[Qemu-devel] [PATCH v2] tcg-i386: Perform cmov detection at runtime for 32-bit.

[Richard Henderson <rth@twiddle.net>]

Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
 configure             | 19 +++++++++++++++++++
 tcg/i386/tcg-target.c | 31 ++++++++++++++++++++++++++++++-
 tcg/i386/tcg-target.h |  5 -----
 3 files changed, 49 insertions(+), 6 deletions(-)

Changes v1->v2:
  * Configure-time detection for cpuid.h.
  * Don't do any checking for preprocessor defines that "imply" cmov.


r~



diff --git a/configure b/configure
index e5aedef..1231600 100755
--- a/configure
+++ b/configure
@@ -3071,6 +3071,21 @@ if compile_prog "" "" ; then
     has_environ=yes
 fi
 
+########################################
+# check if cpuid.h is usable.
+
+cpuid_h=no
+cat > $TMPC << EOF
+#include <cpuid.h>
+int main(void) {
+  return 0;
+}
+EOF
+if compile_prog "" "" ; then
+    cpuid_h=yes
+fi
+
+
 ##########################################
 # End of CC checks
 # After here, no more $cc or $ld runs
@@ -3601,6 +3616,10 @@ if test "$has_environ" = "yes" ; then
   echo "CONFIG_HAS_ENVIRON=y" >> $config_host_mak
 fi
 
+if test "$cpuid_h" = "yes" ; then
+  echo "CONFIG_CPUID_H=y" >> $config_host_mak
+fi
+
 if test "$glusterfs" = "yes" ; then
   echo "CONFIG_GLUSTERFS=y" >> $config_host_mak
 fi
diff --git a/tcg/i386/tcg-target.c b/tcg/i386/tcg-target.c
index 6f3ad3c..8d603a5 100644
--- a/tcg/i386/tcg-target.c
+++ b/tcg/i386/tcg-target.c
@@ -97,6 +97,18 @@ static const int tcg_target_call_oarg_regs[] = {
 # define TCG_REG_L1 TCG_REG_EDX
 #endif
 
+/* For 32-bit, we are going to attempt to determine at runtime whether cmov
+   is available.  However, the host compiler must supply <cpuid.h>, as we're
+   not going to go so far as our own inline assembly.  */
+#if TCG_TARGET_REG_BITS == 64
+# define have_cmov 1
+#elif defined(CONFIG_CPUID_H)
+#include <cpuid.h>
+static bool have_cmov;
+#else
+# define have_cmov 0
+#endif
+
 static uint8_t *tb_ret_addr;
 
 static void patch_reloc(uint8_t *code_ptr, int type,
@@ -943,7 +955,14 @@ static void tcg_out_movcond32(TCGContext *s, TCGCond cond, TCGArg dest,
                               TCGArg v1)
 {
     tcg_out_cmp(s, c1, c2, const_c2, 0);
-    tcg_out_modrm(s, OPC_CMOVCC | tcg_cond_to_jcc[cond], dest, v1);
+    if (have_cmov) {
+        tcg_out_modrm(s, OPC_CMOVCC | tcg_cond_to_jcc[cond], dest, v1);
+    } else {
+        int over = gen_new_label();
+        tcg_out_jxx(s, tcg_cond_to_jcc[tcg_invert_cond(cond)], over, 1);
+        tcg_out_mov(s, TCG_TYPE_I32, dest, v1);
+        tcg_out_label(s, over, s->code_ptr);
+    }
 }
 
 #if TCG_TARGET_REG_BITS == 64
@@ -2243,6 +2262,16 @@ static void tcg_target_qemu_prologue(TCGContext *s)
 
 static void tcg_target_init(TCGContext *s)
 {
+    /* For 32-bit, 99% certainty that we're running on hardware that supports
+       cmov, but we still need to check.  In case cmov is not available, we'll
+       use a small forward branch.  */
+#ifndef have_cmov
+    {
+        unsigned a, b, c, d;
+        have_cmov = (__get_cpuid(1, &a, &b, &c, &d) && (d & bit_CMOV));
+    }
+#endif
+
 #if !defined(CONFIG_USER_ONLY)
     /* fail safe */
     if ((1 << CPU_TLB_ENTRY_BITS) != sizeof(CPUTLBEntry))
diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h
index dbc6756..450078b 100644
--- a/tcg/i386/tcg-target.h
+++ b/tcg/i386/tcg-target.h
@@ -90,12 +90,7 @@ typedef enum {
 #define TCG_TARGET_HAS_nand_i32         0
 #define TCG_TARGET_HAS_nor_i32          0
 #define TCG_TARGET_HAS_deposit_i32      1
-#if defined(__x86_64__) || defined(__i686__)
-/* Use cmov only if the compiler is already doing so.  */
 #define TCG_TARGET_HAS_movcond_i32      1
-#else
-#define TCG_TARGET_HAS_movcond_i32      0
-#endif
 
 #if TCG_TARGET_REG_BITS == 64
 #define TCG_TARGET_HAS_div2_i64         1
-- 
1.7.11.7