summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/mm/tlb_nohash.c
blob: d32ec643c231fa6b038d579b7112e590c03daf92 (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
/*
 * This file contains the routines for TLB flushing.
 * On machines where the MMU does not use a hash table to store virtual to
 * physical translations (ie, SW loaded TLBs or Book3E compilant processors,
 * this does -not- include 603 however which shares the implementation with
 * hash based processors)
 *
 *  -- BenH
 *
 * Copyright 2008,2009 Ben Herrenschmidt <benh@kernel.crashing.org>
 *                     IBM Corp.
 *
 *  Derived from arch/ppc/mm/init.c:
 *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
 *
 *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
 *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
 *    Copyright (C) 1996 Paul Mackerras
 *
 *  Derived from "arch/i386/mm/init.c"
 *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  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.
 *
 */

#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/preempt.h>
#include <linux/spinlock.h>
#include <linux/memblock.h>
#include <linux/of_fdt.h>

#include <asm/tlbflush.h>
#include <asm/tlb.h>
#include <asm/code-patching.h>

#include "mmu_decl.h"

#ifdef CONFIG_PPC_BOOK3E
struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
	[MMU_PAGE_4K] = {
		.shift	= 12,
		.ind	= 20,
		.enc	= BOOK3E_PAGESZ_4K,
	},
	[MMU_PAGE_16K] = {
		.shift	= 14,
		.enc	= BOOK3E_PAGESZ_16K,
	},
	[MMU_PAGE_64K] = {
		.shift	= 16,
		.ind	= 28,
		.enc	= BOOK3E_PAGESZ_64K,
	},
	[MMU_PAGE_1M] = {
		.shift	= 20,
		.enc	= BOOK3E_PAGESZ_1M,
	},
	[MMU_PAGE_16M] = {
		.shift	= 24,
		.ind	= 36,
		.enc	= BOOK3E_PAGESZ_16M,
	},
	[MMU_PAGE_256M] = {
		.shift	= 28,
		.enc	= BOOK3E_PAGESZ_256M,
	},
	[MMU_PAGE_1G] = {
		.shift	= 30,
		.enc	= BOOK3E_PAGESZ_1GB,
	},
};
static inline int mmu_get_tsize(int psize)
{
	return mmu_psize_defs[psize].enc;
}
#else
static inline int mmu_get_tsize(int psize)
{
	/* This isn't used on !Book3E for now */
	return 0;
}
#endif

/* The variables below are currently only used on 64-bit Book3E
 * though this will probably be made common with other nohash
 * implementations at some point
 */
#ifdef CONFIG_PPC64

int mmu_linear_psize;		/* Page size used for the linear mapping */
int mmu_pte_psize;		/* Page size used for PTE pages */
int mmu_vmemmap_psize;		/* Page size used for the virtual mem map */
int book3e_htw_enabled;		/* Is HW tablewalk enabled ? */
unsigned long linear_map_top;	/* Top of linear mapping */

#endif /* CONFIG_PPC64 */

#ifdef CONFIG_PPC_FSL_BOOK3E
/* next_tlbcam_idx is used to round-robin tlbcam entry assignment */
DEFINE_PER_CPU(int, next_tlbcam_idx);
EXPORT_PER_CPU_SYMBOL(next_tlbcam_idx);
#endif

/*
 * Base TLB flushing operations:
 *
 *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
 *  - flush_tlb_page(vma, vmaddr) flushes one page
 *  - flush_tlb_range(vma, start, end) flushes a range of pages
 *  - flush_tlb_kernel_range(start, end) flushes kernel pages
 *
 *  - local_* variants of page and mm only apply to the current
 *    processor
 */

/*
 * These are the base non-SMP variants of page and mm flushing
 */
void local_flush_tlb_mm(struct mm_struct *mm)
{
	unsigned int pid;

	preempt_disable();
	pid = mm->context.id;
	if (pid != MMU_NO_CONTEXT)
		_tlbil_pid(pid);
	preempt_enable();
}
EXPORT_SYMBOL(local_flush_tlb_mm);

void __local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
			    int tsize, int ind)
{
	unsigned int pid;

	preempt_disable();
	pid = mm ? mm->context.id : 0;
	if (pid != MMU_NO_CONTEXT)
		_tlbil_va(vmaddr, pid, tsize, ind);
	preempt_enable();
}

void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
	__local_flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
			       mmu_get_tsize(mmu_virtual_psize), 0);
}
EXPORT_SYMBOL(local_flush_tlb_page);

/*
 * And here are the SMP non-local implementations
 */
#ifdef CONFIG_SMP

static DEFINE_RAW_SPINLOCK(tlbivax_lock);

static int mm_is_core_local(struct mm_struct *mm)
{
	return cpumask_subset(mm_cpumask(mm),
			      topology_thread_cpumask(smp_processor_id()));
}

struct tlb_flush_param {
	unsigned long addr;
	unsigned int pid;
	unsigned int tsize;
	unsigned int ind;
};

static void do_flush_tlb_mm_ipi(void *param)
{
	struct tlb_flush_param *p = param;

	_tlbil_pid(p ? p->pid : 0);
}

static void do_flush_tlb_page_ipi(void *param)
{
	struct tlb_flush_param *p = param;

	_tlbil_va(p->addr, p->pid, p->tsize, p->ind);
}


/* Note on invalidations and PID:
 *
 * We snapshot the PID with preempt disabled. At this point, it can still
 * change either because:
 * - our context is being stolen (PID -> NO_CONTEXT) on another CPU
 * - we are invaliating some target that isn't currently running here
 *   and is concurrently acquiring a new PID on another CPU
 * - some other CPU is re-acquiring a lost PID for this mm
 * etc...
 *
 * However, this shouldn't be a problem as we only guarantee
 * invalidation of TLB entries present prior to this call, so we
 * don't care about the PID changing, and invalidating a stale PID
 * is generally harmless.
 */

void flush_tlb_mm(struct mm_struct *mm)
{
	unsigned int pid;

	preempt_disable();
	pid = mm->context.id;
	if (unlikely(pid == MMU_NO_CONTEXT))
		goto no_context;
	if (!mm_is_core_local(mm)) {
		struct tlb_flush_param p = { .pid = pid };
		/* Ignores smp_processor_id() even if set. */
		smp_call_function_many(mm_cpumask(mm),
				       do_flush_tlb_mm_ipi, &p, 1);
	}
	_tlbil_pid(pid);
 no_context:
	preempt_enable();
}
EXPORT_SYMBOL(flush_tlb_mm);

void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
		      int tsize, int ind)
{
	struct cpumask *cpu_mask;
	unsigned int pid;

	preempt_disable();
	pid = mm ? mm->context.id : 0;
	if (unlikely(pid == MMU_NO_CONTEXT))
		goto bail;
	cpu_mask = mm_cpumask(mm);
	if (!mm_is_core_local(mm)) {
		/* If broadcast tlbivax is supported, use it */
		if (mmu_has_feature(MMU_FTR_USE_TLBIVAX_BCAST)) {
			int lock = mmu_has_feature(MMU_FTR_LOCK_BCAST_INVAL);
			if (lock)
				raw_spin_lock(&tlbivax_lock);
			_tlbivax_bcast(vmaddr, pid, tsize, ind);
			if (lock)
				raw_spin_unlock(&tlbivax_lock);
			goto bail;
		} else {
			struct tlb_flush_param p = {
				.pid = pid,
				.addr = vmaddr,
				.tsize = tsize,
				.ind = ind,
			};
			/* Ignores smp_processor_id() even if set in cpu_mask */
			smp_call_function_many(cpu_mask,
					       do_flush_tlb_page_ipi, &p, 1);
		}
	}
	_tlbil_va(vmaddr, pid, tsize, ind);
 bail:
	preempt_enable();
}

void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
	__flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
			 mmu_get_tsize(mmu_virtual_psize), 0);
}
EXPORT_SYMBOL(flush_tlb_page);

#endif /* CONFIG_SMP */

#ifdef CONFIG_PPC_47x
void __init early_init_mmu_47x(void)
{
#ifdef CONFIG_SMP
	unsigned long root = of_get_flat_dt_root();
	if (of_get_flat_dt_prop(root, "cooperative-partition", NULL))
		mmu_clear_feature(MMU_FTR_USE_TLBIVAX_BCAST);
#endif /* CONFIG_SMP */
}
#endif /* CONFIG_PPC_47x */

/*
 * Flush kernel TLB entries in the given range
 */
void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
#ifdef CONFIG_SMP
	preempt_disable();
	smp_call_function(do_flush_tlb_mm_ipi, NULL, 1);
	_tlbil_pid(0);
	preempt_enable();
#else
	_tlbil_pid(0);
#endif
}
EXPORT_SYMBOL(flush_tlb_kernel_range);

/*
 * Currently, for range flushing, we just do a full mm flush. This should
 * be optimized based on a threshold on the size of the range, since
 * some implementation can stack multiple tlbivax before a tlbsync but
 * for now, we keep it that way
 */
void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
		     unsigned long end)

{
	flush_tlb_mm(vma->vm_mm);
}
EXPORT_SYMBOL(flush_tlb_range);

void tlb_flush(struct mmu_gather *tlb)
{
	flush_tlb_mm(tlb->mm);
}

/*
 * Below are functions specific to the 64-bit variant of Book3E though that
 * may change in the future
 */

#ifdef CONFIG_PPC64

/*
 * Handling of virtual linear page tables or indirect TLB entries
 * flushing when PTE pages are freed
 */
void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address)
{
	int tsize = mmu_psize_defs[mmu_pte_psize].enc;

	if (book3e_htw_enabled) {
		unsigned long start = address & PMD_MASK;
		unsigned long end = address + PMD_SIZE;
		unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift;

		/* This isn't the most optimal, ideally we would factor out the
		 * while preempt & CPU mask mucking around, or even the IPI but
		 * it will do for now
		 */
		while (start < end) {
			__flush_tlb_page(tlb->mm, start, tsize, 1);
			start += size;
		}
	} else {
		unsigned long rmask = 0xf000000000000000ul;
		unsigned long rid = (address & rmask) | 0x1000000000000000ul;
		unsigned long vpte = address & ~rmask;

#ifdef CONFIG_PPC_64K_PAGES
		vpte = (vpte >> (PAGE_SHIFT - 4)) & ~0xfffful;
#else
		vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful;
#endif
		vpte |= rid;
		__flush_tlb_page(tlb->mm, vpte, tsize, 0);
	}
}

static void setup_page_sizes(void)
{
	unsigned int tlb0cfg;
	unsigned int tlb0ps;
	unsigned int eptcfg;
	int i, psize;

#ifdef CONFIG_PPC_FSL_BOOK3E
	unsigned int mmucfg = mfspr(SPRN_MMUCFG);

	if (((mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) &&
		(mmu_has_feature(MMU_FTR_TYPE_FSL_E))) {
		unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG);
		unsigned int min_pg, max_pg;

		min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT;
		max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT;

		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
			struct mmu_psize_def *def;
			unsigned int shift;

			def = &mmu_psize_defs[psize];
			shift = def->shift;

			if (shift == 0)
				continue;

			/* adjust to be in terms of 4^shift Kb */
			shift = (shift - 10) >> 1;

			if ((shift >= min_pg) && (shift <= max_pg))
				def->flags |= MMU_PAGE_SIZE_DIRECT;
		}

		goto no_indirect;
	}
#endif

	tlb0cfg = mfspr(SPRN_TLB0CFG);
	tlb0ps = mfspr(SPRN_TLB0PS);
	eptcfg = mfspr(SPRN_EPTCFG);

	/* Look for supported direct sizes */
	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
		struct mmu_psize_def *def = &mmu_psize_defs[psize];

		if (tlb0ps & (1U << (def->shift - 10)))
			def->flags |= MMU_PAGE_SIZE_DIRECT;
	}

	/* Indirect page sizes supported ? */
	if ((tlb0cfg & TLBnCFG_IND) == 0)
		goto no_indirect;

	/* Now, we only deal with one IND page size for each
	 * direct size. Hopefully all implementations today are
	 * unambiguous, but we might want to be careful in the
	 * future.
	 */
	for (i = 0; i < 3; i++) {
		unsigned int ps, sps;

		sps = eptcfg & 0x1f;
		eptcfg >>= 5;
		ps = eptcfg & 0x1f;
		eptcfg >>= 5;
		if (!ps || !sps)
			continue;
		for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
			struct mmu_psize_def *def = &mmu_psize_defs[psize];

			if (ps == (def->shift - 10))
				def->flags |= MMU_PAGE_SIZE_INDIRECT;
			if (sps == (def->shift - 10))
				def->ind = ps + 10;
		}
	}
 no_indirect:

	/* Cleanup array and print summary */
	pr_info("MMU: Supported page sizes\n");
	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
		struct mmu_psize_def *def = &mmu_psize_defs[psize];
		const char *__page_type_names[] = {
			"unsupported",
			"direct",
			"indirect",
			"direct & indirect"
		};
		if (def->flags == 0) {
			def->shift = 0;	
			continue;
		}
		pr_info("  %8ld KB as %s\n", 1ul << (def->shift - 10),
			__page_type_names[def->flags & 0x3]);
	}
}

static void __patch_exception(int exc, unsigned long addr)
{
	extern unsigned int interrupt_base_book3e;
 	unsigned int *ibase = &interrupt_base_book3e;
 
	/* Our exceptions vectors start with a NOP and -then- a branch
	 * to deal with single stepping from userspace which stops on
	 * the second instruction. Thus we need to patch the second
	 * instruction of the exception, not the first one
	 */

	patch_branch(ibase + (exc / 4) + 1, addr, 0);
}

#define patch_exception(exc, name) do { \
	extern unsigned int name; \
	__patch_exception((exc), (unsigned long)&name); \
} while (0)

static void setup_mmu_htw(void)
{
	/* Check if HW tablewalk is present, and if yes, enable it by:
	 *
	 * - patching the TLB miss handlers to branch to the
	 *   one dedicates to it
	 *
	 * - setting the global book3e_htw_enabled
       	 */
	unsigned int tlb0cfg = mfspr(SPRN_TLB0CFG);

	if ((tlb0cfg & TLBnCFG_IND) &&
	    (tlb0cfg & TLBnCFG_PT)) {
		patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e);
		patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e);
		book3e_htw_enabled = 1;
	}
	pr_info("MMU: Book3E HW tablewalk %s\n",
		book3e_htw_enabled ? "enabled" : "not supported");
}

/*
 * Early initialization of the MMU TLB code
 */
static void __early_init_mmu(int boot_cpu)
{
	unsigned int mas4;

	/* XXX This will have to be decided at runtime, but right
	 * now our boot and TLB miss code hard wires it. Ideally
	 * we should find out a suitable page size and patch the
	 * TLB miss code (either that or use the PACA to store
	 * the value we want)
	 */
	mmu_linear_psize = MMU_PAGE_1G;

	/* XXX This should be decided at runtime based on supported
	 * page sizes in the TLB, but for now let's assume 16M is
	 * always there and a good fit (which it probably is)
	 */
	mmu_vmemmap_psize = MMU_PAGE_16M;

	/* XXX This code only checks for TLB 0 capabilities and doesn't
	 *     check what page size combos are supported by the HW. It
	 *     also doesn't handle the case where a separate array holds
	 *     the IND entries from the array loaded by the PT.
	 */
	if (boot_cpu) {
		/* Look for supported page sizes */
		setup_page_sizes();

		/* Look for HW tablewalk support */
		setup_mmu_htw();
	}

	/* Set MAS4 based on page table setting */

	mas4 = 0x4 << MAS4_WIMGED_SHIFT;
	if (book3e_htw_enabled) {
		mas4 |= mas4 | MAS4_INDD;
#ifdef CONFIG_PPC_64K_PAGES
		mas4 |=	BOOK3E_PAGESZ_256M << MAS4_TSIZED_SHIFT;
		mmu_pte_psize = MMU_PAGE_256M;
#else
		mas4 |=	BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT;
		mmu_pte_psize = MMU_PAGE_1M;
#endif
	} else {
#ifdef CONFIG_PPC_64K_PAGES
		mas4 |=	BOOK3E_PAGESZ_64K << MAS4_TSIZED_SHIFT;
#else
		mas4 |=	BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
#endif
		mmu_pte_psize = mmu_virtual_psize;
	}
	mtspr(SPRN_MAS4, mas4);

	/* Set the global containing the top of the linear mapping
	 * for use by the TLB miss code
	 */
	linear_map_top = memblock_end_of_DRAM();

#ifdef CONFIG_PPC_FSL_BOOK3E
	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
		unsigned int num_cams;

		/* use a quarter of the TLBCAM for bolted linear map */
		num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
		linear_map_top = map_mem_in_cams(linear_map_top, num_cams);

		/* limit memory so we dont have linear faults */
		memblock_enforce_memory_limit(linear_map_top);
		memblock_analyze();

		patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
		patch_exception(0x1e0, exc_instruction_tlb_miss_bolted_book3e);
	}
#endif

	/* A sync won't hurt us after mucking around with
	 * the MMU configuration
	 */
	mb();

	memblock_set_current_limit(linear_map_top);
}

void __init early_init_mmu(void)
{
	__early_init_mmu(1);
}

void __cpuinit early_init_mmu_secondary(void)
{
	__early_init_mmu(0);
}

void setup_initial_memory_limit(phys_addr_t first_memblock_base,
				phys_addr_t first_memblock_size)
{
	/* On Embedded 64-bit, we adjust the RMA size to match
	 * the bolted TLB entry. We know for now that only 1G
	 * entries are supported though that may eventually
	 * change. We crop it to the size of the first MEMBLOCK to
	 * avoid going over total available memory just in case...
	 */
	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);

	/* Finally limit subsequent allocations */
	memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
}
#else /* ! CONFIG_PPC64 */
void __init early_init_mmu(void)
{
#ifdef CONFIG_PPC_47x
	early_init_mmu_47x();
#endif
}
#endif /* CONFIG_PPC64 */