linux/mm/mremap.c
Hugh Dickins 365e9c87a9 [PATCH] mm: update_hiwaters just in time
update_mem_hiwater has attracted various criticisms, in particular from those
concerned with mm scalability.  Originally it was called whenever rss or
total_vm got raised.  Then many of those callsites were replaced by a timer
tick call from account_system_time.  Now Frank van Maarseveen reports that to
be found inadequate.  How about this?  Works for Frank.

Replace update_mem_hiwater, a poor combination of two unrelated ops, by macros
update_hiwater_rss and update_hiwater_vm.  Don't attempt to keep
mm->hiwater_rss up to date at timer tick, nor every time we raise rss (usually
by 1): those are hot paths.  Do the opposite, update only when about to lower
rss (usually by many), or just before final accounting in do_exit.  Handle
mm->hiwater_vm in the same way, though it's much less of an issue.  Demand
that whoever collects these hiwater statistics do the work of taking the
maximum with rss or total_vm.

And there has been no collector of these hiwater statistics in the tree.  The
new convention needs an example, so match Frank's usage by adding a VmPeak
line above VmSize to /proc/<pid>/status, and also a VmHWM line above VmRSS
(High-Water-Mark or High-Water-Memory).

There was a particular anomaly during mremap move, that hiwater_vm might be
captured too high.  A fleeting such anomaly remains, but it's quickly
corrected now, whereas before it would stick.

What locking?  None: if the app is racy then these statistics will be racy,
it's not worth any overhead to make them exact.  But whenever it suits,
hiwater_vm is updated under exclusive mmap_sem, and hiwater_rss under
page_table_lock (for now) or with preemption disabled (later on): without
going to any trouble, minimize the time between reading current values and
updating, to minimize those occasions when a racing thread bumps a count up
and back down in between.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-29 21:40:39 -07:00

420 lines
11 KiB
C

/*
* mm/mremap.c
*
* (C) Copyright 1996 Linus Torvalds
*
* Address space accounting code <alan@redhat.com>
* (C) Copyright 2002 Red Hat Inc, All Rights Reserved
*/
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/slab.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/fs.h>
#include <linux/highmem.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
/*
* We don't need page_table_lock: we have mmap_sem exclusively.
*/
pgd = pgd_offset(mm, addr);
if (pgd_none_or_clear_bad(pgd))
return NULL;
pud = pud_offset(pgd, addr);
if (pud_none_or_clear_bad(pud))
return NULL;
pmd = pmd_offset(pud, addr);
if (pmd_none_or_clear_bad(pmd))
return NULL;
return pmd;
}
static pmd_t *alloc_new_pmd(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd = NULL;
pte_t *pte;
/*
* We do need page_table_lock: because allocators expect that.
*/
spin_lock(&mm->page_table_lock);
pgd = pgd_offset(mm, addr);
pud = pud_alloc(mm, pgd, addr);
if (!pud)
goto out;
pmd = pmd_alloc(mm, pud, addr);
if (!pmd)
goto out;
pte = pte_alloc_map(mm, pmd, addr);
if (!pte) {
pmd = NULL;
goto out;
}
pte_unmap(pte);
out:
spin_unlock(&mm->page_table_lock);
return pmd;
}
static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
unsigned long old_addr, unsigned long old_end,
struct vm_area_struct *new_vma, pmd_t *new_pmd,
unsigned long new_addr)
{
struct address_space *mapping = NULL;
struct mm_struct *mm = vma->vm_mm;
pte_t *old_pte, *new_pte, pte;
if (vma->vm_file) {
/*
* Subtle point from Rajesh Venkatasubramanian: before
* moving file-based ptes, we must lock vmtruncate out,
* since it might clean the dst vma before the src vma,
* and we propagate stale pages into the dst afterward.
*/
mapping = vma->vm_file->f_mapping;
spin_lock(&mapping->i_mmap_lock);
if (new_vma->vm_truncate_count &&
new_vma->vm_truncate_count != vma->vm_truncate_count)
new_vma->vm_truncate_count = 0;
}
spin_lock(&mm->page_table_lock);
old_pte = pte_offset_map(old_pmd, old_addr);
new_pte = pte_offset_map_nested(new_pmd, new_addr);
for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE,
new_pte++, new_addr += PAGE_SIZE) {
if (pte_none(*old_pte))
continue;
pte = ptep_clear_flush(vma, old_addr, old_pte);
/* ZERO_PAGE can be dependant on virtual addr */
pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
set_pte_at(mm, new_addr, new_pte, pte);
}
pte_unmap_nested(new_pte - 1);
pte_unmap(old_pte - 1);
spin_unlock(&mm->page_table_lock);
if (mapping)
spin_unlock(&mapping->i_mmap_lock);
}
#define LATENCY_LIMIT (64 * PAGE_SIZE)
static unsigned long move_page_tables(struct vm_area_struct *vma,
unsigned long old_addr, struct vm_area_struct *new_vma,
unsigned long new_addr, unsigned long len)
{
unsigned long extent, next, old_end;
pmd_t *old_pmd, *new_pmd;
old_end = old_addr + len;
flush_cache_range(vma, old_addr, old_end);
for (; old_addr < old_end; old_addr += extent, new_addr += extent) {
cond_resched();
next = (old_addr + PMD_SIZE) & PMD_MASK;
if (next - 1 > old_end)
next = old_end;
extent = next - old_addr;
old_pmd = get_old_pmd(vma->vm_mm, old_addr);
if (!old_pmd)
continue;
new_pmd = alloc_new_pmd(vma->vm_mm, new_addr);
if (!new_pmd)
break;
next = (new_addr + PMD_SIZE) & PMD_MASK;
if (extent > next - new_addr)
extent = next - new_addr;
if (extent > LATENCY_LIMIT)
extent = LATENCY_LIMIT;
move_ptes(vma, old_pmd, old_addr, old_addr + extent,
new_vma, new_pmd, new_addr);
}
return len + old_addr - old_end; /* how much done */
}
static unsigned long move_vma(struct vm_area_struct *vma,
unsigned long old_addr, unsigned long old_len,
unsigned long new_len, unsigned long new_addr)
{
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *new_vma;
unsigned long vm_flags = vma->vm_flags;
unsigned long new_pgoff;
unsigned long moved_len;
unsigned long excess = 0;
unsigned long hiwater_vm;
int split = 0;
/*
* We'd prefer to avoid failure later on in do_munmap:
* which may split one vma into three before unmapping.
*/
if (mm->map_count >= sysctl_max_map_count - 3)
return -ENOMEM;
new_pgoff = vma->vm_pgoff + ((old_addr - vma->vm_start) >> PAGE_SHIFT);
new_vma = copy_vma(&vma, new_addr, new_len, new_pgoff);
if (!new_vma)
return -ENOMEM;
moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len);
if (moved_len < old_len) {
/*
* On error, move entries back from new area to old,
* which will succeed since page tables still there,
* and then proceed to unmap new area instead of old.
*/
move_page_tables(new_vma, new_addr, vma, old_addr, moved_len);
vma = new_vma;
old_len = new_len;
old_addr = new_addr;
new_addr = -ENOMEM;
}
/* Conceal VM_ACCOUNT so old reservation is not undone */
if (vm_flags & VM_ACCOUNT) {
vma->vm_flags &= ~VM_ACCOUNT;
excess = vma->vm_end - vma->vm_start - old_len;
if (old_addr > vma->vm_start &&
old_addr + old_len < vma->vm_end)
split = 1;
}
/*
* If we failed to move page tables we still do total_vm increment
* since do_munmap() will decrement it by old_len == new_len.
*
* Since total_vm is about to be raised artificially high for a
* moment, we need to restore high watermark afterwards: if stats
* are taken meanwhile, total_vm and hiwater_vm appear too high.
* If this were a serious issue, we'd add a flag to do_munmap().
*/
hiwater_vm = mm->hiwater_vm;
mm->total_vm += new_len >> PAGE_SHIFT;
vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT);
if (do_munmap(mm, old_addr, old_len) < 0) {
/* OOM: unable to split vma, just get accounts right */
vm_unacct_memory(excess >> PAGE_SHIFT);
excess = 0;
}
mm->hiwater_vm = hiwater_vm;
/* Restore VM_ACCOUNT if one or two pieces of vma left */
if (excess) {
vma->vm_flags |= VM_ACCOUNT;
if (split)
vma->vm_next->vm_flags |= VM_ACCOUNT;
}
if (vm_flags & VM_LOCKED) {
mm->locked_vm += new_len >> PAGE_SHIFT;
if (new_len > old_len)
make_pages_present(new_addr + old_len,
new_addr + new_len);
}
return new_addr;
}
/*
* Expand (or shrink) an existing mapping, potentially moving it at the
* same time (controlled by the MREMAP_MAYMOVE flag and available VM space)
*
* MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise
* This option implies MREMAP_MAYMOVE.
*/
unsigned long do_mremap(unsigned long addr,
unsigned long old_len, unsigned long new_len,
unsigned long flags, unsigned long new_addr)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long ret = -EINVAL;
unsigned long charged = 0;
if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
goto out;
if (addr & ~PAGE_MASK)
goto out;
old_len = PAGE_ALIGN(old_len);
new_len = PAGE_ALIGN(new_len);
/*
* We allow a zero old-len as a special case
* for DOS-emu "duplicate shm area" thing. But
* a zero new-len is nonsensical.
*/
if (!new_len)
goto out;
/* new_addr is only valid if MREMAP_FIXED is specified */
if (flags & MREMAP_FIXED) {
if (new_addr & ~PAGE_MASK)
goto out;
if (!(flags & MREMAP_MAYMOVE))
goto out;
if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
goto out;
/* Check if the location we're moving into overlaps the
* old location at all, and fail if it does.
*/
if ((new_addr <= addr) && (new_addr+new_len) > addr)
goto out;
if ((addr <= new_addr) && (addr+old_len) > new_addr)
goto out;
ret = do_munmap(mm, new_addr, new_len);
if (ret)
goto out;
}
/*
* Always allow a shrinking remap: that just unmaps
* the unnecessary pages..
* do_munmap does all the needed commit accounting
*/
if (old_len >= new_len) {
ret = do_munmap(mm, addr+new_len, old_len - new_len);
if (ret && old_len != new_len)
goto out;
ret = addr;
if (!(flags & MREMAP_FIXED) || (new_addr == addr))
goto out;
old_len = new_len;
}
/*
* Ok, we need to grow.. or relocate.
*/
ret = -EFAULT;
vma = find_vma(mm, addr);
if (!vma || vma->vm_start > addr)
goto out;
if (is_vm_hugetlb_page(vma)) {
ret = -EINVAL;
goto out;
}
/* We can't remap across vm area boundaries */
if (old_len > vma->vm_end - addr)
goto out;
if (vma->vm_flags & VM_DONTEXPAND) {
if (new_len > old_len)
goto out;
}
if (vma->vm_flags & VM_LOCKED) {
unsigned long locked, lock_limit;
locked = mm->locked_vm << PAGE_SHIFT;
lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
locked += new_len - old_len;
ret = -EAGAIN;
if (locked > lock_limit && !capable(CAP_IPC_LOCK))
goto out;
}
if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) {
ret = -ENOMEM;
goto out;
}
if (vma->vm_flags & VM_ACCOUNT) {
charged = (new_len - old_len) >> PAGE_SHIFT;
if (security_vm_enough_memory(charged))
goto out_nc;
}
/* old_len exactly to the end of the area..
* And we're not relocating the area.
*/
if (old_len == vma->vm_end - addr &&
!((flags & MREMAP_FIXED) && (addr != new_addr)) &&
(old_len != new_len || !(flags & MREMAP_MAYMOVE))) {
unsigned long max_addr = TASK_SIZE;
if (vma->vm_next)
max_addr = vma->vm_next->vm_start;
/* can we just expand the current mapping? */
if (max_addr - addr >= new_len) {
int pages = (new_len - old_len) >> PAGE_SHIFT;
vma_adjust(vma, vma->vm_start,
addr + new_len, vma->vm_pgoff, NULL);
mm->total_vm += pages;
vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages);
if (vma->vm_flags & VM_LOCKED) {
mm->locked_vm += pages;
make_pages_present(addr + old_len,
addr + new_len);
}
ret = addr;
goto out;
}
}
/*
* We weren't able to just expand or shrink the area,
* we need to create a new one and move it..
*/
ret = -ENOMEM;
if (flags & MREMAP_MAYMOVE) {
if (!(flags & MREMAP_FIXED)) {
unsigned long map_flags = 0;
if (vma->vm_flags & VM_MAYSHARE)
map_flags |= MAP_SHARED;
new_addr = get_unmapped_area(vma->vm_file, 0, new_len,
vma->vm_pgoff, map_flags);
ret = new_addr;
if (new_addr & ~PAGE_MASK)
goto out;
}
ret = move_vma(vma, addr, old_len, new_len, new_addr);
}
out:
if (ret & ~PAGE_MASK)
vm_unacct_memory(charged);
out_nc:
return ret;
}
asmlinkage unsigned long sys_mremap(unsigned long addr,
unsigned long old_len, unsigned long new_len,
unsigned long flags, unsigned long new_addr)
{
unsigned long ret;
down_write(&current->mm->mmap_sem);
ret = do_mremap(addr, old_len, new_len, flags, new_addr);
up_write(&current->mm->mmap_sem);
return ret;
}