crypto: aes - AES CTR x86_64 "by8" AVX optimization

This patch introduces "by8" AES CTR mode AVX optimization inspired by
Intel Optimized IPSEC Cryptograhpic library. For additional information,
please see:
http://downloadcenter.intel.com/Detail_Desc.aspx?agr=Y&DwnldID=22972

The functions aes_ctr_enc_128_avx_by8(), aes_ctr_enc_192_avx_by8() and
aes_ctr_enc_256_avx_by8() are adapted from
Intel Optimized IPSEC Cryptographic library. When both AES and AVX features
are enabled in a platform, the glue code in AESNI module overrieds the
existing "by4" CTR mode en/decryption with the "by8"
AES CTR mode en/decryption.

On a Haswell desktop, with turbo disabled and all cpus running
at maximum frequency, the "by8" CTR mode optimization
shows better performance results across data & key sizes
as measured by tcrypt.

The average performance improvement of the "by8" version over the "by4"
version is as follows:

For 128 bit key and data sizes >= 256 bytes, there is a 10-16% improvement.
For 192 bit key and data sizes >= 256 bytes, there is a 20-22% improvement.
For 256 bit key and data sizes >= 256 bytes, there is a 20-25% improvement.

A typical run of tcrypt with AES CTR mode encryption of the "by4" and "by8"
optimization shows the following results:

tcrypt with "by4" AES CTR mode encryption optimization on a Haswell Desktop:
---------------------------------------------------------------------------

testing speed of __ctr-aes-aesni encryption
test 0 (128 bit key, 16 byte blocks): 1 operation in 343 cycles (16 bytes)
test 1 (128 bit key, 64 byte blocks): 1 operation in 336 cycles (64 bytes)
test 2 (128 bit key, 256 byte blocks): 1 operation in 491 cycles (256 bytes)
test 3 (128 bit key, 1024 byte blocks): 1 operation in 1130 cycles (1024 bytes)
test 4 (128 bit key, 8192 byte blocks): 1 operation in 7309 cycles (8192 bytes)
test 5 (192 bit key, 16 byte blocks): 1 operation in 346 cycles (16 bytes)
test 6 (192 bit key, 64 byte blocks): 1 operation in 361 cycles (64 bytes)
test 7 (192 bit key, 256 byte blocks): 1 operation in 543 cycles (256 bytes)
test 8 (192 bit key, 1024 byte blocks): 1 operation in 1321 cycles (1024 bytes)
test 9 (192 bit key, 8192 byte blocks): 1 operation in 9649 cycles (8192 bytes)
test 10 (256 bit key, 16 byte blocks): 1 operation in 369 cycles (16 bytes)
test 11 (256 bit key, 64 byte blocks): 1 operation in 366 cycles (64 bytes)
test 12 (256 bit key, 256 byte blocks): 1 operation in 595 cycles (256 bytes)
test 13 (256 bit key, 1024 byte blocks): 1 operation in 1531 cycles (1024 bytes)
test 14 (256 bit key, 8192 byte blocks): 1 operation in 10522 cycles (8192 bytes)

testing speed of __ctr-aes-aesni decryption
test 0 (128 bit key, 16 byte blocks): 1 operation in 336 cycles (16 bytes)
test 1 (128 bit key, 64 byte blocks): 1 operation in 350 cycles (64 bytes)
test 2 (128 bit key, 256 byte blocks): 1 operation in 487 cycles (256 bytes)
test 3 (128 bit key, 1024 byte blocks): 1 operation in 1129 cycles (1024 bytes)
test 4 (128 bit key, 8192 byte blocks): 1 operation in 7287 cycles (8192 bytes)
test 5 (192 bit key, 16 byte blocks): 1 operation in 350 cycles (16 bytes)
test 6 (192 bit key, 64 byte blocks): 1 operation in 359 cycles (64 bytes)
test 7 (192 bit key, 256 byte blocks): 1 operation in 635 cycles (256 bytes)
test 8 (192 bit key, 1024 byte blocks): 1 operation in 1324 cycles (1024 bytes)
test 9 (192 bit key, 8192 byte blocks): 1 operation in 9595 cycles (8192 bytes)
test 10 (256 bit key, 16 byte blocks): 1 operation in 364 cycles (16 bytes)
test 11 (256 bit key, 64 byte blocks): 1 operation in 377 cycles (64 bytes)
test 12 (256 bit key, 256 byte blocks): 1 operation in 604 cycles (256 bytes)
test 13 (256 bit key, 1024 byte blocks): 1 operation in 1527 cycles (1024 bytes)
test 14 (256 bit key, 8192 byte blocks): 1 operation in 10549 cycles (8192 bytes)

tcrypt with "by8" AES CTR mode encryption optimization on a Haswell Desktop:
---------------------------------------------------------------------------

testing speed of __ctr-aes-aesni encryption
test 0 (128 bit key, 16 byte blocks): 1 operation in 340 cycles (16 bytes)
test 1 (128 bit key, 64 byte blocks): 1 operation in 330 cycles (64 bytes)
test 2 (128 bit key, 256 byte blocks): 1 operation in 450 cycles (256 bytes)
test 3 (128 bit key, 1024 byte blocks): 1 operation in 1043 cycles (1024 bytes)
test 4 (128 bit key, 8192 byte blocks): 1 operation in 6597 cycles (8192 bytes)
test 5 (192 bit key, 16 byte blocks): 1 operation in 339 cycles (16 bytes)
test 6 (192 bit key, 64 byte blocks): 1 operation in 352 cycles (64 bytes)
test 7 (192 bit key, 256 byte blocks): 1 operation in 539 cycles (256 bytes)
test 8 (192 bit key, 1024 byte blocks): 1 operation in 1153 cycles (1024 bytes)
test 9 (192 bit key, 8192 byte blocks): 1 operation in 8458 cycles (8192 bytes)
test 10 (256 bit key, 16 byte blocks): 1 operation in 353 cycles (16 bytes)
test 11 (256 bit key, 64 byte blocks): 1 operation in 360 cycles (64 bytes)
test 12 (256 bit key, 256 byte blocks): 1 operation in 512 cycles (256 bytes)
test 13 (256 bit key, 1024 byte blocks): 1 operation in 1277 cycles (1024 bytes)
test 14 (256 bit key, 8192 byte blocks): 1 operation in 8745 cycles (8192 bytes)

testing speed of __ctr-aes-aesni decryption
test 0 (128 bit key, 16 byte blocks): 1 operation in 348 cycles (16 bytes)
test 1 (128 bit key, 64 byte blocks): 1 operation in 335 cycles (64 bytes)
test 2 (128 bit key, 256 byte blocks): 1 operation in 451 cycles (256 bytes)
test 3 (128 bit key, 1024 byte blocks): 1 operation in 1030 cycles (1024 bytes)
test 4 (128 bit key, 8192 byte blocks): 1 operation in 6611 cycles (8192 bytes)
test 5 (192 bit key, 16 byte blocks): 1 operation in 354 cycles (16 bytes)
test 6 (192 bit key, 64 byte blocks): 1 operation in 346 cycles (64 bytes)
test 7 (192 bit key, 256 byte blocks): 1 operation in 488 cycles (256 bytes)
test 8 (192 bit key, 1024 byte blocks): 1 operation in 1154 cycles (1024 bytes)
test 9 (192 bit key, 8192 byte blocks): 1 operation in 8390 cycles (8192 bytes)
test 10 (256 bit key, 16 byte blocks): 1 operation in 357 cycles (16 bytes)
test 11 (256 bit key, 64 byte blocks): 1 operation in 362 cycles (64 bytes)
test 12 (256 bit key, 256 byte blocks): 1 operation in 515 cycles (256 bytes)
test 13 (256 bit key, 1024 byte blocks): 1 operation in 1284 cycles (1024 bytes)
test 14 (256 bit key, 8192 byte blocks): 1 operation in 8681 cycles (8192 bytes)

crypto: Incorporate feed back to AES CTR mode optimization patch

Specifically, the following:
a) alignment around main loop in aes_ctrby8_avx_x86_64.S
b) .rodata around data constants used in the assembely code.
c) the use of CONFIG_AVX in the glue code.
d) fix up white space.
e) informational message for "by8" AES CTR mode optimization
f) "by8" AES CTR mode optimization can be simply enabled
if the platform supports both AES and AVX features. The
optimization works superbly on Sandybridge as well.

Testing on Haswell shows no performance change since the last.

Testing on Sandybridge shows that the "by8" AES CTR mode optimization
greatly improves performance.

tcrypt log with "by4" AES CTR mode optimization on Sandybridge
--------------------------------------------------------------

testing speed of __ctr-aes-aesni encryption
test 0 (128 bit key, 16 byte blocks): 1 operation in 383 cycles (16 bytes)
test 1 (128 bit key, 64 byte blocks): 1 operation in 408 cycles (64 bytes)
test 2 (128 bit key, 256 byte blocks): 1 operation in 707 cycles (256 bytes)
test 3 (128 bit key, 1024 byte blocks): 1 operation in 1864 cycles (1024 bytes)
test 4 (128 bit key, 8192 byte blocks): 1 operation in 12813 cycles (8192 bytes)
test 5 (192 bit key, 16 byte blocks): 1 operation in 395 cycles (16 bytes)
test 6 (192 bit key, 64 byte blocks): 1 operation in 432 cycles (64 bytes)
test 7 (192 bit key, 256 byte blocks): 1 operation in 780 cycles (256 bytes)
test 8 (192 bit key, 1024 byte blocks): 1 operation in 2132 cycles (1024 bytes)
test 9 (192 bit key, 8192 byte blocks): 1 operation in 15765 cycles (8192 bytes)
test 10 (256 bit key, 16 byte blocks): 1 operation in 416 cycles (16 bytes)
test 11 (256 bit key, 64 byte blocks): 1 operation in 438 cycles (64 bytes)
test 12 (256 bit key, 256 byte blocks): 1 operation in 842 cycles (256 bytes)
test 13 (256 bit key, 1024 byte blocks): 1 operation in 2383 cycles (1024 bytes)
test 14 (256 bit key, 8192 byte blocks): 1 operation in 16945 cycles (8192 bytes)

testing speed of __ctr-aes-aesni decryption
test 0 (128 bit key, 16 byte blocks): 1 operation in 389 cycles (16 bytes)
test 1 (128 bit key, 64 byte blocks): 1 operation in 409 cycles (64 bytes)
test 2 (128 bit key, 256 byte blocks): 1 operation in 704 cycles (256 bytes)
test 3 (128 bit key, 1024 byte blocks): 1 operation in 1865 cycles (1024 bytes)
test 4 (128 bit key, 8192 byte blocks): 1 operation in 12783 cycles (8192 bytes)
test 5 (192 bit key, 16 byte blocks): 1 operation in 409 cycles (16 bytes)
test 6 (192 bit key, 64 byte blocks): 1 operation in 434 cycles (64 bytes)
test 7 (192 bit key, 256 byte blocks): 1 operation in 792 cycles (256 bytes)
test 8 (192 bit key, 1024 byte blocks): 1 operation in 2151 cycles (1024 bytes)
test 9 (192 bit key, 8192 byte blocks): 1 operation in 15804 cycles (8192 bytes)
test 10 (256 bit key, 16 byte blocks): 1 operation in 421 cycles (16 bytes)
test 11 (256 bit key, 64 byte blocks): 1 operation in 444 cycles (64 bytes)
test 12 (256 bit key, 256 byte blocks): 1 operation in 840 cycles (256 bytes)
test 13 (256 bit key, 1024 byte blocks): 1 operation in 2394 cycles (1024 bytes)
test 14 (256 bit key, 8192 byte blocks): 1 operation in 16928 cycles (8192 bytes)

tcrypt log with "by8" AES CTR mode optimization on Sandybridge
--------------------------------------------------------------

testing speed of __ctr-aes-aesni encryption
test 0 (128 bit key, 16 byte blocks): 1 operation in 383 cycles (16 bytes)
test 1 (128 bit key, 64 byte blocks): 1 operation in 401 cycles (64 bytes)
test 2 (128 bit key, 256 byte blocks): 1 operation in 522 cycles (256 bytes)
test 3 (128 bit key, 1024 byte blocks): 1 operation in 1136 cycles (1024 bytes)
test 4 (128 bit key, 8192 byte blocks): 1 operation in 7046 cycles (8192 bytes)
test 5 (192 bit key, 16 byte blocks): 1 operation in 394 cycles (16 bytes)
test 6 (192 bit key, 64 byte blocks): 1 operation in 418 cycles (64 bytes)
test 7 (192 bit key, 256 byte blocks): 1 operation in 559 cycles (256 bytes)
test 8 (192 bit key, 1024 byte blocks): 1 operation in 1263 cycles (1024 bytes)
test 9 (192 bit key, 8192 byte blocks): 1 operation in 9072 cycles (8192 bytes)
test 10 (256 bit key, 16 byte blocks): 1 operation in 408 cycles (16 bytes)
test 11 (256 bit key, 64 byte blocks): 1 operation in 428 cycles (64 bytes)
test 12 (256 bit key, 256 byte blocks): 1 operation in 595 cycles (256 bytes)
test 13 (256 bit key, 1024 byte blocks): 1 operation in 1385 cycles (1024 bytes)
test 14 (256 bit key, 8192 byte blocks): 1 operation in 9224 cycles (8192 bytes)

testing speed of __ctr-aes-aesni decryption
test 0 (128 bit key, 16 byte blocks): 1 operation in 390 cycles (16 bytes)
test 1 (128 bit key, 64 byte blocks): 1 operation in 402 cycles (64 bytes)
test 2 (128 bit key, 256 byte blocks): 1 operation in 530 cycles (256 bytes)
test 3 (128 bit key, 1024 byte blocks): 1 operation in 1135 cycles (1024 bytes)
test 4 (128 bit key, 8192 byte blocks): 1 operation in 7079 cycles (8192 bytes)
test 5 (192 bit key, 16 byte blocks): 1 operation in 414 cycles (16 bytes)
test 6 (192 bit key, 64 byte blocks): 1 operation in 417 cycles (64 bytes)
test 7 (192 bit key, 256 byte blocks): 1 operation in 572 cycles (256 bytes)
test 8 (192 bit key, 1024 byte blocks): 1 operation in 1312 cycles (1024 bytes)
test 9 (192 bit key, 8192 byte blocks): 1 operation in 9073 cycles (8192 bytes)
test 10 (256 bit key, 16 byte blocks): 1 operation in 415 cycles (16 bytes)
test 11 (256 bit key, 64 byte blocks): 1 operation in 454 cycles (64 bytes)
test 12 (256 bit key, 256 byte blocks): 1 operation in 598 cycles (256 bytes)
test 13 (256 bit key, 1024 byte blocks): 1 operation in 1407 cycles (1024 bytes)
test 14 (256 bit key, 8192 byte blocks): 1 operation in 9288 cycles (8192 bytes)

crypto: Fix redundant checks

a) Fix the redundant check for cpu_has_aes
b) Fix the key length check when invoking the CTR mode "by8"
encryptor/decryptor.

crypto: fix typo in AES ctr mode transform

Signed-off-by: Chandramouli Narayanan <mouli@linux.intel.com>
Reviewed-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 38 insertions, 2 deletions

diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 948ad0e77741..888950f29fd9 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -105,6 +105,9 @@ void crypto_fpu_exit(void);
 #define AVX_GEN4_OPTSIZE 4096
 
 #ifdef CONFIG_X86_64
+
+static void (*aesni_ctr_enc_tfm)(struct crypto_aes_ctx *ctx, u8 *out,
+			      const u8 *in, unsigned int len, u8 *iv);
 asmlinkage void aesni_ctr_enc(struct crypto_aes_ctx *ctx, u8 *out,
 			      const u8 *in, unsigned int len, u8 *iv);
 
@@ -155,6 +158,12 @@ asmlinkage void aesni_gcm_dec(void *ctx, u8 *out,
 
 
 #ifdef CONFIG_AS_AVX
+asmlinkage void aes_ctr_enc_128_avx_by8(const u8 *in, u8 *iv,
+		void *keys, u8 *out, unsigned int num_bytes);
+asmlinkage void aes_ctr_enc_192_avx_by8(const u8 *in, u8 *iv,
+		void *keys, u8 *out, unsigned int num_bytes);
+asmlinkage void aes_ctr_enc_256_avx_by8(const u8 *in, u8 *iv,
+		void *keys, u8 *out, unsigned int num_bytes);
 /*
  * asmlinkage void aesni_gcm_precomp_avx_gen2()
  * gcm_data *my_ctx_data, context data
@@ -472,6 +481,25 @@ static void ctr_crypt_final(struct crypto_aes_ctx *ctx,
 	crypto_inc(ctrblk, AES_BLOCK_SIZE);
 }
 
+#ifdef CONFIG_AS_AVX
+static void aesni_ctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out,
+			      const u8 *in, unsigned int len, u8 *iv)
+{
+	/*
+	 * based on key length, override with the by8 version
+	 * of ctr mode encryption/decryption for improved performance
+	 * aes_set_key_common() ensures that key length is one of
+	 * {128,192,256}
+	 */
+	if (ctx->key_length == AES_KEYSIZE_128)
+		aes_ctr_enc_128_avx_by8(in, iv, (void *)ctx, out, len);
+	else if (ctx->key_length == AES_KEYSIZE_192)
+		aes_ctr_enc_192_avx_by8(in, iv, (void *)ctx, out, len);
+	else
+		aes_ctr_enc_256_avx_by8(in, iv, (void *)ctx, out, len);
+}
+#endif
+
 static int ctr_crypt(struct blkcipher_desc *desc,
 		     struct scatterlist *dst, struct scatterlist *src,
 		     unsigned int nbytes)
@@ -486,8 +514,8 @@ static int ctr_crypt(struct blkcipher_desc *desc,
 
 	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
-		aesni_ctr_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
-			      nbytes & AES_BLOCK_MASK, walk.iv);
+		aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr,
+				  nbytes & AES_BLOCK_MASK, walk.iv);
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
@@ -1493,6 +1521,14 @@ static int __init aesni_init(void)
 		aesni_gcm_enc_tfm = aesni_gcm_enc;
 		aesni_gcm_dec_tfm = aesni_gcm_dec;
 	}
+	aesni_ctr_enc_tfm = aesni_ctr_enc;
+#ifdef CONFIG_AS_AVX
+	if (cpu_has_avx) {
+		/* optimize performance of ctr mode encryption transform */
+		aesni_ctr_enc_tfm = aesni_ctr_enc_avx_tfm;
+		pr_info("AES CTR mode by8 optimization enabled\n");
+	}
+#endif
 #endif
 
 	err = crypto_fpu_init();