summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/memalloc.c
blob: 5f83be1d20181b47a30ebd34cba708b51ea48349 (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
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
#include <linux/mm.h>
#include <linux/llist.h>
#include <linux/bpf.h>
#include <linux/irq_work.h>
#include <linux/bpf_mem_alloc.h>
#include <linux/memcontrol.h>
#include <asm/local.h>

/* Any context (including NMI) BPF specific memory allocator.
 *
 * Tracing BPF programs can attach to kprobe and fentry. Hence they
 * run in unknown context where calling plain kmalloc() might not be safe.
 *
 * Front-end kmalloc() with per-cpu per-bucket cache of free elements.
 * Refill this cache asynchronously from irq_work.
 *
 * CPU_0 buckets
 * 16 32 64 96 128 196 256 512 1024 2048 4096
 * ...
 * CPU_N buckets
 * 16 32 64 96 128 196 256 512 1024 2048 4096
 *
 * The buckets are prefilled at the start.
 * BPF programs always run with migration disabled.
 * It's safe to allocate from cache of the current cpu with irqs disabled.
 * Free-ing is always done into bucket of the current cpu as well.
 * irq_work trims extra free elements from buckets with kfree
 * and refills them with kmalloc, so global kmalloc logic takes care
 * of freeing objects allocated by one cpu and freed on another.
 *
 * Every allocated objected is padded with extra 8 bytes that contains
 * struct llist_node.
 */
#define LLIST_NODE_SZ sizeof(struct llist_node)

/* similar to kmalloc, but sizeof == 8 bucket is gone */
static u8 size_index[24] __ro_after_init = {
	3,	/* 8 */
	3,	/* 16 */
	4,	/* 24 */
	4,	/* 32 */
	5,	/* 40 */
	5,	/* 48 */
	5,	/* 56 */
	5,	/* 64 */
	1,	/* 72 */
	1,	/* 80 */
	1,	/* 88 */
	1,	/* 96 */
	6,	/* 104 */
	6,	/* 112 */
	6,	/* 120 */
	6,	/* 128 */
	2,	/* 136 */
	2,	/* 144 */
	2,	/* 152 */
	2,	/* 160 */
	2,	/* 168 */
	2,	/* 176 */
	2,	/* 184 */
	2	/* 192 */
};

static int bpf_mem_cache_idx(size_t size)
{
	if (!size || size > 4096)
		return -1;

	if (size <= 192)
		return size_index[(size - 1) / 8] - 1;

	return fls(size - 1) - 1;
}

#define NUM_CACHES 11

struct bpf_mem_cache {
	/* per-cpu list of free objects of size 'unit_size'.
	 * All accesses are done with interrupts disabled and 'active' counter
	 * protection with __llist_add() and __llist_del_first().
	 */
	struct llist_head free_llist;
	local_t active;

	/* Operations on the free_list from unit_alloc/unit_free/bpf_mem_refill
	 * are sequenced by per-cpu 'active' counter. But unit_free() cannot
	 * fail. When 'active' is busy the unit_free() will add an object to
	 * free_llist_extra.
	 */
	struct llist_head free_llist_extra;

	struct irq_work refill_work;
	struct obj_cgroup *objcg;
	int unit_size;
	/* count of objects in free_llist */
	int free_cnt;
	int low_watermark, high_watermark, batch;
	int percpu_size;

	struct rcu_head rcu;
	struct llist_head free_by_rcu;
	struct llist_head waiting_for_gp;
	atomic_t call_rcu_in_progress;
};

struct bpf_mem_caches {
	struct bpf_mem_cache cache[NUM_CACHES];
};

static struct llist_node notrace *__llist_del_first(struct llist_head *head)
{
	struct llist_node *entry, *next;

	entry = head->first;
	if (!entry)
		return NULL;
	next = entry->next;
	head->first = next;
	return entry;
}

static void *__alloc(struct bpf_mem_cache *c, int node)
{
	/* Allocate, but don't deplete atomic reserves that typical
	 * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc
	 * will allocate from the current numa node which is what we
	 * want here.
	 */
	gfp_t flags = GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT;

	if (c->percpu_size) {
		void **obj = kmalloc_node(c->percpu_size, flags, node);
		void *pptr = __alloc_percpu_gfp(c->unit_size, 8, flags);

		if (!obj || !pptr) {
			free_percpu(pptr);
			kfree(obj);
			return NULL;
		}
		obj[1] = pptr;
		return obj;
	}

	return kmalloc_node(c->unit_size, flags, node);
}

static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c)
{
#ifdef CONFIG_MEMCG_KMEM
	if (c->objcg)
		return get_mem_cgroup_from_objcg(c->objcg);
#endif

#ifdef CONFIG_MEMCG
	return root_mem_cgroup;
#else
	return NULL;
#endif
}

/* Mostly runs from irq_work except __init phase. */
static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
{
	struct mem_cgroup *memcg = NULL, *old_memcg;
	unsigned long flags;
	void *obj;
	int i;

	memcg = get_memcg(c);
	old_memcg = set_active_memcg(memcg);
	for (i = 0; i < cnt; i++) {
		obj = __alloc(c, node);
		if (!obj)
			break;
		if (IS_ENABLED(CONFIG_PREEMPT_RT))
			/* In RT irq_work runs in per-cpu kthread, so disable
			 * interrupts to avoid preemption and interrupts and
			 * reduce the chance of bpf prog executing on this cpu
			 * when active counter is busy.
			 */
			local_irq_save(flags);
		/* alloc_bulk runs from irq_work which will not preempt a bpf
		 * program that does unit_alloc/unit_free since IRQs are
		 * disabled there. There is no race to increment 'active'
		 * counter. It protects free_llist from corruption in case NMI
		 * bpf prog preempted this loop.
		 */
		WARN_ON_ONCE(local_inc_return(&c->active) != 1);
		__llist_add(obj, &c->free_llist);
		c->free_cnt++;
		local_dec(&c->active);
		if (IS_ENABLED(CONFIG_PREEMPT_RT))
			local_irq_restore(flags);
	}
	set_active_memcg(old_memcg);
	mem_cgroup_put(memcg);
}

static void free_one(struct bpf_mem_cache *c, void *obj)
{
	if (c->percpu_size) {
		free_percpu(((void **)obj)[1]);
		kfree(obj);
		return;
	}

	kfree(obj);
}

static void __free_rcu(struct rcu_head *head)
{
	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
	struct llist_node *llnode = llist_del_all(&c->waiting_for_gp);
	struct llist_node *pos, *t;

	llist_for_each_safe(pos, t, llnode)
		free_one(c, pos);
	atomic_set(&c->call_rcu_in_progress, 0);
}

static void __free_rcu_tasks_trace(struct rcu_head *head)
{
	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);

	call_rcu(&c->rcu, __free_rcu);
}

static void enque_to_free(struct bpf_mem_cache *c, void *obj)
{
	struct llist_node *llnode = obj;

	/* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work.
	 * Nothing races to add to free_by_rcu list.
	 */
	__llist_add(llnode, &c->free_by_rcu);
}

static void do_call_rcu(struct bpf_mem_cache *c)
{
	struct llist_node *llnode, *t;

	if (atomic_xchg(&c->call_rcu_in_progress, 1))
		return;

	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
		/* There is no concurrent __llist_add(waiting_for_gp) access.
		 * It doesn't race with llist_del_all either.
		 * But there could be two concurrent llist_del_all(waiting_for_gp):
		 * from __free_rcu() and from drain_mem_cache().
		 */
		__llist_add(llnode, &c->waiting_for_gp);
	/* Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
	 * Then use call_rcu() to wait for normal progs to finish
	 * and finally do free_one() on each element.
	 */
	call_rcu_tasks_trace(&c->rcu, __free_rcu_tasks_trace);
}

static void free_bulk(struct bpf_mem_cache *c)
{
	struct llist_node *llnode, *t;
	unsigned long flags;
	int cnt;

	do {
		if (IS_ENABLED(CONFIG_PREEMPT_RT))
			local_irq_save(flags);
		WARN_ON_ONCE(local_inc_return(&c->active) != 1);
		llnode = __llist_del_first(&c->free_llist);
		if (llnode)
			cnt = --c->free_cnt;
		else
			cnt = 0;
		local_dec(&c->active);
		if (IS_ENABLED(CONFIG_PREEMPT_RT))
			local_irq_restore(flags);
		if (llnode)
			enque_to_free(c, llnode);
	} while (cnt > (c->high_watermark + c->low_watermark) / 2);

	/* and drain free_llist_extra */
	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
		enque_to_free(c, llnode);
	do_call_rcu(c);
}

static void bpf_mem_refill(struct irq_work *work)
{
	struct bpf_mem_cache *c = container_of(work, struct bpf_mem_cache, refill_work);
	int cnt;

	/* Racy access to free_cnt. It doesn't need to be 100% accurate */
	cnt = c->free_cnt;
	if (cnt < c->low_watermark)
		/* irq_work runs on this cpu and kmalloc will allocate
		 * from the current numa node which is what we want here.
		 */
		alloc_bulk(c, c->batch, NUMA_NO_NODE);
	else if (cnt > c->high_watermark)
		free_bulk(c);
}

static void notrace irq_work_raise(struct bpf_mem_cache *c)
{
	irq_work_queue(&c->refill_work);
}

/* For typical bpf map case that uses bpf_mem_cache_alloc and single bucket
 * the freelist cache will be elem_size * 64 (or less) on each cpu.
 *
 * For bpf programs that don't have statically known allocation sizes and
 * assuming (low_mark + high_mark) / 2 as an average number of elements per
 * bucket and all buckets are used the total amount of memory in freelists
 * on each cpu will be:
 * 64*16 + 64*32 + 64*64 + 64*96 + 64*128 + 64*196 + 64*256 + 32*512 + 16*1024 + 8*2048 + 4*4096
 * == ~ 116 Kbyte using below heuristic.
 * Initialized, but unused bpf allocator (not bpf map specific one) will
 * consume ~ 11 Kbyte per cpu.
 * Typical case will be between 11K and 116K closer to 11K.
 * bpf progs can and should share bpf_mem_cache when possible.
 */

static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
{
	init_irq_work(&c->refill_work, bpf_mem_refill);
	if (c->unit_size <= 256) {
		c->low_watermark = 32;
		c->high_watermark = 96;
	} else {
		/* When page_size == 4k, order-0 cache will have low_mark == 2
		 * and high_mark == 6 with batch alloc of 3 individual pages at
		 * a time.
		 * 8k allocs and above low == 1, high == 3, batch == 1.
		 */
		c->low_watermark = max(32 * 256 / c->unit_size, 1);
		c->high_watermark = max(96 * 256 / c->unit_size, 3);
	}
	c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1);

	/* To avoid consuming memory assume that 1st run of bpf
	 * prog won't be doing more than 4 map_update_elem from
	 * irq disabled region
	 */
	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu));
}

/* When size != 0 bpf_mem_cache for each cpu.
 * This is typical bpf hash map use case when all elements have equal size.
 *
 * When size == 0 allocate 11 bpf_mem_cache-s for each cpu, then rely on
 * kmalloc/kfree. Max allocation size is 4096 in this case.
 * This is bpf_dynptr and bpf_kptr use case.
 */
int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
{
	static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
	struct bpf_mem_caches *cc, __percpu *pcc;
	struct bpf_mem_cache *c, __percpu *pc;
	struct obj_cgroup *objcg = NULL;
	int cpu, i, unit_size, percpu_size = 0;

	if (size) {
		pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL);
		if (!pc)
			return -ENOMEM;

		if (percpu)
			/* room for llist_node and per-cpu pointer */
			percpu_size = LLIST_NODE_SZ + sizeof(void *);
		else
			size += LLIST_NODE_SZ; /* room for llist_node */
		unit_size = size;

#ifdef CONFIG_MEMCG_KMEM
		objcg = get_obj_cgroup_from_current();
#endif
		for_each_possible_cpu(cpu) {
			c = per_cpu_ptr(pc, cpu);
			c->unit_size = unit_size;
			c->objcg = objcg;
			c->percpu_size = percpu_size;
			prefill_mem_cache(c, cpu);
		}
		ma->cache = pc;
		return 0;
	}

	/* size == 0 && percpu is an invalid combination */
	if (WARN_ON_ONCE(percpu))
		return -EINVAL;

	pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
	if (!pcc)
		return -ENOMEM;
#ifdef CONFIG_MEMCG_KMEM
	objcg = get_obj_cgroup_from_current();
#endif
	for_each_possible_cpu(cpu) {
		cc = per_cpu_ptr(pcc, cpu);
		for (i = 0; i < NUM_CACHES; i++) {
			c = &cc->cache[i];
			c->unit_size = sizes[i];
			c->objcg = objcg;
			prefill_mem_cache(c, cpu);
		}
	}
	ma->caches = pcc;
	return 0;
}

static void drain_mem_cache(struct bpf_mem_cache *c)
{
	struct llist_node *llnode, *t;

	/* No progs are using this bpf_mem_cache, but htab_map_free() called
	 * bpf_mem_cache_free() for all remaining elements and they can be in
	 * free_by_rcu or in waiting_for_gp lists, so drain those lists now.
	 */
	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
		free_one(c, llnode);
	llist_for_each_safe(llnode, t, llist_del_all(&c->waiting_for_gp))
		free_one(c, llnode);
	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist))
		free_one(c, llnode);
	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
		free_one(c, llnode);
}

static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
{
	free_percpu(ma->cache);
	free_percpu(ma->caches);
	ma->cache = NULL;
	ma->caches = NULL;
}

static void free_mem_alloc(struct bpf_mem_alloc *ma)
{
	/* waiting_for_gp lists was drained, but __free_rcu might
	 * still execute. Wait for it now before we freeing percpu caches.
	 */
	rcu_barrier_tasks_trace();
	rcu_barrier();
	free_mem_alloc_no_barrier(ma);
}

static void free_mem_alloc_deferred(struct work_struct *work)
{
	struct bpf_mem_alloc *ma = container_of(work, struct bpf_mem_alloc, work);

	free_mem_alloc(ma);
	kfree(ma);
}

static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress)
{
	struct bpf_mem_alloc *copy;

	if (!rcu_in_progress) {
		/* Fast path. No callbacks are pending, hence no need to do
		 * rcu_barrier-s.
		 */
		free_mem_alloc_no_barrier(ma);
		return;
	}

	copy = kmalloc(sizeof(*ma), GFP_KERNEL);
	if (!copy) {
		/* Slow path with inline barrier-s */
		free_mem_alloc(ma);
		return;
	}

	/* Defer barriers into worker to let the rest of map memory to be freed */
	copy->cache = ma->cache;
	ma->cache = NULL;
	copy->caches = ma->caches;
	ma->caches = NULL;
	INIT_WORK(&copy->work, free_mem_alloc_deferred);
	queue_work(system_unbound_wq, &copy->work);
}

void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
{
	struct bpf_mem_caches *cc;
	struct bpf_mem_cache *c;
	int cpu, i, rcu_in_progress;

	if (ma->cache) {
		rcu_in_progress = 0;
		for_each_possible_cpu(cpu) {
			c = per_cpu_ptr(ma->cache, cpu);
			drain_mem_cache(c);
			rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
		}
		/* objcg is the same across cpus */
		if (c->objcg)
			obj_cgroup_put(c->objcg);
		destroy_mem_alloc(ma, rcu_in_progress);
	}
	if (ma->caches) {
		rcu_in_progress = 0;
		for_each_possible_cpu(cpu) {
			cc = per_cpu_ptr(ma->caches, cpu);
			for (i = 0; i < NUM_CACHES; i++) {
				c = &cc->cache[i];
				drain_mem_cache(c);
				rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
			}
		}
		if (c->objcg)
			obj_cgroup_put(c->objcg);
		destroy_mem_alloc(ma, rcu_in_progress);
	}
}

/* notrace is necessary here and in other functions to make sure
 * bpf programs cannot attach to them and cause llist corruptions.
 */
static void notrace *unit_alloc(struct bpf_mem_cache *c)
{
	struct llist_node *llnode = NULL;
	unsigned long flags;
	int cnt = 0;

	/* Disable irqs to prevent the following race for majority of prog types:
	 * prog_A
	 *   bpf_mem_alloc
	 *      preemption or irq -> prog_B
	 *        bpf_mem_alloc
	 *
	 * but prog_B could be a perf_event NMI prog.
	 * Use per-cpu 'active' counter to order free_list access between
	 * unit_alloc/unit_free/bpf_mem_refill.
	 */
	local_irq_save(flags);
	if (local_inc_return(&c->active) == 1) {
		llnode = __llist_del_first(&c->free_llist);
		if (llnode)
			cnt = --c->free_cnt;
	}
	local_dec(&c->active);
	local_irq_restore(flags);

	WARN_ON(cnt < 0);

	if (cnt < c->low_watermark)
		irq_work_raise(c);
	return llnode;
}

/* Though 'ptr' object could have been allocated on a different cpu
 * add it to the free_llist of the current cpu.
 * Let kfree() logic deal with it when it's later called from irq_work.
 */
static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
{
	struct llist_node *llnode = ptr - LLIST_NODE_SZ;
	unsigned long flags;
	int cnt = 0;

	BUILD_BUG_ON(LLIST_NODE_SZ > 8);

	local_irq_save(flags);
	if (local_inc_return(&c->active) == 1) {
		__llist_add(llnode, &c->free_llist);
		cnt = ++c->free_cnt;
	} else {
		/* unit_free() cannot fail. Therefore add an object to atomic
		 * llist. free_bulk() will drain it. Though free_llist_extra is
		 * a per-cpu list we have to use atomic llist_add here, since
		 * it also can be interrupted by bpf nmi prog that does another
		 * unit_free() into the same free_llist_extra.
		 */
		llist_add(llnode, &c->free_llist_extra);
	}
	local_dec(&c->active);
	local_irq_restore(flags);

	if (cnt > c->high_watermark)
		/* free few objects from current cpu into global kmalloc pool */
		irq_work_raise(c);
}

/* Called from BPF program or from sys_bpf syscall.
 * In both cases migration is disabled.
 */
void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size)
{
	int idx;
	void *ret;

	if (!size)
		return ZERO_SIZE_PTR;

	idx = bpf_mem_cache_idx(size + LLIST_NODE_SZ);
	if (idx < 0)
		return NULL;

	ret = unit_alloc(this_cpu_ptr(ma->caches)->cache + idx);
	return !ret ? NULL : ret + LLIST_NODE_SZ;
}

void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
{
	int idx;

	if (!ptr)
		return;

	idx = bpf_mem_cache_idx(ksize(ptr - LLIST_NODE_SZ));
	if (idx < 0)
		return;

	unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr);
}

void notrace *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma)
{
	void *ret;

	ret = unit_alloc(this_cpu_ptr(ma->cache));
	return !ret ? NULL : ret + LLIST_NODE_SZ;
}

void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr)
{
	if (!ptr)
		return;

	unit_free(this_cpu_ptr(ma->cache), ptr);
}