[deliverable/linux.git] / arch / powerpc / mm / init_64.c

/*
 *  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
 *
 *  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/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 <linux/poison.h>
#include <linux/lmb.h>

#include <asm/pgalloc.h>
#include <asm/page.h>
#include <asm/prom.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/sections.h>
#include <asm/system.h>
#include <asm/iommu.h>
#include <asm/abs_addr.h>
#include <asm/vdso.h>

#include "mmu_decl.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

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

void free_initmem(void)
{
	unsigned long addr;

	addr = (unsigned long)__init_begin;
	for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) {
		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
		ClearPageReserved(virt_to_page(addr));
		init_page_count(virt_to_page(addr));
		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));
		init_page_count(virt_to_page(start));
		free_page(start);
		totalram_pages++;
	}
}
#endif

#ifdef CONFIG_PROC_KCORE
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("%s: kmalloc failed\n", __func__);

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

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

	return 0;
}
module_init(setup_kcore);
#endif

static void zero_ctor(struct kmem_cache *cache, void *addr)
{
	memset(addr, 0, kmem_cache_size(cache));
}

static const unsigned int pgtable_cache_size[2] = {
	PGD_TABLE_SIZE, PMD_TABLE_SIZE
};
static const char *pgtable_cache_name[ARRAY_SIZE(pgtable_cache_size)] = {
#ifdef CONFIG_PPC_64K_PAGES
	"pgd_cache", "pmd_cache",
#else
	"pgd_cache", "pud_pmd_cache",
#endif /* CONFIG_PPC_64K_PAGES */
};

#ifdef CONFIG_HUGETLB_PAGE
/* Hugepages need one extra cache, initialized in hugetlbpage.c.  We
 * can't put into the tables above, because HPAGE_SHIFT is not compile
 * time constant. */
struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)+1];
#else
struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)];
#endif

void pgtable_cache_init(void)
{
	int i;

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

		pr_debug("Allocating page table cache %s (#%d) "
			"for size: %08x...\n", name, i, size);
		pgtable_cache[i] = kmem_cache_create(name,
						     size, size,
						     SLAB_PANIC,
						     zero_ctor);
	}
}

#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
 * Given an address within the vmemmap, determine the pfn of the page that
 * represents the start of the section it is within.  Note that we have to
 * do this by hand as the proffered address may not be correctly aligned.
 * Subtraction of non-aligned pointers produces undefined results.
 */
unsigned long __meminit vmemmap_section_start(unsigned long page)
{
	unsigned long offset = page - ((unsigned long)(vmemmap));

	/* Return the pfn of the start of the section. */
	return (offset / sizeof(struct page)) & PAGE_SECTION_MASK;
}

/*
 * Check if this vmemmap page is already initialised.  If any section
 * which overlaps this vmemmap page is initialised then this page is
 * initialised already.
 */
int __meminit vmemmap_populated(unsigned long start, int page_size)
{
	unsigned long end = start + page_size;

	for (; start < end; start += (PAGES_PER_SECTION * sizeof(struct page)))
		if (pfn_valid(vmemmap_section_start(start)))
			return 1;

	return 0;
}

int __meminit vmemmap_populate(struct page *start_page,
					unsigned long nr_pages, int node)
{
	unsigned long mode_rw;
	unsigned long start = (unsigned long)start_page;
	unsigned long end = (unsigned long)(start_page + nr_pages);
	unsigned long page_size = 1 << mmu_psize_defs[mmu_linear_psize].shift;

	mode_rw = _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX;

	/* Align to the page size of the linear mapping. */
	start = _ALIGN_DOWN(start, page_size);

	for (; start < end; start += page_size) {
		int mapped;
		void *p;

		if (vmemmap_populated(start, page_size))
			continue;

		p = vmemmap_alloc_block(page_size, node);
		if (!p)
			return -ENOMEM;

		pr_debug("vmemmap %08lx allocated at %p, physical %08lx.\n",
			start, p, __pa(p));

		mapped = htab_bolt_mapping(start, start + page_size,
					__pa(p), mode_rw, mmu_linear_psize,
					mmu_kernel_ssize);
		BUG_ON(mapped < 0);
	}

	return 0;
}
#endif
Commit	Line	Data
14cf11af PM	1	/*
	2	* PowerPC version
	3	* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
	4	*
	5	* Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
	6	* and Cort Dougan (PReP) (cort@cs.nmt.edu)
	7	* Copyright (C) 1996 Paul Mackerras
14cf11af PM	8	*
	9	* Derived from "arch/i386/mm/init.c"
	10	* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
	11	*
	12	* Dave Engebretsen <engebret@us.ibm.com>
	13	* Rework for PPC64 port.
	14	*
	15	* This program is free software; you can redistribute it and/or
	16	* modify it under the terms of the GNU General Public License
	17	* as published by the Free Software Foundation; either version
	18	* 2 of the License, or (at your option) any later version.
	19	*
	20	*/
	21
14cf11af PM	22	#include <linux/signal.h>
	23	#include <linux/sched.h>
	24	#include <linux/kernel.h>
	25	#include <linux/errno.h>
	26	#include <linux/string.h>
	27	#include <linux/types.h>
	28	#include <linux/mman.h>
	29	#include <linux/mm.h>
	30	#include <linux/swap.h>
	31	#include <linux/stddef.h>
	32	#include <linux/vmalloc.h>
	33	#include <linux/init.h>
	34	#include <linux/delay.h>
	35	#include <linux/bootmem.h>
	36	#include <linux/highmem.h>
	37	#include <linux/idr.h>
	38	#include <linux/nodemask.h>
	39	#include <linux/module.h>
c9cf5528	40	#include <linux/poison.h>
d9b2b2a2	41	#include <linux/lmb.h>
14cf11af PM	42
	43	#include <asm/pgalloc.h>
	44	#include <asm/page.h>
	45	#include <asm/prom.h>
14cf11af PM	46	#include <asm/rtas.h>
	47	#include <asm/io.h>
	48	#include <asm/mmu_context.h>
	49	#include <asm/pgtable.h>
	50	#include <asm/mmu.h>
	51	#include <asm/uaccess.h>
	52	#include <asm/smp.h>
	53	#include <asm/machdep.h>
	54	#include <asm/tlb.h>
	55	#include <asm/eeh.h>
	56	#include <asm/processor.h>
	57	#include <asm/mmzone.h>
	58	#include <asm/cputable.h>
14cf11af PM	59	#include <asm/sections.h>
	60	#include <asm/system.h>
	61	#include <asm/iommu.h>
	62	#include <asm/abs_addr.h>
	63	#include <asm/vdso.h>
800fc3ee DG	64
800fc3ee DG	65	#include "mmu_decl.h"
14cf11af PM	66
	67	#if PGTABLE_RANGE > USER_VSID_RANGE
	68	#warning Limited user VSID range means pagetable space is wasted
	69	#endif
	70
	71	#if (TASK_SIZE_USER64 < PGTABLE_RANGE) && (TASK_SIZE_USER64 < USER_VSID_RANGE)
	72	#warning TASK_SIZE is smaller than it needs to be.
	73	#endif
	74
14cf11af PM	75	/* max amount of RAM to use */
	76	unsigned long __max_memory;
	77
14cf11af PM	78	void free_initmem(void)
	79	{
	80	unsigned long addr;
	81
	82	addr = (unsigned long)__init_begin;
	83	for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) {
c9cf5528	84	memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
14cf11af	85	ClearPageReserved(virt_to_page(addr));
7835e98b	86	init_page_count(virt_to_page(addr));
14cf11af PM	87	free_page(addr);
	88	totalram_pages++;
	89	}
	90	printk ("Freeing unused kernel memory: %luk freed\n",
	91	((unsigned long)__init_end - (unsigned long)__init_begin) >> 10);
	92	}
	93
	94	#ifdef CONFIG_BLK_DEV_INITRD
	95	void free_initrd_mem(unsigned long start, unsigned long end)
	96	{
	97	if (start < end)
	98	printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
	99	for (; start < end; start += PAGE_SIZE) {
	100	ClearPageReserved(virt_to_page(start));
7835e98b	101	init_page_count(virt_to_page(start));
14cf11af PM	102	free_page(start);
	103	totalram_pages++;
	104	}
	105	}
	106	#endif
	107
df174e3b	108	#ifdef CONFIG_PROC_KCORE
14cf11af PM	109	static struct kcore_list kcore_vmem;
	110
	111	static int __init setup_kcore(void)
	112	{
	113	int i;
	114
	115	for (i=0; i < lmb.memory.cnt; i++) {
	116	unsigned long base, size;
	117	struct kcore_list *kcore_mem;
	118
	119	base = lmb.memory.region[i].base;
	120	size = lmb.memory.region[i].size;
	121
	122	/* GFP_ATOMIC to avoid might_sleep warnings during boot */
	123	kcore_mem = kmalloc(sizeof(struct kcore_list), GFP_ATOMIC);
	124	if (!kcore_mem)
e48b1b45	125	panic("%s: kmalloc failed\n", __func__);
14cf11af PM	126
	127	kclist_add(kcore_mem, __va(base), size);
	128	}
	129
	130	kclist_add(&kcore_vmem, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START);
	131
	132	return 0;
	133	}
	134	module_init(setup_kcore);
df174e3b	135	#endif
14cf11af	136
4ba9b9d0	137	static void zero_ctor(struct kmem_cache cache, void addr)
14cf11af PM	138	{
	139	memset(addr, 0, kmem_cache_size(cache));
	140	}
	141
87655ff2	142	static const unsigned int pgtable_cache_size[2] = {
517e2263	143	PGD_TABLE_SIZE, PMD_TABLE_SIZE
14cf11af PM	144	};
14cf11af PM	145	static const char *pgtable_cache_name[ARRAY_SIZE(pgtable_cache_size)] = {
517e2263 HD	146	#ifdef CONFIG_PPC_64K_PAGES
	147	"pgd_cache", "pmd_cache",
	148	#else
	149	"pgd_cache", "pud_pmd_cache",
3c726f8d	150	#endif /* CONFIG_PPC_64K_PAGES */
517e2263	151	};
14cf11af	152
f10a04c0 DG	153	#ifdef CONFIG_HUGETLB_PAGE
	154	/* Hugepages need one extra cache, initialized in hugetlbpage.c. We
	155	* can't put into the tables above, because HPAGE_SHIFT is not compile
	156	* time constant. */
e18b890b	157	struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)+1];
f10a04c0	158	#else
e18b890b	159	struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)];
f10a04c0	160	#endif
14cf11af PM	161
	162	void pgtable_cache_init(void)
	163	{
	164	int i;
	165
14cf11af PM	166	for (i = 0; i < ARRAY_SIZE(pgtable_cache_size); i++) {
	167	int size = pgtable_cache_size[i];
	168	const char *name = pgtable_cache_name[i];
	169
6548d83a SR	170	pr_debug("Allocating page table cache %s (#%d) "
6548d83a SR	171	"for size: %08x...\n", name, i, size);
14cf11af PM	172	pgtable_cache[i] = kmem_cache_create(name,
14cf11af PM	173	size, size,
0e6b9c98	174	SLAB_PANIC,
20c2df83	175	zero_ctor);
14cf11af PM	176	}
14cf11af PM	177	}
d29eff7b AW	178
	179	#ifdef CONFIG_SPARSEMEM_VMEMMAP
	180	/*
	181	* Given an address within the vmemmap, determine the pfn of the page that
	182	* represents the start of the section it is within. Note that we have to
	183	* do this by hand as the proffered address may not be correctly aligned.
	184	* Subtraction of non-aligned pointers produces undefined results.
	185	*/
	186	unsigned long __meminit vmemmap_section_start(unsigned long page)
	187	{
	188	unsigned long offset = page - ((unsigned long)(vmemmap));
	189
	190	/* Return the pfn of the start of the section. */
	191	return (offset / sizeof(struct page)) & PAGE_SECTION_MASK;
	192	}
	193
	194	/*
	195	* Check if this vmemmap page is already initialised. If any section
	196	* which overlaps this vmemmap page is initialised then this page is
	197	* initialised already.
	198	*/
	199	int __meminit vmemmap_populated(unsigned long start, int page_size)
	200	{
	201	unsigned long end = start + page_size;
	202
	203	for (; start < end; start += (PAGES_PER_SECTION * sizeof(struct page)))
	204	if (pfn_valid(vmemmap_section_start(start)))
	205	return 1;
	206
	207	return 0;
	208	}
	209
	210	int __meminit vmemmap_populate(struct page *start_page,
	211	unsigned long nr_pages, int node)
	212	{
	213	unsigned long mode_rw;
	214	unsigned long start = (unsigned long)start_page;
	215	unsigned long end = (unsigned long)(start_page + nr_pages);
	216	unsigned long page_size = 1 << mmu_psize_defs[mmu_linear_psize].shift;
	217
	218	mode_rw = _PAGE_ACCESSED \| _PAGE_DIRTY \| _PAGE_COHERENT \| PP_RWXX;
	219
	220	/* Align to the page size of the linear mapping. */
	221	start = _ALIGN_DOWN(start, page_size);
	222
	223	for (; start < end; start += page_size) {
	224	int mapped;
	225	void *p;
	226
	227	if (vmemmap_populated(start, page_size))
	228	continue;
	229
	230	p = vmemmap_alloc_block(page_size, node);
	231	if (!p)
	232	return -ENOMEM;
	233
6548d83a SR	234	pr_debug("vmemmap %08lx allocated at %p, physical %08lx.\n",
6548d83a SR	235	start, p, __pa(p));
d29eff7b AW	236
d29eff7b AW	237	mapped = htab_bolt_mapping(start, start + page_size,
e95206ab AB	238	__pa(p), mode_rw, mmu_linear_psize,
e95206ab AB	239	mmu_kernel_ssize);
d29eff7b AW	240	BUG_ON(mapped < 0);
	241	}
	242
	243	return 0;
	244	}
	245	#endif