crypto: x86 - add more optimized XTS-mode for serpent-avx

This patch adds AVX optimized XTS-mode helper functions/macros and converts
serpent-avx to use the new facilities. Benefits are slightly improved speed
and reduced stack usage as use of temporary IV-array is avoided.

tcrypt results, with Intel i5-2450M:
        enc     dec
16B     1.00x   1.00x
64B     1.00x   1.00x
256B    1.04x   1.06x
1024B   1.09x   1.09x
8192B   1.10x   1.09x

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

2 files changed, 29 insertions, 0 deletions

diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
index e2d65b0..1eef555 100644
--- a/arch/x86/include/asm/crypto/glue_helper.h
+++ b/arch/x86/include/asm/crypto/glue_helper.h
@@ -14,10 +14,13 @@ typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src);
 typedef void (*common_glue_cbc_func_t)(void *ctx, u128 *dst, const u128 *src);
 typedef void (*common_glue_ctr_func_t)(void *ctx, u128 *dst, const u128 *src,
 				       le128 *iv);
+typedef void (*common_glue_xts_func_t)(void *ctx, u128 *dst, const u128 *src,
+				       le128 *iv);
 
 #define GLUE_FUNC_CAST(fn) ((common_glue_func_t)(fn))
 #define GLUE_CBC_FUNC_CAST(fn) ((common_glue_cbc_func_t)(fn))
 #define GLUE_CTR_FUNC_CAST(fn) ((common_glue_ctr_func_t)(fn))
+#define GLUE_XTS_FUNC_CAST(fn) ((common_glue_xts_func_t)(fn))
 
 struct common_glue_func_entry {
 	unsigned int num_blocks; /* number of blocks that @fn will process */
@@ -25,6 +28,7 @@ struct common_glue_func_entry {
 		common_glue_func_t ecb;
 		common_glue_cbc_func_t cbc;
 		common_glue_ctr_func_t ctr;
+		common_glue_xts_func_t xts;
 	} fn_u;
 };
 
@@ -96,6 +100,16 @@ static inline void le128_inc(le128 *i)
 	i->b = cpu_to_le64(b);
 }
 
+static inline void le128_gf128mul_x_ble(le128 *dst, const le128 *src)
+{
+	u64 a = le64_to_cpu(src->a);
+	u64 b = le64_to_cpu(src->b);
+	u64 _tt = ((s64)a >> 63) & 0x87;
+
+	dst->a = cpu_to_le64((a << 1) ^ (b >> 63));
+	dst->b = cpu_to_le64((b << 1) ^ _tt);
+}
+
 extern int glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
 				 struct blkcipher_desc *desc,
 				 struct scatterlist *dst,
@@ -118,4 +132,14 @@ extern int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
 				 struct scatterlist *dst,
 				 struct scatterlist *src, unsigned int nbytes);
 
+extern int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
+				 struct blkcipher_desc *desc,
+				 struct scatterlist *dst,
+				 struct scatterlist *src, unsigned int nbytes,
+				 common_glue_func_t tweak_fn, void *tweak_ctx,
+				 void *crypt_ctx);
+
+extern void glue_xts_crypt_128bit_one(void *ctx, u128 *dst, const u128 *src,
+				      le128 *iv, common_glue_func_t fn);
+
 #endif /* _CRYPTO_GLUE_HELPER_H */
diff --git a/arch/x86/include/asm/crypto/serpent-avx.h b/arch/x86/include/asm/crypto/serpent-avx.h
index 0da1d3e..56e79cc 100644
--- a/arch/x86/include/asm/crypto/serpent-avx.h
+++ b/arch/x86/include/asm/crypto/serpent-avx.h
@@ -16,4 +16,9 @@ asmlinkage void serpent_cbc_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst,
 asmlinkage void serpent_ctr_8way_avx(struct serpent_ctx *ctx, u8 *dst,
 				     const u8 *src, le128 *iv);
 
+asmlinkage void serpent_xts_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+					 const u8 *src, le128 *iv);
+asmlinkage void serpent_xts_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+					 const u8 *src, le128 *iv);
+
 #endif