crypto: chacha20 - Add an eight block AVX2 variant for x86_64

Extends the x86_64 ChaCha20 implementation by a function processing eight
ChaCha20 blocks in parallel using AVX2.

For large messages, throughput increases by ~55-70% compared to four block
SSSE3:

testing speed of chacha20 (chacha20-simd) encryption
test 0 (256 bit key, 16 byte blocks): 42249230 operations in 10 seconds (675987680 bytes)
test 1 (256 bit key, 64 byte blocks): 46441641 operations in 10 seconds (2972265024 bytes)
test 2 (256 bit key, 256 byte blocks): 33028112 operations in 10 seconds (8455196672 bytes)
test 3 (256 bit key, 1024 byte blocks): 11568759 operations in 10 seconds (11846409216 bytes)
test 4 (256 bit key, 8192 byte blocks): 1448761 operations in 10 seconds (11868250112 bytes)

testing speed of chacha20 (chacha20-simd) encryption
test 0 (256 bit key, 16 byte blocks): 41999675 operations in 10 seconds (671994800 bytes)
test 1 (256 bit key, 64 byte blocks): 45805908 operations in 10 seconds (2931578112 bytes)
test 2 (256 bit key, 256 byte blocks): 32814947 operations in 10 seconds (8400626432 bytes)
test 3 (256 bit key, 1024 byte blocks): 19777167 operations in 10 seconds (20251819008 bytes)
test 4 (256 bit key, 8192 byte blocks): 2279321 operations in 10 seconds (18672197632 bytes)

Benchmark results from a Core i5-4670T.
Signed-off-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/x86/crypto/Makefile

@@ -77,6 +77,7 @@ endif
 
 ifeq ($(avx2_supported),yes)
 	camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o
+	chacha20-x86_64-y += chacha20-avx2-x86_64.o
 	serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
 endif
 

arch/x86/crypto/chacha20_glue.c

@@ -21,12 +21,27 @@
 
 asmlinkage void chacha20_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src);
 asmlinkage void chacha20_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src);
+#ifdef CONFIG_AS_AVX2
+asmlinkage void chacha20_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src);
+static bool chacha20_use_avx2;
+#endif
 
 static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src,
 			    unsigned int bytes)
 {
 	u8 buf[CHACHA20_BLOCK_SIZE];
 
+#ifdef CONFIG_AS_AVX2
+	if (chacha20_use_avx2) {
+		while (bytes >= CHACHA20_BLOCK_SIZE * 8) {
+			chacha20_8block_xor_avx2(state, dst, src);
+			bytes -= CHACHA20_BLOCK_SIZE * 8;
+			src += CHACHA20_BLOCK_SIZE * 8;
+			dst += CHACHA20_BLOCK_SIZE * 8;
+			state[12] += 8;
+		}
+	}
+#endif
 	while (bytes >= CHACHA20_BLOCK_SIZE * 4) {
 		chacha20_4block_xor_ssse3(state, dst, src);
 		bytes -= CHACHA20_BLOCK_SIZE * 4;
@@ -113,6 +128,10 @@ static int __init chacha20_simd_mod_init(void)
 	if (!cpu_has_ssse3)
 		return -ENODEV;
 
+#ifdef CONFIG_AS_AVX2
+	chacha20_use_avx2 = cpu_has_avx && cpu_has_avx2 &&
+			    cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL);
+#endif
 	return crypto_register_alg(&alg);
 }
 

crypto/Kconfig

@@ -1214,7 +1214,7 @@ config CRYPTO_CHACHA20
 	  <http://cr.yp.to/chacha/chacha-20080128.pdf>
 
 config CRYPTO_CHACHA20_X86_64
-	tristate "ChaCha20 cipher algorithm (x86_64/SSSE3)"
+	tristate "ChaCha20 cipher algorithm (x86_64/SSSE3/AVX2)"
 	depends on X86 && 64BIT
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_CHACHA20