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>

31 files changed, 218 insertions, 146 deletions

diff --git a/.gitignore b/.gitignore
index 09c2363acf..cf65316863 100644
--- a/.gitignore
+++ b/.gitignore
@@ -116,6 +116,8 @@ tags
 TAGS
 docker-src.*
 *~
+*.ast_raw
+*.depend_raw
 trace.h
 trace.c
 trace-ust.h
diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c
index 090ebad0a7..37ecafa931 100644
--- a/accel/tcg/translate-all.c
+++ b/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);
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index 87b1b74e3b..440fc31b37 100644
--- a/include/exec/exec-all.h
+++ b/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);
 
diff --git a/include/exec/helper-tcg.h b/include/exec/helper-tcg.h
index bb9287727c..b0c5bafa99 100644
--- a/include/exec/helper-tcg.h
+++ b/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
diff --git a/scripts/coccinelle/tcg_gen_extract.cocci b/scripts/coccinelle/tcg_gen_extract.cocci
new file mode 100644
index 0000000000..81e66a35ae
--- /dev/null
+++ b/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);
+)
diff --git a/target/alpha/translate.c b/target/alpha/translate.c
index 90e6d5285f..f465752208 100644
--- a/target/alpha/translate.c
+++ b/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;
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 3fa39023ca..883e9df0c2 100644
--- a/target/arm/translate-a64.c
+++ b/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;
diff --git a/target/arm/translate.c b/target/arm/translate.c
index e27736ce5b..d1a5f56998 100644
--- a/target/arm/translate.c
+++ b/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;
     }
 
diff --git a/target/arm/translate.h b/target/arm/translate.h
index 12fd79ba8e..2fe144baa9 100644
--- a/target/arm/translate.h
+++ b/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)
 {
 }
 
diff --git a/target/cris/translate.c b/target/cris/translate.c
index 0ee05ca02d..12b96eb68f 100644
--- a/target/cris/translate.c
+++ b/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;
diff --git a/target/hppa/translate.c b/target/hppa/translate.c
index e10abc5e04..900870cd5a 100644
--- a/target/hppa/translate.c
+++ b/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;
diff --git a/target/i386/translate.c b/target/i386/translate.c
index ed3b896db4..cab9e32f91 100644
--- a/target/i386/translate.c
+++ b/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;
diff --git a/target/lm32/translate.c b/target/lm32/translate.c
index 692882f447..f68f372f15 100644
--- a/target/lm32/translate.c
+++ b/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;
diff --git a/target/m68k/translate.c b/target/m68k/translate.c
index 3a519b790d..ada2a91b64 100644
--- a/target/m68k/translate.c
+++ b/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;
diff --git a/target/microblaze/translate.c b/target/microblaze/translate.c
index cb65d1e129..a24373c0be 100644
--- a/target/microblaze/translate.c
+++ b/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;
diff --git a/target/mips/translate.c b/target/mips/translate.c
index fe44f2f807..1fd18e9d2a 100644
--- a/target/mips/translate.c
+++ b/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;
diff --git a/target/moxie/translate.c b/target/moxie/translate.c
index 0660b44c08..3cfd232558 100644
--- a/target/moxie/translate.c
+++ b/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;
diff --git a/target/nios2/translate.c b/target/nios2/translate.c
index 2f3c2e5dfb..8b97d6585f 100644
--- a/target/nios2/translate.c
+++ b/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;
diff --git a/target/openrisc/translate.c b/target/openrisc/translate.c
index e49518e893..a01413113b 100644
--- a/target/openrisc/translate.c
+++ b/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;
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index c0cd64d927..01233e8b6d 100644
--- a/target/ppc/translate.c
+++ b/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;
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index 7f12908029..85ed135d44 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1248,8 +1248,7 @@ static void gen_xsxexpdp(DisasContext *ctx)
         gen_exception(ctx, POWERPC_EXCP_VSXU);
         return;
     }
-    tcg_gen_shri_i64(rt, cpu_vsrh(xB(ctx->opcode)), 52);
-    tcg_gen_andi_i64(rt, rt, 0x7FF);
+    tcg_gen_extract_i64(rt, cpu_vsrh(xB(ctx->opcode)), 52, 11);
 }
 
 static void gen_xsxexpqp(DisasContext *ctx)
@@ -1262,8 +1261,7 @@ static void gen_xsxexpqp(DisasContext *ctx)
         gen_exception(ctx, POWERPC_EXCP_VSXU);
         return;
     }
-    tcg_gen_shri_i64(xth, xbh, 48);
-    tcg_gen_andi_i64(xth, xth, 0x7FFF);
+    tcg_gen_extract_i64(xth, xbh, 48, 15);
     tcg_gen_movi_i64(xtl, 0);
 }
 
@@ -1323,8 +1321,7 @@ static void gen_xsxsigdp(DisasContext *ctx)
     zr = tcg_const_i64(0);
     nan = tcg_const_i64(2047);
 
-    tcg_gen_shri_i64(exp, cpu_vsrh(xB(ctx->opcode)), 52);
-    tcg_gen_andi_i64(exp, exp, 0x7FF);
+    tcg_gen_extract_i64(exp, cpu_vsrh(xB(ctx->opcode)), 52, 11);
     tcg_gen_movi_i64(t0, 0x0010000000000000);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0);
@@ -1352,8 +1349,7 @@ static void gen_xsxsigqp(DisasContext *ctx)
     zr = tcg_const_i64(0);
     nan = tcg_const_i64(32767);
 
-    tcg_gen_shri_i64(exp, cpu_vsrh(rB(ctx->opcode) + 32), 48);
-    tcg_gen_andi_i64(exp, exp, 0x7FFF);
+    tcg_gen_extract_i64(exp, cpu_vsrh(rB(ctx->opcode) + 32), 48, 15);
     tcg_gen_movi_i64(t0, 0x0001000000000000);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0);
@@ -1448,10 +1444,8 @@ static void gen_xvxexpdp(DisasContext *ctx)
         gen_exception(ctx, POWERPC_EXCP_VSXU);
         return;
     }
-    tcg_gen_shri_i64(xth, xbh, 52);
-    tcg_gen_andi_i64(xth, xth, 0x7FF);
-    tcg_gen_shri_i64(xtl, xbl, 52);
-    tcg_gen_andi_i64(xtl, xtl, 0x7FF);
+    tcg_gen_extract_i64(xth, xbh, 52, 11);
+    tcg_gen_extract_i64(xtl, xbl, 52, 11);
 }
 
 GEN_VSX_HELPER_2(xvxsigsp, 0x00, 0x04, 0, PPC2_ISA300)
@@ -1474,16 +1468,14 @@ static void gen_xvxsigdp(DisasContext *ctx)
     zr = tcg_const_i64(0);
     nan = tcg_const_i64(2047);
 
-    tcg_gen_shri_i64(exp, xbh, 52);
-    tcg_gen_andi_i64(exp, exp, 0x7FF);
+    tcg_gen_extract_i64(exp, xbh, 52, 11);
     tcg_gen_movi_i64(t0, 0x0010000000000000);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0);
     tcg_gen_andi_i64(xth, xbh, 0x000FFFFFFFFFFFFF);
     tcg_gen_or_i64(xth, xth, t0);
 
-    tcg_gen_shri_i64(exp, xbl, 52);
-    tcg_gen_andi_i64(exp, exp, 0x7FF);
+    tcg_gen_extract_i64(exp, xbl, 52, 11);
     tcg_gen_movi_i64(t0, 0x0010000000000000);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0);
diff --git a/target/s390x/translate.c b/target/s390x/translate.c
index 1dffcee884..48b71f9604 100644
--- a/target/s390x/translate.c
+++ b/target/s390x/translate.c
@@ -5853,10 +5853,9 @@ static ExitStatus translate_one(CPUS390XState *env, DisasContext *s)
     return ret;
 }
 
-void gen_intermediate_code(CPUS390XState *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
-    S390CPU *cpu = s390_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUS390XState *env = cs->env_ptr;
     DisasContext dc;
     target_ulong pc_start;
     uint64_t next_page_start;
diff --git a/target/sh4/translate.c b/target/sh4/translate.c
index 498bb99dc1..10191073b2 100644
--- a/target/sh4/translate.c
+++ b/target/sh4/translate.c
@@ -2230,10 +2230,9 @@ static int decode_gusa(DisasContext *ctx, CPUSH4State *env, int *pmax_insns)
 }
 #endif
 
-void gen_intermediate_code(CPUSH4State * env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
-    SuperHCPU *cpu = sh_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUSH4State *env = cs->env_ptr;
     DisasContext ctx;
     target_ulong pc_start;
     int num_insns;
diff --git a/target/sparc/translate.c b/target/sparc/translate.c
index aa6734d54e..3bde47be83 100644
--- a/target/sparc/translate.c
+++ b/target/sparc/translate.c
@@ -380,29 +380,25 @@ static inline void gen_goto_tb(DisasContext *s, int tb_num,
 static inline void gen_mov_reg_N(TCGv reg, TCGv_i32 src)
 {
     tcg_gen_extu_i32_tl(reg, src);
-    tcg_gen_shri_tl(reg, reg, PSR_NEG_SHIFT);
-    tcg_gen_andi_tl(reg, reg, 0x1);
+    tcg_gen_extract_tl(reg, reg, PSR_NEG_SHIFT, 1);
 }
 
 static inline void gen_mov_reg_Z(TCGv reg, TCGv_i32 src)
 {
     tcg_gen_extu_i32_tl(reg, src);
-    tcg_gen_shri_tl(reg, reg, PSR_ZERO_SHIFT);
-    tcg_gen_andi_tl(reg, reg, 0x1);
+    tcg_gen_extract_tl(reg, reg, PSR_ZERO_SHIFT, 1);
 }
 
 static inline void gen_mov_reg_V(TCGv reg, TCGv_i32 src)
 {
     tcg_gen_extu_i32_tl(reg, src);
-    tcg_gen_shri_tl(reg, reg, PSR_OVF_SHIFT);
-    tcg_gen_andi_tl(reg, reg, 0x1);
+    tcg_gen_extract_tl(reg, reg, PSR_OVF_SHIFT, 1);
 }
 
 static inline void gen_mov_reg_C(TCGv reg, TCGv_i32 src)
 {
     tcg_gen_extu_i32_tl(reg, src);
-    tcg_gen_shri_tl(reg, reg, PSR_CARRY_SHIFT);
-    tcg_gen_andi_tl(reg, reg, 0x1);
+    tcg_gen_extract_tl(reg, reg, PSR_CARRY_SHIFT, 1);
 }
 
 static inline void gen_op_add_cc(TCGv dst, TCGv src1, TCGv src2)
@@ -636,12 +632,8 @@ static inline void gen_op_mulscc(TCGv dst, TCGv src1, TCGv src2)
 
     // b2 = T0 & 1;
     // env->y = (b2 << 31) | (env->y >> 1);
-    tcg_gen_andi_tl(r_temp, cpu_cc_src, 0x1);
-    tcg_gen_shli_tl(r_temp, r_temp, 31);
-    tcg_gen_shri_tl(t0, cpu_y, 1);
-    tcg_gen_andi_tl(t0, t0, 0x7fffffff);
-    tcg_gen_or_tl(t0, t0, r_temp);
-    tcg_gen_andi_tl(cpu_y, t0, 0xffffffff);
+    tcg_gen_extract_tl(t0, cpu_y, 1, 31);
+    tcg_gen_deposit_tl(cpu_y, t0, cpu_cc_src, 31, 1);
 
     // b1 = N ^ V;
     gen_mov_reg_N(t0, cpu_psr);
@@ -5747,10 +5739,9 @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn)
     }
 }
 
-void gen_intermediate_code(CPUSPARCState * env, TranslationBlock * tb)
+void gen_intermediate_code(CPUState *cs, TranslationBlock * tb)
 {
-    SPARCCPU *cpu = sparc_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUSPARCState *env = cs->env_ptr;
     target_ulong pc_start, last_pc;
     DisasContext dc1, *dc = &dc1;
     int num_insns;
diff --git a/target/tilegx/translate.c b/target/tilegx/translate.c
index ff2ef7b63d..ace2830a84 100644
--- a/target/tilegx/translate.c
+++ b/target/tilegx/translate.c
@@ -2370,12 +2370,11 @@ static void translate_one_bundle(DisasContext *dc, uint64_t bundle)
     }
 }
 
-void gen_intermediate_code(CPUTLGState *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
-    TileGXCPU *cpu = tilegx_env_get_cpu(env);
+    CPUTLGState *env = cs->env_ptr;
     DisasContext ctx;
     DisasContext *dc = &ctx;
-    CPUState *cs = CPU(cpu);
     uint64_t pc_start = tb->pc;
     uint64_t next_page_start = (pc_start & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE;
     int num_insns = 0;
diff --git a/target/tricore/translate.c b/target/tricore/translate.c
index ddd2dd07dd..4e4198e887 100644
--- a/target/tricore/translate.c
+++ b/target/tricore/translate.c
@@ -8782,10 +8782,9 @@ static void decode_opc(CPUTriCoreState *env, DisasContext *ctx, int *is_branch)
     }
 }
 
-void gen_intermediate_code(CPUTriCoreState *env, struct TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, struct TranslationBlock *tb)
 {
-    TriCoreCPU *cpu = tricore_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUTriCoreState *env = cs->env_ptr;
     DisasContext ctx;
     target_ulong pc_start;
     int num_insns, max_insns;
diff --git a/target/unicore32/translate.c b/target/unicore32/translate.c
index 666a2016a8..8f30cff932 100644
--- a/target/unicore32/translate.c
+++ b/target/unicore32/translate.c
@@ -1869,10 +1869,9 @@ static void disas_uc32_insn(CPUUniCore32State *env, DisasContext *s)
 }
 
 /* generate intermediate code for basic block 'tb'.  */
-void gen_intermediate_code(CPUUniCore32State *env, TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, TranslationBlock *tb)
 {
-    UniCore32CPU *cpu = uc32_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUUniCore32State *env = cs->env_ptr;
     DisasContext dc1, *dc = &dc1;
     target_ulong pc_start;
     uint32_t next_page_start;
diff --git a/target/xtensa/translate.c b/target/xtensa/translate.c
index 263002486c..f3f0ff589c 100644
--- a/target/xtensa/translate.c
+++ b/target/xtensa/translate.c
@@ -3117,10 +3117,9 @@ static void gen_ibreak_check(CPUXtensaState *env, DisasContext *dc)
     }
 }
 
-void gen_intermediate_code(CPUXtensaState *env, TranslationBlock *tb)
+void gen_intermediate_code(CPUState *cs, TranslationBlock *tb)
 {
-    XtensaCPU *cpu = xtensa_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUXtensaState *env = cs->env_ptr;
     DisasContext dc;
     int insn_count = 0;
     int max_insns = tb->cflags & CF_COUNT_MASK;
diff --git a/tcg/mips/tcg-target.inc.c b/tcg/mips/tcg-target.inc.c
index 85756b81d5..1a8169f5fc 100644
--- a/tcg/mips/tcg-target.inc.c
+++ b/tcg/mips/tcg-target.inc.c
@@ -85,6 +85,10 @@ static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
 #define TCG_TMP2  TCG_REG_T8
 #define TCG_TMP3  TCG_REG_T7
 
+#ifndef CONFIG_SOFTMMU
+#define TCG_GUEST_BASE_REG TCG_REG_S1
+#endif
+
 /* check if we really need so many registers :P */
 static const int tcg_target_reg_alloc_order[] = {
     /* Call saved registers.  */
@@ -1547,8 +1551,7 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64)
     } else if (guest_base == (int16_t)guest_base) {
         tcg_out_opc_imm(s, ALIAS_PADDI, base, addr_regl, guest_base);
     } else {
-        tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, guest_base);
-        tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_TMP0, addr_regl);
+        tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_GUEST_BASE_REG, addr_regl);
     }
     tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, is_64);
 #endif
@@ -1652,8 +1655,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64)
     } else if (guest_base == (int16_t)guest_base) {
         tcg_out_opc_imm(s, ALIAS_PADDI, base, addr_regl, guest_base);
     } else {
-        tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, guest_base);
-        tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_TMP0, addr_regl);
+        tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_GUEST_BASE_REG, addr_regl);
     }
     tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc);
 #endif
@@ -2452,6 +2454,13 @@ static void tcg_target_qemu_prologue(TCGContext *s)
                    TCG_REG_SP, SAVE_OFS + i * REG_SIZE);
     }
 
+#ifndef CONFIG_SOFTMMU
+    if (guest_base) {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_GUEST_BASE_REG, guest_base);
+        tcg_regset_set_reg(s->reserved_regs, TCG_GUEST_BASE_REG);
+    }
+#endif
+
     /* Call generated code */
     tcg_out_opc_reg(s, OPC_JR, 0, tcg_target_call_iarg_regs[1], 0);
     /* delay slot */
diff --git a/tcg/tci.c b/tcg/tci.c
index 4bdc645f2a..f39bfb95c0 100644
--- a/tcg/tci.c
+++ b/tcg/tci.c
@@ -1046,7 +1046,6 @@ uintptr_t tcg_qemu_tb_exec(CPUArchState *env, uint8_t *tb_ptr)
             break;
 #if TCG_TARGET_HAS_bswap16_i64
         case INDEX_op_bswap16_i64:
-            TODO();
             t0 = *tb_ptr++;
             t1 = tci_read_r16(&tb_ptr);
             tci_write_reg64(t0, bswap16(t1));
diff --git a/util/cacheinfo.c b/util/cacheinfo.c
index 6253049533..593940f27b 100644
--- a/util/cacheinfo.c
+++ b/util/cacheinfo.c
@@ -129,6 +129,7 @@ static void arch_cache_info(int *isize, int *dsize)
 }
 
 #elif defined(_ARCH_PPC) && defined(__linux__)
+# include "elf.h"
 
 static void arch_cache_info(int *isize, int *dsize)
 {