, uint32_t shiftop)
+uint32_t HELPER(neon_qshlu_s32)(CPUState *env, uint32_t valop, uint32_t shiftop)
 {
     if ((int32_t)valop < 0) {
         SET_QC();
         return 0;
     }
-    return helper_neon_qshl_u32(valop, shiftop);
+    return helper_neon_qshl_u32(env, valop, shiftop);
 }
 
-uint64_t HELPER(neon_qshlu_s64)(uint64_t valop, uint64_t shiftop)
+uint64_t HELPER(neon_qshlu_s64)(CPUState *env, uint64_t valop, uint64_t shiftop)
 {
     if ((int64_t)valop < 0) {
         SET_QC();
         return 0;
     }
-    return helper_neon_qshl_u64(valop, shiftop);
+    return helper_neon_qshl_u64(env, valop, shiftop);
 }
 
 /* FIXME: This is wrong.  */
@@ -808,13 +812,13 @@  uint64_t HELPER(neon_qshlu_s64)(uint64_t valop, uint64_t shiftop)
             dest = ~0; \
         } \
     }} while (0)
-NEON_VOP(qrshl_u8, neon_u8, 4)
-NEON_VOP(qrshl_u16, neon_u16, 2)
+NEON_VOP_ENV(qrshl_u8, neon_u8, 4)
+NEON_VOP_ENV(qrshl_u16, neon_u16, 2)
 #undef NEON_FN
 
 /* The addition of the rounding constant may overflow, so we use an
  * intermediate 64 bits accumulator.  */
-uint32_t HELPER(neon_qrshl_u32)(uint32_t val, uint32_t shiftop)
+uint32_t HELPER(neon_qrshl_u32)(CPUState *env, uint32_t val, uint32_t shiftop)
 {
     uint32_t dest;
     int8_t shift = (int8_t)shiftop;
@@ -844,7 +848,7 @@  uint32_t HELPER(neon_qrshl_u32)(uint32_t val, uint32_t shiftop)
 
 /* Handling addition overflow with 64 bits inputs values is more
  * tricky than with 32 bits values.  */
-uint64_t HELPER(neon_qrshl_u64)(uint64_t val, uint64_t shiftop)
+uint64_t HELPER(neon_qrshl_u64)(CPUState *env, uint64_t val, uint64_t shiftop)
 {
     int8_t shift = (int8_t)shiftop;
     if (shift >= 64) {
@@ -905,13 +909,13 @@  uint64_t HELPER(neon_qrshl_u64)(uint64_t val, uint64_t shiftop)
             } \
         } \
     }} while (0)
-NEON_VOP(qrshl_s8, neon_s8, 4)
-NEON_VOP(qrshl_s16, neon_s16, 2)
+NEON_VOP_ENV(qrshl_s8, neon_s8, 4)
+NEON_VOP_ENV(qrshl_s16, neon_s16, 2)
 #undef NEON_FN
 
 /* The addition of the rounding constant may overflow, so we use an
  * intermediate 64 bits accumulator.  */
-uint32_t HELPER(neon_qrshl_s32)(uint32_t valop, uint32_t shiftop)
+uint32_t HELPER(neon_qrshl_s32)(CPUState *env, uint32_t valop, uint32_t shiftop)
 {
     int32_t dest;
     int32_t val = (int32_t)valop;
@@ -940,7 +944,7 @@  uint32_t HELPER(neon_qrshl_s32)(uint32_t valop, uint32_t shiftop)
 
 /* Handling addition overflow with 64 bits inputs values is more
  * tricky than with 32 bits values.  */
-uint64_t HELPER(neon_qrshl_s64)(uint64_t valop, uint64_t shiftop)
+uint64_t HELPER(neon_qrshl_s64)(CPUState *env, uint64_t valop, uint64_t shiftop)
 {
     int8_t shift = (uint8_t)shiftop;
     int64_t val = valop;
@@ -1149,10 +1153,10 @@  uint32_t HELPER(neon_cnt_u8)(uint32_t x)
     dest = tmp >> 16; \
     } while(0)
 #define NEON_FN(dest, src1, src2) NEON_QDMULH16(dest, src1, src2, 0)
-NEON_VOP(qdmulh_s16, neon_s16, 2)
+NEON_VOP_ENV(qdmulh_s16, neon_s16, 2)
 #undef NEON_FN
 #define NEON_FN(dest, src1, src2) NEON_QDMULH16(dest, src1, src2, 1)
-NEON_VOP(qrdmulh_s16, neon_s16, 2)
+NEON_VOP_ENV(qrdmulh_s16, neon_s16, 2)
 #undef NEON_FN
 #undef NEON_QDMULH16
 
@@ -1175,10 +1179,10 @@  NEON_VOP(qrdmulh_s16, neon_s16, 2)
     dest = tmp >> 32; \
     } while(0)
 #define NEON_FN(dest, src1, src2) NEON_QDMULH32(dest, src1, src2, 0)
-NEON_VOP(qdmulh_s32, neon_s32, 1)
+NEON_VOP_ENV(qdmulh_s32, neon_s32, 1)
 #undef NEON_FN
 #define NEON_FN(dest, src1, src2) NEON_QDMULH32(dest, src1, src2, 1)
-NEON_VOP(qrdmulh_s32, neon_s32, 1)
+NEON_VOP_ENV(qrdmulh_s32, neon_s32, 1)
 #undef NEON_FN
 #undef NEON_QDMULH32
 
@@ -1219,7 +1223,7 @@  uint32_t HELPER(neon_narrow_round_high_u16)(uint64_t x)
     return ((x >> 16) & 0xffff) | ((x >> 32) & 0xffff0000);
 }
 
-uint32_t HELPER(neon_unarrow_sat8)(uint64_t x)
+uint32_t HELPER(neon_unarrow_sat8)(CPUState *env, uint64_t x)
 {
     uint16_t s;
     uint8_t d;
@@ -1246,7 +1250,7 @@  uint32_t HELPER(neon_unarrow_sat8)(uint64_t x)
     return res;
 }
 
-uint32_t HELPER(neon_narrow_sat_u8)(uint64_t x)
+uint32_t HELPER(neon_narrow_sat_u8)(CPUState *env, uint64_t x)
 {
     uint16_t s;
     uint8_t d;
@@ -1269,7 +1273,7 @@  uint32_t HELPER(neon_narrow_sat_u8)(uint64_t x)
     return res;
 }
 
-uint32_t HELPER(neon_narrow_sat_s8)(uint64_t x)
+uint32_t HELPER(neon_narrow_sat_s8)(CPUState *env, uint64_t x)
 {
     int16_t s;
     uint8_t d;
@@ -1292,7 +1296,7 @@  uint32_t HELPER(neon_narrow_sat_s8)(uint64_t x)
     return res;
 }
 
-uint32_t HELPER(neon_unarrow_sat16)(uint64_t x)
+uint32_t HELPER(neon_unarrow_sat16)(CPUState *env, uint64_t x)
 {
     uint32_t high;
     uint32_t low;
@@ -1315,7 +1319,7 @@  uint32_t HELPER(neon_unarrow_sat16)(uint64_t x)
     return low | (high << 16);
 }
 
-uint32_t HELPER(neon_narrow_sat_u16)(uint64_t x)
+uint32_t HELPER(neon_narrow_sat_u16)(CPUState *env, uint64_t x)
 {
     uint32_t high;
     uint32_t low;
@@ -1332,7 +1336,7 @@  uint32_t HELPER(neon_narrow_sat_u16)(uint64_t x)
     return low | (high << 16);
 }
 
-uint32_t HELPER(neon_narrow_sat_s16)(uint64_t x)
+uint32_t HELPER(neon_narrow_sat_s16)(CPUState *env, uint64_t x)
 {
     int32_t low;
     int32_t high;
@@ -1349,7 +1353,7 @@  uint32_t HELPER(neon_narrow_sat_s16)(uint64_t x)
     return (uint16_t)low | (high << 16);
 }
 
-uint32_t HELPER(neon_unarrow_sat32)(uint64_t x)
+uint32_t HELPER(neon_unarrow_sat32)(CPUState *env, uint64_t x)
 {
     if (x & 0x8000000000000000ull) {
         SET_QC();
@@ -1362,7 +1366,7 @@  uint32_t HELPER(neon_unarrow_sat32)(uint64_t x)
     return x;
 }
 
-uint32_t HELPER(neon_narrow_sat_u32)(uint64_t x)
+uint32_t HELPER(neon_narrow_sat_u32)(CPUState *env, uint64_t x)
 {
     if (x > 0xffffffffu) {
         SET_QC();
@@ -1371,7 +1375,7 @@  uint32_t HELPER(neon_narrow_sat_u32)(uint64_t x)
     return x;
 }
 
-uint32_t HELPER(neon_narrow_sat_s32)(uint64_t x)
+uint32_t HELPER(neon_narrow_sat_s32)(CPUState *env, uint64_t x)
 {
     if ((int64_t)x != (int32_t)x) {
         SET_QC();
@@ -1478,7 +1482,7 @@  uint64_t HELPER(neon_subl_u32)(uint64_t a, uint64_t b)
     return (a - b) ^ mask;
 }
 
-uint64_t HELPER(neon_addl_saturate_s32)(uint64_t a, uint64_t b)
+uint64_t HELPER(neon_addl_saturate_s32)(CPUState *env, uint64_t a, uint64_t b)
 {
     uint32_t x, y;
     uint32_t low, high;
@@ -1500,7 +1504,7 @@  uint64_t HELPER(neon_addl_saturate_s32)(uint64_t a, uint64_t b)
     return low | ((uint64_t)high << 32);
 }
 
-uint64_t HELPER(neon_addl_saturate_s64)(uint64_t a, uint64_t b)
+uint64_t HELPER(neon_addl_saturate_s64)(CPUState *env, uint64_t a, uint64_t b)
 {
     uint64_t result;
 
@@ -1676,7 +1680,7 @@  uint64_t HELPER(neon_negl_u64)(uint64_t x)
     } else if (x < 0) { \
         x = -x; \
     }} while (0)
-uint32_t HELPER(neon_qabs_s8)(uint32_t x)
+uint32_t HELPER(neon_qabs_s8)(CPUState *env, uint32_t x)
 {
     neon_s8 vec;
     NEON_UNPACK(neon_s8, vec, x);
@@ -1696,7 +1700,7 @@  uint32_t HELPER(neon_qabs_s8)(uint32_t x)
     } else { \
         x = -x; \
     }} while (0)
-uint32_t HELPER(neon_qneg_s8)(uint32_t x)
+uint32_t HELPER(neon_qneg_s8)(CPUState *env, uint32_t x)
 {
     neon_s8 vec;
     NEON_UNPACK(neon_s8, vec, x);
@@ -1716,7 +1720,7 @@  uint32_t HELPER(neon_qneg_s8)(uint32_t x)
     } else if (x < 0) { \
         x = -x; \
     }} while (0)
-uint32_t HELPER(neon_qabs_s16)(uint32_t x)
+uint32_t HELPER(neon_qabs_s16)(CPUState *env, uint32_t x)
 {
     neon_s16 vec;
     NEON_UNPACK(neon_s16, vec, x);
@@ -1734,7 +1738,7 @@  uint32_t HELPER(neon_qabs_s16)(uint32_t x)
     } else { \
         x = -x; \
     }} while (0)
-uint32_t HELPER(neon_qneg_s16)(uint32_t x)
+uint32_t HELPER(neon_qneg_s16)(CPUState *env, uint32_t x)
 {
     neon_s16 vec;
     NEON_UNPACK(neon_s16, vec, x);
@@ -1745,7 +1749,7 @@  uint32_t HELPER(neon_qneg_s16)(uint32_t x)
 }
 #undef DO_QNEG16
 
-uint32_t HELPER(neon_qabs_s32)(uint32_t x)
+uint32_t HELPER(neon_qabs_s32)(CPUState *env, uint32_t x)
 {
     if (x == SIGNBIT) {
         SET_QC();
@@ -1756,7 +1760,7 @@  uint32_t HELPER(neon_qabs_s32)(uint32_t x)
     return x;
 }
 
-uint32_t HELPER(neon_qneg_s32)(uint32_t x)
+uint32_t HELPER(neon_qneg_s32)(CPUState *env, uint32_t x)
 {
     if (x == SIGNBIT) {
         SET_QC();
@@ -1828,7 +1832,7 @@  uint32_t HELPER(neon_acgt_f32)(uint32_t a, uint32_t b, void *fpstp)
 
 #define ELEM(V, N, SIZE) (((V) >> ((N) * (SIZE))) & ((1ull << (SIZE)) - 1))
 
-void HELPER(neon_qunzip8)(uint32_t rd, uint32_t rm)
+void HELPER(neon_qunzip8)(CPUState *env, uint32_t rd, uint32_t rm)
 {
     uint64_t zm0 = float64_val(env->vfp.regs[rm]);
     uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
@@ -1856,7 +1860,7 @@  void HELPER(neon_qunzip8)(uint32_t rd, uint32_t rm)
     env->vfp.regs[rd + 1] = make_float64(d1);
 }
 
-void HELPER(neon_qunzip16)(uint32_t rd, uint32_t rm)
+void HELPER(neon_qunzip16)(CPUState *env, uint32_t rd, uint32_t rm)
 {
     uint64_t zm0 = float64_val(env->vfp.regs[rm]);
     uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
@@ -1876,7 +1880,7 @@  void HELPER(neon_qunzip16)(uint32_t rd, uint32_t rm)
     env->vfp.regs[rd + 1] = make_float64(d1);
 }
 
-void HELPER(neon_qunzip32)(uint32_t rd, uint32_t rm)
+void HELPER(neon_qunzip32)(CPUState *env, uint32_t rd, uint32_t rm)
 {
     uint64_t zm0 = float64_val(env->vfp.regs[rm]);
     uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
@@ -1892,7 +1896,7 @@  void HELPER(neon_qunzip32)(uint32_t rd, uint32_t rm)
     env->vfp.regs[rd + 1] = make_float64(d1);
 }
 
-void HELPER(neon_unzip8)(uint32_t rd, uint32_t rm)
+void HELPER(neon_unzip8)(CPUState *env, uint32_t rd, uint32_t rm)
 {
     uint64_t zm = float64_val(env->vfp.regs[rm]);
     uint64_t zd = float64_val(env->vfp.regs[rd]);
@@ -1908,7 +1912,7 @@  void HELPER(neon_unzip8)(uint32_t rd, uint32_t rm)
     env->vfp.regs[rd] = make_float64(d0);
 }
 
-void HELPER(neon_unzip16)(uint32_t rd, uint32_t rm)
+void HELPER(neon_unzip16)(CPUState *env, uint32_t rd, uint32_t rm)
 {
     uint64_t zm = float64_val(env->vfp.regs[rm]);
     uint64_t zd = float64_val(env->vfp.regs[rd]);
@@ -1920,7 +1924,7 @@  void HELPER(neon_unzip16)(uint32_t rd, uint32_t rm)
     env->vfp.regs[rd] = make_float64(d0);
 }
 
-void HELPER(neon_qzip8)(uint32_t rd, uint32_t rm)
+void HELPER(neon_qzip8)(CPUState *env, uint32_t rd, uint32_t rm)
 {
     uint64_t zm0 = float64_val(env->vfp.regs[rm]);
     uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
@@ -1948,7 +1952,7 @@  void HELPER(neon_qzip8)(uint32_t rd, uint32_t rm)
     env->vfp.regs[rd + 1] = make_float64(d1);
 }
 
-void HELPER(neon_qzip16)(uint32_t rd, uint32_t rm)
+void HELPER(neon_qzip16)(CPUState *env, uint32_t rd, uint32_t rm)
 {
     uint64_t zm0 = float64_val(env->vfp.regs[rm]);
     uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
@@ -1968,7 +1972,7 @@  void HELPER(neon_qzip16)(uint32_t rd, uint32_t rm)
     env->vfp.regs[rd + 1] = make_float64(d1);
 }
 
-void HELPER(neon_qzip32)(uint32_t rd, uint32_t rm)
+void HELPER(neon_qzip32)(CPUState *env, uint32_t rd, uint32_t rm)
 {
     uint64_t zm0 = float64_val(env->vfp.regs[rm]);
     uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
@@ -1984,7 +1988,7 @@  void HELPER(neon_qzip32)(uint32_t rd, uint32_t rm)
     env->vfp.regs[rd + 1] = make_float64(d1);
 }
 
-void HELPER(neon_zip8)(uint32_t rd, uint32_t rm)
+void HELPER(neon_zip8)(CPUState *env, uint32_t rd, uint32_t rm)
 {
     uint64_t zm = float64_val(env->vfp.regs[rm]);
     uint64_t zd = float64_val(env->vfp.regs[rd]);
@@ -2000,7 +2004,7 @@  void HELPER(neon_zip8)(uint32_t rd, uint32_t rm)
     env->vfp.regs[rd] = make_float64(d0);
 }
 
-void HELPER(neon_zip16)(uint32_t rd, uint32_t rm)
+void HELPER(neon_zip16)(CPUState *env, uint32_t rd, uint32_t rm)
 {
     uint64_t zm = float64_val(env->vfp.regs[rm]);
     uint64_t zd = float64_val(env->vfp.regs[rd]);
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 27d9887..0273deb 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -3711,13 +3711,13 @@  static int gen_neon_unzip(int rd, int rm, int size, int q)
     if (q) {
         switch (size) {
         case 0:
-            gen_helper_neon_qunzip8(tmp, tmp2);
+            gen_helper_neon_qunzip8(cpu_env, tmp, tmp2);
             break;
         case 1:
-            gen_helper_neon_qunzip16(tmp, tmp2);
+            gen_helper_neon_qunzip16(cpu_env, tmp, tmp2);
             break;
         case 2:
-            gen_helper_neon_qunzip32(tmp, tmp2);
+            gen_helper_neon_qunzip32(cpu_env, tmp, tmp2);
             break;
         default:
             abort();
@@ -3725,10 +3725,10 @@  static int gen_neon_unzip(int rd, int rm, int size, int q)
     } else {
         switch (size) {
         case 0:
-            gen_helper_neon_unzip8(tmp, tmp2);
+            gen_helper_neon_unzip8(cpu_env, tmp, tmp2);
             break;
         case 1:
-            gen_helper_neon_unzip16(tmp, tmp2);
+            gen_helper_neon_unzip16(cpu_env, tmp, tmp2);
             break;
         default:
             abort();
@@ -3750,13 +3750,13 @@  static int gen_neon_zip(int rd, int rm, int size, int q)
     if (q) {
         switch (size) {
         case 0:
-            gen_helper_neon_qzip8(tmp, tmp2);
+            gen_helper_neon_qzip8(cpu_env, tmp, tmp2);
             break;
         case 1:
-            gen_helper_neon_qzip16(tmp, tmp2);
+            gen_helper_neon_qzip16(cpu_env, tmp, tmp2);
             break;
         case 2:
-            gen_helper_neon_qzip32(tmp, tmp2);
+            gen_helper_neon_qzip32(cpu_env, tmp, tmp2);
             break;
         default:
             abort();
@@ -3764,10 +3764,10 @@  static int gen_neon_zip(int rd, int rm, int size, int q)
     } else {
         switch (size) {
         case 0:
-            gen_helper_neon_zip8(tmp, tmp2);
+            gen_helper_neon_zip8(cpu_env, tmp, tmp2);
             break;
         case 1:
-            gen_helper_neon_zip16(tmp, tmp2);
+            gen_helper_neon_zip16(cpu_env, tmp, tmp2);
             break;
         default:
             abort();
@@ -4167,9 +4167,9 @@  static inline void gen_neon_narrow(int size, TCGv dest, TCGv_i64 src)
 static inline void gen_neon_narrow_sats(int size, TCGv dest, TCGv_i64 src)
 {
     switch (size) {
-    case 0: gen_helper_neon_narrow_sat_s8(dest, src); break;
-    case 1: gen_helper_neon_narrow_sat_s16(dest, src); break;
-    case 2: gen_helper_neon_narrow_sat_s32(dest, src); break;
+    case 0: gen_helper_neon_narrow_sat_s8(dest, cpu_env, src); break;
+    case 1: gen_helper_neon_narrow_sat_s16(dest, cpu_env, src); break;
+    case 2: gen_helper_neon_narrow_sat_s32(dest, cpu_env, src); break;
     default: abort();
     }
 }
@@ -4177,9 +4177,9 @@  static inline void gen_neon_narrow_sats(int size, TCGv dest, TCGv_i64 src)
 static inline void gen_neon_narrow_satu(int size, TCGv dest, TCGv_i64 src)
 {
     switch (size) {
-    case 0: gen_helper_neon_narrow_sat_u8(dest, src); break;
-    case 1: gen_helper_neon_narrow_sat_u16(dest, src); break;
-    case 2: gen_helper_neon_narrow_sat_u32(dest, src); break;
+    case 0: gen_helper_neon_narrow_sat_u8(dest, cpu_env, src); break;
+    case 1: gen_helper_neon_narrow_sat_u16(dest, cpu_env, src); break;
+    case 2: gen_helper_neon_narrow_sat_u32(dest, cpu_env, src); break;
     default: abort();
     }
 }
@@ -4187,9 +4187,9 @@  static inline void gen_neon_narrow_satu(int size, TCGv dest, TCGv_i64 src)
 static inline void gen_neon_unarrow_sats(int size, TCGv dest, TCGv_i64 src)
 {
     switch (size) {
-    case 0: gen_helper_neon_unarrow_sat8(dest, src); break;
-    case 1: gen_helper_neon_unarrow_sat16(dest, src); break;
-    case 2: gen_helper_neon_unarrow_sat32(dest, src); break;
+    case 0: gen_helper_neon_unarrow_sat8(dest, cpu_env, src); break;
+    case 1: gen_helper_neon_unarrow_sat16(dest, cpu_env, src); break;
+    case 2: gen_helper_neon_unarrow_sat32(dest, cpu_env, src); break;
     default: abort();
     }
 }
@@ -4281,8 +4281,8 @@  static inline void gen_neon_negl(TCGv_i64 var, int size)
 static inline void gen_neon_addl_saturate(TCGv_i64 op0, TCGv_i64 op1, int size)
 {
     switch (size) {
-    case 1: gen_helper_neon_addl_saturate_s32(op0, op0, op1); break;
-    case 2: gen_helper_neon_addl_saturate_s64(op0, op0, op1); break;
+    case 1: gen_helper_neon_addl_saturate_s32(op0, cpu_env, op0, op1); break;
+    case 2: gen_helper_neon_addl_saturate_s64(op0, cpu_env, op0, op1); break;
     default: abort();
     }
 }
@@ -4558,16 +4558,20 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                 switch (op) {
                 case NEON_3R_VQADD:
                     if (u) {
-                        gen_helper_neon_qadd_u64(cpu_V0, cpu_V0, cpu_V1);
+                        gen_helper_neon_qadd_u64(cpu_V0, cpu_env,
+                                                 cpu_V0, cpu_V1);
                     } else {
-                        gen_helper_neon_qadd_s64(cpu_V0, cpu_V0, cpu_V1);
+                        gen_helper_neon_qadd_s64(cpu_V0, cpu_env,
+                                                 cpu_V0, cpu_V1);
                     }
                     break;
                 case NEON_3R_VQSUB:
                     if (u) {
-                        gen_helper_neon_qsub_u64(cpu_V0, cpu_V0, cpu_V1);
+                        gen_helper_neon_qsub_u64(cpu_V0, cpu_env,
+                                                 cpu_V0, cpu_V1);
                     } else {
-                        gen_helper_neon_qsub_s64(cpu_V0, cpu_V0, cpu_V1);
+                        gen_helper_neon_qsub_s64(cpu_V0, cpu_env,
+                                                 cpu_V0, cpu_V1);
                     }
                     break;
                 case NEON_3R_VSHL:
@@ -4579,9 +4583,11 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                     break;
                 case NEON_3R_VQSHL:
                     if (u) {
-                        gen_helper_neon_qshl_u64(cpu_V0, cpu_V1, cpu_V0);
+                        gen_helper_neon_qshl_u64(cpu_V0, cpu_env,
+                                                 cpu_V1, cpu_V0);
                     } else {
-                        gen_helper_neon_qshl_s64(cpu_V0, cpu_V1, cpu_V0);
+                        gen_helper_neon_qshl_s64(cpu_V0, cpu_env,
+                                                 cpu_V1, cpu_V0);
                     }
                     break;
                 case NEON_3R_VRSHL:
@@ -4593,9 +4599,11 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                     break;
                 case NEON_3R_VQRSHL:
                     if (u) {
-                        gen_helper_neon_qrshl_u64(cpu_V0, cpu_V1, cpu_V0);
+                        gen_helper_neon_qrshl_u64(cpu_V0, cpu_env,
+                                                  cpu_V1, cpu_V0);
                     } else {
-                        gen_helper_neon_qrshl_s64(cpu_V0, cpu_V1, cpu_V0);
+                        gen_helper_neon_qrshl_s64(cpu_V0, cpu_env,
+                                                  cpu_V1, cpu_V0);
                     }
                     break;
                 case NEON_3R_VADD_VSUB:
@@ -4693,7 +4701,7 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
             GEN_NEON_INTEGER_OP(hadd);
             break;
         case NEON_3R_VQADD:
-            GEN_NEON_INTEGER_OP(qadd);
+            GEN_NEON_INTEGER_OP_ENV(qadd);
             break;
         case NEON_3R_VRHADD:
             GEN_NEON_INTEGER_OP(rhadd);
@@ -4736,7 +4744,7 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
             GEN_NEON_INTEGER_OP(hsub);
             break;
         case NEON_3R_VQSUB:
-            GEN_NEON_INTEGER_OP(qsub);
+            GEN_NEON_INTEGER_OP_ENV(qsub);
             break;
         case NEON_3R_VCGT:
             GEN_NEON_INTEGER_OP(cgt);
@@ -4748,13 +4756,13 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
             GEN_NEON_INTEGER_OP(shl);
             break;
         case NEON_3R_VQSHL:
-            GEN_NEON_INTEGER_OP(qshl);
+            GEN_NEON_INTEGER_OP_ENV(qshl);
             break;
         case NEON_3R_VRSHL:
             GEN_NEON_INTEGER_OP(rshl);
             break;
         case NEON_3R_VQRSHL:
-            GEN_NEON_INTEGER_OP(qrshl);
+            GEN_NEON_INTEGER_OP_ENV(qrshl);
             break;
         case NEON_3R_VMAX:
             GEN_NEON_INTEGER_OP(max);
@@ -4836,14 +4844,22 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
         case NEON_3R_VQDMULH_VQRDMULH: /* Multiply high.  */
             if (!u) { /* VQDMULH */
                 switch (size) {
-                case 1: gen_helper_neon_qdmulh_s16(tmp, tmp, tmp2); break;
-                case 2: gen_helper_neon_qdmulh_s32(tmp, tmp, tmp2); break;
+                case 1:
+                    gen_helper_neon_qdmulh_s16(tmp, cpu_env, tmp, tmp2);
+                    break;
+                case 2:
+                    gen_helper_neon_qdmulh_s32(tmp, cpu_env, tmp, tmp2);
+                    break;
                 default: abort();
                 }
             } else { /* VQRDMULH */
                 switch (size) {
-                case 1: gen_helper_neon_qrdmulh_s16(tmp, tmp, tmp2); break;
-                case 2: gen_helper_neon_qrdmulh_s32(tmp, tmp, tmp2); break;
+                case 1:
+                    gen_helper_neon_qrdmulh_s16(tmp, cpu_env, tmp, tmp2);
+                    break;
+                case 2:
+                    gen_helper_neon_qrdmulh_s32(tmp, cpu_env, tmp, tmp2);
+                    break;
                 default: abort();
                 }
             }
@@ -5035,14 +5051,15 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                             gen_helper_neon_shl_u64(cpu_V0, cpu_V0, cpu_V1);
                             break;
                         case 6: /* VQSHLU */
-                            gen_helper_neon_qshlu_s64(cpu_V0, cpu_V0, cpu_V1);
+                            gen_helper_neon_qshlu_s64(cpu_V0, cpu_env,
+                                                      cpu_V0, cpu_V1);
                             break;
                         case 7: /* VQSHL */
                             if (u) {
-                                gen_helper_neon_qshl_u64(cpu_V0,
+                                gen_helper_neon_qshl_u64(cpu_V0, cpu_env,
                                                          cpu_V0, cpu_V1);
                             } else {
-                                gen_helper_neon_qshl_s64(cpu_V0,
+                                gen_helper_neon_qshl_s64(cpu_V0, cpu_env,
                                                          cpu_V0, cpu_V1);
                             }
                             break;
@@ -5094,20 +5111,23 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                         case 6: /* VQSHLU */
                             switch (size) {
                             case 0:
-                                gen_helper_neon_qshlu_s8(tmp, tmp, tmp2);
+                                gen_helper_neon_qshlu_s8(tmp, cpu_env,
+                                                         tmp, tmp2);
                                 break;
                             case 1:
-                                gen_helper_neon_qshlu_s16(tmp, tmp, tmp2);
+                                gen_helper_neon_qshlu_s16(tmp, cpu_env,
+                                                          tmp, tmp2);
                                 break;
                             case 2:
-                                gen_helper_neon_qshlu_s32(tmp, tmp, tmp2);
+                                gen_helper_neon_qshlu_s32(tmp, cpu_env,
+                                                          tmp, tmp2);
                                 break;
                             default:
                                 abort();
                             }
                             break;
                         case 7: /* VQSHL */
-                            GEN_NEON_INTEGER_OP(qshl);
+                            GEN_NEON_INTEGER_OP_ENV(qshl);
                             break;
                         }
                         tcg_temp_free_i32(tmp2);
@@ -5616,15 +5636,15 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                         tmp2 = neon_load_reg(rn, pass);
                         if (op == 12) {
                             if (size == 1) {
-                                gen_helper_neon_qdmulh_s16(tmp, tmp, tmp2);
+                                gen_helper_neon_qdmulh_s16(tmp, cpu_env, tmp, tmp2);
                             } else {
-                                gen_helper_neon_qdmulh_s32(tmp, tmp, tmp2);
+                                gen_helper_neon_qdmulh_s32(tmp, cpu_env, tmp, tmp2);
                             }
                         } else if (op == 13) {
                             if (size == 1) {
-                                gen_helper_neon_qrdmulh_s16(tmp, tmp, tmp2);
+                                gen_helper_neon_qrdmulh_s16(tmp, cpu_env, tmp, tmp2);
                             } else {
-                                gen_helper_neon_qrdmulh_s32(tmp, tmp, tmp2);
+                                gen_helper_neon_qrdmulh_s32(tmp, cpu_env, tmp, tmp2);
                             }
                         } else if (op & 1) {
                             TCGv_ptr fpstatus = get_fpstatus_ptr(1);
@@ -5996,17 +6016,29 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                             break;
                         case NEON_2RM_VQABS:
                             switch (size) {
-                            case 0: gen_helper_neon_qabs_s8(tmp, tmp); break;
-                            case 1: gen_helper_neon_qabs_s16(tmp, tmp); break;
-                            case 2: gen_helper_neon_qabs_s32(tmp, tmp); break;
+                            case 0:
+                                gen_helper_neon_qabs_s8(tmp, cpu_env, tmp);
+                                break;
+                            case 1:
+                                gen_helper_neon_qabs_s16(tmp, cpu_env, tmp);
+                                break;
+                            case 2:
+                                gen_helper_neon_qabs_s32(tmp, cpu_env, tmp);
+                                break;
                             default: abort();
                             }
                             break;
                         case NEON_2RM_VQNEG:
                             switch (size) {
-                            case 0: gen_helper_neon_qneg_s8(tmp, tmp); break;
-                            case 1: gen_helper_neon_qneg_s16(tmp, tmp); break;
-                            case 2: gen_helper_neon_qneg_s32(tmp, tmp); break;
+                            case 0:
+                                gen_helper_neon_qneg_s8(tmp, cpu_env, tmp);
+                                break;
+                            case 1:
+                                gen_helper_neon_qneg_s16(tmp, cpu_env, tmp);
+                                break;
+                            case 2:
+                                gen_helper_neon_qneg_s32(tmp, cpu_env, tmp);
+                                break;
                             default: abort();
                             }
                             break;