Merge remote-tracking branch 'remotes/rth/tags/pull-tcg-20170719' into staging

Queued tcg and tcg code gen related cleanups

# gpg: Signature made Thu 20 Jul 2017 00:32:00 BST
# gpg:                using RSA key 0xAD1270CC4DD0279B
# gpg: Good signature from "Richard Henderson <rth7680@gmail.com>"
# gpg:                 aka "Richard Henderson <rth@redhat.com>"
# gpg:                 aka "Richard Henderson <rth@twiddle.net>"
# Primary key fingerprint: 9CB1 8DDA F8E8 49AD 2AFC  16A4 AD12 70CC 4DD0 279B

* remotes/rth/tags/pull-tcg-20170719:
  tcg: Pass generic CPUState to gen_intermediate_code()
  tcg/tci: enable bswap16_i64
  target/alpha: optimize gen_cvtlq() using deposit op
  target/sparc: optimize gen_op_mulscc() using deposit op
  target/sparc: optimize various functions using extract op
  target/ppc: optimize various functions using extract op
  target/m68k: optimize bcd_flags() using extract op
  target/arm: optimize aarch32 rev16
  target/arm: Optimize aarch64 rev16
  coccinelle: add a script to optimize tcg op using tcg_gen_extract()
  coccinelle: ignore ASTs pre-parsed cached C files
  tcg: Expand glue macros before stringifying helper names
  util/cacheinfo: Add missing include for ppc linux
  tcg/mips: reserve a register for the guest_base.

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

.gitignore

@@ -116,6 +116,8 @@ tags
 TAGS
 docker-src.*
 *~
+*.ast_raw
+*.depend_raw
 trace.h
 trace.c
 trace-ust.h

accel/tcg/translate-all.c

@@ -1280,7 +1280,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
     tcg_func_start(&tcg_ctx);
 
     tcg_ctx.cpu = ENV_GET_CPU(env);
-    gen_intermediate_code(env, tb);
+    gen_intermediate_code(cpu, tb);
     tcg_ctx.cpu = NULL;
 
     trace_translate_block(tb, tb->pc, tb->tc_ptr);

include/exec/exec-all.h

@@ -66,7 +66,7 @@ typedef ram_addr_t tb_page_addr_t;
 
 #include "qemu/log.h"
 
-void gen_intermediate_code(CPUArchState *env, struct TranslationBlock *tb);
+void gen_intermediate_code(CPUState *cpu, struct TranslationBlock *tb);
 void restore_state_to_opc(CPUArchState *env, struct TranslationBlock *tb,
                           target_ulong *data);
 

include/exec/helper-tcg.h

@@ -6,31 +6,35 @@
 
 #include "exec/helper-head.h"
 
+/* Need one more level of indirection before stringification
+   to get all the macros expanded first.  */
+#define str(s) #s
+
 #define DEF_HELPER_FLAGS_0(NAME, FLAGS, ret) \
-  { .func = HELPER(NAME), .name = #NAME, .flags = FLAGS, \
+  { .func = HELPER(NAME), .name = str(NAME), .flags = FLAGS, \
     .sizemask = dh_sizemask(ret, 0) },
 
 #define DEF_HELPER_FLAGS_1(NAME, FLAGS, ret, t1) \
-  { .func = HELPER(NAME), .name = #NAME, .flags = FLAGS, \
+  { .func = HELPER(NAME), .name = str(NAME), .flags = FLAGS, \
     .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) },
 
 #define DEF_HELPER_FLAGS_2(NAME, FLAGS, ret, t1, t2) \
-  { .func = HELPER(NAME), .name = #NAME, .flags = FLAGS, \
+  { .func = HELPER(NAME), .name = str(NAME), .flags = FLAGS, \
     .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) \
     | dh_sizemask(t2, 2) },
 
 #define DEF_HELPER_FLAGS_3(NAME, FLAGS, ret, t1, t2, t3) \
-  { .func = HELPER(NAME), .name = #NAME, .flags = FLAGS, \
+  { .func = HELPER(NAME), .name = str(NAME), .flags = FLAGS, \
     .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) \
     | dh_sizemask(t2, 2) | dh_sizemask(t3, 3) },
 
 #define DEF_HELPER_FLAGS_4(NAME, FLAGS, ret, t1, t2, t3, t4) \
-  { .func = HELPER(NAME), .name = #NAME, .flags = FLAGS, \
+  { .func = HELPER(NAME), .name = str(NAME), .flags = FLAGS, \
     .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) \
     | dh_sizemask(t2, 2) | dh_sizemask(t3, 3) | dh_sizemask(t4, 4) },
 
 #define DEF_HELPER_FLAGS_5(NAME, FLAGS, ret, t1, t2, t3, t4, t5) \
-  { .func = HELPER(NAME), .name = #NAME, .flags = FLAGS, \
+  { .func = HELPER(NAME), .name = str(NAME), .flags = FLAGS, \
     .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) \
     | dh_sizemask(t2, 2) | dh_sizemask(t3, 3) | dh_sizemask(t4, 4) \
     | dh_sizemask(t5, 5) },
@@ -39,6 +43,7 @@
 #include "trace/generated-helpers.h"
 #include "tcg-runtime.h"
 
+#undef str
 #undef DEF_HELPER_FLAGS_0
 #undef DEF_HELPER_FLAGS_1
 #undef DEF_HELPER_FLAGS_2

scripts/coccinelle/tcg_gen_extract.cocci

@@ -0,0 +1,107 @@
+// optimize TCG using extract op
+//
+// Copyright: (C) 2017 Philippe Mathieu-Daudé. GPLv2+.
+// Confidence: High
+// Options: --macro-file scripts/cocci-macro-file.h
+//
+// Nikunj A Dadhania optimization:
+// http://lists.nongnu.org/archive/html/qemu-devel/2017-02/msg05211.html
+// Aurelien Jarno optimization:
+// http://lists.nongnu.org/archive/html/qemu-devel/2017-05/msg01466.html
+//
+// This script can be run either using spatch locally or via a docker image:
+//
+// $ spatch \
+//     --macro-file scripts/cocci-macro-file.h \
+//     --sp-file scripts/coccinelle/tcg_gen_extract.cocci \
+//     --keep-comments --in-place \
+//     --use-gitgrep --dir target
+//
+// $ docker run --rm -v `pwd`:`pwd` -w `pwd` philmd/coccinelle \
+//     --macro-file scripts/cocci-macro-file.h \
+//     --sp-file scripts/coccinelle/tcg_gen_extract.cocci \
+//     --keep-comments --in-place \
+//     --use-gitgrep --dir target
+
+@initialize:python@
+@@
+import sys
+fd = sys.stderr
+def debug(msg="", trailer="\n"):
+    fd.write("[DBG] " + msg + trailer)
+def low_bits_count(value):
+    bits_count = 0
+    while (value & (1 << bits_count)):
+        bits_count += 1
+    return bits_count
+def Mn(order): # Mersenne number
+    return (1 << order) - 1
+
+@match@
+identifier ret;
+metavariable arg;
+constant ofs, msk;
+position shr_p, and_p;
+@@
+(
+    tcg_gen_shri_i32@shr_p
+|
+    tcg_gen_shri_i64@shr_p
+|
+    tcg_gen_shri_tl@shr_p
+)(ret, arg, ofs);
+...  WHEN != ret
+(
+    tcg_gen_andi_i32@and_p
+|
+    tcg_gen_andi_i64@and_p
+|
+    tcg_gen_andi_tl@and_p
+)(ret, ret, msk);
+
+@script:python verify_len depends on match@
+ret_s << match.ret;
+msk_s << match.msk;
+shr_p << match.shr_p;
+extract_len;
+@@
+is_optimizable = False
+debug("candidate at %s:%s" % (shr_p[0].file, shr_p[0].line))
+try: # only eval integer, no #define like 'SR_M' (cpp did this, else some headers are missing).
+    msk_v = long(msk_s.strip("UL"), 0)
+    msk_b = low_bits_count(msk_v)
+    if msk_b == 0:
+        debug("  value: 0x%x low_bits: %d" % (msk_v, msk_b))
+    else:
+        debug("  value: 0x%x low_bits: %d [Mersenne number: 0x%x]" % (msk_v, msk_b, Mn(msk_b)))
+        is_optimizable = Mn(msk_b) == msk_v # check low_bits
+        coccinelle.extract_len = "%d" % msk_b
+    debug("  candidate %s optimizable" % ("IS" if is_optimizable else "is NOT"))
+except:
+    debug("  ERROR (check included headers?)")
+cocci.include_match(is_optimizable)
+debug()
+
+@replacement depends on verify_len@
+identifier match.ret;
+metavariable match.arg;
+constant match.ofs, match.msk;
+position match.shr_p, match.and_p;
+identifier verify_len.extract_len;
+@@
+(
+-tcg_gen_shri_i32@shr_p(ret, arg, ofs);
++tcg_gen_extract_i32(ret, arg, ofs, extract_len);
+...  WHEN != ret
+-tcg_gen_andi_i32@and_p(ret, ret, msk);
+|
+-tcg_gen_shri_i64@shr_p(ret, arg, ofs);
++tcg_gen_extract_i64(ret, arg, ofs, extract_len);
+...  WHEN != ret
+-tcg_gen_andi_i64@and_p(ret, ret, msk);
+|
+-tcg_gen_shri_tl@shr_p(ret, arg, ofs);
++tcg_gen_extract_tl(ret, arg, ofs, extract_len);
+...  WHEN != ret
+-tcg_gen_andi_tl@and_p(ret, ret, msk);
+)

target/alpha/translate.c

@@ -783,11 +783,9 @@ static void gen_cvtlq(TCGv vc, TCGv vb)
 
     /* The arithmetic right shift here, plus the sign-extended mask below
        yields a sign-extended result without an explicit ext32s_i64.  */
-    tcg_gen_sari_i64(tmp, vb, 32);
-    tcg_gen_shri_i64(vc, vb, 29);
-    tcg_gen_andi_i64(tmp, tmp, (int32_t)0xc0000000);
-    tcg_gen_andi_i64(vc, vc, 0x3fffffff);
-    tcg_gen_or_i64(vc, vc, tmp);
+    tcg_gen_shri_i64(tmp, vb, 29);
+    tcg_gen_sari_i64(vc, vb, 32);
+    tcg_gen_deposit_i64(vc, vc, tmp, 0, 30);
 
     tcg_temp_free(tmp);
 }
@@ -2954,10 +2952,9 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
     return ret;
 }
 
-void gen_intermediate_code(CPUAlphaState *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
-    AlphaCPU *cpu = alpha_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUAlphaState *env = cs->env_ptr;
     DisasContext ctx, *ctxp = &ctx;
     target_ulong pc_start;
     target_ulong pc_mask;

target/arm/translate-a64.c

@@ -4043,25 +4043,13 @@ static void handle_rev16(DisasContext *s, unsigned int sf,
     TCGv_i64 tcg_rd = cpu_reg(s, rd);
     TCGv_i64 tcg_tmp = tcg_temp_new_i64();
     TCGv_i64 tcg_rn = read_cpu_reg(s, rn, sf);
+    TCGv_i64 mask = tcg_const_i64(sf ? 0x00ff00ff00ff00ffull : 0x00ff00ff);
 
-    tcg_gen_andi_i64(tcg_tmp, tcg_rn, 0xffff);
-    tcg_gen_bswap16_i64(tcg_rd, tcg_tmp);
-
-    tcg_gen_shri_i64(tcg_tmp, tcg_rn, 16);
-    tcg_gen_andi_i64(tcg_tmp, tcg_tmp, 0xffff);
-    tcg_gen_bswap16_i64(tcg_tmp, tcg_tmp);
-    tcg_gen_deposit_i64(tcg_rd, tcg_rd, tcg_tmp, 16, 16);
-
-    if (sf) {
-        tcg_gen_shri_i64(tcg_tmp, tcg_rn, 32);
-        tcg_gen_andi_i64(tcg_tmp, tcg_tmp, 0xffff);
-        tcg_gen_bswap16_i64(tcg_tmp, tcg_tmp);
-        tcg_gen_deposit_i64(tcg_rd, tcg_rd, tcg_tmp, 32, 16);
-
-        tcg_gen_shri_i64(tcg_tmp, tcg_rn, 48);
-        tcg_gen_bswap16_i64(tcg_tmp, tcg_tmp);
-        tcg_gen_deposit_i64(tcg_rd, tcg_rd, tcg_tmp, 48, 16);
-    }
+    tcg_gen_shri_i64(tcg_tmp, tcg_rn, 8);
+    tcg_gen_and_i64(tcg_rd, tcg_rn, mask);
+    tcg_gen_and_i64(tcg_tmp, tcg_tmp, mask);
+    tcg_gen_shli_i64(tcg_rd, tcg_rd, 8);
+    tcg_gen_or_i64(tcg_rd, tcg_rd, tcg_tmp);
 
     tcg_temp_free_i64(tcg_tmp);
 }
@@ -11191,10 +11179,10 @@ static void disas_a64_insn(CPUARMState *env, DisasContext *s)
     free_tmp_a64(s);
 }
 
-void gen_intermediate_code_a64(ARMCPU *cpu, TranslationBlock *tb)
+void gen_intermediate_code_a64(CPUState *cs, TranslationBlock *tb)
 {
-    CPUState *cs = CPU(cpu);
-    CPUARMState *env = &cpu->env;
+    CPUARMState *env = cs->env_ptr;
+    ARMCPU *cpu = arm_env_get_cpu(env);
     DisasContext dc1, *dc = &dc1;
     target_ulong pc_start;
     target_ulong next_page_start;

target/arm/translate.c

@@ -343,11 +343,13 @@ static void gen_smul_dual(TCGv_i32 a, TCGv_i32 b)
 static void gen_rev16(TCGv_i32 var)
 {
     TCGv_i32 tmp = tcg_temp_new_i32();
+    TCGv_i32 mask = tcg_const_i32(0x00ff00ff);
     tcg_gen_shri_i32(tmp, var, 8);
-    tcg_gen_andi_i32(tmp, tmp, 0x00ff00ff);
+    tcg_gen_and_i32(tmp, tmp, mask);
+    tcg_gen_and_i32(var, var, mask);
     tcg_gen_shli_i32(var, var, 8);
-    tcg_gen_andi_i32(var, var, 0xff00ff00);
     tcg_gen_or_i32(var, var, tmp);
+    tcg_temp_free_i32(mask);
     tcg_temp_free_i32(tmp);
 }
 
@@ -11793,10 +11795,10 @@ static bool insn_crosses_page(CPUARMState *env, DisasContext *s)
 }
 
 /* generate intermediate code for basic block 'tb'.  */
-void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, TranslationBlock *tb)
 {
+    CPUARMState *env = cs->env_ptr;
     ARMCPU *cpu = arm_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
     DisasContext dc1, *dc = &dc1;
     target_ulong pc_start;
     target_ulong next_page_start;
@@ -11810,7 +11812,7 @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb)
      * the A32/T32 complexity to do with conditional execution/IT blocks/etc.
      */
     if (ARM_TBFLAG_AARCH64_STATE(tb->flags)) {
-        gen_intermediate_code_a64(cpu, tb);
+        gen_intermediate_code_a64(cs, tb);
         return;
     }
 

target/arm/translate.h

@@ -149,7 +149,7 @@ static void disas_set_insn_syndrome(DisasContext *s, uint32_t syn)
 
 #ifdef TARGET_AARCH64
 void a64_translate_init(void);
-void gen_intermediate_code_a64(ARMCPU *cpu, TranslationBlock *tb);
+void gen_intermediate_code_a64(CPUState *cpu, TranslationBlock *tb);
 void gen_a64_set_pc_im(uint64_t val);
 void aarch64_cpu_dump_state(CPUState *cs, FILE *f,
                             fprintf_function cpu_fprintf, int flags);
@@ -158,7 +158,7 @@ static inline void a64_translate_init(void)
 {
 }
 
-static inline void gen_intermediate_code_a64(ARMCPU *cpu, TranslationBlock *tb)
+static inline void gen_intermediate_code_a64(CPUState *cpu, TranslationBlock *tb)
 {
 }
 

target/cris/translate.c

@@ -3080,10 +3080,9 @@ static unsigned int crisv32_decoder(CPUCRISState *env, DisasContext *dc)
  */
 
 /* generate intermediate code for basic block 'tb'.  */
-void gen_intermediate_code(CPUCRISState *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
-    CRISCPU *cpu = cris_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUCRISState *env = cs->env_ptr;
     uint32_t pc_start;
     unsigned int insn_len;
     struct DisasContext ctx;
@@ -3105,7 +3104,7 @@ void gen_intermediate_code(CPUCRISState *env, struct TranslationBlock *tb)
      * delayslot, like in real hw.
      */
     pc_start = tb->pc & ~1;
-    dc->cpu = cpu;
+    dc->cpu = cris_env_get_cpu(env);
     dc->tb = tb;
 
     dc->is_jmp = DISAS_NEXT;

target/hppa/translate.c

@@ -3740,10 +3740,9 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
     return gen_illegal(ctx);
 }
 
-void gen_intermediate_code(CPUHPPAState *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
-    HPPACPU *cpu = hppa_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUHPPAState *env = cs->env_ptr;
     DisasContext ctx;
     ExitStatus ret;
     int num_insns, max_insns, i;

target/i386/translate.c

@@ -8378,10 +8378,9 @@ void tcg_x86_init(void)
 }
 
 /* generate intermediate code for basic block 'tb'.  */
-void gen_intermediate_code(CPUX86State *env, TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, TranslationBlock *tb)
 {
-    X86CPU *cpu = x86_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUX86State *env = cs->env_ptr;
     DisasContext dc1, *dc = &dc1;
     target_ulong pc_ptr;
     uint32_t flags;

target/lm32/translate.c

@@ -1044,10 +1044,10 @@ static inline void decode(DisasContext *dc, uint32_t ir)
 }
 
 /* generate intermediate code for basic block 'tb'.  */
-void gen_intermediate_code(CPULM32State *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
+    CPULM32State *env = cs->env_ptr;
     LM32CPU *cpu = lm32_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
     struct DisasContext ctx, *dc = &ctx;
     uint32_t pc_start;
     uint32_t next_page_start;

target/m68k/translate.c

@@ -1749,8 +1749,7 @@ static void bcd_flags(TCGv val)
     tcg_gen_andi_i32(QREG_CC_C, val, 0x0ff);
     tcg_gen_or_i32(QREG_CC_Z, QREG_CC_Z, QREG_CC_C);
 
-    tcg_gen_shri_i32(QREG_CC_C, val, 8);
-    tcg_gen_andi_i32(QREG_CC_C, QREG_CC_C, 1);
+    tcg_gen_extract_i32(QREG_CC_C, val, 8, 1);
 
     tcg_gen_mov_i32(QREG_CC_X, QREG_CC_C);
 }
@@ -5519,10 +5518,9 @@ static void disas_m68k_insn(CPUM68KState * env, DisasContext *s)
 }
 
 /* generate intermediate code for basic block 'tb'.  */
-void gen_intermediate_code(CPUM68KState *env, TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, TranslationBlock *tb)
 {
-    M68kCPU *cpu = m68k_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUM68KState *env = cs->env_ptr;
     DisasContext dc1, *dc = &dc1;
     target_ulong pc_start;
     int pc_offset;

target/microblaze/translate.c

@@ -1625,10 +1625,10 @@ static inline void decode(DisasContext *dc, uint32_t ir)
 }
 
 /* generate intermediate code for basic block 'tb'.  */
-void gen_intermediate_code(CPUMBState *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
+    CPUMBState *env = cs->env_ptr;
     MicroBlazeCPU *cpu = mb_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
     uint32_t pc_start;
     struct DisasContext ctx;
     struct DisasContext *dc = &ctx;

target/mips/translate.c

@@ -19888,10 +19888,9 @@ static void decode_opc(CPUMIPSState *env, DisasContext *ctx)
     }
 }
 
-void gen_intermediate_code(CPUMIPSState *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
-    MIPSCPU *cpu = mips_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUMIPSState *env = cs->env_ptr;
     DisasContext ctx;
     target_ulong pc_start;
     target_ulong next_page_start;

target/moxie/translate.c

@@ -822,10 +822,10 @@ static int decode_opc(MoxieCPU *cpu, DisasContext *ctx)
 }
 
 /* generate intermediate code for basic block 'tb'.  */
-void gen_intermediate_code(CPUMoxieState *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
+    CPUMoxieState *env = cs->env_ptr;
     MoxieCPU *cpu = moxie_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
     DisasContext ctx;
     target_ulong pc_start;
     int num_insns, max_insns;

target/nios2/translate.c

@@ -799,10 +799,9 @@ static void gen_exception(DisasContext *dc, uint32_t excp)
 }
 
 /* generate intermediate code for basic block 'tb'.  */
-void gen_intermediate_code(CPUNios2State *env, TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, TranslationBlock *tb)
 {
-    Nios2CPU *cpu = nios2_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUNios2State *env = cs->env_ptr;
     DisasContext dc1, *dc = &dc1;
     int num_insns;
     int max_insns;

target/openrisc/translate.c

@@ -1518,10 +1518,10 @@ static void disas_openrisc_insn(DisasContext *dc, OpenRISCCPU *cpu)
     }
 }
 
-void gen_intermediate_code(CPUOpenRISCState *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
+    CPUOpenRISCState *env = cs->env_ptr;
     OpenRISCCPU *cpu = openrisc_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
     struct DisasContext ctx, *dc = &ctx;
     uint32_t pc_start;
     uint32_t next_page_start;

target/ppc/translate.c

@@ -873,8 +873,7 @@ static inline void gen_op_arith_add(DisasContext *ctx, TCGv ret, TCGv arg1,
             }
             tcg_gen_xor_tl(cpu_ca, t0, t1);        /* bits changed w/ carry */
             tcg_temp_free(t1);
-            tcg_gen_shri_tl(cpu_ca, cpu_ca, 32);   /* extract bit 32 */
-            tcg_gen_andi_tl(cpu_ca, cpu_ca, 1);
+            tcg_gen_extract_tl(cpu_ca, cpu_ca, 32, 1);
             if (is_isa300(ctx)) {
                 tcg_gen_mov_tl(cpu_ca32, cpu_ca);
             }
@@ -1404,8 +1403,7 @@ static inline void gen_op_arith_subf(DisasContext *ctx, TCGv ret, TCGv arg1,
             tcg_temp_free(inv1);
             tcg_gen_xor_tl(cpu_ca, t0, t1);         /* bits changes w/ carry */
             tcg_temp_free(t1);
-            tcg_gen_shri_tl(cpu_ca, cpu_ca, 32);    /* extract bit 32 */
-            tcg_gen_andi_tl(cpu_ca, cpu_ca, 1);
+            tcg_gen_extract_tl(cpu_ca, cpu_ca, 32, 1);
             if (is_isa300(ctx)) {
                 tcg_gen_mov_tl(cpu_ca32, cpu_ca);
             }
@@ -4336,8 +4334,7 @@ static void gen_mfsrin(DisasContext *ctx)
 
     CHK_SV;
     t0 = tcg_temp_new();
-    tcg_gen_shri_tl(t0, cpu_gpr[rB(ctx->opcode)], 28);
-    tcg_gen_andi_tl(t0, t0, 0xF);
+    tcg_gen_extract_tl(t0, cpu_gpr[rB(ctx->opcode)], 28, 4);
     gen_helper_load_sr(cpu_gpr[rD(ctx->opcode)], cpu_env, t0);
     tcg_temp_free(t0);
 #endif /* defined(CONFIG_USER_ONLY) */
@@ -4368,8 +4365,7 @@ static void gen_mtsrin(DisasContext *ctx)
     CHK_SV;
 
     t0 = tcg_temp_new();
-    tcg_gen_shri_tl(t0, cpu_gpr[rB(ctx->opcode)], 28);
-    tcg_gen_andi_tl(t0, t0, 0xF);
+    tcg_gen_extract_tl(t0, cpu_gpr[rB(ctx->opcode)], 28, 4);
     gen_helper_store_sr(cpu_env, t0, cpu_gpr[rD(ctx->opcode)]);
     tcg_temp_free(t0);
 #endif /* defined(CONFIG_USER_ONLY) */
@@ -4403,8 +4399,7 @@ static void gen_mfsrin_64b(DisasContext *ctx)
 
     CHK_SV;
     t0 = tcg_temp_new();
-    tcg_gen_shri_tl(t0, cpu_gpr[rB(ctx->opcode)], 28);
-    tcg_gen_andi_tl(t0, t0, 0xF);
+    tcg_gen_extract_tl(t0, cpu_gpr[rB(ctx->opcode)], 28, 4);
     gen_helper_load_sr(cpu_gpr[rD(ctx->opcode)], cpu_env, t0);
     tcg_temp_free(t0);
 #endif /* defined(CONFIG_USER_ONLY) */
@@ -4435,8 +4430,7 @@ static void gen_mtsrin_64b(DisasContext *ctx)
 
     CHK_SV;
     t0 = tcg_temp_new();
-    tcg_gen_shri_tl(t0, cpu_gpr[rB(ctx->opcode)], 28);
-    tcg_gen_andi_tl(t0, t0, 0xF);
+    tcg_gen_extract_tl(t0, cpu_gpr[rB(ctx->opcode)], 28, 4);
     gen_helper_store_sr(cpu_env, t0, cpu_gpr[rS(ctx->opcode)]);
     tcg_temp_free(t0);
 #endif /* defined(CONFIG_USER_ONLY) */
@@ -5414,8 +5408,7 @@ static void gen_mfsri(DisasContext *ctx)
     CHK_SV;
     t0 = tcg_temp_new();
     gen_addr_reg_index(ctx, t0);
-    tcg_gen_shri_tl(t0, t0, 28);
-    tcg_gen_andi_tl(t0, t0, 0xF);
+    tcg_gen_extract_tl(t0, t0, 28, 4);
     gen_helper_load_sr(cpu_gpr[rd], cpu_env, t0);
     tcg_temp_free(t0);
     if (ra != 0 && ra != rd)
@@ -7203,10 +7196,9 @@ void ppc_cpu_dump_statistics(CPUState *cs, FILE*f,
 }
 
 /*****************************************************************************/
-void gen_intermediate_code(CPUPPCState *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
-    PowerPCCPU *cpu = ppc_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUPPCState *env = cs->env_ptr;
     DisasContext ctx, *ctxp = &ctx;
     opc_handler_t **table, *handler;
     target_ulong pc_start;