UPSTREAM: 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>
(cherry picked from commit 48ea8c6ebc96bc0990e12ee1c43d0832c23576bb)
Bug: 152722841
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I1d1ebae722acdb3a908822b8a5b126689e2147c3
This commit is contained in:
Ard Biesheuvel 2019-11-08 13:22:19 +01:00 committed by Greg Kroah-Hartman
parent aff2622b02
commit 4afb116cc1
10 changed files with 249 additions and 216 deletions

View file

@ -11,7 +11,7 @@
#include <crypto/algapi.h>
#include <crypto/internal/hash.h>
#include <crypto/poly1305.h>
#include <crypto/internal/poly1305.h>
#include <linux/crypto.h>
#include <linux/kernel.h>
#include <linux/module.h>

View file

@ -498,12 +498,12 @@ config CRYPTO_KEYWRAP
config CRYPTO_NHPOLY1305
tristate
select CRYPTO_HASH
select CRYPTO_POLY1305
select CRYPTO_LIB_POLY1305_GENERIC
config CRYPTO_ADIANTUM
tristate "Adiantum support"
select CRYPTO_CHACHA20
select CRYPTO_POLY1305
select CRYPTO_LIB_POLY1305_GENERIC
select CRYPTO_NHPOLY1305
help
Adiantum is a tweakable, length-preserving encryption mode
@ -684,6 +684,7 @@ config CRYPTO_GHASH
config CRYPTO_POLY1305
tristate "Poly1305 authenticator algorithm"
select CRYPTO_HASH
select CRYPTO_LIB_POLY1305_GENERIC
help
Poly1305 authenticator algorithm, RFC7539.

View file

@ -33,6 +33,7 @@
#include <crypto/b128ops.h>
#include <crypto/chacha.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/poly1305.h>
#include <crypto/internal/skcipher.h>
#include <crypto/nhpoly1305.h>
#include <crypto/scatterwalk.h>
@ -242,11 +243,11 @@ static void adiantum_hash_header(struct skcipher_request *req)
BUILD_BUG_ON(sizeof(header) % POLY1305_BLOCK_SIZE != 0);
poly1305_core_blocks(&state, &tctx->header_hash_key,
&header, sizeof(header) / POLY1305_BLOCK_SIZE);
&header, sizeof(header) / POLY1305_BLOCK_SIZE, 1);
BUILD_BUG_ON(TWEAK_SIZE % POLY1305_BLOCK_SIZE != 0);
poly1305_core_blocks(&state, &tctx->header_hash_key, req->iv,
TWEAK_SIZE / POLY1305_BLOCK_SIZE);
TWEAK_SIZE / POLY1305_BLOCK_SIZE, 1);
poly1305_core_emit(&state, &rctx->header_hash);
}

View file

@ -33,6 +33,7 @@
#include <asm/unaligned.h>
#include <crypto/algapi.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/poly1305.h>
#include <crypto/nhpoly1305.h>
#include <linux/crypto.h>
#include <linux/kernel.h>
@ -78,7 +79,7 @@ static void process_nh_hash_value(struct nhpoly1305_state *state,
BUILD_BUG_ON(NH_HASH_BYTES % POLY1305_BLOCK_SIZE != 0);
poly1305_core_blocks(&state->poly_state, &key->poly_key, state->nh_hash,
NH_HASH_BYTES / POLY1305_BLOCK_SIZE);
NH_HASH_BYTES / POLY1305_BLOCK_SIZE, 1);
}
/*

View file

@ -13,27 +13,12 @@
#include <crypto/algapi.h>
#include <crypto/internal/hash.h>
#include <crypto/poly1305.h>
#include <crypto/internal/poly1305.h>
#include <linux/crypto.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;
}
int crypto_poly1305_init(struct shash_desc *desc)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
@ -47,124 +32,8 @@ int crypto_poly1305_init(struct shash_desc *desc)
}
EXPORT_SYMBOL_GPL(crypto_poly1305_init);
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);
/*
* Poly1305 requires a unique key for each tag, which implies that we can't set
* it on the tfm that gets accessed by multiple users simultaneously. Instead we
* expect the key as the first 32 bytes in the update() call.
*/
unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
const u8 *src, unsigned int srclen)
{
if (!dctx->sset) {
if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
poly1305_core_setkey(&dctx->r, src);
src += POLY1305_BLOCK_SIZE;
srclen -= POLY1305_BLOCK_SIZE;
dctx->rset = true;
}
if (srclen >= POLY1305_BLOCK_SIZE) {
dctx->s[0] = get_unaligned_le32(src + 0);
dctx->s[1] = get_unaligned_le32(src + 4);
dctx->s[2] = get_unaligned_le32(src + 8);
dctx->s[3] = get_unaligned_le32(src + 12);
src += POLY1305_BLOCK_SIZE;
srclen -= POLY1305_BLOCK_SIZE;
dctx->sset = true;
}
}
return srclen;
}
EXPORT_SYMBOL_GPL(crypto_poly1305_setdesckey);
static void poly1305_blocks_internal(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;
/* 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;
}
void poly1305_core_blocks(struct poly1305_state *state,
const struct poly1305_key *key,
const void *src, unsigned int nblocks)
{
poly1305_blocks_internal(state, key, src, nblocks, 1 << 24);
}
EXPORT_SYMBOL_GPL(poly1305_core_blocks);
static void poly1305_blocks(struct poly1305_desc_ctx *dctx,
const u8 *src, unsigned int srclen, u32 hibit)
static void poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
unsigned int srclen)
{
unsigned int datalen;
@ -174,8 +43,8 @@ static void poly1305_blocks(struct poly1305_desc_ctx *dctx,
srclen = datalen;
}
poly1305_blocks_internal(&dctx->h, &dctx->r,
src, srclen / POLY1305_BLOCK_SIZE, hibit);
poly1305_core_blocks(&dctx->h, &dctx->r, src,
srclen / POLY1305_BLOCK_SIZE, 1);
}
int crypto_poly1305_update(struct shash_desc *desc,
@ -193,13 +62,13 @@ int crypto_poly1305_update(struct shash_desc *desc,
if (dctx->buflen == POLY1305_BLOCK_SIZE) {
poly1305_blocks(dctx, dctx->buf,
POLY1305_BLOCK_SIZE, 1 << 24);
POLY1305_BLOCK_SIZE);
dctx->buflen = 0;
}
}
if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
poly1305_blocks(dctx, src, srclen, 1 << 24);
poly1305_blocks(dctx, src, srclen);
src += srclen - (srclen % POLY1305_BLOCK_SIZE);
srclen %= POLY1305_BLOCK_SIZE;
}
@ -213,54 +82,6 @@ int crypto_poly1305_update(struct shash_desc *desc,
}
EXPORT_SYMBOL_GPL(crypto_poly1305_update);
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);
int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
@ -274,7 +95,7 @@ int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
dctx->buf[dctx->buflen++] = 1;
memset(dctx->buf + dctx->buflen, 0,
POLY1305_BLOCK_SIZE - dctx->buflen);
poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 0);
poly1305_core_blocks(&dctx->h, &dctx->r, dctx->buf, 1, 0);
}
poly1305_core_emit(&dctx->h, digest);

View file

@ -0,0 +1,67 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Common values for the Poly1305 algorithm
*/
#ifndef _CRYPTO_INTERNAL_POLY1305_H
#define _CRYPTO_INTERNAL_POLY1305_H
#include <asm/unaligned.h>
#include <linux/types.h>
#include <crypto/poly1305.h>
struct shash_desc;
/*
* Poly1305 core functions. These implement the ε-almost--universal hash
* function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce
* ("s key") at the end. They also only support block-aligned inputs.
*/
void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key);
static inline void poly1305_core_init(struct poly1305_state *state)
{
*state = (struct poly1305_state){};
}
void poly1305_core_blocks(struct poly1305_state *state,
const struct poly1305_key *key, const void *src,
unsigned int nblocks, u32 hibit);
void poly1305_core_emit(const struct poly1305_state *state, void *dst);
/* Crypto API helper functions for the Poly1305 MAC */
int crypto_poly1305_init(struct shash_desc *desc);
int crypto_poly1305_update(struct shash_desc *desc,
const u8 *src, unsigned int srclen);
int crypto_poly1305_final(struct shash_desc *desc, u8 *dst);
/*
* Poly1305 requires a unique key for each tag, which implies that we can't set
* it on the tfm that gets accessed by multiple users simultaneously. Instead we
* expect the key as the first 32 bytes in the update() call.
*/
static inline
unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
const u8 *src, unsigned int srclen)
{
if (!dctx->sset) {
if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
poly1305_core_setkey(&dctx->r, src);
src += POLY1305_BLOCK_SIZE;
srclen -= POLY1305_BLOCK_SIZE;
dctx->rset = true;
}
if (srclen >= POLY1305_BLOCK_SIZE) {
dctx->s[0] = get_unaligned_le32(src + 0);
dctx->s[1] = get_unaligned_le32(src + 4);
dctx->s[2] = get_unaligned_le32(src + 8);
dctx->s[3] = get_unaligned_le32(src + 12);
src += POLY1305_BLOCK_SIZE;
srclen -= POLY1305_BLOCK_SIZE;
dctx->sset = true;
}
}
return srclen;
}
#endif

View file

@ -38,27 +38,4 @@ struct poly1305_desc_ctx {
bool sset;
};
/*
* Poly1305 core functions. These implement the ε-almost--universal hash
* function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce
* ("s key") at the end. They also only support block-aligned inputs.
*/
void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key);
static inline void poly1305_core_init(struct poly1305_state *state)
{
memset(state->h, 0, sizeof(state->h));
}
void poly1305_core_blocks(struct poly1305_state *state,
const struct poly1305_key *key,
const void *src, unsigned int nblocks);
void poly1305_core_emit(const struct poly1305_state *state, void *dst);
/* Crypto API helper functions for the Poly1305 MAC */
int crypto_poly1305_init(struct shash_desc *desc);
unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
const u8 *src, unsigned int srclen);
int crypto_poly1305_update(struct shash_desc *desc,
const u8 *src, unsigned int srclen);
int crypto_poly1305_final(struct shash_desc *desc, u8 *dst);
#endif

View file

@ -27,3 +27,6 @@ config CRYPTO_LIB_CHACHA
Enable the ChaCha library interface. This interface may be fulfilled
by either the generic implementation or an arch-specific one, if one
is available and enabled.
config CRYPTO_LIB_POLY1305_GENERIC
tristate

View file

@ -3,3 +3,7 @@
# chacha is used by the /dev/random driver which is always builtin
obj-y += chacha.o
obj-$(CONFIG_CRYPTO_LIB_CHACHA_GENERIC) += libchacha.o
obj-$(CONFIG_CRYPTO_LIB_POLY1305_GENERIC) += libpoly1305.o
libpoly1305-y := poly1305.o

158
lib/crypto/poly1305.c Normal file
View file

@ -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>");