Initial commit

2 files changed, 292 insertions, 0 deletions

diff --git a/Makefile b/Makefile
new file mode 100644
index 0000000..526c462
--- /dev/null
+++ b/Makefile
@@ -0,0 +1,14 @@
+obj-m := polybench.o
+KERNELDIR ?= /lib/modules/$(shell uname -r)/build
+PWD := $(shell pwd)
+
+all: polybench.ko
+polybench.ko: polybench.c
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) modules
+clean:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) clean
+run: all
+	@sudo insmod polybench.ko 2>/dev/null || true
+	@dmesg | grep "poly1305 benchmark:" | tail -n 1
+
+.PHONY: all clean run
diff --git a/polybench.c b/polybench.c
new file mode 100644
index 0000000..80eb9df
--- /dev/null
+++ b/polybench.c
@@ -0,0 +1,278 @@
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <asm/unaligned.h>
+
+#define USE_FIRST_METHOD
+
+#define POLY1305_BLOCK_SIZE	16
+#define POLY1305_KEY_SIZE	32
+#define POLY1305_MAC_SIZE	16
+
+struct poly1305_ctx {
+	/* key */
+	u32 r[5];
+	/* finalize key */
+	u32 s[4];
+	/* accumulator */
+	u32 h[5];
+	/* partial buffer */
+	u8 buf[POLY1305_BLOCK_SIZE];
+	/* bytes used in partial buffer */
+	unsigned int buflen;
+};
+
+static inline u32 le32_to_cpuvp(const void *p)
+{
+	return le32_to_cpup(p);
+}
+
+static inline u64 mlt(u64 a, u64 b)
+{
+	return a * b;
+}
+
+static inline u32 sr(u64 v, u_char n)
+{
+	return v >> n;
+}
+
+static inline u32 and(u32 v, u32 mask)
+{
+	return v & mask;
+}
+
+static void poly1305_init(struct poly1305_ctx *ctx, const u8 key[static POLY1305_KEY_SIZE])
+{
+#ifndef USE_FIRST_METHOD
+	u32 t0, t1, t2, t3;
+#endif
+	memset(ctx, 0, sizeof(struct poly1305_ctx));
+	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
+#ifdef USE_FIRST_METHOD
+	ctx->r[0] = (le32_to_cpuvp(key +  0) >> 0) & 0x3ffffff;
+	ctx->r[1] = (get_unaligned_le32(key +  3) >> 2) & 0x3ffff03;
+	ctx->r[2] = (get_unaligned_le32(key +  6) >> 4) & 0x3ffc0ff;
+	ctx->r[3] = (get_unaligned_le32(key +  9) >> 6) & 0x3f03fff;
+	ctx->r[4] = (le32_to_cpuvp(key + 12) >> 8) & 0x00fffff;
+#else
+	t0 = le32_to_cpuvp(key +  0);
+	t1 = le32_to_cpuvp(key +  4);
+	t2 = le32_to_cpuvp(key +  8);
+	t3 = le32_to_cpuvp(key + 12);
+	ctx->r[0] = t0 & 0x3ffffff; t0 >>= 26; t0 |= t1 << 6;
+	ctx->r[1] = t0 & 0x3ffff03; t1 >>= 20; t1 |= t2 << 12;
+	ctx->r[2] = t1 & 0x3ffc0ff; t2 >>= 14; t2 |= t3 << 18;
+	ctx->r[3] = t2 & 0x3f03fff; t3 >>= 8;
+	ctx->r[4] = t3 & 0x00fffff;
+#endif
+	ctx->s[0] = le32_to_cpuvp(key +  16);
+	ctx->s[1] = le32_to_cpuvp(key +  20);
+	ctx->s[2] = le32_to_cpuvp(key +  24);
+	ctx->s[3] = le32_to_cpuvp(key +  28);
+}
+
+static unsigned int poly1305_generic_blocks(struct poly1305_ctx *ctx, const u8 *src, unsigned int srclen, u32 hibit)
+{
+	u32 r0, r1, r2, r3, r4;
+	u32 s1, s2, s3, s4;
+	u32 h0, h1, h2, h3, h4;
+	u64 d0, d1, d2, d3, d4;
+#ifndef USE_FIRST_METHOD
+	u32 t0, t1, t2, t3;
+#endif
+
+	r0 = ctx->r[0];
+	r1 = ctx->r[1];
+	r2 = ctx->r[2];
+	r3 = ctx->r[3];
+	r4 = ctx->r[4];
+
+	s1 = r1 * 5;
+	s2 = r2 * 5;
+	s3 = r3 * 5;
+	s4 = r4 * 5;
+
+	h0 = ctx->h[0];
+	h1 = ctx->h[1];
+	h2 = ctx->h[2];
+	h3 = ctx->h[3];
+	h4 = ctx->h[4];
+
+	while (likely(srclen >= POLY1305_BLOCK_SIZE)) {
+		/* h += m[i] */
+#ifdef USE_FIRST_METHOD
+		h0 += (le32_to_cpuvp(src +  0) >> 0) & 0x3ffffff;
+		h1 += (get_unaligned_le32(src +  3) >> 2) & 0x3ffffff;
+		h2 += (get_unaligned_le32(src +  6) >> 4) & 0x3ffffff;
+		h3 += (get_unaligned_le32(src +  9) >> 6) & 0x3ffffff;
+		h4 += (le32_to_cpuvp(src + 12) >> 8) | hibit;
+#else
+		t0 = le32_to_cpuvp(src +  0);
+		t1 = le32_to_cpuvp(src +  4);
+		t2 = le32_to_cpuvp(src +  8);
+		t3 = le32_to_cpuvp(src + 12);
+		h0 += t0 & 0x3ffffff;
+		h1 += sr((((u64)t1 << 32) | t0), 26) & 0x3ffffff;
+		h2 += sr((((u64)t2 << 32) | t1), 20) & 0x3ffffff;
+		h3 += sr((((u64)t3 << 32) | t2), 14) & 0x3ffffff;
+		h4 += (t3 >> 8) | hibit;
+#endif
+
+		/* h *= r */
+		d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) + mlt(h3, s2) + mlt(h4, s1);
+		d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) + mlt(h3, s3) + mlt(h4, s2);
+		d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) + mlt(h3, s4) + mlt(h4, s3);
+		d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) + mlt(h3, r0) + mlt(h4, s4);
+		d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) + mlt(h3, r1) + mlt(h4, r0);
+
+		/* (partial) h %= p */
+		d1 += sr(d0, 26);     h0 = and(d0, 0x3ffffff);
+		d2 += sr(d1, 26);     h1 = and(d1, 0x3ffffff);
+		d3 += sr(d2, 26);     h2 = and(d2, 0x3ffffff);
+		d4 += sr(d3, 26);     h3 = and(d3, 0x3ffffff);
+		h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff);
+		h1 += h0 >> 26;       h0 = h0 & 0x3ffffff;
+
+		src += POLY1305_BLOCK_SIZE;
+		srclen -= POLY1305_BLOCK_SIZE;
+	}
+
+	ctx->h[0] = h0;
+	ctx->h[1] = h1;
+	ctx->h[2] = h2;
+	ctx->h[3] = h3;
+	ctx->h[4] = h4;
+
+	return srclen;
+}
+
+static void poly1305_update(struct poly1305_ctx *ctx, const u8 *src, unsigned int srclen)
+{
+	unsigned int bytes;
+
+	if (unlikely(ctx->buflen)) {
+		bytes = min(srclen, POLY1305_BLOCK_SIZE - ctx->buflen);
+		memcpy(ctx->buf + ctx->buflen, src, bytes);
+		src += bytes;
+		srclen -= bytes;
+		ctx->buflen += bytes;
+
+		if (ctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_generic_blocks(ctx, ctx->buf, POLY1305_BLOCK_SIZE, 1 << 24);
+			ctx->buflen = 0;
+		}
+	}
+
+	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
+		bytes = poly1305_generic_blocks(ctx, src, srclen, 1 << 24);
+		src += srclen - bytes;
+		srclen = bytes;
+	}
+
+	if (unlikely(srclen)) {
+		ctx->buflen = srclen;
+		memcpy(ctx->buf, src, srclen);
+	}
+}
+
+static void poly1305_finish(struct poly1305_ctx *ctx, u8 *dst)
+{
+	__le32 *mac = (__le32 *)dst;
+	u32 h0, h1, h2, h3, h4;
+	u32 g0, g1, g2, g3, g4;
+	u32 mask;
+	u64 f = 0;
+
+	if (unlikely(ctx->buflen)) {
+		ctx->buf[ctx->buflen++] = 1;
+		memset(ctx->buf + ctx->buflen, 0, POLY1305_BLOCK_SIZE - ctx->buflen);
+		poly1305_generic_blocks(ctx, ctx->buf, POLY1305_BLOCK_SIZE, 0);
+	}
+
+	/* fully carry h */
+	h0 = ctx->h[0];
+	h1 = ctx->h[1];
+	h2 = ctx->h[2];
+	h3 = ctx->h[3];
+	h4 = ctx->h[4];
+
+	h2 += (h1 >> 26);     h1 = h1 & 0x3ffffff;
+	h3 += (h2 >> 26);     h2 = h2 & 0x3ffffff;
+	h4 += (h3 >> 26);     h3 = h3 & 0x3ffffff;
+	h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff;
+	h1 += (h0 >> 26);     h0 = h0 & 0x3ffffff;
+
+	/* compute h + -p */
+	g0 = h0 + 5;
+	g1 = h1 + (g0 >> 26);             g0 &= 0x3ffffff;
+	g2 = h2 + (g1 >> 26);             g1 &= 0x3ffffff;
+	g3 = h3 + (g2 >> 26);             g2 &= 0x3ffffff;
+	g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff;
+
+	/* select h if h < p, or h + -p if h >= p */
+	mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1;
+	g0 &= mask;
+	g1 &= mask;
+	g2 &= mask;
+	g3 &= mask;
+	g4 &= mask;
+	mask = ~mask;
+	h0 = (h0 & mask) | g0;
+	h1 = (h1 & mask) | g1;
+	h2 = (h2 & mask) | g2;
+	h3 = (h3 & mask) | g3;
+	h4 = (h4 & mask) | g4;
+
+	/* h = h % (2^128) */
+	h0 = (h0 >>  0) | (h1 << 26);
+	h1 = (h1 >>  6) | (h2 << 20);
+	h2 = (h2 >> 12) | (h3 << 14);
+	h3 = (h3 >> 18) | (h4 <<  8);
+
+	/* mac = (h + s) % (2^128) */
+	f = (f >> 32) + h0 + ctx->s[0]; mac[0] = cpu_to_le32(f);
+	f = (f >> 32) + h1 + ctx->s[1]; mac[1] = cpu_to_le32(f);
+	f = (f >> 32) + h2 + ctx->s[2]; mac[2] = cpu_to_le32(f);
+	f = (f >> 32) + h3 + ctx->s[3]; mac[3] = cpu_to_le32(f);
+}
+
+static int __init mod_init(void)
+{
+	ktime_t start;
+	s64 elapsed_ns;
+	unsigned int i, j;
+	u8 key[POLY1305_KEY_SIZE];
+	u8 data[POLY1305_BLOCK_SIZE];
+	u8 big_data[8 * POLY1305_BLOCK_SIZE];
+	u8 output[POLY1305_MAC_SIZE];
+	struct poly1305_ctx ctx;
+
+	get_random_bytes(key, POLY1305_KEY_SIZE);
+	get_random_bytes(data, POLY1305_BLOCK_SIZE);
+	get_random_bytes(big_data, 8 * POLY1305_BLOCK_SIZE);
+
+	start = ktime_get();
+	for (i = 0; i < 4096 * 128; ++i) {
+		poly1305_init(&ctx, key);
+		for (j = 0; j < 128; ++j) {
+			poly1305_update(&ctx, data, POLY1305_BLOCK_SIZE);
+			poly1305_update(&ctx, big_data, 8 * POLY1305_BLOCK_SIZE);
+		}
+		poly1305_finish(&ctx, output);
+	}
+	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), start));
+
+	pr_info("poly1305 benchmark: %lld nanoseconds\n", elapsed_ns);
+	return -EINVAL; // We don't actually want to insert this module...
+}
+static void __exit mod_exit(void)
+{
+}
+
+module_init(mod_init);
+module_exit(mod_exit);
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Poly1305 Generic C Benchmarker");
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");