aboutsummaryrefslogtreecommitdiffstats
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-02 14:03:25 +0000 ='n193' href='#n193'>193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 8 Nov 2019 13:22:08 +0100
Subject: [PATCH] crypto: chacha - move existing library code into lib/crypto

commit 5fb8ef25803ef33e2eb60b626435828b937bed75 upstream.

Currently, our generic ChaCha implementation consists of a permute
function in lib/chacha.c that operates on the 64-byte ChaCha state
directly [and which is always included into the core kernel since it
is used by the /dev/random driver], and the crypto API plumbing to
expose it as a skcipher.

In order to support in-kernel users that need the ChaCha streamcipher
but have no need [or tolerance] for going through the abstractions of
the crypto API, let's expose the streamcipher bits via a library API
as well, in a way that permits the implementation to be superseded by
an architecture specific one if provided.

So move the streamcipher code into a separate module in lib/crypto,
and expose the init() and crypt() routines to users of the library.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 arch/arm/crypto/chacha-neon-glue.c   |  2 +-
 arch/arm64/crypto/chacha-neon-glue.c |  2 +-
 arch/x86/crypto/chacha_glue.c        |  2 +-
 crypto/Kconfig                       |  1 +
 crypto/chacha_generic.c              | 60 ++--------------------
 include/crypto/chacha.h              | 77 ++++++++++++++++++++++------
 include/crypto/internal/chacha.h     | 53 +++++++++++++++++++
 lib/Makefile                         |  3 +-
 lib/crypto/Kconfig                   | 26 ++++++++++
 lib/crypto/Makefile                  |  4 ++
 lib/{ => crypto}/chacha.c            | 20 ++++----
 lib/crypto/libchacha.c               | 35 +++++++++++++
 12 files changed, 199 insertions(+), 86 deletions(-)
 create mode 100644 include/crypto/internal/chacha.h
 rename lib/{ => crypto}/chacha.c (88%)
 create mode 100644 lib/crypto/libchacha.c

--- a/arch/arm/crypto/chacha-neon-glue.c
+++ b/arch/arm/crypto/chacha-neon-glue.c
@@ -20,7 +20,7 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
--- a/arch/arm64/crypto/chacha-neon-glue.c
+++ b/arch/arm64/crypto/chacha-neon-glue.c
@@ -20,7 +20,7 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -7,7 +7,7 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1393,6 +1393,7 @@ config CRYPTO_SALSA20
 
 config CRYPTO_CHACHA20
 	tristate "ChaCha stream cipher algorithms"
+	select CRYPTO_LIB_CHACHA_GENERIC
 	select CRYPTO_BLKCIPHER
 	help
 	  The ChaCha20, XChaCha20, and XChaCha12 stream cipher algorithms.
--- a/crypto/chacha_generic.c
+++ b/crypto/chacha_generic.c
@@ -8,29 +8,10 @@
 
 #include <asm/unaligned.h>
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/module.h>
 
-static void chacha_docrypt(u32 *state, u8 *dst, const u8 *src,
-			   unsigned int bytes, int nrounds)
-{
-	/* aligned to potentially speed up crypto_xor() */
-	u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long));
-
-	while (bytes >= CHACHA_BLOCK_SIZE) {
-		chacha_block(state, stream, nrounds);
-		crypto_xor_cpy(dst, src, stream, CHACHA_BLOCK_SIZE);
-		bytes -= CHACHA_BLOCK_SIZE;
-		dst += CHACHA_BLOCK_SIZE;
-		src += CHACHA_BLOCK_SIZE;
-	}
-	if (bytes) {
-		chacha_block(state, stream, nrounds);
-		crypto_xor_cpy(dst, src, stream, bytes);
-	}
-}
-
 static int chacha_stream_xor(struct skcipher_request *req,
 			     const struct chacha_ctx *ctx, const u8 *iv)
 {
@@ -48,8 +29,8 @@ static int chacha_stream_xor(struct skci
 		if (nbytes < walk.total)
 			nbytes = round_down(nbytes, CHACHA_BLOCK_SIZE);
 
-		chacha_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
-			       nbytes, ctx->nrounds);
+		chacha_crypt_generic(state, walk.dst.virt.addr,
+				     walk.src.virt.addr, nbytes, ctx->nrounds);
 		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
@@ -58,41 +39,10 @@ static int chacha_stream_xor(struct skci
 
 void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv)
 {
-	state[0]  = 0x61707865; /* "expa" */
-	state[1]  = 0x3320646e; /* "nd 3" */
-	state[2]  = 0x79622d32; /* "2-by" */
-	state[3]  = 0x6b206574; /* "te k" */
-	state[4]  = ctx->key[0];
-	state[5]  = ctx->key[1];
-	state[6]  = ctx->key[2];
-	state[7]  = ctx->key[3];
-	state[8]  = ctx->key[4];
-	state[9]  = ctx->key[5];
-	state[10] = ctx->key[6];
-	state[11] = ctx->key[7];
-	state[12] = get_unaligned_le32(iv +  0);
-	state[13] = get_unaligned_le32(iv +  4);
-	state[14] = get_unaligned_le32(iv +  8);
-	state[15] = get_unaligned_le32(iv + 12);
+	chacha_init_generic(state, ctx->key, iv);
 }
 EXPORT_SYMBOL_GPL(crypto_chacha_init);
 
-static int chacha_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			 unsigned int keysize, int nrounds)
-{
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int i;
-
-	if (keysize != CHACHA_KEY_SIZE)
-		return -EINVAL;
-
-	for (i = 0; i < ARRAY_SIZE(ctx->key); i++)
-		ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32));
-
-	ctx->nrounds = nrounds;
-	return 0;
-}
-
 int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			   unsigned int keysize)
 {
@@ -126,7 +76,7 @@ int crypto_xchacha_crypt(struct skcipher
 
 	/* Compute the subkey given the original key and first 128 nonce bits */
 	crypto_chacha_init(state, ctx, req->iv);
-	hchacha_block(state, subctx.key, ctx->nrounds);
+	hchacha_block_generic(state, subctx.key, ctx->nrounds);
 	subctx.nrounds = ctx->nrounds;
 
 	/* Build the real IV */
--- a/include/crypto/chacha.h
+++ b/include/crypto/chacha.h
@@ -15,9 +15,8 @@
 #ifndef _CRYPTO_CHACHA_H
 #define _CRYPTO_CHACHA_H
 
-#include <crypto/skcipher.h>
+#include <asm/unaligned.h>
 #include <linux/types.h>
-#include <linux/crypto.h>
 
 /* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */
 #define CHACHA_IV_SIZE		16
@@ -29,26 +28,70 @@
 /* 192-bit nonce, then 64-bit stream position */
 #define XCHACHA_IV_SIZE		32
 
-struct chacha_ctx {
-	u32 key[8];
-	int nrounds;
-};
-
-void chacha_block(u32 *state, u8 *stream, int nrounds);
+void chacha_block_generic(u32 *state, u8 *stream, int nrounds);
 static inline void chacha20_block(u32 *state, u8 *stream)
 {
-	chacha_block(state, stream, 20);
+	chacha_block_generic(state, stream, 20);
 }
-void hchacha_block(const u32 *in, u32 *out, int nrounds);
 
-void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv);
+void hchacha_block_arch(const u32 *state, u32 *out, int nrounds);
+void hchacha_block_generic(const u32 *state, u32 *out, int nrounds);
+
+static inline void hchacha_block(const u32 *state, u32 *out, int nrounds)
+{
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA))
+		hchacha_block_arch(state, out, nrounds);
+	else
+		hchacha_block_generic(state, out, nrounds);
+}
 
-int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			   unsigned int keysize);
-int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			   unsigned int keysize);
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv);
+static inline void chacha_init_generic(u32 *state, const u32 *key, const u8 *iv)
+{
+	state[0]  = 0x61707865; /* "expa" */
+	state[1]  = 0x3320646e; /* "nd 3" */
+	state[2]  = 0x79622d32; /* "2-by" */
+	state[3]  = 0x6b206574; /* "te k" */
+	state[4]  = key[0];
+	state[5]  = key[1];
+	state[6]  = key[2];
+	state[7]  = key[3];
+	state[8]  = key[4];
+	state[9]  = key[5];
+	state[10] = key[6];
+	state[11] = key[7];
+	state[12] = get_unaligned_le32(iv +  0);
+	state[13] = get_unaligned_le32(iv +  4);
+	state[14] = get_unaligned_le32(iv +  8);
+	state[15] = get_unaligned_le32(iv + 12);
+}
 
-int crypto_chacha_crypt(struct skcipher_request *req);
-int crypto_xchacha_crypt(struct skcipher_request *req);
+static inline void chacha_init(u32 *state, const u32 *key, const u8 *iv)
+{
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA))
+		chacha_init_arch(state, key, iv);
+	else
+		chacha_init_generic(state, key, iv);
+}
+
+void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src,
+		       unsigned int bytes, int nrounds);
+void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds);
+
+static inline void chacha_crypt(u32 *state, u8 *dst, const u8 *src,
+				unsigned int bytes, int nrounds)
+{
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA))
+		chacha_crypt_arch(state, dst, src, bytes, nrounds);
+	else
+		chacha_crypt_generic(state, dst, src, bytes, nrounds);
+}
+
+static inline void chacha20_crypt(u32 *state, u8 *dst, const u8 *src,
+				  unsigned int bytes)
+{
+	chacha_crypt(state, dst, src, bytes, 20);
+}
 
 #endif /* _CRYPTO_CHACHA_H */
--- /dev/null
+++ b/include/crypto/internal/chacha.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _CRYPTO_INTERNAL_CHACHA_H
+#define _CRYPTO_INTERNAL_CHACHA_H
+
+#include <crypto/chacha.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/crypto.h>
+
+struct chacha_ctx {
+	u32 key[8];
+	int nrounds;
+};
+
+void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv);
+
+static inline int chacha_setkey(struct crypto_skcipher *tfm, const u8 *key,
+				unsigned int keysize, int nrounds)
+{
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int i;
+
+	if (keysize != CHACHA_KEY_SIZE)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(ctx->key); i++)
+		ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32));
+
+	ctx->nrounds = nrounds;
+	return 0;
+}
+
+static inline int chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
+				  unsigned int keysize)
+{
+	return chacha_setkey(tfm, key, keysize, 20);
+}
+
+static int inline chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key,
+				  unsigned int keysize)
+{
+	return chacha_setkey(tfm, key, keysize, 12);
+}
+
+int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			   unsigned int keysize);
+int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			   unsigned int keysize);
+
+int crypto_chacha_crypt(struct skcipher_request *req);
+int crypto_xchacha_crypt(struct skcipher_request *req);
+
+#endif /* _CRYPTO_CHACHA_H */
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -26,8 +26,7 @@ endif
 
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o xarray.o \
-	 idr.o extable.o \
-	 sha1.o chacha.o irq_regs.o argv_split.o \
+	 idr.o extable.o sha1.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -8,6 +8,32 @@ config CRYPTO_LIB_AES
 config CRYPTO_LIB_ARC4
 	tristate
 
+config CRYPTO_ARCH_HAVE_LIB_CHACHA
+	tristate
+	help
+	  Declares whether the architecture provides an arch-specific
+	  accelerated implementation of the ChaCha library interface,
+	  either builtin or as a module.
+
+config CRYPTO_LIB_CHACHA_GENERIC
+	tristate
+	select CRYPTO_ALGAPI
+	help
+	  This symbol can be depended upon by arch implementations of the
+	  ChaCha library interface that require the generic code as a
+	  fallback, e.g., for SIMD implementations. If no arch specific
+	  implementation is enabled, this implementation serves the users
+	  of CRYPTO_LIB_CHACHA.
+
+config CRYPTO_LIB_CHACHA
+	tristate "ChaCha library interface"
+	depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA
+	select CRYPTO_LIB_CHACHA_GENERIC if CRYPTO_ARCH_HAVE_LIB_CHACHA=n
+	help
+	  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_DES
 	tristate
 
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -1,5 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 
+# 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_AES)			+= libaes.o
 libaes-y					:= aes.o
 
--- a/lib/chacha.c
+++ /dev/null
@@ -1,113 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * The "hash function" used as the core of the ChaCha stream cipher (RFC7539)
- *
- * Copyright (C) 2015 Martin Willi
- */
-
-#include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/bitops.h>
-#include <linux/cryptohash.h>
-#include <asm/unaligned.h>
-#include <crypto/chacha.h>
-
-static void chacha_permute(u32 *x, int nrounds)
-{
-	int i;
-
-	/* whitelist the allowed round counts */
-	WARN_ON_ONCE(nrounds != 20 && nrounds != 12);
-
-	for (i = 0; i < nrounds; i += 2) {
-		x[0]  += x[4];    x[12] = rol32(x[12] ^ x[0],  16);
-		x[1]  += x[5];    x[13] = rol32(x[13] ^ x[1],  16);
-		x[2]  += x[6];    x[14] = rol32(x[14] ^ x[2],  16);
-		x[3]  += x[7];    x[15] = rol32(x[15] ^ x[3],  16);
-
-		x[8]  += x[12];   x[4]  = rol32(x[4]  ^ x[8],  12);
-		x[9]  += x[13];   x[5]  = rol32(x[5]  ^ x[9],  12);
-		x[10] += x[14];   x[6]  = rol32(x[6]  ^ x[10], 12);
-		x[11] += x[15];   x[7]  = rol32(x[7]  ^ x[11], 12);
-
-		x[0]  += x[4];    x[12] = rol32(x[12] ^ x[0],   8);
-		x[1]  += x[5];    x[13] = rol32(x[13] ^ x[1],   8);
-		x[2]  += x[6];    x[14] = rol32(x[14] ^ x[2],   8);
-		x[3]  += x[7];    x[15] = rol32(x[15] ^ x[3],   8);
-
-		x[8]  += x[12];   x[4]  = rol32(x[4]  ^ x[8],   7);
-		x[9]  += x[13];   x[5]  = rol32(x[5]  ^ x[9],   7);
-		x[10] += x[14];   x[6]  = rol32(x[6]  ^ x[10],  7);
-		x[11] += x[15];   x[7]  = rol32(x[7]  ^ x[11],  7);
-
-		x[0]  += x[5];    x[15] = rol32(x[15] ^ x[0],  16);
-		x[1]  += x[6];    x[12] = rol32(x[12] ^ x[1],  16);
-		x[2]  += x[7];    x[13] = rol32(x[13] ^ x[2],  16);
-		x[3]  += x[4];    x[14] = rol32(x[14] ^ x[3],  16);
-
-		x[10] += x[15];   x[5]  = rol32(x[5]  ^ x[10], 12);
-		x[11] += x[12];   x[6]  = rol32(x[6]  ^ x[11], 12);
-		x[8]  += x[13];   x[7]  = rol32(x[7]  ^ x[8],  12);
-		x[9]  += x[14];   x[4]  = rol32(x[4]  ^ x[9],  12);
-
-		x[0]  += x[5];    x[15] = rol32(x[15] ^ x[0],   8);
-		x[1]  += x[6];    x[12] = rol32(x[12] ^ x[1],   8);
-		x[2]  += x[7];    x[13] = rol32(x[13] ^ x[2],   8);
-		x[3]  += x[4];    x[14] = rol32(x[14] ^ x[3],   8);
-
-		x[10] += x[15];   x[5]  = rol32(x[5]  ^ x[10],  7);
-		x[11] += x[12];   x[6]  = rol32(x[6]  ^ x[11],  7);
-		x[8]  += x[13];   x[7]  = rol32(x[7]  ^ x[8],   7);
-		x[9]  += x[14];   x[4]  = rol32(x[4]  ^ x[9],   7);
-	}
-}
-
-/**
- * chacha_block - generate one keystream block and increment block counter
- * @state: input state matrix (16 32-bit words)
- * @stream: output keystream block (64 bytes)
- * @nrounds: number of rounds (20 or 12; 20 is recommended)
- *
- * This is the ChaCha core, a function from 64-byte strings to 64-byte strings.
- * The caller has already converted the endianness of the input.  This function
- * also handles incrementing the block counter in the input matrix.
- */
-void chacha_block(u32 *state, u8 *stream, int nrounds)
-{
-	u32 x[16];
-	int i;
-
-	memcpy(x, state, 64);
-
-	chacha_permute(x, nrounds);
-
-	for (i = 0; i < ARRAY_SIZE(x); i++)
-		put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]);
-
-	state[12]++;
-}
-EXPORT_SYMBOL(chacha_block);
-
-/**
- * hchacha_block - abbreviated ChaCha core, for XChaCha
- * @in: input state matrix (16 32-bit words)
- * @out: output (8 32-bit words)
- * @nrounds: number of rounds (20 or 12; 20 is recommended)
- *
- * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step
- * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf).  HChaCha
- * skips the final addition of the initial state, and outputs only certain words
- * of the state.  It should not be used for streaming directly.
- */
-void hchacha_block(const u32 *in, u32 *out, int nrounds)
-{
-	u32 x[16];
-
-	memcpy(x, in, 64);
-
-	chacha_permute(x, nrounds);
-
-	memcpy(&out[0], &x[0], 16);
-	memcpy(&out[4], &x[12], 16);
-}
-EXPORT_SYMBOL(hchacha_block);
--- /dev/null
+++ b/lib/crypto/chacha.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * The "hash function" used as the core of the ChaCha stream cipher (RFC7539)
+ *
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/bitops.h>
+#include <linux/string.h>
+#include <linux/cryptohash.h>
+#include <asm/unaligned.h>
+#include <crypto/chacha.h>
+
+static void chacha_permute(u32 *x, int nrounds)
+{
+	int i;
+
+	/* whitelist the allowed round counts */
+	WARN_ON_ONCE(nrounds != 20 && nrounds != 12);
+
+	for (i = 0; i < nrounds; i += 2) {
+		x[0]  += x[4];    x[12] = rol32(x[12] ^ x[0],  16);
+		x[1]  += x[5];    x[13] = rol32(x[13] ^ x[1],  16);
+		x[2]  += x[6];    x[14] = rol32(x[14] ^ x[2],  16);
+		x[3]  += x[7];    x[15] = rol32(x[15] ^ x[3],  16);
+
+		x[8]  += x[12];   x[4]  = rol32(x[4]  ^ x[8],  12);
+		x[9]  += x[13];   x[5]  = rol32(x[5]  ^ x[9],  12);
+		x[10] += x[14];   x[6]  = rol32(x[6]  ^ x[10], 12);
+		x[11] += x[15];   x[7]  = rol32(x[7]  ^ x[11], 12);
+
+		x[0]  += x[4];    x[12] = rol32(x[12] ^ x[0],   8);
+		x[1]  += x[5];    x[13] = rol32(x[13] ^ x[1],   8);
+		x[2]  += x[6];    x[14] = rol32(x[14] ^ x[2],   8);
+		x[3]  += x[7];    x[15] = rol32(x[15] ^ x[3],   8);
+
+		x[8]  += x[12];   x[4]  = rol32(x[4]  ^ x[8],   7);
+		x[9]  += x[13];   x[5]  = rol32(x[5]  ^ x[9],   7);
+		x[10] += x[14];   x[6]  = rol32(x[6]  ^ x[10],  7);
+		x[11] += x[15];   x[7]  = rol32(x[7]  ^ x[11],  7);
+
+		x[0]  += x[5];    x[15] = rol32(x[15] ^ x[0],  16);
+		x[1]  += x[6];    x[12] = rol32(x[12] ^ x[1],  16);
+		x[2]  += x[7];    x[13] = rol32(x[13] ^ x[2],  16);
+		x[3]  += x[4];    x[14] = rol32(x[14] ^ x[3],  16);
+
+		x[10] += x[15];   x[5]  = rol32(x[5]  ^ x[10], 12);
+		x[11] += x[12];   x[6]  = rol32(x[6]  ^ x[11], 12);
+		x[8]  += x[13];   x[7]  = rol32(x[7]  ^ x[8],  12);
+		x[9]  += x[14];   x[4]  = rol32(x[4]  ^ x[9],  12);
+
+		x[0]  += x[5];    x[15] = rol32(x[15] ^ x[0],   8);
+		x[1]  += x[6];    x[12] = rol32(x[12] ^ x[1],   8);
+		x[2]  += x[7];    x[13] = rol32(x[13] ^ x[2],   8);
+		x[3]  += x[4];    x[14] = rol32(x[14] ^ x[3],   8);
+
+		x[10] += x[15];   x[5]  = rol32(x[5]  ^ x[10],  7);
+		x[11] += x[12];   x[6]  = rol32(x[6]  ^ x[11],  7);
+		x[8]  += x[13];   x[7]  = rol32(x[7]  ^ x[8],   7);
+		x[9]  += x[14];   x[4]  = rol32(x[4]  ^ x[9],   7);
+	}
+}
+
+/**
+ * chacha_block - generate one keystream block and increment block counter
+ * @state: input state matrix (16 32-bit words)
+ * @stream: output keystream block (64 bytes)
+ * @nrounds: number of rounds (20 or 12; 20 is recommended)
+ *
+ * This is the ChaCha core, a function from 64-byte strings to 64-byte strings.
+ * The caller has already converted the endianness of the input.  This function
+ * also handles incrementing the block counter in the input matrix.
+ */
+void chacha_block_generic(u32 *state, u8 *stream, int nrounds)
+{
+	u32 x[16];
+	int i;
+
+	memcpy(x, state, 64);
+
+	chacha_permute(x, nrounds);
+
+	for (i = 0; i < ARRAY_SIZE(x); i++)
+		put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]);
+
+	state[12]++;
+}
+EXPORT_SYMBOL(chacha_block_generic);
+
+/**
+ * hchacha_block_generic - abbreviated ChaCha core, for XChaCha
+ * @state: input state matrix (16 32-bit words)
+ * @out: output (8 32-bit words)
+ * @nrounds: number of rounds (20 or 12; 20 is recommended)
+ *
+ * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step
+ * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf).  HChaCha
+ * skips the final addition of the initial state, and outputs only certain words
+ * of the state.  It should not be used for streaming directly.
+ */
+void hchacha_block_generic(const u32 *state, u32 *stream, int nrounds)
+{
+	u32 x[16];
+
+	memcpy(x, state, 64);
+
+	chacha_permute(x, nrounds);
+
+	memcpy(&stream[0], &x[0], 16);
+	memcpy(&stream[4], &x[12], 16);
+}
+EXPORT_SYMBOL(hchacha_block_generic);
--- /dev/null
+++ b/lib/crypto/libchacha.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * The ChaCha stream cipher (RFC7539)
+ *
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/module.h>
+
+#include <crypto/algapi.h> // for crypto_xor_cpy
+#include <crypto/chacha.h>
+
+void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds)
+{
+	/* aligned to potentially speed up crypto_xor() */
+	u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long));
+
+	while (bytes >= CHACHA_BLOCK_SIZE) {
+		chacha_block_generic(state, stream, nrounds);
+		crypto_xor_cpy(dst, src, stream, CHACHA_BLOCK_SIZE);
+		bytes -= CHACHA_BLOCK_SIZE;
+		dst += CHACHA_BLOCK_SIZE;
+		src += CHACHA_BLOCK_SIZE;
+	}
+	if (bytes) {
+		chacha_block_generic(state, stream, nrounds);
+		crypto_xor_cpy(dst, src, stream, bytes);
+	}
+}
+EXPORT_SYMBOL(chacha_crypt_generic);
+
+MODULE_LICENSE("GPL");