Commit eca53cb6 authored by Jens Axboe's avatar Jens Axboe
Browse files

Merge branch 'nvme-4.19' of git://git.infradead.org/nvme into for-4.19/block 

Pull NVMe updates from Christoph:

"Highlights:

 - massively improved tracepoints (Keith Busch)
 - support for larger inline data in the RDMA host and target
   (Steve Wise)
 - RDMA setup/teardown path fixes and refactor (Sagi Grimberg)
 - Command Supported and Effects log support for the NVMe target
   (Chaitanya Kulkarni)
 - buffered I/O support for the NVMe target (Chaitanya Kulkarni)

 plus the usual set of cleanups and small enhancements."

* 'nvme-4.19' of git://git.infradead.org/nvme:
  nvmet: don't use uuid_le type
  nvmet: check fileio lba range access boundaries
  nvmet: fix file discard return status
  nvme-rdma: centralize admin/io queue teardown sequence
  nvme-rdma: centralize controller setup sequence
  nvme-rdma: unquiesce queues when deleting the controller
  nvme-rdma: mark expected switch fall-through
  nvme: add disk name to trace events
  nvme: add controller name to trace events
  nvme: use hw qid in trace events
  nvme: cache struct nvme_ctrl reference to struct nvme_request
  nvmet-rdma: add an error flow for post_recv failures
  nvmet-rdma: add unlikely check in the fast path
  nvmet-rdma: support max(16KB, PAGE_SIZE) inline data
  nvme-rdma: support up to 4 segments of inline data
  nvmet: add buffered I/O support for file backed ns
  nvmet: add commands supported and effects log page
  nvme: move init of keep_alive work item to controller initialization
  nvme.h: resync with nvme-cli
parents 42c9cdfe 1b0d2745

drivers/nvme/host/core.c

+5 −7
Original line number Diff line number Diff line
@@ -652,10 +652,7 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req, 
	}



	cmd->common.command_id = req->tag;

	if (ns)

		trace_nvme_setup_nvm_cmd(req->q->id, cmd);

	else

		trace_nvme_setup_admin_cmd(cmd);

	trace_nvme_setup_cmd(req, cmd);

	return ret;

}

EXPORT_SYMBOL_GPL(nvme_setup_cmd);
@@ -848,9 +845,6 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl) 
	if (unlikely(ctrl->kato == 0))

		return;



	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);

	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));

	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;

	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);

}
@@ -3484,6 +3478,10 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, 
	INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);

	INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);



	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);

	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));

	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;



	ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL);

	if (ret < 0)

		goto out;

drivers/nvme/host/fc.c

+1 −0
Original line number Diff line number Diff line
@@ -1737,6 +1737,7 @@ nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq, 
	int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0;

	struct nvme_fc_queue *queue = &ctrl->queues[queue_idx];



	nvme_req(rq)->ctrl = &ctrl->ctrl;

	return __nvme_fc_init_request(ctrl, queue, op, rq, queue->rqcnt++);

}

drivers/nvme/host/nvme.h

+8 −0
Original line number Diff line number Diff line
@@ -102,6 +102,7 @@ struct nvme_request { 
	u8			retries;

	u8			flags;

	u16			status;

	struct nvme_ctrl	*ctrl;

};



/*
@@ -119,6 +120,13 @@ static inline struct nvme_request *nvme_req(struct request *req) 
	return blk_mq_rq_to_pdu(req);

}



static inline u16 nvme_req_qid(struct request *req)

{

	if (!req->rq_disk)

		return 0;

	return blk_mq_unique_tag_to_hwq(blk_mq_unique_tag(req)) + 1;

}



/* The below value is the specific amount of delay needed before checking

 * readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the

 * NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was

drivers/nvme/host/pci.c

+2 −0
Original line number Diff line number Diff line
@@ -418,6 +418,8 @@ static int nvme_init_request(struct blk_mq_tag_set *set, struct request *req, 


	BUG_ON(!nvmeq);

	iod->nvmeq = nvmeq;



	nvme_req(req)->ctrl = &dev->ctrl;

	return 0;

}

drivers/nvme/host/rdma.c

+111 −123
Original line number Diff line number Diff line
@@ -40,13 +40,14 @@ 


#define NVME_RDMA_MAX_SEGMENTS		256



#define NVME_RDMA_MAX_INLINE_SEGMENTS	1

#define NVME_RDMA_MAX_INLINE_SEGMENTS	4



struct nvme_rdma_device {

	struct ib_device	*dev;

	struct ib_pd		*pd;

	struct kref		ref;

	struct list_head	entry;

	unsigned int		num_inline_segments;

};



struct nvme_rdma_qe {
@@ -117,6 +118,7 @@ struct nvme_rdma_ctrl { 
	struct sockaddr_storage src_addr;



	struct nvme_ctrl	ctrl;

	bool			use_inline_data;

};



static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl)
@@ -249,7 +251,7 @@ static int nvme_rdma_create_qp(struct nvme_rdma_queue *queue, const int factor) 
	/* +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.cap.max_send_sge = 1 + dev->num_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;
@@ -286,6 +288,7 @@ static int nvme_rdma_init_request(struct blk_mq_tag_set *set, 
	struct ib_device *ibdev = dev->dev;

	int ret;



	nvme_req(rq)->ctrl = &ctrl->ctrl;

	ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),

			DMA_TO_DEVICE);

	if (ret)
@@ -374,6 +377,8 @@ nvme_rdma_find_get_device(struct rdma_cm_id *cm_id) 
		goto out_free_pd;

	}



	ndev->num_inline_segments = min(NVME_RDMA_MAX_INLINE_SEGMENTS,

					ndev->dev->attrs.max_sge - 1);

	list_add(&ndev->entry, &device_list);

out_unlock:

	mutex_unlock(&device_list_mutex);
@@ -868,6 +873,31 @@ out_free_io_queues: 
	return ret;

}



static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,

		bool remove)

{

	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);

	nvme_rdma_stop_queue(&ctrl->queues[0]);

	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_cancel_request,

			&ctrl->ctrl);

	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);

	nvme_rdma_destroy_admin_queue(ctrl, remove);

}



static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,

		bool remove)

{

	if (ctrl->ctrl.queue_count > 1) {

		nvme_stop_queues(&ctrl->ctrl);

		nvme_rdma_stop_io_queues(ctrl);

		blk_mq_tagset_busy_iter(&ctrl->tag_set, nvme_cancel_request,

				&ctrl->ctrl);

		if (remove)

			nvme_start_queues(&ctrl->ctrl);

		nvme_rdma_destroy_io_queues(ctrl, remove);

	}

}



static void nvme_rdma_stop_ctrl(struct nvme_ctrl *nctrl)

{

	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
@@ -912,21 +942,44 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl) 
	}

}



static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)

static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)

{

	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),

			struct nvme_rdma_ctrl, reconnect_work);

	int ret = -EINVAL;

	bool changed;

	int ret;



	++ctrl->ctrl.nr_reconnects;



	ret = nvme_rdma_configure_admin_queue(ctrl, false);

	ret = nvme_rdma_configure_admin_queue(ctrl, new);

	if (ret)

		goto requeue;

		return ret;



	if (ctrl->ctrl.icdoff) {

		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");

		goto destroy_admin;

	}



	if (!(ctrl->ctrl.sgls & (1 << 2))) {

		dev_err(ctrl->ctrl.device,

			"Mandatory keyed sgls are not supported!\n");

		goto destroy_admin;

	}



	if (ctrl->ctrl.opts->queue_size > ctrl->ctrl.sqsize + 1) {

		dev_warn(ctrl->ctrl.device,

			"queue_size %zu > ctrl sqsize %u, clamping down\n",

			ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);

	}



	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {

		dev_warn(ctrl->ctrl.device,

			"sqsize %u > ctrl maxcmd %u, clamping down\n",

			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);

		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;

	}



	if (ctrl->ctrl.sgls & (1 << 20))

		ctrl->use_inline_data = true;



	if (ctrl->ctrl.queue_count > 1) {

		ret = nvme_rdma_configure_io_queues(ctrl, false);

		ret = nvme_rdma_configure_io_queues(ctrl, new);

		if (ret)

			goto destroy_admin;

	}
@@ -935,10 +988,31 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) 
	if (!changed) {

		/* state change failure is ok if we're in DELETING state */

		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);

		return;

		ret = -EINVAL;

		goto destroy_io;

	}



	nvme_start_ctrl(&ctrl->ctrl);

	return 0;



destroy_io:

	if (ctrl->ctrl.queue_count > 1)

		nvme_rdma_destroy_io_queues(ctrl, new);

destroy_admin:

	nvme_rdma_stop_queue(&ctrl->queues[0]);

	nvme_rdma_destroy_admin_queue(ctrl, new);

	return ret;

}



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);



	++ctrl->ctrl.nr_reconnects;



	if (nvme_rdma_setup_ctrl(ctrl, false))

		goto requeue;



	dev_info(ctrl->ctrl.device, "Successfully reconnected (%d attempts)\n",

			ctrl->ctrl.nr_reconnects);
@@ -947,9 +1021,6 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) 


	return;



destroy_admin:

	nvme_rdma_stop_queue(&ctrl->queues[0]);

	nvme_rdma_destroy_admin_queue(ctrl, false);

requeue:

	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",

			ctrl->ctrl.nr_reconnects);
@@ -962,27 +1033,9 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) 
			struct nvme_rdma_ctrl, err_work);



	nvme_stop_keep_alive(&ctrl->ctrl);



	if (ctrl->ctrl.queue_count > 1) {

		nvme_stop_queues(&ctrl->ctrl);

		nvme_rdma_stop_io_queues(ctrl);

		blk_mq_tagset_busy_iter(&ctrl->tag_set,

					nvme_cancel_request, &ctrl->ctrl);

		nvme_rdma_destroy_io_queues(ctrl, false);

	}



	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);

	nvme_rdma_stop_queue(&ctrl->queues[0]);

	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,

				nvme_cancel_request, &ctrl->ctrl);

	nvme_rdma_destroy_admin_queue(ctrl, false);



	/*

	 * queues are not a live anymore, so restart the queues to fail fast

	 * new IO

	 */

	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);

	nvme_rdma_teardown_io_queues(ctrl, false);

	nvme_start_queues(&ctrl->ctrl);

	nvme_rdma_teardown_admin_queue(ctrl, false);



	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {

		/* state change failure is ok if we're in DELETING state */
@@ -1090,19 +1143,27 @@ static int nvme_rdma_set_sg_null(struct nvme_command *c) 
}



static int nvme_rdma_map_sg_inline(struct nvme_rdma_queue *queue,

		struct nvme_rdma_request *req, struct nvme_command *c)

		struct nvme_rdma_request *req, struct nvme_command *c,

		int count)

{

	struct nvme_sgl_desc *sg = &c->common.dptr.sgl;

	struct scatterlist *sgl = req->sg_table.sgl;

	struct ib_sge *sge = &req->sge[1];

	u32 len = 0;

	int i;



	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;

	for (i = 0; i < count; i++, sgl++, sge++) {

		sge->addr = sg_dma_address(sgl);

		sge->length = sg_dma_len(sgl);

		sge->lkey = queue->device->pd->local_dma_lkey;

		len += sge->length;

	}



	sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff);

	sg->length = cpu_to_le32(sg_dma_len(req->sg_table.sgl));

	sg->length = cpu_to_le32(len);

	sg->type = (NVME_SGL_FMT_DATA_DESC << 4) | NVME_SGL_FMT_OFFSET;



	req->num_sge++;

	req->num_sge += count;

	return 0;

}
@@ -1195,15 +1256,16 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue, 
		goto out_free_table;

	}



	if (count == 1) {

	if (count <= dev->num_inline_segments) {

		if (rq_data_dir(rq) == WRITE && nvme_rdma_queue_idx(queue) &&

		    queue->ctrl->use_inline_data &&

		    blk_rq_payload_bytes(rq) <=

				nvme_rdma_inline_data_size(queue)) {

			ret = nvme_rdma_map_sg_inline(queue, req, c);

			ret = nvme_rdma_map_sg_inline(queue, req, c, count);

			goto out;

		}



		if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {

		if (count == 1 && dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {

			ret = nvme_rdma_map_sg_single(queue, req, c);

			goto out;

		}
@@ -1574,6 +1636,7 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, 
	case RDMA_CM_EVENT_CONNECT_ERROR:

	case RDMA_CM_EVENT_UNREACHABLE:

		nvme_rdma_destroy_queue_ib(queue);

		/* fall through */

	case RDMA_CM_EVENT_ADDR_ERROR:

		dev_dbg(queue->ctrl->ctrl.device,

			"CM error event %d\n", ev->event);
@@ -1736,25 +1799,12 @@ static const struct blk_mq_ops nvme_rdma_admin_mq_ops = { 


static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)

{

	if (ctrl->ctrl.queue_count > 1) {

		nvme_stop_queues(&ctrl->ctrl);

		nvme_rdma_stop_io_queues(ctrl);

		blk_mq_tagset_busy_iter(&ctrl->tag_set,

					nvme_cancel_request, &ctrl->ctrl);

		nvme_rdma_destroy_io_queues(ctrl, shutdown);

	}



	nvme_rdma_teardown_io_queues(ctrl, shutdown);

	if (shutdown)

		nvme_shutdown_ctrl(&ctrl->ctrl);

	else

		nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);



	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);

	nvme_rdma_stop_queue(&ctrl->queues[0]);

	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,

				nvme_cancel_request, &ctrl->ctrl);

	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);

	nvme_rdma_destroy_admin_queue(ctrl, shutdown);

	nvme_rdma_teardown_admin_queue(ctrl, shutdown);

}



static void nvme_rdma_delete_ctrl(struct nvme_ctrl *ctrl)
@@ -1766,8 +1816,6 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) 
{

	struct nvme_rdma_ctrl *ctrl =

		container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work);

	int ret;

	bool changed;



	nvme_stop_ctrl(&ctrl->ctrl);

	nvme_rdma_shutdown_ctrl(ctrl, false);
@@ -1778,25 +1826,9 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) 
		return;

	}



	ret = nvme_rdma_configure_admin_queue(ctrl, false);

	if (ret)

	if (nvme_rdma_setup_ctrl(ctrl, false))

		goto out_fail;



	if (ctrl->ctrl.queue_count > 1) {

		ret = nvme_rdma_configure_io_queues(ctrl, false);

		if (ret)

			goto out_fail;

	}



	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);

	if (!changed) {

		/* state change failure is ok if we're in DELETING state */

		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);

		return;

	}



	nvme_start_ctrl(&ctrl->ctrl);



	return;



out_fail:
@@ -1959,49 +1991,10 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, 
	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);

	WARN_ON_ONCE(!changed);



	ret = nvme_rdma_configure_admin_queue(ctrl, true);

	ret = nvme_rdma_setup_ctrl(ctrl, true);

	if (ret)

		goto out_uninit_ctrl;



	/* sanity check icdoff */

	if (ctrl->ctrl.icdoff) {

		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");

		ret = -EINVAL;

		goto out_remove_admin_queue;

	}



	/* sanity check keyed sgls */

	if (!(ctrl->ctrl.sgls & (1 << 2))) {

		dev_err(ctrl->ctrl.device,

			"Mandatory keyed sgls are not supported!\n");

		ret = -EINVAL;

		goto out_remove_admin_queue;

	}



	/* only warn if argument is too large here, will clamp later */

	if (opts->queue_size > ctrl->ctrl.sqsize + 1) {

		dev_warn(ctrl->ctrl.device,

			"queue_size %zu > ctrl sqsize %u, clamping down\n",

			opts->queue_size, ctrl->ctrl.sqsize + 1);

	}



	/* warn if maxcmd is lower than sqsize+1 */

	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {

		dev_warn(ctrl->ctrl.device,

			"sqsize %u > ctrl maxcmd %u, clamping down\n",

			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);

		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;

	}



	if (opts->nr_io_queues) {

		ret = nvme_rdma_configure_io_queues(ctrl, true);

		if (ret)

			goto out_remove_admin_queue;

	}



	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);

	WARN_ON_ONCE(!changed);



	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",

		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
@@ -2011,13 +2004,8 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, 
	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);

	mutex_unlock(&nvme_rdma_ctrl_mutex);



	nvme_start_ctrl(&ctrl->ctrl);



	return &ctrl->ctrl;



out_remove_admin_queue:

	nvme_rdma_stop_queue(&ctrl->queues[0]);

	nvme_rdma_destroy_admin_queue(ctrl, true);

out_uninit_ctrl:

	nvme_uninit_ctrl(&ctrl->ctrl);

	nvme_put_ctrl(&ctrl->ctrl);

CRA Git | Maintained and supported by SUSTech CRA and CCSE