[PATCH v2 04/18] target/ppc: Use clmul_8* routines

[Richard Henderson <richard.henderson@linaro.org>]

Use generic routines for 8-bit carry-less multiply.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/ppc/int_helper.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index 834da80fe3..343874863a 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -26,6 +26,7 @@
 #include "exec/helper-proto.h"
 #include "crypto/aes.h"
 #include "crypto/aes-round.h"
+#include "crypto/clmul.h"
 #include "fpu/softfloat.h"
 #include "qapi/error.h"
 #include "qemu/guest-random.h"
@@ -1425,6 +1426,18 @@ void helper_vbpermq(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
 #undef VBPERMQ_INDEX
 #undef VBPERMQ_DW
 
+/*
+ * There is no carry across the two doublewords, so their order does
+ * not matter.  Nor is there partial overlap between registers.
+ */
+void helper_vpmsumb(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
+{
+    for (int i = 0; i < 2; ++i) {
+        uint64_t aa = a->u64[i], bb = b->u64[i];
+        r->u64[i] = clmul_8x4_even(aa, bb) ^ clmul_8x4_odd(aa, bb);
+    }
+}
+
 #define PMSUM(name, srcfld, trgfld, trgtyp)                   \
 void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)  \
 {                                                             \
@@ -1445,7 +1458,6 @@ void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)  \
     }                                                         \
 }
 
-PMSUM(vpmsumb, u8, u16, uint16_t)
 PMSUM(vpmsumh, u16, u32, uint32_t)
 PMSUM(vpmsumw, u32, u64, uint64_t)
 
-- 
2.34.1