summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/init64.c
blob: 81f6745b31efd91b152f98c2d7629e93af52b648 (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
/*
 *  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
 *  Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk).
 *
 *  Derived from "arch/i386/mm/init.c"
 *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Dave Engebretsen <engebret@us.ibm.com>
 *      Rework for PPC64 port.
 *
 *  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/config.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/stddef.h>
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
#include <linux/idr.h>
#include <linux/nodemask.h>
#include <linux/module.h>

#include <asm/pgalloc.h>
#include <asm/page.h>
#include <asm/prom.h>
#include <asm/lmb.h>
#include <asm/rtas.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/uaccess.h>
#include <asm/smp.h>
#include <asm/machdep.h>
#include <asm/tlb.h>
#include <asm/eeh.h>
#include <asm/processor.h>
#include <asm/mmzone.h>
#include <asm/cputable.h>
#include <asm/ppcdebug.h>
#include <asm/sections.h>
#include <asm/system.h>
#include <asm/iommu.h>
#include <asm/abs_addr.h>
#include <asm/vdso.h>
#include <asm/imalloc.h>

#if PGTABLE_RANGE > USER_VSID_RANGE
#warning Limited user VSID range means pagetable space is wasted
#endif

#if (TASK_SIZE_USER64 < PGTABLE_RANGE) && (TASK_SIZE_USER64 < USER_VSID_RANGE)
#warning TASK_SIZE is smaller than it needs to be.
#endif

int mem_init_done;
unsigned long ioremap_bot = IMALLOC_BASE;
static unsigned long phbs_io_bot = PHBS_IO_BASE;

extern pgd_t swapper_pg_dir[];
extern struct task_struct *current_set[NR_CPUS];

unsigned long klimit = (unsigned long)_end;

unsigned long _SDR1=0;
unsigned long _ASR=0;

/* max amount of RAM to use */
unsigned long __max_memory;

/* info on what we think the IO hole is */
unsigned long 	io_hole_start;
unsigned long	io_hole_size;

/*
 * Do very early mm setup.
 */
void __init mm_init_ppc64(void)
{
#ifndef CONFIG_PPC_ISERIES
	unsigned long i;
#endif

	ppc64_boot_msg(0x100, "MM Init");

	/* This is the story of the IO hole... please, keep seated,
	 * unfortunately, we are out of oxygen masks at the moment.
	 * So we need some rough way to tell where your big IO hole
	 * is. On pmac, it's between 2G and 4G, on POWER3, it's around
	 * that area as well, on POWER4 we don't have one, etc...
	 * We need that as a "hint" when sizing the TCE table on POWER3
	 * So far, the simplest way that seem work well enough for us it
	 * to just assume that the first discontinuity in our physical
	 * RAM layout is the IO hole. That may not be correct in the future
	 * (and isn't on iSeries but then we don't care ;)
	 */

#ifndef CONFIG_PPC_ISERIES
	for (i = 1; i < lmb.memory.cnt; i++) {
		unsigned long base, prevbase, prevsize;

		prevbase = lmb.memory.region[i-1].base;
		prevsize = lmb.memory.region[i-1].size;
		base = lmb.memory.region[i].base;
		if (base > (prevbase + prevsize)) {
			io_hole_start = prevbase + prevsize;
			io_hole_size = base  - (prevbase + prevsize);
			break;
		}
	}
#endif /* CONFIG_PPC_ISERIES */
	if (io_hole_start)
		printk("IO Hole assumed to be %lx -> %lx\n",
		       io_hole_start, io_hole_start + io_hole_size - 1);

	ppc64_boot_msg(0x100, "MM Init Done");
}

void free_initmem(void)
{
	unsigned long addr;

	addr = (unsigned long)__init_begin;
	for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) {
		memset((void *)addr, 0xcc, PAGE_SIZE);
		ClearPageReserved(virt_to_page(addr));
		set_page_count(virt_to_page(addr), 1);
		free_page(addr);
		totalram_pages++;
	}
	printk ("Freeing unused kernel memory: %luk freed\n",
		((unsigned long)__init_end - (unsigned long)__init_begin) >> 10);
}

#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
	if (start < end)
		printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
	for (; start < end; start += PAGE_SIZE) {
		ClearPageReserved(virt_to_page(start));
		set_page_count(virt_to_page(start), 1);
		free_page(start);
		totalram_pages++;
	}
}
#endif

/*
 * Initialize the bootmem system and give it all the memory we
 * have available.
 */
#ifndef CONFIG_NEED_MULTIPLE_NODES
void __init do_init_bootmem(void)
{
	unsigned long i;
	unsigned long start, bootmap_pages;
	unsigned long total_pages = lmb_end_of_DRAM() >> PAGE_SHIFT;
	int boot_mapsize;

	/*
	 * 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);
	BUG_ON(!start);

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

	max_pfn = max_low_pfn;

	/* Add all physical memory to the bootmem map, mark each area
	 * present.
	 */
	for (i=0; i < lmb.memory.cnt; i++)
		free_bootmem(lmb.memory.region[i].base,
			     lmb_size_bytes(&lmb.memory, i));

	/* 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));

	for (i=0; i < lmb.memory.cnt; i++)
		memory_present(0, lmb_start_pfn(&lmb.memory, i),
			       lmb_end_pfn(&lmb.memory, i));
}

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

	printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
	       top_of_ram, total_ram);
	printk(KERN_INFO "Memory hole size: %ldMB\n",
	       (top_of_ram - total_ram) >> 20);
	/*
	 * All pages are DMA-able so we put them all in the DMA zone.
	 */
	memset(zones_size, 0, sizeof(zones_size));
	memset(zholes_size, 0, sizeof(zholes_size));

	zones_size[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
	zholes_size[ZONE_DMA] = (top_of_ram - total_ram) >> PAGE_SHIFT;

	free_area_init_node(0, NODE_DATA(0), zones_size,
			    __pa(PAGE_OFFSET) >> PAGE_SHIFT, zholes_size);
}
#endif /* ! CONFIG_NEED_MULTIPLE_NODES */

static struct kcore_list kcore_vmem;

static int __init setup_kcore(void)
{
	int i;

	for (i=0; i < lmb.memory.cnt; i++) {
		unsigned long base, size;
		struct kcore_list *kcore_mem;

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

		/* GFP_ATOMIC to avoid might_sleep warnings during boot */
		kcore_mem = kmalloc(sizeof(struct kcore_list), GFP_ATOMIC);
		if (!kcore_mem)
			panic("mem_init: kmalloc failed\n");

		kclist_add(kcore_mem, __va(base), size);
	}

	kclist_add(&kcore_vmem, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START);

	return 0;
}
module_init(setup_kcore);

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 = max_low_pfn;	/* RAM is assumed contiguous */
	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 %x\n", nid);
			totalram_pages +=
				free_all_bootmem_node(NODE_DATA(nid));
		}
	}
#else
	max_mapnr = num_physpages;
	totalram_pages += free_all_bootmem();
#endif

	for_each_pgdat(pgdat) {
		for (i = 0; i < pgdat->node_spanned_pages; i++) {
			page = pgdat_page_nr(pgdat, i);
			if (PageReserved(page))
				reservedpages++;
		}
	}

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

	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;

	/* Initialize the vDSO */
	vdso_init();
}

void __iomem * reserve_phb_iospace(unsigned long size)
{
	void __iomem *virt_addr;
		
	if (phbs_io_bot >= IMALLOC_BASE) 
		panic("reserve_phb_iospace(): phb io space overflow\n");
			
	virt_addr = (void __iomem *) phbs_io_bot;
	phbs_io_bot += size;

	return virt_addr;
}

static void zero_ctor(void *addr, kmem_cache_t *cache, unsigned long flags)
{
	memset(addr, 0, kmem_cache_size(cache));
}

static const int pgtable_cache_size[2] = {
	PTE_TABLE_SIZE, PMD_TABLE_SIZE
};
static const char *pgtable_cache_name[ARRAY_SIZE(pgtable_cache_size)] = {
	"pgd_pte_cache", "pud_pmd_cache",
};

kmem_cache_t *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)];

void pgtable_cache_init(void)
{
	int i;

	BUILD_BUG_ON(PTE_TABLE_SIZE != pgtable_cache_size[PTE_CACHE_NUM]);
	BUILD_BUG_ON(PMD_TABLE_SIZE != pgtable_cache_size[PMD_CACHE_NUM]);
	BUILD_BUG_ON(PUD_TABLE_SIZE != pgtable_cache_size[PUD_CACHE_NUM]);
	BUILD_BUG_ON(PGD_TABLE_SIZE != pgtable_cache_size[PGD_CACHE_NUM]);

	for (i = 0; i < ARRAY_SIZE(pgtable_cache_size); i++) {
		int size = pgtable_cache_size[i];
		const char *name = pgtable_cache_name[i];

		pgtable_cache[i] = kmem_cache_create(name,
						     size, size,
						     SLAB_HWCACHE_ALIGN
						     | SLAB_MUST_HWCACHE_ALIGN,
						     zero_ctor,
						     NULL);
		if (! pgtable_cache[i])
			panic("pgtable_cache_init(): could not create %s!\n",
			      name);
	}
}

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

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