summaryrefslogtreecommitdiffstats
path: root/kernel/cgroup/rdma.c
blob: defad3c5e7dc2a9d60d34b46729f18f71393aeb6 (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
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
441
442
443
444
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
545
546
547
548
549
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
/*
 * RDMA resource limiting controller for cgroups.
 *
 * Used to allow a cgroup hierarchy to stop processes from consuming
 * additional RDMA resources after a certain limit is reached.
 *
 * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com>
 *
 * This file is subject to the terms and conditions of version 2 of the GNU
 * General Public License. See the file COPYING in the main directory of the
 * Linux distribution for more details.
 */

#include <linux/bitops.h>
#include <linux/slab.h>
#include <linux/seq_file.h>
#include <linux/cgroup.h>
#include <linux/parser.h>
#include <linux/cgroup_rdma.h>

#define RDMACG_MAX_STR "max"

/*
 * Protects list of resource pools maintained on per cgroup basis
 * and rdma device list.
 */
static DEFINE_MUTEX(rdmacg_mutex);
static LIST_HEAD(rdmacg_devices);

enum rdmacg_file_type {
	RDMACG_RESOURCE_TYPE_MAX,
	RDMACG_RESOURCE_TYPE_STAT,
};

/*
 * resource table definition as to be seen by the user.
 * Need to add entries to it when more resources are
 * added/defined at IB verb/core layer.
 */
static char const *rdmacg_resource_names[] = {
	[RDMACG_RESOURCE_HCA_HANDLE]	= "hca_handle",
	[RDMACG_RESOURCE_HCA_OBJECT]	= "hca_object",
};

/* resource tracker for each resource of rdma cgroup */
struct rdmacg_resource {
	int max;
	int usage;
};

/*
 * resource pool object which represents per cgroup, per device
 * resources. There are multiple instances of this object per cgroup,
 * therefore it cannot be embedded within rdma_cgroup structure. It
 * is maintained as list.
 */
struct rdmacg_resource_pool {
	struct rdmacg_device	*device;
	struct rdmacg_resource	resources[RDMACG_RESOURCE_MAX];

	struct list_head	cg_node;
	struct list_head	dev_node;

	/* count active user tasks of this pool */
	u64			usage_sum;
	/* total number counts which are set to max */
	int			num_max_cnt;
};

static struct rdma_cgroup *css_rdmacg(struct cgroup_subsys_state *css)
{
	return container_of(css, struct rdma_cgroup, css);
}

static struct rdma_cgroup *parent_rdmacg(struct rdma_cgroup *cg)
{
	return css_rdmacg(cg->css.parent);
}

static inline struct rdma_cgroup *get_current_rdmacg(void)
{
	return css_rdmacg(task_get_css(current, rdma_cgrp_id));
}

static void set_resource_limit(struct rdmacg_resource_pool *rpool,
			       int index, int new_max)
{
	if (new_max == S32_MAX) {
		if (rpool->resources[index].max != S32_MAX)
			rpool->num_max_cnt++;
	} else {
		if (rpool->resources[index].max == S32_MAX)
			rpool->num_max_cnt--;
	}
	rpool->resources[index].max = new_max;
}

static void set_all_resource_max_limit(struct rdmacg_resource_pool *rpool)
{
	int i;

	for (i = 0; i < RDMACG_RESOURCE_MAX; i++)
		set_resource_limit(rpool, i, S32_MAX);
}

static void free_cg_rpool_locked(struct rdmacg_resource_pool *rpool)
{
	lockdep_assert_held(&rdmacg_mutex);

	list_del(&rpool->cg_node);
	list_del(&rpool->dev_node);
	kfree(rpool);
}

static struct rdmacg_resource_pool *
find_cg_rpool_locked(struct rdma_cgroup *cg,
		     struct rdmacg_device *device)

{
	struct rdmacg_resource_pool *pool;

	lockdep_assert_held(&rdmacg_mutex);

	list_for_each_entry(pool, &cg->rpools, cg_node)
		if (pool->device == device)
			return pool;

	return NULL;
}

static struct rdmacg_resource_pool *
get_cg_rpool_locked(struct rdma_cgroup *cg, struct rdmacg_device *device)
{
	struct rdmacg_resource_pool *rpool;

	rpool = find_cg_rpool_locked(cg, device);
	if (rpool)
		return rpool;

	rpool = kzalloc(sizeof(*rpool), GFP_KERNEL);
	if (!rpool)
		return ERR_PTR(-ENOMEM);

	rpool->device = device;
	set_all_resource_max_limit(rpool);

	INIT_LIST_HEAD(&rpool->cg_node);
	INIT_LIST_HEAD(&rpool->dev_node);
	list_add_tail(&rpool->cg_node, &cg->rpools);
	list_add_tail(&rpool->dev_node, &device->rpools);
	return rpool;
}

/**
 * uncharge_cg_locked - uncharge resource for rdma cgroup
 * @cg: pointer to cg to uncharge and all parents in hierarchy
 * @device: pointer to rdmacg device
 * @index: index of the resource to uncharge in cg (resource pool)
 *
 * It also frees the resource pool which was created as part of
 * charging operation when there are no resources attached to
 * resource pool.
 */
static void
uncharge_cg_locked(struct rdma_cgroup *cg,
		   struct rdmacg_device *device,
		   enum rdmacg_resource_type index)
{
	struct rdmacg_resource_pool *rpool;

	rpool = find_cg_rpool_locked(cg, device);

	/*
	 * rpool cannot be null at this stage. Let kernel operate in case
	 * if there a bug in IB stack or rdma controller, instead of crashing
	 * the system.
	 */
	if (unlikely(!rpool)) {
		pr_warn("Invalid device %p or rdma cgroup %p\n", cg, device);
		return;
	}

	rpool->resources[index].usage--;

	/*
	 * A negative count (or overflow) is invalid,
	 * it indicates a bug in the rdma controller.
	 */
	WARN_ON_ONCE(rpool->resources[index].usage < 0);
	rpool->usage_sum--;
	if (rpool->usage_sum == 0 &&
	    rpool->num_max_cnt == RDMACG_RESOURCE_MAX) {
		/*
		 * No user of the rpool and all entries are set to max, so
		 * safe to delete this rpool.
		 */
		free_cg_rpool_locked(rpool);
	}
}

/**
 * rdmacg_uncharge_hierarchy - hierarchically uncharge rdma resource count
 * @device: pointer to rdmacg device
 * @stop_cg: while traversing hirerchy, when meet with stop_cg cgroup
 *           stop uncharging
 * @index: index of the resource to uncharge in cg in given resource pool
 */
static void rdmacg_uncharge_hierarchy(struct rdma_cgroup *cg,
				     struct rdmacg_device *device,
				     struct rdma_cgroup *stop_cg,
				     enum rdmacg_resource_type index)
{
	struct rdma_cgroup *p;

	mutex_lock(&rdmacg_mutex);

	for (p = cg; p != stop_cg; p = parent_rdmacg(p))
		uncharge_cg_locked(p, device, index);

	mutex_unlock(&rdmacg_mutex);

	css_put(&cg->css);
}

/**
 * rdmacg_uncharge - hierarchically uncharge rdma resource count
 * @device: pointer to rdmacg device
 * @index: index of the resource to uncharge in cgroup in given resource pool
 */
void rdmacg_uncharge(struct rdma_cgroup *cg,
		     struct rdmacg_device *device,
		     enum rdmacg_resource_type index)
{
	if (index >= RDMACG_RESOURCE_MAX)
		return;

	rdmacg_uncharge_hierarchy(cg, device, NULL, index);
}
EXPORT_SYMBOL(rdmacg_uncharge);

/**
 * rdmacg_try_charge - hierarchically try to charge the rdma resource
 * @rdmacg: pointer to rdma cgroup which will own this resource
 * @device: pointer to rdmacg device
 * @index: index of the resource to charge in cgroup (resource pool)
 *
 * This function follows charging resource in hierarchical way.
 * It will fail if the charge would cause the new value to exceed the
 * hierarchical limit.
 * Returns 0 if the charge succeded, otherwise -EAGAIN, -ENOMEM or -EINVAL.
 * Returns pointer to rdmacg for this resource when charging is successful.
 *
 * Charger needs to account resources on two criteria.
 * (a) per cgroup & (b) per device resource usage.
 * Per cgroup resource usage ensures that tasks of cgroup doesn't cross
 * the configured limits. Per device provides granular configuration
 * in multi device usage. It allocates resource pool in the hierarchy
 * for each parent it come across for first resource. Later on resource
 * pool will be available. Therefore it will be much faster thereon
 * to charge/uncharge.
 */
int rdmacg_try_charge(struct rdma_cgroup **rdmacg,
		      struct rdmacg_device *device,
		      enum rdmacg_resource_type index)
{
	struct rdma_cgroup *cg, *p;
	struct rdmacg_resource_pool *rpool;
	s64 new;
	int ret = 0;

	if (index >= RDMACG_RESOURCE_MAX)
		return -EINVAL;

	/*
	 * hold on to css, as cgroup can be removed but resource
	 * accounting happens on css.
	 */
	cg = get_current_rdmacg();

	mutex_lock(&rdmacg_mutex);
	for (p = cg; p; p = parent_rdmacg(p)) {
		rpool = get_cg_rpool_locked(p, device);
		if (IS_ERR(rpool)) {
			ret = PTR_ERR(rpool);
			goto err;
		} else {
			new = rpool->resources[index].usage + 1;
			if (new > rpool->resources[index].max) {
				ret = -EAGAIN;
				goto err;
			} else {
				rpool->resources[index].usage = new;
				rpool->usage_sum++;
			}
		}
	}
	mutex_unlock(&rdmacg_mutex);

	*rdmacg = cg;
	return 0;

err:
	mutex_unlock(&rdmacg_mutex);
	rdmacg_uncharge_hierarchy(cg, device, p, index);
	return ret;
}
EXPORT_SYMBOL(rdmacg_try_charge);

/**
 * rdmacg_register_device - register rdmacg device to rdma controller.
 * @device: pointer to rdmacg device whose resources need to be accounted.
 *
 * If IB stack wish a device to participate in rdma cgroup resource
 * tracking, it must invoke this API to register with rdma cgroup before
 * any user space application can start using the RDMA resources.
 * Returns 0 on success or EINVAL when table length given is beyond
 * supported size.
 */
int rdmacg_register_device(struct rdmacg_device *device)
{
	INIT_LIST_HEAD(&device->dev_node);
	INIT_LIST_HEAD(&device->rpools);

	mutex_lock(&rdmacg_mutex);
	list_add_tail(&device->dev_node, &rdmacg_devices);
	mutex_unlock(&rdmacg_mutex);
	return 0;
}
EXPORT_SYMBOL(rdmacg_register_device);

/**
 * rdmacg_unregister_device - unregister rdmacg device from rdma controller.
 * @device: pointer to rdmacg device which was previously registered with rdma
 *          controller using rdmacg_register_device().
 *
 * IB stack must invoke this after all the resources of the IB device
 * are destroyed and after ensuring that no more resources will be created
 * when this API is invoked.
 */
void rdmacg_unregister_device(struct rdmacg_device *device)
{
	struct rdmacg_resource_pool *rpool, *tmp;

	/*
	 * Synchronize with any active resource settings,
	 * usage query happening via configfs.
	 */
	mutex_lock(&rdmacg_mutex);
	list_del_init(&device->dev_node);

	/*
	 * Now that this device is off the cgroup list, its safe to free
	 * all the rpool resources.
	 */
	list_for_each_entry_safe(rpool, tmp, &device->rpools, dev_node)
		free_cg_rpool_locked(rpool);

	mutex_unlock(&rdmacg_mutex);
}
EXPORT_SYMBOL(rdmacg_unregister_device);

static int parse_resource(char *c, int *intval)
{
	substring_t argstr;
	const char **table = &rdmacg_resource_names[0];
	char *name, *value = c;
	size_t len;
	int ret, i = 0;

	name = strsep(&value, "=");
	if (!name || !value)
		return -EINVAL;

	len = strlen(value);

	for (i = 0; i < RDMACG_RESOURCE_MAX; i++) {
		if (strcmp(table[i], name))
			continue;

		argstr.from = value;
		argstr.to = value + len;

		ret = match_int(&argstr, intval);
		if (ret >= 0) {
			if (*intval < 0)
				break;
			return i;
		}
		if (strncmp(value, RDMACG_MAX_STR, len) == 0) {
			*intval = S32_MAX;
			return i;
		}
		break;
	}
	return -EINVAL;
}

static int rdmacg_parse_limits(char *options,
			       int *new_limits, unsigned long *enables)
{
	char *c;
	int err = -EINVAL;

	/* parse resource options */
	while ((c = strsep(&options, " ")) != NULL) {
		int index, intval;

		index = parse_resource(c, &intval);
		if (index < 0)
			goto err;

		new_limits[index] = intval;
		*enables |= BIT(index);
	}
	return 0;

err:
	return err;
}

static struct rdmacg_device *rdmacg_get_device_locked(const char *name)
{
	struct rdmacg_device *device;

	lockdep_assert_held(&rdmacg_mutex);

	list_for_each_entry(device, &rdmacg_devices, dev_node)
		if (!strcmp(name, device->name))
			return device;

	return NULL;
}

static ssize_t rdmacg_resource_set_max(struct kernfs_open_file *of,
				       char *buf, size_t nbytes, loff_t off)
{
	struct rdma_cgroup *cg = css_rdmacg(of_css(of));
	const char *dev_name;
	struct rdmacg_resource_pool *rpool;
	struct rdmacg_device *device;
	char *options = strstrip(buf);
	int *new_limits;
	unsigned long enables = 0;
	int i = 0, ret = 0;

	/* extract the device name first */
	dev_name = strsep(&options, " ");
	if (!dev_name) {
		ret = -EINVAL;
		goto err;
	}

	new_limits = kcalloc(RDMACG_RESOURCE_MAX, sizeof(int), GFP_KERNEL);
	if (!new_limits) {
		ret = -ENOMEM;
		goto err;
	}

	ret = rdmacg_parse_limits(options, new_limits, &enables);
	if (ret)
		goto parse_err;

	/* acquire lock to synchronize with hot plug devices */
	mutex_lock(&rdmacg_mutex);

	device = rdmacg_get_device_locked(dev_name);
	if (!device) {
		ret = -ENODEV;
		goto dev_err;
	}

	rpool = get_cg_rpool_locked(cg, device);
	if (IS_ERR(rpool)) {
		ret = PTR_ERR(rpool);
		goto dev_err;
	}

	/* now set the new limits of the rpool */
	for_each_set_bit(i, &enables, RDMACG_RESOURCE_MAX)
		set_resource_limit(rpool, i, new_limits[i]);

	if (rpool->usage_sum == 0 &&
	    rpool->num_max_cnt == RDMACG_RESOURCE_MAX) {
		/*
		 * No user of the rpool and all entries are set to max, so
		 * safe to delete this rpool.
		 */
		free_cg_rpool_locked(rpool);
	}

dev_err:
	mutex_unlock(&rdmacg_mutex);

parse_err:
	kfree(new_limits);

err:
	return ret ?: nbytes;
}

static void print_rpool_values(struct seq_file *sf,
			       struct rdmacg_resource_pool *rpool)
{
	enum rdmacg_file_type sf_type;
	int i;
	u32 value;

	sf_type = seq_cft(sf)->private;

	for (i = 0; i < RDMACG_RESOURCE_MAX; i++) {
		seq_puts(sf, rdmacg_resource_names[i]);
		seq_putc(sf, '=');
		if (sf_type == RDMACG_RESOURCE_TYPE_MAX) {
			if (rpool)
				value = rpool->resources[i].max;
			else
				value = S32_MAX;
		} else {
			if (rpool)
				value = rpool->resources[i].usage;
			else
				value = 0;
		}

		if (value == S32_MAX)
			seq_puts(sf, RDMACG_MAX_STR);
		else
			seq_printf(sf, "%d", value);
		seq_putc(sf, ' ');
	}
}

static int rdmacg_resource_read(struct seq_file *sf, void *v)
{
	struct rdmacg_device *device;
	struct rdmacg_resource_pool *rpool;
	struct rdma_cgroup *cg = css_rdmacg(seq_css(sf));

	mutex_lock(&rdmacg_mutex);

	list_for_each_entry(device, &rdmacg_devices, dev_node) {
		seq_printf(sf, "%s ", device->name);

		rpool = find_cg_rpool_locked(cg, device);
		print_rpool_values(sf, rpool);

		seq_putc(sf, '\n');
	}

	mutex_unlock(&rdmacg_mutex);
	return 0;
}

static struct cftype rdmacg_files[] = {
	{
		.name = "max",
		.write = rdmacg_resource_set_max,
		.seq_show = rdmacg_resource_read,
		.private = RDMACG_RESOURCE_TYPE_MAX,
		.flags = CFTYPE_NOT_ON_ROOT,
	},
	{
		.name = "current",
		.seq_show = rdmacg_resource_read,
		.private = RDMACG_RESOURCE_TYPE_STAT,
		.flags = CFTYPE_NOT_ON_ROOT,
	},
	{ }	/* terminate */
};

static struct cgroup_subsys_state *
rdmacg_css_alloc(struct cgroup_subsys_state *parent)
{
	struct rdma_cgroup *cg;

	cg = kzalloc(sizeof(*cg), GFP_KERNEL);
	if (!cg)
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&cg->rpools);
	return &cg->css;
}

static void rdmacg_css_free(struct cgroup_subsys_state *css)
{
	struct rdma_cgroup *cg = css_rdmacg(css);

	kfree(cg);
}

/**
 * rdmacg_css_offline - cgroup css_offline callback
 * @css: css of interest
 *
 * This function is called when @css is about to go away and responsible
 * for shooting down all rdmacg associated with @css. As part of that it
 * marks all the resource pool entries to max value, so that when resources are
 * uncharged, associated resource pool can be freed as well.
 */
static void rdmacg_css_offline(struct cgroup_subsys_state *css)
{
	struct rdma_cgroup *cg = css_rdmacg(css);
	struct rdmacg_resource_pool *rpool;

	mutex_lock(&rdmacg_mutex);

	list_for_each_entry(rpool, &cg->rpools, cg_node)
		set_all_resource_max_limit(rpool);

	mutex_unlock(&rdmacg_mutex);
}

struct cgroup_subsys rdma_cgrp_subsys = {
	.css_alloc	= rdmacg_css_alloc,
	.css_free	= rdmacg_css_free,
	.css_offline	= rdmacg_css_offline,
	.legacy_cftypes	= rdmacg_files,
	.dfl_cftypes	= rdmacg_files,
};
OpenPOWER on IntegriCloud