crypto: Add generic 64-bit carry-less multiply routine

Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

crypto/clmul.c

@@ -92,3 +92,20 @@ uint64_t clmul_32(uint32_t n, uint32_t m32)
     }
     return r;
 }
+
+Int128 clmul_64_gen(uint64_t n, uint64_t m)
+{
+    uint64_t rl = 0, rh = 0;
+
+    /* Bit 0 can only influence the low 64-bit result.  */
+    if (n & 1) {
+        rl = m;
+    }
+
+    for (int i = 1; i < 64; ++i) {
+        uint64_t mask = -((n >> i) & 1);
+        rl ^= (m << i) & mask;
+        rh ^= (m >> (64 - i)) & mask;
+    }
+    return int128_make128(rl, rh);
+}

host/include/generic/host/crypto/clmul.h

@@ -0,0 +1,15 @@
+/*
+ * No host specific carry-less multiply acceleration.
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef GENERIC_HOST_CRYPTO_CLMUL_H
+#define GENERIC_HOST_CRYPTO_CLMUL_H
+
+#define HAVE_CLMUL_ACCEL  false
+#define ATTR_CLMUL_ACCEL
+
+Int128 clmul_64_accel(uint64_t, uint64_t)
+    QEMU_ERROR("unsupported accel");
+
+#endif /* GENERIC_HOST_CRYPTO_CLMUL_H */

include/crypto/clmul.h

@@ -8,6 +8,9 @@
 #ifndef CRYPTO_CLMUL_H
 #define CRYPTO_CLMUL_H
 
+#include "qemu/int128.h"
+#include "host/crypto/clmul.h"
+
 /**
  * clmul_8x8_low:
  *
@@ -61,4 +64,20 @@ uint64_t clmul_16x2_odd(uint64_t, uint64_t);
  */
 uint64_t clmul_32(uint32_t, uint32_t);
 
+/**
+ * clmul_64:
+ *
+ * Perform a 64x64->128 carry-less multiply.
+ */
+Int128 clmul_64_gen(uint64_t, uint64_t);
+
+static inline Int128 clmul_64(uint64_t a, uint64_t b)
+{
+    if (HAVE_CLMUL_ACCEL) {
+        return clmul_64_accel(a, b);
+    } else {
+        return clmul_64_gen(a, b);
+    }
+}
+
 #endif /* CRYPTO_CLMUL_H */