summaryrefslogtreecommitdiff
path: root/kernel/bpf/arena.c
blob: 86571e760dd613b6f7315e02b19069ece475645d (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
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/err.h>
#include <linux/btf_ids.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>

/*
 * bpf_arena is a sparsely populated shared memory region between bpf program and
 * user space process.
 *
 * For example on x86-64 the values could be:
 * user_vm_start 7f7d26200000     // picked by mmap()
 * kern_vm_start ffffc90001e69000 // picked by get_vm_area()
 * For user space all pointers within the arena are normal 8-byte addresses.
 * In this example 7f7d26200000 is the address of the first page (pgoff=0).
 * The bpf program will access it as: kern_vm_start + lower_32bit_of_user_ptr
 * (u32)7f7d26200000 -> 26200000
 * hence
 * ffffc90001e69000 + 26200000 == ffffc90028069000 is "pgoff=0" within 4Gb
 * kernel memory region.
 *
 * BPF JITs generate the following code to access arena:
 *   mov eax, eax  // eax has lower 32-bit of user pointer
 *   mov word ptr [rax + r12 + off], bx
 * where r12 == kern_vm_start and off is s16.
 * Hence allocate 4Gb + GUARD_SZ/2 on each side.
 *
 * Initially kernel vm_area and user vma are not populated.
 * User space can fault-in any address which will insert the page
 * into kernel and user vma.
 * bpf program can allocate a page via bpf_arena_alloc_pages() kfunc
 * which will insert it into kernel vm_area.
 * The later fault-in from user space will populate that page into user vma.
 */

/* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */
#define GUARD_SZ (1ull << sizeof(((struct bpf_insn *)0)->off) * 8)
#define KERN_VM_SZ ((1ull << 32) + GUARD_SZ)

struct bpf_arena {
	struct bpf_map map;
	u64 user_vm_start;
	u64 user_vm_end;
	struct vm_struct *kern_vm;
	struct maple_tree mt;
	struct list_head vma_list;
	struct mutex lock;
};

u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena)
{
	return arena ? (u64) (long) arena->kern_vm->addr + GUARD_SZ / 2 : 0;
}

u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena)
{
	return arena ? arena->user_vm_start : 0;
}

static long arena_map_peek_elem(struct bpf_map *map, void *value)
{
	return -EOPNOTSUPP;
}

static long arena_map_push_elem(struct bpf_map *map, void *value, u64 flags)
{
	return -EOPNOTSUPP;
}

static long arena_map_pop_elem(struct bpf_map *map, void *value)
{
	return -EOPNOTSUPP;
}

static long arena_map_delete_elem(struct bpf_map *map, void *value)
{
	return -EOPNOTSUPP;
}

static int arena_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
	return -EOPNOTSUPP;
}

static long compute_pgoff(struct bpf_arena *arena, long uaddr)
{
	return (u32)(uaddr - (u32)arena->user_vm_start) >> PAGE_SHIFT;
}

static struct bpf_map *arena_map_alloc(union bpf_attr *attr)
{
	struct vm_struct *kern_vm;
	int numa_node = bpf_map_attr_numa_node(attr);
	struct bpf_arena *arena;
	u64 vm_range;
	int err = -ENOMEM;

	if (attr->key_size || attr->value_size || attr->max_entries == 0 ||
	    /* BPF_F_MMAPABLE must be set */
	    !(attr->map_flags & BPF_F_MMAPABLE) ||
	    /* No unsupported flags present */
	    (attr->map_flags & ~(BPF_F_SEGV_ON_FAULT | BPF_F_MMAPABLE | BPF_F_NO_USER_CONV)))
		return ERR_PTR(-EINVAL);

	if (attr->map_extra & ~PAGE_MASK)
		/* If non-zero the map_extra is an expected user VMA start address */
		return ERR_PTR(-EINVAL);

	vm_range = (u64)attr->max_entries * PAGE_SIZE;
	if (vm_range > (1ull << 32))
		return ERR_PTR(-E2BIG);

	if ((attr->map_extra >> 32) != ((attr->map_extra + vm_range - 1) >> 32))
		/* user vma must not cross 32-bit boundary */
		return ERR_PTR(-ERANGE);

	kern_vm = get_vm_area(KERN_VM_SZ, VM_SPARSE | VM_USERMAP);
	if (!kern_vm)
		return ERR_PTR(-ENOMEM);

	arena = bpf_map_area_alloc(sizeof(*arena), numa_node);
	if (!arena)
		goto err;

	arena->kern_vm = kern_vm;
	arena->user_vm_start = attr->map_extra;
	if (arena->user_vm_start)
		arena->user_vm_end = arena->user_vm_start + vm_range;

	INIT_LIST_HEAD(&arena->vma_list);
	bpf_map_init_from_attr(&arena->map, attr);
	mt_init_flags(&arena->mt, MT_FLAGS_ALLOC_RANGE);
	mutex_init(&arena->lock);

	return &arena->map;
err:
	free_vm_area(kern_vm);
	return ERR_PTR(err);
}

static int existing_page_cb(pte_t *ptep, unsigned long addr, void *data)
{
	struct page *page;
	pte_t pte;

	pte = ptep_get(ptep);
	if (!pte_present(pte)) /* sanity check */
		return 0;
	page = pte_page(pte);
	/*
	 * We do not update pte here:
	 * 1. Nobody should be accessing bpf_arena's range outside of a kernel bug
	 * 2. TLB flushing is batched or deferred. Even if we clear pte,
	 * the TLB entries can stick around and continue to permit access to
	 * the freed page. So it all relies on 1.
	 */
	__free_page(page);
	return 0;
}

static void arena_map_free(struct bpf_map *map)
{
	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);

	/*
	 * Check that user vma-s are not around when bpf map is freed.
	 * mmap() holds vm_file which holds bpf_map refcnt.
	 * munmap() must have happened on vma followed by arena_vm_close()
	 * which would clear arena->vma_list.
	 */
	if (WARN_ON_ONCE(!list_empty(&arena->vma_list)))
		return;

	/*
	 * free_vm_area() calls remove_vm_area() that calls free_unmap_vmap_area().
	 * It unmaps everything from vmalloc area and clears pgtables.
	 * Call apply_to_existing_page_range() first to find populated ptes and
	 * free those pages.
	 */
	apply_to_existing_page_range(&init_mm, bpf_arena_get_kern_vm_start(arena),
				     KERN_VM_SZ - GUARD_SZ, existing_page_cb, NULL);
	free_vm_area(arena->kern_vm);
	mtree_destroy(&arena->mt);
	bpf_map_area_free(arena);
}

static void *arena_map_lookup_elem(struct bpf_map *map, void *key)
{
	return ERR_PTR(-EINVAL);
}

static long arena_map_update_elem(struct bpf_map *map, void *key,
				  void *value, u64 flags)
{
	return -EOPNOTSUPP;
}

static int arena_map_check_btf(const struct bpf_map *map, const struct btf *btf,
			       const struct btf_type *key_type, const struct btf_type *value_type)
{
	return 0;
}

static u64 arena_map_mem_usage(const struct bpf_map *map)
{
	return 0;
}

struct vma_list {
	struct vm_area_struct *vma;
	struct list_head head;
};

static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma)
{
	struct vma_list *vml;

	vml = kmalloc(sizeof(*vml), GFP_KERNEL);
	if (!vml)
		return -ENOMEM;
	vma->vm_private_data = vml;
	vml->vma = vma;
	list_add(&vml->head, &arena->vma_list);
	return 0;
}

static void arena_vm_close(struct vm_area_struct *vma)
{
	struct bpf_map *map = vma->vm_file->private_data;
	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);
	struct vma_list *vml;

	guard(mutex)(&arena->lock);
	vml = vma->vm_private_data;
	list_del(&vml->head);
	vma->vm_private_data = NULL;
	kfree(vml);
}

#define MT_ENTRY ((void *)&arena_map_ops) /* unused. has to be valid pointer */

static vm_fault_t arena_vm_fault(struct vm_fault *vmf)
{
	struct bpf_map *map = vmf->vma->vm_file->private_data;
	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);
	struct page *page;
	long kbase, kaddr;
	int ret;

	kbase = bpf_arena_get_kern_vm_start(arena);
	kaddr = kbase + (u32)(vmf->address & PAGE_MASK);

	guard(mutex)(&arena->lock);
	page = vmalloc_to_page((void *)kaddr);
	if (page)
		/* already have a page vmap-ed */
		goto out;

	if (arena->map.map_flags & BPF_F_SEGV_ON_FAULT)
		/* User space requested to segfault when page is not allocated by bpf prog */
		return VM_FAULT_SIGSEGV;

	ret = mtree_insert(&arena->mt, vmf->pgoff, MT_ENTRY, GFP_KERNEL);
	if (ret)
		return VM_FAULT_SIGSEGV;

	/* Account into memcg of the process that created bpf_arena */
	ret = bpf_map_alloc_pages(map, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, 1, &page);
	if (ret) {
		mtree_erase(&arena->mt, vmf->pgoff);
		return VM_FAULT_SIGSEGV;
	}

	ret = vm_area_map_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE, &page);
	if (ret) {
		mtree_erase(&arena->mt, vmf->pgoff);
		__free_page(page);
		return VM_FAULT_SIGSEGV;
	}
out:
	page_ref_add(page, 1);
	vmf->page = page;
	return 0;
}

static const struct vm_operations_struct arena_vm_ops = {
	.close		= arena_vm_close,
	.fault          = arena_vm_fault,
};

static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long addr,
					     unsigned long len, unsigned long pgoff,
					     unsigned long flags)
{
	struct bpf_map *map = filp->private_data;
	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);
	long ret;

	if (pgoff)
		return -EINVAL;
	if (len > (1ull << 32))
		return -E2BIG;

	/* if user_vm_start was specified at arena creation time */
	if (arena->user_vm_start) {
		if (len > arena->user_vm_end - arena->user_vm_start)
			return -E2BIG;
		if (len != arena->user_vm_end - arena->user_vm_start)
			return -EINVAL;
		if (addr != arena->user_vm_start)
			return -EINVAL;
	}

	ret = current->mm->get_unmapped_area(filp, addr, len * 2, 0, flags);
	if (IS_ERR_VALUE(ret))
		return ret;
	if ((ret >> 32) == ((ret + len - 1) >> 32))
		return ret;
	if (WARN_ON_ONCE(arena->user_vm_start))
		/* checks at map creation time should prevent this */
		return -EFAULT;
	return round_up(ret, 1ull << 32);
}

static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
{
	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);

	guard(mutex)(&arena->lock);
	if (arena->user_vm_start && arena->user_vm_start != vma->vm_start)
		/*
		 * If map_extra was not specified at arena creation time then
		 * 1st user process can do mmap(NULL, ...) to pick user_vm_start
		 * 2nd user process must pass the same addr to mmap(addr, MAP_FIXED..);
		 *   or
		 * specify addr in map_extra and
		 * use the same addr later with mmap(addr, MAP_FIXED..);
		 */
		return -EBUSY;

	if (arena->user_vm_end && arena->user_vm_end != vma->vm_end)
		/* all user processes must have the same size of mmap-ed region */
		return -EBUSY;

	/* Earlier checks should prevent this */
	if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > (1ull << 32) || vma->vm_pgoff))
		return -EFAULT;

	if (remember_vma(arena, vma))
		return -ENOMEM;

	arena->user_vm_start = vma->vm_start;
	arena->user_vm_end = vma->vm_end;
	/*
	 * bpf_map_mmap() checks that it's being mmaped as VM_SHARED and
	 * clears VM_MAYEXEC. Set VM_DONTEXPAND as well to avoid
	 * potential change of user_vm_start.
	 */
	vm_flags_set(vma, VM_DONTEXPAND);
	vma->vm_ops = &arena_vm_ops;
	return 0;
}

static int arena_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 off)
{
	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);

	if ((u64)off > arena->user_vm_end - arena->user_vm_start)
		return -ERANGE;
	*imm = (unsigned long)arena->user_vm_start;
	return 0;
}

BTF_ID_LIST_SINGLE(bpf_arena_map_btf_ids, struct, bpf_arena)
const struct bpf_map_ops arena_map_ops = {
	.map_meta_equal = bpf_map_meta_equal,
	.map_alloc = arena_map_alloc,
	.map_free = arena_map_free,
	.map_direct_value_addr = arena_map_direct_value_addr,
	.map_mmap = arena_map_mmap,
	.map_get_unmapped_area = arena_get_unmapped_area,
	.map_get_next_key = arena_map_get_next_key,
	.map_push_elem = arena_map_push_elem,
	.map_peek_elem = arena_map_peek_elem,
	.map_pop_elem = arena_map_pop_elem,
	.map_lookup_elem = arena_map_lookup_elem,
	.map_update_elem = arena_map_update_elem,
	.map_delete_elem = arena_map_delete_elem,
	.map_check_btf = arena_map_check_btf,
	.map_mem_usage = arena_map_mem_usage,
	.map_btf_id = &bpf_arena_map_btf_ids[0],
};

static u64 clear_lo32(u64 val)
{
	return val & ~(u64)~0U;
}

/*
 * Allocate pages and vmap them into kernel vmalloc area.
 * Later the pages will be mmaped into user space vma.
 */
static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt, int node_id)
{
	/* user_vm_end/start are fixed before bpf prog runs */
	long page_cnt_max = (arena->user_vm_end - arena->user_vm_start) >> PAGE_SHIFT;
	u64 kern_vm_start = bpf_arena_get_kern_vm_start(arena);
	struct page **pages;
	long pgoff = 0;
	u32 uaddr32;
	int ret, i;

	if (page_cnt > page_cnt_max)
		return 0;

	if (uaddr) {
		if (uaddr & ~PAGE_MASK)
			return 0;
		pgoff = compute_pgoff(arena, uaddr);
		if (pgoff + page_cnt > page_cnt_max)
			/* requested address will be outside of user VMA */
			return 0;
	}

	/* zeroing is needed, since alloc_pages_bulk_array() only fills in non-zero entries */
	pages = kvcalloc(page_cnt, sizeof(struct page *), GFP_KERNEL);
	if (!pages)
		return 0;

	guard(mutex)(&arena->lock);

	if (uaddr)
		ret = mtree_insert_range(&arena->mt, pgoff, pgoff + page_cnt - 1,
					 MT_ENTRY, GFP_KERNEL);
	else
		ret = mtree_alloc_range(&arena->mt, &pgoff, MT_ENTRY,
					page_cnt, 0, page_cnt_max - 1, GFP_KERNEL);
	if (ret)
		goto out_free_pages;

	ret = bpf_map_alloc_pages(&arena->map, GFP_KERNEL | __GFP_ZERO,
				  node_id, page_cnt, pages);
	if (ret)
		goto out;

	uaddr32 = (u32)(arena->user_vm_start + pgoff * PAGE_SIZE);
	/* Earlier checks make sure that uaddr32 + page_cnt * PAGE_SIZE will not overflow 32-bit */
	ret = vm_area_map_pages(arena->kern_vm, kern_vm_start + uaddr32,
				kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE, pages);
	if (ret) {
		for (i = 0; i < page_cnt; i++)
			__free_page(pages[i]);
		goto out;
	}
	kvfree(pages);
	return clear_lo32(arena->user_vm_start) + uaddr32;
out:
	mtree_erase(&arena->mt, pgoff);
out_free_pages:
	kvfree(pages);
	return 0;
}

/*
 * If page is present in vmalloc area, unmap it from vmalloc area,
 * unmap it from all user space vma-s,
 * and free it.
 */
static void zap_pages(struct bpf_arena *arena, long uaddr, long page_cnt)
{
	struct vma_list *vml;

	list_for_each_entry(vml, &arena->vma_list, head)
		zap_page_range_single(vml->vma, uaddr,
				      PAGE_SIZE * page_cnt, NULL);
}

static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt)
{
	u64 full_uaddr, uaddr_end;
	long kaddr, pgoff, i;
	struct page *page;

	/* only aligned lower 32-bit are relevant */
	uaddr = (u32)uaddr;
	uaddr &= PAGE_MASK;
	full_uaddr = clear_lo32(arena->user_vm_start) + uaddr;
	uaddr_end = min(arena->user_vm_end, full_uaddr + (page_cnt << PAGE_SHIFT));
	if (full_uaddr >= uaddr_end)
		return;

	page_cnt = (uaddr_end - full_uaddr) >> PAGE_SHIFT;

	guard(mutex)(&arena->lock);

	pgoff = compute_pgoff(arena, uaddr);
	/* clear range */
	mtree_store_range(&arena->mt, pgoff, pgoff + page_cnt - 1, NULL, GFP_KERNEL);

	if (page_cnt > 1)
		/* bulk zap if multiple pages being freed */
		zap_pages(arena, full_uaddr, page_cnt);

	kaddr = bpf_arena_get_kern_vm_start(arena) + uaddr;
	for (i = 0; i < page_cnt; i++, kaddr += PAGE_SIZE, full_uaddr += PAGE_SIZE) {
		page = vmalloc_to_page((void *)kaddr);
		if (!page)
			continue;
		if (page_cnt == 1 && page_mapped(page)) /* mapped by some user process */
			zap_pages(arena, full_uaddr, 1);
		vm_area_unmap_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE);
		__free_page(page);
	}
}

__bpf_kfunc_start_defs();

__bpf_kfunc void *bpf_arena_alloc_pages(void *p__map, void *addr__ign, u32 page_cnt,
					int node_id, u64 flags)
{
	struct bpf_map *map = p__map;
	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);

	if (map->map_type != BPF_MAP_TYPE_ARENA || flags || !page_cnt)
		return NULL;

	return (void *)arena_alloc_pages(arena, (long)addr__ign, page_cnt, node_id);
}

__bpf_kfunc void bpf_arena_free_pages(void *p__map, void *ptr__ign, u32 page_cnt)
{
	struct bpf_map *map = p__map;
	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);

	if (map->map_type != BPF_MAP_TYPE_ARENA || !page_cnt || !ptr__ign)
		return;
	arena_free_pages(arena, (long)ptr__ign, page_cnt);
}
__bpf_kfunc_end_defs();

BTF_KFUNCS_START(arena_kfuncs)
BTF_ID_FLAGS(func, bpf_arena_alloc_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE)
BTF_ID_FLAGS(func, bpf_arena_free_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE)
BTF_KFUNCS_END(arena_kfuncs)

static const struct btf_kfunc_id_set common_kfunc_set = {
	.owner = THIS_MODULE,
	.set   = &arena_kfuncs,
};

static int __init kfunc_init(void)
{
	return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &common_kfunc_set);
}
late_initcall(kfunc_init);