Merge tag 'v5.20-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu: "API: - Make proc files report fips module name and version Algorithms: - Move generic SHA1 code into lib/crypto - Implement Chinese Remainder Theorem for RSA - Remove blake2s - Add XCTR with x86/arm64 acceleration - Add POLYVAL with x86/arm64 acceleration - Add HCTR2 - Add ARIA Drivers: - Add support for new CCP/PSP device ID in ccp" * tag 'v5.20-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (89 commits) crypto: tcrypt - Remove the static variable initialisations to NULL crypto: arm64/poly1305 - fix a read out-of-bound crypto: hisilicon/zip - Use the bitmap API to allocate bitmaps crypto: hisilicon/sec - fix auth key size error crypto: ccree - Remove a useless dma_supported() call crypto: ccp - Add support for new CCP/PSP device ID crypto: inside-secure - Add missing MODULE_DEVICE_TABLE for of crypto: hisilicon/hpre - don't use GFP_KERNEL to alloc mem during softirq crypto: testmgr - some more fixes to RSA test vectors cyrpto: powerpc/aes - delete the rebundant word "block" in comments hwrng: via - Fix comment typo crypto: twofish - Fix comment typo crypto: rmd160 - fix Kconfig "its" grammar crypto: keembay-ocs-ecc - Drop if with an always false condition Documentation: qat: rewrite description Documentation: qat: Use code block for qat sysfs example crypto: lib - add module license to libsha1 crypto: lib - make the sha1 library optional crypto: lib - move lib/sha1.c into lib/crypto/ crypto: fips - make proc files report fips module name and version ...
2025-07-23 04:33:26 +02:00 · 2022-08-02 17:45:14 -07:00
parent a0b09f2d6f af5d35b83f
commit c2a24a7a03
114 changed files with 9136 additions and 1199 deletions
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -33,6 +33,27 @@ config CRYPTO_FIPS
 	  certification.  You should say no unless you know what
 	  this is.

+config CRYPTO_FIPS_NAME
+	string "FIPS Module Name"
+	default "Linux Kernel Cryptographic API"
+	depends on CRYPTO_FIPS
+	help
+	  This option sets the FIPS Module name reported by the Crypto API via
+	  the /proc/sys/crypto/fips_name file.
+
+config CRYPTO_FIPS_CUSTOM_VERSION
+	bool "Use Custom FIPS Module Version"
+	depends on CRYPTO_FIPS
+	default n
+
+config CRYPTO_FIPS_VERSION
+	string "FIPS Module Version"
+	default "(none)"
+	depends on CRYPTO_FIPS_CUSTOM_VERSION
+	help
+	  This option provides the ability to override the FIPS Module Version.
+	  By default the KERNELRELEASE value is used.
+
 config CRYPTO_ALGAPI
 	tristate
 	select CRYPTO_ALGAPI2
@@ -461,6 +482,15 @@ config CRYPTO_PCBC
 	  PCBC: Propagating Cipher Block Chaining mode
 	  This block cipher algorithm is required for RxRPC.

+config CRYPTO_XCTR
+	tristate
+	select CRYPTO_SKCIPHER
+	select CRYPTO_MANAGER
+	help
+	  XCTR: XOR Counter mode. This blockcipher mode is a variant of CTR mode
+	  using XORs and little-endian addition rather than big-endian arithmetic.
+	  XCTR mode is used to implement HCTR2.
+
 config CRYPTO_XTS
 	tristate "XTS support"
 	select CRYPTO_SKCIPHER
@@ -524,6 +554,17 @@ config CRYPTO_ADIANTUM

 	  If unsure, say N.

+config CRYPTO_HCTR2
+	tristate "HCTR2 support"
+	select CRYPTO_XCTR
+	select CRYPTO_POLYVAL
+	select CRYPTO_MANAGER
+	help
+	  HCTR2 is a length-preserving encryption mode for storage encryption that
+	  is efficient on processors with instructions to accelerate AES and
+	  carryless multiplication, e.g. x86 processors with AES-NI and CLMUL, and
+	  ARM processors with the ARMv8 crypto extensions.
+
 config CRYPTO_ESSIV
 	tristate "ESSIV support for block encryption"
 	select CRYPTO_AUTHENC
@@ -704,26 +745,8 @@ config CRYPTO_BLAKE2B

 	  See https://blake2.net for further information.

-config CRYPTO_BLAKE2S
-	tristate "BLAKE2s digest algorithm"
-	select CRYPTO_LIB_BLAKE2S_GENERIC
-	select CRYPTO_HASH
-	help
-	  Implementation of cryptographic hash function BLAKE2s
-	  optimized for 8-32bit platforms and can produce digests of any size
-	  between 1 to 32.  The keyed hash is also implemented.
-
-	  This module provides the following algorithms:
-
-	  - blake2s-128
-	  - blake2s-160
-	  - blake2s-224
-	  - blake2s-256
-
-	  See https://blake2.net for further information.
-
 config CRYPTO_BLAKE2S_X86
-	tristate "BLAKE2s digest algorithm (x86 accelerated version)"
+	bool "BLAKE2s digest algorithm (x86 accelerated version)"
 	depends on X86 && 64BIT
 	select CRYPTO_LIB_BLAKE2S_GENERIC
 	select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
@@ -777,6 +800,23 @@ config CRYPTO_GHASH
 	  GHASH is the hash function used in GCM (Galois/Counter Mode).
 	  It is not a general-purpose cryptographic hash function.

+config CRYPTO_POLYVAL
+	tristate
+	select CRYPTO_GF128MUL
+	select CRYPTO_HASH
+	help
+	  POLYVAL is the hash function used in HCTR2.  It is not a general-purpose
+	  cryptographic hash function.
+
+config CRYPTO_POLYVAL_CLMUL_NI
+	tristate "POLYVAL hash function (CLMUL-NI accelerated)"
+	depends on X86 && 64BIT
+	select CRYPTO_POLYVAL
+	help
+	  This is the x86_64 CLMUL-NI accelerated implementation of POLYVAL. It is
+	  used to efficiently implement HCTR2 on x86-64 processors that support
+	  carry-less multiplication instructions.
+
 config CRYPTO_POLY1305
 	tristate "Poly1305 authenticator algorithm"
 	select CRYPTO_HASH
@@ -861,7 +901,7 @@ config CRYPTO_RMD160

 	  RIPEMD-160 is a 160-bit cryptographic hash function. It is intended
 	  to be used as a secure replacement for the 128-bit hash functions
-	  MD4, MD5 and it's predecessor RIPEMD
+	  MD4, MD5 and its predecessor RIPEMD
 	  (not to be confused with RIPEMD-128).

 	  It's speed is comparable to SHA1 and there are no known attacks
@@ -873,6 +913,7 @@ config CRYPTO_RMD160
 config CRYPTO_SHA1
 	tristate "SHA1 digest algorithm"
 	select CRYPTO_HASH
+	select CRYPTO_LIB_SHA1
 	help
 	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2).

@@ -1214,7 +1255,7 @@ config CRYPTO_AES_NI_INTEL
 	  In addition to AES cipher algorithm support, the acceleration
 	  for some popular block cipher mode is supported too, including
 	  ECB, CBC, LRW, XTS. The 64 bit version has additional
-	  acceleration for CTR.
+	  acceleration for CTR and XCTR.

 config CRYPTO_AES_SPARC64
 	tristate "AES cipher algorithms (SPARC64)"
@@ -1603,6 +1644,21 @@ config CRYPTO_SEED
 	  See also:
 	  <http://www.kisa.or.kr/kisa/seed/jsp/seed_eng.jsp>

+config CRYPTO_ARIA
+	tristate "ARIA cipher algorithm"
+	select CRYPTO_ALGAPI
+	help
+	  ARIA cipher algorithm (RFC5794).
+
+	  ARIA is a standard encryption algorithm of the Republic of Korea.
+	  The ARIA specifies three key sizes and rounds.
+	  128-bit: 12 rounds.
+	  192-bit: 14 rounds.
+	  256-bit: 16 rounds.
+
+	  See also:
+	  <https://seed.kisa.or.kr/kisa/algorithm/EgovAriaInfo.do>
+
 config CRYPTO_SERPENT
 	tristate "Serpent cipher algorithm"
 	select CRYPTO_ALGAPI
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -84,7 +84,6 @@ obj-$(CONFIG_CRYPTO_STREEBOG) += streebog_generic.o
 obj-$(CONFIG_CRYPTO_WP512) += wp512.o
 CFLAGS_wp512.o := $(call cc-option,-fno-schedule-insns)  # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149
 obj-$(CONFIG_CRYPTO_BLAKE2B) += blake2b_generic.o
-obj-$(CONFIG_CRYPTO_BLAKE2S) += blake2s_generic.o
 obj-$(CONFIG_CRYPTO_GF128MUL) += gf128mul.o
 obj-$(CONFIG_CRYPTO_ECB) += ecb.o
 obj-$(CONFIG_CRYPTO_CBC) += cbc.o
@@ -94,6 +93,8 @@ obj-$(CONFIG_CRYPTO_CTS) += cts.o
 obj-$(CONFIG_CRYPTO_LRW) += lrw.o
 obj-$(CONFIG_CRYPTO_XTS) += xts.o
 obj-$(CONFIG_CRYPTO_CTR) += ctr.o
+obj-$(CONFIG_CRYPTO_XCTR) += xctr.o
+obj-$(CONFIG_CRYPTO_HCTR2) += hctr2.o
 obj-$(CONFIG_CRYPTO_KEYWRAP) += keywrap.o
 obj-$(CONFIG_CRYPTO_ADIANTUM) += adiantum.o
 obj-$(CONFIG_CRYPTO_NHPOLY1305) += nhpoly1305.o
@@ -147,6 +148,7 @@ obj-$(CONFIG_CRYPTO_TEA) += tea.o
 obj-$(CONFIG_CRYPTO_KHAZAD) += khazad.o
 obj-$(CONFIG_CRYPTO_ANUBIS) += anubis.o
 obj-$(CONFIG_CRYPTO_SEED) += seed.o
+obj-$(CONFIG_CRYPTO_ARIA) += aria.o
 obj-$(CONFIG_CRYPTO_CHACHA20) += chacha_generic.o
 obj-$(CONFIG_CRYPTO_POLY1305) += poly1305_generic.o
 obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o
@@ -171,6 +173,7 @@ UBSAN_SANITIZE_jitterentropy.o = n
 jitterentropy_rng-y := jitterentropy.o jitterentropy-kcapi.o
 obj-$(CONFIG_CRYPTO_TEST) += tcrypt.o
 obj-$(CONFIG_CRYPTO_GHASH) += ghash-generic.o
+obj-$(CONFIG_CRYPTO_POLYVAL) += polyval-generic.o
 obj-$(CONFIG_CRYPTO_USER_API) += af_alg.o
 obj-$(CONFIG_CRYPTO_USER_API_HASH) += algif_hash.o
 obj-$(CONFIG_CRYPTO_USER_API_SKCIPHER) += algif_skcipher.o
--- a/crypto/aria.c
+++ b/crypto/aria.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Cryptographic API.
+ *
+ * ARIA Cipher Algorithm.
+ *
+ * Documentation of ARIA can be found in RFC 5794.
+ * Copyright (c) 2022 Taehee Yoo <ap420073@gmail.com>
+ *
+ * Information for ARIA
+ *     http://210.104.33.10/ARIA/index-e.html (English)
+ *     http://seed.kisa.or.kr/ (Korean)
+ *
+ * Public domain version is distributed above.
+ */
+
+#include <crypto/aria.h>
+
+static void aria_set_encrypt_key(struct aria_ctx *ctx, const u8 *in_key,
+				 unsigned int key_len)
+{
+	const __be32 *key = (const __be32 *)in_key;
+	u32 w0[4], w1[4], w2[4], w3[4];
+	u32 reg0, reg1, reg2, reg3;
+	const u32 *ck;
+	int rkidx = 0;
+
+	ck = &key_rc[(key_len - 16) / 8][0];
+
+	w0[0] = be32_to_cpu(key[0]);
+	w0[1] = be32_to_cpu(key[1]);
+	w0[2] = be32_to_cpu(key[2]);
+	w0[3] = be32_to_cpu(key[3]);
+
+	reg0 = w0[0] ^ ck[0];
+	reg1 = w0[1] ^ ck[1];
+	reg2 = w0[2] ^ ck[2];
+	reg3 = w0[3] ^ ck[3];
+
+	aria_subst_diff_odd(&reg0, &reg1, &reg2, &reg3);
+
+	if (key_len > 16) {
+		w1[0] = be32_to_cpu(key[4]);
+		w1[1] = be32_to_cpu(key[5]);
+		if (key_len > 24) {
+			w1[2] = be32_to_cpu(key[6]);
+			w1[3] = be32_to_cpu(key[7]);
+		} else {
+			w1[2] = 0;
+			w1[3] = 0;
+		}
+	} else {
+		w1[0] = 0;
+		w1[1] = 0;
+		w1[2] = 0;
+		w1[3] = 0;
+	}
+
+	w1[0] ^= reg0;
+	w1[1] ^= reg1;
+	w1[2] ^= reg2;
+	w1[3] ^= reg3;
+
+	reg0 = w1[0];
+	reg1 = w1[1];
+	reg2 = w1[2];
+	reg3 = w1[3];
+
+	reg0 ^= ck[4];
+	reg1 ^= ck[5];
+	reg2 ^= ck[6];
+	reg3 ^= ck[7];
+
+	aria_subst_diff_even(&reg0, &reg1, &reg2, &reg3);
+
+	reg0 ^= w0[0];
+	reg1 ^= w0[1];
+	reg2 ^= w0[2];
+	reg3 ^= w0[3];
+
+	w2[0] = reg0;
+	w2[1] = reg1;
+	w2[2] = reg2;
+	w2[3] = reg3;
+
+	reg0 ^= ck[8];
+	reg1 ^= ck[9];
+	reg2 ^= ck[10];
+	reg3 ^= ck[11];
+
+	aria_subst_diff_odd(&reg0, &reg1, &reg2, &reg3);
+
+	w3[0] = reg0 ^ w1[0];
+	w3[1] = reg1 ^ w1[1];
+	w3[2] = reg2 ^ w1[2];
+	w3[3] = reg3 ^ w1[3];
+
+	aria_gsrk(ctx->enc_key[rkidx], w0, w1, 19);
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w1, w2, 19);
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w2, w3, 19);
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w3, w0, 19);
+
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w0, w1, 31);
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w1, w2, 31);
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w2, w3, 31);
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w3, w0, 31);
+
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w0, w1, 67);
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w1, w2, 67);
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w2, w3, 67);
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w3, w0, 67);
+
+	rkidx++;
+	aria_gsrk(ctx->enc_key[rkidx], w0, w1, 97);
+	if (key_len > 16) {
+		rkidx++;
+		aria_gsrk(ctx->enc_key[rkidx], w1, w2, 97);
+		rkidx++;
+		aria_gsrk(ctx->enc_key[rkidx], w2, w3, 97);
+
+		if (key_len > 24) {
+			rkidx++;
+			aria_gsrk(ctx->enc_key[rkidx], w3, w0, 97);
+
+			rkidx++;
+			aria_gsrk(ctx->enc_key[rkidx], w0, w1, 109);
+		}
+	}
+}
+
+static void aria_set_decrypt_key(struct aria_ctx *ctx)
+{
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		ctx->dec_key[0][i] = ctx->enc_key[ctx->rounds][i];
+		ctx->dec_key[ctx->rounds][i] = ctx->enc_key[0][i];
+	}
+
+	for (i = 1; i < ctx->rounds; i++) {
+		ctx->dec_key[i][0] = aria_m(ctx->enc_key[ctx->rounds - i][0]);
+		ctx->dec_key[i][1] = aria_m(ctx->enc_key[ctx->rounds - i][1]);
+		ctx->dec_key[i][2] = aria_m(ctx->enc_key[ctx->rounds - i][2]);
+		ctx->dec_key[i][3] = aria_m(ctx->enc_key[ctx->rounds - i][3]);
+
+		aria_diff_word(&ctx->dec_key[i][0], &ctx->dec_key[i][1],
+			       &ctx->dec_key[i][2], &ctx->dec_key[i][3]);
+		aria_diff_byte(&ctx->dec_key[i][1],
+			       &ctx->dec_key[i][2], &ctx->dec_key[i][3]);
+		aria_diff_word(&ctx->dec_key[i][0], &ctx->dec_key[i][1],
+			       &ctx->dec_key[i][2], &ctx->dec_key[i][3]);
+	}
+}
+
+static int aria_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+			unsigned int key_len)
+{
+	struct aria_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (key_len != 16 && key_len != 24 && key_len != 32)
+		return -EINVAL;
+
+	ctx->key_length = key_len;
+	ctx->rounds = (key_len + 32) / 4;
+
+	aria_set_encrypt_key(ctx, in_key, key_len);
+	aria_set_decrypt_key(ctx);
+
+	return 0;
+}
+
+static void __aria_crypt(struct aria_ctx *ctx, u8 *out, const u8 *in,
+			 u32 key[][ARIA_RD_KEY_WORDS])
+{
+	const __be32 *src = (const __be32 *)in;
+	__be32 *dst = (__be32 *)out;
+	u32 reg0, reg1, reg2, reg3;
+	int rounds, rkidx = 0;
+
+	rounds = ctx->rounds;
+
+	reg0 = be32_to_cpu(src[0]);
+	reg1 = be32_to_cpu(src[1]);
+	reg2 = be32_to_cpu(src[2]);
+	reg3 = be32_to_cpu(src[3]);
+
+	aria_add_round_key(key[rkidx], &reg0, &reg1, &reg2, &reg3);
+	rkidx++;
+
+	aria_subst_diff_odd(&reg0, &reg1, &reg2, &reg3);
+	aria_add_round_key(key[rkidx], &reg0, &reg1, &reg2, &reg3);
+	rkidx++;
+
+	while ((rounds -= 2) > 0) {
+		aria_subst_diff_even(&reg0, &reg1, &reg2, &reg3);
+		aria_add_round_key(key[rkidx], &reg0, &reg1, &reg2, &reg3);
+		rkidx++;
+
+		aria_subst_diff_odd(&reg0, &reg1, &reg2, &reg3);
+		aria_add_round_key(key[rkidx], &reg0, &reg1, &reg2, &reg3);
+		rkidx++;
+	}
+
+	reg0 = key[rkidx][0] ^ make_u32((u8)(x1[get_u8(reg0, 0)]),
+					(u8)(x2[get_u8(reg0, 1)] >> 8),
+					(u8)(s1[get_u8(reg0, 2)]),
+					(u8)(s2[get_u8(reg0, 3)]));
+	reg1 = key[rkidx][1] ^ make_u32((u8)(x1[get_u8(reg1, 0)]),
+					(u8)(x2[get_u8(reg1, 1)] >> 8),
+					(u8)(s1[get_u8(reg1, 2)]),
+					(u8)(s2[get_u8(reg1, 3)]));
+	reg2 = key[rkidx][2] ^ make_u32((u8)(x1[get_u8(reg2, 0)]),
+					(u8)(x2[get_u8(reg2, 1)] >> 8),
+					(u8)(s1[get_u8(reg2, 2)]),
+					(u8)(s2[get_u8(reg2, 3)]));
+	reg3 = key[rkidx][3] ^ make_u32((u8)(x1[get_u8(reg3, 0)]),
+					(u8)(x2[get_u8(reg3, 1)] >> 8),
+					(u8)(s1[get_u8(reg3, 2)]),
+					(u8)(s2[get_u8(reg3, 3)]));
+
+	dst[0] = cpu_to_be32(reg0);
+	dst[1] = cpu_to_be32(reg1);
+	dst[2] = cpu_to_be32(reg2);
+	dst[3] = cpu_to_be32(reg3);
+}
+
+static void aria_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	struct aria_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	__aria_crypt(ctx, out, in, ctx->enc_key);
+}
+
+static void aria_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	struct aria_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	__aria_crypt(ctx, out, in, ctx->dec_key);
+}
+
+static struct crypto_alg aria_alg = {
+	.cra_name		=	"aria",
+	.cra_driver_name	=	"aria-generic",
+	.cra_priority		=	100,
+	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		=	ARIA_BLOCK_SIZE,
+	.cra_ctxsize		=	sizeof(struct aria_ctx),
+	.cra_alignmask		=	3,
+	.cra_module		=	THIS_MODULE,
+	.cra_u			=	{
+		.cipher = {
+			.cia_min_keysize	=	ARIA_MIN_KEY_SIZE,
+			.cia_max_keysize	=	ARIA_MAX_KEY_SIZE,
+			.cia_setkey		=	aria_set_key,
+			.cia_encrypt		=	aria_encrypt,
+			.cia_decrypt		=	aria_decrypt
+		}
+	}
+};
+
+static int __init aria_init(void)
+{
+	return crypto_register_alg(&aria_alg);
+}
+
+static void __exit aria_fini(void)
+{
+	crypto_unregister_alg(&aria_alg);
+}
+
+subsys_initcall(aria_init);
+module_exit(aria_fini);
+
+MODULE_DESCRIPTION("ARIA Cipher Algorithm");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Taehee Yoo <ap420073@gmail.com>");
+MODULE_ALIAS_CRYPTO("aria");
--- a/crypto/blake2s_generic.c
+++ b/crypto/blake2s_generic.c
@@ -1,75 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR MIT
-/*
- * shash interface to the generic implementation of BLAKE2s
- *
- * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- */
-
-#include <crypto/internal/blake2s.h>
-#include <crypto/internal/hash.h>
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-static int crypto_blake2s_update_generic(struct shash_desc *desc,
-					 const u8 *in, unsigned int inlen)
-{
-	return crypto_blake2s_update(desc, in, inlen, true);
-}
-
-static int crypto_blake2s_final_generic(struct shash_desc *desc, u8 *out)
-{
-	return crypto_blake2s_final(desc, out, true);
-}
-
-#define BLAKE2S_ALG(name, driver_name, digest_size)			\
-	{								\
-		.base.cra_name		= name,				\
-		.base.cra_driver_name	= driver_name,			\
-		.base.cra_priority	= 100,				\
-		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,	\
-		.base.cra_blocksize	= BLAKE2S_BLOCK_SIZE,		\
-		.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx), \
-		.base.cra_module	= THIS_MODULE,			\
-		.digestsize		= digest_size,			\
-		.setkey			= crypto_blake2s_setkey,	\
-		.init			= crypto_blake2s_init,		\
-		.update			= crypto_blake2s_update_generic, \
-		.final			= crypto_blake2s_final_generic,	\
-		.descsize		= sizeof(struct blake2s_state),	\
-	}
-
-static struct shash_alg blake2s_algs[] = {
-	BLAKE2S_ALG("blake2s-128", "blake2s-128-generic",
-		    BLAKE2S_128_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-160", "blake2s-160-generic",
-		    BLAKE2S_160_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-224", "blake2s-224-generic",
-		    BLAKE2S_224_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-256", "blake2s-256-generic",
-		    BLAKE2S_256_HASH_SIZE),
-};
-
-static int __init blake2s_mod_init(void)
-{
-	return crypto_register_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
-}
-
-static void __exit blake2s_mod_exit(void)
-{
-	crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
-}
-
-subsys_initcall(blake2s_mod_init);
-module_exit(blake2s_mod_exit);
-
-MODULE_ALIAS_CRYPTO("blake2s-128");
-MODULE_ALIAS_CRYPTO("blake2s-128-generic");
-MODULE_ALIAS_CRYPTO("blake2s-160");
-MODULE_ALIAS_CRYPTO("blake2s-160-generic");
-MODULE_ALIAS_CRYPTO("blake2s-224");
-MODULE_ALIAS_CRYPTO("blake2s-224-generic");
-MODULE_ALIAS_CRYPTO("blake2s-256");
-MODULE_ALIAS_CRYPTO("blake2s-256-generic");
-MODULE_LICENSE("GPL v2");
--- a/crypto/fips.c
+++ b/crypto/fips.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/sysctl.h>
 #include <linux/notifier.h>
+#include <generated/utsrelease.h>

 int fips_enabled;
 EXPORT_SYMBOL_GPL(fips_enabled);
@@ -30,13 +31,37 @@ static int fips_enable(char *str)

 __setup("fips=", fips_enable);

+#define FIPS_MODULE_NAME CONFIG_CRYPTO_FIPS_NAME
+#ifdef CONFIG_CRYPTO_FIPS_CUSTOM_VERSION
+#define FIPS_MODULE_VERSION CONFIG_CRYPTO_FIPS_VERSION
+#else
+#define FIPS_MODULE_VERSION UTS_RELEASE
+#endif
+
+static char fips_name[] = FIPS_MODULE_NAME;
+static char fips_version[] = FIPS_MODULE_VERSION;
+
 static struct ctl_table crypto_sysctl_table[] = {
 	{
-		.procname       = "fips_enabled",
-		.data           = &fips_enabled,
-		.maxlen         = sizeof(int),
-		.mode           = 0444,
-		.proc_handler   = proc_dointvec
+		.procname	= "fips_enabled",
+		.data		= &fips_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "fips_name",
+		.data		= &fips_name,
+		.maxlen		= 64,
+		.mode		= 0444,
+		.proc_handler	= proc_dostring
+	},
+	{
+		.procname	= "fips_version",
+		.data		= &fips_version,
+		.maxlen		= 64,
+		.mode		= 0444,
+		.proc_handler	= proc_dostring
 	},
 	{}
 };
--- a/crypto/hctr2.c
+++ b/crypto/hctr2.c
@@ -0,0 +1,581 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * HCTR2 length-preserving encryption mode
+ *
+ * Copyright 2021 Google LLC
+ */
+
+
+/*
+ * HCTR2 is a length-preserving encryption mode that is efficient on
+ * processors with instructions to accelerate AES and carryless
+ * multiplication, e.g. x86 processors with AES-NI and CLMUL, and ARM
+ * processors with the ARMv8 crypto extensions.
+ *
+ * For more details, see the paper: "Length-preserving encryption with HCTR2"
+ * (https://eprint.iacr.org/2021/1441.pdf)
+ */
+
+#include <crypto/internal/cipher.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/polyval.h>
+#include <crypto/scatterwalk.h>
+#include <linux/module.h>
+
+#define BLOCKCIPHER_BLOCK_SIZE		16
+
+/*
+ * The specification allows variable-length tweaks, but Linux's crypto API
+ * currently only allows algorithms to support a single length.  The "natural"
+ * tweak length for HCTR2 is 16, since that fits into one POLYVAL block for
+ * the best performance.  But longer tweaks are useful for fscrypt, to avoid
+ * needing to derive per-file keys.  So instead we use two blocks, or 32 bytes.
+ */
+#define TWEAK_SIZE		32
+
+struct hctr2_instance_ctx {
+	struct crypto_cipher_spawn blockcipher_spawn;
+	struct crypto_skcipher_spawn xctr_spawn;
+	struct crypto_shash_spawn polyval_spawn;
+};
+
+struct hctr2_tfm_ctx {
+	struct crypto_cipher *blockcipher;
+	struct crypto_skcipher *xctr;
+	struct crypto_shash *polyval;
+	u8 L[BLOCKCIPHER_BLOCK_SIZE];
+	int hashed_tweak_offset;
+	/*
+	 * This struct is allocated with extra space for two exported hash
+	 * states.  Since the hash state size is not known at compile-time, we
+	 * can't add these to the struct directly.
+	 *
+	 * hashed_tweaklen_divisible;
+	 * hashed_tweaklen_remainder;
+	 */
+};
+
+struct hctr2_request_ctx {
+	u8 first_block[BLOCKCIPHER_BLOCK_SIZE];
+	u8 xctr_iv[BLOCKCIPHER_BLOCK_SIZE];
+	struct scatterlist *bulk_part_dst;
+	struct scatterlist *bulk_part_src;
+	struct scatterlist sg_src[2];
+	struct scatterlist sg_dst[2];
+	/*
+	 * Sub-request sizes are unknown at compile-time, so they need to go
+	 * after the members with known sizes.
+	 */
+	union {
+		struct shash_desc hash_desc;
+		struct skcipher_request xctr_req;
+	} u;
+	/*
+	 * This struct is allocated with extra space for one exported hash
+	 * state.  Since the hash state size is not known at compile-time, we
+	 * can't add it to the struct directly.
+	 *
+	 * hashed_tweak;
+	 */
+};
+
+static inline u8 *hctr2_hashed_tweaklen(const struct hctr2_tfm_ctx *tctx,
+					bool has_remainder)
+{
+	u8 *p = (u8 *)tctx + sizeof(*tctx);
+
+	if (has_remainder) /* For messages not a multiple of block length */
+		p += crypto_shash_statesize(tctx->polyval);
+	return p;
+}
+
+static inline u8 *hctr2_hashed_tweak(const struct hctr2_tfm_ctx *tctx,
+				     struct hctr2_request_ctx *rctx)
+{
+	return (u8 *)rctx + tctx->hashed_tweak_offset;
+}
+
+/*
+ * The input data for each HCTR2 hash step begins with a 16-byte block that
+ * contains the tweak length and a flag that indicates whether the input is evenly
+ * divisible into blocks.  Since this implementation only supports one tweak
+ * length, we precompute the two hash states resulting from hashing the two
+ * possible values of this initial block.  This reduces by one block the amount of
+ * data that needs to be hashed for each encryption/decryption
+ *
+ * These precomputed hashes are stored in hctr2_tfm_ctx.
+ */
+static int hctr2_hash_tweaklen(struct hctr2_tfm_ctx *tctx, bool has_remainder)
+{
+	SHASH_DESC_ON_STACK(shash, tfm->polyval);
+	__le64 tweak_length_block[2];
+	int err;
+
+	shash->tfm = tctx->polyval;
+	memset(tweak_length_block, 0, sizeof(tweak_length_block));
+
+	tweak_length_block[0] = cpu_to_le64(TWEAK_SIZE * 8 * 2 + 2 + has_remainder);
+	err = crypto_shash_init(shash);
+	if (err)
+		return err;
+	err = crypto_shash_update(shash, (u8 *)tweak_length_block,
+				  POLYVAL_BLOCK_SIZE);
+	if (err)
+		return err;
+	return crypto_shash_export(shash, hctr2_hashed_tweaklen(tctx, has_remainder));
+}
+
+static int hctr2_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			unsigned int keylen)
+{
+	struct hctr2_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+	u8 hbar[BLOCKCIPHER_BLOCK_SIZE];
+	int err;
+
+	crypto_cipher_clear_flags(tctx->blockcipher, CRYPTO_TFM_REQ_MASK);
+	crypto_cipher_set_flags(tctx->blockcipher,
+				crypto_skcipher_get_flags(tfm) &
+				CRYPTO_TFM_REQ_MASK);
+	err = crypto_cipher_setkey(tctx->blockcipher, key, keylen);
+	if (err)
+		return err;
+
+	crypto_skcipher_clear_flags(tctx->xctr, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(tctx->xctr,
+				  crypto_skcipher_get_flags(tfm) &
+				  CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(tctx->xctr, key, keylen);
+	if (err)
+		return err;
+
+	memset(hbar, 0, sizeof(hbar));
+	crypto_cipher_encrypt_one(tctx->blockcipher, hbar, hbar);
+
+	memset(tctx->L, 0, sizeof(tctx->L));
+	tctx->L[0] = 0x01;
+	crypto_cipher_encrypt_one(tctx->blockcipher, tctx->L, tctx->L);
+
+	crypto_shash_clear_flags(tctx->polyval, CRYPTO_TFM_REQ_MASK);
+	crypto_shash_set_flags(tctx->polyval, crypto_skcipher_get_flags(tfm) &
+			       CRYPTO_TFM_REQ_MASK);
+	err = crypto_shash_setkey(tctx->polyval, hbar, BLOCKCIPHER_BLOCK_SIZE);
+	if (err)
+		return err;
+	memzero_explicit(hbar, sizeof(hbar));
+
+	return hctr2_hash_tweaklen(tctx, true) ?: hctr2_hash_tweaklen(tctx, false);
+}
+
+static int hctr2_hash_tweak(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct hctr2_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+	struct hctr2_request_ctx *rctx = skcipher_request_ctx(req);
+	struct shash_desc *hash_desc = &rctx->u.hash_desc;
+	int err;
+	bool has_remainder = req->cryptlen % POLYVAL_BLOCK_SIZE;
+
+	hash_desc->tfm = tctx->polyval;
+	err = crypto_shash_import(hash_desc, hctr2_hashed_tweaklen(tctx, has_remainder));
+	if (err)
+		return err;
+	err = crypto_shash_update(hash_desc, req->iv, TWEAK_SIZE);
+	if (err)
+		return err;
+
+	// Store the hashed tweak, since we need it when computing both
+	// H(T || N) and H(T || V).
+	return crypto_shash_export(hash_desc, hctr2_hashed_tweak(tctx, rctx));
+}
+
+static int hctr2_hash_message(struct skcipher_request *req,
+			      struct scatterlist *sgl,
+			      u8 digest[POLYVAL_DIGEST_SIZE])
+{
+	static const u8 padding[BLOCKCIPHER_BLOCK_SIZE] = { 0x1 };
+	struct hctr2_request_ctx *rctx = skcipher_request_ctx(req);
+	struct shash_desc *hash_desc = &rctx->u.hash_desc;
+	const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE;
+	struct sg_mapping_iter miter;
+	unsigned int remainder = bulk_len % BLOCKCIPHER_BLOCK_SIZE;
+	int i;
+	int err = 0;
+	int n = 0;
+
+	sg_miter_start(&miter, sgl, sg_nents(sgl),
+		       SG_MITER_FROM_SG | SG_MITER_ATOMIC);
+	for (i = 0; i < bulk_len; i += n) {
+		sg_miter_next(&miter);
+		n = min_t(unsigned int, miter.length, bulk_len - i);
+		err = crypto_shash_update(hash_desc, miter.addr, n);
+		if (err)
+			break;
+	}
+	sg_miter_stop(&miter);
+
+	if (err)
+		return err;
+
+	if (remainder) {
+		err = crypto_shash_update(hash_desc, padding,
+					  BLOCKCIPHER_BLOCK_SIZE - remainder);
+		if (err)
+			return err;
+	}
+	return crypto_shash_final(hash_desc, digest);
+}
+
+static int hctr2_finish(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct hctr2_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+	struct hctr2_request_ctx *rctx = skcipher_request_ctx(req);
+	u8 digest[POLYVAL_DIGEST_SIZE];
+	struct shash_desc *hash_desc = &rctx->u.hash_desc;
+	int err;
+
+	// U = UU ^ H(T || V)
+	// or M = MM ^ H(T || N)
+	hash_desc->tfm = tctx->polyval;
+	err = crypto_shash_import(hash_desc, hctr2_hashed_tweak(tctx, rctx));
+	if (err)
+		return err;
+	err = hctr2_hash_message(req, rctx->bulk_part_dst, digest);
+	if (err)
+		return err;
+	crypto_xor(rctx->first_block, digest, BLOCKCIPHER_BLOCK_SIZE);
+
+	// Copy U (or M) into dst scatterlist
+	scatterwalk_map_and_copy(rctx->first_block, req->dst,
+				 0, BLOCKCIPHER_BLOCK_SIZE, 1);
+	return 0;
+}
+
+static void hctr2_xctr_done(struct crypto_async_request *areq,
+				    int err)
+{
+	struct skcipher_request *req = areq->data;
+
+	if (!err)
+		err = hctr2_finish(req);
+
+	skcipher_request_complete(req, err);
+}
+
+static int hctr2_crypt(struct skcipher_request *req, bool enc)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct hctr2_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+	struct hctr2_request_ctx *rctx = skcipher_request_ctx(req);
+	u8 digest[POLYVAL_DIGEST_SIZE];
+	int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE;
+	int err;
+
+	// Requests must be at least one block
+	if (req->cryptlen < BLOCKCIPHER_BLOCK_SIZE)
+		return -EINVAL;
+
+	// Copy M (or U) into a temporary buffer
+	scatterwalk_map_and_copy(rctx->first_block, req->src,
+				 0, BLOCKCIPHER_BLOCK_SIZE, 0);
+
+	// Create scatterlists for N and V
+	rctx->bulk_part_src = scatterwalk_ffwd(rctx->sg_src, req->src,
+					       BLOCKCIPHER_BLOCK_SIZE);
+	rctx->bulk_part_dst = scatterwalk_ffwd(rctx->sg_dst, req->dst,
+					       BLOCKCIPHER_BLOCK_SIZE);
+
+	// MM = M ^ H(T || N)
+	// or UU = U ^ H(T || V)
+	err = hctr2_hash_tweak(req);
+	if (err)
+		return err;
+	err = hctr2_hash_message(req, rctx->bulk_part_src, digest);
+	if (err)
+		return err;
+	crypto_xor(digest, rctx->first_block, BLOCKCIPHER_BLOCK_SIZE);
+
+	// UU = E(MM)
+	// or MM = D(UU)
+	if (enc)
+		crypto_cipher_encrypt_one(tctx->blockcipher, rctx->first_block,
+					  digest);
+	else
+		crypto_cipher_decrypt_one(tctx->blockcipher, rctx->first_block,
+					  digest);
+
+	// S = MM ^ UU ^ L
+	crypto_xor(digest, rctx->first_block, BLOCKCIPHER_BLOCK_SIZE);
+	crypto_xor_cpy(rctx->xctr_iv, digest, tctx->L, BLOCKCIPHER_BLOCK_SIZE);
+
+	// V = XCTR(S, N)
+	// or N = XCTR(S, V)
+	skcipher_request_set_tfm(&rctx->u.xctr_req, tctx->xctr);
+	skcipher_request_set_crypt(&rctx->u.xctr_req, rctx->bulk_part_src,
+				   rctx->bulk_part_dst, bulk_len,
+				   rctx->xctr_iv);
+	skcipher_request_set_callback(&rctx->u.xctr_req,
+				      req->base.flags,
+				      hctr2_xctr_done, req);
+	return crypto_skcipher_encrypt(&rctx->u.xctr_req) ?:
+		hctr2_finish(req);
+}
+
+static int hctr2_encrypt(struct skcipher_request *req)
+{
+	return hctr2_crypt(req, true);
+}
+
+static int hctr2_decrypt(struct skcipher_request *req)
+{
+	return hctr2_crypt(req, false);
+}
+
+static int hctr2_init_tfm(struct crypto_skcipher *tfm)
+{
+	struct skcipher_instance *inst = skcipher_alg_instance(tfm);
+	struct hctr2_instance_ctx *ictx = skcipher_instance_ctx(inst);
+	struct hctr2_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *xctr;
+	struct crypto_cipher *blockcipher;
+	struct crypto_shash *polyval;
+	unsigned int subreq_size;
+	int err;
+
+	xctr = crypto_spawn_skcipher(&ictx->xctr_spawn);
+	if (IS_ERR(xctr))
+		return PTR_ERR(xctr);
+
+	blockcipher = crypto_spawn_cipher(&ictx->blockcipher_spawn);
+	if (IS_ERR(blockcipher)) {
+		err = PTR_ERR(blockcipher);
+		goto err_free_xctr;
+	}
+
+	polyval = crypto_spawn_shash(&ictx->polyval_spawn);
+	if (IS_ERR(polyval)) {
+		err = PTR_ERR(polyval);
+		goto err_free_blockcipher;
+	}
+
+	tctx->xctr = xctr;
+	tctx->blockcipher = blockcipher;
+	tctx->polyval = polyval;
+
+	BUILD_BUG_ON(offsetofend(struct hctr2_request_ctx, u) !=
+				 sizeof(struct hctr2_request_ctx));
+	subreq_size = max(sizeof_field(struct hctr2_request_ctx, u.hash_desc) +
+			  crypto_shash_descsize(polyval),
+			  sizeof_field(struct hctr2_request_ctx, u.xctr_req) +
+			  crypto_skcipher_reqsize(xctr));
+
+	tctx->hashed_tweak_offset = offsetof(struct hctr2_request_ctx, u) +
+				    subreq_size;
+	crypto_skcipher_set_reqsize(tfm, tctx->hashed_tweak_offset +
+				    crypto_shash_statesize(polyval));
+	return 0;
+
+err_free_blockcipher:
+	crypto_free_cipher(blockcipher);
+err_free_xctr:
+	crypto_free_skcipher(xctr);
+	return err;
+}
+
+static void hctr2_exit_tfm(struct crypto_skcipher *tfm)
+{
+	struct hctr2_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+
+	crypto_free_cipher(tctx->blockcipher);
+	crypto_free_skcipher(tctx->xctr);
+	crypto_free_shash(tctx->polyval);
+}
+
+static void hctr2_free_instance(struct skcipher_instance *inst)
+{
+	struct hctr2_instance_ctx *ictx = skcipher_instance_ctx(inst);
+
+	crypto_drop_cipher(&ictx->blockcipher_spawn);
+	crypto_drop_skcipher(&ictx->xctr_spawn);
+	crypto_drop_shash(&ictx->polyval_spawn);
+	kfree(inst);
+}
+
+static int hctr2_create_common(struct crypto_template *tmpl,
+			       struct rtattr **tb,
+			       const char *xctr_name,
+			       const char *polyval_name)
+{
+	u32 mask;
+	struct skcipher_instance *inst;
+	struct hctr2_instance_ctx *ictx;
+	struct skcipher_alg *xctr_alg;
+	struct crypto_alg *blockcipher_alg;
+	struct shash_alg *polyval_alg;
+	char blockcipher_name[CRYPTO_MAX_ALG_NAME];
+	int len;
+	int err;
+
+	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SKCIPHER, &mask);
+	if (err)
+		return err;
+
+	inst = kzalloc(sizeof(*inst) + sizeof(*ictx), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+	ictx = skcipher_instance_ctx(inst);
+
+	/* Stream cipher, xctr(block_cipher) */
+	err = crypto_grab_skcipher(&ictx->xctr_spawn,
+				   skcipher_crypto_instance(inst),
+				   xctr_name, 0, mask);
+	if (err)
+		goto err_free_inst;
+	xctr_alg = crypto_spawn_skcipher_alg(&ictx->xctr_spawn);
+
+	err = -EINVAL;
+	if (strncmp(xctr_alg->base.cra_name, "xctr(", 5))
+		goto err_free_inst;
+	len = strscpy(blockcipher_name, xctr_alg->base.cra_name + 5,
+		      sizeof(blockcipher_name));
+	if (len < 1)
+		goto err_free_inst;
+	if (blockcipher_name[len - 1] != ')')
+		goto err_free_inst;
+	blockcipher_name[len - 1] = 0;
+
+	/* Block cipher, e.g. "aes" */
+	err = crypto_grab_cipher(&ictx->blockcipher_spawn,
+				 skcipher_crypto_instance(inst),
+				 blockcipher_name, 0, mask);
+	if (err)
+		goto err_free_inst;
+	blockcipher_alg = crypto_spawn_cipher_alg(&ictx->blockcipher_spawn);
+
+	/* Require blocksize of 16 bytes */
+	err = -EINVAL;
+	if (blockcipher_alg->cra_blocksize != BLOCKCIPHER_BLOCK_SIZE)
+		goto err_free_inst;
+
+	/* Polyval ε-∆U hash function */
+	err = crypto_grab_shash(&ictx->polyval_spawn,
+				skcipher_crypto_instance(inst),
+				polyval_name, 0, mask);
+	if (err)
+		goto err_free_inst;
+	polyval_alg = crypto_spawn_shash_alg(&ictx->polyval_spawn);
+
+	/* Ensure Polyval is being used */
+	err = -EINVAL;
+	if (strcmp(polyval_alg->base.cra_name, "polyval") != 0)
+		goto err_free_inst;
+
+	/* Instance fields */
+
+	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, "hctr2(%s)",
+		     blockcipher_alg->cra_name) >= CRYPTO_MAX_ALG_NAME)
+		goto err_free_inst;
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "hctr2_base(%s,%s)",
+		     xctr_alg->base.cra_driver_name,
+		     polyval_alg->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		goto err_free_inst;
+
+	inst->alg.base.cra_blocksize = BLOCKCIPHER_BLOCK_SIZE;
+	inst->alg.base.cra_ctxsize = sizeof(struct hctr2_tfm_ctx) +
+				     polyval_alg->statesize * 2;
+	inst->alg.base.cra_alignmask = xctr_alg->base.cra_alignmask |
+				       polyval_alg->base.cra_alignmask;
+	/*
+	 * The hash function is called twice, so it is weighted higher than the
+	 * xctr and blockcipher.
+	 */
+	inst->alg.base.cra_priority = (2 * xctr_alg->base.cra_priority +
+				       4 * polyval_alg->base.cra_priority +
+				       blockcipher_alg->cra_priority) / 7;
+
+	inst->alg.setkey = hctr2_setkey;
+	inst->alg.encrypt = hctr2_encrypt;
+	inst->alg.decrypt = hctr2_decrypt;
+	inst->alg.init = hctr2_init_tfm;
+	inst->alg.exit = hctr2_exit_tfm;
+	inst->alg.min_keysize = crypto_skcipher_alg_min_keysize(xctr_alg);
+	inst->alg.max_keysize = crypto_skcipher_alg_max_keysize(xctr_alg);
+	inst->alg.ivsize = TWEAK_SIZE;
+
+	inst->free = hctr2_free_instance;
+
+	err = skcipher_register_instance(tmpl, inst);
+	if (err) {
+err_free_inst:
+		hctr2_free_instance(inst);
+	}
+	return err;
+}
+
+static int hctr2_create_base(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	const char *xctr_name;
+	const char *polyval_name;
+
+	xctr_name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(xctr_name))
+		return PTR_ERR(xctr_name);
+
+	polyval_name = crypto_attr_alg_name(tb[2]);
+	if (IS_ERR(polyval_name))
+		return PTR_ERR(polyval_name);
+
+	return hctr2_create_common(tmpl, tb, xctr_name, polyval_name);
+}
+
+static int hctr2_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	const char *blockcipher_name;
+	char xctr_name[CRYPTO_MAX_ALG_NAME];
+
+	blockcipher_name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(blockcipher_name))
+		return PTR_ERR(blockcipher_name);
+
+	if (snprintf(xctr_name, CRYPTO_MAX_ALG_NAME, "xctr(%s)",
+		    blockcipher_name) >= CRYPTO_MAX_ALG_NAME)
+		return -ENAMETOOLONG;
+
+	return hctr2_create_common(tmpl, tb, xctr_name, "polyval");
+}
+
+static struct crypto_template hctr2_tmpls[] = {
+	{
+		/* hctr2_base(xctr_name, polyval_name) */
+		.name = "hctr2_base",
+		.create = hctr2_create_base,
+		.module = THIS_MODULE,
+	}, {
+		/* hctr2(blockcipher_name) */
+		.name = "hctr2",
+		.create = hctr2_create,
+		.module = THIS_MODULE,
+	}
+};
+
+static int __init hctr2_module_init(void)
+{
+	return crypto_register_templates(hctr2_tmpls, ARRAY_SIZE(hctr2_tmpls));
+}
+
+static void __exit hctr2_module_exit(void)
+{
+	return crypto_unregister_templates(hctr2_tmpls,
+					   ARRAY_SIZE(hctr2_tmpls));
+}
+
+subsys_initcall(hctr2_module_init);
+module_exit(hctr2_module_exit);
+
+MODULE_DESCRIPTION("HCTR2 length-preserving encryption mode");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("hctr2");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
--- a/crypto/polyval-generic.c
+++ b/crypto/polyval-generic.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * POLYVAL: hash function for HCTR2.
+ *
+ * Copyright (c) 2007 Nokia Siemens Networks - Mikko Herranen <mh1@iki.fi>
+ * Copyright (c) 2009 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ * Copyright 2021 Google LLC
+ */
+
+/*
+ * Code based on crypto/ghash-generic.c
+ *
+ * POLYVAL is a keyed hash function similar to GHASH. POLYVAL uses a different
+ * modulus for finite field multiplication which makes hardware accelerated
+ * implementations on little-endian machines faster. POLYVAL is used in the
+ * kernel to implement HCTR2, but was originally specified for AES-GCM-SIV
+ * (RFC 8452).
+ *
+ * For more information see:
+ * Length-preserving encryption with HCTR2:
+ *   https://eprint.iacr.org/2021/1441.pdf
+ * AES-GCM-SIV: Nonce Misuse-Resistant Authenticated Encryption:
+ *   https://datatracker.ietf.org/doc/html/rfc8452
+ *
+ * Like GHASH, POLYVAL is not a cryptographic hash function and should
+ * not be used outside of crypto modes explicitly designed to use POLYVAL.
+ *
+ * This implementation uses a convenient trick involving the GHASH and POLYVAL
+ * fields. This trick allows multiplication in the POLYVAL field to be
+ * implemented by using multiplication in the GHASH field as a subroutine. An
+ * element of the POLYVAL field can be converted to an element of the GHASH
+ * field by computing x*REVERSE(a), where REVERSE reverses the byte-ordering of
+ * a. Similarly, an element of the GHASH field can be converted back to the
+ * POLYVAL field by computing REVERSE(x^{-1}*a). For more information, see:
+ * https://datatracker.ietf.org/doc/html/rfc8452#appendix-A
+ *
+ * By using this trick, we do not need to implement the POLYVAL field for the
+ * generic implementation.
+ *
+ * Warning: this generic implementation is not intended to be used in practice
+ * and is not constant time. For practical use, a hardware accelerated
+ * implementation of POLYVAL should be used instead.
+ *
+ */
+
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/gf128mul.h>
+#include <crypto/polyval.h>
+#include <crypto/internal/hash.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+struct polyval_tfm_ctx {
+	struct gf128mul_4k *gf128;
+};
+
+struct polyval_desc_ctx {
+	union {
+		u8 buffer[POLYVAL_BLOCK_SIZE];
+		be128 buffer128;
+	};
+	u32 bytes;
+};
+
+static void copy_and_reverse(u8 dst[POLYVAL_BLOCK_SIZE],
+			     const u8 src[POLYVAL_BLOCK_SIZE])
+{
+	u64 a = get_unaligned((const u64 *)&src[0]);
+	u64 b = get_unaligned((const u64 *)&src[8]);
+
+	put_unaligned(swab64(a), (u64 *)&dst[8]);
+	put_unaligned(swab64(b), (u64 *)&dst[0]);
+}
+
+/*
+ * Performs multiplication in the POLYVAL field using the GHASH field as a
+ * subroutine.  This function is used as a fallback for hardware accelerated
+ * implementations when simd registers are unavailable.
+ *
+ * Note: This function is not used for polyval-generic, instead we use the 4k
+ * lookup table implementation for finite field multiplication.
+ */
+void polyval_mul_non4k(u8 *op1, const u8 *op2)
+{
+	be128 a, b;
+
+	// Assume one argument is in Montgomery form and one is not.
+	copy_and_reverse((u8 *)&a, op1);
+	copy_and_reverse((u8 *)&b, op2);
+	gf128mul_x_lle(&a, &a);
+	gf128mul_lle(&a, &b);
+	copy_and_reverse(op1, (u8 *)&a);
+}
+EXPORT_SYMBOL_GPL(polyval_mul_non4k);
+
+/*
+ * Perform a POLYVAL update using non4k multiplication.  This function is used
+ * as a fallback for hardware accelerated implementations when simd registers
+ * are unavailable.
+ *
+ * Note: This function is not used for polyval-generic, instead we use the 4k
+ * lookup table implementation of finite field multiplication.
+ */
+void polyval_update_non4k(const u8 *key, const u8 *in,
+			  size_t nblocks, u8 *accumulator)
+{
+	while (nblocks--) {
+		crypto_xor(accumulator, in, POLYVAL_BLOCK_SIZE);
+		polyval_mul_non4k(accumulator, key);
+		in += POLYVAL_BLOCK_SIZE;
+	}
+}
+EXPORT_SYMBOL_GPL(polyval_update_non4k);
+
+static int polyval_setkey(struct crypto_shash *tfm,
+			  const u8 *key, unsigned int keylen)
+{
+	struct polyval_tfm_ctx *ctx = crypto_shash_ctx(tfm);
+	be128 k;
+
+	if (keylen != POLYVAL_BLOCK_SIZE)
+		return -EINVAL;
+
+	gf128mul_free_4k(ctx->gf128);
+
+	BUILD_BUG_ON(sizeof(k) != POLYVAL_BLOCK_SIZE);
+	copy_and_reverse((u8 *)&k, key);
+	gf128mul_x_lle(&k, &k);
+
+	ctx->gf128 = gf128mul_init_4k_lle(&k);
+	memzero_explicit(&k, POLYVAL_BLOCK_SIZE);
+
+	if (!ctx->gf128)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int polyval_init(struct shash_desc *desc)
+{
+	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	memset(dctx, 0, sizeof(*dctx));
+
+	return 0;
+}
+
+static int polyval_update(struct shash_desc *desc,
+			 const u8 *src, unsigned int srclen)
+{
+	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
+	const struct polyval_tfm_ctx *ctx = crypto_shash_ctx(desc->tfm);
+	u8 *pos;
+	u8 tmp[POLYVAL_BLOCK_SIZE];
+	int n;
+
+	if (dctx->bytes) {
+		n = min(srclen, dctx->bytes);
+		pos = dctx->buffer + dctx->bytes - 1;
+
+		dctx->bytes -= n;
+		srclen -= n;
+
+		while (n--)
+			*pos-- ^= *src++;
+
+		if (!dctx->bytes)
+			gf128mul_4k_lle(&dctx->buffer128, ctx->gf128);
+	}
+
+	while (srclen >= POLYVAL_BLOCK_SIZE) {
+		copy_and_reverse(tmp, src);
+		crypto_xor(dctx->buffer, tmp, POLYVAL_BLOCK_SIZE);
+		gf128mul_4k_lle(&dctx->buffer128, ctx->gf128);
+		src += POLYVAL_BLOCK_SIZE;
+		srclen -= POLYVAL_BLOCK_SIZE;
+	}
+
+	if (srclen) {
+		dctx->bytes = POLYVAL_BLOCK_SIZE - srclen;
+		pos = dctx->buffer + POLYVAL_BLOCK_SIZE - 1;
+		while (srclen--)
+			*pos-- ^= *src++;
+	}
+
+	return 0;
+}
+
+static int polyval_final(struct shash_desc *desc, u8 *dst)
+{
+	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
+	const struct polyval_tfm_ctx *ctx = crypto_shash_ctx(desc->tfm);
+
+	if (dctx->bytes)
+		gf128mul_4k_lle(&dctx->buffer128, ctx->gf128);
+	copy_and_reverse(dst, dctx->buffer);
+	return 0;
+}
+
+static void polyval_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct polyval_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	gf128mul_free_4k(ctx->gf128);
+}
+
+static struct shash_alg polyval_alg = {
+	.digestsize	= POLYVAL_DIGEST_SIZE,
+	.init		= polyval_init,
+	.update		= polyval_update,
+	.final		= polyval_final,
+	.setkey		= polyval_setkey,
+	.descsize	= sizeof(struct polyval_desc_ctx),
+	.base		= {
+		.cra_name		= "polyval",
+		.cra_driver_name	= "polyval-generic",
+		.cra_priority		= 100,
+		.cra_blocksize		= POLYVAL_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct polyval_tfm_ctx),
+		.cra_module		= THIS_MODULE,
+		.cra_exit		= polyval_exit_tfm,
+	},
+};
+
+static int __init polyval_mod_init(void)
+{
+	return crypto_register_shash(&polyval_alg);
+}
+
+static void __exit polyval_mod_exit(void)
+{
+	crypto_unregister_shash(&polyval_alg);
+}
+
+subsys_initcall(polyval_mod_init);
+module_exit(polyval_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("POLYVAL hash function");
+MODULE_ALIAS_CRYPTO("polyval");
+MODULE_ALIAS_CRYPTO("polyval-generic");
--- a/crypto/rsa.c
+++ b/crypto/rsa.c
@@ -17,6 +17,11 @@ struct rsa_mpi_key {
 	MPI n;
 	MPI e;
 	MPI d;
+	MPI p;
+	MPI q;
+	MPI dp;
+	MPI dq;
+	MPI qinv;
 };

 /*
@@ -35,16 +40,49 @@ static int _rsa_enc(const struct rsa_mpi_key *key, MPI c, MPI m)

 /*
 * RSADP function [RFC3447 sec 5.1.2]
- * m = c^d mod n;
+ * m_1 = c^dP mod p;
+ * m_2 = c^dQ mod q;
+ * h = (m_1 - m_2) * qInv mod p;
+ * m = m_2 + q * h;
 */
-static int _rsa_dec(const struct rsa_mpi_key *key, MPI m, MPI c)
+static int _rsa_dec_crt(const struct rsa_mpi_key *key, MPI m_or_m1_or_h, MPI c)
 {
+	MPI m2, m12_or_qh;
+	int ret = -ENOMEM;
+
 	/* (1) Validate 0 <= c < n */
 	if (mpi_cmp_ui(c, 0) < 0 || mpi_cmp(c, key->n) >= 0)
 		return -EINVAL;

-	/* (2) m = c^d mod n */
-	return mpi_powm(m, c, key->d, key->n);
+	m2 = mpi_alloc(0);
+	m12_or_qh = mpi_alloc(0);
+	if (!m2 || !m12_or_qh)
+		goto err_free_mpi;
+
+	/* (2i) m_1 = c^dP mod p */
+	ret = mpi_powm(m_or_m1_or_h, c, key->dp, key->p);
+	if (ret)
+		goto err_free_mpi;
+
+	/* (2i) m_2 = c^dQ mod q */
+	ret = mpi_powm(m2, c, key->dq, key->q);
+	if (ret)
+		goto err_free_mpi;
+
+	/* (2iii) h = (m_1 - m_2) * qInv mod p */
+	mpi_sub(m12_or_qh, m_or_m1_or_h, m2);
+	mpi_mulm(m_or_m1_or_h, m12_or_qh, key->qinv, key->p);
+
+	/* (2iv) m = m_2 + q * h */
+	mpi_mul(m12_or_qh, key->q, m_or_m1_or_h);
+	mpi_addm(m_or_m1_or_h, m2, m12_or_qh, key->n);
+
+	ret = 0;
+
+err_free_mpi:
+	mpi_free(m12_or_qh);
+	mpi_free(m2);
+	return ret;
 }

 static inline struct rsa_mpi_key *rsa_get_key(struct crypto_akcipher *tfm)
@@ -112,7 +150,7 @@ static int rsa_dec(struct akcipher_request *req)
 	if (!c)
 		goto err_free_m;

-	ret = _rsa_dec(pkey, m, c);
+	ret = _rsa_dec_crt(pkey, m, c);
 	if (ret)
 		goto err_free_c;

@@ -134,9 +172,19 @@ static void rsa_free_mpi_key(struct rsa_mpi_key *key)
 	mpi_free(key->d);
 	mpi_free(key->e);
 	mpi_free(key->n);
+	mpi_free(key->p);
+	mpi_free(key->q);
+	mpi_free(key->dp);
+	mpi_free(key->dq);
+	mpi_free(key->qinv);
 	key->d = NULL;
 	key->e = NULL;
 	key->n = NULL;
+	key->p = NULL;
+	key->q = NULL;
+	key->dp = NULL;
+	key->dq = NULL;
+	key->qinv = NULL;
 }

 static int rsa_check_key_length(unsigned int len)
@@ -217,6 +265,26 @@ static int rsa_set_priv_key(struct crypto_akcipher *tfm, const void *key,
 	if (!mpi_key->n)
 		goto err;

+	mpi_key->p = mpi_read_raw_data(raw_key.p, raw_key.p_sz);
+	if (!mpi_key->p)
+		goto err;
+
+	mpi_key->q = mpi_read_raw_data(raw_key.q, raw_key.q_sz);
+	if (!mpi_key->q)
+		goto err;
+
+	mpi_key->dp = mpi_read_raw_data(raw_key.dp, raw_key.dp_sz);
+	if (!mpi_key->dp)
+		goto err;
+
+	mpi_key->dq = mpi_read_raw_data(raw_key.dq, raw_key.dq_sz);
+	if (!mpi_key->dq)
+		goto err;
+
+	mpi_key->qinv = mpi_read_raw_data(raw_key.qinv, raw_key.qinv_sz);
+	if (!mpi_key->qinv)
+		goto err;
+
 	if (rsa_check_key_length(mpi_get_size(mpi_key->n) << 3)) {
 		rsa_free_mpi_key(mpi_key);
 		return -EINVAL;
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -58,7 +58,7 @@
 */
 static unsigned int sec;

-static char *alg = NULL;
+static char *alg;
 static u32 type;
 static u32 mask;
 static int mode;
@@ -71,7 +71,7 @@ static const char *check[] = {
 	"blowfish", "twofish", "serpent", "sha384", "sha512", "md4", "aes",
 	"cast6", "arc4", "michael_mic", "deflate", "crc32c", "tea", "xtea",
 	"khazad", "wp512", "wp384", "wp256", "xeta",  "fcrypt",
-	"camellia", "seed", "rmd160",
+	"camellia", "seed", "rmd160", "aria",
 	"lzo", "lzo-rle", "cts", "sha3-224", "sha3-256", "sha3-384",
 	"sha3-512", "streebog256", "streebog512",
 	NULL
@@ -1556,6 +1556,7 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		ret += tcrypt_test("rfc3686(ctr(aes))");
 		ret += tcrypt_test("ofb(aes)");
 		ret += tcrypt_test("cfb(aes)");
+		ret += tcrypt_test("xctr(aes)");
 		break;

 	case 11:
@@ -1669,10 +1670,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		ret += tcrypt_test("rmd160");
 		break;

-	case 41:
-		ret += tcrypt_test("blake2s-256");
-		break;
-
 	case 42:
 		ret += tcrypt_test("blake2b-512");
 		break;
@@ -1729,6 +1726,14 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		ret += tcrypt_test("ccm(sm4)");
 		break;

+	case 57:
+		ret += tcrypt_test("polyval");
+		break;
+
+	case 58:
+		ret += tcrypt_test("gcm(aria)");
+		break;
+
 	case 100:
 		ret += tcrypt_test("hmac(md5)");
 		break;
@@ -1865,6 +1870,12 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		ret += tcrypt_test("cfb(sm4)");
 		ret += tcrypt_test("ctr(sm4)");
 		break;
+	case 192:
+		ret += tcrypt_test("ecb(aria)");
+		ret += tcrypt_test("cbc(aria)");
+		ret += tcrypt_test("cfb(aria)");
+		ret += tcrypt_test("ctr(aria)");
+		break;
 	case 200:
 		test_cipher_speed("ecb(aes)", ENCRYPT, sec, NULL, 0,
 				speed_template_16_24_32);
@@ -2186,6 +2197,37 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 				   16, 16, aead_speed_template_19, num_mb);
 		break;

+	case 226:
+		test_cipher_speed("hctr2(aes)", ENCRYPT, sec, NULL,
+				  0, speed_template_32);
+		break;
+
+	case 227:
+		test_cipher_speed("ecb(aria)", ENCRYPT, sec, NULL, 0,
+				  speed_template_16_24_32);
+		test_cipher_speed("ecb(aria)", DECRYPT, sec, NULL, 0,
+				  speed_template_16_24_32);
+		test_cipher_speed("cbc(aria)", ENCRYPT, sec, NULL, 0,
+				  speed_template_16_24_32);
+		test_cipher_speed("cbc(aria)", DECRYPT, sec, NULL, 0,
+				  speed_template_16_24_32);
+		test_cipher_speed("cfb(aria)", ENCRYPT, sec, NULL, 0,
+				  speed_template_16_24_32);
+		test_cipher_speed("cfb(aria)", DECRYPT, sec, NULL, 0,
+				  speed_template_16_24_32);
+		test_cipher_speed("ctr(aria)", ENCRYPT, sec, NULL, 0,
+				  speed_template_16_24_32);
+		test_cipher_speed("ctr(aria)", DECRYPT, sec, NULL, 0,
+				  speed_template_16_24_32);
+		break;
+
+	case 228:
+		test_aead_speed("gcm(aria)", ENCRYPT, sec,
+				NULL, 0, 16, 8, speed_template_16_24_32);
+		test_aead_speed("gcm(aria)", DECRYPT, sec,
+				NULL, 0, 16, 8, speed_template_16_24_32);
+		break;
+
 	case 300:
 		if (alg) {
 			test_hash_speed(alg, sec, generic_hash_speed_template);
@@ -2240,10 +2282,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		test_hash_speed("rmd160", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
 		fallthrough;
-	case 316:
-		test_hash_speed("blake2s-256", sec, generic_hash_speed_template);
-		if (mode > 300 && mode < 400) break;
-		fallthrough;
 	case 317:
 		test_hash_speed("blake2b-512", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
@@ -2352,10 +2390,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		test_ahash_speed("rmd160", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
 		fallthrough;
-	case 416:
-		test_ahash_speed("blake2s-256", sec, generic_hash_speed_template);
-		if (mode > 400 && mode < 500) break;
-		fallthrough;
 	case 417:
 		test_ahash_speed("blake2b-512", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -4375,30 +4375,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.hash = __VECS(blake2b_512_tv_template)
 		}
-	}, {
-		.alg = "blake2s-128",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(blakes2s_128_tv_template)
-		}
-	}, {
-		.alg = "blake2s-160",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(blakes2s_160_tv_template)
-		}
-	}, {
-		.alg = "blake2s-224",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(blakes2s_224_tv_template)
-		}
-	}, {
-		.alg = "blake2s-256",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(blakes2s_256_tv_template)
-		}
 	}, {
 		.alg = "cbc(aes)",
 		.test = alg_test_skcipher,
@@ -4412,6 +4388,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.cipher = __VECS(anubis_cbc_tv_template)
 		},
+	}, {
+		.alg = "cbc(aria)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(aria_cbc_tv_template)
+		},
 	}, {
 		.alg = "cbc(blowfish)",
 		.test = alg_test_skcipher,
@@ -4529,6 +4511,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.cipher = __VECS(aes_cfb_tv_template)
 		},
+	}, {
+		.alg = "cfb(aria)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(aria_cfb_tv_template)
+		},
 	}, {
 		.alg = "cfb(sm4)",
 		.test = alg_test_skcipher,
@@ -4598,6 +4586,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.cipher = __VECS(aes_ctr_tv_template)
 		}
+	}, {
+		.alg = "ctr(aria)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(aria_ctr_tv_template)
+		}
 	}, {
 		.alg = "ctr(blowfish)",
 		.test = alg_test_skcipher,
@@ -4858,6 +4852,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.cipher = __VECS(arc4_tv_template)
 		}
+	}, {
+		.alg = "ecb(aria)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(aria_tv_template)
+		}
 	}, {
 		.alg = "ecb(blowfish)",
 		.test = alg_test_skcipher,
@@ -5074,6 +5074,13 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.aead = __VECS(aes_gcm_tv_template)
 		}
+	}, {
+		.alg = "gcm(aria)",
+		.generic_driver = "gcm_base(ctr(aria-generic),ghash-generic)",
+		.test = alg_test_aead,
+		.suite = {
+			.aead = __VECS(aria_gcm_tv_template)
+		}
 	}, {
 		.alg = "gcm(sm4)",
 		.generic_driver = "gcm_base(ctr(sm4-generic),ghash-generic)",
@@ -5088,6 +5095,14 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.hash = __VECS(ghash_tv_template)
 		}
+	}, {
+		.alg = "hctr2(aes)",
+		.generic_driver =
+		    "hctr2_base(xctr(aes-generic),polyval-generic)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(aes_hctr2_tv_template)
+		}
 	}, {
 		.alg = "hmac(md5)",
 		.test = alg_test_hash,
@@ -5342,6 +5357,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.hash = __VECS(poly1305_tv_template)
 		}
+	}, {
+		.alg = "polyval",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = __VECS(polyval_tv_template)
+		}
 	}, {
 		.alg = "rfc3686(ctr(aes))",
 		.test = alg_test_skcipher,
@@ -5548,6 +5569,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.cipher = __VECS(xchacha20_tv_template)
 		},
+	}, {
+		.alg = "xctr(aes)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(aes_xctr_tv_template)
+		}
 	}, {
 		.alg = "xts(aes)",
 		.generic_driver = "xts(ecb(aes-generic))",
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
--- a/crypto/twofish_common.c
+++ b/crypto/twofish_common.c
@@ -298,7 +298,7 @@ static const u32 mds[4][256] = {
 * multiplication is inefficient without hardware support.  To multiply
 * faster, I make use of the fact x is a generator for the nonzero elements,
 * so that every element p of GF(2)[x]/w(x) is either 0 or equal to (x)^n for
- * some n in 0..254.  Note that that caret is exponentiation in GF(2^8),
+ * some n in 0..254.  Note that caret is exponentiation in GF(2^8),
 * *not* polynomial notation.  So if I want to compute pq where p and q are
 * in GF(2^8), I can just say:
 *    1. if p=0 or q=0 then pq=0
--- a/crypto/xctr.c
+++ b/crypto/xctr.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * XCTR: XOR Counter mode - Adapted from ctr.c
+ *
+ * (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
+ * Copyright 2021 Google LLC
+ */
+
+/*
+ * XCTR mode is a blockcipher mode of operation used to implement HCTR2. XCTR is
+ * closely related to the CTR mode of operation; the main difference is that CTR
+ * generates the keystream using E(CTR + IV) whereas XCTR generates the
+ * keystream using E(CTR ^ IV). This allows implementations to avoid dealing
+ * with multi-limb integers (as is required in CTR mode). XCTR is also specified
+ * using little-endian arithmetic which makes it slightly faster on LE machines.
+ *
+ * See the HCTR2 paper for more details:
+ *	Length-preserving encryption with HCTR2
+ *      (https://eprint.iacr.org/2021/1441.pdf)
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/cipher.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+/* For now this implementation is limited to 16-byte blocks for simplicity */
+#define XCTR_BLOCKSIZE 16
+
+static void crypto_xctr_crypt_final(struct skcipher_walk *walk,
+				   struct crypto_cipher *tfm, u32 byte_ctr)
+{
+	u8 keystream[XCTR_BLOCKSIZE];
+	const u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+	__le32 ctr32 = cpu_to_le32(byte_ctr / XCTR_BLOCKSIZE + 1);
+
+	crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+	crypto_cipher_encrypt_one(tfm, keystream, walk->iv);
+	crypto_xor_cpy(dst, keystream, src, nbytes);
+	crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+}
+
+static int crypto_xctr_crypt_segment(struct skcipher_walk *walk,
+				    struct crypto_cipher *tfm, u32 byte_ctr)
+{
+	void (*fn)(struct crypto_tfm *, u8 *, const u8 *) =
+		   crypto_cipher_alg(tfm)->cia_encrypt;
+	const u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+	__le32 ctr32 = cpu_to_le32(byte_ctr / XCTR_BLOCKSIZE + 1);
+
+	do {
+		crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+		fn(crypto_cipher_tfm(tfm), dst, walk->iv);
+		crypto_xor(dst, src, XCTR_BLOCKSIZE);
+		crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+
+		le32_add_cpu(&ctr32, 1);
+
+		src += XCTR_BLOCKSIZE;
+		dst += XCTR_BLOCKSIZE;
+	} while ((nbytes -= XCTR_BLOCKSIZE) >= XCTR_BLOCKSIZE);
+
+	return nbytes;
+}
+
+static int crypto_xctr_crypt_inplace(struct skcipher_walk *walk,
+				    struct crypto_cipher *tfm, u32 byte_ctr)
+{
+	void (*fn)(struct crypto_tfm *, u8 *, const u8 *) =
+		   crypto_cipher_alg(tfm)->cia_encrypt;
+	unsigned long alignmask = crypto_cipher_alignmask(tfm);
+	unsigned int nbytes = walk->nbytes;
+	u8 *data = walk->src.virt.addr;
+	u8 tmp[XCTR_BLOCKSIZE + MAX_CIPHER_ALIGNMASK];
+	u8 *keystream = PTR_ALIGN(tmp + 0, alignmask + 1);
+	__le32 ctr32 = cpu_to_le32(byte_ctr / XCTR_BLOCKSIZE + 1);
+
+	do {
+		crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+		fn(crypto_cipher_tfm(tfm), keystream, walk->iv);
+		crypto_xor(data, keystream, XCTR_BLOCKSIZE);
+		crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+
+		le32_add_cpu(&ctr32, 1);
+
+		data += XCTR_BLOCKSIZE;
+	} while ((nbytes -= XCTR_BLOCKSIZE) >= XCTR_BLOCKSIZE);
+
+	return nbytes;
+}
+
+static int crypto_xctr_crypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_cipher *cipher = skcipher_cipher_simple(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int err;
+	u32 byte_ctr = 0;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while (walk.nbytes >= XCTR_BLOCKSIZE) {
+		if (walk.src.virt.addr == walk.dst.virt.addr)
+			nbytes = crypto_xctr_crypt_inplace(&walk, cipher,
+							   byte_ctr);
+		else
+			nbytes = crypto_xctr_crypt_segment(&walk, cipher,
+							   byte_ctr);
+
+		byte_ctr += walk.nbytes - nbytes;
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	if (walk.nbytes) {
+		crypto_xctr_crypt_final(&walk, cipher, byte_ctr);
+		err = skcipher_walk_done(&walk, 0);
+	}
+
+	return err;
+}
+
+static int crypto_xctr_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	struct skcipher_instance *inst;
+	struct crypto_alg *alg;
+	int err;
+
+	inst = skcipher_alloc_instance_simple(tmpl, tb);
+	if (IS_ERR(inst))
+		return PTR_ERR(inst);
+
+	alg = skcipher_ialg_simple(inst);
+
+	/* Block size must be 16 bytes. */
+	err = -EINVAL;
+	if (alg->cra_blocksize != XCTR_BLOCKSIZE)
+		goto out_free_inst;
+
+	/* XCTR mode is a stream cipher. */
+	inst->alg.base.cra_blocksize = 1;
+
+	/*
+	 * To simplify the implementation, configure the skcipher walk to only
+	 * give a partial block at the very end, never earlier.
+	 */
+	inst->alg.chunksize = alg->cra_blocksize;
+
+	inst->alg.encrypt = crypto_xctr_crypt;
+	inst->alg.decrypt = crypto_xctr_crypt;
+
+	err = skcipher_register_instance(tmpl, inst);
+	if (err) {
+out_free_inst:
+		inst->free(inst);
+	}
+
+	return err;
+}
+
+static struct crypto_template crypto_xctr_tmpl = {
+	.name = "xctr",
+	.create = crypto_xctr_create,
+	.module = THIS_MODULE,
+};
+
+static int __init crypto_xctr_module_init(void)
+{
+	return crypto_register_template(&crypto_xctr_tmpl);
+}
+
+static void __exit crypto_xctr_module_exit(void)
+{
+	crypto_unregister_template(&crypto_xctr_tmpl);
+}
+
+subsys_initcall(crypto_xctr_module_init);
+module_exit(crypto_xctr_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("XCTR block cipher mode of operation");
+MODULE_ALIAS_CRYPTO("xctr");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);