Release 4.8 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.
 *
 */


#undef DEBUG

#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/highmem.h>
#include <linux/idr.h>
#include <linux/nodemask.h>
#include <linux/module.h>
#include <linux/poison.h>
#include <linux/memblock.h>
#include <linux/hugetlb.h>
#include <linux/slab.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/iommu.h>
#include <asm/vdso.h>

#include "mmu_decl.h"

#ifdef CONFIG_PPC_STD_MMU_64
#if H_PGTABLE_RANGE > USER_VSID_RANGE
#warning Limited user VSID range means pagetable space is wasted
#endif

#if (TASK_SIZE_USER64 < H_PGTABLE_RANGE) && (TASK_SIZE_USER64 < USER_VSID_RANGE)
#warning TASK_SIZE is smaller than it needs to be.
#endif
#endif /* CONFIG_PPC_STD_MMU_64 */


phys_addr_t memstart_addr = ~0;

EXPORT_SYMBOL_GPL(memstart_addr);

phys_addr_t kernstart_addr;

EXPORT_SYMBOL_GPL(kernstart_addr);



static void pgd_ctor(void *addr)
{
	memset(addr, 0, PGD_TABLE_SIZE);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
paul mackerras
paul mackerras
12
63.16%
1
33.33%
alexey dobriyan
alexey dobriyan
4
21.05%
1
33.33%
christoph lameter
christoph lameter
3
15.79%
1
33.33%
Total
19
100.00%
3
100.00%



static void pud_ctor(void *addr)
{
	memset(addr, 0, PUD_TABLE_SIZE);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
aneesh kumar
aneesh kumar
19
100.00%
1
100.00%
Total
19
100.00%
1
100.00%



static void pmd_ctor(void *addr)
{
	memset(addr, 0, PMD_TABLE_SIZE);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
alexey dobriyan
alexey dobriyan
9
47.37%
1
33.33%
aneesh kumar
aneesh kumar
9
47.37%
1
33.33%
paul mackerras
paul mackerras
1
5.26%
1
33.33%
Total
19
100.00%
3
100.00%


struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];

/*
 * Create a kmem_cache() for pagetables.  This is not used for PTE
 * pages - they're linked to struct page, come from the normal free
 * pages pool and have a different entry size (see real_pte_t) to
 * everything else.  Caches created by this function are used for all
 * the higher level pagetables, and for hugepage pagetables.
 */


void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
{
	char *name;
	unsigned long table_size = sizeof(void *) << shift;
	unsigned long align = table_size;

	/* When batching pgtable pointers for RCU freeing, we store
         * the index size in the low bits.  Table alignment must be
         * big enough to fit it.
         *
         * Likewise, hugeapge pagetable pointers contain a (different)
         * shift value in the low bits.  All tables must be aligned so
         * as to leave enough 0 bits in the address to contain it. */
	unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
				     HUGEPD_SHIFT_MASK + 1);
	struct kmem_cache *new;

	/* It would be nice if this was a BUILD_BUG_ON(), but at the
         * moment, gcc doesn't seem to recognize is_power_of_2 as a
         * constant expression, so so much for that. */
	BUG_ON(!is_power_of_2(minalign));
	BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE));

	if (PGT_CACHE(shift))
		return; /* Already have a cache of this size */

	align = max_t(unsigned long, align, minalign);
	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
	new = kmem_cache_create(name, table_size, align, 0, ctor);
	kfree(name);
	pgtable_cache[shift - 1] = new;
	pr_debug("Allocated pgtable cache for order %d\n", shift);
}


Contributors
Person
Tokens
Prop
Commits
CommitProp
david gibson
david gibson
123
80.39%
3
33.33%
paul mackerras
paul mackerras
10
6.54%
1
11.11%
yanjiang jin
yanjiang jin
5
3.27%
1
11.11%
benjamin herrenschmidt
benjamin herrenschmidt
5
3.27%
1
11.11%
aneesh kumar
aneesh kumar
5
3.27%
1
11.11%
alexey dobriyan
alexey dobriyan
3
1.96%
1
11.11%
christoph lameter
christoph lameter
2
1.31%
1
11.11%
Total
153
100.00%
9
100.00%



void pgtable_cache_init(void)
{
	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
	pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
	/*
         * In all current configs, when the PUD index exists it's the
         * same size as either the pgd or pmd index except with THP enabled
         * on book3s 64
         */
	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
		pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor);

	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_CACHE_INDEX))
		panic("Couldn't allocate pgtable caches");
	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
		panic("Couldn't allocate pud pgtable caches");
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
david gibson
david gibson
42
57.53%
1
20.00%
aneesh kumar
aneesh kumar
26
35.62%
2
40.00%
paul mackerras
paul mackerras
4
5.48%
1
20.00%
alexey dobriyan
alexey dobriyan
1
1.37%
1
20.00%
Total
73
100.00%
5
100.00%

#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.
 */


static 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
andy whitcroft
andy whitcroft
41
97.62%
1
50.00%
michael ellerman
michael ellerman
1
2.38%
1
50.00%
Total
42
100.00%
2
100.00%

/*
 * Check if this vmemmap page is already initialised.  If any section
 * which overlaps this vmemmap page is initialised then this page is
 * initialised already.
 */


static int __meminit vmemmap_populated(unsigned long start, int page_size)
{
	unsigned long end = start + page_size;
	start = (unsigned long)(pfn_to_page(vmemmap_section_start(start)));

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

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
andy whitcroft
andy whitcroft
55
70.51%
1
33.33%
li zhong
li zhong
22
28.21%
1
33.33%
michael ellerman
michael ellerman
1
1.28%
1
33.33%
Total
78
100.00%
3
100.00%


struct vmemmap_backing *vmemmap_list;

static struct vmemmap_backing *next;

static int num_left;

static int num_freed;


static __meminit struct vmemmap_backing * vmemmap_list_alloc(int node)
{
        struct vmemmap_backing *vmem_back;
	/* get from freed entries first */
	if (num_freed) {
		num_freed--;
		vmem_back = next;
		next = next->list;

		return vmem_back;
	}

	/* allocate a page when required and hand out chunks */
	if (!num_left) {
		next = vmemmap_alloc_block(PAGE_SIZE, node);
		if (unlikely(!next)) {
			WARN_ON(1);
			return NULL;
		}
		num_left = PAGE_SIZE / sizeof(struct vmemmap_backing);
	}

	num_left--;

	return next++;

}

static 
__meminit void vmemmap_list_populate(unsigned long phys,
					    unsigned long start,
					    int node)
{
	struct vmemmap_backing *vmem_back;

	vmem_back = vmemmap_list_alloc(node);
	if (unlikely(!vmem_back)) {
		WARN_ON(1);
		return;
	}

	vmem_back->phys = phys;
	vmem_back->virt_addr = start;
	vmem_back->list = vmemmap_list;

	vmemmap_list = vmem_back;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
mark nelson
mark nelson
68
100.00%
1
100.00%
Total
68
100.00%
1
100.00%



int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
{
	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;

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

	pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node);

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

		if (vmemmap_populated(start, page_size))
			continue;

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

		vmemmap_list_populate(__pa(p), start, node);

		pr_debug("      * %016lx..%016lx allocated at %p\n",
			 start, start + page_size, p);

		rc = vmemmap_create_mapping(start, page_size, __pa(p));
		if (rc < 0) {
			pr_warning(
				"vmemmap_populate: Unable to create vmemmap mapping: %d\n",
				rc);
			return -EFAULT;
		}
	}

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
li zhong
li zhong
136
85.00%
1
50.00%
david gibson
david gibson
24
15.00%
1
50.00%
Total
160
100.00%
2
100.00%

#ifdef CONFIG_MEMORY_HOTPLUG


static unsigned long vmemmap_list_free(unsigned long start)
{
	struct vmemmap_backing *vmem_back, *vmem_back_prev;

	vmem_back_prev = vmem_back = vmemmap_list;

	/* look for it with prev pointer recorded */
	for (; vmem_back; vmem_back = vmem_back->list) {
		if (vmem_back->virt_addr == start)
			break;
		vmem_back_prev = vmem_back;
	}

	if (unlikely(!vmem_back)) {
		WARN_ON(1);
		return 0;
	}

	/* remove it from vmemmap_list */
	if (vmem_back == vmemmap_list) /* remove head */
		vmemmap_list = vmem_back->list;
	else
		vmem_back_prev->list = vmem_back->list;

	/* next point to this freed entry */
	vmem_back->list = next;
	next = vmem_back;
	num_freed++;

	return vmem_back->phys;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
li zhong
li zhong
112
100.00%
1
100.00%
Total
112
100.00%
1
100.00%



void __ref vmemmap_free(unsigned long start, unsigned long end)
{
	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;

	start = _ALIGN_DOWN(start, page_size);

	pr_debug("vmemmap_free %lx...%lx\n", start, end);

	for (; start < end; start += page_size) {
		unsigned long addr;

		/*
                 * the section has already be marked as invalid, so
                 * vmemmap_populated() true means some other sections still
                 * in this page, so skip it.
                 */
		if (vmemmap_populated(start, page_size))
			continue;

		addr = vmemmap_list_free(start);
		if (addr) {
			struct page *page = pfn_to_page(addr >> PAGE_SHIFT);

			if (PageReserved(page)) {
				/* allocated from bootmem */
				if (page_size < PAGE_SIZE) {
					/*
                                         * this shouldn't happen, but if it is
                                         * the case, leave the memory there
                                         */
					WARN_ON_ONCE(1);
				} else {
					unsigned int nr_pages =
						1 << get_order(page_size);
					while (nr_pages--)
						free_reserved_page(page++);
				}
			} else
				free_pages((unsigned long)(__va(addr)),
							get_order(page_size));

			vmemmap_remove_mapping(start, page_size);
		}
	}
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
li zhong
li zhong
86
49.43%
1
16.67%
andy whitcroft
andy whitcroft
69
39.66%
1
16.67%
benjamin herrenschmidt
benjamin herrenschmidt
10
5.75%
2
33.33%
mark nelson
mark nelson
5
2.87%
1
16.67%
johannes weiner
johannes weiner
4
2.30%
1
16.67%
Total
174
100.00%
6
100.00%

#endif


void register_page_bootmem_memmap(unsigned long section_nr,
				  struct page *start_page, unsigned long size)
{
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
nathan fontenot
nathan fontenot
17
100.00%
1
100.00%
Total
17
100.00%
1
100.00%

/*
 * We do not have access to the sparsemem vmemmap, so we fallback to
 * walking the list of sparsemem blocks which we already maintain for
 * the sake of crashdump. In the long run, we might want to maintain
 * a tree if performance of that linear walk becomes a problem.
 *
 * realmode_pfn_to_page functions can fail due to:
 * 1) As real sparsemem blocks do not lay in RAM continously (they
 * are in virtual address space which is not available in the real mode),
 * the requested page struct can be split between blocks so get_page/put_page
 * may fail.
 * 2) When huge pages are used, the get_page/put_page API will fail
 * in real mode as the linked addresses in the page struct are virtual
 * too.
 */


struct page *realmode_pfn_to_page(unsigned long pfn)
{
	struct vmemmap_backing *vmem_back;
	struct page *page;
	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
	unsigned long pg_va = (unsigned long) pfn_to_page(pfn);

	for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) {
		if (pg_va < vmem_back->virt_addr)
			continue;

		/* After vmemmap_list entry free is possible, need check all */
		if ((pg_va + sizeof(struct page)) <=
				(vmem_back->virt_addr + page_size)) {
			page = (struct page *) (vmem_back->phys + pg_va -
				vmem_back->virt_addr);
			return page;
		}
	}

	/* Probably that page struct is split between real pages */
	return NULL;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
alexey kardashevskiy
alexey kardashevskiy
116
95.87%
1
50.00%
li zhong
li zhong
5
4.13%
1
50.00%
Total
121
100.00%
2
100.00%


EXPORT_SYMBOL_GPL(realmode_pfn_to_page);

#elif defined(CONFIG_FLATMEM)



struct page *realmode_pfn_to_page(unsigned long pfn)
{
	struct page *page = pfn_to_page(pfn);
	return page;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
alexey kardashevskiy
alexey kardashevskiy
24
100.00%
1
100.00%
Total
24
100.00%
1
100.00%


EXPORT_SYMBOL_GPL(realmode_pfn_to_page);

#endif /* CONFIG_SPARSEMEM_VMEMMAP/CONFIG_FLATMEM */

#ifdef CONFIG_PPC_STD_MMU_64

static bool disable_radix;


static int __init parse_disable_radix(char *p)
{
	disable_radix = true;
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
michael ellerman
michael ellerman
18
100.00%
1
100.00%
Total
18
100.00%
1
100.00%

early_param("disable_radix", parse_disable_radix);



void __init mmu_early_init_devtree(void)
{
	/* Disable radix mode based on kernel command line. */
	if (disable_radix)
		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;

	if (early_radix_enabled())
		radix__early_init_devtree();
	else
		hash__early_init_devtree();
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
michael ellerman
michael ellerman
30
93.75%
4
66.67%
aneesh kumar
aneesh kumar
2
6.25%
2
33.33%
Total
32
100.00%
6
100.00%

#endif /* CONFIG_PPC_STD_MMU_64 */
Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
li zhong
li zhong
407
27.63%
3
6.98%
david gibson
david gibson
199
13.51%
6
13.95%
andy whitcroft
andy whitcroft
172
11.68%
1
2.33%
paul mackerras
paul mackerras
162
11.00%
1
2.33%
alexey kardashevskiy
alexey kardashevskiy
158
10.73%
1
2.33%
mark nelson
mark nelson
140
9.50%
1
2.33%
michael ellerman
michael ellerman
67
4.55%
5
11.63%
aneesh kumar
aneesh kumar
63
4.28%
6
13.95%
benjamin herrenschmidt
benjamin herrenschmidt
27
1.83%
5
11.63%
alexey dobriyan
alexey dobriyan
17
1.15%
1
2.33%
nathan fontenot
nathan fontenot
17
1.15%
1
2.33%
sonny rao
sonny rao
10
0.68%
1
2.33%
kumar gala
kumar gala
9
0.61%
2
4.65%
christoph lameter
christoph lameter
5
0.34%
2
4.65%
yanjiang jin
yanjiang jin
5
0.34%
1
2.33%
johannes weiner
johannes weiner
4
0.27%
1
2.33%
tejun heo
tejun heo
3
0.20%
1
2.33%
david s. miller
david s. miller
3
0.20%
1
2.33%
randy dunlap
randy dunlap
3
0.20%
1
2.33%
yinghai lu
yinghai lu
1
0.07%
1
2.33%
hugh dickins
hugh dickins
1
0.07%
1
2.33%
Total
1473
100.00%
43
100.00%
  
Directory: arch/powerpc/mm

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.