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
|
/*
* Copyright(c) 2016 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
*
* GPL LICENSE SUMMARY
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* published by the Free Software Foundation.
*
* 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 for more details.
*
* BSD 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.
* - Neither the name of Intel Corporation nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* 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
* OWNER 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 <linux/err.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <rdma/uverbs_ioctl.h>
#include "srq.h"
#include "vt.h"
#include "qp.h"
/**
* rvt_driver_srq_init - init srq resources on a per driver basis
* @rdi: rvt dev structure
*
* Do any initialization needed when a driver registers with rdmavt.
*/
void rvt_driver_srq_init(struct rvt_dev_info *rdi)
{
spin_lock_init(&rdi->n_srqs_lock);
rdi->n_srqs_allocated = 0;
}
/**
* rvt_create_srq - create a shared receive queue
* @ibsrq: the protection domain of the SRQ to create
* @srq_init_attr: the attributes of the SRQ
* @udata: data from libibverbs when creating a user SRQ
*
* Return: 0 on success
*/
int rvt_create_srq(struct ib_srq *ibsrq, struct ib_srq_init_attr *srq_init_attr,
struct ib_udata *udata)
{
struct rvt_dev_info *dev = ib_to_rvt(ibsrq->device);
struct rvt_srq *srq = ibsrq_to_rvtsrq(ibsrq);
u32 sz;
int ret;
if (srq_init_attr->srq_type != IB_SRQT_BASIC)
return -EOPNOTSUPP;
if (srq_init_attr->attr.max_sge == 0 ||
srq_init_attr->attr.max_sge > dev->dparms.props.max_srq_sge ||
srq_init_attr->attr.max_wr == 0 ||
srq_init_attr->attr.max_wr > dev->dparms.props.max_srq_wr)
return -EINVAL;
/*
* Need to use vmalloc() if we want to support large #s of entries.
*/
srq->rq.size = srq_init_attr->attr.max_wr + 1;
srq->rq.max_sge = srq_init_attr->attr.max_sge;
sz = sizeof(struct ib_sge) * srq->rq.max_sge +
sizeof(struct rvt_rwqe);
if (rvt_alloc_rq(&srq->rq, srq->rq.size * sz,
dev->dparms.node, udata)) {
ret = -ENOMEM;
goto bail_srq;
}
/*
* Return the address of the RWQ as the offset to mmap.
* See rvt_mmap() for details.
*/
if (udata && udata->outlen >= sizeof(__u64)) {
u32 s = sizeof(struct rvt_rwq) + srq->rq.size * sz;
srq->ip = rvt_create_mmap_info(dev, s, udata, srq->rq.wq);
if (IS_ERR(srq->ip)) {
ret = PTR_ERR(srq->ip);
goto bail_wq;
}
ret = ib_copy_to_udata(udata, &srq->ip->offset,
sizeof(srq->ip->offset));
if (ret)
goto bail_ip;
}
/*
* ib_create_srq() will initialize srq->ibsrq.
*/
spin_lock_init(&srq->rq.lock);
srq->limit = srq_init_attr->attr.srq_limit;
spin_lock(&dev->n_srqs_lock);
if (dev->n_srqs_allocated == dev->dparms.props.max_srq) {
spin_unlock(&dev->n_srqs_lock);
ret = -ENOMEM;
goto bail_ip;
}
dev->n_srqs_allocated++;
spin_unlock(&dev->n_srqs_lock);
if (srq->ip) {
spin_lock_irq(&dev->pending_lock);
list_add(&srq->ip->pending_mmaps, &dev->pending_mmaps);
spin_unlock_irq(&dev->pending_lock);
}
return 0;
bail_ip:
kfree(srq->ip);
bail_wq:
rvt_free_rq(&srq->rq);
bail_srq:
return ret;
}
/**
* rvt_modify_srq - modify a shared receive queue
* @ibsrq: the SRQ to modify
* @attr: the new attributes of the SRQ
* @attr_mask: indicates which attributes to modify
* @udata: user data for libibverbs.so
*
* Return: 0 on success
*/
int rvt_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
enum ib_srq_attr_mask attr_mask,
struct ib_udata *udata)
{
struct rvt_srq *srq = ibsrq_to_rvtsrq(ibsrq);
struct rvt_dev_info *dev = ib_to_rvt(ibsrq->device);
struct rvt_rq tmp_rq = {};
int ret = 0;
if (attr_mask & IB_SRQ_MAX_WR) {
struct rvt_krwq *okwq = NULL;
struct rvt_rwq *owq = NULL;
struct rvt_rwqe *p;
u32 sz, size, n, head, tail;
/* Check that the requested sizes are below the limits. */
if ((attr->max_wr > dev->dparms.props.max_srq_wr) ||
((attr_mask & IB_SRQ_LIMIT) ?
attr->srq_limit : srq->limit) > attr->max_wr)
return -EINVAL;
sz = sizeof(struct rvt_rwqe) +
srq->rq.max_sge * sizeof(struct ib_sge);
size = attr->max_wr + 1;
if (rvt_alloc_rq(&tmp_rq, size * sz, dev->dparms.node,
udata))
return -ENOMEM;
/* Check that we can write the offset to mmap. */
if (udata && udata->inlen >= sizeof(__u64)) {
__u64 offset_addr;
__u64 offset = 0;
ret = ib_copy_from_udata(&offset_addr, udata,
sizeof(offset_addr));
if (ret)
goto bail_free;
udata->outbuf = (void __user *)
(unsigned long)offset_addr;
ret = ib_copy_to_udata(udata, &offset,
sizeof(offset));
if (ret)
goto bail_free;
}
spin_lock_irq(&srq->rq.kwq->c_lock);
/*
* validate head and tail pointer values and compute
* the number of remaining WQEs.
*/
if (udata) {
owq = srq->rq.wq;
head = RDMA_READ_UAPI_ATOMIC(owq->head);
tail = RDMA_READ_UAPI_ATOMIC(owq->tail);
} else {
okwq = srq->rq.kwq;
head = okwq->head;
tail = okwq->tail;
}
if (head >= srq->rq.size || tail >= srq->rq.size) {
ret = -EINVAL;
goto bail_unlock;
}
n = head;
if (n < tail)
n += srq->rq.size - tail;
else
n -= tail;
if (size <= n) {
ret = -EINVAL;
goto bail_unlock;
}
n = 0;
p = tmp_rq.kwq->curr_wq;
while (tail != head) {
struct rvt_rwqe *wqe;
int i;
wqe = rvt_get_rwqe_ptr(&srq->rq, tail);
p->wr_id = wqe->wr_id;
p->num_sge = wqe->num_sge;
for (i = 0; i < wqe->num_sge; i++)
p->sg_list[i] = wqe->sg_list[i];
n++;
p = (struct rvt_rwqe *)((char *)p + sz);
if (++tail >= srq->rq.size)
tail = 0;
}
srq->rq.kwq = tmp_rq.kwq;
if (udata) {
srq->rq.wq = tmp_rq.wq;
RDMA_WRITE_UAPI_ATOMIC(tmp_rq.wq->head, n);
RDMA_WRITE_UAPI_ATOMIC(tmp_rq.wq->tail, 0);
} else {
tmp_rq.kwq->head = n;
tmp_rq.kwq->tail = 0;
}
srq->rq.size = size;
if (attr_mask & IB_SRQ_LIMIT)
srq->limit = attr->srq_limit;
spin_unlock_irq(&srq->rq.kwq->c_lock);
vfree(owq);
kvfree(okwq);
if (srq->ip) {
struct rvt_mmap_info *ip = srq->ip;
struct rvt_dev_info *dev = ib_to_rvt(srq->ibsrq.device);
u32 s = sizeof(struct rvt_rwq) + size * sz;
rvt_update_mmap_info(dev, ip, s, tmp_rq.wq);
/*
* Return the offset to mmap.
* See rvt_mmap() for details.
*/
if (udata && udata->inlen >= sizeof(__u64)) {
ret = ib_copy_to_udata(udata, &ip->offset,
sizeof(ip->offset));
if (ret)
return ret;
}
/*
* Put user mapping info onto the pending list
* unless it already is on the list.
*/
spin_lock_irq(&dev->pending_lock);
if (list_empty(&ip->pending_mmaps))
list_add(&ip->pending_mmaps,
&dev->pending_mmaps);
spin_unlock_irq(&dev->pending_lock);
}
} else if (attr_mask & IB_SRQ_LIMIT) {
spin_lock_irq(&srq->rq.kwq->c_lock);
if (attr->srq_limit >= srq->rq.size)
ret = -EINVAL;
else
srq->limit = attr->srq_limit;
spin_unlock_irq(&srq->rq.kwq->c_lock);
}
return ret;
bail_unlock:
spin_unlock_irq(&srq->rq.kwq->c_lock);
bail_free:
rvt_free_rq(&tmp_rq);
return ret;
}
/**
* rvt_query_srq - query srq data
* @ibsrq: srq to query
* @attr: return info in attr
*
* Return: always 0
*/
int rvt_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr)
{
struct rvt_srq *srq = ibsrq_to_rvtsrq(ibsrq);
attr->max_wr = srq->rq.size - 1;
attr->max_sge = srq->rq.max_sge;
attr->srq_limit = srq->limit;
return 0;
}
/**
* rvt_destroy_srq - destory an srq
* @ibsrq: srq object to destroy
* @udata: user data for libibverbs.so
*/
int rvt_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
{
struct rvt_srq *srq = ibsrq_to_rvtsrq(ibsrq);
struct rvt_dev_info *dev = ib_to_rvt(ibsrq->device);
spin_lock(&dev->n_srqs_lock);
dev->n_srqs_allocated--;
spin_unlock(&dev->n_srqs_lock);
if (srq->ip)
kref_put(&srq->ip->ref, rvt_release_mmap_info);
kvfree(srq->rq.kwq);
return 0;
}
|