Make the pclmulqdq helper AVX ready

Signed-off-by: Paul Brook <paul@nowt.org>
---
 target/i386/ops_sse.h | 31 ++++++++++++++++++++++++-------
 1 file changed, 24 insertions(+), 7 deletions(-)

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 9f388b02b9..b7100fdce1 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -2885,14 +2885,14 @@ target_ulong helper_crc32(uint32_t crc1, target_ulong msg, uint32_t len)
 
 #endif
 
-void glue(helper_pclmulqdq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
-                                    uint32_t ctrl)
+#if SHIFT == 1
+static void clmulq(uint64_t *dest_l, uint64_t *dest_h,
+                          uint64_t a, uint64_t b)
 {
-    uint64_t ah, al, b, resh, resl;
+    uint64_t al, ah, resh, resl;
 
     ah = 0;
-    al = d->Q((ctrl & 1) != 0);
-    b = s->Q((ctrl & 16) != 0);
+    al = a;
     resh = resl = 0;
 
     while (b) {
@@ -2905,8 +2905,25 @@ void glue(helper_pclmulqdq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
         b >>= 1;
     }
 
-    d->Q(0) = resl;
-    d->Q(1) = resh;
+    *dest_l = resl;
+    *dest_h = resh;
+}
+#endif
+
+void glue(helper_pclmulqdq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
+                                    uint32_t ctrl)
+{
+    Reg *v = d;
+    uint64_t a, b;
+
+    a = v->Q((ctrl & 1) != 0);
+    b = s->Q((ctrl & 16) != 0);
+    clmulq(&d->Q(0), &d->Q(1), a, b);
+#if SHIFT == 2
+    a = v->Q(((ctrl & 1) != 0) + 2);
+    b = s->Q(((ctrl & 16) != 0) + 2);
+    clmulq(&d->Q(2), &d->Q(3), a, b);
+#endif
 }
 
 void glue(helper_aesdec, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
-- 
2.36.0