diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-06 01:02:30 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-06 01:02:30 +0000 |
commit | 76cb841cb886eef6b3bee341a2266c76578724ad (patch) | |
tree | f5892e5ba6cc11949952a6ce4ecbe6d516d6ce58 /drivers/crypto/chelsio | |
parent | Initial commit. (diff) | |
download | linux-76cb841cb886eef6b3bee341a2266c76578724ad.tar.xz linux-76cb841cb886eef6b3bee341a2266c76578724ad.zip |
Adding upstream version 4.19.249.upstream/4.19.249upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'drivers/crypto/chelsio')
-rw-r--r-- | drivers/crypto/chelsio/Kconfig | 42 | ||||
-rw-r--r-- | drivers/crypto/chelsio/Makefile | 6 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chcr_algo.c | 4316 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chcr_algo.h | 442 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chcr_core.c | 270 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chcr_core.h | 195 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chcr_crypto.h | 344 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chcr_ipsec.c | 655 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chtls/Makefile | 4 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chtls/chtls.h | 489 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chtls/chtls_cm.c | 2123 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chtls/chtls_cm.h | 221 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chtls/chtls_hw.c | 415 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chtls/chtls_io.c | 1879 | ||||
-rw-r--r-- | drivers/crypto/chelsio/chtls/chtls_main.c | 597 |
15 files changed, 11998 insertions, 0 deletions
diff --git a/drivers/crypto/chelsio/Kconfig b/drivers/crypto/chelsio/Kconfig new file mode 100644 index 000000000..930d82d99 --- /dev/null +++ b/drivers/crypto/chelsio/Kconfig @@ -0,0 +1,42 @@ +config CRYPTO_DEV_CHELSIO + tristate "Chelsio Crypto Co-processor Driver" + depends on CHELSIO_T4 + select CRYPTO_SHA1 + select CRYPTO_SHA256 + select CRYPTO_SHA512 + select CRYPTO_AUTHENC + select CRYPTO_GF128MUL + ---help--- + The Chelsio Crypto Co-processor driver for T6 adapters. + + For general information about Chelsio and our products, visit + our website at <http://www.chelsio.com>. + + For customer support, please visit our customer support page at + <http://www.chelsio.com/support.html>. + + Please send feedback to <linux-bugs@chelsio.com>. + + To compile this driver as a module, choose M here: the module + will be called chcr. + +config CHELSIO_IPSEC_INLINE + bool "Chelsio IPSec XFRM Tx crypto offload" + depends on CHELSIO_T4 + depends on CRYPTO_DEV_CHELSIO + depends on XFRM_OFFLOAD + depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD + default n + ---help--- + Enable support for IPSec Tx Inline. + +config CRYPTO_DEV_CHELSIO_TLS + tristate "Chelsio Crypto Inline TLS Driver" + depends on CHELSIO_T4 + depends on TLS + select CRYPTO_DEV_CHELSIO + ---help--- + Support Chelsio Inline TLS with Chelsio crypto accelerator. + + To compile this driver as a module, choose M here: the module + will be called chtls. diff --git a/drivers/crypto/chelsio/Makefile b/drivers/crypto/chelsio/Makefile new file mode 100644 index 000000000..639e5718d --- /dev/null +++ b/drivers/crypto/chelsio/Makefile @@ -0,0 +1,6 @@ +ccflags-y := -Idrivers/net/ethernet/chelsio/cxgb4 + +obj-$(CONFIG_CRYPTO_DEV_CHELSIO) += chcr.o +chcr-objs := chcr_core.o chcr_algo.o +chcr-$(CONFIG_CHELSIO_IPSEC_INLINE) += chcr_ipsec.o +obj-$(CONFIG_CRYPTO_DEV_CHELSIO_TLS) += chtls/ diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c new file mode 100644 index 000000000..ee508bbbb --- /dev/null +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -0,0 +1,4316 @@ +/* + * This file is part of the Chelsio T6 Crypto driver for Linux. + * + * Copyright (c) 2003-2016 Chelsio Communications, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + * Written and Maintained by: + * Manoj Malviya (manojmalviya@chelsio.com) + * Atul Gupta (atul.gupta@chelsio.com) + * Jitendra Lulla (jlulla@chelsio.com) + * Yeshaswi M R Gowda (yeshaswi@chelsio.com) + * Harsh Jain (harsh@chelsio.com) + */ + +#define pr_fmt(fmt) "chcr:" fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/crypto.h> +#include <linux/cryptohash.h> +#include <linux/skbuff.h> +#include <linux/rtnetlink.h> +#include <linux/highmem.h> +#include <linux/scatterlist.h> + +#include <crypto/aes.h> +#include <crypto/algapi.h> +#include <crypto/hash.h> +#include <crypto/gcm.h> +#include <crypto/sha.h> +#include <crypto/authenc.h> +#include <crypto/ctr.h> +#include <crypto/gf128mul.h> +#include <crypto/internal/aead.h> +#include <crypto/null.h> +#include <crypto/internal/skcipher.h> +#include <crypto/aead.h> +#include <crypto/scatterwalk.h> +#include <crypto/internal/hash.h> + +#include "t4fw_api.h" +#include "t4_msg.h" +#include "chcr_core.h" +#include "chcr_algo.h" +#include "chcr_crypto.h" + +#define IV AES_BLOCK_SIZE + +static unsigned int sgl_ent_len[] = { + 0, 0, 16, 24, 40, 48, 64, 72, 88, + 96, 112, 120, 136, 144, 160, 168, 184, + 192, 208, 216, 232, 240, 256, 264, 280, + 288, 304, 312, 328, 336, 352, 360, 376 +}; + +static unsigned int dsgl_ent_len[] = { + 0, 32, 32, 48, 48, 64, 64, 80, 80, + 112, 112, 128, 128, 144, 144, 160, 160, + 192, 192, 208, 208, 224, 224, 240, 240, + 272, 272, 288, 288, 304, 304, 320, 320 +}; + +static u32 round_constant[11] = { + 0x01000000, 0x02000000, 0x04000000, 0x08000000, + 0x10000000, 0x20000000, 0x40000000, 0x80000000, + 0x1B000000, 0x36000000, 0x6C000000 +}; + +static int chcr_handle_cipher_resp(struct ablkcipher_request *req, + unsigned char *input, int err); + +static inline struct chcr_aead_ctx *AEAD_CTX(struct chcr_context *ctx) +{ + return ctx->crypto_ctx->aeadctx; +} + +static inline struct ablk_ctx *ABLK_CTX(struct chcr_context *ctx) +{ + return ctx->crypto_ctx->ablkctx; +} + +static inline struct hmac_ctx *HMAC_CTX(struct chcr_context *ctx) +{ + return ctx->crypto_ctx->hmacctx; +} + +static inline struct chcr_gcm_ctx *GCM_CTX(struct chcr_aead_ctx *gctx) +{ + return gctx->ctx->gcm; +} + +static inline struct chcr_authenc_ctx *AUTHENC_CTX(struct chcr_aead_ctx *gctx) +{ + return gctx->ctx->authenc; +} + +static inline struct uld_ctx *ULD_CTX(struct chcr_context *ctx) +{ + return ctx->dev->u_ctx; +} + +static inline int is_ofld_imm(const struct sk_buff *skb) +{ + return (skb->len <= SGE_MAX_WR_LEN); +} + +static inline void chcr_init_hctx_per_wr(struct chcr_ahash_req_ctx *reqctx) +{ + memset(&reqctx->hctx_wr, 0, sizeof(struct chcr_hctx_per_wr)); +} + +static int sg_nents_xlen(struct scatterlist *sg, unsigned int reqlen, + unsigned int entlen, + unsigned int skip) +{ + int nents = 0; + unsigned int less; + unsigned int skip_len = 0; + + while (sg && skip) { + if (sg_dma_len(sg) <= skip) { + skip -= sg_dma_len(sg); + skip_len = 0; + sg = sg_next(sg); + } else { + skip_len = skip; + skip = 0; + } + } + + while (sg && reqlen) { + less = min(reqlen, sg_dma_len(sg) - skip_len); + nents += DIV_ROUND_UP(less, entlen); + reqlen -= less; + skip_len = 0; + sg = sg_next(sg); + } + return nents; +} + +static inline int get_aead_subtype(struct crypto_aead *aead) +{ + struct aead_alg *alg = crypto_aead_alg(aead); + struct chcr_alg_template *chcr_crypto_alg = + container_of(alg, struct chcr_alg_template, alg.aead); + return chcr_crypto_alg->type & CRYPTO_ALG_SUB_TYPE_MASK; +} + +void chcr_verify_tag(struct aead_request *req, u8 *input, int *err) +{ + u8 temp[SHA512_DIGEST_SIZE]; + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + int authsize = crypto_aead_authsize(tfm); + struct cpl_fw6_pld *fw6_pld; + int cmp = 0; + + fw6_pld = (struct cpl_fw6_pld *)input; + if ((get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106) || + (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_GCM)) { + cmp = crypto_memneq(&fw6_pld->data[2], (fw6_pld + 1), authsize); + } else { + + sg_pcopy_to_buffer(req->src, sg_nents(req->src), temp, + authsize, req->assoclen + + req->cryptlen - authsize); + cmp = crypto_memneq(temp, (fw6_pld + 1), authsize); + } + if (cmp) + *err = -EBADMSG; + else + *err = 0; +} + +static inline void chcr_handle_aead_resp(struct aead_request *req, + unsigned char *input, + int err) +{ + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + + chcr_aead_common_exit(req); + if (reqctx->verify == VERIFY_SW) { + chcr_verify_tag(req, input, &err); + reqctx->verify = VERIFY_HW; + } + req->base.complete(&req->base, err); +} + +static void get_aes_decrypt_key(unsigned char *dec_key, + const unsigned char *key, + unsigned int keylength) +{ + u32 temp; + u32 w_ring[MAX_NK]; + int i, j, k; + u8 nr, nk; + + switch (keylength) { + case AES_KEYLENGTH_128BIT: + nk = KEYLENGTH_4BYTES; + nr = NUMBER_OF_ROUNDS_10; + break; + case AES_KEYLENGTH_192BIT: + nk = KEYLENGTH_6BYTES; + nr = NUMBER_OF_ROUNDS_12; + break; + case AES_KEYLENGTH_256BIT: + nk = KEYLENGTH_8BYTES; + nr = NUMBER_OF_ROUNDS_14; + break; + default: + return; + } + for (i = 0; i < nk; i++) + w_ring[i] = be32_to_cpu(*(u32 *)&key[4 * i]); + + i = 0; + temp = w_ring[nk - 1]; + while (i + nk < (nr + 1) * 4) { + if (!(i % nk)) { + /* RotWord(temp) */ + temp = (temp << 8) | (temp >> 24); + temp = aes_ks_subword(temp); + temp ^= round_constant[i / nk]; + } else if (nk == 8 && (i % 4 == 0)) { + temp = aes_ks_subword(temp); + } + w_ring[i % nk] ^= temp; + temp = w_ring[i % nk]; + i++; + } + i--; + for (k = 0, j = i % nk; k < nk; k++) { + *((u32 *)dec_key + k) = htonl(w_ring[j]); + j--; + if (j < 0) + j += nk; + } +} + +static struct crypto_shash *chcr_alloc_shash(unsigned int ds) +{ + struct crypto_shash *base_hash = ERR_PTR(-EINVAL); + + switch (ds) { + case SHA1_DIGEST_SIZE: + base_hash = crypto_alloc_shash("sha1", 0, 0); + break; + case SHA224_DIGEST_SIZE: + base_hash = crypto_alloc_shash("sha224", 0, 0); + break; + case SHA256_DIGEST_SIZE: + base_hash = crypto_alloc_shash("sha256", 0, 0); + break; + case SHA384_DIGEST_SIZE: + base_hash = crypto_alloc_shash("sha384", 0, 0); + break; + case SHA512_DIGEST_SIZE: + base_hash = crypto_alloc_shash("sha512", 0, 0); + break; + } + + return base_hash; +} + +static int chcr_compute_partial_hash(struct shash_desc *desc, + char *iopad, char *result_hash, + int digest_size) +{ + struct sha1_state sha1_st; + struct sha256_state sha256_st; + struct sha512_state sha512_st; + int error; + + if (digest_size == SHA1_DIGEST_SIZE) { + error = crypto_shash_init(desc) ?: + crypto_shash_update(desc, iopad, SHA1_BLOCK_SIZE) ?: + crypto_shash_export(desc, (void *)&sha1_st); + memcpy(result_hash, sha1_st.state, SHA1_DIGEST_SIZE); + } else if (digest_size == SHA224_DIGEST_SIZE) { + error = crypto_shash_init(desc) ?: + crypto_shash_update(desc, iopad, SHA256_BLOCK_SIZE) ?: + crypto_shash_export(desc, (void *)&sha256_st); + memcpy(result_hash, sha256_st.state, SHA256_DIGEST_SIZE); + + } else if (digest_size == SHA256_DIGEST_SIZE) { + error = crypto_shash_init(desc) ?: + crypto_shash_update(desc, iopad, SHA256_BLOCK_SIZE) ?: + crypto_shash_export(desc, (void *)&sha256_st); + memcpy(result_hash, sha256_st.state, SHA256_DIGEST_SIZE); + + } else if (digest_size == SHA384_DIGEST_SIZE) { + error = crypto_shash_init(desc) ?: + crypto_shash_update(desc, iopad, SHA512_BLOCK_SIZE) ?: + crypto_shash_export(desc, (void *)&sha512_st); + memcpy(result_hash, sha512_st.state, SHA512_DIGEST_SIZE); + + } else if (digest_size == SHA512_DIGEST_SIZE) { + error = crypto_shash_init(desc) ?: + crypto_shash_update(desc, iopad, SHA512_BLOCK_SIZE) ?: + crypto_shash_export(desc, (void *)&sha512_st); + memcpy(result_hash, sha512_st.state, SHA512_DIGEST_SIZE); + } else { + error = -EINVAL; + pr_err("Unknown digest size %d\n", digest_size); + } + return error; +} + +static void chcr_change_order(char *buf, int ds) +{ + int i; + + if (ds == SHA512_DIGEST_SIZE) { + for (i = 0; i < (ds / sizeof(u64)); i++) + *((__be64 *)buf + i) = + cpu_to_be64(*((u64 *)buf + i)); + } else { + for (i = 0; i < (ds / sizeof(u32)); i++) + *((__be32 *)buf + i) = + cpu_to_be32(*((u32 *)buf + i)); + } +} + +static inline int is_hmac(struct crypto_tfm *tfm) +{ + struct crypto_alg *alg = tfm->__crt_alg; + struct chcr_alg_template *chcr_crypto_alg = + container_of(__crypto_ahash_alg(alg), struct chcr_alg_template, + alg.hash); + if (chcr_crypto_alg->type == CRYPTO_ALG_TYPE_HMAC) + return 1; + return 0; +} + +static inline void dsgl_walk_init(struct dsgl_walk *walk, + struct cpl_rx_phys_dsgl *dsgl) +{ + walk->dsgl = dsgl; + walk->nents = 0; + walk->to = (struct phys_sge_pairs *)(dsgl + 1); +} + +static inline void dsgl_walk_end(struct dsgl_walk *walk, unsigned short qid, + int pci_chan_id) +{ + struct cpl_rx_phys_dsgl *phys_cpl; + + phys_cpl = walk->dsgl; + + phys_cpl->op_to_tid = htonl(CPL_RX_PHYS_DSGL_OPCODE_V(CPL_RX_PHYS_DSGL) + | CPL_RX_PHYS_DSGL_ISRDMA_V(0)); + phys_cpl->pcirlxorder_to_noofsgentr = + htonl(CPL_RX_PHYS_DSGL_PCIRLXORDER_V(0) | + CPL_RX_PHYS_DSGL_PCINOSNOOP_V(0) | + CPL_RX_PHYS_DSGL_PCITPHNTENB_V(0) | + CPL_RX_PHYS_DSGL_PCITPHNT_V(0) | + CPL_RX_PHYS_DSGL_DCAID_V(0) | + CPL_RX_PHYS_DSGL_NOOFSGENTR_V(walk->nents)); + phys_cpl->rss_hdr_int.opcode = CPL_RX_PHYS_ADDR; + phys_cpl->rss_hdr_int.qid = htons(qid); + phys_cpl->rss_hdr_int.hash_val = 0; + phys_cpl->rss_hdr_int.channel = pci_chan_id; +} + +static inline void dsgl_walk_add_page(struct dsgl_walk *walk, + size_t size, + dma_addr_t *addr) +{ + int j; + + if (!size) + return; + j = walk->nents; + walk->to->len[j % 8] = htons(size); + walk->to->addr[j % 8] = cpu_to_be64(*addr); + j++; + if ((j % 8) == 0) + walk->to++; + walk->nents = j; +} + +static void dsgl_walk_add_sg(struct dsgl_walk *walk, + struct scatterlist *sg, + unsigned int slen, + unsigned int skip) +{ + int skip_len = 0; + unsigned int left_size = slen, len = 0; + unsigned int j = walk->nents; + int offset, ent_len; + + if (!slen) + return; + while (sg && skip) { + if (sg_dma_len(sg) <= skip) { + skip -= sg_dma_len(sg); + skip_len = 0; + sg = sg_next(sg); + } else { + skip_len = skip; + skip = 0; + } + } + + while (left_size && sg) { + len = min_t(u32, left_size, sg_dma_len(sg) - skip_len); + offset = 0; + while (len) { + ent_len = min_t(u32, len, CHCR_DST_SG_SIZE); + walk->to->len[j % 8] = htons(ent_len); + walk->to->addr[j % 8] = cpu_to_be64(sg_dma_address(sg) + + offset + skip_len); + offset += ent_len; + len -= ent_len; + j++; + if ((j % 8) == 0) + walk->to++; + } + walk->last_sg = sg; + walk->last_sg_len = min_t(u32, left_size, sg_dma_len(sg) - + skip_len) + skip_len; + left_size -= min_t(u32, left_size, sg_dma_len(sg) - skip_len); + skip_len = 0; + sg = sg_next(sg); + } + walk->nents = j; +} + +static inline void ulptx_walk_init(struct ulptx_walk *walk, + struct ulptx_sgl *ulp) +{ + walk->sgl = ulp; + walk->nents = 0; + walk->pair_idx = 0; + walk->pair = ulp->sge; + walk->last_sg = NULL; + walk->last_sg_len = 0; +} + +static inline void ulptx_walk_end(struct ulptx_walk *walk) +{ + walk->sgl->cmd_nsge = htonl(ULPTX_CMD_V(ULP_TX_SC_DSGL) | + ULPTX_NSGE_V(walk->nents)); +} + + +static inline void ulptx_walk_add_page(struct ulptx_walk *walk, + size_t size, + dma_addr_t *addr) +{ + if (!size) + return; + + if (walk->nents == 0) { + walk->sgl->len0 = cpu_to_be32(size); + walk->sgl->addr0 = cpu_to_be64(*addr); + } else { + walk->pair->addr[walk->pair_idx] = cpu_to_be64(*addr); + walk->pair->len[walk->pair_idx] = cpu_to_be32(size); + walk->pair_idx = !walk->pair_idx; + if (!walk->pair_idx) + walk->pair++; + } + walk->nents++; +} + +static void ulptx_walk_add_sg(struct ulptx_walk *walk, + struct scatterlist *sg, + unsigned int len, + unsigned int skip) +{ + int small; + int skip_len = 0; + unsigned int sgmin; + + if (!len) + return; + while (sg && skip) { + if (sg_dma_len(sg) <= skip) { + skip -= sg_dma_len(sg); + skip_len = 0; + sg = sg_next(sg); + } else { + skip_len = skip; + skip = 0; + } + } + WARN(!sg, "SG should not be null here\n"); + if (sg && (walk->nents == 0)) { + small = min_t(unsigned int, sg_dma_len(sg) - skip_len, len); + sgmin = min_t(unsigned int, small, CHCR_SRC_SG_SIZE); + walk->sgl->len0 = cpu_to_be32(sgmin); + walk->sgl->addr0 = cpu_to_be64(sg_dma_address(sg) + skip_len); + walk->nents++; + len -= sgmin; + walk->last_sg = sg; + walk->last_sg_len = sgmin + skip_len; + skip_len += sgmin; + if (sg_dma_len(sg) == skip_len) { + sg = sg_next(sg); + skip_len = 0; + } + } + + while (sg && len) { + small = min(sg_dma_len(sg) - skip_len, len); + sgmin = min_t(unsigned int, small, CHCR_SRC_SG_SIZE); + walk->pair->len[walk->pair_idx] = cpu_to_be32(sgmin); + walk->pair->addr[walk->pair_idx] = + cpu_to_be64(sg_dma_address(sg) + skip_len); + walk->pair_idx = !walk->pair_idx; + walk->nents++; + if (!walk->pair_idx) + walk->pair++; + len -= sgmin; + skip_len += sgmin; + walk->last_sg = sg; + walk->last_sg_len = skip_len; + if (sg_dma_len(sg) == skip_len) { + sg = sg_next(sg); + skip_len = 0; + } + } +} + +static inline int get_cryptoalg_subtype(struct crypto_tfm *tfm) +{ + struct crypto_alg *alg = tfm->__crt_alg; + struct chcr_alg_template *chcr_crypto_alg = + container_of(alg, struct chcr_alg_template, alg.crypto); + + return chcr_crypto_alg->type & CRYPTO_ALG_SUB_TYPE_MASK; +} + +static int cxgb4_is_crypto_q_full(struct net_device *dev, unsigned int idx) +{ + struct adapter *adap = netdev2adap(dev); + struct sge_uld_txq_info *txq_info = + adap->sge.uld_txq_info[CXGB4_TX_CRYPTO]; + struct sge_uld_txq *txq; + int ret = 0; + + local_bh_disable(); + txq = &txq_info->uldtxq[idx]; + spin_lock(&txq->sendq.lock); + if (txq->full) + ret = -1; + spin_unlock(&txq->sendq.lock); + local_bh_enable(); + return ret; +} + +static int generate_copy_rrkey(struct ablk_ctx *ablkctx, + struct _key_ctx *key_ctx) +{ + if (ablkctx->ciph_mode == CHCR_SCMD_CIPHER_MODE_AES_CBC) { + memcpy(key_ctx->key, ablkctx->rrkey, ablkctx->enckey_len); + } else { + memcpy(key_ctx->key, + ablkctx->key + (ablkctx->enckey_len >> 1), + ablkctx->enckey_len >> 1); + memcpy(key_ctx->key + (ablkctx->enckey_len >> 1), + ablkctx->rrkey, ablkctx->enckey_len >> 1); + } + return 0; +} + +static int chcr_hash_ent_in_wr(struct scatterlist *src, + unsigned int minsg, + unsigned int space, + unsigned int srcskip) +{ + int srclen = 0; + int srcsg = minsg; + int soffset = 0, sless; + + if (sg_dma_len(src) == srcskip) { + src = sg_next(src); + srcskip = 0; + } + while (src && space > (sgl_ent_len[srcsg + 1])) { + sless = min_t(unsigned int, sg_dma_len(src) - soffset - srcskip, + CHCR_SRC_SG_SIZE); + srclen += sless; + soffset += sless; + srcsg++; + if (sg_dma_len(src) == (soffset + srcskip)) { + src = sg_next(src); + soffset = 0; + srcskip = 0; + } + } + return srclen; +} + +static int chcr_sg_ent_in_wr(struct scatterlist *src, + struct scatterlist *dst, + unsigned int minsg, + unsigned int space, + unsigned int srcskip, + unsigned int dstskip) +{ + int srclen = 0, dstlen = 0; + int srcsg = minsg, dstsg = minsg; + int offset = 0, soffset = 0, less, sless = 0; + + if (sg_dma_len(src) == srcskip) { + src = sg_next(src); + srcskip = 0; + } + if (sg_dma_len(dst) == dstskip) { + dst = sg_next(dst); + dstskip = 0; + } + + while (src && dst && + space > (sgl_ent_len[srcsg + 1] + dsgl_ent_len[dstsg])) { + sless = min_t(unsigned int, sg_dma_len(src) - srcskip - soffset, + CHCR_SRC_SG_SIZE); + srclen += sless; + srcsg++; + offset = 0; + while (dst && ((dstsg + 1) <= MAX_DSGL_ENT) && + space > (sgl_ent_len[srcsg] + dsgl_ent_len[dstsg + 1])) { + if (srclen <= dstlen) + break; + less = min_t(unsigned int, sg_dma_len(dst) - offset - + dstskip, CHCR_DST_SG_SIZE); + dstlen += less; + offset += less; + if ((offset + dstskip) == sg_dma_len(dst)) { + dst = sg_next(dst); + offset = 0; + } + dstsg++; + dstskip = 0; + } + soffset += sless; + if ((soffset + srcskip) == sg_dma_len(src)) { + src = sg_next(src); + srcskip = 0; + soffset = 0; + } + + } + return min(srclen, dstlen); +} + +static int chcr_cipher_fallback(struct crypto_skcipher *cipher, + u32 flags, + struct scatterlist *src, + struct scatterlist *dst, + unsigned int nbytes, + u8 *iv, + unsigned short op_type) +{ + int err; + + SKCIPHER_REQUEST_ON_STACK(subreq, cipher); + + skcipher_request_set_tfm(subreq, cipher); + skcipher_request_set_callback(subreq, flags, NULL, NULL); + skcipher_request_set_crypt(subreq, src, dst, + nbytes, iv); + + err = op_type ? crypto_skcipher_decrypt(subreq) : + crypto_skcipher_encrypt(subreq); + skcipher_request_zero(subreq); + + return err; + +} +static inline void create_wreq(struct chcr_context *ctx, + struct chcr_wr *chcr_req, + struct crypto_async_request *req, + unsigned int imm, + int hash_sz, + unsigned int len16, + unsigned int sc_len, + unsigned int lcb) +{ + struct uld_ctx *u_ctx = ULD_CTX(ctx); + int qid = u_ctx->lldi.rxq_ids[ctx->rx_qidx]; + + + chcr_req->wreq.op_to_cctx_size = FILL_WR_OP_CCTX_SIZE; + chcr_req->wreq.pld_size_hash_size = + htonl(FW_CRYPTO_LOOKASIDE_WR_HASH_SIZE_V(hash_sz)); + chcr_req->wreq.len16_pkd = + htonl(FW_CRYPTO_LOOKASIDE_WR_LEN16_V(DIV_ROUND_UP(len16, 16))); + chcr_req->wreq.cookie = cpu_to_be64((uintptr_t)req); + chcr_req->wreq.rx_chid_to_rx_q_id = + FILL_WR_RX_Q_ID(ctx->dev->rx_channel_id, qid, + !!lcb, ctx->tx_qidx); + + chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->tx_chan_id, + qid); + chcr_req->ulptx.len = htonl((DIV_ROUND_UP(len16, 16) - + ((sizeof(chcr_req->wreq)) >> 4))); + + chcr_req->sc_imm.cmd_more = FILL_CMD_MORE(!imm); + chcr_req->sc_imm.len = cpu_to_be32(sizeof(struct cpl_tx_sec_pdu) + + sizeof(chcr_req->key_ctx) + sc_len); +} + +/** + * create_cipher_wr - form the WR for cipher operations + * @req: cipher req. + * @ctx: crypto driver context of the request. + * @qid: ingress qid where response of this WR should be received. + * @op_type: encryption or decryption + */ +static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(wrparam->req); + struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(tfm)); + struct sk_buff *skb = NULL; + struct chcr_wr *chcr_req; + struct cpl_rx_phys_dsgl *phys_cpl; + struct ulptx_sgl *ulptx; + struct chcr_blkcipher_req_ctx *reqctx = + ablkcipher_request_ctx(wrparam->req); + unsigned int temp = 0, transhdr_len, dst_size; + int error; + int nents; + unsigned int kctx_len; + gfp_t flags = wrparam->req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? + GFP_KERNEL : GFP_ATOMIC; + struct adapter *adap = padap(c_ctx(tfm)->dev); + + nents = sg_nents_xlen(reqctx->dstsg, wrparam->bytes, CHCR_DST_SG_SIZE, + reqctx->dst_ofst); + dst_size = get_space_for_phys_dsgl(nents); + kctx_len = roundup(ablkctx->enckey_len, 16); + transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size); + nents = sg_nents_xlen(reqctx->srcsg, wrparam->bytes, + CHCR_SRC_SG_SIZE, reqctx->src_ofst); + temp = reqctx->imm ? roundup(wrparam->bytes, 16) : + (sgl_len(nents) * 8); + transhdr_len += temp; + transhdr_len = roundup(transhdr_len, 16); + skb = alloc_skb(SGE_MAX_WR_LEN, flags); + if (!skb) { + error = -ENOMEM; + goto err; + } + chcr_req = __skb_put_zero(skb, transhdr_len); + chcr_req->sec_cpl.op_ivinsrtofst = + FILL_SEC_CPL_OP_IVINSR(c_ctx(tfm)->dev->rx_channel_id, 2, 1); + + chcr_req->sec_cpl.pldlen = htonl(IV + wrparam->bytes); + chcr_req->sec_cpl.aadstart_cipherstop_hi = + FILL_SEC_CPL_CIPHERSTOP_HI(0, 0, IV + 1, 0); + + chcr_req->sec_cpl.cipherstop_lo_authinsert = + FILL_SEC_CPL_AUTHINSERT(0, 0, 0, 0); + chcr_req->sec_cpl.seqno_numivs = FILL_SEC_CPL_SCMD0_SEQNO(reqctx->op, 0, + ablkctx->ciph_mode, + 0, 0, IV >> 1); + chcr_req->sec_cpl.ivgen_hdrlen = FILL_SEC_CPL_IVGEN_HDRLEN(0, 0, 0, + 0, 1, dst_size); + + chcr_req->key_ctx.ctx_hdr = ablkctx->key_ctx_hdr; + if ((reqctx->op == CHCR_DECRYPT_OP) && + (!(get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) == + CRYPTO_ALG_SUB_TYPE_CTR)) && + (!(get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) == + CRYPTO_ALG_SUB_TYPE_CTR_RFC3686))) { + generate_copy_rrkey(ablkctx, &chcr_req->key_ctx); + } else { + if ((ablkctx->ciph_mode == CHCR_SCMD_CIPHER_MODE_AES_CBC) || + (ablkctx->ciph_mode == CHCR_SCMD_CIPHER_MODE_AES_CTR)) { + memcpy(chcr_req->key_ctx.key, ablkctx->key, + ablkctx->enckey_len); + } else { + memcpy(chcr_req->key_ctx.key, ablkctx->key + + (ablkctx->enckey_len >> 1), + ablkctx->enckey_len >> 1); + memcpy(chcr_req->key_ctx.key + + (ablkctx->enckey_len >> 1), + ablkctx->key, + ablkctx->enckey_len >> 1); + } + } + phys_cpl = (struct cpl_rx_phys_dsgl *)((u8 *)(chcr_req + 1) + kctx_len); + ulptx = (struct ulptx_sgl *)((u8 *)(phys_cpl + 1) + dst_size); + chcr_add_cipher_src_ent(wrparam->req, ulptx, wrparam); + chcr_add_cipher_dst_ent(wrparam->req, phys_cpl, wrparam, wrparam->qid); + + atomic_inc(&adap->chcr_stats.cipher_rqst); + temp = sizeof(struct cpl_rx_phys_dsgl) + dst_size + kctx_len + IV + + (reqctx->imm ? (wrparam->bytes) : 0); + create_wreq(c_ctx(tfm), chcr_req, &(wrparam->req->base), reqctx->imm, 0, + transhdr_len, temp, + ablkctx->ciph_mode == CHCR_SCMD_CIPHER_MODE_AES_CBC); + reqctx->skb = skb; + + if (reqctx->op && (ablkctx->ciph_mode == + CHCR_SCMD_CIPHER_MODE_AES_CBC)) + sg_pcopy_to_buffer(wrparam->req->src, + sg_nents(wrparam->req->src), wrparam->req->info, 16, + reqctx->processed + wrparam->bytes - AES_BLOCK_SIZE); + + return skb; +err: + return ERR_PTR(error); +} + +static inline int chcr_keyctx_ck_size(unsigned int keylen) +{ + int ck_size = 0; + + if (keylen == AES_KEYSIZE_128) + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128; + else if (keylen == AES_KEYSIZE_192) + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_192; + else if (keylen == AES_KEYSIZE_256) + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256; + else + ck_size = 0; + + return ck_size; +} +static int chcr_cipher_fallback_setkey(struct crypto_ablkcipher *cipher, + const u8 *key, + unsigned int keylen) +{ + struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher); + struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(cipher)); + int err = 0; + + crypto_skcipher_clear_flags(ablkctx->sw_cipher, CRYPTO_TFM_REQ_MASK); + crypto_skcipher_set_flags(ablkctx->sw_cipher, cipher->base.crt_flags & + CRYPTO_TFM_REQ_MASK); + err = crypto_skcipher_setkey(ablkctx->sw_cipher, key, keylen); + tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK; + tfm->crt_flags |= + crypto_skcipher_get_flags(ablkctx->sw_cipher) & + CRYPTO_TFM_RES_MASK; + return err; +} + +static int chcr_aes_cbc_setkey(struct crypto_ablkcipher *cipher, + const u8 *key, + unsigned int keylen) +{ + struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(cipher)); + unsigned int ck_size, context_size; + u16 alignment = 0; + int err; + + err = chcr_cipher_fallback_setkey(cipher, key, keylen); + if (err) + goto badkey_err; + + ck_size = chcr_keyctx_ck_size(keylen); + alignment = ck_size == CHCR_KEYCTX_CIPHER_KEY_SIZE_192 ? 8 : 0; + memcpy(ablkctx->key, key, keylen); + ablkctx->enckey_len = keylen; + get_aes_decrypt_key(ablkctx->rrkey, ablkctx->key, keylen << 3); + context_size = (KEY_CONTEXT_HDR_SALT_AND_PAD + + keylen + alignment) >> 4; + + ablkctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size, CHCR_KEYCTX_NO_KEY, + 0, 0, context_size); + ablkctx->ciph_mode = CHCR_SCMD_CIPHER_MODE_AES_CBC; + return 0; +badkey_err: + crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN); + ablkctx->enckey_len = 0; + + return err; +} + +static int chcr_aes_ctr_setkey(struct crypto_ablkcipher *cipher, + const u8 *key, + unsigned int keylen) +{ + struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(cipher)); + unsigned int ck_size, context_size; + u16 alignment = 0; + int err; + + err = chcr_cipher_fallback_setkey(cipher, key, keylen); + if (err) + goto badkey_err; + ck_size = chcr_keyctx_ck_size(keylen); + alignment = (ck_size == CHCR_KEYCTX_CIPHER_KEY_SIZE_192) ? 8 : 0; + memcpy(ablkctx->key, key, keylen); + ablkctx->enckey_len = keylen; + context_size = (KEY_CONTEXT_HDR_SALT_AND_PAD + + keylen + alignment) >> 4; + + ablkctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size, CHCR_KEYCTX_NO_KEY, + 0, 0, context_size); + ablkctx->ciph_mode = CHCR_SCMD_CIPHER_MODE_AES_CTR; + + return 0; +badkey_err: + crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN); + ablkctx->enckey_len = 0; + + return err; +} + +static int chcr_aes_rfc3686_setkey(struct crypto_ablkcipher *cipher, + const u8 *key, + unsigned int keylen) +{ + struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(cipher)); + unsigned int ck_size, context_size; + u16 alignment = 0; + int err; + + if (keylen < CTR_RFC3686_NONCE_SIZE) + return -EINVAL; + memcpy(ablkctx->nonce, key + (keylen - CTR_RFC3686_NONCE_SIZE), + CTR_RFC3686_NONCE_SIZE); + + keylen -= CTR_RFC3686_NONCE_SIZE; + err = chcr_cipher_fallback_setkey(cipher, key, keylen); + if (err) + goto badkey_err; + + ck_size = chcr_keyctx_ck_size(keylen); + alignment = (ck_size == CHCR_KEYCTX_CIPHER_KEY_SIZE_192) ? 8 : 0; + memcpy(ablkctx->key, key, keylen); + ablkctx->enckey_len = keylen; + context_size = (KEY_CONTEXT_HDR_SALT_AND_PAD + + keylen + alignment) >> 4; + + ablkctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size, CHCR_KEYCTX_NO_KEY, + 0, 0, context_size); + ablkctx->ciph_mode = CHCR_SCMD_CIPHER_MODE_AES_CTR; + + return 0; +badkey_err: + crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN); + ablkctx->enckey_len = 0; + + return err; +} +static void ctr_add_iv(u8 *dstiv, u8 *srciv, u32 add) +{ + unsigned int size = AES_BLOCK_SIZE; + __be32 *b = (__be32 *)(dstiv + size); + u32 c, prev; + + memcpy(dstiv, srciv, AES_BLOCK_SIZE); + for (; size >= 4; size -= 4) { + prev = be32_to_cpu(*--b); + c = prev + add; + *b = cpu_to_be32(c); + if (prev < c) + break; + add = 1; + } + +} + +static unsigned int adjust_ctr_overflow(u8 *iv, u32 bytes) +{ + __be32 *b = (__be32 *)(iv + AES_BLOCK_SIZE); + u64 c; + u32 temp = be32_to_cpu(*--b); + + temp = ~temp; + c = (u64)temp + 1; // No of block can processed withou overflow + if ((bytes / AES_BLOCK_SIZE) > c) + bytes = c * AES_BLOCK_SIZE; + return bytes; +} + +static int chcr_update_tweak(struct ablkcipher_request *req, u8 *iv, + u32 isfinal) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(tfm)); + struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req); + struct crypto_cipher *cipher; + int ret, i; + u8 *key; + unsigned int keylen; + int round = reqctx->last_req_len / AES_BLOCK_SIZE; + int round8 = round / 8; + + cipher = ablkctx->aes_generic; + memcpy(iv, reqctx->iv, AES_BLOCK_SIZE); + + keylen = ablkctx->enckey_len / 2; + key = ablkctx->key + keylen; + ret = crypto_cipher_setkey(cipher, key, keylen); + if (ret) + goto out; + crypto_cipher_encrypt_one(cipher, iv, iv); + for (i = 0; i < round8; i++) + gf128mul_x8_ble((le128 *)iv, (le128 *)iv); + + for (i = 0; i < (round % 8); i++) + gf128mul_x_ble((le128 *)iv, (le128 *)iv); + + if (!isfinal) + crypto_cipher_decrypt_one(cipher, iv, iv); +out: + return ret; +} + +static int chcr_update_cipher_iv(struct ablkcipher_request *req, + struct cpl_fw6_pld *fw6_pld, u8 *iv) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req); + int subtype = get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)); + int ret = 0; + + if (subtype == CRYPTO_ALG_SUB_TYPE_CTR) + ctr_add_iv(iv, req->info, (reqctx->processed / + AES_BLOCK_SIZE)); + else if (subtype == CRYPTO_ALG_SUB_TYPE_CTR_RFC3686) + *(__be32 *)(reqctx->iv + CTR_RFC3686_NONCE_SIZE + + CTR_RFC3686_IV_SIZE) = cpu_to_be32((reqctx->processed / + AES_BLOCK_SIZE) + 1); + else if (subtype == CRYPTO_ALG_SUB_TYPE_XTS) + ret = chcr_update_tweak(req, iv, 0); + else if (subtype == CRYPTO_ALG_SUB_TYPE_CBC) { + if (reqctx->op) + /*Updated before sending last WR*/ + memcpy(iv, req->info, AES_BLOCK_SIZE); + else + memcpy(iv, &fw6_pld->data[2], AES_BLOCK_SIZE); + } + + return ret; + +} + +/* We need separate function for final iv because in rfc3686 Initial counter + * starts from 1 and buffer size of iv is 8 byte only which remains constant + * for subsequent update requests + */ + +static int chcr_final_cipher_iv(struct ablkcipher_request *req, + struct cpl_fw6_pld *fw6_pld, u8 *iv) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req); + int subtype = get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)); + int ret = 0; + + if (subtype == CRYPTO_ALG_SUB_TYPE_CTR) + ctr_add_iv(iv, req->info, (reqctx->processed / + AES_BLOCK_SIZE)); + else if (subtype == CRYPTO_ALG_SUB_TYPE_XTS) + ret = chcr_update_tweak(req, iv, 1); + else if (subtype == CRYPTO_ALG_SUB_TYPE_CBC) { + /*Already updated for Decrypt*/ + if (!reqctx->op) + memcpy(iv, &fw6_pld->data[2], AES_BLOCK_SIZE); + + } + return ret; + +} + +static int chcr_handle_cipher_resp(struct ablkcipher_request *req, + unsigned char *input, int err) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct uld_ctx *u_ctx = ULD_CTX(c_ctx(tfm)); + struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(tfm)); + struct sk_buff *skb; + struct cpl_fw6_pld *fw6_pld = (struct cpl_fw6_pld *)input; + struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req); + struct cipher_wr_param wrparam; + int bytes; + + if (err) + goto unmap; + if (req->nbytes == reqctx->processed) { + chcr_cipher_dma_unmap(&ULD_CTX(c_ctx(tfm))->lldi.pdev->dev, + req); + err = chcr_final_cipher_iv(req, fw6_pld, req->info); + goto complete; + } + + if (!reqctx->imm) { + bytes = chcr_sg_ent_in_wr(reqctx->srcsg, reqctx->dstsg, 0, + CIP_SPACE_LEFT(ablkctx->enckey_len), + reqctx->src_ofst, reqctx->dst_ofst); + if ((bytes + reqctx->processed) >= req->nbytes) + bytes = req->nbytes - reqctx->processed; + else + bytes = rounddown(bytes, 16); + } else { + /*CTR mode counter overfloa*/ + bytes = req->nbytes - reqctx->processed; + } + err = chcr_update_cipher_iv(req, fw6_pld, reqctx->iv); + if (err) + goto unmap; + + if (unlikely(bytes == 0)) { + chcr_cipher_dma_unmap(&ULD_CTX(c_ctx(tfm))->lldi.pdev->dev, + req); + err = chcr_cipher_fallback(ablkctx->sw_cipher, + req->base.flags, + req->src, + req->dst, + req->nbytes, + req->info, + reqctx->op); + goto complete; + } + + if (get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) == + CRYPTO_ALG_SUB_TYPE_CTR) + bytes = adjust_ctr_overflow(reqctx->iv, bytes); + wrparam.qid = u_ctx->lldi.rxq_ids[c_ctx(tfm)->rx_qidx]; + wrparam.req = req; + wrparam.bytes = bytes; + skb = create_cipher_wr(&wrparam); + if (IS_ERR(skb)) { + pr_err("chcr : %s : Failed to form WR. No memory\n", __func__); + err = PTR_ERR(skb); + goto unmap; + } + skb->dev = u_ctx->lldi.ports[0]; + set_wr_txq(skb, CPL_PRIORITY_DATA, c_ctx(tfm)->tx_qidx); + chcr_send_wr(skb); + reqctx->last_req_len = bytes; + reqctx->processed += bytes; + return 0; +unmap: + chcr_cipher_dma_unmap(&ULD_CTX(c_ctx(tfm))->lldi.pdev->dev, req); +complete: + req->base.complete(&req->base, err); + return err; +} + +static int process_cipher(struct ablkcipher_request *req, + unsigned short qid, + struct sk_buff **skb, + unsigned short op_type) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + unsigned int ivsize = crypto_ablkcipher_ivsize(tfm); + struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req); + struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(tfm)); + struct cipher_wr_param wrparam; + int bytes, err = -EINVAL; + + reqctx->processed = 0; + if (!req->info) + goto error; + if ((ablkctx->enckey_len == 0) || (ivsize > AES_BLOCK_SIZE) || + (req->nbytes == 0) || + (req->nbytes % crypto_ablkcipher_blocksize(tfm))) { + pr_err("AES: Invalid value of Key Len %d nbytes %d IV Len %d\n", + ablkctx->enckey_len, req->nbytes, ivsize); + goto error; + } + chcr_cipher_dma_map(&ULD_CTX(c_ctx(tfm))->lldi.pdev->dev, req); + if (req->nbytes < (SGE_MAX_WR_LEN - (sizeof(struct chcr_wr) + + AES_MIN_KEY_SIZE + + sizeof(struct cpl_rx_phys_dsgl) + + /*Min dsgl size*/ + 32))) { + /* Can be sent as Imm*/ + unsigned int dnents = 0, transhdr_len, phys_dsgl, kctx_len; + + dnents = sg_nents_xlen(req->dst, req->nbytes, + CHCR_DST_SG_SIZE, 0); + phys_dsgl = get_space_for_phys_dsgl(dnents); + kctx_len = roundup(ablkctx->enckey_len, 16); + transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, phys_dsgl); + reqctx->imm = (transhdr_len + IV + req->nbytes) <= + SGE_MAX_WR_LEN; + bytes = IV + req->nbytes; + + } else { + reqctx->imm = 0; + } + + if (!reqctx->imm) { + bytes = chcr_sg_ent_in_wr(req->src, req->dst, 0, + CIP_SPACE_LEFT(ablkctx->enckey_len), + 0, 0); + if ((bytes + reqctx->processed) >= req->nbytes) + bytes = req->nbytes - reqctx->processed; + else + bytes = rounddown(bytes, 16); + } else { + bytes = req->nbytes; + } + if (get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) == + CRYPTO_ALG_SUB_TYPE_CTR) { + bytes = adjust_ctr_overflow(req->info, bytes); + } + if (get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) == + CRYPTO_ALG_SUB_TYPE_CTR_RFC3686) { + memcpy(reqctx->iv, ablkctx->nonce, CTR_RFC3686_NONCE_SIZE); + memcpy(reqctx->iv + CTR_RFC3686_NONCE_SIZE, req->info, + CTR_RFC3686_IV_SIZE); + + /* initialize counter portion of counter block */ + *(__be32 *)(reqctx->iv + CTR_RFC3686_NONCE_SIZE + + CTR_RFC3686_IV_SIZE) = cpu_to_be32(1); + + } else { + + memcpy(reqctx->iv, req->info, IV); + } + if (unlikely(bytes == 0)) { + chcr_cipher_dma_unmap(&ULD_CTX(c_ctx(tfm))->lldi.pdev->dev, + req); + err = chcr_cipher_fallback(ablkctx->sw_cipher, + req->base.flags, + req->src, + req->dst, + req->nbytes, + reqctx->iv, + op_type); + goto error; + } + reqctx->op = op_type; + reqctx->srcsg = req->src; + reqctx->dstsg = req->dst; + reqctx->src_ofst = 0; + reqctx->dst_ofst = 0; + wrparam.qid = qid; + wrparam.req = req; + wrparam.bytes = bytes; + *skb = create_cipher_wr(&wrparam); + if (IS_ERR(*skb)) { + err = PTR_ERR(*skb); + goto unmap; + } + reqctx->processed = bytes; + reqctx->last_req_len = bytes; + + return 0; +unmap: + chcr_cipher_dma_unmap(&ULD_CTX(c_ctx(tfm))->lldi.pdev->dev, req); +error: + return err; +} + +static int chcr_aes_encrypt(struct ablkcipher_request *req) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct sk_buff *skb = NULL; + int err, isfull = 0; + struct uld_ctx *u_ctx = ULD_CTX(c_ctx(tfm)); + + if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0], + c_ctx(tfm)->tx_qidx))) { + isfull = 1; + if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) + return -ENOSPC; + } + + err = process_cipher(req, u_ctx->lldi.rxq_ids[c_ctx(tfm)->rx_qidx], + &skb, CHCR_ENCRYPT_OP); + if (err || !skb) + return err; + skb->dev = u_ctx->lldi.ports[0]; + set_wr_txq(skb, CPL_PRIORITY_DATA, c_ctx(tfm)->tx_qidx); + chcr_send_wr(skb); + return isfull ? -EBUSY : -EINPROGRESS; +} + +static int chcr_aes_decrypt(struct ablkcipher_request *req) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct uld_ctx *u_ctx = ULD_CTX(c_ctx(tfm)); + struct sk_buff *skb = NULL; + int err, isfull = 0; + + if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0], + c_ctx(tfm)->tx_qidx))) { + isfull = 1; + if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) + return -ENOSPC; + } + + err = process_cipher(req, u_ctx->lldi.rxq_ids[c_ctx(tfm)->rx_qidx], + &skb, CHCR_DECRYPT_OP); + if (err || !skb) + return err; + skb->dev = u_ctx->lldi.ports[0]; + set_wr_txq(skb, CPL_PRIORITY_DATA, c_ctx(tfm)->tx_qidx); + chcr_send_wr(skb); + return isfull ? -EBUSY : -EINPROGRESS; +} + +static int chcr_device_init(struct chcr_context *ctx) +{ + struct uld_ctx *u_ctx = NULL; + struct adapter *adap; + unsigned int id; + int txq_perchan, txq_idx, ntxq; + int err = 0, rxq_perchan, rxq_idx; + + id = smp_processor_id(); + if (!ctx->dev) { + u_ctx = assign_chcr_device(); + if (!u_ctx) { + pr_err("chcr device assignment fails\n"); + goto out; + } + ctx->dev = u_ctx->dev; + adap = padap(ctx->dev); + ntxq = min_not_zero((unsigned int)u_ctx->lldi.nrxq, + adap->vres.ncrypto_fc); + rxq_perchan = u_ctx->lldi.nrxq / u_ctx->lldi.nchan; + txq_perchan = ntxq / u_ctx->lldi.nchan; + spin_lock(&ctx->dev->lock_chcr_dev); + ctx->tx_chan_id = ctx->dev->tx_channel_id; + ctx->dev->tx_channel_id = !ctx->dev->tx_channel_id; + ctx->dev->rx_channel_id = 0; + spin_unlock(&ctx->dev->lock_chcr_dev); + rxq_idx = ctx->tx_chan_id * rxq_perchan; + rxq_idx += id % rxq_perchan; + txq_idx = ctx->tx_chan_id * txq_perchan; + txq_idx += id % txq_perchan; + ctx->rx_qidx = rxq_idx; + ctx->tx_qidx = txq_idx; + /* Channel Id used by SGE to forward packet to Host. + * Same value should be used in cpl_fw6_pld RSS_CH field + * by FW. Driver programs PCI channel ID to be used in fw + * at the time of queue allocation with value "pi->tx_chan" + */ + ctx->pci_chan_id = txq_idx / txq_perchan; + } +out: + return err; +} + +static int chcr_cra_init(struct crypto_tfm *tfm) +{ + struct crypto_alg *alg = tfm->__crt_alg; + struct chcr_context *ctx = crypto_tfm_ctx(tfm); + struct ablk_ctx *ablkctx = ABLK_CTX(ctx); + + ablkctx->sw_cipher = crypto_alloc_skcipher(alg->cra_name, 0, + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(ablkctx->sw_cipher)) { + pr_err("failed to allocate fallback for %s\n", alg->cra_name); + return PTR_ERR(ablkctx->sw_cipher); + } + + if (get_cryptoalg_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_XTS) { + /* To update tweak*/ + ablkctx->aes_generic = crypto_alloc_cipher("aes-generic", 0, 0); + if (IS_ERR(ablkctx->aes_generic)) { + pr_err("failed to allocate aes cipher for tweak\n"); + return PTR_ERR(ablkctx->aes_generic); + } + } else + ablkctx->aes_generic = NULL; + + tfm->crt_ablkcipher.reqsize = sizeof(struct chcr_blkcipher_req_ctx); + return chcr_device_init(crypto_tfm_ctx(tfm)); +} + +static int chcr_rfc3686_init(struct crypto_tfm *tfm) +{ + struct crypto_alg *alg = tfm->__crt_alg; + struct chcr_context *ctx = crypto_tfm_ctx(tfm); + struct ablk_ctx *ablkctx = ABLK_CTX(ctx); + + /*RFC3686 initialises IV counter value to 1, rfc3686(ctr(aes)) + * cannot be used as fallback in chcr_handle_cipher_response + */ + ablkctx->sw_cipher = crypto_alloc_skcipher("ctr(aes)", 0, + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(ablkctx->sw_cipher)) { + pr_err("failed to allocate fallback for %s\n", alg->cra_name); + return PTR_ERR(ablkctx->sw_cipher); + } + tfm->crt_ablkcipher.reqsize = sizeof(struct chcr_blkcipher_req_ctx); + return chcr_device_init(crypto_tfm_ctx(tfm)); +} + + +static void chcr_cra_exit(struct crypto_tfm *tfm) +{ + struct chcr_context *ctx = crypto_tfm_ctx(tfm); + struct ablk_ctx *ablkctx = ABLK_CTX(ctx); + + crypto_free_skcipher(ablkctx->sw_cipher); + if (ablkctx->aes_generic) + crypto_free_cipher(ablkctx->aes_generic); +} + +static int get_alg_config(struct algo_param *params, + unsigned int auth_size) +{ + switch (auth_size) { + case SHA1_DIGEST_SIZE: + params->mk_size = CHCR_KEYCTX_MAC_KEY_SIZE_160; + params->auth_mode = CHCR_SCMD_AUTH_MODE_SHA1; + params->result_size = SHA1_DIGEST_SIZE; + break; + case SHA224_DIGEST_SIZE: + params->mk_size = CHCR_KEYCTX_MAC_KEY_SIZE_256; + params->auth_mode = CHCR_SCMD_AUTH_MODE_SHA224; + params->result_size = SHA256_DIGEST_SIZE; + break; + case SHA256_DIGEST_SIZE: + params->mk_size = CHCR_KEYCTX_MAC_KEY_SIZE_256; + params->auth_mode = CHCR_SCMD_AUTH_MODE_SHA256; + params->result_size = SHA256_DIGEST_SIZE; + break; + case SHA384_DIGEST_SIZE: + params->mk_size = CHCR_KEYCTX_MAC_KEY_SIZE_512; + params->auth_mode = CHCR_SCMD_AUTH_MODE_SHA512_384; + params->result_size = SHA512_DIGEST_SIZE; + break; + case SHA512_DIGEST_SIZE: + params->mk_size = CHCR_KEYCTX_MAC_KEY_SIZE_512; + params->auth_mode = CHCR_SCMD_AUTH_MODE_SHA512_512; + params->result_size = SHA512_DIGEST_SIZE; + break; + default: + pr_err("chcr : ERROR, unsupported digest size\n"); + return -EINVAL; + } + return 0; +} + +static inline void chcr_free_shash(struct crypto_shash *base_hash) +{ + crypto_free_shash(base_hash); +} + +/** + * create_hash_wr - Create hash work request + * @req - Cipher req base + */ +static struct sk_buff *create_hash_wr(struct ahash_request *req, + struct hash_wr_param *param) +{ + struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(req); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct hmac_ctx *hmacctx = HMAC_CTX(h_ctx(tfm)); + struct sk_buff *skb = NULL; + struct uld_ctx *u_ctx = ULD_CTX(h_ctx(tfm)); + struct chcr_wr *chcr_req; + struct ulptx_sgl *ulptx; + unsigned int nents = 0, transhdr_len; + unsigned int temp = 0; + gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : + GFP_ATOMIC; + struct adapter *adap = padap(h_ctx(tfm)->dev); + int error = 0; + + transhdr_len = HASH_TRANSHDR_SIZE(param->kctx_len); + req_ctx->hctx_wr.imm = (transhdr_len + param->bfr_len + + param->sg_len) <= SGE_MAX_WR_LEN; + nents = sg_nents_xlen(req_ctx->hctx_wr.srcsg, param->sg_len, + CHCR_SRC_SG_SIZE, req_ctx->hctx_wr.src_ofst); + nents += param->bfr_len ? 1 : 0; + transhdr_len += req_ctx->hctx_wr.imm ? roundup(param->bfr_len + + param->sg_len, 16) : (sgl_len(nents) * 8); + transhdr_len = roundup(transhdr_len, 16); + + skb = alloc_skb(transhdr_len, flags); + if (!skb) + return ERR_PTR(-ENOMEM); + chcr_req = __skb_put_zero(skb, transhdr_len); + + chcr_req->sec_cpl.op_ivinsrtofst = + FILL_SEC_CPL_OP_IVINSR(h_ctx(tfm)->dev->rx_channel_id, 2, 0); + chcr_req->sec_cpl.pldlen = htonl(param->bfr_len + param->sg_len); + + chcr_req->sec_cpl.aadstart_cipherstop_hi = + FILL_SEC_CPL_CIPHERSTOP_HI(0, 0, 0, 0); + chcr_req->sec_cpl.cipherstop_lo_authinsert = + FILL_SEC_CPL_AUTHINSERT(0, 1, 0, 0); + chcr_req->sec_cpl.seqno_numivs = + FILL_SEC_CPL_SCMD0_SEQNO(0, 0, 0, param->alg_prm.auth_mode, + param->opad_needed, 0); + + chcr_req->sec_cpl.ivgen_hdrlen = + FILL_SEC_CPL_IVGEN_HDRLEN(param->last, param->more, 0, 1, 0, 0); + + memcpy(chcr_req->key_ctx.key, req_ctx->partial_hash, + param->alg_prm.result_size); + + if (param->opad_needed) + memcpy(chcr_req->key_ctx.key + + ((param->alg_prm.result_size <= 32) ? 32 : + CHCR_HASH_MAX_DIGEST_SIZE), + hmacctx->opad, param->alg_prm.result_size); + + chcr_req->key_ctx.ctx_hdr = FILL_KEY_CTX_HDR(CHCR_KEYCTX_NO_KEY, + param->alg_prm.mk_size, 0, + param->opad_needed, + ((param->kctx_len + + sizeof(chcr_req->key_ctx)) >> 4)); + chcr_req->sec_cpl.scmd1 = cpu_to_be64((u64)param->scmd1); + ulptx = (struct ulptx_sgl *)((u8 *)(chcr_req + 1) + param->kctx_len + + DUMMY_BYTES); + if (param->bfr_len != 0) { + req_ctx->hctx_wr.dma_addr = + dma_map_single(&u_ctx->lldi.pdev->dev, req_ctx->reqbfr, + param->bfr_len, DMA_TO_DEVICE); + if (dma_mapping_error(&u_ctx->lldi.pdev->dev, + req_ctx->hctx_wr. dma_addr)) { + error = -ENOMEM; + goto err; + } + req_ctx->hctx_wr.dma_len = param->bfr_len; + } else { + req_ctx->hctx_wr.dma_addr = 0; + } + chcr_add_hash_src_ent(req, ulptx, param); + /* Request upto max wr size */ + temp = param->kctx_len + DUMMY_BYTES + (req_ctx->hctx_wr.imm ? + (param->sg_len + param->bfr_len) : 0); + atomic_inc(&adap->chcr_stats.digest_rqst); + create_wreq(h_ctx(tfm), chcr_req, &req->base, req_ctx->hctx_wr.imm, + param->hash_size, transhdr_len, + temp, 0); + req_ctx->hctx_wr.skb = skb; + return skb; +err: + kfree_skb(skb); + return ERR_PTR(error); +} + +static int chcr_ahash_update(struct ahash_request *req) +{ + struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(req); + struct crypto_ahash *rtfm = crypto_ahash_reqtfm(req); + struct uld_ctx *u_ctx = NULL; + struct sk_buff *skb; + u8 remainder = 0, bs; + unsigned int nbytes = req->nbytes; + struct hash_wr_param params; + int error, isfull = 0; + + bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm)); + u_ctx = ULD_CTX(h_ctx(rtfm)); + if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0], + h_ctx(rtfm)->tx_qidx))) { + isfull = 1; + if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) + return -ENOSPC; + } + + if (nbytes + req_ctx->reqlen >= bs) { + remainder = (nbytes + req_ctx->reqlen) % bs; + nbytes = nbytes + req_ctx->reqlen - remainder; + } else { + sg_pcopy_to_buffer(req->src, sg_nents(req->src), req_ctx->reqbfr + + req_ctx->reqlen, nbytes, 0); + req_ctx->reqlen += nbytes; + return 0; + } + chcr_init_hctx_per_wr(req_ctx); + error = chcr_hash_dma_map(&u_ctx->lldi.pdev->dev, req); + if (error) + return -ENOMEM; + get_alg_config(¶ms.alg_prm, crypto_ahash_digestsize(rtfm)); + params.kctx_len = roundup(params.alg_prm.result_size, 16); + params.sg_len = chcr_hash_ent_in_wr(req->src, !!req_ctx->reqlen, + HASH_SPACE_LEFT(params.kctx_len), 0); + if (params.sg_len > req->nbytes) + params.sg_len = req->nbytes; + params.sg_len = rounddown(params.sg_len + req_ctx->reqlen, bs) - + req_ctx->reqlen; + params.opad_needed = 0; + params.more = 1; + params.last = 0; + params.bfr_len = req_ctx->reqlen; + params.scmd1 = 0; + req_ctx->hctx_wr.srcsg = req->src; + + params.hash_size = params.alg_prm.result_size; + req_ctx->data_len += params.sg_len + params.bfr_len; + skb = create_hash_wr(req, ¶ms); + if (IS_ERR(skb)) { + error = PTR_ERR(skb); + goto unmap; + } + + req_ctx->hctx_wr.processed += params.sg_len; + if (remainder) { + /* Swap buffers */ + swap(req_ctx->reqbfr, req_ctx->skbfr); + sg_pcopy_to_buffer(req->src, sg_nents(req->src), + req_ctx->reqbfr, remainder, req->nbytes - + remainder); + } + req_ctx->reqlen = remainder; + skb->dev = u_ctx->lldi.ports[0]; + set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx); + chcr_send_wr(skb); + + return isfull ? -EBUSY : -EINPROGRESS; +unmap: + chcr_hash_dma_unmap(&u_ctx->lldi.pdev->dev, req); + return error; +} + +static void create_last_hash_block(char *bfr_ptr, unsigned int bs, u64 scmd1) +{ + memset(bfr_ptr, 0, bs); + *bfr_ptr = 0x80; + if (bs == 64) + *(__be64 *)(bfr_ptr + 56) = cpu_to_be64(scmd1 << 3); + else + *(__be64 *)(bfr_ptr + 120) = cpu_to_be64(scmd1 << 3); +} + +static int chcr_ahash_final(struct ahash_request *req) +{ + struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(req); + struct crypto_ahash *rtfm = crypto_ahash_reqtfm(req); + struct hash_wr_param params; + struct sk_buff *skb; + struct uld_ctx *u_ctx = NULL; + u8 bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm)); + + chcr_init_hctx_per_wr(req_ctx); + u_ctx = ULD_CTX(h_ctx(rtfm)); + if (is_hmac(crypto_ahash_tfm(rtfm))) + params.opad_needed = 1; + else + params.opad_needed = 0; + params.sg_len = 0; + req_ctx->hctx_wr.isfinal = 1; + get_alg_config(¶ms.alg_prm, crypto_ahash_digestsize(rtfm)); + params.kctx_len = roundup(params.alg_prm.result_size, 16); + if (is_hmac(crypto_ahash_tfm(rtfm))) { + params.opad_needed = 1; + params.kctx_len *= 2; + } else { + params.opad_needed = 0; + } + + req_ctx->hctx_wr.result = 1; + params.bfr_len = req_ctx->reqlen; + req_ctx->data_len += params.bfr_len + params.sg_len; + req_ctx->hctx_wr.srcsg = req->src; + if (req_ctx->reqlen == 0) { + create_last_hash_block(req_ctx->reqbfr, bs, req_ctx->data_len); + params.last = 0; + params.more = 1; + params.scmd1 = 0; + params.bfr_len = bs; + + } else { + params.scmd1 = req_ctx->data_len; + params.last = 1; + params.more = 0; + } + params.hash_size = crypto_ahash_digestsize(rtfm); + skb = create_hash_wr(req, ¶ms); + if (IS_ERR(skb)) + return PTR_ERR(skb); + req_ctx->reqlen = 0; + skb->dev = u_ctx->lldi.ports[0]; + set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx); + chcr_send_wr(skb); + return -EINPROGRESS; +} + +static int chcr_ahash_finup(struct ahash_request *req) +{ + struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(req); + struct crypto_ahash *rtfm = crypto_ahash_reqtfm(req); + struct uld_ctx *u_ctx = NULL; + struct sk_buff *skb; + struct hash_wr_param params; + u8 bs; + int error, isfull = 0; + + bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm)); + u_ctx = ULD_CTX(h_ctx(rtfm)); + + if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0], + h_ctx(rtfm)->tx_qidx))) { + isfull = 1; + if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) + return -ENOSPC; + } + chcr_init_hctx_per_wr(req_ctx); + error = chcr_hash_dma_map(&u_ctx->lldi.pdev->dev, req); + if (error) + return -ENOMEM; + + get_alg_config(¶ms.alg_prm, crypto_ahash_digestsize(rtfm)); + params.kctx_len = roundup(params.alg_prm.result_size, 16); + if (is_hmac(crypto_ahash_tfm(rtfm))) { + params.kctx_len *= 2; + params.opad_needed = 1; + } else { + params.opad_needed = 0; + } + + params.sg_len = chcr_hash_ent_in_wr(req->src, !!req_ctx->reqlen, + HASH_SPACE_LEFT(params.kctx_len), 0); + if (params.sg_len < req->nbytes) { + if (is_hmac(crypto_ahash_tfm(rtfm))) { + params.kctx_len /= 2; + params.opad_needed = 0; + } + params.last = 0; + params.more = 1; + params.sg_len = rounddown(params.sg_len + req_ctx->reqlen, bs) + - req_ctx->reqlen; + params.hash_size = params.alg_prm.result_size; + params.scmd1 = 0; + } else { + params.last = 1; + params.more = 0; + params.sg_len = req->nbytes; + params.hash_size = crypto_ahash_digestsize(rtfm); + params.scmd1 = req_ctx->data_len + req_ctx->reqlen + + params.sg_len; + } + params.bfr_len = req_ctx->reqlen; + req_ctx->data_len += params.bfr_len + params.sg_len; + req_ctx->hctx_wr.result = 1; + req_ctx->hctx_wr.srcsg = req->src; + if ((req_ctx->reqlen + req->nbytes) == 0) { + create_last_hash_block(req_ctx->reqbfr, bs, req_ctx->data_len); + params.last = 0; + params.more = 1; + params.scmd1 = 0; + params.bfr_len = bs; + } + skb = create_hash_wr(req, ¶ms); + if (IS_ERR(skb)) { + error = PTR_ERR(skb); + goto unmap; + } + req_ctx->reqlen = 0; + req_ctx->hctx_wr.processed += params.sg_len; + skb->dev = u_ctx->lldi.ports[0]; + set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx); + chcr_send_wr(skb); + + return isfull ? -EBUSY : -EINPROGRESS; +unmap: + chcr_hash_dma_unmap(&u_ctx->lldi.pdev->dev, req); + return error; +} + +static int chcr_ahash_digest(struct ahash_request *req) +{ + struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(req); + struct crypto_ahash *rtfm = crypto_ahash_reqtfm(req); + struct uld_ctx *u_ctx = NULL; + struct sk_buff *skb; + struct hash_wr_param params; + u8 bs; + int error, isfull = 0; + + rtfm->init(req); + bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm)); + + u_ctx = ULD_CTX(h_ctx(rtfm)); + if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0], + h_ctx(rtfm)->tx_qidx))) { + isfull = 1; + if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) + return -ENOSPC; + } + + chcr_init_hctx_per_wr(req_ctx); + error = chcr_hash_dma_map(&u_ctx->lldi.pdev->dev, req); + if (error) + return -ENOMEM; + + get_alg_config(¶ms.alg_prm, crypto_ahash_digestsize(rtfm)); + params.kctx_len = roundup(params.alg_prm.result_size, 16); + if (is_hmac(crypto_ahash_tfm(rtfm))) { + params.kctx_len *= 2; + params.opad_needed = 1; + } else { + params.opad_needed = 0; + } + params.sg_len = chcr_hash_ent_in_wr(req->src, !!req_ctx->reqlen, + HASH_SPACE_LEFT(params.kctx_len), 0); + if (params.sg_len < req->nbytes) { + if (is_hmac(crypto_ahash_tfm(rtfm))) { + params.kctx_len /= 2; + params.opad_needed = 0; + } + params.last = 0; + params.more = 1; + params.scmd1 = 0; + params.sg_len = rounddown(params.sg_len, bs); + params.hash_size = params.alg_prm.result_size; + } else { + params.sg_len = req->nbytes; + params.hash_size = crypto_ahash_digestsize(rtfm); + params.last = 1; + params.more = 0; + params.scmd1 = req->nbytes + req_ctx->data_len; + + } + params.bfr_len = 0; + req_ctx->hctx_wr.result = 1; + req_ctx->hctx_wr.srcsg = req->src; + req_ctx->data_len += params.bfr_len + params.sg_len; + + if (req->nbytes == 0) { + create_last_hash_block(req_ctx->reqbfr, bs, 0); + params.more = 1; + params.bfr_len = bs; + } + + skb = create_hash_wr(req, ¶ms); + if (IS_ERR(skb)) { + error = PTR_ERR(skb); + goto unmap; + } + req_ctx->hctx_wr.processed += params.sg_len; + skb->dev = u_ctx->lldi.ports[0]; + set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx); + chcr_send_wr(skb); + return isfull ? -EBUSY : -EINPROGRESS; +unmap: + chcr_hash_dma_unmap(&u_ctx->lldi.pdev->dev, req); + return error; +} + +static int chcr_ahash_continue(struct ahash_request *req) +{ + struct chcr_ahash_req_ctx *reqctx = ahash_request_ctx(req); + struct chcr_hctx_per_wr *hctx_wr = &reqctx->hctx_wr; + struct crypto_ahash *rtfm = crypto_ahash_reqtfm(req); + struct uld_ctx *u_ctx = NULL; + struct sk_buff *skb; + struct hash_wr_param params; + u8 bs; + int error; + + bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm)); + u_ctx = ULD_CTX(h_ctx(rtfm)); + get_alg_config(¶ms.alg_prm, crypto_ahash_digestsize(rtfm)); + params.kctx_len = roundup(params.alg_prm.result_size, 16); + if (is_hmac(crypto_ahash_tfm(rtfm))) { + params.kctx_len *= 2; + params.opad_needed = 1; + } else { + params.opad_needed = 0; + } + params.sg_len = chcr_hash_ent_in_wr(hctx_wr->srcsg, 0, + HASH_SPACE_LEFT(params.kctx_len), + hctx_wr->src_ofst); + if ((params.sg_len + hctx_wr->processed) > req->nbytes) + params.sg_len = req->nbytes - hctx_wr->processed; + if (!hctx_wr->result || + ((params.sg_len + hctx_wr->processed) < req->nbytes)) { + if (is_hmac(crypto_ahash_tfm(rtfm))) { + params.kctx_len /= 2; + params.opad_needed = 0; + } + params.last = 0; + params.more = 1; + params.sg_len = rounddown(params.sg_len, bs); + params.hash_size = params.alg_prm.result_size; + params.scmd1 = 0; + } else { + params.last = 1; + params.more = 0; + params.hash_size = crypto_ahash_digestsize(rtfm); + params.scmd1 = reqctx->data_len + params.sg_len; + } + params.bfr_len = 0; + reqctx->data_len += params.sg_len; + skb = create_hash_wr(req, ¶ms); + if (IS_ERR(skb)) { + error = PTR_ERR(skb); + goto err; + } + hctx_wr->processed += params.sg_len; + skb->dev = u_ctx->lldi.ports[0]; + set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx); + chcr_send_wr(skb); + return 0; +err: + return error; +} + +static inline void chcr_handle_ahash_resp(struct ahash_request *req, + unsigned char *input, + int err) +{ + struct chcr_ahash_req_ctx *reqctx = ahash_request_ctx(req); + struct chcr_hctx_per_wr *hctx_wr = &reqctx->hctx_wr; + int digestsize, updated_digestsize; + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct uld_ctx *u_ctx = ULD_CTX(h_ctx(tfm)); + + if (input == NULL) + goto out; + digestsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req)); + updated_digestsize = digestsize; + if (digestsize == SHA224_DIGEST_SIZE) + updated_digestsize = SHA256_DIGEST_SIZE; + else if (digestsize == SHA384_DIGEST_SIZE) + updated_digestsize = SHA512_DIGEST_SIZE; + + if (hctx_wr->dma_addr) { + dma_unmap_single(&u_ctx->lldi.pdev->dev, hctx_wr->dma_addr, + hctx_wr->dma_len, DMA_TO_DEVICE); + hctx_wr->dma_addr = 0; + } + if (hctx_wr->isfinal || ((hctx_wr->processed + reqctx->reqlen) == + req->nbytes)) { + if (hctx_wr->result == 1) { + hctx_wr->result = 0; + memcpy(req->result, input + sizeof(struct cpl_fw6_pld), + digestsize); + } else { + memcpy(reqctx->partial_hash, + input + sizeof(struct cpl_fw6_pld), + updated_digestsize); + + } + goto unmap; + } + memcpy(reqctx->partial_hash, input + sizeof(struct cpl_fw6_pld), + updated_digestsize); + + err = chcr_ahash_continue(req); + if (err) + goto unmap; + return; +unmap: + if (hctx_wr->is_sg_map) + chcr_hash_dma_unmap(&u_ctx->lldi.pdev->dev, req); + + +out: + req->base.complete(&req->base, err); +} + +/* + * chcr_handle_resp - Unmap the DMA buffers associated with the request + * @req: crypto request + */ +int chcr_handle_resp(struct crypto_async_request *req, unsigned char *input, + int err) +{ + struct crypto_tfm *tfm = req->tfm; + struct chcr_context *ctx = crypto_tfm_ctx(tfm); + struct adapter *adap = padap(ctx->dev); + + switch (tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK) { + case CRYPTO_ALG_TYPE_AEAD: + chcr_handle_aead_resp(aead_request_cast(req), input, err); + break; + + case CRYPTO_ALG_TYPE_ABLKCIPHER: + err = chcr_handle_cipher_resp(ablkcipher_request_cast(req), + input, err); + break; + + case CRYPTO_ALG_TYPE_AHASH: + chcr_handle_ahash_resp(ahash_request_cast(req), input, err); + } + atomic_inc(&adap->chcr_stats.complete); + return err; +} +static int chcr_ahash_export(struct ahash_request *areq, void *out) +{ + struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(areq); + struct chcr_ahash_req_ctx *state = out; + + state->reqlen = req_ctx->reqlen; + state->data_len = req_ctx->data_len; + memcpy(state->bfr1, req_ctx->reqbfr, req_ctx->reqlen); + memcpy(state->partial_hash, req_ctx->partial_hash, + CHCR_HASH_MAX_DIGEST_SIZE); + chcr_init_hctx_per_wr(state); + return 0; +} + +static int chcr_ahash_import(struct ahash_request *areq, const void *in) +{ + struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(areq); + struct chcr_ahash_req_ctx *state = (struct chcr_ahash_req_ctx *)in; + + req_ctx->reqlen = state->reqlen; + req_ctx->data_len = state->data_len; + req_ctx->reqbfr = req_ctx->bfr1; + req_ctx->skbfr = req_ctx->bfr2; + memcpy(req_ctx->bfr1, state->bfr1, CHCR_HASH_MAX_BLOCK_SIZE_128); + memcpy(req_ctx->partial_hash, state->partial_hash, + CHCR_HASH_MAX_DIGEST_SIZE); + chcr_init_hctx_per_wr(req_ctx); + return 0; +} + +static int chcr_ahash_setkey(struct crypto_ahash *tfm, const u8 *key, + unsigned int keylen) +{ + struct hmac_ctx *hmacctx = HMAC_CTX(h_ctx(tfm)); + unsigned int digestsize = crypto_ahash_digestsize(tfm); + unsigned int bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm)); + unsigned int i, err = 0, updated_digestsize; + + SHASH_DESC_ON_STACK(shash, hmacctx->base_hash); + + /* use the key to calculate the ipad and opad. ipad will sent with the + * first request's data. opad will be sent with the final hash result + * ipad in hmacctx->ipad and opad in hmacctx->opad location + */ + shash->tfm = hmacctx->base_hash; + shash->flags = crypto_shash_get_flags(hmacctx->base_hash); + if (keylen > bs) { + err = crypto_shash_digest(shash, key, keylen, + hmacctx->ipad); + if (err) + goto out; + keylen = digestsize; + } else { + memcpy(hmacctx->ipad, key, keylen); + } + memset(hmacctx->ipad + keylen, 0, bs - keylen); + memcpy(hmacctx->opad, hmacctx->ipad, bs); + + for (i = 0; i < bs / sizeof(int); i++) { + *((unsigned int *)(&hmacctx->ipad) + i) ^= IPAD_DATA; + *((unsigned int *)(&hmacctx->opad) + i) ^= OPAD_DATA; + } + + updated_digestsize = digestsize; + if (digestsize == SHA224_DIGEST_SIZE) + updated_digestsize = SHA256_DIGEST_SIZE; + else if (digestsize == SHA384_DIGEST_SIZE) + updated_digestsize = SHA512_DIGEST_SIZE; + err = chcr_compute_partial_hash(shash, hmacctx->ipad, + hmacctx->ipad, digestsize); + if (err) + goto out; + chcr_change_order(hmacctx->ipad, updated_digestsize); + + err = chcr_compute_partial_hash(shash, hmacctx->opad, + hmacctx->opad, digestsize); + if (err) + goto out; + chcr_change_order(hmacctx->opad, updated_digestsize); +out: + return err; +} + +static int chcr_aes_xts_setkey(struct crypto_ablkcipher *cipher, const u8 *key, + unsigned int key_len) +{ + struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(cipher)); + unsigned short context_size = 0; + int err; + + err = chcr_cipher_fallback_setkey(cipher, key, key_len); + if (err) + goto badkey_err; + + memcpy(ablkctx->key, key, key_len); + ablkctx->enckey_len = key_len; + get_aes_decrypt_key(ablkctx->rrkey, ablkctx->key, key_len << 2); + context_size = (KEY_CONTEXT_HDR_SALT_AND_PAD + key_len) >> 4; + ablkctx->key_ctx_hdr = + FILL_KEY_CTX_HDR((key_len == AES_KEYSIZE_256) ? + CHCR_KEYCTX_CIPHER_KEY_SIZE_128 : + CHCR_KEYCTX_CIPHER_KEY_SIZE_256, + CHCR_KEYCTX_NO_KEY, 1, + 0, context_size); + ablkctx->ciph_mode = CHCR_SCMD_CIPHER_MODE_AES_XTS; + return 0; +badkey_err: + crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN); + ablkctx->enckey_len = 0; + + return err; +} + +static int chcr_sha_init(struct ahash_request *areq) +{ + struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(areq); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + int digestsize = crypto_ahash_digestsize(tfm); + + req_ctx->data_len = 0; + req_ctx->reqlen = 0; + req_ctx->reqbfr = req_ctx->bfr1; + req_ctx->skbfr = req_ctx->bfr2; + copy_hash_init_values(req_ctx->partial_hash, digestsize); + + return 0; +} + +static int chcr_sha_cra_init(struct crypto_tfm *tfm) +{ + crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm), + sizeof(struct chcr_ahash_req_ctx)); + return chcr_device_init(crypto_tfm_ctx(tfm)); +} + +static int chcr_hmac_init(struct ahash_request *areq) +{ + struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(areq); + struct crypto_ahash *rtfm = crypto_ahash_reqtfm(areq); + struct hmac_ctx *hmacctx = HMAC_CTX(h_ctx(rtfm)); + unsigned int digestsize = crypto_ahash_digestsize(rtfm); + unsigned int bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm)); + + chcr_sha_init(areq); + req_ctx->data_len = bs; + if (is_hmac(crypto_ahash_tfm(rtfm))) { + if (digestsize == SHA224_DIGEST_SIZE) + memcpy(req_ctx->partial_hash, hmacctx->ipad, + SHA256_DIGEST_SIZE); + else if (digestsize == SHA384_DIGEST_SIZE) + memcpy(req_ctx->partial_hash, hmacctx->ipad, + SHA512_DIGEST_SIZE); + else + memcpy(req_ctx->partial_hash, hmacctx->ipad, + digestsize); + } + return 0; +} + +static int chcr_hmac_cra_init(struct crypto_tfm *tfm) +{ + struct chcr_context *ctx = crypto_tfm_ctx(tfm); + struct hmac_ctx *hmacctx = HMAC_CTX(ctx); + unsigned int digestsize = + crypto_ahash_digestsize(__crypto_ahash_cast(tfm)); + + crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm), + sizeof(struct chcr_ahash_req_ctx)); + hmacctx->base_hash = chcr_alloc_shash(digestsize); + if (IS_ERR(hmacctx->base_hash)) + return PTR_ERR(hmacctx->base_hash); + return chcr_device_init(crypto_tfm_ctx(tfm)); +} + +static void chcr_hmac_cra_exit(struct crypto_tfm *tfm) +{ + struct chcr_context *ctx = crypto_tfm_ctx(tfm); + struct hmac_ctx *hmacctx = HMAC_CTX(ctx); + + if (hmacctx->base_hash) { + chcr_free_shash(hmacctx->base_hash); + hmacctx->base_hash = NULL; + } +} + +inline void chcr_aead_common_exit(struct aead_request *req) +{ + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct uld_ctx *u_ctx = ULD_CTX(a_ctx(tfm)); + + chcr_aead_dma_unmap(&u_ctx->lldi.pdev->dev, req, reqctx->op); +} + +static int chcr_aead_common_init(struct aead_request *req) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + unsigned int authsize = crypto_aead_authsize(tfm); + int error = -EINVAL; + + /* validate key size */ + if (aeadctx->enckey_len == 0) + goto err; + if (reqctx->op && req->cryptlen < authsize) + goto err; + if (reqctx->b0_len) + reqctx->scratch_pad = reqctx->iv + IV; + else + reqctx->scratch_pad = NULL; + + error = chcr_aead_dma_map(&ULD_CTX(a_ctx(tfm))->lldi.pdev->dev, req, + reqctx->op); + if (error) { + error = -ENOMEM; + goto err; + } + reqctx->aad_nents = sg_nents_xlen(req->src, req->assoclen, + CHCR_SRC_SG_SIZE, 0); + reqctx->src_nents = sg_nents_xlen(req->src, req->cryptlen, + CHCR_SRC_SG_SIZE, req->assoclen); + return 0; +err: + return error; +} + +static int chcr_aead_need_fallback(struct aead_request *req, int dst_nents, + int aadmax, int wrlen, + unsigned short op_type) +{ + unsigned int authsize = crypto_aead_authsize(crypto_aead_reqtfm(req)); + + if (((req->cryptlen - (op_type ? authsize : 0)) == 0) || + dst_nents > MAX_DSGL_ENT || + (req->assoclen > aadmax) || + (wrlen > SGE_MAX_WR_LEN)) + return 1; + return 0; +} + +static int chcr_aead_fallback(struct aead_request *req, unsigned short op_type) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + struct aead_request *subreq = aead_request_ctx(req); + + aead_request_set_tfm(subreq, aeadctx->sw_cipher); + aead_request_set_callback(subreq, req->base.flags, + req->base.complete, req->base.data); + aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen, + req->iv); + aead_request_set_ad(subreq, req->assoclen); + return op_type ? crypto_aead_decrypt(subreq) : + crypto_aead_encrypt(subreq); +} + +static struct sk_buff *create_authenc_wr(struct aead_request *req, + unsigned short qid, + int size) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + struct chcr_authenc_ctx *actx = AUTHENC_CTX(aeadctx); + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + struct sk_buff *skb = NULL; + struct chcr_wr *chcr_req; + struct cpl_rx_phys_dsgl *phys_cpl; + struct ulptx_sgl *ulptx; + unsigned int transhdr_len; + unsigned int dst_size = 0, temp, subtype = get_aead_subtype(tfm); + unsigned int kctx_len = 0, dnents; + unsigned int assoclen = req->assoclen; + unsigned int authsize = crypto_aead_authsize(tfm); + int error = -EINVAL; + int null = 0; + gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : + GFP_ATOMIC; + struct adapter *adap = padap(a_ctx(tfm)->dev); + + if (req->cryptlen == 0) + return NULL; + + reqctx->b0_len = 0; + error = chcr_aead_common_init(req); + if (error) + return ERR_PTR(error); + + if (subtype == CRYPTO_ALG_SUB_TYPE_CBC_NULL || + subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) { + null = 1; + assoclen = 0; + reqctx->aad_nents = 0; + } + dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0); + dnents += sg_nents_xlen(req->dst, req->cryptlen + + (reqctx->op ? -authsize : authsize), CHCR_DST_SG_SIZE, + req->assoclen); + dnents += MIN_AUTH_SG; // For IV + + dst_size = get_space_for_phys_dsgl(dnents); + kctx_len = (ntohl(KEY_CONTEXT_CTX_LEN_V(aeadctx->key_ctx_hdr)) << 4) + - sizeof(chcr_req->key_ctx); + transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size); + reqctx->imm = (transhdr_len + assoclen + IV + req->cryptlen) < + SGE_MAX_WR_LEN; + temp = reqctx->imm ? roundup(assoclen + IV + req->cryptlen, 16) + : (sgl_len(reqctx->src_nents + reqctx->aad_nents + + MIN_GCM_SG) * 8); + transhdr_len += temp; + transhdr_len = roundup(transhdr_len, 16); + + if (chcr_aead_need_fallback(req, dnents, T6_MAX_AAD_SIZE, + transhdr_len, reqctx->op)) { + atomic_inc(&adap->chcr_stats.fallback); + chcr_aead_common_exit(req); + return ERR_PTR(chcr_aead_fallback(req, reqctx->op)); + } + skb = alloc_skb(SGE_MAX_WR_LEN, flags); + if (!skb) { + error = -ENOMEM; + goto err; + } + + chcr_req = __skb_put_zero(skb, transhdr_len); + + temp = (reqctx->op == CHCR_ENCRYPT_OP) ? 0 : authsize; + + /* + * Input order is AAD,IV and Payload. where IV should be included as + * the part of authdata. All other fields should be filled according + * to the hardware spec + */ + chcr_req->sec_cpl.op_ivinsrtofst = + FILL_SEC_CPL_OP_IVINSR(a_ctx(tfm)->dev->rx_channel_id, 2, + assoclen + 1); + chcr_req->sec_cpl.pldlen = htonl(assoclen + IV + req->cryptlen); + chcr_req->sec_cpl.aadstart_cipherstop_hi = FILL_SEC_CPL_CIPHERSTOP_HI( + assoclen ? 1 : 0, assoclen, + assoclen + IV + 1, + (temp & 0x1F0) >> 4); + chcr_req->sec_cpl.cipherstop_lo_authinsert = FILL_SEC_CPL_AUTHINSERT( + temp & 0xF, + null ? 0 : assoclen + IV + 1, + temp, temp); + if (subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL || + subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA) + temp = CHCR_SCMD_CIPHER_MODE_AES_CTR; + else + temp = CHCR_SCMD_CIPHER_MODE_AES_CBC; + chcr_req->sec_cpl.seqno_numivs = FILL_SEC_CPL_SCMD0_SEQNO(reqctx->op, + (reqctx->op == CHCR_ENCRYPT_OP) ? 1 : 0, + temp, + actx->auth_mode, aeadctx->hmac_ctrl, + IV >> 1); + chcr_req->sec_cpl.ivgen_hdrlen = FILL_SEC_CPL_IVGEN_HDRLEN(0, 0, 1, + 0, 0, dst_size); + + chcr_req->key_ctx.ctx_hdr = aeadctx->key_ctx_hdr; + if (reqctx->op == CHCR_ENCRYPT_OP || + subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA || + subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) + memcpy(chcr_req->key_ctx.key, aeadctx->key, + aeadctx->enckey_len); + else + memcpy(chcr_req->key_ctx.key, actx->dec_rrkey, + aeadctx->enckey_len); + + memcpy(chcr_req->key_ctx.key + roundup(aeadctx->enckey_len, 16), + actx->h_iopad, kctx_len - roundup(aeadctx->enckey_len, 16)); + if (subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA || + subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) { + memcpy(reqctx->iv, aeadctx->nonce, CTR_RFC3686_NONCE_SIZE); + memcpy(reqctx->iv + CTR_RFC3686_NONCE_SIZE, req->iv, + CTR_RFC3686_IV_SIZE); + *(__be32 *)(reqctx->iv + CTR_RFC3686_NONCE_SIZE + + CTR_RFC3686_IV_SIZE) = cpu_to_be32(1); + } else { + memcpy(reqctx->iv, req->iv, IV); + } + phys_cpl = (struct cpl_rx_phys_dsgl *)((u8 *)(chcr_req + 1) + kctx_len); + ulptx = (struct ulptx_sgl *)((u8 *)(phys_cpl + 1) + dst_size); + chcr_add_aead_dst_ent(req, phys_cpl, assoclen, qid); + chcr_add_aead_src_ent(req, ulptx, assoclen); + atomic_inc(&adap->chcr_stats.cipher_rqst); + temp = sizeof(struct cpl_rx_phys_dsgl) + dst_size + + kctx_len + (reqctx->imm ? (assoclen + IV + req->cryptlen) : 0); + create_wreq(a_ctx(tfm), chcr_req, &req->base, reqctx->imm, size, + transhdr_len, temp, 0); + reqctx->skb = skb; + + return skb; +err: + chcr_aead_common_exit(req); + + return ERR_PTR(error); +} + +int chcr_aead_dma_map(struct device *dev, + struct aead_request *req, + unsigned short op_type) +{ + int error; + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + unsigned int authsize = crypto_aead_authsize(tfm); + int dst_size; + + dst_size = req->assoclen + req->cryptlen + (op_type ? + -authsize : authsize); + if (!req->cryptlen || !dst_size) + return 0; + reqctx->iv_dma = dma_map_single(dev, reqctx->iv, (IV + reqctx->b0_len), + DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, reqctx->iv_dma)) + return -ENOMEM; + if (reqctx->b0_len) + reqctx->b0_dma = reqctx->iv_dma + IV; + else + reqctx->b0_dma = 0; + if (req->src == req->dst) { + error = dma_map_sg(dev, req->src, + sg_nents_for_len(req->src, dst_size), + DMA_BIDIRECTIONAL); + if (!error) + goto err; + } else { + error = dma_map_sg(dev, req->src, sg_nents(req->src), + DMA_TO_DEVICE); + if (!error) + goto err; + error = dma_map_sg(dev, req->dst, sg_nents(req->dst), + DMA_FROM_DEVICE); + if (!error) { + dma_unmap_sg(dev, req->src, sg_nents(req->src), + DMA_TO_DEVICE); + goto err; + } + } + + return 0; +err: + dma_unmap_single(dev, reqctx->iv_dma, IV, DMA_BIDIRECTIONAL); + return -ENOMEM; +} + +void chcr_aead_dma_unmap(struct device *dev, + struct aead_request *req, + unsigned short op_type) +{ + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + unsigned int authsize = crypto_aead_authsize(tfm); + int dst_size; + + dst_size = req->assoclen + req->cryptlen + (op_type ? + -authsize : authsize); + if (!req->cryptlen || !dst_size) + return; + + dma_unmap_single(dev, reqctx->iv_dma, (IV + reqctx->b0_len), + DMA_BIDIRECTIONAL); + if (req->src == req->dst) { + dma_unmap_sg(dev, req->src, sg_nents(req->src), + DMA_BIDIRECTIONAL); + } else { + dma_unmap_sg(dev, req->src, sg_nents(req->src), + DMA_TO_DEVICE); + dma_unmap_sg(dev, req->dst, sg_nents(req->dst), + DMA_FROM_DEVICE); + } +} + +void chcr_add_aead_src_ent(struct aead_request *req, + struct ulptx_sgl *ulptx, + unsigned int assoclen) +{ + struct ulptx_walk ulp_walk; + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + + if (reqctx->imm) { + u8 *buf = (u8 *)ulptx; + + if (reqctx->b0_len) { + memcpy(buf, reqctx->scratch_pad, reqctx->b0_len); + buf += reqctx->b0_len; + } + sg_pcopy_to_buffer(req->src, sg_nents(req->src), + buf, assoclen, 0); + buf += assoclen; + memcpy(buf, reqctx->iv, IV); + buf += IV; + sg_pcopy_to_buffer(req->src, sg_nents(req->src), + buf, req->cryptlen, req->assoclen); + } else { + ulptx_walk_init(&ulp_walk, ulptx); + if (reqctx->b0_len) + ulptx_walk_add_page(&ulp_walk, reqctx->b0_len, + &reqctx->b0_dma); + ulptx_walk_add_sg(&ulp_walk, req->src, assoclen, 0); + ulptx_walk_add_page(&ulp_walk, IV, &reqctx->iv_dma); + ulptx_walk_add_sg(&ulp_walk, req->src, req->cryptlen, + req->assoclen); + ulptx_walk_end(&ulp_walk); + } +} + +void chcr_add_aead_dst_ent(struct aead_request *req, + struct cpl_rx_phys_dsgl *phys_cpl, + unsigned int assoclen, + unsigned short qid) +{ + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct dsgl_walk dsgl_walk; + unsigned int authsize = crypto_aead_authsize(tfm); + struct chcr_context *ctx = a_ctx(tfm); + u32 temp; + + dsgl_walk_init(&dsgl_walk, phys_cpl); + if (reqctx->b0_len) + dsgl_walk_add_page(&dsgl_walk, reqctx->b0_len, &reqctx->b0_dma); + dsgl_walk_add_sg(&dsgl_walk, req->dst, assoclen, 0); + dsgl_walk_add_page(&dsgl_walk, IV, &reqctx->iv_dma); + temp = req->cryptlen + (reqctx->op ? -authsize : authsize); + dsgl_walk_add_sg(&dsgl_walk, req->dst, temp, req->assoclen); + dsgl_walk_end(&dsgl_walk, qid, ctx->pci_chan_id); +} + +void chcr_add_cipher_src_ent(struct ablkcipher_request *req, + void *ulptx, + struct cipher_wr_param *wrparam) +{ + struct ulptx_walk ulp_walk; + struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req); + u8 *buf = ulptx; + + memcpy(buf, reqctx->iv, IV); + buf += IV; + if (reqctx->imm) { + sg_pcopy_to_buffer(req->src, sg_nents(req->src), + buf, wrparam->bytes, reqctx->processed); + } else { + ulptx_walk_init(&ulp_walk, (struct ulptx_sgl *)buf); + ulptx_walk_add_sg(&ulp_walk, reqctx->srcsg, wrparam->bytes, + reqctx->src_ofst); + reqctx->srcsg = ulp_walk.last_sg; + reqctx->src_ofst = ulp_walk.last_sg_len; + ulptx_walk_end(&ulp_walk); + } +} + +void chcr_add_cipher_dst_ent(struct ablkcipher_request *req, + struct cpl_rx_phys_dsgl *phys_cpl, + struct cipher_wr_param *wrparam, + unsigned short qid) +{ + struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req); + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(wrparam->req); + struct chcr_context *ctx = c_ctx(tfm); + struct dsgl_walk dsgl_walk; + + dsgl_walk_init(&dsgl_walk, phys_cpl); + dsgl_walk_add_sg(&dsgl_walk, reqctx->dstsg, wrparam->bytes, + reqctx->dst_ofst); + reqctx->dstsg = dsgl_walk.last_sg; + reqctx->dst_ofst = dsgl_walk.last_sg_len; + + dsgl_walk_end(&dsgl_walk, qid, ctx->pci_chan_id); +} + +void chcr_add_hash_src_ent(struct ahash_request *req, + struct ulptx_sgl *ulptx, + struct hash_wr_param *param) +{ + struct ulptx_walk ulp_walk; + struct chcr_ahash_req_ctx *reqctx = ahash_request_ctx(req); + + if (reqctx->hctx_wr.imm) { + u8 *buf = (u8 *)ulptx; + + if (param->bfr_len) { + memcpy(buf, reqctx->reqbfr, param->bfr_len); + buf += param->bfr_len; + } + + sg_pcopy_to_buffer(reqctx->hctx_wr.srcsg, + sg_nents(reqctx->hctx_wr.srcsg), buf, + param->sg_len, 0); + } else { + ulptx_walk_init(&ulp_walk, ulptx); + if (param->bfr_len) + ulptx_walk_add_page(&ulp_walk, param->bfr_len, + &reqctx->hctx_wr.dma_addr); + ulptx_walk_add_sg(&ulp_walk, reqctx->hctx_wr.srcsg, + param->sg_len, reqctx->hctx_wr.src_ofst); + reqctx->hctx_wr.srcsg = ulp_walk.last_sg; + reqctx->hctx_wr.src_ofst = ulp_walk.last_sg_len; + ulptx_walk_end(&ulp_walk); + } +} + +int chcr_hash_dma_map(struct device *dev, + struct ahash_request *req) +{ + struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(req); + int error = 0; + + if (!req->nbytes) + return 0; + error = dma_map_sg(dev, req->src, sg_nents(req->src), + DMA_TO_DEVICE); + if (!error) + return -ENOMEM; + req_ctx->hctx_wr.is_sg_map = 1; + return 0; +} + +void chcr_hash_dma_unmap(struct device *dev, + struct ahash_request *req) +{ + struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(req); + + if (!req->nbytes) + return; + + dma_unmap_sg(dev, req->src, sg_nents(req->src), + DMA_TO_DEVICE); + req_ctx->hctx_wr.is_sg_map = 0; + +} + +int chcr_cipher_dma_map(struct device *dev, + struct ablkcipher_request *req) +{ + int error; + + if (req->src == req->dst) { + error = dma_map_sg(dev, req->src, sg_nents(req->src), + DMA_BIDIRECTIONAL); + if (!error) + goto err; + } else { + error = dma_map_sg(dev, req->src, sg_nents(req->src), + DMA_TO_DEVICE); + if (!error) + goto err; + error = dma_map_sg(dev, req->dst, sg_nents(req->dst), + DMA_FROM_DEVICE); + if (!error) { + dma_unmap_sg(dev, req->src, sg_nents(req->src), + DMA_TO_DEVICE); + goto err; + } + } + + return 0; +err: + return -ENOMEM; +} + +void chcr_cipher_dma_unmap(struct device *dev, + struct ablkcipher_request *req) +{ + if (req->src == req->dst) { + dma_unmap_sg(dev, req->src, sg_nents(req->src), + DMA_BIDIRECTIONAL); + } else { + dma_unmap_sg(dev, req->src, sg_nents(req->src), + DMA_TO_DEVICE); + dma_unmap_sg(dev, req->dst, sg_nents(req->dst), + DMA_FROM_DEVICE); + } +} + +static int set_msg_len(u8 *block, unsigned int msglen, int csize) +{ + __be32 data; + + memset(block, 0, csize); + block += csize; + + if (csize >= 4) + csize = 4; + else if (msglen > (unsigned int)(1 << (8 * csize))) + return -EOVERFLOW; + + data = cpu_to_be32(msglen); + memcpy(block - csize, (u8 *)&data + 4 - csize, csize); + + return 0; +} + +static void generate_b0(struct aead_request *req, + struct chcr_aead_ctx *aeadctx, + unsigned short op_type) +{ + unsigned int l, lp, m; + int rc; + struct crypto_aead *aead = crypto_aead_reqtfm(req); + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + u8 *b0 = reqctx->scratch_pad; + + m = crypto_aead_authsize(aead); + + memcpy(b0, reqctx->iv, 16); + + lp = b0[0]; + l = lp + 1; + + /* set m, bits 3-5 */ + *b0 |= (8 * ((m - 2) / 2)); + + /* set adata, bit 6, if associated data is used */ + if (req->assoclen) + *b0 |= 64; + rc = set_msg_len(b0 + 16 - l, + (op_type == CHCR_DECRYPT_OP) ? + req->cryptlen - m : req->cryptlen, l); +} + +static inline int crypto_ccm_check_iv(const u8 *iv) +{ + /* 2 <= L <= 8, so 1 <= L' <= 7. */ + if (iv[0] < 1 || iv[0] > 7) + return -EINVAL; + + return 0; +} + +static int ccm_format_packet(struct aead_request *req, + struct chcr_aead_ctx *aeadctx, + unsigned int sub_type, + unsigned short op_type, + unsigned int assoclen) +{ + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + int rc = 0; + + if (sub_type == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309) { + reqctx->iv[0] = 3; + memcpy(reqctx->iv + 1, &aeadctx->salt[0], 3); + memcpy(reqctx->iv + 4, req->iv, 8); + memset(reqctx->iv + 12, 0, 4); + } else { + memcpy(reqctx->iv, req->iv, 16); + } + if (assoclen) + *((unsigned short *)(reqctx->scratch_pad + 16)) = + htons(assoclen); + + generate_b0(req, aeadctx, op_type); + /* zero the ctr value */ + memset(reqctx->iv + 15 - reqctx->iv[0], 0, reqctx->iv[0] + 1); + return rc; +} + +static void fill_sec_cpl_for_aead(struct cpl_tx_sec_pdu *sec_cpl, + unsigned int dst_size, + struct aead_request *req, + unsigned short op_type) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + unsigned int cipher_mode = CHCR_SCMD_CIPHER_MODE_AES_CCM; + unsigned int mac_mode = CHCR_SCMD_AUTH_MODE_CBCMAC; + unsigned int c_id = a_ctx(tfm)->dev->rx_channel_id; + unsigned int ccm_xtra; + unsigned int tag_offset = 0, auth_offset = 0; + unsigned int assoclen; + + if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309) + assoclen = req->assoclen - 8; + else + assoclen = req->assoclen; + ccm_xtra = CCM_B0_SIZE + + ((assoclen) ? CCM_AAD_FIELD_SIZE : 0); + + auth_offset = req->cryptlen ? + (assoclen + IV + 1 + ccm_xtra) : 0; + if (op_type == CHCR_DECRYPT_OP) { + if (crypto_aead_authsize(tfm) != req->cryptlen) + tag_offset = crypto_aead_authsize(tfm); + else + auth_offset = 0; + } + + + sec_cpl->op_ivinsrtofst = FILL_SEC_CPL_OP_IVINSR(c_id, + 2, assoclen + 1 + ccm_xtra); + sec_cpl->pldlen = + htonl(assoclen + IV + req->cryptlen + ccm_xtra); + /* For CCM there wil be b0 always. So AAD start will be 1 always */ + sec_cpl->aadstart_cipherstop_hi = FILL_SEC_CPL_CIPHERSTOP_HI( + 1, assoclen + ccm_xtra, assoclen + + IV + 1 + ccm_xtra, 0); + + sec_cpl->cipherstop_lo_authinsert = FILL_SEC_CPL_AUTHINSERT(0, + auth_offset, tag_offset, + (op_type == CHCR_ENCRYPT_OP) ? 0 : + crypto_aead_authsize(tfm)); + sec_cpl->seqno_numivs = FILL_SEC_CPL_SCMD0_SEQNO(op_type, + (op_type == CHCR_ENCRYPT_OP) ? 0 : 1, + cipher_mode, mac_mode, + aeadctx->hmac_ctrl, IV >> 1); + + sec_cpl->ivgen_hdrlen = FILL_SEC_CPL_IVGEN_HDRLEN(0, 0, 1, 0, + 0, dst_size); +} + +static int aead_ccm_validate_input(unsigned short op_type, + struct aead_request *req, + struct chcr_aead_ctx *aeadctx, + unsigned int sub_type) +{ + if (sub_type != CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309) { + if (crypto_ccm_check_iv(req->iv)) { + pr_err("CCM: IV check fails\n"); + return -EINVAL; + } + } else { + if (req->assoclen != 16 && req->assoclen != 20) { + pr_err("RFC4309: Invalid AAD length %d\n", + req->assoclen); + return -EINVAL; + } + } + return 0; +} + +static struct sk_buff *create_aead_ccm_wr(struct aead_request *req, + unsigned short qid, + int size) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + struct sk_buff *skb = NULL; + struct chcr_wr *chcr_req; + struct cpl_rx_phys_dsgl *phys_cpl; + struct ulptx_sgl *ulptx; + unsigned int transhdr_len; + unsigned int dst_size = 0, kctx_len, dnents, temp; + unsigned int sub_type, assoclen = req->assoclen; + unsigned int authsize = crypto_aead_authsize(tfm); + int error = -EINVAL; + gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : + GFP_ATOMIC; + struct adapter *adap = padap(a_ctx(tfm)->dev); + + sub_type = get_aead_subtype(tfm); + if (sub_type == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309) + assoclen -= 8; + reqctx->b0_len = CCM_B0_SIZE + (assoclen ? CCM_AAD_FIELD_SIZE : 0); + error = chcr_aead_common_init(req); + if (error) + return ERR_PTR(error); + + error = aead_ccm_validate_input(reqctx->op, req, aeadctx, sub_type); + if (error) + goto err; + dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0); + dnents += sg_nents_xlen(req->dst, req->cryptlen + + (reqctx->op ? -authsize : authsize), + CHCR_DST_SG_SIZE, req->assoclen); + dnents += MIN_CCM_SG; // For IV and B0 + dst_size = get_space_for_phys_dsgl(dnents); + kctx_len = roundup(aeadctx->enckey_len, 16) * 2; + transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size); + reqctx->imm = (transhdr_len + assoclen + IV + req->cryptlen + + reqctx->b0_len) <= SGE_MAX_WR_LEN; + temp = reqctx->imm ? roundup(assoclen + IV + req->cryptlen + + reqctx->b0_len, 16) : + (sgl_len(reqctx->src_nents + reqctx->aad_nents + + MIN_CCM_SG) * 8); + transhdr_len += temp; + transhdr_len = roundup(transhdr_len, 16); + + if (chcr_aead_need_fallback(req, dnents, T6_MAX_AAD_SIZE - + reqctx->b0_len, transhdr_len, reqctx->op)) { + atomic_inc(&adap->chcr_stats.fallback); + chcr_aead_common_exit(req); + return ERR_PTR(chcr_aead_fallback(req, reqctx->op)); + } + skb = alloc_skb(SGE_MAX_WR_LEN, flags); + + if (!skb) { + error = -ENOMEM; + goto err; + } + + chcr_req = (struct chcr_wr *) __skb_put_zero(skb, transhdr_len); + + fill_sec_cpl_for_aead(&chcr_req->sec_cpl, dst_size, req, reqctx->op); + + chcr_req->key_ctx.ctx_hdr = aeadctx->key_ctx_hdr; + memcpy(chcr_req->key_ctx.key, aeadctx->key, aeadctx->enckey_len); + memcpy(chcr_req->key_ctx.key + roundup(aeadctx->enckey_len, 16), + aeadctx->key, aeadctx->enckey_len); + + phys_cpl = (struct cpl_rx_phys_dsgl *)((u8 *)(chcr_req + 1) + kctx_len); + ulptx = (struct ulptx_sgl *)((u8 *)(phys_cpl + 1) + dst_size); + error = ccm_format_packet(req, aeadctx, sub_type, reqctx->op, assoclen); + if (error) + goto dstmap_fail; + chcr_add_aead_dst_ent(req, phys_cpl, assoclen, qid); + chcr_add_aead_src_ent(req, ulptx, assoclen); + + atomic_inc(&adap->chcr_stats.aead_rqst); + temp = sizeof(struct cpl_rx_phys_dsgl) + dst_size + + kctx_len + (reqctx->imm ? (assoclen + IV + req->cryptlen + + reqctx->b0_len) : 0); + create_wreq(a_ctx(tfm), chcr_req, &req->base, reqctx->imm, 0, + transhdr_len, temp, 0); + reqctx->skb = skb; + + return skb; +dstmap_fail: + kfree_skb(skb); +err: + chcr_aead_common_exit(req); + return ERR_PTR(error); +} + +static struct sk_buff *create_gcm_wr(struct aead_request *req, + unsigned short qid, + int size) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + struct sk_buff *skb = NULL; + struct chcr_wr *chcr_req; + struct cpl_rx_phys_dsgl *phys_cpl; + struct ulptx_sgl *ulptx; + unsigned int transhdr_len, dnents = 0; + unsigned int dst_size = 0, temp = 0, kctx_len, assoclen = req->assoclen; + unsigned int authsize = crypto_aead_authsize(tfm); + int error = -EINVAL; + gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : + GFP_ATOMIC; + struct adapter *adap = padap(a_ctx(tfm)->dev); + + if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106) + assoclen = req->assoclen - 8; + + reqctx->b0_len = 0; + error = chcr_aead_common_init(req); + if (error) + return ERR_PTR(error); + dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0); + dnents += sg_nents_xlen(req->dst, req->cryptlen + + (reqctx->op ? -authsize : authsize), + CHCR_DST_SG_SIZE, req->assoclen); + dnents += MIN_GCM_SG; // For IV + dst_size = get_space_for_phys_dsgl(dnents); + kctx_len = roundup(aeadctx->enckey_len, 16) + AEAD_H_SIZE; + transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size); + reqctx->imm = (transhdr_len + assoclen + IV + req->cryptlen) <= + SGE_MAX_WR_LEN; + temp = reqctx->imm ? roundup(assoclen + IV + req->cryptlen, 16) : + (sgl_len(reqctx->src_nents + + reqctx->aad_nents + MIN_GCM_SG) * 8); + transhdr_len += temp; + transhdr_len = roundup(transhdr_len, 16); + if (chcr_aead_need_fallback(req, dnents, T6_MAX_AAD_SIZE, + transhdr_len, reqctx->op)) { + + atomic_inc(&adap->chcr_stats.fallback); + chcr_aead_common_exit(req); + return ERR_PTR(chcr_aead_fallback(req, reqctx->op)); + } + skb = alloc_skb(SGE_MAX_WR_LEN, flags); + if (!skb) { + error = -ENOMEM; + goto err; + } + + chcr_req = __skb_put_zero(skb, transhdr_len); + + //Offset of tag from end + temp = (reqctx->op == CHCR_ENCRYPT_OP) ? 0 : authsize; + chcr_req->sec_cpl.op_ivinsrtofst = FILL_SEC_CPL_OP_IVINSR( + a_ctx(tfm)->dev->rx_channel_id, 2, + (assoclen + 1)); + chcr_req->sec_cpl.pldlen = + htonl(assoclen + IV + req->cryptlen); + chcr_req->sec_cpl.aadstart_cipherstop_hi = FILL_SEC_CPL_CIPHERSTOP_HI( + assoclen ? 1 : 0, assoclen, + assoclen + IV + 1, 0); + chcr_req->sec_cpl.cipherstop_lo_authinsert = + FILL_SEC_CPL_AUTHINSERT(0, assoclen + IV + 1, + temp, temp); + chcr_req->sec_cpl.seqno_numivs = + FILL_SEC_CPL_SCMD0_SEQNO(reqctx->op, (reqctx->op == + CHCR_ENCRYPT_OP) ? 1 : 0, + CHCR_SCMD_CIPHER_MODE_AES_GCM, + CHCR_SCMD_AUTH_MODE_GHASH, + aeadctx->hmac_ctrl, IV >> 1); + chcr_req->sec_cpl.ivgen_hdrlen = FILL_SEC_CPL_IVGEN_HDRLEN(0, 0, 1, + 0, 0, dst_size); + chcr_req->key_ctx.ctx_hdr = aeadctx->key_ctx_hdr; + memcpy(chcr_req->key_ctx.key, aeadctx->key, aeadctx->enckey_len); + memcpy(chcr_req->key_ctx.key + roundup(aeadctx->enckey_len, 16), + GCM_CTX(aeadctx)->ghash_h, AEAD_H_SIZE); + + /* prepare a 16 byte iv */ + /* S A L T | IV | 0x00000001 */ + if (get_aead_subtype(tfm) == + CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106) { + memcpy(reqctx->iv, aeadctx->salt, 4); + memcpy(reqctx->iv + 4, req->iv, GCM_RFC4106_IV_SIZE); + } else { + memcpy(reqctx->iv, req->iv, GCM_AES_IV_SIZE); + } + *((unsigned int *)(reqctx->iv + 12)) = htonl(0x01); + + phys_cpl = (struct cpl_rx_phys_dsgl *)((u8 *)(chcr_req + 1) + kctx_len); + ulptx = (struct ulptx_sgl *)((u8 *)(phys_cpl + 1) + dst_size); + + chcr_add_aead_dst_ent(req, phys_cpl, assoclen, qid); + chcr_add_aead_src_ent(req, ulptx, assoclen); + atomic_inc(&adap->chcr_stats.aead_rqst); + temp = sizeof(struct cpl_rx_phys_dsgl) + dst_size + + kctx_len + (reqctx->imm ? (assoclen + IV + req->cryptlen) : 0); + create_wreq(a_ctx(tfm), chcr_req, &req->base, reqctx->imm, size, + transhdr_len, temp, reqctx->verify); + reqctx->skb = skb; + return skb; + +err: + chcr_aead_common_exit(req); + return ERR_PTR(error); +} + + + +static int chcr_aead_cra_init(struct crypto_aead *tfm) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + struct aead_alg *alg = crypto_aead_alg(tfm); + + aeadctx->sw_cipher = crypto_alloc_aead(alg->base.cra_name, 0, + CRYPTO_ALG_NEED_FALLBACK | + CRYPTO_ALG_ASYNC); + if (IS_ERR(aeadctx->sw_cipher)) + return PTR_ERR(aeadctx->sw_cipher); + crypto_aead_set_reqsize(tfm, max(sizeof(struct chcr_aead_reqctx), + sizeof(struct aead_request) + + crypto_aead_reqsize(aeadctx->sw_cipher))); + return chcr_device_init(a_ctx(tfm)); +} + +static void chcr_aead_cra_exit(struct crypto_aead *tfm) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + + crypto_free_aead(aeadctx->sw_cipher); +} + +static int chcr_authenc_null_setauthsize(struct crypto_aead *tfm, + unsigned int authsize) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_NOP; + aeadctx->mayverify = VERIFY_HW; + return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize); +} +static int chcr_authenc_setauthsize(struct crypto_aead *tfm, + unsigned int authsize) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + u32 maxauth = crypto_aead_maxauthsize(tfm); + + /*SHA1 authsize in ipsec is 12 instead of 10 i.e maxauthsize / 2 is not + * true for sha1. authsize == 12 condition should be before + * authsize == (maxauth >> 1) + */ + if (authsize == ICV_4) { + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_PL1; + aeadctx->mayverify = VERIFY_HW; + } else if (authsize == ICV_6) { + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_PL2; + aeadctx->mayverify = VERIFY_HW; + } else if (authsize == ICV_10) { + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_TRUNC_RFC4366; + aeadctx->mayverify = VERIFY_HW; + } else if (authsize == ICV_12) { + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_IPSEC_96BIT; + aeadctx->mayverify = VERIFY_HW; + } else if (authsize == ICV_14) { + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_PL3; + aeadctx->mayverify = VERIFY_HW; + } else if (authsize == (maxauth >> 1)) { + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_DIV2; + aeadctx->mayverify = VERIFY_HW; + } else if (authsize == maxauth) { + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_NO_TRUNC; + aeadctx->mayverify = VERIFY_HW; + } else { + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_NO_TRUNC; + aeadctx->mayverify = VERIFY_SW; + } + return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize); +} + + +static int chcr_gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + + switch (authsize) { + case ICV_4: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_PL1; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_8: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_DIV2; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_12: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_IPSEC_96BIT; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_14: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_PL3; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_16: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_NO_TRUNC; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_13: + case ICV_15: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_NO_TRUNC; + aeadctx->mayverify = VERIFY_SW; + break; + default: + return -EINVAL; + } + return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize); +} + +static int chcr_4106_4309_setauthsize(struct crypto_aead *tfm, + unsigned int authsize) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + + switch (authsize) { + case ICV_8: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_DIV2; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_12: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_IPSEC_96BIT; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_16: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_NO_TRUNC; + aeadctx->mayverify = VERIFY_HW; + break; + default: + return -EINVAL; + } + return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize); +} + +static int chcr_ccm_setauthsize(struct crypto_aead *tfm, + unsigned int authsize) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + + switch (authsize) { + case ICV_4: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_PL1; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_6: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_PL2; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_8: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_DIV2; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_10: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_TRUNC_RFC4366; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_12: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_IPSEC_96BIT; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_14: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_PL3; + aeadctx->mayverify = VERIFY_HW; + break; + case ICV_16: + aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_NO_TRUNC; + aeadctx->mayverify = VERIFY_HW; + break; + default: + return -EINVAL; + } + return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize); +} + +static int chcr_ccm_common_setkey(struct crypto_aead *aead, + const u8 *key, + unsigned int keylen) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(aead)); + unsigned char ck_size, mk_size; + int key_ctx_size = 0; + + key_ctx_size = sizeof(struct _key_ctx) + roundup(keylen, 16) * 2; + if (keylen == AES_KEYSIZE_128) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128; + mk_size = CHCR_KEYCTX_MAC_KEY_SIZE_128; + } else if (keylen == AES_KEYSIZE_192) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_192; + mk_size = CHCR_KEYCTX_MAC_KEY_SIZE_192; + } else if (keylen == AES_KEYSIZE_256) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256; + mk_size = CHCR_KEYCTX_MAC_KEY_SIZE_256; + } else { + crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); + aeadctx->enckey_len = 0; + return -EINVAL; + } + aeadctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size, mk_size, 0, 0, + key_ctx_size >> 4); + memcpy(aeadctx->key, key, keylen); + aeadctx->enckey_len = keylen; + + return 0; +} + +static int chcr_aead_ccm_setkey(struct crypto_aead *aead, + const u8 *key, + unsigned int keylen) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(aead)); + int error; + + crypto_aead_clear_flags(aeadctx->sw_cipher, CRYPTO_TFM_REQ_MASK); + crypto_aead_set_flags(aeadctx->sw_cipher, crypto_aead_get_flags(aead) & + CRYPTO_TFM_REQ_MASK); + error = crypto_aead_setkey(aeadctx->sw_cipher, key, keylen); + crypto_aead_clear_flags(aead, CRYPTO_TFM_RES_MASK); + crypto_aead_set_flags(aead, crypto_aead_get_flags(aeadctx->sw_cipher) & + CRYPTO_TFM_RES_MASK); + if (error) + return error; + return chcr_ccm_common_setkey(aead, key, keylen); +} + +static int chcr_aead_rfc4309_setkey(struct crypto_aead *aead, const u8 *key, + unsigned int keylen) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(aead)); + int error; + + if (keylen < 3) { + crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); + aeadctx->enckey_len = 0; + return -EINVAL; + } + crypto_aead_clear_flags(aeadctx->sw_cipher, CRYPTO_TFM_REQ_MASK); + crypto_aead_set_flags(aeadctx->sw_cipher, crypto_aead_get_flags(aead) & + CRYPTO_TFM_REQ_MASK); + error = crypto_aead_setkey(aeadctx->sw_cipher, key, keylen); + crypto_aead_clear_flags(aead, CRYPTO_TFM_RES_MASK); + crypto_aead_set_flags(aead, crypto_aead_get_flags(aeadctx->sw_cipher) & + CRYPTO_TFM_RES_MASK); + if (error) + return error; + keylen -= 3; + memcpy(aeadctx->salt, key + keylen, 3); + return chcr_ccm_common_setkey(aead, key, keylen); +} + +static int chcr_gcm_setkey(struct crypto_aead *aead, const u8 *key, + unsigned int keylen) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(aead)); + struct chcr_gcm_ctx *gctx = GCM_CTX(aeadctx); + struct crypto_cipher *cipher; + unsigned int ck_size; + int ret = 0, key_ctx_size = 0; + + aeadctx->enckey_len = 0; + crypto_aead_clear_flags(aeadctx->sw_cipher, CRYPTO_TFM_REQ_MASK); + crypto_aead_set_flags(aeadctx->sw_cipher, crypto_aead_get_flags(aead) + & CRYPTO_TFM_REQ_MASK); + ret = crypto_aead_setkey(aeadctx->sw_cipher, key, keylen); + crypto_aead_clear_flags(aead, CRYPTO_TFM_RES_MASK); + crypto_aead_set_flags(aead, crypto_aead_get_flags(aeadctx->sw_cipher) & + CRYPTO_TFM_RES_MASK); + if (ret) + goto out; + + if (get_aead_subtype(aead) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106 && + keylen > 3) { + keylen -= 4; /* nonce/salt is present in the last 4 bytes */ + memcpy(aeadctx->salt, key + keylen, 4); + } + if (keylen == AES_KEYSIZE_128) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128; + } else if (keylen == AES_KEYSIZE_192) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_192; + } else if (keylen == AES_KEYSIZE_256) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256; + } else { + crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); + pr_err("GCM: Invalid key length %d\n", keylen); + ret = -EINVAL; + goto out; + } + + memcpy(aeadctx->key, key, keylen); + aeadctx->enckey_len = keylen; + key_ctx_size = sizeof(struct _key_ctx) + roundup(keylen, 16) + + AEAD_H_SIZE; + aeadctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size, + CHCR_KEYCTX_MAC_KEY_SIZE_128, + 0, 0, + key_ctx_size >> 4); + /* Calculate the H = CIPH(K, 0 repeated 16 times). + * It will go in key context + */ + cipher = crypto_alloc_cipher("aes-generic", 0, 0); + if (IS_ERR(cipher)) { + aeadctx->enckey_len = 0; + ret = -ENOMEM; + goto out; + } + + ret = crypto_cipher_setkey(cipher, key, keylen); + if (ret) { + aeadctx->enckey_len = 0; + goto out1; + } + memset(gctx->ghash_h, 0, AEAD_H_SIZE); + crypto_cipher_encrypt_one(cipher, gctx->ghash_h, gctx->ghash_h); + +out1: + crypto_free_cipher(cipher); +out: + return ret; +} + +static int chcr_authenc_setkey(struct crypto_aead *authenc, const u8 *key, + unsigned int keylen) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(authenc)); + struct chcr_authenc_ctx *actx = AUTHENC_CTX(aeadctx); + /* it contains auth and cipher key both*/ + struct crypto_authenc_keys keys; + unsigned int bs, subtype; + unsigned int max_authsize = crypto_aead_alg(authenc)->maxauthsize; + int err = 0, i, key_ctx_len = 0; + unsigned char ck_size = 0; + unsigned char pad[CHCR_HASH_MAX_BLOCK_SIZE_128] = { 0 }; + struct crypto_shash *base_hash = ERR_PTR(-EINVAL); + struct algo_param param; + int align; + u8 *o_ptr = NULL; + + crypto_aead_clear_flags(aeadctx->sw_cipher, CRYPTO_TFM_REQ_MASK); + crypto_aead_set_flags(aeadctx->sw_cipher, crypto_aead_get_flags(authenc) + & CRYPTO_TFM_REQ_MASK); + err = crypto_aead_setkey(aeadctx->sw_cipher, key, keylen); + crypto_aead_clear_flags(authenc, CRYPTO_TFM_RES_MASK); + crypto_aead_set_flags(authenc, crypto_aead_get_flags(aeadctx->sw_cipher) + & CRYPTO_TFM_RES_MASK); + if (err) + goto out; + + if (crypto_authenc_extractkeys(&keys, key, keylen) != 0) { + crypto_aead_set_flags(authenc, CRYPTO_TFM_RES_BAD_KEY_LEN); + goto out; + } + + if (get_alg_config(¶m, max_authsize)) { + pr_err("chcr : Unsupported digest size\n"); + goto out; + } + subtype = get_aead_subtype(authenc); + if (subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA || + subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) { + if (keys.enckeylen < CTR_RFC3686_NONCE_SIZE) + goto out; + memcpy(aeadctx->nonce, keys.enckey + (keys.enckeylen + - CTR_RFC3686_NONCE_SIZE), CTR_RFC3686_NONCE_SIZE); + keys.enckeylen -= CTR_RFC3686_NONCE_SIZE; + } + if (keys.enckeylen == AES_KEYSIZE_128) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128; + } else if (keys.enckeylen == AES_KEYSIZE_192) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_192; + } else if (keys.enckeylen == AES_KEYSIZE_256) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256; + } else { + pr_err("chcr : Unsupported cipher key\n"); + goto out; + } + + /* Copy only encryption key. We use authkey to generate h(ipad) and + * h(opad) so authkey is not needed again. authkeylen size have the + * size of the hash digest size. + */ + memcpy(aeadctx->key, keys.enckey, keys.enckeylen); + aeadctx->enckey_len = keys.enckeylen; + if (subtype == CRYPTO_ALG_SUB_TYPE_CBC_SHA || + subtype == CRYPTO_ALG_SUB_TYPE_CBC_NULL) { + + get_aes_decrypt_key(actx->dec_rrkey, aeadctx->key, + aeadctx->enckey_len << 3); + } + base_hash = chcr_alloc_shash(max_authsize); + if (IS_ERR(base_hash)) { + pr_err("chcr : Base driver cannot be loaded\n"); + aeadctx->enckey_len = 0; + memzero_explicit(&keys, sizeof(keys)); + return -EINVAL; + } + { + SHASH_DESC_ON_STACK(shash, base_hash); + + shash->tfm = base_hash; + shash->flags = crypto_shash_get_flags(base_hash); + bs = crypto_shash_blocksize(base_hash); + align = KEYCTX_ALIGN_PAD(max_authsize); + o_ptr = actx->h_iopad + param.result_size + align; + + if (keys.authkeylen > bs) { + err = crypto_shash_digest(shash, keys.authkey, + keys.authkeylen, + o_ptr); + if (err) { + pr_err("chcr : Base driver cannot be loaded\n"); + goto out; + } + keys.authkeylen = max_authsize; + } else + memcpy(o_ptr, keys.authkey, keys.authkeylen); + + /* Compute the ipad-digest*/ + memset(pad + keys.authkeylen, 0, bs - keys.authkeylen); + memcpy(pad, o_ptr, keys.authkeylen); + for (i = 0; i < bs >> 2; i++) + *((unsigned int *)pad + i) ^= IPAD_DATA; + + if (chcr_compute_partial_hash(shash, pad, actx->h_iopad, + max_authsize)) + goto out; + /* Compute the opad-digest */ + memset(pad + keys.authkeylen, 0, bs - keys.authkeylen); + memcpy(pad, o_ptr, keys.authkeylen); + for (i = 0; i < bs >> 2; i++) + *((unsigned int *)pad + i) ^= OPAD_DATA; + + if (chcr_compute_partial_hash(shash, pad, o_ptr, max_authsize)) + goto out; + + /* convert the ipad and opad digest to network order */ + chcr_change_order(actx->h_iopad, param.result_size); + chcr_change_order(o_ptr, param.result_size); + key_ctx_len = sizeof(struct _key_ctx) + + roundup(keys.enckeylen, 16) + + (param.result_size + align) * 2; + aeadctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size, param.mk_size, + 0, 1, key_ctx_len >> 4); + actx->auth_mode = param.auth_mode; + chcr_free_shash(base_hash); + + memzero_explicit(&keys, sizeof(keys)); + return 0; + } +out: + aeadctx->enckey_len = 0; + memzero_explicit(&keys, sizeof(keys)); + if (!IS_ERR(base_hash)) + chcr_free_shash(base_hash); + return -EINVAL; +} + +static int chcr_aead_digest_null_setkey(struct crypto_aead *authenc, + const u8 *key, unsigned int keylen) +{ + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(authenc)); + struct chcr_authenc_ctx *actx = AUTHENC_CTX(aeadctx); + struct crypto_authenc_keys keys; + int err; + /* it contains auth and cipher key both*/ + unsigned int subtype; + int key_ctx_len = 0; + unsigned char ck_size = 0; + + crypto_aead_clear_flags(aeadctx->sw_cipher, CRYPTO_TFM_REQ_MASK); + crypto_aead_set_flags(aeadctx->sw_cipher, crypto_aead_get_flags(authenc) + & CRYPTO_TFM_REQ_MASK); + err = crypto_aead_setkey(aeadctx->sw_cipher, key, keylen); + crypto_aead_clear_flags(authenc, CRYPTO_TFM_RES_MASK); + crypto_aead_set_flags(authenc, crypto_aead_get_flags(aeadctx->sw_cipher) + & CRYPTO_TFM_RES_MASK); + if (err) + goto out; + + if (crypto_authenc_extractkeys(&keys, key, keylen) != 0) { + crypto_aead_set_flags(authenc, CRYPTO_TFM_RES_BAD_KEY_LEN); + goto out; + } + subtype = get_aead_subtype(authenc); + if (subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA || + subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) { + if (keys.enckeylen < CTR_RFC3686_NONCE_SIZE) + goto out; + memcpy(aeadctx->nonce, keys.enckey + (keys.enckeylen + - CTR_RFC3686_NONCE_SIZE), CTR_RFC3686_NONCE_SIZE); + keys.enckeylen -= CTR_RFC3686_NONCE_SIZE; + } + if (keys.enckeylen == AES_KEYSIZE_128) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128; + } else if (keys.enckeylen == AES_KEYSIZE_192) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_192; + } else if (keys.enckeylen == AES_KEYSIZE_256) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256; + } else { + pr_err("chcr : Unsupported cipher key %d\n", keys.enckeylen); + goto out; + } + memcpy(aeadctx->key, keys.enckey, keys.enckeylen); + aeadctx->enckey_len = keys.enckeylen; + if (subtype == CRYPTO_ALG_SUB_TYPE_CBC_SHA || + subtype == CRYPTO_ALG_SUB_TYPE_CBC_NULL) { + get_aes_decrypt_key(actx->dec_rrkey, aeadctx->key, + aeadctx->enckey_len << 3); + } + key_ctx_len = sizeof(struct _key_ctx) + roundup(keys.enckeylen, 16); + + aeadctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size, CHCR_KEYCTX_NO_KEY, 0, + 0, key_ctx_len >> 4); + actx->auth_mode = CHCR_SCMD_AUTH_MODE_NOP; + memzero_explicit(&keys, sizeof(keys)); + return 0; +out: + aeadctx->enckey_len = 0; + memzero_explicit(&keys, sizeof(keys)); + return -EINVAL; +} + +static int chcr_aead_op(struct aead_request *req, + int size, + create_wr_t create_wr_fn) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct uld_ctx *u_ctx; + struct sk_buff *skb; + int isfull = 0; + + if (!a_ctx(tfm)->dev) { + pr_err("chcr : %s : No crypto device.\n", __func__); + return -ENXIO; + } + u_ctx = ULD_CTX(a_ctx(tfm)); + if (cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0], + a_ctx(tfm)->tx_qidx)) { + isfull = 1; + if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) + return -ENOSPC; + } + + /* Form a WR from req */ + skb = create_wr_fn(req, u_ctx->lldi.rxq_ids[a_ctx(tfm)->rx_qidx], size); + + if (IS_ERR(skb) || !skb) + return PTR_ERR(skb); + + skb->dev = u_ctx->lldi.ports[0]; + set_wr_txq(skb, CPL_PRIORITY_DATA, a_ctx(tfm)->tx_qidx); + chcr_send_wr(skb); + return isfull ? -EBUSY : -EINPROGRESS; +} + +static int chcr_aead_encrypt(struct aead_request *req) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + + reqctx->verify = VERIFY_HW; + reqctx->op = CHCR_ENCRYPT_OP; + + switch (get_aead_subtype(tfm)) { + case CRYPTO_ALG_SUB_TYPE_CTR_SHA: + case CRYPTO_ALG_SUB_TYPE_CBC_SHA: + case CRYPTO_ALG_SUB_TYPE_CBC_NULL: + case CRYPTO_ALG_SUB_TYPE_CTR_NULL: + return chcr_aead_op(req, 0, create_authenc_wr); + case CRYPTO_ALG_SUB_TYPE_AEAD_CCM: + case CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309: + return chcr_aead_op(req, 0, create_aead_ccm_wr); + default: + return chcr_aead_op(req, 0, create_gcm_wr); + } +} + +static int chcr_aead_decrypt(struct aead_request *req) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm)); + struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); + int size; + + if (aeadctx->mayverify == VERIFY_SW) { + size = crypto_aead_maxauthsize(tfm); + reqctx->verify = VERIFY_SW; + } else { + size = 0; + reqctx->verify = VERIFY_HW; + } + reqctx->op = CHCR_DECRYPT_OP; + switch (get_aead_subtype(tfm)) { + case CRYPTO_ALG_SUB_TYPE_CBC_SHA: + case CRYPTO_ALG_SUB_TYPE_CTR_SHA: + case CRYPTO_ALG_SUB_TYPE_CBC_NULL: + case CRYPTO_ALG_SUB_TYPE_CTR_NULL: + return chcr_aead_op(req, size, create_authenc_wr); + case CRYPTO_ALG_SUB_TYPE_AEAD_CCM: + case CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309: + return chcr_aead_op(req, size, create_aead_ccm_wr); + default: + return chcr_aead_op(req, size, create_gcm_wr); + } +} + +static struct chcr_alg_template driver_algs[] = { + /* AES-CBC */ + { + .type = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_SUB_TYPE_CBC, + .is_registered = 0, + .alg.crypto = { + .cra_name = "cbc(aes)", + .cra_driver_name = "cbc-aes-chcr", + .cra_blocksize = AES_BLOCK_SIZE, + .cra_init = chcr_cra_init, + .cra_exit = chcr_cra_exit, + .cra_u.ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = chcr_aes_cbc_setkey, + .encrypt = chcr_aes_encrypt, + .decrypt = chcr_aes_decrypt, + } + } + }, + { + .type = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_SUB_TYPE_XTS, + .is_registered = 0, + .alg.crypto = { + .cra_name = "xts(aes)", + .cra_driver_name = "xts-aes-chcr", + .cra_blocksize = AES_BLOCK_SIZE, + .cra_init = chcr_cra_init, + .cra_exit = NULL, + .cra_u .ablkcipher = { + .min_keysize = 2 * AES_MIN_KEY_SIZE, + .max_keysize = 2 * AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = chcr_aes_xts_setkey, + .encrypt = chcr_aes_encrypt, + .decrypt = chcr_aes_decrypt, + } + } + }, + { + .type = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_SUB_TYPE_CTR, + .is_registered = 0, + .alg.crypto = { + .cra_name = "ctr(aes)", + .cra_driver_name = "ctr-aes-chcr", + .cra_blocksize = 1, + .cra_init = chcr_cra_init, + .cra_exit = chcr_cra_exit, + .cra_u.ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = chcr_aes_ctr_setkey, + .encrypt = chcr_aes_encrypt, + .decrypt = chcr_aes_decrypt, + } + } + }, + { + .type = CRYPTO_ALG_TYPE_ABLKCIPHER | + CRYPTO_ALG_SUB_TYPE_CTR_RFC3686, + .is_registered = 0, + .alg.crypto = { + .cra_name = "rfc3686(ctr(aes))", + .cra_driver_name = "rfc3686-ctr-aes-chcr", + .cra_blocksize = 1, + .cra_init = chcr_rfc3686_init, + .cra_exit = chcr_cra_exit, + .cra_u.ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE + + CTR_RFC3686_NONCE_SIZE, + .max_keysize = AES_MAX_KEY_SIZE + + CTR_RFC3686_NONCE_SIZE, + .ivsize = CTR_RFC3686_IV_SIZE, + .setkey = chcr_aes_rfc3686_setkey, + .encrypt = chcr_aes_encrypt, + .decrypt = chcr_aes_decrypt, + .geniv = "seqiv", + } + } + }, + /* SHA */ + { + .type = CRYPTO_ALG_TYPE_AHASH, + .is_registered = 0, + .alg.hash = { + .halg.digestsize = SHA1_DIGEST_SIZE, + .halg.base = { + .cra_name = "sha1", + .cra_driver_name = "sha1-chcr", + .cra_blocksize = SHA1_BLOCK_SIZE, + } + } + }, + { + .type = CRYPTO_ALG_TYPE_AHASH, + .is_registered = 0, + .alg.hash = { + .halg.digestsize = SHA256_DIGEST_SIZE, + .halg.base = { + .cra_name = "sha256", + .cra_driver_name = "sha256-chcr", + .cra_blocksize = SHA256_BLOCK_SIZE, + } + } + }, + { + .type = CRYPTO_ALG_TYPE_AHASH, + .is_registered = 0, + .alg.hash = { + .halg.digestsize = SHA224_DIGEST_SIZE, + .halg.base = { + .cra_name = "sha224", + .cra_driver_name = "sha224-chcr", + .cra_blocksize = SHA224_BLOCK_SIZE, + } + } + }, + { + .type = CRYPTO_ALG_TYPE_AHASH, + .is_registered = 0, + .alg.hash = { + .halg.digestsize = SHA384_DIGEST_SIZE, + .halg.base = { + .cra_name = "sha384", + .cra_driver_name = "sha384-chcr", + .cra_blocksize = SHA384_BLOCK_SIZE, + } + } + }, + { + .type = CRYPTO_ALG_TYPE_AHASH, + .is_registered = 0, + .alg.hash = { + .halg.digestsize = SHA512_DIGEST_SIZE, + .halg.base = { + .cra_name = "sha512", + .cra_driver_name = "sha512-chcr", + .cra_blocksize = SHA512_BLOCK_SIZE, + } + } + }, + /* HMAC */ + { + .type = CRYPTO_ALG_TYPE_HMAC, + .is_registered = 0, + .alg.hash = { + .halg.digestsize = SHA1_DIGEST_SIZE, + .halg.base = { + .cra_name = "hmac(sha1)", + .cra_driver_name = "hmac-sha1-chcr", + .cra_blocksize = SHA1_BLOCK_SIZE, + } + } + }, + { + .type = CRYPTO_ALG_TYPE_HMAC, + .is_registered = 0, + .alg.hash = { + .halg.digestsize = SHA224_DIGEST_SIZE, + .halg.base = { + .cra_name = "hmac(sha224)", + .cra_driver_name = "hmac-sha224-chcr", + .cra_blocksize = SHA224_BLOCK_SIZE, + } + } + }, + { + .type = CRYPTO_ALG_TYPE_HMAC, + .is_registered = 0, + .alg.hash = { + .halg.digestsize = SHA256_DIGEST_SIZE, + .halg.base = { + .cra_name = "hmac(sha256)", + .cra_driver_name = "hmac-sha256-chcr", + .cra_blocksize = SHA256_BLOCK_SIZE, + } + } + }, + { + .type = CRYPTO_ALG_TYPE_HMAC, + .is_registered = 0, + .alg.hash = { + .halg.digestsize = SHA384_DIGEST_SIZE, + .halg.base = { + .cra_name = "hmac(sha384)", + .cra_driver_name = "hmac-sha384-chcr", + .cra_blocksize = SHA384_BLOCK_SIZE, + } + } + }, + { + .type = CRYPTO_ALG_TYPE_HMAC, + .is_registered = 0, + .alg.hash = { + .halg.digestsize = SHA512_DIGEST_SIZE, + .halg.base = { + .cra_name = "hmac(sha512)", + .cra_driver_name = "hmac-sha512-chcr", + .cra_blocksize = SHA512_BLOCK_SIZE, + } + } + }, + /* Add AEAD Algorithms */ + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_AEAD_GCM, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "gcm(aes)", + .cra_driver_name = "gcm-aes-chcr", + .cra_blocksize = 1, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_gcm_ctx), + }, + .ivsize = GCM_AES_IV_SIZE, + .maxauthsize = GHASH_DIGEST_SIZE, + .setkey = chcr_gcm_setkey, + .setauthsize = chcr_gcm_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "rfc4106(gcm(aes))", + .cra_driver_name = "rfc4106-gcm-aes-chcr", + .cra_blocksize = 1, + .cra_priority = CHCR_AEAD_PRIORITY + 1, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_gcm_ctx), + + }, + .ivsize = GCM_RFC4106_IV_SIZE, + .maxauthsize = GHASH_DIGEST_SIZE, + .setkey = chcr_gcm_setkey, + .setauthsize = chcr_4106_4309_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_AEAD_CCM, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "ccm(aes)", + .cra_driver_name = "ccm-aes-chcr", + .cra_blocksize = 1, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx), + + }, + .ivsize = AES_BLOCK_SIZE, + .maxauthsize = GHASH_DIGEST_SIZE, + .setkey = chcr_aead_ccm_setkey, + .setauthsize = chcr_ccm_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "rfc4309(ccm(aes))", + .cra_driver_name = "rfc4309-ccm-aes-chcr", + .cra_blocksize = 1, + .cra_priority = CHCR_AEAD_PRIORITY + 1, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx), + + }, + .ivsize = 8, + .maxauthsize = GHASH_DIGEST_SIZE, + .setkey = chcr_aead_rfc4309_setkey, + .setauthsize = chcr_4106_4309_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_SHA, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "authenc(hmac(sha1),cbc(aes))", + .cra_driver_name = + "authenc-hmac-sha1-cbc-aes-chcr", + .cra_blocksize = AES_BLOCK_SIZE, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + + }, + .ivsize = AES_BLOCK_SIZE, + .maxauthsize = SHA1_DIGEST_SIZE, + .setkey = chcr_authenc_setkey, + .setauthsize = chcr_authenc_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_SHA, + .is_registered = 0, + .alg.aead = { + .base = { + + .cra_name = "authenc(hmac(sha256),cbc(aes))", + .cra_driver_name = + "authenc-hmac-sha256-cbc-aes-chcr", + .cra_blocksize = AES_BLOCK_SIZE, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + + }, + .ivsize = AES_BLOCK_SIZE, + .maxauthsize = SHA256_DIGEST_SIZE, + .setkey = chcr_authenc_setkey, + .setauthsize = chcr_authenc_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_SHA, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "authenc(hmac(sha224),cbc(aes))", + .cra_driver_name = + "authenc-hmac-sha224-cbc-aes-chcr", + .cra_blocksize = AES_BLOCK_SIZE, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + }, + .ivsize = AES_BLOCK_SIZE, + .maxauthsize = SHA224_DIGEST_SIZE, + .setkey = chcr_authenc_setkey, + .setauthsize = chcr_authenc_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_SHA, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "authenc(hmac(sha384),cbc(aes))", + .cra_driver_name = + "authenc-hmac-sha384-cbc-aes-chcr", + .cra_blocksize = AES_BLOCK_SIZE, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + + }, + .ivsize = AES_BLOCK_SIZE, + .maxauthsize = SHA384_DIGEST_SIZE, + .setkey = chcr_authenc_setkey, + .setauthsize = chcr_authenc_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_SHA, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "authenc(hmac(sha512),cbc(aes))", + .cra_driver_name = + "authenc-hmac-sha512-cbc-aes-chcr", + .cra_blocksize = AES_BLOCK_SIZE, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + + }, + .ivsize = AES_BLOCK_SIZE, + .maxauthsize = SHA512_DIGEST_SIZE, + .setkey = chcr_authenc_setkey, + .setauthsize = chcr_authenc_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_NULL, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "authenc(digest_null,cbc(aes))", + .cra_driver_name = + "authenc-digest_null-cbc-aes-chcr", + .cra_blocksize = AES_BLOCK_SIZE, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + + }, + .ivsize = AES_BLOCK_SIZE, + .maxauthsize = 0, + .setkey = chcr_aead_digest_null_setkey, + .setauthsize = chcr_authenc_null_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_SHA, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "authenc(hmac(sha1),rfc3686(ctr(aes)))", + .cra_driver_name = + "authenc-hmac-sha1-rfc3686-ctr-aes-chcr", + .cra_blocksize = 1, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + + }, + .ivsize = CTR_RFC3686_IV_SIZE, + .maxauthsize = SHA1_DIGEST_SIZE, + .setkey = chcr_authenc_setkey, + .setauthsize = chcr_authenc_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_SHA, + .is_registered = 0, + .alg.aead = { + .base = { + + .cra_name = "authenc(hmac(sha256),rfc3686(ctr(aes)))", + .cra_driver_name = + "authenc-hmac-sha256-rfc3686-ctr-aes-chcr", + .cra_blocksize = 1, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + + }, + .ivsize = CTR_RFC3686_IV_SIZE, + .maxauthsize = SHA256_DIGEST_SIZE, + .setkey = chcr_authenc_setkey, + .setauthsize = chcr_authenc_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_SHA, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "authenc(hmac(sha224),rfc3686(ctr(aes)))", + .cra_driver_name = + "authenc-hmac-sha224-rfc3686-ctr-aes-chcr", + .cra_blocksize = 1, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + }, + .ivsize = CTR_RFC3686_IV_SIZE, + .maxauthsize = SHA224_DIGEST_SIZE, + .setkey = chcr_authenc_setkey, + .setauthsize = chcr_authenc_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_SHA, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "authenc(hmac(sha384),rfc3686(ctr(aes)))", + .cra_driver_name = + "authenc-hmac-sha384-rfc3686-ctr-aes-chcr", + .cra_blocksize = 1, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + + }, + .ivsize = CTR_RFC3686_IV_SIZE, + .maxauthsize = SHA384_DIGEST_SIZE, + .setkey = chcr_authenc_setkey, + .setauthsize = chcr_authenc_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_SHA, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "authenc(hmac(sha512),rfc3686(ctr(aes)))", + .cra_driver_name = + "authenc-hmac-sha512-rfc3686-ctr-aes-chcr", + .cra_blocksize = 1, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + + }, + .ivsize = CTR_RFC3686_IV_SIZE, + .maxauthsize = SHA512_DIGEST_SIZE, + .setkey = chcr_authenc_setkey, + .setauthsize = chcr_authenc_setauthsize, + } + }, + { + .type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_NULL, + .is_registered = 0, + .alg.aead = { + .base = { + .cra_name = "authenc(digest_null,rfc3686(ctr(aes)))", + .cra_driver_name = + "authenc-digest_null-rfc3686-ctr-aes-chcr", + .cra_blocksize = 1, + .cra_priority = CHCR_AEAD_PRIORITY, + .cra_ctxsize = sizeof(struct chcr_context) + + sizeof(struct chcr_aead_ctx) + + sizeof(struct chcr_authenc_ctx), + + }, + .ivsize = CTR_RFC3686_IV_SIZE, + .maxauthsize = 0, + .setkey = chcr_aead_digest_null_setkey, + .setauthsize = chcr_authenc_null_setauthsize, + } + }, + +}; + +/* + * chcr_unregister_alg - Deregister crypto algorithms with + * kernel framework. + */ +static int chcr_unregister_alg(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(driver_algs); i++) { + switch (driver_algs[i].type & CRYPTO_ALG_TYPE_MASK) { + case CRYPTO_ALG_TYPE_ABLKCIPHER: + if (driver_algs[i].is_registered) + crypto_unregister_alg( + &driver_algs[i].alg.crypto); + break; + case CRYPTO_ALG_TYPE_AEAD: + if (driver_algs[i].is_registered) + crypto_unregister_aead( + &driver_algs[i].alg.aead); + break; + case CRYPTO_ALG_TYPE_AHASH: + if (driver_algs[i].is_registered) + crypto_unregister_ahash( + &driver_algs[i].alg.hash); + break; + } + driver_algs[i].is_registered = 0; + } + return 0; +} + +#define SZ_AHASH_CTX sizeof(struct chcr_context) +#define SZ_AHASH_H_CTX (sizeof(struct chcr_context) + sizeof(struct hmac_ctx)) +#define SZ_AHASH_REQ_CTX sizeof(struct chcr_ahash_req_ctx) + +/* + * chcr_register_alg - Register crypto algorithms with kernel framework. + */ +static int chcr_register_alg(void) +{ + struct crypto_alg ai; + struct ahash_alg *a_hash; + int err = 0, i; + char *name = NULL; + + for (i = 0; i < ARRAY_SIZE(driver_algs); i++) { + if (driver_algs[i].is_registered) + continue; + switch (driver_algs[i].type & CRYPTO_ALG_TYPE_MASK) { + case CRYPTO_ALG_TYPE_ABLKCIPHER: + driver_algs[i].alg.crypto.cra_priority = + CHCR_CRA_PRIORITY; + driver_algs[i].alg.crypto.cra_module = THIS_MODULE; + driver_algs[i].alg.crypto.cra_flags = + CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK; + driver_algs[i].alg.crypto.cra_ctxsize = + sizeof(struct chcr_context) + + sizeof(struct ablk_ctx); + driver_algs[i].alg.crypto.cra_alignmask = 0; + driver_algs[i].alg.crypto.cra_type = + &crypto_ablkcipher_type; + err = crypto_register_alg(&driver_algs[i].alg.crypto); + name = driver_algs[i].alg.crypto.cra_driver_name; + break; + case CRYPTO_ALG_TYPE_AEAD: + driver_algs[i].alg.aead.base.cra_flags = + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK; + driver_algs[i].alg.aead.encrypt = chcr_aead_encrypt; + driver_algs[i].alg.aead.decrypt = chcr_aead_decrypt; + driver_algs[i].alg.aead.init = chcr_aead_cra_init; + driver_algs[i].alg.aead.exit = chcr_aead_cra_exit; + driver_algs[i].alg.aead.base.cra_module = THIS_MODULE; + err = crypto_register_aead(&driver_algs[i].alg.aead); + name = driver_algs[i].alg.aead.base.cra_driver_name; + break; + case CRYPTO_ALG_TYPE_AHASH: + a_hash = &driver_algs[i].alg.hash; + a_hash->update = chcr_ahash_update; + a_hash->final = chcr_ahash_final; + a_hash->finup = chcr_ahash_finup; + a_hash->digest = chcr_ahash_digest; + a_hash->export = chcr_ahash_export; + a_hash->import = chcr_ahash_import; + a_hash->halg.statesize = SZ_AHASH_REQ_CTX; + a_hash->halg.base.cra_priority = CHCR_CRA_PRIORITY; + a_hash->halg.base.cra_module = THIS_MODULE; + a_hash->halg.base.cra_flags = CRYPTO_ALG_ASYNC; + a_hash->halg.base.cra_alignmask = 0; + a_hash->halg.base.cra_exit = NULL; + + if (driver_algs[i].type == CRYPTO_ALG_TYPE_HMAC) { + a_hash->halg.base.cra_init = chcr_hmac_cra_init; + a_hash->halg.base.cra_exit = chcr_hmac_cra_exit; + a_hash->init = chcr_hmac_init; + a_hash->setkey = chcr_ahash_setkey; + a_hash->halg.base.cra_ctxsize = SZ_AHASH_H_CTX; + } else { + a_hash->init = chcr_sha_init; + a_hash->halg.base.cra_ctxsize = SZ_AHASH_CTX; + a_hash->halg.base.cra_init = chcr_sha_cra_init; + } + err = crypto_register_ahash(&driver_algs[i].alg.hash); + ai = driver_algs[i].alg.hash.halg.base; + name = ai.cra_driver_name; + break; + } + if (err) { + pr_err("chcr : %s : Algorithm registration failed\n", + name); + goto register_err; + } else { + driver_algs[i].is_registered = 1; + } + } + return 0; + +register_err: + chcr_unregister_alg(); + return err; +} + +/* + * start_crypto - Register the crypto algorithms. + * This should called once when the first device comesup. After this + * kernel will start calling driver APIs for crypto operations. + */ +int start_crypto(void) +{ + return chcr_register_alg(); +} + +/* + * stop_crypto - Deregister all the crypto algorithms with kernel. + * This should be called once when the last device goes down. After this + * kernel will not call the driver API for crypto operations. + */ +int stop_crypto(void) +{ + chcr_unregister_alg(); + return 0; +} diff --git a/drivers/crypto/chelsio/chcr_algo.h b/drivers/crypto/chelsio/chcr_algo.h new file mode 100644 index 000000000..187150030 --- /dev/null +++ b/drivers/crypto/chelsio/chcr_algo.h @@ -0,0 +1,442 @@ +/* + * This file is part of the Chelsio T6 Crypto driver for Linux. + * + * Copyright (c) 2003-2016 Chelsio Communications, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __CHCR_ALGO_H__ +#define __CHCR_ALGO_H__ + +/* Crypto key context */ +#define KEY_CONTEXT_CTX_LEN_S 24 +#define KEY_CONTEXT_CTX_LEN_M 0xff +#define KEY_CONTEXT_CTX_LEN_V(x) ((x) << KEY_CONTEXT_CTX_LEN_S) +#define KEY_CONTEXT_CTX_LEN_G(x) \ + (((x) >> KEY_CONTEXT_CTX_LEN_S) & KEY_CONTEXT_CTX_LEN_M) + +#define KEY_CONTEXT_DUAL_CK_S 12 +#define KEY_CONTEXT_DUAL_CK_M 0x1 +#define KEY_CONTEXT_DUAL_CK_V(x) ((x) << KEY_CONTEXT_DUAL_CK_S) +#define KEY_CONTEXT_DUAL_CK_G(x) \ +(((x) >> KEY_CONTEXT_DUAL_CK_S) & KEY_CONTEXT_DUAL_CK_M) +#define KEY_CONTEXT_DUAL_CK_F KEY_CONTEXT_DUAL_CK_V(1U) + +#define KEY_CONTEXT_SALT_PRESENT_S 10 +#define KEY_CONTEXT_SALT_PRESENT_M 0x1 +#define KEY_CONTEXT_SALT_PRESENT_V(x) ((x) << KEY_CONTEXT_SALT_PRESENT_S) +#define KEY_CONTEXT_SALT_PRESENT_G(x) \ + (((x) >> KEY_CONTEXT_SALT_PRESENT_S) & \ + KEY_CONTEXT_SALT_PRESENT_M) +#define KEY_CONTEXT_SALT_PRESENT_F KEY_CONTEXT_SALT_PRESENT_V(1U) + +#define KEY_CONTEXT_VALID_S 0 +#define KEY_CONTEXT_VALID_M 0x1 +#define KEY_CONTEXT_VALID_V(x) ((x) << KEY_CONTEXT_VALID_S) +#define KEY_CONTEXT_VALID_G(x) \ + (((x) >> KEY_CONTEXT_VALID_S) & \ + KEY_CONTEXT_VALID_M) +#define KEY_CONTEXT_VALID_F KEY_CONTEXT_VALID_V(1U) + +#define KEY_CONTEXT_CK_SIZE_S 6 +#define KEY_CONTEXT_CK_SIZE_M 0xf +#define KEY_CONTEXT_CK_SIZE_V(x) ((x) << KEY_CONTEXT_CK_SIZE_S) +#define KEY_CONTEXT_CK_SIZE_G(x) \ + (((x) >> KEY_CONTEXT_CK_SIZE_S) & KEY_CONTEXT_CK_SIZE_M) + +#define KEY_CONTEXT_MK_SIZE_S 2 +#define KEY_CONTEXT_MK_SIZE_M 0xf +#define KEY_CONTEXT_MK_SIZE_V(x) ((x) << KEY_CONTEXT_MK_SIZE_S) +#define KEY_CONTEXT_MK_SIZE_G(x) \ + (((x) >> KEY_CONTEXT_MK_SIZE_S) & KEY_CONTEXT_MK_SIZE_M) + +#define KEY_CONTEXT_OPAD_PRESENT_S 11 +#define KEY_CONTEXT_OPAD_PRESENT_M 0x1 +#define KEY_CONTEXT_OPAD_PRESENT_V(x) ((x) << KEY_CONTEXT_OPAD_PRESENT_S) +#define KEY_CONTEXT_OPAD_PRESENT_G(x) \ + (((x) >> KEY_CONTEXT_OPAD_PRESENT_S) & \ + KEY_CONTEXT_OPAD_PRESENT_M) +#define KEY_CONTEXT_OPAD_PRESENT_F KEY_CONTEXT_OPAD_PRESENT_V(1U) + +#define TLS_KEYCTX_RXFLIT_CNT_S 24 +#define TLS_KEYCTX_RXFLIT_CNT_V(x) ((x) << TLS_KEYCTX_RXFLIT_CNT_S) + +#define TLS_KEYCTX_RXPROT_VER_S 20 +#define TLS_KEYCTX_RXPROT_VER_M 0xf +#define TLS_KEYCTX_RXPROT_VER_V(x) ((x) << TLS_KEYCTX_RXPROT_VER_S) + +#define TLS_KEYCTX_RXCIPH_MODE_S 16 +#define TLS_KEYCTX_RXCIPH_MODE_M 0xf +#define TLS_KEYCTX_RXCIPH_MODE_V(x) ((x) << TLS_KEYCTX_RXCIPH_MODE_S) + +#define TLS_KEYCTX_RXAUTH_MODE_S 12 +#define TLS_KEYCTX_RXAUTH_MODE_M 0xf +#define TLS_KEYCTX_RXAUTH_MODE_V(x) ((x) << TLS_KEYCTX_RXAUTH_MODE_S) + +#define TLS_KEYCTX_RXCIAU_CTRL_S 11 +#define TLS_KEYCTX_RXCIAU_CTRL_V(x) ((x) << TLS_KEYCTX_RXCIAU_CTRL_S) + +#define TLS_KEYCTX_RX_SEQCTR_S 9 +#define TLS_KEYCTX_RX_SEQCTR_M 0x3 +#define TLS_KEYCTX_RX_SEQCTR_V(x) ((x) << TLS_KEYCTX_RX_SEQCTR_S) + +#define TLS_KEYCTX_RX_VALID_S 8 +#define TLS_KEYCTX_RX_VALID_V(x) ((x) << TLS_KEYCTX_RX_VALID_S) + +#define TLS_KEYCTX_RXCK_SIZE_S 3 +#define TLS_KEYCTX_RXCK_SIZE_M 0x7 +#define TLS_KEYCTX_RXCK_SIZE_V(x) ((x) << TLS_KEYCTX_RXCK_SIZE_S) + +#define TLS_KEYCTX_RXMK_SIZE_S 0 +#define TLS_KEYCTX_RXMK_SIZE_M 0x7 +#define TLS_KEYCTX_RXMK_SIZE_V(x) ((x) << TLS_KEYCTX_RXMK_SIZE_S) + +#define CHCR_HASH_MAX_DIGEST_SIZE 64 +#define CHCR_MAX_SHA_DIGEST_SIZE 64 + +#define IPSEC_TRUNCATED_ICV_SIZE 12 +#define TLS_TRUNCATED_HMAC_SIZE 10 +#define CBCMAC_DIGEST_SIZE 16 +#define MAX_HASH_NAME 20 + +#define SHA1_INIT_STATE_5X4B 5 +#define SHA256_INIT_STATE_8X4B 8 +#define SHA512_INIT_STATE_8X8B 8 +#define SHA1_INIT_STATE SHA1_INIT_STATE_5X4B +#define SHA224_INIT_STATE SHA256_INIT_STATE_8X4B +#define SHA256_INIT_STATE SHA256_INIT_STATE_8X4B +#define SHA384_INIT_STATE SHA512_INIT_STATE_8X8B +#define SHA512_INIT_STATE SHA512_INIT_STATE_8X8B + +#define DUMMY_BYTES 16 + +#define IPAD_DATA 0x36363636 +#define OPAD_DATA 0x5c5c5c5c + +#define TRANSHDR_SIZE(kctx_len)\ + (sizeof(struct chcr_wr) +\ + kctx_len) +#define CIPHER_TRANSHDR_SIZE(kctx_len, sge_pairs) \ + (TRANSHDR_SIZE((kctx_len)) + (sge_pairs) +\ + sizeof(struct cpl_rx_phys_dsgl) + AES_BLOCK_SIZE) +#define HASH_TRANSHDR_SIZE(kctx_len)\ + (TRANSHDR_SIZE(kctx_len) + DUMMY_BYTES) + + +#define FILL_SEC_CPL_OP_IVINSR(id, len, ofst) \ + htonl( \ + CPL_TX_SEC_PDU_OPCODE_V(CPL_TX_SEC_PDU) | \ + CPL_TX_SEC_PDU_RXCHID_V((id)) | \ + CPL_TX_SEC_PDU_ACKFOLLOWS_V(0) | \ + CPL_TX_SEC_PDU_ULPTXLPBK_V(1) | \ + CPL_TX_SEC_PDU_CPLLEN_V((len)) | \ + CPL_TX_SEC_PDU_PLACEHOLDER_V(0) | \ + CPL_TX_SEC_PDU_IVINSRTOFST_V((ofst))) + +#define FILL_SEC_CPL_CIPHERSTOP_HI(a_start, a_stop, c_start, c_stop_hi) \ + htonl( \ + CPL_TX_SEC_PDU_AADSTART_V((a_start)) | \ + CPL_TX_SEC_PDU_AADSTOP_V((a_stop)) | \ + CPL_TX_SEC_PDU_CIPHERSTART_V((c_start)) | \ + CPL_TX_SEC_PDU_CIPHERSTOP_HI_V((c_stop_hi))) + +#define FILL_SEC_CPL_AUTHINSERT(c_stop_lo, a_start, a_stop, a_inst) \ + htonl( \ + CPL_TX_SEC_PDU_CIPHERSTOP_LO_V((c_stop_lo)) | \ + CPL_TX_SEC_PDU_AUTHSTART_V((a_start)) | \ + CPL_TX_SEC_PDU_AUTHSTOP_V((a_stop)) | \ + CPL_TX_SEC_PDU_AUTHINSERT_V((a_inst))) + +#define FILL_SEC_CPL_SCMD0_SEQNO(ctrl, seq, cmode, amode, opad, size) \ + htonl( \ + SCMD_SEQ_NO_CTRL_V(0) | \ + SCMD_STATUS_PRESENT_V(0) | \ + SCMD_PROTO_VERSION_V(CHCR_SCMD_PROTO_VERSION_GENERIC) | \ + SCMD_ENC_DEC_CTRL_V((ctrl)) | \ + SCMD_CIPH_AUTH_SEQ_CTRL_V((seq)) | \ + SCMD_CIPH_MODE_V((cmode)) | \ + SCMD_AUTH_MODE_V((amode)) | \ + SCMD_HMAC_CTRL_V((opad)) | \ + SCMD_IV_SIZE_V((size)) | \ + SCMD_NUM_IVS_V(0)) + +#define FILL_SEC_CPL_IVGEN_HDRLEN(last, more, ctx_in, mac, ivdrop, len) htonl( \ + SCMD_ENB_DBGID_V(0) | \ + SCMD_IV_GEN_CTRL_V(0) | \ + SCMD_LAST_FRAG_V((last)) | \ + SCMD_MORE_FRAGS_V((more)) | \ + SCMD_TLS_COMPPDU_V(0) | \ + SCMD_KEY_CTX_INLINE_V((ctx_in)) | \ + SCMD_TLS_FRAG_ENABLE_V(0) | \ + SCMD_MAC_ONLY_V((mac)) | \ + SCMD_AADIVDROP_V((ivdrop)) | \ + SCMD_HDR_LEN_V((len))) + +#define FILL_KEY_CTX_HDR(ck_size, mk_size, d_ck, opad, ctx_len) \ + htonl(KEY_CONTEXT_VALID_V(1) | \ + KEY_CONTEXT_CK_SIZE_V((ck_size)) | \ + KEY_CONTEXT_MK_SIZE_V(mk_size) | \ + KEY_CONTEXT_DUAL_CK_V((d_ck)) | \ + KEY_CONTEXT_OPAD_PRESENT_V((opad)) | \ + KEY_CONTEXT_SALT_PRESENT_V(1) | \ + KEY_CONTEXT_CTX_LEN_V((ctx_len))) + +#define FILL_KEY_CRX_HDR(ck_size, mk_size, d_ck, opad, ctx_len) \ + htonl(TLS_KEYCTX_RXMK_SIZE_V(mk_size) | \ + TLS_KEYCTX_RXCK_SIZE_V(ck_size) | \ + TLS_KEYCTX_RX_VALID_V(1) | \ + TLS_KEYCTX_RX_SEQCTR_V(3) | \ + TLS_KEYCTX_RXAUTH_MODE_V(4) | \ + TLS_KEYCTX_RXCIPH_MODE_V(2) | \ + TLS_KEYCTX_RXFLIT_CNT_V((ctx_len))) + +#define FILL_WR_OP_CCTX_SIZE \ + htonl( \ + FW_CRYPTO_LOOKASIDE_WR_OPCODE_V( \ + FW_CRYPTO_LOOKASIDE_WR) | \ + FW_CRYPTO_LOOKASIDE_WR_COMPL_V(0) | \ + FW_CRYPTO_LOOKASIDE_WR_IMM_LEN_V((0)) | \ + FW_CRYPTO_LOOKASIDE_WR_CCTX_LOC_V(0) | \ + FW_CRYPTO_LOOKASIDE_WR_CCTX_SIZE_V(0)) + +#define FILL_WR_RX_Q_ID(cid, qid, lcb, fid) \ + htonl( \ + FW_CRYPTO_LOOKASIDE_WR_RX_CHID_V((cid)) | \ + FW_CRYPTO_LOOKASIDE_WR_RX_Q_ID_V((qid)) | \ + FW_CRYPTO_LOOKASIDE_WR_LCB_V((lcb)) | \ + FW_CRYPTO_LOOKASIDE_WR_IV_V((IV_NOP)) | \ + FW_CRYPTO_LOOKASIDE_WR_FQIDX_V(fid)) + +#define FILL_ULPTX_CMD_DEST(cid, qid) \ + htonl(ULPTX_CMD_V(ULP_TX_PKT) | \ + ULP_TXPKT_DEST_V(0) | \ + ULP_TXPKT_DATAMODIFY_V(0) | \ + ULP_TXPKT_CHANNELID_V((cid)) | \ + ULP_TXPKT_RO_V(1) | \ + ULP_TXPKT_FID_V(qid)) + +#define KEYCTX_ALIGN_PAD(bs) ({unsigned int _bs = (bs);\ + _bs == SHA1_DIGEST_SIZE ? 12 : 0; }) + +#define FILL_PLD_SIZE_HASH_SIZE(payload_sgl_len, sgl_lengths, total_frags) \ + htonl(FW_CRYPTO_LOOKASIDE_WR_PLD_SIZE_V(payload_sgl_len ? \ + sgl_lengths[total_frags] : 0) |\ + FW_CRYPTO_LOOKASIDE_WR_HASH_SIZE_V(0)) + +#define FILL_LEN_PKD(calc_tx_flits_ofld, skb) \ + htonl(FW_CRYPTO_LOOKASIDE_WR_LEN16_V(DIV_ROUND_UP((\ + calc_tx_flits_ofld(skb) * 8), 16))) + +#define FILL_CMD_MORE(immdatalen) htonl(ULPTX_CMD_V(ULP_TX_SC_IMM) |\ + ULP_TX_SC_MORE_V((immdatalen))) +#define MAX_NK 8 +#define MAX_DSGL_ENT 32 +#define MIN_AUTH_SG 1 /* IV */ +#define MIN_GCM_SG 1 /* IV */ +#define MIN_DIGEST_SG 1 /*Partial Buffer*/ +#define MIN_CCM_SG 2 /*IV+B0*/ +#define CIP_SPACE_LEFT(len) \ + ((SGE_MAX_WR_LEN - CIP_WR_MIN_LEN - (len))) +#define HASH_SPACE_LEFT(len) \ + ((SGE_MAX_WR_LEN - HASH_WR_MIN_LEN - (len))) + +struct algo_param { + unsigned int auth_mode; + unsigned int mk_size; + unsigned int result_size; +}; + +struct hash_wr_param { + struct algo_param alg_prm; + unsigned int opad_needed; + unsigned int more; + unsigned int last; + unsigned int kctx_len; + unsigned int sg_len; + unsigned int bfr_len; + unsigned int hash_size; + u64 scmd1; +}; + +struct cipher_wr_param { + struct ablkcipher_request *req; + char *iv; + int bytes; + unsigned short qid; +}; +enum { + AES_KEYLENGTH_128BIT = 128, + AES_KEYLENGTH_192BIT = 192, + AES_KEYLENGTH_256BIT = 256 +}; + +enum { + KEYLENGTH_3BYTES = 3, + KEYLENGTH_4BYTES = 4, + KEYLENGTH_6BYTES = 6, + KEYLENGTH_8BYTES = 8 +}; + +enum { + NUMBER_OF_ROUNDS_10 = 10, + NUMBER_OF_ROUNDS_12 = 12, + NUMBER_OF_ROUNDS_14 = 14, +}; + +/* + * CCM defines values of 4, 6, 8, 10, 12, 14, and 16 octets, + * where they indicate the size of the integrity check value (ICV) + */ +enum { + ICV_4 = 4, + ICV_6 = 6, + ICV_8 = 8, + ICV_10 = 10, + ICV_12 = 12, + ICV_13 = 13, + ICV_14 = 14, + ICV_15 = 15, + ICV_16 = 16 +}; + +struct phys_sge_pairs { + __be16 len[8]; + __be64 addr[8]; +}; + + +static const u32 sha1_init[SHA1_DIGEST_SIZE / 4] = { + SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4, +}; + +static const u32 sha224_init[SHA256_DIGEST_SIZE / 4] = { + SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3, + SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7, +}; + +static const u32 sha256_init[SHA256_DIGEST_SIZE / 4] = { + SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3, + SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7, +}; + +static const u64 sha384_init[SHA512_DIGEST_SIZE / 8] = { + SHA384_H0, SHA384_H1, SHA384_H2, SHA384_H3, + SHA384_H4, SHA384_H5, SHA384_H6, SHA384_H7, +}; + +static const u64 sha512_init[SHA512_DIGEST_SIZE / 8] = { + SHA512_H0, SHA512_H1, SHA512_H2, SHA512_H3, + SHA512_H4, SHA512_H5, SHA512_H6, SHA512_H7, +}; + +static inline void copy_hash_init_values(char *key, int digestsize) +{ + u8 i; + __be32 *dkey = (__be32 *)key; + u64 *ldkey = (u64 *)key; + __be64 *sha384 = (__be64 *)sha384_init; + __be64 *sha512 = (__be64 *)sha512_init; + + switch (digestsize) { + case SHA1_DIGEST_SIZE: + for (i = 0; i < SHA1_INIT_STATE; i++) + dkey[i] = cpu_to_be32(sha1_init[i]); + break; + case SHA224_DIGEST_SIZE: + for (i = 0; i < SHA224_INIT_STATE; i++) + dkey[i] = cpu_to_be32(sha224_init[i]); + break; + case SHA256_DIGEST_SIZE: + for (i = 0; i < SHA256_INIT_STATE; i++) + dkey[i] = cpu_to_be32(sha256_init[i]); + break; + case SHA384_DIGEST_SIZE: + for (i = 0; i < SHA384_INIT_STATE; i++) + ldkey[i] = be64_to_cpu(sha384[i]); + break; + case SHA512_DIGEST_SIZE: + for (i = 0; i < SHA512_INIT_STATE; i++) + ldkey[i] = be64_to_cpu(sha512[i]); + break; + } +} + +static const u8 sgl_lengths[20] = { + 0, 1, 2, 3, 4, 4, 5, 6, 7, 7, 8, 9, 10, 10, 11, 12, 13, 13, 14, 15 +}; + +/* Number of len fields(8) * size of one addr field */ +#define PHYSDSGL_MAX_LEN_SIZE 16 + +static inline u16 get_space_for_phys_dsgl(unsigned int sgl_entr) +{ + /* len field size + addr field size */ + return ((sgl_entr >> 3) + ((sgl_entr % 8) ? + 1 : 0)) * PHYSDSGL_MAX_LEN_SIZE + + (sgl_entr << 3) + ((sgl_entr % 2 ? 1 : 0) << 3); +} + +/* The AES s-transform matrix (s-box). */ +static const u8 aes_sbox[256] = { + 99, 124, 119, 123, 242, 107, 111, 197, 48, 1, 103, 43, 254, 215, + 171, 118, 202, 130, 201, 125, 250, 89, 71, 240, 173, 212, 162, 175, + 156, 164, 114, 192, 183, 253, 147, 38, 54, 63, 247, 204, 52, 165, + 229, 241, 113, 216, 49, 21, 4, 199, 35, 195, 24, 150, 5, 154, 7, + 18, 128, 226, 235, 39, 178, 117, 9, 131, 44, 26, 27, 110, 90, + 160, 82, 59, 214, 179, 41, 227, 47, 132, 83, 209, 0, 237, 32, + 252, 177, 91, 106, 203, 190, 57, 74, 76, 88, 207, 208, 239, 170, + 251, 67, 77, 51, 133, 69, 249, 2, 127, 80, 60, 159, 168, 81, + 163, 64, 143, 146, 157, 56, 245, 188, 182, 218, 33, 16, 255, 243, + 210, 205, 12, 19, 236, 95, 151, 68, 23, 196, 167, 126, 61, 100, + 93, 25, 115, 96, 129, 79, 220, 34, 42, 144, 136, 70, 238, 184, + 20, 222, 94, 11, 219, 224, 50, 58, 10, 73, 6, 36, 92, 194, + 211, 172, 98, 145, 149, 228, 121, 231, 200, 55, 109, 141, 213, 78, + 169, 108, 86, 244, 234, 101, 122, 174, 8, 186, 120, 37, 46, 28, 166, + 180, 198, 232, 221, 116, 31, 75, 189, 139, 138, 112, 62, 181, 102, + 72, 3, 246, 14, 97, 53, 87, 185, 134, 193, 29, 158, 225, 248, + 152, 17, 105, 217, 142, 148, 155, 30, 135, 233, 206, 85, 40, 223, + 140, 161, 137, 13, 191, 230, 66, 104, 65, 153, 45, 15, 176, 84, + 187, 22 +}; + +static inline u32 aes_ks_subword(const u32 w) +{ + u8 bytes[4]; + + *(u32 *)(&bytes[0]) = w; + bytes[0] = aes_sbox[bytes[0]]; + bytes[1] = aes_sbox[bytes[1]]; + bytes[2] = aes_sbox[bytes[2]]; + bytes[3] = aes_sbox[bytes[3]]; + return *(u32 *)(&bytes[0]); +} + +#endif /* __CHCR_ALGO_H__ */ diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c new file mode 100644 index 000000000..04f277cad --- /dev/null +++ b/drivers/crypto/chelsio/chcr_core.c @@ -0,0 +1,270 @@ +/** + * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux. + * + * Copyright (C) 2011-2016 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + * + * Written and Maintained by: + * Manoj Malviya (manojmalviya@chelsio.com) + * Atul Gupta (atul.gupta@chelsio.com) + * Jitendra Lulla (jlulla@chelsio.com) + * Yeshaswi M R Gowda (yeshaswi@chelsio.com) + * Harsh Jain (harsh@chelsio.com) + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> + +#include <crypto/aes.h> +#include <crypto/hash.h> + +#include "t4_msg.h" +#include "chcr_core.h" +#include "cxgb4_uld.h" + +static LIST_HEAD(uld_ctx_list); +static DEFINE_MUTEX(dev_mutex); +static atomic_t dev_count; +static struct uld_ctx *ctx_rr; + +typedef int (*chcr_handler_func)(struct chcr_dev *dev, unsigned char *input); +static int cpl_fw6_pld_handler(struct chcr_dev *dev, unsigned char *input); +static void *chcr_uld_add(const struct cxgb4_lld_info *lld); +static int chcr_uld_state_change(void *handle, enum cxgb4_state state); + +static chcr_handler_func work_handlers[NUM_CPL_CMDS] = { + [CPL_FW6_PLD] = cpl_fw6_pld_handler, +}; + +static struct cxgb4_uld_info chcr_uld_info = { + .name = DRV_MODULE_NAME, + .nrxq = MAX_ULD_QSETS, + .ntxq = MAX_ULD_QSETS, + .rxq_size = 1024, + .add = chcr_uld_add, + .state_change = chcr_uld_state_change, + .rx_handler = chcr_uld_rx_handler, +#ifdef CONFIG_CHELSIO_IPSEC_INLINE + .tx_handler = chcr_uld_tx_handler, +#endif /* CONFIG_CHELSIO_IPSEC_INLINE */ +}; + +struct uld_ctx *assign_chcr_device(void) +{ + struct uld_ctx *u_ctx = NULL; + + /* + * When multiple devices are present in system select + * device in round-robin fashion for crypto operations + * Although One session must use the same device to + * maintain request-response ordering. + */ + mutex_lock(&dev_mutex); + if (!list_empty(&uld_ctx_list)) { + u_ctx = ctx_rr; + if (list_is_last(&ctx_rr->entry, &uld_ctx_list)) + ctx_rr = list_first_entry(&uld_ctx_list, + struct uld_ctx, + entry); + else + ctx_rr = list_next_entry(ctx_rr, entry); + } + mutex_unlock(&dev_mutex); + return u_ctx; +} + +static int chcr_dev_add(struct uld_ctx *u_ctx) +{ + struct chcr_dev *dev; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENXIO; + + spin_lock_init(&dev->lock_chcr_dev); + u_ctx->dev = dev; + dev->u_ctx = u_ctx; + atomic_inc(&dev_count); + mutex_lock(&dev_mutex); + list_add_tail(&u_ctx->entry, &uld_ctx_list); + if (!ctx_rr) + ctx_rr = u_ctx; + mutex_unlock(&dev_mutex); + return 0; +} + +static int chcr_dev_remove(struct uld_ctx *u_ctx) +{ + if (ctx_rr == u_ctx) { + if (list_is_last(&ctx_rr->entry, &uld_ctx_list)) + ctx_rr = list_first_entry(&uld_ctx_list, + struct uld_ctx, + entry); + else + ctx_rr = list_next_entry(ctx_rr, entry); + } + list_del(&u_ctx->entry); + if (list_empty(&uld_ctx_list)) + ctx_rr = NULL; + kfree(u_ctx->dev); + u_ctx->dev = NULL; + atomic_dec(&dev_count); + return 0; +} + +static int cpl_fw6_pld_handler(struct chcr_dev *dev, + unsigned char *input) +{ + struct crypto_async_request *req; + struct cpl_fw6_pld *fw6_pld; + u32 ack_err_status = 0; + int error_status = 0; + struct adapter *adap = padap(dev); + + fw6_pld = (struct cpl_fw6_pld *)input; + req = (struct crypto_async_request *)(uintptr_t)be64_to_cpu( + fw6_pld->data[1]); + + ack_err_status = + ntohl(*(__be32 *)((unsigned char *)&fw6_pld->data[0] + 4)); + if (ack_err_status) { + if (CHK_MAC_ERR_BIT(ack_err_status) || + CHK_PAD_ERR_BIT(ack_err_status)) + error_status = -EBADMSG; + atomic_inc(&adap->chcr_stats.error); + } + /* call completion callback with failure status */ + if (req) { + error_status = chcr_handle_resp(req, input, error_status); + } else { + pr_err("Incorrect request address from the firmware\n"); + return -EFAULT; + } + return 0; +} + +int chcr_send_wr(struct sk_buff *skb) +{ + return cxgb4_crypto_send(skb->dev, skb); +} + +static void *chcr_uld_add(const struct cxgb4_lld_info *lld) +{ + struct uld_ctx *u_ctx; + + /* Create the device and add it in the device list */ + if (!(lld->ulp_crypto & ULP_CRYPTO_LOOKASIDE)) + return ERR_PTR(-EOPNOTSUPP); + + /* Create the device and add it in the device list */ + u_ctx = kzalloc(sizeof(*u_ctx), GFP_KERNEL); + if (!u_ctx) { + u_ctx = ERR_PTR(-ENOMEM); + goto out; + } + u_ctx->lldi = *lld; +#ifdef CONFIG_CHELSIO_IPSEC_INLINE + if (lld->crypto & ULP_CRYPTO_IPSEC_INLINE) + chcr_add_xfrmops(lld); +#endif /* CONFIG_CHELSIO_IPSEC_INLINE */ +out: + return u_ctx; +} + +int chcr_uld_rx_handler(void *handle, const __be64 *rsp, + const struct pkt_gl *pgl) +{ + struct uld_ctx *u_ctx = (struct uld_ctx *)handle; + struct chcr_dev *dev = u_ctx->dev; + const struct cpl_fw6_pld *rpl = (struct cpl_fw6_pld *)rsp; + + if (rpl->opcode != CPL_FW6_PLD) { + pr_err("Unsupported opcode\n"); + return 0; + } + + if (!pgl) + work_handlers[rpl->opcode](dev, (unsigned char *)&rsp[1]); + else + work_handlers[rpl->opcode](dev, pgl->va); + return 0; +} + +#ifdef CONFIG_CHELSIO_IPSEC_INLINE +int chcr_uld_tx_handler(struct sk_buff *skb, struct net_device *dev) +{ + return chcr_ipsec_xmit(skb, dev); +} +#endif /* CONFIG_CHELSIO_IPSEC_INLINE */ + +static int chcr_uld_state_change(void *handle, enum cxgb4_state state) +{ + struct uld_ctx *u_ctx = handle; + int ret = 0; + + switch (state) { + case CXGB4_STATE_UP: + if (!u_ctx->dev) { + ret = chcr_dev_add(u_ctx); + if (ret != 0) + return ret; + } + if (atomic_read(&dev_count) == 1) + ret = start_crypto(); + break; + + case CXGB4_STATE_DETACH: + if (u_ctx->dev) { + mutex_lock(&dev_mutex); + chcr_dev_remove(u_ctx); + mutex_unlock(&dev_mutex); + } + if (!atomic_read(&dev_count)) + stop_crypto(); + break; + + case CXGB4_STATE_START_RECOVERY: + case CXGB4_STATE_DOWN: + default: + break; + } + return ret; +} + +static int __init chcr_crypto_init(void) +{ + if (cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info)) + pr_err("ULD register fail: No chcr crypto support in cxgb4\n"); + + return 0; +} + +static void __exit chcr_crypto_exit(void) +{ + struct uld_ctx *u_ctx, *tmp; + + if (atomic_read(&dev_count)) + stop_crypto(); + + /* Remove all devices from list */ + mutex_lock(&dev_mutex); + list_for_each_entry_safe(u_ctx, tmp, &uld_ctx_list, entry) { + if (u_ctx->dev) + chcr_dev_remove(u_ctx); + kfree(u_ctx); + } + mutex_unlock(&dev_mutex); + cxgb4_unregister_uld(CXGB4_ULD_CRYPTO); +} + +module_init(chcr_crypto_init); +module_exit(chcr_crypto_exit); + +MODULE_DESCRIPTION("Crypto Co-processor for Chelsio Terminator cards."); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Chelsio Communications"); +MODULE_VERSION(DRV_VERSION); diff --git a/drivers/crypto/chelsio/chcr_core.h b/drivers/crypto/chelsio/chcr_core.h new file mode 100644 index 000000000..de3a9c085 --- /dev/null +++ b/drivers/crypto/chelsio/chcr_core.h @@ -0,0 +1,195 @@ +/* + * This file is part of the Chelsio T6 Crypto driver for Linux. + * + * Copyright (c) 2003-2016 Chelsio Communications, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __CHCR_CORE_H__ +#define __CHCR_CORE_H__ + +#include <crypto/algapi.h> +#include "t4_hw.h" +#include "cxgb4.h" +#include "t4_msg.h" +#include "cxgb4_uld.h" + +#define DRV_MODULE_NAME "chcr" +#define DRV_VERSION "1.0.0.0" + +#define MAX_PENDING_REQ_TO_HW 20 +#define CHCR_TEST_RESPONSE_TIMEOUT 1000 + +#define PAD_ERROR_BIT 1 +#define CHK_PAD_ERR_BIT(x) (((x) >> PAD_ERROR_BIT) & 1) + +#define MAC_ERROR_BIT 0 +#define CHK_MAC_ERR_BIT(x) (((x) >> MAC_ERROR_BIT) & 1) +#define MAX_SALT 4 +#define CIP_WR_MIN_LEN (sizeof(struct chcr_wr) + \ + sizeof(struct cpl_rx_phys_dsgl) + \ + sizeof(struct ulptx_sgl) + 16) //IV + +#define HASH_WR_MIN_LEN (sizeof(struct chcr_wr) + \ + DUMMY_BYTES + \ + sizeof(struct ulptx_sgl)) + +#define padap(dev) pci_get_drvdata(dev->u_ctx->lldi.pdev) + +struct uld_ctx; + +struct _key_ctx { + __be32 ctx_hdr; + u8 salt[MAX_SALT]; + __be64 iv_to_auth; + unsigned char key[0]; +}; + +#define KEYCTX_TX_WR_IV_S 55 +#define KEYCTX_TX_WR_IV_M 0x1ffULL +#define KEYCTX_TX_WR_IV_V(x) ((x) << KEYCTX_TX_WR_IV_S) +#define KEYCTX_TX_WR_IV_G(x) \ + (((x) >> KEYCTX_TX_WR_IV_S) & KEYCTX_TX_WR_IV_M) + +#define KEYCTX_TX_WR_AAD_S 47 +#define KEYCTX_TX_WR_AAD_M 0xffULL +#define KEYCTX_TX_WR_AAD_V(x) ((x) << KEYCTX_TX_WR_AAD_S) +#define KEYCTX_TX_WR_AAD_G(x) (((x) >> KEYCTX_TX_WR_AAD_S) & \ + KEYCTX_TX_WR_AAD_M) + +#define KEYCTX_TX_WR_AADST_S 39 +#define KEYCTX_TX_WR_AADST_M 0xffULL +#define KEYCTX_TX_WR_AADST_V(x) ((x) << KEYCTX_TX_WR_AADST_S) +#define KEYCTX_TX_WR_AADST_G(x) \ + (((x) >> KEYCTX_TX_WR_AADST_S) & KEYCTX_TX_WR_AADST_M) + +#define KEYCTX_TX_WR_CIPHER_S 30 +#define KEYCTX_TX_WR_CIPHER_M 0x1ffULL +#define KEYCTX_TX_WR_CIPHER_V(x) ((x) << KEYCTX_TX_WR_CIPHER_S) +#define KEYCTX_TX_WR_CIPHER_G(x) \ + (((x) >> KEYCTX_TX_WR_CIPHER_S) & KEYCTX_TX_WR_CIPHER_M) + +#define KEYCTX_TX_WR_CIPHERST_S 23 +#define KEYCTX_TX_WR_CIPHERST_M 0x7f +#define KEYCTX_TX_WR_CIPHERST_V(x) ((x) << KEYCTX_TX_WR_CIPHERST_S) +#define KEYCTX_TX_WR_CIPHERST_G(x) \ + (((x) >> KEYCTX_TX_WR_CIPHERST_S) & KEYCTX_TX_WR_CIPHERST_M) + +#define KEYCTX_TX_WR_AUTH_S 14 +#define KEYCTX_TX_WR_AUTH_M 0x1ff +#define KEYCTX_TX_WR_AUTH_V(x) ((x) << KEYCTX_TX_WR_AUTH_S) +#define KEYCTX_TX_WR_AUTH_G(x) \ + (((x) >> KEYCTX_TX_WR_AUTH_S) & KEYCTX_TX_WR_AUTH_M) + +#define KEYCTX_TX_WR_AUTHST_S 7 +#define KEYCTX_TX_WR_AUTHST_M 0x7f +#define KEYCTX_TX_WR_AUTHST_V(x) ((x) << KEYCTX_TX_WR_AUTHST_S) +#define KEYCTX_TX_WR_AUTHST_G(x) \ + (((x) >> KEYCTX_TX_WR_AUTHST_S) & KEYCTX_TX_WR_AUTHST_M) + +#define KEYCTX_TX_WR_AUTHIN_S 0 +#define KEYCTX_TX_WR_AUTHIN_M 0x7f +#define KEYCTX_TX_WR_AUTHIN_V(x) ((x) << KEYCTX_TX_WR_AUTHIN_S) +#define KEYCTX_TX_WR_AUTHIN_G(x) \ + (((x) >> KEYCTX_TX_WR_AUTHIN_S) & KEYCTX_TX_WR_AUTHIN_M) + +struct chcr_wr { + struct fw_crypto_lookaside_wr wreq; + struct ulp_txpkt ulptx; + struct ulptx_idata sc_imm; + struct cpl_tx_sec_pdu sec_cpl; + struct _key_ctx key_ctx; +}; + +struct chcr_dev { + spinlock_t lock_chcr_dev; + struct uld_ctx *u_ctx; + unsigned char tx_channel_id; + unsigned char rx_channel_id; +}; + +struct uld_ctx { + struct list_head entry; + struct cxgb4_lld_info lldi; + struct chcr_dev *dev; +}; + +struct sge_opaque_hdr { + void *dev; + dma_addr_t addr[MAX_SKB_FRAGS + 1]; +}; + +struct chcr_ipsec_req { + struct ulp_txpkt ulptx; + struct ulptx_idata sc_imm; + struct cpl_tx_sec_pdu sec_cpl; + struct _key_ctx key_ctx; +}; + +struct chcr_ipsec_wr { + struct fw_ulptx_wr wreq; + struct chcr_ipsec_req req; +}; + +struct ipsec_sa_entry { + int hmac_ctrl; + unsigned int enckey_len; + unsigned int kctx_len; + unsigned int authsize; + __be32 key_ctx_hdr; + char salt[MAX_SALT]; + char key[2 * AES_MAX_KEY_SIZE]; +}; + +/* + * sgl_len - calculates the size of an SGL of the given capacity + * @n: the number of SGL entries + * Calculates the number of flits needed for a scatter/gather list that + * can hold the given number of entries. + */ +static inline unsigned int sgl_len(unsigned int n) +{ + n--; + return (3 * n) / 2 + (n & 1) + 2; +} + +struct uld_ctx *assign_chcr_device(void); +int chcr_send_wr(struct sk_buff *skb); +int start_crypto(void); +int stop_crypto(void); +int chcr_uld_rx_handler(void *handle, const __be64 *rsp, + const struct pkt_gl *pgl); +int chcr_uld_tx_handler(struct sk_buff *skb, struct net_device *dev); +int chcr_handle_resp(struct crypto_async_request *req, unsigned char *input, + int err); +int chcr_ipsec_xmit(struct sk_buff *skb, struct net_device *dev); +void chcr_add_xfrmops(const struct cxgb4_lld_info *lld); +#endif /* __CHCR_CORE_H__ */ diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h new file mode 100644 index 000000000..0d2c70c34 --- /dev/null +++ b/drivers/crypto/chelsio/chcr_crypto.h @@ -0,0 +1,344 @@ +/* + * This file is part of the Chelsio T6 Crypto driver for Linux. + * + * Copyright (c) 2003-2016 Chelsio Communications, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __CHCR_CRYPTO_H__ +#define __CHCR_CRYPTO_H__ + +#define GHASH_BLOCK_SIZE 16 +#define GHASH_DIGEST_SIZE 16 + +#define CCM_B0_SIZE 16 +#define CCM_AAD_FIELD_SIZE 2 +#define T6_MAX_AAD_SIZE 511 + + +/* Define following if h/w is not dropping the AAD and IV data before + * giving the processed data + */ + +#define CHCR_CRA_PRIORITY 500 +#define CHCR_AEAD_PRIORITY 6000 +#define CHCR_AES_MAX_KEY_LEN (2 * (AES_MAX_KEY_SIZE)) /* consider xts */ +#define CHCR_MAX_CRYPTO_IV_LEN 16 /* AES IV len */ + +#define CHCR_MAX_AUTHENC_AES_KEY_LEN 32 /* max aes key length*/ +#define CHCR_MAX_AUTHENC_SHA_KEY_LEN 128 /* max sha key length*/ + +#define CHCR_GIVENCRYPT_OP 2 +/* CPL/SCMD parameters */ + +#define CHCR_ENCRYPT_OP 0 +#define CHCR_DECRYPT_OP 1 + +#define CHCR_SCMD_SEQ_NO_CTRL_32BIT 1 +#define CHCR_SCMD_SEQ_NO_CTRL_48BIT 2 +#define CHCR_SCMD_SEQ_NO_CTRL_64BIT 3 + +#define CHCR_SCMD_PROTO_VERSION_GENERIC 4 + +#define CHCR_SCMD_AUTH_CTRL_AUTH_CIPHER 0 +#define CHCR_SCMD_AUTH_CTRL_CIPHER_AUTH 1 + +#define CHCR_SCMD_CIPHER_MODE_NOP 0 +#define CHCR_SCMD_CIPHER_MODE_AES_CBC 1 +#define CHCR_SCMD_CIPHER_MODE_AES_GCM 2 +#define CHCR_SCMD_CIPHER_MODE_AES_CTR 3 +#define CHCR_SCMD_CIPHER_MODE_GENERIC_AES 4 +#define CHCR_SCMD_CIPHER_MODE_AES_XTS 6 +#define CHCR_SCMD_CIPHER_MODE_AES_CCM 7 + +#define CHCR_SCMD_AUTH_MODE_NOP 0 +#define CHCR_SCMD_AUTH_MODE_SHA1 1 +#define CHCR_SCMD_AUTH_MODE_SHA224 2 +#define CHCR_SCMD_AUTH_MODE_SHA256 3 +#define CHCR_SCMD_AUTH_MODE_GHASH 4 +#define CHCR_SCMD_AUTH_MODE_SHA512_224 5 +#define CHCR_SCMD_AUTH_MODE_SHA512_256 6 +#define CHCR_SCMD_AUTH_MODE_SHA512_384 7 +#define CHCR_SCMD_AUTH_MODE_SHA512_512 8 +#define CHCR_SCMD_AUTH_MODE_CBCMAC 9 +#define CHCR_SCMD_AUTH_MODE_CMAC 10 + +#define CHCR_SCMD_HMAC_CTRL_NOP 0 +#define CHCR_SCMD_HMAC_CTRL_NO_TRUNC 1 +#define CHCR_SCMD_HMAC_CTRL_TRUNC_RFC4366 2 +#define CHCR_SCMD_HMAC_CTRL_IPSEC_96BIT 3 +#define CHCR_SCMD_HMAC_CTRL_PL1 4 +#define CHCR_SCMD_HMAC_CTRL_PL2 5 +#define CHCR_SCMD_HMAC_CTRL_PL3 6 +#define CHCR_SCMD_HMAC_CTRL_DIV2 7 +#define VERIFY_HW 0 +#define VERIFY_SW 1 + +#define CHCR_SCMD_IVGEN_CTRL_HW 0 +#define CHCR_SCMD_IVGEN_CTRL_SW 1 +/* This are not really mac key size. They are intermediate values + * of sha engine and its size + */ +#define CHCR_KEYCTX_MAC_KEY_SIZE_128 0 +#define CHCR_KEYCTX_MAC_KEY_SIZE_160 1 +#define CHCR_KEYCTX_MAC_KEY_SIZE_192 2 +#define CHCR_KEYCTX_MAC_KEY_SIZE_256 3 +#define CHCR_KEYCTX_MAC_KEY_SIZE_512 4 +#define CHCR_KEYCTX_CIPHER_KEY_SIZE_128 0 +#define CHCR_KEYCTX_CIPHER_KEY_SIZE_192 1 +#define CHCR_KEYCTX_CIPHER_KEY_SIZE_256 2 +#define CHCR_KEYCTX_NO_KEY 15 + +#define CHCR_CPL_FW4_PLD_IV_OFFSET (5 * 64) /* bytes. flt #5 and #6 */ +#define CHCR_CPL_FW4_PLD_HASH_RESULT_OFFSET (7 * 64) /* bytes. flt #7 */ +#define CHCR_CPL_FW4_PLD_DATA_SIZE (4 * 64) /* bytes. flt #4 to #7 */ + +#define KEY_CONTEXT_HDR_SALT_AND_PAD 16 +#define flits_to_bytes(x) (x * 8) + +#define IV_NOP 0 +#define IV_IMMEDIATE 1 +#define IV_DSGL 2 + +#define AEAD_H_SIZE 16 + +#define CRYPTO_ALG_SUB_TYPE_MASK 0x0f000000 +#define CRYPTO_ALG_SUB_TYPE_HASH_HMAC 0x01000000 +#define CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106 0x02000000 +#define CRYPTO_ALG_SUB_TYPE_AEAD_GCM 0x03000000 +#define CRYPTO_ALG_SUB_TYPE_CBC_SHA 0x04000000 +#define CRYPTO_ALG_SUB_TYPE_AEAD_CCM 0x05000000 +#define CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309 0x06000000 +#define CRYPTO_ALG_SUB_TYPE_CBC_NULL 0x07000000 +#define CRYPTO_ALG_SUB_TYPE_CTR 0x08000000 +#define CRYPTO_ALG_SUB_TYPE_CTR_RFC3686 0x09000000 +#define CRYPTO_ALG_SUB_TYPE_XTS 0x0a000000 +#define CRYPTO_ALG_SUB_TYPE_CBC 0x0b000000 +#define CRYPTO_ALG_SUB_TYPE_CTR_SHA 0x0c000000 +#define CRYPTO_ALG_SUB_TYPE_CTR_NULL 0x0d000000 +#define CRYPTO_ALG_TYPE_HMAC (CRYPTO_ALG_TYPE_AHASH |\ + CRYPTO_ALG_SUB_TYPE_HASH_HMAC) + +#define MAX_SCRATCH_PAD_SIZE 32 + +#define CHCR_HASH_MAX_BLOCK_SIZE_64 64 +#define CHCR_HASH_MAX_BLOCK_SIZE_128 128 +#define CHCR_SRC_SG_SIZE (0x10000 - sizeof(int)) +#define CHCR_DST_SG_SIZE 2048 + +static inline struct chcr_context *a_ctx(struct crypto_aead *tfm) +{ + return crypto_aead_ctx(tfm); +} + +static inline struct chcr_context *c_ctx(struct crypto_ablkcipher *tfm) +{ + return crypto_ablkcipher_ctx(tfm); +} + +static inline struct chcr_context *h_ctx(struct crypto_ahash *tfm) +{ + return crypto_tfm_ctx(crypto_ahash_tfm(tfm)); +} + +struct ablk_ctx { + struct crypto_skcipher *sw_cipher; + struct crypto_cipher *aes_generic; + __be32 key_ctx_hdr; + unsigned int enckey_len; + unsigned char ciph_mode; + u8 key[CHCR_AES_MAX_KEY_LEN]; + u8 nonce[4]; + u8 rrkey[AES_MAX_KEY_SIZE]; +}; +struct chcr_aead_reqctx { + struct sk_buff *skb; + dma_addr_t iv_dma; + dma_addr_t b0_dma; + unsigned int b0_len; + unsigned int op; + short int aad_nents; + short int src_nents; + short int dst_nents; + u16 imm; + u16 verify; + u8 iv[CHCR_MAX_CRYPTO_IV_LEN + MAX_SCRATCH_PAD_SIZE]; + u8 *scratch_pad; +}; + +struct ulptx_walk { + struct ulptx_sgl *sgl; + unsigned int nents; + unsigned int pair_idx; + unsigned int last_sg_len; + struct scatterlist *last_sg; + struct ulptx_sge_pair *pair; + +}; + +struct dsgl_walk { + unsigned int nents; + unsigned int last_sg_len; + struct scatterlist *last_sg; + struct cpl_rx_phys_dsgl *dsgl; + struct phys_sge_pairs *to; +}; + +struct chcr_gcm_ctx { + u8 ghash_h[AEAD_H_SIZE]; +}; + +struct chcr_authenc_ctx { + u8 dec_rrkey[AES_MAX_KEY_SIZE]; + u8 h_iopad[2 * CHCR_HASH_MAX_DIGEST_SIZE]; + unsigned char auth_mode; +}; + +struct __aead_ctx { + struct chcr_gcm_ctx gcm[0]; + struct chcr_authenc_ctx authenc[0]; +}; + +struct chcr_aead_ctx { + __be32 key_ctx_hdr; + unsigned int enckey_len; + struct crypto_aead *sw_cipher; + u8 salt[MAX_SALT]; + u8 key[CHCR_AES_MAX_KEY_LEN]; + u8 nonce[4]; + u16 hmac_ctrl; + u16 mayverify; + struct __aead_ctx ctx[0]; +}; + +struct hmac_ctx { + struct crypto_shash *base_hash; + u8 ipad[CHCR_HASH_MAX_BLOCK_SIZE_128]; + u8 opad[CHCR_HASH_MAX_BLOCK_SIZE_128]; +}; + +struct __crypto_ctx { + struct hmac_ctx hmacctx[0]; + struct ablk_ctx ablkctx[0]; + struct chcr_aead_ctx aeadctx[0]; +}; + +struct chcr_context { + struct chcr_dev *dev; + unsigned char tx_qidx; + unsigned char rx_qidx; + unsigned char tx_chan_id; + unsigned char pci_chan_id; + struct __crypto_ctx crypto_ctx[0]; +}; + +struct chcr_hctx_per_wr { + struct scatterlist *srcsg; + struct sk_buff *skb; + dma_addr_t dma_addr; + u32 dma_len; + unsigned int src_ofst; + unsigned int processed; + u32 result; + u8 is_sg_map; + u8 imm; + /*Final callback called. Driver cannot rely on nbytes to decide + * final call + */ + u8 isfinal; +}; + +struct chcr_ahash_req_ctx { + struct chcr_hctx_per_wr hctx_wr; + u8 *reqbfr; + u8 *skbfr; + /* SKB which is being sent to the hardware for processing */ + u64 data_len; /* Data len till time */ + u8 reqlen; + u8 partial_hash[CHCR_HASH_MAX_DIGEST_SIZE]; + u8 bfr1[CHCR_HASH_MAX_BLOCK_SIZE_128]; + u8 bfr2[CHCR_HASH_MAX_BLOCK_SIZE_128]; +}; + +struct chcr_blkcipher_req_ctx { + struct sk_buff *skb; + struct scatterlist *dstsg; + unsigned int processed; + unsigned int last_req_len; + struct scatterlist *srcsg; + unsigned int src_ofst; + unsigned int dst_ofst; + unsigned int op; + u16 imm; + u8 iv[CHCR_MAX_CRYPTO_IV_LEN]; +}; + +struct chcr_alg_template { + u32 type; + u32 is_registered; + union { + struct crypto_alg crypto; + struct ahash_alg hash; + struct aead_alg aead; + } alg; +}; + +typedef struct sk_buff *(*create_wr_t)(struct aead_request *req, + unsigned short qid, + int size); + +void chcr_verify_tag(struct aead_request *req, u8 *input, int *err); +int chcr_aead_dma_map(struct device *dev, struct aead_request *req, + unsigned short op_type); +void chcr_aead_dma_unmap(struct device *dev, struct aead_request *req, + unsigned short op_type); +void chcr_add_aead_dst_ent(struct aead_request *req, + struct cpl_rx_phys_dsgl *phys_cpl, + unsigned int assoclen, + unsigned short qid); +void chcr_add_aead_src_ent(struct aead_request *req, struct ulptx_sgl *ulptx, + unsigned int assoclen); +void chcr_add_cipher_src_ent(struct ablkcipher_request *req, + void *ulptx, + struct cipher_wr_param *wrparam); +int chcr_cipher_dma_map(struct device *dev, struct ablkcipher_request *req); +void chcr_cipher_dma_unmap(struct device *dev, struct ablkcipher_request *req); +void chcr_add_cipher_dst_ent(struct ablkcipher_request *req, + struct cpl_rx_phys_dsgl *phys_cpl, + struct cipher_wr_param *wrparam, + unsigned short qid); +int sg_nents_len_skip(struct scatterlist *sg, u64 len, u64 skip); +void chcr_add_hash_src_ent(struct ahash_request *req, struct ulptx_sgl *ulptx, + struct hash_wr_param *param); +int chcr_hash_dma_map(struct device *dev, struct ahash_request *req); +void chcr_hash_dma_unmap(struct device *dev, struct ahash_request *req); +void chcr_aead_common_exit(struct aead_request *req); +#endif /* __CHCR_CRYPTO_H__ */ diff --git a/drivers/crypto/chelsio/chcr_ipsec.c b/drivers/crypto/chelsio/chcr_ipsec.c new file mode 100644 index 000000000..1ff873863 --- /dev/null +++ b/drivers/crypto/chelsio/chcr_ipsec.c @@ -0,0 +1,655 @@ +/* + * This file is part of the Chelsio T6 Crypto driver for Linux. + * + * Copyright (c) 2003-2017 Chelsio Communications, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + * Written and Maintained by: + * Atul Gupta (atul.gupta@chelsio.com) + */ + +#define pr_fmt(fmt) "chcr:" fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/crypto.h> +#include <linux/cryptohash.h> +#include <linux/skbuff.h> +#include <linux/rtnetlink.h> +#include <linux/highmem.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/netdevice.h> +#include <net/esp.h> +#include <net/xfrm.h> +#include <crypto/aes.h> +#include <crypto/algapi.h> +#include <crypto/hash.h> +#include <crypto/sha.h> +#include <crypto/authenc.h> +#include <crypto/internal/aead.h> +#include <crypto/null.h> +#include <crypto/internal/skcipher.h> +#include <crypto/aead.h> +#include <crypto/scatterwalk.h> +#include <crypto/internal/hash.h> + +#include "chcr_core.h" +#include "chcr_algo.h" +#include "chcr_crypto.h" + +/* + * Max Tx descriptor space we allow for an Ethernet packet to be inlined + * into a WR. + */ +#define MAX_IMM_TX_PKT_LEN 256 +#define GCM_ESP_IV_SIZE 8 + +static int chcr_xfrm_add_state(struct xfrm_state *x); +static void chcr_xfrm_del_state(struct xfrm_state *x); +static void chcr_xfrm_free_state(struct xfrm_state *x); +static bool chcr_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x); + +static const struct xfrmdev_ops chcr_xfrmdev_ops = { + .xdo_dev_state_add = chcr_xfrm_add_state, + .xdo_dev_state_delete = chcr_xfrm_del_state, + .xdo_dev_state_free = chcr_xfrm_free_state, + .xdo_dev_offload_ok = chcr_ipsec_offload_ok, +}; + +/* Add offload xfrms to Chelsio Interface */ +void chcr_add_xfrmops(const struct cxgb4_lld_info *lld) +{ + struct net_device *netdev = NULL; + int i; + + for (i = 0; i < lld->nports; i++) { + netdev = lld->ports[i]; + if (!netdev) + continue; + netdev->xfrmdev_ops = &chcr_xfrmdev_ops; + netdev->hw_enc_features |= NETIF_F_HW_ESP; + netdev->features |= NETIF_F_HW_ESP; + rtnl_lock(); + netdev_change_features(netdev); + rtnl_unlock(); + } +} + +static inline int chcr_ipsec_setauthsize(struct xfrm_state *x, + struct ipsec_sa_entry *sa_entry) +{ + int hmac_ctrl; + int authsize = x->aead->alg_icv_len / 8; + + sa_entry->authsize = authsize; + + switch (authsize) { + case ICV_8: + hmac_ctrl = CHCR_SCMD_HMAC_CTRL_DIV2; + break; + case ICV_12: + hmac_ctrl = CHCR_SCMD_HMAC_CTRL_IPSEC_96BIT; + break; + case ICV_16: + hmac_ctrl = CHCR_SCMD_HMAC_CTRL_NO_TRUNC; + break; + default: + return -EINVAL; + } + return hmac_ctrl; +} + +static inline int chcr_ipsec_setkey(struct xfrm_state *x, + struct ipsec_sa_entry *sa_entry) +{ + struct crypto_cipher *cipher; + int keylen = (x->aead->alg_key_len + 7) / 8; + unsigned char *key = x->aead->alg_key; + int ck_size, key_ctx_size = 0; + unsigned char ghash_h[AEAD_H_SIZE]; + int ret = 0; + + if (keylen > 3) { + keylen -= 4; /* nonce/salt is present in the last 4 bytes */ + memcpy(sa_entry->salt, key + keylen, 4); + } + + if (keylen == AES_KEYSIZE_128) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128; + } else if (keylen == AES_KEYSIZE_192) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_192; + } else if (keylen == AES_KEYSIZE_256) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256; + } else { + pr_err("GCM: Invalid key length %d\n", keylen); + ret = -EINVAL; + goto out; + } + + memcpy(sa_entry->key, key, keylen); + sa_entry->enckey_len = keylen; + key_ctx_size = sizeof(struct _key_ctx) + + ((DIV_ROUND_UP(keylen, 16)) << 4) + + AEAD_H_SIZE; + + sa_entry->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size, + CHCR_KEYCTX_MAC_KEY_SIZE_128, + 0, 0, + key_ctx_size >> 4); + + /* Calculate the H = CIPH(K, 0 repeated 16 times). + * It will go in key context + */ + cipher = crypto_alloc_cipher("aes-generic", 0, 0); + if (IS_ERR(cipher)) { + sa_entry->enckey_len = 0; + ret = -ENOMEM; + goto out; + } + + ret = crypto_cipher_setkey(cipher, key, keylen); + if (ret) { + sa_entry->enckey_len = 0; + goto out1; + } + memset(ghash_h, 0, AEAD_H_SIZE); + crypto_cipher_encrypt_one(cipher, ghash_h, ghash_h); + memcpy(sa_entry->key + (DIV_ROUND_UP(sa_entry->enckey_len, 16) * + 16), ghash_h, AEAD_H_SIZE); + sa_entry->kctx_len = ((DIV_ROUND_UP(sa_entry->enckey_len, 16)) << 4) + + AEAD_H_SIZE; +out1: + crypto_free_cipher(cipher); +out: + return ret; +} + +/* + * chcr_xfrm_add_state + * returns 0 on success, negative error if failed to send message to FPGA + * positive error if FPGA returned a bad response + */ +static int chcr_xfrm_add_state(struct xfrm_state *x) +{ + struct ipsec_sa_entry *sa_entry; + int res = 0; + + if (x->props.aalgo != SADB_AALG_NONE) { + pr_debug("CHCR: Cannot offload authenticated xfrm states\n"); + return -EINVAL; + } + if (x->props.calgo != SADB_X_CALG_NONE) { + pr_debug("CHCR: Cannot offload compressed xfrm states\n"); + return -EINVAL; + } + if (x->props.flags & XFRM_STATE_ESN) { + pr_debug("CHCR: Cannot offload ESN xfrm states\n"); + return -EINVAL; + } + if (x->props.family != AF_INET && + x->props.family != AF_INET6) { + pr_debug("CHCR: Only IPv4/6 xfrm state offloaded\n"); + return -EINVAL; + } + if (x->props.mode != XFRM_MODE_TRANSPORT && + x->props.mode != XFRM_MODE_TUNNEL) { + pr_debug("CHCR: Only transport and tunnel xfrm offload\n"); + return -EINVAL; + } + if (x->id.proto != IPPROTO_ESP) { + pr_debug("CHCR: Only ESP xfrm state offloaded\n"); + return -EINVAL; + } + if (x->encap) { + pr_debug("CHCR: Encapsulated xfrm state not offloaded\n"); + return -EINVAL; + } + if (!x->aead) { + pr_debug("CHCR: Cannot offload xfrm states without aead\n"); + return -EINVAL; + } + if (x->aead->alg_icv_len != 128 && + x->aead->alg_icv_len != 96) { + pr_debug("CHCR: Cannot offload xfrm states with AEAD ICV length other than 96b & 128b\n"); + return -EINVAL; + } + if ((x->aead->alg_key_len != 128 + 32) && + (x->aead->alg_key_len != 256 + 32)) { + pr_debug("CHCR: Cannot offload xfrm states with AEAD key length other than 128/256 bit\n"); + return -EINVAL; + } + if (x->tfcpad) { + pr_debug("CHCR: Cannot offload xfrm states with tfc padding\n"); + return -EINVAL; + } + if (!x->geniv) { + pr_debug("CHCR: Cannot offload xfrm states without geniv\n"); + return -EINVAL; + } + if (strcmp(x->geniv, "seqiv")) { + pr_debug("CHCR: Cannot offload xfrm states with geniv other than seqiv\n"); + return -EINVAL; + } + + sa_entry = kzalloc(sizeof(*sa_entry), GFP_KERNEL); + if (!sa_entry) { + res = -ENOMEM; + goto out; + } + + sa_entry->hmac_ctrl = chcr_ipsec_setauthsize(x, sa_entry); + chcr_ipsec_setkey(x, sa_entry); + x->xso.offload_handle = (unsigned long)sa_entry; + try_module_get(THIS_MODULE); +out: + return res; +} + +static void chcr_xfrm_del_state(struct xfrm_state *x) +{ + /* do nothing */ + if (!x->xso.offload_handle) + return; +} + +static void chcr_xfrm_free_state(struct xfrm_state *x) +{ + struct ipsec_sa_entry *sa_entry; + + if (!x->xso.offload_handle) + return; + + sa_entry = (struct ipsec_sa_entry *)x->xso.offload_handle; + kfree(sa_entry); + module_put(THIS_MODULE); +} + +static bool chcr_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x) +{ + /* Offload with IP options is not supported yet */ + if (ip_hdr(skb)->ihl > 5) + return false; + + return true; +} + +static inline int is_eth_imm(const struct sk_buff *skb, unsigned int kctx_len) +{ + int hdrlen; + + hdrlen = sizeof(struct fw_ulptx_wr) + + sizeof(struct chcr_ipsec_req) + kctx_len; + + hdrlen += sizeof(struct cpl_tx_pkt); + if (skb->len <= MAX_IMM_TX_PKT_LEN - hdrlen) + return hdrlen; + return 0; +} + +static inline unsigned int calc_tx_sec_flits(const struct sk_buff *skb, + unsigned int kctx_len) +{ + unsigned int flits; + int hdrlen = is_eth_imm(skb, kctx_len); + + /* If the skb is small enough, we can pump it out as a work request + * with only immediate data. In that case we just have to have the + * TX Packet header plus the skb data in the Work Request. + */ + + if (hdrlen) + return DIV_ROUND_UP(skb->len + hdrlen, sizeof(__be64)); + + flits = sgl_len(skb_shinfo(skb)->nr_frags + 1); + + /* Otherwise, we're going to have to construct a Scatter gather list + * of the skb body and fragments. We also include the flits necessary + * for the TX Packet Work Request and CPL. We always have a firmware + * Write Header (incorporated as part of the cpl_tx_pkt_lso and + * cpl_tx_pkt structures), followed by either a TX Packet Write CPL + * message or, if we're doing a Large Send Offload, an LSO CPL message + * with an embedded TX Packet Write CPL message. + */ + flits += (sizeof(struct fw_ulptx_wr) + + sizeof(struct chcr_ipsec_req) + + kctx_len + + sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64); + return flits; +} + +inline void *copy_cpltx_pktxt(struct sk_buff *skb, + struct net_device *dev, + void *pos) +{ + struct cpl_tx_pkt_core *cpl; + struct sge_eth_txq *q; + struct adapter *adap; + struct port_info *pi; + u32 ctrl0, qidx; + u64 cntrl = 0; + int left; + + pi = netdev_priv(dev); + adap = pi->adapter; + qidx = skb->queue_mapping; + q = &adap->sge.ethtxq[qidx + pi->first_qset]; + + left = (void *)q->q.stat - pos; + if (!left) + pos = q->q.desc; + + cpl = (struct cpl_tx_pkt_core *)pos; + + cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F; + ctrl0 = TXPKT_OPCODE_V(CPL_TX_PKT_XT) | TXPKT_INTF_V(pi->tx_chan) | + TXPKT_PF_V(adap->pf); + if (skb_vlan_tag_present(skb)) { + q->vlan_ins++; + cntrl |= TXPKT_VLAN_VLD_F | TXPKT_VLAN_V(skb_vlan_tag_get(skb)); + } + + cpl->ctrl0 = htonl(ctrl0); + cpl->pack = htons(0); + cpl->len = htons(skb->len); + cpl->ctrl1 = cpu_to_be64(cntrl); + + pos += sizeof(struct cpl_tx_pkt_core); + return pos; +} + +inline void *copy_key_cpltx_pktxt(struct sk_buff *skb, + struct net_device *dev, + void *pos, + struct ipsec_sa_entry *sa_entry) +{ + struct _key_ctx *key_ctx; + int left, eoq, key_len; + struct sge_eth_txq *q; + struct adapter *adap; + struct port_info *pi; + unsigned int qidx; + + pi = netdev_priv(dev); + adap = pi->adapter; + qidx = skb->queue_mapping; + q = &adap->sge.ethtxq[qidx + pi->first_qset]; + key_len = sa_entry->kctx_len; + + /* end of queue, reset pos to start of queue */ + eoq = (void *)q->q.stat - pos; + left = eoq; + if (!eoq) { + pos = q->q.desc; + left = 64 * q->q.size; + } + + /* Copy the Key context header */ + key_ctx = (struct _key_ctx *)pos; + key_ctx->ctx_hdr = sa_entry->key_ctx_hdr; + memcpy(key_ctx->salt, sa_entry->salt, MAX_SALT); + pos += sizeof(struct _key_ctx); + left -= sizeof(struct _key_ctx); + + if (likely(key_len <= left)) { + memcpy(key_ctx->key, sa_entry->key, key_len); + pos += key_len; + } else { + memcpy(pos, sa_entry->key, left); + memcpy(q->q.desc, sa_entry->key + left, + key_len - left); + pos = (u8 *)q->q.desc + (key_len - left); + } + /* Copy CPL TX PKT XT */ + pos = copy_cpltx_pktxt(skb, dev, pos); + + return pos; +} + +inline void *chcr_crypto_wreq(struct sk_buff *skb, + struct net_device *dev, + void *pos, + int credits, + struct ipsec_sa_entry *sa_entry) +{ + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + unsigned int immdatalen = 0; + unsigned int ivsize = GCM_ESP_IV_SIZE; + struct chcr_ipsec_wr *wr; + unsigned int flits; + u32 wr_mid; + int qidx = skb_get_queue_mapping(skb); + struct sge_eth_txq *q = &adap->sge.ethtxq[qidx + pi->first_qset]; + unsigned int kctx_len = sa_entry->kctx_len; + int qid = q->q.cntxt_id; + + atomic_inc(&adap->chcr_stats.ipsec_cnt); + + flits = calc_tx_sec_flits(skb, kctx_len); + + if (is_eth_imm(skb, kctx_len)) + immdatalen = skb->len; + + /* WR Header */ + wr = (struct chcr_ipsec_wr *)pos; + wr->wreq.op_to_compl = htonl(FW_WR_OP_V(FW_ULPTX_WR)); + wr_mid = FW_CRYPTO_LOOKASIDE_WR_LEN16_V(DIV_ROUND_UP(flits, 2)); + + if (unlikely(credits < ETHTXQ_STOP_THRES)) { + netif_tx_stop_queue(q->txq); + q->q.stops++; + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + } + wr_mid |= FW_ULPTX_WR_DATA_F; + wr->wreq.flowid_len16 = htonl(wr_mid); + + /* ULPTX */ + wr->req.ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(pi->port_id, qid); + wr->req.ulptx.len = htonl(DIV_ROUND_UP(flits, 2) - 1); + + /* Sub-command */ + wr->req.sc_imm.cmd_more = FILL_CMD_MORE(!immdatalen); + wr->req.sc_imm.len = cpu_to_be32(sizeof(struct cpl_tx_sec_pdu) + + sizeof(wr->req.key_ctx) + + kctx_len + + sizeof(struct cpl_tx_pkt_core) + + immdatalen); + + /* CPL_SEC_PDU */ + wr->req.sec_cpl.op_ivinsrtofst = htonl( + CPL_TX_SEC_PDU_OPCODE_V(CPL_TX_SEC_PDU) | + CPL_TX_SEC_PDU_CPLLEN_V(2) | + CPL_TX_SEC_PDU_PLACEHOLDER_V(1) | + CPL_TX_SEC_PDU_IVINSRTOFST_V( + (skb_transport_offset(skb) + + sizeof(struct ip_esp_hdr) + 1))); + + wr->req.sec_cpl.pldlen = htonl(skb->len); + + wr->req.sec_cpl.aadstart_cipherstop_hi = FILL_SEC_CPL_CIPHERSTOP_HI( + (skb_transport_offset(skb) + 1), + (skb_transport_offset(skb) + + sizeof(struct ip_esp_hdr)), + (skb_transport_offset(skb) + + sizeof(struct ip_esp_hdr) + + GCM_ESP_IV_SIZE + 1), 0); + + wr->req.sec_cpl.cipherstop_lo_authinsert = + FILL_SEC_CPL_AUTHINSERT(0, skb_transport_offset(skb) + + sizeof(struct ip_esp_hdr) + + GCM_ESP_IV_SIZE + 1, + sa_entry->authsize, + sa_entry->authsize); + wr->req.sec_cpl.seqno_numivs = + FILL_SEC_CPL_SCMD0_SEQNO(CHCR_ENCRYPT_OP, 1, + CHCR_SCMD_CIPHER_MODE_AES_GCM, + CHCR_SCMD_AUTH_MODE_GHASH, + sa_entry->hmac_ctrl, + ivsize >> 1); + wr->req.sec_cpl.ivgen_hdrlen = FILL_SEC_CPL_IVGEN_HDRLEN(0, 0, 1, + 0, 0, 0); + + pos += sizeof(struct fw_ulptx_wr) + + sizeof(struct ulp_txpkt) + + sizeof(struct ulptx_idata) + + sizeof(struct cpl_tx_sec_pdu); + + pos = copy_key_cpltx_pktxt(skb, dev, pos, sa_entry); + + return pos; +} + +/** + * flits_to_desc - returns the num of Tx descriptors for the given flits + * @n: the number of flits + * + * Returns the number of Tx descriptors needed for the supplied number + * of flits. + */ +static inline unsigned int flits_to_desc(unsigned int n) +{ + WARN_ON(n > SGE_MAX_WR_LEN / 8); + return DIV_ROUND_UP(n, 8); +} + +static inline unsigned int txq_avail(const struct sge_txq *q) +{ + return q->size - 1 - q->in_use; +} + +static void eth_txq_stop(struct sge_eth_txq *q) +{ + netif_tx_stop_queue(q->txq); + q->q.stops++; +} + +static inline void txq_advance(struct sge_txq *q, unsigned int n) +{ + q->in_use += n; + q->pidx += n; + if (q->pidx >= q->size) + q->pidx -= q->size; +} + +/* + * chcr_ipsec_xmit called from ULD Tx handler + */ +int chcr_ipsec_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct xfrm_state *x = xfrm_input_state(skb); + struct ipsec_sa_entry *sa_entry; + u64 *pos, *end, *before, *sgl; + int qidx, left, credits; + unsigned int flits = 0, ndesc, kctx_len; + struct adapter *adap; + struct sge_eth_txq *q; + struct port_info *pi; + dma_addr_t addr[MAX_SKB_FRAGS + 1]; + bool immediate = false; + + if (!x->xso.offload_handle) + return NETDEV_TX_BUSY; + + sa_entry = (struct ipsec_sa_entry *)x->xso.offload_handle; + kctx_len = sa_entry->kctx_len; + + if (skb->sp->len != 1) { +out_free: dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + pi = netdev_priv(dev); + adap = pi->adapter; + qidx = skb->queue_mapping; + q = &adap->sge.ethtxq[qidx + pi->first_qset]; + + cxgb4_reclaim_completed_tx(adap, &q->q, true); + + flits = calc_tx_sec_flits(skb, sa_entry->kctx_len); + ndesc = flits_to_desc(flits); + credits = txq_avail(&q->q) - ndesc; + + if (unlikely(credits < 0)) { + eth_txq_stop(q); + dev_err(adap->pdev_dev, + "%s: Tx ring %u full while queue awake! cred:%d %d %d flits:%d\n", + dev->name, qidx, credits, ndesc, txq_avail(&q->q), + flits); + return NETDEV_TX_BUSY; + } + + if (is_eth_imm(skb, kctx_len)) + immediate = true; + + if (!immediate && + unlikely(cxgb4_map_skb(adap->pdev_dev, skb, addr) < 0)) { + q->mapping_err++; + goto out_free; + } + + pos = (u64 *)&q->q.desc[q->q.pidx]; + before = (u64 *)pos; + end = (u64 *)pos + flits; + /* Setup IPSec CPL */ + pos = (void *)chcr_crypto_wreq(skb, dev, (void *)pos, + credits, sa_entry); + if (before > (u64 *)pos) { + left = (u8 *)end - (u8 *)q->q.stat; + end = (void *)q->q.desc + left; + } + if (pos == (u64 *)q->q.stat) { + left = (u8 *)end - (u8 *)q->q.stat; + end = (void *)q->q.desc + left; + pos = (void *)q->q.desc; + } + + sgl = (void *)pos; + if (immediate) { + cxgb4_inline_tx_skb(skb, &q->q, sgl); + dev_consume_skb_any(skb); + } else { + int last_desc; + + cxgb4_write_sgl(skb, &q->q, (void *)sgl, end, + 0, addr); + skb_orphan(skb); + + last_desc = q->q.pidx + ndesc - 1; + if (last_desc >= q->q.size) + last_desc -= q->q.size; + q->q.sdesc[last_desc].skb = skb; + q->q.sdesc[last_desc].sgl = (struct ulptx_sgl *)sgl; + } + txq_advance(&q->q, ndesc); + + cxgb4_ring_tx_db(adap, &q->q, ndesc); + return NETDEV_TX_OK; +} diff --git a/drivers/crypto/chelsio/chtls/Makefile b/drivers/crypto/chelsio/chtls/Makefile new file mode 100644 index 000000000..df1379570 --- /dev/null +++ b/drivers/crypto/chelsio/chtls/Makefile @@ -0,0 +1,4 @@ +ccflags-y := -Idrivers/net/ethernet/chelsio/cxgb4 -Idrivers/crypto/chelsio/ + +obj-$(CONFIG_CRYPTO_DEV_CHELSIO_TLS) += chtls.o +chtls-objs := chtls_main.o chtls_cm.o chtls_io.o chtls_hw.o diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/crypto/chelsio/chtls/chtls.h new file mode 100644 index 000000000..fcb6747ed --- /dev/null +++ b/drivers/crypto/chelsio/chtls/chtls.h @@ -0,0 +1,489 @@ +/* + * Copyright (c) 2018 Chelsio Communications, Inc. + * + * 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. + */ + +#ifndef __CHTLS_H__ +#define __CHTLS_H__ + +#include <crypto/aes.h> +#include <crypto/algapi.h> +#include <crypto/hash.h> +#include <crypto/sha.h> +#include <crypto/authenc.h> +#include <crypto/ctr.h> +#include <crypto/gf128mul.h> +#include <crypto/internal/aead.h> +#include <crypto/null.h> +#include <crypto/internal/skcipher.h> +#include <crypto/aead.h> +#include <crypto/scatterwalk.h> +#include <crypto/internal/hash.h> +#include <linux/tls.h> +#include <net/tls.h> + +#include "t4fw_api.h" +#include "t4_msg.h" +#include "cxgb4.h" +#include "cxgb4_uld.h" +#include "l2t.h" +#include "chcr_algo.h" +#include "chcr_core.h" +#include "chcr_crypto.h" + +#define MAX_IVS_PAGE 256 +#define TLS_KEY_CONTEXT_SZ 64 +#define CIPHER_BLOCK_SIZE 16 +#define GCM_TAG_SIZE 16 +#define KEY_ON_MEM_SZ 16 +#define AEAD_EXPLICIT_DATA_SIZE 8 +#define TLS_HEADER_LENGTH 5 +#define SCMD_CIPH_MODE_AES_GCM 2 +/* Any MFS size should work and come from openssl */ +#define TLS_MFS 16384 + +#define RSS_HDR sizeof(struct rss_header) +#define TLS_WR_CPL_LEN \ + (sizeof(struct fw_tlstx_data_wr) + sizeof(struct cpl_tx_tls_sfo)) + +enum { + CHTLS_KEY_CONTEXT_DSGL, + CHTLS_KEY_CONTEXT_IMM, + CHTLS_KEY_CONTEXT_DDR, +}; + +enum { + CHTLS_LISTEN_START, + CHTLS_LISTEN_STOP, +}; + +/* Flags for return value of CPL message handlers */ +enum { + CPL_RET_BUF_DONE = 1, /* buffer processing done */ + CPL_RET_BAD_MSG = 2, /* bad CPL message */ + CPL_RET_UNKNOWN_TID = 4 /* unexpected unknown TID */ +}; + +#define LISTEN_INFO_HASH_SIZE 32 +#define RSPQ_HASH_BITS 5 +struct listen_info { + struct listen_info *next; /* Link to next entry */ + struct sock *sk; /* The listening socket */ + unsigned int stid; /* The server TID */ +}; + +enum { + T4_LISTEN_START_PENDING, + T4_LISTEN_STARTED +}; + +enum csk_flags { + CSK_CALLBACKS_CHKD, /* socket callbacks have been sanitized */ + CSK_ABORT_REQ_RCVD, /* received one ABORT_REQ_RSS message */ + CSK_TX_MORE_DATA, /* sending ULP data; don't set SHOVE bit */ + CSK_TX_WAIT_IDLE, /* suspend Tx until in-flight data is ACKed */ + CSK_ABORT_SHUTDOWN, /* shouldn't send more abort requests */ + CSK_ABORT_RPL_PENDING, /* expecting an abort reply */ + CSK_CLOSE_CON_REQUESTED,/* we've sent a close_conn_req */ + CSK_TX_DATA_SENT, /* sent a TX_DATA WR on this connection */ + CSK_TX_FAILOVER, /* Tx traffic failing over */ + CSK_UPDATE_RCV_WND, /* Need to update rcv window */ + CSK_RST_ABORTED, /* outgoing RST was aborted */ + CSK_TLS_HANDSHK, /* TLS Handshake */ + CSK_CONN_INLINE, /* Connection on HW */ +}; + +enum chtls_cdev_state { + CHTLS_CDEV_STATE_UP = 1 +}; + +struct listen_ctx { + struct sock *lsk; + struct chtls_dev *cdev; + struct sk_buff_head synq; + u32 state; +}; + +struct key_map { + unsigned long *addr; + unsigned int start; + unsigned int available; + unsigned int size; + spinlock_t lock; /* lock for key id request from map */ +} __packed; + +struct tls_scmd { + u32 seqno_numivs; + u32 ivgen_hdrlen; +}; + +struct chtls_dev { + struct tls_device tlsdev; + struct list_head list; + struct cxgb4_lld_info *lldi; + struct pci_dev *pdev; + struct listen_info *listen_hash_tab[LISTEN_INFO_HASH_SIZE]; + spinlock_t listen_lock; /* lock for listen list */ + struct net_device **ports; + struct tid_info *tids; + unsigned int pfvf; + const unsigned short *mtus; + + struct idr hwtid_idr; + struct idr stid_idr; + + spinlock_t idr_lock ____cacheline_aligned_in_smp; + + struct net_device *egr_dev[NCHAN * 2]; + struct sk_buff *rspq_skb_cache[1 << RSPQ_HASH_BITS]; + struct sk_buff *askb; + + struct sk_buff_head deferq; + struct work_struct deferq_task; + + struct list_head list_node; + struct list_head rcu_node; + struct list_head na_node; + unsigned int send_page_order; + int max_host_sndbuf; + struct key_map kmap; + unsigned int cdev_state; +}; + +struct chtls_listen { + struct chtls_dev *cdev; + struct sock *sk; +}; + +struct chtls_hws { + struct sk_buff_head sk_recv_queue; + u8 txqid; + u8 ofld; + u16 type; + u16 rstate; + u16 keyrpl; + u16 pldlen; + u16 rcvpld; + u16 compute; + u16 expansion; + u16 keylen; + u16 pdus; + u16 adjustlen; + u16 ivsize; + u16 txleft; + u32 mfs; + s32 txkey; + s32 rxkey; + u32 fcplenmax; + u32 copied_seq; + u64 tx_seq_no; + struct tls_scmd scmd; + struct tls12_crypto_info_aes_gcm_128 crypto_info; +}; + +struct chtls_sock { + struct sock *sk; + struct chtls_dev *cdev; + struct l2t_entry *l2t_entry; /* pointer to the L2T entry */ + struct net_device *egress_dev; /* TX_CHAN for act open retry */ + + struct sk_buff_head txq; + struct sk_buff *wr_skb_head; + struct sk_buff *wr_skb_tail; + struct sk_buff *ctrl_skb_cache; + struct sk_buff *txdata_skb_cache; /* abort path messages */ + struct kref kref; + unsigned long flags; + u32 opt2; + u32 wr_credits; + u32 wr_unacked; + u32 wr_max_credits; + u32 wr_nondata; + u32 hwtid; /* TCP Control Block ID */ + u32 txq_idx; + u32 rss_qid; + u32 tid; + u32 idr; + u32 mss; + u32 ulp_mode; + u32 tx_chan; + u32 rx_chan; + u32 sndbuf; + u32 txplen_max; + u32 mtu_idx; /* MTU table index */ + u32 smac_idx; + u8 port_id; + u8 tos; + u16 resv2; + u32 delack_mode; + u32 delack_seq; + + void *passive_reap_next; /* placeholder for passive */ + struct chtls_hws tlshws; + struct synq { + struct sk_buff *next; + struct sk_buff *prev; + } synq; + struct listen_ctx *listen_ctx; +}; + +struct tls_hdr { + u8 type; + u16 version; + u16 length; +} __packed; + +struct tlsrx_cmp_hdr { + u8 type; + u16 version; + u16 length; + + u64 tls_seq; + u16 reserved1; + u8 res_to_mac_error; +} __packed; + +/* res_to_mac_error fields */ +#define TLSRX_HDR_PKT_INT_ERROR_S 4 +#define TLSRX_HDR_PKT_INT_ERROR_M 0x1 +#define TLSRX_HDR_PKT_INT_ERROR_V(x) \ + ((x) << TLSRX_HDR_PKT_INT_ERROR_S) +#define TLSRX_HDR_PKT_INT_ERROR_G(x) \ + (((x) >> TLSRX_HDR_PKT_INT_ERROR_S) & TLSRX_HDR_PKT_INT_ERROR_M) +#define TLSRX_HDR_PKT_INT_ERROR_F TLSRX_HDR_PKT_INT_ERROR_V(1U) + +#define TLSRX_HDR_PKT_SPP_ERROR_S 3 +#define TLSRX_HDR_PKT_SPP_ERROR_M 0x1 +#define TLSRX_HDR_PKT_SPP_ERROR_V(x) ((x) << TLSRX_HDR_PKT_SPP_ERROR) +#define TLSRX_HDR_PKT_SPP_ERROR_G(x) \ + (((x) >> TLSRX_HDR_PKT_SPP_ERROR_S) & TLSRX_HDR_PKT_SPP_ERROR_M) +#define TLSRX_HDR_PKT_SPP_ERROR_F TLSRX_HDR_PKT_SPP_ERROR_V(1U) + +#define TLSRX_HDR_PKT_CCDX_ERROR_S 2 +#define TLSRX_HDR_PKT_CCDX_ERROR_M 0x1 +#define TLSRX_HDR_PKT_CCDX_ERROR_V(x) ((x) << TLSRX_HDR_PKT_CCDX_ERROR_S) +#define TLSRX_HDR_PKT_CCDX_ERROR_G(x) \ + (((x) >> TLSRX_HDR_PKT_CCDX_ERROR_S) & TLSRX_HDR_PKT_CCDX_ERROR_M) +#define TLSRX_HDR_PKT_CCDX_ERROR_F TLSRX_HDR_PKT_CCDX_ERROR_V(1U) + +#define TLSRX_HDR_PKT_PAD_ERROR_S 1 +#define TLSRX_HDR_PKT_PAD_ERROR_M 0x1 +#define TLSRX_HDR_PKT_PAD_ERROR_V(x) ((x) << TLSRX_HDR_PKT_PAD_ERROR_S) +#define TLSRX_HDR_PKT_PAD_ERROR_G(x) \ + (((x) >> TLSRX_HDR_PKT_PAD_ERROR_S) & TLSRX_HDR_PKT_PAD_ERROR_M) +#define TLSRX_HDR_PKT_PAD_ERROR_F TLSRX_HDR_PKT_PAD_ERROR_V(1U) + +#define TLSRX_HDR_PKT_MAC_ERROR_S 0 +#define TLSRX_HDR_PKT_MAC_ERROR_M 0x1 +#define TLSRX_HDR_PKT_MAC_ERROR_V(x) ((x) << TLSRX_HDR_PKT_MAC_ERROR) +#define TLSRX_HDR_PKT_MAC_ERROR_G(x) \ + (((x) >> S_TLSRX_HDR_PKT_MAC_ERROR_S) & TLSRX_HDR_PKT_MAC_ERROR_M) +#define TLSRX_HDR_PKT_MAC_ERROR_F TLSRX_HDR_PKT_MAC_ERROR_V(1U) + +#define TLSRX_HDR_PKT_ERROR_M 0x1F +#define CONTENT_TYPE_ERROR 0x7F + +struct ulp_mem_rw { + __be32 cmd; + __be32 len16; /* command length */ + __be32 dlen; /* data length in 32-byte units */ + __be32 lock_addr; +}; + +struct tls_key_wr { + __be32 op_to_compl; + __be32 flowid_len16; + __be32 ftid; + u8 reneg_to_write_rx; + u8 protocol; + __be16 mfs; +}; + +struct tls_key_req { + struct tls_key_wr wr; + struct ulp_mem_rw req; + struct ulptx_idata sc_imm; +}; + +/* + * This lives in skb->cb and is used to chain WRs in a linked list. + */ +struct wr_skb_cb { + struct l2t_skb_cb l2t; /* reserve space for l2t CB */ + struct sk_buff *next_wr; /* next write request */ +}; + +/* Per-skb backlog handler. Run when a socket's backlog is processed. */ +struct blog_skb_cb { + void (*backlog_rcv)(struct sock *sk, struct sk_buff *skb); + struct chtls_dev *cdev; +}; + +/* + * Similar to tcp_skb_cb but with ULP elements added to support TLS, + * etc. + */ +struct ulp_skb_cb { + struct wr_skb_cb wr; /* reserve space for write request */ + u16 flags; /* TCP-like flags */ + u8 psh; + u8 ulp_mode; /* ULP mode/submode of sk_buff */ + u32 seq; /* TCP sequence number */ + union { /* ULP-specific fields */ + struct { + u8 type; + u8 ofld; + u8 iv; + } tls; + } ulp; +}; + +#define ULP_SKB_CB(skb) ((struct ulp_skb_cb *)&((skb)->cb[0])) +#define BLOG_SKB_CB(skb) ((struct blog_skb_cb *)(skb)->cb) + +/* + * Flags for ulp_skb_cb.flags. + */ +enum { + ULPCB_FLAG_NEED_HDR = 1 << 0, /* packet needs a TX_DATA_WR header */ + ULPCB_FLAG_NO_APPEND = 1 << 1, /* don't grow this skb */ + ULPCB_FLAG_BARRIER = 1 << 2, /* set TX_WAIT_IDLE after sending */ + ULPCB_FLAG_HOLD = 1 << 3, /* skb not ready for Tx yet */ + ULPCB_FLAG_COMPL = 1 << 4, /* request WR completion */ + ULPCB_FLAG_URG = 1 << 5, /* urgent data */ + ULPCB_FLAG_TLS_HDR = 1 << 6, /* payload with tls hdr */ + ULPCB_FLAG_NO_HDR = 1 << 7, /* not a ofld wr */ +}; + +/* The ULP mode/submode of an skbuff */ +#define skb_ulp_mode(skb) (ULP_SKB_CB(skb)->ulp_mode) +#define TCP_PAGE(sk) (sk->sk_frag.page) +#define TCP_OFF(sk) (sk->sk_frag.offset) + +static inline struct chtls_dev *to_chtls_dev(struct tls_device *tlsdev) +{ + return container_of(tlsdev, struct chtls_dev, tlsdev); +} + +static inline void csk_set_flag(struct chtls_sock *csk, + enum csk_flags flag) +{ + __set_bit(flag, &csk->flags); +} + +static inline void csk_reset_flag(struct chtls_sock *csk, + enum csk_flags flag) +{ + __clear_bit(flag, &csk->flags); +} + +static inline bool csk_conn_inline(const struct chtls_sock *csk) +{ + return test_bit(CSK_CONN_INLINE, &csk->flags); +} + +static inline int csk_flag(const struct sock *sk, enum csk_flags flag) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + + if (!csk_conn_inline(csk)) + return 0; + return test_bit(flag, &csk->flags); +} + +static inline int csk_flag_nochk(const struct chtls_sock *csk, + enum csk_flags flag) +{ + return test_bit(flag, &csk->flags); +} + +static inline void *cplhdr(struct sk_buff *skb) +{ + return skb->data; +} + +static inline int is_neg_adv(unsigned int status) +{ + return status == CPL_ERR_RTX_NEG_ADVICE || + status == CPL_ERR_KEEPALV_NEG_ADVICE || + status == CPL_ERR_PERSIST_NEG_ADVICE; +} + +static inline void process_cpl_msg(void (*fn)(struct sock *, struct sk_buff *), + struct sock *sk, + struct sk_buff *skb) +{ + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + + bh_lock_sock(sk); + if (unlikely(sock_owned_by_user(sk))) { + BLOG_SKB_CB(skb)->backlog_rcv = fn; + __sk_add_backlog(sk, skb); + } else { + fn(sk, skb); + } + bh_unlock_sock(sk); +} + +static inline void chtls_sock_free(struct kref *ref) +{ + struct chtls_sock *csk = container_of(ref, struct chtls_sock, + kref); + kfree(csk); +} + +static inline void __chtls_sock_put(const char *fn, struct chtls_sock *csk) +{ + kref_put(&csk->kref, chtls_sock_free); +} + +static inline void __chtls_sock_get(const char *fn, + struct chtls_sock *csk) +{ + kref_get(&csk->kref); +} + +static inline void send_or_defer(struct sock *sk, struct tcp_sock *tp, + struct sk_buff *skb, int through_l2t) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + + if (through_l2t) { + /* send through L2T */ + cxgb4_l2t_send(csk->egress_dev, skb, csk->l2t_entry); + } else { + /* send directly */ + cxgb4_ofld_send(csk->egress_dev, skb); + } +} + +typedef int (*chtls_handler_func)(struct chtls_dev *, struct sk_buff *); +extern chtls_handler_func chtls_handlers[NUM_CPL_CMDS]; +void chtls_install_cpl_ops(struct sock *sk); +int chtls_init_kmap(struct chtls_dev *cdev, struct cxgb4_lld_info *lldi); +void chtls_listen_stop(struct chtls_dev *cdev, struct sock *sk); +int chtls_listen_start(struct chtls_dev *cdev, struct sock *sk); +void chtls_close(struct sock *sk, long timeout); +int chtls_disconnect(struct sock *sk, int flags); +void chtls_shutdown(struct sock *sk, int how); +void chtls_destroy_sock(struct sock *sk); +int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +int chtls_recvmsg(struct sock *sk, struct msghdr *msg, + size_t len, int nonblock, int flags, int *addr_len); +int chtls_sendpage(struct sock *sk, struct page *page, + int offset, size_t size, int flags); +int send_tx_flowc_wr(struct sock *sk, int compl, + u32 snd_nxt, u32 rcv_nxt); +void chtls_tcp_push(struct sock *sk, int flags); +int chtls_push_frames(struct chtls_sock *csk, int comp); +int chtls_set_tcb_tflag(struct sock *sk, unsigned int bit_pos, int val); +int chtls_setkey(struct chtls_sock *csk, u32 keylen, u32 mode); +void skb_entail(struct sock *sk, struct sk_buff *skb, int flags); +unsigned int keyid_to_addr(int start_addr, int keyid); +void free_tls_keyid(struct sock *sk); +#endif diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c new file mode 100644 index 000000000..08ed3ff8b --- /dev/null +++ b/drivers/crypto/chelsio/chtls/chtls_cm.c @@ -0,0 +1,2123 @@ +/* + * Copyright (c) 2018 Chelsio Communications, Inc. + * + * 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. + * + * Written by: Atul Gupta (atul.gupta@chelsio.com) + */ + +#include <linux/module.h> +#include <linux/list.h> +#include <linux/workqueue.h> +#include <linux/skbuff.h> +#include <linux/timer.h> +#include <linux/notifier.h> +#include <linux/inetdevice.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/sched/signal.h> +#include <linux/kallsyms.h> +#include <linux/kprobes.h> +#include <linux/if_vlan.h> +#include <net/tcp.h> +#include <net/dst.h> + +#include "chtls.h" +#include "chtls_cm.h" + +/* + * State transitions and actions for close. Note that if we are in SYN_SENT + * we remain in that state as we cannot control a connection while it's in + * SYN_SENT; such connections are allowed to establish and are then aborted. + */ +static unsigned char new_state[16] = { + /* current state: new state: action: */ + /* (Invalid) */ TCP_CLOSE, + /* TCP_ESTABLISHED */ TCP_FIN_WAIT1 | TCP_ACTION_FIN, + /* TCP_SYN_SENT */ TCP_SYN_SENT, + /* TCP_SYN_RECV */ TCP_FIN_WAIT1 | TCP_ACTION_FIN, + /* TCP_FIN_WAIT1 */ TCP_FIN_WAIT1, + /* TCP_FIN_WAIT2 */ TCP_FIN_WAIT2, + /* TCP_TIME_WAIT */ TCP_CLOSE, + /* TCP_CLOSE */ TCP_CLOSE, + /* TCP_CLOSE_WAIT */ TCP_LAST_ACK | TCP_ACTION_FIN, + /* TCP_LAST_ACK */ TCP_LAST_ACK, + /* TCP_LISTEN */ TCP_CLOSE, + /* TCP_CLOSING */ TCP_CLOSING, +}; + +static struct chtls_sock *chtls_sock_create(struct chtls_dev *cdev) +{ + struct chtls_sock *csk = kzalloc(sizeof(*csk), GFP_ATOMIC); + + if (!csk) + return NULL; + + csk->txdata_skb_cache = alloc_skb(TXDATA_SKB_LEN, GFP_ATOMIC); + if (!csk->txdata_skb_cache) { + kfree(csk); + return NULL; + } + + kref_init(&csk->kref); + csk->cdev = cdev; + skb_queue_head_init(&csk->txq); + csk->wr_skb_head = NULL; + csk->wr_skb_tail = NULL; + csk->mss = MAX_MSS; + csk->tlshws.ofld = 1; + csk->tlshws.txkey = -1; + csk->tlshws.rxkey = -1; + csk->tlshws.mfs = TLS_MFS; + skb_queue_head_init(&csk->tlshws.sk_recv_queue); + return csk; +} + +static void chtls_sock_release(struct kref *ref) +{ + struct chtls_sock *csk = + container_of(ref, struct chtls_sock, kref); + + kfree(csk); +} + +static struct net_device *chtls_ipv4_netdev(struct chtls_dev *cdev, + struct sock *sk) +{ + struct net_device *ndev = cdev->ports[0]; + + if (likely(!inet_sk(sk)->inet_rcv_saddr)) + return ndev; + + ndev = ip_dev_find(&init_net, inet_sk(sk)->inet_rcv_saddr); + if (!ndev) + return NULL; + + if (is_vlan_dev(ndev)) + return vlan_dev_real_dev(ndev); + return ndev; +} + +static void assign_rxopt(struct sock *sk, unsigned int opt) +{ + const struct chtls_dev *cdev; + struct chtls_sock *csk; + struct tcp_sock *tp; + + csk = rcu_dereference_sk_user_data(sk); + tp = tcp_sk(sk); + + cdev = csk->cdev; + tp->tcp_header_len = sizeof(struct tcphdr); + tp->rx_opt.mss_clamp = cdev->mtus[TCPOPT_MSS_G(opt)] - 40; + tp->mss_cache = tp->rx_opt.mss_clamp; + tp->rx_opt.tstamp_ok = TCPOPT_TSTAMP_G(opt); + tp->rx_opt.snd_wscale = TCPOPT_SACK_G(opt); + tp->rx_opt.wscale_ok = TCPOPT_WSCALE_OK_G(opt); + SND_WSCALE(tp) = TCPOPT_SND_WSCALE_G(opt); + if (!tp->rx_opt.wscale_ok) + tp->rx_opt.rcv_wscale = 0; + if (tp->rx_opt.tstamp_ok) { + tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; + tp->rx_opt.mss_clamp -= TCPOLEN_TSTAMP_ALIGNED; + } else if (csk->opt2 & TSTAMPS_EN_F) { + csk->opt2 &= ~TSTAMPS_EN_F; + csk->mtu_idx = TCPOPT_MSS_G(opt); + } +} + +static void chtls_purge_receive_queue(struct sock *sk) +{ + struct sk_buff *skb; + + while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { + skb_dst_set(skb, (void *)NULL); + kfree_skb(skb); + } +} + +static void chtls_purge_write_queue(struct sock *sk) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct sk_buff *skb; + + while ((skb = __skb_dequeue(&csk->txq))) { + sk->sk_wmem_queued -= skb->truesize; + __kfree_skb(skb); + } +} + +static void chtls_purge_recv_queue(struct sock *sk) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct chtls_hws *tlsk = &csk->tlshws; + struct sk_buff *skb; + + while ((skb = __skb_dequeue(&tlsk->sk_recv_queue)) != NULL) { + skb_dst_set(skb, NULL); + kfree_skb(skb); + } +} + +static void abort_arp_failure(void *handle, struct sk_buff *skb) +{ + struct cpl_abort_req *req = cplhdr(skb); + struct chtls_dev *cdev; + + cdev = (struct chtls_dev *)handle; + req->cmd = CPL_ABORT_NO_RST; + cxgb4_ofld_send(cdev->lldi->ports[0], skb); +} + +static struct sk_buff *alloc_ctrl_skb(struct sk_buff *skb, int len) +{ + if (likely(skb && !skb_shared(skb) && !skb_cloned(skb))) { + __skb_trim(skb, 0); + refcount_inc(&skb->users); + } else { + skb = alloc_skb(len, GFP_KERNEL | __GFP_NOFAIL); + } + return skb; +} + +static void chtls_send_abort(struct sock *sk, int mode, struct sk_buff *skb) +{ + struct cpl_abort_req *req; + struct chtls_sock *csk; + struct tcp_sock *tp; + + csk = rcu_dereference_sk_user_data(sk); + tp = tcp_sk(sk); + + if (!skb) + skb = alloc_ctrl_skb(csk->txdata_skb_cache, sizeof(*req)); + + req = (struct cpl_abort_req *)skb_put(skb, sizeof(*req)); + INIT_TP_WR_CPL(req, CPL_ABORT_REQ, csk->tid); + skb_set_queue_mapping(skb, (csk->txq_idx << 1) | CPL_PRIORITY_DATA); + req->rsvd0 = htonl(tp->snd_nxt); + req->rsvd1 = !csk_flag_nochk(csk, CSK_TX_DATA_SENT); + req->cmd = mode; + t4_set_arp_err_handler(skb, csk->cdev, abort_arp_failure); + send_or_defer(sk, tp, skb, mode == CPL_ABORT_SEND_RST); +} + +static void chtls_send_reset(struct sock *sk, int mode, struct sk_buff *skb) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + + if (unlikely(csk_flag_nochk(csk, CSK_ABORT_SHUTDOWN) || + !csk->cdev)) { + if (sk->sk_state == TCP_SYN_RECV) + csk_set_flag(csk, CSK_RST_ABORTED); + goto out; + } + + if (!csk_flag_nochk(csk, CSK_TX_DATA_SENT)) { + struct tcp_sock *tp = tcp_sk(sk); + + if (send_tx_flowc_wr(sk, 0, tp->snd_nxt, tp->rcv_nxt) < 0) + WARN_ONCE(1, "send tx flowc error"); + csk_set_flag(csk, CSK_TX_DATA_SENT); + } + + csk_set_flag(csk, CSK_ABORT_RPL_PENDING); + chtls_purge_write_queue(sk); + + csk_set_flag(csk, CSK_ABORT_SHUTDOWN); + if (sk->sk_state != TCP_SYN_RECV) + chtls_send_abort(sk, mode, skb); + else + goto out; + + return; +out: + if (skb) + kfree_skb(skb); +} + +static void release_tcp_port(struct sock *sk) +{ + if (inet_csk(sk)->icsk_bind_hash) + inet_put_port(sk); +} + +static void tcp_uncork(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (tp->nonagle & TCP_NAGLE_CORK) { + tp->nonagle &= ~TCP_NAGLE_CORK; + chtls_tcp_push(sk, 0); + } +} + +static void chtls_close_conn(struct sock *sk) +{ + struct cpl_close_con_req *req; + struct chtls_sock *csk; + struct sk_buff *skb; + unsigned int tid; + unsigned int len; + + len = roundup(sizeof(struct cpl_close_con_req), 16); + csk = rcu_dereference_sk_user_data(sk); + tid = csk->tid; + + skb = alloc_skb(len, GFP_KERNEL | __GFP_NOFAIL); + req = (struct cpl_close_con_req *)__skb_put(skb, len); + memset(req, 0, len); + req->wr.wr_hi = htonl(FW_WR_OP_V(FW_TP_WR) | + FW_WR_IMMDLEN_V(sizeof(*req) - + sizeof(req->wr))); + req->wr.wr_mid = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*req), 16)) | + FW_WR_FLOWID_V(tid)); + + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_CLOSE_CON_REQ, tid)); + + tcp_uncork(sk); + skb_entail(sk, skb, ULPCB_FLAG_NO_HDR | ULPCB_FLAG_NO_APPEND); + if (sk->sk_state != TCP_SYN_SENT) + chtls_push_frames(csk, 1); +} + +/* + * Perform a state transition during close and return the actions indicated + * for the transition. Do not make this function inline, the main reason + * it exists at all is to avoid multiple inlining of tcp_set_state. + */ +static int make_close_transition(struct sock *sk) +{ + int next = (int)new_state[sk->sk_state]; + + tcp_set_state(sk, next & TCP_STATE_MASK); + return next & TCP_ACTION_FIN; +} + +void chtls_close(struct sock *sk, long timeout) +{ + int data_lost, prev_state; + struct chtls_sock *csk; + + csk = rcu_dereference_sk_user_data(sk); + + lock_sock(sk); + sk->sk_shutdown |= SHUTDOWN_MASK; + + data_lost = skb_queue_len(&sk->sk_receive_queue); + data_lost |= skb_queue_len(&csk->tlshws.sk_recv_queue); + chtls_purge_recv_queue(sk); + chtls_purge_receive_queue(sk); + + if (sk->sk_state == TCP_CLOSE) { + goto wait; + } else if (data_lost || sk->sk_state == TCP_SYN_SENT) { + chtls_send_reset(sk, CPL_ABORT_SEND_RST, NULL); + release_tcp_port(sk); + goto unlock; + } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { + sk->sk_prot->disconnect(sk, 0); + } else if (make_close_transition(sk)) { + chtls_close_conn(sk); + } +wait: + if (timeout) + sk_stream_wait_close(sk, timeout); + +unlock: + prev_state = sk->sk_state; + sock_hold(sk); + sock_orphan(sk); + + release_sock(sk); + + local_bh_disable(); + bh_lock_sock(sk); + + if (prev_state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) + goto out; + + if (sk->sk_state == TCP_FIN_WAIT2 && tcp_sk(sk)->linger2 < 0 && + !csk_flag(sk, CSK_ABORT_SHUTDOWN)) { + struct sk_buff *skb; + + skb = alloc_skb(sizeof(struct cpl_abort_req), GFP_ATOMIC); + if (skb) + chtls_send_reset(sk, CPL_ABORT_SEND_RST, skb); + } + + if (sk->sk_state == TCP_CLOSE) + inet_csk_destroy_sock(sk); + +out: + bh_unlock_sock(sk); + local_bh_enable(); + sock_put(sk); +} + +/* + * Wait until a socket enters on of the given states. + */ +static int wait_for_states(struct sock *sk, unsigned int states) +{ + DECLARE_WAITQUEUE(wait, current); + struct socket_wq _sk_wq; + long current_timeo; + int err = 0; + + current_timeo = 200; + + /* + * We want this to work even when there's no associated struct socket. + * In that case we provide a temporary wait_queue_head_t. + */ + if (!sk->sk_wq) { + init_waitqueue_head(&_sk_wq.wait); + _sk_wq.fasync_list = NULL; + init_rcu_head_on_stack(&_sk_wq.rcu); + RCU_INIT_POINTER(sk->sk_wq, &_sk_wq); + } + + add_wait_queue(sk_sleep(sk), &wait); + while (!sk_in_state(sk, states)) { + if (!current_timeo) { + err = -EBUSY; + break; + } + if (signal_pending(current)) { + err = sock_intr_errno(current_timeo); + break; + } + set_current_state(TASK_UNINTERRUPTIBLE); + release_sock(sk); + if (!sk_in_state(sk, states)) + current_timeo = schedule_timeout(current_timeo); + __set_current_state(TASK_RUNNING); + lock_sock(sk); + } + remove_wait_queue(sk_sleep(sk), &wait); + + if (rcu_dereference(sk->sk_wq) == &_sk_wq) + sk->sk_wq = NULL; + return err; +} + +int chtls_disconnect(struct sock *sk, int flags) +{ + struct chtls_sock *csk; + struct tcp_sock *tp; + int err; + + tp = tcp_sk(sk); + csk = rcu_dereference_sk_user_data(sk); + chtls_purge_recv_queue(sk); + chtls_purge_receive_queue(sk); + chtls_purge_write_queue(sk); + + if (sk->sk_state != TCP_CLOSE) { + sk->sk_err = ECONNRESET; + chtls_send_reset(sk, CPL_ABORT_SEND_RST, NULL); + err = wait_for_states(sk, TCPF_CLOSE); + if (err) + return err; + } + chtls_purge_recv_queue(sk); + chtls_purge_receive_queue(sk); + tp->max_window = 0xFFFF << (tp->rx_opt.snd_wscale); + return tcp_disconnect(sk, flags); +} + +#define SHUTDOWN_ELIGIBLE_STATE (TCPF_ESTABLISHED | \ + TCPF_SYN_RECV | TCPF_CLOSE_WAIT) +void chtls_shutdown(struct sock *sk, int how) +{ + if ((how & SEND_SHUTDOWN) && + sk_in_state(sk, SHUTDOWN_ELIGIBLE_STATE) && + make_close_transition(sk)) + chtls_close_conn(sk); +} + +void chtls_destroy_sock(struct sock *sk) +{ + struct chtls_sock *csk; + + csk = rcu_dereference_sk_user_data(sk); + chtls_purge_recv_queue(sk); + csk->ulp_mode = ULP_MODE_NONE; + chtls_purge_write_queue(sk); + free_tls_keyid(sk); + kref_put(&csk->kref, chtls_sock_release); + sk->sk_prot = &tcp_prot; + sk->sk_prot->destroy(sk); +} + +static void reset_listen_child(struct sock *child) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(child); + struct sk_buff *skb; + + skb = alloc_ctrl_skb(csk->txdata_skb_cache, + sizeof(struct cpl_abort_req)); + + chtls_send_reset(child, CPL_ABORT_SEND_RST, skb); + sock_orphan(child); + INC_ORPHAN_COUNT(child); + if (child->sk_state == TCP_CLOSE) + inet_csk_destroy_sock(child); +} + +static void chtls_disconnect_acceptq(struct sock *listen_sk) +{ + struct request_sock **pprev; + + pprev = ACCEPT_QUEUE(listen_sk); + while (*pprev) { + struct request_sock *req = *pprev; + + if (req->rsk_ops == &chtls_rsk_ops) { + struct sock *child = req->sk; + + *pprev = req->dl_next; + sk_acceptq_removed(listen_sk); + reqsk_put(req); + sock_hold(child); + local_bh_disable(); + bh_lock_sock(child); + release_tcp_port(child); + reset_listen_child(child); + bh_unlock_sock(child); + local_bh_enable(); + sock_put(child); + } else { + pprev = &req->dl_next; + } + } +} + +static int listen_hashfn(const struct sock *sk) +{ + return ((unsigned long)sk >> 10) & (LISTEN_INFO_HASH_SIZE - 1); +} + +static struct listen_info *listen_hash_add(struct chtls_dev *cdev, + struct sock *sk, + unsigned int stid) +{ + struct listen_info *p = kmalloc(sizeof(*p), GFP_KERNEL); + + if (p) { + int key = listen_hashfn(sk); + + p->sk = sk; + p->stid = stid; + spin_lock(&cdev->listen_lock); + p->next = cdev->listen_hash_tab[key]; + cdev->listen_hash_tab[key] = p; + spin_unlock(&cdev->listen_lock); + } + return p; +} + +static int listen_hash_find(struct chtls_dev *cdev, + struct sock *sk) +{ + struct listen_info *p; + int stid = -1; + int key; + + key = listen_hashfn(sk); + + spin_lock(&cdev->listen_lock); + for (p = cdev->listen_hash_tab[key]; p; p = p->next) + if (p->sk == sk) { + stid = p->stid; + break; + } + spin_unlock(&cdev->listen_lock); + return stid; +} + +static int listen_hash_del(struct chtls_dev *cdev, + struct sock *sk) +{ + struct listen_info *p, **prev; + int stid = -1; + int key; + + key = listen_hashfn(sk); + prev = &cdev->listen_hash_tab[key]; + + spin_lock(&cdev->listen_lock); + for (p = *prev; p; prev = &p->next, p = p->next) + if (p->sk == sk) { + stid = p->stid; + *prev = p->next; + kfree(p); + break; + } + spin_unlock(&cdev->listen_lock); + return stid; +} + +static void cleanup_syn_rcv_conn(struct sock *child, struct sock *parent) +{ + struct request_sock *req; + struct chtls_sock *csk; + + csk = rcu_dereference_sk_user_data(child); + req = csk->passive_reap_next; + + reqsk_queue_removed(&inet_csk(parent)->icsk_accept_queue, req); + __skb_unlink((struct sk_buff *)&csk->synq, &csk->listen_ctx->synq); + chtls_reqsk_free(req); + csk->passive_reap_next = NULL; +} + +static void chtls_reset_synq(struct listen_ctx *listen_ctx) +{ + struct sock *listen_sk = listen_ctx->lsk; + + while (!skb_queue_empty(&listen_ctx->synq)) { + struct chtls_sock *csk = + container_of((struct synq *)skb_peek + (&listen_ctx->synq), struct chtls_sock, synq); + struct sock *child = csk->sk; + + cleanup_syn_rcv_conn(child, listen_sk); + sock_hold(child); + local_bh_disable(); + bh_lock_sock(child); + release_tcp_port(child); + reset_listen_child(child); + bh_unlock_sock(child); + local_bh_enable(); + sock_put(child); + } +} + +int chtls_listen_start(struct chtls_dev *cdev, struct sock *sk) +{ + struct net_device *ndev; + struct listen_ctx *ctx; + struct adapter *adap; + struct port_info *pi; + int stid; + int ret; + + if (sk->sk_family != PF_INET) + return -EAGAIN; + + rcu_read_lock(); + ndev = chtls_ipv4_netdev(cdev, sk); + rcu_read_unlock(); + if (!ndev) + return -EBADF; + + pi = netdev_priv(ndev); + adap = pi->adapter; + if (!(adap->flags & FULL_INIT_DONE)) + return -EBADF; + + if (listen_hash_find(cdev, sk) >= 0) /* already have it */ + return -EADDRINUSE; + + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + __module_get(THIS_MODULE); + ctx->lsk = sk; + ctx->cdev = cdev; + ctx->state = T4_LISTEN_START_PENDING; + skb_queue_head_init(&ctx->synq); + + stid = cxgb4_alloc_stid(cdev->tids, sk->sk_family, ctx); + if (stid < 0) + goto free_ctx; + + sock_hold(sk); + if (!listen_hash_add(cdev, sk, stid)) + goto free_stid; + + ret = cxgb4_create_server(ndev, stid, + inet_sk(sk)->inet_rcv_saddr, + inet_sk(sk)->inet_sport, 0, + cdev->lldi->rxq_ids[0]); + if (ret > 0) + ret = net_xmit_errno(ret); + if (ret) + goto del_hash; + return 0; +del_hash: + listen_hash_del(cdev, sk); +free_stid: + cxgb4_free_stid(cdev->tids, stid, sk->sk_family); + sock_put(sk); +free_ctx: + kfree(ctx); + module_put(THIS_MODULE); + return -EBADF; +} + +void chtls_listen_stop(struct chtls_dev *cdev, struct sock *sk) +{ + struct listen_ctx *listen_ctx; + int stid; + + stid = listen_hash_del(cdev, sk); + if (stid < 0) + return; + + listen_ctx = (struct listen_ctx *)lookup_stid(cdev->tids, stid); + chtls_reset_synq(listen_ctx); + + cxgb4_remove_server(cdev->lldi->ports[0], stid, + cdev->lldi->rxq_ids[0], 0); + chtls_disconnect_acceptq(sk); +} + +static int chtls_pass_open_rpl(struct chtls_dev *cdev, struct sk_buff *skb) +{ + struct cpl_pass_open_rpl *rpl = cplhdr(skb) + RSS_HDR; + unsigned int stid = GET_TID(rpl); + struct listen_ctx *listen_ctx; + + listen_ctx = (struct listen_ctx *)lookup_stid(cdev->tids, stid); + if (!listen_ctx) + return CPL_RET_BUF_DONE; + + if (listen_ctx->state == T4_LISTEN_START_PENDING) { + listen_ctx->state = T4_LISTEN_STARTED; + return CPL_RET_BUF_DONE; + } + + if (rpl->status != CPL_ERR_NONE) { + pr_info("Unexpected PASS_OPEN_RPL status %u for STID %u\n", + rpl->status, stid); + } else { + cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family); + sock_put(listen_ctx->lsk); + kfree(listen_ctx); + module_put(THIS_MODULE); + } + return CPL_RET_BUF_DONE; +} + +static int chtls_close_listsrv_rpl(struct chtls_dev *cdev, struct sk_buff *skb) +{ + struct cpl_close_listsvr_rpl *rpl = cplhdr(skb) + RSS_HDR; + struct listen_ctx *listen_ctx; + unsigned int stid; + void *data; + + stid = GET_TID(rpl); + data = lookup_stid(cdev->tids, stid); + listen_ctx = (struct listen_ctx *)data; + + if (rpl->status != CPL_ERR_NONE) { + pr_info("Unexpected CLOSE_LISTSRV_RPL status %u for STID %u\n", + rpl->status, stid); + } else { + cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family); + sock_put(listen_ctx->lsk); + kfree(listen_ctx); + module_put(THIS_MODULE); + } + return CPL_RET_BUF_DONE; +} + +static void chtls_purge_wr_queue(struct sock *sk) +{ + struct sk_buff *skb; + + while ((skb = dequeue_wr(sk)) != NULL) + kfree_skb(skb); +} + +static void chtls_release_resources(struct sock *sk) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct chtls_dev *cdev = csk->cdev; + unsigned int tid = csk->tid; + struct tid_info *tids; + + if (!cdev) + return; + + tids = cdev->tids; + kfree_skb(csk->txdata_skb_cache); + csk->txdata_skb_cache = NULL; + + if (csk->wr_credits != csk->wr_max_credits) { + chtls_purge_wr_queue(sk); + chtls_reset_wr_list(csk); + } + + if (csk->l2t_entry) { + cxgb4_l2t_release(csk->l2t_entry); + csk->l2t_entry = NULL; + } + + cxgb4_remove_tid(tids, csk->port_id, tid, sk->sk_family); + sock_put(sk); +} + +static void chtls_conn_done(struct sock *sk) +{ + if (sock_flag(sk, SOCK_DEAD)) + chtls_purge_receive_queue(sk); + sk_wakeup_sleepers(sk, 0); + tcp_done(sk); +} + +static void do_abort_syn_rcv(struct sock *child, struct sock *parent) +{ + /* + * If the server is still open we clean up the child connection, + * otherwise the server already did the clean up as it was purging + * its SYN queue and the skb was just sitting in its backlog. + */ + if (likely(parent->sk_state == TCP_LISTEN)) { + cleanup_syn_rcv_conn(child, parent); + /* Without the below call to sock_orphan, + * we leak the socket resource with syn_flood test + * as inet_csk_destroy_sock will not be called + * in tcp_done since SOCK_DEAD flag is not set. + * Kernel handles this differently where new socket is + * created only after 3 way handshake is done. + */ + sock_orphan(child); + percpu_counter_inc((child)->sk_prot->orphan_count); + chtls_release_resources(child); + chtls_conn_done(child); + } else { + if (csk_flag(child, CSK_RST_ABORTED)) { + chtls_release_resources(child); + chtls_conn_done(child); + } + } +} + +static void pass_open_abort(struct sock *child, struct sock *parent, + struct sk_buff *skb) +{ + do_abort_syn_rcv(child, parent); + kfree_skb(skb); +} + +static void bl_pass_open_abort(struct sock *lsk, struct sk_buff *skb) +{ + pass_open_abort(skb->sk, lsk, skb); +} + +static void chtls_pass_open_arp_failure(struct sock *sk, + struct sk_buff *skb) +{ + const struct request_sock *oreq; + struct chtls_sock *csk; + struct chtls_dev *cdev; + struct sock *parent; + void *data; + + csk = rcu_dereference_sk_user_data(sk); + cdev = csk->cdev; + + /* + * If the connection is being aborted due to the parent listening + * socket going away there's nothing to do, the ABORT_REQ will close + * the connection. + */ + if (csk_flag(sk, CSK_ABORT_RPL_PENDING)) { + kfree_skb(skb); + return; + } + + oreq = csk->passive_reap_next; + data = lookup_stid(cdev->tids, oreq->ts_recent); + parent = ((struct listen_ctx *)data)->lsk; + + bh_lock_sock(parent); + if (!sock_owned_by_user(parent)) { + pass_open_abort(sk, parent, skb); + } else { + BLOG_SKB_CB(skb)->backlog_rcv = bl_pass_open_abort; + __sk_add_backlog(parent, skb); + } + bh_unlock_sock(parent); +} + +static void chtls_accept_rpl_arp_failure(void *handle, + struct sk_buff *skb) +{ + struct sock *sk = (struct sock *)handle; + + sock_hold(sk); + process_cpl_msg(chtls_pass_open_arp_failure, sk, skb); + sock_put(sk); +} + +static unsigned int chtls_select_mss(const struct chtls_sock *csk, + unsigned int pmtu, + struct cpl_pass_accept_req *req) +{ + struct chtls_dev *cdev; + struct dst_entry *dst; + unsigned int tcpoptsz; + unsigned int iphdrsz; + unsigned int mtu_idx; + struct tcp_sock *tp; + unsigned int mss; + struct sock *sk; + + mss = ntohs(req->tcpopt.mss); + sk = csk->sk; + dst = __sk_dst_get(sk); + cdev = csk->cdev; + tp = tcp_sk(sk); + tcpoptsz = 0; + + iphdrsz = sizeof(struct iphdr) + sizeof(struct tcphdr); + if (req->tcpopt.tstamp) + tcpoptsz += round_up(TCPOLEN_TIMESTAMP, 4); + + tp->advmss = dst_metric_advmss(dst); + if (USER_MSS(tp) && tp->advmss > USER_MSS(tp)) + tp->advmss = USER_MSS(tp); + if (tp->advmss > pmtu - iphdrsz) + tp->advmss = pmtu - iphdrsz; + if (mss && tp->advmss > mss) + tp->advmss = mss; + + tp->advmss = cxgb4_best_aligned_mtu(cdev->lldi->mtus, + iphdrsz + tcpoptsz, + tp->advmss - tcpoptsz, + 8, &mtu_idx); + tp->advmss -= iphdrsz; + + inet_csk(sk)->icsk_pmtu_cookie = pmtu; + return mtu_idx; +} + +static unsigned int select_rcv_wnd(struct chtls_sock *csk) +{ + unsigned int rcvwnd; + unsigned int wnd; + struct sock *sk; + + sk = csk->sk; + wnd = tcp_full_space(sk); + + if (wnd < MIN_RCV_WND) + wnd = MIN_RCV_WND; + + rcvwnd = MAX_RCV_WND; + + csk_set_flag(csk, CSK_UPDATE_RCV_WND); + return min(wnd, rcvwnd); +} + +static unsigned int select_rcv_wscale(int space, int wscale_ok, int win_clamp) +{ + int wscale = 0; + + if (space > MAX_RCV_WND) + space = MAX_RCV_WND; + if (win_clamp && win_clamp < space) + space = win_clamp; + + if (wscale_ok) { + while (wscale < 14 && (65535 << wscale) < space) + wscale++; + } + return wscale; +} + +static void chtls_pass_accept_rpl(struct sk_buff *skb, + struct cpl_pass_accept_req *req, + unsigned int tid) + +{ + struct cpl_t5_pass_accept_rpl *rpl5; + struct cxgb4_lld_info *lldi; + const struct tcphdr *tcph; + const struct tcp_sock *tp; + struct chtls_sock *csk; + unsigned int len; + struct sock *sk; + u32 opt2, hlen; + u64 opt0; + + sk = skb->sk; + tp = tcp_sk(sk); + csk = sk->sk_user_data; + csk->tid = tid; + lldi = csk->cdev->lldi; + len = roundup(sizeof(*rpl5), 16); + + rpl5 = __skb_put_zero(skb, len); + INIT_TP_WR(rpl5, tid); + + OPCODE_TID(rpl5) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL, + csk->tid)); + csk->mtu_idx = chtls_select_mss(csk, dst_mtu(__sk_dst_get(sk)), + req); + opt0 = TCAM_BYPASS_F | + WND_SCALE_V((tp)->rx_opt.rcv_wscale) | + MSS_IDX_V(csk->mtu_idx) | + L2T_IDX_V(csk->l2t_entry->idx) | + NAGLE_V(!(tp->nonagle & TCP_NAGLE_OFF)) | + TX_CHAN_V(csk->tx_chan) | + SMAC_SEL_V(csk->smac_idx) | + DSCP_V(csk->tos >> 2) | + ULP_MODE_V(ULP_MODE_TLS) | + RCV_BUFSIZ_V(min(tp->rcv_wnd >> 10, RCV_BUFSIZ_M)); + + opt2 = RX_CHANNEL_V(0) | + RSS_QUEUE_VALID_F | RSS_QUEUE_V(csk->rss_qid); + + if (!is_t5(lldi->adapter_type)) + opt2 |= RX_FC_DISABLE_F; + if (req->tcpopt.tstamp) + opt2 |= TSTAMPS_EN_F; + if (req->tcpopt.sack) + opt2 |= SACK_EN_F; + hlen = ntohl(req->hdr_len); + + tcph = (struct tcphdr *)((u8 *)(req + 1) + + T6_ETH_HDR_LEN_G(hlen) + T6_IP_HDR_LEN_G(hlen)); + if (tcph->ece && tcph->cwr) + opt2 |= CCTRL_ECN_V(1); + opt2 |= CONG_CNTRL_V(CONG_ALG_NEWRENO); + opt2 |= T5_ISS_F; + opt2 |= T5_OPT_2_VALID_F; + rpl5->opt0 = cpu_to_be64(opt0); + rpl5->opt2 = cpu_to_be32(opt2); + rpl5->iss = cpu_to_be32((prandom_u32() & ~7UL) - 1); + set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->port_id); + t4_set_arp_err_handler(skb, sk, chtls_accept_rpl_arp_failure); + cxgb4_l2t_send(csk->egress_dev, skb, csk->l2t_entry); +} + +static void inet_inherit_port(struct inet_hashinfo *hash_info, + struct sock *lsk, struct sock *newsk) +{ + local_bh_disable(); + __inet_inherit_port(lsk, newsk); + local_bh_enable(); +} + +static int chtls_backlog_rcv(struct sock *sk, struct sk_buff *skb) +{ + if (skb->protocol) { + kfree_skb(skb); + return 0; + } + BLOG_SKB_CB(skb)->backlog_rcv(sk, skb); + return 0; +} + +static struct sock *chtls_recv_sock(struct sock *lsk, + struct request_sock *oreq, + void *network_hdr, + const struct cpl_pass_accept_req *req, + struct chtls_dev *cdev) +{ + struct adapter *adap = pci_get_drvdata(cdev->pdev); + const struct tcphdr *tcph; + struct inet_sock *newinet; + const struct iphdr *iph; + struct net_device *ndev; + struct chtls_sock *csk; + struct dst_entry *dst; + struct neighbour *n; + struct tcp_sock *tp; + struct sock *newsk; + bool found = false; + u16 port_id; + int rxq_idx; + int step, i; + + iph = (const struct iphdr *)network_hdr; + newsk = tcp_create_openreq_child(lsk, oreq, cdev->askb); + if (!newsk) + goto free_oreq; + + dst = inet_csk_route_child_sock(lsk, newsk, oreq); + if (!dst) + goto free_sk; + + tcph = (struct tcphdr *)(iph + 1); + n = dst_neigh_lookup(dst, &iph->saddr); + if (!n || !n->dev) + goto free_dst; + + ndev = n->dev; + if (is_vlan_dev(ndev)) + ndev = vlan_dev_real_dev(ndev); + + for_each_port(adap, i) + if (cdev->ports[i] == ndev) + found = true; + + if (!found) + goto free_dst; + + port_id = cxgb4_port_idx(ndev); + + csk = chtls_sock_create(cdev); + if (!csk) + goto free_dst; + + csk->l2t_entry = cxgb4_l2t_get(cdev->lldi->l2t, n, ndev, 0); + if (!csk->l2t_entry) + goto free_csk; + + newsk->sk_user_data = csk; + newsk->sk_backlog_rcv = chtls_backlog_rcv; + + tp = tcp_sk(newsk); + newinet = inet_sk(newsk); + + newinet->inet_daddr = iph->saddr; + newinet->inet_rcv_saddr = iph->daddr; + newinet->inet_saddr = iph->daddr; + + oreq->ts_recent = PASS_OPEN_TID_G(ntohl(req->tos_stid)); + sk_setup_caps(newsk, dst); + newsk->sk_prot_creator = lsk->sk_prot_creator; + csk->sk = newsk; + csk->passive_reap_next = oreq; + csk->tx_chan = cxgb4_port_chan(ndev); + csk->port_id = port_id; + csk->egress_dev = ndev; + csk->tos = PASS_OPEN_TOS_G(ntohl(req->tos_stid)); + csk->ulp_mode = ULP_MODE_TLS; + step = cdev->lldi->nrxq / cdev->lldi->nchan; + csk->rss_qid = cdev->lldi->rxq_ids[port_id * step]; + rxq_idx = port_id * step; + csk->txq_idx = (rxq_idx < cdev->lldi->ntxq) ? rxq_idx : + port_id * step; + csk->sndbuf = newsk->sk_sndbuf; + csk->smac_idx = cxgb4_tp_smt_idx(cdev->lldi->adapter_type, + cxgb4_port_viid(ndev)); + tp->rcv_wnd = select_rcv_wnd(csk); + RCV_WSCALE(tp) = select_rcv_wscale(tcp_full_space(newsk), + WSCALE_OK(tp), + tp->window_clamp); + neigh_release(n); + inet_inherit_port(&tcp_hashinfo, lsk, newsk); + csk_set_flag(csk, CSK_CONN_INLINE); + bh_unlock_sock(newsk); /* tcp_create_openreq_child ->sk_clone_lock */ + + return newsk; +free_csk: + chtls_sock_release(&csk->kref); +free_dst: + if (n) + neigh_release(n); + dst_release(dst); +free_sk: + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); +free_oreq: + chtls_reqsk_free(oreq); + return NULL; +} + +/* + * Populate a TID_RELEASE WR. The skb must be already propely sized. + */ +static void mk_tid_release(struct sk_buff *skb, + unsigned int chan, unsigned int tid) +{ + struct cpl_tid_release *req; + unsigned int len; + + len = roundup(sizeof(struct cpl_tid_release), 16); + req = (struct cpl_tid_release *)__skb_put(skb, len); + memset(req, 0, len); + set_wr_txq(skb, CPL_PRIORITY_SETUP, chan); + INIT_TP_WR_CPL(req, CPL_TID_RELEASE, tid); +} + +static int chtls_get_module(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (!try_module_get(icsk->icsk_ulp_ops->owner)) + return -1; + + return 0; +} + +static void chtls_pass_accept_request(struct sock *sk, + struct sk_buff *skb) +{ + struct cpl_t5_pass_accept_rpl *rpl; + struct cpl_pass_accept_req *req; + struct listen_ctx *listen_ctx; + struct request_sock *oreq; + struct sk_buff *reply_skb; + struct chtls_sock *csk; + struct chtls_dev *cdev; + struct tcphdr *tcph; + struct sock *newsk; + struct ethhdr *eh; + struct iphdr *iph; + void *network_hdr; + unsigned int stid; + unsigned int len; + unsigned int tid; + + req = cplhdr(skb) + RSS_HDR; + tid = GET_TID(req); + cdev = BLOG_SKB_CB(skb)->cdev; + newsk = lookup_tid(cdev->tids, tid); + stid = PASS_OPEN_TID_G(ntohl(req->tos_stid)); + if (newsk) { + pr_info("tid (%d) already in use\n", tid); + return; + } + + len = roundup(sizeof(*rpl), 16); + reply_skb = alloc_skb(len, GFP_ATOMIC); + if (!reply_skb) { + cxgb4_remove_tid(cdev->tids, 0, tid, sk->sk_family); + kfree_skb(skb); + return; + } + + if (sk->sk_state != TCP_LISTEN) + goto reject; + + if (inet_csk_reqsk_queue_is_full(sk)) + goto reject; + + if (sk_acceptq_is_full(sk)) + goto reject; + + oreq = inet_reqsk_alloc(&chtls_rsk_ops, sk, true); + if (!oreq) + goto reject; + + oreq->rsk_rcv_wnd = 0; + oreq->rsk_window_clamp = 0; + oreq->cookie_ts = 0; + oreq->mss = 0; + oreq->ts_recent = 0; + + eh = (struct ethhdr *)(req + 1); + iph = (struct iphdr *)(eh + 1); + if (iph->version != 0x4) + goto free_oreq; + + network_hdr = (void *)(eh + 1); + tcph = (struct tcphdr *)(iph + 1); + + tcp_rsk(oreq)->tfo_listener = false; + tcp_rsk(oreq)->rcv_isn = ntohl(tcph->seq); + chtls_set_req_port(oreq, tcph->source, tcph->dest); + inet_rsk(oreq)->ecn_ok = 0; + chtls_set_req_addr(oreq, iph->daddr, iph->saddr); + if (req->tcpopt.wsf <= 14) { + inet_rsk(oreq)->wscale_ok = 1; + inet_rsk(oreq)->snd_wscale = req->tcpopt.wsf; + } + inet_rsk(oreq)->ir_iif = sk->sk_bound_dev_if; + + newsk = chtls_recv_sock(sk, oreq, network_hdr, req, cdev); + if (!newsk) + goto reject; + + if (chtls_get_module(newsk)) + goto reject; + inet_csk_reqsk_queue_added(sk); + reply_skb->sk = newsk; + chtls_install_cpl_ops(newsk); + cxgb4_insert_tid(cdev->tids, newsk, tid, newsk->sk_family); + csk = rcu_dereference_sk_user_data(newsk); + listen_ctx = (struct listen_ctx *)lookup_stid(cdev->tids, stid); + csk->listen_ctx = listen_ctx; + __skb_queue_tail(&listen_ctx->synq, (struct sk_buff *)&csk->synq); + chtls_pass_accept_rpl(reply_skb, req, tid); + kfree_skb(skb); + return; + +free_oreq: + chtls_reqsk_free(oreq); +reject: + mk_tid_release(reply_skb, 0, tid); + cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb); + kfree_skb(skb); +} + +/* + * Handle a CPL_PASS_ACCEPT_REQ message. + */ +static int chtls_pass_accept_req(struct chtls_dev *cdev, struct sk_buff *skb) +{ + struct cpl_pass_accept_req *req = cplhdr(skb) + RSS_HDR; + struct listen_ctx *ctx; + unsigned int stid; + unsigned int tid; + struct sock *lsk; + void *data; + + stid = PASS_OPEN_TID_G(ntohl(req->tos_stid)); + tid = GET_TID(req); + + data = lookup_stid(cdev->tids, stid); + if (!data) + return 1; + + ctx = (struct listen_ctx *)data; + lsk = ctx->lsk; + + if (unlikely(tid >= cdev->tids->ntids)) { + pr_info("passive open TID %u too large\n", tid); + return 1; + } + + BLOG_SKB_CB(skb)->cdev = cdev; + process_cpl_msg(chtls_pass_accept_request, lsk, skb); + return 0; +} + +/* + * Completes some final bits of initialization for just established connections + * and changes their state to TCP_ESTABLISHED. + * + * snd_isn here is the ISN after the SYN, i.e., the true ISN + 1. + */ +static void make_established(struct sock *sk, u32 snd_isn, unsigned int opt) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tp->pushed_seq = snd_isn; + tp->write_seq = snd_isn; + tp->snd_nxt = snd_isn; + tp->snd_una = snd_isn; + inet_sk(sk)->inet_id = prandom_u32(); + assign_rxopt(sk, opt); + + if (tp->rcv_wnd > (RCV_BUFSIZ_M << 10)) + tp->rcv_wup -= tp->rcv_wnd - (RCV_BUFSIZ_M << 10); + + smp_mb(); + tcp_set_state(sk, TCP_ESTABLISHED); +} + +static void chtls_abort_conn(struct sock *sk, struct sk_buff *skb) +{ + struct sk_buff *abort_skb; + + abort_skb = alloc_skb(sizeof(struct cpl_abort_req), GFP_ATOMIC); + if (abort_skb) + chtls_send_reset(sk, CPL_ABORT_SEND_RST, abort_skb); +} + +static struct sock *reap_list; +static DEFINE_SPINLOCK(reap_list_lock); + +/* + * Process the reap list. + */ +DECLARE_TASK_FUNC(process_reap_list, task_param) +{ + spin_lock_bh(&reap_list_lock); + while (reap_list) { + struct sock *sk = reap_list; + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + + reap_list = csk->passive_reap_next; + csk->passive_reap_next = NULL; + spin_unlock(&reap_list_lock); + sock_hold(sk); + + bh_lock_sock(sk); + chtls_abort_conn(sk, NULL); + sock_orphan(sk); + if (sk->sk_state == TCP_CLOSE) + inet_csk_destroy_sock(sk); + bh_unlock_sock(sk); + sock_put(sk); + spin_lock(&reap_list_lock); + } + spin_unlock_bh(&reap_list_lock); +} + +static DECLARE_WORK(reap_task, process_reap_list); + +static void add_to_reap_list(struct sock *sk) +{ + struct chtls_sock *csk = sk->sk_user_data; + + local_bh_disable(); + release_tcp_port(sk); /* release the port immediately */ + + spin_lock(&reap_list_lock); + csk->passive_reap_next = reap_list; + reap_list = sk; + if (!csk->passive_reap_next) + schedule_work(&reap_task); + spin_unlock(&reap_list_lock); + local_bh_enable(); +} + +static void add_pass_open_to_parent(struct sock *child, struct sock *lsk, + struct chtls_dev *cdev) +{ + struct request_sock *oreq; + struct chtls_sock *csk; + + if (lsk->sk_state != TCP_LISTEN) + return; + + csk = child->sk_user_data; + oreq = csk->passive_reap_next; + csk->passive_reap_next = NULL; + + reqsk_queue_removed(&inet_csk(lsk)->icsk_accept_queue, oreq); + __skb_unlink((struct sk_buff *)&csk->synq, &csk->listen_ctx->synq); + + if (sk_acceptq_is_full(lsk)) { + chtls_reqsk_free(oreq); + add_to_reap_list(child); + } else { + refcount_set(&oreq->rsk_refcnt, 1); + inet_csk_reqsk_queue_add(lsk, oreq, child); + lsk->sk_data_ready(lsk); + } +} + +static void bl_add_pass_open_to_parent(struct sock *lsk, struct sk_buff *skb) +{ + struct sock *child = skb->sk; + + skb->sk = NULL; + add_pass_open_to_parent(child, lsk, BLOG_SKB_CB(skb)->cdev); + kfree_skb(skb); +} + +static int chtls_pass_establish(struct chtls_dev *cdev, struct sk_buff *skb) +{ + struct cpl_pass_establish *req = cplhdr(skb) + RSS_HDR; + struct chtls_sock *csk; + struct sock *lsk, *sk; + unsigned int hwtid; + + hwtid = GET_TID(req); + sk = lookup_tid(cdev->tids, hwtid); + if (!sk) + return (CPL_RET_UNKNOWN_TID | CPL_RET_BUF_DONE); + + bh_lock_sock(sk); + if (unlikely(sock_owned_by_user(sk))) { + kfree_skb(skb); + } else { + unsigned int stid; + void *data; + + csk = sk->sk_user_data; + csk->wr_max_credits = 64; + csk->wr_credits = 64; + csk->wr_unacked = 0; + make_established(sk, ntohl(req->snd_isn), ntohs(req->tcp_opt)); + stid = PASS_OPEN_TID_G(ntohl(req->tos_stid)); + sk->sk_state_change(sk); + if (unlikely(sk->sk_socket)) + sk_wake_async(sk, 0, POLL_OUT); + + data = lookup_stid(cdev->tids, stid); + if (!data) { + /* listening server close */ + kfree_skb(skb); + goto unlock; + } + lsk = ((struct listen_ctx *)data)->lsk; + + bh_lock_sock(lsk); + if (unlikely(skb_queue_empty(&csk->listen_ctx->synq))) { + /* removed from synq */ + bh_unlock_sock(lsk); + kfree_skb(skb); + goto unlock; + } + + if (likely(!sock_owned_by_user(lsk))) { + kfree_skb(skb); + add_pass_open_to_parent(sk, lsk, cdev); + } else { + skb->sk = sk; + BLOG_SKB_CB(skb)->cdev = cdev; + BLOG_SKB_CB(skb)->backlog_rcv = + bl_add_pass_open_to_parent; + __sk_add_backlog(lsk, skb); + } + bh_unlock_sock(lsk); + } +unlock: + bh_unlock_sock(sk); + return 0; +} + +/* + * Handle receipt of an urgent pointer. + */ +static void handle_urg_ptr(struct sock *sk, u32 urg_seq) +{ + struct tcp_sock *tp = tcp_sk(sk); + + urg_seq--; + if (tp->urg_data && !after(urg_seq, tp->urg_seq)) + return; /* duplicate pointer */ + + sk_send_sigurg(sk); + if (tp->urg_seq == tp->copied_seq && tp->urg_data && + !sock_flag(sk, SOCK_URGINLINE) && + tp->copied_seq != tp->rcv_nxt) { + struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + + tp->copied_seq++; + if (skb && tp->copied_seq - ULP_SKB_CB(skb)->seq >= skb->len) + chtls_free_skb(sk, skb); + } + + tp->urg_data = TCP_URG_NOTYET; + tp->urg_seq = urg_seq; +} + +static void check_sk_callbacks(struct chtls_sock *csk) +{ + struct sock *sk = csk->sk; + + if (unlikely(sk->sk_user_data && + !csk_flag_nochk(csk, CSK_CALLBACKS_CHKD))) + csk_set_flag(csk, CSK_CALLBACKS_CHKD); +} + +/* + * Handles Rx data that arrives in a state where the socket isn't accepting + * new data. + */ +static void handle_excess_rx(struct sock *sk, struct sk_buff *skb) +{ + if (!csk_flag(sk, CSK_ABORT_SHUTDOWN)) + chtls_abort_conn(sk, skb); + + kfree_skb(skb); +} + +static void chtls_recv_data(struct sock *sk, struct sk_buff *skb) +{ + struct cpl_rx_data *hdr = cplhdr(skb) + RSS_HDR; + struct chtls_sock *csk; + struct tcp_sock *tp; + + csk = rcu_dereference_sk_user_data(sk); + tp = tcp_sk(sk); + + if (unlikely(sk->sk_shutdown & RCV_SHUTDOWN)) { + handle_excess_rx(sk, skb); + return; + } + + ULP_SKB_CB(skb)->seq = ntohl(hdr->seq); + ULP_SKB_CB(skb)->psh = hdr->psh; + skb_ulp_mode(skb) = ULP_MODE_NONE; + + skb_reset_transport_header(skb); + __skb_pull(skb, sizeof(*hdr) + RSS_HDR); + if (!skb->data_len) + __skb_trim(skb, ntohs(hdr->len)); + + if (unlikely(hdr->urg)) + handle_urg_ptr(sk, tp->rcv_nxt + ntohs(hdr->urg)); + if (unlikely(tp->urg_data == TCP_URG_NOTYET && + tp->urg_seq - tp->rcv_nxt < skb->len)) + tp->urg_data = TCP_URG_VALID | + skb->data[tp->urg_seq - tp->rcv_nxt]; + + if (unlikely(hdr->dack_mode != csk->delack_mode)) { + csk->delack_mode = hdr->dack_mode; + csk->delack_seq = tp->rcv_nxt; + } + + tcp_hdr(skb)->fin = 0; + tp->rcv_nxt += skb->len; + + __skb_queue_tail(&sk->sk_receive_queue, skb); + + if (!sock_flag(sk, SOCK_DEAD)) { + check_sk_callbacks(csk); + sk->sk_data_ready(sk); + } +} + +static int chtls_rx_data(struct chtls_dev *cdev, struct sk_buff *skb) +{ + struct cpl_rx_data *req = cplhdr(skb) + RSS_HDR; + unsigned int hwtid = GET_TID(req); + struct sock *sk; + + sk = lookup_tid(cdev->tids, hwtid); + if (unlikely(!sk)) { + pr_err("can't find conn. for hwtid %u.\n", hwtid); + return -EINVAL; + } + skb_dst_set(skb, NULL); + process_cpl_msg(chtls_recv_data, sk, skb); + return 0; +} + +static void chtls_recv_pdu(struct sock *sk, struct sk_buff *skb) +{ + struct cpl_tls_data *hdr = cplhdr(skb); + struct chtls_sock *csk; + struct chtls_hws *tlsk; + struct tcp_sock *tp; + + csk = rcu_dereference_sk_user_data(sk); + tlsk = &csk->tlshws; + tp = tcp_sk(sk); + + if (unlikely(sk->sk_shutdown & RCV_SHUTDOWN)) { + handle_excess_rx(sk, skb); + return; + } + + ULP_SKB_CB(skb)->seq = ntohl(hdr->seq); + ULP_SKB_CB(skb)->flags = 0; + skb_ulp_mode(skb) = ULP_MODE_TLS; + + skb_reset_transport_header(skb); + __skb_pull(skb, sizeof(*hdr)); + if (!skb->data_len) + __skb_trim(skb, + CPL_TLS_DATA_LENGTH_G(ntohl(hdr->length_pkd))); + + if (unlikely(tp->urg_data == TCP_URG_NOTYET && tp->urg_seq - + tp->rcv_nxt < skb->len)) + tp->urg_data = TCP_URG_VALID | + skb->data[tp->urg_seq - tp->rcv_nxt]; + + tcp_hdr(skb)->fin = 0; + tlsk->pldlen = CPL_TLS_DATA_LENGTH_G(ntohl(hdr->length_pkd)); + __skb_queue_tail(&tlsk->sk_recv_queue, skb); +} + +static int chtls_rx_pdu(struct chtls_dev *cdev, struct sk_buff *skb) +{ + struct cpl_tls_data *req = cplhdr(skb); + unsigned int hwtid = GET_TID(req); + struct sock *sk; + + sk = lookup_tid(cdev->tids, hwtid); + if (unlikely(!sk)) { + pr_err("can't find conn. for hwtid %u.\n", hwtid); + return -EINVAL; + } + skb_dst_set(skb, NULL); + process_cpl_msg(chtls_recv_pdu, sk, skb); + return 0; +} + +static void chtls_set_hdrlen(struct sk_buff *skb, unsigned int nlen) +{ + struct tlsrx_cmp_hdr *tls_cmp_hdr = cplhdr(skb); + + skb->hdr_len = ntohs((__force __be16)tls_cmp_hdr->length); + tls_cmp_hdr->length = ntohs((__force __be16)nlen); +} + +static void chtls_rx_hdr(struct sock *sk, struct sk_buff *skb) +{ + struct tlsrx_cmp_hdr *tls_hdr_pkt; + struct cpl_rx_tls_cmp *cmp_cpl; + struct sk_buff *skb_rec; + struct chtls_sock *csk; + struct chtls_hws *tlsk; + struct tcp_sock *tp; + + cmp_cpl = cplhdr(skb); + csk = rcu_dereference_sk_user_data(sk); + tlsk = &csk->tlshws; + tp = tcp_sk(sk); + + ULP_SKB_CB(skb)->seq = ntohl(cmp_cpl->seq); + ULP_SKB_CB(skb)->flags = 0; + + skb_reset_transport_header(skb); + __skb_pull(skb, sizeof(*cmp_cpl)); + tls_hdr_pkt = (struct tlsrx_cmp_hdr *)skb->data; + if (tls_hdr_pkt->res_to_mac_error & TLSRX_HDR_PKT_ERROR_M) + tls_hdr_pkt->type = CONTENT_TYPE_ERROR; + if (!skb->data_len) + __skb_trim(skb, TLS_HEADER_LENGTH); + + tp->rcv_nxt += + CPL_RX_TLS_CMP_PDULENGTH_G(ntohl(cmp_cpl->pdulength_length)); + + ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_TLS_HDR; + skb_rec = __skb_dequeue(&tlsk->sk_recv_queue); + if (!skb_rec) { + __skb_queue_tail(&sk->sk_receive_queue, skb); + } else { + chtls_set_hdrlen(skb, tlsk->pldlen); + tlsk->pldlen = 0; + __skb_queue_tail(&sk->sk_receive_queue, skb); + __skb_queue_tail(&sk->sk_receive_queue, skb_rec); + } + + if (!sock_flag(sk, SOCK_DEAD)) { + check_sk_callbacks(csk); + sk->sk_data_ready(sk); + } +} + +static int chtls_rx_cmp(struct chtls_dev *cdev, struct sk_buff *skb) +{ + struct cpl_rx_tls_cmp *req = cplhdr(skb); + unsigned int hwtid = GET_TID(req); + struct sock *sk; + + sk = lookup_tid(cdev->tids, hwtid); + if (unlikely(!sk)) { + pr_err("can't find conn. for hwtid %u.\n", hwtid); + return -EINVAL; + } + skb_dst_set(skb, NULL); + process_cpl_msg(chtls_rx_hdr, sk, skb); + + return 0; +} + +static void chtls_timewait(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tp->rcv_nxt++; + tp->rx_opt.ts_recent_stamp = ktime_get_seconds(); + tp->srtt_us = 0; + tcp_time_wait(sk, TCP_TIME_WAIT, 0); +} + +static void chtls_peer_close(struct sock *sk, struct sk_buff *skb) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + + sk->sk_shutdown |= RCV_SHUTDOWN; + sock_set_flag(sk, SOCK_DONE); + + switch (sk->sk_state) { + case TCP_SYN_RECV: + case TCP_ESTABLISHED: + tcp_set_state(sk, TCP_CLOSE_WAIT); + break; + case TCP_FIN_WAIT1: + tcp_set_state(sk, TCP_CLOSING); + break; + case TCP_FIN_WAIT2: + chtls_release_resources(sk); + if (csk_flag_nochk(csk, CSK_ABORT_RPL_PENDING)) + chtls_conn_done(sk); + else + chtls_timewait(sk); + break; + default: + pr_info("cpl_peer_close in bad state %d\n", sk->sk_state); + } + + if (!sock_flag(sk, SOCK_DEAD)) { + sk->sk_state_change(sk); + /* Do not send POLL_HUP for half duplex close. */ + + if ((sk->sk_shutdown & SEND_SHUTDOWN) || + sk->sk_state == TCP_CLOSE) + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); + else + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + } + kfree_skb(skb); +} + +static void chtls_close_con_rpl(struct sock *sk, struct sk_buff *skb) +{ + struct cpl_close_con_rpl *rpl = cplhdr(skb) + RSS_HDR; + struct chtls_sock *csk; + struct tcp_sock *tp; + + csk = rcu_dereference_sk_user_data(sk); + tp = tcp_sk(sk); + + tp->snd_una = ntohl(rpl->snd_nxt) - 1; /* exclude FIN */ + + switch (sk->sk_state) { + case TCP_CLOSING: + chtls_release_resources(sk); + if (csk_flag_nochk(csk, CSK_ABORT_RPL_PENDING)) + chtls_conn_done(sk); + else + chtls_timewait(sk); + break; + case TCP_LAST_ACK: + chtls_release_resources(sk); + chtls_conn_done(sk); + break; + case TCP_FIN_WAIT1: + tcp_set_state(sk, TCP_FIN_WAIT2); + sk->sk_shutdown |= SEND_SHUTDOWN; + + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_state_change(sk); + else if (tcp_sk(sk)->linger2 < 0 && + !csk_flag_nochk(csk, CSK_ABORT_SHUTDOWN)) + chtls_abort_conn(sk, skb); + break; + default: + pr_info("close_con_rpl in bad state %d\n", sk->sk_state); + } + kfree_skb(skb); +} + +static struct sk_buff *get_cpl_skb(struct sk_buff *skb, + size_t len, gfp_t gfp) +{ + if (likely(!skb_is_nonlinear(skb) && !skb_cloned(skb))) { + WARN_ONCE(skb->len < len, "skb alloc error"); + __skb_trim(skb, len); + skb_get(skb); + } else { + skb = alloc_skb(len, gfp); + if (skb) + __skb_put(skb, len); + } + return skb; +} + +static void set_abort_rpl_wr(struct sk_buff *skb, unsigned int tid, + int cmd) +{ + struct cpl_abort_rpl *rpl = cplhdr(skb); + + INIT_TP_WR_CPL(rpl, CPL_ABORT_RPL, tid); + rpl->cmd = cmd; +} + +static void send_defer_abort_rpl(struct chtls_dev *cdev, struct sk_buff *skb) +{ + struct cpl_abort_req_rss *req = cplhdr(skb); + struct sk_buff *reply_skb; + + reply_skb = alloc_skb(sizeof(struct cpl_abort_rpl), + GFP_KERNEL | __GFP_NOFAIL); + __skb_put(reply_skb, sizeof(struct cpl_abort_rpl)); + set_abort_rpl_wr(reply_skb, GET_TID(req), + (req->status & CPL_ABORT_NO_RST)); + set_wr_txq(reply_skb, CPL_PRIORITY_DATA, req->status >> 1); + cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb); + kfree_skb(skb); +} + +/* + * Add an skb to the deferred skb queue for processing from process context. + */ +static void t4_defer_reply(struct sk_buff *skb, struct chtls_dev *cdev, + defer_handler_t handler) +{ + DEFERRED_SKB_CB(skb)->handler = handler; + spin_lock_bh(&cdev->deferq.lock); + __skb_queue_tail(&cdev->deferq, skb); + if (skb_queue_len(&cdev->deferq) == 1) + schedule_work(&cdev->deferq_task); + spin_unlock_bh(&cdev->deferq.lock); +} + +static void chtls_send_abort_rpl(struct sock *sk, struct sk_buff *skb, + struct chtls_dev *cdev, + int status, int queue) +{ + struct cpl_abort_req_rss *req = cplhdr(skb) + RSS_HDR; + struct sk_buff *reply_skb; + struct chtls_sock *csk; + unsigned int tid; + + csk = rcu_dereference_sk_user_data(sk); + tid = GET_TID(req); + + reply_skb = get_cpl_skb(skb, sizeof(struct cpl_abort_rpl), gfp_any()); + if (!reply_skb) { + req->status = (queue << 1) | status; + t4_defer_reply(skb, cdev, send_defer_abort_rpl); + return; + } + + set_abort_rpl_wr(reply_skb, tid, status); + set_wr_txq(reply_skb, CPL_PRIORITY_DATA, queue); + if (csk_conn_inline(csk)) { + struct l2t_entry *e = csk->l2t_entry; + + if (e && sk->sk_state != TCP_SYN_RECV) { + cxgb4_l2t_send(csk->egress_dev, reply_skb, e); + return; + } + } + cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb); + kfree_skb(skb); +} + +/* + * This is run from a listener's backlog to abort a child connection in + * SYN_RCV state (i.e., one on the listener's SYN queue). + */ +static void bl_abort_syn_rcv(struct sock *lsk, struct sk_buff *skb) +{ + struct chtls_sock *csk; + struct sock *child; + int queue; + + child = skb->sk; + csk = rcu_dereference_sk_user_data(child); + queue = csk->txq_idx; + + skb->sk = NULL; + chtls_send_abort_rpl(child, skb, BLOG_SKB_CB(skb)->cdev, + CPL_ABORT_NO_RST, queue); + do_abort_syn_rcv(child, lsk); +} + +static int abort_syn_rcv(struct sock *sk, struct sk_buff *skb) +{ + const struct request_sock *oreq; + struct listen_ctx *listen_ctx; + struct chtls_sock *csk; + struct chtls_dev *cdev; + struct sock *psk; + void *ctx; + + csk = sk->sk_user_data; + oreq = csk->passive_reap_next; + cdev = csk->cdev; + + if (!oreq) + return -1; + + ctx = lookup_stid(cdev->tids, oreq->ts_recent); + if (!ctx) + return -1; + + listen_ctx = (struct listen_ctx *)ctx; + psk = listen_ctx->lsk; + + bh_lock_sock(psk); + if (!sock_owned_by_user(psk)) { + int queue = csk->txq_idx; + + chtls_send_abort_rpl(sk, skb, cdev, CPL_ABORT_NO_RST, queue); + do_abort_syn_rcv(sk, psk); + } else { + skb->sk = sk; + BLOG_SKB_CB(skb)->backlog_rcv = bl_abort_syn_rcv; + __sk_add_backlog(psk, skb); + } + bh_unlock_sock(psk); + return 0; +} + +static void chtls_abort_req_rss(struct sock *sk, struct sk_buff *skb) +{ + const struct cpl_abort_req_rss *req = cplhdr(skb) + RSS_HDR; + struct chtls_sock *csk = sk->sk_user_data; + int rst_status = CPL_ABORT_NO_RST; + int queue = csk->txq_idx; + + if (is_neg_adv(req->status)) { + kfree_skb(skb); + return; + } + + csk_reset_flag(csk, CSK_ABORT_REQ_RCVD); + + if (!csk_flag_nochk(csk, CSK_ABORT_SHUTDOWN) && + !csk_flag_nochk(csk, CSK_TX_DATA_SENT)) { + struct tcp_sock *tp = tcp_sk(sk); + + if (send_tx_flowc_wr(sk, 0, tp->snd_nxt, tp->rcv_nxt) < 0) + WARN_ONCE(1, "send_tx_flowc error"); + csk_set_flag(csk, CSK_TX_DATA_SENT); + } + + csk_set_flag(csk, CSK_ABORT_SHUTDOWN); + + if (!csk_flag_nochk(csk, CSK_ABORT_RPL_PENDING)) { + sk->sk_err = ETIMEDOUT; + + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + + if (sk->sk_state == TCP_SYN_RECV && !abort_syn_rcv(sk, skb)) + return; + } + + chtls_send_abort_rpl(sk, skb, csk->cdev, rst_status, queue); + chtls_release_resources(sk); + chtls_conn_done(sk); +} + +static void chtls_abort_rpl_rss(struct sock *sk, struct sk_buff *skb) +{ + struct cpl_abort_rpl_rss *rpl = cplhdr(skb) + RSS_HDR; + struct chtls_sock *csk; + struct chtls_dev *cdev; + + csk = rcu_dereference_sk_user_data(sk); + cdev = csk->cdev; + + if (csk_flag_nochk(csk, CSK_ABORT_RPL_PENDING)) { + csk_reset_flag(csk, CSK_ABORT_RPL_PENDING); + if (!csk_flag_nochk(csk, CSK_ABORT_REQ_RCVD)) { + if (sk->sk_state == TCP_SYN_SENT) { + cxgb4_remove_tid(cdev->tids, + csk->port_id, + GET_TID(rpl), + sk->sk_family); + sock_put(sk); + } + chtls_release_resources(sk); + chtls_conn_done(sk); + } + } + kfree_skb(skb); +} + +static int chtls_conn_cpl(struct chtls_dev *cdev, struct sk_buff *skb) +{ + struct cpl_peer_close *req = cplhdr(skb) + RSS_HDR; + void (*fn)(struct sock *sk, struct sk_buff *skb); + unsigned int hwtid = GET_TID(req); + struct sock *sk; + u8 opcode; + + opcode = ((const struct rss_header *)cplhdr(skb))->opcode; + + sk = lookup_tid(cdev->tids, hwtid); + if (!sk) + goto rel_skb; + + switch (opcode) { + case CPL_PEER_CLOSE: + fn = chtls_peer_close; + break; + case CPL_CLOSE_CON_RPL: + fn = chtls_close_con_rpl; + break; + case CPL_ABORT_REQ_RSS: + fn = chtls_abort_req_rss; + break; + case CPL_ABORT_RPL_RSS: + fn = chtls_abort_rpl_rss; + break; + default: + goto rel_skb; + } + + process_cpl_msg(fn, sk, skb); + return 0; + +rel_skb: + kfree_skb(skb); + return 0; +} + +static void chtls_rx_ack(struct sock *sk, struct sk_buff *skb) +{ + struct cpl_fw4_ack *hdr = cplhdr(skb) + RSS_HDR; + struct chtls_sock *csk = sk->sk_user_data; + struct tcp_sock *tp = tcp_sk(sk); + u32 credits = hdr->credits; + u32 snd_una; + + snd_una = ntohl(hdr->snd_una); + csk->wr_credits += credits; + + if (csk->wr_unacked > csk->wr_max_credits - csk->wr_credits) + csk->wr_unacked = csk->wr_max_credits - csk->wr_credits; + + while (credits) { + struct sk_buff *pskb = csk->wr_skb_head; + u32 csum; + + if (unlikely(!pskb)) { + if (csk->wr_nondata) + csk->wr_nondata -= credits; + break; + } + csum = (__force u32)pskb->csum; + if (unlikely(credits < csum)) { + pskb->csum = (__force __wsum)(csum - credits); + break; + } + dequeue_wr(sk); + credits -= csum; + kfree_skb(pskb); + } + if (hdr->seq_vld & CPL_FW4_ACK_FLAGS_SEQVAL) { + if (unlikely(before(snd_una, tp->snd_una))) { + kfree_skb(skb); + return; + } + + if (tp->snd_una != snd_una) { + tp->snd_una = snd_una; + tp->rcv_tstamp = tcp_time_stamp(tp); + if (tp->snd_una == tp->snd_nxt && + !csk_flag_nochk(csk, CSK_TX_FAILOVER)) + csk_reset_flag(csk, CSK_TX_WAIT_IDLE); + } + } + + if (hdr->seq_vld & CPL_FW4_ACK_FLAGS_CH) { + unsigned int fclen16 = roundup(failover_flowc_wr_len, 16); + + csk->wr_credits -= fclen16; + csk_reset_flag(csk, CSK_TX_WAIT_IDLE); + csk_reset_flag(csk, CSK_TX_FAILOVER); + } + if (skb_queue_len(&csk->txq) && chtls_push_frames(csk, 0)) + sk->sk_write_space(sk); + + kfree_skb(skb); +} + +static int chtls_wr_ack(struct chtls_dev *cdev, struct sk_buff *skb) +{ + struct cpl_fw4_ack *rpl = cplhdr(skb) + RSS_HDR; + unsigned int hwtid = GET_TID(rpl); + struct sock *sk; + + sk = lookup_tid(cdev->tids, hwtid); + if (unlikely(!sk)) { + pr_err("can't find conn. for hwtid %u.\n", hwtid); + return -EINVAL; + } + process_cpl_msg(chtls_rx_ack, sk, skb); + + return 0; +} + +chtls_handler_func chtls_handlers[NUM_CPL_CMDS] = { + [CPL_PASS_OPEN_RPL] = chtls_pass_open_rpl, + [CPL_CLOSE_LISTSRV_RPL] = chtls_close_listsrv_rpl, + [CPL_PASS_ACCEPT_REQ] = chtls_pass_accept_req, + [CPL_PASS_ESTABLISH] = chtls_pass_establish, + [CPL_RX_DATA] = chtls_rx_data, + [CPL_TLS_DATA] = chtls_rx_pdu, + [CPL_RX_TLS_CMP] = chtls_rx_cmp, + [CPL_PEER_CLOSE] = chtls_conn_cpl, + [CPL_CLOSE_CON_RPL] = chtls_conn_cpl, + [CPL_ABORT_REQ_RSS] = chtls_conn_cpl, + [CPL_ABORT_RPL_RSS] = chtls_conn_cpl, + [CPL_FW4_ACK] = chtls_wr_ack, +}; diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.h b/drivers/crypto/chelsio/chtls/chtls_cm.h new file mode 100644 index 000000000..ef7261072 --- /dev/null +++ b/drivers/crypto/chelsio/chtls/chtls_cm.h @@ -0,0 +1,221 @@ +/* + * Copyright (c) 2018 Chelsio Communications, Inc. + * + * 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. + */ + +#ifndef __CHTLS_CM_H__ +#define __CHTLS_CM_H__ + +/* + * TCB settings + */ +/* 3:0 */ +#define TCB_ULP_TYPE_W 0 +#define TCB_ULP_TYPE_S 0 +#define TCB_ULP_TYPE_M 0xfULL +#define TCB_ULP_TYPE_V(x) ((x) << TCB_ULP_TYPE_S) + +/* 11:4 */ +#define TCB_ULP_RAW_W 0 +#define TCB_ULP_RAW_S 4 +#define TCB_ULP_RAW_M 0xffULL +#define TCB_ULP_RAW_V(x) ((x) << TCB_ULP_RAW_S) + +#define TF_TLS_KEY_SIZE_S 7 +#define TF_TLS_KEY_SIZE_V(x) ((x) << TF_TLS_KEY_SIZE_S) + +#define TF_TLS_CONTROL_S 2 +#define TF_TLS_CONTROL_V(x) ((x) << TF_TLS_CONTROL_S) + +#define TF_TLS_ACTIVE_S 1 +#define TF_TLS_ACTIVE_V(x) ((x) << TF_TLS_ACTIVE_S) + +#define TF_TLS_ENABLE_S 0 +#define TF_TLS_ENABLE_V(x) ((x) << TF_TLS_ENABLE_S) + +#define TF_RX_QUIESCE_S 15 +#define TF_RX_QUIESCE_V(x) ((x) << TF_RX_QUIESCE_S) + +/* + * Max receive window supported by HW in bytes. Only a small part of it can + * be set through option0, the rest needs to be set through RX_DATA_ACK. + */ +#define MAX_RCV_WND ((1U << 27) - 1) +#define MAX_MSS 65536 + +/* + * Min receive window. We want it to be large enough to accommodate receive + * coalescing, handle jumbo frames, and not trigger sender SWS avoidance. + */ +#define MIN_RCV_WND (24 * 1024U) +#define LOOPBACK(x) (((x) & htonl(0xff000000)) == htonl(0x7f000000)) + +/* for TX: a skb must have a headroom of at least TX_HEADER_LEN bytes */ +#define TX_HEADER_LEN \ + (sizeof(struct fw_ofld_tx_data_wr) + sizeof(struct sge_opaque_hdr)) +#define TX_TLSHDR_LEN \ + (sizeof(struct fw_tlstx_data_wr) + sizeof(struct cpl_tx_tls_sfo) + \ + sizeof(struct sge_opaque_hdr)) +#define TXDATA_SKB_LEN 128 + +enum { + CPL_TX_TLS_SFO_TYPE_CCS, + CPL_TX_TLS_SFO_TYPE_ALERT, + CPL_TX_TLS_SFO_TYPE_HANDSHAKE, + CPL_TX_TLS_SFO_TYPE_DATA, + CPL_TX_TLS_SFO_TYPE_HEARTBEAT, +}; + +enum { + TLS_HDR_TYPE_CCS = 20, + TLS_HDR_TYPE_ALERT, + TLS_HDR_TYPE_HANDSHAKE, + TLS_HDR_TYPE_RECORD, + TLS_HDR_TYPE_HEARTBEAT, +}; + +typedef void (*defer_handler_t)(struct chtls_dev *dev, struct sk_buff *skb); +extern struct request_sock_ops chtls_rsk_ops; + +struct deferred_skb_cb { + defer_handler_t handler; + struct chtls_dev *dev; +}; + +#define DEFERRED_SKB_CB(skb) ((struct deferred_skb_cb *)(skb)->cb) +#define failover_flowc_wr_len offsetof(struct fw_flowc_wr, mnemval[3]) +#define WR_SKB_CB(skb) ((struct wr_skb_cb *)(skb)->cb) +#define ACCEPT_QUEUE(sk) (&inet_csk(sk)->icsk_accept_queue.rskq_accept_head) + +#define SND_WSCALE(tp) ((tp)->rx_opt.snd_wscale) +#define RCV_WSCALE(tp) ((tp)->rx_opt.rcv_wscale) +#define USER_MSS(tp) ((tp)->rx_opt.user_mss) +#define TS_RECENT_STAMP(tp) ((tp)->rx_opt.ts_recent_stamp) +#define WSCALE_OK(tp) ((tp)->rx_opt.wscale_ok) +#define TSTAMP_OK(tp) ((tp)->rx_opt.tstamp_ok) +#define SACK_OK(tp) ((tp)->rx_opt.sack_ok) +#define INC_ORPHAN_COUNT(sk) percpu_counter_inc((sk)->sk_prot->orphan_count) + +/* TLS SKB */ +#define skb_ulp_tls_inline(skb) (ULP_SKB_CB(skb)->ulp.tls.ofld) +#define skb_ulp_tls_iv_imm(skb) (ULP_SKB_CB(skb)->ulp.tls.iv) + +void chtls_defer_reply(struct sk_buff *skb, struct chtls_dev *dev, + defer_handler_t handler); + +/* + * Returns true if the socket is in one of the supplied states. + */ +static inline unsigned int sk_in_state(const struct sock *sk, + unsigned int states) +{ + return states & (1 << sk->sk_state); +} + +static void chtls_rsk_destructor(struct request_sock *req) +{ + /* do nothing */ +} + +static inline void chtls_init_rsk_ops(struct proto *chtls_tcp_prot, + struct request_sock_ops *chtls_tcp_ops, + struct proto *tcp_prot, int family) +{ + memset(chtls_tcp_ops, 0, sizeof(*chtls_tcp_ops)); + chtls_tcp_ops->family = family; + chtls_tcp_ops->obj_size = sizeof(struct tcp_request_sock); + chtls_tcp_ops->destructor = chtls_rsk_destructor; + chtls_tcp_ops->slab = tcp_prot->rsk_prot->slab; + chtls_tcp_prot->rsk_prot = chtls_tcp_ops; +} + +static inline void chtls_reqsk_free(struct request_sock *req) +{ + if (req->rsk_listener) + sock_put(req->rsk_listener); + kmem_cache_free(req->rsk_ops->slab, req); +} + +#define DECLARE_TASK_FUNC(task, task_param) \ + static void task(struct work_struct *task_param) + +static inline void sk_wakeup_sleepers(struct sock *sk, bool interruptable) +{ + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (skwq_has_sleeper(wq)) { + if (interruptable) + wake_up_interruptible(sk_sleep(sk)); + else + wake_up_all(sk_sleep(sk)); + } + rcu_read_unlock(); +} + +static inline void chtls_set_req_port(struct request_sock *oreq, + __be16 source, __be16 dest) +{ + inet_rsk(oreq)->ir_rmt_port = source; + inet_rsk(oreq)->ir_num = ntohs(dest); +} + +static inline void chtls_set_req_addr(struct request_sock *oreq, + __be32 local_ip, __be32 peer_ip) +{ + inet_rsk(oreq)->ir_loc_addr = local_ip; + inet_rsk(oreq)->ir_rmt_addr = peer_ip; +} + +static inline void chtls_free_skb(struct sock *sk, struct sk_buff *skb) +{ + skb_dst_set(skb, NULL); + __skb_unlink(skb, &sk->sk_receive_queue); + __kfree_skb(skb); +} + +static inline void chtls_kfree_skb(struct sock *sk, struct sk_buff *skb) +{ + skb_dst_set(skb, NULL); + __skb_unlink(skb, &sk->sk_receive_queue); + kfree_skb(skb); +} + +static inline void chtls_reset_wr_list(struct chtls_sock *csk) +{ + csk->wr_skb_head = NULL; + csk->wr_skb_tail = NULL; +} + +static inline void enqueue_wr(struct chtls_sock *csk, struct sk_buff *skb) +{ + WR_SKB_CB(skb)->next_wr = NULL; + + skb_get(skb); + + if (!csk->wr_skb_head) + csk->wr_skb_head = skb; + else + WR_SKB_CB(csk->wr_skb_tail)->next_wr = skb; + csk->wr_skb_tail = skb; +} + +static inline struct sk_buff *dequeue_wr(struct sock *sk) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct sk_buff *skb = NULL; + + skb = csk->wr_skb_head; + + if (likely(skb)) { + /* Don't bother clearing the tail */ + csk->wr_skb_head = WR_SKB_CB(skb)->next_wr; + WR_SKB_CB(skb)->next_wr = NULL; + } + return skb; +} +#endif diff --git a/drivers/crypto/chelsio/chtls/chtls_hw.c b/drivers/crypto/chelsio/chtls/chtls_hw.c new file mode 100644 index 000000000..7ea9dcfd7 --- /dev/null +++ b/drivers/crypto/chelsio/chtls/chtls_hw.c @@ -0,0 +1,415 @@ +/* + * Copyright (c) 2018 Chelsio Communications, Inc. + * + * 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. + * + * Written by: Atul Gupta (atul.gupta@chelsio.com) + */ + +#include <linux/module.h> +#include <linux/list.h> +#include <linux/workqueue.h> +#include <linux/skbuff.h> +#include <linux/timer.h> +#include <linux/notifier.h> +#include <linux/inetdevice.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/tls.h> +#include <net/tls.h> + +#include "chtls.h" +#include "chtls_cm.h" + +static void __set_tcb_field_direct(struct chtls_sock *csk, + struct cpl_set_tcb_field *req, u16 word, + u64 mask, u64 val, u8 cookie, int no_reply) +{ + struct ulptx_idata *sc; + + INIT_TP_WR_CPL(req, CPL_SET_TCB_FIELD, csk->tid); + req->wr.wr_mid |= htonl(FW_WR_FLOWID_V(csk->tid)); + req->reply_ctrl = htons(NO_REPLY_V(no_reply) | + QUEUENO_V(csk->rss_qid)); + req->word_cookie = htons(TCB_WORD_V(word) | TCB_COOKIE_V(cookie)); + req->mask = cpu_to_be64(mask); + req->val = cpu_to_be64(val); + sc = (struct ulptx_idata *)(req + 1); + sc->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_NOOP)); + sc->len = htonl(0); +} + +static void __set_tcb_field(struct sock *sk, struct sk_buff *skb, u16 word, + u64 mask, u64 val, u8 cookie, int no_reply) +{ + struct cpl_set_tcb_field *req; + struct chtls_sock *csk; + struct ulptx_idata *sc; + unsigned int wrlen; + + wrlen = roundup(sizeof(*req) + sizeof(*sc), 16); + csk = rcu_dereference_sk_user_data(sk); + + req = (struct cpl_set_tcb_field *)__skb_put(skb, wrlen); + __set_tcb_field_direct(csk, req, word, mask, val, cookie, no_reply); + set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->port_id); +} + +/* + * Send control message to HW, message go as immediate data and packet + * is freed immediately. + */ +static int chtls_set_tcb_field(struct sock *sk, u16 word, u64 mask, u64 val) +{ + struct cpl_set_tcb_field *req; + unsigned int credits_needed; + struct chtls_sock *csk; + struct ulptx_idata *sc; + struct sk_buff *skb; + unsigned int wrlen; + int ret; + + wrlen = roundup(sizeof(*req) + sizeof(*sc), 16); + + skb = alloc_skb(wrlen, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + credits_needed = DIV_ROUND_UP(wrlen, 16); + csk = rcu_dereference_sk_user_data(sk); + + __set_tcb_field(sk, skb, word, mask, val, 0, 1); + skb_set_queue_mapping(skb, (csk->txq_idx << 1) | CPL_PRIORITY_DATA); + csk->wr_credits -= credits_needed; + csk->wr_unacked += credits_needed; + enqueue_wr(csk, skb); + ret = cxgb4_ofld_send(csk->egress_dev, skb); + if (ret < 0) + kfree_skb(skb); + return ret < 0 ? ret : 0; +} + +/* + * Set one of the t_flags bits in the TCB. + */ +int chtls_set_tcb_tflag(struct sock *sk, unsigned int bit_pos, int val) +{ + return chtls_set_tcb_field(sk, 1, 1ULL << bit_pos, + (u64)val << bit_pos); +} + +static int chtls_set_tcb_keyid(struct sock *sk, int keyid) +{ + return chtls_set_tcb_field(sk, 31, 0xFFFFFFFFULL, keyid); +} + +static int chtls_set_tcb_seqno(struct sock *sk) +{ + return chtls_set_tcb_field(sk, 28, ~0ULL, 0); +} + +static int chtls_set_tcb_quiesce(struct sock *sk, int val) +{ + return chtls_set_tcb_field(sk, 1, (1ULL << TF_RX_QUIESCE_S), + TF_RX_QUIESCE_V(val)); +} + +/* TLS Key bitmap processing */ +int chtls_init_kmap(struct chtls_dev *cdev, struct cxgb4_lld_info *lldi) +{ + unsigned int num_key_ctx, bsize; + int ksize; + + num_key_ctx = (lldi->vr->key.size / TLS_KEY_CONTEXT_SZ); + bsize = BITS_TO_LONGS(num_key_ctx); + + cdev->kmap.size = num_key_ctx; + cdev->kmap.available = bsize; + ksize = sizeof(*cdev->kmap.addr) * bsize; + cdev->kmap.addr = kvzalloc(ksize, GFP_KERNEL); + if (!cdev->kmap.addr) + return -ENOMEM; + + cdev->kmap.start = lldi->vr->key.start; + spin_lock_init(&cdev->kmap.lock); + return 0; +} + +static int get_new_keyid(struct chtls_sock *csk, u32 optname) +{ + struct net_device *dev = csk->egress_dev; + struct chtls_dev *cdev = csk->cdev; + struct chtls_hws *hws; + struct adapter *adap; + int keyid; + + adap = netdev2adap(dev); + hws = &csk->tlshws; + + spin_lock_bh(&cdev->kmap.lock); + keyid = find_first_zero_bit(cdev->kmap.addr, cdev->kmap.size); + if (keyid < cdev->kmap.size) { + __set_bit(keyid, cdev->kmap.addr); + if (optname == TLS_RX) + hws->rxkey = keyid; + else + hws->txkey = keyid; + atomic_inc(&adap->chcr_stats.tls_key); + } else { + keyid = -1; + } + spin_unlock_bh(&cdev->kmap.lock); + return keyid; +} + +void free_tls_keyid(struct sock *sk) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct net_device *dev = csk->egress_dev; + struct chtls_dev *cdev = csk->cdev; + struct chtls_hws *hws; + struct adapter *adap; + + if (!cdev->kmap.addr) + return; + + adap = netdev2adap(dev); + hws = &csk->tlshws; + + spin_lock_bh(&cdev->kmap.lock); + if (hws->rxkey >= 0) { + __clear_bit(hws->rxkey, cdev->kmap.addr); + atomic_dec(&adap->chcr_stats.tls_key); + hws->rxkey = -1; + } + if (hws->txkey >= 0) { + __clear_bit(hws->txkey, cdev->kmap.addr); + atomic_dec(&adap->chcr_stats.tls_key); + hws->txkey = -1; + } + spin_unlock_bh(&cdev->kmap.lock); +} + +unsigned int keyid_to_addr(int start_addr, int keyid) +{ + return (start_addr + (keyid * TLS_KEY_CONTEXT_SZ)) >> 5; +} + +static void chtls_rxkey_ivauth(struct _key_ctx *kctx) +{ + kctx->iv_to_auth = cpu_to_be64(KEYCTX_TX_WR_IV_V(6ULL) | + KEYCTX_TX_WR_AAD_V(1ULL) | + KEYCTX_TX_WR_AADST_V(5ULL) | + KEYCTX_TX_WR_CIPHER_V(14ULL) | + KEYCTX_TX_WR_CIPHERST_V(0ULL) | + KEYCTX_TX_WR_AUTH_V(14ULL) | + KEYCTX_TX_WR_AUTHST_V(16ULL) | + KEYCTX_TX_WR_AUTHIN_V(16ULL)); +} + +static int chtls_key_info(struct chtls_sock *csk, + struct _key_ctx *kctx, + u32 keylen, u32 optname) +{ + unsigned char key[AES_KEYSIZE_128]; + struct tls12_crypto_info_aes_gcm_128 *gcm_ctx; + unsigned char ghash_h[AEAD_H_SIZE]; + struct crypto_cipher *cipher; + int ck_size, key_ctx_size; + int ret; + + gcm_ctx = (struct tls12_crypto_info_aes_gcm_128 *) + &csk->tlshws.crypto_info; + + key_ctx_size = sizeof(struct _key_ctx) + + roundup(keylen, 16) + AEAD_H_SIZE; + + if (keylen == AES_KEYSIZE_128) { + ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128; + } else { + pr_err("GCM: Invalid key length %d\n", keylen); + return -EINVAL; + } + memcpy(key, gcm_ctx->key, keylen); + + /* Calculate the H = CIPH(K, 0 repeated 16 times). + * It will go in key context + */ + cipher = crypto_alloc_cipher("aes", 0, 0); + if (IS_ERR(cipher)) { + ret = -ENOMEM; + goto out; + } + + ret = crypto_cipher_setkey(cipher, key, keylen); + if (ret) + goto out1; + + memset(ghash_h, 0, AEAD_H_SIZE); + crypto_cipher_encrypt_one(cipher, ghash_h, ghash_h); + csk->tlshws.keylen = key_ctx_size; + + /* Copy the Key context */ + if (optname == TLS_RX) { + int key_ctx; + + key_ctx = ((key_ctx_size >> 4) << 3); + kctx->ctx_hdr = FILL_KEY_CRX_HDR(ck_size, + CHCR_KEYCTX_MAC_KEY_SIZE_128, + 0, 0, key_ctx); + chtls_rxkey_ivauth(kctx); + } else { + kctx->ctx_hdr = FILL_KEY_CTX_HDR(ck_size, + CHCR_KEYCTX_MAC_KEY_SIZE_128, + 0, 0, key_ctx_size >> 4); + } + + memcpy(kctx->salt, gcm_ctx->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + memcpy(kctx->key, gcm_ctx->key, keylen); + memcpy(kctx->key + keylen, ghash_h, AEAD_H_SIZE); + /* erase key info from driver */ + memset(gcm_ctx->key, 0, keylen); + +out1: + crypto_free_cipher(cipher); +out: + return ret; +} + +static void chtls_set_scmd(struct chtls_sock *csk) +{ + struct chtls_hws *hws = &csk->tlshws; + + hws->scmd.seqno_numivs = + SCMD_SEQ_NO_CTRL_V(3) | + SCMD_PROTO_VERSION_V(0) | + SCMD_ENC_DEC_CTRL_V(0) | + SCMD_CIPH_AUTH_SEQ_CTRL_V(1) | + SCMD_CIPH_MODE_V(2) | + SCMD_AUTH_MODE_V(4) | + SCMD_HMAC_CTRL_V(0) | + SCMD_IV_SIZE_V(4) | + SCMD_NUM_IVS_V(1); + + hws->scmd.ivgen_hdrlen = + SCMD_IV_GEN_CTRL_V(1) | + SCMD_KEY_CTX_INLINE_V(0) | + SCMD_TLS_FRAG_ENABLE_V(1); +} + +int chtls_setkey(struct chtls_sock *csk, u32 keylen, u32 optname) +{ + struct tls_key_req *kwr; + struct chtls_dev *cdev; + struct _key_ctx *kctx; + int wrlen, klen, len; + struct sk_buff *skb; + struct sock *sk; + int keyid; + int kaddr; + int ret; + + cdev = csk->cdev; + sk = csk->sk; + + klen = roundup((keylen + AEAD_H_SIZE) + sizeof(*kctx), 32); + wrlen = roundup(sizeof(*kwr), 16); + len = klen + wrlen; + + /* Flush out-standing data before new key takes effect */ + if (optname == TLS_TX) { + lock_sock(sk); + if (skb_queue_len(&csk->txq)) + chtls_push_frames(csk, 0); + release_sock(sk); + } + + skb = alloc_skb(len, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + keyid = get_new_keyid(csk, optname); + if (keyid < 0) { + ret = -ENOSPC; + goto out_nokey; + } + + kaddr = keyid_to_addr(cdev->kmap.start, keyid); + kwr = (struct tls_key_req *)__skb_put_zero(skb, len); + kwr->wr.op_to_compl = + cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR) | FW_WR_COMPL_F | + FW_WR_ATOMIC_V(1U)); + kwr->wr.flowid_len16 = + cpu_to_be32(FW_WR_LEN16_V(DIV_ROUND_UP(len, 16) | + FW_WR_FLOWID_V(csk->tid))); + kwr->wr.protocol = 0; + kwr->wr.mfs = htons(TLS_MFS); + kwr->wr.reneg_to_write_rx = optname; + + /* ulptx command */ + kwr->req.cmd = cpu_to_be32(ULPTX_CMD_V(ULP_TX_MEM_WRITE) | + T5_ULP_MEMIO_ORDER_V(1) | + T5_ULP_MEMIO_IMM_V(1)); + kwr->req.len16 = cpu_to_be32((csk->tid << 8) | + DIV_ROUND_UP(len - sizeof(kwr->wr), 16)); + kwr->req.dlen = cpu_to_be32(ULP_MEMIO_DATA_LEN_V(klen >> 5)); + kwr->req.lock_addr = cpu_to_be32(ULP_MEMIO_ADDR_V(kaddr)); + + /* sub command */ + kwr->sc_imm.cmd_more = cpu_to_be32(ULPTX_CMD_V(ULP_TX_SC_IMM)); + kwr->sc_imm.len = cpu_to_be32(klen); + + lock_sock(sk); + /* key info */ + kctx = (struct _key_ctx *)(kwr + 1); + ret = chtls_key_info(csk, kctx, keylen, optname); + if (ret) + goto out_notcb; + + if (unlikely(csk_flag(sk, CSK_ABORT_SHUTDOWN))) + goto out_notcb; + + set_wr_txq(skb, CPL_PRIORITY_DATA, csk->tlshws.txqid); + csk->wr_credits -= DIV_ROUND_UP(len, 16); + csk->wr_unacked += DIV_ROUND_UP(len, 16); + enqueue_wr(csk, skb); + cxgb4_ofld_send(csk->egress_dev, skb); + skb = NULL; + + chtls_set_scmd(csk); + /* Clear quiesce for Rx key */ + if (optname == TLS_RX) { + ret = chtls_set_tcb_keyid(sk, keyid); + if (ret) + goto out_notcb; + ret = chtls_set_tcb_field(sk, 0, + TCB_ULP_RAW_V(TCB_ULP_RAW_M), + TCB_ULP_RAW_V((TF_TLS_KEY_SIZE_V(1) | + TF_TLS_CONTROL_V(1) | + TF_TLS_ACTIVE_V(1) | + TF_TLS_ENABLE_V(1)))); + if (ret) + goto out_notcb; + ret = chtls_set_tcb_seqno(sk); + if (ret) + goto out_notcb; + ret = chtls_set_tcb_quiesce(sk, 0); + if (ret) + goto out_notcb; + csk->tlshws.rxkey = keyid; + } else { + csk->tlshws.tx_seq_no = 0; + csk->tlshws.txkey = keyid; + } + + release_sock(sk); + return ret; +out_notcb: + release_sock(sk); + free_tls_keyid(sk); +out_nokey: + kfree_skb(skb); + return ret; +} diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c new file mode 100644 index 000000000..f9874da23 --- /dev/null +++ b/drivers/crypto/chelsio/chtls/chtls_io.c @@ -0,0 +1,1879 @@ +/* + * Copyright (c) 2018 Chelsio Communications, Inc. + * + * 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. + * + * Written by: Atul Gupta (atul.gupta@chelsio.com) + */ + +#include <linux/module.h> +#include <linux/list.h> +#include <linux/workqueue.h> +#include <linux/skbuff.h> +#include <linux/timer.h> +#include <linux/notifier.h> +#include <linux/inetdevice.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/sched/signal.h> +#include <net/tcp.h> +#include <net/busy_poll.h> +#include <crypto/aes.h> + +#include "chtls.h" +#include "chtls_cm.h" + +static bool is_tls_tx(struct chtls_sock *csk) +{ + return csk->tlshws.txkey >= 0; +} + +static bool is_tls_rx(struct chtls_sock *csk) +{ + return csk->tlshws.rxkey >= 0; +} + +static int data_sgl_len(const struct sk_buff *skb) +{ + unsigned int cnt; + + cnt = skb_shinfo(skb)->nr_frags; + return sgl_len(cnt) * 8; +} + +static int nos_ivs(struct sock *sk, unsigned int size) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + + return DIV_ROUND_UP(size, csk->tlshws.mfs); +} + +static int set_ivs_imm(struct sock *sk, const struct sk_buff *skb) +{ + int ivs_size = nos_ivs(sk, skb->len) * CIPHER_BLOCK_SIZE; + int hlen = TLS_WR_CPL_LEN + data_sgl_len(skb); + + if ((hlen + KEY_ON_MEM_SZ + ivs_size) < + MAX_IMM_OFLD_TX_DATA_WR_LEN) { + ULP_SKB_CB(skb)->ulp.tls.iv = 1; + return 1; + } + ULP_SKB_CB(skb)->ulp.tls.iv = 0; + return 0; +} + +static int max_ivs_size(struct sock *sk, int size) +{ + return nos_ivs(sk, size) * CIPHER_BLOCK_SIZE; +} + +static int ivs_size(struct sock *sk, const struct sk_buff *skb) +{ + return set_ivs_imm(sk, skb) ? (nos_ivs(sk, skb->len) * + CIPHER_BLOCK_SIZE) : 0; +} + +static int flowc_wr_credits(int nparams, int *flowclenp) +{ + int flowclen16, flowclen; + + flowclen = offsetof(struct fw_flowc_wr, mnemval[nparams]); + flowclen16 = DIV_ROUND_UP(flowclen, 16); + flowclen = flowclen16 * 16; + + if (flowclenp) + *flowclenp = flowclen; + + return flowclen16; +} + +static struct sk_buff *create_flowc_wr_skb(struct sock *sk, + struct fw_flowc_wr *flowc, + int flowclen) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct sk_buff *skb; + + skb = alloc_skb(flowclen, GFP_ATOMIC); + if (!skb) + return NULL; + + memcpy(__skb_put(skb, flowclen), flowc, flowclen); + skb_set_queue_mapping(skb, (csk->txq_idx << 1) | CPL_PRIORITY_DATA); + + return skb; +} + +static int send_flowc_wr(struct sock *sk, struct fw_flowc_wr *flowc, + int flowclen) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + int flowclen16; + int ret; + + flowclen16 = flowclen / 16; + + if (csk_flag(sk, CSK_TX_DATA_SENT)) { + skb = create_flowc_wr_skb(sk, flowc, flowclen); + if (!skb) + return -ENOMEM; + + skb_entail(sk, skb, + ULPCB_FLAG_NO_HDR | ULPCB_FLAG_NO_APPEND); + return 0; + } + + ret = cxgb4_immdata_send(csk->egress_dev, + csk->txq_idx, + flowc, flowclen); + if (!ret) + return flowclen16; + skb = create_flowc_wr_skb(sk, flowc, flowclen); + if (!skb) + return -ENOMEM; + send_or_defer(sk, tp, skb, 0); + return flowclen16; +} + +static u8 tcp_state_to_flowc_state(u8 state) +{ + switch (state) { + case TCP_ESTABLISHED: + return FW_FLOWC_MNEM_TCPSTATE_ESTABLISHED; + case TCP_CLOSE_WAIT: + return FW_FLOWC_MNEM_TCPSTATE_CLOSEWAIT; + case TCP_FIN_WAIT1: + return FW_FLOWC_MNEM_TCPSTATE_FINWAIT1; + case TCP_CLOSING: + return FW_FLOWC_MNEM_TCPSTATE_CLOSING; + case TCP_LAST_ACK: + return FW_FLOWC_MNEM_TCPSTATE_LASTACK; + case TCP_FIN_WAIT2: + return FW_FLOWC_MNEM_TCPSTATE_FINWAIT2; + } + + return FW_FLOWC_MNEM_TCPSTATE_ESTABLISHED; +} + +int send_tx_flowc_wr(struct sock *sk, int compl, + u32 snd_nxt, u32 rcv_nxt) +{ + struct flowc_packed { + struct fw_flowc_wr fc; + struct fw_flowc_mnemval mnemval[FW_FLOWC_MNEM_MAX]; + } __packed sflowc; + int nparams, paramidx, flowclen16, flowclen; + struct fw_flowc_wr *flowc; + struct chtls_sock *csk; + struct tcp_sock *tp; + + csk = rcu_dereference_sk_user_data(sk); + tp = tcp_sk(sk); + memset(&sflowc, 0, sizeof(sflowc)); + flowc = &sflowc.fc; + +#define FLOWC_PARAM(__m, __v) \ + do { \ + flowc->mnemval[paramidx].mnemonic = FW_FLOWC_MNEM_##__m; \ + flowc->mnemval[paramidx].val = cpu_to_be32(__v); \ + paramidx++; \ + } while (0) + + paramidx = 0; + + FLOWC_PARAM(PFNVFN, FW_PFVF_CMD_PFN_V(csk->cdev->lldi->pf)); + FLOWC_PARAM(CH, csk->tx_chan); + FLOWC_PARAM(PORT, csk->tx_chan); + FLOWC_PARAM(IQID, csk->rss_qid); + FLOWC_PARAM(SNDNXT, tp->snd_nxt); + FLOWC_PARAM(RCVNXT, tp->rcv_nxt); + FLOWC_PARAM(SNDBUF, csk->sndbuf); + FLOWC_PARAM(MSS, tp->mss_cache); + FLOWC_PARAM(TCPSTATE, tcp_state_to_flowc_state(sk->sk_state)); + + if (SND_WSCALE(tp)) + FLOWC_PARAM(RCV_SCALE, SND_WSCALE(tp)); + + if (csk->ulp_mode == ULP_MODE_TLS) + FLOWC_PARAM(ULD_MODE, ULP_MODE_TLS); + + if (csk->tlshws.fcplenmax) + FLOWC_PARAM(TXDATAPLEN_MAX, csk->tlshws.fcplenmax); + + nparams = paramidx; +#undef FLOWC_PARAM + + flowclen16 = flowc_wr_credits(nparams, &flowclen); + flowc->op_to_nparams = + cpu_to_be32(FW_WR_OP_V(FW_FLOWC_WR) | + FW_WR_COMPL_V(compl) | + FW_FLOWC_WR_NPARAMS_V(nparams)); + flowc->flowid_len16 = cpu_to_be32(FW_WR_LEN16_V(flowclen16) | + FW_WR_FLOWID_V(csk->tid)); + + return send_flowc_wr(sk, flowc, flowclen); +} + +/* Copy IVs to WR */ +static int tls_copy_ivs(struct sock *sk, struct sk_buff *skb) + +{ + struct chtls_sock *csk; + unsigned char *iv_loc; + struct chtls_hws *hws; + unsigned char *ivs; + u16 number_of_ivs; + struct page *page; + int err = 0; + + csk = rcu_dereference_sk_user_data(sk); + hws = &csk->tlshws; + number_of_ivs = nos_ivs(sk, skb->len); + + if (number_of_ivs > MAX_IVS_PAGE) { + pr_warn("MAX IVs in PAGE exceeded %d\n", number_of_ivs); + return -ENOMEM; + } + + /* generate the IVs */ + ivs = kmalloc_array(CIPHER_BLOCK_SIZE, number_of_ivs, GFP_ATOMIC); + if (!ivs) + return -ENOMEM; + get_random_bytes(ivs, number_of_ivs * CIPHER_BLOCK_SIZE); + + if (skb_ulp_tls_iv_imm(skb)) { + /* send the IVs as immediate data in the WR */ + iv_loc = (unsigned char *)__skb_push(skb, number_of_ivs * + CIPHER_BLOCK_SIZE); + if (iv_loc) + memcpy(iv_loc, ivs, number_of_ivs * CIPHER_BLOCK_SIZE); + + hws->ivsize = number_of_ivs * CIPHER_BLOCK_SIZE; + } else { + /* Send the IVs as sgls */ + /* Already accounted IV DSGL for credits */ + skb_shinfo(skb)->nr_frags--; + page = alloc_pages(sk->sk_allocation | __GFP_COMP, 0); + if (!page) { + pr_info("%s : Page allocation for IVs failed\n", + __func__); + err = -ENOMEM; + goto out; + } + memcpy(page_address(page), ivs, number_of_ivs * + CIPHER_BLOCK_SIZE); + skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, page, 0, + number_of_ivs * CIPHER_BLOCK_SIZE); + hws->ivsize = 0; + } +out: + kfree(ivs); + return err; +} + +/* Copy Key to WR */ +static void tls_copy_tx_key(struct sock *sk, struct sk_buff *skb) +{ + struct ulptx_sc_memrd *sc_memrd; + struct chtls_sock *csk; + struct chtls_dev *cdev; + struct ulptx_idata *sc; + struct chtls_hws *hws; + u32 immdlen; + int kaddr; + + csk = rcu_dereference_sk_user_data(sk); + hws = &csk->tlshws; + cdev = csk->cdev; + + immdlen = sizeof(*sc) + sizeof(*sc_memrd); + kaddr = keyid_to_addr(cdev->kmap.start, hws->txkey); + sc = (struct ulptx_idata *)__skb_push(skb, immdlen); + if (sc) { + sc->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_NOOP)); + sc->len = htonl(0); + sc_memrd = (struct ulptx_sc_memrd *)(sc + 1); + sc_memrd->cmd_to_len = + htonl(ULPTX_CMD_V(ULP_TX_SC_MEMRD) | + ULP_TX_SC_MORE_V(1) | + ULPTX_LEN16_V(hws->keylen >> 4)); + sc_memrd->addr = htonl(kaddr); + } +} + +static u64 tlstx_incr_seqnum(struct chtls_hws *hws) +{ + return hws->tx_seq_no++; +} + +static bool is_sg_request(const struct sk_buff *skb) +{ + return skb->peeked || + (skb->len > MAX_IMM_ULPTX_WR_LEN); +} + +/* + * Returns true if an sk_buff carries urgent data. + */ +static bool skb_urgent(struct sk_buff *skb) +{ + return ULP_SKB_CB(skb)->flags & ULPCB_FLAG_URG; +} + +/* TLS content type for CPL SFO */ +static unsigned char tls_content_type(unsigned char content_type) +{ + switch (content_type) { + case TLS_HDR_TYPE_CCS: + return CPL_TX_TLS_SFO_TYPE_CCS; + case TLS_HDR_TYPE_ALERT: + return CPL_TX_TLS_SFO_TYPE_ALERT; + case TLS_HDR_TYPE_HANDSHAKE: + return CPL_TX_TLS_SFO_TYPE_HANDSHAKE; + case TLS_HDR_TYPE_HEARTBEAT: + return CPL_TX_TLS_SFO_TYPE_HEARTBEAT; + } + return CPL_TX_TLS_SFO_TYPE_DATA; +} + +static void tls_tx_data_wr(struct sock *sk, struct sk_buff *skb, + int dlen, int tls_immd, u32 credits, + int expn, int pdus) +{ + struct fw_tlstx_data_wr *req_wr; + struct cpl_tx_tls_sfo *req_cpl; + unsigned int wr_ulp_mode_force; + struct tls_scmd *updated_scmd; + unsigned char data_type; + struct chtls_sock *csk; + struct net_device *dev; + struct chtls_hws *hws; + struct tls_scmd *scmd; + struct adapter *adap; + unsigned char *req; + int immd_len; + int iv_imm; + int len; + + csk = rcu_dereference_sk_user_data(sk); + iv_imm = skb_ulp_tls_iv_imm(skb); + dev = csk->egress_dev; + adap = netdev2adap(dev); + hws = &csk->tlshws; + scmd = &hws->scmd; + len = dlen + expn; + + dlen = (dlen < hws->mfs) ? dlen : hws->mfs; + atomic_inc(&adap->chcr_stats.tls_pdu_tx); + + updated_scmd = scmd; + updated_scmd->seqno_numivs &= 0xffffff80; + updated_scmd->seqno_numivs |= SCMD_NUM_IVS_V(pdus); + hws->scmd = *updated_scmd; + + req = (unsigned char *)__skb_push(skb, sizeof(struct cpl_tx_tls_sfo)); + req_cpl = (struct cpl_tx_tls_sfo *)req; + req = (unsigned char *)__skb_push(skb, (sizeof(struct + fw_tlstx_data_wr))); + + req_wr = (struct fw_tlstx_data_wr *)req; + immd_len = (tls_immd ? dlen : 0); + req_wr->op_to_immdlen = + htonl(FW_WR_OP_V(FW_TLSTX_DATA_WR) | + FW_TLSTX_DATA_WR_COMPL_V(1) | + FW_TLSTX_DATA_WR_IMMDLEN_V(immd_len)); + req_wr->flowid_len16 = htonl(FW_TLSTX_DATA_WR_FLOWID_V(csk->tid) | + FW_TLSTX_DATA_WR_LEN16_V(credits)); + wr_ulp_mode_force = TX_ULP_MODE_V(ULP_MODE_TLS); + + if (is_sg_request(skb)) + wr_ulp_mode_force |= FW_OFLD_TX_DATA_WR_ALIGNPLD_F | + ((tcp_sk(sk)->nonagle & TCP_NAGLE_OFF) ? 0 : + FW_OFLD_TX_DATA_WR_SHOVE_F); + + req_wr->lsodisable_to_flags = + htonl(TX_ULP_MODE_V(ULP_MODE_TLS) | + FW_OFLD_TX_DATA_WR_URGENT_V(skb_urgent(skb)) | + T6_TX_FORCE_F | wr_ulp_mode_force | + TX_SHOVE_V((!csk_flag(sk, CSK_TX_MORE_DATA)) && + skb_queue_empty(&csk->txq))); + + req_wr->ctxloc_to_exp = + htonl(FW_TLSTX_DATA_WR_NUMIVS_V(pdus) | + FW_TLSTX_DATA_WR_EXP_V(expn) | + FW_TLSTX_DATA_WR_CTXLOC_V(CHTLS_KEY_CONTEXT_DDR) | + FW_TLSTX_DATA_WR_IVDSGL_V(!iv_imm) | + FW_TLSTX_DATA_WR_KEYSIZE_V(hws->keylen >> 4)); + + /* Fill in the length */ + req_wr->plen = htonl(len); + req_wr->mfs = htons(hws->mfs); + req_wr->adjustedplen_pkd = + htons(FW_TLSTX_DATA_WR_ADJUSTEDPLEN_V(hws->adjustlen)); + req_wr->expinplenmax_pkd = + htons(FW_TLSTX_DATA_WR_EXPINPLENMAX_V(hws->expansion)); + req_wr->pdusinplenmax_pkd = + FW_TLSTX_DATA_WR_PDUSINPLENMAX_V(hws->pdus); + req_wr->r10 = 0; + + data_type = tls_content_type(ULP_SKB_CB(skb)->ulp.tls.type); + req_cpl->op_to_seg_len = htonl(CPL_TX_TLS_SFO_OPCODE_V(CPL_TX_TLS_SFO) | + CPL_TX_TLS_SFO_DATA_TYPE_V(data_type) | + CPL_TX_TLS_SFO_CPL_LEN_V(2) | + CPL_TX_TLS_SFO_SEG_LEN_V(dlen)); + req_cpl->pld_len = htonl(len - expn); + + req_cpl->type_protover = htonl(CPL_TX_TLS_SFO_TYPE_V + ((data_type == CPL_TX_TLS_SFO_TYPE_HEARTBEAT) ? + TLS_HDR_TYPE_HEARTBEAT : 0) | + CPL_TX_TLS_SFO_PROTOVER_V(0)); + + /* create the s-command */ + req_cpl->r1_lo = 0; + req_cpl->seqno_numivs = cpu_to_be32(hws->scmd.seqno_numivs); + req_cpl->ivgen_hdrlen = cpu_to_be32(hws->scmd.ivgen_hdrlen); + req_cpl->scmd1 = cpu_to_be64(tlstx_incr_seqnum(hws)); +} + +/* + * Calculate the TLS data expansion size + */ +static int chtls_expansion_size(struct sock *sk, int data_len, + int fullpdu, + unsigned short *pducnt) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct chtls_hws *hws = &csk->tlshws; + struct tls_scmd *scmd = &hws->scmd; + int fragsize = hws->mfs; + int expnsize = 0; + int fragleft; + int fragcnt; + int expppdu; + + if (SCMD_CIPH_MODE_G(scmd->seqno_numivs) == + SCMD_CIPH_MODE_AES_GCM) { + expppdu = GCM_TAG_SIZE + AEAD_EXPLICIT_DATA_SIZE + + TLS_HEADER_LENGTH; + + if (fullpdu) { + *pducnt = data_len / (expppdu + fragsize); + if (*pducnt > 32) + *pducnt = 32; + else if (!*pducnt) + *pducnt = 1; + expnsize = (*pducnt) * expppdu; + return expnsize; + } + fragcnt = (data_len / fragsize); + expnsize = fragcnt * expppdu; + fragleft = data_len % fragsize; + if (fragleft > 0) + expnsize += expppdu; + } + return expnsize; +} + +/* WR with IV, KEY and CPL SFO added */ +static void make_tlstx_data_wr(struct sock *sk, struct sk_buff *skb, + int tls_tx_imm, int tls_len, u32 credits) +{ + unsigned short pdus_per_ulp = 0; + struct chtls_sock *csk; + struct chtls_hws *hws; + int expn_sz; + int pdus; + + csk = rcu_dereference_sk_user_data(sk); + hws = &csk->tlshws; + pdus = DIV_ROUND_UP(tls_len, hws->mfs); + expn_sz = chtls_expansion_size(sk, tls_len, 0, NULL); + if (!hws->compute) { + hws->expansion = chtls_expansion_size(sk, + hws->fcplenmax, + 1, &pdus_per_ulp); + hws->pdus = pdus_per_ulp; + hws->adjustlen = hws->pdus * + ((hws->expansion / hws->pdus) + hws->mfs); + hws->compute = 1; + } + if (tls_copy_ivs(sk, skb)) + return; + tls_copy_tx_key(sk, skb); + tls_tx_data_wr(sk, skb, tls_len, tls_tx_imm, credits, expn_sz, pdus); + hws->tx_seq_no += (pdus - 1); +} + +static void make_tx_data_wr(struct sock *sk, struct sk_buff *skb, + unsigned int immdlen, int len, + u32 credits, u32 compl) +{ + struct fw_ofld_tx_data_wr *req; + unsigned int wr_ulp_mode_force; + struct chtls_sock *csk; + unsigned int opcode; + + csk = rcu_dereference_sk_user_data(sk); + opcode = FW_OFLD_TX_DATA_WR; + + req = (struct fw_ofld_tx_data_wr *)__skb_push(skb, sizeof(*req)); + req->op_to_immdlen = htonl(WR_OP_V(opcode) | + FW_WR_COMPL_V(compl) | + FW_WR_IMMDLEN_V(immdlen)); + req->flowid_len16 = htonl(FW_WR_FLOWID_V(csk->tid) | + FW_WR_LEN16_V(credits)); + + wr_ulp_mode_force = TX_ULP_MODE_V(csk->ulp_mode); + if (is_sg_request(skb)) + wr_ulp_mode_force |= FW_OFLD_TX_DATA_WR_ALIGNPLD_F | + ((tcp_sk(sk)->nonagle & TCP_NAGLE_OFF) ? 0 : + FW_OFLD_TX_DATA_WR_SHOVE_F); + + req->tunnel_to_proxy = htonl(wr_ulp_mode_force | + FW_OFLD_TX_DATA_WR_URGENT_V(skb_urgent(skb)) | + FW_OFLD_TX_DATA_WR_SHOVE_V((!csk_flag + (sk, CSK_TX_MORE_DATA)) && + skb_queue_empty(&csk->txq))); + req->plen = htonl(len); +} + +static int chtls_wr_size(struct chtls_sock *csk, const struct sk_buff *skb, + bool size) +{ + int wr_size; + + wr_size = TLS_WR_CPL_LEN; + wr_size += KEY_ON_MEM_SZ; + wr_size += ivs_size(csk->sk, skb); + + if (size) + return wr_size; + + /* frags counted for IV dsgl */ + if (!skb_ulp_tls_iv_imm(skb)) + skb_shinfo(skb)->nr_frags++; + + return wr_size; +} + +static bool is_ofld_imm(struct chtls_sock *csk, const struct sk_buff *skb) +{ + int length = skb->len; + + if (skb->peeked || skb->len > MAX_IMM_ULPTX_WR_LEN) + return false; + + if (likely(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NEED_HDR)) { + /* Check TLS header len for Immediate */ + if (csk->ulp_mode == ULP_MODE_TLS && + skb_ulp_tls_inline(skb)) + length += chtls_wr_size(csk, skb, true); + else + length += sizeof(struct fw_ofld_tx_data_wr); + + return length <= MAX_IMM_OFLD_TX_DATA_WR_LEN; + } + return true; +} + +static unsigned int calc_tx_flits(const struct sk_buff *skb, + unsigned int immdlen) +{ + unsigned int flits, cnt; + + flits = immdlen / 8; /* headers */ + cnt = skb_shinfo(skb)->nr_frags; + if (skb_tail_pointer(skb) != skb_transport_header(skb)) + cnt++; + return flits + sgl_len(cnt); +} + +static void arp_failure_discard(void *handle, struct sk_buff *skb) +{ + kfree_skb(skb); +} + +int chtls_push_frames(struct chtls_sock *csk, int comp) +{ + struct chtls_hws *hws = &csk->tlshws; + struct tcp_sock *tp; + struct sk_buff *skb; + int total_size = 0; + struct sock *sk; + int wr_size; + + wr_size = sizeof(struct fw_ofld_tx_data_wr); + sk = csk->sk; + tp = tcp_sk(sk); + + if (unlikely(sk_in_state(sk, TCPF_SYN_SENT | TCPF_CLOSE))) + return 0; + + if (unlikely(csk_flag(sk, CSK_ABORT_SHUTDOWN))) + return 0; + + while (csk->wr_credits && (skb = skb_peek(&csk->txq)) && + (!(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_HOLD) || + skb_queue_len(&csk->txq) > 1)) { + unsigned int credit_len = skb->len; + unsigned int credits_needed; + unsigned int completion = 0; + int tls_len = skb->len;/* TLS data len before IV/key */ + unsigned int immdlen; + int len = skb->len; /* length [ulp bytes] inserted by hw */ + int flowclen16 = 0; + int tls_tx_imm = 0; + + immdlen = skb->len; + if (!is_ofld_imm(csk, skb)) { + immdlen = skb_transport_offset(skb); + if (skb_ulp_tls_inline(skb)) + wr_size = chtls_wr_size(csk, skb, false); + credit_len = 8 * calc_tx_flits(skb, immdlen); + } else { + if (skb_ulp_tls_inline(skb)) { + wr_size = chtls_wr_size(csk, skb, false); + tls_tx_imm = 1; + } + } + if (likely(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NEED_HDR)) + credit_len += wr_size; + credits_needed = DIV_ROUND_UP(credit_len, 16); + if (!csk_flag_nochk(csk, CSK_TX_DATA_SENT)) { + flowclen16 = send_tx_flowc_wr(sk, 1, tp->snd_nxt, + tp->rcv_nxt); + if (flowclen16 <= 0) + break; + csk->wr_credits -= flowclen16; + csk->wr_unacked += flowclen16; + csk->wr_nondata += flowclen16; + csk_set_flag(csk, CSK_TX_DATA_SENT); + } + + if (csk->wr_credits < credits_needed) { + if (skb_ulp_tls_inline(skb) && + !skb_ulp_tls_iv_imm(skb)) + skb_shinfo(skb)->nr_frags--; + break; + } + + __skb_unlink(skb, &csk->txq); + skb_set_queue_mapping(skb, (csk->txq_idx << 1) | + CPL_PRIORITY_DATA); + if (hws->ofld) + hws->txqid = (skb->queue_mapping >> 1); + skb->csum = (__force __wsum)(credits_needed + csk->wr_nondata); + csk->wr_credits -= credits_needed; + csk->wr_unacked += credits_needed; + csk->wr_nondata = 0; + enqueue_wr(csk, skb); + + if (likely(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NEED_HDR)) { + if ((comp && csk->wr_unacked == credits_needed) || + (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_COMPL) || + csk->wr_unacked >= csk->wr_max_credits / 2) { + completion = 1; + csk->wr_unacked = 0; + } + if (skb_ulp_tls_inline(skb)) + make_tlstx_data_wr(sk, skb, tls_tx_imm, + tls_len, credits_needed); + else + make_tx_data_wr(sk, skb, immdlen, len, + credits_needed, completion); + tp->snd_nxt += len; + tp->lsndtime = tcp_jiffies32; + if (completion) + ULP_SKB_CB(skb)->flags &= ~ULPCB_FLAG_NEED_HDR; + } else { + struct cpl_close_con_req *req = cplhdr(skb); + unsigned int cmd = CPL_OPCODE_G(ntohl + (OPCODE_TID(req))); + + if (cmd == CPL_CLOSE_CON_REQ) + csk_set_flag(csk, + CSK_CLOSE_CON_REQUESTED); + + if ((ULP_SKB_CB(skb)->flags & ULPCB_FLAG_COMPL) && + (csk->wr_unacked >= csk->wr_max_credits / 2)) { + req->wr.wr_hi |= htonl(FW_WR_COMPL_F); + csk->wr_unacked = 0; + } + } + total_size += skb->truesize; + if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_BARRIER) + csk_set_flag(csk, CSK_TX_WAIT_IDLE); + t4_set_arp_err_handler(skb, NULL, arp_failure_discard); + cxgb4_l2t_send(csk->egress_dev, skb, csk->l2t_entry); + } + sk->sk_wmem_queued -= total_size; + return total_size; +} + +static void mark_urg(struct tcp_sock *tp, int flags, + struct sk_buff *skb) +{ + if (unlikely(flags & MSG_OOB)) { + tp->snd_up = tp->write_seq; + ULP_SKB_CB(skb)->flags = ULPCB_FLAG_URG | + ULPCB_FLAG_BARRIER | + ULPCB_FLAG_NO_APPEND | + ULPCB_FLAG_NEED_HDR; + } +} + +/* + * Returns true if a connection should send more data to TCP engine + */ +static bool should_push(struct sock *sk) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct chtls_dev *cdev = csk->cdev; + struct tcp_sock *tp = tcp_sk(sk); + + /* + * If we've released our offload resources there's nothing to do ... + */ + if (!cdev) + return false; + + /* + * If there aren't any work requests in flight, or there isn't enough + * data in flight, or Nagle is off then send the current TX_DATA + * otherwise hold it and wait to accumulate more data. + */ + return csk->wr_credits == csk->wr_max_credits || + (tp->nonagle & TCP_NAGLE_OFF); +} + +/* + * Returns true if a TCP socket is corked. + */ +static bool corked(const struct tcp_sock *tp, int flags) +{ + return (flags & MSG_MORE) || (tp->nonagle & TCP_NAGLE_CORK); +} + +/* + * Returns true if a send should try to push new data. + */ +static bool send_should_push(struct sock *sk, int flags) +{ + return should_push(sk) && !corked(tcp_sk(sk), flags); +} + +void chtls_tcp_push(struct sock *sk, int flags) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + int qlen = skb_queue_len(&csk->txq); + + if (likely(qlen)) { + struct sk_buff *skb = skb_peek_tail(&csk->txq); + struct tcp_sock *tp = tcp_sk(sk); + + mark_urg(tp, flags, skb); + + if (!(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) && + corked(tp, flags)) { + ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_HOLD; + return; + } + + ULP_SKB_CB(skb)->flags &= ~ULPCB_FLAG_HOLD; + if (qlen == 1 && + ((ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) || + should_push(sk))) + chtls_push_frames(csk, 1); + } +} + +/* + * Calculate the size for a new send sk_buff. It's maximum size so we can + * pack lots of data into it, unless we plan to send it immediately, in which + * case we size it more tightly. + * + * Note: we don't bother compensating for MSS < PAGE_SIZE because it doesn't + * arise in normal cases and when it does we are just wasting memory. + */ +static int select_size(struct sock *sk, int io_len, int flags, int len) +{ + const int pgbreak = SKB_MAX_HEAD(len); + + /* + * If the data wouldn't fit in the main body anyway, put only the + * header in the main body so it can use immediate data and place all + * the payload in page fragments. + */ + if (io_len > pgbreak) + return 0; + + /* + * If we will be accumulating payload get a large main body. + */ + if (!send_should_push(sk, flags)) + return pgbreak; + + return io_len; +} + +void skb_entail(struct sock *sk, struct sk_buff *skb, int flags) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct tcp_sock *tp = tcp_sk(sk); + + ULP_SKB_CB(skb)->seq = tp->write_seq; + ULP_SKB_CB(skb)->flags = flags; + __skb_queue_tail(&csk->txq, skb); + sk->sk_wmem_queued += skb->truesize; + + if (TCP_PAGE(sk) && TCP_OFF(sk)) { + put_page(TCP_PAGE(sk)); + TCP_PAGE(sk) = NULL; + TCP_OFF(sk) = 0; + } +} + +static struct sk_buff *get_tx_skb(struct sock *sk, int size) +{ + struct sk_buff *skb; + + skb = alloc_skb(size + TX_HEADER_LEN, sk->sk_allocation); + if (likely(skb)) { + skb_reserve(skb, TX_HEADER_LEN); + skb_entail(sk, skb, ULPCB_FLAG_NEED_HDR); + skb_reset_transport_header(skb); + } + return skb; +} + +static struct sk_buff *get_record_skb(struct sock *sk, int size, bool zcopy) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct sk_buff *skb; + + skb = alloc_skb(((zcopy ? 0 : size) + TX_TLSHDR_LEN + + KEY_ON_MEM_SZ + max_ivs_size(sk, size)), + sk->sk_allocation); + if (likely(skb)) { + skb_reserve(skb, (TX_TLSHDR_LEN + + KEY_ON_MEM_SZ + max_ivs_size(sk, size))); + skb_entail(sk, skb, ULPCB_FLAG_NEED_HDR); + skb_reset_transport_header(skb); + ULP_SKB_CB(skb)->ulp.tls.ofld = 1; + ULP_SKB_CB(skb)->ulp.tls.type = csk->tlshws.type; + } + return skb; +} + +static void tx_skb_finalize(struct sk_buff *skb) +{ + struct ulp_skb_cb *cb = ULP_SKB_CB(skb); + + if (!(cb->flags & ULPCB_FLAG_NO_HDR)) + cb->flags = ULPCB_FLAG_NEED_HDR; + cb->flags |= ULPCB_FLAG_NO_APPEND; +} + +static void push_frames_if_head(struct sock *sk) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + + if (skb_queue_len(&csk->txq) == 1) + chtls_push_frames(csk, 1); +} + +static int chtls_skb_copy_to_page_nocache(struct sock *sk, + struct iov_iter *from, + struct sk_buff *skb, + struct page *page, + int off, int copy) +{ + int err; + + err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + + off, copy, skb->len); + if (err) + return err; + + skb->len += copy; + skb->data_len += copy; + skb->truesize += copy; + sk->sk_wmem_queued += copy; + return 0; +} + +/* Read TLS header to find content type and data length */ +static int tls_header_read(struct tls_hdr *thdr, struct iov_iter *from) +{ + if (copy_from_iter(thdr, sizeof(*thdr), from) != sizeof(*thdr)) + return -EFAULT; + return (__force int)cpu_to_be16(thdr->length); +} + +static bool csk_mem_free(struct chtls_dev *cdev, struct sock *sk) +{ + return (cdev->max_host_sndbuf - sk->sk_wmem_queued > 0); +} + +static int csk_wait_memory(struct chtls_dev *cdev, + struct sock *sk, long *timeo_p) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int sndbuf, err = 0; + long current_timeo; + long vm_wait = 0; + bool noblock; + + current_timeo = *timeo_p; + noblock = (*timeo_p ? false : true); + sndbuf = cdev->max_host_sndbuf; + if (csk_mem_free(cdev, sk)) { + current_timeo = (prandom_u32() % (HZ / 5)) + 2; + vm_wait = (prandom_u32() % (HZ / 5)) + 2; + } + + add_wait_queue(sk_sleep(sk), &wait); + while (1) { + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); + + if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + goto do_error; + if (!*timeo_p) { + if (noblock) + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + goto do_nonblock; + } + if (signal_pending(current)) + goto do_interrupted; + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); + if (csk_mem_free(cdev, sk) && !vm_wait) + break; + + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + sk->sk_write_pending++; + sk_wait_event(sk, ¤t_timeo, sk->sk_err || + (sk->sk_shutdown & SEND_SHUTDOWN) || + (csk_mem_free(cdev, sk) && !vm_wait), &wait); + sk->sk_write_pending--; + + if (vm_wait) { + vm_wait -= current_timeo; + current_timeo = *timeo_p; + if (current_timeo != MAX_SCHEDULE_TIMEOUT) { + current_timeo -= vm_wait; + if (current_timeo < 0) + current_timeo = 0; + } + vm_wait = 0; + } + *timeo_p = current_timeo; + } +do_rm_wq: + remove_wait_queue(sk_sleep(sk), &wait); + return err; +do_error: + err = -EPIPE; + goto do_rm_wq; +do_nonblock: + err = -EAGAIN; + goto do_rm_wq; +do_interrupted: + err = sock_intr_errno(*timeo_p); + goto do_rm_wq; +} + +int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct chtls_dev *cdev = csk->cdev; + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + int mss, flags, err; + int recordsz = 0; + int copied = 0; + int hdrlen = 0; + long timeo; + + lock_sock(sk); + flags = msg->msg_flags; + timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + + if (!sk_in_state(sk, TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { + err = sk_stream_wait_connect(sk, &timeo); + if (err) + goto out_err; + } + + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); + err = -EPIPE; + if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + goto out_err; + + mss = csk->mss; + csk_set_flag(csk, CSK_TX_MORE_DATA); + + while (msg_data_left(msg)) { + int copy = 0; + + skb = skb_peek_tail(&csk->txq); + if (skb) { + copy = mss - skb->len; + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + if (!csk_mem_free(cdev, sk)) + goto wait_for_sndbuf; + + if (is_tls_tx(csk) && !csk->tlshws.txleft) { + struct tls_hdr hdr; + + recordsz = tls_header_read(&hdr, &msg->msg_iter); + size -= TLS_HEADER_LENGTH; + hdrlen += TLS_HEADER_LENGTH; + csk->tlshws.txleft = recordsz; + csk->tlshws.type = hdr.type; + if (skb) + ULP_SKB_CB(skb)->ulp.tls.type = hdr.type; + } + + if (!skb || (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) || + copy <= 0) { +new_buf: + if (skb) { + tx_skb_finalize(skb); + push_frames_if_head(sk); + } + + if (is_tls_tx(csk)) { + skb = get_record_skb(sk, + select_size(sk, + recordsz, + flags, + TX_TLSHDR_LEN), + false); + } else { + skb = get_tx_skb(sk, + select_size(sk, size, flags, + TX_HEADER_LEN)); + } + if (unlikely(!skb)) + goto wait_for_memory; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + copy = mss; + } + if (copy > size) + copy = size; + + if (skb_tailroom(skb) > 0) { + copy = min(copy, skb_tailroom(skb)); + if (is_tls_tx(csk)) + copy = min_t(int, copy, csk->tlshws.txleft); + err = skb_add_data_nocache(sk, skb, + &msg->msg_iter, copy); + if (err) + goto do_fault; + } else { + int i = skb_shinfo(skb)->nr_frags; + struct page *page = TCP_PAGE(sk); + int pg_size = PAGE_SIZE; + int off = TCP_OFF(sk); + bool merge; + + if (!page) + goto wait_for_memory; + + pg_size <<= compound_order(page); + if (off < pg_size && + skb_can_coalesce(skb, i, page, off)) { + merge = 1; + goto copy; + } + merge = 0; + if (i == (is_tls_tx(csk) ? (MAX_SKB_FRAGS - 1) : + MAX_SKB_FRAGS)) + goto new_buf; + + if (page && off == pg_size) { + put_page(page); + TCP_PAGE(sk) = page = NULL; + pg_size = PAGE_SIZE; + } + + if (!page) { + gfp_t gfp = sk->sk_allocation; + int order = cdev->send_page_order; + + if (order) { + page = alloc_pages(gfp | __GFP_COMP | + __GFP_NOWARN | + __GFP_NORETRY, + order); + if (page) + pg_size <<= + compound_order(page); + } + if (!page) { + page = alloc_page(gfp); + pg_size = PAGE_SIZE; + } + if (!page) + goto wait_for_memory; + off = 0; + } +copy: + if (copy > pg_size - off) + copy = pg_size - off; + if (is_tls_tx(csk)) + copy = min_t(int, copy, csk->tlshws.txleft); + + err = chtls_skb_copy_to_page_nocache(sk, &msg->msg_iter, + skb, page, + off, copy); + if (unlikely(err)) { + if (!TCP_PAGE(sk)) { + TCP_PAGE(sk) = page; + TCP_OFF(sk) = 0; + } + goto do_fault; + } + /* Update the skb. */ + if (merge) { + skb_shinfo(skb)->frags[i - 1].size += copy; + } else { + skb_fill_page_desc(skb, i, page, off, copy); + if (off + copy < pg_size) { + /* space left keep page */ + get_page(page); + TCP_PAGE(sk) = page; + } else { + TCP_PAGE(sk) = NULL; + } + } + TCP_OFF(sk) = off + copy; + } + if (unlikely(skb->len == mss)) + tx_skb_finalize(skb); + tp->write_seq += copy; + copied += copy; + size -= copy; + + if (is_tls_tx(csk)) + csk->tlshws.txleft -= copy; + + if (corked(tp, flags) && + (sk_stream_wspace(sk) < sk_stream_min_wspace(sk))) + ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_NO_APPEND; + + if (size == 0) + goto out; + + if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) + push_frames_if_head(sk); + continue; +wait_for_sndbuf: + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); +wait_for_memory: + err = csk_wait_memory(cdev, sk, &timeo); + if (err) + goto do_error; + } +out: + csk_reset_flag(csk, CSK_TX_MORE_DATA); + if (copied) + chtls_tcp_push(sk, flags); +done: + release_sock(sk); + return copied + hdrlen; +do_fault: + if (!skb->len) { + __skb_unlink(skb, &csk->txq); + sk->sk_wmem_queued -= skb->truesize; + __kfree_skb(skb); + } +do_error: + if (copied) + goto out; +out_err: + if (csk_conn_inline(csk)) + csk_reset_flag(csk, CSK_TX_MORE_DATA); + copied = sk_stream_error(sk, flags, err); + goto done; +} + +int chtls_sendpage(struct sock *sk, struct page *page, + int offset, size_t size, int flags) +{ + struct chtls_sock *csk; + struct chtls_dev *cdev; + int mss, err, copied; + struct tcp_sock *tp; + long timeo; + + tp = tcp_sk(sk); + copied = 0; + csk = rcu_dereference_sk_user_data(sk); + cdev = csk->cdev; + lock_sock(sk); + timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + + err = sk_stream_wait_connect(sk, &timeo); + if (!sk_in_state(sk, TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) && + err != 0) + goto out_err; + + mss = csk->mss; + csk_set_flag(csk, CSK_TX_MORE_DATA); + + while (size > 0) { + struct sk_buff *skb = skb_peek_tail(&csk->txq); + int copy, i; + + if (!skb || (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) || + (copy = mss - skb->len) <= 0) { +new_buf: + if (!csk_mem_free(cdev, sk)) + goto wait_for_sndbuf; + + if (is_tls_tx(csk)) { + skb = get_record_skb(sk, + select_size(sk, size, + flags, + TX_TLSHDR_LEN), + true); + } else { + skb = get_tx_skb(sk, 0); + } + if (!skb) + goto wait_for_memory; + copy = mss; + } + if (copy > size) + copy = size; + + i = skb_shinfo(skb)->nr_frags; + if (skb_can_coalesce(skb, i, page, offset)) { + skb_shinfo(skb)->frags[i - 1].size += copy; + } else if (i < MAX_SKB_FRAGS) { + get_page(page); + skb_fill_page_desc(skb, i, page, offset, copy); + } else { + tx_skb_finalize(skb); + push_frames_if_head(sk); + goto new_buf; + } + + skb->len += copy; + if (skb->len == mss) + tx_skb_finalize(skb); + skb->data_len += copy; + skb->truesize += copy; + sk->sk_wmem_queued += copy; + tp->write_seq += copy; + copied += copy; + offset += copy; + size -= copy; + + if (corked(tp, flags) && + (sk_stream_wspace(sk) < sk_stream_min_wspace(sk))) + ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_NO_APPEND; + + if (!size) + break; + + if (unlikely(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND)) + push_frames_if_head(sk); + continue; +wait_for_sndbuf: + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); +wait_for_memory: + err = csk_wait_memory(cdev, sk, &timeo); + if (err) + goto do_error; + } +out: + csk_reset_flag(csk, CSK_TX_MORE_DATA); + if (copied) + chtls_tcp_push(sk, flags); +done: + release_sock(sk); + return copied; + +do_error: + if (copied) + goto out; + +out_err: + if (csk_conn_inline(csk)) + csk_reset_flag(csk, CSK_TX_MORE_DATA); + copied = sk_stream_error(sk, flags, err); + goto done; +} + +static void chtls_select_window(struct sock *sk) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct tcp_sock *tp = tcp_sk(sk); + unsigned int wnd = tp->rcv_wnd; + + wnd = max_t(unsigned int, wnd, tcp_full_space(sk)); + wnd = max_t(unsigned int, MIN_RCV_WND, wnd); + + if (wnd > MAX_RCV_WND) + wnd = MAX_RCV_WND; + +/* + * Check if we need to grow the receive window in response to an increase in + * the socket's receive buffer size. Some applications increase the buffer + * size dynamically and rely on the window to grow accordingly. + */ + + if (wnd > tp->rcv_wnd) { + tp->rcv_wup -= wnd - tp->rcv_wnd; + tp->rcv_wnd = wnd; + /* Mark the receive window as updated */ + csk_reset_flag(csk, CSK_UPDATE_RCV_WND); + } +} + +/* + * Send RX credits through an RX_DATA_ACK CPL message. We are permitted + * to return without sending the message in case we cannot allocate + * an sk_buff. Returns the number of credits sent. + */ +static u32 send_rx_credits(struct chtls_sock *csk, u32 credits) +{ + struct cpl_rx_data_ack *req; + struct sk_buff *skb; + + skb = alloc_skb(sizeof(*req), GFP_ATOMIC); + if (!skb) + return 0; + __skb_put(skb, sizeof(*req)); + req = (struct cpl_rx_data_ack *)skb->head; + + set_wr_txq(skb, CPL_PRIORITY_ACK, csk->port_id); + INIT_TP_WR(req, csk->tid); + OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_RX_DATA_ACK, + csk->tid)); + req->credit_dack = cpu_to_be32(RX_CREDITS_V(credits) | + RX_FORCE_ACK_F); + cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb); + return credits; +} + +#define CREDIT_RETURN_STATE (TCPF_ESTABLISHED | \ + TCPF_FIN_WAIT1 | \ + TCPF_FIN_WAIT2) + +/* + * Called after some received data has been read. It returns RX credits + * to the HW for the amount of data processed. + */ +static void chtls_cleanup_rbuf(struct sock *sk, int copied) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct tcp_sock *tp; + int must_send; + u32 credits; + u32 thres; + + thres = 15 * 1024; + + if (!sk_in_state(sk, CREDIT_RETURN_STATE)) + return; + + chtls_select_window(sk); + tp = tcp_sk(sk); + credits = tp->copied_seq - tp->rcv_wup; + if (unlikely(!credits)) + return; + +/* + * For coalescing to work effectively ensure the receive window has + * at least 16KB left. + */ + must_send = credits + 16384 >= tp->rcv_wnd; + + if (must_send || credits >= thres) + tp->rcv_wup += send_rx_credits(csk, credits); +} + +static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, int *addr_len) +{ + struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); + struct net_device *dev = csk->egress_dev; + struct chtls_hws *hws = &csk->tlshws; + struct tcp_sock *tp = tcp_sk(sk); + struct adapter *adap; + unsigned long avail; + int buffers_freed; + int copied = 0; + int request; + int target; + long timeo; + + adap = netdev2adap(dev); + buffers_freed = 0; + + timeo = sock_rcvtimeo(sk, nonblock); + target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + request = len; + + if (unlikely(csk_flag(sk, CSK_UPDATE_RCV_WND))) + chtls_cleanup_rbuf(sk, copied); + + do { + struct sk_buff *skb; + u32 offset = 0; + + if (unlikely(tp->urg_data && + tp->urg_seq == tp->copied_seq)) { + if (copied) + break; + if (signal_pending(current)) { + copied = timeo ? sock_intr_errno(timeo) : + -EAGAIN; + break; + } + } + skb = skb_peek(&sk->sk_receive_queue); + if (skb) + goto found_ok_skb; + if (csk->wr_credits && + skb_queue_len(&csk->txq) && + chtls_push_frames(csk, csk->wr_credits == + csk->wr_max_credits)) + sk->sk_write_space(sk); + + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) + break; + + if (copied) { + if (sk->sk_err || sk->sk_state == TCP_CLOSE || + (sk->sk_shutdown & RCV_SHUTDOWN) || + signal_pending(current)) + break; + + if (!timeo) + break; + } else { + if (sock_flag(sk, SOCK_DONE)) + break; + if (sk->sk_err) { + copied = sock_error(sk); + break; + } + if (sk->sk_shutdown & RCV_SHUTDOWN) + break; + if (sk->sk_state == TCP_CLOSE) { + copied = -ENOTCONN; + break; + } + if (!timeo) { + copied = -EAGAIN; + break; + } + if (signal_pending(current)) { + copied = sock_intr_errno(timeo); + break; + } + } + if (READ_ONCE(sk->sk_backlog.tail)) { + release_sock(sk); + lock_sock(sk); + chtls_cleanup_rbuf(sk, copied); + continue; + } + + if (copied >= target) + break; + chtls_cleanup_rbuf(sk, copied); + sk_wait_data(sk, &timeo, NULL); + continue; +found_ok_skb: + if (!skb->len) { + skb_dst_set(skb, NULL); + __skb_unlink(skb, &sk->sk_receive_queue); + kfree_skb(skb); + + if (!copied && !timeo) { + copied = -EAGAIN; + break; + } + + if (copied < target) { + release_sock(sk); + lock_sock(sk); + continue; + } + break; + } + offset = hws->copied_seq; + avail = skb->len - offset; + if (len < avail) + avail = len; + + if (unlikely(tp->urg_data)) { + u32 urg_offset = tp->urg_seq - tp->copied_seq; + + if (urg_offset < avail) { + if (urg_offset) { + avail = urg_offset; + } else if (!sock_flag(sk, SOCK_URGINLINE)) { + /* First byte is urgent, skip */ + tp->copied_seq++; + offset++; + avail--; + if (!avail) + goto skip_copy; + } + } + } + if (skb_copy_datagram_msg(skb, offset, msg, avail)) { + if (!copied) { + copied = -EFAULT; + break; + } + } + + copied += avail; + len -= avail; + hws->copied_seq += avail; +skip_copy: + if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) + tp->urg_data = 0; + + if ((avail + offset) >= skb->len) { + struct sk_buff *next_skb; + if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) { + tp->copied_seq += skb->len; + hws->rcvpld = skb->hdr_len; + } else { + tp->copied_seq += hws->rcvpld; + } + chtls_free_skb(sk, skb); + buffers_freed++; + hws->copied_seq = 0; + next_skb = skb_peek(&sk->sk_receive_queue); + if (copied >= target && !next_skb) + break; + if (ULP_SKB_CB(next_skb)->flags & ULPCB_FLAG_TLS_HDR) + break; + } + } while (len > 0); + + if (buffers_freed) + chtls_cleanup_rbuf(sk, copied); + release_sock(sk); + return copied; +} + +/* + * Peek at data in a socket's receive buffer. + */ +static int peekmsg(struct sock *sk, struct msghdr *msg, + size_t len, int nonblock, int flags) +{ + struct tcp_sock *tp = tcp_sk(sk); + u32 peek_seq, offset; + struct sk_buff *skb; + int copied = 0; + size_t avail; /* amount of available data in current skb */ + long timeo; + + lock_sock(sk); + timeo = sock_rcvtimeo(sk, nonblock); + peek_seq = tp->copied_seq; + + do { + if (unlikely(tp->urg_data && tp->urg_seq == peek_seq)) { + if (copied) + break; + if (signal_pending(current)) { + copied = timeo ? sock_intr_errno(timeo) : + -EAGAIN; + break; + } + } + + skb_queue_walk(&sk->sk_receive_queue, skb) { + offset = peek_seq - ULP_SKB_CB(skb)->seq; + if (offset < skb->len) + goto found_ok_skb; + } + + /* empty receive queue */ + if (copied) + break; + if (sock_flag(sk, SOCK_DONE)) + break; + if (sk->sk_err) { + copied = sock_error(sk); + break; + } + if (sk->sk_shutdown & RCV_SHUTDOWN) + break; + if (sk->sk_state == TCP_CLOSE) { + copied = -ENOTCONN; + break; + } + if (!timeo) { + copied = -EAGAIN; + break; + } + if (signal_pending(current)) { + copied = sock_intr_errno(timeo); + break; + } + + if (READ_ONCE(sk->sk_backlog.tail)) { + /* Do not sleep, just process backlog. */ + release_sock(sk); + lock_sock(sk); + } else { + sk_wait_data(sk, &timeo, NULL); + } + + if (unlikely(peek_seq != tp->copied_seq)) { + if (net_ratelimit()) + pr_info("TCP(%s:%d), race in MSG_PEEK.\n", + current->comm, current->pid); + peek_seq = tp->copied_seq; + } + continue; + +found_ok_skb: + avail = skb->len - offset; + if (len < avail) + avail = len; + /* + * Do we have urgent data here? We need to skip over the + * urgent byte. + */ + if (unlikely(tp->urg_data)) { + u32 urg_offset = tp->urg_seq - peek_seq; + + if (urg_offset < avail) { + /* + * The amount of data we are preparing to copy + * contains urgent data. + */ + if (!urg_offset) { /* First byte is urgent */ + if (!sock_flag(sk, SOCK_URGINLINE)) { + peek_seq++; + offset++; + avail--; + } + if (!avail) + continue; + } else { + /* stop short of the urgent data */ + avail = urg_offset; + } + } + } + + /* + * If MSG_TRUNC is specified the data is discarded. + */ + if (likely(!(flags & MSG_TRUNC))) + if (skb_copy_datagram_msg(skb, offset, msg, len)) { + if (!copied) { + copied = -EFAULT; + break; + } + } + peek_seq += avail; + copied += avail; + len -= avail; + } while (len > 0); + + release_sock(sk); + return copied; +} + +int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, int *addr_len) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct chtls_sock *csk; + struct chtls_hws *hws; + unsigned long avail; /* amount of available data in current skb */ + int buffers_freed; + int copied = 0; + int request; + long timeo; + int target; /* Read at least this many bytes */ + + buffers_freed = 0; + + if (unlikely(flags & MSG_OOB)) + return tcp_prot.recvmsg(sk, msg, len, nonblock, flags, + addr_len); + + if (unlikely(flags & MSG_PEEK)) + return peekmsg(sk, msg, len, nonblock, flags); + + if (sk_can_busy_loop(sk) && + skb_queue_empty_lockless(&sk->sk_receive_queue) && + sk->sk_state == TCP_ESTABLISHED) + sk_busy_loop(sk, nonblock); + + lock_sock(sk); + csk = rcu_dereference_sk_user_data(sk); + hws = &csk->tlshws; + + if (is_tls_rx(csk)) + return chtls_pt_recvmsg(sk, msg, len, nonblock, + flags, addr_len); + + timeo = sock_rcvtimeo(sk, nonblock); + target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + request = len; + + if (unlikely(csk_flag(sk, CSK_UPDATE_RCV_WND))) + chtls_cleanup_rbuf(sk, copied); + + do { + struct sk_buff *skb; + u32 offset; + + if (unlikely(tp->urg_data && tp->urg_seq == tp->copied_seq)) { + if (copied) + break; + if (signal_pending(current)) { + copied = timeo ? sock_intr_errno(timeo) : + -EAGAIN; + break; + } + } + + skb = skb_peek(&sk->sk_receive_queue); + if (skb) + goto found_ok_skb; + + if (csk->wr_credits && + skb_queue_len(&csk->txq) && + chtls_push_frames(csk, csk->wr_credits == + csk->wr_max_credits)) + sk->sk_write_space(sk); + + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) + break; + + if (copied) { + if (sk->sk_err || sk->sk_state == TCP_CLOSE || + (sk->sk_shutdown & RCV_SHUTDOWN) || + signal_pending(current)) + break; + } else { + if (sock_flag(sk, SOCK_DONE)) + break; + if (sk->sk_err) { + copied = sock_error(sk); + break; + } + if (sk->sk_shutdown & RCV_SHUTDOWN) + break; + if (sk->sk_state == TCP_CLOSE) { + copied = -ENOTCONN; + break; + } + if (!timeo) { + copied = -EAGAIN; + break; + } + if (signal_pending(current)) { + copied = sock_intr_errno(timeo); + break; + } + } + + if (READ_ONCE(sk->sk_backlog.tail)) { + release_sock(sk); + lock_sock(sk); + chtls_cleanup_rbuf(sk, copied); + continue; + } + + if (copied >= target) + break; + chtls_cleanup_rbuf(sk, copied); + sk_wait_data(sk, &timeo, NULL); + continue; + +found_ok_skb: + if (!skb->len) { + chtls_kfree_skb(sk, skb); + if (!copied && !timeo) { + copied = -EAGAIN; + break; + } + + if (copied < target) + continue; + + break; + } + + offset = tp->copied_seq - ULP_SKB_CB(skb)->seq; + avail = skb->len - offset; + if (len < avail) + avail = len; + + if (unlikely(tp->urg_data)) { + u32 urg_offset = tp->urg_seq - tp->copied_seq; + + if (urg_offset < avail) { + if (urg_offset) { + avail = urg_offset; + } else if (!sock_flag(sk, SOCK_URGINLINE)) { + tp->copied_seq++; + offset++; + avail--; + if (!avail) + goto skip_copy; + } + } + } + + if (likely(!(flags & MSG_TRUNC))) { + if (skb_copy_datagram_msg(skb, offset, + msg, avail)) { + if (!copied) { + copied = -EFAULT; + break; + } + } + } + + tp->copied_seq += avail; + copied += avail; + len -= avail; + +skip_copy: + if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) + tp->urg_data = 0; + + if (avail + offset >= skb->len) { + if (likely(skb)) + chtls_free_skb(sk, skb); + buffers_freed++; + + if (copied >= target && + !skb_peek(&sk->sk_receive_queue)) + break; + } + } while (len > 0); + + if (buffers_freed) + chtls_cleanup_rbuf(sk, copied); + + release_sock(sk); + return copied; +} diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c new file mode 100644 index 000000000..2bf084afe --- /dev/null +++ b/drivers/crypto/chelsio/chtls/chtls_main.c @@ -0,0 +1,597 @@ +/* + * Copyright (c) 2018 Chelsio Communications, Inc. + * + * 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. + * + * Written by: Atul Gupta (atul.gupta@chelsio.com) + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/socket.h> +#include <linux/hash.h> +#include <linux/in.h> +#include <linux/net.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <net/tcp.h> +#include <net/tls.h> + +#include "chtls.h" +#include "chtls_cm.h" + +#define DRV_NAME "chtls" + +/* + * chtls device management + * maintains a list of the chtls devices + */ +static LIST_HEAD(cdev_list); +static DEFINE_MUTEX(cdev_mutex); +static DEFINE_MUTEX(cdev_list_lock); + +static DEFINE_MUTEX(notify_mutex); +static RAW_NOTIFIER_HEAD(listen_notify_list); +static struct proto chtls_cpl_prot; +struct request_sock_ops chtls_rsk_ops; +static uint send_page_order = (14 - PAGE_SHIFT < 0) ? 0 : 14 - PAGE_SHIFT; + +static void register_listen_notifier(struct notifier_block *nb) +{ + mutex_lock(¬ify_mutex); + raw_notifier_chain_register(&listen_notify_list, nb); + mutex_unlock(¬ify_mutex); +} + +static void unregister_listen_notifier(struct notifier_block *nb) +{ + mutex_lock(¬ify_mutex); + raw_notifier_chain_unregister(&listen_notify_list, nb); + mutex_unlock(¬ify_mutex); +} + +static int listen_notify_handler(struct notifier_block *this, + unsigned long event, void *data) +{ + struct chtls_listen *clisten; + int ret = NOTIFY_DONE; + + clisten = (struct chtls_listen *)data; + + switch (event) { + case CHTLS_LISTEN_START: + ret = chtls_listen_start(clisten->cdev, clisten->sk); + kfree(clisten); + break; + case CHTLS_LISTEN_STOP: + chtls_listen_stop(clisten->cdev, clisten->sk); + kfree(clisten); + break; + } + return ret; +} + +static struct notifier_block listen_notifier = { + .notifier_call = listen_notify_handler +}; + +static int listen_backlog_rcv(struct sock *sk, struct sk_buff *skb) +{ + if (likely(skb_transport_header(skb) != skb_network_header(skb))) + return tcp_v4_do_rcv(sk, skb); + BLOG_SKB_CB(skb)->backlog_rcv(sk, skb); + return 0; +} + +static int chtls_start_listen(struct chtls_dev *cdev, struct sock *sk) +{ + struct chtls_listen *clisten; + int err; + + if (sk->sk_protocol != IPPROTO_TCP) + return -EPROTONOSUPPORT; + + if (sk->sk_family == PF_INET && + LOOPBACK(inet_sk(sk)->inet_rcv_saddr)) + return -EADDRNOTAVAIL; + + sk->sk_backlog_rcv = listen_backlog_rcv; + clisten = kmalloc(sizeof(*clisten), GFP_KERNEL); + if (!clisten) + return -ENOMEM; + clisten->cdev = cdev; + clisten->sk = sk; + mutex_lock(¬ify_mutex); + err = raw_notifier_call_chain(&listen_notify_list, + CHTLS_LISTEN_START, clisten); + mutex_unlock(¬ify_mutex); + return err; +} + +static void chtls_stop_listen(struct chtls_dev *cdev, struct sock *sk) +{ + struct chtls_listen *clisten; + + if (sk->sk_protocol != IPPROTO_TCP) + return; + + clisten = kmalloc(sizeof(*clisten), GFP_KERNEL); + if (!clisten) + return; + clisten->cdev = cdev; + clisten->sk = sk; + mutex_lock(¬ify_mutex); + raw_notifier_call_chain(&listen_notify_list, + CHTLS_LISTEN_STOP, clisten); + mutex_unlock(¬ify_mutex); +} + +static int chtls_inline_feature(struct tls_device *dev) +{ + struct net_device *netdev; + struct chtls_dev *cdev; + int i; + + cdev = to_chtls_dev(dev); + + for (i = 0; i < cdev->lldi->nports; i++) { + netdev = cdev->ports[i]; + if (netdev->features & NETIF_F_HW_TLS_RECORD) + return 1; + } + return 0; +} + +static int chtls_create_hash(struct tls_device *dev, struct sock *sk) +{ + struct chtls_dev *cdev = to_chtls_dev(dev); + + if (sk->sk_state == TCP_LISTEN) + return chtls_start_listen(cdev, sk); + return 0; +} + +static void chtls_destroy_hash(struct tls_device *dev, struct sock *sk) +{ + struct chtls_dev *cdev = to_chtls_dev(dev); + + if (sk->sk_state == TCP_LISTEN) + chtls_stop_listen(cdev, sk); +} + +static void chtls_register_dev(struct chtls_dev *cdev) +{ + struct tls_device *tlsdev = &cdev->tlsdev; + + strlcpy(tlsdev->name, "chtls", TLS_DEVICE_NAME_MAX); + strlcat(tlsdev->name, cdev->lldi->ports[0]->name, + TLS_DEVICE_NAME_MAX); + tlsdev->feature = chtls_inline_feature; + tlsdev->hash = chtls_create_hash; + tlsdev->unhash = chtls_destroy_hash; + tls_register_device(&cdev->tlsdev); + cdev->cdev_state = CHTLS_CDEV_STATE_UP; +} + +static void chtls_unregister_dev(struct chtls_dev *cdev) +{ + tls_unregister_device(&cdev->tlsdev); +} + +static void process_deferq(struct work_struct *task_param) +{ + struct chtls_dev *cdev = container_of(task_param, + struct chtls_dev, deferq_task); + struct sk_buff *skb; + + spin_lock_bh(&cdev->deferq.lock); + while ((skb = __skb_dequeue(&cdev->deferq)) != NULL) { + spin_unlock_bh(&cdev->deferq.lock); + DEFERRED_SKB_CB(skb)->handler(cdev, skb); + spin_lock_bh(&cdev->deferq.lock); + } + spin_unlock_bh(&cdev->deferq.lock); +} + +static int chtls_get_skb(struct chtls_dev *cdev) +{ + cdev->askb = alloc_skb(sizeof(struct tcphdr), GFP_KERNEL); + if (!cdev->askb) + return -ENOMEM; + + skb_put(cdev->askb, sizeof(struct tcphdr)); + skb_reset_transport_header(cdev->askb); + memset(cdev->askb->data, 0, cdev->askb->len); + return 0; +} + +static void *chtls_uld_add(const struct cxgb4_lld_info *info) +{ + struct cxgb4_lld_info *lldi; + struct chtls_dev *cdev; + int i, j; + + cdev = kzalloc(sizeof(*cdev) + info->nports * + (sizeof(struct net_device *)), GFP_KERNEL); + if (!cdev) + goto out; + + lldi = kzalloc(sizeof(*lldi), GFP_KERNEL); + if (!lldi) + goto out_lldi; + + if (chtls_get_skb(cdev)) + goto out_skb; + + *lldi = *info; + cdev->lldi = lldi; + cdev->pdev = lldi->pdev; + cdev->tids = lldi->tids; + cdev->ports = lldi->ports; + cdev->mtus = lldi->mtus; + cdev->tids = lldi->tids; + cdev->pfvf = FW_VIID_PFN_G(cxgb4_port_viid(lldi->ports[0])) + << FW_VIID_PFN_S; + + for (i = 0; i < (1 << RSPQ_HASH_BITS); i++) { + unsigned int size = 64 - sizeof(struct rsp_ctrl) - 8; + + cdev->rspq_skb_cache[i] = __alloc_skb(size, + gfp_any(), 0, + lldi->nodeid); + if (unlikely(!cdev->rspq_skb_cache[i])) + goto out_rspq_skb; + } + + idr_init(&cdev->hwtid_idr); + INIT_WORK(&cdev->deferq_task, process_deferq); + spin_lock_init(&cdev->listen_lock); + spin_lock_init(&cdev->idr_lock); + cdev->send_page_order = min_t(uint, get_order(32768), + send_page_order); + cdev->max_host_sndbuf = 48 * 1024; + + if (lldi->vr->key.size) + if (chtls_init_kmap(cdev, lldi)) + goto out_rspq_skb; + + mutex_lock(&cdev_mutex); + list_add_tail(&cdev->list, &cdev_list); + mutex_unlock(&cdev_mutex); + + return cdev; +out_rspq_skb: + for (j = 0; j < i; j++) + kfree_skb(cdev->rspq_skb_cache[j]); + kfree_skb(cdev->askb); +out_skb: + kfree(lldi); +out_lldi: + kfree(cdev); +out: + return NULL; +} + +static void chtls_free_uld(struct chtls_dev *cdev) +{ + int i; + + chtls_unregister_dev(cdev); + kvfree(cdev->kmap.addr); + idr_destroy(&cdev->hwtid_idr); + for (i = 0; i < (1 << RSPQ_HASH_BITS); i++) + kfree_skb(cdev->rspq_skb_cache[i]); + kfree(cdev->lldi); + if (cdev->askb) + kfree_skb(cdev->askb); + kfree(cdev); +} + +static void chtls_free_all_uld(void) +{ + struct chtls_dev *cdev, *tmp; + + mutex_lock(&cdev_mutex); + list_for_each_entry_safe(cdev, tmp, &cdev_list, list) { + if (cdev->cdev_state == CHTLS_CDEV_STATE_UP) + chtls_free_uld(cdev); + } + mutex_unlock(&cdev_mutex); +} + +static int chtls_uld_state_change(void *handle, enum cxgb4_state new_state) +{ + struct chtls_dev *cdev = handle; + + switch (new_state) { + case CXGB4_STATE_UP: + chtls_register_dev(cdev); + break; + case CXGB4_STATE_DOWN: + break; + case CXGB4_STATE_START_RECOVERY: + break; + case CXGB4_STATE_DETACH: + mutex_lock(&cdev_mutex); + list_del(&cdev->list); + mutex_unlock(&cdev_mutex); + chtls_free_uld(cdev); + break; + default: + break; + } + return 0; +} + +static struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl, + const __be64 *rsp, + u32 pktshift) +{ + struct sk_buff *skb; + + /* Allocate space for cpl_pass_accpet_req which will be synthesized by + * driver. Once driver synthesizes cpl_pass_accpet_req the skb will go + * through the regular cpl_pass_accept_req processing in TOM. + */ + skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req) + - pktshift, GFP_ATOMIC); + if (unlikely(!skb)) + return NULL; + __skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req) + - pktshift); + /* For now we will copy cpl_rx_pkt in the skb */ + skb_copy_to_linear_data(skb, rsp, sizeof(struct cpl_rx_pkt)); + skb_copy_to_linear_data_offset(skb, sizeof(struct cpl_pass_accept_req) + , gl->va + pktshift, + gl->tot_len - pktshift); + + return skb; +} + +static int chtls_recv_packet(struct chtls_dev *cdev, + const struct pkt_gl *gl, const __be64 *rsp) +{ + unsigned int opcode = *(u8 *)rsp; + struct sk_buff *skb; + int ret; + + skb = copy_gl_to_skb_pkt(gl, rsp, cdev->lldi->sge_pktshift); + if (!skb) + return -ENOMEM; + + ret = chtls_handlers[opcode](cdev, skb); + if (ret & CPL_RET_BUF_DONE) + kfree_skb(skb); + + return 0; +} + +static int chtls_recv_rsp(struct chtls_dev *cdev, const __be64 *rsp) +{ + unsigned long rspq_bin; + unsigned int opcode; + struct sk_buff *skb; + unsigned int len; + int ret; + + len = 64 - sizeof(struct rsp_ctrl) - 8; + opcode = *(u8 *)rsp; + + rspq_bin = hash_ptr((void *)rsp, RSPQ_HASH_BITS); + skb = cdev->rspq_skb_cache[rspq_bin]; + if (skb && !skb_is_nonlinear(skb) && + !skb_shared(skb) && !skb_cloned(skb)) { + refcount_inc(&skb->users); + if (refcount_read(&skb->users) == 2) { + __skb_trim(skb, 0); + if (skb_tailroom(skb) >= len) + goto copy_out; + } + refcount_dec(&skb->users); + } + skb = alloc_skb(len, GFP_ATOMIC); + if (unlikely(!skb)) + return -ENOMEM; + +copy_out: + __skb_put(skb, len); + skb_copy_to_linear_data(skb, rsp, len); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + ret = chtls_handlers[opcode](cdev, skb); + + if (ret & CPL_RET_BUF_DONE) + kfree_skb(skb); + return 0; +} + +static void chtls_recv(struct chtls_dev *cdev, + struct sk_buff **skbs, const __be64 *rsp) +{ + struct sk_buff *skb = *skbs; + unsigned int opcode; + int ret; + + opcode = *(u8 *)rsp; + + __skb_push(skb, sizeof(struct rss_header)); + skb_copy_to_linear_data(skb, rsp, sizeof(struct rss_header)); + + ret = chtls_handlers[opcode](cdev, skb); + if (ret & CPL_RET_BUF_DONE) + kfree_skb(skb); +} + +static int chtls_uld_rx_handler(void *handle, const __be64 *rsp, + const struct pkt_gl *gl) +{ + struct chtls_dev *cdev = handle; + unsigned int opcode; + struct sk_buff *skb; + + opcode = *(u8 *)rsp; + + if (unlikely(opcode == CPL_RX_PKT)) { + if (chtls_recv_packet(cdev, gl, rsp) < 0) + goto nomem; + return 0; + } + + if (!gl) + return chtls_recv_rsp(cdev, rsp); + +#define RX_PULL_LEN 128 + skb = cxgb4_pktgl_to_skb(gl, RX_PULL_LEN, RX_PULL_LEN); + if (unlikely(!skb)) + goto nomem; + chtls_recv(cdev, &skb, rsp); + return 0; + +nomem: + return -ENOMEM; +} + +static int do_chtls_getsockopt(struct sock *sk, char __user *optval, + int __user *optlen) +{ + struct tls_crypto_info crypto_info = { 0 }; + + crypto_info.version = TLS_1_2_VERSION; + if (copy_to_user(optval, &crypto_info, sizeof(struct tls_crypto_info))) + return -EFAULT; + return 0; +} + +static int chtls_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (level != SOL_TLS) + return ctx->getsockopt(sk, level, optname, optval, optlen); + + return do_chtls_getsockopt(sk, optval, optlen); +} + +static int do_chtls_setsockopt(struct sock *sk, int optname, + char __user *optval, unsigned int optlen) +{ + struct tls_crypto_info *crypto_info, tmp_crypto_info; + struct chtls_sock *csk; + int keylen; + int rc = 0; + + csk = rcu_dereference_sk_user_data(sk); + + if (!optval || optlen < sizeof(*crypto_info)) { + rc = -EINVAL; + goto out; + } + + rc = copy_from_user(&tmp_crypto_info, optval, sizeof(*crypto_info)); + if (rc) { + rc = -EFAULT; + goto out; + } + + /* check version */ + if (tmp_crypto_info.version != TLS_1_2_VERSION) { + rc = -ENOTSUPP; + goto out; + } + + crypto_info = (struct tls_crypto_info *)&csk->tlshws.crypto_info; + + switch (tmp_crypto_info.cipher_type) { + case TLS_CIPHER_AES_GCM_128: { + /* Obtain version and type from previous copy */ + crypto_info[0] = tmp_crypto_info; + /* Now copy the following data */ + rc = copy_from_user((char *)crypto_info + sizeof(*crypto_info), + optval + sizeof(*crypto_info), + sizeof(struct tls12_crypto_info_aes_gcm_128) + - sizeof(*crypto_info)); + + if (rc) { + rc = -EFAULT; + goto out; + } + + keylen = TLS_CIPHER_AES_GCM_128_KEY_SIZE; + rc = chtls_setkey(csk, keylen, optname); + break; + } + default: + rc = -EINVAL; + goto out; + } +out: + return rc; +} + +static int chtls_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (level != SOL_TLS) + return ctx->setsockopt(sk, level, optname, optval, optlen); + + return do_chtls_setsockopt(sk, optname, optval, optlen); +} + +static struct cxgb4_uld_info chtls_uld_info = { + .name = DRV_NAME, + .nrxq = MAX_ULD_QSETS, + .ntxq = MAX_ULD_QSETS, + .rxq_size = 1024, + .add = chtls_uld_add, + .state_change = chtls_uld_state_change, + .rx_handler = chtls_uld_rx_handler, +}; + +void chtls_install_cpl_ops(struct sock *sk) +{ + sk->sk_prot = &chtls_cpl_prot; +} + +static void __init chtls_init_ulp_ops(void) +{ + chtls_cpl_prot = tcp_prot; + chtls_init_rsk_ops(&chtls_cpl_prot, &chtls_rsk_ops, + &tcp_prot, PF_INET); + chtls_cpl_prot.close = chtls_close; + chtls_cpl_prot.disconnect = chtls_disconnect; + chtls_cpl_prot.destroy = chtls_destroy_sock; + chtls_cpl_prot.shutdown = chtls_shutdown; + chtls_cpl_prot.sendmsg = chtls_sendmsg; + chtls_cpl_prot.sendpage = chtls_sendpage; + chtls_cpl_prot.recvmsg = chtls_recvmsg; + chtls_cpl_prot.setsockopt = chtls_setsockopt; + chtls_cpl_prot.getsockopt = chtls_getsockopt; +} + +static int __init chtls_register(void) +{ + chtls_init_ulp_ops(); + register_listen_notifier(&listen_notifier); + cxgb4_register_uld(CXGB4_ULD_TLS, &chtls_uld_info); + return 0; +} + +static void __exit chtls_unregister(void) +{ + unregister_listen_notifier(&listen_notifier); + chtls_free_all_uld(); + cxgb4_unregister_uld(CXGB4_ULD_TLS); +} + +module_init(chtls_register); +module_exit(chtls_unregister); + +MODULE_DESCRIPTION("Chelsio TLS Inline driver"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Chelsio Communications"); +MODULE_VERSION(DRV_VERSION); |