/*
* linux/arch/x86_64/mm/init.c
*
* Copyright (C) 1995 Linus Torvalds
* Copyright (C) 2000 Pavel Machek <pavel@ucw.cz>
* Copyright (C) 2002,2003 Andi Kleen <ak@suse.de>
*/
#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/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/initrd.h>
#include <linux/pagemap.h>
#include <linux/memblock.h>
#include <linux/proc_fs.h>
#include <linux/pci.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/dma-mapping.h>
#include <linux/memory.h>
#include <linux/memory_hotplug.h>
#include <linux/memremap.h>
#include <linux/nmi.h>
#include <linux/gfp.h>
#include <linux/kcore.h>
#include <asm/processor.h>
#include <asm/bios_ebda.h>
#include <linux/uaccess.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820/api.h>
#include <asm/apic.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/smp.h>
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/numa.h>
#include <asm/set_memory.h>
#include <asm/init.h>
#include <asm/uv/uv.h>
#include <asm/setup.h>
#include "mm_internal.h"
#include "ident_map.c"
/*
* NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
* physical space so we can cache the place of the first one and move
* around without checking the pgd every time.
*/
/* Bits supported by the hardware: */
pteval_t __supported_pte_mask __read_mostly = ~0;
/* Bits allowed in normal kernel mappings: */
pteval_t __default_kernel_pte_mask __read_mostly = ~0;
EXPORT_SYMBOL_GPL(__supported_pte_mask);
/* Used in PAGE_KERNEL_* macros which are reasonably used out-of-tree: */
EXPORT_SYMBOL(__default_kernel_pte_mask);
int force_personality32;
/*
* noexec32=on|off
* Control non executable heap for 32bit processes.
* To control the stack too use noexec=off
*
* on PROT_READ does not imply PROT_EXEC for 32-bit processes (default)
* off PROT_READ implies PROT_EXEC
*/
static int __init nonx32_setup(char *str)
{
if (!strcmp(str, "on"))
force_personality32 &= ~READ_IMPLIES_EXEC;
else if (!strcmp(str, "off"))
force_personality32 |= READ_IMPLIES_EXEC;
return 1;
}
__setup("noexec32=", nonx32_setup);
static void sync_global_pgds_l5(unsigned long start, unsigned long end)
{
unsigned long addr;
for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
const pgd_t *pgd_ref = pgd_offset_k(addr);
struct page *page;
/* Check for overflow */
if (addr < start)
break;
if (pgd_none(*pgd_ref))
continue;
spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
pgd_t *pgd;
spinlock_t *pgt_lock;
pgd = (pgd_t *)page_address(page) + pgd_index(addr);
/* the pgt_lock only for Xen */
pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
spin_lock(pgt_lock);
if (!pgd_none(*pgd_ref) && !pgd_none(*pgd))
BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
if (pgd_none(*pgd))
set_pgd(pgd, *pgd_ref);
spin_unlock(pgt_lock);
}
spin_unlock(&pgd_lock);
}
}
static void sync_global_pgds_l4(unsigned long start, unsigned long end)
{
unsigned long addr;
for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
pgd_t *pgd_ref = pgd_offset_k(addr);
const p4d_t *p4d_ref;
struct page *page;
/*
* With folded p4d, pgd_none() is always false, we need to
* handle synchonization on p4d level.
*/
MAYBE_BUILD_BUG_ON(pgd_none(*pgd_ref));
p4d_ref = p4d_offset(pgd_ref, addr);
if (p4d_none(*p4d_ref))
continue;
spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
pgd_t *pgd;
p4d_t *p4d;
spinlock_t *pgt_lock;
pgd = (pgd_t *)page_address(page) + pgd_index(addr);
p4d = p4d_offset(pgd, addr);
/* the pgt_lock only for Xen */
pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
spin_lock(pgt_lock);
if (!p4d_none(*p4d_ref) && !p4d_none(*p4d))
BUG_ON(p4d_page_vaddr(*p4d)
!= p4d_page_vaddr(*p4d_ref));
if (p4d_none(*p4d))
set_p4d(p4d, *p4d_ref);
spin_unlock(pgt_lock);
}
spin_unlock(&pgd_lock);
}
}
/*
* When memory was added make sure all the processes MM have
* suitable PGD entries in the local PGD level page.
*/
void sync_global_pgds(unsigned long start, unsigned long end)
{
if (pgtable_l5_enabled())
sync_global_pgds_l5(start, end);
else
sync_global_pgds_l4(start, end);
}
/*
* NOTE: This function is marked __ref because it calls __init function
* (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
*/
static __ref void *spp_getpage(void)
{
void *ptr;
if (after_bootmem)
ptr = (void *) get_zeroed_page(GFP_ATOMIC);
else
ptr = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) {
panic("set_pte_phys: cannot allocate page data %s\n",
after_bootmem ? "after bootmem" : "");
}
pr_debug("spp_getpage %p\n", ptr);
return ptr;
}
static p4d_t *fill_p4d(pgd_t *pgd, unsigned long vaddr)
{
if (pgd_none(*pgd)) {
p4d_t *p4d = (p4d_t *)spp_getpage();
pgd_populate(&init_mm, pgd, p4d);
if (p4d != p4d_offset(pgd, 0))
printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n",
p4d, p4d_offset(pgd, 0));
}
return p4d_offset(pgd, vaddr);
}
static pud_t *fill_pud(p4d_t *p4d, unsigned long vaddr)
{
if (p4d_none(*p4d)) {
pud_t *pud = (pud_t *)spp_getpage();
p4d_populate(&init_mm, p4d, pud);
if (pud != pud_offset(p4d, 0))
printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
pud, pud_offset(p4d, 0));
}
return pud_offset(p4d, vaddr);
}
static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr)
{
if (pud_none(*pud)) {
pmd_t *pmd = (pmd_t *) spp_getpage();
pud_populate(&init_mm, pud, pmd);
if (pmd != pmd_offset(pud, 0))
printk(KERN_ERR "PAGETABLE BUG #02! %p <-> %p\n",
pmd, pmd_offset(pud, 0));
}
return pmd_offset(pud, vaddr);
}
static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr)
{
if (pmd_none(*pmd)) {
pte_t *pte = (pte_t *) spp_getpage();
pmd_populate_kernel(&init_mm, pmd,
|