util: Introduce include/qemu/cpuid.h

Clang 3.9 passes the CONFIG_AVX2_OPT configure test. However, the
supplied <cpuid.h> does not contain the bit_AVX2 define that we use
when detecting whether the routine can be enabled.

Introduce a qemu-specific header that uses the compiler's definition
of __cpuid et al, but supplies any missing bit_* definitions needed.
This avoids introducing any extra ifdefs to util/bufferiszero.c, and
allows quite a few to be removed from tcg/i386/tcg-target.inc.c.

Backports commit 5dd8990841a9e331d9d4838a116291698208cbb6 from qemu

qemu/configure

@@ -175,6 +175,8 @@ solaris="no"
 softmmu="yes"
 pie=""
 tcg="yes"
+cpuid_h="no"
+avx2_opt="no"
 
 # parse CC options first
 for opt do
@@ -1043,7 +1045,6 @@ fi
 ########################################
 # check if cpuid.h is usable.
 
-cpuid_h=no
 cat > $TMPC << EOF
 #include <cpuid.h>
 int main(void) {
@@ -1065,6 +1066,29 @@ if compile_prog "" "" ; then
     cpuid_h=yes
 fi
 
+##########################################
+# avx2 optimization requirement check
+#
+# There is no point enabling this if cpuid.h is not usable,
+# since we won't be able to select the new routines.
+
+if test $cpuid_h = yes; then
+  cat > $TMPC << EOF
+#pragma GCC push_options
+#pragma GCC target("avx2")
+#include <cpuid.h>
+#include <immintrin.h>
+static int bar(void *a) {
+    __m256i x = *(__m256i *)a;
+    return _mm256_testz_si256(x, x);
+}
+int main(int argc, char *argv[]) { return bar(argv[0]); }
+EOF
+  if compile_object "" ; then
+    avx2_opt="yes"
+  fi
+fi
+
 ########################################
 # check if __[u]int128_t is usable.
 
@@ -1279,6 +1303,7 @@ if test "$tcg" = "yes" ; then
     echo "TCG debug enabled $debug_tcg"
     echo "TCG interpreter   $tcg_interpreter"
 fi
+echo "avx2 optimization $avx2_opt"
 
 config_host_mak="config-host.mak"
 
@@ -1343,6 +1368,10 @@ if test "$tcg" = "yes"; then
   fi
 fi
 
+if test "$avx2_opt" = "yes" ; then
+  echo "CONFIG_AVX2_OPT=y" >> $config_host_mak
+fi
+
 # XXX: suppress that
 if [ "$bsd" = "yes" ] ; then
   echo "CONFIG_BSD=y" >> $config_host_mak

qemu/include/qemu/cpuid.h

@@ -0,0 +1,59 @@
+/* cpuid.h: Macros to identify the properties of an x86 host.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_CPUID_H
+#define QEMU_CPUID_H
+
+#if !defined(CONFIG_CPUID_H) && !defined(_MSC_VER)
+# error "<cpuid.h> is unusable with this compiler"
+#endif
+
+#if defined(CONFIG_CPUID_H) && !defined(_MSC_VER)
+#include <cpuid.h>
+#endif
+
+/* Cover the uses that we have within qemu.  */
+/* ??? Irritating that we have the same information in target/i386/.  */
+
+/* Leaf 1, %edx */
+#ifndef bit_CMOV
+#define bit_CMOV        (1 << 15)
+#endif
+#ifndef bit_SSE2
+#define bit_SSE2        (1 << 26)
+#endif
+
+/* Leaf 1, %ecx */
+#ifndef bit_SSE4_1
+#define bit_SSE4_1      (1 << 19)
+#endif
+#ifndef bit_MOVBE
+#define bit_MOVBE       (1 << 22)
+#endif
+#ifndef bit_OSXSAVE
+#define bit_OSXSAVE     (1 << 27)
+#endif
+#ifndef bit_AVX
+#define bit_AVX         (1 << 28)
+#endif
+
+/* Leaf 7, %ebx */
+#ifndef bit_BMI
+#define bit_BMI         (1 << 3)
+#endif
+#ifndef bit_AVX2
+#define bit_AVX2        (1 << 5)
+#endif
+#ifndef bit_BMI2
+#define bit_BMI2        (1 << 8)
+#endif
+
+/* Leaf 0x80000001, %ecx */
+#ifndef bit_LZCNT
+#define bit_LZCNT       (1 << 5)
+#endif
+
+#endif /* QEMU_CPUID_H */

qemu/target/i386/cpu.c

@@ -29,7 +29,7 @@
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qerror.h"
 
-#include "qapi-visit.h"
+#include "qapi/qapi-visit.h"
 #include "qapi/visitor.h"
 
 #include "hw/hw.h"

qemu/tcg/i386/tcg-target.inc.c

@@ -144,23 +144,14 @@ static const int tcg_target_call_oarg_regs[] = {
 #if defined(CONFIG_CPUID_H)
 #ifdef _MSC_VER
 #include <intrin.h>
-/* %ecx */
-#define bit_MOVBE  (1 << 22)
-/* %edx */
-#define bit_CMOV   (1 << 15)
-/* Extended Features (%eax == 7) */
-#define bit_BMI    (1 <<  3)
-#define bit_BMI2   (1 <<  8)
-#else
-#include <cpuid.h>
 #endif
+#include "qemu/cpuid.h"
 #endif
 
-/* For 32-bit, we are going to attempt to determine at runtime whether cmov
-   is available.  */
+/* For 64-bit, we always know that CMOV is available.  */
 #if TCG_TARGET_REG_BITS == 64
 # define have_cmov 1
-#elif defined(CONFIG_CPUID_H) && defined(bit_CMOV)
+#elif defined(CONFIG_CPUID_H)
 static bool have_cmov;
 #else
 # define have_cmov 0
@@ -173,14 +164,13 @@ bool have_popcnt;
 bool have_avx1;
 bool have_avx2;
 
-#if defined(CONFIG_CPUID_H) && defined(bit_BMI2)
+#ifdef CONFIG_CPUID_H
+static bool have_movbe;
 static bool have_bmi2;
-#else
-static bool have_bmi2 = 0;
-#endif
-#if defined(CONFIG_CPUID_H) && defined(bit_LZCNT)
 static bool have_lzcnt;
 #else
+# define have_movbe 0
+# define have_bmi2 0
 # define have_lzcnt 0
 #endif
 
@@ -3598,14 +3588,10 @@ static void tcg_target_init(TCGContext *s)
            available, we'll use a small forward branch.  */
         have_cmov = (d & bit_CMOV) != 0;
 #endif
-#ifndef have_movbe
         /* MOVBE is only available on Intel Atom and Haswell CPUs, so we
            need to probe for it.  */
         s->have_movbe = (c & bit_MOVBE) != 0;
-#endif
-#ifdef bit_POPCNT
         have_popcnt = (c & bit_POPCNT) != 0;
-#endif
 
         /* There are a number of things we must check before we can be
            sure of not hitting invalid opcode.  */
@@ -3620,15 +3606,13 @@ static void tcg_target_init(TCGContext *s)
     }
 
 // TODO: MSVC-compatible equivalent
-#ifndef have_lzcnt
     max = __get_cpuid_max(0x8000000, 0);
     if (max >= 1) {
         __cpuid(0x80000001, a, b, c, d);
         /* LZCNT was introduced with AMD Barcelona and Intel Haswell CPUs.  */
         have_lzcnt = (c & bit_LZCNT) != 0;
     }
-#endif
-#endif
+#endif /* CONFIG_CPUID_H */
 
     s->tcg_target_available_regs[TCG_TYPE_I32] = ALL_GENERAL_REGS;