diff options
Diffstat (limited to 'drivers/nvme/host/tcp.c')
-rw-r--r-- | drivers/nvme/host/tcp.c | 2278 |
1 files changed, 2278 insertions, 0 deletions
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c new file mode 100644 index 000000000000..de174912445e --- /dev/null +++ b/drivers/nvme/host/tcp.c @@ -0,0 +1,2278 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVMe over Fabrics TCP host. + * Copyright (c) 2018 Lightbits Labs. All rights reserved. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/nvme-tcp.h> +#include <net/sock.h> +#include <net/tcp.h> +#include <linux/blk-mq.h> +#include <crypto/hash.h> + +#include "nvme.h" +#include "fabrics.h" + +struct nvme_tcp_queue; + +enum nvme_tcp_send_state { + NVME_TCP_SEND_CMD_PDU = 0, + NVME_TCP_SEND_H2C_PDU, + NVME_TCP_SEND_DATA, + NVME_TCP_SEND_DDGST, +}; + +struct nvme_tcp_request { + struct nvme_request req; + void *pdu; + struct nvme_tcp_queue *queue; + u32 data_len; + u32 pdu_len; + u32 pdu_sent; + u16 ttag; + struct list_head entry; + __le32 ddgst; + + struct bio *curr_bio; + struct iov_iter iter; + + /* send state */ + size_t offset; + size_t data_sent; + enum nvme_tcp_send_state state; +}; + +enum nvme_tcp_queue_flags { + NVME_TCP_Q_ALLOCATED = 0, + NVME_TCP_Q_LIVE = 1, +}; + +enum nvme_tcp_recv_state { + NVME_TCP_RECV_PDU = 0, + NVME_TCP_RECV_DATA, + NVME_TCP_RECV_DDGST, +}; + +struct nvme_tcp_ctrl; +struct nvme_tcp_queue { + struct socket *sock; + struct work_struct io_work; + int io_cpu; + + spinlock_t lock; + struct list_head send_list; + + /* recv state */ + void *pdu; + int pdu_remaining; + int pdu_offset; + size_t data_remaining; + size_t ddgst_remaining; + + /* send state */ + struct nvme_tcp_request *request; + + int queue_size; + size_t cmnd_capsule_len; + struct nvme_tcp_ctrl *ctrl; + unsigned long flags; + bool rd_enabled; + + bool hdr_digest; + bool data_digest; + struct ahash_request *rcv_hash; + struct ahash_request *snd_hash; + __le32 exp_ddgst; + __le32 recv_ddgst; + + struct page_frag_cache pf_cache; + + void (*state_change)(struct sock *); + void (*data_ready)(struct sock *); + void (*write_space)(struct sock *); +}; + +struct nvme_tcp_ctrl { + /* read only in the hot path */ + struct nvme_tcp_queue *queues; + struct blk_mq_tag_set tag_set; + + /* other member variables */ + struct list_head list; + struct blk_mq_tag_set admin_tag_set; + struct sockaddr_storage addr; + struct sockaddr_storage src_addr; + struct nvme_ctrl ctrl; + + struct work_struct err_work; + struct delayed_work connect_work; + struct nvme_tcp_request async_req; +}; + +static LIST_HEAD(nvme_tcp_ctrl_list); +static DEFINE_MUTEX(nvme_tcp_ctrl_mutex); +static struct workqueue_struct *nvme_tcp_wq; +static struct blk_mq_ops nvme_tcp_mq_ops; +static struct blk_mq_ops nvme_tcp_admin_mq_ops; + +static inline struct nvme_tcp_ctrl *to_tcp_ctrl(struct nvme_ctrl *ctrl) +{ + return container_of(ctrl, struct nvme_tcp_ctrl, ctrl); +} + +static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue) +{ + return queue - queue->ctrl->queues; +} + +static inline struct blk_mq_tags *nvme_tcp_tagset(struct nvme_tcp_queue *queue) +{ + u32 queue_idx = nvme_tcp_queue_id(queue); + + if (queue_idx == 0) + return queue->ctrl->admin_tag_set.tags[queue_idx]; + return queue->ctrl->tag_set.tags[queue_idx - 1]; +} + +static inline u8 nvme_tcp_hdgst_len(struct nvme_tcp_queue *queue) +{ + return queue->hdr_digest ? NVME_TCP_DIGEST_LENGTH : 0; +} + +static inline u8 nvme_tcp_ddgst_len(struct nvme_tcp_queue *queue) +{ + return queue->data_digest ? NVME_TCP_DIGEST_LENGTH : 0; +} + +static inline size_t nvme_tcp_inline_data_size(struct nvme_tcp_queue *queue) +{ + return queue->cmnd_capsule_len - sizeof(struct nvme_command); +} + +static inline bool nvme_tcp_async_req(struct nvme_tcp_request *req) +{ + return req == &req->queue->ctrl->async_req; +} + +static inline bool nvme_tcp_has_inline_data(struct nvme_tcp_request *req) +{ + struct request *rq; + unsigned int bytes; + + if (unlikely(nvme_tcp_async_req(req))) + return false; /* async events don't have a request */ + + rq = blk_mq_rq_from_pdu(req); + bytes = blk_rq_payload_bytes(rq); + + return rq_data_dir(rq) == WRITE && bytes && + bytes <= nvme_tcp_inline_data_size(req->queue); +} + +static inline struct page *nvme_tcp_req_cur_page(struct nvme_tcp_request *req) +{ + return req->iter.bvec->bv_page; +} + +static inline size_t nvme_tcp_req_cur_offset(struct nvme_tcp_request *req) +{ + return req->iter.bvec->bv_offset + req->iter.iov_offset; +} + +static inline size_t nvme_tcp_req_cur_length(struct nvme_tcp_request *req) +{ + return min_t(size_t, req->iter.bvec->bv_len - req->iter.iov_offset, + req->pdu_len - req->pdu_sent); +} + +static inline size_t nvme_tcp_req_offset(struct nvme_tcp_request *req) +{ + return req->iter.iov_offset; +} + +static inline size_t nvme_tcp_pdu_data_left(struct nvme_tcp_request *req) +{ + return rq_data_dir(blk_mq_rq_from_pdu(req)) == WRITE ? + req->pdu_len - req->pdu_sent : 0; +} + +static inline size_t nvme_tcp_pdu_last_send(struct nvme_tcp_request *req, + int len) +{ + return nvme_tcp_pdu_data_left(req) <= len; +} + +static void nvme_tcp_init_iter(struct nvme_tcp_request *req, + unsigned int dir) +{ + struct request *rq = blk_mq_rq_from_pdu(req); + struct bio_vec *vec; + unsigned int size; + int nsegs; + size_t offset; + + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) { + vec = &rq->special_vec; + nsegs = 1; + size = blk_rq_payload_bytes(rq); + offset = 0; + } else { + struct bio *bio = req->curr_bio; + + vec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); + nsegs = bio_segments(bio); + size = bio->bi_iter.bi_size; + offset = bio->bi_iter.bi_bvec_done; + } + + iov_iter_bvec(&req->iter, dir, vec, nsegs, size); + req->iter.iov_offset = offset; +} + +static inline void nvme_tcp_advance_req(struct nvme_tcp_request *req, + int len) +{ + req->data_sent += len; + req->pdu_sent += len; + iov_iter_advance(&req->iter, len); + if (!iov_iter_count(&req->iter) && + req->data_sent < req->data_len) { + req->curr_bio = req->curr_bio->bi_next; + nvme_tcp_init_iter(req, WRITE); + } +} + +static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req) +{ + struct nvme_tcp_queue *queue = req->queue; + + spin_lock(&queue->lock); + list_add_tail(&req->entry, &queue->send_list); + spin_unlock(&queue->lock); + + queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); +} + +static inline struct nvme_tcp_request * +nvme_tcp_fetch_request(struct nvme_tcp_queue *queue) +{ + struct nvme_tcp_request *req; + + spin_lock(&queue->lock); + req = list_first_entry_or_null(&queue->send_list, + struct nvme_tcp_request, entry); + if (req) + list_del(&req->entry); + spin_unlock(&queue->lock); + + return req; +} + +static inline void nvme_tcp_ddgst_final(struct ahash_request *hash, + __le32 *dgst) +{ + ahash_request_set_crypt(hash, NULL, (u8 *)dgst, 0); + crypto_ahash_final(hash); +} + +static inline void nvme_tcp_ddgst_update(struct ahash_request *hash, + struct page *page, off_t off, size_t len) +{ + struct scatterlist sg; + + sg_init_marker(&sg, 1); + sg_set_page(&sg, page, len, off); + ahash_request_set_crypt(hash, &sg, NULL, len); + crypto_ahash_update(hash); +} + +static inline void nvme_tcp_hdgst(struct ahash_request *hash, + void *pdu, size_t len) +{ + struct scatterlist sg; + + sg_init_one(&sg, pdu, len); + ahash_request_set_crypt(hash, &sg, pdu + len, len); + crypto_ahash_digest(hash); +} + +static int nvme_tcp_verify_hdgst(struct nvme_tcp_queue *queue, + void *pdu, size_t pdu_len) +{ + struct nvme_tcp_hdr *hdr = pdu; + __le32 recv_digest; + __le32 exp_digest; + + if (unlikely(!(hdr->flags & NVME_TCP_F_HDGST))) { + dev_err(queue->ctrl->ctrl.device, + "queue %d: header digest flag is cleared\n", + nvme_tcp_queue_id(queue)); + return -EPROTO; + } + + recv_digest = *(__le32 *)(pdu + hdr->hlen); + nvme_tcp_hdgst(queue->rcv_hash, pdu, pdu_len); + exp_digest = *(__le32 *)(pdu + hdr->hlen); + if (recv_digest != exp_digest) { + dev_err(queue->ctrl->ctrl.device, + "header digest error: recv %#x expected %#x\n", + le32_to_cpu(recv_digest), le32_to_cpu(exp_digest)); + return -EIO; + } + + return 0; +} + +static int nvme_tcp_check_ddgst(struct nvme_tcp_queue *queue, void *pdu) +{ + struct nvme_tcp_hdr *hdr = pdu; + u8 digest_len = nvme_tcp_hdgst_len(queue); + u32 len; + + len = le32_to_cpu(hdr->plen) - hdr->hlen - + ((hdr->flags & NVME_TCP_F_HDGST) ? digest_len : 0); + + if (unlikely(len && !(hdr->flags & NVME_TCP_F_DDGST))) { + dev_err(queue->ctrl->ctrl.device, + "queue %d: data digest flag is cleared\n", + nvme_tcp_queue_id(queue)); + return -EPROTO; + } + crypto_ahash_init(queue->rcv_hash); + + return 0; +} + +static void nvme_tcp_exit_request(struct blk_mq_tag_set *set, + struct request *rq, unsigned int hctx_idx) +{ + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + + page_frag_free(req->pdu); +} + +static int nvme_tcp_init_request(struct blk_mq_tag_set *set, + struct request *rq, unsigned int hctx_idx, + unsigned int numa_node) +{ + struct nvme_tcp_ctrl *ctrl = set->driver_data; + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0; + struct nvme_tcp_queue *queue = &ctrl->queues[queue_idx]; + u8 hdgst = nvme_tcp_hdgst_len(queue); + + req->pdu = page_frag_alloc(&queue->pf_cache, + sizeof(struct nvme_tcp_cmd_pdu) + hdgst, + GFP_KERNEL | __GFP_ZERO); + if (!req->pdu) + return -ENOMEM; + + req->queue = queue; + nvme_req(rq)->ctrl = &ctrl->ctrl; + + return 0; +} + +static int nvme_tcp_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, + unsigned int hctx_idx) +{ + struct nvme_tcp_ctrl *ctrl = data; + struct nvme_tcp_queue *queue = &ctrl->queues[hctx_idx + 1]; + + hctx->driver_data = queue; + return 0; +} + +static int nvme_tcp_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, + unsigned int hctx_idx) +{ + struct nvme_tcp_ctrl *ctrl = data; + struct nvme_tcp_queue *queue = &ctrl->queues[0]; + + hctx->driver_data = queue; + return 0; +} + +static enum nvme_tcp_recv_state +nvme_tcp_recv_state(struct nvme_tcp_queue *queue) +{ + return (queue->pdu_remaining) ? NVME_TCP_RECV_PDU : + (queue->ddgst_remaining) ? NVME_TCP_RECV_DDGST : + NVME_TCP_RECV_DATA; +} + +static void nvme_tcp_init_recv_ctx(struct nvme_tcp_queue *queue) +{ + queue->pdu_remaining = sizeof(struct nvme_tcp_rsp_pdu) + + nvme_tcp_hdgst_len(queue); + queue->pdu_offset = 0; + queue->data_remaining = -1; + queue->ddgst_remaining = 0; +} + +static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl) +{ + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) + return; + + queue_work(nvme_wq, &to_tcp_ctrl(ctrl)->err_work); +} + +static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue, + struct nvme_completion *cqe) +{ + struct request *rq; + + rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), cqe->command_id); + if (!rq) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag 0x%x not found\n", + nvme_tcp_queue_id(queue), cqe->command_id); + nvme_tcp_error_recovery(&queue->ctrl->ctrl); + return -EINVAL; + } + + nvme_end_request(rq, cqe->status, cqe->result); + + return 0; +} + +static int nvme_tcp_handle_c2h_data(struct nvme_tcp_queue *queue, + struct nvme_tcp_data_pdu *pdu) +{ + struct request *rq; + + rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id); + if (!rq) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag %#x not found\n", + nvme_tcp_queue_id(queue), pdu->command_id); + return -ENOENT; + } + + if (!blk_rq_payload_bytes(rq)) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag %#x unexpected data\n", + nvme_tcp_queue_id(queue), rq->tag); + return -EIO; + } + + queue->data_remaining = le32_to_cpu(pdu->data_length); + + return 0; + +} + +static int nvme_tcp_handle_comp(struct nvme_tcp_queue *queue, + struct nvme_tcp_rsp_pdu *pdu) +{ + struct nvme_completion *cqe = &pdu->cqe; + int ret = 0; + + /* + * AEN requests are special as they don't time out and can + * survive any kind of queue freeze and often don't respond to + * aborts. We don't even bother to allocate a struct request + * for them but rather special case them here. + */ + if (unlikely(nvme_tcp_queue_id(queue) == 0 && + cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) + nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, + &cqe->result); + else + ret = nvme_tcp_process_nvme_cqe(queue, cqe); + + return ret; +} + +static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req, + struct nvme_tcp_r2t_pdu *pdu) +{ + struct nvme_tcp_data_pdu *data = req->pdu; + struct nvme_tcp_queue *queue = req->queue; + struct request *rq = blk_mq_rq_from_pdu(req); + u8 hdgst = nvme_tcp_hdgst_len(queue); + u8 ddgst = nvme_tcp_ddgst_len(queue); + + req->pdu_len = le32_to_cpu(pdu->r2t_length); + req->pdu_sent = 0; + + if (unlikely(req->data_sent + req->pdu_len > req->data_len)) { + dev_err(queue->ctrl->ctrl.device, + "req %d r2t len %u exceeded data len %u (%zu sent)\n", + rq->tag, req->pdu_len, req->data_len, + req->data_sent); + return -EPROTO; + } + + if (unlikely(le32_to_cpu(pdu->r2t_offset) < req->data_sent)) { + dev_err(queue->ctrl->ctrl.device, + "req %d unexpected r2t offset %u (expected %zu)\n", + rq->tag, le32_to_cpu(pdu->r2t_offset), + req->data_sent); + return -EPROTO; + } + + memset(data, 0, sizeof(*data)); + data->hdr.type = nvme_tcp_h2c_data; + data->hdr.flags = NVME_TCP_F_DATA_LAST; + if (queue->hdr_digest) + data->hdr.flags |= NVME_TCP_F_HDGST; + if (queue->data_digest) + data->hdr.flags |= NVME_TCP_F_DDGST; + data->hdr.hlen = sizeof(*data); + data->hdr.pdo = data->hdr.hlen + hdgst; + data->hdr.plen = + cpu_to_le32(data->hdr.hlen + hdgst + req->pdu_len + ddgst); + data->ttag = pdu->ttag; + data->command_id = rq->tag; + data->data_offset = cpu_to_le32(req->data_sent); + data->data_length = cpu_to_le32(req->pdu_len); + return 0; +} + +static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue, + struct nvme_tcp_r2t_pdu *pdu) +{ + struct nvme_tcp_request *req; + struct request *rq; + int ret; + + rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id); + if (!rq) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag %#x not found\n", + nvme_tcp_queue_id(queue), pdu->command_id); + return -ENOENT; + } + req = blk_mq_rq_to_pdu(rq); + + ret = nvme_tcp_setup_h2c_data_pdu(req, pdu); + if (unlikely(ret)) + return ret; + + req->state = NVME_TCP_SEND_H2C_PDU; + req->offset = 0; + + nvme_tcp_queue_request(req); + + return 0; +} + +static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb, + unsigned int *offset, size_t *len) +{ + struct nvme_tcp_hdr *hdr; + char *pdu = queue->pdu; + size_t rcv_len = min_t(size_t, *len, queue->pdu_remaining); + int ret; + + ret = skb_copy_bits(skb, *offset, + &pdu[queue->pdu_offset], rcv_len); + if (unlikely(ret)) + return ret; + + queue->pdu_remaining -= rcv_len; + queue->pdu_offset += rcv_len; + *offset += rcv_len; + *len -= rcv_len; + if (queue->pdu_remaining) + return 0; + + hdr = queue->pdu; + if (queue->hdr_digest) { + ret = nvme_tcp_verify_hdgst(queue, queue->pdu, hdr->hlen); + if (unlikely(ret)) + return ret; + } + + + if (queue->data_digest) { + ret = nvme_tcp_check_ddgst(queue, queue->pdu); + if (unlikely(ret)) + return ret; + } + + switch (hdr->type) { + case nvme_tcp_c2h_data: + ret = nvme_tcp_handle_c2h_data(queue, (void *)queue->pdu); + break; + case nvme_tcp_rsp: + nvme_tcp_init_recv_ctx(queue); + ret = nvme_tcp_handle_comp(queue, (void *)queue->pdu); + break; + case nvme_tcp_r2t: + nvme_tcp_init_recv_ctx(queue); + ret = nvme_tcp_handle_r2t(queue, (void *)queue->pdu); + break; + default: + dev_err(queue->ctrl->ctrl.device, + "unsupported pdu type (%d)\n", hdr->type); + return -EINVAL; + } + + return ret; +} + +static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb, + unsigned int *offset, size_t *len) +{ + struct nvme_tcp_data_pdu *pdu = (void *)queue->pdu; + struct nvme_tcp_request *req; + struct request *rq; + + rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id); + if (!rq) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag %#x not found\n", + nvme_tcp_queue_id(queue), pdu->command_id); + return -ENOENT; + } + req = blk_mq_rq_to_pdu(rq); + + while (true) { + int recv_len, ret; + + recv_len = min_t(size_t, *len, queue->data_remaining); + if (!recv_len) + break; + + if (!iov_iter_count(&req->iter)) { + req->curr_bio = req->curr_bio->bi_next; + + /* + * If we don`t have any bios it means that controller + * sent more data than we requested, hence error + */ + if (!req->curr_bio) { + dev_err(queue->ctrl->ctrl.device, + "queue %d no space in request %#x", + nvme_tcp_queue_id(queue), rq->tag); + nvme_tcp_init_recv_ctx(queue); + return -EIO; + } + nvme_tcp_init_iter(req, READ); + } + + /* we can read only from what is left in this bio */ + recv_len = min_t(size_t, recv_len, + iov_iter_count(&req->iter)); + + if (queue->data_digest) + ret = skb_copy_and_hash_datagram_iter(skb, *offset, + &req->iter, recv_len, queue->rcv_hash); + else + ret = skb_copy_datagram_iter(skb, *offset, + &req->iter, recv_len); + if (ret) { + dev_err(queue->ctrl->ctrl.device, + "queue %d failed to copy request %#x data", + nvme_tcp_queue_id(queue), rq->tag); + return ret; + } + + *len -= recv_len; + *offset += recv_len; + queue->data_remaining -= recv_len; + } + + if (!queue->data_remaining) { + if (queue->data_digest) { + nvme_tcp_ddgst_final(queue->rcv_hash, &queue->exp_ddgst); + queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH; + } else { + nvme_tcp_init_recv_ctx(queue); + } + } + + return 0; +} + +static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue, + struct sk_buff *skb, unsigned int *offset, size_t *len) +{ + char *ddgst = (char *)&queue->recv_ddgst; + size_t recv_len = min_t(size_t, *len, queue->ddgst_remaining); + off_t off = NVME_TCP_DIGEST_LENGTH - queue->ddgst_remaining; + int ret; + + ret = skb_copy_bits(skb, *offset, &ddgst[off], recv_len); + if (unlikely(ret)) + return ret; + + queue->ddgst_remaining -= recv_len; + *offset += recv_len; + *len -= recv_len; + if (queue->ddgst_remaining) + return 0; + + if (queue->recv_ddgst != queue->exp_ddgst) { + dev_err(queue->ctrl->ctrl.device, + "data digest error: recv %#x expected %#x\n", + le32_to_cpu(queue->recv_ddgst), + le32_to_cpu(queue->exp_ddgst)); + return -EIO; + } + + nvme_tcp_init_recv_ctx(queue); + return 0; +} + +static int nvme_tcp_recv_skb(read_descriptor_t *desc, struct sk_buff *skb, + unsigned int offset, size_t len) +{ + struct nvme_tcp_queue *queue = desc->arg.data; + size_t consumed = len; + int result; + + while (len) { + switch (nvme_tcp_recv_state(queue)) { + case NVME_TCP_RECV_PDU: + result = nvme_tcp_recv_pdu(queue, skb, &offset, &len); + break; + case NVME_TCP_RECV_DATA: + result = nvme_tcp_recv_data(queue, skb, &offset, &len); + break; + case NVME_TCP_RECV_DDGST: + result = nvme_tcp_recv_ddgst(queue, skb, &offset, &len); + break; + default: + result = -EFAULT; + } + if (result) { + dev_err(queue->ctrl->ctrl.device, + "receive failed: %d\n", result); + queue->rd_enabled = false; + nvme_tcp_error_recovery(&queue->ctrl->ctrl); + return result; + } + } + + return consumed; +} + +static void nvme_tcp_data_ready(struct sock *sk) +{ + struct nvme_tcp_queue *queue; + + read_lock(&sk->sk_callback_lock); + queue = sk->sk_user_data; + if (likely(queue && queue->rd_enabled)) + queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); + read_unlock(&sk->sk_callback_lock); +} + +static void nvme_tcp_write_space(struct sock *sk) +{ + struct nvme_tcp_queue *queue; + + read_lock_bh(&sk->sk_callback_lock); + queue = sk->sk_user_data; + if (likely(queue && sk_stream_is_writeable(sk))) { + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); + } + read_unlock_bh(&sk->sk_callback_lock); +} + +static void nvme_tcp_state_change(struct sock *sk) +{ + struct nvme_tcp_queue *queue; + + read_lock(&sk->sk_callback_lock); + queue = sk->sk_user_data; + if (!queue) + goto done; + + switch (sk->sk_state) { + case TCP_CLOSE: + case TCP_CLOSE_WAIT: + case TCP_LAST_ACK: + case TCP_FIN_WAIT1: + case TCP_FIN_WAIT2: + /* fallthrough */ + nvme_tcp_error_recovery(&queue->ctrl->ctrl); + break; + default: + dev_info(queue->ctrl->ctrl.device, + "queue %d socket state %d\n", + nvme_tcp_queue_id(queue), sk->sk_state); + } + + queue->state_change(sk); +done: + read_unlock(&sk->sk_callback_lock); +} + +static inline void nvme_tcp_done_send_req(struct nvme_tcp_queue *queue) +{ + queue->request = NULL; +} + +static void nvme_tcp_fail_request(struct nvme_tcp_request *req) +{ + union nvme_result res = {}; + + nvme_end_request(blk_mq_rq_from_pdu(req), + cpu_to_le16(NVME_SC_DATA_XFER_ERROR), res); +} + +static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) +{ + struct nvme_tcp_queue *queue = req->queue; + + while (true) { + struct page *page = nvme_tcp_req_cur_page(req); + size_t offset = nvme_tcp_req_cur_offset(req); + size_t len = nvme_tcp_req_cur_length(req); + bool last = nvme_tcp_pdu_last_send(req, len); + int ret, flags = MSG_DONTWAIT; + + if (last && !queue->data_digest) + flags |= MSG_EOR; + else + flags |= MSG_MORE; + + ret = kernel_sendpage(queue->sock, page, offset, len, flags); + if (ret <= 0) + return ret; + + nvme_tcp_advance_req(req, ret); + if (queue->data_digest) + nvme_tcp_ddgst_update(queue->snd_hash, page, + offset, ret); + + /* fully successful last write*/ + if (last && ret == len) { + if (queue->data_digest) { + nvme_tcp_ddgst_final(queue->snd_hash, + &req->ddgst); + req->state = NVME_TCP_SEND_DDGST; + req->offset = 0; + } else { + nvme_tcp_done_send_req(queue); + } + return 1; + } + } + return -EAGAIN; +} + +static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req) +{ + struct nvme_tcp_queue *queue = req->queue; + struct nvme_tcp_cmd_pdu *pdu = req->pdu; + bool inline_data = nvme_tcp_has_inline_data(req); + int flags = MSG_DONTWAIT | (inline_data ? MSG_MORE : MSG_EOR); + u8 hdgst = nvme_tcp_hdgst_len(queue); + int len = sizeof(*pdu) + hdgst - req->offset; + int ret; + + if (queue->hdr_digest && !req->offset) + nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu)); + + ret = kernel_sendpage(queue->sock, virt_to_page(pdu), + offset_in_page(pdu) + req->offset, len, flags); + if (unlikely(ret <= 0)) + return ret; + + len -= ret; + if (!len) { + if (inline_data) { + req->state = NVME_TCP_SEND_DATA; + if (queue->data_digest) + crypto_ahash_init(queue->snd_hash); + nvme_tcp_init_iter(req, WRITE); + } else { + nvme_tcp_done_send_req(queue); + } + return 1; + } + req->offset += ret; + + return -EAGAIN; +} + +static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req) +{ + struct nvme_tcp_queue *queue = req->queue; + struct nvme_tcp_data_pdu *pdu = req->pdu; + u8 hdgst = nvme_tcp_hdgst_len(queue); + int len = sizeof(*pdu) - req->offset + hdgst; + int ret; + + if (queue->hdr_digest && !req->offset) + nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu)); + + ret = kernel_sendpage(queue->sock, virt_to_page(pdu), + offset_in_page(pdu) + req->offset, len, + MSG_DONTWAIT | MSG_MORE); + if (unlikely(ret <= 0)) + return ret; + + len -= ret; + if (!len) { + req->state = NVME_TCP_SEND_DATA; + if (queue->data_digest) + crypto_ahash_init(queue->snd_hash); + if (!req->data_sent) + nvme_tcp_init_iter(req, WRITE); + return 1; + } + req->offset += ret; + + return -EAGAIN; +} + +static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req) +{ + struct nvme_tcp_queue *queue = req->queue; + int ret; + struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_EOR }; + struct kvec iov = { + .iov_base = &req->ddgst + req->offset, + .iov_len = NVME_TCP_DIGEST_LENGTH - req->offset + }; + + ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); + if (unlikely(ret <= 0)) + return ret; + + if (req->offset + ret == NVME_TCP_DIGEST_LENGTH) { + nvme_tcp_done_send_req(queue); + return 1; + } + + req->offset += ret; + return -EAGAIN; +} + +static int nvme_tcp_try_send(struct nvme_tcp_queue *queue) +{ + struct nvme_tcp_request *req; + int ret = 1; + + if (!queue->request) { + queue->request = nvme_tcp_fetch_request(queue); + if (!queue->request) + return 0; + } + req = queue->request; + + if (req->state == NVME_TCP_SEND_CMD_PDU) { + ret = nvme_tcp_try_send_cmd_pdu(req); + if (ret <= 0) + goto done; + if (!nvme_tcp_has_inline_data(req)) + return ret; + } + + if (req->state == NVME_TCP_SEND_H2C_PDU) { + ret = nvme_tcp_try_send_data_pdu(req); + if (ret <= 0) + goto done; + } + + if (req->state == NVME_TCP_SEND_DATA) { + ret = nvme_tcp_try_send_data(req); + if (ret <= 0) + goto done; + } + + if (req->state == NVME_TCP_SEND_DDGST) + ret = nvme_tcp_try_send_ddgst(req); +done: + if (ret == -EAGAIN) + ret = 0; + return ret; +} + +static int nvme_tcp_try_recv(struct nvme_tcp_queue *queue) +{ + struct sock *sk = queue->sock->sk; + read_descriptor_t rd_desc; + int consumed; + + rd_desc.arg.data = queue; + rd_desc.count = 1; + lock_sock(sk); + consumed = tcp_read_sock(sk, &rd_desc, nvme_tcp_recv_skb); + release_sock(sk); + return consumed; +} + +static void nvme_tcp_io_work(struct work_struct *w) +{ + struct nvme_tcp_queue *queue = + container_of(w, struct nvme_tcp_queue, io_work); + unsigned long start = jiffies + msecs_to_jiffies(1); + + do { + bool pending = false; + int result; + + result = nvme_tcp_try_send(queue); + if (result > 0) { + pending = true; + } else if (unlikely(result < 0)) { + dev_err(queue->ctrl->ctrl.device, + "failed to send request %d\n", result); + if (result != -EPIPE) + nvme_tcp_fail_request(queue->request); + nvme_tcp_done_send_req(queue); + return; + } + + result = nvme_tcp_try_recv(queue); + if (result > 0) + pending = true; + + if (!pending) + return; + + } while (time_after(jiffies, start)); /* quota is exhausted */ + + queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); +} + +static void nvme_tcp_free_crypto(struct nvme_tcp_queue *queue) +{ + struct crypto_ahash *tfm = crypto_ahash_reqtfm(queue->rcv_hash); + + ahash_request_free(queue->rcv_hash); + ahash_request_free(queue->snd_hash); + crypto_free_ahash(tfm); +} + +static int nvme_tcp_alloc_crypto(struct nvme_tcp_queue *queue) +{ + struct crypto_ahash *tfm; + + tfm = crypto_alloc_ahash("crc32c", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + queue->snd_hash = ahash_request_alloc(tfm, GFP_KERNEL); + if (!queue->snd_hash) + goto free_tfm; + ahash_request_set_callback(queue->snd_hash, 0, NULL, NULL); + + queue->rcv_hash = ahash_request_alloc(tfm, GFP_KERNEL); + if (!queue->rcv_hash) + goto free_snd_hash; + ahash_request_set_callback(queue->rcv_hash, 0, NULL, NULL); + + return 0; +free_snd_hash: + ahash_request_free(queue->snd_hash); +free_tfm: + crypto_free_ahash(tfm); + return -ENOMEM; +} + +static void nvme_tcp_free_async_req(struct nvme_tcp_ctrl *ctrl) +{ + struct nvme_tcp_request *async = &ctrl->async_req; + + page_frag_free(async->pdu); +} + +static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl) +{ + struct nvme_tcp_queue *queue = &ctrl->queues[0]; + struct nvme_tcp_request *async = &ctrl->async_req; + u8 hdgst = nvme_tcp_hdgst_len(queue); + + async->pdu = page_frag_alloc(&queue->pf_cache, + sizeof(struct nvme_tcp_cmd_pdu) + hdgst, + GFP_KERNEL | __GFP_ZERO); + if (!async->pdu) + return -ENOMEM; + + async->queue = &ctrl->queues[0]; + return 0; +} + +static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) +{ + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + struct nvme_tcp_queue *queue = &ctrl->queues[qid]; + + if (!test_and_clear_bit(NVME_TCP_Q_ALLOCATED, &queue->flags)) + return; + + if (queue->hdr_digest || queue->data_digest) + nvme_tcp_free_crypto(queue); + + sock_release(queue->sock); + kfree(queue->pdu); +} + +static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) +{ + struct nvme_tcp_icreq_pdu *icreq; + struct nvme_tcp_icresp_pdu *icresp; + struct msghdr msg = {}; + struct kvec iov; + bool ctrl_hdgst, ctrl_ddgst; + int ret; + + icreq = kzalloc(sizeof(*icreq), GFP_KERNEL); + if (!icreq) + return -ENOMEM; + + icresp = kzalloc(sizeof(*icresp), GFP_KERNEL); + if (!icresp) { + ret = -ENOMEM; + goto free_icreq; + } + + icreq->hdr.type = nvme_tcp_icreq; + icreq->hdr.hlen = sizeof(*icreq); + icreq->hdr.pdo = 0; + icreq->hdr.plen = cpu_to_le32(icreq->hdr.hlen); + icreq->pfv = cpu_to_le16(NVME_TCP_PFV_1_0); + icreq->maxr2t = 0; /* single inflight r2t supported */ + icreq->hpda = 0; /* no alignment constraint */ + if (queue->hdr_digest) + icreq->digest |= NVME_TCP_HDR_DIGEST_ENABLE; + if (queue->data_digest) + icreq->digest |= NVME_TCP_DATA_DIGEST_ENABLE; + + iov.iov_base = icreq; + iov.iov_len = sizeof(*icreq); + ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); + if (ret < 0) + goto free_icresp; + + memset(&msg, 0, sizeof(msg)); + iov.iov_base = icresp; + iov.iov_len = sizeof(*icresp); + ret = kernel_recvmsg(queue->sock, &msg, &iov, 1, + iov.iov_len, msg.msg_flags); + if (ret < 0) + goto free_icresp; + + ret = -EINVAL; + if (icresp->hdr.type != nvme_tcp_icresp) { + pr_err("queue %d: bad type returned %d\n", + nvme_tcp_queue_id(queue), icresp->hdr.type); + goto free_icresp; + } + + if (le32_to_cpu(icresp->hdr.plen) != sizeof(*icresp)) { + pr_err("queue %d: bad pdu length returned %d\n", + nvme_tcp_queue_id(queue), icresp->hdr.plen); + goto free_icresp; + } + + if (icresp->pfv != NVME_TCP_PFV_1_0) { + pr_err("queue %d: bad pfv returned %d\n", + nvme_tcp_queue_id(queue), icresp->pfv); + goto free_icresp; + } + + ctrl_ddgst = !!(icresp->digest & NVME_TCP_DATA_DIGEST_ENABLE); + if ((queue->data_digest && !ctrl_ddgst) || + (!queue->data_digest && ctrl_ddgst)) { + pr_err("queue %d: data digest mismatch host: %s ctrl: %s\n", + nvme_tcp_queue_id(queue), + queue->data_digest ? "enabled" : "disabled", + ctrl_ddgst ? "enabled" : "disabled"); + goto free_icresp; + } + + ctrl_hdgst = !!(icresp->digest & NVME_TCP_HDR_DIGEST_ENABLE); + if ((queue->hdr_digest && !ctrl_hdgst) || + (!queue->hdr_digest && ctrl_hdgst)) { + pr_err("queue %d: header digest mismatch host: %s ctrl: %s\n", + nvme_tcp_queue_id(queue), + queue->hdr_digest ? "enabled" : "disabled", + ctrl_hdgst ? "enabled" : "disabled"); + goto free_icresp; + } + + if (icresp->cpda != 0) { + pr_err("queue %d: unsupported cpda returned %d\n", + nvme_tcp_queue_id(queue), icresp->cpda); + goto free_icresp; + } + + ret = 0; +free_icresp: + kfree(icresp); +free_icreq: + kfree(icreq); + return ret; +} + +static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, + int qid, size_t queue_size) +{ + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + struct nvme_tcp_queue *queue = &ctrl->queues[qid]; + struct linger sol = { .l_onoff = 1, .l_linger = 0 }; + int ret, opt, rcv_pdu_size, n; + + queue->ctrl = ctrl; + INIT_LIST_HEAD(&queue->send_list); + spin_lock_init(&queue->lock); + INIT_WORK(&queue->io_work, nvme_tcp_io_work); + queue->queue_size = queue_size; + + if (qid > 0) + queue->cmnd_capsule_len = ctrl->ctrl.ioccsz * 16; + |