diff options
Diffstat (limited to 'drivers/nvme/host/rdma.c')
| -rw-r--r-- | drivers/nvme/host/rdma.c | 2018 |
1 files changed, 2018 insertions, 0 deletions
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c new file mode 100644 index 000000000000..3e3ce2b0424e --- /dev/null +++ b/drivers/nvme/host/rdma.c @@ -0,0 +1,2018 @@ +/* + * NVMe over Fabrics RDMA host code. + * Copyright (c) 2015-2016 HGST, a Western Digital Company. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/string.h> +#include <linux/jiffies.h> +#include <linux/atomic.h> +#include <linux/blk-mq.h> +#include <linux/types.h> +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/scatterlist.h> +#include <linux/nvme.h> +#include <linux/t10-pi.h> +#include <asm/unaligned.h> + +#include <rdma/ib_verbs.h> +#include <rdma/rdma_cm.h> +#include <rdma/ib_cm.h> +#include <linux/nvme-rdma.h> + +#include "nvme.h" +#include "fabrics.h" + + +#define NVME_RDMA_CONNECT_TIMEOUT_MS 1000 /* 1 second */ + +#define NVME_RDMA_MAX_SEGMENT_SIZE 0xffffff /* 24-bit SGL field */ + +#define NVME_RDMA_MAX_SEGMENTS 256 + +#define NVME_RDMA_MAX_INLINE_SEGMENTS 1 + +#define NVME_RDMA_MAX_PAGES_PER_MR 512 + +#define NVME_RDMA_DEF_RECONNECT_DELAY 20 + +/* + * We handle AEN commands ourselves and don't even let the + * block layer know about them. + */ +#define NVME_RDMA_NR_AEN_COMMANDS 1 +#define NVME_RDMA_AQ_BLKMQ_DEPTH \ + (NVMF_AQ_DEPTH - NVME_RDMA_NR_AEN_COMMANDS) + +struct nvme_rdma_device { + struct ib_device *dev; + struct ib_pd *pd; + struct ib_mr *mr; + struct kref ref; + struct list_head entry; +}; + +struct nvme_rdma_qe { + struct ib_cqe cqe; + void *data; + u64 dma; +}; + +struct nvme_rdma_queue; +struct nvme_rdma_request { + struct ib_mr *mr; + struct nvme_rdma_qe sqe; + struct ib_sge sge[1 + NVME_RDMA_MAX_INLINE_SEGMENTS]; + u32 num_sge; + int nents; + bool inline_data; + bool need_inval; + struct ib_reg_wr reg_wr; + struct ib_cqe reg_cqe; + struct nvme_rdma_queue *queue; + struct sg_table sg_table; + struct scatterlist first_sgl[]; +}; + +enum nvme_rdma_queue_flags { + NVME_RDMA_Q_CONNECTED = (1 << 0), +}; + +struct nvme_rdma_queue { + struct nvme_rdma_qe *rsp_ring; + u8 sig_count; + int queue_size; + size_t cmnd_capsule_len; + struct nvme_rdma_ctrl *ctrl; + struct nvme_rdma_device *device; + struct ib_cq *ib_cq; + struct ib_qp *qp; + + unsigned long flags; + struct rdma_cm_id *cm_id; + int cm_error; + struct completion cm_done; +}; + +struct nvme_rdma_ctrl { + /* read and written in the hot path */ + spinlock_t lock; + + /* read only in the hot path */ + struct nvme_rdma_queue *queues; + u32 queue_count; + + /* other member variables */ + struct blk_mq_tag_set tag_set; + struct work_struct delete_work; + struct work_struct reset_work; + struct work_struct err_work; + + struct nvme_rdma_qe async_event_sqe; + + int reconnect_delay; + struct delayed_work reconnect_work; + + struct list_head list; + + struct blk_mq_tag_set admin_tag_set; + struct nvme_rdma_device *device; + + u64 cap; + u32 max_fr_pages; + + union { + struct sockaddr addr; + struct sockaddr_in addr_in; + }; + + struct nvme_ctrl ctrl; +}; + +static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl) +{ + return container_of(ctrl, struct nvme_rdma_ctrl, ctrl); +} + +static LIST_HEAD(device_list); +static DEFINE_MUTEX(device_list_mutex); + +static LIST_HEAD(nvme_rdma_ctrl_list); +static DEFINE_MUTEX(nvme_rdma_ctrl_mutex); + +static struct workqueue_struct *nvme_rdma_wq; + +/* + * Disabling this option makes small I/O goes faster, but is fundamentally + * unsafe. With it turned off we will have to register a global rkey that + * allows read and write access to all physical memory. + */ +static bool register_always = true; +module_param(register_always, bool, 0444); +MODULE_PARM_DESC(register_always, + "Use memory registration even for contiguous memory regions"); + +static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, + struct rdma_cm_event *event); +static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc); +static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl); + +/* XXX: really should move to a generic header sooner or later.. */ +static inline void put_unaligned_le24(u32 val, u8 *p) +{ + *p++ = val; + *p++ = val >> 8; + *p++ = val >> 16; +} + +static inline int nvme_rdma_queue_idx(struct nvme_rdma_queue *queue) +{ + return queue - queue->ctrl->queues; +} + +static inline size_t nvme_rdma_inline_data_size(struct nvme_rdma_queue *queue) +{ + return queue->cmnd_capsule_len - sizeof(struct nvme_command); +} + +static void nvme_rdma_free_qe(struct ib_device *ibdev, struct nvme_rdma_qe *qe, + size_t capsule_size, enum dma_data_direction dir) +{ + ib_dma_unmap_single(ibdev, qe->dma, capsule_size, dir); + kfree(qe->data); +} + +static int nvme_rdma_alloc_qe(struct ib_device *ibdev, struct nvme_rdma_qe *qe, + size_t capsule_size, enum dma_data_direction dir) +{ + qe->data = kzalloc(capsule_size, GFP_KERNEL); + if (!qe->data) + return -ENOMEM; + + qe->dma = ib_dma_map_single(ibdev, qe->data, capsule_size, dir); + if (ib_dma_mapping_error(ibdev, qe->dma)) { + kfree(qe->data); + return -ENOMEM; + } + + return 0; +} + +static void nvme_rdma_free_ring(struct ib_device *ibdev, + struct nvme_rdma_qe *ring, size_t ib_queue_size, + size_t capsule_size, enum dma_data_direction dir) +{ + int i; + + for (i = 0; i < ib_queue_size; i++) + nvme_rdma_free_qe(ibdev, &ring[i], capsule_size, dir); + kfree(ring); +} + +static struct nvme_rdma_qe *nvme_rdma_alloc_ring(struct ib_device *ibdev, + size_t ib_queue_size, size_t capsule_size, + enum dma_data_direction dir) +{ + struct nvme_rdma_qe *ring; + int i; + + ring = kcalloc(ib_queue_size, sizeof(struct nvme_rdma_qe), GFP_KERNEL); + if (!ring) + return NULL; + + for (i = 0; i < ib_queue_size; i++) { + if (nvme_rdma_alloc_qe(ibdev, &ring[i], capsule_size, dir)) + goto out_free_ring; + } + + return ring; + +out_free_ring: + nvme_rdma_free_ring(ibdev, ring, i, capsule_size, dir); + return NULL; +} + +static void nvme_rdma_qp_event(struct ib_event *event, void *context) +{ + pr_debug("QP event %d\n", event->event); +} + +static int nvme_rdma_wait_for_cm(struct nvme_rdma_queue *queue) +{ + wait_for_completion_interruptible_timeout(&queue->cm_done, + msecs_to_jiffies(NVME_RDMA_CONNECT_TIMEOUT_MS) + 1); + return queue->cm_error; +} + +static int nvme_rdma_create_qp(struct nvme_rdma_queue *queue, const int factor) +{ + struct nvme_rdma_device *dev = queue->device; + struct ib_qp_init_attr init_attr; + int ret; + + memset(&init_attr, 0, sizeof(init_attr)); + init_attr.event_handler = nvme_rdma_qp_event; + /* +1 for drain */ + init_attr.cap.max_send_wr = factor * queue->queue_size + 1; + /* +1 for drain */ + init_attr.cap.max_recv_wr = queue->queue_size + 1; + init_attr.cap.max_recv_sge = 1; + init_attr.cap.max_send_sge = 1 + NVME_RDMA_MAX_INLINE_SEGMENTS; + init_attr.sq_sig_type = IB_SIGNAL_REQ_WR; + init_attr.qp_type = IB_QPT_RC; + init_attr.send_cq = queue->ib_cq; + init_attr.recv_cq = queue->ib_cq; + + ret = rdma_create_qp(queue->cm_id, dev->pd, &init_attr); + + queue->qp = queue->cm_id->qp; + return ret; +} + +static int nvme_rdma_reinit_request(void *data, struct request *rq) +{ + struct nvme_rdma_ctrl *ctrl = data; + struct nvme_rdma_device *dev = ctrl->device; + struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); + int ret = 0; + + if (!req->need_inval) + goto out; + + ib_dereg_mr(req->mr); + + req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG, + ctrl->max_fr_pages); + if (IS_ERR(req->mr)) { + ret = PTR_ERR(req->mr); + req->mr = NULL; + } + + req->need_inval = false; + +out: + return ret; +} + +static void __nvme_rdma_exit_request(struct nvme_rdma_ctrl *ctrl, + struct request *rq, unsigned int queue_idx) +{ + struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx]; + struct nvme_rdma_device *dev = queue->device; + + if (req->mr) + ib_dereg_mr(req->mr); + + nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command), + DMA_TO_DEVICE); +} + +static void nvme_rdma_exit_request(void *data, struct request *rq, + unsigned int hctx_idx, unsigned int rq_idx) +{ + return __nvme_rdma_exit_request(data, rq, hctx_idx + 1); +} + +static void nvme_rdma_exit_admin_request(void *data, struct request *rq, + unsigned int hctx_idx, unsigned int rq_idx) +{ + return __nvme_rdma_exit_request(data, rq, 0); +} + +static int __nvme_rdma_init_request(struct nvme_rdma_ctrl *ctrl, + struct request *rq, unsigned int queue_idx) +{ + struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx]; + struct nvme_rdma_device *dev = queue->device; + struct ib_device *ibdev = dev->dev; + int ret; + + BUG_ON(queue_idx >= ctrl->queue_count); + + ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command), + DMA_TO_DEVICE); + if (ret) + return ret; + + req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG, + ctrl->max_fr_pages); + if (IS_ERR(req->mr)) { + ret = PTR_ERR(req->mr); + goto out_free_qe; + } + + req->queue = queue; + + return 0; + +out_free_qe: + nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command), + DMA_TO_DEVICE); + return -ENOMEM; +} + +static int nvme_rdma_init_request(void *data, struct request *rq, + unsigned int hctx_idx, unsigned int rq_idx, + unsigned int numa_node) +{ + return __nvme_rdma_init_request(data, rq, hctx_idx + 1); +} + +static int nvme_rdma_init_admin_request(void *data, struct request *rq, + unsigned int hctx_idx, unsigned int rq_idx, + unsigned int numa_node) +{ + return __nvme_rdma_init_request(data, rq, 0); +} + +static int nvme_rdma_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, + unsigned int hctx_idx) +{ + struct nvme_rdma_ctrl *ctrl = data; + struct nvme_rdma_queue *queue = &ctrl->queues[hctx_idx + 1]; + + BUG_ON(hctx_idx >= ctrl->queue_count); + + hctx->driver_data = queue; + return 0; +} + +static int nvme_rdma_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, + unsigned int hctx_idx) +{ + struct nvme_rdma_ctrl *ctrl = data; + struct nvme_rdma_queue *queue = &ctrl->queues[0]; + + BUG_ON(hctx_idx != 0); + + hctx->driver_data = queue; + return 0; +} + +static void nvme_rdma_free_dev(struct kref *ref) +{ + struct nvme_rdma_device *ndev = + container_of(ref, struct nvme_rdma_device, ref); + + mutex_lock(&device_list_mutex); + list_del(&ndev->entry); + mutex_unlock(&device_list_mutex); + + if (!register_always) + ib_dereg_mr(ndev->mr); + ib_dealloc_pd(ndev->pd); + + kfree(ndev); +} + +static void nvme_rdma_dev_put(struct nvme_rdma_device *dev) +{ + kref_put(&dev->ref, nvme_rdma_free_dev); +} + +static int nvme_rdma_dev_get(struct nvme_rdma_device *dev) +{ + return kref_get_unless_zero(&dev->ref); +} + +static struct nvme_rdma_device * +nvme_rdma_find_get_device(struct rdma_cm_id *cm_id) +{ + struct nvme_rdma_device *ndev; + + mutex_lock(&device_list_mutex); + list_for_each_entry(ndev, &device_list, entry) { + if (ndev->dev->node_guid == cm_id->device->node_guid && + nvme_rdma_dev_get(ndev)) + goto out_unlock; + } + + ndev = kzalloc(sizeof(*ndev), GFP_KERNEL); + if (!ndev) + goto out_err; + + ndev->dev = cm_id->device; + kref_init(&ndev->ref); + + ndev->pd = ib_alloc_pd(ndev->dev); + if (IS_ERR(ndev->pd)) + goto out_free_dev; + + if (!register_always) { + ndev->mr = ib_get_dma_mr(ndev->pd, + IB_ACCESS_LOCAL_WRITE | + IB_ACCESS_REMOTE_READ | + IB_ACCESS_REMOTE_WRITE); + if (IS_ERR(ndev->mr)) + goto out_free_pd; + } + + if (!(ndev->dev->attrs.device_cap_flags & + IB_DEVICE_MEM_MGT_EXTENSIONS)) { + dev_err(&ndev->dev->dev, + "Memory registrations not supported.\n"); + goto out_free_mr; + } + + list_add(&ndev->entry, &device_list); +out_unlock: + mutex_unlock(&device_list_mutex); + return ndev; + +out_free_mr: + if (!register_always) + ib_dereg_mr(ndev->mr); +out_free_pd: + ib_dealloc_pd(ndev->pd); +out_free_dev: + kfree(ndev); +out_err: + mutex_unlock(&device_list_mutex); + return NULL; +} + +static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue) +{ + struct nvme_rdma_device *dev = queue->device; + struct ib_device *ibdev = dev->dev; + + rdma_destroy_qp(queue->cm_id); + ib_free_cq(queue->ib_cq); + + nvme_rdma_free_ring(ibdev, queue->rsp_ring, queue->queue_size, + sizeof(struct nvme_completion), DMA_FROM_DEVICE); + + nvme_rdma_dev_put(dev); +} + +static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue, + struct nvme_rdma_device *dev) +{ + struct ib_device *ibdev = dev->dev; + const int send_wr_factor = 3; /* MR, SEND, INV */ + const int cq_factor = send_wr_factor + 1; /* + RECV */ + int comp_vector, idx = nvme_rdma_queue_idx(queue); + + int ret; + + queue->device = dev; + + /* + * The admin queue is barely used once the controller is live, so don't + * bother to spread it out. + */ + if (idx == 0) + comp_vector = 0; + else + comp_vector = idx % ibdev->num_comp_vectors; + + + /* +1 for ib_stop_cq */ + queue->ib_cq = ib_alloc_cq(dev->dev, queue, + cq_factor * queue->queue_size + 1, comp_vector, + IB_POLL_SOFTIRQ); + if (IS_ERR(queue->ib_cq)) { + ret = PTR_ERR(queue->ib_cq); + goto out; + } + + ret = nvme_rdma_create_qp(queue, send_wr_factor); + if (ret) + goto out_destroy_ib_cq; + + queue->rsp_ring = nvme_rdma_alloc_ring(ibdev, queue->queue_size, + sizeof(struct nvme_completion), DMA_FROM_DEVICE); + if (!queue->rsp_ring) { + ret = -ENOMEM; + goto out_destroy_qp; + } + + return 0; + +out_destroy_qp: + ib_destroy_qp(queue->qp); +out_destroy_ib_cq: + ib_free_cq(queue->ib_cq); +out: + return ret; +} + +static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl, + int idx, size_t queue_size) +{ + struct nvme_rdma_queue *queue; + int ret; + + queue = &ctrl->queues[idx]; + queue->ctrl = ctrl; + init_completion(&queue->cm_done); + + if (idx > 0) + queue->cmnd_capsule_len = ctrl->ctrl.ioccsz * 16; + else + queue->cmnd_capsule_len = sizeof(struct nvme_command); + + queue->queue_size = queue_size; + + queue->cm_id = rdma_create_id(&init_net, nvme_rdma_cm_handler, queue, + RDMA_PS_TCP, IB_QPT_RC); + if (IS_ERR(queue->cm_id)) { + dev_info(ctrl->ctrl.device, + "failed to create CM ID: %ld\n", PTR_ERR(queue->cm_id)); + return PTR_ERR(queue->cm_id); + } + + queue->cm_error = -ETIMEDOUT; + ret = rdma_resolve_addr(queue->cm_id, NULL, &ctrl->addr, + NVME_RDMA_CONNECT_TIMEOUT_MS); + if (ret) { + dev_info(ctrl->ctrl.device, + "rdma_resolve_addr failed (%d).\n", ret); + goto out_destroy_cm_id; + } + + ret = nvme_rdma_wait_for_cm(queue); + if (ret) { + dev_info(ctrl->ctrl.device, + "rdma_resolve_addr wait failed (%d).\n", ret); + goto out_destroy_cm_id; + } + + set_bit(NVME_RDMA_Q_CONNECTED, &queue->flags); + + return 0; + +out_destroy_cm_id: + rdma_destroy_id(queue->cm_id); + return ret; +} + +static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) +{ + rdma_disconnect(queue->cm_id); + ib_drain_qp(queue->qp); +} + +static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) +{ + nvme_rdma_destroy_queue_ib(queue); + rdma_destroy_id(queue->cm_id); +} + +static void nvme_rdma_stop_and_free_queue(struct nvme_rdma_queue *queue) +{ + if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) + return; + nvme_rdma_stop_queue(queue); + nvme_rdma_free_queue(queue); +} + +static void nvme_rdma_free_io_queues(struct nvme_rdma_ctrl *ctrl) +{ + int i; + + for (i = 1; i < ctrl->queue_count; i++) + nvme_rdma_stop_and_free_queue(&ctrl->queues[i]); +} + +static int nvme_rdma_connect_io_queues(struct nvme_rdma_ctrl *ctrl) +{ + int i, ret = 0; + + for (i = 1; i < ctrl->queue_count; i++) { + ret = nvmf_connect_io_queue(&ctrl->ctrl, i); + if (ret) + break; + } + + return ret; +} + +static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl) +{ + int i, ret; + + for (i = 1; i < ctrl->queue_count; i++) { + ret = nvme_rdma_init_queue(ctrl, i, ctrl->ctrl.sqsize); + if (ret) { + dev_info(ctrl->ctrl.device, + "failed to initialize i/o queue: %d\n", ret); + goto out_free_queues; + } + } + + return 0; + +out_free_queues: + for (; i >= 1; i--) + nvme_rdma_stop_and_free_queue(&ctrl->queues[i]); + + return ret; +} + +static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl) +{ + nvme_rdma_free_qe(ctrl->queues[0].device->dev, &ctrl->async_event_sqe, + sizeof(struct nvme_command), DMA_TO_DEVICE); + nvme_rdma_stop_and_free_queue(&ctrl->queues[0]); + blk_cleanup_queue(ctrl->ctrl.admin_q); + blk_mq_free_tag_set(&ctrl->admin_tag_set); + nvme_rdma_dev_put(ctrl->device); +} + +static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl) +{ + struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); + + if (list_empty(&ctrl->list)) + goto free_ctrl; + + mutex_lock(&nvme_rdma_ctrl_mutex); + list_del(&ctrl->list); + mutex_unlock(&nvme_rdma_ctrl_mutex); + + if (ctrl->ctrl.tagset) { + blk_cleanup_queue(ctrl->ctrl.connect_q); + blk_mq_free_tag_set(&ctrl->tag_set); + nvme_rdma_dev_put(ctrl->device); + } + kfree(ctrl->queues); + nvmf_free_options(nctrl->opts); +free_ctrl: + kfree(ctrl); +} + +static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) +{ + struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work), + struct nvme_rdma_ctrl, reconnect_work); + bool changed; + int ret; + + if (ctrl->queue_count > 1) { + nvme_rdma_free_io_queues(ctrl); + + ret = blk_mq_reinit_tagset(&ctrl->tag_set); + if (ret) + goto requeue; + } + + nvme_rdma_stop_and_free_queue(&ctrl->queues[0]); + + ret = blk_mq_reinit_tagset(&ctrl->admin_tag_set); + if (ret) + goto requeue; + + ret = nvme_rdma_init_queue(ctrl, 0, NVMF_AQ_DEPTH); + if (ret) + goto requeue; + + blk_mq_start_stopped_hw_queues(ctrl->ctrl.admin_q, true); + + ret = nvmf_connect_admin_queue(&ctrl->ctrl); + if (ret) + goto stop_admin_q; + + ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap); + if (ret) + goto stop_admin_q; + + nvme_start_keep_alive(&ctrl->ctrl); + + if (ctrl->queue_count > 1) { + ret = nvme_rdma_init_io_queues(ctrl); + if (ret) + goto stop_admin_q; + + ret = nvme_rdma_connect_io_queues(ctrl); + if (ret) + goto stop_admin_q; + } + + changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); + WARN_ON_ONCE(!changed); + + if (ctrl->queue_count > 1) + nvme_start_queues(&ctrl->ctrl); + + dev_info(ctrl->ctrl.device, "Successfully reconnected\n"); + + return; + +stop_admin_q: + blk_mq_stop_hw_queues(ctrl->ctrl.admin_q); +requeue: + /* Make sure we are not resetting/deleting */ + if (ctrl->ctrl.state == NVME_CTRL_RECONNECTING) { + dev_info(ctrl->ctrl.device, + "Failed reconnect attempt, requeueing...\n"); + queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work, + ctrl->reconnect_delay * HZ); + } +} + +static void nvme_rdma_error_recovery_work(struct work_struct *work) +{ + struct nvme_rdma_ctrl *ctrl = container_of(work, + struct nvme_rdma_ctrl, err_work); + + nvme_stop_keep_alive(&ctrl->ctrl); + if (ctrl->queue_count > 1) + nvme_stop_queues(&ctrl->ctrl); + blk_mq_stop_hw_queues(ctrl->ctrl.admin_q); + + /* We must take care of fastfail/requeue all our inflight requests */ + if (ctrl->queue_count > 1) + blk_mq_tagset_busy_iter(&ctrl->tag_set, + nvme_cancel_request, &ctrl->ctrl); + blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, + nvme_cancel_request, &ctrl->ctrl); + + dev_info(ctrl->ctrl.device, "reconnecting in %d seconds\n", + ctrl->reconnect_delay); + + queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work, + ctrl->reconnect_delay * HZ); +} + +static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl) +{ + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) + return; + + queue_work(nvme_rdma_wq, &ctrl->err_work); +} + +static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc, + const char *op) +{ + struct nvme_rdma_queue *queue = cq->cq_context; + struct nvme_rdma_ctrl *ctrl = queue->ctrl; + + if (ctrl->ctrl.state == NVME_CTRL_LIVE) + dev_info(ctrl->ctrl.device, + "%s for CQE 0x%p failed with status %s (%d)\n", + op, wc->wr_cqe, + ib_wc_status_msg(wc->status), wc->status); + nvme_rdma_error_recovery(ctrl); +} + +static void nvme_rdma_memreg_done(struct ib_cq *cq, struct ib_wc *wc) +{ + if (unlikely(wc->status != IB_WC_SUCCESS)) + nvme_rdma_wr_error(cq, wc, "MEMREG"); +} + +static void nvme_rdma_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc) +{ + if (unlikely(wc->status != IB_WC_SUCCESS)) + nvme_rdma_wr_error(cq, wc, "LOCAL_INV"); +} + +static int nvme_rdma_inv_rkey(struct nvme_rdma_queue *queue, + struct nvme_rdma_request *req) +{ + struct ib_send_wr *bad_wr; + struct ib_send_wr wr = { + .opcode = IB_WR_LOCAL_INV, + .next = NULL, + .num_sge = 0, + .send_flags = 0, + .ex.invalidate_rkey = req->mr->rkey, + }; + + req->reg_cqe.done = nvme_rdma_inv_rkey_done; + wr.wr_cqe = &req->reg_cqe; + + return ib_post_send(queue->qp, &wr, &bad_wr); +} + +static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue, + struct request *rq) +{ + struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_rdma_ctrl *ctrl = queue->ctrl; + struct nvme_rdma_device *dev = queue->device; + struct ib_device *ibdev = dev->dev; + int res; + + if (!blk_rq_bytes(rq)) + return; + + if (req->need_inval) { + res = nvme_rdma_inv_rkey(queue, req); + if (res < 0) { + dev_err(ctrl->ctrl.device, + "Queueing INV WR for rkey %#x failed (%d)\n", + req->mr->rkey, res); + nvme_rdma_error_recovery(queue->ctrl); + } + } + + ib_dma_unmap_sg(ibdev, req->sg_table.sgl, + req->nents, rq_data_dir(rq) == + WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE); + + nvme_cleanup_cmd(rq); + sg_free_table_chained(&req->sg_table, true); +} + +static int nvme_rdma_set_sg_null(struct nvme_command *c) +{ + struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl; + + sg->addr = 0; + put_unaligned_le24(0, sg->length); + put_unaligned_le32(0, sg->key); + sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4; + return 0; +} + +static int nvme_rdma_map_sg_inline(struct nvme_rdma_queue *queue, + struct nvme_rdma_request *req, struct nvme_command *c) +{ + struct nvme_sgl_desc *sg = &c->common.dptr.sgl; + + req->sge[1].addr = sg_dma_address(req->sg_table.sgl); + req->sge[1].length = sg_dma_len(req->sg_table.sgl); + req->sge[1].lkey = queue->device->pd->local_dma_lkey; + + sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff); + sg->length = cpu_to_le32(sg_dma_len(req->sg_table.sgl)); + sg->type = (NVME_SGL_FMT_DATA_DESC << 4) | NVME_SGL_FMT_OFFSET; + + req->inline_data = true; + req->num_sge++; + return 0; +} + +static int nvme_rdma_map_sg_single(struct nvme_rdma_queue *queue, + struct nvme_rdma_request *req, struct nvme_command *c) +{ + struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl; + + sg->addr = cpu_to_le64(sg_dma_address(req->sg_table.sgl)); + put_unaligned_le24(sg_dma_len(req->sg_table.sgl), sg->length); + put_unaligned_le32(queue->device->mr->rkey, sg->key); + sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4; + return 0; +} + +static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue, + struct nvme_rdma_request *req, struct nvme_command *c, + int count) +{ + struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl; + int nr; + + nr = ib_map_mr_sg(req->mr, req->sg_table.sgl, count, NULL, PAGE_SIZE); + if (nr < count) { + if (nr < 0) + return nr; + return -EINVAL; + } + + ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey)); + + req->reg_cqe.done = nvme_rdma_memreg_done; + memset(&req->reg_wr, 0, sizeof(req->reg_wr)); + req->reg_wr.wr.opcode = IB_WR_REG_MR; + req->reg_wr.wr.wr_cqe = &req->reg_cqe; + req->reg_wr.wr.num_sge = 0; + req->reg_wr.mr = req->mr; + req->reg_wr.key = req->mr->rkey; + req->reg_wr.access = IB_ACCESS_LOCAL_WRITE | + IB_ACCESS_REMOTE_READ | + IB_ACCESS_REMOTE_WRITE; + + req->need_inval = true; + + sg->addr = cpu_to_le64(req->mr->iova); + put_unaligned_le24(req->mr->length, sg->length); + put_unaligned_le32(req->mr->rkey, sg->key); + sg->type = (NVME_KEY_SGL_FMT_DATA_DESC << 4) | + NVME_SGL_FMT_INVALIDATE; + + return 0; +} + +static int nvme_rdma_map_data(struct nvme_rdma_queue *queue, + struct request *rq, unsigned int map_len, + struct nvme_command *c) +{ + struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_rdma_device *dev = queue->device; + struct ib_device *ibdev = dev->dev; + int nents, count; + int ret; + + req->num_sge = 1; + req->inline_data = false; + req->need_inval = false; + + c->common.flags |= NVME_CMD_SGL_METABUF; + + if (!blk_rq_bytes(rq)) + return nvme_rdma_set_sg_null(c); + + req->sg_table.sgl = req->first_sgl; + ret = sg_alloc_table_chained(&req->sg_table, rq->nr_phys_segments, + req->sg_table.sgl); + if (ret) + return -ENOMEM; + + nents = blk_rq_map_sg(rq->q, rq, req->sg_table.sgl); + BUG_ON(nents > rq->nr_phys_segments); + req->nents = nents; + + count = ib_dma_map_sg(ibdev, req->sg_table.sgl, nents, + rq_data_dir(rq) == WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE); + if (unlikely(count <= 0)) { + sg_free_table_chained(&req->sg_table, true); + return -EIO; + } + + if (count == 1) { + if (rq_data_dir(rq) == WRITE && + map_len <= nvme_rdma_inline_data_size(queue) && + nvme_rdma_queue_idx(queue)) + return nvme_rdma_map_sg_inline(queue, req, c); + + if (!register_always) + return nvme_rdma_map_sg_single(queue, req, c); + } + + return nvme_rdma_map_sg_fr(queue, req, c, count); +} + +static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc) +{ + if (unlikely(wc->status != IB_WC_SUCCESS)) + nvme_rdma_wr_error(cq, wc, "SEND"); +} + +static int nvme_rdma_post_send(struct nvme_rdma_queue *queue, + struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge, + struct ib_send_wr *first, bool flush) +{ + struct ib_send_wr wr, *bad_wr; + int ret; + + sge->addr = qe->dma; + sge->length = sizeof(struct nvme_command), + sge->lkey = queue->device->pd->local_dma_lkey; + + qe->cqe.done = nvme_rdma_send_done; + + wr.next = NULL; + wr.wr_cqe = &qe->cqe; + wr.sg_list = sge; + wr.num_sge = num_sge; + wr.opcode = IB_WR_SEND; + wr.send_flags = 0; + + /* + * Unsignalled send completions are another giant desaster in the + * IB Verbs spec: If we don't regularly post signalled sends + * the send queue will fill up and only a QP reset will rescue us. + * Would have been way to obvious to handle this in hardware or + * at least the RDMA stack.. + * + * This messy and racy code sniplet is copy and pasted from the iSER + * initiator, and the magic '32' comes from there as well. + * + * Always signal the flushes. The magic request used for the flush + * sequencer is not allocated in our driver's tagset and it's + * triggered to be freed by blk_cleanup_queue(). So we need to + * always mark it as signaled to ensure that the "wr_cqe", which is + * embeded in request's payload, is not freed when __ib_process_cq() + * calls wr_cqe->done(). + */ + if ((++queue->sig_count % 32) == 0 || flush) + wr.send_flags |= IB_SEND_SIGNALED; + + if (first) + first->next = ≀ + else + first = ≀ + + ret = ib_post_send(queue->qp, first, &bad_wr); + if (ret) { + dev_err(queue->ctrl->ctrl.device, + "%s failed with error code %d\n", __func__, ret); + } + return ret; +} + +static int nvme_rdma_post_recv(struct nvme_rdma_queue *queue, + struct nvme_rdma_qe *qe) +{ + struct ib_recv_wr wr, *bad_wr; + struct ib_sge list; + int ret; + + list.addr = qe->dma; + list.length = sizeof(struct nvme_completion); + list.lkey = queue->device->pd->local_dma_lkey; + + qe->cqe.done = nvme_rdma_recv_done; + + wr.next = NULL; + wr.wr_cqe = &qe->cqe; + wr.sg_list = &list; + wr.num_sge = 1; + + ret = ib_post_recv(queue->qp, &wr, &bad_wr); + if (ret) { + dev_err(queue->ctrl->ctrl.device, + "%s failed with error code %d\n", __func__, ret); + } + return ret; +} + +static struct blk_mq_tags *nvme_rdma_tagset(struct nvme_rdma_queue *queue) +{ + u32 queue_idx = nvme_rdma_queue_idx(queue); + + if (queue_idx == 0) + return queue->ctrl->admin_tag_set.tags[queue_idx]; + return queue->ctrl->tag_set.tags[queue_idx - 1]; +} + +static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg, int aer_idx) +{ + struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(arg); + struct nvme_rdma_queue *queue = &ctrl->queues[0]; + struct ib_device *dev = queue->device->dev; + struct nvme_rdma_qe *sqe = &ctrl->async_event_sqe; + struct nvme_command *cmd = sqe->data; + struct ib_sge sge; + int ret; + + if (WARN_ON_ONCE(aer_idx != 0)) + return; + + ib_dma_sync_single_for_cpu(dev, sqe->dma, sizeof(*cmd), DMA_TO_DEVICE); + + memset(cmd, 0, sizeof(*cmd)); + cmd->common.opcode = nvme_admin_async_event; + cmd->common.command_id = NVME_RDMA_AQ_BLKMQ_DEPTH; + cmd->common.flags |= NVME_CMD_SGL_METABUF; + nvme_rdma_set_sg_null(cmd); + + ib_dma_sync_single_for_device(dev, sqe->dma, sizeof(*cmd), + DMA_TO_DEVICE); + + ret = nvme_rdma_post_send(queue, sqe, &sge, 1, NULL, false); + WARN_ON_ONCE(ret); +} + +static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue, + struct nvme_completion *cqe, struct ib_wc *wc, int tag) +{ + u16 status = le16_to_cpu(cqe->status); + struct request *rq; + struct nvme_rdma_request *req; + int ret = 0; + + status >>= 1; + + rq = blk_mq_tag_to_rq(nvme_rdma_tagset(queue), cqe->command_id); + if (!rq) { + dev_err(queue->ctrl->ctrl.device, + "tag 0x%x on QP %#x not found\n", + cqe->command_id, queue->qp->qp_num); + nvme_rdma_error_recovery(queue->ctrl); + return ret; + } + req = blk_mq_rq_to_pdu(rq); + + if (rq->cmd_type == REQ_TYPE_DRV_PRIV && rq->special) + memcpy(rq->special, cqe, sizeof(*cqe)); + + if (rq->tag == tag) + ret = 1; + + if ((wc->wc_flags & IB_WC_WITH_INVALIDATE) && + wc->ex.invalidate_rkey == req->mr->rkey) + req->need_inval = false; + + blk_mq_complete_request(rq, status); + + return ret; +} + +static int __nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc, int tag) +{ + struct nvme_rdma_qe *qe = + container_of(wc->wr_cqe, struct nvme_rdma_qe, cqe); + struct nvme_rdma_queue *queue = cq->cq_context; + struct ib_device *ibdev = queue->device->dev; + struct nvme_completion *cqe = qe->data; + const size_t len = sizeof(struct nvme_completion); + int ret = 0; + + if (unlikely(wc->status != IB_WC_SUCCESS)) { + nvme_rdma_wr_error(cq, wc, "RECV"); + return 0; + } + + ib_dma_sync_single_for_cpu(ibdev, qe->dma, len, DMA_FROM_DEVICE); + /* + * 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_rdma_queue_idx(queue) == 0 |