diff options
Diffstat (limited to 'drivers/crypto')
-rw-r--r-- | drivers/crypto/Kconfig | 9 | ||||
-rw-r--r-- | drivers/crypto/Makefile | 2 | ||||
-rw-r--r-- | drivers/crypto/geode-aes.c | 36 | ||||
-rw-r--r-- | drivers/crypto/mv_cesa.c | 688 | ||||
-rw-r--r-- | drivers/crypto/mv_cesa.h | 40 | ||||
-rw-r--r-- | drivers/crypto/omap-sham.c | 1259 |
6 files changed, 1942 insertions, 92 deletions
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index b08403d..9073aa0 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -222,4 +222,13 @@ config CRYPTO_DEV_PPC4XX help This option allows you to have support for AMCC crypto acceleration. +config CRYPTO_DEV_OMAP_SHAM + tristate "Support for OMAP SHA1/MD5 hw accelerator" + depends on ARCH_OMAP2 || ARCH_OMAP3 + select CRYPTO_SHA1 + select CRYPTO_MD5 + help + OMAP processors have SHA1/MD5 hw accelerator. Select this if you + want to use the OMAP module for SHA1/MD5 algorithms. + endif # CRYPTO_HW diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile index 6ffcb3f..c9494e1 100644 --- a/drivers/crypto/Makefile +++ b/drivers/crypto/Makefile @@ -6,3 +6,5 @@ obj-$(CONFIG_CRYPTO_DEV_MV_CESA) += mv_cesa.o obj-$(CONFIG_CRYPTO_DEV_TALITOS) += talitos.o obj-$(CONFIG_CRYPTO_DEV_IXP4XX) += ixp4xx_crypto.o obj-$(CONFIG_CRYPTO_DEV_PPC4XX) += amcc/ +obj-$(CONFIG_CRYPTO_DEV_OMAP_SHAM) += omap-sham.o + diff --git a/drivers/crypto/geode-aes.c b/drivers/crypto/geode-aes.c index c7a5a43..09389dd 100644 --- a/drivers/crypto/geode-aes.c +++ b/drivers/crypto/geode-aes.c @@ -15,14 +15,14 @@ #include <crypto/algapi.h> #include <crypto/aes.h> -#include <asm/io.h> -#include <asm/delay.h> +#include <linux/io.h> +#include <linux/delay.h> #include "geode-aes.h" /* Static structures */ -static void __iomem * _iobase; +static void __iomem *_iobase; static spinlock_t lock; /* Write a 128 bit field (either a writable key or IV) */ @@ -30,7 +30,7 @@ static inline void _writefield(u32 offset, void *value) { int i; - for(i = 0; i < 4; i++) + for (i = 0; i < 4; i++) iowrite32(((u32 *) value)[i], _iobase + offset + (i * 4)); } @@ -39,7 +39,7 @@ static inline void _readfield(u32 offset, void *value) { int i; - for(i = 0; i < 4; i++) + for (i = 0; i < 4; i++) ((u32 *) value)[i] = ioread32(_iobase + offset + (i * 4)); } @@ -59,7 +59,7 @@ do_crypt(void *src, void *dst, int len, u32 flags) do { status = ioread32(_iobase + AES_INTR_REG); cpu_relax(); - } while(!(status & AES_INTRA_PENDING) && --counter); + } while (!(status & AES_INTRA_PENDING) && --counter); /* Clear the event */ iowrite32((status & 0xFF) | AES_INTRA_PENDING, _iobase + AES_INTR_REG); @@ -317,7 +317,7 @@ geode_cbc_decrypt(struct blkcipher_desc *desc, err = blkcipher_walk_virt(desc, &walk); op->iv = walk.iv; - while((nbytes = walk.nbytes)) { + while ((nbytes = walk.nbytes)) { op->src = walk.src.virt.addr, op->dst = walk.dst.virt.addr; op->mode = AES_MODE_CBC; @@ -349,7 +349,7 @@ geode_cbc_encrypt(struct blkcipher_desc *desc, err = blkcipher_walk_virt(desc, &walk); op->iv = walk.iv; - while((nbytes = walk.nbytes)) { + while ((nbytes = walk.nbytes)) { op->src = walk.src.virt.addr, op->dst = walk.dst.virt.addr; op->mode = AES_MODE_CBC; @@ -429,7 +429,7 @@ geode_ecb_decrypt(struct blkcipher_desc *desc, blkcipher_walk_init(&walk, dst, src, nbytes); err = blkcipher_walk_virt(desc, &walk); - while((nbytes = walk.nbytes)) { + while ((nbytes = walk.nbytes)) { op->src = walk.src.virt.addr, op->dst = walk.dst.virt.addr; op->mode = AES_MODE_ECB; @@ -459,7 +459,7 @@ geode_ecb_encrypt(struct blkcipher_desc *desc, blkcipher_walk_init(&walk, dst, src, nbytes); err = blkcipher_walk_virt(desc, &walk); - while((nbytes = walk.nbytes)) { + while ((nbytes = walk.nbytes)) { op->src = walk.src.virt.addr, op->dst = walk.dst.virt.addr; op->mode = AES_MODE_ECB; @@ -518,11 +518,12 @@ static int __devinit geode_aes_probe(struct pci_dev *dev, const struct pci_device_id *id) { int ret; - - if ((ret = pci_enable_device(dev))) + ret = pci_enable_device(dev); + if (ret) return ret; - if ((ret = pci_request_regions(dev, "geode-aes"))) + ret = pci_request_regions(dev, "geode-aes"); + if (ret) goto eenable; _iobase = pci_iomap(dev, 0, 0); @@ -537,13 +538,16 @@ geode_aes_probe(struct pci_dev *dev, const struct pci_device_id *id) /* Clear any pending activity */ iowrite32(AES_INTR_PENDING | AES_INTR_MASK, _iobase + AES_INTR_REG); - if ((ret = crypto_register_alg(&geode_alg))) + ret = crypto_register_alg(&geode_alg); + if (ret) goto eiomap; - if ((ret = crypto_register_alg(&geode_ecb_alg))) + ret = crypto_register_alg(&geode_ecb_alg); + if (ret) goto ealg; - if ((ret = crypto_register_alg(&geode_cbc_alg))) + ret = crypto_register_alg(&geode_cbc_alg); + if (ret) goto eecb; printk(KERN_NOTICE "geode-aes: GEODE AES engine enabled.\n"); diff --git a/drivers/crypto/mv_cesa.c b/drivers/crypto/mv_cesa.c index 6f29012..18a436c 100644 --- a/drivers/crypto/mv_cesa.c +++ b/drivers/crypto/mv_cesa.c @@ -15,8 +15,14 @@ #include <linux/platform_device.h> #include <linux/scatterlist.h> #include <linux/slab.h> +#include <crypto/internal/hash.h> +#include <crypto/sha.h> #include "mv_cesa.h" + +#define MV_CESA "MV-CESA:" +#define MAX_HW_HASH_SIZE 0xFFFF + /* * STM: * /---------------------------------------\ @@ -39,10 +45,12 @@ enum engine_status { * @dst_sg_it: sg iterator for dst * @sg_src_left: bytes left in src to process (scatter list) * @src_start: offset to add to src start position (scatter list) - * @crypt_len: length of current crypt process + * @crypt_len: length of current hw crypt/hash process + * @hw_nbytes: total bytes to process in hw for this request + * @copy_back: whether to copy data back (crypt) or not (hash) * @sg_dst_left: bytes left dst to process in this scatter list * @dst_start: offset to add to dst start position (scatter list) - * @total_req_bytes: total number of bytes processed (request). + * @hw_processed_bytes: number of bytes processed by hw (request). * * sg helper are used to iterate over the scatterlist. Since the size of the * SRAM may be less than the scatter size, this struct struct is used to keep @@ -51,15 +59,19 @@ enum engine_status { struct req_progress { struct sg_mapping_iter src_sg_it; struct sg_mapping_iter dst_sg_it; + void (*complete) (void); + void (*process) (int is_first); /* src mostly */ int sg_src_left; int src_start; int crypt_len; + int hw_nbytes; /* dst mostly */ + int copy_back; int sg_dst_left; int dst_start; - int total_req_bytes; + int hw_processed_bytes; }; struct crypto_priv { @@ -72,10 +84,12 @@ struct crypto_priv { spinlock_t lock; struct crypto_queue queue; enum engine_status eng_st; - struct ablkcipher_request *cur_req; + struct crypto_async_request *cur_req; struct req_progress p; int max_req_size; int sram_size; + int has_sha1; + int has_hmac_sha1; }; static struct crypto_priv *cpg; @@ -97,6 +111,31 @@ struct mv_req_ctx { int decrypt; }; +enum hash_op { + COP_SHA1, + COP_HMAC_SHA1 +}; + +struct mv_tfm_hash_ctx { + struct crypto_shash *fallback; + struct crypto_shash *base_hash; + u32 ivs[2 * SHA1_DIGEST_SIZE / 4]; + int count_add; + enum hash_op op; +}; + +struct mv_req_hash_ctx { + u64 count; + u32 state[SHA1_DIGEST_SIZE / 4]; + u8 buffer[SHA1_BLOCK_SIZE]; + int first_hash; /* marks that we don't have previous state */ + int last_chunk; /* marks that this is the 'final' request */ + int extra_bytes; /* unprocessed bytes in buffer */ + enum hash_op op; + int count_add; + struct scatterlist dummysg; +}; + static void compute_aes_dec_key(struct mv_ctx *ctx) { struct crypto_aes_ctx gen_aes_key; @@ -144,32 +183,51 @@ static int mv_setkey_aes(struct crypto_ablkcipher *cipher, const u8 *key, return 0; } -static void setup_data_in(struct ablkcipher_request *req) +static void copy_src_to_buf(struct req_progress *p, char *dbuf, int len) { int ret; - void *buf; + void *sbuf; + int copied = 0; - if (!cpg->p.sg_src_left) { - ret = sg_miter_next(&cpg->p.src_sg_it); - BUG_ON(!ret); - cpg->p.sg_src_left = cpg->p.src_sg_it.length; - cpg->p.src_start = 0; - } - - cpg->p.crypt_len = min(cpg->p.sg_src_left, cpg->max_req_size); - - buf = cpg->p.src_sg_it.addr; - buf += cpg->p.src_start; + while (1) { + if (!p->sg_src_left) { + ret = sg_miter_next(&p->src_sg_it); + BUG_ON(!ret); + p->sg_src_left = p->src_sg_it.length; + p->src_start = 0; + } - memcpy(cpg->sram + SRAM_DATA_IN_START, buf, cpg->p.crypt_len); + sbuf = p->src_sg_it.addr + p->src_start; + + if (p->sg_src_left <= len - copied) { + memcpy(dbuf + copied, sbuf, p->sg_src_left); + copied += p->sg_src_left; + p->sg_src_left = 0; + if (copied >= len) + break; + } else { + int copy_len = len - copied; + memcpy(dbuf + copied, sbuf, copy_len); + p->src_start += copy_len; + p->sg_src_left -= copy_len; + break; + } + } +} - cpg->p.sg_src_left -= cpg->p.crypt_len; - cpg->p.src_start += cpg->p.crypt_len; +static void setup_data_in(void) +{ + struct req_progress *p = &cpg->p; + int data_in_sram = + min(p->hw_nbytes - p->hw_processed_bytes, cpg->max_req_size); + copy_src_to_buf(p, cpg->sram + SRAM_DATA_IN_START + p->crypt_len, + data_in_sram - p->crypt_len); + p->crypt_len = data_in_sram; } static void mv_process_current_q(int first_block) { - struct ablkcipher_request *req = cpg->cur_req; + struct ablkcipher_request *req = ablkcipher_request_cast(cpg->cur_req); struct mv_ctx *ctx = crypto_tfm_ctx(req->base.tfm); struct mv_req_ctx *req_ctx = ablkcipher_request_ctx(req); struct sec_accel_config op; @@ -179,6 +237,7 @@ static void mv_process_current_q(int first_block) op.config = CFG_OP_CRYPT_ONLY | CFG_ENCM_AES | CFG_ENC_MODE_ECB; break; case COP_AES_CBC: + default: op.config = CFG_OP_CRYPT_ONLY | CFG_ENCM_AES | CFG_ENC_MODE_CBC; op.enc_iv = ENC_IV_POINT(SRAM_DATA_IV) | ENC_IV_BUF_POINT(SRAM_DATA_IV_BUF); @@ -211,7 +270,7 @@ static void mv_process_current_q(int first_block) ENC_P_DST(SRAM_DATA_OUT_START); op.enc_key_p = SRAM_DATA_KEY_P; - setup_data_in(req); + setup_data_in(); op.enc_len = cpg->p.crypt_len; memcpy(cpg->sram + SRAM_CONFIG, &op, sizeof(struct sec_accel_config)); @@ -228,91 +287,294 @@ static void mv_process_current_q(int first_block) static void mv_crypto_algo_completion(void) { - struct ablkcipher_request *req = cpg->cur_req; + struct ablkcipher_request *req = ablkcipher_request_cast(cpg->cur_req); struct mv_req_ctx *req_ctx = ablkcipher_request_ctx(req); + sg_miter_stop(&cpg->p.src_sg_it); + sg_miter_stop(&cpg->p.dst_sg_it); + if (req_ctx->op != COP_AES_CBC) return ; memcpy(req->info, cpg->sram + SRAM_DATA_IV_BUF, 16); } +static void mv_process_hash_current(int first_block) +{ + struct ahash_request *req = ahash_request_cast(cpg->cur_req); + struct mv_req_hash_ctx *req_ctx = ahash_request_ctx(req); + struct req_progress *p = &cpg->p; + struct sec_accel_config op = { 0 }; + int is_last; + + switch (req_ctx->op) { + case COP_SHA1: + default: + op.config = CFG_OP_MAC_ONLY | CFG_MACM_SHA1; + break; + case COP_HMAC_SHA1: + op.config = CFG_OP_MAC_ONLY | CFG_MACM_HMAC_SHA1; + break; + } + + op.mac_src_p = + MAC_SRC_DATA_P(SRAM_DATA_IN_START) | MAC_SRC_TOTAL_LEN((u32) + req_ctx-> + count); + + setup_data_in(); + + op.mac_digest = + MAC_DIGEST_P(SRAM_DIGEST_BUF) | MAC_FRAG_LEN(p->crypt_len); + op.mac_iv = + MAC_INNER_IV_P(SRAM_HMAC_IV_IN) | + MAC_OUTER_IV_P(SRAM_HMAC_IV_OUT); + + is_last = req_ctx->last_chunk + && (p->hw_processed_bytes + p->crypt_len >= p->hw_nbytes) + && (req_ctx->count <= MAX_HW_HASH_SIZE); + if (req_ctx->first_hash) { + if (is_last) + op.config |= CFG_NOT_FRAG; + else + op.config |= CFG_FIRST_FRAG; + + req_ctx->first_hash = 0; + } else { + if (is_last) + op.config |= CFG_LAST_FRAG; + else + op.config |= CFG_MID_FRAG; + } + + memcpy(cpg->sram + SRAM_CONFIG, &op, sizeof(struct sec_accel_config)); + + writel(SRAM_CONFIG, cpg->reg + SEC_ACCEL_DESC_P0); + /* GO */ + writel(SEC_CMD_EN_SEC_ACCL0, cpg->reg + SEC_ACCEL_CMD); + + /* + * XXX: add timer if the interrupt does not occur for some mystery + * reason + */ +} + +static inline int mv_hash_import_sha1_ctx(const struct mv_req_hash_ctx *ctx, + struct shash_desc *desc) +{ + int i; + struct sha1_state shash_state; + + shash_state.count = ctx->count + ctx->count_add; + for (i = 0; i < 5; i++) + shash_state.state[i] = ctx->state[i]; + memcpy(shash_state.buffer, ctx->buffer, sizeof(shash_state.buffer)); + return crypto_shash_import(desc, &shash_state); +} + +static int mv_hash_final_fallback(struct ahash_request *req) +{ + const struct mv_tfm_hash_ctx *tfm_ctx = crypto_tfm_ctx(req->base.tfm); + struct mv_req_hash_ctx *req_ctx = ahash_request_ctx(req); + struct { + struct shash_desc shash; + char ctx[crypto_shash_descsize(tfm_ctx->fallback)]; + } desc; + int rc; + + desc.shash.tfm = tfm_ctx->fallback; + desc.shash.flags = CRYPTO_TFM_REQ_MAY_SLEEP; + if (unlikely(req_ctx->first_hash)) { + crypto_shash_init(&desc.shash); + crypto_shash_update(&desc.shash, req_ctx->buffer, + req_ctx->extra_bytes); + } else { + /* only SHA1 for now.... + */ + rc = mv_hash_import_sha1_ctx(req_ctx, &desc.shash); + if (rc) + goto out; + } + rc = crypto_shash_final(&desc.shash, req->result); +out: + return rc; +} + +static void mv_hash_algo_completion(void) +{ + struct ahash_request *req = ahash_request_cast(cpg->cur_req); + struct mv_req_hash_ctx *ctx = ahash_request_ctx(req); + + if (ctx->extra_bytes) + copy_src_to_buf(&cpg->p, ctx->buffer, ctx->extra_bytes); + sg_miter_stop(&cpg->p.src_sg_it); + + ctx->state[0] = readl(cpg->reg + DIGEST_INITIAL_VAL_A); + ctx->state[1] = readl(cpg->reg + DIGEST_INITIAL_VAL_B); + ctx->state[2] = readl(cpg->reg + DIGEST_INITIAL_VAL_C); + ctx->state[3] = readl(cpg->reg + DIGEST_INITIAL_VAL_D); + ctx->state[4] = readl(cpg->reg + DIGEST_INITIAL_VAL_E); + + if (likely(ctx->last_chunk)) { + if (likely(ctx->count <= MAX_HW_HASH_SIZE)) { + memcpy(req->result, cpg->sram + SRAM_DIGEST_BUF, + crypto_ahash_digestsize(crypto_ahash_reqtfm + (req))); + } else + mv_hash_final_fallback(req); + } +} + static void dequeue_complete_req(void) { - struct ablkcipher_request *req = cpg->cur_req; + struct crypto_async_request *req = cpg->cur_req; void *buf; int ret; + cpg->p.hw_processed_bytes += cpg->p.crypt_len; + if (cpg->p.copy_back) { + int need_copy_len = cpg->p.crypt_len; + int sram_offset = 0; + do { + int dst_copy; + + if (!cpg->p.sg_dst_left) { + ret = sg_miter_next(&cpg->p.dst_sg_it); + BUG_ON(!ret); + cpg->p.sg_dst_left = cpg->p.dst_sg_it.length; + cpg->p.dst_start = 0; + } - cpg->p.total_req_bytes += cpg->p.crypt_len; - do { - int dst_copy; - - if (!cpg->p.sg_dst_left) { - ret = sg_miter_next(&cpg->p.dst_sg_it); - BUG_ON(!ret); - cpg->p.sg_dst_left = cpg->p.dst_sg_it.length; - cpg->p.dst_start = 0; - } - - buf = cpg->p.dst_sg_it.addr; - buf += cpg->p.dst_start; + buf = cpg->p.dst_sg_it.addr; + buf += cpg->p.dst_start; - dst_copy = min(cpg->p.crypt_len, cpg->p.sg_dst_left); + dst_copy = min(need_copy_len, cpg->p.sg_dst_left); - memcpy(buf, cpg->sram + SRAM_DATA_OUT_START, dst_copy); + memcpy(buf, + cpg->sram + SRAM_DATA_OUT_START + sram_offset, + dst_copy); + sram_offset += dst_copy; + cpg->p.sg_dst_left -= dst_copy; + need_copy_len -= dst_copy; + cpg->p.dst_start += dst_copy; + } while (need_copy_len > 0); + } - cpg->p.sg_dst_left -= dst_copy; - cpg->p.crypt_len -= dst_copy; - cpg->p.dst_start += dst_copy; - } while (cpg->p.crypt_len > 0); + cpg->p.crypt_len = 0; BUG_ON(cpg->eng_st != ENGINE_W_DEQUEUE); - if (cpg->p.total_req_bytes < req->nbytes) { + if (cpg->p.hw_processed_bytes < cpg->p.hw_nbytes) { /* process next scatter list entry */ cpg->eng_st = ENGINE_BUSY; - mv_process_current_q(0); + cpg->p.process(0); } else { - sg_miter_stop(&cpg->p.src_sg_it); - sg_miter_stop(&cpg->p.dst_sg_it); - mv_crypto_algo_completion(); + cpg->p.complete(); cpg->eng_st = ENGINE_IDLE; - req->base.complete(&req->base, 0); + local_bh_disable(); + req->complete(req, 0); + local_bh_enable(); } } static int count_sgs(struct scatterlist *sl, unsigned int total_bytes) { int i = 0; - - do { - total_bytes -= sl[i].length; - i++; - - } while (total_bytes > 0); + size_t cur_len; + + while (1) { + cur_len = sl[i].length; + ++i; + if (total_bytes > cur_len) + total_bytes -= cur_len; + else + break; + } return i; } -static void mv_enqueue_new_req(struct ablkcipher_request *req) +static void mv_start_new_crypt_req(struct ablkcipher_request *req) { + struct req_progress *p = &cpg->p; int num_sgs; - cpg->cur_req = req; - memset(&cpg->p, 0, sizeof(struct req_progress)); + cpg->cur_req = &req->base; + memset(p, 0, sizeof(struct req_progress)); + p->hw_nbytes = req->nbytes; + p->complete = mv_crypto_algo_completion; + p->process = mv_process_current_q; + p->copy_back = 1; num_sgs = count_sgs(req->src, req->nbytes); - sg_miter_start(&cpg->p.src_sg_it, req->src, num_sgs, SG_MITER_FROM_SG); + sg_miter_start(&p->src_sg_it, req->src, num_sgs, SG_MITER_FROM_SG); num_sgs = count_sgs(req->dst, req->nbytes); - sg_miter_start(&cpg->p.dst_sg_it, req->dst, num_sgs, SG_MITER_TO_SG); + sg_miter_start(&p->dst_sg_it, req->dst, num_sgs, SG_MITER_TO_SG); + mv_process_current_q(1); } +static void mv_start_new_hash_req(struct ahash_request *req) +{ + struct req_progress *p = &cpg->p; + struct mv_req_hash_ctx *ctx = ahash_request_ctx(req); + const struct mv_tfm_hash_ctx *tfm_ctx = crypto_tfm_ctx(req->base.tfm); + int num_sgs, hw_bytes, old_extra_bytes, rc; + cpg->cur_req = &req->base; + memset(p, 0, sizeof(struct req_progress)); + hw_bytes = req->nbytes + ctx->extra_bytes; + old_extra_bytes = ctx->extra_bytes; + + if (unlikely(ctx->extra_bytes)) { + memcpy(cpg->sram + SRAM_DATA_IN_START, ctx->buffer, + ctx->extra_bytes); + p->crypt_len = ctx->extra_bytes; + } + + memcpy(cpg->sram + SRAM_HMAC_IV_IN, tfm_ctx->ivs, sizeof(tfm_ctx->ivs)); + + if (unlikely(!ctx->first_hash)) { + writel(ctx->state[0], cpg->reg + DIGEST_INITIAL_VAL_A); + writel(ctx->state[1], cpg->reg + DIGEST_INITIAL_VAL_B); + writel(ctx->state[2], cpg->reg + DIGEST_INITIAL_VAL_C); + writel(ctx->state[3], cpg->reg + DIGEST_INITIAL_VAL_D); + writel(ctx->state[4], cpg->reg + DIGEST_INITIAL_VAL_E); + } + + ctx->extra_bytes = hw_bytes % SHA1_BLOCK_SIZE; + if (ctx->extra_bytes != 0 + && (!ctx->last_chunk || ctx->count > MAX_HW_HASH_SIZE)) + hw_bytes -= ctx->extra_bytes; + else + ctx->extra_bytes = 0; + + num_sgs = count_sgs(req->src, req->nbytes); + sg_miter_start(&p->src_sg_it, req->src, num_sgs, SG_MITER_FROM_SG); + + if (hw_bytes) { + p->hw_nbytes = hw_bytes; + p->complete = mv_hash_algo_completion; + p->process = mv_process_hash_current; + + mv_process_hash_current(1); + } else { + copy_src_to_buf(p, ctx->buffer + old_extra_bytes, + ctx->extra_bytes - old_extra_bytes); + sg_miter_stop(&p->src_sg_it); + if (ctx->last_chunk) + rc = mv_hash_final_fallback(req); + else + rc = 0; + cpg->eng_st = ENGINE_IDLE; + local_bh_disable(); + req->base.complete(&req->base, rc); + local_bh_enable(); + } +} + static int queue_manag(void *data) { cpg->eng_st = ENGINE_IDLE; do { - struct ablkcipher_request *req; struct crypto_async_request *async_req = NULL; struct crypto_async_request *backlog; @@ -338,9 +600,18 @@ static int queue_manag(void *data) } if (async_req) { - req = container_of(async_req, - struct ablkcipher_request, base); - mv_enqueue_new_req(req); + if (async_req->tfm->__crt_alg->cra_type != + &crypto_ahash_type) { + struct ablkcipher_request *req = + container_of(async_req, + struct ablkcipher_request, + base); + mv_start_new_crypt_req(req); + } else { + struct ahash_request *req = + ahash_request_cast(async_req); + mv_start_new_hash_req(req); + } async_req = NULL; } @@ -350,13 +621,13 @@ static int queue_manag(void *data) return 0; } -static int mv_handle_req(struct ablkcipher_request *req) +static int mv_handle_req(struct crypto_async_request *req) { unsigned long flags; int ret; spin_lock_irqsave(&cpg->lock, flags); - ret = ablkcipher_enqueue_request(&cpg->queue, req); + ret = crypto_enqueue_request(&cpg->queue, req); spin_unlock_irqrestore(&cpg->lock, flags); wake_up_process(cpg->queue_th); return ret; @@ -369,7 +640,7 @@ static int mv_enc_aes_ecb(struct ablkcipher_request *req) req_ctx->op = COP_AES_ECB; req_ctx->decrypt = 0; - return mv_handle_req(req); + return mv_handle_req(&req->base); } static int mv_dec_aes_ecb(struct ablkcipher_request *req) @@ -381,7 +652,7 @@ static int mv_dec_aes_ecb(struct ablkcipher_request *req) req_ctx->decrypt = 1; compute_aes_dec_key(ctx); - return mv_handle_req(req); + return mv_handle_req(&req->base); } static int mv_enc_aes_cbc(struct ablkcipher_request *req) @@ -391,7 +662,7 @@ static int mv_enc_aes_cbc(struct ablkcipher_request *req) req_ctx->op = COP_AES_CBC; req_ctx->decrypt = 0; - return mv_handle_req(req); + return mv_handle_req(&req->base); } static int mv_dec_aes_cbc(struct ablkcipher_request *req) @@ -403,7 +674,7 @@ static int mv_dec_aes_cbc(struct ablkcipher_request *req) req_ctx->decrypt = 1; compute_aes_dec_key(ctx); - return mv_handle_req(req); + return mv_handle_req(&req->base); } static int mv_cra_init(struct crypto_tfm *tfm) @@ -412,6 +683,215 @@ static int mv_cra_init(struct crypto_tfm *tfm) return 0; } +static void mv_init_hash_req_ctx(struct mv_req_hash_ctx *ctx, int op, + int is_last, unsigned int req_len, + int count_add) +{ + memset(ctx, 0, sizeof(*ctx)); + ctx->op = op; + ctx->count = req_len; + ctx->first_hash = 1; + ctx->last_chunk = is_last; + ctx->count_add = count_add; +} + +static void mv_update_hash_req_ctx(struct mv_req_hash_ctx *ctx, int is_last, + unsigned req_len) +{ + ctx->last_chunk = is_last; + ctx->count += req_len; +} + +static int mv_hash_init(struct ahash_request *req) +{ + const struct mv_tfm_hash_ctx *tfm_ctx = crypto_tfm_ctx(req->base.tfm); + mv_init_hash_req_ctx(ahash_request_ctx(req), tfm_ctx->op, 0, 0, + tfm_ctx->count_add); + return 0; +} + +static int mv_hash_update(struct ahash_request *req) +{ + if (!req->nbytes) + return 0; + + mv_update_hash_req_ctx(ahash_request_ctx(req), 0, req->nbytes); + return mv_handle_req(&req->base); +} + +static int mv_hash_final(struct ahash_request *req) +{ + struct mv_req_hash_ctx *ctx = ahash_request_ctx(req); + /* dummy buffer of 4 bytes */ + sg_init_one(&ctx->dummysg, ctx->buffer, 4); + /* I think I'm allowed to do that... */ + ahash_request_set_crypt(req, &ctx->dummysg, req->result, 0); + mv_update_hash_req_ctx(ctx, 1, 0); + return mv_handle_req(&req->base); +} + +static int mv_hash_finup(struct ahash_request *req) +{ + if (!req->nbytes) + return mv_hash_final(req); + + mv_update_hash_req_ctx(ahash_request_ctx(req), 1, req->nbytes); + return mv_handle_req(&req->base); +} + +static int mv_hash_digest(struct ahash_request *req) +{ + const struct mv_tfm_hash_ctx *tfm_ctx = crypto_tfm_ctx(req->base.tfm); + mv_init_hash_req_ctx(ahash_request_ctx(req), tfm_ctx->op, 1, + req->nbytes, tfm_ctx->count_add); + return mv_handle_req(&req->base); +} + +static void mv_hash_init_ivs(struct mv_tfm_hash_ctx *ctx, const void *istate, + const void *ostate) +{ + const struct sha1_state *isha1_state = istate, *osha1_state = ostate; + int i; + for (i = 0; i < 5; i++) { + ctx->ivs[i] = cpu_to_be32(isha1_state->state[i]); + ctx->ivs[i + 5] = cpu_to_be32(osha1_state->state[i]); + } +} + +static int mv_hash_setkey(struct crypto_ahash *tfm, const u8 * key, + unsigned int keylen) +{ + int rc; + struct mv_tfm_hash_ctx *ctx = crypto_tfm_ctx(&tfm->base); + int bs, ds, ss; + + if (!ctx->base_hash) + return 0; + + rc = crypto_shash_setkey(ctx->fallback, key, keylen); + if (rc) + return rc; + + /* Can't see a way to extract the ipad/opad from the fallback tfm + so I'm basically copying code from the hmac module */ + bs = crypto_shash_blocksize(ctx->base_hash); + ds = crypto_shash_digestsize(ctx->base_hash); + ss = crypto_shash_statesize(ctx->base_hash); + + { + struct { + struct shash_desc shash; + char ctx[crypto_shash_descsize(ctx->base_hash)]; + } desc; + unsigned int i; + char ipad[ss]; + char opad[ss]; + + desc.shash.tfm = ctx->base_hash; + desc.shash.flags = crypto_shash_get_flags(ctx->base_hash) & + CRYPTO_TFM_REQ_MAY_SLEEP; + + if (keylen > bs) { + int err; + + err = + crypto_shash_digest(&desc.shash, key, keylen, ipad); + if (err) + return err; + + keylen = ds; + } else + memcpy(ipad, key, keylen); + + memset(ipad + keylen, 0, bs - keylen); + memcpy(opad, ipad, bs); + + for (i = 0; i < bs; i++) { + ipad[i] ^= 0x36; + opad[i] ^= 0x5c; + } + + rc = crypto_shash_init(&desc.shash) ? : + crypto_shash_update(&desc.shash, ipad, bs) ? : + crypto_shash_export(&desc.shash, ipad) ? : + crypto_shash_init(&desc.shash) ? : + crypto_shash_update(&desc.shash, opad, bs) ? : + crypto_shash_export(&desc.shash, opad); + + if (rc == 0) + mv_hash_init_ivs(ctx, ipad, opad); + + return rc; + } +} + +static int mv_cra_hash_init(struct crypto_tfm *tfm, const char *base_hash_name, + enum hash_op op, int count_add) +{ + const char *fallback_driver_name = tfm->__crt_alg->cra_name; + struct mv_tfm_hash_ctx *ctx = crypto_tfm_ctx(tfm); + struct crypto_shash *fallback_tfm = NULL; + struct crypto_shash *base_hash = NULL; + int err = -ENOMEM; + + ctx->op = op; + ctx->count_add = count_add; + + /* Allocate a fallback and abort if it failed. */ + fallback_tfm = crypto_alloc_shash(fallback_driver_name, 0, + CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(fallback_tfm)) { + printk(KERN_WARNING MV_CESA + "Fallback driver '%s' could not be loaded!\n", + fallback_driver_name); + err = PTR_ERR(fallback_tfm); + goto out; + } + ctx->fallback = fallback_tfm; + + if (base_hash_name) { + /* Allocate a hash to compute the ipad/opad of hmac. */ + base_hash = crypto_alloc_shash(base_hash_name, 0, + CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(base_hash)) { + printk(KERN_WARNING MV_CESA + "Base driver '%s' could not be loaded!\n", + base_hash_name); + err = PTR_ERR(fallback_tfm); + goto err_bad_base; + } + } + ctx->base_hash = base_hash; + + crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm), + sizeof(struct mv_req_hash_ctx) + + crypto_shash_descsize(ctx->fallback)); + return 0; +err_bad_base: + crypto_free_shash(fallback_tfm); +out: + return err; +} + +static void mv_cra_hash_exit(struct crypto_tfm *tfm) +{ + struct mv_tfm_hash_ctx *ctx = crypto_tfm_ctx(tfm); + + crypto_free_shash(ctx->fallback); + if (ctx->base_hash) + crypto_free_shash(ctx->base_hash); +} + +static int mv_cra_hash_sha1_init(struct crypto_tfm *tfm) +{ + return mv_cra_hash_init(tfm, NULL, COP_SHA1, 0); +} + +static int mv_cra_hash_hmac_sha1_init(struct crypto_tfm *tfm) +{ + return mv_cra_hash_init(tfm, "sha1", COP_HMAC_SHA1, SHA1_BLOCK_SIZE); +} + irqreturn_t crypto_int(int irq, void *priv) { u32 val; @@ -474,6 +954,53 @@ struct crypto_alg mv_aes_alg_cbc = { }, }; +struct ahash_alg mv_sha1_alg = { + .init = mv_hash_init, + .update = mv_hash_update, + .final = mv_hash_final, + .finup = mv_hash_finup, + .digest = mv_hash_digest, + .halg = { + .digestsize = SHA1_DIGEST_SIZE, + .base = { + .cra_name = "sha1", + .cra_driver_name = "mv-sha1", + .cra_priority = 300, + .cra_flags = + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct mv_tfm_hash_ctx), + .cra_init = mv_cra_hash_sha1_init, + .cra_exit = mv_cra_hash_exit, + .cra_module = THIS_MODULE, + } + } +}; + +struct ahash_alg mv_hmac_sha1_alg = { + .init = mv_hash_init, + .update = mv_hash_update, + .final = mv_hash_final, + .finup = mv_hash_finup, + .digest = mv_hash_digest, + .setkey = mv_hash_setkey, + .halg = { + .digestsize = SHA1_DIGEST_SIZE, + .base = { + .cra_name = "hmac(sha1)", + .cra_driver_name = "mv-hmac-sha1", + .cra_priority = 300, + .cra_flags = + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct mv_tfm_hash_ctx), + .cra_init = mv_cra_hash_hmac_sha1_init, + .cra_exit = mv_cra_hash_exit, + .cra_module = THIS_MODULE, + } + } +}; + static int mv_probe(struct platform_device *pdev) { struct crypto_priv *cp; @@ -482,7 +1009,7 @@ static int mv_probe(struct platform_device *pdev) int ret; if (cpg) { - printk(KERN_ERR "Second crypto dev?\n"); + printk(KERN_ERR MV_CESA "Second crypto dev?\n"); return -EEXIST; } @@ -546,6 +1073,21 @@ static int mv_probe(struct platform_device *pdev) ret = crypto_register_alg(&mv_aes_alg_cbc); if (ret) goto err_unreg_ecb; + + ret = crypto_register_ahash(&mv_sha1_alg); + if (ret == 0) + cpg->has_sha1 = 1; + else + printk(KERN_WARNING MV_CESA "Could not register sha1 driver\n"); + + ret = crypto_register_ahash(&mv_hmac_sha1_alg); + if (ret == 0) { + cpg->has_hmac_sha1 = 1; + } else { + printk(KERN_WARNING MV_CESA + "Could not register hmac-sha1 driver\n"); + } + return 0; err_unreg_ecb: crypto_unregister_alg(&mv_aes_alg_ecb); @@ -570,6 +1112,10 @@ static int mv_remove(struct platform_device *pdev) crypto_unregister_alg(&mv_aes_alg_ecb); crypto_unregister_alg(&mv_aes_alg_cbc); + if (cp->has_sha1) + crypto_unregister_ahash(&mv_sha1_alg); + if (cp->has_hmac_sha1) + crypto_unregister_ahash(&mv_hmac_sha1_alg); kthread_stop(cp->queue_th); free_irq(cp->irq, cp); memset(cp->sram, 0, cp->sram_size); diff --git a/drivers/crypto/mv_cesa.h b/drivers/crypto/mv_cesa.h index c3e25d3..08fcb11 100644 --- a/drivers/crypto/mv_cesa.h +++ b/drivers/crypto/mv_cesa.h @@ -1,6 +1,10 @@ #ifndef __MV_CRYPTO_H__ #define DIGEST_INITIAL_VAL_A 0xdd00 +#define DIGEST_INITIAL_VAL_B 0xdd04 +#define DIGEST_INITIAL_VAL_C 0xdd08 +#define DIGEST_INITIAL_VAL_D 0xdd0c +#define DIGEST_INITIAL_VAL_E 0xdd10 #define DES_CMD_REG 0xdd58 #define SEC_ACCEL_CMD 0xde00 @@ -70,6 +74,10 @@ struct sec_accel_config { #define CFG_AES_LEN_128 (0 << 24) #define CFG_AES_LEN_192 (1 << 24) #define CFG_AES_LEN_256 (2 << 24) +#define CFG_NOT_FRAG (0 << 30) +#define CFG_FIRST_FRAG (1 << 30) +#define CFG_LAST_FRAG (2 << 30) +#define CFG_MID_FRAG (3 << 30) u32 enc_p; #define ENC_P_SRC(x) (x) @@ -90,7 +98,11 @@ struct sec_accel_config { #define MAC_SRC_TOTAL_LEN(x) ((x) << 16) u32 mac_digest; +#define MAC_DIGEST_P(x) (x) +#define MAC_FRAG_LEN(x) ((x) << 16) u32 mac_iv; +#define MAC_INNER_IV_P(x) (x) +#define MAC_OUTER_IV_P(x) ((x) << 16) }__attribute__ ((packed)); /* * /-----------\ 0 @@ -101,19 +113,37 @@ struct sec_accel_config { * | IV IN | 4 * 4 * |-----------| 0x40 (inplace) * | IV BUF | 4 * 4 - * |-----------| 0x50 + * |-----------| 0x80 * | DATA IN | 16 * x (max ->max_req_size) - * |-----------| 0x50 (inplace operation) + * |-----------| 0x80 (inplace operation) * | DATA OUT | 16 * x (max ->max_req_size) * \-----------/ SRAM size */ + + /* Hashing memory map: + * /-----------\ 0 + * | ACCEL CFG | 4 * 8 + * |-----------| 0x20 + * | Inner IV | 5 * 4 + * |-----------| 0x34 + * | Outer IV | 5 * 4 + * |-----------| 0x48 + * | Output BUF| 5 * 4 + * |-----------| 0x80 + * | DATA IN | 64 * x (max ->max_req_size) + * \-----------/ SRAM size + */ #define SRAM_CONFIG 0x00 #define SRAM_DATA_KEY_P 0x20 #define SRAM_DATA_IV 0x40 #define SRAM_DATA_IV_BUF 0x40 -#define SRAM_DATA_IN_START 0x50 -#define SRAM_DATA_OUT_START 0x50 +#define SRAM_DATA_IN_START 0x80 +#define SRAM_DATA_OUT_START 0x80 + +#define SRAM_HMAC_IV_IN 0x20 +#define SRAM_HMAC_IV_OUT 0x34 +#define SRAM_DIGEST_BUF 0x48 -#define SRAM_CFG_SPACE 0x50 +#define SRAM_CFG_SPACE 0x80 #endif diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c new file mode 100644 index 0000000..8b03433 --- /dev/null +++ b/drivers/crypto/omap-sham.c @@ -0,0 +1,1259 @@ +/* + * Cryptographic API. + * + * Support for OMAP SHA1/MD5 HW acceleration. + * + * Copyright (c) 2010 Nokia Corporation + * Author: Dmitry Kasatkin <dmitry.kasatkin@nokia.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + * + * Some ideas are from old omap-sha1-md5.c driver. + */ + +#define pr_fmt(fmt) "%s: " fmt, __func__ + +#include <linux/version.h> +#include <linux/err.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/clk.h> +#include <linux/irq.h> +#include <linux/io.h> +#include <linux/platform_device.h> +#include <linux/scatterlist.h> +#include <linux/dma-mapping.h> +#include <linux/delay.h> +#include <linux/crypto.h> +#include <linux/cryptohash.h> +#include <crypto/scatterwalk.h> +#include <crypto/algapi.h> +#include <crypto/sha.h> +#include <crypto/hash.h> +#include <crypto/internal/hash.h> + +#include <plat/cpu.h> +#include <plat/dma.h> +#include <mach/irqs.h> + +#define SHA_REG_DIGEST(x) (0x00 + ((x) * 0x04)) +#define SHA_REG_DIN(x) (0x1C + ((x) * 0x04)) + +#define SHA1_MD5_BLOCK_SIZE SHA1_BLOCK_SIZE +#define MD5_DIGEST_SIZE 16 + +#define SHA_REG_DIGCNT 0x14 + +#define SHA_REG_CTRL 0x18 +#define SHA_REG_CTRL_LENGTH (0xFFFFFFFF << 5) +#define SHA_REG_CTRL_CLOSE_HASH (1 << 4) +#define SHA_REG_CTRL_ALGO_CONST (1 << 3) +#define SHA_REG_CTRL_ALGO (1 << 2) +#define SHA_REG_CTRL_INPUT_READY (1 << 1) +#define SHA_REG_CTRL_OUTPUT_READY (1 << 0) + +#define SHA_REG_REV 0x5C +#define SHA_REG_REV_MAJOR 0xF0 +#define SHA_REG_REV_MINOR 0x0F + +#define SHA_REG_MASK 0x60 +#define SHA_REG_MASK_DMA_EN (1 << 3) +#define SHA_REG_MASK_IT_EN (1 << 2) +#define SHA_REG_MASK_SOFTRESET (1 << 1) +#define SHA_REG_AUTOIDLE (1 << 0) + +#define SHA_REG_SYSSTATUS 0x64 +#define SHA_REG_SYSSTATUS_RESETDONE (1 << 0) + +#define DEFAULT_TIMEOUT_INTERVAL HZ + +#define FLAGS_FIRST 0x0001 +#define FLAGS_FINUP 0x0002 +#define FLAGS_FINAL 0x0004 +#define FLAGS_FAST 0x0008 +#define FLAGS_SHA1 0x0010 +#define FLAGS_DMA_ACTIVE 0x0020 +#define FLAGS_OUTPUT_READY 0x0040 +#define FLAGS_CLEAN 0x0080 +#define FLAGS_INIT 0x0100 +#define FLAGS_CPU 0x0200 +#define FLAGS_HMAC 0x0400 + +/* 3rd byte */ +#define FLAGS_BUSY 16 + +#define OP_UPDATE 1 +#define OP_FINAL 2 + +struct omap_sham_dev; + +struct omap_sham_reqctx { + struct omap_sham_dev *dd; + unsigned long flags; + unsigned long op; + + size_t digcnt; + u8 *buffer; + size_t bufcnt; + size_t buflen; + dma_addr_t dma_addr; + + /* walk state */ + struct scatterlist *sg; + unsigned int offset; /* offset in current sg */ + unsigned int total; /* total request */ +}; + +struct omap_sham_hmac_ctx { + struct crypto_shash *shash; + u8 ipad[SHA1_MD5_BLOCK_SIZE]; + u8 opad[SHA1_MD5_BLOCK_SIZE]; +}; + +struct omap_sham_ctx { + struct omap_sham_dev *dd; + + unsigned long flags; + + /* fallback stuff */ + struct crypto_shash *fallback; + + struct omap_sham_hmac_ctx base[0]; +}; + +#define OMAP_SHAM_QUEUE_LENGTH 1 + +struct omap_sham_dev { + struct list_head list; + unsigned long phys_base; + struct device *dev; + void __iomem *io_base; + int irq; + struct clk *iclk; + spinlock_t lock; + int dma; + int dma_lch; + struct tasklet_struct done_task; + struct tasklet_struct queue_task; + + unsigned long flags; + struct crypto_queue queue; + struct ahash_request *req; +}; + +struct omap_sham_drv { + struct list_head dev_list; + spinlock_t lock; + unsigned long flags; +}; + +static struct omap_sham_drv sham = { + .dev_list = LIST_HEAD_INIT(sham.dev_list), + .lock = __SPIN_LOCK_UNLOCKED(sham.lock), +}; + +static inline u32 omap_sham_read(struct omap_sham_dev *dd, u32 offset) +{ + return __raw_readl(dd->io_base + offset); +} + +static inline void omap_sham_write(struct omap_sham_dev *dd, + u32 offset, u32 value) +{ + __raw_writel(value, dd->io_base + offset); +} + +static inline void omap_sham_write_mask(struct omap_sham_dev *dd, u32 address, + u32 value, u32 mask) +{ + u32 val; + + val = omap_sham_read(dd, address); + val &= ~mask; + val |= value; + omap_sham_write(dd, address, val); +} + +static inline int omap_sham_wait(struct omap_sham_dev *dd, u32 offset, u32 bit) +{ + unsigned long timeout = jiffies + DEFAULT_TIMEOUT_INTERVAL; + + while (!(omap_sham_read(dd, offset) & bit)) { + if (time_is_before_jiffies(timeout)) + return -ETIMEDOUT; + } + + return 0; +} + +static void omap_sham_copy_hash(struct ahash_request *req, int out) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + u32 *hash = (u32 *)req->result; + int i; + + if (likely(ctx->flags & FLAGS_SHA1)) { + /* SHA1 results are in big endian */ + for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(u32); i++) + if (out) + hash[i] = be32_to_cpu(omap_sham_read(ctx->dd, + SHA_REG_DIGEST(i))); + else + omap_sham_write(ctx->dd, SHA_REG_DIGEST(i), + cpu_to_be32(hash[i])); + } else { + /* MD5 results are in little endian */ + for (i = 0; i < MD5_DIGEST_SIZE / sizeof(u32); i++) + if (out) + hash[i] = le32_to_cpu(omap_sham_read(ctx->dd, + SHA_REG_DIGEST(i))); + else + omap_sham_write(ctx->dd, SHA_REG_DIGEST(i), + cpu_to_le32(hash[i])); + } +} + +static int omap_sham_write_ctrl(struct omap_sham_dev *dd, size_t length, + int final, int dma) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req); + u32 val = length << 5, mask; + + if (unlikely(!ctx->digcnt)) { + + clk_enable(dd->iclk); + + if (!(dd->flags & FLAGS_INIT)) { + omap_sham_write_mask(dd, SHA_REG_MASK, + SHA_REG_MASK_SOFTRESET, SHA_REG_MASK_SOFTRESET); + + if (omap_sham_wait(dd, SHA_REG_SYSSTATUS, + SHA_REG_SYSSTATUS_RESETDONE)) + return -ETIMEDOUT; + + dd->flags |= FLAGS_INIT; + } + } else { + omap_sham_write(dd, SHA_REG_DIGCNT, ctx->digcnt); + } + + omap_sham_write_mask(dd, SHA_REG_MASK, + SHA_REG_MASK_IT_EN | (dma ? SHA_REG_MASK_DMA_EN : 0), + SHA_REG_MASK_IT_EN | SHA_REG_MASK_DMA_EN); + /* + * Setting ALGO_CONST only for the first iteration + * and CLOSE_HASH only for the last one. + */ + if (ctx->flags & FLAGS_SHA1) + val |= SHA_REG_CTRL_ALGO; + if (!ctx->digcnt) + val |= SHA_REG_CTRL_ALGO_CONST; + if (final) + val |= SHA_REG_CTRL_CLOSE_HASH; + + mask = SHA_REG_CTRL_ALGO_CONST | SHA_REG_CTRL_CLOSE_HASH | + SHA_REG_CTRL_ALGO | SHA_REG_CTRL_LENGTH; + + omap_sham_write_mask(dd, SHA_REG_CTRL, val, mask); + + return 0; +} + +static int omap_sham_xmit_cpu(struct omap_sham_dev *dd, const u8 *buf, + size_t length, int final) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req); + int err, count, len32; + const u32 *buffer = (const u32 *)buf; + + dev_dbg(dd->dev, "xmit_cpu: digcnt: %d, length: %d, final: %d\n", + ctx->digcnt, length, final); + + err = omap_sham_write_ctrl(dd, length, final, 0); + if (err) + return err; + + if (omap_sham_wait(dd, SHA_REG_CTRL, SHA_REG_CTRL_INPUT_READY)) + return -ETIMEDOUT; + + ctx->digcnt += length; + + if (final) + ctx->flags |= FLAGS_FINAL; /* catch last interrupt */ + + len32 = DIV_ROUND_UP(length, sizeof(u32)); + + for (count = 0; count < len32; count++) + omap_sham_write(dd, SHA_REG_DIN(count), buffer[count]); + + return -EINPROGRESS; +} + +static int omap_sham_xmit_dma(struct omap_sham_dev *dd, dma_addr_t dma_addr, + size_t length, int final) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req); + int err, len32; + + dev_dbg(dd->dev, "xmit_dma: digcnt: %d, length: %d, final: %d\n", + ctx->digcnt, length, final); + + /* flush cache entries related to our page */ + if (dma_addr == ctx->dma_addr) + dma_sync_single_for_device(dd->dev, dma_addr, length, + DMA_TO_DEVICE); + + len32 = DIV_ROUND_UP(length, sizeof(u32)); + + omap_set_dma_transfer_params(dd->dma_lch, OMAP_DMA_DATA_TYPE_S32, len32, + 1, OMAP_DMA_SYNC_PACKET, dd->dma, OMAP_DMA_DST_SYNC); + + omap_set_dma_src_params(dd->dma_lch, 0, OMAP_DMA_AMODE_POST_INC, + dma_addr, 0, 0); + + err = omap_sham_write_ctrl(dd, length, final, 1); + if (err) + return err; + + ctx->digcnt += length; + + if (final) + ctx->flags |= FLAGS_FINAL; /* catch last interrupt */ + + dd->flags |= FLAGS_DMA_ACTIVE; + + omap_start_dma(dd->dma_lch); + + return -EINPROGRESS; +} + +static size_t omap_sham_append_buffer(struct omap_sham_reqctx *ctx, + const u8 *data, size_t length) +{ + size_t count = min(length, ctx->buflen - ctx->bufcnt); + + count = min(count, ctx->total); + if (count <= 0) + return 0; + memcpy(ctx->buffer + ctx->bufcnt, data, count); + ctx->bufcnt += count; + + return count; +} + +static size_t omap_sham_append_sg(struct omap_sham_reqctx *ctx) +{ + size_t count; + + while (ctx->sg) { + count = omap_sham_append_buffer(ctx, + sg_virt(ctx->sg) + ctx->offset, + ctx->sg->length - ctx->offset); + if (!count) + break; + ctx->offset += count; + ctx->total -= count; + if (ctx->offset == ctx->sg->length) { + ctx->sg = sg_next(ctx->sg); + if (ctx->sg) + ctx->offset = 0; + else + ctx->total = 0; + } + } + + return 0; +} + +static int omap_sham_update_dma_slow(struct omap_sham_dev *dd) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req); + unsigned int final; + size_t count; + + if (!ctx->total) + return 0; + + omap_sham_append_sg(ctx); + + final = (ctx->flags & FLAGS_FINUP) && !ctx->total; + + dev_dbg(dd->dev, "slow: bufcnt: %u, digcnt: %d, final: %d\n", + ctx->bufcnt, ctx->digcnt, final); + + if (final || (ctx->bufcnt == ctx->buflen && ctx->total)) { + count = ctx->bufcnt; + ctx->bufcnt = 0; + return omap_sham_xmit_dma(dd, ctx->dma_addr, count, final); + } + + return 0; +} + +static int omap_sham_update_dma_fast(struct omap_sham_dev *dd) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req); + unsigned int length; + + ctx->flags |= FLAGS_FAST; + + length = min(ctx->total, sg_dma_len(ctx->sg)); + ctx->total = length; + + if (!dma_map_sg(dd->dev, ctx->sg, 1, DMA_TO_DEVICE)) { + dev_err(dd->dev, "dma_map_sg error\n"); + return -EINVAL; + } + + ctx->total -= length; + + return omap_sham_xmit_dma(dd, sg_dma_address(ctx->sg), length, 1); +} + +static int omap_sham_update_cpu(struct omap_sham_dev *dd) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req); + int bufcnt; + + omap_sham_append_sg(ctx); + bufcnt = ctx->bufcnt; + ctx->bufcnt = 0; + + return omap_sham_xmit_cpu(dd, ctx->buffer, bufcnt, 1); +} + +static int omap_sham_update_dma_stop(struct omap_sham_dev *dd) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req); + + omap_stop_dma(dd->dma_lch); + if (ctx->flags & FLAGS_FAST) + dma_unmap_sg(dd->dev, ctx->sg, 1, DMA_TO_DEVICE); + + return 0; +} + +static void omap_sham_cleanup(struct ahash_request *req) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + struct omap_sham_dev *dd = ctx->dd; + unsigned long flags; + + spin_lock_irqsave(&dd->lock, flags); + if (ctx->flags & FLAGS_CLEAN) { + spin_unlock_irqrestore(&dd->lock, flags); + return; + } + ctx->flags |= FLAGS_CLEAN; + spin_unlock_irqrestore(&dd->lock, flags); + + if (ctx->digcnt) + clk_disable(dd->iclk); + + if (ctx->dma_addr) + dma_unmap_single(dd->dev, ctx->dma_addr, ctx->buflen, + DMA_TO_DEVICE); + + if (ctx->buffer) + free_page((unsigned long)ctx->buffer); + + dev_dbg(dd->dev, "digcnt: %d, bufcnt: %d\n", ctx->digcnt, ctx->bufcnt); +} + +static int omap_sham_init(struct ahash_request *req) +{ + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct omap_sham_ctx *tctx = crypto_ahash_ctx(tfm); + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + struct omap_sham_dev *dd = NULL, *tmp; + + spin_lock_bh(&sham.lock); + if (!tctx->dd) { + list_for_each_entry(tmp, &sham.dev_list, list) { + dd = tmp; + break; + } + tctx->dd = dd; + } else { + dd = tctx->dd; + } + spin_unlock_bh(&sham.lock); + + ctx->dd = dd; + + ctx->flags = 0; + + ctx->flags |= FLAGS_FIRST; + + dev_dbg(dd->dev, "init: digest size: %d\n", + crypto_ahash_digestsize(tfm)); + + if (crypto_ahash_digestsize(tfm) == SHA1_DIGEST_SIZE) + ctx->flags |= FLAGS_SHA1; + + ctx->bufcnt = 0; + ctx->digcnt = 0; + + ctx->buflen = PAGE_SIZE; + ctx->buffer = (void *)__get_free_page( + (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ? + GFP_KERNEL : GFP_ATOMIC); + if (!ctx->buffer) + return -ENOMEM; + + ctx->dma_addr = dma_map_single(dd->dev, ctx->buffer, ctx->buflen, + DMA_TO_DEVICE); + if (dma_mapping_error(dd->dev, ctx->dma_addr)) { + dev_err(dd->dev, "dma %u bytes error\n", ctx->buflen); + free_page((unsigned long)ctx->buffer); + return -EINVAL; + } + + if (tctx->flags & FLAGS_HMAC) { + struct omap_sham_hmac_ctx *bctx = tctx->base; + + memcpy(ctx->buffer, bctx->ipad, SHA1_MD5_BLOCK_SIZE); + ctx->bufcnt = SHA1_MD5_BLOCK_SIZE; + ctx->flags |= FLAGS_HMAC; + } + + return 0; + +} + +static int omap_sham_update_req(struct omap_sham_dev *dd) +{ + struct ahash_request *req = dd->req; + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + int err; + + dev_dbg(dd->dev, "update_req: total: %u, digcnt: %d, finup: %d\n", + ctx->total, ctx->digcnt, (ctx->flags & FLAGS_FINUP) != 0); + + if (ctx->flags & FLAGS_CPU) + err = omap_sham_update_cpu(dd); + else if (ctx->flags & FLAGS_FAST) + err = omap_sham_update_dma_fast(dd); + else + err = omap_sham_update_dma_slow(dd); + + /* wait for dma completion before can take more data */ + dev_dbg(dd->dev, "update: err: %d, digcnt: %d\n", err, ctx->digcnt); + + return err; +} + +static int omap_sham_final_req(struct omap_sham_dev *dd) +{ + struct ahash_request *req = dd->req; + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + int err = 0, use_dma = 1; + + if (ctx->bufcnt <= 64) + /* faster to handle last block with cpu */ + use_dma = 0; + + if (use_dma) + err = omap_sham_xmit_dma(dd, ctx->dma_addr, ctx->bufcnt, 1); + else + err = omap_sham_xmit_cpu(dd, ctx->buffer, ctx->bufcnt, 1); + + ctx->bufcnt = 0; + + if (err != -EINPROGRESS) + omap_sham_cleanup(req); + + dev_dbg(dd->dev, "final_req: err: %d\n", err); + + return err; +} + +static int omap_sham_finish_req_hmac(struct ahash_request *req) +{ + struct omap_sham_ctx *tctx = crypto_tfm_ctx(req->base.tfm); + struct omap_sham_hmac_ctx *bctx = tctx->base; + int bs = crypto_shash_blocksize(bctx->shash); + int ds = crypto_shash_digestsize(bctx->shash); + struct { + struct shash_desc shash; + char ctx[crypto_shash_descsize(bctx->shash)]; + } desc; + + desc.shash.tfm = bctx->shash; + desc.shash.flags = 0; /* not CRYPTO_TFM_REQ_MAY_SLEEP */ + + return crypto_shash_init(&desc.shash) ?: + crypto_shash_update(&desc.shash, bctx->opad, bs) ?: + crypto_shash_finup(&desc.shash, req->result, ds, req->result); +} + +static void omap_sham_finish_req(struct ahash_request *req, int err) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + + if (!err) { + omap_sham_copy_hash(ctx->dd->req, 1); + if (ctx->flags & FLAGS_HMAC) + err = omap_sham_finish_req_hmac(req); + } + + if (ctx->flags & FLAGS_FINAL) + omap_sham_cleanup(req); + + clear_bit(FLAGS_BUSY, &ctx->dd->flags); + + if (req->base.complete) + req->base.complete(&req->base, err); +} + +static int omap_sham_handle_queue(struct omap_sham_dev *dd) +{ + struct crypto_async_request *async_req, *backlog; + struct omap_sham_reqctx *ctx; + struct ahash_request *req, *prev_req; + unsigned long flags; + int err = 0; + + if (test_and_set_bit(FLAGS_BUSY, &dd->flags)) + return 0; + + spin_lock_irqsave(&dd->lock, flags); + backlog = crypto_get_backlog(&dd->queue); + async_req = crypto_dequeue_request(&dd->queue); + if (!async_req) + clear_bit(FLAGS_BUSY, &dd->flags); + spin_unlock_irqrestore(&dd->lock, flags); + + if (!async_req) + return 0; + + if (backlog) + backlog->complete(backlog, -EINPROGRESS); + + req = ahash_request_cast(async_req); + + prev_req = dd->req; + dd->req = req; + + ctx = ahash_request_ctx(req); + + dev_dbg(dd->dev, "handling new req, op: %lu, nbytes: %d\n", + ctx->op, req->nbytes); + + if (req != prev_req && ctx->digcnt) + /* request has changed - restore hash */ + omap_sham_copy_hash(req, 0); + + if (ctx->op == OP_UPDATE) { + err = omap_sham_update_req(dd); + if (err != -EINPROGRESS && (ctx->flags & FLAGS_FINUP)) + /* no final() after finup() */ + err = omap_sham_final_req(dd); + } else if (ctx->op == OP_FINAL) { + err = omap_sham_final_req(dd); + } + + if (err != -EINPROGRESS) { + /* done_task will not finish it, so do it here */ + omap_sham_finish_req(req, err); + tasklet_schedule(&dd->queue_task); + } + + dev_dbg(dd->dev, "exit, err: %d\n", err); + + return err; +} + +static int omap_sham_enqueue(struct ahash_request *req, unsigned int op) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + struct omap_sham_ctx *tctx = crypto_tfm_ctx(req->base.tfm); + struct omap_sham_dev *dd = tctx->dd; + unsigned long flags; + int err; + + ctx->op = op; + + spin_lock_irqsave(&dd->lock, flags); + err = ahash_enqueue_request(&dd->queue, req); + spin_unlock_irqrestore(&dd->lock, flags); + + omap_sham_handle_queue(dd); + + return err; +} + +static int omap_sham_update(struct ahash_request *req) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + + if (!req->nbytes) + return 0; + + ctx->total = req->nbytes; + ctx->sg = req->src; + ctx->offset = 0; + + if (ctx->flags & FLAGS_FINUP) { + if ((ctx->digcnt + ctx->bufcnt + ctx->total) < 9) { + /* + * OMAP HW accel works only with buffers >= 9 + * will switch to bypass in final() + * final has the same request and data + */ + omap_sham_append_sg(ctx); + return 0; + } else if (ctx->bufcnt + ctx->total <= 64) { + ctx->flags |= FLAGS_CPU; + } else if (!ctx->bufcnt && sg_is_last(ctx->sg)) { + /* may be can use faster functions */ + int aligned = IS_ALIGNED((u32)ctx->sg->offset, + sizeof(u32)); + + if (aligned && (ctx->flags & FLAGS_FIRST)) + /* digest: first and final */ + ctx->flags |= FLAGS_FAST; + + ctx->flags &= ~FLAGS_FIRST; + } + } else if (ctx->bufcnt + ctx->total <= ctx->buflen) { + /* if not finaup -> not fast */ + omap_sham_append_sg(ctx); + return 0; + } + + return omap_sham_enqueue(req, OP_UPDATE); +} + +static int omap_sham_shash_digest(struct crypto_shash *shash, u32 flags, + const u8 *data, unsigned int len, u8 *out) +{ + struct { + struct shash_desc shash; + char ctx[crypto_shash_descsize(shash)]; + } desc; + + desc.shash.tfm = shash; + desc.shash.flags = flags & CRYPTO_TFM_REQ_MAY_SLEEP; + + return crypto_shash_digest(&desc.shash, data, len, out); +} + +static int omap_sham_final_shash(struct ahash_request *req) +{ + struct omap_sham_ctx *tctx = crypto_tfm_ctx(req->base.tfm); + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + + return omap_sham_shash_digest(tctx->fallback, req->base.flags, + ctx->buffer, ctx->bufcnt, req->result); +} + +static int omap_sham_final(struct ahash_request *req) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + int err = 0; + + ctx->flags |= FLAGS_FINUP; + + /* OMAP HW accel works only with buffers >= 9 */ + /* HMAC is always >= 9 because of ipad */ + if ((ctx->digcnt + ctx->bufcnt) < 9) + err = omap_sham_final_shash(req); + else if (ctx->bufcnt) + return omap_sham_enqueue(req, OP_FINAL); + + omap_sham_cleanup(req); + + return err; +} + +static int omap_sham_finup(struct ahash_request *req) +{ + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + int err1, err2; + + ctx->flags |= FLAGS_FINUP; + + err1 = omap_sham_update(req); + if (err1 == -EINPROGRESS) + return err1; + /* + * final() has to be always called to cleanup resources + * even if udpate() failed, except EINPROGRESS + */ + err2 = omap_sham_final(req); + + return err1 ?: err2; +} + +static int omap_sham_digest(struct ahash_request *req) +{ + return omap_sham_init(req) ?: omap_sham_finup(req); +} + +static int omap_sham_setkey(struct crypto_ahash *tfm, const u8 *key, + unsigned int keylen) +{ + struct omap_sham_ctx *tctx = crypto_ahash_ctx(tfm); + struct omap_sham_hmac_ctx *bctx = tctx->base; + int bs = crypto_shash_blocksize(bctx->shash); + int ds = crypto_shash_digestsize(bctx->shash); + int err, i; + err = crypto_shash_setkey(tctx->fallback, key, keylen); + if (err) + return err; + + if (keylen > bs) { + err = omap_sham_shash_digest(bctx->shash, + crypto_shash_get_flags(bctx->shash), + key, keylen, bctx->ipad); + if (err) + return err; + keylen = ds; + } else { + memcpy(bctx->ipad, key, keylen); + } + + memset(bctx->ipad + keylen, 0, bs - keylen); + memcpy(bctx->opad, bctx->ipad, bs); + + for (i = 0; i < bs; i++) { + bctx->ipad[i] ^= 0x36; + bctx->opad[i] ^= 0x5c; + } + + return err; +} + +static int omap_sham_cra_init_alg(struct crypto_tfm *tfm, const char *alg_base) +{ + struct omap_sham_ctx *tctx = crypto_tfm_ctx(tfm); + const char *alg_name = crypto_tfm_alg_name(tfm); + + /* Allocate a fallback and abort if it failed. */ + tctx->fallback = crypto_alloc_shash(alg_name, 0, + CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(tctx->fallback)) { + pr_err("omap-sham: fallback driver '%s' " + "could not be loaded.\n", alg_name); + return PTR_ERR(tctx->fallback); + } + + crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm), + sizeof(struct omap_sham_reqctx)); + + if (alg_base) { + struct omap_sham_hmac_ctx *bctx = tctx->base; + tctx->flags |= FLAGS_HMAC; + bctx->shash = crypto_alloc_shash(alg_base, 0, + CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(bctx->shash)) { + pr_err("omap-sham: base driver '%s' " + "could not be loaded.\n", alg_base); + crypto_free_shash(tctx->fallback); + return PTR_ERR(bctx->shash); + } + + } + + return 0; +} + +static int omap_sham_cra_init(struct crypto_tfm *tfm) +{ + return omap_sham_cra_init_alg(tfm, NULL); +} + +static int omap_sham_cra_sha1_init(struct crypto_tfm *tfm) +{ + return omap_sham_cra_init_alg(tfm, "sha1"); +} + +static int omap_sham_cra_md5_init(struct crypto_tfm *tfm) +{ + return omap_sham_cra_init_alg(tfm, "md5"); +} + +static void omap_sham_cra_exit(struct crypto_tfm *tfm) +{ + struct omap_sham_ctx *tctx = crypto_tfm_ctx(tfm); + + crypto_free_shash(tctx->fallback); + tctx->fallback = NULL; + + if (tctx->flags & FLAGS_HMAC) { + struct omap_sham_hmac_ctx *bctx = tctx->base; + crypto_free_shash(bctx->shash); + } +} + +static struct ahash_alg algs[] = { +{ + .init = omap_sham_init, + .update = omap_sham_update, + .final = omap_sham_final, + .finup = omap_sham_finup, + .digest = omap_sham_digest, + .halg.digestsize = SHA1_DIGEST_SIZE, + .halg.base = { + .cra_name = "sha1", + .cra_driver_name = "omap-sha1", + .cra_priority = 100, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct omap_sham_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = omap_sham_cra_init, + .cra_exit = omap_sham_cra_exit, + } +}, +{ + .init = omap_sham_init, + .update = omap_sham_update, + .final = omap_sham_final, + .finup = omap_sham_finup, + .digest = omap_sham_digest, + .halg.digestsize = MD5_DIGEST_SIZE, + .halg.base = { + .cra_name = "md5", + .cra_driver_name = "omap-md5", + .cra_priority = 100, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct omap_sham_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = omap_sham_cra_init, + .cra_exit = omap_sham_cra_exit, + } +}, +{ + .init = omap_sham_init, + .update = omap_sham_update, + .final = omap_sham_final, + .finup = omap_sham_finup, + .digest = omap_sham_digest, + .setkey = omap_sham_setkey, + .halg.digestsize = SHA1_DIGEST_SIZE, + .halg.base = { + .cra_name = "hmac(sha1)", + .cra_driver_name = "omap-hmac-sha1", + .cra_priority = 100, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct omap_sham_ctx) + + sizeof(struct omap_sham_hmac_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = omap_sham_cra_sha1_init, + .cra_exit = omap_sham_cra_exit, + } +}, +{ + .init = omap_sham_init, + .update = omap_sham_update, + .final = omap_sham_final, + .finup = omap_sham_finup, + .digest = omap_sham_digest, + .setkey = omap_sham_setkey, + .halg.digestsize = MD5_DIGEST_SIZE, + .halg.base = { + .cra_name = "hmac(md5)", + .cra_driver_name = "omap-hmac-md5", + .cra_priority = 100, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct omap_sham_ctx) + + sizeof(struct omap_sham_hmac_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = omap_sham_cra_md5_init, + .cra_exit = omap_sham_cra_exit, + } +} +}; + +static void omap_sham_done_task(unsigned long data) +{ + struct omap_sham_dev *dd = (struct omap_sham_dev *)data; + struct ahash_request *req = dd->req; + struct omap_sham_reqctx *ctx = ahash_request_ctx(req); + int ready = 1; + + if (ctx->flags & FLAGS_OUTPUT_READY) { + ctx->flags &= ~FLAGS_OUTPUT_READY; + ready = 1; + } + + if (dd->flags & FLAGS_DMA_ACTIVE) { + dd->flags &= ~FLAGS_DMA_ACTIVE; + omap_sham_update_dma_stop(dd); + omap_sham_update_dma_slow(dd); + } + + if (ready && !(dd->flags & FLAGS_DMA_ACTIVE)) { + dev_dbg(dd->dev, "update done\n"); + /* finish curent request */ + omap_sham_finish_req(req, 0); + /* start new request */ + omap_sham_handle_queue(dd); + } +} + +static void omap_sham_queue_task(unsigned long data) +{ + struct omap_sham_dev *dd = (struct omap_sham_dev *)data; + + omap_sham_handle_queue(dd); +} + +static irqreturn_t omap_sham_irq(int irq, void *dev_id) +{ + struct omap_sham_dev *dd = dev_id; + struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req); + + if (!ctx) { + dev_err(dd->dev, "unknown interrupt.\n"); + return IRQ_HANDLED; + } + + if (unlikely(ctx->flags & FLAGS_FINAL)) + /* final -> allow device to go to power-saving mode */ + omap_sham_write_mask(dd, SHA_REG_CTRL, 0, SHA_REG_CTRL_LENGTH); + + omap_sham_write_mask(dd, SHA_REG_CTRL, SHA_REG_CTRL_OUTPUT_READY, + SHA_REG_CTRL_OUTPUT_READY); + omap_sham_read(dd, SHA_REG_CTRL); + + ctx->flags |= FLAGS_OUTPUT_READY; + tasklet_schedule(&dd->done_task); + + return IRQ_HANDLED; +} + +static void omap_sham_dma_callback(int lch, u16 ch_status, void *data) +{ + struct omap_sham_dev *dd = data; + + if (likely(lch == dd->dma_lch)) + tasklet_schedule(&dd->done_task); +} + +static int omap_sham_dma_init(struct omap_sham_dev *dd) +{ + int err; + + dd->dma_lch = -1; + + err = omap_request_dma(dd->dma, dev_name(dd->dev), + omap_sham_dma_callback, dd, &dd->dma_lch); + if (err) { + dev_err(dd->dev, "Unable to request DMA channel\n"); + return err; + } + omap_set_dma_dest_params(dd->dma_lch, 0, + OMAP_DMA_AMODE_CONSTANT, + dd->phys_base + SHA_REG_DIN(0), 0, 16); + + omap_set_dma_dest_burst_mode(dd->dma_lch, + OMAP_DMA_DATA_BURST_16); + + return 0; +} + +static void omap_sham_dma_cleanup(struct omap_sham_dev *dd) +{ + if (dd->dma_lch >= 0) { + omap_free_dma(dd->dma_lch); + dd->dma_lch = -1; + } +} + +static int __devinit omap_sham_probe(struct platform_device *pdev) +{ + struct omap_sham_dev *dd; + struct device *dev = &pdev->dev; + struct resource *res; + int err, i, j; + + dd = kzalloc(sizeof(struct omap_sham_dev), GFP_KERNEL); + if (dd == NULL) { + dev_err(dev, "unable to alloc data struct.\n"); + err = -ENOMEM; + goto data_err; + } + dd->dev = dev; + platform_set_drvdata(pdev, dd); + + INIT_LIST_HEAD(&dd->list); + spin_lock_init(&dd->lock); + tasklet_init(&dd->done_task, omap_sham_done_task, (unsigned long)dd); + tasklet_init(&dd->queue_task, omap_sham_queue_task, (unsigned long)dd); + crypto_init_queue(&dd->queue, OMAP_SHAM_QUEUE_LENGTH); + + dd->irq = -1; + + /* Get the base address */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(dev, "no MEM resource info\n"); + err = -ENODEV; + goto res_err; + } + dd->phys_base = res->start; + + /* Get the DMA */ + res = platform_get_resource(pdev, IORESOURCE_DMA, 0); + if (!res) { + dev_err(dev, "no DMA resource info\n"); + err = -ENODEV; + goto res_err; + } + dd->dma = res->start; + + /* Get the IRQ */ + dd->irq = platform_get_irq(pdev, 0); + if (dd->irq < 0) { + dev_err(dev, "no IRQ resource info\n"); + err = dd->irq; + goto res_err; + } + + err = request_irq(dd->irq, omap_sham_irq, + IRQF_TRIGGER_LOW, dev_name(dev), dd); + if (err) { + dev_err(dev, "unable to request irq.\n"); + goto res_err; + } + + err = omap_sham_dma_init(dd); + if (err) + goto dma_err; + + /* Initializing the clock */ + dd->iclk = clk_get(dev, "ick"); + if (!dd->iclk) { + dev_err(dev, "clock intialization failed.\n"); + err = -ENODEV; + goto clk_err; + } + + dd->io_base = ioremap(dd->phys_base, SZ_4K); + if (!dd->io_base) { + dev_err(dev, "can't ioremap\n"); + err = -ENOMEM; + goto io_err; + } + + clk_enable(dd->iclk); + dev_info(dev, "hw accel on OMAP rev %u.%u\n", + (omap_sham_read(dd, SHA_REG_REV) & SHA_REG_REV_MAJOR) >> 4, + omap_sham_read(dd, SHA_REG_REV) & SHA_REG_REV_MINOR); + clk_disable(dd->iclk); + + spin_lock(&sham.lock); + list_add_tail(&dd->list, &sham.dev_list); + spin_unlock(&sham.lock); + + for (i = 0; i < ARRAY_SIZE(algs); i++) { + err = crypto_register_ahash(&algs[i]); + if (err) + goto err_algs; + } + + return 0; + +err_algs: + for (j = 0; j < i; j++) + crypto_unregister_ahash(&algs[j]); + iounmap(dd->io_base); +io_err: + clk_put(dd->iclk); +clk_err: + omap_sham_dma_cleanup(dd); +dma_err: + if (dd->irq >= 0) + free_irq(dd->irq, dd); +res_err: + kfree(dd); + dd = NULL; +data_err: + dev_err(dev, "initialization failed.\n"); + + return err; +} + +static int __devexit omap_sham_remove(struct platform_device *pdev) +{ + static struct omap_sham_dev *dd; + int i; + + dd = platform_get_drvdata(pdev); + if (!dd) + return -ENODEV; + spin_lock(&sham.lock); + list_del(&dd->list); + spin_unlock(&sham.lock); + for (i = 0; i < ARRAY_SIZE(algs); i++) + crypto_unregister_ahash(&algs[i]); + tasklet_kill(&dd->done_task); + tasklet_kill(&dd->queue_task); + iounmap(dd->io_base); + clk_put(dd->iclk); + omap_sham_dma_cleanup(dd); + if (dd->irq >= 0) + free_irq(dd->irq, dd); + kfree(dd); + dd = NULL; + + return 0; +} + +static struct platform_driver omap_sham_driver = { + .probe = omap_sham_probe, + .remove = omap_sham_remove, + .driver = { + .name = "omap-sham", + .owner = THIS_MODULE, + }, +}; + +static int __init omap_sham_mod_init(void) +{ + pr_info("loading %s driver\n", "omap-sham"); + + if (!cpu_class_is_omap2() || + omap_type() != OMAP2_DEVICE_TYPE_SEC) { + pr_err("Unsupported cpu\n"); + return -ENODEV; + } + + return platform_driver_register(&omap_sham_driver); +} + +static void __exit omap_sham_mod_exit(void) +{ + platform_driver_unregister(&omap_sham_driver); +} + +module_init(omap_sham_mod_init); +module_exit(omap_sham_mod_exit); + +MODULE_DESCRIPTION("OMAP SHA1/MD5 hw acceleration support."); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Dmitry Kasatkin"); |