Revert "[CRYPTO] cast6: inline bloat--"

This reverts commit e6ccc727.

Above commit caused performance regression for CAST6. Reverting gives
following increase in tcrypt speed tests (revert-vs-old ratios).

AMD Phenom II X6 1055T, x86-64:

size    ecb             cbc             ctr             lrw             xts
        enc     dec     enc     dec     enc     dec     enc     dec     enc     dec
16b     1.15x   1.17x   1.16x   1.17x   1.16x   1.16x   1.14x   1.19x   1.05x   1.07x
64b     1.19x   1.23x   1.20x   1.22x   1.19x   1.19x   1.16x   1.24x   1.12x   1.12x
256b    1.21x   1.24x   1.22x   1.24x   1.20x   1.20x   1.17x   1.21x   1.16x   1.14x
1kb     1.21x   1.25x   1.22x   1.24x   1.21x   1.21x   1.18x   1.22x   1.17x   1.15x
8kb     1.21x   1.25x   1.22x   1.24x   1.21x   1.21x   1.18x   1.22x   1.18x   1.15x

Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NJussi Kivilinna <jussi.kivilinna@mbnet.fi>
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>

crypto/cast6_generic.c

@@ -370,7 +370,7 @@ static const u8 Tr[4][8] = {
 };
 
 /* forward octave */
-static void W(u32 *key, unsigned int i)
+static inline void W(u32 *key, unsigned int i)
 {
 	u32 I;
 	key[6] ^= F1(key[7], Tr[i % 4][0], Tm[i][0]);
@@ -434,7 +434,7 @@ int cast6_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen)
 EXPORT_SYMBOL_GPL(cast6_setkey);
 
 /*forward quad round*/
-static void Q(u32 *block, u8 *Kr, u32 *Km)
+static inline void Q(u32 *block, u8 *Kr, u32 *Km)
 {
 	u32 I;
 	block[2] ^= F1(block[3], Kr[0], Km[0]);
@@ -444,7 +444,7 @@ static void Q(u32 *block, u8 *Kr, u32 *Km)
 }
 
 /*reverse quad round*/
-static void QBAR(u32 *block, u8 *Kr, u32 *Km)
+static inline void QBAR(u32 *block, u8 *Kr, u32 *Km)
 {
 	u32 I;
 	block[3] ^= F1(block[0], Kr[3], Km[3]);