crypto: caam/qi - add ablkcipher and authenc algorithms

Add support to submit ablkcipher and authenc algorithms
via the QI backend:
-ablkcipher:
cbc({aes,des,des3_ede})
ctr(aes), rfc3686(ctr(aes))
xts(aes)
-authenc:
authenc(hmac(md5),cbc({aes,des,des3_ede}))
authenc(hmac(sha*),cbc({aes,des,des3_ede}))

caam/qi being a new driver, let's wait some time to settle down without
interfering with existing caam/jr driver.
Accordingly, for now all caam/qi algorithms (caamalg_qi module) are
marked to be of lower priority than caam/jr ones (caamalg module).

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: Alex Porosanu <alexandru.porosanu@nxp.com>
Signed-off-by: Horia Geantă <horia.geanta@nxp.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This commit is contained in:
Horia Geantă 2017-03-17 12:06:02 +02:00 committed by Herbert Xu
parent 67c2315def
commit b189817cf7
7 changed files with 2601 additions and 16 deletions

View File

@ -87,6 +87,23 @@ config CRYPTO_DEV_FSL_CAAM_CRYPTO_API
To compile this as a module, choose M here: the module
will be called caamalg.
config CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI
tristate "Queue Interface as Crypto API backend"
depends on CRYPTO_DEV_FSL_CAAM_JR && FSL_DPAA && NET
default y
select CRYPTO_AUTHENC
select CRYPTO_BLKCIPHER
help
Selecting this will use CAAM Queue Interface (QI) for sending
& receiving crypto jobs to/from CAAM. This gives better performance
than job ring interface when the number of cores are more than the
number of job rings assigned to the kernel. The number of portals
assigned to the kernel should also be more than the number of
job rings.
To compile this as a module, choose M here: the module
will be called caamalg_qi.
config CRYPTO_DEV_FSL_CAAM_AHASH_API
tristate "Register hash algorithm implementations with Crypto API"
depends on CRYPTO_DEV_FSL_CAAM_JR
@ -136,4 +153,5 @@ config CRYPTO_DEV_FSL_CAAM_DEBUG
information in the CAAM driver.
config CRYPTO_DEV_FSL_CAAM_CRYPTO_API_DESC
def_tristate CRYPTO_DEV_FSL_CAAM_CRYPTO_API
def_tristate (CRYPTO_DEV_FSL_CAAM_CRYPTO_API || \
CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI)

View File

@ -8,6 +8,7 @@ endif
obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM) += caam.o
obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_JR) += caam_jr.o
obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API) += caamalg.o
obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI) += caamalg_qi.o
obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_DESC) += caamalg_desc.o
obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_AHASH_API) += caamhash.o
obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_RNG_API) += caamrng.o

View File

@ -266,8 +266,9 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
/* aead_encrypt shared descriptor */
desc = ctx->sh_desc_enc;
cnstr_shdsc_aead_encap(desc, &ctx->cdata, &ctx->adata, ctx->authsize,
is_rfc3686, nonce, ctx1_iv_off);
cnstr_shdsc_aead_encap(desc, &ctx->cdata, &ctx->adata, ivsize,
ctx->authsize, is_rfc3686, nonce, ctx1_iv_off,
false);
dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
desc_bytes(desc), DMA_TO_DEVICE);
@ -299,7 +300,7 @@ skip_enc:
desc = ctx->sh_desc_dec;
cnstr_shdsc_aead_decap(desc, &ctx->cdata, &ctx->adata, ivsize,
ctx->authsize, alg->caam.geniv, is_rfc3686,
nonce, ctx1_iv_off);
nonce, ctx1_iv_off, false);
dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
desc_bytes(desc), DMA_TO_DEVICE);
@ -333,7 +334,7 @@ skip_enc:
desc = ctx->sh_desc_enc;
cnstr_shdsc_aead_givencap(desc, &ctx->cdata, &ctx->adata, ivsize,
ctx->authsize, is_rfc3686, nonce,
ctx1_iv_off);
ctx1_iv_off, false);
dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
desc_bytes(desc), DMA_TO_DEVICE);

View File

@ -265,17 +265,19 @@ static void init_sh_desc_key_aead(u32 * const desc,
* split key is to be used, the size of the split key itself is
* specified. Valid algorithm values - one of OP_ALG_ALGSEL_{MD5, SHA1,
* SHA224, SHA256, SHA384, SHA512} ANDed with OP_ALG_AAI_HMAC_PRECOMP.
* @ivsize: initialization vector size
* @icvsize: integrity check value (ICV) size (truncated or full)
* @is_rfc3686: true when ctr(aes) is wrapped by rfc3686 template
* @nonce: pointer to rfc3686 nonce
* @ctx1_iv_off: IV offset in CONTEXT1 register
* @is_qi: true when called from caam/qi
*
* Note: Requires an MDHA split key.
*/
void cnstr_shdsc_aead_encap(u32 * const desc, struct alginfo *cdata,
struct alginfo *adata, unsigned int icvsize,
const bool is_rfc3686, u32 *nonce,
const u32 ctx1_iv_off)
struct alginfo *adata, unsigned int ivsize,
unsigned int icvsize, const bool is_rfc3686,
u32 *nonce, const u32 ctx1_iv_off, const bool is_qi)
{
/* Note: Context registers are saved. */
init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce);
@ -284,6 +286,25 @@ void cnstr_shdsc_aead_encap(u32 * const desc, struct alginfo *cdata,
append_operation(desc, adata->algtype | OP_ALG_AS_INITFINAL |
OP_ALG_ENCRYPT);
if (is_qi) {
u32 *wait_load_cmd;
/* REG3 = assoclen */
append_seq_load(desc, 4, LDST_CLASS_DECO |
LDST_SRCDST_WORD_DECO_MATH3 |
(4 << LDST_OFFSET_SHIFT));
wait_load_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
JUMP_COND_CALM | JUMP_COND_NCP |
JUMP_COND_NOP | JUMP_COND_NIP |
JUMP_COND_NIFP);
set_jump_tgt_here(desc, wait_load_cmd);
append_seq_load(desc, ivsize, LDST_CLASS_1_CCB |
LDST_SRCDST_BYTE_CONTEXT |
(ctx1_iv_off << LDST_OFFSET_SHIFT));
}
/* Read and write assoclen bytes */
append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
@ -338,6 +359,7 @@ EXPORT_SYMBOL(cnstr_shdsc_aead_encap);
* @is_rfc3686: true when ctr(aes) is wrapped by rfc3686 template
* @nonce: pointer to rfc3686 nonce
* @ctx1_iv_off: IV offset in CONTEXT1 register
* @is_qi: true when called from caam/qi
*
* Note: Requires an MDHA split key.
*/
@ -345,7 +367,7 @@ void cnstr_shdsc_aead_decap(u32 * const desc, struct alginfo *cdata,
struct alginfo *adata, unsigned int ivsize,
unsigned int icvsize, const bool geniv,
const bool is_rfc3686, u32 *nonce,
const u32 ctx1_iv_off)
const u32 ctx1_iv_off, const bool is_qi)
{
/* Note: Context registers are saved. */
init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce);
@ -354,6 +376,26 @@ void cnstr_shdsc_aead_decap(u32 * const desc, struct alginfo *cdata,
append_operation(desc, adata->algtype | OP_ALG_AS_INITFINAL |
OP_ALG_DECRYPT | OP_ALG_ICV_ON);
if (is_qi) {
u32 *wait_load_cmd;
/* REG3 = assoclen */
append_seq_load(desc, 4, LDST_CLASS_DECO |
LDST_SRCDST_WORD_DECO_MATH3 |
(4 << LDST_OFFSET_SHIFT));
wait_load_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
JUMP_COND_CALM | JUMP_COND_NCP |
JUMP_COND_NOP | JUMP_COND_NIP |
JUMP_COND_NIFP);
set_jump_tgt_here(desc, wait_load_cmd);
if (!geniv)
append_seq_load(desc, ivsize, LDST_CLASS_1_CCB |
LDST_SRCDST_BYTE_CONTEXT |
(ctx1_iv_off << LDST_OFFSET_SHIFT));
}
/* Read and write assoclen bytes */
append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
if (geniv)
@ -423,21 +465,44 @@ EXPORT_SYMBOL(cnstr_shdsc_aead_decap);
* @is_rfc3686: true when ctr(aes) is wrapped by rfc3686 template
* @nonce: pointer to rfc3686 nonce
* @ctx1_iv_off: IV offset in CONTEXT1 register
* @is_qi: true when called from caam/qi
*
* Note: Requires an MDHA split key.
*/
void cnstr_shdsc_aead_givencap(u32 * const desc, struct alginfo *cdata,
struct alginfo *adata, unsigned int ivsize,
unsigned int icvsize, const bool is_rfc3686,
u32 *nonce, const u32 ctx1_iv_off)
u32 *nonce, const u32 ctx1_iv_off,
const bool is_qi)
{
u32 geniv, moveiv;
/* Note: Context registers are saved. */
init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce);
if (is_rfc3686)
if (is_qi) {
u32 *wait_load_cmd;
/* REG3 = assoclen */
append_seq_load(desc, 4, LDST_CLASS_DECO |
LDST_SRCDST_WORD_DECO_MATH3 |
(4 << LDST_OFFSET_SHIFT));
wait_load_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
JUMP_COND_CALM | JUMP_COND_NCP |
JUMP_COND_NOP | JUMP_COND_NIP |
JUMP_COND_NIFP);
set_jump_tgt_here(desc, wait_load_cmd);
}
if (is_rfc3686) {
if (is_qi)
append_seq_load(desc, ivsize, LDST_CLASS_1_CCB |
LDST_SRCDST_BYTE_CONTEXT |
(ctx1_iv_off << LDST_OFFSET_SHIFT));
goto copy_iv;
}
/* Generate IV */
geniv = NFIFOENTRY_STYPE_PAD | NFIFOENTRY_DEST_DECO |

View File

@ -12,6 +12,9 @@
#define DESC_AEAD_ENC_LEN (DESC_AEAD_BASE + 11 * CAAM_CMD_SZ)
#define DESC_AEAD_DEC_LEN (DESC_AEAD_BASE + 15 * CAAM_CMD_SZ)
#define DESC_AEAD_GIVENC_LEN (DESC_AEAD_ENC_LEN + 7 * CAAM_CMD_SZ)
#define DESC_QI_AEAD_ENC_LEN (DESC_AEAD_ENC_LEN + 3 * CAAM_CMD_SZ)
#define DESC_QI_AEAD_DEC_LEN (DESC_AEAD_DEC_LEN + 3 * CAAM_CMD_SZ)
#define DESC_QI_AEAD_GIVENC_LEN (DESC_AEAD_GIVENC_LEN + 3 * CAAM_CMD_SZ)
/* Note: Nonce is counted in cdata.keylen */
#define DESC_AEAD_CTR_RFC3686_LEN (4 * CAAM_CMD_SZ)
@ -45,20 +48,22 @@ void cnstr_shdsc_aead_null_decap(u32 * const desc, struct alginfo *adata,
unsigned int icvsize);
void cnstr_shdsc_aead_encap(u32 * const desc, struct alginfo *cdata,
struct alginfo *adata, unsigned int icvsize,
const bool is_rfc3686, u32 *nonce,
const u32 ctx1_iv_off);
struct alginfo *adata, unsigned int ivsize,
unsigned int icvsize, const bool is_rfc3686,
u32 *nonce, const u32 ctx1_iv_off,
const bool is_qi);
void cnstr_shdsc_aead_decap(u32 * const desc, struct alginfo *cdata,
struct alginfo *adata, unsigned int ivsize,
unsigned int icvsize, const bool geniv,
const bool is_rfc3686, u32 *nonce,
const u32 ctx1_iv_off);
const u32 ctx1_iv_off, const bool is_qi);
void cnstr_shdsc_aead_givencap(u32 * const desc, struct alginfo *cdata,
struct alginfo *adata, unsigned int ivsize,
unsigned int icvsize, const bool is_rfc3686,
u32 *nonce, const u32 ctx1_iv_off);
u32 *nonce, const u32 ctx1_iv_off,
const bool is_qi);
void cnstr_shdsc_gcm_encap(u32 * const desc, struct alginfo *cdata,
unsigned int icvsize);

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,108 @@
/*
* Copyright 2013-2016 Freescale Semiconductor, Inc.
* Copyright 2016-2017 NXP
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of Freescale Semiconductor nor the
* names of its contributors may be used to endorse or promote products
* derived from this software without specific prior written permission.
*
*
* ALTERNATIVELY, this software may be distributed under the terms of the
* GNU General Public License ("GPL") as published by the Free Software
* Foundation, either version 2 of that License or (at your option) any
* later version.
*
* THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
* DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef __SG_SW_QM_H
#define __SG_SW_QM_H
#include <soc/fsl/qman.h>
#include "regs.h"
static inline void __dma_to_qm_sg(struct qm_sg_entry *qm_sg_ptr, dma_addr_t dma,
u16 offset)
{
qm_sg_entry_set64(qm_sg_ptr, dma);
qm_sg_ptr->__reserved2 = 0;
qm_sg_ptr->bpid = 0;
qm_sg_ptr->offset = cpu_to_be16(offset & QM_SG_OFF_MASK);
}
static inline void dma_to_qm_sg_one(struct qm_sg_entry *qm_sg_ptr,
dma_addr_t dma, u32 len, u16 offset)
{
__dma_to_qm_sg(qm_sg_ptr, dma, offset);
qm_sg_entry_set_len(qm_sg_ptr, len);
}
static inline void dma_to_qm_sg_one_last(struct qm_sg_entry *qm_sg_ptr,
dma_addr_t dma, u32 len, u16 offset)
{
__dma_to_qm_sg(qm_sg_ptr, dma, offset);
qm_sg_entry_set_f(qm_sg_ptr, len);
}
static inline void dma_to_qm_sg_one_ext(struct qm_sg_entry *qm_sg_ptr,
dma_addr_t dma, u32 len, u16 offset)
{
__dma_to_qm_sg(qm_sg_ptr, dma, offset);
qm_sg_ptr->cfg = cpu_to_be32(QM_SG_EXT | (len & QM_SG_LEN_MASK));
}
static inline void dma_to_qm_sg_one_last_ext(struct qm_sg_entry *qm_sg_ptr,
dma_addr_t dma, u32 len,
u16 offset)
{
__dma_to_qm_sg(qm_sg_ptr, dma, offset);
qm_sg_ptr->cfg = cpu_to_be32(QM_SG_EXT | QM_SG_FIN |
(len & QM_SG_LEN_MASK));
}
/*
* convert scatterlist to h/w link table format
* but does not have final bit; instead, returns last entry
*/
static inline struct qm_sg_entry *
sg_to_qm_sg(struct scatterlist *sg, int sg_count,
struct qm_sg_entry *qm_sg_ptr, u16 offset)
{
while (sg_count && sg) {
dma_to_qm_sg_one(qm_sg_ptr, sg_dma_address(sg),
sg_dma_len(sg), offset);
qm_sg_ptr++;
sg = sg_next(sg);
sg_count--;
}
return qm_sg_ptr - 1;
}
/*
* convert scatterlist to h/w link table format
* scatterlist must have been previously dma mapped
*/
static inline void sg_to_qm_sg_last(struct scatterlist *sg, int sg_count,
struct qm_sg_entry *qm_sg_ptr, u16 offset)
{
qm_sg_ptr = sg_to_qm_sg(sg, sg_count, qm_sg_ptr, offset);
qm_sg_entry_set_f(qm_sg_ptr, qm_sg_entry_get_len(qm_sg_ptr));
}
#endif /* __SG_SW_QM_H */