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
|
/* include/asm-generic/tlb.h
*
* Generic TLB shootdown code
*
* Copyright 2001 Red Hat, Inc.
* Based on code from mm/memory.c Copyright Linus Torvalds and others.
*
* Copyright 2011 Red Hat, Inc., Peter Zijlstra
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _ASM_GENERIC__TLB_H
#define _ASM_GENERIC__TLB_H
#include <linux/mmu_notifier.h>
#include <linux/swap.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#ifdef CONFIG_MMU
/*
* Generic MMU-gather implementation.
*
* The mmu_gather data structure is used by the mm code to implement the
* correct and efficient ordering of freeing pages and TLB invalidations.
*
* This correct ordering is:
*
* 1) unhook page
* 2) TLB invalidate page
* 3) free page
*
* That is, we must never free a page before we have ensured there are no live
* translations left to it. Otherwise it might be possible to observe (or
* worse, change) the page content after it has been reused.
*
* The mmu_gather API consists of:
*
* - tlb_gather_mmu() / tlb_finish_mmu(); start and finish a mmu_gather
*
* Finish in particular will issue a (final) TLB invalidate and free
* all (remaining) queued pages.
*
* - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA
*
* Defaults to flushing at tlb_end_vma() to reset the range; helps when
* there's large holes between the VMAs.
*
* - tlb_remove_page() / __tlb_remove_page()
* - tlb_remove_page_size() / __tlb_remove_page_size()
*
* __tlb_remove_page_size() is the basic primitive that queues a page for
* freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a
* boolean indicating if the queue is (now) full and a call to
* tlb_flush_mmu() is required.
*
* tlb_remove_page() and tlb_remove_page_size() imply the call to
* tlb_flush_mmu() when required and has no return value.
*
* - tlb_change_page_size()
*
* call before __tlb_remove_page*() to set the current page-size; implies a
* possible tlb_flush_mmu() call.
*
* - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() / tlb_flush_mmu_free()
*
* tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets
* related state, like the range)
*
* tlb_flush_mmu_free() - frees the queued pages; make absolutely
* sure no additional tlb_remove_page()
* calls happen between _tlbonly() and this.
*
* tlb_flush_mmu() - the above two calls.
*
* - mmu_gather::fullmm
*
* A flag set by tlb_gather_mmu() to indicate we're going to free
* the entire mm; this allows a number of optimizations.
*
* - We can ignore tlb_{start,end}_vma(); because we don't
* care about ranges. Everything will be shot down.
*
* - (RISC) architectures that use ASIDs can cycle to a new ASID
* and delay the invalidation until ASID space runs out.
*
* - mmu_gather::need_flush_all
*
* A flag that can be set by the arch code if it wants to force
* flush the entire TLB irrespective of the range. For instance
* x86-PAE needs this when changing top-level entries.
*
* And requires the architecture to provide and implement tlb_flush().
*
* tlb_flush() may, in addition to the above mentioned mmu_gather fields, make
* use of:
*
* - mmu_gather::start / mmu_gather::end
*
* which provides the range that needs to be flushed to cover the pages to
* be freed.
*
* - mmu_gather::freed_tables
*
* set when we freed page table pages
*
* - tlb_get_unmap_shift() / tlb_get_unmap_size()
*
* returns the smallest TLB entry size unmapped in this range
*
* Additionally there are a few opt-in features:
*
* HAVE_MMU_GATHER_PAGE_SIZE
*
* This ensures we call tlb_flush() every time tlb_change_page_size() actually
* changes the size and provides mmu_gather::page_size to tlb_flush().
*
* HAVE_RCU_TABLE_FREE
*
* This provides tlb_remove_table(), to be used instead of tlb_remove_page()
* for page directores (__p*_free_tlb()). This provides separate freeing of
* the page-table pages themselves in a semi-RCU fashion (see comment below).
* Useful if your architecture doesn't use IPIs for remote TLB invalidates
* and therefore doesn't naturally serialize with software page-table walkers.
*
* When used, an architecture is expected to provide __tlb_remove_table()
* which does the actual freeing of these pages.
*
* HAVE_RCU_TABLE_INVALIDATE
*
* This makes HAVE_RCU_TABLE_FREE call tlb_flush_mmu_tlbonly() before freeing
* the page-table pages. Required if you use HAVE_RCU_TABLE_FREE and your
* architecture uses the Linux page-tables natively.
*
*/
#define HAVE_GENERIC_MMU_GATHER
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
/*
* Semi RCU freeing of the page directories.
*
* This is needed by some architectures to implement software pagetable walkers.
*
* gup_fast() and other software pagetable walkers do a lockless page-table
* walk and therefore needs some synchronization with the freeing of the page
* directories. The chosen means to accomplish that is by disabling IRQs over
* the walk.
*
* Architectures that use IPIs to flush TLBs will then automagically DTRT,
* since we unlink the page, flush TLBs, free the page. Since the disabling of
* IRQs delays the completion of the TLB flush we can never observe an already
* freed page.
*
* Architectures that do not have this (PPC) need to delay the freeing by some
* other means, this is that means.
*
* What we do is batch the freed directory pages (tables) and RCU free them.
* We use the sched RCU variant, as that guarantees that IRQ/preempt disabling
* holds off grace periods.
*
* However, in order to batch these pages we need to allocate storage, this
* allocation is deep inside the MM code and can thus easily fail on memory
* pressure. To guarantee progress we fall back to single table freeing, see
* the implementation of tlb_remove_table_one().
*
*/
struct mmu_table_batch {
struct rcu_head rcu;
unsigned int nr;
void *tables[0];
};
#define MAX_TABLE_BATCH \
((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
extern void tlb_table_flush(struct mmu_gather *tlb);
extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
#endif
/*
* If we can't allocate a page to make a big batch of page pointers
* to work on, then just handle a few from the on-stack structure.
*/
#define MMU_GATHER_BUNDLE 8
struct mmu_gather_batch {
struct mmu_gather_batch *next;
unsigned int nr;
unsigned int max;
struct page *pages[0];
};
#define MAX_GATHER_BATCH \
((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *))
/*
* Limit the maximum number of mmu_gather batches to reduce a risk of soft
* lockups for non-preemptible kernels on huge machines when a lot of memory
* is zapped during unmapping.
* 10K pages freed at once should be safe even without a preemption point.
*/
#define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH)
/*
* struct mmu_gather is an opaque type used by the mm code for passing around
* any data needed by arch specific code for tlb_remove_page.
*/
struct mmu_gather {
struct mm_struct *mm;
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
struct mmu_table_batch *batch;
#endif
unsigned long start;
unsigned long end;
/*
* we are in the middle of an operation to clear
* a full mm and can make some optimizations
*/
unsigned int fullmm : 1;
/*
* we have performed an operation which
* requires a complete flush of the tlb
*/
unsigned int need_flush_all : 1;
/*
* we have removed page directories
*/
unsigned int freed_tables : 1;
/*
* at which levels have we cleared entries?
*/
unsigned int cleared_ptes : 1;
unsigned int cleared_pmds : 1;
unsigned int cleared_puds : 1;
unsigned int cleared_p4ds : 1;
unsigned int batch_count;
struct mmu_gather_batch *active;
struct mmu_gather_batch local;
struct page *__pages[MMU_GATHER_BUNDLE];
#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
unsigned int page_size;
#endif
};
void arch_tlb_gather_mmu(struct mmu_gather *tlb,
struct mm_struct *mm, unsigned long start, unsigned long end);
void tlb_flush_mmu(struct mmu_gather *tlb);
void arch_tlb_finish_mmu(struct mmu_gather *tlb,
unsigned long start, unsigned long end, bool force);
void tlb_flush_mmu_free(struct mmu_gather *tlb);
extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
int page_size);
static inline void __tlb_adjust_range(struct mmu_gather *tlb,
unsigned long address,
unsigned int range_size)
{
tlb->start = min(tlb->start, address);
tlb->end = max(tlb->end, address + range_size);
}
static inline void __tlb_reset_range(struct mmu_gather *tlb)
{
if (tlb->fullmm) {
tlb->start = tlb->end = ~0;
} else {
tlb->start = TASK_SIZE;
tlb->end = 0;
}
tlb->freed_tables = 0;
tlb->cleared_ptes = 0;
tlb->cleared_pmds = 0;
tlb->cleared_puds = 0;
tlb->cleared_p4ds = 0;
}
static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
{
if (!tlb->end)
return;
tlb_flush(tlb);
mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
__tlb_reset_range(tlb);
}
static inline void tlb_remove_page_size(struct mmu_gather *tlb,
struct page *page, int page_size)
{
if (__tlb_remove_page_size(tlb, page, page_size))
tlb_flush_mmu(tlb);
}
static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
return __tlb_remove_page_size(tlb, page, PAGE_SIZE);
}
/* tlb_remove_page
* Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
* required.
*/
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
return tlb_remove_page_size(tlb, page, PAGE_SIZE);
}
static inline void tlb_change_page_size(struct mmu_gather *tlb,
unsigned int page_size)
{
#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
if (tlb->page_size && tlb->page_size != page_size) {
if (!tlb->fullmm)
tlb_flush_mmu(tlb);
}
tlb->page_size = page_size;
#endif
}
static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb)
{
if (tlb->cleared_ptes)
return PAGE_SHIFT;
if (tlb->cleared_pmds)
return PMD_SHIFT;
if (tlb->cleared_puds)
return PUD_SHIFT;
if (tlb->cleared_p4ds)
return P4D_SHIFT;
return PAGE_SHIFT;
}
static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
{
return 1UL << tlb_get_unmap_shift(tlb);
}
/*
* In the case of tlb vma handling, we can optimise these away in the
* case where we're doing a full MM flush. When we're doing a munmap,
* the vmas are adjusted to only cover the region to be torn down.
*/
#ifndef tlb_start_vma
#define tlb_start_vma(tlb, vma) do { } while (0)
#endif
#define __tlb_end_vma(tlb, vma) \
do { \
if (!tlb->fullmm) \
tlb_flush_mmu_tlbonly(tlb); \
} while (0)
#ifndef tlb_end_vma
#define tlb_end_vma __tlb_end_vma
#endif
#ifndef __tlb_remove_tlb_entry
#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
#endif
/**
* tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
*
* Record the fact that pte's were really unmapped by updating the range,
* so we can later optimise away the tlb invalidate. This helps when
* userspace is unmapping already-unmapped pages, which happens quite a lot.
*/
#define tlb_remove_tlb_entry(tlb, ptep, address) \
do { \
__tlb_adjust_range(tlb, address, PAGE_SIZE); \
tlb->cleared_ptes = 1; \
__tlb_remove_tlb_entry(tlb, ptep, address); \
} while (0)
#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
do { \
unsigned long _sz = huge_page_size(h); \
__tlb_adjust_range(tlb, address, _sz); \
if (_sz == PMD_SIZE) \
tlb->cleared_pmds = 1; \
else if (_sz == PUD_SIZE) \
tlb->cleared_puds = 1; \
__tlb_remove_tlb_entry(tlb, ptep, address); \
} while (0)
/**
* tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation
* This is a nop so far, because only x86 needs it.
*/
#ifndef __tlb_remove_pmd_tlb_entry
#define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0)
#endif
#define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \
do { \
__tlb_adjust_range(tlb, address, HPAGE_PMD_SIZE); \
tlb->cleared_pmds = 1; \
__tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \
} while (0)
/**
|