Aksal/nuttx
3
1
Fork 1
mirror of https://github.com/apache/nuttx.git synced 2026-08-01 20:28:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2
nuttx/crypto/chacha_private.h
makejian bdd68ed1e5 crypto: Add ChaCha20/ChaCha20-Poly1305 to /dev/crypto, fix RFC 8439 nonce. 
Expose the ChaCha20 stream cipher and the ChaCha20-Poly1305 AEAD through
the OCF crypto framework (/dev/crypto) so applications such as an SSH
server (chacha20-poly1305) can use them directly, and fix the underlying
ChaCha nonce/counter layout so both match RFC 8439.

RFC 8439 nonce layout fix
-------------------------
chacha_ivsetup() previously used the original DJB layout: a 64-bit block
counter (input[12..13]) followed by a 64-bit nonce (input[14..15]). RFC
8439 defines a 32-bit block counter (input[12]) and a 96-bit / 12-byte
nonce (input[13..15]). With the old layout the existing ChaCha20-Poly1305
AEAD could not reproduce the RFC 8439 test vectors (the last 4 bytes of a
12-byte nonce were consumed as the high half of the counter). This
commit switches chacha_ivsetup() to the RFC 8439 layout and updates the
ChaCha20-Poly1305 one-shot helpers to pass a 12-byte nonce accordingly.

Standalone ChaCha20 on the unified enc path
-------------------------------------------
Instead of introducing a separate multi-buffer stream path (parallel
encrypt_multi/decrypt_multi callbacks), extend the existing enc_xform
encrypt/decrypt callback signature with a length argument:

  void (*encrypt)(caddr_t, FAR uint8_t *, size_t len);
  void (*decrypt)(caddr_t, FAR uint8_t *, size_t len);

With that single change every cipher, block or stream, flows through the
same swcr_encdec path. swcr_encdec already handles a short final block
via buflen = MIN(i, blocksize), so arbitrary-length data works without a
second code path. This is exactly how the existing stream ciphers
(AES-CTR/OFB/CFB) already behave: the cipher keeps its own counter in the
context and swcr_encdec feeds it whole blocks (only the last one may be
shorter). chacha20_crypt likewise relies on the underlying chacha state
block counter (input[12]) to continue the keystream across calls, so no
per-call keystream caching is needed.

  * chacha_private.h: chacha_ivsetup uses a 4-byte counter and a 12-byte
    nonce (RFC 8439).
  * chachapoly.c / chachapoly.h: split reinit into chacha20_reinit (raw,
    counter 0) and chachapoly_reinit (AEAD, counter 1); chacha20_crypt
    takes a length and encrypts it in one pass, mirroring aes_ctr_crypt;
    12-byte nonce for the one-shot AEAD helpers.
  * xform.h / xform.c: add size_t len to encrypt/decrypt; add
    enc_xform_chacha20 (blocksize 64, 12-byte IV).
  * cryptodev.c / cryptosoft.c: register CRYPTO_CHACHA20 as a txform
    cipher, route new sessions to enc_xform_chacha20, feed the AEAD AAD
    through crp_aad/crp_aadlen, and handle the short final block in
    swcr_encdec.
  * cryptodev.h: add CRYPTO_CHACHA20; bump EALG_MAX_BLOCK_LEN to 64.

This keeps all ciphers on one uniform path instead of maintaining two,
and any future stream cipher drops in with just an xform table entry.

Impact: extends an internal kernel callback signature (enc_xform
encrypt/decrypt). All in-tree implementations are updated in the same
commit and the user-facing /dev/crypto ABI is unchanged, so this is
self-contained and not a breaking change for existing configurations.

Testing:
  Build host: Ubuntu Linux x86_64, GCC (host sim toolchain)
  Target: sim:crypto (CONFIG_ARCH=sim)
  Ran the crypto test apps. ChaCha20 uses RFC 8439 2.4.2 vectors
  (including a 375-byte multi-block vector exercising cross-block counter
  continuity); ChaCha20-Poly1305 uses the RFC 8439 2.8.2 AEAD vector.
  A full regression of the other ciphers was run to confirm the extended
  encrypt/decrypt signature does not change their behaviour:

    nsh> chacha20
    chacha20: 2/2 vectors passed
    nsh> chachapoly
    OK test vector 0
    chachapoly: 1/1 vectors passed
    nsh> des3cbc          -> all vectors OK
    nsh> aescbc           -> all vectors OK
    nsh> aesctr           -> all vectors OK
    nsh> aesxts           -> 14 vectors OK (encrypt + decrypt)
    nsh> hmac             -> md5 / sha1 / sha256 all success

Signed-off-by: makejian <makejian@xiaomi.com>
2026-07-11 10:19:39 -03:00

336 lines
8.2 KiB
C
Raw Permalink Blame History

/****************************************************************************
* crypto/chacha_private.h
*
* SPDX-License-Identifier: LicenseRef-NuttX-PublicDomain
*
* D. J. Bernstein
* Public domain.
****************************************************************************/
/****************************************************************************
* Included Files
****************************************************************************/
#include <string.h>
#include <sys/types.h>
typedef struct
{
uint32_t input[16]; /* could be compressed */
}
chacha_ctx;
#define U8C(v) (v##U)
#define U32C(v) (v##U)
#define U8V(v) ((uint8_t)(v) & U8C(0xFF))
#define U32V(v) ((uint32_t)(v) & U32C(0xFFFFFFFF))
#define ROTL32(v, n) \
(U32V((v) << (n)) | ((v) >> (32 - (n))))
#define U8TO32_LITTLE(p) \
(((uint32_t)((p)[0])) | \
((uint32_t)((p)[1]) << 8) | \
((uint32_t)((p)[2]) << 16) | \
((uint32_t)((p)[3]) << 24)) \
#define U32TO8_LITTLE(p, v) \
do { \
(p)[0] = U8V((v)); \
(p)[1] = U8V((v) >> 8); \
(p)[2] = U8V((v) >> 16); \
(p)[3] = U8V((v) >> 24); \
} while (0)
#define ROTATE(v, c) (ROTL32(v, c))
#define XOR(v, w) ((v) ^ (w))
#define PLUS(v, w) (U32V((v) + (w)))
#define PLUSONE(v) (PLUS((v), 1))
#define QUARTERROUND(a, b, c, d) \
do \
{ \
a = PLUS(a, b); d = ROTATE(XOR(d, a), 16); \
c = PLUS(c, d); b = ROTATE(XOR(b, c), 12); \
a = PLUS(a, b); d = ROTATE(XOR(d, a), 8); \
c = PLUS(c, d); b = ROTATE(XOR(b, c), 7); \
} \
while (0)
static const char sigma[16] = "expand 32-byte k";
static const char tau[16] = "expand 16-byte k";
static inline void hchacha20(FAR uint32_t *derived_key,
FAR const uint8_t *nonce,
FAR const uint8_t *key)
{
int i;
uint32_t x[] =
{
U8TO32_LITTLE(sigma + 0),
U8TO32_LITTLE(sigma + 4),
U8TO32_LITTLE(sigma + 8),
U8TO32_LITTLE(sigma + 12),
U8TO32_LITTLE(key + 0),
U8TO32_LITTLE(key + 4),
U8TO32_LITTLE(key + 8),
U8TO32_LITTLE(key + 12),
U8TO32_LITTLE(key + 16),
U8TO32_LITTLE(key + 20),
U8TO32_LITTLE(key + 24),
U8TO32_LITTLE(key + 28),
U8TO32_LITTLE(nonce + 0),
U8TO32_LITTLE(nonce + 4),
U8TO32_LITTLE(nonce + 8),
U8TO32_LITTLE(nonce + 12)
};
for (i = 20; i > 0; i -= 2)
{
QUARTERROUND(x[0], x[4], x[8], x[12]);
QUARTERROUND(x[1], x[5], x[9], x[13]);
QUARTERROUND(x[2], x[6], x[10], x[14]);
QUARTERROUND(x[3], x[7], x[11], x[15]);
QUARTERROUND(x[0], x[5], x[10], x[15]);
QUARTERROUND(x[1], x[6], x[11], x[12]);
QUARTERROUND(x[2], x[7], x[8], x[13]);
QUARTERROUND(x[3], x[4], x[9], x[14]);
}
memcpy(derived_key + 0, x + 0, sizeof(uint32_t) * 4);
memcpy(derived_key + 4, x + 12, sizeof(uint32_t) * 4);
}
static void chacha_keysetup(FAR chacha_ctx *x,
FAR const uint8_t *k,
FAR uint32_t kbits)
{
FAR const char *constants;
x->input[4] = U8TO32_LITTLE(k + 0);
x->input[5] = U8TO32_LITTLE(k + 4);
x->input[6] = U8TO32_LITTLE(k + 8);
x->input[7] = U8TO32_LITTLE(k + 12);
if (kbits == 256)
{
/* recommended */
k += 16;
constants = sigma;
}
else
{
/* kbits == 128 */
constants = tau;
}
x->input[8] = U8TO32_LITTLE(k + 0);
x->input[9] = U8TO32_LITTLE(k + 4);
x->input[10] = U8TO32_LITTLE(k + 8);
x->input[11] = U8TO32_LITTLE(k + 12);
x->input[0] = U8TO32_LITTLE(constants + 0);
x->input[1] = U8TO32_LITTLE(constants + 4);
x->input[2] = U8TO32_LITTLE(constants + 8);
x->input[3] = U8TO32_LITTLE(constants + 12);
}
static void chacha_ivsetup(FAR chacha_ctx *x,
FAR const uint8_t *iv,
FAR const uint8_t *counter)
{
x->input[12] = counter == NULL ? 0 : U8TO32_LITTLE(counter + 0);
x->input[13] = U8TO32_LITTLE(iv + 0);
x->input[14] = U8TO32_LITTLE(iv + 4);
x->input[15] = U8TO32_LITTLE(iv + 8);
}
static void chacha_encrypt_bytes(FAR chacha_ctx *x,
FAR const uint8_t *m,
FAR uint8_t *c,
uint32_t bytes)
{
uint32_t x0;
uint32_t x1;
uint32_t x2;
uint32_t x3;
uint32_t x4;
uint32_t x5;
uint32_t x6;
uint32_t x7;
uint32_t x8;
uint32_t x9;
uint32_t x10;
uint32_t x11;
uint32_t x12;
uint32_t x13;
uint32_t x14;
uint32_t x15;
uint32_t j0;
uint32_t j1;
uint32_t j2;
uint32_t j3;
uint32_t j4;
uint32_t j5;
uint32_t j6;
uint32_t j7;
uint32_t j8;
uint32_t j9;
uint32_t j10;
uint32_t j11;
uint32_t j12;
uint32_t j13;
uint32_t j14;
uint32_t j15;
FAR uint8_t *ctarget = NULL;
uint8_t tmp[64];
u_int i;
if (!bytes)
{
return;
}
j0 = x->input[0];
j1 = x->input[1];
j2 = x->input[2];
j3 = x->input[3];
j4 = x->input[4];
j5 = x->input[5];
j6 = x->input[6];
j7 = x->input[7];
j8 = x->input[8];
j9 = x->input[9];
j10 = x->input[10];
j11 = x->input[11];
j12 = x->input[12];
j13 = x->input[13];
j14 = x->input[14];
j15 = x->input[15];
for (; ; )
{
if (bytes < 64)
{
for (i = 0; i < bytes; ++i)
{
tmp[i] = m[i];
}
m = tmp;
ctarget = c;
c = tmp;
}
x0 = j0;
x1 = j1;
x2 = j2;
x3 = j3;
x4 = j4;
x5 = j5;
x6 = j6;
x7 = j7;
x8 = j8;
x9 = j9;
x10 = j10;
x11 = j11;
x12 = j12;
x13 = j13;
x14 = j14;
x15 = j15;
for (i = 20; i > 0; i -= 2)
{
QUARTERROUND(x0, x4, x8, x12);
QUARTERROUND(x1, x5, x9, x13);
QUARTERROUND(x2, x6, x10, x14);
QUARTERROUND(x3, x7, x11, x15);
QUARTERROUND(x0, x5, x10, x15);
QUARTERROUND(x1, x6, x11, x12);
QUARTERROUND(x2, x7, x8, x13);
QUARTERROUND(x3, x4, x9, x14);
}
x0 = PLUS(x0, j0);
x1 = PLUS(x1, j1);
x2 = PLUS(x2, j2);
x3 = PLUS(x3, j3);
x4 = PLUS(x4, j4);
x5 = PLUS(x5, j5);
x6 = PLUS(x6, j6);
x7 = PLUS(x7, j7);
x8 = PLUS(x8, j8);
x9 = PLUS(x9, j9);
x10 = PLUS(x10, j10);
x11 = PLUS(x11, j11);
x12 = PLUS(x12, j12);
x13 = PLUS(x13, j13);
x14 = PLUS(x14, j14);
x15 = PLUS(x15, j15);
#ifndef KEYSTREAM_ONLY
x0 = XOR(x0, U8TO32_LITTLE(m + 0));
x1 = XOR(x1, U8TO32_LITTLE(m + 4));
x2 = XOR(x2, U8TO32_LITTLE(m + 8));
x3 = XOR(x3, U8TO32_LITTLE(m + 12));
x4 = XOR(x4, U8TO32_LITTLE(m + 16));
x5 = XOR(x5, U8TO32_LITTLE(m + 20));
x6 = XOR(x6, U8TO32_LITTLE(m + 24));
x7 = XOR(x7, U8TO32_LITTLE(m + 28));
x8 = XOR(x8, U8TO32_LITTLE(m + 32));
x9 = XOR(x9, U8TO32_LITTLE(m + 36));
x10 = XOR(x10, U8TO32_LITTLE(m + 40));
x11 = XOR(x11, U8TO32_LITTLE(m + 44));
x12 = XOR(x12, U8TO32_LITTLE(m + 48));
x13 = XOR(x13, U8TO32_LITTLE(m + 52));
x14 = XOR(x14, U8TO32_LITTLE(m + 56));
x15 = XOR(x15, U8TO32_LITTLE(m + 60));
#endif
j12 = PLUSONE(j12);
if (!j12)
{
j13 = PLUSONE(j13);
/* stopping at 2^70 bytes per nonce is user's responsibility */
}
U32TO8_LITTLE(c + 0, x0);
U32TO8_LITTLE(c + 4, x1);
U32TO8_LITTLE(c + 8, x2);
U32TO8_LITTLE(c + 12, x3);
U32TO8_LITTLE(c + 16, x4);
U32TO8_LITTLE(c + 20, x5);
U32TO8_LITTLE(c + 24, x6);
U32TO8_LITTLE(c + 28, x7);
U32TO8_LITTLE(c + 32, x8);
U32TO8_LITTLE(c + 36, x9);
U32TO8_LITTLE(c + 40, x10);
U32TO8_LITTLE(c + 44, x11);
U32TO8_LITTLE(c + 48, x12);
U32TO8_LITTLE(c + 52, x13);
U32TO8_LITTLE(c + 56, x14);
U32TO8_LITTLE(c + 60, x15);
if (bytes <= 64)
{
if (bytes < 64)
{
for (i = 0; i < bytes; ++i)
{
ctarget[i] = c[i];
}
}
x->input[12] = j12;
x->input[13] = j13;
return;
}
bytes -= 64;
c += 64;
#ifndef KEYSTREAM_ONLY
m += 64;
#endif
}
}
Reference in a new issue View git blame Copy permalink