crypto: poly1305 - move core routines into a separate library

Move the core Poly1305 routines shared between the generic Poly1305
shash driver and the Adiantum and NHPoly1305 drivers into a separate
library so that using just this pieces does not pull in the crypto
API pieces of the generic Poly1305 routine.

In a subsequent patch, we will augment this generic library with
init/update/final routines so that Poyl1305 algorithm can be used
directly without the need for using the crypto API's shash abstraction.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

3 files changed, 164 insertions, 0 deletions

diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index 6a11931ae105..c4882d29879e 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -37,5 +37,8 @@ config CRYPTO_LIB_CHACHA
 config CRYPTO_LIB_DES
 	tristate
 
+config CRYPTO_LIB_POLY1305_GENERIC
+	tristate
+
 config CRYPTO_LIB_SHA256
 	tristate
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index 0ce40604e104..b58ab6843a9d 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -13,5 +13,8 @@ libarc4-y					:= arc4.o
 obj-$(CONFIG_CRYPTO_LIB_DES)			+= libdes.o
 libdes-y					:= des.o
 
+obj-$(CONFIG_CRYPTO_LIB_POLY1305_GENERIC)	+= libpoly1305.o
+libpoly1305-y					:= poly1305.o
+
 obj-$(CONFIG_CRYPTO_LIB_SHA256)			+= libsha256.o
 libsha256-y					:= sha256.o
diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c
new file mode 100644
index 000000000000..f019a57dbc1b
--- /dev/null
+++ b/lib/crypto/poly1305.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Poly1305 authenticator algorithm, RFC7539
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * Based on public domain code by Andrew Moon and Daniel J. Bernstein.
+ */
+
+#include <crypto/internal/poly1305.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <asm/unaligned.h>
+
+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;
+}
+
+void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key)
+{
+	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
+	key->r[0] = (get_unaligned_le32(raw_key +  0) >> 0) & 0x3ffffff;
+	key->r[1] = (get_unaligned_le32(raw_key +  3) >> 2) & 0x3ffff03;
+	key->r[2] = (get_unaligned_le32(raw_key +  6) >> 4) & 0x3ffc0ff;
+	key->r[3] = (get_unaligned_le32(raw_key +  9) >> 6) & 0x3f03fff;
+	key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff;
+}
+EXPORT_SYMBOL_GPL(poly1305_core_setkey);
+
+void poly1305_core_blocks(struct poly1305_state *state,
+			  const struct poly1305_key *key, const void *src,
+			  unsigned int nblocks, 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;
+
+	if (!nblocks)
+		return;
+
+	r0 = key->r[0];
+	r1 = key->r[1];
+	r2 = key->r[2];
+	r3 = key->r[3];
+	r4 = key->r[4];
+
+	s1 = r1 * 5;
+	s2 = r2 * 5;
+	s3 = r3 * 5;
+	s4 = r4 * 5;
+
+	h0 = state->h[0];
+	h1 = state->h[1];
+	h2 = state->h[2];
+	h3 = state->h[3];
+	h4 = state->h[4];
+
+	do {
+		/* h += m[i] */
+		h0 += (get_unaligned_le32(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 += (get_unaligned_le32(src + 12) >> 8) | (hibit << 24);
+
+		/* 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;
+	} while (--nblocks);
+
+	state->h[0] = h0;
+	state->h[1] = h1;
+	state->h[2] = h2;
+	state->h[3] = h3;
+	state->h[4] = h4;
+}
+EXPORT_SYMBOL_GPL(poly1305_core_blocks);
+
+void poly1305_core_emit(const struct poly1305_state *state, void *dst)
+{
+	u32 h0, h1, h2, h3, h4;
+	u32 g0, g1, g2, g3, g4;
+	u32 mask;
+
+	/* fully carry h */
+	h0 = state->h[0];
+	h1 = state->h[1];
+	h2 = state->h[2];
+	h3 = state->h[3];
+	h4 = state->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) */
+	put_unaligned_le32((h0 >>  0) | (h1 << 26), dst +  0);
+	put_unaligned_le32((h1 >>  6) | (h2 << 20), dst +  4);
+	put_unaligned_le32((h2 >> 12) | (h3 << 14), dst +  8);
+	put_unaligned_le32((h3 >> 18) | (h4 <<  8), dst + 12);
+}
+EXPORT_SYMBOL_GPL(poly1305_core_emit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");