crypto: aesni-intel - Ported implementation to x86-32
The AES-NI instructions are also available in legacy mode so the 32-bit
architecture may profit from those, too.
To illustrate the performance gain here's a short summary of a dm-crypt
speed test on a Core i7 M620 running at 2.67GHz comparing both assembler
implementations:
x86: i568 aes-ni delta
ECB, 256 bit: 93.8 MB/s 123.3 MB/s +31.4%
CBC, 256 bit: 84.8 MB/s 262.3 MB/s +209.3%
LRW, 256 bit: 108.6 MB/s 222.1 MB/s +104.5%
XTS, 256 bit: 105.0 MB/s 205.5 MB/s +95.7%
Additionally, due to some minor optimizations, the 64-bit version also
got a minor performance gain as seen below:
x86-64: old impl. new impl. delta
ECB, 256 bit: 121.1 MB/s 123.0 MB/s +1.5%
CBC, 256 bit: 285.3 MB/s 290.8 MB/s +1.9%
LRW, 256 bit: 263.7 MB/s 265.3 MB/s +0.6%
XTS, 256 bit: 251.1 MB/s 255.3 MB/s +1.7%
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Reviewed-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 02d349d..8a3b800 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -94,8 +94,10 @@
const u8 *in, unsigned int len, u8 *iv);
asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
const u8 *in, unsigned int len, u8 *iv);
+#ifdef CONFIG_X86_64
asmlinkage void aesni_ctr_enc(struct crypto_aes_ctx *ctx, u8 *out,
const u8 *in, unsigned int len, u8 *iv);
+#endif
/* asmlinkage void aesni_gcm_enc()
* void *ctx, AES Key schedule. Starts on a 16 byte boundary.
@@ -410,6 +412,7 @@
},
};
+#ifdef CONFIG_X86_64
static void ctr_crypt_final(struct crypto_aes_ctx *ctx,
struct blkcipher_walk *walk)
{
@@ -475,6 +478,7 @@
},
},
};
+#endif
static int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
unsigned int key_len)
@@ -622,6 +626,7 @@
},
};
+#ifdef CONFIG_X86_64
static int ablk_ctr_init(struct crypto_tfm *tfm)
{
struct cryptd_ablkcipher *cryptd_tfm;
@@ -698,6 +703,7 @@
},
};
#endif
+#endif
#ifdef HAS_LRW
static int ablk_lrw_init(struct crypto_tfm *tfm)
@@ -1249,18 +1255,20 @@
goto blk_ecb_err;
if ((err = crypto_register_alg(&blk_cbc_alg)))
goto blk_cbc_err;
- if ((err = crypto_register_alg(&blk_ctr_alg)))
- goto blk_ctr_err;
if ((err = crypto_register_alg(&ablk_ecb_alg)))
goto ablk_ecb_err;
if ((err = crypto_register_alg(&ablk_cbc_alg)))
goto ablk_cbc_err;
+#ifdef CONFIG_X86_64
+ if ((err = crypto_register_alg(&blk_ctr_alg)))
+ goto blk_ctr_err;
if ((err = crypto_register_alg(&ablk_ctr_alg)))
goto ablk_ctr_err;
#ifdef HAS_CTR
if ((err = crypto_register_alg(&ablk_rfc3686_ctr_alg)))
goto ablk_rfc3686_ctr_err;
#endif
+#endif
#ifdef HAS_LRW
if ((err = crypto_register_alg(&ablk_lrw_alg)))
goto ablk_lrw_err;
@@ -1296,18 +1304,20 @@
crypto_unregister_alg(&ablk_lrw_alg);
ablk_lrw_err:
#endif
+#ifdef CONFIG_X86_64
#ifdef HAS_CTR
crypto_unregister_alg(&ablk_rfc3686_ctr_alg);
ablk_rfc3686_ctr_err:
#endif
crypto_unregister_alg(&ablk_ctr_alg);
ablk_ctr_err:
+ crypto_unregister_alg(&blk_ctr_alg);
+blk_ctr_err:
+#endif
crypto_unregister_alg(&ablk_cbc_alg);
ablk_cbc_err:
crypto_unregister_alg(&ablk_ecb_alg);
ablk_ecb_err:
- crypto_unregister_alg(&blk_ctr_alg);
-blk_ctr_err:
crypto_unregister_alg(&blk_cbc_alg);
blk_cbc_err:
crypto_unregister_alg(&blk_ecb_alg);
@@ -1332,13 +1342,15 @@
#ifdef HAS_LRW
crypto_unregister_alg(&ablk_lrw_alg);
#endif
+#ifdef CONFIG_X86_64
#ifdef HAS_CTR
crypto_unregister_alg(&ablk_rfc3686_ctr_alg);
#endif
crypto_unregister_alg(&ablk_ctr_alg);
+ crypto_unregister_alg(&blk_ctr_alg);
+#endif
crypto_unregister_alg(&ablk_cbc_alg);
crypto_unregister_alg(&ablk_ecb_alg);
- crypto_unregister_alg(&blk_ctr_alg);
crypto_unregister_alg(&blk_cbc_alg);
crypto_unregister_alg(&blk_ecb_alg);
crypto_unregister_alg(&__aesni_alg);