summaryrefslogtreecommitdiffstats
path: root/arch/parisc/kernel/cache.c
blob: f6448c7c62b51f3785c758b2073b0eb967362633 (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
/*
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * Copyright (C) 1999-2006 Helge Deller <deller@gmx.de> (07-13-1999)
 * Copyright (C) 1999 SuSE GmbH Nuernberg
 * Copyright (C) 2000 Philipp Rumpf (prumpf@tux.org)
 *
 * Cache and TLB management
 *
 */
 
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/pagemap.h>
#include <linux/sched.h>
#include <asm/pdc.h>
#include <asm/cache.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
#include <asm/pgalloc.h>
#include <asm/processor.h>
#include <asm/sections.h>
#include <asm/shmparam.h>

int split_tlb __read_mostly;
int dcache_stride __read_mostly;
int icache_stride __read_mostly;
EXPORT_SYMBOL(dcache_stride);

void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
EXPORT_SYMBOL(flush_dcache_page_asm);
void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr);


/* On some machines (e.g. ones with the Merced bus), there can be
 * only a single PxTLB broadcast at a time; this must be guaranteed
 * by software.  We put a spinlock around all TLB flushes  to
 * ensure this.
 */
DEFINE_SPINLOCK(pa_tlb_lock);

struct pdc_cache_info cache_info __read_mostly;
#ifndef CONFIG_PA20
static struct pdc_btlb_info btlb_info __read_mostly;
#endif

#ifdef CONFIG_SMP
void
flush_data_cache(void)
{
	on_each_cpu(flush_data_cache_local, NULL, 1);
}
void 
flush_instruction_cache(void)
{
	on_each_cpu(flush_instruction_cache_local, NULL, 1);
}
#endif

void
flush_cache_all_local(void)
{
	flush_instruction_cache_local(NULL);
	flush_data_cache_local(NULL);
}
EXPORT_SYMBOL(flush_cache_all_local);

/* Virtual address of pfn.  */
#define pfn_va(pfn)	__va(PFN_PHYS(pfn))

void
update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
{
	unsigned long pfn = pte_pfn(*ptep);
	struct page *page;

	/* We don't have pte special.  As a result, we can be called with
	   an invalid pfn and we don't need to flush the kernel dcache page.
	   This occurs with FireGL card in C8000.  */
	if (!pfn_valid(pfn))
		return;

	page = pfn_to_page(pfn);
	if (page_mapping(page) && test_bit(PG_dcache_dirty, &page->flags)) {
		flush_kernel_dcache_page_addr(pfn_va(pfn));
		clear_bit(PG_dcache_dirty, &page->flags);
	} else if (parisc_requires_coherency())
		flush_kernel_dcache_page_addr(pfn_va(pfn));
}

void
show_cache_info(struct seq_file *m)
{
	char buf[32];

	seq_printf(m, "I-cache\t\t: %ld KB\n", 
		cache_info.ic_size/1024 );
	if (cache_info.dc_loop != 1)
		snprintf(buf, 32, "%lu-way associative", cache_info.dc_loop);
	seq_printf(m, "D-cache\t\t: %ld KB (%s%s, %s)\n",
		cache_info.dc_size/1024,
		(cache_info.dc_conf.cc_wt ? "WT":"WB"),
		(cache_info.dc_conf.cc_sh ? ", shared I/D":""),
		((cache_info.dc_loop == 1) ? "direct mapped" : buf));
	seq_printf(m, "ITLB entries\t: %ld\n" "DTLB entries\t: %ld%s\n",
		cache_info.it_size,
		cache_info.dt_size,
		cache_info.dt_conf.tc_sh ? " - shared with ITLB":""
	);
		
#ifndef CONFIG_PA20
	/* BTLB - Block TLB */
	if (btlb_info.max_size==0) {
		seq_printf(m, "BTLB\t\t: not supported\n" );
	} else {
		seq_printf(m, 
		"BTLB fixed\t: max. %d pages, pagesize=%d (%dMB)\n"
		"BTLB fix-entr.\t: %d instruction, %d data (%d combined)\n"
		"BTLB var-entr.\t: %d instruction, %d data (%d combined)\n",
		btlb_info.max_size, (int)4096,
		btlb_info.max_size>>8,
		btlb_info.fixed_range_info.num_i,
		btlb_info.fixed_range_info.num_d,
		btlb_info.fixed_range_info.num_comb, 
		btlb_info.variable_range_info.num_i,
		btlb_info.variable_range_info.num_d,
		btlb_info.variable_range_info.num_comb
		);
	}
#endif
}

void __init 
parisc_cache_init(void)
{
	if (pdc_cache_info(&cache_info) < 0)
		panic("parisc_cache_init: pdc_cache_info failed");

#if 0
	printk("ic_size %lx dc_size %lx it_size %lx\n",
		cache_info.ic_size,
		cache_info.dc_size,
		cache_info.it_size);

	printk("DC  base 0x%lx stride 0x%lx count 0x%lx loop 0x%lx\n",
		cache_info.dc_base,
		cache_info.dc_stride,
		cache_info.dc_count,
		cache_info.dc_loop);

	printk("dc_conf = 0x%lx  alias %d blk %d line %d shift %d\n",
		*(unsigned long *) (&cache_info.dc_conf),
		cache_info.dc_conf.cc_alias,
		cache_info.dc_conf.cc_block,
		cache_info.dc_conf.cc_line,
		cache_info.dc_conf.cc_shift);
	printk("	wt %d sh %d cst %d hv %d\n",
		cache_info.dc_conf.cc_wt,
		cache_info.dc_conf.cc_sh,
		cache_info.dc_conf.cc_cst,
		cache_info.dc_conf.cc_hv);

	printk("IC  base 0x%lx stride 0x%lx count 0x%lx loop 0x%lx\n",
		cache_info.ic_base,
		cache_info.ic_stride,
		cache_info.ic_count,
		cache_info.ic_loop);

	printk("ic_conf = 0x%lx  alias %d blk %d line %d shift %d\n",
		*(unsigned long *) (&cache_info.ic_conf),
		cache_info.ic_conf.cc_alias,
		cache_info.ic_conf.cc_block,
		cache_info.ic_conf.cc_line,
		cache_info.ic_conf.cc_shift);
	printk("	wt %d sh %d cst %d hv %d\n",
		cache_info.ic_conf.cc_wt,
		cache_info.ic_conf.cc_sh,
		cache_info.ic_conf.cc_cst,
		cache_info.ic_conf.cc_hv);

	printk("D-TLB conf: sh %d page %d cst %d aid %d pad1 %d\n",
		cache_info.dt_conf.tc_sh,
		cache_info.dt_conf.tc_page,
		cache_info.dt_conf.tc_cst,
		cache_info.dt_conf.tc_aid,
		cache_info.dt_conf.tc_pad1);

	printk("I-TLB conf: sh %d page %d cst %d aid %d pad1 %d\n",
		cache_info.it_conf.tc_sh,
		cache_info.it_conf.tc_page,
		cache_info.it_conf.tc_cst,
		cache_info.it_conf.tc_aid,
		cache_info.it_conf.tc_pad1);
#endif

	split_tlb = 0;
	if (cache_info.dt_conf.tc_sh == 0 || cache_info.dt_conf.tc_sh == 2) {
		if (cache_info.dt_conf.tc_sh == 2)
			printk(KERN_WARNING "Unexpected TLB configuration. "
			"Will flush I/D separately (could be optimized).\n");

		split_tlb = 1;
	}

	/* "New and Improved" version from Jim Hull 
	 *	(1 << (cc_block-1)) * (cc_line << (4 + cnf.cc_shift))
	 * The following CAFL_STRIDE is an optimized version, see
	 * http://lists.parisc-linux.org/pipermail/parisc-linux/2004-June/023625.html
	 * http://lists.parisc-linux.org/pipermail/parisc-linux/2004-June/023671.html
	 */
#define CAFL_STRIDE(cnf) (cnf.cc_line << (3 + cnf.cc_block + cnf.cc_shift))
	dcache_stride = CAFL_STRIDE(cache_info.dc_conf);
	icache_stride = CAFL_STRIDE(cache_info.ic_conf);
#undef CAFL_STRIDE

#ifndef CONFIG_PA20
	if (pdc_btlb_info(&btlb_info) < 0) {
		memset(&btlb_info, 0, sizeof btlb_info);
	}
#endif

	if ((boot_cpu_data.pdc.capabilities & PDC_MODEL_NVA_MASK) ==
						PDC_MODEL_NVA_UNSUPPORTED) {
		printk(KERN_WARNING "parisc_cache_init: Only equivalent aliasing supported!\n");
#if 0
		panic("SMP kernel required to avoid non-equivalent aliasing");
#endif
	}
}

void disable_sr_hashing(void)
{
	int srhash_type, retval;
	unsigned long space_bits;

	switch (boot_cpu_data.cpu_type) {
	case pcx: /* We shouldn't get this far.  setup.c should prevent it. */
		BUG();
		return;

	case pcxs:
	case pcxt:
	case pcxt_:
		srhash_type = SRHASH_PCXST;
		break;

	case pcxl:
		srhash_type = SRHASH_PCXL;
		break;

	case pcxl2: /* pcxl2 doesn't support space register hashing */
		return;

	default: /* Currently all PA2.0 machines use the same ins. sequence */
		srhash_type = SRHASH_PA20;
		break;
	}

	disable_sr_hashing_asm(srhash_type);

	retval = pdc_spaceid_bits(&space_bits);
	/* If this procedure isn't implemented, don't panic. */
	if (retval < 0 && retval != PDC_BAD_OPTION)
		panic("pdc_spaceid_bits call failed.\n");
	if (space_bits != 0)
		panic("SpaceID hashing is still on!\n");
}

static inline void
__flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
		   unsigned long physaddr)
{
	preempt_disable();
	flush_dcache_page_asm(physaddr, vmaddr);
	if (vma->vm_flags & VM_EXEC)
		flush_icache_page_asm(physaddr, vmaddr);
	preempt_enable();
}

void flush_dcache_page(struct page *page)
{
	struct address_space *mapping = page_mapping(page);
	struct vm_area_struct *mpnt;
	unsigned long offset;
	unsigned long addr, old_addr = 0;
	pgoff_t pgoff;

	if (mapping && !mapping_mapped(mapping)) {
		set_bit(PG_dcache_dirty, &page->flags);
		return;
	}

	flush_kernel_dcache_page(page);

	if (!mapping)
		return;

	pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);

	/* We have carefully arranged in arch_get_unmapped_area() that
	 * *any* mappings of a file are always congruently mapped (whether
	 * declared as MAP_PRIVATE or MAP_SHARED), so we only need
	 * to flush one address here for them all to become coherent */

	flush_dcache_mmap_lock(mapping);
	vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
		offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
		addr = mpnt->vm_start + offset;

		/* The TLB is the engine of coherence on parisc: The
		 * CPU is entitled to speculate any page with a TLB
		 * mapping, so here we kill the mapping then flush the
		 * page along a special flush only alias mapping.
		 * This guarantees that the page is no-longer in the
		 * cache for any process and nor may it be
		 * speculatively read in (until the user or kernel
		 * specifically accesses it, of course) */

		flush_tlb_page(mpnt, addr);
		if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1))
				      != (addr & (SHM_COLOUR - 1))) {
			__flush_cache_page(mpnt, addr, page_to_phys(page));
			if (old_addr)
				printk(KERN_ERR "INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %s\n", old_addr, addr, mpnt->vm_file ? (char *)mpnt->vm_file->f_path.dentry->d_name.name : "(null)");
			old_addr = addr;
		}
	}
	flush_dcache_mmap_unlock(mapping);
}
EXPORT_SYMBOL(flush_dcache_page);

/* Defined in arch/parisc/kernel/pacache.S */
EXPORT_SYMBOL(flush_kernel_dcache_range_asm);
EXPORT_SYMBOL(flush_kernel_dcache_page_asm);
EXPORT_SYMBOL(flush_data_cache_local);
EXPORT_SYMBOL(flush_kernel_icache_range_asm);

#define FLUSH_THRESHOLD 0x80000 /* 0.5MB */
int parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;

void __init parisc_setup_cache_timing(void)
{
	unsigned long rangetime, alltime;
	unsigned long size;

	alltime = mfctl(16);
	flush_data_cache();
	alltime = mfctl(16) - alltime;

	size = (unsigned long)(_end - _text);
	rangetime = mfctl(16);
	flush_kernel_dcache_range((unsigned long)_text, size);
	rangetime = mfctl(16) - rangetime;

	printk(KERN_DEBUG "Whole cache flush %lu cycles, flushing %lu bytes %lu cycles\n",
		alltime, size, rangetime);

	/* Racy, but if we see an intermediate value, it's ok too... */
	parisc_cache_flush_threshold = size * alltime / rangetime;

	parisc_cache_flush_threshold = (parisc_cache_flush_threshold + L1_CACHE_BYTES - 1) &~ (L1_CACHE_BYTES - 1); 
	if (!parisc_cache_flush_threshold)
		parisc_cache_flush_threshold = FLUSH_THRESHOLD;

	if (parisc_cache_flush_threshold > cache_info.dc_size)
		parisc_cache_flush_threshold = cache_info.dc_size;

	printk(KERN_INFO "Setting cache flush threshold to %x (%d CPUs online)\n", parisc_cache_flush_threshold, num_online_cpus());
}

extern void purge_kernel_dcache_page_asm(unsigned long);
extern void clear_user_page_asm(void *, unsigned long);
extern void copy_user_page_asm(void *, void *, unsigned long);

void flush_kernel_dcache_page_addr(void *addr)
{
	unsigned long flags;

	flush_kernel_dcache_page_asm(addr);
	purge_tlb_start(flags);
	pdtlb_kernel(addr);
	purge_tlb_end(flags);
}
EXPORT_SYMBOL(flush_kernel_dcache_page_addr);

void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
	struct page *pg)
{
       /* Copy using kernel mapping.  No coherency is needed (all in
	  kunmap) for the `to' page.  However, the `from' page needs to
	  be flushed through a mapping equivalent to the user mapping
	  before it can be accessed through the kernel mapping. */
	preempt_disable();
	flush_dcache_page_asm(__pa(vfrom), vaddr);
	preempt_enable();
	copy_page_asm(vto, vfrom);
}
EXPORT_SYMBOL(copy_user_page);

void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
{
	unsigned long flags;

	/* Note: purge_tlb_entries can be called at startup with
	   no context.  */

	purge_tlb_start(flags);
	mtsp(mm->context, 1);
	pdtlb(addr);
	pitlb(addr);
	purge_tlb_end(flags);
}
EXPORT_SYMBOL(purge_tlb_entries);

void __flush_tlb_range(unsigned long sid, unsigned long start,
		       unsigned long end)
{
	unsigned long npages;

	npages = ((end - (start & PAGE_MASK)) + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
	if (npages >= 512)  /* 2MB of space: arbitrary, should be tuned */
		flush_tlb_all();
	else {
		unsigned long flags;

		purge_tlb_start(flags);
		mtsp(sid, 1);
		if (split_tlb) {
			while (npages--) {
				pdtlb(start);
				pitlb(start);
				start += PAGE_SIZE;
			}
		} else {
			while (npages--) {
				pdtlb(start);
				start += PAGE_SIZE;
			}
		}
		purge_tlb_end(flags);
	}
}

static void cacheflush_h_tmp_function(void *dummy)
{
	flush_cache_all_local();
}

void flush_cache_all(void)
{
	on_each_cpu(cacheflush_h_tmp_function, NULL, 1);
}

static inline unsigned long mm_total_size(struct mm_struct *mm)
{
	struct vm_area_struct *vma;
	unsigned long usize = 0;

	for (vma = mm->mmap; vma; vma = vma->vm_next)
		usize += vma->vm_end - vma->vm_start;
	return usize;
}

static inline pte_t *get_ptep(pgd_t *pgd, unsigned long addr)
{
	pte_t *ptep = NULL;

	if (!pgd_none(*pgd)) {
		pud_t *pud = pud_offset(pgd, addr);
		if (!pud_none(*pud)) {
			pmd_t *pmd = pmd_offset(pud, addr);
			if (!pmd_none(*pmd))
				ptep = pte_offset_map(pmd, addr);
		}
	}
	return ptep;
}

void flush_cache_mm(struct mm_struct *mm)
{
	struct vm_area_struct *vma;
	pgd_t *pgd;

	/* Flushing the whole cache on each cpu takes forever on
	   rp3440, etc.  So, avoid it if the mm isn't too big.  */
	if (mm_total_size(mm) >= parisc_cache_flush_threshold) {
		flush_cache_all();
		return;
	}

	if (mm->context == mfsp(3)) {
		for (vma = mm->mmap; vma; vma = vma->vm_next) {
			flush_user_dcache_range_asm(vma->vm_start, vma->vm_end);
			if ((vma->vm_flags & VM_EXEC) == 0)
				continue;
			flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
		}
		return;
	}

	pgd = mm->pgd;
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		unsigned long addr;

		for (addr = vma->vm_start; addr < vma->vm_end;
		     addr += PAGE_SIZE) {
			unsigned long pfn;
			pte_t *ptep = get_ptep(pgd, addr);
			if (!ptep)
				continue;
			pfn = pte_pfn(*ptep);
			if (!pfn_valid(pfn))
				continue;
			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
		}
	}
}

void
flush_user_dcache_range(unsigned long start, unsigned long end)
{
	if ((end - start) < parisc_cache_flush_threshold)
		flush_user_dcache_range_asm(start,end);
	else
		flush_data_cache();
}

void
flush_user_icache_range(unsigned long start, unsigned long end)
{
	if ((end - start) < parisc_cache_flush_threshold)
		flush_user_icache_range_asm(start,end);
	else
		flush_instruction_cache();
}

void flush_cache_range(struct vm_area_struct *vma,
		unsigned long start, unsigned long end)
{
	unsigned long addr;
	pgd_t *pgd;

	BUG_ON(!vma->vm_mm->context);

	if ((end - start) >= parisc_cache_flush_threshold) {
		flush_cache_all();
		return;
	}

	if (vma->vm_mm->context == mfsp(3)) {
		flush_user_dcache_range_asm(start, end);
		if (vma->vm_flags & VM_EXEC)
			flush_user_icache_range_asm(start, end);
		return;
	}

	pgd = vma->vm_mm->pgd;
	for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) {
		unsigned long pfn;
		pte_t *ptep = get_ptep(pgd, addr);
		if (!ptep)
			continue;
		pfn = pte_pfn(*ptep);
		if (pfn_valid(pfn))
			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
	}
}

void
flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn)
{
	BUG_ON(!vma->vm_mm->context);

	if (pfn_valid(pfn)) {
		flush_tlb_page(vma, vmaddr);
		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
	}
}