ccp-ops.c 59.8 KB
Newer Older
1 2 3
/*
 * AMD Cryptographic Coprocessor (CCP) driver
 *
4
 * Copyright (C) 2013,2017 Advanced Micro Devices, Inc.
5 6
 *
 * Author: Tom Lendacky <thomas.lendacky@amd.com>
7
 * Author: Gary R Hook <gary.hook@amd.com>
8 9 10 11 12 13 14 15 16 17 18
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/pci.h>
#include <linux/interrupt.h>
#include <crypto/scatterwalk.h>
19
#include <crypto/des.h>
20
#include <linux/ccp.h>
21 22 23

#include "ccp-dev.h"

24
/* SHA initial context values */
25
static const __be32 ccp_sha1_init[SHA1_DIGEST_SIZE / sizeof(__be32)] = {
26 27
	cpu_to_be32(SHA1_H0), cpu_to_be32(SHA1_H1),
	cpu_to_be32(SHA1_H2), cpu_to_be32(SHA1_H3),
28
	cpu_to_be32(SHA1_H4),
29 30
};

31
static const __be32 ccp_sha224_init[SHA256_DIGEST_SIZE / sizeof(__be32)] = {
32 33 34 35 36 37
	cpu_to_be32(SHA224_H0), cpu_to_be32(SHA224_H1),
	cpu_to_be32(SHA224_H2), cpu_to_be32(SHA224_H3),
	cpu_to_be32(SHA224_H4), cpu_to_be32(SHA224_H5),
	cpu_to_be32(SHA224_H6), cpu_to_be32(SHA224_H7),
};

38
static const __be32 ccp_sha256_init[SHA256_DIGEST_SIZE / sizeof(__be32)] = {
39 40 41 42 43 44
	cpu_to_be32(SHA256_H0), cpu_to_be32(SHA256_H1),
	cpu_to_be32(SHA256_H2), cpu_to_be32(SHA256_H3),
	cpu_to_be32(SHA256_H4), cpu_to_be32(SHA256_H5),
	cpu_to_be32(SHA256_H6), cpu_to_be32(SHA256_H7),
};

45 46 47 48 49 50 51 52 53 54 55 56 57 58
static const __be64 ccp_sha384_init[SHA512_DIGEST_SIZE / sizeof(__be64)] = {
	cpu_to_be64(SHA384_H0), cpu_to_be64(SHA384_H1),
	cpu_to_be64(SHA384_H2), cpu_to_be64(SHA384_H3),
	cpu_to_be64(SHA384_H4), cpu_to_be64(SHA384_H5),
	cpu_to_be64(SHA384_H6), cpu_to_be64(SHA384_H7),
};

static const __be64 ccp_sha512_init[SHA512_DIGEST_SIZE / sizeof(__be64)] = {
	cpu_to_be64(SHA512_H0), cpu_to_be64(SHA512_H1),
	cpu_to_be64(SHA512_H2), cpu_to_be64(SHA512_H3),
	cpu_to_be64(SHA512_H4), cpu_to_be64(SHA512_H5),
	cpu_to_be64(SHA512_H6), cpu_to_be64(SHA512_H7),
};

59 60 61
#define	CCP_NEW_JOBID(ccp)	((ccp->vdata->version == CCP_VERSION(3, 0)) ? \
					ccp_gen_jobid(ccp) : 0)

62 63 64 65 66 67 68 69 70 71 72 73 74 75
static u32 ccp_gen_jobid(struct ccp_device *ccp)
{
	return atomic_inc_return(&ccp->current_id) & CCP_JOBID_MASK;
}

static void ccp_sg_free(struct ccp_sg_workarea *wa)
{
	if (wa->dma_count)
		dma_unmap_sg(wa->dma_dev, wa->dma_sg, wa->nents, wa->dma_dir);

	wa->dma_count = 0;
}

static int ccp_init_sg_workarea(struct ccp_sg_workarea *wa, struct device *dev,
76
				struct scatterlist *sg, u64 len,
77 78 79 80 81 82 83 84
				enum dma_data_direction dma_dir)
{
	memset(wa, 0, sizeof(*wa));

	wa->sg = sg;
	if (!sg)
		return 0;

85 86 87 88
	wa->nents = sg_nents_for_len(sg, len);
	if (wa->nents < 0)
		return wa->nents;

89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109
	wa->bytes_left = len;
	wa->sg_used = 0;

	if (len == 0)
		return 0;

	if (dma_dir == DMA_NONE)
		return 0;

	wa->dma_sg = sg;
	wa->dma_dev = dev;
	wa->dma_dir = dma_dir;
	wa->dma_count = dma_map_sg(dev, sg, wa->nents, dma_dir);
	if (!wa->dma_count)
		return -ENOMEM;

	return 0;
}

static void ccp_update_sg_workarea(struct ccp_sg_workarea *wa, unsigned int len)
{
110
	unsigned int nbytes = min_t(u64, len, wa->bytes_left);
111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200

	if (!wa->sg)
		return;

	wa->sg_used += nbytes;
	wa->bytes_left -= nbytes;
	if (wa->sg_used == wa->sg->length) {
		wa->sg = sg_next(wa->sg);
		wa->sg_used = 0;
	}
}

static void 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);
	}

	wa->address = NULL;
	wa->dma.address = 0;
}

static int ccp_init_dm_workarea(struct ccp_dm_workarea *wa,
				struct ccp_cmd_queue *cmd_q,
				unsigned int len,
				enum dma_data_direction dir)
{
	memset(wa, 0, sizeof(*wa));

	if (!len)
		return 0;

	wa->dev = cmd_q->ccp->dev;
	wa->length = len;

	if (len <= CCP_DMAPOOL_MAX_SIZE) {
		wa->dma_pool = cmd_q->dma_pool;

		wa->address = dma_pool_alloc(wa->dma_pool, GFP_KERNEL,
					     &wa->dma.address);
		if (!wa->address)
			return -ENOMEM;

		wa->dma.length = CCP_DMAPOOL_MAX_SIZE;

		memset(wa->address, 0, CCP_DMAPOOL_MAX_SIZE);
	} else {
		wa->address = kzalloc(len, GFP_KERNEL);
		if (!wa->address)
			return -ENOMEM;

		wa->dma.address = dma_map_single(wa->dev, wa->address, len,
						 dir);
		if (!wa->dma.address)
			return -ENOMEM;

		wa->dma.length = len;
	}
	wa->dma.dir = dir;

	return 0;
}

static void ccp_set_dm_area(struct ccp_dm_workarea *wa, unsigned int wa_offset,
			    struct scatterlist *sg, unsigned int sg_offset,
			    unsigned int len)
{
	WARN_ON(!wa->address);

	scatterwalk_map_and_copy(wa->address + wa_offset, sg, sg_offset, len,
				 0);
}

static void ccp_get_dm_area(struct ccp_dm_workarea *wa, unsigned int wa_offset,
			    struct scatterlist *sg, unsigned int sg_offset,
			    unsigned int len)
{
	WARN_ON(!wa->address);

	scatterwalk_map_and_copy(wa->address + wa_offset, sg, sg_offset, len,
				 1);
}

201
static int ccp_reverse_set_dm_area(struct ccp_dm_workarea *wa,
202
				   unsigned int wa_offset,
203
				   struct scatterlist *sg,
204 205
				   unsigned int sg_offset,
				   unsigned int len)
206
{
207 208 209 210 211 212 213 214 215 216 217 218
	u8 *p, *q;

	ccp_set_dm_area(wa, wa_offset, sg, sg_offset, len);

	p = wa->address + wa_offset;
	q = p + len - 1;
	while (p < q) {
		*p = *p ^ *q;
		*q = *p ^ *q;
		*p = *p ^ *q;
		p++;
		q--;
219
	}
220
	return 0;
221 222 223
}

static void ccp_reverse_get_dm_area(struct ccp_dm_workarea *wa,
224
				    unsigned int wa_offset,
225
				    struct scatterlist *sg,
226
				    unsigned int sg_offset,
227 228
				    unsigned int len)
{
229 230 231 232 233 234 235 236 237 238
	u8 *p, *q;

	p = wa->address + wa_offset;
	q = p + len - 1;
	while (p < q) {
		*p = *p ^ *q;
		*q = *p ^ *q;
		*p = *p ^ *q;
		p++;
		q--;
239
	}
240 241

	ccp_get_dm_area(wa, wa_offset, sg, sg_offset, len);
242 243 244 245 246 247 248 249 250
}

static void ccp_free_data(struct ccp_data *data, struct ccp_cmd_queue *cmd_q)
{
	ccp_dm_free(&data->dm_wa);
	ccp_sg_free(&data->sg_wa);
}

static int ccp_init_data(struct ccp_data *data, struct ccp_cmd_queue *cmd_q,
251
			 struct scatterlist *sg, u64 sg_len,
252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288
			 unsigned int dm_len,
			 enum dma_data_direction dir)
{
	int ret;

	memset(data, 0, sizeof(*data));

	ret = ccp_init_sg_workarea(&data->sg_wa, cmd_q->ccp->dev, sg, sg_len,
				   dir);
	if (ret)
		goto e_err;

	ret = ccp_init_dm_workarea(&data->dm_wa, cmd_q, dm_len, dir);
	if (ret)
		goto e_err;

	return 0;

e_err:
	ccp_free_data(data, cmd_q);

	return ret;
}

static unsigned int ccp_queue_buf(struct ccp_data *data, unsigned int from)
{
	struct ccp_sg_workarea *sg_wa = &data->sg_wa;
	struct ccp_dm_workarea *dm_wa = &data->dm_wa;
	unsigned int buf_count, nbytes;

	/* Clear the buffer if setting it */
	if (!from)
		memset(dm_wa->address, 0, dm_wa->length);

	if (!sg_wa->sg)
		return 0;

289 290 291 292 293
	/* 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);
294 295 296 297 298 299
	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)) {
300 301 302
		nbytes = min(sg_wa->sg->length - sg_wa->sg_used,
			     dm_wa->length - buf_count);
		nbytes = min_t(u64, sg_wa->bytes_left, nbytes);
303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328

		buf_count += nbytes;
		ccp_update_sg_workarea(sg_wa, nbytes);
	}

	return buf_count;
}

static unsigned int ccp_fill_queue_buf(struct ccp_data *data)
{
	return ccp_queue_buf(data, 0);
}

static unsigned int ccp_empty_queue_buf(struct ccp_data *data)
{
	return ccp_queue_buf(data, 1);
}

static void ccp_prepare_data(struct ccp_data *src, struct ccp_data *dst,
			     struct ccp_op *op, unsigned int block_size,
			     bool blocksize_op)
{
	unsigned int sg_src_len, sg_dst_len, op_len;

	/* The CCP can only DMA from/to one address each per operation. This
	 * requires that we find the smallest DMA area between the source
329 330
	 * and destination. The resulting len values will always be <= UINT_MAX
	 * because the dma length is an unsigned int.
331
	 */
332 333
	sg_src_len = sg_dma_len(src->sg_wa.sg) - src->sg_wa.sg_used;
	sg_src_len = min_t(u64, src->sg_wa.bytes_left, sg_src_len);
334 335

	if (dst) {
336 337
		sg_dst_len = sg_dma_len(dst->sg_wa.sg) - dst->sg_wa.sg_used;
		sg_dst_len = min_t(u64, src->sg_wa.bytes_left, sg_dst_len);
338
		op_len = min(sg_src_len, sg_dst_len);
339
	} else {
340
		op_len = sg_src_len;
341
	}
342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407

	/* 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.sg);
		op->src.u.dma.offset = src->sg_wa.sg_used;
		op->src.u.dma.length = op_len & ~(block_size - 1);

		ccp_update_sg_workarea(&src->sg_wa, op->src.u.dma.length);
	}

	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.sg);
			op->dst.u.dma.offset = dst->sg_wa.sg_used;
			op->dst.u.dma.length = op->src.u.dma.length;
		}
	}
}

static void ccp_process_data(struct ccp_data *src, struct ccp_data *dst,
			     struct ccp_op *op)
{
	op->init = 0;

	if (dst) {
		if (op->dst.u.dma.address == dst->dm_wa.dma.address)
			ccp_empty_queue_buf(dst);
		else
			ccp_update_sg_workarea(&dst->sg_wa,
					       op->dst.u.dma.length);
	}
}

408 409 410
static int ccp_copy_to_from_sb(struct ccp_cmd_queue *cmd_q,
			       struct ccp_dm_workarea *wa, u32 jobid, u32 sb,
			       u32 byte_swap, bool from)
411 412 413 414 415 416 417 418 419 420 421
{
	struct ccp_op op;

	memset(&op, 0, sizeof(op));

	op.cmd_q = cmd_q;
	op.jobid = jobid;
	op.eom = 1;

	if (from) {
		op.soc = 1;
422 423
		op.src.type = CCP_MEMTYPE_SB;
		op.src.u.sb = sb;
424 425 426 427 428 429 430
		op.dst.type = CCP_MEMTYPE_SYSTEM;
		op.dst.u.dma.address = wa->dma.address;
		op.dst.u.dma.length = wa->length;
	} else {
		op.src.type = CCP_MEMTYPE_SYSTEM;
		op.src.u.dma.address = wa->dma.address;
		op.src.u.dma.length = wa->length;
431 432
		op.dst.type = CCP_MEMTYPE_SB;
		op.dst.u.sb = sb;
433 434 435 436
	}

	op.u.passthru.byte_swap = byte_swap;

437
	return cmd_q->ccp->vdata->perform->passthru(&op);
438 439
}

440 441 442
static int ccp_copy_to_sb(struct ccp_cmd_queue *cmd_q,
			  struct ccp_dm_workarea *wa, u32 jobid, u32 sb,
			  u32 byte_swap)
443
{
444
	return ccp_copy_to_from_sb(cmd_q, wa, jobid, sb, byte_swap, false);
445 446
}

447 448 449
static int ccp_copy_from_sb(struct ccp_cmd_queue *cmd_q,
			    struct ccp_dm_workarea *wa, u32 jobid, u32 sb,
			    u32 byte_swap)
450
{
451
	return ccp_copy_to_from_sb(cmd_q, wa, jobid, sb, byte_swap, true);
452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485
}

static int ccp_run_aes_cmac_cmd(struct ccp_cmd_queue *cmd_q,
				struct ccp_cmd *cmd)
{
	struct ccp_aes_engine *aes = &cmd->u.aes;
	struct ccp_dm_workarea key, ctx;
	struct ccp_data src;
	struct ccp_op op;
	unsigned int dm_offset;
	int ret;

	if (!((aes->key_len == AES_KEYSIZE_128) ||
	      (aes->key_len == AES_KEYSIZE_192) ||
	      (aes->key_len == AES_KEYSIZE_256)))
		return -EINVAL;

	if (aes->src_len & (AES_BLOCK_SIZE - 1))
		return -EINVAL;

	if (aes->iv_len != AES_BLOCK_SIZE)
		return -EINVAL;

	if (!aes->key || !aes->iv || !aes->src)
		return -EINVAL;

	if (aes->cmac_final) {
		if (aes->cmac_key_len != AES_BLOCK_SIZE)
			return -EINVAL;

		if (!aes->cmac_key)
			return -EINVAL;
	}

486 487
	BUILD_BUG_ON(CCP_AES_KEY_SB_COUNT != 1);
	BUILD_BUG_ON(CCP_AES_CTX_SB_COUNT != 1);
488 489 490 491

	ret = -EIO;
	memset(&op, 0, sizeof(op));
	op.cmd_q = cmd_q;
492
	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
493 494
	op.sb_key = cmd_q->sb_key;
	op.sb_ctx = cmd_q->sb_ctx;
495 496 497 498 499
	op.init = 1;
	op.u.aes.type = aes->type;
	op.u.aes.mode = aes->mode;
	op.u.aes.action = aes->action;

500
	/* All supported key sizes fit in a single (32-byte) SB entry
501 502 503 504 505
	 * 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,
506
				   CCP_AES_KEY_SB_COUNT * CCP_SB_BYTES,
507 508 509 510
				   DMA_TO_DEVICE);
	if (ret)
		return ret;

511
	dm_offset = CCP_SB_BYTES - aes->key_len;
512
	ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
513 514
	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
			     CCP_PASSTHRU_BYTESWAP_256BIT);
515 516 517 518 519
	if (ret) {
		cmd->engine_error = cmd_q->cmd_error;
		goto e_key;
	}

520
	/* The AES context fits in a single (32-byte) SB entry and
521 522 523 524
	 * 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,
525
				   CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES,
526 527 528 529
				   DMA_BIDIRECTIONAL);
	if (ret)
		goto e_key;

530
	dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
531
	ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
532 533
	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
			     CCP_PASSTHRU_BYTESWAP_256BIT);
534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550
	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 */
551 552 553
			ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid,
					       op.sb_ctx,
					       CCP_PASSTHRU_BYTESWAP_256BIT);
554 555 556 557 558 559 560
			if (ret) {
				cmd->engine_error = cmd_q->cmd_error;
				goto e_src;
			}

			ccp_set_dm_area(&ctx, 0, aes->cmac_key, 0,
					aes->cmac_key_len);
561 562
			ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
					     CCP_PASSTHRU_BYTESWAP_256BIT);
563 564 565 566 567 568
			if (ret) {
				cmd->engine_error = cmd_q->cmd_error;
				goto e_src;
			}
		}

569
		ret = cmd_q->ccp->vdata->perform->aes(&op);
570 571 572 573 574 575 576 577 578 579 580
		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
	 */
581 582
	ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
			       CCP_PASSTHRU_BYTESWAP_256BIT);
583 584 585 586 587 588
	if (ret) {
		cmd->engine_error = cmd_q->cmd_error;
		goto e_src;
	}

	/* ...but we only need AES_BLOCK_SIZE bytes */
589
	dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
590 591 592 593 594 595 596 597 598 599 600 601 602 603
	ccp_get_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);

e_src:
	ccp_free_data(&src, cmd_q);

e_ctx:
	ccp_dm_free(&ctx);

e_key:
	ccp_dm_free(&key);

	return ret;
}

604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852
static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
			       struct ccp_cmd *cmd)
{
	struct ccp_aes_engine *aes = &cmd->u.aes;
	struct ccp_dm_workarea key, ctx, final_wa, tag;
	struct ccp_data src, dst;
	struct ccp_data aad;
	struct ccp_op op;

	unsigned long long *final;
	unsigned int dm_offset;
	unsigned int ilen;
	bool in_place = true; /* Default value */
	int ret;

	struct scatterlist *p_inp, sg_inp[2];
	struct scatterlist *p_tag, sg_tag[2];
	struct scatterlist *p_outp, sg_outp[2];
	struct scatterlist *p_aad;

	if (!aes->iv)
		return -EINVAL;

	if (!((aes->key_len == AES_KEYSIZE_128) ||
		(aes->key_len == AES_KEYSIZE_192) ||
		(aes->key_len == AES_KEYSIZE_256)))
		return -EINVAL;

	if (!aes->key) /* Gotta have a key SGL */
		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 - AES_BLOCK_SIZE;
		p_tag = scatterwalk_ffwd(sg_tag, p_inp, ilen);
	}

	memset(&op, 0, sizeof(op));
	op.cmd_q = cmd_q;
	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
	op.sb_key = cmd_q->sb_key; /* Pre-allocated */
	op.sb_ctx = cmd_q->sb_ctx; /* Pre-allocated */
	op.init = 1;
	op.u.aes.type = aes->type;

	/* Copy the key to the LSB */
	ret = ccp_init_dm_workarea(&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;
	ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
	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;
	}

	/* 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(&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;
	ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);

	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;
	}

	op.init = 1;
	if (aes->aad_len > 0) {
		/* Step 1: Run a GHASH over the Additional Authenticated Data */
		ret = ccp_init_data(&aad, cmd_q, p_aad, aes->aad_len,
				    AES_BLOCK_SIZE,
				    DMA_TO_DEVICE);
		if (ret)
			goto e_ctx;

		op.u.aes.mode = CCP_AES_MODE_GHASH;
		op.u.aes.action = CCP_AES_GHASHAAD;

		while (aad.sg_wa.bytes_left) {
			ccp_prepare_data(&aad, NULL, &op, AES_BLOCK_SIZE, true);

			ret = cmd_q->ccp->vdata->perform->aes(&op);
			if (ret) {
				cmd->engine_error = cmd_q->cmd_error;
				goto e_aad;
			}

			ccp_process_data(&aad, NULL, &op);
			op.init = 0;
		}
	}

	op.u.aes.mode = CCP_AES_MODE_GCTR;
	op.u.aes.action = aes->action;

	if (ilen > 0) {
		/* Step 2: Run a GCTR over the plaintext */
		in_place = (sg_virt(p_inp) == sg_virt(p_outp)) ? true : false;

		ret = ccp_init_data(&src, cmd_q, p_inp, ilen,
				    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, p_outp, ilen,
					    AES_BLOCK_SIZE, DMA_FROM_DEVICE);
			if (ret)
				goto e_src;
		}

		op.soc = 0;
		op.eom = 0;
		op.init = 1;
		while (src.sg_wa.bytes_left) {
			ccp_prepare_data(&src, &dst, &op, AES_BLOCK_SIZE, true);
			if (!src.sg_wa.bytes_left) {
				unsigned int nbytes = aes->src_len
						      % AES_BLOCK_SIZE;

				if (nbytes) {
					op.eom = 1;
					op.u.aes.size = (nbytes * 8) - 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);
			op.init = 0;
		}
	}

	/* Step 3: Update the IV portion of the context with the original IV */
	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;
	}

	ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);

	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_dst;
	}

	/* Step 4: Concatenate the lengths of the AAD and source, and
	 * hash that 16 byte buffer.
	 */
	ret = ccp_init_dm_workarea(&final_wa, cmd_q, AES_BLOCK_SIZE,
				   DMA_BIDIRECTIONAL);
	if (ret)
		goto e_dst;
	final = (unsigned long long *) final_wa.address;
	final[0] = cpu_to_be64(aes->aad_len * 8);
	final[1] = cpu_to_be64(ilen * 8);

	op.u.aes.mode = CCP_AES_MODE_GHASH;
	op.u.aes.action = CCP_AES_GHASHFINAL;
	op.src.type = CCP_MEMTYPE_SYSTEM;
	op.src.u.dma.address = final_wa.dma.address;
	op.src.u.dma.length = AES_BLOCK_SIZE;
	op.dst.type = CCP_MEMTYPE_SYSTEM;
	op.dst.u.dma.address = final_wa.dma.address;
	op.dst.u.dma.length = AES_BLOCK_SIZE;
	op.eom = 1;
	op.u.aes.size = 0;
	ret = cmd_q->ccp->vdata->perform->aes(&op);
	if (ret)
		goto e_dst;

	if (aes->action == CCP_AES_ACTION_ENCRYPT) {
		/* Put the ciphered tag after the ciphertext. */
		ccp_get_dm_area(&final_wa, 0, p_tag, 0, AES_BLOCK_SIZE);
	} else {
		/* Does this ciphered tag match the input? */
		ret = ccp_init_dm_workarea(&tag, cmd_q, AES_BLOCK_SIZE,
					   DMA_BIDIRECTIONAL);
		if (ret)
			goto e_tag;
		ccp_set_dm_area(&tag, 0, p_tag, 0, AES_BLOCK_SIZE);

		ret = memcmp(tag.address, final_wa.address, AES_BLOCK_SIZE);
		ccp_dm_free(&tag);
	}

e_tag:
	ccp_dm_free(&final_wa);

e_dst:
	if (aes->src_len && !in_place)
		ccp_free_data(&dst, cmd_q);

e_src:
	if (aes->src_len)
		ccp_free_data(&src, cmd_q);

e_aad:
	if (aes->aad_len)
		ccp_free_data(&aad, cmd_q);

e_ctx:
	ccp_dm_free(&ctx);

e_key:
	ccp_dm_free(&key);

	return ret;
}

853 854 855 856 857 858 859 860 861 862 863 864 865
static int ccp_run_aes_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
{
	struct ccp_aes_engine *aes = &cmd->u.aes;
	struct ccp_dm_workarea key, ctx;
	struct ccp_data src, dst;
	struct ccp_op op;
	unsigned int dm_offset;
	bool in_place = false;
	int ret;

	if (aes->mode == CCP_AES_MODE_CMAC)
		return ccp_run_aes_cmac_cmd(cmd_q, cmd);

866 867 868
	if (aes->mode == CCP_AES_MODE_GCM)
		return ccp_run_aes_gcm_cmd(cmd_q, cmd);

869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890
	if (!((aes->key_len == AES_KEYSIZE_128) ||
	      (aes->key_len == AES_KEYSIZE_192) ||
	      (aes->key_len == AES_KEYSIZE_256)))
		return -EINVAL;

	if (((aes->mode == CCP_AES_MODE_ECB) ||
	     (aes->mode == CCP_AES_MODE_CBC) ||
	     (aes->mode == CCP_AES_MODE_CFB)) &&
	    (aes->src_len & (AES_BLOCK_SIZE - 1)))
		return -EINVAL;

	if (!aes->key || !aes->src || !aes->dst)
		return -EINVAL;

	if (aes->mode != CCP_AES_MODE_ECB) {
		if (aes->iv_len != AES_BLOCK_SIZE)
			return -EINVAL;

		if (!aes->iv)
			return -EINVAL;
	}

891 892
	BUILD_BUG_ON(CCP_AES_KEY_SB_COUNT != 1);
	BUILD_BUG_ON(CCP_AES_CTX_SB_COUNT != 1);
893 894 895 896

	ret = -EIO;
	memset(&op, 0, sizeof(op));
	op.cmd_q = cmd_q;
897
	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
898 899
	op.sb_key = cmd_q->sb_key;
	op.sb_ctx = cmd_q->sb_ctx;
900 901 902 903 904
	op.init = (aes->mode == CCP_AES_MODE_ECB) ? 0 : 1;
	op.u.aes.type = aes->type;
	op.u.aes.mode = aes->mode;
	op.u.aes.action = aes->action;

905
	/* All supported key sizes fit in a single (32-byte) SB entry
906 907 908 909 910
	 * 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,
911
				   CCP_AES_KEY_SB_COUNT * CCP_SB_BYTES,
912 913 914 915
				   DMA_TO_DEVICE);
	if (ret)
		return ret;

916
	dm_offset = CCP_SB_BYTES - aes->key_len;
917
	ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
918 919
	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
			     CCP_PASSTHRU_BYTESWAP_256BIT);
920 921 922 923 924
	if (ret) {
		cmd->engine_error = cmd_q->cmd_error;
		goto e_key;
	}

925
	/* The AES context fits in a single (32-byte) SB entry and
926 927 928 929
	 * 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,
930
				   CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES,
931 932 933 934 935
				   DMA_BIDIRECTIONAL);
	if (ret)
		goto e_key;

	if (aes->mode != CCP_AES_MODE_ECB) {
936
		/* Load the AES context - convert to LE */
937
		dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
938
		ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
939 940
		ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
				     CCP_PASSTHRU_BYTESWAP_256BIT);
941 942 943 944 945
		if (ret) {
			cmd->engine_error = cmd_q->cmd_error;
			goto e_ctx;
		}
	}
946 947 948 949 950 951 952 953
	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;
	}
954 955 956 957 958 959 960 961 962 963 964 965 966 967

	/* 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;

968
	if (in_place) {
969
		dst = src;
970
	} else {
971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990
		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;
		}

991
		ret = cmd_q->ccp->vdata->perform->aes(&op);
992 993 994 995 996 997 998 999 1000 1001 1002 1003
		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
		 */
1004 1005
		ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
				       CCP_PASSTHRU_BYTESWAP_256BIT);
1006 1007 1008 1009 1010 1011
		if (ret) {
			cmd->engine_error = cmd_q->cmd_error;
			goto e_dst;
		}

		/* ...but we only need AES_BLOCK_SIZE bytes */
1012
		dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040
		ccp_get_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
	}

e_dst:
	if (!in_place)
		ccp_free_data(&dst, cmd_q);

e_src:
	ccp_free_data(&src, cmd_q);

e_ctx:
	ccp_dm_free(&ctx);

e_key:
	ccp_dm_free(&key);

	return ret;
}

static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
			       struct ccp_cmd *cmd)
{
	struct ccp_xts_aes_engine *xts = &cmd->u.xts;
	struct ccp_dm_workarea key, ctx;
	struct ccp_data src, dst;
	struct ccp_op op;
	unsigned int unit_size, dm_offset;
	bool in_place = false;
1041 1042
	unsigned int sb_count;
	enum ccp_aes_type aestype;
1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065
	int ret;

	switch (xts->unit_size) {
	case CCP_XTS_AES_UNIT_SIZE_16:
		unit_size = 16;
		break;
	case CCP_XTS_AES_UNIT_SIZE_512:
		unit_size = 512;
		break;
	case CCP_XTS_AES_UNIT_SIZE_1024:
		unit_size = 1024;
		break;
	case CCP_XTS_AES_UNIT_SIZE_2048:
		unit_size = 2048;
		break;
	case CCP_XTS_AES_UNIT_SIZE_4096:
		unit_size = 4096;
		break;

	default:
		return -EINVAL;
	}

1066 1067
	if (xts->key_len == AES_KEYSIZE_128)
		aestype = CCP_AES_TYPE_128;
1068 1069
	else if (xts->key_len == AES_KEYSIZE_256)
		aestype = CCP_AES_TYPE_256;
1070
	else
1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081
		return -EINVAL;

	if (!xts->final && (xts->src_len & (AES_BLOCK_SIZE - 1)))
		return -EINVAL;

	if (xts->iv_len != AES_BLOCK_SIZE)
		return -EINVAL;

	if (!xts->key || !xts->iv || !xts->src || !xts->dst)
		return -EINVAL;

1082 1083
	BUILD_BUG_ON(CCP_XTS_AES_KEY_SB_COUNT != 1);
	BUILD_BUG_ON(CCP_XTS_AES_CTX_SB_COUNT != 1);
1084 1085 1086 1087

	ret = -EIO;
	memset(&op, 0, sizeof(op));
	op.cmd_q = cmd_q;
1088
	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
1089 1090
	op.sb_key = cmd_q->sb_key;
	op.sb_ctx = cmd_q->sb_ctx;
1091
	op.init = 1;
1092
	op.u.xts.type = aestype;
1093 1094 1095
	op.u.xts.action = xts->action;
	op.u.xts.unit_size = xts->unit_size;

1096 1097 1098
	/* 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.
1099
	 */
1100 1101 1102 1103
	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;
1104
	ret = ccp_init_dm_workarea(&key, cmd_q,
1105
				   sb_count * CCP_SB_BYTES,
1106 1107 1108 1109
				   DMA_TO_DEVICE);
	if (ret)
		return ret;

1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129
	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;
		ccp_set_dm_area(&key, dm_offset, xts->key, 0, xts->key_len);
		ccp_set_dm_area(&key, 0, xts->key, xts->key_len, xts->key_len);
	} 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.
		 */
		unsigned int pad;

		dm_offset = CCP_SB_BYTES;
		pad = dm_offset - xts->key_len;
		ccp_set_dm_area(&key, pad, xts->key, 0, xts->key_len);
		ccp_set_dm_area(&key, dm_offset + pad, xts->key, xts->key_len,
				xts->key_len);
	}
1130 1131
	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
			     CCP_PASSTHRU_BYTESWAP_256BIT);
1132 1133 1134 1135 1136
	if (ret) {
		cmd->engine_error = cmd_q->cmd_error;
		goto e_key;
	}

1137
	/* The AES context fits in a single (32-byte) SB entry and
1138 1139 1140 1141
	 * for XTS is already in little endian format so no byte swapping
	 * is needed.
	 */
	ret = ccp_init_dm_workarea(&ctx, cmd_q,
1142
				   CCP_XTS_AES_CTX_SB_COUNT * CCP_SB_BYTES,
1143 1144 1145 1146 1147
				   DMA_BIDIRECTIONAL);
	if (ret)
		goto e_key;

	ccp_set_dm_area(&ctx, 0, xts->iv, 0, xts->iv_len);
1148 1149
	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
			     CCP_PASSTHRU_BYTESWAP_NOOP);
1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167
	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;

1168
	if (in_place) {
1169
		dst = src;
1170
	} else {
1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182
		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;

1183
		ret = cmd_q->ccp->vdata->perform->xts_aes(&op);
1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194
		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
	 */
1195 1196
	ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
			       CCP_PASSTHRU_BYTESWAP_256BIT);
1197 1198 1199 1200 1201 1202
	if (ret) {
		cmd->engine_error = cmd_q->cmd_error;
		goto e_dst;
	}

	/* ...but we only need AES_BLOCK_SIZE bytes */
1203
	dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221
	ccp_get_dm_area(&ctx, dm_offset, xts->iv, 0, xts->iv_len);

e_dst:
	if (!in_place)
		ccp_free_data(&dst, cmd_q);

e_src:
	ccp_free_data(&src, cmd_q);

e_ctx:
	ccp_dm_free(&ctx);

e_key:
	ccp_dm_free(&key);

	return ret;
}

1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415
static int ccp_run_des3_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
{
	struct ccp_des3_engine *des3 = &cmd->u.des3;

	struct ccp_dm_workarea key, ctx;
	struct ccp_data src, dst;
	struct ccp_op op;
	unsigned int dm_offset;
	unsigned int len_singlekey;
	bool in_place = false;
	int ret;

	/* Error checks */
	if (!cmd_q->ccp->vdata->perform->des3)
		return -EINVAL;

	if (des3->key_len != DES3_EDE_KEY_SIZE)
		return -EINVAL;

	if (((des3->mode == CCP_DES3_MODE_ECB) ||
		(des3->mode == CCP_DES3_MODE_CBC)) &&
		(des3->src_len & (DES3_EDE_BLOCK_SIZE - 1)))
		return -EINVAL;

	if (!des3->key || !des3->src || !des3->dst)
		return -EINVAL;

	if (des3->mode != CCP_DES3_MODE_ECB) {
		if (des3->iv_len != DES3_EDE_BLOCK_SIZE)
			return -EINVAL;

		if (!des3->iv)
			return -EINVAL;
	}

	ret = -EIO;
	/* Zero out all the fields of the command desc */
	memset(&op, 0, sizeof(op));

	/* Set up the Function field */
	op.cmd_q = cmd_q;
	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
	op.sb_key = cmd_q->sb_key;

	op.init = (des3->mode == CCP_DES3_MODE_ECB) ? 0 : 1;
	op.u.des3.type = des3->type;
	op.u.des3.mode = des3->mode;
	op.u.des3.action = des3->action;

	/*
	 * 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;
	ccp_set_dm_area(&key, dm_offset + 2 * len_singlekey,
			des3->key, 0, len_singlekey);
	ccp_set_dm_area(&key, dm_offset + len_singlekey,
			des3->key, len_singlekey, len_singlekey);
	ccp_set_dm_area(&key, dm_offset,
			des3->key, 2 * len_singlekey, len_singlekey);

	/* 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) {
		u32 load_mode;

		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;
		ccp_set_dm_area(&ctx, dm_offset, des3->iv, 0, des3->iv_len);

		if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0))
			load_mode = CCP_PASSTHRU_BYTESWAP_NOOP;
		else
			load_mode = CCP_PASSTHRU_BYTESWAP_256BIT;
		ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
				     load_mode);
		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 */
		if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0))
			dm_offset = CCP_SB_BYTES - des3->iv_len;
		else
			dm_offset = 0;
		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;
}

1416 1417 1418 1419 1420 1421
static 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;
1422 1423 1424 1425 1426 1427
	unsigned int ioffset, ooffset;
	unsigned int digest_size;
	int sb_count;
	const void *init;
	u64 block_size;
	int ctx_size;
1428 1429
	int ret;

1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445
	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;
1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457
	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;
1458
	default:
1459
		return -EINVAL;
1460
	}
1461 1462 1463 1464

	if (!sha->ctx)
		return -EINVAL;

1465
	if (!sha->final && (sha->src_len & (block_size - 1)))
1466 1467
		return -EINVAL;

1468 1469
	/* The version 3 device can't handle zero-length input */
	if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0)) {
1470

1471 1472 1473
		if (!sha->src_len) {
			unsigned int digest_len;
			const u8 *sha_zero;
1474

1475 1476 1477
			/* Not final, just return */
			if (!sha->final)
				return 0;
1478

1479 1480 1481 1482 1483
			/* CCP can't do a zero length sha operation so the
			 * caller must buffer the data.
			 */
			if (sha->msg_bits)
				return -EINVAL;
1484

1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506
			/* 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;
			}
1507

1508 1509 1510 1511 1512
			scatterwalk_map_and_copy((void *)sha_zero, sha->ctx, 0,
						 digest_len, 1);

			return 0;
		}
1513 1514
	}

1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544
	/* Set variables used throughout */
	switch (sha->type) {
	case CCP_SHA_TYPE_1:
		digest_size = SHA1_DIGEST_SIZE;
		init = (void *) ccp_sha1_init;
		ctx_size = SHA1_DIGEST_SIZE;
		sb_count = 1;
		if (cmd_q->ccp->vdata->version != CCP_VERSION(3, 0))
			ooffset = ioffset = CCP_SB_BYTES - SHA1_DIGEST_SIZE;
		else
			ooffset = ioffset = 0;
		break;
	case CCP_SHA_TYPE_224:
		digest_size = SHA224_DIGEST_SIZE;
		init = (void *) ccp_sha224_init;
		ctx_size = SHA256_DIGEST_SIZE;
		sb_count = 1;
		ioffset = 0;
		if (cmd_q->ccp->vdata->version != CCP_VERSION(3, 0))
			ooffset = CCP_SB_BYTES - SHA224_DIGEST_SIZE;
		else
			ooffset = 0;
		break;
	case CCP_SHA_TYPE_256:
		digest_size = SHA256_DIGEST_SIZE;
		init = (void *) ccp_sha256_init;
		ctx_size = SHA256_DIGEST_SIZE;
		sb_count = 1;
		ooffset = ioffset = 0;
		break;
1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559
	case CCP_SHA_TYPE_384:
		digest_size = SHA384_DIGEST_SIZE;
		init = (void *) ccp_sha384_init;
		ctx_size = SHA512_DIGEST_SIZE;
		sb_count = 2;
		ioffset = 0;
		ooffset = 2 * CCP_SB_BYTES - SHA384_DIGEST_SIZE;
		break;
	case CCP_SHA_TYPE_512:
		digest_size = SHA512_DIGEST_SIZE;
		init = (void *) ccp_sha512_init;
		ctx_size = SHA512_DIGEST_SIZE;
		sb_count = 2;
		ooffset = ioffset = 0;
		break;
1560 1561 1562 1563
	default:
		ret = -EINVAL;
		goto e_data;
	}
1564

1565 1566 1567 1568 1569
	/* For zero-length plaintext the src pointer is ignored;
	 * otherwise both parts must be valid
	 */
	if (sha->src_len && !sha->src)
		return -EINVAL;
1570 1571 1572

	memset(&op, 0, sizeof(op));
	op.cmd_q = cmd_q;
1573 1574
	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
	op.sb_ctx = cmd_q->sb_ctx; /* Pre-allocated */
1575 1576 1577
	op.u.sha.type = sha->type;
	op.u.sha.msg_bits = sha->msg_bits;

1578 1579 1580 1581 1582
	/* 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.
	 */
1583
	ret = ccp_init_dm_workarea(&ctx, cmd_q, sb_count * CCP_SB_BYTES,
1584 1585 1586
				   DMA_BIDIRECTIONAL);
	if (ret)
		return ret;
1587 1588 1589 1590 1591
	if (sha->first) {
		switch (sha->type) {
		case CCP_SHA_TYPE_1:
		case CCP_SHA_TYPE_224:
		case CCP_SHA_TYPE_256:
1592
			memcpy(ctx.address + ioffset, init, ctx_size);
1593
			break;
1594 1595 1596 1597 1598 1599 1600
		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;
1601 1602 1603 1604
		default:
			ret = -EINVAL;
			goto e_ctx;
		}
1605
	} else {
1606 1607 1608
		/* Restore the context */
		ccp_set_dm_area(&ctx, 0, sha->ctx, 0,
				sb_count * CCP_SB_BYTES);
1609
	}
1610

1611 1612
	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
			     CCP_PASSTHRU_BYTESWAP_256BIT);
1613 1614 1615 1616 1617
	if (ret) {
		cmd->engine_error = cmd_q->cmd_error;
		goto e_ctx;
	}

1618 1619 1620 1621 1622 1623
	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;
1624

1625 1626 1627 1628 1629 1630 1631 1632 1633 1634
		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;
			}
1635

1636 1637 1638 1639
			ccp_process_data(&src, NULL, &op);
		}
	} else {
		op.eom = 1;
1640
		ret = cmd_q->ccp->vdata->perform->sha(&op);
1641 1642 1643 1644 1645 1646 1647 1648 1649
		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
	 */
1650 1651
	ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
			       CCP_PASSTHRU_BYTESWAP_256BIT);
1652 1653 1654 1655 1656
	if (ret) {
		cmd->engine_error = cmd_q->cmd_error;
		goto e_data;
	}

1657 1658
	if (sha->final) {
		/* Finishing up, so get the digest */
1659 1660 1661 1662
		switch (sha->type) {
		case CCP_SHA_TYPE_1:
		case CCP_SHA_TYPE_224:
		case CCP_SHA_TYPE_256:
1663 1664 1665
			ccp_get_dm_area(&ctx, ooffset,
					sha->ctx, 0,
					digest_size);
1666
			break;
1667 1668 1669 1670 1671 1672 1673 1674 1675
		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;
1676 1677
		default:
			ret = -EINVAL;
1678
			goto e_ctx;
1679
		}
1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690
	} else {
		/* Stash the context */
		ccp_get_dm_area(&ctx, 0, sha->ctx, 0,
				sb_count * CCP_SB_BYTES);
	}

	if (sha->final && sha->opad) {
		/* HMAC operation, recursively perform final SHA */
		struct ccp_cmd hmac_cmd;
		struct scatterlist sg;
		u8 *hmac_buf;
1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704

		if (sha->opad_len != block_size) {
			ret = -EINVAL;
			goto e_data;
		}

		hmac_buf = kmalloc(block_size + digest_size, GFP_KERNEL);
		if (!hmac_buf) {
			ret = -ENOMEM;
			goto e_data;
		}
		sg_init_one(&sg, hmac_buf, block_size + digest_size);

		scatterwalk_map_and_copy(hmac_buf, sha->opad, 0, block_size, 0);
1705 1706 1707 1708 1709 1710 1711 1712
		switch (sha->type) {
		case CCP_SHA_TYPE_1:
		case CCP_SHA_TYPE_224:
		case CCP_SHA_TYPE_256:
			memcpy(hmac_buf + block_size,
			       ctx.address + ooffset,
			       digest_size);
			break;
1713 1714 1715 1716 1717 1718 1719 1720 1721 1722
		case CCP_SHA_TYPE_384:
		case CCP_SHA_TYPE_512:
			memcpy(hmac_buf + block_size,
			       ctx.address + LSB_ITEM_SIZE + ooffset,
			       LSB_ITEM_SIZE);
			memcpy(hmac_buf + block_size +
			       (LSB_ITEM_SIZE - ooffset),
			       ctx.address,
			       LSB_ITEM_SIZE);
			break;
1723 1724 1725 1726
		default:
			ret = -EINVAL;
			goto e_ctx;
		}
1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747

		memset(&hmac_cmd, 0, sizeof(hmac_cmd));
		hmac_cmd.engine = CCP_ENGINE_SHA;
		hmac_cmd.u.sha.type = sha->type;
		hmac_cmd.u.sha.ctx = sha->ctx;
		hmac_cmd.u.sha.ctx_len = sha->ctx_len;
		hmac_cmd.u.sha.src = &sg;
		hmac_cmd.u.sha.src_len = block_size + digest_size;
		hmac_cmd.u.sha.opad = NULL;
		hmac_cmd.u.sha.opad_len = 0;
		hmac_cmd.u.sha.first = 1;
		hmac_cmd.u.sha.final = 1;
		hmac_cmd.u.sha.msg_bits = (block_size + digest_size) << 3;

		ret = ccp_run_sha_cmd(cmd_q, &hmac_cmd);
		if (ret)
			cmd->engine_error = hmac_cmd.engine_error;

		kfree(hmac_buf);
	}

1748
e_data:
1749 1750
	if (sha->src)
		ccp_free_data(&src, cmd_q);
1751 1752 1753 1754 1755 1756 1757 1758 1759 1760

e_ctx:
	ccp_dm_free(&ctx);

	return ret;
}

static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
{
	struct ccp_rsa_engine *rsa = &cmd->u.rsa;
1761
	struct ccp_dm_workarea exp, src, dst;
1762
	struct ccp_op op;
1763
	unsigned int sb_count, i_len, o_len;
1764 1765
	int ret;

1766 1767
	/* Check against the maximum allowable size, in bits */
	if (rsa->key_size > cmd_q->ccp->vdata->rsamax)
1768 1769 1770 1771 1772
		return -EINVAL;

	if (!rsa->exp || !rsa->mod || !rsa->src || !rsa->dst)
		return -EINVAL;

1773 1774 1775 1776
	memset(&op, 0, sizeof(op));
	op.cmd_q = cmd_q;
	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);

1777 1778 1779 1780
	/* 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
1781 1782 1783
	 * 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.
1784
	 */
1785
	o_len = 32 * ((rsa->key_size + 255) / 256);
1786 1787
	i_len = o_len * 2;

1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803
	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;
	}
1804

1805 1806
	/* The RSA exponent must be in little endian format. Reverse its
	 * byte order.
1807 1808 1809
	 */
	ret = ccp_init_dm_workarea(&exp, cmd_q, o_len, DMA_TO_DEVICE);
	if (ret)
1810
		goto e_sb;
1811

1812
	ret = ccp_reverse_set_dm_area(&exp, 0, rsa->exp, 0, rsa->exp_len);
1813 1814
	if (ret)
		goto e_exp;
1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830

	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;
1831 1832 1833 1834 1835 1836 1837 1838 1839 1840
	}

	/* 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;

1841
	ret = ccp_reverse_set_dm_area(&src, 0, rsa->mod, 0, rsa->mod_len);
1842 1843
	if (ret)
		goto e_src;
1844
	ret = ccp_reverse_set_dm_area(&src, o_len, rsa->src, 0, rsa->src_len);
1845 1846
	if (ret)
		goto e_src;
1847 1848

	/* Prepare the output area for the operation */
1849
	ret = ccp_init_dm_workarea(&dst, cmd_q, o_len, DMA_FROM_DEVICE);
1850 1851 1852 1853 1854 1855 1856
	if (ret)
		goto e_src;

	op.soc = 1;
	op.src.u.dma.address = src.dma.address;
	op.src.u.dma.offset = 0;
	op.src.u.dma.length = i_len;
1857
	op.dst.u.dma.address = dst.dma.address;
1858 1859 1860 1861 1862 1863
	op.dst.u.dma.offset = 0;
	op.dst.u.dma.length = o_len;

	op.u.rsa.mod_size = rsa->key_size;
	op.u.rsa.input_len = i_len;

1864
	ret = cmd_q->ccp->vdata->perform->rsa(&op);
1865 1866 1867 1868 1869
	if (ret) {
		cmd->engine_error = cmd_q->cmd_error;
		goto e_dst;
	}

1870
	ccp_reverse_get_dm_area(&dst, 0, rsa->dst, 0, rsa->mod_len);
1871 1872

e_dst:
1873
	ccp_dm_free(&dst);
1874 1875 1876 1877 1878 1879 1880

e_src:
	ccp_dm_free(&src);

e_exp:
	ccp_dm_free(&exp);

1881
e_sb:
1882 1883
	if (cmd_q->ccp->vdata->version < CCP_VERSION(5, 0))
		cmd_q->ccp->vdata->perform->sbfree(cmd_q, op.sb_key, sb_count);
1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896

	return ret;
}

static int ccp_run_passthru_cmd(struct ccp_cmd_queue *cmd_q,
				struct ccp_cmd *cmd)
{
	struct ccp_passthru_engine *pt = &cmd->u.passthru;
	struct ccp_dm_workarea mask;
	struct ccp_data src, dst;
	struct ccp_op op;
	bool in_place = false;
	unsigned int i;
1897
	int ret = 0;
1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911

	if (!pt->final && (pt->src_len & (CCP_PASSTHRU_BLOCKSIZE - 1)))
		return -EINVAL;

	if (!pt->src || !pt->dst)
		return -EINVAL;

	if (pt->bit_mod != CCP_PASSTHRU_BITWISE_NOOP) {
		if (pt->mask_len != CCP_PASSTHRU_MASKSIZE)
			return -EINVAL;
		if (!pt->mask)
			return -EINVAL;
	}

1912
	BUILD_BUG_ON(CCP_PASSTHRU_SB_COUNT != 1);
1913 1914 1915

	memset(&op, 0, sizeof(op));
	op.cmd_q = cmd_q;
1916
	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
1917 1918 1919

	if (pt->bit_mod != CCP_PASSTHRU_BITWISE_NOOP) {
		/* Load the mask */
1920
		op.sb_key = cmd_q->sb_key;
1921 1922

		ret = ccp_init_dm_workarea(&mask, cmd_q,
1923 1924
					   CCP_PASSTHRU_SB_COUNT *
					   CCP_SB_BYTES,
1925 1926 1927 1928 1929
					   DMA_TO_DEVICE);
		if (ret)
			return ret;

		ccp_set_dm_area(&mask, 0, pt->mask, 0, pt->mask_len);
1930 1931
		ret = ccp_copy_to_sb(cmd_q, &mask, op.jobid, op.sb_key,
				     CCP_PASSTHRU_BYTESWAP_NOOP);
1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950
		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;

1951
	if (in_place) {
1952
		dst = src;
1953
	} else {
1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986
		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 ||
		    (dst.sg_wa.sg->length < src.sg_wa.sg->length)) {
			ret = -EINVAL;
			goto e_dst;
		}

		if (i == src.sg_wa.dma_count) {
			op.eom = 1;
			op.soc = 1;
		}

		op.src.type = CCP_MEMTYPE_SYSTEM;
		op.src.u.dma.address = sg_dma_address(src.sg_wa.sg);
		op.src.u.dma.offset = 0;
		op.src.u.dma.length = sg_dma_len(src.sg_wa.sg);

		op.dst.type = CCP_MEMTYPE_SYSTEM;
		op.dst.u.dma.address = sg_dma_address(dst.sg_wa.sg);
1987 1988
		op.dst.u.dma.offset = dst.sg_wa.sg_used;
		op.dst.u.dma.length = op.src.u.dma.length;
1989

1990
		ret = cmd_q->ccp->vdata->perform->passthru(&op);
1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017
		if (ret) {
			cmd->engine_error = cmd_q->cmd_error;
			goto e_dst;
		}

		dst.sg_wa.sg_used += src.sg_wa.sg->length;
		if (dst.sg_wa.sg_used == dst.sg_wa.sg->length) {
			dst.sg_wa.sg = sg_next(dst.sg_wa.sg);
			dst.sg_wa.sg_used = 0;
		}
		src.sg_wa.sg = sg_next(src.sg_wa.sg);
	}

e_dst:
	if (!in_place)
		ccp_free_data(&dst, cmd_q);

e_src:
	ccp_free_data(&src, cmd_q);

e_mask:
	if (pt->bit_mod != CCP_PASSTHRU_BITWISE_NOOP)
		ccp_dm_free(&mask);

	return ret;
}

2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038
static int ccp_run_passthru_nomap_cmd(struct ccp_cmd_queue *cmd_q,
				      struct ccp_cmd *cmd)
{
	struct ccp_passthru_nomap_engine *pt = &cmd->u.passthru_nomap;
	struct ccp_dm_workarea mask;
	struct ccp_op op;
	int ret;

	if (!pt->final && (pt->src_len & (CCP_PASSTHRU_BLOCKSIZE - 1)))
		return -EINVAL;

	if (!pt->src_dma || !pt->dst_dma)
		return -EINVAL;

	if (pt->bit_mod != CCP_PASSTHRU_BITWISE_NOOP) {
		if (pt->mask_len != CCP_PASSTHRU_MASKSIZE)
			return -EINVAL;
		if (!pt->mask)
			return -EINVAL;
	}

2039
	BUILD_BUG_ON(CCP_PASSTHRU_SB_COUNT != 1);
2040 2041 2042

	memset(&op, 0, sizeof(op));
	op.cmd_q = cmd_q;
2043
	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
2044 2045 2046

	if (pt->bit_mod != CCP_PASSTHRU_BITWISE_NOOP) {
		/* Load the mask */
2047
		op.sb_key = cmd_q->sb_key;
2048 2049 2050 2051 2052

		mask.length = pt->mask_len;
		mask.dma.address = pt->mask;
		mask.dma.length = pt->mask_len;

2053
		ret = ccp_copy_to_sb(cmd_q, &mask, op.jobid, op.sb_key,
2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074
				     CCP_PASSTHRU_BYTESWAP_NOOP);
		if (ret) {
			cmd->engine_error = cmd_q->cmd_error;
			return ret;
		}
	}

	/* Send data to the CCP Passthru engine */
	op.eom = 1;
	op.soc = 1;

	op.src.type = CCP_MEMTYPE_SYSTEM;
	op.src.u.dma.address = pt->src_dma;
	op.src.u.dma.offset = 0;
	op.src.u.dma.length = pt->src_len;

	op.dst.type = CCP_MEMTYPE_SYSTEM;
	op.dst.u.dma.address = pt->dst_dma;
	op.dst.u.dma.offset = 0;
	op.dst.u.dma.length = pt->src_len;

2075
	ret = cmd_q->ccp->vdata->perform->passthru(&op);
2076 2077 2078 2079 2080 2081
	if (ret)
		cmd->engine_error = cmd_q->cmd_error;

	return ret;
}

2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104
static int ccp_run_ecc_mm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
{
	struct ccp_ecc_engine *ecc = &cmd->u.ecc;
	struct ccp_dm_workarea src, dst;
	struct ccp_op op;
	int ret;
	u8 *save;

	if (!ecc->u.mm.operand_1 ||
	    (ecc->u.mm.operand_1_len > CCP_ECC_MODULUS_BYTES))
		return -EINVAL;

	if (ecc->function != CCP_ECC_FUNCTION_MINV_384BIT)
		if (!ecc->u.mm.operand_2 ||
		    (ecc->u.mm.operand_2_len > CCP_ECC_MODULUS_BYTES))
			return -EINVAL;

	if (!ecc->u.mm.result ||
	    (ecc->u.mm.result_len < CCP_ECC_MODULUS_BYTES))
		return -EINVAL;

	memset(&op, 0, sizeof(op));
	op.cmd_q = cmd_q;
2105
	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122

	/* 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 */
2123
	ret = ccp_reverse_set_dm_area(&src, 0, ecc->mod, 0, ecc->mod_len);
2124 2125
	if (ret)
		goto e_src;
2126 2127 2128
	src.address += CCP_ECC_OPERAND_SIZE;

	/* Copy the first operand */
2129 2130
	ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.mm.operand_1, 0,
				      ecc->u.mm.operand_1_len);
2131 2132
	if (ret)
		goto e_src;
2133 2134 2135 2136
	src.address += CCP_ECC_OPERAND_SIZE;

	if (ecc->function != CCP_ECC_FUNCTION_MINV_384BIT) {
		/* Copy the second operand */
2137 2138
		ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.mm.operand_2, 0,
					      ecc->u.mm.operand_2_len);
2139 2140
		if (ret)
			goto e_src;
2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162
		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;

	op.soc = 1;
	op.src.u.dma.address = src.dma.address;
	op.src.u.dma.offset = 0;
	op.src.u.dma.length = src.length;
	op.dst.u.dma.address = dst.dma.address;
	op.dst.u.dma.offset = 0;
	op.dst.u.dma.length = dst.length;

	op.u.ecc.function = cmd->u.ecc.function;

2163
	ret = cmd_q->ccp->vdata->perform->ecc(&op);
2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176
	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 ECC result */
2177 2178
	ccp_reverse_get_dm_area(&dst, 0, ecc->u.mm.result, 0,
				CCP_ECC_MODULUS_BYTES);
2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227

e_dst:
	ccp_dm_free(&dst);

e_src:
	ccp_dm_free(&src);

	return ret;
}

static int ccp_run_ecc_pm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
{
	struct ccp_ecc_engine *ecc = &cmd->u.ecc;
	struct ccp_dm_workarea src, dst;
	struct ccp_op op;
	int ret;
	u8 *save;

	if (!ecc->u.pm.point_1.x ||
	    (ecc->u.pm.point_1.x_len > CCP_ECC_MODULUS_BYTES) ||
	    !ecc->u.pm.point_1.y ||
	    (ecc->u.pm.point_1.y_len > CCP_ECC_MODULUS_BYTES))
		return -EINVAL;

	if (ecc->function == CCP_ECC_FUNCTION_PADD_384BIT) {
		if (!ecc->u.pm.point_2.x ||
		    (ecc->u.pm.point_2.x_len > CCP_ECC_MODULUS_BYTES) ||
		    !ecc->u.pm.point_2.y ||
		    (ecc->u.pm.point_2.y_len > CCP_ECC_MODULUS_BYTES))
			return -EINVAL;
	} else {
		if (!ecc->u.pm.domain_a ||
		    (ecc->u.pm.domain_a_len > CCP_ECC_MODULUS_BYTES))
			return -EINVAL;

		if (ecc->function == CCP_ECC_FUNCTION_PMUL_384BIT)
			if (!ecc->u.pm.scalar ||
			    (ecc->u.pm.scalar_len > CCP_ECC_MODULUS_BYTES))
				return -EINVAL;
	}

	if (!ecc->u.pm.result.x ||
	    (ecc->u.pm.result.x_len < CCP_ECC_MODULUS_BYTES) ||
	    !ecc->u.pm.result.y ||
	    (ecc->u.pm.result.y_len < CCP_ECC_MODULUS_BYTES))
		return -EINVAL;

	memset(&op, 0, sizeof(op));
	op.cmd_q = cmd_q;
2228
	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245

	/* 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 */
2246
	ret = ccp_reverse_set_dm_area(&src, 0, ecc->mod, 0, ecc->mod_len);
2247 2248
	if (ret)
		goto e_src;
2249 2250 2251
	src.address += CCP_ECC_OPERAND_SIZE;

	/* Copy the first point X and Y coordinate */
2252 2253
	ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.pm.point_1.x, 0,
				      ecc->u.pm.point_1.x_len);
2254 2255
	if (ret)
		goto e_src;
2256
	src.address += CCP_ECC_OPERAND_SIZE;
2257 2258
	ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.pm.point_1.y, 0,
				      ecc->u.pm.point_1.y_len);
2259 2260
	if (ret)
		goto e_src;
2261 2262
	src.address += CCP_ECC_OPERAND_SIZE;

2263
	/* Set the first point Z coordinate to 1 */
2264
	*src.address = 0x01;
2265 2266 2267 2268
	src.address += CCP_ECC_OPERAND_SIZE;

	if (ecc->function == CCP_ECC_FUNCTION_PADD_384BIT) {
		/* Copy the second point X and Y coordinate */
2269 2270
		ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.pm.point_2.x, 0,
					      ecc->u.pm.point_2.x_len);
2271 2272
		if (ret)
			goto e_src;
2273
		src.address += CCP_ECC_OPERAND_SIZE;
2274 2275
		ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.pm.point_2.y, 0,
					      ecc->u.pm.point_2.y_len);
2276 2277
		if (ret)
			goto e_src;
2278 2279
		src.address += CCP_ECC_OPERAND_SIZE;

2280
		/* Set the second point Z coordinate to 1 */
2281
		*src.address = 0x01;
2282 2283 2284
		src.address += CCP_ECC_OPERAND_SIZE;
	} else {
		/* Copy the Domain "a" parameter */
2285 2286
		ret = ccp_reverse_set_dm_area(&src, 0, ecc->u.pm.domain_a, 0,
					      ecc->u.pm.domain_a_len);
2287 2288
		if (ret)
			goto e_src;
2289 2290 2291 2292
		src.address += CCP_ECC_OPERAND_SIZE;

		if (ecc->function == CCP_ECC_FUNCTION_PMUL_384BIT) {
			/* Copy the scalar value */
2293 2294 2295
			ret = ccp_reverse_set_dm_area(&src, 0,
						      ecc->u.pm.scalar, 0,
						      ecc->u.pm.scalar_len);
2296 2297
			if (ret)
				goto e_src;
2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320
			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;

	op.soc = 1;
	op.src.u.dma.address = src.dma.address;
	op.src.u.dma.offset = 0;
	op.src.u.dma.length = src.length;
	op.dst.u.dma.address = dst.dma.address;
	op.dst.u.dma.offset = 0;
	op.dst.u.dma.length = dst.length;

	op.u.ecc.function = cmd->u.ecc.function;

2321
	ret = cmd_q->ccp->vdata->perform->ecc(&op);
2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339
	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 */
2340
	ccp_reverse_get_dm_area(&dst, 0, ecc->u.pm.result.x, 0,
2341 2342
				CCP_ECC_MODULUS_BYTES);
	dst.address += CCP_ECC_OUTPUT_SIZE;
2343
	ccp_reverse_get_dm_area(&dst, 0, ecc->u.pm.result.y, 0,
2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391
				CCP_ECC_MODULUS_BYTES);
	dst.address += CCP_ECC_OUTPUT_SIZE;

	/* Restore the workarea address */
	dst.address = save;

e_dst:
	ccp_dm_free(&dst);

e_src:
	ccp_dm_free(&src);

	return ret;
}

static int ccp_run_ecc_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
{
	struct ccp_ecc_engine *ecc = &cmd->u.ecc;

	ecc->ecc_result = 0;

	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;

	cmd->engine_error = 0;
	cmd_q->cmd_error = 0;
	cmd_q->int_rcvd = 0;
2392
	cmd_q->free_slots = cmd_q->ccp->vdata->perform->get_free_slots(cmd_q);
2393 2394 2395 2396 2397 2398 2399 2400

	switch (cmd->engine) {
	case CCP_ENGINE_AES:
		ret = ccp_run_aes_cmd(cmd_q, cmd);
		break;
	case CCP_ENGINE_XTS_AES_128:
		ret = ccp_run_xts_aes_cmd(cmd_q, cmd);
		break;
2401 2402 2403
	case CCP_ENGINE_DES3:
		ret = ccp_run_des3_cmd(cmd_q, cmd);
		break;
2404 2405 2406 2407 2408 2409 2410
	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:
2411 2412 2413 2414
		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);
2415 2416 2417 2418 2419 2420 2421 2422 2423 2424
		break;
	case CCP_ENGINE_ECC:
		ret = ccp_run_ecc_cmd(cmd_q, cmd);
		break;
	default:
		ret = -EINVAL;
	}

	return ret;
}