/*
* linux/mm/memory.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*/
/*
* demand-loading started 01.12.91 - seems it is high on the list of
* things wanted, and it should be easy to implement. - Linus
*/
/*
* Ok, demand-loading was easy, shared pages a little bit tricker. Shared
* pages started 02.12.91, seems to work. - Linus.
*
* Tested sharing by executing about 30 /bin/sh: under the old kernel it
* would have taken more than the 6M I have free, but it worked well as
* far as I could see.
*
* Also corrected some "invalidate()"s - I wasn't doing enough of them.
*/
/*
* Real VM (paging to/from disk) started 18.12.91. Much more work and
* thought has to go into this. Oh, well..
* 19.12.91 - works, somewhat. Sometimes I get faults, don't know why.
* Found it. Everything seems to work now.
* 20.12.91 - Ok, making the swap-device changeable like the root.
*/
/*
* 05.04.94 - Multi-page memory management added for v1.1.
* Idea by Alex Bligh (alex@cconcepts.co.uk)
*
* 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG
* (Gerhard.Wichert@pdb.siemens.de)
*
* Aug/Sep 2004 Changed to four level page tables (Andi Kleen)
*/
#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/module.h>
#include <linux/delayacct.h>
#include <linux/init.h>
#include <linux/writeback.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/kallsyms.h>
#include <linux/swapops.h>
#include <linux/elf.h>
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>
#include "internal.h"
#ifndef CONFIG_NEED_MULTIPLE_NODES
/* use the per-pgdat data instead for discontigmem - mbligh */
unsigned long max_mapnr;
struct page *mem_map;
EXPORT_SYMBOL(max_mapnr);
EXPORT_SYMBOL(mem_map);
#endif
unsigned long num_physpages;
/*
* A number of key systems in x86 including ioremap() rely on the assumption
* that high_memory defines the upper bound on direct map memory, then end
* of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and
* highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
* and ZONE_HIGHMEM.
*/
void * high_memory;
EXPORT_SYMBOL(num_physpages);
EXPORT_SYMBOL(high_memory);
/*
* Randomize the address space (stacks, mmaps, brk, etc.).
*
* ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization,
* as ancient (libc5 based) binaries can segfault. )
*/
int randomize_va_space __read_mostly =
#ifdef CONFIG_COMPAT_BRK
1;
#else
2;
#endif
static int __init disable_randmaps(char *s)
{
randomize_va_space = 0;
return 1;
}
__setup("norandmaps", disable_randmaps);
/*
* If a p?d_bad entry is found while walking page tables, report
* the error, before resetting entry to p?d_none. Usually (but
* very seldom) called out from the p?d_none_or_clear_bad macros.
*/
void pgd_clear_bad(pgd_t *pgd)
{
pgd_ERROR(*pgd);
pgd_clear(pgd);
}
void pud_clear_bad(pud_t *pud)
{
pud_ERROR(*pud);
pud_clear(pud);
}
void pmd_clear_bad(pmd_t *pmd)
{
pmd_ERROR(*pmd);
pmd_clear(pmd);
}
/*
* Note: this doesn't free the actual pages themselves. That
* has been handled earlier when unmapping all the memory regions.
*/
static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
{
pgtable_t token = pmd_pgtable(*pmd);
pmd_clear(pmd);
pte_free_tlb(tlb, token);
tlb->mm->nr_ptes--;
}
static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pmd_t *pmd;
unsigned long next;
unsigned long start;
start = addr;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
free_pte_range(tlb, pmd);
} while (pmd++, addr = next, addr != end);
start &= PUD_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= PUD_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
return;
pmd = pmd_offset(pud, start);
pud_clear(pud);
pmd_free_tlb(tlb, pmd);
}
static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pud_t *pud;
unsigned long next;
unsigned long start;
start = addr;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
free_pmd_range(tlb, pud, addr, next, floor, ceiling);
} while (pud++, addr = next, addr != end);
start &= PGDIR_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= PGDIR_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
return;
pud = pud_offset(pgd, start);
pgd_clear(pgd);
pud_free_tlb(tlb, pud);
}
/*
* This function frees user-level page tables of a process.
*
* Must be called with pagetable lock held.
*/
void free_pgd_range(struct mmu_gather *tlb,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pgd_t *pgd;
unsigned long next;
unsigned long start;
/*
* The next few lines have given us lots of grief...
*
* Why are we testing PMD* at this top level? Because often
* there will be no work to do at all, and we'd prefer not to
* go all the way down to the bottom just to discover that.
*
* Why all these "- 1"s? Because 0 represents both the bottom
* of the address space and the top of it (using -1 for the
* top wouldn't help much: the masks would do the wrong thing).
* The rule is that addr 0 and floor 0 refer to the bottom of
* the address space, but end 0 and ceiling 0 refer to the top
* Comparisons need to use "end - 1" and "ceiling - 1" (though
* that end 0 case should be mythical).
*
* Wherever addr is brought up or ceiling brought down, we must
* be careful to reject "the opposite 0" before it confuses the
* subsequent tests. But what about where end is brought down
* by PMD_SIZE below? no, end can't go down to 0 there.
*
* Whereas we round start (addr) and ceiling down, by different
* masks at different levels, in order to test whether a table
* now has no other vmas using it, so can be freed, we don't
* bother to round floor or end up - the tests don't need that.
*/
addr &= PMD_MASK;
if (addr < floor) {
addr += PMD_SIZE;
if (!addr)
return;
}
if (ceiling) {
ceiling &= PMD_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
end -= PMD_SIZE;
if (addr > end - 1)
return;
start = addr;
pgd = pgd_offset(tlb->mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
free_pud_range(tlb, pgd, addr, next, floor, ceiling);
} while (pgd++, addr = next, addr != end);
}
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long floor, unsigned long ceiling)
{
while (vma) {
struct vm_area_struct *next = vma->vm_next;
unsigned long addr = vma->vm_start;
/*
* Hide vma from rmap and vmtruncate before freeing pgtables
*/
anon_vma_unlink(vma);
unlink_file_vma(vma);
if (is_vm_hugetlb_page(vma)) {
hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
floor, next? next->vm_start: ceiling);
} else {
/*
* Optimization: gather nearby vmas into one call down
*/
while (next && next->vm_start <= vma->vm_end + PMD_SIZE
&& !is_vm_hugetlb_page(next)) {
vma = next;
next = vma->vm_next;
anon_vma_unlink(vma);
unlink_file_vma(vma);
}
free_pgd_range(tlb, addr, vma->vm_end,
floor, next? next->vm_start: ceiling);
}
vma = next;
}
}
int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
{
pgtable_t new = pte_alloc_one(mm, address);
if (!new)
return -ENOMEM;
/*
* Ensure all pte setup (eg. pte page lock and page clearing) are
* visible before the pte is made visible to other CPUs by being
* put into page tables.
*
* The other side of the story is the pointer chasing in the page
* table walking code (when walking the page table without locking;
* ie. most of the time). Fortunately, these data accesses consist
* of a chain of data-dependent loads, meaning most CPUs (alpha
* being the notable exception) will already guarantee loads are
* seen in-order. See the alpha page table accessors for the
* smp_read_barrier_depends() barriers in page table walking code.
*/
smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
spin_lock(&mm->page_table_lock);
if (!pmd_present(*pmd)) { /* Has another populated it ? */
mm->nr_ptes++;
pmd_populate(mm, pmd, new);
new = NULL;
}
spin_unlock(&mm->page_table_lock);
if (new)
pte_free(mm, new);
return 0;
}
int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
{
pte_t *new = pte_alloc_one_kernel(&init_mm, address);
if (!new)
return -ENOMEM;
smp_wmb(); /* See comment in __pte_alloc */
spin_lock(&init_mm.page_table_lock);
if (!pmd_present(*pmd)) { /* Has another populated it ? */
pmd_populate_kernel(&init_mm, pmd, new);
new = NULL;
}
spin_unlock(&init_mm.page_table_lock);
if (new)
pte_free_kernel(&init_mm, new);
return 0;
}
static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss)
{
if (file_rss)
add_mm_counter(mm, file_rss, file_rss);
if (anon_rss)
add_mm_counter(mm, anon_rss, anon_rss);
}
/*
* This function is called to print an error when a bad pte
* is found. For example, we might have a PFN-mapped pte in
* a region that doesn't allow it.
*
* The calling function must still handle the error.
*/
static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
pte_t pte, struct page *page)
{
pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
pud_t *pud = pud_offset(pgd, addr);
pmd_t *pmd = pmd_offset(pud, addr);
struct address_space *mapping;
pgoff_t index;
static unsigned long resume;
static unsigned long nr_shown;
static unsigned long nr_unshown;
/*
* Allow a burst of 60 reports, then keep quiet for that minute;
* or allow a steady drip of one report per second.
*/
if (nr_shown == 60) {
if (time_before(jiffies, resume)) {
nr_unshown++;
return;
}
if (nr_unshown) {
printk(KERN_ALERT
"BUG: Bad page map: %lu messages suppressed\n",
nr_unshown);
nr_unshown = 0;
}
nr_shown = 0;
}
if (nr_shown++ == 0)
resume = jiffies + 60 * HZ;
mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL;
index = linear_page_index(vma, addr);
printk(KERN_ALERT
"BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n",
current->comm,
(long long)pte_val(pte), (long long)pmd_val(*pmd));
if (page) {
printk(KERN_ALERT
"page:%p flags:%p count:%d mapcount:%d mapping:%p index:%lx\n",
page, (void *)page->flags, page_count(page),
page_mapcount(page), page->mapping, page->index);
}
printk(KERN_ALERT
"addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n",
(void *)addr, vma->vm_flags, vma->anon_vma, mapping, index);
/*
* Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y
*/
if (vma->vm_ops)
print_symbol(KERN_ALERT "vma->vm_ops->fault: %s\n",
(unsigned long)vma->vm_ops->fault);
if (vma->vm_file && vma->vm_file->f_op)
print_symbol(KERN_ALERT "vma->vm_file->f_op->mmap: %s\n",
(unsigned long)vma->vm_file->f_op->mmap);
dump_stack();
add_taint(TAINT_BAD_PAGE);
}
static inline int is_cow_mapping(unsigned int flags)
{
return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
}
/*
* vm_normal_page -- This function gets the "struct page" associated with a pte.
*
* "Special" mappings do not wish to be associated with a "struct page" (either
* it doesn't exist, or it exists but they don't want to touch it). In this
* case, NULL is returned here. "Normal" mappings do have a struct page.
*
* There are 2 broad cases. Firstly, an architecture may define a pte_special()
* pte bit, in which case this function is trivial. Secondly, an architecture
* may not have a spare pte bit, which requires a more complicated scheme,
* described below.
*
* A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a
* special mapping (even if there are underlying and valid "struct pages").
* COWed pages of a VM_PFNMAP are always normal.
*
* The way we recognize COWed pages within VM_PFNMAP mappings is through the
* rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit
* set, and the vm_pgoff will point to the first PFN mapped: thus every special
* mapping will always honor the rule
*
* pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT)
*
* And for normal mappings this is false.
*
* This restricts such mappings to be a linear translation from virtual address
* to pfn. To get around this restriction, we allow arbitrary mappings so long
* as the vma is not a COW mapping; in that case, we know that all ptes are
* special (because none can have been COWed).
*
*
* In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP.
*
* VM_MIXEDMAP mappings can likewise contain memory with or without "struct
* page" backing, however the difference is that _all_ pages with a struct
* page (that is, those where pfn_valid is true) are refcounted and considered
* normal pages by the VM. The disadvantage is that pages are refcounted
* (which can be slower and simply not an option for some PFNMAP users). The
* advantage is that we don't have to follow the strict linearity rule of
* PFNMAP mappings in order to support COWable mappings.
*
*/
#ifdef __HAVE_ARCH_PTE_SPECIAL
# define HAVE_PTE_SPECIAL 1
#else
# define HAVE_PTE_SPECIAL 0
#endif
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
pte_t pte)
{
unsigned long pfn = pte_pfn(pte);
if (HAVE_PTE_SPECIAL) {
if (likely(!pte_special(pte)))
goto check_pfn;
if (!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)))
print_bad_pte(vma, addr, pte, NULL);
return NULL;
}
/* !HAVE_PTE_SPECIAL case follows: */
if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
if (vma->vm_flags & VM_MIXEDMAP) {
if (!pfn_valid(pfn))
return NULL;
goto out;
} else {
unsigned long off;
off = (addr - vma->vm_start) >> PAGE_SHIFT;
if (pfn == vma->vm_pgoff + off)
return NULL;
if (!is_cow_mapping(vma->vm_flags))
return NULL;
}
}
check_pfn:
if (unlikely(pfn > highest_memmap_pfn)) {
print_bad_pte(vma, addr, pte, NULL);
return NULL;
}
/*
* NOTE! We still have PageReserved() pages in the page tables.
* eg. VDSO mappings can cause them to exist.
*/
out:
return pfn_to_page(pfn);
}
/*
* copy one vm_area from one task to the other. Assumes the page tables
* already present in the new task to be cleared in the whole range
* covered by this vma.
*/
static inline void
copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
unsigned long addr, int *rss)
{
unsigned long vm_flags = vma->vm_flags;
pte_t pte = *src_pte;
struct page *page;
/* pte contains position in swap or file, so copy. */
if (unlikely(!pte_present(pte))) {
if (!pte_file(pte)) {
swp_entry_t entry = pte_to_swp_entry(pte);
swap_duplicate(entry);
/* make sure dst_mm is on swapoff's mmlist. */
if (unlikely(list_empty(&dst_mm->mmlist))) {
spin_lock(&mmlist_lock);
if (list_empty(&dst_mm->mmlist))
list_add(&dst_mm->mmlist,
&src_mm->mmlist);
spin_unlock(&mmlist_lock);
}
if (is_write_migration_entry(entry) &&
is_cow_mapping(vm_flags)) {
/*
* COW mappings require pages in both parent
* and child to be set to read.
*/
make_migration_entry_read(&entry);
pte = swp_entry_to_pte(entry);
set_pte_at(src_mm, addr, src_pte, pte);
}
}
goto out_set_pte;
}
/*
* If it's a COW mapping, write protect it both
* in the parent and the child
*/
if (is_cow_mapping(vm_flags)) {
ptep_set_wrprotect(src_mm, addr, src_pte);
pte = pte_wrprotect(pte);
}
/*
* If it's a shared mapping, mark it clean in
* the child
*/
if (vm_flags & VM_SHARED)
pte = pte_mkclean(pte);
pte = pte_mkold(pte);
page = vm_normal_page(vma, addr, pte);
if (page) {
get_page(page);
page_dup_rmap(page, vma, addr);
rss[!!PageAnon(page)]++;
}
out_set_pte:
set_pte_at(dst_mm, addr, dst_pte, pte);
}
static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
pte_t *src_pte, *dst_pte;
spinlock_t *src_ptl, *dst_ptl;
int progress = 0;
int rss[2];
again:
rss[1] = rss[0] = 0;
dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
if (!dst_pte)
return -ENOMEM;
src_pte = pte_offset_map_nested(src_pmd, addr);
src_ptl = pte_lockptr(src_mm, src_pmd);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
arch_enter_lazy_mmu_mode();
do {
/*
* We are holding two locks at this point - either of them
* could generate latencies in another task on another CPU.
*/
if (progress >= 32) {
progress = 0;
if (need_resched() ||
spin_needbreak(src_ptl) || spin_needbreak(dst_ptl))
break;
}
if (pte_none(*src_pte)) {
progress++;
continue;
}
copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma, addr, rss);
progress += 8;
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
spin_unlock(src_ptl);
pte_unmap_nested(src_pte - 1);
add_mm_rss(dst_mm, rss[0], rss[1]);
pte_unmap_unlock(dst_pte - 1, dst_ptl);
cond_resched();
if (addr != end)
goto again;
return 0;
}
static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
pmd_t *src_pmd, *dst_pmd;
unsigned long next;
dst_pmd = pmd_alloc(dst_mm, dst_pud, addr);
if (!dst_pmd)
return -ENOMEM;
src_pmd = pmd_offset(src_pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(src_pmd))
continue;
if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
vma, addr, next))
return -ENOMEM;
|