summaryrefslogtreecommitdiffstats
path: root/include/linux/hmm.h
blob: b8a08b2a10ca058a192086ab3507d66ccbe984f1 (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
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
 * Copyright 2013 Red Hat Inc.
 *
 * Authors: Jérôme Glisse <jglisse@redhat.com>
 */
/*
 * Heterogeneous Memory Management (HMM)
 *
 * See Documentation/vm/hmm.rst for reasons and overview of what HMM is and it
 * is for. Here we focus on the HMM API description, with some explanation of
 * the underlying implementation.
 *
 * Short description: HMM provides a set of helpers to share a virtual address
 * space between CPU and a device, so that the device can access any valid
 * address of the process (while still obeying memory protection). HMM also
 * provides helpers to migrate process memory to device memory, and back. Each
 * set of functionality (address space mirroring, and migration to and from
 * device memory) can be used independently of the other.
 *
 *
 * HMM address space mirroring API:
 *
 * Use HMM address space mirroring if you want to mirror a range of the CPU
 * page tables of a process into a device page table. Here, "mirror" means "keep
 * synchronized". Prerequisites: the device must provide the ability to write-
 * protect its page tables (at PAGE_SIZE granularity), and must be able to
 * recover from the resulting potential page faults.
 *
 * HMM guarantees that at any point in time, a given virtual address points to
 * either the same memory in both CPU and device page tables (that is: CPU and
 * device page tables each point to the same pages), or that one page table (CPU
 * or device) points to no entry, while the other still points to the old page
 * for the address. The latter case happens when the CPU page table update
 * happens first, and then the update is mirrored over to the device page table.
 * This does not cause any issue, because the CPU page table cannot start
 * pointing to a new page until the device page table is invalidated.
 *
 * HMM uses mmu_notifiers to monitor the CPU page tables, and forwards any
 * updates to each device driver that has registered a mirror. It also provides
 * some API calls to help with taking a snapshot of the CPU page table, and to
 * synchronize with any updates that might happen concurrently.
 *
 *
 * HMM migration to and from device memory:
 *
 * HMM provides a set of helpers to hotplug device memory as ZONE_DEVICE, with
 * a new MEMORY_DEVICE_PRIVATE type. This provides a struct page for each page
 * of the device memory, and allows the device driver to manage its memory
 * using those struct pages. Having struct pages for device memory makes
 * migration easier. Because that memory is not addressable by the CPU it must
 * never be pinned to the device; in other words, any CPU page fault can always
 * cause the device memory to be migrated (copied/moved) back to regular memory.
 *
 * A new migrate helper (migrate_vma()) has been added (see mm/migrate.c) that
 * allows use of a device DMA engine to perform the copy operation between
 * regular system memory and device memory.
 */
#ifndef LINUX_HMM_H
#define LINUX_HMM_H

#include <linux/kconfig.h>
#include <asm/pgtable.h>

#ifdef CONFIG_HMM_MIRROR

#include <linux/device.h>
#include <linux/migrate.h>
#include <linux/memremap.h>
#include <linux/completion.h>
#include <linux/mmu_notifier.h>


/*
 * struct hmm - HMM per mm struct
 *
 * @mm: mm struct this HMM struct is bound to
 * @lock: lock protecting ranges list
 * @ranges: list of range being snapshotted
 * @mirrors: list of mirrors for this mm
 * @mmu_notifier: mmu notifier to track updates to CPU page table
 * @mirrors_sem: read/write semaphore protecting the mirrors list
 * @wq: wait queue for user waiting on a range invalidation
 * @notifiers: count of active mmu notifiers
 */
struct hmm {
	struct mm_struct	*mm;
	struct kref		kref;
	spinlock_t		ranges_lock;
	struct list_head	ranges;
	struct list_head	mirrors;
	struct mmu_notifier	mmu_notifier;
	struct rw_semaphore	mirrors_sem;
	wait_queue_head_t	wq;
	struct rcu_head		rcu;
	long			notifiers;
};

/*
 * hmm_pfn_flag_e - HMM flag enums
 *
 * Flags:
 * HMM_PFN_VALID: pfn is valid. It has, at least, read permission.
 * HMM_PFN_WRITE: CPU page table has write permission set
 * HMM_PFN_DEVICE_PRIVATE: private device memory (ZONE_DEVICE)
 *
 * The driver provides a flags array for mapping page protections to device
 * PTE bits. If the driver valid bit for an entry is bit 3,
 * i.e., (entry & (1 << 3)), then the driver must provide
 * an array in hmm_range.flags with hmm_range.flags[HMM_PFN_VALID] == 1 << 3.
 * Same logic apply to all flags. This is the same idea as vm_page_prot in vma
 * except that this is per device driver rather than per architecture.
 */
enum hmm_pfn_flag_e {
	HMM_PFN_VALID = 0,
	HMM_PFN_WRITE,
	HMM_PFN_DEVICE_PRIVATE,
	HMM_PFN_FLAG_MAX
};

/*
 * hmm_pfn_value_e - HMM pfn special value
 *
 * Flags:
 * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory
 * HMM_PFN_NONE: corresponding CPU page table entry is pte_none()
 * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the
 *      result of vmf_insert_pfn() or vm_insert_page(). Therefore, it should not
 *      be mirrored by a device, because the entry will never have HMM_PFN_VALID
 *      set and the pfn value is undefined.
 *
 * Driver provides values for none entry, error entry, and special entry.
 * Driver can alias (i.e., use same value) error and special, but
 * it should not alias none with error or special.
 *
 * HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be:
 * hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous,
 * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table entry,
 * hmm_range.values[HMM_PFN_SPECIAL] if CPU page table entry is a special one
 */
enum hmm_pfn_value_e {
	HMM_PFN_ERROR,
	HMM_PFN_NONE,
	HMM_PFN_SPECIAL,
	HMM_PFN_VALUE_MAX
};

/*
 * struct hmm_range - track invalidation lock on virtual address range
 *
 * @hmm: the core HMM structure this range is active against
 * @vma: the vm area struct for the range
 * @list: all range lock are on a list
 * @start: range virtual start address (inclusive)
 * @end: range virtual end address (exclusive)
 * @pfns: array of pfns (big enough for the range)
 * @flags: pfn flags to match device driver page table
 * @values: pfn value for some special case (none, special, error, ...)
 * @default_flags: default flags for the range (write, read, ... see hmm doc)
 * @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter
 * @page_shift: device virtual address shift value (should be >= PAGE_SHIFT)
 * @pfn_shifts: pfn shift value (should be <= PAGE_SHIFT)
 * @valid: pfns array did not change since it has been fill by an HMM function
 */
struct hmm_range {
	struct hmm		*hmm;
	struct vm_area_struct	*vma;
	struct list_head	list;
	unsigned long		start;
	unsigned long		end;
	uint64_t		*pfns;
	const uint64_t		*flags;
	const uint64_t		*values;
	uint64_t		default_flags;
	uint64_t		pfn_flags_mask;
	uint8_t			page_shift;
	uint8_t			pfn_shift;
	bool			valid;
};

/*
 * hmm_range_page_shift() - return the page shift for the range
 * @range: range being queried
 * Return: page shift (page size = 1 << page shift) for the range
 */
static inline unsigned hmm_range_page_shift(const struct hmm_range *range)
{
	return range->page_shift;
}

/*
 * hmm_range_page_size() - return the page size for the range
 * @range: range being queried
 * Return: page size for the range in bytes
 */
static inline unsigned long hmm_range_page_size(const struct hmm_range *range)
{
	return 1UL << hmm_range_page_shift(range);
}

/*
 * hmm_range_wait_until_valid() - wait for range to be valid
 * @range: range affected by invalidation to wait on
 * @timeout: time out for wait in ms (ie abort wait after that period of time)
 * Return: true if the range is valid, false otherwise.
 */
static inline bool hmm_range_wait_until_valid(struct hmm_range *range,
					      unsigned long timeout)
{
	return wait_event_timeout(range->hmm->wq, range->valid,
				  msecs_to_jiffies(timeout)) != 0;
}

/*
 * hmm_range_valid() - test if a range is valid or not
 * @range: range
 * Return: true if the range is valid, false otherwise.
 */
static inline bool hmm_range_valid(struct hmm_range *range)
{
	return range->valid;
}

/*
 * hmm_device_entry_to_page() - return struct page pointed to by a device entry
 * @range: range use to decode device entry value
 * @entry: device entry value to get corresponding struct page from
 * Return: struct page pointer if entry is a valid, NULL otherwise
 *
 * If the device entry is valid (ie valid flag set) then return the struct page
 * matching the entry value. Otherwise return NULL.
 */
static inline struct page *hmm_device_entry_to_page(const struct hmm_range *range,
						    uint64_t entry)
{
	if (entry == range->values[HMM_PFN_NONE])
		return NULL;
	if (entry == range->values[HMM_PFN_ERROR])
		return NULL;
	if (entry == range->values[HMM_PFN_SPECIAL])
		return NULL;
	if (!(entry & range->flags[HMM_PFN_VALID]))
		return NULL;
	return pfn_to_page(entry >> range->pfn_shift);
}

/*
 * hmm_device_entry_to_pfn() - return pfn value store in a device entry
 * @range: range use to decode device entry value
 * @entry: device entry to extract pfn from
 * Return: pfn value if device entry is valid, -1UL otherwise
 */
static inline unsigned long
hmm_device_entry_to_pfn(const struct hmm_range *range, uint64_t pfn)
{
	if (pfn == range->values[HMM_PFN_NONE])
		return -1UL;
	if (pfn == range->values[HMM_PFN_ERROR])
		return -1UL;
	if (pfn == range->values[HMM_PFN_SPECIAL])
		return -1UL;
	if (!(pfn & range->flags[HMM_PFN_VALID]))
		return -1UL;
	return (pfn >> range->pfn_shift);
}

/*
 * hmm_device_entry_from_page() - create a valid device entry for a page
 * @range: range use to encode HMM pfn value
 * @page: page for which to create the device entry
 * Return: valid device entry for the page
 */
static inline uint64_t hmm_device_entry_from_page(const struct hmm_range *range,
						  struct page *page)
{
	return (page_to_pfn(page) << range->pfn_shift) |
		range->flags[HMM_PFN_VALID];
}

/*
 * hmm_device_entry_from_pfn() - create a valid device entry value from pfn
 * @range: range use to encode HMM pfn value
 * @pfn: pfn value for which to create the device entry
 * Return: valid device entry for the pfn
 */
static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range,
						 unsigned long pfn)
{
	return (pfn << range->pfn_shift) |
		range->flags[HMM_PFN_VALID];
}

/*
 * Old API:
 * hmm_pfn_to_page()
 * hmm_pfn_to_pfn()
 * hmm_pfn_from_page()
 * hmm_pfn_from_pfn()
 *
 * This are the OLD API please use new API, it is here to avoid cross-tree
 * merge painfullness ie we convert things to new API in stages.
 */
static inline struct page *hmm_pfn_to_page(const struct hmm_range *range,
					   uint64_t pfn)
{
	return hmm_device_entry_to_page(range, pfn);
}

static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range,
					   uint64_t pfn)
{
	return hmm_device_entry_to_pfn(range, pfn);
}

static inline uint64_t hmm_pfn_from_page(const struct hmm_range *range,
					 struct page *page)
{
	return hmm_device_entry_from_page(range, page);
}

static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range,
					unsigned long pfn)
{
	return hmm_device_entry_from_pfn(range, pfn);
}

/*
 * Mirroring: how to synchronize device page table with CPU page table.
 *
 * A device driver that is participating in HMM mirroring must always
 * synchronize with CPU page table updates. For this, device drivers can either
 * directly use mmu_notifier APIs or they can use the hmm_mirror API. Device
 * drivers can decide to register one mirror per device per process, or just
 * one mirror per process for a group of devices. The pattern is:
 *
 *      int device_bind_address_space(..., struct mm_struct *mm, ...)
 *      {
 *          struct device_address_space *das;
 *
 *          // Device driver specific initialization, and allocation of das
 *          // which contains an hmm_mirror struct as one of its fields.
 *          ...
 *
 *          ret = hmm_mirror_register(&das->mirror, mm, &device_mirror_ops);
 *          if (ret) {
 *              // Cleanup on error
 *              return ret;
 *          }
 *
 *          // Other device driver specific initialization
 *          ...
 *      }
 *
 * Once an hmm_mirror is registered for an address space, the device driver
 * will get callbacks through sync_cpu_device_pagetables() operation (see
 * hmm_mirror_ops struct).
 *
 * Device driver must not free the struct containing the hmm_mirror struct
 * before calling hmm_mirror_unregister(). The expected usage is to do that when
 * the device driver is unbinding from an address space.
 *
 *
 *      void device_unbind_address_space(struct device_address_space *das)
 *      {
 *          // Device driver specific cleanup
 *          ...
 *
 *          hmm_mirror_unregister(&das->mirror);
 *
 *          // Other device driver specific cleanup, and now das can be freed
 *          ...
 *      }
 */

struct hmm_mirror;

/*
 * enum hmm_update_event - type of update
 * @HMM_UPDATE_INVALIDATE: invalidate range (no indication as to why)
 */
enum hmm_update_event {
	HMM_UPDATE_INVALIDATE,
};

/*
 * struct hmm_update - HMM update information for callback
 *
 * @start: virtual start address of the range to update
 * @end: virtual end address of the range to update
 * @event: event triggering the update (what is happening)
 * @blockable: can the callback block/sleep ?
 */
struct hmm_update {
	unsigned long start;
	unsigned long end;
	enum hmm_update_event event;
	bool blockable;
};

/*
 * struct hmm_mirror_ops - HMM mirror device operations callback
 *
 * @update: callback to update range on a device
 */
struct hmm_mirror_ops {
	/* release() - release hmm_mirror
	 *
	 * @mirror: pointer to struct hmm_mirror
	 *
	 * This is called when the mm_struct is being released.  The callback
	 * must ensure that all access to any pages obtained from this mirror
	 * is halted before the callback returns. All future access should
	 * fault.
	 */
	void (*release)(struct hmm_mirror *mirror);

	/* sync_cpu_device_pagetables() - synchronize page tables
	 *
	 * @mirror: pointer to struct hmm_mirror
	 * @update: update information (see struct hmm_update)
	 * Return: -EAGAIN if update.blockable false and callback need to
	 *          block, 0 otherwise.
	 *
	 * This callback ultimately originates from mmu_notifiers when the CPU
	 * page table is updated. The device driver must update its page table
	 * in response to this callback. The update argument tells what action
	 * to perform.
	 *
	 * The device driver must not return from this callback until the device
	 * page tables are completely updated (TLBs flushed, etc); this is a
	 * synchronous call.
	 */
	int (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror,
					  const struct hmm_update *update);
};

/*
 * struct hmm_mirror - mirror struct for a device driver
 *
 * @hmm: pointer to struct hmm (which is unique per mm_struct)
 * @ops: device driver callback for HMM mirror operations
 * @list: for list of mirrors of a given mm
 *
 * Each address space (mm_struct) being mirrored by a device must register one
 * instance of an hmm_mirror struct with HMM. HMM will track the list of all
 * mirrors for each mm_struct.
 */
struct hmm_mirror {
	struct hmm			*hmm;
	const struct hmm_mirror_ops	*ops;
	struct list_head		list;
};

int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm);
void hmm_mirror_unregister(struct hmm_mirror *mirror);

/*
 * Please see Documentation/vm/hmm.rst for how to use the range API.
 */
int hmm_range_register(struct hmm_range *range,
		       struct hmm_mirror *mirror,
		       unsigned long start,
		       unsigned long end,
		       unsigned page_shift);
void hmm_range_unregister(struct hmm_range *range);
long hmm_range_snapshot(struct hmm_range *range);
long hmm_range_fault(struct hmm_range *range, bool block);
long hmm_range_dma_map(struct hmm_range *range,
		       struct device *device,
		       dma_addr_t *daddrs,
		       bool block);
long hmm_range_dma_unmap(struct hmm_range *range,
			 struct vm_area_struct *vma,
			 struct device *device,
			 dma_addr_t *daddrs,
			 bool dirty);

/*
 * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range
 *
 * When waiting for mmu notifiers we need some kind of time out otherwise we
 * could potentialy wait for ever, 1000ms ie 1s sounds like a long time to
 * wait already.
 */
#define HMM_RANGE_DEFAULT_TIMEOUT 1000

/* This is a temporary helper to avoid merge conflict between trees. */
static inline bool hmm_vma_range_done(struct hmm_range *range)
{
	bool ret = hmm_range_valid(range);

	hmm_range_unregister(range);
	return ret;
}

/* This is a temporary helper to avoid merge conflict between trees. */
static inline int hmm_vma_fault(struct hmm_mirror *mirror,
				struct hmm_range *range, bool block)
{
	long ret;

	/*
	 * With the old API the driver must set each individual entries with
	 * the requested flags (valid, write, ...). So here we set the mask to
	 * keep intact the entries provided by the driver and zero out the
	 * default_flags.
	 */
	range->default_flags = 0;
	range->pfn_flags_mask = -1UL;

	ret = hmm_range_register(range, mirror,
				 range->start, range->end,
				 PAGE_SHIFT);
	if (ret)
		return (int)ret;

	if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) {
		/*
		 * The mmap_sem was taken by driver we release it here and
		 * returns -EAGAIN which correspond to mmap_sem have been
		 * drop in the old API.
		 */
		up_read(&range->vma->vm_mm->mmap_sem);
		return -EAGAIN;
	}

	ret = hmm_range_fault(range, block);
	if (ret <= 0) {
		if (ret == -EBUSY || !ret) {
			/* Same as above, drop mmap_sem to match old API. */
			up_read(&range->vma->vm_mm->mmap_sem);
			ret = -EBUSY;
		} else if (ret == -EAGAIN)
			ret = -EBUSY;
		hmm_range_unregister(range);
		return ret;
	}
	return 0;
}

/* Below are for HMM internal use only! Not to be used by device driver! */
static inline void hmm_mm_init(struct mm_struct *mm)
{
	mm->hmm = NULL;
}
#else /* IS_ENABLED(CONFIG_HMM_MIRROR) */
static inline void hmm_mm_init(struct mm_struct *mm) {}
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */

#endif /* LINUX_HMM_H */