crypto: gf128mul - The x8_ble multiplication functions

It multiply GF(2^128) elements in the ble format.
It will be used by chelsio driver to speed up gf multiplication.
Signed-off-by: NHarsh Jain <harsh@chelsio.com>
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>

crypto/gf128mul.c

@@ -156,6 +156,19 @@ static void gf128mul_x8_bbe(be128 *x)
 	x->b = cpu_to_be64((b << 8) ^ _tt);
 }
 
+void gf128mul_x8_ble(le128 *r, const le128 *x)
+{
+	u64 a = le64_to_cpu(x->a);
+	u64 b = le64_to_cpu(x->b);
+
+	/* equivalent to gf128mul_table_be[b >> 63] (see crypto/gf128mul.c): */
+	u64 _tt = gf128mul_table_be[a >> 56];
+
+	r->a = cpu_to_le64((a << 8) | (b >> 56));
+	r->b = cpu_to_le64((b << 8) ^ _tt);
+}
+EXPORT_SYMBOL(gf128mul_x8_ble);
+
 void gf128mul_lle(be128 *r, const be128 *b)
 {
 	be128 p[8];

include/crypto/gf128mul.h

@@ -227,7 +227,7 @@ struct gf128mul_4k *gf128mul_init_4k_lle(const be128 *g);
 struct gf128mul_4k *gf128mul_init_4k_bbe(const be128 *g);
 void gf128mul_4k_lle(be128 *a, const struct gf128mul_4k *t);
 void gf128mul_4k_bbe(be128 *a, const struct gf128mul_4k *t);
-
+void gf128mul_x8_ble(le128 *r, const le128 *x);
 static inline void gf128mul_free_4k(struct gf128mul_4k *t)
 {
 	kzfree(t);