summaryrefslogtreecommitdiff
path: root/arch/arm64/include/asm/tlbflush.h
blob: bb2c2833a98722640f27c78d67a3a1a5bdc557c7 (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Based on arch/arm/include/asm/tlbflush.h
 *
 * Copyright (C) 1999-2003 Russell King
 * Copyright (C) 2012 ARM Ltd.
 */
#ifndef __ASM_TLBFLUSH_H
#define __ASM_TLBFLUSH_H

#ifndef __ASSEMBLY__

#include <linux/bitfield.h>
#include <linux/mm_types.h>
#include <linux/sched.h>
#include <linux/mmu_notifier.h>
#include <asm/cputype.h>
#include <asm/mmu.h>

/*
 * Raw TLBI operations.
 *
 * Where necessary, use the __tlbi() macro to avoid asm()
 * boilerplate. Drivers and most kernel code should use the TLB
 * management routines in preference to the macro below.
 *
 * The macro can be used as __tlbi(op) or __tlbi(op, arg), depending
 * on whether a particular TLBI operation takes an argument or
 * not. The macros handles invoking the asm with or without the
 * register argument as appropriate.
 */
#define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE			       \
			       "tlbi " #op "\n"				       \
		   ALTERNATIVE("nop\n			nop",		       \
			       "dsb ish\n		tlbi " #op,	       \
			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
			    : : )

#define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
			       "tlbi " #op ", %0\n"			       \
		   ALTERNATIVE("nop\n			nop",		       \
			       "dsb ish\n		tlbi " #op ", %0",     \
			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
			    : : "r" (arg))

#define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)

#define __tlbi(op, ...)		__TLBI_N(op, ##__VA_ARGS__, 1, 0)

#define __tlbi_user(op, arg) do {						\
	if (arm64_kernel_unmapped_at_el0())					\
		__tlbi(op, (arg) | USER_ASID_FLAG);				\
} while (0)

/* This macro creates a properly formatted VA operand for the TLBI */
#define __TLBI_VADDR(addr, asid)				\
	({							\
		unsigned long __ta = (addr) >> 12;		\
		__ta &= GENMASK_ULL(43, 0);			\
		__ta |= (unsigned long)(asid) << 48;		\
		__ta;						\
	})

/*
 * Get translation granule of the system, which is decided by
 * PAGE_SIZE.  Used by TTL.
 *  - 4KB	: 1
 *  - 16KB	: 2
 *  - 64KB	: 3
 */
#define TLBI_TTL_TG_4K		1
#define TLBI_TTL_TG_16K		2
#define TLBI_TTL_TG_64K		3

static inline unsigned long get_trans_granule(void)
{
	switch (PAGE_SIZE) {
	case SZ_4K:
		return TLBI_TTL_TG_4K;
	case SZ_16K:
		return TLBI_TTL_TG_16K;
	case SZ_64K:
		return TLBI_TTL_TG_64K;
	default:
		return 0;
	}
}

/*
 * Level-based TLBI operations.
 *
 * When ARMv8.4-TTL exists, TLBI operations take an additional hint for
 * the level at which the invalidation must take place. If the level is
 * wrong, no invalidation may take place. In the case where the level
 * cannot be easily determined, a 0 value for the level parameter will
 * perform a non-hinted invalidation.
 *
 * For Stage-2 invalidation, use the level values provided to that effect
 * in asm/stage2_pgtable.h.
 */
#define TLBI_TTL_MASK		GENMASK_ULL(47, 44)

#define __tlbi_level(op, addr, level) do {				\
	u64 arg = addr;							\
									\
	if (alternative_has_cap_unlikely(ARM64_HAS_ARMv8_4_TTL) &&	\
	    level) {							\
		u64 ttl = level & 3;					\
		ttl |= get_trans_granule() << 2;			\
		arg &= ~TLBI_TTL_MASK;					\
		arg |= FIELD_PREP(TLBI_TTL_MASK, ttl);			\
	}								\
									\
	__tlbi(op, arg);						\
} while(0)

#define __tlbi_user_level(op, arg, level) do {				\
	if (arm64_kernel_unmapped_at_el0())				\
		__tlbi_level(op, (arg | USER_ASID_FLAG), level);	\
} while (0)

/*
 * This macro creates a properly formatted VA operand for the TLB RANGE.
 * The value bit assignments are:
 *
 * +----------+------+-------+-------+-------+----------------------+
 * |   ASID   |  TG  | SCALE |  NUM  |  TTL  |        BADDR         |
 * +-----------------+-------+-------+-------+----------------------+
 * |63      48|47  46|45   44|43   39|38   37|36                   0|
 *
 * The address range is determined by below formula:
 * [BADDR, BADDR + (NUM + 1) * 2^(5*SCALE + 1) * PAGESIZE)
 *
 */
#define __TLBI_VADDR_RANGE(addr, asid, scale, num, ttl)		\
	({							\
		unsigned long __ta = (addr) >> PAGE_SHIFT;	\
		__ta &= GENMASK_ULL(36, 0);			\
		__ta |= (unsigned long)(ttl) << 37;		\
		__ta |= (unsigned long)(num) << 39;		\
		__ta |= (unsigned long)(scale) << 44;		\
		__ta |= get_trans_granule() << 46;		\
		__ta |= (unsigned long)(asid) << 48;		\
		__ta;						\
	})

/* These macros are used by the TLBI RANGE feature. */
#define __TLBI_RANGE_PAGES(num, scale)	\
	((unsigned long)((num) + 1) << (5 * (scale) + 1))
#define MAX_TLBI_RANGE_PAGES		__TLBI_RANGE_PAGES(31, 3)

/*
 * Generate 'num' values from -1 to 30 with -1 rejected by the
 * __flush_tlb_range() loop below.
 */
#define TLBI_RANGE_MASK			GENMASK_ULL(4, 0)
#define __TLBI_RANGE_NUM(pages, scale)	\
	((((pages) >> (5 * (scale) + 1)) & TLBI_RANGE_MASK) - 1)

/*
 *	TLB Invalidation
 *	================
 *
 * 	This header file implements the low-level TLB invalidation routines
 *	(sometimes referred to as "flushing" in the kernel) for arm64.
 *
 *	Every invalidation operation uses the following template:
 *
 *	DSB ISHST	// Ensure prior page-table updates have completed
 *	TLBI ...	// Invalidate the TLB
 *	DSB ISH		// Ensure the TLB invalidation has completed
 *      if (invalidated kernel mappings)
 *		ISB	// Discard any instructions fetched from the old mapping
 *
 *
 *	The following functions form part of the "core" TLB invalidation API,
 *	as documented in Documentation/core-api/cachetlb.rst:
 *
 *	flush_tlb_all()
 *		Invalidate the entire TLB (kernel + user) on all CPUs
 *
 *	flush_tlb_mm(mm)
 *		Invalidate an entire user address space on all CPUs.
 *		The 'mm' argument identifies the ASID to invalidate.
 *
 *	flush_tlb_range(vma, start, end)
 *		Invalidate the virtual-address range '[start, end)' on all
 *		CPUs for the user address space corresponding to 'vma->mm'.
 *		Note that this operation also invalidates any walk-cache
 *		entries associated with translations for the specified address
 *		range.
 *
 *	flush_tlb_kernel_range(start, end)
 *		Same as flush_tlb_range(..., start, end), but applies to
 * 		kernel mappings rather than a particular user address space.
 *		Whilst not explicitly documented, this function is used when
 *		unmapping pages from vmalloc/io space.
 *
 *	flush_tlb_page(vma, addr)
 *		Invalidate a single user mapping for address 'addr' in the
 *		address space corresponding to 'vma->mm'.  Note that this
 *		operation only invalidates a single, last-level page-table
 *		entry and therefore does not affect any walk-caches.
 *
 *
 *	Next, we have some undocumented invalidation routines that you probably
 *	don't want to call unless you know what you're doing:
 *
 *	local_flush_tlb_all()
 *		Same as flush_tlb_all(), but only applies to the calling CPU.
 *
 *	__flush_tlb_kernel_pgtable(addr)
 *		Invalidate a single kernel mapping for address 'addr' on all
 *		CPUs, ensuring that any walk-cache entries associated with the
 *		translation are also invalidated.
 *
 *	__flush_tlb_range(vma, start, end, stride, last_level)
 *		Invalidate the virtual-address range '[start, end)' on all
 *		CPUs for the user address space corresponding to 'vma->mm'.
 *		The invalidation operations are issued at a granularity
 *		determined by 'stride' and only affect any walk-cache entries
 *		if 'last_level' is equal to false.
 *
 *
 *	Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented
 *	on top of these routines, since that is our interface to the mmu_gather
 *	API as used by munmap() and friends.
 */
static inline void local_flush_tlb_all(void)
{
	dsb(nshst);
	__tlbi(vmalle1);
	dsb(nsh);
	isb();
}

static inline void flush_tlb_all(void)
{
	dsb(ishst);
	__tlbi(vmalle1is);
	dsb(ish);
	isb();
}

static inline void flush_tlb_mm(struct mm_struct *mm)
{
	unsigned long asid;

	dsb(ishst);
	asid = __TLBI_VADDR(0, ASID(mm));
	__tlbi(aside1is, asid);
	__tlbi_user(aside1is, asid);
	dsb(ish);
	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
}

static inline void __flush_tlb_page_nosync(struct mm_struct *mm,
					   unsigned long uaddr)
{
	unsigned long addr;

	dsb(ishst);
	addr = __TLBI_VADDR(uaddr, ASID(mm));
	__tlbi(vale1is, addr);
	__tlbi_user(vale1is, addr);
	mmu_notifier_arch_invalidate_secondary_tlbs(mm, uaddr & PAGE_MASK,
						(uaddr & PAGE_MASK) + PAGE_SIZE);
}

static inline void flush_tlb_page_nosync(struct vm_area_struct *vma,
					 unsigned long uaddr)
{
	return __flush_tlb_page_nosync(vma->vm_mm, uaddr);
}

static inline void flush_tlb_page(struct vm_area_struct *vma,
				  unsigned long uaddr)
{
	flush_tlb_page_nosync(vma, uaddr);
	dsb(ish);
}

static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
{
	/*
	 * TLB flush deferral is not required on systems which are affected by
	 * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation
	 * will have two consecutive TLBI instructions with a dsb(ish) in between
	 * defeating the purpose (i.e save overall 'dsb ish' cost).
	 */
	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))
		return false;

	return true;
}

static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
					     struct mm_struct *mm,
					     unsigned long uaddr)
{
	__flush_tlb_page_nosync(mm, uaddr);
}

/*
 * If mprotect/munmap/etc occurs during TLB batched flushing, we need to
 * synchronise all the TLBI issued with a DSB to avoid the race mentioned in
 * flush_tlb_batched_pending().
 */
static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm)
{
	dsb(ish);
}

/*
 * To support TLB batched flush for multiple pages unmapping, we only send
 * the TLBI for each page in arch_tlbbatch_add_pending() and wait for the
 * completion at the end in arch_tlbbatch_flush(). Since we've already issued
 * TLBI for each page so only a DSB is needed to synchronise its effect on the
 * other CPUs.
 *
 * This will save the time waiting on DSB comparing issuing a TLBI;DSB sequence
 * for each page.
 */
static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
{
	dsb(ish);
}

/*
 * This is meant to avoid soft lock-ups on large TLB flushing ranges and not
 * necessarily a performance improvement.
 */
#define MAX_DVM_OPS	PTRS_PER_PTE

/*
 * __flush_tlb_range_op - Perform TLBI operation upon a range
 *
 * @op:	TLBI instruction that operates on a range (has 'r' prefix)
 * @start:	The start address of the range
 * @pages:	Range as the number of pages from 'start'
 * @stride:	Flush granularity
 * @asid:	The ASID of the task (0 for IPA instructions)
 * @tlb_level:	Translation Table level hint, if known
 * @tlbi_user:	If 'true', call an additional __tlbi_user()
 *              (typically for user ASIDs). 'flase' for IPA instructions
 *
 * When the CPU does not support TLB range operations, flush the TLB
 * entries one by one at the granularity of 'stride'. If the TLB
 * range ops are supported, then:
 *
 * 1. If 'pages' is odd, flush the first page through non-range
 *    operations;
 *
 * 2. For remaining pages: the minimum range granularity is decided
 *    by 'scale', so multiple range TLBI operations may be required.
 *    Start from scale = 0, flush the corresponding number of pages
 *    ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
 *    until no pages left.
 *
 * Note that certain ranges can be represented by either num = 31 and
 * scale or num = 0 and scale + 1. The loop below favours the latter
 * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
 */
#define __flush_tlb_range_op(op, start, pages, stride,			\
				asid, tlb_level, tlbi_user)		\
do {									\
	int num = 0;							\
	int scale = 0;							\
	unsigned long addr;						\
									\
	while (pages > 0) {						\
		if (!system_supports_tlb_range() ||			\
		    pages % 2 == 1) {					\
			addr = __TLBI_VADDR(start, asid);		\
			__tlbi_level(op, addr, tlb_level);		\
			if (tlbi_user)					\
				__tlbi_user_level(op, addr, tlb_level);	\
			start += stride;				\
			pages -= stride >> PAGE_SHIFT;			\
			continue;					\
		}							\
									\
		num = __TLBI_RANGE_NUM(pages, scale);			\
		if (num >= 0) {						\
			addr = __TLBI_VADDR_RANGE(start, asid, scale,	\
						  num, tlb_level);	\
			__tlbi(r##op, addr);				\
			if (tlbi_user)					\
				__tlbi_user(r##op, addr);		\
			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
			pages -= __TLBI_RANGE_PAGES(num, scale);	\
		}							\
		scale++;						\
	}								\
} while (0)

#define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \
	__flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false)

static inline void __flush_tlb_range(struct vm_area_struct *vma,
				     unsigned long start, unsigned long end,
				     unsigned long stride, bool last_level,
				     int tlb_level)
{
	unsigned long asid, pages;

	start = round_down(start, stride);
	end = round_up(end, stride);
	pages = (end - start) >> PAGE_SHIFT;

	/*
	 * When not uses TLB range ops, we can handle up to
	 * (MAX_DVM_OPS - 1) pages;
	 * When uses TLB range ops, we can handle up to
	 * (MAX_TLBI_RANGE_PAGES - 1) pages.
	 */
	if ((!system_supports_tlb_range() &&
	     (end - start) >= (MAX_DVM_OPS * stride)) ||
	    pages >= MAX_TLBI_RANGE_PAGES) {
		flush_tlb_mm(vma->vm_mm);
		return;
	}

	dsb(ishst);
	asid = ASID(vma->vm_mm);

	if (last_level)
		__flush_tlb_range_op(vale1is, start, pages, stride, asid, tlb_level, true);
	else
		__flush_tlb_range_op(vae1is, start, pages, stride, asid, tlb_level, true);

	dsb(ish);
	mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end);
}

static inline void flush_tlb_range(struct vm_area_struct *vma,
				   unsigned long start, unsigned long end)
{
	/*
	 * We cannot use leaf-only invalidation here, since we may be invalidating
	 * table entries as part of collapsing hugepages or moving page tables.
	 * Set the tlb_level to 0 because we can not get enough information here.
	 */
	__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
}

static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
	unsigned long addr;

	if ((end - start) > (MAX_DVM_OPS * PAGE_SIZE)) {
		flush_tlb_all();
		return;
	}

	start = __TLBI_VADDR(start, 0);
	end = __TLBI_VADDR(end, 0);

	dsb(ishst);
	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
		__tlbi(vaale1is, addr);
	dsb(ish);
	isb();
}

/*
 * Used to invalidate the TLB (walk caches) corresponding to intermediate page
 * table levels (pgd/pud/pmd).
 */
static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
{
	unsigned long addr = __TLBI_VADDR(kaddr, 0);

	dsb(ishst);
	__tlbi(vaae1is, addr);
	dsb(ish);
	isb();
}
#endif

#endif