crypto: poly1305 - Add a two block SSE2 variant for x86_64

Extends the x86_64 SSE2 Poly1305 authenticator by a function processing two
consecutive Poly1305 blocks in parallel using a derived key r^2. Loop
unrolling can be more effectively mapped to SSE instructions, further
increasing throughput.

For large messages, throughput increases by ~45-65% compared to single
block SSE2:

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

testing speed of poly1305 (poly1305-simd)
test  0 (   96 byte blocks,   16 bytes per update,   6 updates): 3809514 opers/sec,  365713411 bytes/sec
test  1 (   96 byte blocks,   32 bytes per update,   3 updates): 5973423 opers/sec,  573448627 bytes/sec
test  2 (   96 byte blocks,   96 bytes per update,   1 updates): 9446779 opers/sec,  906890803 bytes/sec
test  3 (  288 byte blocks,   16 bytes per update,  18 updates): 1364814 opers/sec,  393066691 bytes/sec
test  4 (  288 byte blocks,   32 bytes per update,   9 updates): 2045780 opers/sec,  589184697 bytes/sec
test  5 (  288 byte blocks,  288 bytes per update,   1 updates): 3711946 opers/sec, 1069040592 bytes/sec
test  6 ( 1056 byte blocks,   32 bytes per update,  33 updates):  573686 opers/sec,  605812732 bytes/sec
test  7 ( 1056 byte blocks, 1056 bytes per update,   1 updates): 1647802 opers/sec, 1740079440 bytes/sec
test  8 ( 2080 byte blocks,   32 bytes per update,  65 updates):  292970 opers/sec,  609378224 bytes/sec
test  9 ( 2080 byte blocks, 2080 bytes per update,   1 updates):  943229 opers/sec, 1961916528 bytes/sec
test 10 ( 4128 byte blocks, 4128 bytes per update,   1 updates):  494623 opers/sec, 2041804569 bytes/sec
test 11 ( 8224 byte blocks, 8224 bytes per update,   1 updates):  254045 opers/sec, 2089271014 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, 49 insertions, 5 deletions

diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 1e59274a0af3..b7c33d0d9ef2 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -18,24 +18,68 @@
 #include <asm/fpu/api.h>
 #include <asm/simd.h>
 
+struct poly1305_simd_desc_ctx {
+	struct poly1305_desc_ctx base;
+	/* derived key u set? */
+	bool uset;
+	/* derived Poly1305 key r^2 */
+	u32 u[5];
+};
+
 asmlinkage void poly1305_block_sse2(u32 *h, const u8 *src,
 				    const u32 *r, unsigned int blocks);
+asmlinkage void poly1305_2block_sse2(u32 *h, const u8 *src, const u32 *r,
+				     unsigned int blocks, const u32 *u);
+
+static int poly1305_simd_init(struct shash_desc *desc)
+{
+	struct poly1305_simd_desc_ctx *sctx = shash_desc_ctx(desc);
+
+	sctx->uset = false;
+
+	return crypto_poly1305_init(desc);
+}
+
+static void poly1305_simd_mult(u32 *a, const u32 *b)
+{
+	u8 m[POLY1305_BLOCK_SIZE];
+
+	memset(m, 0, sizeof(m));
+	/* The poly1305 block function adds a hi-bit to the accumulator which
+	 * we don't need for key multiplication; compensate for it. */
+	a[4] -= 1 << 24;
+	poly1305_block_sse2(a, m, b, 1);
+}
 
 static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx,
 					 const u8 *src, unsigned int srclen)
 {
+	struct poly1305_simd_desc_ctx *sctx;
 	unsigned int blocks, datalen;
 
+	BUILD_BUG_ON(offsetof(struct poly1305_simd_desc_ctx, base));
+	sctx = container_of(dctx, struct poly1305_simd_desc_ctx, base);
+
 	if (unlikely(!dctx->sset)) {
 		datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
 		src += srclen - datalen;
 		srclen = datalen;
 	}
 
+	if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) {
+		if (unlikely(!sctx->uset)) {
+			memcpy(sctx->u, dctx->r, sizeof(sctx->u));
+			poly1305_simd_mult(sctx->u, dctx->r);
+			sctx->uset = true;
+		}
+		blocks = srclen / (POLY1305_BLOCK_SIZE * 2);
+		poly1305_2block_sse2(dctx->h, src, dctx->r, blocks, sctx->u);
+		src += POLY1305_BLOCK_SIZE * 2 * blocks;
+		srclen -= POLY1305_BLOCK_SIZE * 2 * blocks;
+	}
 	if (srclen >= POLY1305_BLOCK_SIZE) {
-		blocks = srclen / POLY1305_BLOCK_SIZE;
-		poly1305_block_sse2(dctx->h, src, dctx->r, blocks);
-		srclen -= POLY1305_BLOCK_SIZE * blocks;
+		poly1305_block_sse2(dctx->h, src, dctx->r, 1);
+		srclen -= POLY1305_BLOCK_SIZE;
 	}
 	return srclen;
 }
@@ -84,11 +128,11 @@ static int poly1305_simd_update(struct shash_desc *desc,
 
 static struct shash_alg alg = {
 	.digestsize	= POLY1305_DIGEST_SIZE,
-	.init		= crypto_poly1305_init,
+	.init		= poly1305_simd_init,
 	.update		= poly1305_simd_update,
 	.final		= crypto_poly1305_final,
 	.setkey		= crypto_poly1305_setkey,
-	.descsize	= sizeof(struct poly1305_desc_ctx),
+	.descsize	= sizeof(struct poly1305_simd_desc_ctx),
 	.base		= {
 		.cra_name		= "poly1305",
 		.cra_driver_name	= "poly1305-simd",