aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/mem.c
blob: be5c506779a74595d8950cfece610f9a378ce220 (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
/*
 *  PowerPC version
 *    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
 *  PPC44x/36-bit changes by Matt Porter (mporter@mvista.com)
 *
 *  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/module.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/stddef.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
#include <linux/initrd.h>
#include <linux/pagemap.h>
#include <linux/suspend.h>

#include <asm/pgalloc.h>
#include <asm/prom.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/smp.h>
#include <asm/machdep.h>
#include <asm/btext.h>
#include <asm/tlb.h>
#include <asm/lmb.h>
#include <asm/sections.h>
#include <asm/vdso.h>

#include "mmu_decl.h"

#ifndef CPU_FTR_COHERENT_ICACHE
#define CPU_FTR_COHERENT_ICACHE	0	/* XXX for now */
#define CPU_FTR_NOEXECUTE	0
#endif

int init_bootmem_done;
int mem_init_done;
unsigned long memory_limit;

int page_is_ram(unsigned long pfn)
{
	unsigned long paddr = (pfn << PAGE_SHIFT);

#ifndef CONFIG_PPC64	/* XXX for now */
	return paddr < __pa(high_memory);
#else
	int i;
	for (i=0; i < lmb.memory.cnt; i++) {
		unsigned long base;

		base = lmb.memory.region[i].base;

		if ((paddr >= base) &&
			(paddr < (base + lmb.memory.region[i].size))) {
			return 1;
		}
	}

	return 0;
#endif
}

pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
			      unsigned long size, pgprot_t vma_prot)
{
	if (ppc_md.phys_mem_access_prot)
		return ppc_md.phys_mem_access_prot(file, pfn, size, vma_prot);

	if (!page_is_ram(pfn))
		vma_prot = __pgprot(pgprot_val(vma_prot)
				    | _PAGE_GUARDED | _PAGE_NO_CACHE);
	return vma_prot;
}
EXPORT_SYMBOL(phys_mem_access_prot);

#ifdef CONFIG_MEMORY_HOTPLUG

void online_page(struct page *page)
{
	ClearPageReserved(page);
	init_page_count(page);
	__free_page(page);
	totalram_pages++;
	num_physpages++;
}

#ifdef CONFIG_NUMA
int memory_add_physaddr_to_nid(u64 start)
{
	return hot_add_scn_to_nid(start);
}
#endif

int __devinit arch_add_memory(int nid, u64 start, u64 size)
{
	struct pglist_data *pgdata;
	struct zone *zone;
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;

	pgdata = NODE_DATA(nid);

	start = (unsigned long)__va(start);
	create_section_mapping(start, start + size);

	/* this should work for most non-highmem platforms */
	zone = pgdata->node_zones;

	return __add_pages(zone, start_pfn, nr_pages);
}

#ifdef CONFIG_MEMORY_HOTREMOVE
int remove_memory(u64 start, u64 size)
{
	unsigned long start_pfn, end_pfn;
	int ret;

	start_pfn = start >> PAGE_SHIFT;
	end_pfn = start_pfn + (size >> PAGE_SHIFT);
	ret = offline_pages(start_pfn, end_pfn, 120 * HZ);
	if (ret)
		goto out;
	/* Arch-specific calls go here - next patch */
out:
	return ret;
}
#endif /* CONFIG_MEMORY_HOTREMOVE */

/*
 * walk_memory_resource() needs to make sure there is no holes in a given
 * memory range. On PPC64, since this range comes from /sysfs, the range
 * is guaranteed to be valid, non-overlapping and can not contain any
 * holes. By the time we get here (memory add or remove), /proc/device-tree
 * is updated and correct. Only reason we need to check against device-tree
 * would be if we allow user-land to specify a memory range through a
 * system call/ioctl etc. instead of doing offline/online through /sysfs.
 */
int
walk_memory_resource(unsigned long start_pfn, unsigned long nr_pages, void *arg,
			int (*func)(unsigned long, unsigned long, void *))
{
	return  (*func)(start_pfn, nr_pages, arg);
}

#endif /* CONFIG_MEMORY_HOTPLUG */

void show_mem(void)
{
	unsigned long total = 0, reserved = 0;
	unsigned long shared = 0, cached = 0;
	unsigned long highmem = 0;
	struct page *page;
	pg_data_t *pgdat;
	unsigned long i;

	printk("Mem-info:\n");
	show_free_areas();
	printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
	for_each_online_pgdat(pgdat) {
		unsigned long flags;
		pgdat_resize_lock(pgdat, &flags);
		for (i = 0; i < pgdat->node_spanned_pages; i++) {
			if (!pfn_valid(pgdat->node_start_pfn + i))
				continue;
			page = pgdat_page_nr(pgdat, i);
			total++;
			if (PageHighMem(page))
				highmem++;
			if (PageReserved(page))
				reserved++;
			else if (PageSwapCache(page))
				cached++;
			else if (page_count(page))
				shared += page_count(page) - 1;
		}
		pgdat_resize_unlock(pgdat, &flags);
	}
	printk("%ld pages of RAM\n", total);
#ifdef CONFIG_HIGHMEM
	printk("%ld pages of HIGHMEM\n", highmem);
#endif
	printk("%ld reserved pages\n", reserved);
	printk("%ld pages shared\n", shared);
	printk("%ld pages swap cached\n", cached);
}

/*
 * Initialize the bootmem system and give it all the memory we
 * have available.  If we are using highmem, we only put the
 * lowmem into the bootmem system.
 */
#ifndef CONFIG_NEED_MULTIPLE_NODES
void __init do_init_bootmem(void)
{
	unsigned long i;
	unsigned long start, bootmap_pages;
	unsigned long total_pages;
	int boot_mapsize;

	max_pfn = total_pages = lmb_end_of_DRAM() >> PAGE_SHIFT;
#ifdef CONFIG_HIGHMEM
	total_pages = total_lowmem >> PAGE_SHIFT;
#endif

	/*
	 * Find an area to use for the bootmem bitmap.  Calculate the size of
	 * bitmap required as (Total Memory) / PAGE_SIZE / BITS_PER_BYTE.
	 * Add 1 additional page in case the address isn't page-aligned.
	 */
	bootmap_pages = bootmem_bootmap_pages(total_pages);

	start = lmb_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE);

	boot_mapsize = init_bootmem(start >> PAGE_SHIFT, total_pages);

	/* Add active regions with valid PFNs */
	for (i = 0; i < lmb.memory.cnt; i++) {
		unsigned long start_pfn, end_pfn;
		start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT;
		end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i);
		add_active_range(0, start_pfn, end_pfn);
	}

	/* Add all physical memory to the bootmem map, mark each area
	 * present.
	 */
#ifdef CONFIG_HIGHMEM
	free_bootmem_with_active_regions(0, total_lowmem >> PAGE_SHIFT);

	/* reserve the sections we're already using */
	for (i = 0; i < lmb.reserved.cnt; i++) {
		unsigned long addr = lmb.reserved.region[i].base +
				     lmb_size_bytes(&lmb.reserved, i) - 1;
		if (addr < total_lowmem)
			reserve_bootmem(lmb.reserved.region[i].base,
					lmb_size_bytes(&lmb.reserved, i),
					BOOTMEM_DEFAULT);
		else if (lmb.reserved.region[i].base < total_lowmem) {
			unsigned long adjusted_size = total_lowmem -
				      lmb.reserved.region[i].base;
			reserve_bootmem(lmb.reserved.region[i].base,
					adjusted_size, BOOTMEM_DEFAULT);
		}
	}
#else
	free_bootmem_with_active_regions(0, max_pfn);

	/* reserve the sections we're already using */
	for (i = 0; i < lmb.reserved.cnt; i++)
		reserve_bootmem(lmb.reserved.region[i].base,
				lmb_size_bytes(&lmb.reserved, i),
				BOOTMEM_DEFAULT);

#endif
	/* XXX need to clip this if using highmem? */
	sparse_memory_present_with_active_regions(0);

	init_bootmem_done = 1;
}

/* mark pages that don't exist as nosave */
static int __init mark_nonram_nosave(void)
{
	unsigned long lmb_next_region_start_pfn,
		      lmb_region_max_pfn;
	int i;

	for (i = 0; i < lmb.memory.cnt - 1; i++) {
		lmb_region_max_pfn =
			(lmb.memory.region[i].base >> PAGE_SHIFT) +
			(lmb.memory.region[i].size >> PAGE_SHIFT);
		lmb_next_region_start_pfn =
			lmb.memory.region[i+1].base >> PAGE_SHIFT;

		if (lmb_region_max_pfn < lmb_next_region_start_pfn)
			register_nosave_region(lmb_region_max_pfn,
					       lmb_next_region_start_pfn);
	}

	return 0;
}

/*
 * paging_init() sets up the page tables - in fact we've already done this.
 */
void __init paging_init(void)
{
	unsigned long total_ram = lmb_phys_mem_size();
	unsigned long top_of_ram = lmb_end_of_DRAM();
	unsigned long max_zone_pfns[MAX_NR_ZONES];

#ifdef CONFIG_HIGHMEM
	map_page(PKMAP_BASE, 0, 0);	/* XXX gross */
	pkmap_page_table = pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k
			(PKMAP_BASE), PKMAP_BASE), PKMAP_BASE), PKMAP_BASE);
	map_page(KMAP_FIX_BEGIN, 0, 0);	/* XXX gross */
	kmap_pte = pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k
			(KMAP_FIX_BEGIN), KMAP_FIX_BEGIN), KMAP_FIX_BEGIN),
			 KMAP_FIX_BEGIN);
	kmap_prot = PAGE_KERNEL;
#endif /* CONFIG_HIGHMEM */

	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
	       top_of_ram, total_ram);
	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
	       (top_of_ram - total_ram) >> 20);
	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
#ifdef CONFIG_HIGHMEM
	max_zone_pfns[ZONE_DMA] = total_lowmem >> PAGE_SHIFT;
	max_zone_pfns[ZONE_HIGHMEM] = top_of_ram >> PAGE_SHIFT;
#else
	max_zone_pfns[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
#endif
	free_area_init_nodes(max_zone_pfns);

	mark_nonram_nosave();
}
#endif /* ! CONFIG_NEED_MULTIPLE_NODES */

void __init mem_init(void)
{
#ifdef CONFIG_NEED_MULTIPLE_NODES
	int nid;
#endif
	pg_data_t *pgdat;
	unsigned long i;
	struct page *page;
	unsigned long reservedpages = 0, codesize, initsize, datasize, bsssize;

	num_physpages = lmb.memory.size >> PAGE_SHIFT;
	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);

#ifdef CONFIG_NEED_MULTIPLE_NODES
        for_each_online_node(nid) {
		if (NODE_DATA(nid)->node_spanned_pages != 0) {
			printk("freeing bootmem node %d\n", nid);
			totalram_pages +=
				free_all_bootmem_node(NODE_DATA(nid));
		}
	}
#else
	max_mapnr = max_pfn;
	totalram_pages += free_all_bootmem();
#endif
	for_each_online_pgdat(pgdat) {
		for (i = 0; i < pgdat->node_spanned_pages; i++) {
			if (!pfn_valid(pgdat->node_start_pfn + i))
				continue;
			page = pgdat_page_nr(pgdat, i);
			if (PageReserved(page))
				reservedpages++;
		}
	}

	codesize = (unsigned long)&_sdata - (unsigned long)&_stext;
	datasize = (unsigned long)&_edata - (unsigned long)&_sdata;
	initsize = (unsigned long)&__init_end - (unsigned long)&__init_begin;
	bsssize = (unsigned long)&__bss_stop - (unsigned long)&__bss_start;

#ifdef CONFIG_HIGHMEM
	{
		unsigned long pfn, highmem_mapnr;

		highmem_mapnr = total_lowmem >> PAGE_SHIFT;
		for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) {
			struct page *page = pfn_to_page(pfn);
			if (lmb_is_reserved(pfn << PAGE_SHIFT))
				continue;
			ClearPageReserved(page);
			init_page_count(page);
			__free_page(page);
			totalhigh_pages++;
			reservedpages--;
		}
		totalram_pages += totalhigh_pages;
		printk(KERN_DEBUG "High memory: %luk\n",
		       totalhigh_pages << (PAGE_SHIFT-10));
	}
#endif /* CONFIG_HIGHMEM */

	printk(KERN_INFO "Memory: %luk/%luk available (%luk kernel code, "
	       "%luk reserved, %luk data, %luk bss, %luk init)\n",
		(unsigned long)nr_free_pages() << (PAGE_SHIFT-10),
		num_physpages << (PAGE_SHIFT-10),
		codesize >> 10,
		reservedpages << (PAGE_SHIFT-10),
		datasize >> 10,
		bsssize >> 10,
		initsize >> 10);

	mem_init_done = 1;
}

/*
 * This is called when a page has been modified by the kernel.
 * It just marks the page as not i-cache clean.  We do the i-cache
 * flush later when the page is given to a user process, if necessary.
 */
void flush_dcache_page(struct page *page)
{
	if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
		return;
	/* avoid an atomic op if possible */
	if (test_bit(PG_arch_1, &page->flags))
		clear_bit(PG_arch_1, &page->flags);
}
EXPORT_SYMBOL(flush_dcache_page);

void flush_dcache_icache_page(struct page *page)
{
#ifdef CONFIG_BOOKE
	void *start = kmap_atomic(page, KM_PPC_SYNC_ICACHE);
	__flush_dcache_icache(start);
	kunmap_atomic(start, KM_PPC_SYNC_ICACHE);
#elif defined(CONFIG_8xx) || defined(CONFIG_PPC64)
	/* On 8xx there is no need to kmap since highmem is not supported */
	__flush_dcache_icache(page_address(page)); 
#else
	__flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT);
#endif

}
void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
{
	clear_page(page);

	/*
	 * We shouldnt have to do this, but some versions of glibc
	 * require it (ld.so assumes zero filled pages are icache clean)
	 * - Anton
	 */
	flush_dcache_page(pg);
}
EXPORT_SYMBOL(clear_user_page);

void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
		    struct page *pg)
{
	copy_page(vto, vfrom);

	/*
	 * We should be able to use the following optimisation, however
	 * there are two problems.
	 * Firstly a bug in some versions of binutils meant PLT sections
	 * were not marked executable.
	 * Secondly the first word in the GOT section is blrl, used
	 * to establish the GOT address. Until recently the GOT was
	 * not marked executable.
	 * - Anton
	 */
#if 0
	if (!vma->vm_file && ((vma->vm_flags & VM_EXEC) == 0))
		return;
#endif

	flush_dcache_page(pg);
}

void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
			     unsigned long addr, int len)
{
	unsigned long maddr;

	maddr = (unsigned long) kmap(page) + (addr & ~PAGE_MASK);
	flush_icache_range(maddr, maddr + len);
	kunmap(page);
}
EXPORT_SYMBOL(flush_icache_user_range);

/*
 * This is called at the end of handling a user page fault, when the
 * fault has been handled by updating a PTE in the linux page tables.
 * We use it to preload an HPTE into the hash table corresponding to
 * the updated linux PTE.
 * 
 * This must always be called with the pte lock held.
 */
void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
		      pte_t pte)
{
#ifdef CONFIG_PPC_STD_MMU
	unsigned long access = 0, trap;
#endif
	unsigned long pfn = pte_pfn(pte);

	/* handle i-cache coherency */
	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE) &&
	    !cpu_has_feature(CPU_FTR_NOEXECUTE) &&
	    pfn_valid(pfn)) {
		struct page *page = pfn_to_page(pfn);
#ifdef CONFIG_8xx
		/* On 8xx, cache control instructions (particularly
		 * "dcbst" from flush_dcache_icache) fault as write
		 * operation if there is an unpopulated TLB entry
		 * for the address in question. To workaround that,
		 * we invalidate the TLB here, thus avoiding dcbst
		 * misbehaviour.
		 */
		_tlbie(address, 0 /* 8xx doesn't care about PID */);
#endif
		/* The _PAGE_USER test should really be _PAGE_EXEC, but
		 * older glibc versions execute some code from no-exec
		 * pages, which for now we are supporting.  If exec-only
		 * pages are ever implemented, this will have to change.
		 */
		if (!PageReserved(page) && (pte_val(pte) & _PAGE_USER)
		    && !test_bit(PG_arch_1, &page->flags)) {
			if (vma->vm_mm == current->active_mm) {
				__flush_dcache_icache((void *) address);
			} else
				flush_dcache_icache_page(page);
			set_bit(PG_arch_1, &page->flags);
		}
	}

#ifdef CONFIG_PPC_STD_MMU
	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
	if (!pte_young(pte) || address >= TASK_SIZE)
		return;

	/* We try to figure out if we are coming from an instruction
	 * access fault and pass that down to __hash_page so we avoid
	 * double-faulting on execution of fresh text. We have to test
	 * for regs NULL since init will get here first thing at boot
	 *
	 * We also avoid filling the hash if not coming from a fault
	 */
	if (current->thread.regs == NULL)
		return;
	trap = TRAP(current->thread.regs);
	if (trap == 0x400)
		access |= _PAGE_EXEC;
	else if (trap != 0x300)
		return;
	hash_preload(vma->vm_mm, address, access, trap);
#endif /* CONFIG_PPC_STD_MMU */
}