static int chacha20_neon(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm);
struct skcipher_walk walk;
u32 state[16];
int err;
if (!may_use_simd() || req->cryptlen <= CHACHA20_BLOCK_SIZE)
return crypto_chacha20_crypt(req);
err = skcipher_walk_virt(&walk, req, true);
crypto_chacha20_init(state, ctx, walk.iv);
kernel_neon_begin();
while (walk.nbytes > 0) {
unsigned int nbytes = walk.nbytes;
if (nbytes < walk.total)
nbytes = round_down(nbytes, walk.stride);
chacha20_doneon(state, walk.dst.virt.addr, walk.src.virt.addr,
nbytes);
err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
}
kernel_neon_end();
return err;
}
static int sha256_neon_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
struct sha256_state *sctx = shash_desc_ctx(desc);
unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
int res;
/* Handle the fast case right here */
if (partial + len < SHA256_BLOCK_SIZE) {
sctx->count += len;
memcpy(sctx->buf + partial, data, len);
return 0;
}
if (!may_use_simd()) {
res = __sha256_update(desc, data, len, partial);
} else {
kernel_neon_begin();
res = __sha256_neon_update(desc, data, len, partial);
kernel_neon_end();
}
return res;
}
static int crc32_pmull_update(struct shash_desc *desc, const u8 *data,
unsigned int length)
{
u32 *crc = shash_desc_ctx(desc);
unsigned int l;
if ((u64)data % SCALE_F) {
l = min_t(u32, length, SCALE_F - ((u64)data % SCALE_F));
*crc = fallback_crc32(*crc, data, l);
data += l;
length -= l;
}
if (length >= PMULL_MIN_LEN && may_use_simd()) {
l = round_down(length, SCALE_F);
kernel_neon_begin();
*crc = crc32_pmull_le(data, l, *crc);
kernel_neon_end();
data += l;
length -= l;
}
if (length > 0)
*crc = fallback_crc32(*crc, data, length);
return 0;
}
static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes)
{
struct blkcipher_walk walk;
u32 state[16];
int err;
if (nbytes <= CHACHA20_BLOCK_SIZE || !may_use_simd())
return crypto_chacha20_crypt(desc, dst, src, nbytes);
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
kernel_neon_begin();
while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
err = blkcipher_walk_done(desc, &walk,
walk.nbytes % CHACHA20_BLOCK_SIZE);
}
if (walk.nbytes) {
chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
walk.nbytes);
err = blkcipher_walk_done(desc, &walk, 0);
}
kernel_neon_end();
return err;
}
static int sha512_ce_final(struct shash_desc *desc, u8 *out)
{
if (!may_use_simd()) {
sha512_base_do_finalize(desc,
(sha512_block_fn *)sha512_block_data_order);
return sha512_base_finish(desc, out);
}
kernel_neon_begin();
sha512_base_do_finalize(desc, (sha512_block_fn *)sha512_ce_transform);
kernel_neon_end();
return sha512_base_finish(desc, out);
}
static int sha512_ce_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
if (!may_use_simd())
return sha512_base_do_update(desc, data, len,
(sha512_block_fn *)sha512_block_data_order);
kernel_neon_begin();
sha512_base_do_update(desc, data, len,
(sha512_block_fn *)sha512_ce_transform);
kernel_neon_end();
return 0;
}
static int sha2_ce_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
if (!may_use_simd())
return crypto_sha256_arm_finup(desc, data, len, out);
kernel_neon_begin();
if (len)
sha256_base_do_update(desc, data, len,
(sha256_block_fn *)sha2_ce_transform);
sha256_base_do_finalize(desc, (sha256_block_fn *)sha2_ce_transform);
kernel_neon_end();
return sha256_base_finish(desc, out);
}
static int sha2_ce_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
struct sha256_state *sctx = shash_desc_ctx(desc);
if (!may_use_simd() ||
(sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
return crypto_sha256_arm_update(desc, data, len);
kernel_neon_begin();
sha256_base_do_update(desc, data, len,
(sha256_block_fn *)sha2_ce_transform);
kernel_neon_end();
return 0;
}
int ablk_encrypt(struct ablkcipher_request *req)
{
struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
if (!may_use_simd()) {
struct ablkcipher_request *cryptd_req =
ablkcipher_request_ctx(req);
memcpy(cryptd_req, req, sizeof(*req));
ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
return crypto_ablkcipher_encrypt(cryptd_req);
} else {
return __ablk_encrypt(req);
}
}
static int sha256_update_neon(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
/*
* Stacking and unstacking a substantial slice of the NEON register
* file may significantly affect performance for small updates when
* executing in interrupt context, so fall back to the scalar code
* in that case.
*/
if (!may_use_simd())
return sha256_base_do_update(desc, data, len,
(sha256_block_fn *)sha256_block_data_order);
kernel_neon_begin();
sha256_base_do_update(desc, data, len,
(sha256_block_fn *)sha256_block_neon);
kernel_neon_end();
return 0;
}
static int sha256_finup_neon(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
if (!may_use_simd()) {
if (len)
sha256_base_do_update(desc, data, len,
(sha256_block_fn *)sha256_block_data_order);
sha256_base_do_finalize(desc,
(sha256_block_fn *)sha256_block_data_order);
} else {
kernel_neon_begin();
if (len)
sha256_base_do_update(desc, data, len,
(sha256_block_fn *)sha256_block_neon);
sha256_base_do_finalize(desc,
(sha256_block_fn *)sha256_block_neon);
kernel_neon_end();
}
return sha256_base_finish(desc, out);
}
/* Add padding and return the message digest. */
static int sha256_neon_final(struct shash_desc *desc, u8 *out)
{
struct sha256_state *sctx = shash_desc_ctx(desc);
unsigned int i, index, padlen;
__be32 *dst = (__be32 *)out;
__be64 bits;
static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
/* save number of bits */
bits = cpu_to_be64(sctx->count << 3);
/* Pad out to 56 mod 64 and append length */
index = sctx->count % SHA256_BLOCK_SIZE;
padlen = (index < 56) ? (56 - index) : ((SHA256_BLOCK_SIZE+56)-index);
if (!may_use_simd()) {
sha256_update(desc, padding, padlen);
sha256_update(desc, (const u8 *)&bits, sizeof(bits));
} else {
kernel_neon_begin();
/* We need to fill a whole block for __sha256_neon_update() */
if (padlen <= 56) {
sctx->count += padlen;
memcpy(sctx->buf + index, padding, padlen);
} else {
__sha256_neon_update(desc, padding, padlen, index);
}
__sha256_neon_update(desc, (const u8 *)&bits,
sizeof(bits), 56);
kernel_neon_end();
}
/* Store state in digest */
for (i = 0; i < 8; i++)
dst[i] = cpu_to_be32(sctx->state[i]);
/* Wipe context */
memset(sctx, 0, sizeof(*sctx));
return 0;
}
static int chacha20_simd(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm);
u32 *state, state_buf[16 + 2] __aligned(8);
struct skcipher_walk walk;
int err;
BUILD_BUG_ON(CHACHA20_STATE_ALIGN != 16);
state = PTR_ALIGN(state_buf + 0, CHACHA20_STATE_ALIGN);
if (req->cryptlen <= CHACHA20_BLOCK_SIZE || !may_use_simd())
return crypto_chacha20_crypt(req);
err = skcipher_walk_virt(&walk, req, true);
crypto_chacha20_init(state, ctx, walk.iv);
kernel_fpu_begin();
while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
err = skcipher_walk_done(&walk,
walk.nbytes % CHACHA20_BLOCK_SIZE);
}
if (walk.nbytes) {
chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
walk.nbytes);
err = skcipher_walk_done(&walk, 0);
}
kernel_fpu_end();
return err;
}
int ablk_decrypt(struct ablkcipher_request *req)
{
struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
if (!may_use_simd()) {
struct ablkcipher_request *cryptd_req =
ablkcipher_request_ctx(req);
memcpy(cryptd_req, req, sizeof(*req));
ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
return crypto_ablkcipher_decrypt(cryptd_req);
} else {
struct blkcipher_desc desc;
desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
desc.info = req->info;
desc.flags = 0;
return crypto_blkcipher_crt(desc.tfm)->decrypt(
&desc, req->dst, req->src, req->nbytes);
}
}
static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes)
{
u32 *state, state_buf[16 + (CHACHA20_STATE_ALIGN / sizeof(u32)) - 1];
struct blkcipher_walk walk;
int err;
if (!may_use_simd())
return crypto_chacha20_crypt(desc, dst, src, nbytes);
state = (u32 *)roundup((uintptr_t)state_buf, CHACHA20_STATE_ALIGN);
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
kernel_fpu_begin();
while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
err = blkcipher_walk_done(desc, &walk,
walk.nbytes % CHACHA20_BLOCK_SIZE);
}
if (walk.nbytes) {
chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
walk.nbytes);
err = blkcipher_walk_done(desc, &walk, 0);
}
kernel_fpu_end();
return err;
}
