summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
blob: 6aa40bd2fd52d3dd921b32b7425adf338e1b0188 (plain)
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
80
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
/*
 * Copyright (c) 2012-2016 VMware, Inc.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of EITHER the GNU General Public License
 * version 2 as published by the Free Software Foundation or the BSD
 * 2-Clause License. This program is distributed in the hope that 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 version 2 for more details at
 * http://www.gnu.org/licenses/old-licenses/gpl-2.0.en.html.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program available in the file COPYING in the main
 * directory of this source tree.
 *
 * The BSD 2-Clause License
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
 * COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
 * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
 * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
 * OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <asm/page.h>
#include <linux/io.h>
#include <linux/wait.h>
#include <rdma/ib_addr.h>
#include <rdma/ib_smi.h>
#include <rdma/ib_user_verbs.h>
#include <rdma/uverbs_ioctl.h>

#include "pvrdma.h"

/**
 * pvrdma_req_notify_cq - request notification for a completion queue
 * @ibcq: the completion queue
 * @notify_flags: notification flags
 *
 * @return: 0 for success.
 */
int pvrdma_req_notify_cq(struct ib_cq *ibcq,
			 enum ib_cq_notify_flags notify_flags)
{
	struct pvrdma_dev *dev = to_vdev(ibcq->device);
	struct pvrdma_cq *cq = to_vcq(ibcq);
	u32 val = cq->cq_handle;
	unsigned long flags;
	int has_data = 0;

	val |= (notify_flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED ?
		PVRDMA_UAR_CQ_ARM_SOL : PVRDMA_UAR_CQ_ARM;

	spin_lock_irqsave(&cq->cq_lock, flags);

	pvrdma_write_uar_cq(dev, val);

	if (notify_flags & IB_CQ_REPORT_MISSED_EVENTS) {
		unsigned int head;

		has_data = pvrdma_idx_ring_has_data(&cq->ring_state->rx,
						    cq->ibcq.cqe, &head);
		if (unlikely(has_data == PVRDMA_INVALID_IDX))
			dev_err(&dev->pdev->dev, "CQ ring state invalid\n");
	}

	spin_unlock_irqrestore(&cq->cq_lock, flags);

	return has_data;
}

/**
 * pvrdma_create_cq - create completion queue
 * @ibcq: Allocated CQ
 * @attr: completion queue attributes
 * @udata: user data
 *
 * @return: 0 on success
 */
int pvrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
		     struct ib_udata *udata)
{
	struct ib_device *ibdev = ibcq->device;
	int entries = attr->cqe;
	struct pvrdma_dev *dev = to_vdev(ibdev);
	struct pvrdma_cq *cq = to_vcq(ibcq);
	int ret;
	int npages;
	unsigned long flags;
	union pvrdma_cmd_req req;
	union pvrdma_cmd_resp rsp;
	struct pvrdma_cmd_create_cq *cmd = &req.create_cq;
	struct pvrdma_cmd_create_cq_resp *resp = &rsp.create_cq_resp;
	struct pvrdma_create_cq_resp cq_resp = {};
	struct pvrdma_create_cq ucmd;
	struct pvrdma_ucontext *context = rdma_udata_to_drv_context(
		udata, struct pvrdma_ucontext, ibucontext);

	BUILD_BUG_ON(sizeof(struct pvrdma_cqe) != 64);

	if (attr->flags)
		return -EOPNOTSUPP;

	entries = roundup_pow_of_two(entries);
	if (entries < 1 || entries > dev->dsr->caps.max_cqe)
		return -EINVAL;

	if (!atomic_add_unless(&dev->num_cqs, 1, dev->dsr->caps.max_cq))
		return -ENOMEM;

	cq->ibcq.cqe = entries;
	cq->is_kernel = !udata;

	if (!cq->is_kernel) {
		if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) {
			ret = -EFAULT;
			goto err_cq;
		}

		cq->umem = ib_umem_get(ibdev, ucmd.buf_addr, ucmd.buf_size,
				       IB_ACCESS_LOCAL_WRITE);
		if (IS_ERR(cq->umem)) {
			ret = PTR_ERR(cq->umem);
			goto err_cq;
		}

		npages = ib_umem_num_dma_blocks(cq->umem, PAGE_SIZE);
	} else {
		/* One extra page for shared ring state */
		npages = 1 + (entries * sizeof(struct pvrdma_cqe) +
			      PAGE_SIZE - 1) / PAGE_SIZE;

		/* Skip header page. */
		cq->offset = PAGE_SIZE;
	}

	if (npages < 0 || npages > PVRDMA_PAGE_DIR_MAX_PAGES) {
		dev_warn(&dev->pdev->dev,
			 "overflow pages in completion queue\n");
		ret = -EINVAL;
		goto err_umem;
	}

	ret = pvrdma_page_dir_init(dev, &cq->pdir, npages, cq->is_kernel);
	if (ret) {
		dev_warn(&dev->pdev->dev,
			 "could not allocate page directory\n");
		goto err_umem;
	}

	/* Ring state is always the first page. Set in library for user cq. */
	if (cq->is_kernel)
		cq->ring_state = cq->pdir.pages[0];
	else
		pvrdma_page_dir_insert_umem(&cq->pdir, cq->umem, 0);

	refcount_set(&cq->refcnt, 1);
	init_completion(&cq->free);
	spin_lock_init(&cq->cq_lock);

	memset(cmd, 0, sizeof(*cmd));
	cmd->hdr.cmd = PVRDMA_CMD_CREATE_CQ;
	cmd->nchunks = npages;
	cmd->ctx_handle = context ? context->ctx_handle : 0;
	cmd->cqe = entries;
	cmd->pdir_dma = cq->pdir.dir_dma;
	ret = pvrdma_cmd_post(dev, &req, &rsp, PVRDMA_CMD_CREATE_CQ_RESP);
	if (ret < 0) {
		dev_warn(&dev->pdev->dev,
			 "could not create completion queue, error: %d\n", ret);
		goto err_page_dir;
	}

	cq->ibcq.cqe = resp->cqe;
	cq->cq_handle = resp->cq_handle;
	cq_resp.cqn = resp->cq_handle;
	spin_lock_irqsave(&dev->cq_tbl_lock, flags);
	dev->cq_tbl[cq->cq_handle % dev->dsr->caps.max_cq] = cq;
	spin_unlock_irqrestore(&dev->cq_tbl_lock, flags);

	if (!cq->is_kernel) {
		cq->uar = &context->uar;

		/* Copy udata back. */
		if (ib_copy_to_udata(udata, &cq_resp, sizeof(cq_resp))) {
			dev_warn(&dev->pdev->dev,
				 "failed to copy back udata\n");
			pvrdma_destroy_cq(&cq->ibcq, udata);
			return -EINVAL;
		}
	}

	return 0;

err_page_dir:
	pvrdma_page_dir_cleanup(dev, &cq->pdir);
err_umem:
	ib_umem_release(cq->umem);
err_cq:
	atomic_dec(&dev->num_cqs);
	return ret;
}

static void pvrdma_free_cq(struct pvrdma_dev *dev, struct pvrdma_cq *cq)
{
	if (refcount_dec_and_test(&cq->refcnt))
		complete(&cq->free);
	wait_for_completion(&cq->free);

	ib_umem_release(cq->umem);

	pvrdma_page_dir_cleanup(dev, &cq->pdir);
}

/**
 * pvrdma_destroy_cq - destroy completion queue
 * @cq: the completion queue to destroy.
 * @udata: user data or null for kernel object
 */
int pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
{
	struct pvrdma_cq *vcq = to_vcq(cq);
	union pvrdma_cmd_req req;
	struct pvrdma_cmd_destroy_cq *cmd = &req.destroy_cq;
	struct pvrdma_dev *dev = to_vdev(cq->device);
	unsigned long flags;
	int ret;

	memset(cmd, 0, sizeof(*cmd));
	cmd->hdr.cmd = PVRDMA_CMD_DESTROY_CQ;
	cmd->cq_handle = vcq->cq_handle;

	ret = pvrdma_cmd_post(dev, &req, NULL, 0);
	if (ret < 0)
		dev_warn(&dev->pdev->dev,
			 "could not destroy completion queue, error: %d\n",
			 ret);

	/* free cq's resources */
	spin_lock_irqsave(&dev->cq_tbl_lock, flags);
	dev->cq_tbl[vcq->cq_handle] = NULL;
	spin_unlock_irqrestore(&dev->cq_tbl_lock, flags);

	pvrdma_free_cq(dev, vcq);
	atomic_dec(&dev->num_cqs);
	return 0;
}

static inline struct pvrdma_cqe *get_cqe(struct pvrdma_cq *cq, int i)
{
	return (struct pvrdma_cqe *)pvrdma_page_dir_get_ptr(
					&cq->pdir,
					cq->offset +
					sizeof(struct pvrdma_cqe) * i);
}

void _pvrdma_flush_cqe(struct pvrdma_qp *qp, struct pvrdma_cq *cq)
{
	unsigned int head;
	int has_data;

	if (!cq->is_kernel)
		return;

	/* Lock held */
	has_data = pvrdma_idx_ring_has_data(&cq->ring_state->rx,
					    cq->ibcq.cqe, &head);
	if (unlikely(has_data > 0)) {
		int items;
		int curr;
		int tail = pvrdma_idx(&cq->ring_state->rx.prod_tail,
				      cq->ibcq.cqe);
		struct pvrdma_cqe *cqe;
		struct pvrdma_cqe *curr_cqe;

		items = (tail > head) ? (tail - head) :
			(cq->ibcq.cqe - head + tail);
		curr = --tail;
		while (items-- > 0) {
			if (curr < 0)
				curr = cq->ibcq.cqe - 1;
			if (tail < 0)
				tail = cq->ibcq.cqe - 1;
			curr_cqe = get_cqe(cq, curr);
			if ((curr_cqe->qp & 0xFFFF) != qp->qp_handle) {
				if (curr != tail) {
					cqe = get_cqe(cq, tail);
					*cqe = *curr_cqe;
				}
				tail--;
			} else {
				pvrdma_idx_ring_inc(
					&cq->ring_state->rx.cons_head,
					cq->ibcq.cqe);
			}
			curr--;
		}
	}
}

static int pvrdma_poll_one(struct pvrdma_cq *cq, struct pvrdma_qp **cur_qp,
			   struct ib_wc *wc)
{
	struct pvrdma_dev *dev = to_vdev(cq->ibcq.device);
	int has_data;
	unsigned int head;
	bool tried = false;
	struct pvrdma_cqe *cqe;

retry:
	has_data = pvrdma_idx_ring_has_data(&cq->ring_state->rx,
					    cq->ibcq.cqe, &head);
	if (has_data == 0) {
		if (tried)
			return -EAGAIN;

		pvrdma_write_uar_cq(dev, cq->cq_handle | PVRDMA_UAR_CQ_POLL);

		tried = true;
		goto retry;
	} else if (has_data == PVRDMA_INVALID_IDX) {
		dev_err(&dev->pdev->dev, "CQ ring state invalid\n");
		return -EAGAIN;
	}

	cqe = get_cqe(cq, head);

	/* Ensure cqe is valid. */
	rmb();
	if (dev->qp_tbl[cqe->qp & 0xffff])
		*cur_qp = (struct pvrdma_qp *)dev->qp_tbl[cqe->qp & 0xffff];
	else
		return -EAGAIN;

	wc->opcode = pvrdma_wc_opcode_to_ib(cqe->opcode);
	wc->status = pvrdma_wc_status_to_ib(cqe->status);
	wc->wr_id = cqe->wr_id;
	wc->qp = &(*cur_qp)->ibqp;
	wc->byte_len = cqe->byte_len;
	wc->ex.imm_data = cqe->imm_data;
	wc->src_qp = cqe->src_qp;
	wc->wc_flags = pvrdma_wc_flags_to_ib(cqe->wc_flags);
	wc->pkey_index = cqe->pkey_index;
	wc->slid = cqe->slid;
	wc->sl = cqe->sl;
	wc->dlid_path_bits = cqe->dlid_path_bits;
	wc->port_num = cqe->port_num;
	wc->vendor_err = cqe->vendor_err;
	wc->network_hdr_type = pvrdma_network_type_to_ib(cqe->network_hdr_type);

	/* Update shared ring state */
	pvrdma_idx_ring_inc(&cq->ring_state->rx.cons_head, cq->ibcq.cqe);

	return 0;
}

/**
 * pvrdma_poll_cq - poll for work completion queue entries
 * @ibcq: completion queue
 * @num_entries: the maximum number of entries
 * @wc: pointer to work completion array
 *
 * @return: number of polled completion entries
 */
int pvrdma_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
{
	struct pvrdma_cq *cq = to_vcq(ibcq);
	struct pvrdma_qp *cur_qp = NULL;
	unsigned long flags;
	int npolled;

	if (num_entries < 1 || wc == NULL)
		return 0;

	spin_lock_irqsave(&cq->cq_lock, flags);
	for (npolled = 0; npolled < num_entries; ++npolled) {
		if (pvrdma_poll_one(cq, &cur_qp, wc + npolled))
			break;
	}

	spin_unlock_irqrestore(&cq->cq_lock, flags);

	/* Ensure we do not return errors from poll_cq */
	return npolled;
}