linux/mm/mremap.c
Andrea Arcangeli 37a1c49a91 thp: mremap support and TLB optimization
This adds THP support to mremap (decreases the number of split_huge_page()
calls).

Here are also some benchmarks with a proggy like this:

===
#define _GNU_SOURCE
#include <sys/mman.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <sys/time.h>

#define SIZE (5UL*1024*1024*1024)

int main()
{
        static struct timeval oldstamp, newstamp;
	long diffsec;
	char *p, *p2, *p3, *p4;
	if (posix_memalign((void **)&p, 2*1024*1024, SIZE))
		perror("memalign"), exit(1);
	if (posix_memalign((void **)&p2, 2*1024*1024, SIZE))
		perror("memalign"), exit(1);
	if (posix_memalign((void **)&p3, 2*1024*1024, 4096))
		perror("memalign"), exit(1);

	memset(p, 0xff, SIZE);
	memset(p2, 0xff, SIZE);
	memset(p3, 0x77, 4096);
	gettimeofday(&oldstamp, NULL);
	p4 = mremap(p, SIZE, SIZE, MREMAP_FIXED|MREMAP_MAYMOVE, p3);
	gettimeofday(&newstamp, NULL);
	diffsec = newstamp.tv_sec - oldstamp.tv_sec;
	diffsec = newstamp.tv_usec - oldstamp.tv_usec + 1000000 * diffsec;
	printf("usec %ld\n", diffsec);
	if (p == MAP_FAILED || p4 != p3)
	//if (p == MAP_FAILED)
		perror("mremap"), exit(1);
	if (memcmp(p4, p2, SIZE))
		printf("mremap bug\n"), exit(1);
	printf("ok\n");

	return 0;
}
===

THP on

 Performance counter stats for './largepage13' (3 runs):

          69195836 dTLB-loads                 ( +-   3.546% )  (scaled from 50.30%)
             60708 dTLB-load-misses           ( +-  11.776% )  (scaled from 52.62%)
         676266476 dTLB-stores                ( +-   5.654% )  (scaled from 69.54%)
             29856 dTLB-store-misses          ( +-   4.081% )  (scaled from 89.22%)
        1055848782 iTLB-loads                 ( +-   4.526% )  (scaled from 80.18%)
              8689 iTLB-load-misses           ( +-   2.987% )  (scaled from 58.20%)

        7.314454164  seconds time elapsed   ( +-   0.023% )

THP off

 Performance counter stats for './largepage13' (3 runs):

        1967379311 dTLB-loads                 ( +-   0.506% )  (scaled from 60.59%)
           9238687 dTLB-load-misses           ( +-  22.547% )  (scaled from 61.87%)
        2014239444 dTLB-stores                ( +-   0.692% )  (scaled from 60.40%)
           3312335 dTLB-store-misses          ( +-   7.304% )  (scaled from 67.60%)
        6764372065 iTLB-loads                 ( +-   0.925% )  (scaled from 79.00%)
              8202 iTLB-load-misses           ( +-   0.475% )  (scaled from 70.55%)

        9.693655243  seconds time elapsed   ( +-   0.069% )

grep thp /proc/vmstat
thp_fault_alloc 35849
thp_fault_fallback 0
thp_collapse_alloc 3
thp_collapse_alloc_failed 0
thp_split 0

thp_split 0 confirms no thp split despite plenty of hugepages allocated.

The measurement of only the mremap time (so excluding the 3 long
memset and final long 10GB memory accessing memcmp):

THP on

usec 14824
usec 14862
usec 14859

THP off

usec 256416
usec 255981
usec 255847

With an older kernel without the mremap optimizations (the below patch
optimizes the non THP version too).

THP on

usec 392107
usec 390237
usec 404124

THP off

usec 444294
usec 445237
usec 445820

I guess with a threaded program that sends more IPI on large SMP it'd
create an even larger difference.

All debug options are off except DEBUG_VM to avoid skewing the
results.

The only problem for native 2M mremap like it happens above both the
source and destination address must be 2M aligned or the hugepmd can't be
moved without a split but that is an hardware limitation.

[akpm@linux-foundation.org: coding-style nitpicking]
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Johannes Weiner <jweiner@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-10-31 17:30:48 -07:00

545 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)
{
struct address_space *mapping = NULL;
struct mm_struct *mm = vma->vm_mm;
pte_t *old_pte, *new_pte, pte;
spinlock_t *old_ptl, *new_ptl;
if (vma->vm_file) {
/*
* Subtle point from Rajesh Venkatasubramanian: before
* moving file-based ptes, we must lock truncate_pagecache
* 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;
mutex_lock(&mapping->i_mmap_mutex);
}
/*
* 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 (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)
{
unsigned long extent, next, old_end;
pmd_t *old_pmd, *new_pmd;
bool need_flush = false;
old_end = old_addr + len;
flush_cache_range(vma, old_addr, old_end);
mmu_notifier_invalidate_range_start(vma->vm_mm, old_addr, old_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->vm_mm, 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_flush = true;
}
if (likely(need_flush))
flush_tlb_range(vma, old_end-len, old_addr);
mmu_notifier_invalidate_range_end(vma->vm_mm, old_end-len, old_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;
/*
* 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);
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)
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(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 = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
if (ret)
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.
*/
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;
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;
}
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;
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 = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
if (ret)
goto out;
ret = move_vma(vma, addr, old_len, new_len, new_addr);
}
out:
if (ret & ~PAGE_MASK)
vm_unacct_memory(charged);
return ret;
}
SYSCALL_DEFINE5(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;
}