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
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
|
/*
* Copyright (c) 2012 Mellanox Technologies. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* 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.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#include <rdma/ib_mad.h>
#include <linux/mlx4/cmd.h>
#include <linux/idr.h>
#include <rdma/ib_cm.h>
#include "mlx4_ib.h"
#define CM_CLEANUP_CACHE_TIMEOUT (5 * HZ)
struct id_map_entry {
struct rb_node node;
u32 sl_cm_id;
u32 pv_cm_id;
int slave_id;
int scheduled_delete;
struct mlx4_ib_dev *dev;
struct list_head list;
struct delayed_work timeout;
};
struct cm_generic_msg {
struct ib_mad_hdr hdr;
__be32 local_comm_id;
__be32 remote_comm_id;
};
struct cm_req_msg {
unsigned char unused[0x60];
union ib_gid primary_path_sgid;
};
static void set_local_comm_id(struct ib_mad *mad, u32 cm_id)
{
struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
msg->local_comm_id = cpu_to_be32(cm_id);
}
static u32 get_local_comm_id(struct ib_mad *mad)
{
struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
return be32_to_cpu(msg->local_comm_id);
}
static void set_remote_comm_id(struct ib_mad *mad, u32 cm_id)
{
struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
msg->remote_comm_id = cpu_to_be32(cm_id);
}
static u32 get_remote_comm_id(struct ib_mad *mad)
{
struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
return be32_to_cpu(msg->remote_comm_id);
}
static union ib_gid gid_from_req_msg(struct ib_device *ibdev, struct ib_mad *mad)
{
struct cm_req_msg *msg = (struct cm_req_msg *)mad;
return msg->primary_path_sgid;
}
/* Lock should be taken before called */
static struct id_map_entry *
id_map_find_by_sl_id(struct ib_device *ibdev, u32 slave_id, u32 sl_cm_id)
{
struct rb_root *sl_id_map = &to_mdev(ibdev)->sriov.sl_id_map;
struct rb_node *node = sl_id_map->rb_node;
while (node) {
struct id_map_entry *id_map_entry =
rb_entry(node, struct id_map_entry, node);
if (id_map_entry->sl_cm_id > sl_cm_id)
node = node->rb_left;
else if (id_map_entry->sl_cm_id < sl_cm_id)
node = node->rb_right;
else if (id_map_entry->slave_id > slave_id)
node = node->rb_left;
else if (id_map_entry->slave_id < slave_id)
node = node->rb_right;
else
return id_map_entry;
}
return NULL;
}
static void id_map_ent_timeout(struct work_struct *work)
{
struct delayed_work *delay = to_delayed_work(work);
struct id_map_entry *ent = container_of(delay, struct id_map_entry, timeout);
struct id_map_entry *db_ent, *found_ent;
struct mlx4_ib_dev *dev = ent->dev;
struct mlx4_ib_sriov *sriov = &dev->sriov;
struct rb_root *sl_id_map = &sriov->sl_id_map;
int pv_id = (int) ent->pv_cm_id;
spin_lock(&sriov->id_map_lock);
db_ent = (struct id_map_entry *)idr_find(&sriov->pv_id_table, pv_id);
if (!db_ent)
goto out;
found_ent = id_map_find_by_sl_id(&dev->ib_dev, ent->slave_id, ent->sl_cm_id);
if (found_ent && found_ent == ent)
rb_erase(&found_ent->node, sl_id_map);
idr_remove(&sriov->pv_id_table, pv_id);
out:
list_del(&ent->list);
spin_unlock(&sriov->id_map_lock);
kfree(ent);
}
static void id_map_find_del(struct ib_device *ibdev, int pv_cm_id)
{
struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
struct rb_root *sl_id_map = &sriov->sl_id_map;
struct id_map_entry *ent, *found_ent;
spin_lock(&sriov->id_map_lock);
ent = (struct id_map_entry *)idr_find(&sriov->pv_id_table, pv_cm_id);
if (!ent)
goto out;
found_ent = id_map_find_by_sl_id(ibdev, ent->slave_id, ent->sl_cm_id);
if (found_ent && found_ent == ent)
rb_erase(&found_ent->node, sl_id_map);
idr_remove(&sriov->pv_id_table, pv_cm_id);
out:
spin_unlock(&sriov->id_map_lock);
}
static void sl_id_map_add(struct ib_device *ibdev, struct id_map_entry *new)
{
struct rb_root *sl_id_map = &to_mdev(ibdev)->sriov.sl_id_map;
struct rb_node **link = &sl_id_map->rb_node, *parent = NULL;
struct id_map_entry *ent;
int slave_id = new->slave_id;
int sl_cm_id = new->sl_cm_id;
ent = id_map_find_by_sl_id(ibdev, slave_id, sl_cm_id);
if (ent) {
pr_debug("overriding existing sl_id_map entry (cm_id = %x)\n",
sl_cm_id);
rb_replace_node(&ent->node, &new->node, sl_id_map);
return;
}
/* Go to the bottom of the tree */
while (*link) {
parent = *link;
ent = rb_entry(parent, struct id_map_entry, node);
if (ent->sl_cm_id > sl_cm_id || (ent->sl_cm_id == sl_cm_id && ent->slave_id > slave_id))
link = &(*link)->rb_left;
else
link = &(*link)->rb_right;
}
rb_link_node(&new->node, parent, link);
rb_insert_color(&new->node, sl_id_map);
}
static struct id_map_entry *
id_map_alloc(struct ib_device *ibdev, int slave_id, u32 sl_cm_id)
{
int ret, id;
static int next_id;
struct id_map_entry *ent;
struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
ent = kmalloc(sizeof (struct id_map_entry), GFP_KERNEL);
if (!ent) {
mlx4_ib_warn(ibdev, "Couldn't allocate id cache entry - out of memory\n");
return ERR_PTR(-ENOMEM);
}
ent->sl_cm_id = sl_cm_id;
ent->slave_id = slave_id;
ent->scheduled_delete = 0;
ent->dev = to_mdev(ibdev);
INIT_DELAYED_WORK(&ent->timeout, id_map_ent_timeout);
do {
spin_lock(&to_mdev(ibdev)->sriov.id_map_lock);
ret = idr_get_new_above(&sriov->pv_id_table, ent,
next_id, &id);
if (!ret) {
next_id = ((unsigned) id + 1) & MAX_IDR_MASK;
ent->pv_cm_id = (u32)id;
sl_id_map_add(ibdev, ent);
}
spin_unlock(&sriov->id_map_lock);
} while (ret == -EAGAIN && idr_pre_get(&sriov->pv_id_table, GFP_KERNEL));
/*the function idr_get_new_above can return -ENOSPC, so don't insert in that case.*/
if (!ret) {
spin_lock(&sriov->id_map_lock);
list_add_tail(&ent->list, &sriov->cm_list);
spin_unlock(&sriov->id_map_lock);
return ent;
}
/*error flow*/
kfree(ent);
mlx4_ib_warn(ibdev, "No more space in the idr (err:0x%x)\n", ret);
return ERR_PTR(-ENOMEM);
}
static struct id_map_entry *
id_map_get(struct ib_device *ibdev, int *pv_cm_id, int sl_cm_id, int slave_id)
{
struct id_map_entry *ent;
struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
spin_lock(&sriov->id_map_lock);
if (*pv_cm_id == -1) {
ent = id_map_find_by_sl_id(ibdev, sl_cm_id, slave_id);
if (ent)
*pv_cm_id = (int) ent->pv_cm_id;
} else
ent = (struct id_map_entry *)idr_find(&sriov->pv_id_table, *pv_cm_id);
spin_unlock(&sriov->id_map_lock);
return ent;
}
static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id)
{
struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
unsigned long flags;
spin_lock(&sriov->id_map_lock);
spin_lock_irqsave(&sriov->going_down_lock, flags);
/*make sure that there is no schedule inside the scheduled work.*/
if (!sriov->is_going_down) {
id->scheduled_delete = 1;
schedule_delayed_work(&id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
}
spin_unlock_irqrestore(&sriov->going_down_lock, flags);
spin_unlock(&sriov->id_map_lock);
}
int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id,
struct ib_mad *mad)
{
struct id_map_entry *id;
u32 sl_cm_id;
int pv_cm_id = -1;
sl_cm_id = get_local_comm_id(mad);
if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID ||
mad->mad_hdr.attr_id == CM_REP_ATTR_ID) {
id = id_map_alloc(ibdev, slave_id, sl_cm_id);
if (IS_ERR(id)) {
mlx4_ib_warn(ibdev, "%s: id{slave: %d, sl_cm_id: 0x%x} Failed to id_map_alloc\n",
__func__, slave_id, sl_cm_id);
return PTR_ERR(id);
}
} else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID) {
return 0;
} else {
id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id);
}
if (!id) {
pr_debug("id{slave: %d, sl_cm_id: 0x%x} is NULL!\n",
slave_id, sl_cm_id);
return -EINVAL;
}
set_local_comm_id(mad, id->pv_cm_id);
if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID)
schedule_delayed(ibdev, id);
else if (mad->mad_hdr.attr_id == CM_DREP_ATTR_ID)
id_map_find_del(ibdev, pv_cm_id);
return 0;
}
int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
struct ib_mad *mad, int is_eth)
{
u32 pv_cm_id;
struct id_map_entry *id;
if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID) {
union ib_gid gid;
if (is_eth)
return 0;
gid = gid_from_req_msg(ibdev, mad);
*slave = mlx4_ib_find_real_gid(ibdev, port, gid.global.interface_id);
if (*slave < 0) {
mlx4_ib_warn(ibdev, "failed matching slave_id by gid (0x%llx)\n",
gid.global.interface_id);
return -ENOENT;
}
return 0;
}
pv_cm_id = get_remote_comm_id(mad);
id = id_map_get(ibdev, (int *)&pv_cm_id, -1, -1);
if (!id) {
pr_debug("Couldn't find an entry for pv_cm_id 0x%x\n", pv_cm_id);
return -ENOENT;
}
if (!is_eth)
*slave = id->slave_id;
set_remote_comm_id(mad, id->sl_cm_id);
if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID)
schedule_delayed(ibdev, id);
else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID ||
mad->mad_hdr.attr_id == CM_DREP_ATTR_ID) {
id_map_find_del(ibdev, (int) pv_cm_id);
}
return 0;
}
void mlx4_ib_cm_paravirt_init(struct mlx4_ib_dev *dev)
{
spin_lock_init(&dev->sriov.id_map_lock);
INIT_LIST_HEAD(&dev->sriov.cm_list);
dev->sriov.sl_id_map = RB_ROOT;
idr_init(&dev->sriov.pv_id_table);
idr_pre_get(&dev->sriov.pv_id_table, GFP_KERNEL);
}
/* slave = -1 ==> all slaves */
/* TBD -- call paravirt clean for single slave. Need for slave RESET event */
void mlx4_ib_cm_paravirt_clean(struct mlx4_ib_dev *dev, int slave)
{
struct mlx4_ib_sriov *sriov = &dev->sriov;
struct rb_root *sl_id_map = &sriov->sl_id_map;
struct list_head lh;
struct rb_node *nd;
int need_flush = 1;
struct id_map_entry *map, *tmp_map;
/* cancel all delayed work queue entries */
INIT_LIST_HEAD(&lh);
spin_lock(&sriov->id_map_lock);
list_for_each_entry_safe(map, tmp_map, &dev->sriov.cm_list, list) {
if (slave < 0 || slave == map->slave_id) {
if (map->scheduled_delete)
need_flush &= !!cancel_delayed_work(&map->timeout);
}
}
spin_unlock(&sriov->id_map_lock);
if (!need_flush)
flush_scheduled_work(); /* make sure all timers were flushed */
/* now, remove all leftover entries from databases*/
spin_lock(&sriov->id_map_lock);
if (slave < 0) {
while (rb_first(sl_id_map)) {
struct id_map_entry *ent =
rb_entry(rb_first(sl_id_map),
struct id_map_entry, node);
rb_erase(&ent->node, sl_id_map);
idr_remove(&sriov->pv_id_table, (int) ent->pv_cm_id);
}
list_splice_init(&dev->sriov.cm_list, &lh);
} else {
/* first, move nodes belonging to slave to db remove list */
nd = rb_first(sl_id_map);
while (nd) {
struct id_map_entry *ent =
rb_entry(nd, struct id_map_entry, node);
nd = rb_next(nd);
if (ent->slave_id == slave)
list_move_tail(&ent->list, &lh);
}
/* remove those nodes from databases */
list_for_each_entry_safe(map, tmp_map, &lh, list) {
rb_erase(&map->node, sl_id_map);
idr_remove(&sriov->pv_id_table, (int) map->pv_cm_id);
}
/* add remaining nodes from cm_list */
list_for_each_entry_safe(map, tmp_map, &dev->sriov.cm_list, list) {
if (slave == map->slave_id)
list_move_tail(&map->list, &lh);
}
}
spin_unlock(&sriov->id_map_lock);
/* free any map entries left behind due to cancel_delayed_work above */
list_for_each_entry_safe(map, tmp_map, &lh, list) {
list_del(&map->list);
kfree(map);
}
}
|