rdma.c 37.2 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
/*
 * NVMe over Fabrics RDMA target.
 * 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/atomic.h>
#include <linux/ctype.h>
#include <linux/delay.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/nvme.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/wait.h>
#include <linux/inet.h>
#include <asm/unaligned.h>

#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
#include <rdma/rw.h>

#include <linux/nvme-rdma.h>
#include "nvmet.h"

/*
 * We allow up to a page of inline data to go with the SQE
 */
#define NVMET_RDMA_INLINE_DATA_SIZE	PAGE_SIZE

struct nvmet_rdma_cmd {
	struct ib_sge		sge[2];
	struct ib_cqe		cqe;
	struct ib_recv_wr	wr;
	struct scatterlist	inline_sg;
	struct page		*inline_page;
	struct nvme_command     *nvme_cmd;
	struct nvmet_rdma_queue	*queue;
};

enum {
	NVMET_RDMA_REQ_INLINE_DATA	= (1 << 0),
	NVMET_RDMA_REQ_INVALIDATE_RKEY	= (1 << 1),
};

struct nvmet_rdma_rsp {
	struct ib_sge		send_sge;
	struct ib_cqe		send_cqe;
	struct ib_send_wr	send_wr;

	struct nvmet_rdma_cmd	*cmd;
	struct nvmet_rdma_queue	*queue;

	struct ib_cqe		read_cqe;
	struct rdma_rw_ctx	rw;

	struct nvmet_req	req;

	u8			n_rdma;
	u32			flags;
	u32			invalidate_rkey;

	struct list_head	wait_list;
	struct list_head	free_list;
};

enum nvmet_rdma_queue_state {
	NVMET_RDMA_Q_CONNECTING,
	NVMET_RDMA_Q_LIVE,
	NVMET_RDMA_Q_DISCONNECTING,
80
	NVMET_RDMA_IN_DEVICE_REMOVAL,
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
};

struct nvmet_rdma_queue {
	struct rdma_cm_id	*cm_id;
	struct nvmet_port	*port;
	struct ib_cq		*cq;
	atomic_t		sq_wr_avail;
	struct nvmet_rdma_device *dev;
	spinlock_t		state_lock;
	enum nvmet_rdma_queue_state state;
	struct nvmet_cq		nvme_cq;
	struct nvmet_sq		nvme_sq;

	struct nvmet_rdma_rsp	*rsps;
	struct list_head	free_rsps;
	spinlock_t		rsps_lock;
	struct nvmet_rdma_cmd	*cmds;

	struct work_struct	release_work;
	struct list_head	rsp_wait_list;
	struct list_head	rsp_wr_wait_list;
	spinlock_t		rsp_wr_wait_lock;

	int			idx;
	int			host_qid;
	int			recv_queue_size;
	int			send_queue_size;

	struct list_head	queue_list;
};

struct nvmet_rdma_device {
	struct ib_device	*device;
	struct ib_pd		*pd;
	struct ib_srq		*srq;
	struct nvmet_rdma_cmd	*srq_cmds;
	size_t			srq_size;
	struct kref		ref;
	struct list_head	entry;
};

static bool nvmet_rdma_use_srq;
module_param_named(use_srq, nvmet_rdma_use_srq, bool, 0444);
MODULE_PARM_DESC(use_srq, "Use shared receive queue.");

static DEFINE_IDA(nvmet_rdma_queue_ida);
static LIST_HEAD(nvmet_rdma_queue_list);
static DEFINE_MUTEX(nvmet_rdma_queue_mutex);

static LIST_HEAD(device_list);
static DEFINE_MUTEX(device_list_mutex);

static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp);
static void nvmet_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc);
static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc);
static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc);
static void nvmet_rdma_qp_event(struct ib_event *event, void *priv);
static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue);

static struct nvmet_fabrics_ops nvmet_rdma_ops;

/* XXX: really should move to a generic header sooner or later.. */
static inline u32 get_unaligned_le24(const u8 *p)
{
	return (u32)p[0] | (u32)p[1] << 8 | (u32)p[2] << 16;
}

static inline bool nvmet_rdma_need_data_in(struct nvmet_rdma_rsp *rsp)
{
	return nvme_is_write(rsp->req.cmd) &&
		rsp->req.data_len &&
		!(rsp->flags & NVMET_RDMA_REQ_INLINE_DATA);
}

static inline bool nvmet_rdma_need_data_out(struct nvmet_rdma_rsp *rsp)
{
	return !nvme_is_write(rsp->req.cmd) &&
		rsp->req.data_len &&
		!rsp->req.rsp->status &&
		!(rsp->flags & NVMET_RDMA_REQ_INLINE_DATA);
}

static inline struct nvmet_rdma_rsp *
nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue)
{
	struct nvmet_rdma_rsp *rsp;
	unsigned long flags;

	spin_lock_irqsave(&queue->rsps_lock, flags);
	rsp = list_first_entry(&queue->free_rsps,
				struct nvmet_rdma_rsp, free_list);
	list_del(&rsp->free_list);
	spin_unlock_irqrestore(&queue->rsps_lock, flags);

	return rsp;
}

static inline void
nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp)
{
	unsigned long flags;

	spin_lock_irqsave(&rsp->queue->rsps_lock, flags);
	list_add_tail(&rsp->free_list, &rsp->queue->free_rsps);
	spin_unlock_irqrestore(&rsp->queue->rsps_lock, flags);
}

static void nvmet_rdma_free_sgl(struct scatterlist *sgl, unsigned int nents)
{
	struct scatterlist *sg;
	int count;

	if (!sgl || !nents)
		return;

	for_each_sg(sgl, sg, nents, count)
		__free_page(sg_page(sg));
	kfree(sgl);
}

static int nvmet_rdma_alloc_sgl(struct scatterlist **sgl, unsigned int *nents,
		u32 length)
{
	struct scatterlist *sg;
	struct page *page;
	unsigned int nent;
	int i = 0;

	nent = DIV_ROUND_UP(length, PAGE_SIZE);
	sg = kmalloc_array(nent, sizeof(struct scatterlist), GFP_KERNEL);
	if (!sg)
		goto out;

	sg_init_table(sg, nent);

	while (length) {
		u32 page_len = min_t(u32, length, PAGE_SIZE);

		page = alloc_page(GFP_KERNEL);
		if (!page)
			goto out_free_pages;

		sg_set_page(&sg[i], page, page_len, 0);
		length -= page_len;
		i++;
	}
	*sgl = sg;
	*nents = nent;
	return 0;

out_free_pages:
	while (i > 0) {
		i--;
		__free_page(sg_page(&sg[i]));
	}
	kfree(sg);
out:
	return NVME_SC_INTERNAL;
}

static int nvmet_rdma_alloc_cmd(struct nvmet_rdma_device *ndev,
			struct nvmet_rdma_cmd *c, bool admin)
{
	/* NVMe command / RDMA RECV */
	c->nvme_cmd = kmalloc(sizeof(*c->nvme_cmd), GFP_KERNEL);
	if (!c->nvme_cmd)
		goto out;

	c->sge[0].addr = ib_dma_map_single(ndev->device, c->nvme_cmd,
			sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
	if (ib_dma_mapping_error(ndev->device, c->sge[0].addr))
		goto out_free_cmd;

	c->sge[0].length = sizeof(*c->nvme_cmd);
	c->sge[0].lkey = ndev->pd->local_dma_lkey;

	if (!admin) {
		c->inline_page = alloc_pages(GFP_KERNEL,
				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
		if (!c->inline_page)
			goto out_unmap_cmd;
		c->sge[1].addr = ib_dma_map_page(ndev->device,
				c->inline_page, 0, NVMET_RDMA_INLINE_DATA_SIZE,
				DMA_FROM_DEVICE);
		if (ib_dma_mapping_error(ndev->device, c->sge[1].addr))
			goto out_free_inline_page;
		c->sge[1].length = NVMET_RDMA_INLINE_DATA_SIZE;
		c->sge[1].lkey = ndev->pd->local_dma_lkey;
	}

	c->cqe.done = nvmet_rdma_recv_done;

	c->wr.wr_cqe = &c->cqe;
	c->wr.sg_list = c->sge;
	c->wr.num_sge = admin ? 1 : 2;

	return 0;

out_free_inline_page:
	if (!admin) {
		__free_pages(c->inline_page,
				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
	}
out_unmap_cmd:
	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
			sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
out_free_cmd:
	kfree(c->nvme_cmd);

out:
	return -ENOMEM;
}

static void nvmet_rdma_free_cmd(struct nvmet_rdma_device *ndev,
		struct nvmet_rdma_cmd *c, bool admin)
{
	if (!admin) {
		ib_dma_unmap_page(ndev->device, c->sge[1].addr,
				NVMET_RDMA_INLINE_DATA_SIZE, DMA_FROM_DEVICE);
		__free_pages(c->inline_page,
				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
	}
	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
				sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
	kfree(c->nvme_cmd);
}

static struct nvmet_rdma_cmd *
nvmet_rdma_alloc_cmds(struct nvmet_rdma_device *ndev,
		int nr_cmds, bool admin)
{
	struct nvmet_rdma_cmd *cmds;
	int ret = -EINVAL, i;

	cmds = kcalloc(nr_cmds, sizeof(struct nvmet_rdma_cmd), GFP_KERNEL);
	if (!cmds)
		goto out;

	for (i = 0; i < nr_cmds; i++) {
		ret = nvmet_rdma_alloc_cmd(ndev, cmds + i, admin);
		if (ret)
			goto out_free;
	}

	return cmds;

out_free:
	while (--i >= 0)
		nvmet_rdma_free_cmd(ndev, cmds + i, admin);
	kfree(cmds);
out:
	return ERR_PTR(ret);
}

static void nvmet_rdma_free_cmds(struct nvmet_rdma_device *ndev,
		struct nvmet_rdma_cmd *cmds, int nr_cmds, bool admin)
{
	int i;

	for (i = 0; i < nr_cmds; i++)
		nvmet_rdma_free_cmd(ndev, cmds + i, admin);
	kfree(cmds);
}

static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
		struct nvmet_rdma_rsp *r)
{
	/* NVMe CQE / RDMA SEND */
	r->req.rsp = kmalloc(sizeof(*r->req.rsp), GFP_KERNEL);
	if (!r->req.rsp)
		goto out;

	r->send_sge.addr = ib_dma_map_single(ndev->device, r->req.rsp,
			sizeof(*r->req.rsp), DMA_TO_DEVICE);
	if (ib_dma_mapping_error(ndev->device, r->send_sge.addr))
		goto out_free_rsp;

	r->send_sge.length = sizeof(*r->req.rsp);
	r->send_sge.lkey = ndev->pd->local_dma_lkey;

	r->send_cqe.done = nvmet_rdma_send_done;

	r->send_wr.wr_cqe = &r->send_cqe;
	r->send_wr.sg_list = &r->send_sge;
	r->send_wr.num_sge = 1;
	r->send_wr.send_flags = IB_SEND_SIGNALED;

	/* Data In / RDMA READ */
	r->read_cqe.done = nvmet_rdma_read_data_done;
	return 0;

out_free_rsp:
	kfree(r->req.rsp);
out:
	return -ENOMEM;
}

static void nvmet_rdma_free_rsp(struct nvmet_rdma_device *ndev,
		struct nvmet_rdma_rsp *r)
{
	ib_dma_unmap_single(ndev->device, r->send_sge.addr,
				sizeof(*r->req.rsp), DMA_TO_DEVICE);
	kfree(r->req.rsp);
}

static int
nvmet_rdma_alloc_rsps(struct nvmet_rdma_queue *queue)
{
	struct nvmet_rdma_device *ndev = queue->dev;
	int nr_rsps = queue->recv_queue_size * 2;
	int ret = -EINVAL, i;

	queue->rsps = kcalloc(nr_rsps, sizeof(struct nvmet_rdma_rsp),
			GFP_KERNEL);
	if (!queue->rsps)
		goto out;

	for (i = 0; i < nr_rsps; i++) {
		struct nvmet_rdma_rsp *rsp = &queue->rsps[i];

		ret = nvmet_rdma_alloc_rsp(ndev, rsp);
		if (ret)
			goto out_free;

		list_add_tail(&rsp->free_list, &queue->free_rsps);
	}

	return 0;

out_free:
	while (--i >= 0) {
		struct nvmet_rdma_rsp *rsp = &queue->rsps[i];

		list_del(&rsp->free_list);
		nvmet_rdma_free_rsp(ndev, rsp);
	}
	kfree(queue->rsps);
out:
	return ret;
}

static void nvmet_rdma_free_rsps(struct nvmet_rdma_queue *queue)
{
	struct nvmet_rdma_device *ndev = queue->dev;
	int i, nr_rsps = queue->recv_queue_size * 2;

	for (i = 0; i < nr_rsps; i++) {
		struct nvmet_rdma_rsp *rsp = &queue->rsps[i];

		list_del(&rsp->free_list);
		nvmet_rdma_free_rsp(ndev, rsp);
	}
	kfree(queue->rsps);
}

static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
		struct nvmet_rdma_cmd *cmd)
{
	struct ib_recv_wr *bad_wr;

441
442
443
444
	ib_dma_sync_single_for_device(ndev->device,
		cmd->sge[0].addr, cmd->sge[0].length,
		DMA_FROM_DEVICE);

445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
	if (ndev->srq)
		return ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
	return ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
}

static void nvmet_rdma_process_wr_wait_list(struct nvmet_rdma_queue *queue)
{
	spin_lock(&queue->rsp_wr_wait_lock);
	while (!list_empty(&queue->rsp_wr_wait_list)) {
		struct nvmet_rdma_rsp *rsp;
		bool ret;

		rsp = list_entry(queue->rsp_wr_wait_list.next,
				struct nvmet_rdma_rsp, wait_list);
		list_del(&rsp->wait_list);

		spin_unlock(&queue->rsp_wr_wait_lock);
		ret = nvmet_rdma_execute_command(rsp);
		spin_lock(&queue->rsp_wr_wait_lock);

		if (!ret) {
			list_add(&rsp->wait_list, &queue->rsp_wr_wait_list);
			break;
		}
	}
	spin_unlock(&queue->rsp_wr_wait_lock);
}


static void nvmet_rdma_release_rsp(struct nvmet_rdma_rsp *rsp)
{
	struct nvmet_rdma_queue *queue = rsp->queue;

	atomic_add(1 + rsp->n_rdma, &queue->sq_wr_avail);

	if (rsp->n_rdma) {
		rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp,
				queue->cm_id->port_num, rsp->req.sg,
				rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
	}

	if (rsp->req.sg != &rsp->cmd->inline_sg)
		nvmet_rdma_free_sgl(rsp->req.sg, rsp->req.sg_cnt);

	if (unlikely(!list_empty_careful(&queue->rsp_wr_wait_list)))
		nvmet_rdma_process_wr_wait_list(queue);

	nvmet_rdma_put_rsp(rsp);
}

static void nvmet_rdma_error_comp(struct nvmet_rdma_queue *queue)
{
	if (queue->nvme_sq.ctrl) {
		nvmet_ctrl_fatal_error(queue->nvme_sq.ctrl);
	} else {
		/*
		 * we didn't setup the controller yet in case
		 * of admin connect error, just disconnect and
		 * cleanup the queue
		 */
		nvmet_rdma_queue_disconnect(queue);
	}
}

static void nvmet_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
{
	struct nvmet_rdma_rsp *rsp =
		container_of(wc->wr_cqe, struct nvmet_rdma_rsp, send_cqe);

	nvmet_rdma_release_rsp(rsp);

	if (unlikely(wc->status != IB_WC_SUCCESS &&
		     wc->status != IB_WC_WR_FLUSH_ERR)) {
		pr_err("SEND for CQE 0x%p failed with status %s (%d).\n",
			wc->wr_cqe, ib_wc_status_msg(wc->status), wc->status);
		nvmet_rdma_error_comp(rsp->queue);
	}
}

static void nvmet_rdma_queue_response(struct nvmet_req *req)
{
	struct nvmet_rdma_rsp *rsp =
		container_of(req, struct nvmet_rdma_rsp, req);
	struct rdma_cm_id *cm_id = rsp->queue->cm_id;
	struct ib_send_wr *first_wr, *bad_wr;

	if (rsp->flags & NVMET_RDMA_REQ_INVALIDATE_RKEY) {
		rsp->send_wr.opcode = IB_WR_SEND_WITH_INV;
		rsp->send_wr.ex.invalidate_rkey = rsp->invalidate_rkey;
	} else {
		rsp->send_wr.opcode = IB_WR_SEND;
	}

	if (nvmet_rdma_need_data_out(rsp))
		first_wr = rdma_rw_ctx_wrs(&rsp->rw, cm_id->qp,
				cm_id->port_num, NULL, &rsp->send_wr);
	else
		first_wr = &rsp->send_wr;

	nvmet_rdma_post_recv(rsp->queue->dev, rsp->cmd);
545
546
547
548
549

	ib_dma_sync_single_for_device(rsp->queue->dev->device,
		rsp->send_sge.addr, rsp->send_sge.length,
		DMA_TO_DEVICE);

550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
	if (ib_post_send(cm_id->qp, first_wr, &bad_wr)) {
		pr_err("sending cmd response failed\n");
		nvmet_rdma_release_rsp(rsp);
	}
}

static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc)
{
	struct nvmet_rdma_rsp *rsp =
		container_of(wc->wr_cqe, struct nvmet_rdma_rsp, read_cqe);
	struct nvmet_rdma_queue *queue = cq->cq_context;

	WARN_ON(rsp->n_rdma <= 0);
	atomic_add(rsp->n_rdma, &queue->sq_wr_avail);
	rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp,
			queue->cm_id->port_num, rsp->req.sg,
			rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
	rsp->n_rdma = 0;

	if (unlikely(wc->status != IB_WC_SUCCESS)) {
		nvmet_rdma_release_rsp(rsp);
		if (wc->status != IB_WC_WR_FLUSH_ERR) {
			pr_info("RDMA READ for CQE 0x%p failed with status %s (%d).\n",
				wc->wr_cqe, ib_wc_status_msg(wc->status), wc->status);
			nvmet_rdma_error_comp(queue);
		}
		return;
	}

	rsp->req.execute(&rsp->req);
}

static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len,
		u64 off)
{
	sg_init_table(&rsp->cmd->inline_sg, 1);
	sg_set_page(&rsp->cmd->inline_sg, rsp->cmd->inline_page, len, off);
	rsp->req.sg = &rsp->cmd->inline_sg;
	rsp->req.sg_cnt = 1;
}

static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
{
	struct nvme_sgl_desc *sgl = &rsp->req.cmd->common.dptr.sgl;
	u64 off = le64_to_cpu(sgl->addr);
	u32 len = le32_to_cpu(sgl->length);

	if (!nvme_is_write(rsp->req.cmd))
		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;

	if (off + len > NVMET_RDMA_INLINE_DATA_SIZE) {
		pr_err("invalid inline data offset!\n");
		return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
	}

	/* no data command? */
	if (!len)
		return 0;

	nvmet_rdma_use_inline_sg(rsp, len, off);
	rsp->flags |= NVMET_RDMA_REQ_INLINE_DATA;
	return 0;
}

static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp,
		struct nvme_keyed_sgl_desc *sgl, bool invalidate)
{
	struct rdma_cm_id *cm_id = rsp->queue->cm_id;
	u64 addr = le64_to_cpu(sgl->addr);
	u32 len = get_unaligned_le24(sgl->length);
	u32 key = get_unaligned_le32(sgl->key);
	int ret;
	u16 status;

	/* no data command? */
	if (!len)
		return 0;

628
629
630
631
	status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt,
			len);
	if (status)
		return status;
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709

	ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num,
			rsp->req.sg, rsp->req.sg_cnt, 0, addr, key,
			nvmet_data_dir(&rsp->req));
	if (ret < 0)
		return NVME_SC_INTERNAL;
	rsp->n_rdma += ret;

	if (invalidate) {
		rsp->invalidate_rkey = key;
		rsp->flags |= NVMET_RDMA_REQ_INVALIDATE_RKEY;
	}

	return 0;
}

static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
{
	struct nvme_keyed_sgl_desc *sgl = &rsp->req.cmd->common.dptr.ksgl;

	switch (sgl->type >> 4) {
	case NVME_SGL_FMT_DATA_DESC:
		switch (sgl->type & 0xf) {
		case NVME_SGL_FMT_OFFSET:
			return nvmet_rdma_map_sgl_inline(rsp);
		default:
			pr_err("invalid SGL subtype: %#x\n", sgl->type);
			return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
		}
	case NVME_KEY_SGL_FMT_DATA_DESC:
		switch (sgl->type & 0xf) {
		case NVME_SGL_FMT_ADDRESS | NVME_SGL_FMT_INVALIDATE:
			return nvmet_rdma_map_sgl_keyed(rsp, sgl, true);
		case NVME_SGL_FMT_ADDRESS:
			return nvmet_rdma_map_sgl_keyed(rsp, sgl, false);
		default:
			pr_err("invalid SGL subtype: %#x\n", sgl->type);
			return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
		}
	default:
		pr_err("invalid SGL type: %#x\n", sgl->type);
		return NVME_SC_SGL_INVALID_TYPE | NVME_SC_DNR;
	}
}

static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp)
{
	struct nvmet_rdma_queue *queue = rsp->queue;

	if (unlikely(atomic_sub_return(1 + rsp->n_rdma,
			&queue->sq_wr_avail) < 0)) {
		pr_debug("IB send queue full (needed %d): queue %u cntlid %u\n",
				1 + rsp->n_rdma, queue->idx,
				queue->nvme_sq.ctrl->cntlid);
		atomic_add(1 + rsp->n_rdma, &queue->sq_wr_avail);
		return false;
	}

	if (nvmet_rdma_need_data_in(rsp)) {
		if (rdma_rw_ctx_post(&rsp->rw, queue->cm_id->qp,
				queue->cm_id->port_num, &rsp->read_cqe, NULL))
			nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR);
	} else {
		rsp->req.execute(&rsp->req);
	}

	return true;
}

static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
		struct nvmet_rdma_rsp *cmd)
{
	u16 status;

	cmd->queue = queue;
	cmd->n_rdma = 0;
	cmd->req.port = queue->port;

710
711
712
713
714
715
716
717

	ib_dma_sync_single_for_cpu(queue->dev->device,
		cmd->cmd->sge[0].addr, cmd->cmd->sge[0].length,
		DMA_FROM_DEVICE);
	ib_dma_sync_single_for_cpu(queue->dev->device,
		cmd->send_sge.addr, cmd->send_sge.length,
		DMA_TO_DEVICE);

718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
	if (!nvmet_req_init(&cmd->req, &queue->nvme_cq,
			&queue->nvme_sq, &nvmet_rdma_ops))
		return;

	status = nvmet_rdma_map_sgl(cmd);
	if (status)
		goto out_err;

	if (unlikely(!nvmet_rdma_execute_command(cmd))) {
		spin_lock(&queue->rsp_wr_wait_lock);
		list_add_tail(&cmd->wait_list, &queue->rsp_wr_wait_list);
		spin_unlock(&queue->rsp_wr_wait_lock);
	}

	return;

out_err:
	nvmet_req_complete(&cmd->req, status);
}

static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
{
	struct nvmet_rdma_cmd *cmd =
		container_of(wc->wr_cqe, struct nvmet_rdma_cmd, cqe);
	struct nvmet_rdma_queue *queue = cq->cq_context;
	struct nvmet_rdma_rsp *rsp;

	if (unlikely(wc->status != IB_WC_SUCCESS)) {
		if (wc->status != IB_WC_WR_FLUSH_ERR) {
			pr_err("RECV for CQE 0x%p failed with status %s (%d)\n",
				wc->wr_cqe, ib_wc_status_msg(wc->status),
				wc->status);
			nvmet_rdma_error_comp(queue);
		}
		return;
	}

	if (unlikely(wc->byte_len < sizeof(struct nvme_command))) {
		pr_err("Ctrl Fatal Error: capsule size less than 64 bytes\n");
		nvmet_rdma_error_comp(queue);
		return;
	}

	cmd->queue = queue;
	rsp = nvmet_rdma_get_rsp(queue);
	rsp->cmd = cmd;
	rsp->flags = 0;
	rsp->req.cmd = cmd->nvme_cmd;

	if (unlikely(queue->state != NVMET_RDMA_Q_LIVE)) {
		unsigned long flags;

		spin_lock_irqsave(&queue->state_lock, flags);
		if (queue->state == NVMET_RDMA_Q_CONNECTING)
			list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
		else
			nvmet_rdma_put_rsp(rsp);
		spin_unlock_irqrestore(&queue->state_lock, flags);
		return;
	}

	nvmet_rdma_handle_command(queue, rsp);
}

static void nvmet_rdma_destroy_srq(struct nvmet_rdma_device *ndev)
{
	if (!ndev->srq)
		return;

	nvmet_rdma_free_cmds(ndev, ndev->srq_cmds, ndev->srq_size, false);
	ib_destroy_srq(ndev->srq);
}

static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
{
	struct ib_srq_init_attr srq_attr = { NULL, };
	struct ib_srq *srq;
	size_t srq_size;
	int ret, i;

	srq_size = 4095;	/* XXX: tune */

	srq_attr.attr.max_wr = srq_size;
	srq_attr.attr.max_sge = 2;
	srq_attr.attr.srq_limit = 0;
	srq_attr.srq_type = IB_SRQT_BASIC;
	srq = ib_create_srq(ndev->pd, &srq_attr);
	if (IS_ERR(srq)) {
		/*
		 * If SRQs aren't supported we just go ahead and use normal
		 * non-shared receive queues.
		 */
		pr_info("SRQ requested but not supported.\n");
		return 0;
	}

	ndev->srq_cmds = nvmet_rdma_alloc_cmds(ndev, srq_size, false);
	if (IS_ERR(ndev->srq_cmds)) {
		ret = PTR_ERR(ndev->srq_cmds);
		goto out_destroy_srq;
	}

	ndev->srq = srq;
	ndev->srq_size = srq_size;

	for (i = 0; i < srq_size; i++)
		nvmet_rdma_post_recv(ndev, &ndev->srq_cmds[i]);

	return 0;

out_destroy_srq:
	ib_destroy_srq(srq);
	return ret;
}

static void nvmet_rdma_free_dev(struct kref *ref)
{
	struct nvmet_rdma_device *ndev =
		container_of(ref, struct nvmet_rdma_device, ref);

	mutex_lock(&device_list_mutex);
	list_del(&ndev->entry);
	mutex_unlock(&device_list_mutex);

	nvmet_rdma_destroy_srq(ndev);
	ib_dealloc_pd(ndev->pd);

	kfree(ndev);
}

static struct nvmet_rdma_device *
nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
{
	struct nvmet_rdma_device *ndev;
	int ret;

	mutex_lock(&device_list_mutex);
	list_for_each_entry(ndev, &device_list, entry) {
		if (ndev->device->node_guid == cm_id->device->node_guid &&
		    kref_get_unless_zero(&ndev->ref))
			goto out_unlock;
	}

	ndev = kzalloc(sizeof(*ndev), GFP_KERNEL);
	if (!ndev)
		goto out_err;

	ndev->device = cm_id->device;
	kref_init(&ndev->ref);

868
	ndev->pd = ib_alloc_pd(ndev->device, 0);
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
	if (IS_ERR(ndev->pd))
		goto out_free_dev;

	if (nvmet_rdma_use_srq) {
		ret = nvmet_rdma_init_srq(ndev);
		if (ret)
			goto out_free_pd;
	}

	list_add(&ndev->entry, &device_list);
out_unlock:
	mutex_unlock(&device_list_mutex);
	pr_debug("added %s.\n", ndev->device->name);
	return ndev;

out_free_pd:
	ib_dealloc_pd(ndev->pd);
out_free_dev:
	kfree(ndev);
out_err:
	mutex_unlock(&device_list_mutex);
	return NULL;
}

static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
{
	struct ib_qp_init_attr qp_attr;
	struct nvmet_rdma_device *ndev = queue->dev;
	int comp_vector, nr_cqe, ret, i;

	/*
	 * Spread the io queues across completion vectors,
	 * but still keep all admin queues on vector 0.
	 */
	comp_vector = !queue->host_qid ? 0 :
		queue->idx % ndev->device->num_comp_vectors;

	/*
	 * Reserve CQ slots for RECV + RDMA_READ/RDMA_WRITE + RDMA_SEND.
	 */
	nr_cqe = queue->recv_queue_size + 2 * queue->send_queue_size;

	queue->cq = ib_alloc_cq(ndev->device, queue,
			nr_cqe + 1, comp_vector,
			IB_POLL_WORKQUEUE);
	if (IS_ERR(queue->cq)) {
		ret = PTR_ERR(queue->cq);
		pr_err("failed to create CQ cqe= %d ret= %d\n",
		       nr_cqe + 1, ret);
		goto out;
	}

	memset(&qp_attr, 0, sizeof(qp_attr));
	qp_attr.qp_context = queue;
	qp_attr.event_handler = nvmet_rdma_qp_event;
	qp_attr.send_cq = queue->cq;
	qp_attr.recv_cq = queue->cq;
	qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
	qp_attr.qp_type = IB_QPT_RC;
	/* +1 for drain */
	qp_attr.cap.max_send_wr = queue->send_queue_size + 1;
	qp_attr.cap.max_rdma_ctxs = queue->send_queue_size;
	qp_attr.cap.max_send_sge = max(ndev->device->attrs.max_sge_rd,
					ndev->device->attrs.max_sge);

	if (ndev->srq) {
		qp_attr.srq = ndev->srq;
	} else {
		/* +1 for drain */
		qp_attr.cap.max_recv_wr = 1 + queue->recv_queue_size;
		qp_attr.cap.max_recv_sge = 2;
	}

	ret = rdma_create_qp(queue->cm_id, ndev->pd, &qp_attr);
	if (ret) {
		pr_err("failed to create_qp ret= %d\n", ret);
		goto err_destroy_cq;
	}

	atomic_set(&queue->sq_wr_avail, qp_attr.cap.max_send_wr);

	pr_debug("%s: max_cqe= %d max_sge= %d sq_size = %d cm_id= %p\n",
		 __func__, queue->cq->cqe, qp_attr.cap.max_send_sge,
		 qp_attr.cap.max_send_wr, queue->cm_id);

	if (!ndev->srq) {
		for (i = 0; i < queue->recv_queue_size; i++) {
			queue->cmds[i].queue = queue;
			nvmet_rdma_post_recv(ndev, &queue->cmds[i]);
		}
	}

out:
	return ret;

err_destroy_cq:
	ib_free_cq(queue->cq);
	goto out;
}

static void nvmet_rdma_destroy_queue_ib(struct nvmet_rdma_queue *queue)
{
971
	ib_drain_qp(queue->cm_id->qp);
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
	rdma_destroy_qp(queue->cm_id);
	ib_free_cq(queue->cq);
}

static void nvmet_rdma_free_queue(struct nvmet_rdma_queue *queue)
{
	pr_info("freeing queue %d\n", queue->idx);

	nvmet_sq_destroy(&queue->nvme_sq);

	nvmet_rdma_destroy_queue_ib(queue);
	if (!queue->dev->srq) {
		nvmet_rdma_free_cmds(queue->dev, queue->cmds,
				queue->recv_queue_size,
				!queue->host_qid);
	}
	nvmet_rdma_free_rsps(queue);
	ida_simple_remove(&nvmet_rdma_queue_ida, queue->idx);
	kfree(queue);
}

static void nvmet_rdma_release_queue_work(struct work_struct *w)
{
	struct nvmet_rdma_queue *queue =
		container_of(w, struct nvmet_rdma_queue, release_work);
	struct rdma_cm_id *cm_id = queue->cm_id;
	struct nvmet_rdma_device *dev = queue->dev;
999
	enum nvmet_rdma_queue_state state = queue->state;
1000