// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Support for Intel AES-NI instructions. This file contains glue
 * code, the real AES implementation is in intel-aes_asm.S.
 *
 * Copyright (C) 2008, Intel Corp.
 *    Author: Huang Ying <ying.huang@intel.com>
 *
 * Added RFC4106 AES-GCM support for 128-bit keys under the AEAD
 * interface for 64-bit kernels.
 *    Authors: Adrian Hoban <adrian.hoban@intel.com>
 *             Gabriele Paoloni <gabriele.paoloni@intel.com>
 *             Tadeusz Struk (tadeusz.struk@intel.com)
 *             Aidan O'Mahony (aidan.o.mahony@intel.com)
 *    Copyright (c) 2010, Intel Corporation.
 */

#include <linux/hardirq.h>
#include <linux/types.h>
#include <linux/module.h>
#include <linux/err.h>
#include <crypto/algapi.h>
#include <crypto/aes.h>
#include <crypto/ctr.h>
#include <crypto/b128ops.h>
#include <crypto/gcm.h>
#include <crypto/xts.h>
#include <asm/cpu_device_id.h>
#include <asm/simd.h>
#include <crypto/scatterwalk.h>
#include <crypto/internal/aead.h>
#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <linux/jump_label.h>
#include <linux/workqueue.h>
#include <linux/spinlock.h>
#include <linux/static_call.h>

#include "aes-intel_glue.h"
#include "aesni-intel_glue.h"

#define RFC4106_HASH_SUBKEY_SIZE 16

/* This data is stored at the end of the crypto_tfm struct.
 * It's a type of per "session" data storage location.
 * This needs to be 16 byte aligned.
 */
struct aesni_rfc4106_gcm_ctx {
	u8 hash_subkey[16] AES_ALIGN_ATTR;
	struct crypto_aes_ctx aes_key_expanded AES_ALIGN_ATTR;
	u8 nonce[4];
};

struct generic_gcmaes_ctx {
	u8 hash_subkey[16] AES_ALIGN_ATTR;
	struct crypto_aes_ctx aes_key_expanded AES_ALIGN_ATTR;
};

#define GCM_BLOCK_LEN 16

struct gcm_context_data {
	/* init, update and finalize context data */
	u8 aad_hash[GCM_BLOCK_LEN];
	u64 aad_length;
	u64 in_length;
	u8 partial_block_enc_key[GCM_BLOCK_LEN];
	u8 orig_IV[GCM_BLOCK_LEN];
	u8 current_counter[GCM_BLOCK_LEN];
	u64 partial_block_len;
	u64 unused;
	u8 hash_keys[GCM_BLOCK_LEN * 16];
};

asmlinkage int _aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
			      unsigned int key_len);
asmlinkage void _aesni_enc(const void *ctx, u8 *out, const u8 *in);
asmlinkage void _aesni_dec(const void *ctx, u8 *out, const u8 *in);
asmlinkage void aesni_ecb_enc(struct crypto_aes_ctx *ctx, u8 *out,
			      const u8 *in, unsigned int len);
asmlinkage void aesni_ecb_dec(struct crypto_aes_ctx *ctx, u8 *out,
			      const u8 *in, unsigned int len);
asmlinkage void aesni_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out,
			      const u8 *in, unsigned int len, u8 *iv);
asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
			      const u8 *in, unsigned int len, u8 *iv);
asmlinkage void aesni_cts_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out,
				  const u8 *in, unsigned int len, u8 *iv);
asmlinkage void aesni_cts_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
				  const u8 *in, unsigned int len, u8 *iv);

int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
		  unsigned int key_len)
{
	return _aesni_set_key(ctx, in_key, key_len);
}
EXPORT_SYMBOL_GPL(aesni_set_key);

int aesni_enc(const void *ctx, u8 *out, const u8 *in)
{
	_aesni_enc(ctx, out, in);
	return 0;
}
EXPORT_SYMBOL_GPL(aesni_enc);

int aesni_dec(const void *ctx, u8 *out, const u8 *in)
{
	_aesni_dec(ctx, out, in);
	return 0;
}
EXPORT_SYMBOL_GPL(aesni_dec);

#define AVX_GEN2_OPTSIZE 640
#define AVX_GEN4_OPTSIZE 4096

asmlinkage void _aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *out,
				   const u8 *in, unsigned int len, u8 *iv);

asmlinkage void _aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *out,
				   const u8 *in, unsigned int len, u8 *iv);

int aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *out, const u8 *in,
		      unsigned int len, u8 *iv)
{
	_aesni_xts_encrypt(ctx, out, in, len, iv);
	return 0;
}
EXPORT_SYMBOL_GPL(aesni_xts_encrypt);

int aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *out, const u8 *in,
		      unsigned int len, u8 *iv)
{
	_aesni_xts_decrypt(ctx, out, in, len, iv);
	return 0;
}
EXPORT_SYMBOL_GPL(aesni_xts_decrypt);

#ifdef CONFIG_X86_64

asmlinkage void aesni_ctr_enc(struct crypto_aes_ctx *ctx, u8 *out,
			      const u8 *in, unsigned int len, u8 *iv);
DEFINE_STATIC_CALL(aesni_ctr_enc_tfm, aesni_ctr_enc);

/* Scatter / Gather routines, with args similar to above */
asmlinkage void aesni_gcm_init(void *ctx,
			       struct gcm_context_data *gdata,
			       u8 *iv,
			       u8 *hash_subkey, const u8 *aad,
			       unsigned long aad_len);
asmlinkage void aesni_gcm_enc_update(void *ctx,
				     struct gcm_context_data *gdata, u8 *out,
				     const u8 *in, unsigned long plaintext_len);
asmlinkage void aesni_gcm_dec_update(void *ctx,
				     struct gcm_context_data *gdata, u8 *out,
				     const u8 *in,
				     unsigned long ciphertext_len);
asmlinkage void aesni_gcm_finalize(void *ctx,
				   struct gcm_context_data *gdata,
				   u8 *auth_tag, unsigned long auth_tag_len);

asmlinkage void aes_ctr_enc_128_avx_by8(const u8 *in, u8 *iv,
		void *keys, u8 *out, unsigned int num_bytes);
asmlinkage void aes_ctr_enc_192_avx_by8(const u8 *in, u8 *iv,
		void *keys, u8 *out, unsigned int num_bytes);
asmlinkage void aes_ctr_enc_256_avx_by8(const u8 *in, u8 *iv,
		void *keys, u8 *out, unsigned int num_bytes);
/*
 * asmlinkage void aesni_gcm_init_avx_gen2()
 * gcm_data *my_ctx_data, context data
 * u8 *hash_subkey,  the Hash sub key input. Data starts on a 16-byte boundary.
 */
asmlinkage void aesni_gcm_init_avx_gen2(void *my_ctx_data,
					struct gcm_context_data *gdata,
					u8 *iv,
					u8 *hash_subkey,
					const u8 *aad,
					unsigned long aad_len);

asmlinkage void aesni_gcm_enc_update_avx_gen2(void *ctx,
				     struct gcm_context_data *gdata, u8 *out,
				     const u8 *in, unsigned long plaintext_len);
asmlinkage void aesni_gcm_dec_update_avx_gen2(void *ctx,
				     struct gcm_context_data *gdata, u8 *out,
				     const u8 *in,
				     unsigned long ciphertext_len);
asmlinkage void aesni_gcm_finalize_avx_gen2(void *ctx,
				   struct gcm_context_data *gdata,
				   u8 *auth_tag, unsigned long auth_tag_len);

/*
 * asmlinkage void aesni_gcm_init_avx_gen4()
 * gcm_data *my_ctx_data, context data
 * u8 *hash_subkey,  the Hash sub key input. Data starts on a 16-byte boundary.
 */
asmlinkage void aesni_gcm_init_avx_gen4(void *my_ctx_data,
					struct gcm_context_data *gdata,
					u8 *iv,
					u8 *hash_subkey,
					const u8 *aad,
					unsigned long aad_len);

asmlinkage void aesni_gcm_enc_update_avx_gen4(void *ctx,
				     struct gcm_context_data *gdata, u8 *out,
				     const u8 *in, unsigned long plaintext_len);
asmlinkage void aesni_gcm_dec_update_avx_gen4(void *ctx,
				     struct gcm_context_data *gdata, u8 *out,
				     const u8 *in,
				     unsigned long ciphertext_len);
asmlinkage void aesni_gcm_finalize_avx_gen4(void *ctx,
				   struct gcm_context_data *gdata,
				   u8 *auth_tag, unsigned long auth_tag_len);

static __ro_after_init DEFINE_STATIC_KEY_FALSE(gcm_use_avx);
static __ro_after_init DEFINE_STATIC_KEY_FALSE(gcm_use_avx2);

static inline struct
aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm)
{
	unsigned long align = AES_ALIGN;

	if (align <= crypto_tfm_ctx_alignment())
		align = 1;
	return PTR_ALIGN(crypto_aead_ctx(tfm), align);
}

static inline struct
generic_gcmaes_ctx *generic_gcmaes_ctx_get(struct crypto_aead *tfm)
{
	unsigned long align = AES_ALIGN;

	if (align <= crypto_tfm_ctx_alignment())
		align = 1;
	return PTR_ALIGN(crypto_aead_ctx(tfm), align);
}
#endif

static int aes_set_key_common(struct crypto_tfm *tfm, void *raw_ctx,
			      const u8 *in_key, unsigned int key_len)
{
	struct crypto_aes_ctx *ctx = aes_ctx(raw_ctx);
	int err;

	if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 &&
	    key_len != AES_KEYSIZE_256)
		return -EINVAL;

	if (!crypto_simd_usable())
		err = aes_expandkey(ctx, in_key, key_len);
	else {
		kernel_fpu_begin();
		err = _aesni_set_key(ctx, in_key, key_len);
		kernel_fpu_end();
	}

	return err;
}

static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
		       unsigned int key_len)
{
	return aes_set_key_common(tfm, crypto_tfm_ctx(tfm), in_key, key_len);
}

static void aesni_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
{
	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));

	if (!crypto_simd_usable()) {
		aes_encrypt(ctx, dst, src);
	} else {
		kernel_fpu_begin();
		_aesni_enc(ctx, dst, src);
		kernel_fpu_end();
	}
}

static void aesni_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
{
	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));

	if (!crypto_simd_usable()) {
		aes_decrypt(ctx, dst, src);
	} else {
		kernel_fpu_begin();
		_aesni_dec(ctx, dst, src);
		kernel_fpu_end();
	}
}

static int aesni_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
			         unsigned int len)
{
	return aes_set_key_common(crypto_skcipher_tfm(tfm),
				  crypto_skcipher_ctx(tfm), key, len);
}

static int ecb_encrypt(struct skcipher_request *req)
{
	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
	struct skcipher_walk walk;
	unsigned int nbytes;
	int err;

	err = skcipher_walk_virt(&walk, req, false);

	while ((nbytes = walk.nbytes)) {
		kernel_fpu_begin();
		aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
			      nbytes & AES_BLOCK_MASK);
		kernel_fpu_end();
		nbytes &= AES_BLOCK_SIZE - 1;
		err = skcipher_walk_done(&walk, nbytes);
	}

	return err;
}

static int ecb_decrypt(struct skcipher_request *req)
{
	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
	struct skcipher_walk walk;
	unsigned int nbytes;
	int err;

	err = skcipher_walk_virt(&walk, req, false);

	while ((nbytes = walk.nbytes)) {
		kernel_fpu_begin();
		aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
			      nbytes & AES_BLOCK_MASK);
		kernel_fpu_end();
		nbytes &= AES_BLOCK_SIZE - 1;
		err = skcipher_walk_done(&walk, nbytes);
	}

	return err;
}

static int cbc_encrypt(struct skcipher_request *req)
{
	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
	struct skcipher_walk walk;
	unsigned int nbytes;
	int err;

	err = skcipher_walk_virt(&walk, req, false);

	while ((nbytes = walk.nbytes)) {
		kernel_fpu_begin();
		aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
			      nbytes & AES_BLOCK_MASK, walk.iv);
		kernel_fpu_end();
		nbytes &= AES_BLOCK_SIZE - 1;
		err = skcipher_walk_done(&walk, nbytes);
	}

	return err;
}

static int cbc_decrypt(struct skcipher_request *req)
{
	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
	struct skcipher_walk walk;
	unsigned int nbytes;
	int err;

	err = skcipher_walk_virt(&walk, req, false);

	while ((nbytes = walk.nbytes)) {
		kernel_fpu_begin();
		aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
			      nbytes & AES_BLOCK_MASK, walk.iv);
		kernel_fpu_end();
		nbytes &= AES_BLOCK_SIZE - 1;
		err = skcipher_walk_done(&walk, nbytes);
	}

	return err;
}

static int cts_cbc_encrypt(struct skcipher_request *req)
{
	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
	int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
	struct scatterlist *src = req->src, *dst = req->dst;
	struct scatterlist sg_src[2], sg_dst[2];
	struct skcipher_request subreq;
	struct skcipher_walk walk;
	int err;

	skcipher_request_set_tfm(&subreq, tfm);
	skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
				      NULL, NULL);

	if (req->cryptlen <= AES_BLOCK_SIZE) {
		if (req->cryptlen < AES_BLOCK_SIZE)
			return -EINVAL;
		cbc_blocks = 1;
	}

	if (cbc_blocks > 0) {
		skcipher_request_set_crypt(&subreq, req->src, req->dst,
					   cbc_blocks * AES_BLOCK_SIZE,
					   req->iv);

		err = cbc_encrypt(&subreq);
		if (err)
			return err;

		if (req->cryptlen == AES_BLOCK_SIZE)
			return 0;

		dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
		if (req->dst != req->src)
			dst = scatterwalk_ffwd(sg_dst, req->dst,
					       subreq.cryptlen);
	}

	/* handle ciphertext stealing */
	skcipher_request_set_crypt(&subreq, src, dst,
				   req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
				   req->iv);

	err = skcipher_walk_virt(&walk, &subreq, false);
	if (err)
		return err;

	kernel_fpu_begin();
	aesni_cts_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
			  walk.nbytes, walk.iv);
	kernel_fpu_end();

	return skcipher_walk_done(&walk, 0);
}

static int cts_cbc_decrypt(struct skcipher_request *req)
{
	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
	int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
	struct scatterlist *src = req->src, *dst = req->dst;
	struct scatterlist sg_src[2], sg_dst[2];
	struct skcipher_request subreq;
	struct skcipher_walk walk;
	int err;

	skcipher_request_set_tfm(&subreq, tfm);
	skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
				      NULL, NULL);

	if (req->cryptlen <= AES_BLOCK_SIZE) {
		if (req->cryptlen < AES_BLOCK_SIZE)
			return -EINVAL;
		cbc_blocks = 1;
	}

	if (cbc_blocks > 0) {
		skcipher_request_set_crypt(&subreq, req->src, req->dst,
					   cbc_blocks * AES_BLOCK_SIZE,
					   req->iv);

		err = cbc_decrypt(&subreq);
		if (err)
			return err;

		if (req->cryptlen == AES_BLOCK_SIZE)
			return 0;

		dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
		if (req->dst != req->src)
			dst = scatterwalk_ffwd(sg_dst, req->dst,
					       subreq.cryptlen);
	}

	/* handle ciphertext stealing */
	skcipher_request_set_crypt(&subreq, src, dst,
				   req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
				   req->iv);

	err = skcipher_walk_virt(&walk, &subreq, false);
	if (err)
		return err;

	kernel_fpu_begin();
	aesni_cts_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
			  walk.nbytes, walk.iv);
	kernel_fpu_end();

	return skcipher_walk_done(&walk, 0);
}

#ifdef CONFIG_X86_64
static void aesni_ctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out,
				 const u8 *in, unsigned int len, u8 *iv)
{
	/*
	 * based on key length, override with the by8 version
	 * of ctr mode encryption/decryption for improved performance
	 * aes_set_key_common() ensures that key length is one of
	 * {128,192,256}
	 */
	if (ctx->key_length == AES_KEYSIZE_128)
		aes_ctr_enc_128_avx_by8(in, iv, (void *)ctx, out, len);
	else if (ctx->key_length == AES_KEYSIZE_192)
		aes_ctr_enc_192_avx_by8(in, iv, (void *)ctx, out, len);
	else
		aes_ctr_enc_256_avx_by8(in, iv, (void *)ctx, out, len);
}

static int ctr_crypt(struct skcipher_request *req)
{
	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
	u8 keystream[AES_BLOCK_SIZE];
	struct skcipher_walk walk;
	unsigned int nbytes;
	int err;

	err = skcipher_walk_virt(&walk, req, false);

	while ((nbytes = walk.nbytes) > 0) {
		kernel_fpu_begin();
		if (nbytes & AES_BLOCK_MASK)
			static_call(aesni_ctr_enc_tfm)(ctx, walk.dst.virt.addr,
						       walk.src.virt.addr,
						       nbytes & AES_BLOCK_MASK,
						       walk.iv);
		nbytes &= ~AES_BLOCK_MASK;

		if (walk.nbytes == walk.total && nbytes > 0) {
			_aesni_enc(ctx, keystream, walk.iv);
			crypto_xor_cpy(walk.dst.virt.addr + walk.nbytes - nbytes,
				       walk.src.virt.addr + walk.nbytes - nbytes,
				       keystream, nbytes);
			crypto_inc(walk.iv, AES_BLOCK_SIZE);
			nbytes = 0;
		}
		kernel_fpu_end();
		err = skcipher_walk_done(&walk, nbytes);
	}
	return err;
}

static int
rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len)
{
	struct crypto_aes_ctx ctx;
	int ret;

	ret = aes_expandkey(&ctx, key, key_len);
	if (ret)
		return ret;

	/* Clear the data in the hash sub key container to zero.*/
	/* We want to cipher all zeros to create the hash sub key. */
	memset(hash_subkey, 0, RFC4106_HASH_SUBKEY_SIZE);

	aes_encrypt(&ctx, hash_subkey, hash_subkey);

	memzero_explicit(&ctx, sizeof(ctx));
	return 0;
}

static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key,
				  unsigned int key_len)
{
	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(aead);

	if (key_len < 4)
		return -EINVAL;

	/*Account for 4 byte nonce at the end.*/
	key_len -= 4;

	memcpy(ctx->nonce, key + key_len, sizeof(ctx->nonce));

	return aes_set_key_common(crypto_aead_tfm(aead),
				  &ctx->aes_key_expanded, key, key_len) ?:
	       rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
}

/* This is the Integrity Check Value (aka the authentication tag) length and can
 * be 8, 12 or 16 bytes long. */
static int common_rfc4106_set_authsize(struct crypto_aead *aead,
				       unsigned int authsize)
{
	switch (authsize) {
	case 8:
	case 12:
	case 16:
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static int generic_gcmaes_set_authsize(struct crypto_aead *tfm,
				       unsigned int authsize)
{
	switch (authsize) {
	case 4:
	case 8:
	case 12:
	case 13:
	case 14:
	case 15:
	case 16:
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req,
			      unsigned int assoclen, u8 *hash_subkey,
			      u8 *iv, void *aes_ctx, u8 *auth_tag,
			      unsigned long auth_tag_len)
{
	u8 databuf[sizeof(struct gcm_context_data) + (AES_ALIGN - 8)] __aligned(8);
	struct gcm_context_data *data = PTR_ALIGN((void *)databuf, AES_ALIGN);
	unsigned long left = req->cryptlen;
	struct scatter_walk assoc_sg_walk;
	struct skcipher_walk walk;
	bool do_avx, do_avx2;
	u8 *assocmem = NULL;
	u8 *assoc;
	int err;

	if (!enc)
		left -= auth_tag_len;

	do_avx = (left >= AVX_GEN2_OPTSIZE);
	do_avx2 = (left >= AVX_GEN4_OPTSIZE);

	/* Linearize assoc, if not already linear */
	if (req->src->length >= assoclen && req->src->length) {
		scatterwalk_start(&assoc_sg_walk, req->src);
		assoc = scatterwalk_map(&assoc_sg_walk);
	} else {
		gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
			      GFP_KERNEL : GFP_ATOMIC;

		/* assoc can be any length, so must be on heap */
		assocmem = kmalloc(assoclen, flags);
		if (unlikely(!assocmem))
			return -ENOMEM;
		assoc = assocmem;

		scatterwalk_map_and_copy(assoc, req->src, 0, assoclen, 0);
	}

	kernel_fpu_begin();
	if (static_branch_likely(&gcm_use_avx2) && do_avx2)
		aesni_gcm_init_avx_gen4(aes_ctx, data, iv, hash_subkey, assoc,
					assoclen);
	else if (static_branch_likely(&gcm_use_avx) && do_avx)
		aesni_gcm_init_avx_gen2(aes_ctx, data, iv, hash_subkey, assoc,
					assoclen);
	else
		aesni_gcm_init(aes_ctx, data, iv, hash_subkey, assoc, assoclen);
	kernel_fpu_end();

	if (!assocmem)
		scatterwalk_unmap(assoc);
	else
		kfree(assocmem);

	err = enc ? skcipher_walk_aead_encrypt(&walk, req, false)
		  : skcipher_walk_aead_decrypt(&walk, req, false);

	while (walk.nbytes > 0) {
		kernel_fpu_begin();
		if (static_branch_likely(&gcm_use_avx2) && do_avx2) {
			if (enc)
				aesni_gcm_enc_update_avx_gen4(aes_ctx, data,
							      walk.dst.virt.addr,
							      walk.src.virt.addr,
							      walk.nbytes);
			else
				aesni_gcm_dec_update_avx_gen4(aes_ctx, data,
							      walk.dst.virt.addr,
							      walk.src.virt.addr,
							      walk.nbytes);
		} else if (static_branch_likely(&gcm_use_avx) && do_avx) {
			if (enc)
				aesni_gcm_enc_update_avx_gen2(aes_ctx, data,
							      walk.dst.virt.addr,
							      walk.src.virt.addr,
							      walk.nbytes);
			else
				aesni_gcm_dec_update_avx_gen2(aes_ctx, data,
							      walk.dst.virt.addr,
							      walk.src.virt.addr,
							      walk.nbytes);
		} else if (enc) {
			aesni_gcm_enc_update(aes_ctx, data, walk.dst.virt.addr,
					     walk.src.virt.addr, walk.nbytes);
		} else {
			aesni_gcm_dec_update(aes_ctx, data, walk.dst.virt.addr,
					     walk.src.virt.addr, walk.nbytes);
		}
		kernel_fpu_end();

		err = skcipher_walk_done(&walk, 0);
	}

	if (err)
		return err;

	kernel_fpu_begin();
	if (static_branch_likely(&gcm_use_avx2) && do_avx2)
		aesni_gcm_finalize_avx_gen4(aes_ctx, data, auth_tag,
					    auth_tag_len);
	else if (static_branch_likely(&gcm_use_avx) && do_avx)
		aesni_gcm_finalize_avx_gen2(aes_ctx, data, auth_tag,
					    auth_tag_len);
	else
		aesni_gcm_finalize(aes_ctx, data, auth_tag, auth_tag_len);
	kernel_fpu_end();

	return 0;
}

static int gcmaes_encrypt(struct aead_request *req, unsigned int assoclen,
			  u8 *hash_subkey, u8 *iv, void *aes_ctx)
{
	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
	u8 auth_tag[16];
	int err;

	err = gcmaes_crypt_by_sg(true, req, assoclen, hash_subkey, iv, aes_ctx,
				 auth_tag, auth_tag_len);
	if (err)
		return err;

	scatterwalk_map_and_copy(auth_tag, req->dst,
				 req->assoclen + req->cryptlen,
				 auth_tag_len, 1);
	return 0;
}

static int gcmaes_decrypt(struct aead_request *req, unsigned int assoclen,
			  u8 *hash_subkey, u8 *iv, void *aes_ctx)
{
	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
	u8 auth_tag_msg[16];
	u8 auth_tag[16];
	int err;

	err = gcmaes_crypt_by_sg(false, req, assoclen, hash_subkey, iv, aes_ctx,
				 auth_tag, auth_tag_len);
	if (err)
		return err;

	/* Copy out original auth_tag */
	scatterwalk_map_and_copy(auth_tag_msg, req->src,
				 req->assoclen + req->cryptlen - auth_tag_len,
				 auth_tag_len, 0);

	/* Compare generated tag with passed in tag. */
	if (crypto_memneq(auth_tag_msg, auth_tag, auth_tag_len)) {
		memzero_explicit(auth_tag, sizeof(auth_tag));
		return -EBADMSG;
	}
	return 0;
}

static int helper_rfc4106_encrypt(struct aead_request *req)
{
	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
	void *aes_ctx = &(ctx->aes_key_expanded);
	u8 ivbuf[16 + (AES_ALIGN - 8)] __aligned(8);
	u8 *iv = PTR_ALIGN(&ivbuf[0], AES_ALIGN);
	unsigned int i;
	__be32 counter = cpu_to_be32(1);

	/* Assuming we are supporting rfc4106 64-bit extended */
	/* sequence numbers We need to have the AAD length equal */
	/* to 16 or 20 bytes */
	if (unlikely(req->assoclen != 16 && req->assoclen != 20))
		return -EINVAL;

	/* IV below built */
	for (i = 0; i < 4; i++)
		*(iv+i) = ctx->nonce[i];
	for (i = 0; i < 8; i++)
		*(iv+4+i) = req->iv[i];
	*((__be32 *)(iv+12)) = counter;

	return gcmaes_encrypt(req, req->assoclen - 8, ctx->hash_subkey, iv,
			      aes_ctx);
}

static int helper_rfc4106_decrypt(struct aead_request *req)
{
	__be32 counter = cpu_to_be32(1);
	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
	void *aes_ctx = &(ctx->aes_key_expanded);
	u8 ivbuf[16 + (AES_ALIGN - 8)] __aligned(8);
	u8 *iv = PTR_ALIGN(&ivbuf[0], AES_ALIGN);
	unsigned int i;

	if (unlikely(req->assoclen != 16 && req->assoclen != 20))
		return -EINVAL;

	/* Assuming we are supporting rfc4106 64-bit extended */
	/* sequence numbers We need to have the AAD length */
	/* equal to 16 or 20 bytes */

	/* IV below built */
	for (i = 0; i < 4; i++)
		*(iv+i) = ctx->nonce[i];
	for (i = 0; i < 8; i++)
		*(iv+4+i) = req->iv[i];
	*((__be32 *)(iv+12)) = counter;

	return gcmaes_decrypt(req, req->assoclen - 8, ctx->hash_subkey, iv,
			      aes_ctx);
}
#endif

static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key,
			    unsigned int keylen)
{
	return xts_setkey_common(tfm, key, keylen, aes_set_key_common);
}

static int xts_encrypt(struct skcipher_request *req)
{
	return xts_crypt_common(req, aesni_xts_encrypt, aesni_enc);
}

static int xts_decrypt(struct skcipher_request *req)
{
	return xts_crypt_common(req, aesni_xts_decrypt, aesni_enc);
}

static struct crypto_alg aesni_cipher_alg = {
	.cra_name		= "aes",
	.cra_driver_name	= "aes-aesni",
	.cra_priority		= 300,
	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
	.cra_blocksize		= AES_BLOCK_SIZE,
	.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
	.cra_module		= THIS_MODULE,
	.cra_u	= {
		.cipher	= {
			.cia_min_keysize	= AES_MIN_KEY_SIZE,
			.cia_max_keysize	= AES_MAX_KEY_SIZE,
			.cia_setkey		= aes_set_key,
			.cia_encrypt		= aesni_encrypt,
			.cia_decrypt		= aesni_decrypt
		}
	}
};

static struct skcipher_alg aesni_skciphers[] = {
	{
		.base = {
			.cra_name		= "__ecb(aes)",
			.cra_driver_name	= "__ecb-aes-aesni",
			.cra_priority		= 400,
			.cra_flags		= CRYPTO_ALG_INTERNAL,
			.cra_blocksize		= AES_BLOCK_SIZE,
			.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
			.cra_module		= THIS_MODULE,
		},
		.min_keysize	= AES_MIN_KEY_SIZE,
		.max_keysize	= AES_MAX_KEY_SIZE,
		.setkey		= aesni_skcipher_setkey,
		.encrypt	= ecb_encrypt,
		.decrypt	= ecb_decrypt,
	}, {
		.base = {
			.cra_name		= "__cbc(aes)",
			.cra_driver_name	= "__cbc-aes-aesni",
			.cra_priority		= 400,
			.cra_flags		= CRYPTO_ALG_INTERNAL,
			.cra_blocksize		= AES_BLOCK_SIZE,
			.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
			.cra_module		= THIS_MODULE,
		},
		.min_keysize	= AES_MIN_KEY_SIZE,
		.max_keysize	= AES_MAX_KEY_SIZE,
		.ivsize		= AES_BLOCK_SIZE,
		.setkey		= aesni_skcipher_setkey,
		.encrypt	= cbc_encrypt,
		.decrypt	= cbc_decrypt,
	}, {
		.base = {
			.cra_name		= "__cts(cbc(aes))",
			.cra_driver_name	= "__cts-cbc-aes-aesni",
			.cra_priority		= 400,
			.cra_flags		= CRYPTO_ALG_INTERNAL,
			.cra_blocksize		= AES_BLOCK_SIZE,
			.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
			.cra_module		= THIS_MODULE,
		},
		.min_keysize	= AES_MIN_KEY_SIZE,
		.max_keysize	= AES_MAX_KEY_SIZE,
		.ivsize		= AES_BLOCK_SIZE,
		.walksize	= 2 * AES_BLOCK_SIZE,
		.setkey		= aesni_skcipher_setkey,
		.encrypt	= cts_cbc_encrypt,
		.decrypt	= cts_cbc_decrypt,
#ifdef CONFIG_X86_64
	}, {
		.base = {
			.cra_name		= "__ctr(aes)",
			.cra_driver_name	= "__ctr-aes-aesni",
			.cra_priority		= 400,
			.cra_flags		= CRYPTO_ALG_INTERNAL,
			.cra_blocksize		= 1,
			.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
			.cra_module		= THIS_MODULE,
		},
		.min_keysize	= AES_MIN_KEY_SIZE,
		.max_keysize	= AES_MAX_KEY_SIZE,
		.ivsize		= AES_BLOCK_SIZE,
		.chunksize	= AES_BLOCK_SIZE,
		.setkey		= aesni_skcipher_setkey,
		.encrypt	= ctr_crypt,
		.decrypt	= ctr_crypt,
#endif
	}, {
		.base = {
			.cra_name		= "__xts(aes)",
			.cra_driver_name	= "__xts-aes-aesni",
			.cra_priority		= 401,
			.cra_flags		= CRYPTO_ALG_INTERNAL,
			.cra_blocksize		= AES_BLOCK_SIZE,
			.cra_ctxsize		= XTS_AES_CTX_SIZE,
			.cra_module		= THIS_MODULE,
		},
		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
		.ivsize		= AES_BLOCK_SIZE,
		.walksize	= 2 * AES_BLOCK_SIZE,
		.setkey		= xts_aesni_setkey,
		.encrypt	= xts_encrypt,
		.decrypt	= xts_decrypt,
	}
};

static
struct simd_skcipher_alg *aesni_simd_skciphers[ARRAY_SIZE(aesni_skciphers)];

#ifdef CONFIG_X86_64
static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key,
				  unsigned int key_len)
{
	struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(aead);

	return aes_set_key_common(crypto_aead_tfm(aead),
				  &ctx->aes_key_expanded, key, key_len) ?:
	       rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
}

static int generic_gcmaes_encrypt(struct aead_request *req)
{
	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
	struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm);
	void *aes_ctx = &(ctx->aes_key_expanded);
	u8 ivbuf[16 + (AES_ALIGN - 8)] __aligned(8);
	u8 *iv = PTR_ALIGN(&ivbuf[0], AES_ALIGN);
	__be32 counter = cpu_to_be32(1);

	memcpy(iv, req->iv, 12);
	*((__be32 *)(iv+12)) = counter;

	return gcmaes_encrypt(req, req->assoclen, ctx->hash_subkey, iv,
			      aes_ctx);
}

static int generic_gcmaes_decrypt(struct aead_request *req)
{
	__be32 counter = cpu_to_be32(1);
	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
	struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm);
	void *aes_ctx = &(ctx->aes_key_expanded);
	u8 ivbuf[16 + (AES_ALIGN - 8)] __aligned(8);
	u8 *iv = PTR_ALIGN(&ivbuf[0], AES_ALIGN);

	memcpy(iv, req->iv, 12);
	*((__be32 *)(iv+12)) = counter;

	return gcmaes_decrypt(req, req->assoclen, ctx->hash_subkey, iv,
			      aes_ctx);
}

static struct aead_alg aesni_aeads[] = { {
	.setkey			= common_rfc4106_set_key,
	.setauthsize		= common_rfc4106_set_authsize,
	.encrypt		= helper_rfc4106_encrypt,
	.decrypt		= helper_rfc4106_decrypt,
	.ivsize			= GCM_RFC4106_IV_SIZE,
	.maxauthsize		= 16,
	.base = {
		.cra_name		= "__rfc4106(gcm(aes))",
		.cra_driver_name	= "__rfc4106-gcm-aesni",
		.cra_priority		= 400,
		.cra_flags		= CRYPTO_ALG_INTERNAL,
		.cra_blocksize		= 1,
		.cra_ctxsize		= sizeof(struct aesni_rfc4106_gcm_ctx),
		.cra_alignmask		= AES_ALIGN - 1,
		.cra_module		= THIS_MODULE,
	},
}, {
	.setkey			= generic_gcmaes_set_key,
	.setauthsize		= generic_gcmaes_set_authsize,
	.encrypt		= generic_gcmaes_encrypt,
	.decrypt		= generic_gcmaes_decrypt,
	.ivsize			= GCM_AES_IV_SIZE,
	.maxauthsize		= 16,
	.base = {
		.cra_name		= "__gcm(aes)",
		.cra_driver_name	= "__generic-gcm-aesni",
		.cra_priority		= 400,
		.cra_flags		= CRYPTO_ALG_INTERNAL,
		.cra_blocksize		= 1,
		.cra_ctxsize		= sizeof(struct generic_gcmaes_ctx),
		.cra_alignmask		= AES_ALIGN - 1,
		.cra_module		= THIS_MODULE,
	},
} };
#else
static struct aead_alg aesni_aeads[0];
#endif

static struct simd_aead_alg *aesni_simd_aeads[ARRAY_SIZE(aesni_aeads)];

static const struct x86_cpu_id aesni_cpu_id[] = {
	X86_MATCH_FEATURE(X86_FEATURE_AES, NULL),
	{}
};
MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);

static int __init aesni_init(void)
{
	int err;

	if (!x86_match_cpu(aesni_cpu_id))
		return -ENODEV;
#ifdef CONFIG_X86_64
	if (boot_cpu_has(X86_FEATURE_AVX2)) {
		pr_info("AVX2 version of gcm_enc/dec engaged.\n");
		static_branch_enable(&gcm_use_avx);
		static_branch_enable(&gcm_use_avx2);
	} else
	if (boot_cpu_has(X86_FEATURE_AVX)) {
		pr_info("AVX version of gcm_enc/dec engaged.\n");
		static_branch_enable(&gcm_use_avx);
	} else {
		pr_info("SSE version of gcm_enc/dec engaged.\n");
	}
	if (boot_cpu_has(X86_FEATURE_AVX)) {
		/* optimize performance of ctr mode encryption transform */
		static_call_update(aesni_ctr_enc_tfm, aesni_ctr_enc_avx_tfm);
		pr_info("AES CTR mode by8 optimization enabled\n");
	}
#endif

	err = crypto_register_alg(&aesni_cipher_alg);
	if (err)
		return err;

	err = simd_register_skciphers_compat(aesni_skciphers,
					     ARRAY_SIZE(aesni_skciphers),
					     aesni_simd_skciphers);
	if (err)
		goto unregister_cipher;

	err = simd_register_aeads_compat(aesni_aeads, ARRAY_SIZE(aesni_aeads),
					 aesni_simd_aeads);
	if (err)
		goto unregister_skciphers;

	return 0;

unregister_skciphers:
	simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
				  aesni_simd_skciphers);
unregister_cipher:
	crypto_unregister_alg(&aesni_cipher_alg);
	return err;
}

static void __exit aesni_exit(void)
{
	simd_unregister_aeads(aesni_aeads, ARRAY_SIZE(aesni_aeads),
			      aesni_simd_aeads);
	simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
				  aesni_simd_skciphers);
	crypto_unregister_alg(&aesni_cipher_alg);
}

late_initcall(aesni_init);
module_exit(aesni_exit);

MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized");
MODULE_LICENSE("GPL");
MODULE_ALIAS_CRYPTO("aes");