Merge branch 'target-arm.for-upstream' of git://git.linaro.org/people/pmaydell/qemu-arm

* 'target-arm.for-upstream' of git://git.linaro.org/people/pmaydell/qemu-arm:
  target-arm: Drop unused DECODE_CPREG_CRN macro
  target-arm: use deposit instead of hardcoded version
  target-arm: mark a few integer helpers const and pure
  target-arm: convert sar, shl and shr helpers to TCG
  target-arm: convert add_cc and sub_cc helpers to TCG
  target-arm: use globals for CC flags
  target-arm: Reinstate display of VFP registers in cpu_dump_state
  cpu_dump_state: move DUMP_FPU and DUMP_CCOP flags from x86-only to generic

14 files changed, 183 insertions, 238 deletions

diff --git a/cpu-all.h b/cpu-all.h
index 74d3681c29..2b99682677 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -356,6 +356,9 @@ CPUArchState *cpu_copy(CPUArchState *env);
 CPUArchState *qemu_get_cpu(int cpu);
 
 #define CPU_DUMP_CODE 0x00010000
+#define CPU_DUMP_FPU 0x00020000 /* dump FPU register state, not just integer */
+/* dump info about TCG QEMU's condition code optimization state */
+#define CPU_DUMP_CCOP 0x00040000
 
 void cpu_dump_state(CPUArchState *env, FILE *f, fprintf_function cpu_fprintf,
                     int flags);
diff --git a/cpu-exec.c b/cpu-exec.c
index 134b3c4fcf..252da86882 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -552,7 +552,7 @@ int cpu_exec(CPUArchState *env)
 #if defined(TARGET_I386)
                     env->eflags = env->eflags | cpu_cc_compute_all(env, CC_OP)
                         | (DF & DF_MASK);
-                    log_cpu_state(env, X86_DUMP_CCOP);
+                    log_cpu_state(env, CPU_DUMP_CCOP);
                     env->eflags &= ~(DF_MASK | CC_O | CC_S | CC_Z | CC_A | CC_P | CC_C);
 #elif defined(TARGET_M68K)
                     cpu_m68k_flush_flags(env, env->cc_op);
diff --git a/cpus.c b/cpus.c
index 1d5d4904cc..750a76fbc8 100644
--- a/cpus.c
+++ b/cpus.c
@@ -395,11 +395,7 @@ void hw_error(const char *fmt, ...)
     fprintf(stderr, "\n");
     for(env = first_cpu; env != NULL; env = env->next_cpu) {
         fprintf(stderr, "CPU #%d:\n", env->cpu_index);
-#ifdef TARGET_I386
-        cpu_dump_state(env, stderr, fprintf, X86_DUMP_FPU);
-#else
-        cpu_dump_state(env, stderr, fprintf, 0);
-#endif
+        cpu_dump_state(env, stderr, fprintf, CPU_DUMP_FPU);
     }
     va_end(ap);
     abort();
diff --git a/exec.c b/exec.c
index 1114a0932b..7899042ce9 100644
--- a/exec.c
+++ b/exec.c
@@ -1742,20 +1742,12 @@ void cpu_abort(CPUArchState *env, const char *fmt, ...)
     fprintf(stderr, "qemu: fatal: ");
     vfprintf(stderr, fmt, ap);
     fprintf(stderr, "\n");
-#ifdef TARGET_I386
-    cpu_dump_state(env, stderr, fprintf, X86_DUMP_FPU | X86_DUMP_CCOP);
-#else
-    cpu_dump_state(env, stderr, fprintf, 0);
-#endif
+    cpu_dump_state(env, stderr, fprintf, CPU_DUMP_FPU | CPU_DUMP_CCOP);
     if (qemu_log_enabled()) {
         qemu_log("qemu: fatal: ");
         qemu_log_vprintf(fmt, ap2);
         qemu_log("\n");
-#ifdef TARGET_I386
-        log_cpu_state(env, X86_DUMP_FPU | X86_DUMP_CCOP);
-#else
-        log_cpu_state(env, 0);
-#endif
+        log_cpu_state(env, CPU_DUMP_FPU | CPU_DUMP_CCOP);
         qemu_log_flush();
         qemu_log_close();
     }
diff --git a/monitor.c b/monitor.c
index a0e3ffb924..131b325f1b 100644
--- a/monitor.c
+++ b/monitor.c
@@ -898,13 +898,7 @@ static void do_info_registers(Monitor *mon)
 {
     CPUArchState *env;
     env = mon_get_cpu();
-#ifdef TARGET_I386
-    cpu_dump_state(env, (FILE *)mon, monitor_fprintf,
-                   X86_DUMP_FPU);
-#else
-    cpu_dump_state(env, (FILE *)mon, monitor_fprintf,
-                   0);
-#endif
+    cpu_dump_state(env, (FILE *)mon, monitor_fprintf, CPU_DUMP_FPU);
 }
 
 static void do_info_jit(Monitor *mon)
diff --git a/target-arm/cpu.h b/target-arm/cpu.h
index 7fac94f817..ff4de10f12 100644
--- a/target-arm/cpu.h
+++ b/target-arm/cpu.h
@@ -423,8 +423,6 @@ void armv7m_nvic_complete_irq(void *opaque, int irq);
     (((cp) << 16) | ((is64) << 15) | ((crn) << 11) |    \
      ((crm) << 7) | ((opc1) << 3) | (opc2))
 
-#define DECODE_CPREG_CRN(enc) (((enc) >> 7) & 0xf)
-
 /* ARMCPRegInfo type field bits. If the SPECIAL bit is set this is a
  * special-behaviour cp reg and bits [15..8] indicate what behaviour
  * it has. Otherwise it is a simple cp reg, where CONST indicates that
diff --git a/target-arm/helper.h b/target-arm/helper.h
index afdb2b5b1a..8b9adf1311 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -1,8 +1,8 @@
 #include "def-helper.h"
 
-DEF_HELPER_1(clz, i32, i32)
-DEF_HELPER_1(sxtb16, i32, i32)
-DEF_HELPER_1(uxtb16, i32, i32)
+DEF_HELPER_FLAGS_1(clz, TCG_CALL_CONST | TCG_CALL_PURE, i32, i32)
+DEF_HELPER_FLAGS_1(sxtb16, TCG_CALL_CONST | TCG_CALL_PURE, i32, i32)
+DEF_HELPER_FLAGS_1(uxtb16, TCG_CALL_CONST | TCG_CALL_PURE, i32, i32)
 
 DEF_HELPER_3(add_setq, i32, env, i32, i32)
 DEF_HELPER_3(add_saturate, i32, env, i32, i32)
@@ -10,10 +10,10 @@ DEF_HELPER_3(sub_saturate, i32, env, i32, i32)
 DEF_HELPER_3(add_usaturate, i32, env, i32, i32)
 DEF_HELPER_3(sub_usaturate, i32, env, i32, i32)
 DEF_HELPER_2(double_saturate, i32, env, s32)
-DEF_HELPER_2(sdiv, s32, s32, s32)
-DEF_HELPER_2(udiv, i32, i32, i32)
-DEF_HELPER_1(rbit, i32, i32)
-DEF_HELPER_1(abs, i32, i32)
+DEF_HELPER_FLAGS_2(sdiv, TCG_CALL_CONST | TCG_CALL_PURE, s32, s32, s32)
+DEF_HELPER_FLAGS_2(udiv, TCG_CALL_CONST | TCG_CALL_PURE, i32, i32, i32)
+DEF_HELPER_FLAGS_1(rbit, TCG_CALL_CONST | TCG_CALL_PURE, i32, i32)
+DEF_HELPER_FLAGS_1(abs, TCG_CALL_CONST | TCG_CALL_PURE, i32, i32)
 
 #define PAS_OP(pfx)  \
     DEF_HELPER_3(pfx ## add8, i32, i32, i32, ptr) \
@@ -45,11 +45,12 @@ DEF_HELPER_3(usat, i32, env, i32, i32)
 DEF_HELPER_3(ssat16, i32, env, i32, i32)
 DEF_HELPER_3(usat16, i32, env, i32, i32)
 
-DEF_HELPER_2(usad8, i32, i32, i32)
+DEF_HELPER_FLAGS_2(usad8, TCG_CALL_CONST | TCG_CALL_PURE, i32, i32, i32)
 
 DEF_HELPER_1(logicq_cc, i32, i64)
 
-DEF_HELPER_3(sel_flags, i32, i32, i32, i32)
+DEF_HELPER_FLAGS_3(sel_flags, TCG_CALL_CONST | TCG_CALL_PURE,
+                   i32, i32, i32, i32)
 DEF_HELPER_2(exception, void, env, i32)
 DEF_HELPER_1(wfi, void, env)
 
@@ -142,14 +143,9 @@ DEF_HELPER_2(recpe_u32, i32, i32, env)
 DEF_HELPER_2(rsqrte_u32, i32, i32, env)
 DEF_HELPER_5(neon_tbl, i32, env, i32, i32, i32, i32)
 
-DEF_HELPER_3(add_cc, i32, env, i32, i32)
 DEF_HELPER_3(adc_cc, i32, env, i32, i32)
-DEF_HELPER_3(sub_cc, i32, env, i32, i32)
 DEF_HELPER_3(sbc_cc, i32, env, i32, i32)
 
-DEF_HELPER_3(shl, i32, env, i32, i32)
-DEF_HELPER_3(shr, i32, env, i32, i32)
-DEF_HELPER_3(sar, i32, env, i32, i32)
 DEF_HELPER_3(shl_cc, i32, env, i32, i32)
 DEF_HELPER_3(shr_cc, i32, env, i32, i32)
 DEF_HELPER_3(sar_cc, i32, env, i32, i32)
diff --git a/target-arm/op_helper.c b/target-arm/op_helper.c
index f13fc3ae57..aef592ab8d 100644
--- a/target-arm/op_helper.c
+++ b/target-arm/op_helper.c
@@ -323,16 +323,6 @@ uint64_t HELPER(get_cp_reg64)(CPUARMState *env, void *rip)
    The only way to do that in TCG is a conditional branch, which clobbers
    all our temporaries.  For now implement these as helper functions.  */
 
-uint32_t HELPER (add_cc)(CPUARMState *env, uint32_t a, uint32_t b)
-{
-    uint32_t result;
-    result = a + b;
-    env->NF = env->ZF = result;
-    env->CF = result < a;
-    env->VF = (a ^ b ^ -1) & (a ^ result);
-    return result;
-}
-
 uint32_t HELPER(adc_cc)(CPUARMState *env, uint32_t a, uint32_t b)
 {
     uint32_t result;
@@ -348,16 +338,6 @@ uint32_t HELPER(adc_cc)(CPUARMState *env, uint32_t a, uint32_t b)
     return result;
 }
 
-uint32_t HELPER(sub_cc)(CPUARMState *env, uint32_t a, uint32_t b)
-{
-    uint32_t result;
-    result = a - b;
-    env->NF = env->ZF = result;
-    env->CF = a >= b;
-    env->VF = (a ^ b) & (a ^ result);
-    return result;
-}
-
 uint32_t HELPER(sbc_cc)(CPUARMState *env, uint32_t a, uint32_t b)
 {
     uint32_t result;
@@ -375,30 +355,6 @@ uint32_t HELPER(sbc_cc)(CPUARMState *env, uint32_t a, uint32_t b)
 
 /* Similarly for variable shift instructions.  */
 
-uint32_t HELPER(shl)(CPUARMState *env, uint32_t x, uint32_t i)
-{
-    int shift = i & 0xff;
-    if (shift >= 32)
-        return 0;
-    return x << shift;
-}
-
-uint32_t HELPER(shr)(CPUARMState *env, uint32_t x, uint32_t i)
-{
-    int shift = i & 0xff;
-    if (shift >= 32)
-        return 0;
-    return (uint32_t)x >> shift;
-}
-
-uint32_t HELPER(sar)(CPUARMState *env, uint32_t x, uint32_t i)
-{
-    int shift = i & 0xff;
-    if (shift >= 32)
-        shift = 31;
-    return (int32_t)x >> shift;
-}
-
 uint32_t HELPER(shl_cc)(CPUARMState *env, uint32_t x, uint32_t i)
 {
     int shift = i & 0xff;
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 5fded491ec..c6840b7832 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -85,6 +85,7 @@ static TCGv_ptr cpu_env;
 /* We reuse the same 64-bit temporaries for efficiency.  */
 static TCGv_i64 cpu_V0, cpu_V1, cpu_M0;
 static TCGv_i32 cpu_R[16];
+static TCGv_i32 cpu_CF, cpu_NF, cpu_VF, cpu_ZF;
 static TCGv_i32 cpu_exclusive_addr;
 static TCGv_i32 cpu_exclusive_val;
 static TCGv_i32 cpu_exclusive_high;
@@ -115,6 +116,11 @@ void arm_translate_init(void)
                                           offsetof(CPUARMState, regs[i]),
                                           regnames[i]);
     }
+    cpu_CF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, CF), "CF");
+    cpu_NF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, NF), "NF");
+    cpu_VF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, VF), "VF");
+    cpu_ZF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, ZF), "ZF");
+
     cpu_exclusive_addr = tcg_global_mem_new_i32(TCG_AREG0,
         offsetof(CPUARMState, exclusive_addr), "exclusive_addr");
     cpu_exclusive_val = tcg_global_mem_new_i32(TCG_AREG0,
@@ -271,15 +277,6 @@ static void gen_sbfx(TCGv var, int shift, int width)
     }
 }
 
-/* Bitfield insertion.  Insert val into base.  Clobbers base and val.  */
-static void gen_bfi(TCGv dest, TCGv base, TCGv val, int shift, uint32_t mask)
-{
-    tcg_gen_andi_i32(val, val, mask);
-    tcg_gen_shli_i32(val, val, shift);
-    tcg_gen_andi_i32(base, base, ~(mask << shift));
-    tcg_gen_or_i32(dest, base, val);
-}
-
 /* Return (b << 32) + a. Mark inputs as dead */
 static TCGv_i64 gen_addq_msw(TCGv_i64 a, TCGv b)
 {
@@ -369,53 +366,100 @@ static void gen_add16(TCGv t0, TCGv t1)
     tcg_temp_free_i32(t1);
 }
 
-#define gen_set_CF(var) tcg_gen_st_i32(var, cpu_env, offsetof(CPUARMState, CF))
-
 /* Set CF to the top bit of var.  */
 static void gen_set_CF_bit31(TCGv var)
 {
-    TCGv tmp = tcg_temp_new_i32();
-    tcg_gen_shri_i32(tmp, var, 31);
-    gen_set_CF(tmp);
-    tcg_temp_free_i32(tmp);
+    tcg_gen_shri_i32(cpu_CF, var, 31);
 }
 
 /* Set N and Z flags from var.  */
 static inline void gen_logic_CC(TCGv var)
 {
-    tcg_gen_st_i32(var, cpu_env, offsetof(CPUARMState, NF));
-    tcg_gen_st_i32(var, cpu_env, offsetof(CPUARMState, ZF));
+    tcg_gen_mov_i32(cpu_NF, var);
+    tcg_gen_mov_i32(cpu_ZF, var);
 }
 
 /* T0 += T1 + CF.  */
 static void gen_adc(TCGv t0, TCGv t1)
 {
-    TCGv tmp;
     tcg_gen_add_i32(t0, t0, t1);
-    tmp = load_cpu_field(CF);
-    tcg_gen_add_i32(t0, t0, tmp);
-    tcg_temp_free_i32(tmp);
+    tcg_gen_add_i32(t0, t0, cpu_CF);
 }
 
 /* dest = T0 + T1 + CF. */
 static void gen_add_carry(TCGv dest, TCGv t0, TCGv t1)
 {
-    TCGv tmp;
     tcg_gen_add_i32(dest, t0, t1);
-    tmp = load_cpu_field(CF);
-    tcg_gen_add_i32(dest, dest, tmp);
-    tcg_temp_free_i32(tmp);
+    tcg_gen_add_i32(dest, dest, cpu_CF);
 }
 
 /* dest = T0 - T1 + CF - 1.  */
 static void gen_sub_carry(TCGv dest, TCGv t0, TCGv t1)
 {
-    TCGv tmp;
     tcg_gen_sub_i32(dest, t0, t1);
-    tmp = load_cpu_field(CF);
-    tcg_gen_add_i32(dest, dest, tmp);
+    tcg_gen_add_i32(dest, dest, cpu_CF);
     tcg_gen_subi_i32(dest, dest, 1);
+}
+
+/* dest = T0 + T1. Compute C, N, V and Z flags */
+static void gen_add_CC(TCGv dest, TCGv t0, TCGv t1)
+{
+    TCGv tmp;
+    tcg_gen_add_i32(cpu_NF, t0, t1);
+    tcg_gen_mov_i32(cpu_ZF, cpu_NF);
+    tcg_gen_setcond_i32(TCG_COND_LTU, cpu_CF, cpu_NF, t0);
+    tcg_gen_xor_i32(cpu_VF, cpu_NF, t0);
+    tmp = tcg_temp_new_i32();
+    tcg_gen_xor_i32(tmp, t0, t1);
+    tcg_gen_andc_i32(cpu_VF, cpu_VF, tmp);
     tcg_temp_free_i32(tmp);
+    tcg_gen_mov_i32(dest, cpu_NF);
+}
+
+/* dest = T0 - T1. Compute C, N, V and Z flags */
+static void gen_sub_CC(TCGv dest, TCGv t0, TCGv t1)
+{
+    TCGv tmp;
+    tcg_gen_sub_i32(cpu_NF, t0, t1);
+    tcg_gen_mov_i32(cpu_ZF, cpu_NF);
+    tcg_gen_setcond_i32(TCG_COND_GEU, cpu_CF, t0, t1);
+    tcg_gen_xor_i32(cpu_VF, cpu_NF, t0);
+    tmp = tcg_temp_new_i32();
+    tcg_gen_xor_i32(tmp, t0, t1);
+    tcg_gen_and_i32(cpu_VF, cpu_VF, tmp);
+    tcg_temp_free_i32(tmp);
+    tcg_gen_mov_i32(dest, cpu_NF);
+}
+
+#define GEN_SHIFT(name)                                               \
+static void gen_##name(TCGv dest, TCGv t0, TCGv t1)                   \
+{                                                                     \
+    TCGv tmp1, tmp2, tmp3;                                            \
+    tmp1 = tcg_temp_new_i32();                                        \
+    tcg_gen_andi_i32(tmp1, t1, 0xff);                                 \
+    tmp2 = tcg_const_i32(0);                                          \
+    tmp3 = tcg_const_i32(0x1f);                                       \
+    tcg_gen_movcond_i32(TCG_COND_GTU, tmp2, tmp1, tmp3, tmp2, t0);    \
+    tcg_temp_free_i32(tmp3);                                          \
+    tcg_gen_andi_i32(tmp1, tmp1, 0x1f);                               \
+    tcg_gen_##name##_i32(dest, tmp2, tmp1);                           \
+    tcg_temp_free_i32(tmp2);                                          \
+    tcg_temp_free_i32(tmp1);                                          \
+}
+GEN_SHIFT(shl)
+GEN_SHIFT(shr)
+#undef GEN_SHIFT
+
+static void gen_sar(TCGv dest, TCGv t0, TCGv t1)
+{
+    TCGv tmp1, tmp2;
+    tmp1 = tcg_temp_new_i32();
+    tcg_gen_andi_i32(tmp1, t1, 0xff);
+    tmp2 = tcg_const_i32(0x1f);
+    tcg_gen_movcond_i32(TCG_COND_GTU, tmp1, tmp1, tmp2, tmp2, tmp1);
+    tcg_temp_free_i32(tmp2);
+    tcg_gen_sar_i32(dest, t0, tmp1);
+    tcg_temp_free_i32(tmp1);
 }
 
 /* FIXME:  Implement this natively.  */
@@ -423,16 +467,14 @@ static void gen_sub_carry(TCGv dest, TCGv t0, TCGv t1)
 
 static void shifter_out_im(TCGv var, int shift)
 {
-    TCGv tmp = tcg_temp_new_i32();
     if (shift == 0) {
-        tcg_gen_andi_i32(tmp, var, 1);
+        tcg_gen_andi_i32(cpu_CF, var, 1);
     } else {
-        tcg_gen_shri_i32(tmp, var, shift);
-        if (shift != 31)
-            tcg_gen_andi_i32(tmp, tmp, 1);
+        tcg_gen_shri_i32(cpu_CF, var, shift);
+        if (shift != 31) {
+            tcg_gen_andi_i32(cpu_CF, cpu_CF, 1);
+        }
     }
-    gen_set_CF(tmp);
-    tcg_temp_free_i32(tmp);
 }
 
 /* Shift by immediate.  Includes special handling for shift == 0.  */
@@ -449,8 +491,7 @@ static inline void gen_arm_shift_im(TCGv var, int shiftop, int shift, int flags)
     case 1: /* LSR */
         if (shift == 0) {
             if (flags) {
-                tcg_gen_shri_i32(var, var, 31);
-                gen_set_CF(var);
+                tcg_gen_shri_i32(cpu_CF, var, 31);
             }
             tcg_gen_movi_i32(var, 0);
         } else {
@@ -474,11 +515,11 @@ static inline void gen_arm_shift_im(TCGv var, int shiftop, int shift, int flags)
                 shifter_out_im(var, shift - 1);
             tcg_gen_rotri_i32(var, var, shift); break;
         } else {
-            TCGv tmp = load_cpu_field(CF);
+            TCGv tmp = tcg_temp_new_i32();
             if (flags)
                 shifter_out_im(var, 0);
             tcg_gen_shri_i32(var, var, 1);
-            tcg_gen_shli_i32(tmp, tmp, 31);
+            tcg_gen_shli_i32(tmp, cpu_CF, 31);
             tcg_gen_or_i32(var, var, tmp);
             tcg_temp_free_i32(tmp);
         }
@@ -497,9 +538,15 @@ static inline void gen_arm_shift_reg(TCGv var, int shiftop,
         }
     } else {
         switch (shiftop) {
-        case 0: gen_helper_shl(var, cpu_env, var, shift); break;
-        case 1: gen_helper_shr(var, cpu_env, var, shift); break;
-        case 2: gen_helper_sar(var, cpu_env, var, shift); break;
+        case 0:
+            gen_shl(var, var, shift);
+            break;
+        case 1:
+            gen_shr(var, var, shift);
+            break;
+        case 2:
+            gen_sar(var, var, shift);
+            break;
         case 3: tcg_gen_andi_i32(shift, shift, 0x1f);
                 tcg_gen_rotr_i32(var, var, shift); break;
         }
@@ -603,99 +650,75 @@ static void gen_thumb2_parallel_addsub(int op1, int op2, TCGv a, TCGv b)
 static void gen_test_cc(int cc, int label)
 {
     TCGv tmp;
-    TCGv tmp2;
     int inv;
 
     switch (cc) {
     case 0: /* eq: Z */
-        tmp = load_cpu_field(ZF);
-        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, label);
+        tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_ZF, 0, label);
         break;
     case 1: /* ne: !Z */
-        tmp = load_cpu_field(ZF);
-        tcg_gen_brcondi_i32(TCG_COND_NE, tmp, 0, label);
+        tcg_gen_brcondi_i32(TCG_COND_NE, cpu_ZF, 0, label);
         break;
     case 2: /* cs: C */
-        tmp = load_cpu_field(CF);
-        tcg_gen_brcondi_i32(TCG_COND_NE, tmp, 0, label);
+        tcg_gen_brcondi_i32(TCG_COND_NE, cpu_CF, 0, label);
         break;
     case 3: /* cc: !C */
-        tmp = load_cpu_field(CF);
-        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, label);
+        tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_CF, 0, label);
         break;
     case 4: /* mi: N */
-        tmp = load_cpu_field(NF);
-        tcg_gen_brcondi_i32(TCG_COND_LT, tmp, 0, label);
+        tcg_gen_brcondi_i32(TCG_COND_LT, cpu_NF, 0, label);
         break;
     case 5: /* pl: !N */
-        tmp = load_cpu_field(NF);
-        tcg_gen_brcondi_i32(TCG_COND_GE, tmp, 0, label);
+        tcg_gen_brcondi_i32(TCG_COND_GE, cpu_NF, 0, label);
         break;
     case 6: /* vs: V */
-        tmp = load_cpu_field(VF);
-        tcg_gen_brcondi_i32(TCG_COND_LT, tmp, 0, label);
+        tcg_gen_brcondi_i32(TCG_COND_LT, cpu_VF, 0, label);
         break;
     case 7: /* vc: !V */
-        tmp = load_cpu_field(VF);
-        tcg_gen_brcondi_i32(TCG_COND_GE, tmp, 0, label);
+        tcg_gen_brcondi_i32(TCG_COND_GE, cpu_VF, 0, label);
         break;
     case 8: /* hi: C && !Z */
         inv = gen_new_label();
-        tmp = load_cpu_field(CF);
-        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, inv);
-        tcg_temp_free_i32(tmp);
-        tmp = load_cpu_field(ZF);
-        tcg_gen_brcondi_i32(TCG_COND_NE, tmp, 0, label);
+        tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_CF, 0, inv);
+        tcg_gen_brcondi_i32(TCG_COND_NE, cpu_ZF, 0, label);
         gen_set_label(inv);
         break;
     case 9: /* ls: !C || Z */
-        tmp = load_cpu_field(CF);
-        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, label);
-        tcg_temp_free_i32(tmp);
-        tmp = load_cpu_field(ZF);
-        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, label);
+        tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_CF, 0, label);
+        tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_ZF, 0, label);
         break;
     case 10: /* ge: N == V -> N ^ V == 0 */
-        tmp = load_cpu_field(VF);
-        tmp2 = load_cpu_field(NF);
-        tcg_gen_xor_i32(tmp, tmp, tmp2);
-        tcg_temp_free_i32(tmp2);
+        tmp = tcg_temp_new_i32();
+        tcg_gen_xor_i32(tmp, cpu_VF, cpu_NF);
         tcg_gen_brcondi_i32(TCG_COND_GE, tmp, 0, label);
+        tcg_temp_free_i32(tmp);
         break;
     case 11: /* lt: N != V -> N ^ V != 0 */
-        tmp = load_cpu_field(VF);
-        tmp2 = load_cpu_field(NF);
-        tcg_gen_xor_i32(tmp, tmp, tmp2);
-        tcg_temp_free_i32(tmp2);
+        tmp = tcg_temp_new_i32();
+        tcg_gen_xor_i32(tmp, cpu_VF, cpu_NF);
         tcg_gen_brcondi_i32(TCG_COND_LT, tmp, 0, label);
+        tcg_temp_free_i32(tmp);
         break;
     case 12: /* gt: !Z && N == V */
         inv = gen_new_label();
-        tmp = load_cpu_field(ZF);
-        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, inv);
-        tcg_temp_free_i32(tmp);
-        tmp = load_cpu_field(VF);
-        tmp2 = load_cpu_field(NF);
-        tcg_gen_xor_i32(tmp, tmp, tmp2);
-        tcg_temp_free_i32(tmp2);
+        tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_ZF, 0, inv);
+        tmp = tcg_temp_new_i32();
+        tcg_gen_xor_i32(tmp, cpu_VF, cpu_NF);
         tcg_gen_brcondi_i32(TCG_COND_GE, tmp, 0, label);
+        tcg_temp_free_i32(tmp);
         gen_set_label(inv);
         break;
     case 13: /* le: Z || N != V */
-        tmp = load_cpu_field(ZF);
-        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, label);
-        tcg_temp_free_i32(tmp);
-        tmp = load_cpu_field(VF);
-        tmp2 = load_cpu_field(NF);
-        tcg_gen_xor_i32(tmp, tmp, tmp2);
-        tcg_temp_free_i32(tmp2);
+        tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_ZF, 0, label);
+        tmp = tcg_temp_new_i32();
+        tcg_gen_xor_i32(tmp, cpu_VF, cpu_NF);
         tcg_gen_brcondi_i32(TCG_COND_LT, tmp, 0, label);
+        tcg_temp_free_i32(tmp);
         break;
     default:
         fprintf(stderr, "Bad condition code 0x%x\n", cc);
         abort();
     }
-    tcg_temp_free_i32(tmp);
 }
 
 static const uint8_t table_logic_cc[16] = {
@@ -2628,12 +2651,12 @@ static int disas_vfp_insn(CPUARMState * env, DisasContext *s, uint32_t insn)
                         switch (size) {
                         case 0:
                             tmp2 = neon_load_reg(rn, pass);
-                            gen_bfi(tmp, tmp2, tmp, offset, 0xff);
+                            tcg_gen_deposit_i32(tmp, tmp2, tmp, offset, 8);
                             tcg_temp_free_i32(tmp2);
                             break;
                         case 1:
                             tmp2 = neon_load_reg(rn, pass);
-                            gen_bfi(tmp, tmp2, tmp, offset, 0xffff);
+                            tcg_gen_deposit_i32(tmp, tmp2, tmp, offset, 16);
                             tcg_temp_free_i32(tmp2);
                             break;
                         case 2:
@@ -3989,7 +4012,8 @@ static int disas_neon_ls_insn(CPUARMState * env, DisasContext *s, uint32_t insn)
                     }
                     if (size != 2) {
                         tmp2 = neon_load_reg(rd, pass);
-                        gen_bfi(tmp, tmp2, tmp, shift, size ? 0xffff : 0xff);
+                        tcg_gen_deposit_i32(tmp, tmp2, tmp,
+                                            shift, size ? 16 : 8);
                         tcg_temp_free_i32(tmp2);
                     }
                     neon_store_reg(rd, pass, tmp);
@@ -7005,11 +7029,11 @@ static void disas_arm_insn(CPUARMState * env, DisasContext *s)
                 if (IS_USER(s)) {
                     goto illegal_op;
                 }
-                gen_helper_sub_cc(tmp, cpu_env, tmp, tmp2);
+                gen_sub_CC(tmp, tmp, tmp2);
                 gen_exception_return(s, tmp);
             } else {
                 if (set_cc) {
-                    gen_helper_sub_cc(tmp, cpu_env, tmp, tmp2);
+                    gen_sub_CC(tmp, tmp, tmp2);
                 } else {
                     tcg_gen_sub_i32(tmp, tmp, tmp2);
                 }
@@ -7018,7 +7042,7 @@ static void disas_arm_insn(CPUARMState * env, DisasContext *s)
             break;
         case 0x03:
             if (set_cc) {
-                gen_helper_sub_cc(tmp, cpu_env, tmp2, tmp);
+                gen_sub_CC(tmp, tmp2, tmp);
             } else {
                 tcg_gen_sub_i32(tmp, tmp2, tmp);
             }
@@ -7026,7 +7050,7 @@ static void disas_arm_insn(CPUARMState * env, DisasContext *s)
             break;
         case 0x04:
             if (set_cc) {
-                gen_helper_add_cc(tmp, cpu_env, tmp, tmp2);
+                gen_add_CC(tmp, tmp, tmp2);
             } else {
                 tcg_gen_add_i32(tmp, tmp, tmp2);
             }
@@ -7072,13 +7096,13 @@ static void disas_arm_insn(CPUARMState * env, DisasContext *s)
             break;
         case 0x0a:
             if (set_cc) {
-                gen_helper_sub_cc(tmp, cpu_env, tmp, tmp2);
+                gen_sub_CC(tmp, tmp, tmp2);
             }
             tcg_temp_free_i32(tmp);
             break;
         case 0x0b:
             if (set_cc) {
-                gen_helper_add_cc(tmp, cpu_env, tmp, tmp2);
+                gen_add_CC(tmp, tmp, tmp2);
             }
             tcg_temp_free_i32(tmp);
             break;
@@ -7593,7 +7617,7 @@ static void disas_arm_insn(CPUARMState * env, DisasContext *s)
                         }
                         if (i != 32) {
                             tmp2 = load_reg(s, rd);
-                            gen_bfi(tmp, tmp2, tmp, shift, (1u << i) - 1);
+                            tcg_gen_deposit_i32(tmp, tmp2, tmp, shift, i);
                             tcg_temp_free_i32(tmp2);
                         }
                         store_reg(s, rd, tmp);
@@ -7865,7 +7889,7 @@ gen_thumb2_data_op(DisasContext *s, int op, int conds, uint32_t shifter_out, TCG
         break;
     case 8: /* add */
         if (conds)
-            gen_helper_add_cc(t0, cpu_env, t0, t1);
+            gen_add_CC(t0, t0, t1);
         else
             tcg_gen_add_i32(t0, t0, t1);
         break;
@@ -7883,13 +7907,13 @@ gen_thumb2_data_op(DisasContext *s, int op, int conds, uint32_t shifter_out, TCG
         break;
     case 13: /* sub */
         if (conds)
-            gen_helper_sub_cc(t0, cpu_env, t0, t1);
+            gen_sub_CC(t0, t0, t1);
         else
             tcg_gen_sub_i32(t0, t0, t1);
         break;
     case 14: /* rsb */
         if (conds)
-            gen_helper_sub_cc(t0, cpu_env, t1, t0);
+            gen_sub_CC(t0, t1, t0);
         else
             tcg_gen_sub_i32(t0, t1, t0);
         break;
@@ -8704,7 +8728,7 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
                         imm = imm + 1 - shift;
                         if (imm != 32) {
                             tmp2 = load_reg(s, rd);
-                            gen_bfi(tmp, tmp2, tmp, shift, (1u << imm) - 1);
+                            tcg_gen_deposit_i32(tmp, tmp2, tmp, shift, imm);
                             tcg_temp_free_i32(tmp2);
                         }
                         break;
@@ -9017,12 +9041,12 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
                 if (s->condexec_mask)
                     tcg_gen_sub_i32(tmp, tmp, tmp2);
                 else
-                    gen_helper_sub_cc(tmp, cpu_env, tmp, tmp2);
+                    gen_sub_CC(tmp, tmp, tmp2);
             } else {
                 if (s->condexec_mask)
                     tcg_gen_add_i32(tmp, tmp, tmp2);
                 else
-                    gen_helper_add_cc(tmp, cpu_env, tmp, tmp2);
+                    gen_add_CC(tmp, tmp, tmp2);
             }
             tcg_temp_free_i32(tmp2);
             store_reg(s, rd, tmp);
@@ -9053,7 +9077,7 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
             tcg_gen_movi_i32(tmp2, insn & 0xff);
             switch (op) {
             case 1: /* cmp */
-                gen_helper_sub_cc(tmp, cpu_env, tmp, tmp2);
+                gen_sub_CC(tmp, tmp, tmp2);
                 tcg_temp_free_i32(tmp);
                 tcg_temp_free_i32(tmp2);
                 break;
@@ -9061,7 +9085,7 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
                 if (s->condexec_mask)
                     tcg_gen_add_i32(tmp, tmp, tmp2);
                 else
-                    gen_helper_add_cc(tmp, cpu_env, tmp, tmp2);
+                    gen_add_CC(tmp, tmp, tmp2);
                 tcg_temp_free_i32(tmp2);
                 store_reg(s, rd, tmp);
                 break;
@@ -9069,7 +9093,7 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
                 if (s->condexec_mask)
                     tcg_gen_sub_i32(tmp, tmp, tmp2);
                 else
-                    gen_helper_sub_cc(tmp, cpu_env, tmp, tmp2);
+                    gen_sub_CC(tmp, tmp, tmp2);
                 tcg_temp_free_i32(tmp2);
                 store_reg(s, rd, tmp);
                 break;
@@ -9105,7 +9129,7 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
             case 1: /* cmp */
                 tmp = load_reg(s, rd);
                 tmp2 = load_reg(s, rm);
-                gen_helper_sub_cc(tmp, cpu_env, tmp, tmp2);
+                gen_sub_CC(tmp, tmp, tmp2);
                 tcg_temp_free_i32(tmp2);
                 tcg_temp_free_i32(tmp);
                 break;
@@ -9166,7 +9190,7 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
             break;
         case 0x2: /* lsl */
             if (s->condexec_mask) {
-                gen_helper_shl(tmp2, cpu_env, tmp2, tmp);
+                gen_shl(tmp2, tmp2, tmp);
             } else {
                 gen_helper_shl_cc(tmp2, cpu_env, tmp2, tmp);
                 gen_logic_CC(tmp2);
@@ -9174,7 +9198,7 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
             break;
         case 0x3: /* lsr */
             if (s->condexec_mask) {
-                gen_helper_shr(tmp2, cpu_env, tmp2, tmp);
+                gen_shr(tmp2, tmp2, tmp);
             } else {
                 gen_helper_shr_cc(tmp2, cpu_env, tmp2, tmp);
                 gen_logic_CC(tmp2);
@@ -9182,7 +9206,7 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
             break;
         case 0x4: /* asr */
             if (s->condexec_mask) {
-                gen_helper_sar(tmp2, cpu_env, tmp2, tmp);
+                gen_sar(tmp2, tmp2, tmp);
             } else {
                 gen_helper_sar_cc(tmp2, cpu_env, tmp2, tmp);
                 gen_logic_CC(tmp2);
@@ -9218,14 +9242,14 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
             if (s->condexec_mask)
                 tcg_gen_neg_i32(tmp, tmp2);
             else
-                gen_helper_sub_cc(tmp, cpu_env, tmp, tmp2);
+                gen_sub_CC(tmp, tmp, tmp2);
             break;
         case 0xa: /* cmp */
-            gen_helper_sub_cc(tmp, cpu_env, tmp, tmp2);
+            gen_sub_CC(tmp, tmp, tmp2);
             rd = 16;
             break;
         case 0xb: /* cmn */
-            gen_helper_add_cc(tmp, cpu_env, tmp, tmp2);
+            gen_add_CC(tmp, tmp, tmp2);
             rd = 16;
             break;
         case 0xc: /* orr */
@@ -9970,19 +9994,6 @@ void cpu_dump_state(CPUARMState *env, FILE *f, fprintf_function cpu_fprintf,
                     int flags)
 {
     int i;
-#if 0
-    union {
-        uint32_t i;
-        float s;
-    } s0, s1;
-    CPU_DoubleU d;
-    /* ??? This assumes float64 and double have the same layout.
-       Oh well, it's only debug dumps.  */
-    union {
-        float64 f64;
-        double d;
-    } d0;
-#endif
     uint32_t psr;
 
     for(i=0;i<16;i++) {
@@ -10002,20 +10013,23 @@ void cpu_dump_state(CPUARMState *env, FILE *f, fprintf_function cpu_fprintf,
                 psr & CPSR_T ? 'T' : 'A',
                 cpu_mode_names[psr & 0xf], (psr & 0x10) ? 32 : 26);
 
-#if 0
-    for (i = 0; i < 16; i++) {
-        d.d = env->vfp.regs[i];
-        s0.i = d.l.lower;
-        s1.i = d.l.upper;
-        d0.f64 = d.d;
-        cpu_fprintf(f, "s%02d=%08x(%8g) s%02d=%08x(%8g) d%02d=%08x%08x(%8g)\n",
-                    i * 2, (int)s0.i, s0.s,
-                    i * 2 + 1, (int)s1.i, s1.s,
-                    i, (int)(uint32_t)d.l.upper, (int)(uint32_t)d.l.lower,
-                    d0.d);
+    if (flags & CPU_DUMP_FPU) {
+        int numvfpregs = 0;
+        if (arm_feature(env, ARM_FEATURE_VFP)) {
+            numvfpregs += 16;
+        }
+        if (arm_feature(env, ARM_FEATURE_VFP3)) {
+            numvfpregs += 16;
+        }
+        for (i = 0; i < numvfpregs; i++) {
+            uint64_t v = float64_val(env->vfp.regs[i]);
+            cpu_fprintf(f, "s%02d=%08x s%02d=%08x d%02d=%016" PRIx64 "\n",
+                        i * 2, (uint32_t)v,
+                        i * 2 + 1, (uint32_t)(v >> 32),
+                        i, v);
+        }
+        cpu_fprintf(f, "FPSCR: %08x\n", (int)env->vfp.xregs[ARM_VFP_FPSCR]);
     }
-    cpu_fprintf(f, "FPSCR: %08x\n", (int)env->vfp.xregs[ARM_VFP_FPSCR]);
-#endif
 }
 
 void restore_state_to_opc(CPUARMState *env, TranslationBlock *tb, int pc_pos)
diff --git a/target-i386/cpu.c b/target-i386/cpu.c
index bb1e44eb01..f3708e63b7 100644
--- a/target-i386/cpu.c
+++ b/target-i386/cpu.c
@@ -1759,7 +1759,7 @@ static void x86_cpu_reset(CPUState *s)
 
     if (qemu_loglevel_mask(CPU_LOG_RESET)) {
         qemu_log("CPU Reset (CPU %d)\n", env->cpu_index);
-        log_cpu_state(env, X86_DUMP_FPU | X86_DUMP_CCOP);
+        log_cpu_state(env, CPU_DUMP_FPU | CPU_DUMP_CCOP);
     }
 
     xcc->parent_reset(s);
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index e4a7d5b6e4..871c270116 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -995,10 +995,6 @@ void cpu_x86_update_cr4(CPUX86State *env, uint32_t new_cr4);
 void cpu_smm_update(CPUX86State *env);
 uint64_t cpu_get_tsc(CPUX86State *env);
 
-/* used to debug */
-#define X86_DUMP_FPU  0x0001 /* dump FPU state too */
-#define X86_DUMP_CCOP 0x0002 /* dump qemu flag cache */
-
 #define TARGET_PAGE_BITS 12
 
 #ifdef TARGET_X86_64
diff --git a/target-i386/helper.c b/target-i386/helper.c
index c635667d60..2ee7c6d1b1 100644
--- a/target-i386/helper.c
+++ b/target-i386/helper.c
@@ -284,7 +284,7 @@ void cpu_dump_state(CPUX86State *env, FILE *f, fprintf_function cpu_fprintf,
         cpu_fprintf(f, "\nDR6=" TARGET_FMT_lx " DR7=" TARGET_FMT_lx "\n",
                     env->dr[6], env->dr[7]);
     }
-    if (flags & X86_DUMP_CCOP) {
+    if (flags & CPU_DUMP_CCOP) {
         if ((unsigned)env->cc_op < CC_OP_NB)
             snprintf(cc_op_name, sizeof(cc_op_name), "%s", cc_op_str[env->cc_op]);
         else
@@ -303,7 +303,7 @@ void cpu_dump_state(CPUX86State *env, FILE *f, fprintf_function cpu_fprintf,
         }
     }
     cpu_fprintf(f, "EFER=%016" PRIx64 "\n", env->efer);
-    if (flags & X86_DUMP_FPU) {
+    if (flags & CPU_DUMP_FPU) {
         int fptag;
         fptag = 0;
         for(i = 0; i < 8; i++) {
diff --git a/target-i386/seg_helper.c b/target-i386/seg_helper.c
index 5fff8d59c6..ff9337441b 100644
--- a/target-i386/seg_helper.c
+++ b/target-i386/seg_helper.c
@@ -31,7 +31,7 @@
 #ifdef DEBUG_PCALL
 # define LOG_PCALL(...) qemu_log_mask(CPU_LOG_PCALL, ## __VA_ARGS__)
 # define LOG_PCALL_STATE(env)                                  \
-    log_cpu_state_mask(CPU_LOG_PCALL, (env), X86_DUMP_CCOP)
+    log_cpu_state_mask(CPU_LOG_PCALL, (env), CPU_DUMP_CCOP)
 #else
 # define LOG_PCALL(...) do { } while (0)
 # define LOG_PCALL_STATE(env) do { } while (0)
@@ -1177,7 +1177,7 @@ static void do_interrupt_all(CPUX86State *env, int intno, int is_int,
                 qemu_log(" EAX=" TARGET_FMT_lx, EAX);
             }
             qemu_log("\n");
-            log_cpu_state(env, X86_DUMP_CCOP);
+            log_cpu_state(env, CPU_DUMP_CCOP);
 #if 0
             {
                 int i;
diff --git a/target-i386/smm_helper.c b/target-i386/smm_helper.c
index 8b04eb2e00..eea2fe9782 100644
--- a/target-i386/smm_helper.c
+++ b/target-i386/smm_helper.c
@@ -47,7 +47,7 @@ void do_smm_enter(CPUX86State *env)
     int i, offset;
 
     qemu_log_mask(CPU_LOG_INT, "SMM: enter\n");
-    log_cpu_state_mask(CPU_LOG_INT, env, X86_DUMP_CCOP);
+    log_cpu_state_mask(CPU_LOG_INT, env, CPU_DUMP_CCOP);
 
     env->hflags |= HF_SMM_MASK;
     cpu_smm_update(env);
@@ -295,7 +295,7 @@ void helper_rsm(CPUX86State *env)
     cpu_smm_update(env);
 
     qemu_log_mask(CPU_LOG_INT, "SMM: after RSM\n");
-    log_cpu_state_mask(CPU_LOG_INT, env, X86_DUMP_CCOP);
+    log_cpu_state_mask(CPU_LOG_INT, env, CPU_DUMP_CCOP);
 }
 
 #endif /* !CONFIG_USER_ONLY */