This accelerator is found inside hisilicon hip06 and hip07 SoCs. Each instance provides a number of queues which feed a different number of backend acceleration units. The queues are operating in an out of order mode in the interests of throughput. The silicon does not do tracking of dependencies between multiple 'messages' or update of the IVs as appropriate for training. Hence where relevant we need to do this in software. Signed-off-by: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx> --- drivers/crypto/Kconfig | 2 + drivers/crypto/Makefile | 1 + drivers/crypto/hisilicon/Kconfig | 14 + drivers/crypto/hisilicon/Makefile | 2 + drivers/crypto/hisilicon/sec/Makefile | 3 + drivers/crypto/hisilicon/sec/sec_algs.c | 1116 ++++++++++++++++++++++++++ drivers/crypto/hisilicon/sec/sec_drv.c | 1323 +++++++++++++++++++++++++++++++ drivers/crypto/hisilicon/sec/sec_drv.h | 428 ++++++++++ 8 files changed, 2889 insertions(+) diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index d1ea1a07cecb..d0b80d0d1f8b 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -750,4 +750,6 @@ config CRYPTO_DEV_CCREE cryptographic operations on the system REE. If unsure say Y. +source "drivers/crypto/hisilicon/Kconfig" + endif # CRYPTO_HW diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile index 7ae87b4f6c8d..ee43aed8cb69 100644 --- a/drivers/crypto/Makefile +++ b/drivers/crypto/Makefile @@ -45,3 +45,4 @@ obj-$(CONFIG_CRYPTO_DEV_VMX) += vmx/ obj-$(CONFIG_CRYPTO_DEV_BCM_SPU) += bcm/ obj-$(CONFIG_CRYPTO_DEV_SAFEXCEL) += inside-secure/ obj-$(CONFIG_CRYPTO_DEV_ARTPEC6) += axis/ +obj-y += hisilicon/ diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig new file mode 100644 index 000000000000..8ca9c503bcb0 --- /dev/null +++ b/drivers/crypto/hisilicon/Kconfig @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0 + +config CRYPTO_DEV_HISI_SEC + tristate "Support for Hisilicon SEC crypto block cipher accelerator" + select CRYPTO_BLKCIPHER + select CRYPTO_ALGAPI + select SG_SPLIT + depends on ARM64 || COMPILE_TEST + depends on HAS_IOMEM + help + Support for Hisilicon SEC Engine in Hip06 and Hip07 + + To compile this as a module, choose M here: the module + will be called hisi_sec. diff --git a/drivers/crypto/hisilicon/Makefile b/drivers/crypto/hisilicon/Makefile new file mode 100644 index 000000000000..463f46ace182 --- /dev/null +++ b/drivers/crypto/hisilicon/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += sec/ diff --git a/drivers/crypto/hisilicon/sec/Makefile b/drivers/crypto/hisilicon/sec/Makefile new file mode 100644 index 000000000000..a55b698e0c27 --- /dev/null +++ b/drivers/crypto/hisilicon/sec/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += hisi_sec.o +hisi_sec-y = sec_algs.o sec_drv.o diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c new file mode 100644 index 000000000000..a9401e98d2e2 --- /dev/null +++ b/drivers/crypto/hisilicon/sec/sec_algs.c @@ -0,0 +1,1116 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2016-2017 Hisilicon Limited. */ +#include <linux/crypto.h> +#include <linux/dma-mapping.h> +#include <linux/dmapool.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/slab.h> + +#include <crypto/aes.h> +#include <crypto/algapi.h> +#include <crypto/des.h> +#include <crypto/skcipher.h> +#include <crypto/internal/skcipher.h> + +#include "sec_drv.h" + +#define SEC_MAX_CIPHER_KEY 64 +#define SEC_REQ_LIMIT SZ_32M + +struct sec_c_alg_cfg { + unsigned c_alg : 3; + unsigned c_mode : 3; + unsigned key_len : 2; + unsigned c_width : 2; +}; + +static const struct sec_c_alg_cfg sec_c_alg_cfgs[] = { + [SEC_C_DES_ECB_64] = { + .c_alg = SEC_C_ALG_DES, + .c_mode = SEC_C_MODE_ECB, + .key_len = SEC_KEY_LEN_DES, + }, + [SEC_C_DES_CBC_64] = { + .c_alg = SEC_C_ALG_DES, + .c_mode = SEC_C_MODE_CBC, + .key_len = SEC_KEY_LEN_DES, + }, + [SEC_C_3DES_ECB_192_3KEY] = { + .c_alg = SEC_C_ALG_3DES, + .c_mode = SEC_C_MODE_ECB, + .key_len = SEC_KEY_LEN_3DES_3_KEY, + }, + [SEC_C_3DES_ECB_192_2KEY] = { + .c_alg = SEC_C_ALG_3DES, + .c_mode = SEC_C_MODE_ECB, + .key_len = SEC_KEY_LEN_3DES_2_KEY, + }, + [SEC_C_3DES_CBC_192_3KEY] = { + .c_alg = SEC_C_ALG_3DES, + .c_mode = SEC_C_MODE_CBC, + .key_len = SEC_KEY_LEN_3DES_3_KEY, + }, + [SEC_C_3DES_CBC_192_2KEY] = { + .c_alg = SEC_C_ALG_3DES, + .c_mode = SEC_C_MODE_CBC, + .key_len = SEC_KEY_LEN_3DES_2_KEY, + }, + [SEC_C_AES_ECB_128] = { + .c_alg = SEC_C_ALG_AES, + .c_mode = SEC_C_MODE_ECB, + .key_len = SEC_KEY_LEN_AES_128, + }, + [SEC_C_AES_ECB_192] = { + .c_alg = SEC_C_ALG_AES, + .c_mode = SEC_C_MODE_ECB, + .key_len = SEC_KEY_LEN_AES_192, + }, + [SEC_C_AES_ECB_256] = { + .c_alg = SEC_C_ALG_AES, + .c_mode = SEC_C_MODE_ECB, + .key_len = SEC_KEY_LEN_AES_256, + }, + [SEC_C_AES_CBC_128] = { + .c_alg = SEC_C_ALG_AES, + .c_mode = SEC_C_MODE_CBC, + .key_len = SEC_KEY_LEN_AES_128, + }, + [SEC_C_AES_CBC_192] = { + .c_alg = SEC_C_ALG_AES, + .c_mode = SEC_C_MODE_CBC, + .key_len = SEC_KEY_LEN_AES_192, + }, + [SEC_C_AES_CBC_256] = { + .c_alg = SEC_C_ALG_AES, + .c_mode = SEC_C_MODE_CBC, + .key_len = SEC_KEY_LEN_AES_256, + }, + [SEC_C_AES_CTR_128] = { + .c_alg = SEC_C_ALG_AES, + .c_mode = SEC_C_MODE_CTR, + .key_len = SEC_KEY_LEN_AES_128, + }, + [SEC_C_AES_CTR_192] = { + .c_alg = SEC_C_ALG_AES, + .c_mode = SEC_C_MODE_CTR, + .key_len = SEC_KEY_LEN_AES_192, + }, + [SEC_C_AES_CTR_256] = { + .c_alg = SEC_C_ALG_AES, + .c_mode = SEC_C_MODE_CTR, + .key_len = SEC_KEY_LEN_AES_256, + }, + [SEC_C_AES_XTS_128] = { + .c_alg = SEC_C_ALG_AES, + .c_mode = SEC_C_MODE_XTS, + .key_len = SEC_KEY_LEN_AES_128, + }, + [SEC_C_AES_XTS_256] = { + .c_alg = SEC_C_ALG_AES, + .c_mode = SEC_C_MODE_XTS, + .key_len = SEC_KEY_LEN_AES_256, + }, + [SEC_C_NULL] = { + }, +}; + +/* + * Mutex used to ensure safe operation of reference count of + * alg providers + */ +static DEFINE_MUTEX(algs_lock); +static unsigned int active_devs; + +static void sec_alg_skcipher_init_template(struct sec_alg_tfm_ctx *ctx, + struct sec_bd_info *req, + enum sec_cipher_alg alg) +{ + const struct sec_c_alg_cfg *cfg = &sec_c_alg_cfgs[alg]; + + memset(req, 0, sizeof(*req)); + req->w0 |= cfg->c_mode << SEC_BD_W0_C_MODE_S; + req->w1 |= cfg->c_alg << SEC_BD_W1_C_ALG_S; + req->w3 |= cfg->key_len << SEC_BD_W3_C_KEY_LEN_S; + req->w0 |= cfg->c_width << SEC_BD_W0_C_WIDTH_S; + + req->cipher_key_addr_lo = lower_32_bits(ctx->pkey); + req->cipher_key_addr_hi = upper_32_bits(ctx->pkey); +} + +static void sec_alg_skcipher_init_context(struct crypto_skcipher *atfm, + const u8 *key, + unsigned int keylen, + enum sec_cipher_alg alg) +{ + struct crypto_tfm *tfm = crypto_skcipher_tfm(atfm); + struct sec_alg_tfm_ctx *ctx = crypto_tfm_ctx(tfm); + + ctx->cipher_alg = alg; + memcpy(ctx->key, key, keylen); + sec_alg_skcipher_init_template(ctx, &ctx->req_template, + ctx->cipher_alg); +} + +static int sec_alloc_and_fill_hw_sgl(struct sec_hw_sgl **sec_sgl, + dma_addr_t *psec_sgl, + struct scatterlist *sgl, + int count, + struct sec_dev_info *info) +{ + struct sec_hw_sgl *sgl_current = NULL; + struct sec_hw_sgl *sgl_next; + dma_addr_t sgl_next_dma; + struct scatterlist *sg; + int ret, sge_index, i; + + if (!count) + return -EINVAL; + + for_each_sg(sgl, sg, count, i) { + sge_index = i % SEC_MAX_SGE_NUM; + if (sge_index == 0) { + sgl_next = dma_pool_zalloc(info->hw_sgl_pool, + GFP_KERNEL, &sgl_next_dma); + if (!sgl_next) { + ret = -ENOMEM; + goto err_free_hw_sgls; + } + + if (!sgl_current) { /* First one */ + *psec_sgl = sgl_next_dma; + *sec_sgl = sgl_next; + } else { /* Chained */ + sgl_current->entry_sum_in_sgl = SEC_MAX_SGE_NUM; + sgl_current->next_sgl = sgl_next_dma; + sgl_current->next = sgl_next; + } + sgl_current = sgl_next; + } + sgl_current->sge_entries[sge_index].buf = sg_dma_address(sg); + sgl_current->sge_entries[sge_index].len = sg_dma_len(sg); + sgl_current->data_bytes_in_sgl += sg_dma_len(sg); + } + sgl_current->entry_sum_in_sgl = count % SEC_MAX_SGE_NUM; + sgl_current->next_sgl = 0; + (*sec_sgl)->entry_sum_in_chain = count; + + return 0; + +err_free_hw_sgls: + sgl_current = *sec_sgl; + while (sgl_current) { + sgl_next = sgl_current->next; + dma_pool_free(info->hw_sgl_pool, sgl_current, + sgl_current->next_sgl); + sgl_current = sgl_next; + } + *psec_sgl = 0; + + return ret; +} + +static void sec_free_hw_sgl(struct sec_hw_sgl *hw_sgl, + dma_addr_t psec_sgl, struct sec_dev_info *info) +{ + struct sec_hw_sgl *sgl_current, *sgl_next; + + if (!hw_sgl) + return; + sgl_current = hw_sgl; + while (sgl_current->next) { + sgl_next = sgl_current->next; + dma_pool_free(info->hw_sgl_pool, sgl_current, + sgl_current->next_sgl); + sgl_current = sgl_next; + } + dma_pool_free(info->hw_sgl_pool, hw_sgl, psec_sgl); +} + +static int sec_alg_skcipher_setkey(struct crypto_skcipher *tfm, + const u8 *key, unsigned int keylen, + enum sec_cipher_alg alg) +{ + struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm); + struct device *dev = ctx->queue->dev_info->dev; + + mutex_lock(&ctx->lock); + if (ctx->key) { + /* rekeying */ + memset(ctx->key, 0, SEC_MAX_CIPHER_KEY); + } else { + /* new key */ + ctx->key = dma_zalloc_coherent(dev, SEC_MAX_CIPHER_KEY, + &ctx->pkey, GFP_KERNEL); + if (!ctx->key) { + mutex_unlock(&ctx->lock); + return -ENOMEM; + } + } + mutex_unlock(&ctx->lock); + sec_alg_skcipher_init_context(tfm, key, keylen, alg); + + return 0; +} + +static int sec_alg_skcipher_setkey_aes_ecb(struct crypto_skcipher *tfm, + const u8 *key, unsigned int keylen) +{ + enum sec_cipher_alg alg; + + switch (keylen) { + case AES_KEYSIZE_128: + alg = SEC_C_AES_ECB_128; + break; + case AES_KEYSIZE_192: + alg = SEC_C_AES_ECB_192; + break; + case AES_KEYSIZE_256: + alg = SEC_C_AES_ECB_256; + break; + default: + return -EINVAL; + } + + return sec_alg_skcipher_setkey(tfm, key, keylen, alg); +} + +static int sec_alg_skcipher_setkey_aes_cbc(struct crypto_skcipher *tfm, + const u8 *key, unsigned int keylen) +{ + enum sec_cipher_alg alg; + + switch (keylen) { + case AES_KEYSIZE_128: + alg = SEC_C_AES_CBC_128; + break; + case AES_KEYSIZE_192: + alg = SEC_C_AES_CBC_192; + break; + case AES_KEYSIZE_256: + alg = SEC_C_AES_CBC_256; + break; + default: + return -EINVAL; + } + + return sec_alg_skcipher_setkey(tfm, key, keylen, alg); +} + +static int sec_alg_skcipher_setkey_aes_ctr(struct crypto_skcipher *tfm, + const u8 *key, unsigned int keylen) +{ + enum sec_cipher_alg alg; + + switch (keylen) { + case AES_KEYSIZE_128: + alg = SEC_C_AES_CTR_128; + break; + case AES_KEYSIZE_192: + alg = SEC_C_AES_CTR_192; + break; + case AES_KEYSIZE_256: + alg = SEC_C_AES_CTR_256; + break; + default: + return -EINVAL; + } + + return sec_alg_skcipher_setkey(tfm, key, keylen, alg); +} + +static int sec_alg_skcipher_setkey_aes_xts(struct crypto_skcipher *tfm, + const u8 *key, unsigned int keylen) +{ + enum sec_cipher_alg alg; + + switch (keylen) { + case AES_KEYSIZE_128 * 2: + alg = SEC_C_AES_XTS_128; + break; + case AES_KEYSIZE_256 * 2: + alg = SEC_C_AES_XTS_256; + break; + default: + return -EINVAL; + } + + return sec_alg_skcipher_setkey(tfm, key, keylen, alg); +} + +static int sec_alg_skcipher_setkey_des_ecb(struct crypto_skcipher *tfm, + const u8 *key, unsigned int keylen) +{ + if (keylen != DES_KEY_SIZE) + return -EINVAL; + + return sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_DES_ECB_64); +} + +static int sec_alg_skcipher_setkey_des_cbc(struct crypto_skcipher *tfm, + const u8 *key, unsigned int keylen) +{ + if (keylen != DES_KEY_SIZE) + return -EINVAL; + + return sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_DES_CBC_64); +} + +static int sec_alg_skcipher_setkey_3des_ecb(struct crypto_skcipher *tfm, + const u8 *key, unsigned int keylen) +{ + if (keylen != DES_KEY_SIZE * 3) + return -EINVAL; + + return sec_alg_skcipher_setkey(tfm, key, keylen, + SEC_C_3DES_ECB_192_3KEY); +} + +static int sec_alg_skcipher_setkey_3des_cbc(struct crypto_skcipher *tfm, + const u8 *key, unsigned int keylen) +{ + if (keylen != DES3_EDE_KEY_SIZE) + return -EINVAL; + + return sec_alg_skcipher_setkey(tfm, key, keylen, + SEC_C_3DES_CBC_192_3KEY); +} + +static void sec_alg_free_el(struct sec_request_el *el, + struct sec_dev_info *info) +{ + sec_free_hw_sgl(el->out, el->dma_out, info); + sec_free_hw_sgl(el->in, el->dma_in, info); + kfree(el->sgl_in); + kfree(el->sgl_out); + kfree(el); +} + +/* queuelock must be held */ +int sec_send_request(struct sec_request *sec_req, struct sec_queue *queue) +{ + struct sec_request_el *el, *temp; + int ret = 0; + + mutex_lock(&sec_req->lock); + list_for_each_entry_safe(el, temp, &sec_req->elements, head) { + /* + * Add to hardware queue only under following circumstances + * 1) Software and hardware queue empty so no chain dependencies + * 2) No dependencies as new IV - (check software queue empty + * to maintain order) + * 3) No dependencies because the mode does no chaining. + * + * In other cases first insert onto the software queue which + * is then emptied as requests complete + */ + if (!queue->havesoftqueue || + (kfifo_is_empty(&queue->softqueue) && + sec_queue_empty(queue))) { + ret = sec_queue_send(queue, &el->req, sec_req); + if (ret == -EAGAIN) { + /* Wait unti we can send then try again */ + /* DEAD if here - should not happen */ + ret = -EBUSY; + goto err_unlock; + } + } else { + kfifo_put(&queue->softqueue, el); + } + } +err_unlock: + mutex_unlock(&sec_req->lock); + + return ret; +} + +static void sec_skcipher_alg_callback(struct sec_bd_info *sec_resp, + struct crypto_async_request *req_base) +{ + struct skcipher_request *skreq = container_of(req_base, + struct skcipher_request, + base); + struct sec_request *sec_req = skcipher_request_ctx(skreq); + struct sec_request *backlog_req; + struct sec_request_el *sec_req_el, *nextrequest; + struct sec_alg_tfm_ctx *ctx = sec_req->tfm_ctx; + struct crypto_skcipher *atfm = crypto_skcipher_reqtfm(skreq); + struct device *dev = ctx->queue->dev_info->dev; + int icv_or_skey_en, ret; + bool done; + + sec_req_el = list_first_entry(&sec_req->elements, struct sec_request_el, + head); + icv_or_skey_en = (sec_resp->w0 & SEC_BD_W0_ICV_OR_SKEY_EN_M) >> + SEC_BD_W0_ICV_OR_SKEY_EN_S; + if (sec_resp->w1 & SEC_BD_W1_BD_INVALID || icv_or_skey_en == 3) { + dev_err(dev, "Got an invalid answer %lu %d\n", + sec_resp->w1 & SEC_BD_W1_BD_INVALID, + icv_or_skey_en); + sec_req->err = -EINVAL; + /* + * We need to muddle on to avoid getting stuck with elements + * on the queue. Error will be reported so requester so + * it should be able to handle appropriately. + */ + } + + mutex_lock(&ctx->queue->queuelock); + /* Put the IV in place for chained cases */ + switch (ctx->cipher_alg) { + case SEC_C_AES_CBC_128: + case SEC_C_AES_CBC_192: + case SEC_C_AES_CBC_256: + if (sec_req_el->req.w0 & SEC_BD_W0_DE) + sg_pcopy_to_buffer(sec_req_el->sgl_out, + sg_nents(sec_req_el->sgl_out), + skreq->iv, + crypto_skcipher_ivsize(atfm), + sec_req_el->el_length - + crypto_skcipher_ivsize(atfm)); + else + sg_pcopy_to_buffer(sec_req_el->sgl_in, + sg_nents(sec_req_el->sgl_in), + skreq->iv, + crypto_skcipher_ivsize(atfm), + sec_req_el->el_length - + crypto_skcipher_ivsize(atfm)); + /* No need to sync to the device as coherent DMA */ + break; + case SEC_C_AES_CTR_128: + case SEC_C_AES_CTR_192: + case SEC_C_AES_CTR_256: + crypto_inc(skreq->iv, 16); + break; + default: + /* Do not update */ + break; + } + + if (ctx->queue->havesoftqueue && + !kfifo_is_empty(&ctx->queue->softqueue) && + sec_queue_empty(ctx->queue)) { + ret = kfifo_get(&ctx->queue->softqueue, &nextrequest); + if (ret <= 0) + dev_err(dev, + "Error getting next element from kfifo %d\n", + ret); + else + /* We know there is space so this cannot fail */ + sec_queue_send(ctx->queue, &nextrequest->req, + nextrequest->sec_req); + } else if (!list_empty(&ctx->backlog)) { + /* Need to verify there is room first */ + backlog_req = list_first_entry(&ctx->backlog, + typeof(*backlog_req), + backlog_head); + if (sec_queue_can_enqueue(ctx->queue, + backlog_req->num_elements) || + (ctx->queue->havesoftqueue && + kfifo_avail(&ctx->queue->softqueue) > + backlog_req->num_elements)) { + sec_send_request(backlog_req, ctx->queue); + backlog_req->req_base->complete(backlog_req->req_base, + -EINPROGRESS); + list_del(&backlog_req->backlog_head); + } + } + mutex_unlock(&ctx->queue->queuelock); + + mutex_lock(&sec_req->lock); + list_del(&sec_req_el->head); + mutex_unlock(&sec_req->lock); + sec_alg_free_el(sec_req_el, ctx->queue->dev_info); + + /* + * Request is done. + * The dance is needed as the lock is freed in the completion + */ + mutex_lock(&sec_req->lock); + done = list_empty(&sec_req->elements); + mutex_unlock(&sec_req->lock); + if (done) { + if (crypto_skcipher_ivsize(atfm)) { + dma_unmap_single(dev, sec_req->dma_iv, + crypto_skcipher_ivsize(atfm), + DMA_TO_DEVICE); + } + dma_unmap_sg(dev, skreq->src, sec_req->len_in, + DMA_BIDIRECTIONAL); + if (skreq->src != skreq->dst) + dma_unmap_sg(dev, skreq->dst, sec_req->len_out, + DMA_BIDIRECTIONAL); + skreq->base.complete(&skreq->base, sec_req->err); + } +} + +void sec_alg_callback(struct sec_bd_info *resp, void *shadow) +{ + struct sec_request *sec_req = shadow; + + sec_req->cb(resp, sec_req->req_base); +} + +static int sec_alg_alloc_and_calc_split_sizes(int length, size_t **split_sizes, + int *steps) +{ + size_t *sizes; + int i; + + /* Split into suitable sized blocks */ + *steps = roundup(length, SEC_REQ_LIMIT) / SEC_REQ_LIMIT; + sizes = kcalloc(*steps, sizeof(*sizes), GFP_KERNEL); + if (!sizes) + return -ENOMEM; + + for (i = 0; i < *steps - 1; i++) + sizes[i] = SEC_REQ_LIMIT; + sizes[*steps - 1] = length - SEC_REQ_LIMIT * (*steps - 1); + *split_sizes = sizes; + + return 0; +} + +static int sec_map_and_split_sg(struct scatterlist *sgl, size_t *split_sizes, + int steps, struct scatterlist ***splits, + int **splits_nents, + int sgl_len_in, + struct device *dev) +{ + int ret, count; + + count = dma_map_sg(dev, sgl, sgl_len_in, DMA_BIDIRECTIONAL); + if (!count) + return -EINVAL; + + *splits = kcalloc(steps, sizeof(struct scatterlist *), GFP_KERNEL); + if (!*splits) { + ret = -ENOMEM; + goto err_unmap_sg; + } + *splits_nents = kcalloc(steps, sizeof(int), GFP_KERNEL); + if (!*splits_nents) { + ret = -ENOMEM; + goto err_free_splits; + } + + /* output the scatter list before and after this */ + ret = sg_split(sgl, count, 0, steps, split_sizes, + *splits, *splits_nents, GFP_KERNEL); + if (ret) { + ret = -ENOMEM; + goto err_free_splits_nents; + } + + return 0; + +err_free_splits_nents: + kfree(*splits_nents); +err_free_splits: + kfree(*splits); +err_unmap_sg: + dma_unmap_sg(dev, sgl, sgl_len_in, DMA_BIDIRECTIONAL); + + return ret; +} + +/* + * Reverses the sec_map_and_split_sg call for messages not yet added to + * the queues. + */ +static void sec_unmap_sg_on_err(struct scatterlist *sgl, int steps, + struct scatterlist **splits, int *splits_nents, + int sgl_len_in, struct device *dev) +{ + int i; + + for (i = 0; i < steps; i++) + kfree(splits[i]); + kfree(splits_nents); + kfree(splits); + + dma_unmap_sg(dev, sgl, sgl_len_in, DMA_BIDIRECTIONAL); +} + +static struct sec_request_el +*sec_alg_alloc_and_fill_el(struct sec_bd_info *template, int encrypt, + int el_size, bool different_dest, + struct scatterlist *sgl_in, int n_ents_in, + struct scatterlist *sgl_out, int n_ents_out, + struct sec_dev_info *info) +{ + struct sec_request_el *el; + struct sec_bd_info *req; + int ret; + + el = kzalloc(sizeof(*el), GFP_KERNEL); + if (!el) + return ERR_PTR(-ENOMEM); + el->el_length = el_size; + req = &el->req; + memcpy(req, template, sizeof(*req)); + + req->w0 &= ~SEC_BD_W0_CIPHER_M; + if (encrypt) + req->w0 |= SEC_CIPHER_ENCRYPT << SEC_BD_W0_CIPHER_S; + else + req->w0 |= SEC_CIPHER_DECRYPT << SEC_BD_W0_CIPHER_S; + + req->w0 &= ~SEC_BD_W0_C_GRAN_SIZE_19_16_M; + req->w0 |= ((el_size >> 16) << SEC_BD_W0_C_GRAN_SIZE_19_16_S) & + SEC_BD_W0_C_GRAN_SIZE_19_16_M; + + req->w0 &= ~SEC_BD_W0_C_GRAN_SIZE_21_20_M; + req->w0 |= ((el_size >> 20) << SEC_BD_W0_C_GRAN_SIZE_21_20_S) & + SEC_BD_W0_C_GRAN_SIZE_21_20_M; + + /* Writing whole u32 so no need to take care of masking */ + req->w2 = ((1 << SEC_BD_W2_GRAN_NUM_S) & SEC_BD_W2_GRAN_NUM_M) | + ((el_size << SEC_BD_W2_C_GRAN_SIZE_15_0_S) & + SEC_BD_W2_C_GRAN_SIZE_15_0_M); + + req->w3 &= ~SEC_BD_W3_CIPHER_LEN_OFFSET_M; + req->w1 |= SEC_BD_W1_ADDR_TYPE; + + el->sgl_in = sgl_in; + + ret = sec_alloc_and_fill_hw_sgl(&el->in, &el->dma_in, el->sgl_in, + n_ents_in, info); + if (ret) + goto err_free_el; + + req->data_addr_lo = lower_32_bits(el->dma_in); + req->data_addr_hi = upper_32_bits(el->dma_in); + + if (different_dest) { + el->sgl_out = sgl_out; + ret = sec_alloc_and_fill_hw_sgl(&el->out, &el->dma_out, + el->sgl_out, + n_ents_out, info); + if (ret) + goto err_free_hw_sgl_in; + + req->w0 |= SEC_BD_W0_DE; + req->cipher_destin_addr_lo = lower_32_bits(el->dma_out); + req->cipher_destin_addr_hi = upper_32_bits(el->dma_out); + + } else { + req->w0 &= ~SEC_BD_W0_DE; + req->cipher_destin_addr_lo = lower_32_bits(el->dma_in); + req->cipher_destin_addr_hi = upper_32_bits(el->dma_in); + } + + return el; + +err_free_hw_sgl_in: + sec_free_hw_sgl(el->in, el->dma_in, info); +err_free_el: + kfree(el); + + return ERR_PTR(ret); +} + +static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, + bool encrypt) +{ + struct crypto_skcipher *atfm = crypto_skcipher_reqtfm(skreq); + struct crypto_tfm *tfm = crypto_skcipher_tfm(atfm); + struct sec_alg_tfm_ctx *ctx = crypto_tfm_ctx(tfm); + struct sec_queue *queue = ctx->queue; + struct sec_request *sec_req = skcipher_request_ctx(skreq); + struct sec_dev_info *info = queue->dev_info; + int i, ret, steps; + size_t *split_sizes; + struct scatterlist **splits_in; + struct scatterlist **splits_out = NULL; + int *splits_in_nents; + int *splits_out_nents = NULL; + struct sec_request_el *el, *temp; + + mutex_init(&sec_req->lock); + sec_req->req_base = &skreq->base; + sec_req->err = 0; + /* SGL mapping out here to allow us to break it up as necessary */ + sec_req->len_in = sg_nents(skreq->src); + + ret = sec_alg_alloc_and_calc_split_sizes(skreq->cryptlen, &split_sizes, + &steps); + if (ret) + return ret; + sec_req->num_elements = steps; + ret = sec_map_and_split_sg(skreq->src, split_sizes, steps, &splits_in, + &splits_in_nents, sec_req->len_in, + info->dev); + if (ret) + goto err_free_split_sizes; + + if (skreq->src != skreq->dst) { + sec_req->len_out = sg_nents(skreq->dst); + ret = sec_map_and_split_sg(skreq->dst, split_sizes, steps, + &splits_out, &splits_out_nents, + sec_req->len_out, info->dev); + if (ret) + goto err_unmap_in_sg; + } + /* Shared info stored in seq_req - applies to all BDs */ + sec_req->tfm_ctx = ctx; + sec_req->cb = sec_skcipher_alg_callback; + INIT_LIST_HEAD(&sec_req->elements); + + /* + * Future optimization. + * In the chaining case we can't use a dma pool bounce buffer + * but in the case where we know there is no chaining we can + */ + if (crypto_skcipher_ivsize(atfm)) { + sec_req->dma_iv = dma_map_single(info->dev, skreq->iv, + crypto_skcipher_ivsize(atfm), + DMA_TO_DEVICE); + if (dma_mapping_error(info->dev, sec_req->dma_iv)) { + ret = -ENOMEM; + goto err_unmap_out_sg; + } + } + + /* Set them all up then queue - cleaner error handling. */ + for (i = 0; i < steps; i++) { + el = sec_alg_alloc_and_fill_el(&ctx->req_template, + encrypt ? 1 : 0, + split_sizes[i], + skreq->src != skreq->dst, + splits_in[i], splits_in_nents[i], + splits_out[i], + splits_out_nents[i], info); + if (IS_ERR(el)) { + ret = PTR_ERR(el); + goto err_free_elements; + } + el->req.cipher_iv_addr_lo = lower_32_bits(sec_req->dma_iv); + el->req.cipher_iv_addr_hi = upper_32_bits(sec_req->dma_iv); + el->sec_req = sec_req; + list_add_tail(&el->head, &sec_req->elements); + } + + /* + * Only attempt to queue if the whole lot can fit in the queue - + * we can't successfully cleanup after a partial queing so this + * must succeed or fail atomically. + * + * Big hammer test of both software and hardware queues - could be + * more refined but this is unlikely to happen so no need. + */ + + /* Cleanup - all elements in pointer arrays have been coppied */ + kfree(splits_in_nents); + kfree(splits_in); + kfree(splits_out_nents); + kfree(splits_out); + kfree(split_sizes); + + /* Grab a big lock for a long time to avoid concurrency issues */ + mutex_lock(&queue->queuelock); + + /* + * Can go on to queue if we have space in either: + * 1) The hardware queue and no software queue + * 2) The software queue + * AND there is nothing in the backlog. If there is backlog we + * have to only queue to the backlog queue and return busy. + */ + if ((!sec_queue_can_enqueue(queue, steps) && + (!queue->havesoftqueue || + kfifo_avail(&queue->softqueue) > steps)) || + !list_empty(&ctx->backlog)) { + if ((skreq->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) { + list_add_tail(&sec_req->backlog_head, &ctx->backlog); + mutex_unlock(&queue->queuelock); + return -EBUSY; + } + + ret = -EBUSY; + mutex_unlock(&queue->queuelock); + goto err_free_elements; + } + ret = sec_send_request(sec_req, queue); + mutex_unlock(&queue->queuelock); + if (ret) + goto err_free_elements; + + return -EINPROGRESS; + +err_free_elements: + list_for_each_entry_safe(el, temp, &sec_req->elements, head) { + list_del(&el->head); + sec_alg_free_el(el, info); + } + if (crypto_skcipher_ivsize(atfm)) + dma_unmap_single(info->dev, sec_req->dma_iv, + crypto_skcipher_ivsize(atfm), + DMA_BIDIRECTIONAL); +err_unmap_out_sg: + if (skreq->src != skreq->dst) + sec_unmap_sg_on_err(skreq->dst, steps, splits_out, + splits_out_nents, sec_req->len_out, + info->dev); +err_unmap_in_sg: + sec_unmap_sg_on_err(skreq->src, steps, splits_in, splits_in_nents, + sec_req->len_in, info->dev); +err_free_split_sizes: + kfree(split_sizes); + + return ret; +} + +static int sec_alg_skcipher_encrypt(struct skcipher_request *req) +{ + return sec_alg_skcipher_crypto(req, true); +} + +static int sec_alg_skcipher_decrypt(struct skcipher_request *req) +{ + return sec_alg_skcipher_crypto(req, false); +} + +static int sec_alg_skcipher_init(struct crypto_skcipher *tfm) +{ + struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm); + + mutex_init(&ctx->lock); + INIT_LIST_HEAD(&ctx->backlog); + crypto_skcipher_set_reqsize(tfm, sizeof(struct sec_request)); + + ctx->queue = sec_queue_alloc_start_safe(); + if (IS_ERR(ctx->queue)) + return PTR_ERR(ctx->queue); + + mutex_init(&ctx->queue->queuelock); + ctx->queue->havesoftqueue = false; + + return 0; +} + +static void sec_alg_skcipher_exit(struct crypto_skcipher *tfm) +{ + struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm); + struct device *dev = ctx->queue->dev_info->dev; + + if (ctx->key) { + memzero_explicit(ctx->key, SEC_MAX_CIPHER_KEY); + dma_free_coherent(dev, SEC_MAX_CIPHER_KEY, ctx->key, + ctx->pkey); + } + sec_queue_stop_release(ctx->queue); +} + +static int sec_alg_skcipher_init_with_queue(struct crypto_skcipher *tfm) +{ + struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm); + int ret; + + ret = sec_alg_skcipher_init(tfm); + if (ret) + return ret; + + INIT_KFIFO(ctx->queue->softqueue); + ret = kfifo_alloc(&ctx->queue->softqueue, 512, GFP_KERNEL); + if (ret) { + sec_alg_skcipher_exit(tfm); + return ret; + } + ctx->queue->havesoftqueue = true; + + return 0; +} + +static void sec_alg_skcipher_exit_with_queue(struct crypto_skcipher *tfm) +{ + struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm); + + kfifo_free(&ctx->queue->softqueue); + sec_alg_skcipher_exit(tfm); +} + +static struct skcipher_alg sec_algs[] = { + { + .base = { + .cra_name = "ecb(aes)", + .cra_driver_name = "hisi_sec_aes_ecb", + .cra_priority = 4001, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sec_alg_tfm_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + }, + .init = sec_alg_skcipher_init, + .exit = sec_alg_skcipher_exit, + .setkey = sec_alg_skcipher_setkey_aes_ecb, + .decrypt = sec_alg_skcipher_decrypt, + .encrypt = sec_alg_skcipher_encrypt, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = 0, + }, { + .base = { + .cra_name = "cbc(aes)", + .cra_driver_name = "hisi_sec_aes_cbc", + .cra_priority = 4001, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sec_alg_tfm_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + }, + .init = sec_alg_skcipher_init_with_queue, + .exit = sec_alg_skcipher_exit_with_queue, + .setkey = sec_alg_skcipher_setkey_aes_cbc, + .decrypt = sec_alg_skcipher_decrypt, + .encrypt = sec_alg_skcipher_encrypt, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + }, { + .base = { + .cra_name = "ctr(aes)", + .cra_driver_name = "hisi_sec_aes_ctr", + .cra_priority = 4001, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sec_alg_tfm_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + }, + .init = sec_alg_skcipher_init_with_queue, + .exit = sec_alg_skcipher_exit_with_queue, + .setkey = sec_alg_skcipher_setkey_aes_ctr, + .decrypt = sec_alg_skcipher_decrypt, + .encrypt = sec_alg_skcipher_encrypt, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + }, { + .base = { + .cra_name = "xts(aes)", + .cra_driver_name = "hisi_sec_aes_xts", + .cra_priority = 4001, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sec_alg_tfm_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + }, + .init = sec_alg_skcipher_init, + .exit = sec_alg_skcipher_exit, + .setkey = sec_alg_skcipher_setkey_aes_xts, + .decrypt = sec_alg_skcipher_decrypt, + .encrypt = sec_alg_skcipher_encrypt, + .min_keysize = 2 * AES_MIN_KEY_SIZE, + .max_keysize = 2 * AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + }, { + /* Unable to find any test vectors so untested */ + .base = { + .cra_name = "ecb(des)", + .cra_driver_name = "hisi_sec_des_ecb", + .cra_priority = 4001, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = DES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sec_alg_tfm_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + }, + .init = sec_alg_skcipher_init, + .exit = sec_alg_skcipher_exit, + .setkey = sec_alg_skcipher_setkey_des_ecb, + .decrypt = sec_alg_skcipher_decrypt, + .encrypt = sec_alg_skcipher_encrypt, + .min_keysize = DES_KEY_SIZE, + .max_keysize = DES_KEY_SIZE, + .ivsize = 0, + }, { + .base = { + .cra_name = "cbc(des)", + .cra_driver_name = "hisi_sec_des_cbc", + .cra_priority = 4001, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = DES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sec_alg_tfm_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + }, + .init = sec_alg_skcipher_init_with_queue, + .exit = sec_alg_skcipher_exit_with_queue, + .setkey = sec_alg_skcipher_setkey_des_cbc, + .decrypt = sec_alg_skcipher_decrypt, + .encrypt = sec_alg_skcipher_encrypt, + .min_keysize = DES_KEY_SIZE, + .max_keysize = DES_KEY_SIZE, + .ivsize = DES_BLOCK_SIZE, + }, { + .base = { + .cra_name = "cbc(des3_ede)", + .cra_driver_name = "hisi_sec_3des_cbc", + .cra_priority = 4001, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = DES3_EDE_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sec_alg_tfm_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + }, + .init = sec_alg_skcipher_init_with_queue, + .exit = sec_alg_skcipher_exit_with_queue, + .setkey = sec_alg_skcipher_setkey_3des_cbc, + .decrypt = sec_alg_skcipher_decrypt, + .encrypt = sec_alg_skcipher_encrypt, + .min_keysize = DES3_EDE_KEY_SIZE, + .max_keysize = DES3_EDE_KEY_SIZE, + .ivsize = DES3_EDE_BLOCK_SIZE, + }, { + .base = { + .cra_name = "ecb(des3_ede)", + .cra_driver_name = "hisi_sec_3des_ecb", + .cra_priority = 4001, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = DES3_EDE_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sec_alg_tfm_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + }, + .init = sec_alg_skcipher_init, + .exit = sec_alg_skcipher_exit, + .setkey = sec_alg_skcipher_setkey_3des_ecb, + .decrypt = sec_alg_skcipher_decrypt, + .encrypt = sec_alg_skcipher_encrypt, + .min_keysize = DES3_EDE_KEY_SIZE, + .max_keysize = DES3_EDE_KEY_SIZE, + .ivsize = 0, + } +}; + +int sec_algs_register(void) +{ + int ret = 0; + + mutex_lock(&algs_lock); + if (++active_devs != 1) + goto unlock; + + ret = crypto_register_skciphers(sec_algs, ARRAY_SIZE(sec_algs)); + if (ret) + --active_devs; +unlock: + mutex_unlock(&algs_lock); + + return ret; +} + +void sec_algs_unregister(void) +{ + mutex_lock(&algs_lock); + if (--active_devs != 0) + goto unlock; + crypto_unregister_skciphers(sec_algs, ARRAY_SIZE(sec_algs)); + +unlock: + mutex_unlock(&algs_lock); +} diff --git a/drivers/crypto/hisilicon/sec/sec_drv.c b/drivers/crypto/hisilicon/sec/sec_drv.c new file mode 100644 index 000000000000..3bd46eb9a2ca --- /dev/null +++ b/drivers/crypto/hisilicon/sec/sec_drv.c @@ -0,0 +1,1323 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Driver for the Hisilicon SEC units found on Hip06 Hip07 + * + * Copyright (c) 2016-2017 Hisilicon Limited. + */ +#include <linux/acpi.h> +#include <linux/atomic.h> +#include <linux/delay.h> +#include <linux/dma-direction.h> +#include <linux/dma-mapping.h> +#include <linux/dmapool.h> +#include <linux/io.h> +#include <linux/iommu.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqreturn.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "sec_drv.h" + +#define SEC_QUEUE_AR_FROCE_ALLOC 0 +#define SEC_QUEUE_AR_FROCE_NOALLOC 1 +#define SEC_QUEUE_AR_FROCE_DIS 2 + +#define SEC_QUEUE_AW_FROCE_ALLOC 0 +#define SEC_QUEUE_AW_FROCE_NOALLOC 1 +#define SEC_QUEUE_AW_FROCE_DIS 2 + +/* SEC_ALGSUB registers */ +#define SEC_ALGSUB_CLK_EN_REG 0x03b8 +#define SEC_ALGSUB_CLK_DIS_REG 0x03bc +#define SEC_ALGSUB_CLK_ST_REG 0x535c +#define SEC_ALGSUB_RST_REQ_REG 0x0aa8 +#define SEC_ALGSUB_RST_DREQ_REG 0x0aac +#define SEC_ALGSUB_RST_ST_REG 0x5a54 +#define SEC_ALGSUB_RST_ST_IS_RST BIT(0) + +#define SEC_ALGSUB_BUILD_RST_REQ_REG 0x0ab8 +#define SEC_ALGSUB_BUILD_RST_DREQ_REG 0x0abc +#define SEC_ALGSUB_BUILD_RST_ST_REG 0x5a5c +#define SEC_ALGSUB_BUILD_RST_ST_IS_RST BIT(0) + +#define SEC_SAA_BASE 0x00001000UL + +/* SEC_SAA registers */ +#define SEC_SAA_CTRL_REG(x) ((x) * SEC_SAA_ADDR_SIZE) +#define SEC_SAA_CTRL_GET_QM_EN BIT(0) + +#define SEC_ST_INTMSK1_REG 0x0200 +#define SEC_ST_RINT1_REG 0x0400 +#define SEC_ST_INTSTS1_REG 0x0600 +#define SEC_BD_MNG_STAT_REG 0x0800 +#define SEC_PARSING_STAT_REG 0x0804 +#define SEC_LOAD_TIME_OUT_CNT_REG 0x0808 +#define SEC_CORE_WORK_TIME_OUT_CNT_REG 0x080c +#define SEC_BACK_TIME_OUT_CNT_REG 0x0810 +#define SEC_BD1_PARSING_RD_TIME_OUT_CNT_REG 0x0814 +#define SEC_BD1_PARSING_WR_TIME_OUT_CNT_REG 0x0818 +#define SEC_BD2_PARSING_RD_TIME_OUT_CNT_REG 0x081c +#define SEC_BD2_PARSING_WR_TIME_OUT_CNT_REG 0x0820 +#define SEC_SAA_ACC_REG 0x083c +#define SEC_BD_NUM_CNT_IN_SEC_REG 0x0858 +#define SEC_LOAD_WORK_TIME_CNT_REG 0x0860 +#define SEC_CORE_WORK_WORK_TIME_CNT_REG 0x0864 +#define SEC_BACK_WORK_TIME_CNT_REG 0x0868 +#define SEC_SAA_IDLE_TIME_CNT_REG 0x086c +#define SEC_SAA_CLK_CNT_REG 0x0870 + +/* SEC_COMMON registers */ +#define SEC_CLK_EN_REG 0x0000 +#define SEC_CTRL_REG 0x0004 + +#define SEC_COMMON_CNT_CLR_CE_REG 0x0008 +#define SEC_COMMON_CNT_CLR_CE_CLEAR BIT(0) +#define SEC_COMMON_CNT_CLR_CE_SNAP_EN BIT(1) + +#define SEC_SECURE_CTRL_REG 0x000c +#define SEC_AXI_CACHE_CFG_REG 0x0010 +#define SEC_AXI_QOS_CFG_REG 0x0014 +#define SEC_IPV4_MASK_TABLE_REG 0x0020 +#define SEC_IPV6_MASK_TABLE_X_REG(x) (0x0024 + (x) * 4) +#define SEC_FSM_MAX_CNT_REG 0x0064 + +#define SEC_CTRL2_REG 0x0068 +#define SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_M GENMASK(3, 0) +#define SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_S 0 +#define SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_M GENMASK(6, 4) +#define SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_S 4 +#define SEC_CTRL2_CLK_GATE_EN BIT(7) +#define SEC_CTRL2_ENDIAN_BD BIT(8) +#define SEC_CTRL2_ENDIAN_BD_TYPE BIT(9) + +#define SEC_CNT_PRECISION_CFG_REG 0x006c +#define SEC_DEBUG_BD_CFG_REG 0x0070 +#define SEC_DEBUG_BD_CFG_WB_NORMAL BIT(0) +#define SEC_DEBUG_BD_CFG_WB_EN BIT(1) + +#define SEC_Q_SIGHT_SEL 0x0074 +#define SEC_Q_SIGHT_HIS_CLR 0x0078 +#define SEC_Q_VMID_CFG_REG(q) (0x0100 + (q) * 4) +#define SEC_Q_WEIGHT_CFG_REG(q) (0x200 + (q) * 4) +#define SEC_STAT_CLR_REG 0x0a00 +#define SEC_SAA_IDLE_CNT_CLR_REG 0x0a04 +#define SEC_QM_CPL_Q_IDBUF_DFX_CFG_REG 0x0b00 +#define SEC_QM_CPL_Q_IDBUF_DFX_RESULT_REG 0x0b04 +#define SEC_QM_BD_DFX_CFG_REG 0x0b08 +#define SEC_QM_BD_DFX_RESULT_REG 0x0b0c +#define SEC_QM_BDID_DFX_RESULT_REG 0x0b10 +#define SEC_QM_BD_DFIFO_STATUS_REG 0x0b14 +#define SEC_QM_BD_DFX_CFG2_REG 0x0b1c +#define SEC_QM_BD_DFX_RESULT2_REG 0x0b20 +#define SEC_QM_BD_IDFIFO_STATUS_REG 0x0b18 +#define SEC_QM_BD_DFIFO_STATUS2_REG 0x0b28 +#define SEC_QM_BD_IDFIFO_STATUS2_REG 0x0b2c + +#define SEC_HASH_IPV4_MASK 0xfff00000 +#define SEC_MAX_SAA_NUM 0xa +#define SEC_SAA_ADDR_SIZE 0x1000 + +#define SEC_Q_INIT_REG 0x0 +#define SEC_Q_INIT_WO_STAT_CLEAR 0x2 +#define SEC_Q_INIT_AND_STAT_CLEAR 0x3 + +#define SEC_Q_CFG_REG 0x8 +#define SEC_Q_CFG_REORDER BIT(0) + +#define SEC_Q_PROC_NUM_CFG_REG 0x10 +#define SEC_QUEUE_ENB_REG 0x18 + +#define SEC_Q_DEPTH_CFG_REG 0x50 +#define SEC_Q_DEPTH_CFG_DEPTH_M GENMASK(11, 0) +#define SEC_Q_DEPTH_CFG_DEPTH_S 0 + +#define SEC_Q_BASE_HADDR_REG 0x54 +#define SEC_Q_BASE_LADDR_REG 0x58 +#define SEC_Q_WR_PTR_REG 0x5c +#define SEC_Q_OUTORDER_BASE_HADDR_REG 0x60 +#define SEC_Q_OUTORDER_BASE_LADDR_REG 0x64 +#define SEC_Q_OUTORDER_RD_PTR_REG 0x68 +#define SEC_Q_OT_TH_REG 0x6c + +#define SEC_Q_ARUSER_CFG_REG 0x70 +#define SEC_Q_ARUSER_CFG_FA BIT(0) +#define SEC_Q_ARUSER_CFG_FNA BIT(1) +#define SEC_Q_ARUSER_CFG_RINVLD BIT(2) +#define SEC_Q_ARUSER_CFG_PKG BIT(3) + +#define SEC_Q_AWUSER_CFG_REG 0x74 +#define SEC_Q_AWUSER_CFG_FA BIT(0) +#define SEC_Q_AWUSER_CFG_FNA BIT(1) +#define SEC_Q_AWUSER_CFG_PKG BIT(2) + +#define SEC_Q_ERR_BASE_HADDR_REG 0x7c +#define SEC_Q_ERR_BASE_LADDR_REG 0x80 +#define SEC_Q_CFG_VF_NUM_REG 0x84 +#define SEC_Q_SOFT_PROC_PTR_REG 0x88 +#define SEC_Q_FAIL_INT_MSK_REG 0x300 +#define SEC_Q_FLOW_INT_MKS_REG 0x304 +#define SEC_Q_FAIL_RINT_REG 0x400 +#define SEC_Q_FLOW_RINT_REG 0x404 +#define SEC_Q_FAIL_INT_STATUS_REG 0x500 +#define SEC_Q_FLOW_INT_STATUS_REG 0x504 +#define SEC_Q_STATUS_REG 0x600 +#define SEC_Q_RD_PTR_REG 0x604 +#define SEC_Q_PRO_PTR_REG 0x608 +#define SEC_Q_OUTORDER_WR_PTR_REG 0x60c +#define SEC_Q_OT_CNT_STATUS_REG 0x610 +#define SEC_Q_INORDER_BD_NUM_ST_REG 0x650 +#define SEC_Q_INORDER_GET_FLAG_ST_REG 0x654 +#define SEC_Q_INORDER_ADD_FLAG_ST_REG 0x658 +#define SEC_Q_INORDER_TASK_INT_NUM_LEFT_ST_REG 0x65c +#define SEC_Q_RD_DONE_PTR_REG 0x660 +#define SEC_Q_CPL_Q_BD_NUM_ST_REG 0x700 +#define SEC_Q_CPL_Q_PTR_ST_REG 0x704 +#define SEC_Q_CPL_Q_H_ADDR_ST_REG 0x708 +#define SEC_Q_CPL_Q_L_ADDR_ST_REG 0x70c +#define SEC_Q_CPL_TASK_INT_NUM_LEFT_ST_REG 0x710 +#define SEC_Q_WRR_ID_CHECK_REG 0x714 +#define SEC_Q_CPLQ_FULL_CHECK_REG 0x718 +#define SEC_Q_SUCCESS_BD_CNT_REG 0x800 +#define SEC_Q_FAIL_BD_CNT_REG 0x804 +#define SEC_Q_GET_BD_CNT_REG 0x808 +#define SEC_Q_IVLD_CNT_REG 0x80c +#define SEC_Q_BD_PROC_GET_CNT_REG 0x810 +#define SEC_Q_BD_PROC_DONE_CNT_REG 0x814 +#define SEC_Q_LAT_CLR_REG 0x850 +#define SEC_Q_PKT_LAT_MAX_REG 0x854 +#define SEC_Q_PKT_LAT_AVG_REG 0x858 +#define SEC_Q_PKT_LAT_MIN_REG 0x85c +#define SEC_Q_ID_CLR_CFG_REG 0x900 +#define SEC_Q_1ST_BD_ERR_ID_REG 0x904 +#define SEC_Q_1ST_AUTH_FAIL_ID_REG 0x908 +#define SEC_Q_1ST_RD_ERR_ID_REG 0x90c +#define SEC_Q_1ST_ECC2_ERR_ID_REG 0x910 +#define SEC_Q_1ST_IVLD_ID_REG 0x914 +#define SEC_Q_1ST_BD_WR_ERR_ID_REG 0x918 +#define SEC_Q_1ST_ERR_BD_WR_ERR_ID_REG 0x91c +#define SEC_Q_1ST_BD_MAC_WR_ERR_ID_REG 0x920 + +struct sec_debug_bd_info { +#define SEC_DEBUG_BD_INFO_SOFT_ERR_CHECK_M GENMASK(22, 0) + u32 soft_err_check; +#define SEC_DEBUG_BD_INFO_HARD_ERR_CHECK_M GENMASK(9, 0) + u32 hard_err_check; + u32 icv_mac1st_word; +#define SEC_DEBUG_BD_INFO_GET_ID_M GENMASK(19, 0) + u32 sec_get_id; + /* W4---W15 */ + u32 reserv_left[12]; +}; + +struct sec_out_bd_info { +#define SEC_OUT_BD_INFO_Q_ID_M GENMASK(11, 0) +#define SEC_OUT_BD_INFO_ECC_2BIT_ERR BIT(14) + u16 data; +}; + +#define SEC_MAX_DEVICES 8 +static struct sec_dev_info *sec_devices[SEC_MAX_DEVICES]; +static DEFINE_MUTEX(sec_id_lock); + +static int sec_queue_map_io(struct sec_queue *queue) +{ + struct device *dev = queue->dev_info->dev; + struct resource *res; + + res = platform_get_resource(to_platform_device(dev), + IORESOURCE_MEM, + 2 + queue->queue_id); + if (!res) { + dev_err(dev, "Failed to get queue %d memory resource\n", + queue->queue_id); + return -ENOMEM; + } + queue->regs = ioremap(res->start, resource_size(res)); + if (!queue->regs) + return -ENOMEM; + + return 0; +} + +static void sec_queue_unmap_io(struct sec_queue *queue) +{ + iounmap(queue->regs); +} + +static int sec_queue_ar_pkgattr(struct sec_queue *queue, u32 ar_pkg) +{ + void __iomem *addr = queue->regs + SEC_Q_ARUSER_CFG_REG; + u32 regval; + + regval = readl_relaxed(addr); + if (ar_pkg) + regval |= SEC_Q_ARUSER_CFG_PKG; + else + regval &= ~SEC_Q_ARUSER_CFG_PKG; + writel_relaxed(regval, addr); + + return 0; +} + +static int sec_queue_aw_pkgattr(struct sec_queue *queue, u32 aw_pkg) +{ + void __iomem *addr = queue->regs + SEC_Q_AWUSER_CFG_REG; + u32 regval; + + regval = readl_relaxed(addr); + regval |= SEC_Q_AWUSER_CFG_PKG; + writel_relaxed(regval, addr); + + return 0; +} + +static int sec_clk_en(struct sec_dev_info *info) +{ + void __iomem *base = info->regs[SEC_COMMON]; + u32 i = 0; + + writel_relaxed(0x7, base + SEC_ALGSUB_CLK_EN_REG); + do { + usleep_range(1000, 10000); + if ((readl_relaxed(base + SEC_ALGSUB_CLK_ST_REG) & 0x7) == 0x7) + return 0; + i++; + } while (i < 10); + dev_err(info->dev, "sec clock enable fail!\n"); + + return -EIO; +} + +static int sec_clk_dis(struct sec_dev_info *info) +{ + void __iomem *base = info->regs[SEC_COMMON]; + u32 i = 0; + + writel_relaxed(0x7, base + SEC_ALGSUB_CLK_DIS_REG); + do { + usleep_range(1000, 10000); + if ((readl_relaxed(base + SEC_ALGSUB_CLK_ST_REG) & 0x7) == 0) + return 0; + i++; + } while (i < 10); + dev_err(info->dev, "sec clock disable fail!\n"); + + return -EIO; +} + +static int sec_reset_whole_module(struct sec_dev_info *info) +{ + void __iomem *base = info->regs[SEC_COMMON]; + bool is_reset, b_is_reset; + u32 i = 0; + + writel_relaxed(1, base + SEC_ALGSUB_RST_REQ_REG); + writel_relaxed(1, base + SEC_ALGSUB_BUILD_RST_REQ_REG); + while (1) { + usleep_range(1000, 10000); + is_reset = readl_relaxed(base + SEC_ALGSUB_RST_ST_REG) & + SEC_ALGSUB_RST_ST_IS_RST; + b_is_reset = readl_relaxed(base + SEC_ALGSUB_BUILD_RST_ST_REG) & + SEC_ALGSUB_BUILD_RST_ST_IS_RST; + if (is_reset && b_is_reset) + break; + i++; + if (i > 10) { + dev_err(info->dev, "Reset req failed\n"); + return -EIO; + } + } + + i = 0; + writel_relaxed(1, base + SEC_ALGSUB_RST_DREQ_REG); + writel_relaxed(1, base + SEC_ALGSUB_BUILD_RST_DREQ_REG); + while (1) { + usleep_range(1000, 10000); + is_reset = readl_relaxed(base + SEC_ALGSUB_RST_ST_REG) & + SEC_ALGSUB_RST_ST_IS_RST; + b_is_reset = readl_relaxed(base + SEC_ALGSUB_BUILD_RST_ST_REG) & + SEC_ALGSUB_BUILD_RST_ST_IS_RST; + if (!is_reset && !b_is_reset) + break; + + i++; + if (i > 10) { + dev_err(info->dev, "Reset dreq failed\n"); + return -EIO; + } + } + + return 0; +} + +static void sec_bd_endian_little(struct sec_dev_info *info) +{ + void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG; + u32 regval; + + regval = readl_relaxed(addr); + regval &= ~(SEC_CTRL2_ENDIAN_BD | SEC_CTRL2_ENDIAN_BD_TYPE); + writel_relaxed(regval, addr); +} + +/* + * sec_cache_config - configure optimum cache placement + */ +static void sec_cache_config(struct sec_dev_info *info) +{ + struct iommu_domain *domain; + void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL_REG; + + domain = iommu_get_domain_for_dev(info->dev); + + /* Check that translation is occurring */ + if (domain && (domain->type & __IOMMU_DOMAIN_PAGING)) + writel_relaxed(0x44cf9e, addr); + else + writel_relaxed(0x4cfd9, addr); +} + +static void sec_data_axiwr_otsd_cfg(struct sec_dev_info *info, u32 cfg) +{ + void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG; + u32 regval; + + regval = readl_relaxed(addr); + regval &= ~SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_M; + regval |= (cfg << SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_S) & + SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_M; + writel_relaxed(regval, addr); +} + +static void sec_data_axird_otsd_cfg(struct sec_dev_info *info, u32 cfg) +{ + void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG; + u32 regval; + + regval = readl_relaxed(addr); + regval &= ~SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_M; + regval |= (cfg << SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_S) & + SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_M; + writel_relaxed(regval, addr); +} + +static void sec_clk_gate_en(struct sec_dev_info *info, bool clkgate) +{ + void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG; + u32 regval; + + regval = readl_relaxed(addr); + if (clkgate) + regval |= SEC_CTRL2_CLK_GATE_EN; + else + regval &= ~SEC_CTRL2_CLK_GATE_EN; + writel_relaxed(regval, addr); +} + +static void sec_comm_cnt_cfg(struct sec_dev_info *info, bool clr_ce) +{ + void __iomem *addr = info->regs[SEC_SAA] + SEC_COMMON_CNT_CLR_CE_REG; + u32 regval; + + regval = readl_relaxed(addr); + if (clr_ce) + regval |= SEC_COMMON_CNT_CLR_CE_CLEAR; + else + regval &= ~SEC_COMMON_CNT_CLR_CE_CLEAR; + writel_relaxed(regval, addr); +} + +static void sec_commsnap_en(struct sec_dev_info *info, bool snap_en) +{ + void __iomem *addr = info->regs[SEC_SAA] + SEC_COMMON_CNT_CLR_CE_REG; + u32 regval; + + regval = readl_relaxed(addr); + if (snap_en) + regval |= SEC_COMMON_CNT_CLR_CE_SNAP_EN; + else + regval &= ~SEC_COMMON_CNT_CLR_CE_SNAP_EN; + writel_relaxed(regval, addr); +} + +static void sec_ipv6_hashmask(struct sec_dev_info *info, u32 hash_mask[]) +{ + void __iomem *base = info->regs[SEC_SAA]; + int i; + + for (i = 0; i < 10; i++) + writel_relaxed(hash_mask[0], + base + SEC_IPV6_MASK_TABLE_X_REG(i)); +} + +static int sec_ipv4_hashmask(struct sec_dev_info *info, u32 hash_mask) +{ + if (hash_mask & SEC_HASH_IPV4_MASK) { + dev_err(info->dev, "Sec Ipv4 Hash Mask Input Error!\n "); + return -EINVAL; + } + + writel_relaxed(hash_mask, + info->regs[SEC_SAA] + SEC_IPV4_MASK_TABLE_REG); + + return 0; +} + +static void sec_set_dbg_bd_cfg(struct sec_dev_info *info, u32 cfg) +{ + void __iomem *addr = info->regs[SEC_SAA] + SEC_DEBUG_BD_CFG_REG; + u32 regval; + + regval = readl_relaxed(addr); + /* Always disable write back of normal bd */ + regval &= ~SEC_DEBUG_BD_CFG_WB_NORMAL; + + if (cfg) + regval &= ~SEC_DEBUG_BD_CFG_WB_EN; + else + regval |= SEC_DEBUG_BD_CFG_WB_EN; + + writel_relaxed(regval, addr); +} + +static void sec_saa_getqm_en(struct sec_dev_info *info, u32 saa_indx, u32 en) +{ + void __iomem *addr = info->regs[SEC_SAA] + SEC_SAA_BASE + + SEC_SAA_CTRL_REG(saa_indx); + u32 regval; + + regval = readl_relaxed(addr); + if (en) + regval |= SEC_SAA_CTRL_GET_QM_EN; + else + regval &= ~SEC_SAA_CTRL_GET_QM_EN; + writel_relaxed(regval, addr); +} + +static void sec_saa_int_mask(struct sec_dev_info *info, u32 saa_indx, + u32 saa_int_mask) +{ + writel_relaxed(saa_int_mask, + info->regs[SEC_SAA] + SEC_SAA_BASE + SEC_ST_INTMSK1_REG + + saa_indx * SEC_SAA_ADDR_SIZE); +} + +static void sec_streamid(struct sec_dev_info *info, int i) +{ + #define SEC_SID 0x600 + #define SEC_VMID 0 + + writel_relaxed((SEC_VMID | ((SEC_SID & 0xffff) << 8)), + info->regs[SEC_SAA] + SEC_Q_VMID_CFG_REG(i)); +} + +static void sec_queue_ar_alloc(struct sec_queue *queue, u32 alloc) +{ + void __iomem *addr = queue->regs + SEC_Q_ARUSER_CFG_REG; + u32 regval; + + regval = readl_relaxed(addr); + if (alloc == SEC_QUEUE_AR_FROCE_ALLOC) { + regval |= SEC_Q_ARUSER_CFG_FA; + regval &= ~SEC_Q_ARUSER_CFG_FNA; + } else { + regval &= ~SEC_Q_ARUSER_CFG_FA; + regval |= SEC_Q_ARUSER_CFG_FNA; + } + + writel_relaxed(regval, addr); +} + +static void sec_queue_aw_alloc(struct sec_queue *queue, u32 alloc) +{ + void __iomem *addr = queue->regs + SEC_Q_AWUSER_CFG_REG; + u32 regval; + + regval = readl_relaxed(addr); + if (alloc == SEC_QUEUE_AW_FROCE_ALLOC) { + regval |= SEC_Q_AWUSER_CFG_FA; + regval &= ~SEC_Q_AWUSER_CFG_FNA; + } else { + regval &= ~SEC_Q_AWUSER_CFG_FA; + regval |= SEC_Q_AWUSER_CFG_FNA; + } + + writel_relaxed(regval, addr); +} + +static void sec_queue_reorder(struct sec_queue *queue, bool reorder) +{ + void __iomem *base = queue->regs; + u32 regval; + + regval = readl_relaxed(base + SEC_Q_CFG_REG); + if (reorder) + regval |= SEC_Q_CFG_REORDER; + else + regval &= ~SEC_Q_CFG_REORDER; + writel_relaxed(regval, base + SEC_Q_CFG_REG); +} + +static void sec_queue_depth(struct sec_queue *queue, u32 depth) +{ + void __iomem *addr = queue->regs + SEC_Q_DEPTH_CFG_REG; + u32 regval; + + regval = readl_relaxed(addr); + regval &= ~SEC_Q_DEPTH_CFG_DEPTH_M; + regval |= (depth << SEC_Q_DEPTH_CFG_DEPTH_S) & SEC_Q_DEPTH_CFG_DEPTH_M; + + writel_relaxed(regval, addr); +} + +static void sec_queue_cmdbase_addr(struct sec_queue *queue, u64 addr) +{ + writel_relaxed(upper_32_bits(addr), queue->regs + SEC_Q_BASE_HADDR_REG); + writel_relaxed(lower_32_bits(addr), queue->regs + SEC_Q_BASE_LADDR_REG); +} + +static void sec_queue_outorder_addr(struct sec_queue *queue, u64 addr) +{ + writel_relaxed(upper_32_bits(addr), + queue->regs + SEC_Q_OUTORDER_BASE_HADDR_REG); + writel_relaxed(lower_32_bits(addr), + queue->regs + SEC_Q_OUTORDER_BASE_LADDR_REG); +} + +static void sec_queue_errbase_addr(struct sec_queue *queue, u64 addr) +{ + writel_relaxed(upper_32_bits(addr), + queue->regs + SEC_Q_ERR_BASE_HADDR_REG); + writel_relaxed(lower_32_bits(addr), + queue->regs + SEC_Q_ERR_BASE_LADDR_REG); +} + +static void sec_queue_irq_disable(struct sec_queue *queue) +{ + writel_relaxed((u32)~0, queue->regs + SEC_Q_FLOW_INT_MKS_REG); +} + +static void sec_queue_irq_enable(struct sec_queue *queue) +{ + writel_relaxed(0, queue->regs + SEC_Q_FLOW_INT_MKS_REG); +} + +static void sec_queue_abn_irq_disable(struct sec_queue *queue) +{ + writel_relaxed((u32)~0, queue->regs + SEC_Q_FAIL_INT_MSK_REG); +} + +static void sec_queue_stop(struct sec_queue *queue) +{ + disable_irq(queue->task_irq); + sec_queue_irq_disable(queue); + writel_relaxed(0x0, queue->regs + SEC_QUEUE_ENB_REG); +} + +static void sec_queue_start(struct sec_queue *queue) +{ + sec_queue_irq_enable(queue); + enable_irq(queue->task_irq); + queue->expected = 0; + writel_relaxed(SEC_Q_INIT_AND_STAT_CLEAR, queue->regs + SEC_Q_INIT_REG); + writel_relaxed(0x1, queue->regs + SEC_QUEUE_ENB_REG); +} + +static struct sec_queue *sec_alloc_queue(struct sec_dev_info *info) +{ + int i; + + mutex_lock(&info->dev_lock); + + /* Get the first idle queue in SEC device */ + for (i = 0; i < SEC_Q_NUM; i++) + if (!info->queues[i].in_use) { + info->queues[i].in_use = true; + info->queues_in_use++; + mutex_unlock(&info->dev_lock); + + return &info->queues[i]; + } + mutex_unlock(&info->dev_lock); + + return ERR_PTR(-ENODEV); +} + +static int sec_queue_free(struct sec_queue *queue) +{ + struct sec_dev_info *info = queue->dev_info; + + if (queue->queue_id >= SEC_Q_NUM) { + dev_err(info->dev, "No queue %d\n", queue->queue_id); + return -ENODEV; + } + + if (!queue->in_use) { + dev_err(info->dev, "Queue %d is idle\n", queue->queue_id); + return -ENODEV; + } + + mutex_lock(&info->dev_lock); + queue->in_use = false; + info->queues_in_use--; + mutex_unlock(&info->dev_lock); + + return 0; +} + +static irqreturn_t sec_isr_handle_th(int irq, void *q) +{ + sec_queue_irq_disable(q); + return IRQ_WAKE_THREAD; +} + +static irqreturn_t sec_isr_handle(int irq, void *q) +{ + struct sec_queue *queue = q; + struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd; + struct sec_queue_ring_cq *cq_ring = &queue->ring_cq; + struct sec_out_bd_info *outorder_msg; + struct sec_bd_info *msg; + u32 ooo_read, ooo_write; + void __iomem *base = queue->regs; + int q_id; + + ooo_read = readl(base + SEC_Q_OUTORDER_RD_PTR_REG); + ooo_write = readl(base + SEC_Q_OUTORDER_WR_PTR_REG); + outorder_msg = cq_ring->vaddr + ooo_read; + q_id = outorder_msg->data & SEC_OUT_BD_INFO_Q_ID_M; + msg = msg_ring->vaddr + q_id; + + while ((ooo_write != ooo_read) && msg->w0 & SEC_BD_W0_DONE) { + /* + * Must be before callback otherwise blocks adding other chained + * elements + */ + set_bit(q_id, queue->unprocessed); + if (q_id == queue->expected) + while (test_bit(queue->expected, queue->unprocessed)) { + clear_bit(queue->expected, queue->unprocessed); + msg = msg_ring->vaddr + queue->expected; + msg->w0 &= ~SEC_BD_W0_DONE; + queue->shadow[queue->expected] = NULL; + msg_ring->callback(msg, + queue->shadow[queue->expected]); + queue->expected = (queue->expected + 1) % + SEC_QUEUE_LEN; + atomic_dec(&msg_ring->used); + } + + ooo_read = (ooo_read + 1) % SEC_QUEUE_LEN; + writel(ooo_read, base + SEC_Q_OUTORDER_RD_PTR_REG); + ooo_write = readl(base + SEC_Q_OUTORDER_WR_PTR_REG); + outorder_msg = cq_ring->vaddr + ooo_read; + q_id = outorder_msg->data & SEC_OUT_BD_INFO_Q_ID_M; + msg = msg_ring->vaddr + q_id; + } + + sec_queue_irq_enable(queue); + + return IRQ_HANDLED; +} + +static int sec_queue_irq_init(struct sec_queue *queue) +{ + struct sec_dev_info *info = queue->dev_info; + int irq = queue->task_irq; + int ret; + + ret = request_threaded_irq(irq, sec_isr_handle_th, sec_isr_handle, + IRQF_TRIGGER_RISING, queue->name, queue); + if (ret) { + dev_err(info->dev, "request irq(%d) failed %d\n", irq, ret); + return ret; + } + disable_irq(irq); + + return 0; +} + +static int sec_queue_irq_uninit(struct sec_queue *queue) +{ + free_irq(queue->task_irq, queue); + + return 0; +} + +static struct sec_dev_info *sec_device_get(void) +{ + struct sec_dev_info *sec_dev = NULL; + struct sec_dev_info *this_sec_dev; + int least_busy_n = SEC_Q_NUM + 1; + int i; + + /* Find which one is least busy and use that first */ + for (i = 0; i < SEC_MAX_DEVICES; i++) { + this_sec_dev = sec_devices[i]; + if (this_sec_dev && + this_sec_dev->queues_in_use < least_busy_n) { + least_busy_n = this_sec_dev->queues_in_use; + sec_dev = this_sec_dev; + } + } + + return sec_dev; +} + +static struct sec_queue *sec_queue_alloc_start(struct sec_dev_info *info) +{ + struct sec_queue *queue; + + queue = sec_alloc_queue(info); + if (IS_ERR(queue)) { + dev_err(info->dev, "alloc sec queue failed! %ld\n", + PTR_ERR(queue)); + return queue; + } + + sec_queue_start(queue); + + return queue; +} + +/** + * sec_queue_alloc_start_safe - get a hw queue from appropriate instance + * + * This function does extremely simplistic load balancing. It does not take into + * account NUMA locality of the accelerator, or which cpu has requested the + * queue. Future work may focus on optimizing this in order to improve full + * machine throughput. + */ +struct sec_queue *sec_queue_alloc_start_safe(void) +{ + struct sec_dev_info *info; + struct sec_queue *queue = ERR_PTR(-ENODEV); + + mutex_lock(&sec_id_lock); + info = sec_device_get(); + if (!info) + goto unlock; + + queue = sec_queue_alloc_start(info); + +unlock: + mutex_unlock(&sec_id_lock); + + return queue; +} + +/** + * sec_queue_stop_release() - free up a hw queue for reuse + * @queue: The queue we are done with. + * + * This will stop the current queue, terminanting any transactions + * that are inflight an return it to the pool of available hw queuess + */ +int sec_queue_stop_release(struct sec_queue *queue) +{ + struct device *dev = queue->dev_info->dev; + int ret; + + sec_queue_stop(queue); + + ret = sec_queue_free(queue); + if (ret) + dev_err(dev, "Releasing queue failed %d\n", ret); + + return ret; +} + +/** + * sec_queue_empty() - Is this hardware queue currently empty. + * + * We need to know if we have an empty queue for some of the chaining modes + * as if it is not empty we may need to hold the message in a software queue + * until the hw queue is drained. + */ +bool sec_queue_empty(struct sec_queue *queue) +{ + struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd; + + return !atomic_read(&msg_ring->used); +} + +/** + * sec_queue_send() - queue up a single operation in the hw queue + * @queue: The queue in which to put the message + * @msg: The message + * @ctx: Context to be put in the shadow array and passed back to cb on result. + * + * This function will return -EAGAIN if the queue is currently full. + */ +int sec_queue_send(struct sec_queue *queue, struct sec_bd_info *msg, void *ctx) +{ + struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd; + void __iomem *base = queue->regs; + u32 write, read; + + mutex_lock(&msg_ring->lock); + read = readl(base + SEC_Q_RD_PTR_REG); + write = readl(base + SEC_Q_WR_PTR_REG); + if (write == read && atomic_read(&msg_ring->used) == SEC_QUEUE_LEN) { + mutex_unlock(&msg_ring->lock); + return -EAGAIN; + } + memcpy(msg_ring->vaddr + write, msg, sizeof(*msg)); + queue->shadow[write] = ctx; + write = (write + 1) % SEC_QUEUE_LEN; + + /* Ensure content updated before queue advance */ + wmb(); + writel(write, base + SEC_Q_WR_PTR_REG); + + atomic_inc(&msg_ring->used); + mutex_unlock(&msg_ring->lock); + + return 0; +} + +bool sec_queue_can_enqueue(struct sec_queue *queue, int num) +{ + struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd; + + return SEC_QUEUE_LEN - atomic_read(&msg_ring->used) >= num; +} + +static void sec_queue_hw_init(struct sec_queue *queue) +{ + sec_queue_ar_alloc(queue, SEC_QUEUE_AR_FROCE_NOALLOC); + sec_queue_aw_alloc(queue, SEC_QUEUE_AR_FROCE_NOALLOC); + sec_queue_ar_pkgattr(queue, 1); + sec_queue_aw_pkgattr(queue, 1); + + /* Enable out of order queue */ + sec_queue_reorder(queue, true); + + /* Interrupt after a single complete element */ + writel_relaxed(1, queue->regs + SEC_Q_PROC_NUM_CFG_REG); + + sec_queue_depth(queue, SEC_QUEUE_LEN - 1); + + sec_queue_cmdbase_addr(queue, queue->ring_cmd.paddr); + + sec_queue_outorder_addr(queue, queue->ring_cq.paddr); + + sec_queue_errbase_addr(queue, queue->ring_db.paddr); + + writel_relaxed(0x100, queue->regs + SEC_Q_OT_TH_REG); + + sec_queue_abn_irq_disable(queue); + sec_queue_irq_disable(queue); + writel_relaxed(SEC_Q_INIT_AND_STAT_CLEAR, queue->regs + SEC_Q_INIT_REG); +} + +static int sec_hw_init(struct sec_dev_info *info) +{ + struct iommu_domain *domain; + u32 sec_ipv4_mask = 0; + u32 sec_ipv6_mask[10] = {}; + u32 i, ret; + + domain = iommu_get_domain_for_dev(info->dev); + + /* + * Enable all available processing unit clocks. + * Only the first cluster is usable with translations. + */ + if (domain && (domain->type & __IOMMU_DOMAIN_PAGING)) + info->num_saas = 5; + + else + info->num_saas = 10; + + writel_relaxed(GENMASK(info->num_saas - 1, 0), + info->regs[SEC_SAA] + SEC_CLK_EN_REG); + + /* 32 bit little endian */ + sec_bd_endian_little(info); + + sec_cache_config(info); + + /* Data axi port write and read outstanding config as per datasheet */ + sec_data_axiwr_otsd_cfg(info, 0x7); + sec_data_axird_otsd_cfg(info, 0x7); + + /* Enable clock gating */ + sec_clk_gate_en(info, true); + + /* Set CNT_CYC register not read clear */ + sec_comm_cnt_cfg(info, false); + + /* Enable CNT_CYC */ + sec_commsnap_en(info, false); + + writel_relaxed((u32)~0, info->regs[SEC_SAA] + SEC_FSM_MAX_CNT_REG); + + ret = sec_ipv4_hashmask(info, sec_ipv4_mask); + if (ret) { + dev_err(info->dev, "Failed to set ipv4 hashmask %d\n", ret); + return -EIO; + } + + sec_ipv6_hashmask(info, sec_ipv6_mask); + + /* do not use debug bd */ + sec_set_dbg_bd_cfg(info, 0); + + if (domain && (domain->type & __IOMMU_DOMAIN_PAGING)) { + for (i = 0; i < SEC_Q_NUM; i++) { + sec_streamid(info, i); + /* Same QoS for all queues */ + writel_relaxed(0x3f, + info->regs[SEC_SAA] + + SEC_Q_WEIGHT_CFG_REG(i)); + } + } + + for (i = 0; i < info->num_saas; i++) { + sec_saa_getqm_en(info, i, 1); + sec_saa_int_mask(info, i, 0); + } + + return 0; +} + +static void sec_hw_exit(struct sec_dev_info *info) +{ + int i; + + for (i = 0; i < SEC_MAX_SAA_NUM; i++) { + sec_saa_int_mask(info, i, (u32)~0); + sec_saa_getqm_en(info, i, 0); + } +} + +static void sec_queue_base_init(struct sec_dev_info *info, + struct sec_queue *queue, int queue_id) +{ + queue->dev_info = info; + queue->queue_id = queue_id; + snprintf(queue->name, sizeof(queue->name), + "%s_%d", dev_name(info->dev), queue->queue_id); +} + +static int sec_map_io(struct sec_dev_info *info, struct platform_device *pdev) +{ + struct resource *res; + int i; + + for (i = 0; i < SEC_NUM_ADDR_REGIONS; i++) { + res = platform_get_resource(pdev, IORESOURCE_MEM, i); + + if (!res) { + dev_err(info->dev, "Memory resource %d not found\n", i); + return -EINVAL; + } + + info->regs[i] = devm_ioremap(info->dev, res->start, + resource_size(res)); + if (!info->regs[i]) { + dev_err(info->dev, + "Memory resource %d could not be remapped\n", + i); + return -EINVAL; + } + } + + return 0; +} + +static int sec_base_init(struct sec_dev_info *info, + struct platform_device *pdev) +{ + int ret; + + ret = sec_map_io(info, pdev); + if (ret) + return ret; + + ret = sec_clk_en(info); + if (ret) + return ret; + + ret = sec_reset_whole_module(info); + if (ret) + goto sec_clk_disable; + + ret = sec_hw_init(info); + if (ret) + goto sec_clk_disable; + + return 0; + +sec_clk_disable: + sec_clk_dis(info); + + return ret; +} + +static void sec_base_exit(struct sec_dev_info *info) +{ + sec_hw_exit(info); + sec_clk_dis(info); +} + +#define SEC_Q_CMD_SIZE \ + round_up(SEC_QUEUE_LEN * sizeof(struct sec_bd_info), PAGE_SIZE) +#define SEC_Q_CQ_SIZE \ + round_up(SEC_QUEUE_LEN * sizeof(struct sec_out_bd_info), PAGE_SIZE) +#define SEC_Q_DB_SIZE \ + round_up(SEC_QUEUE_LEN * sizeof(struct sec_debug_bd_info), PAGE_SIZE) + +static int sec_queue_res_cfg(struct sec_queue *queue) +{ + struct device *dev = queue->dev_info->dev; + struct sec_queue_ring_cmd *ring_cmd = &queue->ring_cmd; + struct sec_queue_ring_cq *ring_cq = &queue->ring_cq; + struct sec_queue_ring_db *ring_db = &queue->ring_db; + int ret; + + ring_cmd->vaddr = dma_zalloc_coherent(dev, SEC_Q_CMD_SIZE, + &ring_cmd->paddr, + GFP_KERNEL); + if (!ring_cmd->vaddr) + return -ENOMEM; + + atomic_set(&ring_cmd->used, 0); + mutex_init(&ring_cmd->lock); + ring_cmd->callback = sec_alg_callback; + + ring_cq->vaddr = dma_zalloc_coherent(dev, SEC_Q_CQ_SIZE, + &ring_cq->paddr, + GFP_KERNEL); + if (!ring_cq->vaddr) { + ret = -ENOMEM; + goto err_free_ring_cmd; + } + + ring_db->vaddr = dma_zalloc_coherent(dev, SEC_Q_DB_SIZE, + &ring_db->paddr, + GFP_KERNEL); + if (!ring_db->vaddr) { + ret = -ENOMEM; + goto err_free_ring_cq; + } + queue->task_irq = platform_get_irq(to_platform_device(dev), + queue->queue_id * 2 + 1); + if (queue->task_irq <= 0) { + ret = -EINVAL; + goto err_free_ring_db; + } + + return 0; + +err_free_ring_db: + dma_free_coherent(dev, SEC_Q_DB_SIZE, queue->ring_db.vaddr, + queue->ring_db.paddr); +err_free_ring_cq: + dma_free_coherent(dev, SEC_Q_CQ_SIZE, queue->ring_cq.vaddr, + queue->ring_cq.paddr); +err_free_ring_cmd: + dma_free_coherent(dev, SEC_Q_CMD_SIZE, queue->ring_cmd.vaddr, + queue->ring_cmd.paddr); + + return ret; +} + +static void sec_queue_free_ring_pages(struct sec_queue *queue) +{ + struct device *dev = queue->dev_info->dev; + + dma_free_coherent(dev, SEC_Q_DB_SIZE, queue->ring_db.vaddr, + queue->ring_db.paddr); + dma_free_coherent(dev, SEC_Q_CQ_SIZE, queue->ring_cq.vaddr, + queue->ring_cq.paddr); + dma_free_coherent(dev, SEC_Q_CMD_SIZE, queue->ring_cmd.vaddr, + queue->ring_cmd.paddr); +} + +static int sec_queue_config(struct sec_dev_info *info, struct sec_queue *queue, + int queue_id) +{ + int ret; + + sec_queue_base_init(info, queue, queue_id); + + ret = sec_queue_res_cfg(queue); + if (ret) + return ret; + + ret = sec_queue_map_io(queue); + if (ret) { + dev_err(info->dev, "Queue map failed %d\n", ret); + sec_queue_free_ring_pages(queue); + return ret; + } + + sec_queue_hw_init(queue); + + return 0; +} + +static void sec_queue_unconfig(struct sec_dev_info *info, + struct sec_queue *queue) +{ + sec_queue_unmap_io(queue); + sec_queue_free_ring_pages(queue); +} + +static int sec_id_alloc(struct sec_dev_info *info) +{ + int ret = 0; + int i; + + mutex_lock(&sec_id_lock); + + for (i = 0; i < SEC_MAX_DEVICES; i++) + if (!sec_devices[i]) + break; + if (i == SEC_MAX_DEVICES) { + ret = -ENOMEM; + goto unlock; + } + info->sec_id = i; + sec_devices[info->sec_id] = info; + +unlock: + mutex_unlock(&sec_id_lock); + + return ret; +} + +static void sec_id_free(struct sec_dev_info *info) +{ + mutex_lock(&sec_id_lock); + sec_devices[info->sec_id] = NULL; + mutex_unlock(&sec_id_lock); +} + +static int sec_probe(struct platform_device *pdev) +{ + struct sec_dev_info *info; + struct device *dev = &pdev->dev; + int i, j; + int ret; + + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (ret) { + dev_err(dev, "Failed to set 64 bit dma mask %d", ret); + return -ENODEV; + } + + info = devm_kzalloc(dev, (sizeof(*info)), GFP_KERNEL); + if (!info) + return -ENOMEM; + + info->dev = dev; + mutex_init(&info->dev_lock); + + info->hw_sgl_pool = dmam_pool_create("sgl", dev, + sizeof(struct sec_hw_sgl), 64, 0); + if (!info->hw_sgl_pool) { + dev_err(dev, "Failed to create sec sgl dma pool\n"); + return -ENOMEM; + } + + ret = sec_base_init(info, pdev); + if (ret) { + dev_err(dev, "Base initialization fail! %d\n", ret); + return ret; + } + + for (i = 0; i < SEC_Q_NUM; i++) { + ret = sec_queue_config(info, &info->queues[i], i); + if (ret) + goto queues_unconfig; + + ret = sec_queue_irq_init(&info->queues[i]); + if (ret) { + sec_queue_unconfig(info, &info->queues[i]); + goto queues_unconfig; + } + } + + ret = sec_algs_register(); + if (ret) { + dev_err(dev, "Failed to register algorithms with crypto %d\n", + ret); + goto queues_unconfig; + } + + platform_set_drvdata(pdev, info); + + ret = sec_id_alloc(info); + if (ret) + goto algs_unregister; + + return 0; + +algs_unregister: + sec_algs_unregister(); +queues_unconfig: + for (j = i - 1; j >= 0; j--) { + sec_queue_irq_uninit(&info->queues[j]); + sec_queue_unconfig(info, &info->queues[j]); + } + sec_base_exit(info); + + return ret; +} + +static int sec_remove(struct platform_device *pdev) +{ + struct sec_dev_info *info = platform_get_drvdata(pdev); + int i; + + /* Unexpose as soon as possible, reuse during remove is fine */ + sec_id_free(info); + + sec_algs_unregister(); + + for (i = 0; i < SEC_Q_NUM; i++) { + sec_queue_irq_uninit(&info->queues[i]); + sec_queue_unconfig(info, &info->queues[i]); + } + + sec_base_exit(info); + + return 0; +} + +static const __maybe_unused struct of_device_id sec_match[] = { + { .compatible = "hisilicon,hip06-sec" }, + { .compatible = "hisilicon,hip07-sec" }, + {} +}; +MODULE_DEVICE_TABLE(of, sec_match); + +static const __maybe_unused struct acpi_device_id sec_acpi_match[] = { + { "HISI02C1", 0 }, + { } +}; +MODULE_DEVICE_TABLE(acpi, sec_acpi_match); + +static struct platform_driver sec_driver = { + .probe = sec_probe, + .remove = sec_remove, + .driver = { + .name = "hisi_sec_platform_driver", + .of_match_table = sec_match, + .acpi_match_table = ACPI_PTR(sec_acpi_match), + }, +}; +module_platform_driver(sec_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Hisilicon Security Accelerators"); +MODULE_AUTHOR("Zaibo Xu <xuzaibo@xxxxxxxxxx"); +MODULE_AUTHOR("Jonathan Cameron <jonathan.cameron@xxxxxxxxxx>"); diff --git a/drivers/crypto/hisilicon/sec/sec_drv.h b/drivers/crypto/hisilicon/sec/sec_drv.h new file mode 100644 index 000000000000..2d2f186674ba --- /dev/null +++ b/drivers/crypto/hisilicon/sec/sec_drv.h @@ -0,0 +1,428 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2016-2017 Hisilicon Limited. */ + +#ifndef _SEC_DRV_H_ +#define _SEC_DRV_H_ + +#include <crypto/algapi.h> +#include <linux/kfifo.h> + +#define SEC_MAX_SGE_NUM 64 +#define SEC_HW_RING_NUM 3 + +#define SEC_CMD_RING 0 +#define SEC_OUTORDER_RING 1 +#define SEC_DBG_RING 2 + +/* A reasonable length to balance memory use against flexibility */ +#define SEC_QUEUE_LEN 512 + +#define SEC_MAX_SGE_NUM 64 + +struct sec_bd_info { +#define SEC_BD_W0_T_LEN_M GENMASK(4, 0) +#define SEC_BD_W0_T_LEN_S 0 + +#define SEC_BD_W0_C_WIDTH_M GENMASK(6, 5) +#define SEC_BD_W0_C_WIDTH_S 5 +#define SEC_C_WIDTH_AES_128BIT 0 +#define SEC_C_WIDTH_AES_8BIT 1 +#define SEC_C_WIDTH_AES_1BIT 2 +#define SEC_C_WIDTH_DES_64BIT 0 +#define SEC_C_WIDTH_DES_8BIT 1 +#define SEC_C_WIDTH_DES_1BIT 2 + +#define SEC_BD_W0_C_MODE_M GENMASK(9, 7) +#define SEC_BD_W0_C_MODE_S 7 +#define SEC_C_MODE_ECB 0 +#define SEC_C_MODE_CBC 1 +#define SEC_C_MODE_CTR 4 +#define SEC_C_MODE_CCM 5 +#define SEC_C_MODE_GCM 6 +#define SEC_C_MODE_XTS 7 + +#define SEC_BD_W0_SEQ BIT(10) +#define SEC_BD_W0_DE BIT(11) +#define SEC_BD_W0_DAT_SKIP_M GENMASK(13, 12) +#define SEC_BD_W0_DAT_SKIP_S 12 +#define SEC_BD_W0_C_GRAN_SIZE_19_16_M GENMASK(17, 14) +#define SEC_BD_W0_C_GRAN_SIZE_19_16_S 14 + +#define SEC_BD_W0_CIPHER_M GENMASK(19, 18) +#define SEC_BD_W0_CIPHER_S 18 +#define SEC_CIPHER_NULL 0 +#define SEC_CIPHER_ENCRYPT 1 +#define SEC_CIPHER_DECRYPT 2 + +#define SEC_BD_W0_AUTH_M GENMASK(21, 20) +#define SEC_BD_W0_AUTH_S 20 +#define SEC_AUTH_NULL 0 +#define SEC_AUTH_MAC 1 +#define SEC_AUTH_VERIF 2 + +#define SEC_BD_W0_AI_GEN BIT(22) +#define SEC_BD_W0_CI_GEN BIT(23) +#define SEC_BD_W0_NO_HPAD BIT(24) +#define SEC_BD_W0_HM_M GENMASK(26, 25) +#define SEC_BD_W0_HM_S 25 +#define SEC_BD_W0_ICV_OR_SKEY_EN_M GENMASK(28, 27) +#define SEC_BD_W0_ICV_OR_SKEY_EN_S 27 + +/* Multi purpose field - gran size bits for send, flag for recv */ +#define SEC_BD_W0_FLAG_M GENMASK(30, 29) +#define SEC_BD_W0_C_GRAN_SIZE_21_20_M GENMASK(30, 29) +#define SEC_BD_W0_FLAG_S 29 +#define SEC_BD_W0_C_GRAN_SIZE_21_20_S 29 + +#define SEC_BD_W0_DONE BIT(31) + u32 w0; + +#define SEC_BD_W1_AUTH_GRAN_SIZE_M GENMASK(21, 0) +#define SEC_BD_W1_AUTH_GRAN_SIZE_S 0 +#define SEC_BD_W1_M_KEY_EN BIT(22) +#define SEC_BD_W1_BD_INVALID BIT(23) +#define SEC_BD_W1_ADDR_TYPE BIT(24) + +#define SEC_BD_W1_A_ALG_M GENMASK(28, 25) +#define SEC_BD_W1_A_ALG_S 25 +#define SEC_A_ALG_SHA1 0 +#define SEC_A_ALG_SHA256 1 +#define SEC_A_ALG_MD5 2 +#define SEC_A_ALG_SHA224 3 +#define SEC_A_ALG_HMAC_SHA1 8 +#define SEC_A_ALG_HMAC_SHA224 10 +#define SEC_A_ALG_HMAC_SHA256 11 +#define SEC_A_ALG_HMAC_MD5 12 +#define SEC_A_ALG_AES_XCBC 13 +#define SEC_A_ALG_AES_CMAC 14 + +#define SEC_BD_W1_C_ALG_M GENMASK(31, 29) +#define SEC_BD_W1_C_ALG_S 29 +#define SEC_C_ALG_DES 0 +#define SEC_C_ALG_3DES 1 +#define SEC_C_ALG_AES 2 + + u32 w1; + +#define SEC_BD_W2_C_GRAN_SIZE_15_0_M GENMASK(15, 0) +#define SEC_BD_W2_C_GRAN_SIZE_15_0_S 0 +#define SEC_BD_W2_GRAN_NUM_M GENMASK(31, 16) +#define SEC_BD_W2_GRAN_NUM_S 16 + u32 w2; + +#define SEC_BD_W3_AUTH_LEN_OFFSET_M GENMASK(9, 0) +#define SEC_BD_W3_AUTH_LEN_OFFSET_S 0 +#define SEC_BD_W3_CIPHER_LEN_OFFSET_M GENMASK(19, 10) +#define SEC_BD_W3_CIPHER_LEN_OFFSET_S 10 +#define SEC_BD_W3_MAC_LEN_M GENMASK(24, 20) +#define SEC_BD_W3_MAC_LEN_S 20 +#define SEC_BD_W3_A_KEY_LEN_M GENMASK(29, 25) +#define SEC_BD_W3_A_KEY_LEN_S 25 +#define SEC_BD_W3_C_KEY_LEN_M GENMASK(31, 30) +#define SEC_BD_W3_C_KEY_LEN_S 30 +#define SEC_KEY_LEN_AES_128 0 +#define SEC_KEY_LEN_AES_192 1 +#define SEC_KEY_LEN_AES_256 2 +#define SEC_KEY_LEN_DES 1 +#define SEC_KEY_LEN_3DES_3_KEY 1 +#define SEC_KEY_LEN_3DES_2_KEY 3 + u32 w3; + + /* W4,5 */ + union { + u32 authkey_addr_lo; + u32 authiv_addr_lo; + }; + union { + u32 authkey_addr_hi; + u32 authiv_addr_hi; + }; + + /* W6,7 */ + u32 cipher_key_addr_lo; + u32 cipher_key_addr_hi; + + /* W8,9 */ + u32 cipher_iv_addr_lo; + u32 cipher_iv_addr_hi; + + /* W10,11 */ + u32 data_addr_lo; + u32 data_addr_hi; + + /* W12,13 */ + u32 mac_addr_lo; + u32 mac_addr_hi; + + /* W14,15 */ + u32 cipher_destin_addr_lo; + u32 cipher_destin_addr_hi; +}; + +enum sec_mem_region { + SEC_COMMON = 0, + SEC_SAA, + SEC_NUM_ADDR_REGIONS +}; + +#define SEC_NAME_SIZE 64 +#define SEC_Q_NUM 16 + + +/** + * struct sec_queue_ring_cmd - store information about a SEC HW cmd ring + * @used: Local counter used to cheaply establish if the ring is empty. + * @lock: Protect against simultaneous adjusting of the read and write pointers. + * @vaddr: Virtual address for the ram pages used for the ring. + * @paddr: Physical address of the dma mapped region of ram used for the ring. + * @callback: Callback function called on a ring element completing. + */ +struct sec_queue_ring_cmd { + atomic_t used; + struct mutex lock; + struct sec_bd_info *vaddr; + dma_addr_t paddr; + void (*callback)(struct sec_bd_info *resp, void *ctx); +}; + +struct sec_debug_bd_info; +struct sec_queue_ring_db { + struct sec_debug_bd_info *vaddr; + dma_addr_t paddr; +}; + +struct sec_out_bd_info; +struct sec_queue_ring_cq { + struct sec_out_bd_info *vaddr; + dma_addr_t paddr; +}; + +struct sec_dev_info; + +enum sec_cipher_alg { + SEC_C_DES_ECB_64, + SEC_C_DES_CBC_64, + + SEC_C_3DES_ECB_192_3KEY, + SEC_C_3DES_ECB_192_2KEY, + + SEC_C_3DES_CBC_192_3KEY, + SEC_C_3DES_CBC_192_2KEY, + + SEC_C_AES_ECB_128, + SEC_C_AES_ECB_192, + SEC_C_AES_ECB_256, + + SEC_C_AES_CBC_128, + SEC_C_AES_CBC_192, + SEC_C_AES_CBC_256, + + SEC_C_AES_CTR_128, + SEC_C_AES_CTR_192, + SEC_C_AES_CTR_256, + + SEC_C_AES_XTS_128, + SEC_C_AES_XTS_256, + + SEC_C_NULL, +}; + +/** + * struct sec_alg_tfm_ctx - hardware specific tranformation context + * @cipher_alg: Cipher algorithm enabled include encryption mode. + * @key: Key storage if required. + * @pkey: DMA address for the key storage. + * @req_template: Request template to save time on setup. + * @queue: The hardware queue associated with this tfm context. + * @lock: Protect key and pkey to ensure they are consistent + * @auth_buf: Current context buffer for auth operations. + * @backlog: The backlog queue used for cases where our buffers aren't + * large enough. + */ +struct sec_alg_tfm_ctx { + enum sec_cipher_alg cipher_alg; + u8 *key; + dma_addr_t pkey; + struct sec_bd_info req_template; + struct sec_queue *queue; + struct mutex lock; + u8 *auth_buf; + struct list_head backlog; +}; + +/** + * struct sec_request - data associate with a single crypto request + * @elements: List of subparts of this request (hardware size restriction) + * @num_elements: The number of subparts (used as an optimization) + * @lock: Protect elements of this structure against concurrent change. + * @tfm_ctx: hardware specific context. + * @len_in: length of in sgl from upper layers + * @len_out: length of out sgl from upper layers + * @dma_iv: initialization vector - phsyical address + * @err: store used to track errors across subelements of this request. + * @req_base: pointer to base element of associate crypto context. + * This is needed to allow shared handling skcipher, ahash etc. + * @cb: completion callback. + * @backlog_head: list head to allow backlog maintenance. + * + * The hardware is limited in the maximum size of data that it can + * process from a single BD. Typically this is fairly large (32MB) + * but still requires the complexity of splitting the incoming + * skreq up into a number of elements complete with appropriate + * iv chaining. + */ +struct sec_request { + struct list_head elements; + int num_elements; + struct mutex lock; + struct sec_alg_tfm_ctx *tfm_ctx; + int len_in; + int len_out; + dma_addr_t dma_iv; + int err; + struct crypto_async_request *req_base; + void (*cb)(struct sec_bd_info *resp, struct crypto_async_request *req); + struct list_head backlog_head; +}; + +/** + * struct sec_request_el - A subpart of a request. + * @head: allow us to attach this to the list in the sec_request + * @req: hardware block descriptor corresponding to this request subpart + * @in: hardware sgl for input - virtual address + * @dma_in: hardware sgl for input - physical address + * @sgl_in: scatterlist for this request subpart + * @out: hardware sgl for output - virtual address + * @dma_out: hardware sgl for output - physical address + * @sgl_out: scatterlist for this request subpart + * @sec_req: The request which this subpart forms a part of + * @el_length: Number of bytes in this subpart. Needed to locate + * last ivsize chunk for iv chaining. + */ +struct sec_request_el { + struct list_head head; + struct sec_bd_info req; + struct sec_hw_sgl *in; + dma_addr_t dma_in; + struct scatterlist *sgl_in; + struct sec_hw_sgl *out; + dma_addr_t dma_out; + struct scatterlist *sgl_out; + struct sec_request *sec_req; + size_t el_length; +}; + +/** + * struct sec_queue - All the information about a HW queue + * @dev_info: The parent SEC device to which this queue belongs. + * @task_irq: Completion interrupt for the queue. + * @name: Human readable queue description also used as irq name. + * @ring: The several HW rings associated with one queue. + * @regs: The iomapped device registers + * @queue_id: Index of the queue used for naming and resource selection. + * @in_use: Flag to say if the queue is in use. + * @expected: The next expected element to finish assuming we were in order. + * @uprocessed: A bitmap to track which OoO elements are done but not handled. + * @softqueue: A software queue used when chaining requirements prevent direct + * use of the hardware queues. + * @havesoftqueue: A flag to say we have a queues - as we may need one for the + * current mode. + * @queuelock: Protect the soft queue from concurrent changes to avoid some + * potential loss of data races. + * @shadow: Pointers back to the shadow copy of the hardware ring element + * need because we can't store any context reference in the bd element. + */ +struct sec_queue { + struct sec_dev_info *dev_info; + int task_irq; + char name[SEC_NAME_SIZE]; + struct sec_queue_ring_cmd ring_cmd; + struct sec_queue_ring_cq ring_cq; + struct sec_queue_ring_db ring_db; + void __iomem *regs; + u32 queue_id; + bool in_use; + int expected; + + DECLARE_BITMAP(unprocessed, SEC_QUEUE_LEN); + DECLARE_KFIFO_PTR(softqueue, typeof(struct sec_request_el *)); + bool havesoftqueue; + struct mutex queuelock; + void *shadow[SEC_QUEUE_LEN]; +}; + +/** + * struct sec_hw_sge: Track each of the 64 element SEC HW SGL entries + * @buf: The IOV dma address for this entry. + * @len: Length of this IOV. + * @pad: Reserved space. + */ +struct sec_hw_sge { + dma_addr_t buf; + unsigned int len; + unsigned int pad; +}; + +/** + * struct sec_hw_sgl: One hardware SGL entry. + * @next_sgl: The next entry if we need to chain dma address. Null if last. + * @entry_sum_in_chain: The full count of SGEs - only matters for first SGL. + * @entry_sum_in_sgl: The number of SGEs in this SGL element. + * @flag: Unused in skciphers. + * @serial_num: Unsued in skciphers. + * @cpuid: Currently unused. + * @data_bytes_in_sgl: Count of bytes from all SGEs in this SGL. + * @next: Virtual address used to stash the next sgl - useful in completion. + * @reserved: A reserved field not currently used. + * @sge_entries: The (up to) 64 Scatter Gather Entries, representing IOVs. + * @node: Currently unused. + */ +struct sec_hw_sgl { + dma_addr_t next_sgl; + u16 entry_sum_in_chain; + u16 entry_sum_in_sgl; + u32 flag; + u64 serial_num; + u32 cpuid; + u32 data_bytes_in_sgl; + struct sec_hw_sgl *next; + u64 reserved; + struct sec_hw_sge sge_entries[SEC_MAX_SGE_NUM]; + u8 node[16]; +}; + +struct dma_pool; + +/** + * struct sec_dev_info: The full SEC unit comprising queues and processors. + * @sec_id: Index used to track which SEC this is when more than one is present. + * @num_saas: The number of backed processors enabled. + * @regs: iomapped register regions shared by whole SEC unit. + * @dev_lock: Protects concurrent queue allocation / freeing for the SEC. + * @queues: The 16 queues that this SEC instance provides. + * @dev: Device pointer. + * @hw_sgl_pool: DMA pool used to mimise mapping for the scatter gather lists. + */ +struct sec_dev_info { + int sec_id; + int num_saas; + void __iomem *regs[SEC_NUM_ADDR_REGIONS]; + struct mutex dev_lock; + int queues_in_use; + struct sec_queue queues[SEC_Q_NUM]; + struct device *dev; + struct dma_pool *hw_sgl_pool; +}; + +int sec_queue_send(struct sec_queue *queue, struct sec_bd_info *msg, void *ctx); +bool sec_queue_can_enqueue(struct sec_queue *queue, int num); +int sec_queue_stop_release(struct sec_queue *queue); +struct sec_queue *sec_queue_alloc_start_safe(void); +bool sec_queue_empty(struct sec_queue *queue); + +/* Algorithm specific elements from sec_algs.c */ +void sec_alg_callback(struct sec_bd_info *resp, void *ctx); +int sec_algs_register(void); +void sec_algs_unregister(void); + +#endif /* _SEC_DRV_H_ */ -- 2.16.2