Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "Algorithms:

   - Add AES-NI/AVX/x86_64 implementation of SM4.

  Drivers:

   - Add Arm SMCCC TRNG based driver"

[ And obviously a lot of random fixes and updates  - Linus]

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (84 commits)
  crypto: sha512 - remove imaginary and mystifying clearing of variables
  crypto: aesni - xts_crypt() return if walk.nbytes is 0
  padata: Remove repeated verbose license text
  crypto: ccp - Add support for new CCP/PSP device ID
  crypto: x86/sm4 - add AES-NI/AVX2/x86_64 implementation
  crypto: x86/sm4 - export reusable AESNI/AVX functions
  crypto: rmd320 - remove rmd320 in Makefile
  crypto: skcipher - in_irq() cleanup
  crypto: hisilicon - check _PS0 and _PR0 method
  crypto: hisilicon - change parameter passing of debugfs function
  crypto: hisilicon - support runtime PM for accelerator device
  crypto: hisilicon - add runtime PM ops
  crypto: hisilicon - using 'debugfs_create_file' instead of 'debugfs_create_regset32'
  crypto: tcrypt - add GCM/CCM mode test for SM4 algorithm
  crypto: testmgr - Add GCM/CCM mode test of SM4 algorithm
  crypto: tcrypt - Fix missing return value check
  crypto: hisilicon/sec - modify the hardware endian configuration
  crypto: hisilicon/sec - fix the abnormal exiting process
  crypto: qat - store vf.compatible flag
  crypto: qat - do not export adf_iov_putmsg()
  ...

7 files changed, 195 insertions, 13 deletions

diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index 14c032de276e..545ccbddf6a1 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -128,3 +128,6 @@ config CRYPTO_LIB_CHACHA20POLY1305
 
 config CRYPTO_LIB_SHA256
 	tristate
+
+config CRYPTO_LIB_SM4
+	tristate
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index 3a435629d9ce..73205ed269ba 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -38,6 +38,9 @@ libpoly1305-y					+= poly1305.o
 obj-$(CONFIG_CRYPTO_LIB_SHA256)			+= libsha256.o
 libsha256-y					:= sha256.o
 
+obj-$(CONFIG_CRYPTO_LIB_SM4)			+= libsm4.o
+libsm4-y					:= sm4.o
+
 ifneq ($(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS),y)
 libblake2s-y					+= blake2s-selftest.o
 libchacha20poly1305-y				+= chacha20poly1305-selftest.o
diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c
index c64ac8bfb6a9..4055aa593ec4 100644
--- a/lib/crypto/blake2s.c
+++ b/lib/crypto/blake2s.c
@@ -73,7 +73,7 @@ void blake2s256_hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen,
 }
 EXPORT_SYMBOL(blake2s256_hmac);
 
-static int __init mod_init(void)
+static int __init blake2s_mod_init(void)
 {
 	if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) &&
 	    WARN_ON(!blake2s_selftest()))
@@ -81,12 +81,12 @@ static int __init mod_init(void)
 	return 0;
 }
 
-static void __exit mod_exit(void)
+static void __exit blake2s_mod_exit(void)
 {
 }
 
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(blake2s_mod_init);
+module_exit(blake2s_mod_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("BLAKE2s hash function");
 MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
diff --git a/lib/crypto/chacha20poly1305.c b/lib/crypto/chacha20poly1305.c
index c2fcdb98cc02..fa6a9440fc95 100644
--- a/lib/crypto/chacha20poly1305.c
+++ b/lib/crypto/chacha20poly1305.c
@@ -354,7 +354,7 @@ bool chacha20poly1305_decrypt_sg_inplace(struct scatterlist *src, size_t src_len
 }
 EXPORT_SYMBOL(chacha20poly1305_decrypt_sg_inplace);
 
-static int __init mod_init(void)
+static int __init chacha20poly1305_init(void)
 {
 	if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) &&
 	    WARN_ON(!chacha20poly1305_selftest()))
@@ -362,12 +362,12 @@ static int __init mod_init(void)
 	return 0;
 }
 
-static void __exit mod_exit(void)
+static void __exit chacha20poly1305_exit(void)
 {
 }
 
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(chacha20poly1305_init);
+module_exit(chacha20poly1305_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("ChaCha20Poly1305 AEAD construction");
 MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
diff --git a/lib/crypto/curve25519.c b/lib/crypto/curve25519.c
index fb29739e8c29..064b352c6907 100644
--- a/lib/crypto/curve25519.c
+++ b/lib/crypto/curve25519.c
@@ -13,7 +13,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 
-static int __init mod_init(void)
+static int __init curve25519_init(void)
 {
 	if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) &&
 	    WARN_ON(!curve25519_selftest()))
@@ -21,12 +21,12 @@ static int __init mod_init(void)
 	return 0;
 }
 
-static void __exit mod_exit(void)
+static void __exit curve25519_exit(void)
 {
 }
 
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(curve25519_init);
+module_exit(curve25519_exit);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Curve25519 scalar multiplication");
diff --git a/lib/crypto/sm4.c b/lib/crypto/sm4.c
new file mode 100644
index 000000000000..633b59fed9db
--- /dev/null
+++ b/lib/crypto/sm4.c
@@ -0,0 +1,176 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * SM4, as specified in
+ * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html
+ *
+ * Copyright (C) 2018 ARM Limited or its affiliates.
+ * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
+ */
+
+#include <linux/module.h>
+#include <asm/unaligned.h>
+#include <crypto/sm4.h>
+
+static const u32 fk[4] = {
+	0xa3b1bac6, 0x56aa3350, 0x677d9197, 0xb27022dc
+};
+
+static const u32 __cacheline_aligned ck[32] = {
+	0x00070e15, 0x1c232a31, 0x383f464d, 0x545b6269,
+	0x70777e85, 0x8c939aa1, 0xa8afb6bd, 0xc4cbd2d9,
+	0xe0e7eef5, 0xfc030a11, 0x181f262d, 0x343b4249,
+	0x50575e65, 0x6c737a81, 0x888f969d, 0xa4abb2b9,
+	0xc0c7ced5, 0xdce3eaf1, 0xf8ff060d, 0x141b2229,
+	0x30373e45, 0x4c535a61, 0x686f767d, 0x848b9299,
+	0xa0a7aeb5, 0xbcc3cad1, 0xd8dfe6ed, 0xf4fb0209,
+	0x10171e25, 0x2c333a41, 0x484f565d, 0x646b7279
+};
+
+static const u8 __cacheline_aligned sbox[256] = {
+	0xd6, 0x90, 0xe9, 0xfe, 0xcc, 0xe1, 0x3d, 0xb7,
+	0x16, 0xb6, 0x14, 0xc2, 0x28, 0xfb, 0x2c, 0x05,
+	0x2b, 0x67, 0x9a, 0x76, 0x2a, 0xbe, 0x04, 0xc3,
+	0xaa, 0x44, 0x13, 0x26, 0x49, 0x86, 0x06, 0x99,
+	0x9c, 0x42, 0x50, 0xf4, 0x91, 0xef, 0x98, 0x7a,
+	0x33, 0x54, 0x0b, 0x43, 0xed, 0xcf, 0xac, 0x62,
+	0xe4, 0xb3, 0x1c, 0xa9, 0xc9, 0x08, 0xe8, 0x95,
+	0x80, 0xdf, 0x94, 0xfa, 0x75, 0x8f, 0x3f, 0xa6,
+	0x47, 0x07, 0xa7, 0xfc, 0xf3, 0x73, 0x17, 0xba,
+	0x83, 0x59, 0x3c, 0x19, 0xe6, 0x85, 0x4f, 0xa8,
+	0x68, 0x6b, 0x81, 0xb2, 0x71, 0x64, 0xda, 0x8b,
+	0xf8, 0xeb, 0x0f, 0x4b, 0x70, 0x56, 0x9d, 0x35,
+	0x1e, 0x24, 0x0e, 0x5e, 0x63, 0x58, 0xd1, 0xa2,
+	0x25, 0x22, 0x7c, 0x3b, 0x01, 0x21, 0x78, 0x87,
+	0xd4, 0x00, 0x46, 0x57, 0x9f, 0xd3, 0x27, 0x52,
+	0x4c, 0x36, 0x02, 0xe7, 0xa0, 0xc4, 0xc8, 0x9e,
+	0xea, 0xbf, 0x8a, 0xd2, 0x40, 0xc7, 0x38, 0xb5,
+	0xa3, 0xf7, 0xf2, 0xce, 0xf9, 0x61, 0x15, 0xa1,
+	0xe0, 0xae, 0x5d, 0xa4, 0x9b, 0x34, 0x1a, 0x55,
+	0xad, 0x93, 0x32, 0x30, 0xf5, 0x8c, 0xb1, 0xe3,
+	0x1d, 0xf6, 0xe2, 0x2e, 0x82, 0x66, 0xca, 0x60,
+	0xc0, 0x29, 0x23, 0xab, 0x0d, 0x53, 0x4e, 0x6f,
+	0xd5, 0xdb, 0x37, 0x45, 0xde, 0xfd, 0x8e, 0x2f,
+	0x03, 0xff, 0x6a, 0x72, 0x6d, 0x6c, 0x5b, 0x51,
+	0x8d, 0x1b, 0xaf, 0x92, 0xbb, 0xdd, 0xbc, 0x7f,
+	0x11, 0xd9, 0x5c, 0x41, 0x1f, 0x10, 0x5a, 0xd8,
+	0x0a, 0xc1, 0x31, 0x88, 0xa5, 0xcd, 0x7b, 0xbd,
+	0x2d, 0x74, 0xd0, 0x12, 0xb8, 0xe5, 0xb4, 0xb0,
+	0x89, 0x69, 0x97, 0x4a, 0x0c, 0x96, 0x77, 0x7e,
+	0x65, 0xb9, 0xf1, 0x09, 0xc5, 0x6e, 0xc6, 0x84,
+	0x18, 0xf0, 0x7d, 0xec, 0x3a, 0xdc, 0x4d, 0x20,
+	0x79, 0xee, 0x5f, 0x3e, 0xd7, 0xcb, 0x39, 0x48
+};
+
+static inline u32 sm4_t_non_lin_sub(u32 x)
+{
+	u32 out;
+
+	out  = (u32)sbox[x & 0xff];
+	out |= (u32)sbox[(x >> 8) & 0xff] << 8;
+	out |= (u32)sbox[(x >> 16) & 0xff] << 16;
+	out |= (u32)sbox[(x >> 24) & 0xff] << 24;
+
+	return out;
+}
+
+static inline u32 sm4_key_lin_sub(u32 x)
+{
+	return x ^ rol32(x, 13) ^ rol32(x, 23);
+}
+
+static inline u32 sm4_enc_lin_sub(u32 x)
+{
+	return x ^ rol32(x, 2) ^ rol32(x, 10) ^ rol32(x, 18) ^ rol32(x, 24);
+}
+
+static inline u32 sm4_key_sub(u32 x)
+{
+	return sm4_key_lin_sub(sm4_t_non_lin_sub(x));
+}
+
+static inline u32 sm4_enc_sub(u32 x)
+{
+	return sm4_enc_lin_sub(sm4_t_non_lin_sub(x));
+}
+
+static inline u32 sm4_round(u32 x0, u32 x1, u32 x2, u32 x3, u32 rk)
+{
+	return x0 ^ sm4_enc_sub(x1 ^ x2 ^ x3 ^ rk);
+}
+
+
+/**
+ * sm4_expandkey - Expands the SM4 key as described in GB/T 32907-2016
+ * @ctx:	The location where the computed key will be stored.
+ * @in_key:	The supplied key.
+ * @key_len:	The length of the supplied key.
+ *
+ * Returns 0 on success. The function fails only if an invalid key size (or
+ * pointer) is supplied.
+ */
+int sm4_expandkey(struct sm4_ctx *ctx, const u8 *in_key,
+			  unsigned int key_len)
+{
+	u32 rk[4];
+	const u32 *key = (u32 *)in_key;
+	int i;
+
+	if (key_len != SM4_KEY_SIZE)
+		return -EINVAL;
+
+	rk[0] = get_unaligned_be32(&key[0]) ^ fk[0];
+	rk[1] = get_unaligned_be32(&key[1]) ^ fk[1];
+	rk[2] = get_unaligned_be32(&key[2]) ^ fk[2];
+	rk[3] = get_unaligned_be32(&key[3]) ^ fk[3];
+
+	for (i = 0; i < 32; i += 4) {
+		rk[0] ^= sm4_key_sub(rk[1] ^ rk[2] ^ rk[3] ^ ck[i + 0]);
+		rk[1] ^= sm4_key_sub(rk[2] ^ rk[3] ^ rk[0] ^ ck[i + 1]);
+		rk[2] ^= sm4_key_sub(rk[3] ^ rk[0] ^ rk[1] ^ ck[i + 2]);
+		rk[3] ^= sm4_key_sub(rk[0] ^ rk[1] ^ rk[2] ^ ck[i + 3]);
+
+		ctx->rkey_enc[i + 0] = rk[0];
+		ctx->rkey_enc[i + 1] = rk[1];
+		ctx->rkey_enc[i + 2] = rk[2];
+		ctx->rkey_enc[i + 3] = rk[3];
+		ctx->rkey_dec[31 - 0 - i] = rk[0];
+		ctx->rkey_dec[31 - 1 - i] = rk[1];
+		ctx->rkey_dec[31 - 2 - i] = rk[2];
+		ctx->rkey_dec[31 - 3 - i] = rk[3];
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sm4_expandkey);
+
+/**
+ * sm4_crypt_block - Encrypt or decrypt a single SM4 block
+ * @rk:		The rkey_enc for encrypt or rkey_dec for decrypt
+ * @out:	Buffer to store output data
+ * @in: 	Buffer containing the input data
+ */
+void sm4_crypt_block(const u32 *rk, u8 *out, const u8 *in)
+{
+	u32 x[4], i;
+
+	x[0] = get_unaligned_be32(in + 0 * 4);
+	x[1] = get_unaligned_be32(in + 1 * 4);
+	x[2] = get_unaligned_be32(in + 2 * 4);
+	x[3] = get_unaligned_be32(in + 3 * 4);
+
+	for (i = 0; i < 32; i += 4) {
+		x[0] = sm4_round(x[0], x[1], x[2], x[3], rk[i + 0]);
+		x[1] = sm4_round(x[1], x[2], x[3], x[0], rk[i + 1]);
+		x[2] = sm4_round(x[2], x[3], x[0], x[1], rk[i + 2]);
+		x[3] = sm4_round(x[3], x[0], x[1], x[2], rk[i + 3]);
+	}
+
+	put_unaligned_be32(x[3 - 0], out + 0 * 4);
+	put_unaligned_be32(x[3 - 1], out + 1 * 4);
+	put_unaligned_be32(x[3 - 2], out + 2 * 4);
+	put_unaligned_be32(x[3 - 3], out + 3 * 4);
+}
+EXPORT_SYMBOL_GPL(sm4_crypt_block);
+
+MODULE_DESCRIPTION("Generic SM4 library");
+MODULE_LICENSE("GPL v2");
diff --git a/lib/mpi/mpiutil.c b/lib/mpi/mpiutil.c
index 9a75ca3f7edf..bc81419f400c 100644
--- a/lib/mpi/mpiutil.c
+++ b/lib/mpi/mpiutil.c
@@ -148,7 +148,7 @@ int mpi_resize(MPI a, unsigned nlimbs)
 		return 0;	/* no need to do it */
 
 	if (a->d) {
-		p = kmalloc_array(nlimbs, sizeof(mpi_limb_t), GFP_KERNEL);
+		p = kcalloc(nlimbs, sizeof(mpi_limb_t), GFP_KERNEL);
 		if (!p)
 			return -ENOMEM;
 		memcpy(p, a->d, a->alloced * sizeof(mpi_limb_t));