crypto: poly1305 - Add a SSE2 SIMD variant for x86_64

Implements an x86_64 assembler driver for the Poly1305 authenticator. This
single block variant holds the 130-bit integer in 5 32-bit words, but uses
SSE to do two multiplications/additions in parallel.

When calling updates with small blocks, the overhead for kernel_fpu_begin/
kernel_fpu_end() negates the perfmance gain. We therefore use the
poly1305-generic fallback for small updates.

For large messages, throughput increases by ~5-10% compared to
poly1305-generic:

testing speed of poly1305 (poly1305-generic)
test  0 (   96 byte blocks,   16 bytes per update,   6 updates): 4080026 opers/sec,  391682496 bytes/sec
test  1 (   96 byte blocks,   32 bytes per update,   3 updates): 6221094 opers/sec,  597225024 bytes/sec
test  2 (   96 byte blocks,   96 bytes per update,   1 updates): 9609750 opers/sec,  922536057 bytes/sec
test  3 (  288 byte blocks,   16 bytes per update,  18 updates): 1459379 opers/sec,  420301267 bytes/sec
test  4 (  288 byte blocks,   32 bytes per update,   9 updates): 2115179 opers/sec,  609171609 bytes/sec
test  5 (  288 byte blocks,  288 bytes per update,   1 updates): 3729874 opers/sec, 1074203856 bytes/sec
test  6 ( 1056 byte blocks,   32 bytes per update,  33 updates):  593000 opers/sec,  626208000 bytes/sec
test  7 ( 1056 byte blocks, 1056 bytes per update,   1 updates): 1081536 opers/sec, 1142102332 bytes/sec
test  8 ( 2080 byte blocks,   32 bytes per update,  65 updates):  302077 opers/sec,  628320576 bytes/sec
test  9 ( 2080 byte blocks, 2080 bytes per update,   1 updates):  554384 opers/sec, 1153120176 bytes/sec
test 10 ( 4128 byte blocks, 4128 bytes per update,   1 updates):  278715 opers/sec, 1150536345 bytes/sec
test 11 ( 8224 byte blocks, 8224 bytes per update,   1 updates):  140202 opers/sec, 1153022070 bytes/sec

testing speed of poly1305 (poly1305-simd)
test  0 (   96 byte blocks,   16 bytes per update,   6 updates): 3790063 opers/sec,  363846076 bytes/sec
test  1 (   96 byte blocks,   32 bytes per update,   3 updates): 5913378 opers/sec,  567684355 bytes/sec
test  2 (   96 byte blocks,   96 bytes per update,   1 updates): 9352574 opers/sec,  897847104 bytes/sec
test  3 (  288 byte blocks,   16 bytes per update,  18 updates): 1362145 opers/sec,  392297990 bytes/sec
test  4 (  288 byte blocks,   32 bytes per update,   9 updates): 2007075 opers/sec,  578037628 bytes/sec
test  5 (  288 byte blocks,  288 bytes per update,   1 updates): 3709811 opers/sec, 1068425798 bytes/sec
test  6 ( 1056 byte blocks,   32 bytes per update,  33 updates):  566272 opers/sec,  597984182 bytes/sec
test  7 ( 1056 byte blocks, 1056 bytes per update,   1 updates): 1111657 opers/sec, 1173910108 bytes/sec
test  8 ( 2080 byte blocks,   32 bytes per update,  65 updates):  288857 opers/sec,  600823808 bytes/sec
test  9 ( 2080 byte blocks, 2080 bytes per update,   1 updates):  590746 opers/sec, 1228751888 bytes/sec
test 10 ( 4128 byte blocks, 4128 bytes per update,   1 updates):  301825 opers/sec, 1245936902 bytes/sec
test 11 ( 8224 byte blocks, 8224 bytes per update,   1 updates):  153075 opers/sec, 1258896201 bytes/sec

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>

1 files changed, 123 insertions, 0 deletions

diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
new file mode 100644
index 000000000000..1e59274a0af3
--- /dev/null
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -0,0 +1,123 @@
+/*
+ * Poly1305 authenticator algorithm, RFC7539, SIMD glue code
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/poly1305.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+#include <asm/simd.h>
+
+asmlinkage void poly1305_block_sse2(u32 *h, const u8 *src,
+				    const u32 *r, unsigned int blocks);
+
+static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx,
+					 const u8 *src, unsigned int srclen)
+{
+	unsigned int blocks, datalen;
+
+	if (unlikely(!dctx->sset)) {
+		datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
+		src += srclen - datalen;
+		srclen = datalen;
+	}
+
+	if (srclen >= POLY1305_BLOCK_SIZE) {
+		blocks = srclen / POLY1305_BLOCK_SIZE;
+		poly1305_block_sse2(dctx->h, src, dctx->r, blocks);
+		srclen -= POLY1305_BLOCK_SIZE * blocks;
+	}
+	return srclen;
+}
+
+static int poly1305_simd_update(struct shash_desc *desc,
+				const u8 *src, unsigned int srclen)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+	unsigned int bytes;
+
+	/* kernel_fpu_begin/end is costly, use fallback for small updates */
+	if (srclen <= 288 || !may_use_simd())
+		return crypto_poly1305_update(desc, src, srclen);
+
+	kernel_fpu_begin();
+
+	if (unlikely(dctx->buflen)) {
+		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		srclen -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_simd_blocks(dctx, dctx->buf,
+					     POLY1305_BLOCK_SIZE);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
+		bytes = poly1305_simd_blocks(dctx, src, srclen);
+		src += srclen - bytes;
+		srclen = bytes;
+	}
+
+	kernel_fpu_end();
+
+	if (unlikely(srclen)) {
+		dctx->buflen = srclen;
+		memcpy(dctx->buf, src, srclen);
+	}
+
+	return 0;
+}
+
+static struct shash_alg alg = {
+	.digestsize	= POLY1305_DIGEST_SIZE,
+	.init		= crypto_poly1305_init,
+	.update		= poly1305_simd_update,
+	.final		= crypto_poly1305_final,
+	.setkey		= crypto_poly1305_setkey,
+	.descsize	= sizeof(struct poly1305_desc_ctx),
+	.base		= {
+		.cra_name		= "poly1305",
+		.cra_driver_name	= "poly1305-simd",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_alignmask		= sizeof(u32) - 1,
+		.cra_blocksize		= POLY1305_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	},
+};
+
+static int __init poly1305_simd_mod_init(void)
+{
+	if (!cpu_has_xmm2)
+		return -ENODEV;
+
+	return crypto_register_shash(&alg);
+}
+
+static void __exit poly1305_simd_mod_exit(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(poly1305_simd_mod_init);
+module_exit(poly1305_simd_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("Poly1305 authenticator");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-simd");