kernel-ark/arch/powerpc/mm/init_64.c
David Gibson f10a04c034 [PATCH] powerpc: Fix pagetable bloat for hugepages
At present, ARCH=powerpc kernels can waste considerable space in
pagetables when making large hugepage mappings.  Hugepage PTEs go in
PMD pages, but each PMD page maps 256M and so contains only 16
hugepage PTEs (128 bytes of data), but takes up a 1024 byte
allocation.  With CONFIG_PPC_64K_PAGES enabled (64k base page size),
the situation is worse.  Now hugepage PTEs are at the PTE page level
(also mapping 256M), so we store 16 hugepage PTEs in a 64k allocation.

The PowerPC MMU already means that any 256M region is either all
hugepage, or all normal pages.  Thus, with some care, we can use a
different allocation for the hugepage PTE tables and only allocate the
128 bytes necessary.

Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-04-28 15:02:51 +10:00

195 lines
4.9 KiB
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
* 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.
*
*/
#undef DEBUG
#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/sections.h>
#include <asm/system.h>
#include <asm/iommu.h>
#include <asm/abs_addr.h>
#include <asm/vdso.h>
#include "mmu_decl.h"
#ifdef DEBUG
#define DBG(fmt...) printk(fmt)
#else
#define DBG(fmt...)
#endif
#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, 0xcc, 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
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);
static void zero_ctor(void *addr, kmem_cache_t *cache, unsigned long flags)
{
memset(addr, 0, kmem_cache_size(cache));
}
#ifdef CONFIG_PPC_64K_PAGES
static const unsigned int pgtable_cache_size[3] = {
PTE_TABLE_SIZE, PMD_TABLE_SIZE, PGD_TABLE_SIZE
};
static const char *pgtable_cache_name[ARRAY_SIZE(pgtable_cache_size)] = {
"pte_pmd_cache", "pmd_cache", "pgd_cache",
};
#else
static const unsigned 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",
};
#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. */
kmem_cache_t *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)+1];
#else
kmem_cache_t *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];
DBG("Allocating page table cache %s (#%d) "
"for size: %08x...\n", name, i, size);
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);
}
}