int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
struct blkcipher_desc *desc, struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes)
{
const unsigned int bsize = 128 / 8;
bool fpu_enabled = false;
struct blkcipher_walk walk;
int err;
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt_block(desc, &walk, bsize);
while ((nbytes = walk.nbytes) >= bsize) {
fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
desc, fpu_enabled, nbytes);
nbytes = __glue_ctr_crypt_128bit(gctx, desc, &walk);
err = blkcipher_walk_done(desc, &walk, nbytes);
}
glue_fpu_end(fpu_enabled);
if (walk.nbytes) {
glue_ctr_crypt_final_128bit(
gctx->funcs[gctx->num_funcs - 1].fn_u.ctr, desc, &walk);
err = blkcipher_walk_done(desc, &walk, 0);
}
return err;
}
/* for implementations implementing faster XTS IV generator */
int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
struct blkcipher_desc *desc, struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes,
void (*tweak_fn)(void *ctx, u8 *dst, const u8 *src),
void *tweak_ctx, void *crypt_ctx)
{
const unsigned int bsize = 128 / 8;
bool fpu_enabled;
struct blkcipher_walk walk;
int err;
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt(desc, &walk);
nbytes = walk.nbytes;
if (!nbytes)
return err;
/* set minimum length to bsize, for tweak_fn */
fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
desc, false,
nbytes < bsize ? bsize : nbytes);
/* calculate first value of T */
tweak_fn(tweak_ctx, walk.iv, walk.iv);
glue_fpu_end(fpu_enabled);
while (nbytes) {
fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
desc, false, nbytes);
nbytes = __glue_xts_crypt_128bit(gctx, crypt_ctx, desc, &walk);
glue_fpu_end(fpu_enabled);
err = blkcipher_walk_done(desc, &walk, nbytes);
nbytes = walk.nbytes;
}
return err;
}
static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
struct blkcipher_desc *desc,
struct blkcipher_walk *walk)
{
void *ctx = crypto_blkcipher_ctx(desc->tfm);
const unsigned int bsize = 128 / 8;
unsigned int nbytes, i, func_bytes;
bool fpu_enabled = false;
int err;
err = blkcipher_walk_virt(desc, walk);
while ((nbytes = walk->nbytes)) {
u8 *wsrc = walk->src.virt.addr;
u8 *wdst = walk->dst.virt.addr;
fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
desc, fpu_enabled, nbytes);
for (i = 0; i < gctx->num_funcs; i++) {
func_bytes = bsize * gctx->funcs[i].num_blocks;
/* Process multi-block batch */
if (nbytes >= func_bytes) {
do {
gctx->funcs[i].fn_u.ecb(ctx, wdst,
wsrc);
wsrc += func_bytes;
wdst += func_bytes;
nbytes -= func_bytes;
} while (nbytes >= func_bytes);
if (nbytes < bsize)
goto done;
}
}
done:
err = blkcipher_walk_done(desc, walk, nbytes);
}
glue_fpu_end(fpu_enabled);
return err;
}
int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
struct blkcipher_desc *desc,
struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes)
{
const unsigned int bsize = 128 / 8;
bool fpu_enabled = false;
struct blkcipher_walk walk;
int err;
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt(desc, &walk);
while ((nbytes = walk.nbytes)) {
fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
desc, fpu_enabled, nbytes);
nbytes = __glue_cbc_decrypt_128bit(gctx, desc, &walk);
err = blkcipher_walk_done(desc, &walk, nbytes);
}
glue_fpu_end(fpu_enabled);
return err;
}
static inline bool serpent_fpu_begin(bool fpu_enabled, unsigned int nbytes)
{
/* since reusing AVX functions, starts using FPU at 8 parallel blocks */
return glue_fpu_begin(SERPENT_BLOCK_SIZE, 8, NULL, fpu_enabled, nbytes);
}
static inline bool cast6_fpu_begin(bool fpu_enabled, unsigned int nbytes)
{
return glue_fpu_begin(CAST6_BLOCK_SIZE, CAST6_PARALLEL_BLOCKS,
NULL, fpu_enabled, nbytes);
}
static inline bool camellia_fpu_begin(bool fpu_enabled, unsigned int nbytes)
{
return glue_fpu_begin(CAMELLIA_BLOCK_SIZE,
CAMELLIA_AESNI_PARALLEL_BLOCKS, NULL, fpu_enabled,
nbytes);
}
static inline bool serpent_fpu_begin(bool fpu_enabled, unsigned int nbytes)
{
return glue_fpu_begin(SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS,
NULL, fpu_enabled, nbytes);
}
static inline bool twofish_fpu_begin(bool fpu_enabled, unsigned int nbytes)
{
return glue_fpu_begin(TF_BLOCK_SIZE, TWOFISH_PARALLEL_BLOCKS, NULL,
fpu_enabled, nbytes);
}
