wa->sg_used += nbytes;
wa->bytes_left -= nbytes; if (wa->sg_used == sg_dma_len(wa->dma_sg)) { /* Advance to the next DMA scatterlist entry */
wa->dma_sg = sg_next(wa->dma_sg);
/* In the case that the DMA mapped scatterlist has entries * that have been merged, the non-DMA mapped scatterlist * must be advanced multiple times for each merged entry. * This ensures that the current non-DMA mapped entry * corresponds to the current DMA mapped entry.
*/ do {
sg_combined_len += wa->sg->length;
wa->sg = sg_next(wa->sg);
} while (wa->sg_used > sg_combined_len);
wa->sg_used = 0;
}
}
staticvoid ccp_dm_free(struct ccp_dm_workarea *wa)
{ if (wa->length <= CCP_DMAPOOL_MAX_SIZE) { if (wa->address)
dma_pool_free(wa->dma_pool, wa->address,
wa->dma.address);
} else { if (wa->dma.address)
dma_unmap_single(wa->dev, wa->dma.address, wa->length,
wa->dma.dir);
kfree(wa->address);
}
/* Clear the buffer if setting it */ if (!from)
memset(dm_wa->address, 0, dm_wa->length);
if (!sg_wa->sg) return 0;
/* Perform the copy operation * nbytes will always be <= UINT_MAX because dm_wa->length is * an unsigned int
*/
nbytes = min_t(u64, sg_wa->bytes_left, dm_wa->length);
scatterwalk_map_and_copy(dm_wa->address, sg_wa->sg, sg_wa->sg_used,
nbytes, from);
/* Update the structures and generate the count */
buf_count = 0; while (sg_wa->bytes_left && (buf_count < dm_wa->length)) {
nbytes = min(sg_dma_len(sg_wa->dma_sg) - sg_wa->sg_used,
dm_wa->length - buf_count);
nbytes = min_t(u64, sg_wa->bytes_left, nbytes);
/* The CCP can only DMA from/to one address each per operation. This * requires that we find the smallest DMA area between the source * and destination. The resulting len values will always be <= UINT_MAX * because the dma length is an unsigned int.
*/
sg_src_len = sg_dma_len(src->sg_wa.dma_sg) - src->sg_wa.sg_used;
sg_src_len = min_t(u64, src->sg_wa.bytes_left, sg_src_len);
/* The data operation length will be at least block_size in length * or the smaller of available sg room remaining for the source or * the destination
*/
op_len = max(op_len, block_size);
/* Unless we have to buffer data, there's no reason to wait */
op->soc = 0;
if (sg_src_len < block_size) { /* Not enough data in the sg element, so it * needs to be buffered into a blocksize chunk
*/ int cp_len = ccp_fill_queue_buf(src);
op->soc = 1;
op->src.u.dma.address = src->dm_wa.dma.address;
op->src.u.dma.offset = 0;
op->src.u.dma.length = (blocksize_op) ? block_size : cp_len;
} else { /* Enough data in the sg element, but we need to * adjust for any previously copied data
*/
op->src.u.dma.address = sg_dma_address(src->sg_wa.dma_sg);
op->src.u.dma.offset = src->sg_wa.sg_used;
op->src.u.dma.length = op_len & ~(block_size - 1);
if (dst) { if (sg_dst_len < block_size) { /* Not enough room in the sg element or we're on the * last piece of data (when using padding), so the * output needs to be buffered into a blocksize chunk
*/
op->soc = 1;
op->dst.u.dma.address = dst->dm_wa.dma.address;
op->dst.u.dma.offset = 0;
op->dst.u.dma.length = op->src.u.dma.length;
} else { /* Enough room in the sg element, but we need to * adjust for any previously used area
*/
op->dst.u.dma.address = sg_dma_address(dst->sg_wa.dma_sg);
op->dst.u.dma.offset = dst->sg_wa.sg_used;
op->dst.u.dma.length = op->src.u.dma.length;
}
}
}
/* All supported key sizes fit in a single (32-byte) SB entry * and must be in little endian format. Use the 256-bit byte * swap passthru option to convert from big endian to little * endian.
*/
ret = ccp_init_dm_workarea(&key, cmd_q,
CCP_AES_KEY_SB_COUNT * CCP_SB_BYTES,
DMA_TO_DEVICE); if (ret) return ret;
dm_offset = CCP_SB_BYTES - aes->key_len;
ret = ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len); if (ret) goto e_key;
ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_key;
}
/* The AES context fits in a single (32-byte) SB entry and * must be in little endian format. Use the 256-bit byte swap * passthru option to convert from big endian to little endian.
*/
ret = ccp_init_dm_workarea(&ctx, cmd_q,
CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES,
DMA_BIDIRECTIONAL); if (ret) goto e_key;
dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
ret = ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len); if (ret) goto e_ctx;
ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_ctx;
}
/* Send data to the CCP AES engine */
ret = ccp_init_data(&src, cmd_q, aes->src, aes->src_len,
AES_BLOCK_SIZE, DMA_TO_DEVICE); if (ret) goto e_ctx;
while (src.sg_wa.bytes_left) {
ccp_prepare_data(&src, NULL, &op, AES_BLOCK_SIZE, true); if (aes->cmac_final && !src.sg_wa.bytes_left) {
op.eom = 1;
/* Push the K1/K2 key to the CCP now */
ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid,
op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_src;
}
ret = ccp_set_dm_area(&ctx, 0, aes->cmac_key, 0,
aes->cmac_key_len); if (ret) goto e_src;
ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_src;
}
}
ret = cmd_q->ccp->vdata->perform->aes(&op); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_src;
}
ccp_process_data(&src, NULL, &op);
}
/* Retrieve the AES context - convert from LE to BE using * 32-byte (256-bit) byteswapping
*/
ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_src;
}
/* ...but we only need AES_BLOCK_SIZE bytes */
dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
ccp_get_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
if (!aes->key) /* Gotta have a key SGL */ return -EINVAL;
/* Zero defaults to 16 bytes, the maximum size */
authsize = aes->authsize ? aes->authsize : AES_BLOCK_SIZE; switch (authsize) { case 16: case 15: case 14: case 13: case 12: case 8: case 4: break; default: return -EINVAL;
}
/* First, decompose the source buffer into AAD & PT, * and the destination buffer into AAD, CT & tag, or * the input into CT & tag. * It is expected that the input and output SGs will * be valid, even if the AAD and input lengths are 0.
*/
p_aad = aes->src;
p_inp = scatterwalk_ffwd(sg_inp, aes->src, aes->aad_len);
p_outp = scatterwalk_ffwd(sg_outp, aes->dst, aes->aad_len); if (aes->action == CCP_AES_ACTION_ENCRYPT) {
ilen = aes->src_len;
p_tag = scatterwalk_ffwd(sg_tag, p_outp, ilen);
} else { /* Input length for decryption includes tag */
ilen = aes->src_len - authsize;
p_tag = scatterwalk_ffwd(sg_tag, p_inp, ilen);
}
/* Copy the key to the LSB */
ret = ccp_init_dm_workarea(&wa->key, cmd_q,
CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES,
DMA_TO_DEVICE); if (ret) return ret;
dm_offset = CCP_SB_BYTES - aes->key_len;
ret = ccp_set_dm_area(&wa->key, dm_offset, aes->key, 0, aes->key_len); if (ret) goto e_key;
ret = ccp_copy_to_sb(cmd_q, &wa->key, wa->op.jobid, wa->op.sb_key,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_key;
}
/* Copy the context (IV) to the LSB. * There is an assumption here that the IV is 96 bits in length, plus * a nonce of 32 bits. If no IV is present, use a zeroed buffer.
*/
ret = ccp_init_dm_workarea(&wa->ctx, cmd_q,
CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES,
DMA_BIDIRECTIONAL); if (ret) goto e_key;
dm_offset = CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES - aes->iv_len;
ret = ccp_set_dm_area(&wa->ctx, dm_offset, aes->iv, 0, aes->iv_len); if (ret) goto e_ctx;
ret = ccp_copy_to_sb(cmd_q, &wa->ctx, wa->op.jobid, wa->op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_ctx;
}
wa->op.init = 1; if (aes->aad_len > 0) { /* Step 1: Run a GHASH over the Additional Authenticated Data */
ret = ccp_init_data(&wa->aad, cmd_q, p_aad, aes->aad_len,
AES_BLOCK_SIZE,
DMA_TO_DEVICE); if (ret) goto e_ctx;
/* Step 3: Update the IV portion of the context with the original IV */
ret = ccp_copy_from_sb(cmd_q, &wa->ctx, wa->op.jobid, wa->op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_dst;
}
ret = ccp_set_dm_area(&wa->ctx, dm_offset, aes->iv, 0, aes->iv_len); if (ret) goto e_dst;
ret = ccp_copy_to_sb(cmd_q, &wa->ctx, wa->op.jobid, wa->op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_dst;
}
/* Step 4: Concatenate the lengths of the AAD and source, and * hash that 16 byte buffer.
*/
ret = ccp_init_dm_workarea(&wa->final, cmd_q, AES_BLOCK_SIZE,
DMA_BIDIRECTIONAL); if (ret) goto e_dst;
final = (__be64 *)wa->final.address;
final[0] = cpu_to_be64(aes->aad_len * 8);
final[1] = cpu_to_be64(ilen * 8);
if (aes->action == CCP_AES_ACTION_ENCRYPT) { /* Put the ciphered tag after the ciphertext. */
ccp_get_dm_area(&wa->final, 0, p_tag, 0, authsize);
} else { /* Does this ciphered tag match the input? */
ret = ccp_init_dm_workarea(&wa->tag, cmd_q, authsize,
DMA_BIDIRECTIONAL); if (ret) goto e_final_wa;
ret = ccp_set_dm_area(&wa->tag, 0, p_tag, 0, authsize); if (ret) {
ccp_dm_free(&wa->tag); goto e_final_wa;
}
/* All supported key sizes fit in a single (32-byte) SB entry * and must be in little endian format. Use the 256-bit byte * swap passthru option to convert from big endian to little * endian.
*/
ret = ccp_init_dm_workarea(&key, cmd_q,
CCP_AES_KEY_SB_COUNT * CCP_SB_BYTES,
DMA_TO_DEVICE); if (ret) return ret;
dm_offset = CCP_SB_BYTES - aes->key_len;
ret = ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len); if (ret) goto e_key;
ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_key;
}
/* The AES context fits in a single (32-byte) SB entry and * must be in little endian format. Use the 256-bit byte swap * passthru option to convert from big endian to little endian.
*/
ret = ccp_init_dm_workarea(&ctx, cmd_q,
CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES,
DMA_BIDIRECTIONAL); if (ret) goto e_key;
if (aes->mode != CCP_AES_MODE_ECB) { /* Load the AES context - convert to LE */
dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
ret = ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len); if (ret) goto e_ctx;
ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_ctx;
}
} switch (aes->mode) { case CCP_AES_MODE_CFB: /* CFB128 only */ case CCP_AES_MODE_CTR:
op.u.aes.size = AES_BLOCK_SIZE * BITS_PER_BYTE - 1; break; default:
op.u.aes.size = 0;
}
/* Prepare the input and output data workareas. For in-place * operations we need to set the dma direction to BIDIRECTIONAL * and copy the src workarea to the dst workarea.
*/ if (sg_virt(aes->src) == sg_virt(aes->dst))
in_place = true;
ret = ccp_init_data(&src, cmd_q, aes->src, aes->src_len,
AES_BLOCK_SIZE,
in_place ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE); if (ret) goto e_ctx;
if (in_place) {
dst = src;
} else {
ret = ccp_init_data(&dst, cmd_q, aes->dst, aes->src_len,
AES_BLOCK_SIZE, DMA_FROM_DEVICE); if (ret) goto e_src;
}
/* Send data to the CCP AES engine */ while (src.sg_wa.bytes_left) {
ccp_prepare_data(&src, &dst, &op, AES_BLOCK_SIZE, true); if (!src.sg_wa.bytes_left) {
op.eom = 1;
/* Since we don't retrieve the AES context in ECB * mode we have to wait for the operation to complete * on the last piece of data
*/ if (aes->mode == CCP_AES_MODE_ECB)
op.soc = 1;
}
ret = cmd_q->ccp->vdata->perform->aes(&op); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_dst;
}
ccp_process_data(&src, &dst, &op);
}
if (aes->mode != CCP_AES_MODE_ECB) { /* Retrieve the AES context - convert from LE to BE using * 32-byte (256-bit) byteswapping
*/
ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_dst;
}
/* ...but we only need AES_BLOCK_SIZE bytes */
dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
ccp_get_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
}
/* A version 3 device only supports 128-bit keys, which fits into a * single SB entry. A version 5 device uses a 512-bit vector, so two * SB entries.
*/ if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0))
sb_count = CCP_XTS_AES_KEY_SB_COUNT; else
sb_count = CCP5_XTS_AES_KEY_SB_COUNT;
ret = ccp_init_dm_workarea(&key, cmd_q,
sb_count * CCP_SB_BYTES,
DMA_TO_DEVICE); if (ret) return ret;
if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0)) { /* All supported key sizes must be in little endian format. * Use the 256-bit byte swap passthru option to convert from * big endian to little endian.
*/
dm_offset = CCP_SB_BYTES - AES_KEYSIZE_128;
ret = ccp_set_dm_area(&key, dm_offset, xts->key, 0, xts->key_len); if (ret) goto e_key;
ret = ccp_set_dm_area(&key, 0, xts->key, xts->key_len, xts->key_len); if (ret) goto e_key;
} else { /* Version 5 CCPs use a 512-bit space for the key: each portion * occupies 256 bits, or one entire slot, and is zero-padded.
*/ unsignedint pad;
dm_offset = CCP_SB_BYTES;
pad = dm_offset - xts->key_len;
ret = ccp_set_dm_area(&key, pad, xts->key, 0, xts->key_len); if (ret) goto e_key;
ret = ccp_set_dm_area(&key, dm_offset + pad, xts->key,
xts->key_len, xts->key_len); if (ret) goto e_key;
}
ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_key;
}
/* The AES context fits in a single (32-byte) SB entry and * for XTS is already in little endian format so no byte swapping * is needed.
*/
ret = ccp_init_dm_workarea(&ctx, cmd_q,
CCP_XTS_AES_CTX_SB_COUNT * CCP_SB_BYTES,
DMA_BIDIRECTIONAL); if (ret) goto e_key;
ret = ccp_set_dm_area(&ctx, 0, xts->iv, 0, xts->iv_len); if (ret) goto e_ctx;
ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_NOOP); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_ctx;
}
/* Prepare the input and output data workareas. For in-place * operations we need to set the dma direction to BIDIRECTIONAL * and copy the src workarea to the dst workarea.
*/ if (sg_virt(xts->src) == sg_virt(xts->dst))
in_place = true;
ret = ccp_init_data(&src, cmd_q, xts->src, xts->src_len,
unit_size,
in_place ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE); if (ret) goto e_ctx;
if (in_place) {
dst = src;
} else {
ret = ccp_init_data(&dst, cmd_q, xts->dst, xts->src_len,
unit_size, DMA_FROM_DEVICE); if (ret) goto e_src;
}
/* Send data to the CCP AES engine */ while (src.sg_wa.bytes_left) {
ccp_prepare_data(&src, &dst, &op, unit_size, true); if (!src.sg_wa.bytes_left)
op.eom = 1;
ret = cmd_q->ccp->vdata->perform->xts_aes(&op); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_dst;
}
ccp_process_data(&src, &dst, &op);
}
/* Retrieve the AES context - convert from LE to BE using * 32-byte (256-bit) byteswapping
*/
ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_dst;
}
/* ...but we only need AES_BLOCK_SIZE bytes */
dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
ccp_get_dm_area(&ctx, dm_offset, xts->iv, 0, xts->iv_len);
/* * All supported key sizes fit in a single (32-byte) KSB entry and * (like AES) must be in little endian format. Use the 256-bit byte * swap passthru option to convert from big endian to little endian.
*/
ret = ccp_init_dm_workarea(&key, cmd_q,
CCP_DES3_KEY_SB_COUNT * CCP_SB_BYTES,
DMA_TO_DEVICE); if (ret) return ret;
/* * The contents of the key triplet are in the reverse order of what * is required by the engine. Copy the 3 pieces individually to put * them where they belong.
*/
dm_offset = CCP_SB_BYTES - des3->key_len; /* Basic offset */
len_singlekey = des3->key_len / 3;
ret = ccp_set_dm_area(&key, dm_offset + 2 * len_singlekey,
des3->key, 0, len_singlekey); if (ret) goto e_key;
ret = ccp_set_dm_area(&key, dm_offset + len_singlekey,
des3->key, len_singlekey, len_singlekey); if (ret) goto e_key;
ret = ccp_set_dm_area(&key, dm_offset,
des3->key, 2 * len_singlekey, len_singlekey); if (ret) goto e_key;
/* Copy the key to the SB */
ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_key;
}
/* * The DES3 context fits in a single (32-byte) KSB entry and * must be in little endian format. Use the 256-bit byte swap * passthru option to convert from big endian to little endian.
*/ if (des3->mode != CCP_DES3_MODE_ECB) {
op.sb_ctx = cmd_q->sb_ctx;
ret = ccp_init_dm_workarea(&ctx, cmd_q,
CCP_DES3_CTX_SB_COUNT * CCP_SB_BYTES,
DMA_BIDIRECTIONAL); if (ret) goto e_key;
/* Load the context into the LSB */
dm_offset = CCP_SB_BYTES - des3->iv_len;
ret = ccp_set_dm_area(&ctx, dm_offset, des3->iv, 0,
des3->iv_len); if (ret) goto e_ctx;
ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_ctx;
}
}
/* * Prepare the input and output data workareas. For in-place * operations we need to set the dma direction to BIDIRECTIONAL * and copy the src workarea to the dst workarea.
*/ if (sg_virt(des3->src) == sg_virt(des3->dst))
in_place = true;
ret = ccp_init_data(&src, cmd_q, des3->src, des3->src_len,
DES3_EDE_BLOCK_SIZE,
in_place ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE); if (ret) goto e_ctx;
if (in_place)
dst = src; else {
ret = ccp_init_data(&dst, cmd_q, des3->dst, des3->src_len,
DES3_EDE_BLOCK_SIZE, DMA_FROM_DEVICE); if (ret) goto e_src;
}
/* Send data to the CCP DES3 engine */ while (src.sg_wa.bytes_left) {
ccp_prepare_data(&src, &dst, &op, DES3_EDE_BLOCK_SIZE, true); if (!src.sg_wa.bytes_left) {
op.eom = 1;
/* Since we don't retrieve the context in ECB mode * we have to wait for the operation to complete * on the last piece of data
*/
op.soc = 0;
}
ret = cmd_q->ccp->vdata->perform->des3(&op); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_dst;
}
ccp_process_data(&src, &dst, &op);
}
if (des3->mode != CCP_DES3_MODE_ECB) { /* Retrieve the context and make BE */
ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_dst;
}
/* ...but we only need the last DES3_EDE_BLOCK_SIZE bytes */
ccp_get_dm_area(&ctx, dm_offset, des3->iv, 0,
DES3_EDE_BLOCK_SIZE);
}
e_dst: if (!in_place)
ccp_free_data(&dst, cmd_q);
e_src:
ccp_free_data(&src, cmd_q);
e_ctx: if (des3->mode != CCP_DES3_MODE_ECB)
ccp_dm_free(&ctx);
e_key:
ccp_dm_free(&key);
return ret;
}
static noinline_for_stack int
ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
{ struct ccp_sha_engine *sha = &cmd->u.sha; struct ccp_dm_workarea ctx; struct ccp_data src; struct ccp_op op; unsignedint ioffset, ooffset; unsignedint digest_size; int sb_count; constvoid *init;
u64 block_size; int ctx_size; int ret;
switch (sha->type) { case CCP_SHA_TYPE_1: if (sha->ctx_len < SHA1_DIGEST_SIZE) return -EINVAL;
block_size = SHA1_BLOCK_SIZE; break; case CCP_SHA_TYPE_224: if (sha->ctx_len < SHA224_DIGEST_SIZE) return -EINVAL;
block_size = SHA224_BLOCK_SIZE; break; case CCP_SHA_TYPE_256: if (sha->ctx_len < SHA256_DIGEST_SIZE) return -EINVAL;
block_size = SHA256_BLOCK_SIZE; break; case CCP_SHA_TYPE_384: if (cmd_q->ccp->vdata->version < CCP_VERSION(4, 0)
|| sha->ctx_len < SHA384_DIGEST_SIZE) return -EINVAL;
block_size = SHA384_BLOCK_SIZE; break; case CCP_SHA_TYPE_512: if (cmd_q->ccp->vdata->version < CCP_VERSION(4, 0)
|| sha->ctx_len < SHA512_DIGEST_SIZE) return -EINVAL;
block_size = SHA512_BLOCK_SIZE; break; default: return -EINVAL;
}
if (!sha->ctx) return -EINVAL;
if (!sha->final && (sha->src_len & (block_size - 1))) return -EINVAL;
/* The version 3 device can't handle zero-length input */ if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0)) {
if (!sha->src_len) { unsignedint digest_len; const u8 *sha_zero;
/* Not final, just return */ if (!sha->final) return 0;
/* CCP can't do a zero length sha operation so the * caller must buffer the data.
*/ if (sha->msg_bits) return -EINVAL;
/* The CCP cannot perform zero-length sha operations * so the caller is required to buffer data for the * final operation. However, a sha operation for a * message with a total length of zero is valid so * known values are required to supply the result.
*/ switch (sha->type) { case CCP_SHA_TYPE_1:
sha_zero = sha1_zero_message_hash;
digest_len = SHA1_DIGEST_SIZE; break; case CCP_SHA_TYPE_224:
sha_zero = sha224_zero_message_hash;
digest_len = SHA224_DIGEST_SIZE; break; case CCP_SHA_TYPE_256:
sha_zero = sha256_zero_message_hash;
digest_len = SHA256_DIGEST_SIZE; break; default: return -EINVAL;
}
/* For SHA1/224/256 the context fits in a single (32-byte) SB entry; * SHA384/512 require 2 adjacent SB slots, with the right half in the * first slot, and the left half in the second. Each portion must then * be in little endian format: use the 256-bit byte swap option.
*/
ret = ccp_init_dm_workarea(&ctx, cmd_q, sb_count * CCP_SB_BYTES,
DMA_BIDIRECTIONAL); if (ret) return ret; if (sha->first) { switch (sha->type) { case CCP_SHA_TYPE_1: case CCP_SHA_TYPE_224: case CCP_SHA_TYPE_256:
memcpy(ctx.address + ioffset, init, ctx_size); break; case CCP_SHA_TYPE_384: case CCP_SHA_TYPE_512:
memcpy(ctx.address + ctx_size / 2, init,
ctx_size / 2);
memcpy(ctx.address, init + ctx_size / 2,
ctx_size / 2); break; default:
ret = -EINVAL; goto e_ctx;
}
} else { /* Restore the context */
ret = ccp_set_dm_area(&ctx, 0, sha->ctx, 0,
sb_count * CCP_SB_BYTES); if (ret) goto e_ctx;
}
ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_ctx;
}
if (sha->src) { /* Send data to the CCP SHA engine; block_size is set above */
ret = ccp_init_data(&src, cmd_q, sha->src, sha->src_len,
block_size, DMA_TO_DEVICE); if (ret) goto e_ctx;
while (src.sg_wa.bytes_left) {
ccp_prepare_data(&src, NULL, &op, block_size, false); if (sha->final && !src.sg_wa.bytes_left)
op.eom = 1;
ret = cmd_q->ccp->vdata->perform->sha(&op); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_data;
}
/* Retrieve the SHA context - convert from LE to BE using * 32-byte (256-bit) byteswapping to BE
*/
ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
CCP_PASSTHRU_BYTESWAP_256BIT); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_data;
}
if (sha->final) { /* Finishing up, so get the digest */ switch (sha->type) { case CCP_SHA_TYPE_1: case CCP_SHA_TYPE_224: case CCP_SHA_TYPE_256:
ccp_get_dm_area(&ctx, ooffset,
sha->ctx, 0,
digest_size); break; case CCP_SHA_TYPE_384: case CCP_SHA_TYPE_512:
ccp_get_dm_area(&ctx, 0,
sha->ctx, LSB_ITEM_SIZE - ooffset,
LSB_ITEM_SIZE);
ccp_get_dm_area(&ctx, LSB_ITEM_SIZE + ooffset,
sha->ctx, 0,
LSB_ITEM_SIZE - ooffset); break; default:
ret = -EINVAL; goto e_data;
}
} else { /* Stash the context */
ccp_get_dm_area(&ctx, 0, sha->ctx, 0,
sb_count * CCP_SB_BYTES);
}
/* The RSA modulus must precede the message being acted upon, so * it must be copied to a DMA area where the message and the * modulus can be concatenated. Therefore the input buffer * length required is twice the output buffer length (which * must be a multiple of 256-bits). Compute o_len, i_len in bytes. * Buffer sizes must be a multiple of 32 bytes; rounding up may be * required.
*/
o_len = 32 * ((rsa->key_size + 255) / 256);
i_len = o_len * 2;
sb_count = 0; if (cmd_q->ccp->vdata->version < CCP_VERSION(5, 0)) { /* sb_count is the number of storage block slots required * for the modulus.
*/
sb_count = o_len / CCP_SB_BYTES;
op.sb_key = cmd_q->ccp->vdata->perform->sballoc(cmd_q,
sb_count); if (!op.sb_key) return -EIO;
} else { /* A version 5 device allows a modulus size that will not fit * in the LSB, so the command will transfer it from memory. * Set the sb key to the default, even though it's not used.
*/
op.sb_key = cmd_q->sb_key;
}
/* The RSA exponent must be in little endian format. Reverse its * byte order.
*/
ret = ccp_init_dm_workarea(&exp, cmd_q, o_len, DMA_TO_DEVICE); if (ret) goto e_sb;
ret = ccp_reverse_set_dm_area(&exp, 0, rsa->exp, 0, rsa->exp_len); if (ret) goto e_exp;
if (cmd_q->ccp->vdata->version < CCP_VERSION(5, 0)) { /* Copy the exponent to the local storage block, using * as many 32-byte blocks as were allocated above. It's * already little endian, so no further change is required.
*/
ret = ccp_copy_to_sb(cmd_q, &exp, op.jobid, op.sb_key,
CCP_PASSTHRU_BYTESWAP_NOOP); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_exp;
}
} else { /* The exponent can be retrieved from memory via DMA. */
op.exp.u.dma.address = exp.dma.address;
op.exp.u.dma.offset = 0;
}
/* Concatenate the modulus and the message. Both the modulus and * the operands must be in little endian format. Since the input * is in big endian format it must be converted.
*/
ret = ccp_init_dm_workarea(&src, cmd_q, i_len, DMA_TO_DEVICE); if (ret) goto e_exp;
ret = ccp_reverse_set_dm_area(&src, 0, rsa->mod, 0, rsa->mod_len); if (ret) goto e_src;
ret = ccp_reverse_set_dm_area(&src, o_len, rsa->src, 0, rsa->src_len); if (ret) goto e_src;
/* Prepare the output area for the operation */
ret = ccp_init_dm_workarea(&dst, cmd_q, o_len, DMA_FROM_DEVICE); if (ret) goto e_src;
if (pt->bit_mod != CCP_PASSTHRU_BITWISE_NOOP) { /* Load the mask */
op.sb_key = cmd_q->sb_key;
ret = ccp_init_dm_workarea(&mask, cmd_q,
CCP_PASSTHRU_SB_COUNT *
CCP_SB_BYTES,
DMA_TO_DEVICE); if (ret) return ret;
ret = ccp_set_dm_area(&mask, 0, pt->mask, 0, pt->mask_len); if (ret) goto e_mask;
ret = ccp_copy_to_sb(cmd_q, &mask, op.jobid, op.sb_key,
CCP_PASSTHRU_BYTESWAP_NOOP); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_mask;
}
}
/* Prepare the input and output data workareas. For in-place * operations we need to set the dma direction to BIDIRECTIONAL * and copy the src workarea to the dst workarea.
*/ if (sg_virt(pt->src) == sg_virt(pt->dst))
in_place = true;
ret = ccp_init_data(&src, cmd_q, pt->src, pt->src_len,
CCP_PASSTHRU_MASKSIZE,
in_place ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE); if (ret) goto e_mask;
if (in_place) {
dst = src;
} else {
ret = ccp_init_data(&dst, cmd_q, pt->dst, pt->src_len,
CCP_PASSTHRU_MASKSIZE, DMA_FROM_DEVICE); if (ret) goto e_src;
}
/* Send data to the CCP Passthru engine * Because the CCP engine works on a single source and destination * dma address at a time, each entry in the source scatterlist * (after the dma_map_sg call) must be less than or equal to the * (remaining) length in the destination scatterlist entry and the * length must be a multiple of CCP_PASSTHRU_BLOCKSIZE
*/
dst.sg_wa.sg_used = 0; for (i = 1; i <= src.sg_wa.dma_count; i++) { if (!dst.sg_wa.sg ||
(sg_dma_len(dst.sg_wa.sg) < sg_dma_len(src.sg_wa.sg))) {
ret = -EINVAL; goto e_dst;
}
if (i == src.sg_wa.dma_count) {
op.eom = 1;
op.soc = 1;
}
/* Concatenate the modulus and the operands. Both the modulus and * the operands must be in little endian format. Since the input * is in big endian format it must be converted and placed in a * fixed length buffer.
*/
ret = ccp_init_dm_workarea(&src, cmd_q, CCP_ECC_SRC_BUF_SIZE,
DMA_TO_DEVICE); if (ret) return ret;
/* Save the workarea address since it is updated in order to perform * the concatenation
*/
save = src.address;
/* Copy the ECC modulus */
ret = ccp_reverse_set_dm_area(&src, 0, ecc->mod, 0, ecc->mod_len); if (ret) goto e_src;
src.address += CCP_ECC_OPERAND_SIZE;
/* Copy the first operand */
ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.mm.operand_1, 0,
ecc->u.mm.operand_1_len); if (ret) goto e_src;
src.address += CCP_ECC_OPERAND_SIZE;
if (ecc->function != CCP_ECC_FUNCTION_MINV_384BIT) { /* Copy the second operand */
ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.mm.operand_2, 0,
ecc->u.mm.operand_2_len); if (ret) goto e_src;
src.address += CCP_ECC_OPERAND_SIZE;
}
/* Restore the workarea address */
src.address = save;
/* Prepare the output area for the operation */
ret = ccp_init_dm_workarea(&dst, cmd_q, CCP_ECC_DST_BUF_SIZE,
DMA_FROM_DEVICE); if (ret) goto e_src;
/* Concatenate the modulus and the operands. Both the modulus and * the operands must be in little endian format. Since the input * is in big endian format it must be converted and placed in a * fixed length buffer.
*/
ret = ccp_init_dm_workarea(&src, cmd_q, CCP_ECC_SRC_BUF_SIZE,
DMA_TO_DEVICE); if (ret) return ret;
/* Save the workarea address since it is updated in order to perform * the concatenation
*/
save = src.address;
/* Copy the ECC modulus */
ret = ccp_reverse_set_dm_area(&src, 0, ecc->mod, 0, ecc->mod_len); if (ret) goto e_src;
src.address += CCP_ECC_OPERAND_SIZE;
/* Copy the first point X and Y coordinate */
ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.pm.point_1.x, 0,
ecc->u.pm.point_1.x_len); if (ret) goto e_src;
src.address += CCP_ECC_OPERAND_SIZE;
ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.pm.point_1.y, 0,
ecc->u.pm.point_1.y_len); if (ret) goto e_src;
src.address += CCP_ECC_OPERAND_SIZE;
/* Set the first point Z coordinate to 1 */
*src.address = 0x01;
src.address += CCP_ECC_OPERAND_SIZE;
if (ecc->function == CCP_ECC_FUNCTION_PADD_384BIT) { /* Copy the second point X and Y coordinate */
ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.pm.point_2.x, 0,
ecc->u.pm.point_2.x_len); if (ret) goto e_src;
src.address += CCP_ECC_OPERAND_SIZE;
ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.pm.point_2.y, 0,
ecc->u.pm.point_2.y_len); if (ret) goto e_src;
src.address += CCP_ECC_OPERAND_SIZE;
/* Set the second point Z coordinate to 1 */
*src.address = 0x01;
src.address += CCP_ECC_OPERAND_SIZE;
} else { /* Copy the Domain "a" parameter */
ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.pm.domain_a, 0,
ecc->u.pm.domain_a_len); if (ret) goto e_src;
src.address += CCP_ECC_OPERAND_SIZE;
if (ecc->function == CCP_ECC_FUNCTION_PMUL_384BIT) { /* Copy the scalar value */
ret = ccp_reverse_set_dm_area(&src, 0,
ecc->u.pm.scalar, 0,
ecc->u.pm.scalar_len); if (ret) goto e_src;
src.address += CCP_ECC_OPERAND_SIZE;
}
}
/* Restore the workarea address */
src.address = save;
/* Prepare the output area for the operation */
ret = ccp_init_dm_workarea(&dst, cmd_q, CCP_ECC_DST_BUF_SIZE,
DMA_FROM_DEVICE); if (ret) goto e_src;
ret = cmd_q->ccp->vdata->perform->ecc(&op); if (ret) {
cmd->engine_error = cmd_q->cmd_error; goto e_dst;
}
ecc->ecc_result = le16_to_cpup(
(const __le16 *)(dst.address + CCP_ECC_RESULT_OFFSET)); if (!(ecc->ecc_result & CCP_ECC_RESULT_SUCCESS)) {
ret = -EIO; goto e_dst;
}
/* Save the workarea address since it is updated as we walk through * to copy the point math result
*/
save = dst.address;
/* Save the ECC result X and Y coordinates */
ccp_reverse_get_dm_area(&dst, 0, ecc->u.pm.result.x, 0,
CCP_ECC_MODULUS_BYTES);
dst.address += CCP_ECC_OUTPUT_SIZE;
ccp_reverse_get_dm_area(&dst, 0, ecc->u.pm.result.y, 0,
CCP_ECC_MODULUS_BYTES);
/* Restore the workarea address */
dst.address = save;
if (!ecc->mod ||
(ecc->mod_len > CCP_ECC_MODULUS_BYTES)) return -EINVAL;
switch (ecc->function) { case CCP_ECC_FUNCTION_MMUL_384BIT: case CCP_ECC_FUNCTION_MADD_384BIT: case CCP_ECC_FUNCTION_MINV_384BIT: return ccp_run_ecc_mm_cmd(cmd_q, cmd);
case CCP_ECC_FUNCTION_PADD_384BIT: case CCP_ECC_FUNCTION_PMUL_384BIT: case CCP_ECC_FUNCTION_PDBL_384BIT: return ccp_run_ecc_pm_cmd(cmd_q, cmd);
default: return -EINVAL;
}
}
int ccp_run_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
{ int ret;
switch (cmd->engine) { case CCP_ENGINE_AES: switch (cmd->u.aes.mode) { case CCP_AES_MODE_CMAC:
ret = ccp_run_aes_cmac_cmd(cmd_q, cmd); break; case CCP_AES_MODE_GCM:
ret = ccp_run_aes_gcm_cmd(cmd_q, cmd); break; default:
ret = ccp_run_aes_cmd(cmd_q, cmd); break;
} break; case CCP_ENGINE_XTS_AES_128:
ret = ccp_run_xts_aes_cmd(cmd_q, cmd); break; case CCP_ENGINE_DES3:
ret = ccp_run_des3_cmd(cmd_q, cmd); break; case CCP_ENGINE_SHA:
ret = ccp_run_sha_cmd(cmd_q, cmd); break; case CCP_ENGINE_RSA:
ret = ccp_run_rsa_cmd(cmd_q, cmd); break; case CCP_ENGINE_PASSTHRU: if (cmd->flags & CCP_CMD_PASSTHRU_NO_DMA_MAP)
ret = ccp_run_passthru_nomap_cmd(cmd_q, cmd); else
ret = ccp_run_passthru_cmd(cmd_q, cmd); break; case CCP_ENGINE_ECC:
ret = ccp_run_ecc_cmd(cmd_q, cmd); break; default:
ret = -EINVAL;
}
return ret;
}
Messung V0.5
¤ Dauer der Verarbeitung: 0.26 Sekunden
(vorverarbeitet)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.