linux/mm/mremap.c
Linus Torvalds 3d59eebc5e Automatic NUMA Balancing V11
-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.18 (GNU/Linux)
 
 iQIcBAABAgAGBQJQx0kQAAoJEHzG/DNEskfi4fQP/R5PRovayroZALBMLnVJDaLD
 Ttr9p40VNXbiJ+MfRgatJjSSJZ4Jl+fC3NEqBhcwVZhckZZb9R2s0WtrSQo5+ZbB
 vdRfiuKoCaKM4cSZ08C12uTvsF6xjhjd27CTUlMkyOcDoKxMEFKelv0hocSxe4Wo
 xqlv3eF+VsY7kE1BNbgBP06SX4tDpIHRxXfqJPMHaSKQmre+cU0xG2GcEu3QGbHT
 DEDTI788YSaWLmBfMC+kWoaQl1+bV/FYvavIAS8/o4K9IKvgR42VzrXmaFaqrbgb
 72ksa6xfAi57yTmZHqyGmts06qYeBbPpKI+yIhCMInxA9CY3lPbvHppRf0RQOyzj
 YOi4hovGEMJKE+BCILukhJcZ9jCTtS3zut6v1rdvR88f4y7uhR9RfmRfsxuW7PNj
 3Rmh191+n0lVWDmhOs2psXuCLJr3LEiA0dFffN1z8REUTtTAZMsj8Rz+SvBNAZDR
 hsJhERVeXB6X5uQ5rkLDzbn1Zic60LjVw7LIp6SF2OYf/YKaF8vhyWOA8dyCEu8W
 CGo7AoG0BO8tIIr8+LvFe8CweypysZImx4AjCfIs4u9pu/v11zmBvO9NO5yfuObF
 BreEERYgTes/UITxn1qdIW4/q+Nr0iKO3CTqsmu6L1GfCz3/XzPGs3U26fUhllqi
 Ka0JKgnWvsa6ez6FSzKI
 =ivQa
 -----END PGP SIGNATURE-----

Merge tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma

Pull Automatic NUMA Balancing bare-bones from Mel Gorman:
 "There are three implementations for NUMA balancing, this tree
  (balancenuma), numacore which has been developed in tip/master and
  autonuma which is in aa.git.

  In almost all respects balancenuma is the dumbest of the three because
  its main impact is on the VM side with no attempt to be smart about
  scheduling.  In the interest of getting the ball rolling, it would be
  desirable to see this much merged for 3.8 with the view to building
  scheduler smarts on top and adapting the VM where required for 3.9.

  The most recent set of comparisons available from different people are

    mel:    https://lkml.org/lkml/2012/12/9/108
    mingo:  https://lkml.org/lkml/2012/12/7/331
    tglx:   https://lkml.org/lkml/2012/12/10/437
    srikar: https://lkml.org/lkml/2012/12/10/397

  The results are a mixed bag.  In my own tests, balancenuma does
  reasonably well.  It's dumb as rocks and does not regress against
  mainline.  On the other hand, Ingo's tests shows that balancenuma is
  incapable of converging for this workloads driven by perf which is bad
  but is potentially explained by the lack of scheduler smarts.  Thomas'
  results show balancenuma improves on mainline but falls far short of
  numacore or autonuma.  Srikar's results indicate we all suffer on a
  large machine with imbalanced node sizes.

  My own testing showed that recent numacore results have improved
  dramatically, particularly in the last week but not universally.
  We've butted heads heavily on system CPU usage and high levels of
  migration even when it shows that overall performance is better.
  There are also cases where it regresses.  Of interest is that for
  specjbb in some configurations it will regress for lower numbers of
  warehouses and show gains for higher numbers which is not reported by
  the tool by default and sometimes missed in treports.  Recently I
  reported for numacore that the JVM was crashing with
  NullPointerExceptions but currently it's unclear what the source of
  this problem is.  Initially I thought it was in how numacore batch
  handles PTEs but I'm no longer think this is the case.  It's possible
  numacore is just able to trigger it due to higher rates of migration.

  These reports were quite late in the cycle so I/we would like to start
  with this tree as it contains much of the code we can agree on and has
  not changed significantly over the last 2-3 weeks."

* tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma: (50 commits)
  mm/rmap, migration: Make rmap_walk_anon() and try_to_unmap_anon() more scalable
  mm/rmap: Convert the struct anon_vma::mutex to an rwsem
  mm: migrate: Account a transhuge page properly when rate limiting
  mm: numa: Account for failed allocations and isolations as migration failures
  mm: numa: Add THP migration for the NUMA working set scanning fault case build fix
  mm: numa: Add THP migration for the NUMA working set scanning fault case.
  mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node
  mm: sched: numa: Control enabling and disabling of NUMA balancing if !SCHED_DEBUG
  mm: sched: numa: Control enabling and disabling of NUMA balancing
  mm: sched: Adapt the scanning rate if a NUMA hinting fault does not migrate
  mm: numa: Use a two-stage filter to restrict pages being migrated for unlikely task<->node relationships
  mm: numa: migrate: Set last_nid on newly allocated page
  mm: numa: split_huge_page: Transfer last_nid on tail page
  mm: numa: Introduce last_nid to the page frame
  sched: numa: Slowly increase the scanning period as NUMA faults are handled
  mm: numa: Rate limit setting of pte_numa if node is saturated
  mm: numa: Rate limit the amount of memory that is migrated between nodes
  mm: numa: Structures for Migrate On Fault per NUMA migration rate limiting
  mm: numa: Migrate pages handled during a pmd_numa hinting fault
  mm: numa: Migrate on reference policy
  ...
2012-12-16 15:18:08 -08:00

557 lines
14 KiB
C

/*
* mm/mremap.c
*
* (C) Copyright 1996 Linus Torvalds
*
* Address space accounting code <alan@lxorguk.ukuu.org.uk>
* (C) Copyright 2002 Red Hat Inc, All Rights Reserved
*/
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/shm.h>
#include <linux/ksm.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/capability.h>
#include <linux/fs.h>
#include <linux/highmem.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/mmu_notifier.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include "internal.h"
static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
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(*pmd))
return NULL;
return pmd;
}
static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pgd = pgd_offset(mm, addr);
pud = pud_alloc(mm, pgd, addr);
if (!pud)
return NULL;
pmd = pmd_alloc(mm, pud, addr);
if (!pmd)
return NULL;
VM_BUG_ON(pmd_trans_huge(*pmd));
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, bool need_rmap_locks)
{
struct address_space *mapping = NULL;
struct anon_vma *anon_vma = NULL;
struct mm_struct *mm = vma->vm_mm;
pte_t *old_pte, *new_pte, pte;
spinlock_t *old_ptl, *new_ptl;
/*
* When need_rmap_locks is true, we take the i_mmap_mutex and anon_vma
* locks to ensure that rmap will always observe either the old or the
* new ptes. This is the easiest way to avoid races with
* truncate_pagecache(), page migration, etc...
*
* When need_rmap_locks is false, we use other ways to avoid
* such races:
*
* - During exec() shift_arg_pages(), we use a specially tagged vma
* which rmap call sites look for using is_vma_temporary_stack().
*
* - During mremap(), new_vma is often known to be placed after vma
* in rmap traversal order. This ensures rmap will always observe
* either the old pte, or the new pte, or both (the page table locks
* serialize access to individual ptes, but only rmap traversal
* order guarantees that we won't miss both the old and new ptes).
*/
if (need_rmap_locks) {
if (vma->vm_file) {
mapping = vma->vm_file->f_mapping;
mutex_lock(&mapping->i_mmap_mutex);
}
if (vma->anon_vma) {
anon_vma = vma->anon_vma;
anon_vma_lock_write(anon_vma);
}
}
/*
* We don't have to worry about the ordering of src and dst
* pte locks because exclusive mmap_sem prevents deadlock.
*/
old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl);
new_pte = pte_offset_map(new_pmd, new_addr);
new_ptl = pte_lockptr(mm, new_pmd);
if (new_ptl != old_ptl)
spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
arch_enter_lazy_mmu_mode();
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_get_and_clear(mm, old_addr, old_pte);
pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
set_pte_at(mm, new_addr, new_pte, pte);
}
arch_leave_lazy_mmu_mode();
if (new_ptl != old_ptl)
spin_unlock(new_ptl);
pte_unmap(new_pte - 1);
pte_unmap_unlock(old_pte - 1, old_ptl);
if (anon_vma)
anon_vma_unlock(anon_vma);
if (mapping)
mutex_unlock(&mapping->i_mmap_mutex);
}
#define LATENCY_LIMIT (64 * PAGE_SIZE)
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,
bool need_rmap_locks)
{
unsigned long extent, next, old_end;
pmd_t *old_pmd, *new_pmd;
bool need_flush = false;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
old_end = old_addr + len;
flush_cache_range(vma, old_addr, old_end);
mmun_start = old_addr;
mmun_end = old_end;
mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end);
for (; old_addr < old_end; old_addr += extent, new_addr += extent) {
cond_resched();
next = (old_addr + PMD_SIZE) & PMD_MASK;
/* even if next overflowed, extent below will be ok */
extent = next - old_addr;
if (extent > old_end - old_addr)
extent = old_end - old_addr;
old_pmd = get_old_pmd(vma->vm_mm, old_addr);
if (!old_pmd)
continue;
new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
if (!new_pmd)
break;
if (pmd_trans_huge(*old_pmd)) {
int err = 0;
if (extent == HPAGE_PMD_SIZE)
err = move_huge_pmd(vma, new_vma, old_addr,
new_addr, old_end,
old_pmd, new_pmd);
if (err > 0) {
need_flush = true;
continue;
} else if (!err) {
split_huge_page_pmd(vma, old_addr, old_pmd);
}
VM_BUG_ON(pmd_trans_huge(*old_pmd));
}
if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma,
new_pmd, new_addr))
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, need_rmap_locks);
need_flush = true;
}
if (likely(need_flush))
flush_tlb_range(vma, old_end-len, old_addr);
mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
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;
int err;
bool need_rmap_locks;
/*
* 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;
/*
* Advise KSM to break any KSM pages in the area to be moved:
* it would be confusing if they were to turn up at the new
* location, where they happen to coincide with different KSM
* pages recently unmapped. But leave vma->vm_flags as it was,
* so KSM can come around to merge on vma and new_vma afterwards.
*/
err = ksm_madvise(vma, old_addr, old_addr + old_len,
MADV_UNMERGEABLE, &vm_flags);
if (err)
return err;
new_pgoff = vma->vm_pgoff + ((old_addr - vma->vm_start) >> PAGE_SHIFT);
new_vma = copy_vma(&vma, new_addr, new_len, new_pgoff,
&need_rmap_locks);
if (!new_vma)
return -ENOMEM;
moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len,
need_rmap_locks);
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,
true);
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;
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)
mlock_vma_pages_range(new_vma, new_addr + old_len,
new_addr + new_len);
}
return new_addr;
}
static struct vm_area_struct *vma_to_resize(unsigned long addr,
unsigned long old_len, unsigned long new_len, unsigned long *p)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma = find_vma(mm, addr);
if (!vma || vma->vm_start > addr)
goto Efault;
if (is_vm_hugetlb_page(vma))
goto Einval;
/* We can't remap across vm area boundaries */
if (old_len > vma->vm_end - addr)
goto Efault;
/* Need to be careful about a growing mapping */
if (new_len > old_len) {
unsigned long pgoff;
if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP))
goto Efault;
pgoff = (addr - vma->vm_start) >> PAGE_SHIFT;
pgoff += vma->vm_pgoff;
if (pgoff + (new_len >> PAGE_SHIFT) < pgoff)
goto Einval;
}
if (vma->vm_flags & VM_LOCKED) {
unsigned long locked, lock_limit;
locked = mm->locked_vm << PAGE_SHIFT;
lock_limit = rlimit(RLIMIT_MEMLOCK);
locked += new_len - old_len;
if (locked > lock_limit && !capable(CAP_IPC_LOCK))
goto Eagain;
}
if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT))
goto Enomem;
if (vma->vm_flags & VM_ACCOUNT) {
unsigned long charged = (new_len - old_len) >> PAGE_SHIFT;
if (security_vm_enough_memory_mm(mm, charged))
goto Efault;
*p = charged;
}
return vma;
Efault: /* very odd choice for most of the cases, but... */
return ERR_PTR(-EFAULT);
Einval:
return ERR_PTR(-EINVAL);
Enomem:
return ERR_PTR(-ENOMEM);
Eagain:
return ERR_PTR(-EAGAIN);
}
static unsigned long mremap_to(unsigned long addr,
unsigned long old_len, unsigned long new_addr,
unsigned long new_len)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long ret = -EINVAL;
unsigned long charged = 0;
unsigned long map_flags;
if (new_addr & ~PAGE_MASK)
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;
if (old_len >= new_len) {
ret = do_munmap(mm, addr+new_len, old_len - new_len);
if (ret && old_len != new_len)
goto out;
old_len = new_len;
}
vma = vma_to_resize(addr, old_len, new_len, &charged);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto out;
}
map_flags = MAP_FIXED;
if (vma->vm_flags & VM_MAYSHARE)
map_flags |= MAP_SHARED;
ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff +
((addr - vma->vm_start) >> PAGE_SHIFT),
map_flags);
if (ret & ~PAGE_MASK)
goto out1;
ret = move_vma(vma, addr, old_len, new_len, new_addr);
if (!(ret & ~PAGE_MASK))
goto out;
out1:
vm_unacct_memory(charged);
out:
return ret;
}
static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
{
unsigned long end = vma->vm_end + delta;
if (end < vma->vm_end) /* overflow */
return 0;
if (vma->vm_next && vma->vm_next->vm_start < end) /* intersection */
return 0;
if (get_unmapped_area(NULL, vma->vm_start, end - vma->vm_start,
0, MAP_FIXED) & ~PAGE_MASK)
return 0;
return 1;
}
/*
* 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.
*/
SYSCALL_DEFINE5(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;
down_write(&current->mm->mmap_sem);
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;
if (flags & MREMAP_FIXED) {
if (flags & MREMAP_MAYMOVE)
ret = mremap_to(addr, old_len, new_addr, new_len);
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;
goto out;
}
/*
* Ok, we need to grow..
*/
vma = vma_to_resize(addr, old_len, new_len, &charged);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto out;
}
/* old_len exactly to the end of the area..
*/
if (old_len == vma->vm_end - addr) {
/* can we just expand the current mapping? */
if (vma_expandable(vma, new_len - old_len)) {
int pages = (new_len - old_len) >> PAGE_SHIFT;
if (vma_adjust(vma, vma->vm_start, addr + new_len,
vma->vm_pgoff, NULL)) {
ret = -ENOMEM;
goto out;
}
vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages);
if (vma->vm_flags & VM_LOCKED) {
mm->locked_vm += pages;
mlock_vma_pages_range(vma, 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) {
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 +
((addr - vma->vm_start) >> PAGE_SHIFT),
map_flags);
if (new_addr & ~PAGE_MASK) {
ret = new_addr;
goto out;
}
ret = move_vma(vma, addr, old_len, new_len, new_addr);
}
out:
if (ret & ~PAGE_MASK)
vm_unacct_memory(charged);
up_write(&current->mm->mmap_sem);
return ret;
}