linux-stable/mm/madvise.c
Minchan Kim b8d3c4c300 mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called
We don't need to split THP page when MADV_FREE syscall is called if
[start, len] is aligned with THP size.  The split could be done when VM
decide to free it in reclaim path if memory pressure is heavy.  With
that, we could avoid unnecessary THP split.

For the feature, this patch changes pte dirtness marking logic of THP.
Now, it marks every ptes of pages dirty unconditionally in splitting,
which makes MADV_FREE void.  So, instead, this patch propagates pmd
dirtiness to all pages via PG_dirty and restores pte dirtiness from
PG_dirty.  With this, if pmd is clean(ie, MADV_FREEed) when split
happens(e,g, shrink_page_list), all of pages are clean too so we could
discard them.

Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Shaohua Li <shli@kernel.org>
Cc: <yalin.wang2010@gmail.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chen Gang <gang.chen.5i5j@gmail.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Daniel Micay <danielmicay@gmail.com>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Helge Deller <deller@gmx.de>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Jason Evans <je@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mika Penttil <mika.penttila@nextfour.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Rik van Riel <riel@redhat.com>
Cc: Roland Dreier <roland@kernel.org>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Shaohua Li <shli@kernel.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-15 17:56:32 -08:00

752 lines
18 KiB
C

/*
* linux/mm/madvise.c
*
* Copyright (C) 1999 Linus Torvalds
* Copyright (C) 2002 Christoph Hellwig
*/
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/mempolicy.h>
#include <linux/page-isolation.h>
#include <linux/hugetlb.h>
#include <linux/falloc.h>
#include <linux/sched.h>
#include <linux/ksm.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mmu_notifier.h>
#include <asm/tlb.h>
/*
* Any behaviour which results in changes to the vma->vm_flags needs to
* take mmap_sem for writing. Others, which simply traverse vmas, need
* to only take it for reading.
*/
static int madvise_need_mmap_write(int behavior)
{
switch (behavior) {
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
case MADV_FREE:
return 0;
default:
/* be safe, default to 1. list exceptions explicitly */
return 1;
}
}
/*
* We can potentially split a vm area into separate
* areas, each area with its own behavior.
*/
static long madvise_behavior(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end, int behavior)
{
struct mm_struct *mm = vma->vm_mm;
int error = 0;
pgoff_t pgoff;
unsigned long new_flags = vma->vm_flags;
switch (behavior) {
case MADV_NORMAL:
new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ;
break;
case MADV_SEQUENTIAL:
new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ;
break;
case MADV_RANDOM:
new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ;
break;
case MADV_DONTFORK:
new_flags |= VM_DONTCOPY;
break;
case MADV_DOFORK:
if (vma->vm_flags & VM_IO) {
error = -EINVAL;
goto out;
}
new_flags &= ~VM_DONTCOPY;
break;
case MADV_DONTDUMP:
new_flags |= VM_DONTDUMP;
break;
case MADV_DODUMP:
if (new_flags & VM_SPECIAL) {
error = -EINVAL;
goto out;
}
new_flags &= ~VM_DONTDUMP;
break;
case MADV_MERGEABLE:
case MADV_UNMERGEABLE:
error = ksm_madvise(vma, start, end, behavior, &new_flags);
if (error)
goto out;
break;
case MADV_HUGEPAGE:
case MADV_NOHUGEPAGE:
error = hugepage_madvise(vma, &new_flags, behavior);
if (error)
goto out;
break;
}
if (new_flags == vma->vm_flags) {
*prev = vma;
goto out;
}
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma,
vma->vm_file, pgoff, vma_policy(vma),
vma->vm_userfaultfd_ctx);
if (*prev) {
vma = *prev;
goto success;
}
*prev = vma;
if (start != vma->vm_start) {
error = split_vma(mm, vma, start, 1);
if (error)
goto out;
}
if (end != vma->vm_end) {
error = split_vma(mm, vma, end, 0);
if (error)
goto out;
}
success:
/*
* vm_flags is protected by the mmap_sem held in write mode.
*/
vma->vm_flags = new_flags;
out:
if (error == -ENOMEM)
error = -EAGAIN;
return error;
}
#ifdef CONFIG_SWAP
static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
unsigned long end, struct mm_walk *walk)
{
pte_t *orig_pte;
struct vm_area_struct *vma = walk->private;
unsigned long index;
if (pmd_none_or_trans_huge_or_clear_bad(pmd))
return 0;
for (index = start; index != end; index += PAGE_SIZE) {
pte_t pte;
swp_entry_t entry;
struct page *page;
spinlock_t *ptl;
orig_pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
pte = *(orig_pte + ((index - start) / PAGE_SIZE));
pte_unmap_unlock(orig_pte, ptl);
if (pte_present(pte) || pte_none(pte))
continue;
entry = pte_to_swp_entry(pte);
if (unlikely(non_swap_entry(entry)))
continue;
page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
vma, index);
if (page)
page_cache_release(page);
}
return 0;
}
static void force_swapin_readahead(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
struct mm_walk walk = {
.mm = vma->vm_mm,
.pmd_entry = swapin_walk_pmd_entry,
.private = vma,
};
walk_page_range(start, end, &walk);
lru_add_drain(); /* Push any new pages onto the LRU now */
}
static void force_shm_swapin_readahead(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct address_space *mapping)
{
pgoff_t index;
struct page *page;
swp_entry_t swap;
for (; start < end; start += PAGE_SIZE) {
index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
page = find_get_entry(mapping, index);
if (!radix_tree_exceptional_entry(page)) {
if (page)
page_cache_release(page);
continue;
}
swap = radix_to_swp_entry(page);
page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
NULL, 0);
if (page)
page_cache_release(page);
}
lru_add_drain(); /* Push any new pages onto the LRU now */
}
#endif /* CONFIG_SWAP */
/*
* Schedule all required I/O operations. Do not wait for completion.
*/
static long madvise_willneed(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
struct file *file = vma->vm_file;
#ifdef CONFIG_SWAP
if (!file) {
*prev = vma;
force_swapin_readahead(vma, start, end);
return 0;
}
if (shmem_mapping(file->f_mapping)) {
*prev = vma;
force_shm_swapin_readahead(vma, start, end,
file->f_mapping);
return 0;
}
#else
if (!file)
return -EBADF;
#endif
if (IS_DAX(file_inode(file))) {
/* no bad return value, but ignore advice */
return 0;
}
*prev = vma;
start = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
if (end > vma->vm_end)
end = vma->vm_end;
end = ((end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
force_page_cache_readahead(file->f_mapping, file, start, end - start);
return 0;
}
static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct mmu_gather *tlb = walk->private;
struct mm_struct *mm = tlb->mm;
struct vm_area_struct *vma = walk->vma;
spinlock_t *ptl;
pte_t *orig_pte, *pte, ptent;
struct page *page;
int nr_swap = 0;
unsigned long next;
next = pmd_addr_end(addr, end);
if (pmd_trans_huge(*pmd))
if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next))
goto next;
if (pmd_trans_unstable(pmd))
return 0;
orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
arch_enter_lazy_mmu_mode();
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
if (pte_none(ptent))
continue;
/*
* If the pte has swp_entry, just clear page table to
* prevent swap-in which is more expensive rather than
* (page allocation + zeroing).
*/
if (!pte_present(ptent)) {
swp_entry_t entry;
entry = pte_to_swp_entry(ptent);
if (non_swap_entry(entry))
continue;
nr_swap--;
free_swap_and_cache(entry);
pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
continue;
}
page = vm_normal_page(vma, addr, ptent);
if (!page)
continue;
/*
* If pmd isn't transhuge but the page is THP and
* is owned by only this process, split it and
* deactivate all pages.
*/
if (PageTransCompound(page)) {
if (page_mapcount(page) != 1)
goto out;
get_page(page);
if (!trylock_page(page)) {
put_page(page);
goto out;
}
pte_unmap_unlock(orig_pte, ptl);
if (split_huge_page(page)) {
unlock_page(page);
put_page(page);
pte_offset_map_lock(mm, pmd, addr, &ptl);
goto out;
}
put_page(page);
unlock_page(page);
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
pte--;
addr -= PAGE_SIZE;
continue;
}
VM_BUG_ON_PAGE(PageTransCompound(page), page);
if (PageSwapCache(page) || PageDirty(page)) {
if (!trylock_page(page))
continue;
/*
* If page is shared with others, we couldn't clear
* PG_dirty of the page.
*/
if (page_mapcount(page) != 1) {
unlock_page(page);
continue;
}
if (PageSwapCache(page) && !try_to_free_swap(page)) {
unlock_page(page);
continue;
}
ClearPageDirty(page);
unlock_page(page);
}
if (pte_young(ptent) || pte_dirty(ptent)) {
/*
* Some of architecture(ex, PPC) don't update TLB
* with set_pte_at and tlb_remove_tlb_entry so for
* the portability, remap the pte with old|clean
* after pte clearing.
*/
ptent = ptep_get_and_clear_full(mm, addr, pte,
tlb->fullmm);
ptent = pte_mkold(ptent);
ptent = pte_mkclean(ptent);
set_pte_at(mm, addr, pte, ptent);
if (PageActive(page))
deactivate_page(page);
tlb_remove_tlb_entry(tlb, pte, addr);
}
}
out:
if (nr_swap) {
if (current->mm == mm)
sync_mm_rss(mm);
add_mm_counter(mm, MM_SWAPENTS, nr_swap);
}
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(orig_pte, ptl);
cond_resched();
next:
return 0;
}
static void madvise_free_page_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
struct mm_walk free_walk = {
.pmd_entry = madvise_free_pte_range,
.mm = vma->vm_mm,
.private = tlb,
};
tlb_start_vma(tlb, vma);
walk_page_range(addr, end, &free_walk);
tlb_end_vma(tlb, vma);
}
static int madvise_free_single_vma(struct vm_area_struct *vma,
unsigned long start_addr, unsigned long end_addr)
{
unsigned long start, end;
struct mm_struct *mm = vma->vm_mm;
struct mmu_gather tlb;
if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
return -EINVAL;
/* MADV_FREE works for only anon vma at the moment */
if (!vma_is_anonymous(vma))
return -EINVAL;
start = max(vma->vm_start, start_addr);
if (start >= vma->vm_end)
return -EINVAL;
end = min(vma->vm_end, end_addr);
if (end <= vma->vm_start)
return -EINVAL;
lru_add_drain();
tlb_gather_mmu(&tlb, mm, start, end);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(mm, start, end);
madvise_free_page_range(&tlb, vma, start, end);
mmu_notifier_invalidate_range_end(mm, start, end);
tlb_finish_mmu(&tlb, start, end);
return 0;
}
static long madvise_free(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
*prev = vma;
return madvise_free_single_vma(vma, start, end);
}
/*
* Application no longer needs these pages. If the pages are dirty,
* it's OK to just throw them away. The app will be more careful about
* data it wants to keep. Be sure to free swap resources too. The
* zap_page_range call sets things up for shrink_active_list to actually free
* these pages later if no one else has touched them in the meantime,
* although we could add these pages to a global reuse list for
* shrink_active_list to pick up before reclaiming other pages.
*
* NB: This interface discards data rather than pushes it out to swap,
* as some implementations do. This has performance implications for
* applications like large transactional databases which want to discard
* pages in anonymous maps after committing to backing store the data
* that was kept in them. There is no reason to write this data out to
* the swap area if the application is discarding it.
*
* An interface that causes the system to free clean pages and flush
* dirty pages is already available as msync(MS_INVALIDATE).
*/
static long madvise_dontneed(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
*prev = vma;
if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
return -EINVAL;
zap_page_range(vma, start, end - start, NULL);
return 0;
}
/*
* Application wants to free up the pages and associated backing store.
* This is effectively punching a hole into the middle of a file.
*/
static long madvise_remove(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
loff_t offset;
int error;
struct file *f;
*prev = NULL; /* tell sys_madvise we drop mmap_sem */
if (vma->vm_flags & VM_LOCKED)
return -EINVAL;
f = vma->vm_file;
if (!f || !f->f_mapping || !f->f_mapping->host) {
return -EINVAL;
}
if ((vma->vm_flags & (VM_SHARED|VM_WRITE)) != (VM_SHARED|VM_WRITE))
return -EACCES;
offset = (loff_t)(start - vma->vm_start)
+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
/*
* Filesystem's fallocate may need to take i_mutex. We need to
* explicitly grab a reference because the vma (and hence the
* vma's reference to the file) can go away as soon as we drop
* mmap_sem.
*/
get_file(f);
up_read(&current->mm->mmap_sem);
error = vfs_fallocate(f,
FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
offset, end - start);
fput(f);
down_read(&current->mm->mmap_sem);
return error;
}
#ifdef CONFIG_MEMORY_FAILURE
/*
* Error injection support for memory error handling.
*/
static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
{
struct page *p;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
for (; start < end; start += PAGE_SIZE <<
compound_order(compound_head(p))) {
int ret;
ret = get_user_pages_fast(start, 1, 0, &p);
if (ret != 1)
return ret;
if (PageHWPoison(p)) {
put_page(p);
continue;
}
if (bhv == MADV_SOFT_OFFLINE) {
pr_info("Soft offlining page %#lx at %#lx\n",
page_to_pfn(p), start);
ret = soft_offline_page(p, MF_COUNT_INCREASED);
if (ret)
return ret;
continue;
}
pr_info("Injecting memory failure for page %#lx at %#lx\n",
page_to_pfn(p), start);
/* Ignore return value for now */
memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
}
return 0;
}
#endif
static long
madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
unsigned long start, unsigned long end, int behavior)
{
switch (behavior) {
case MADV_REMOVE:
return madvise_remove(vma, prev, start, end);
case MADV_WILLNEED:
return madvise_willneed(vma, prev, start, end);
case MADV_FREE:
/*
* XXX: In this implementation, MADV_FREE works like
* MADV_DONTNEED on swapless system or full swap.
*/
if (get_nr_swap_pages() > 0)
return madvise_free(vma, prev, start, end);
/* passthrough */
case MADV_DONTNEED:
return madvise_dontneed(vma, prev, start, end);
default:
return madvise_behavior(vma, prev, start, end, behavior);
}
}
static bool
madvise_behavior_valid(int behavior)
{
switch (behavior) {
case MADV_DOFORK:
case MADV_DONTFORK:
case MADV_NORMAL:
case MADV_SEQUENTIAL:
case MADV_RANDOM:
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
case MADV_FREE:
#ifdef CONFIG_KSM
case MADV_MERGEABLE:
case MADV_UNMERGEABLE:
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
case MADV_HUGEPAGE:
case MADV_NOHUGEPAGE:
#endif
case MADV_DONTDUMP:
case MADV_DODUMP:
return true;
default:
return false;
}
}
/*
* The madvise(2) system call.
*
* Applications can use madvise() to advise the kernel how it should
* handle paging I/O in this VM area. The idea is to help the kernel
* use appropriate read-ahead and caching techniques. The information
* provided is advisory only, and can be safely disregarded by the
* kernel without affecting the correct operation of the application.
*
* behavior values:
* MADV_NORMAL - the default behavior is to read clusters. This
* results in some read-ahead and read-behind.
* MADV_RANDOM - the system should read the minimum amount of data
* on any access, since it is unlikely that the appli-
* cation will need more than what it asks for.
* MADV_SEQUENTIAL - pages in the given range will probably be accessed
* once, so they can be aggressively read ahead, and
* can be freed soon after they are accessed.
* MADV_WILLNEED - the application is notifying the system to read
* some pages ahead.
* MADV_DONTNEED - the application is finished with the given range,
* so the kernel can free resources associated with it.
* MADV_REMOVE - the application wants to free up the given range of
* pages and associated backing store.
* MADV_DONTFORK - omit this area from child's address space when forking:
* typically, to avoid COWing pages pinned by get_user_pages().
* MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking.
* MADV_MERGEABLE - the application recommends that KSM try to merge pages in
* this area with pages of identical content from other such areas.
* MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others.
*
* return values:
* zero - success
* -EINVAL - start + len < 0, start is not page-aligned,
* "behavior" is not a valid value, or application
* is attempting to release locked or shared pages.
* -ENOMEM - addresses in the specified range are not currently
* mapped, or are outside the AS of the process.
* -EIO - an I/O error occurred while paging in data.
* -EBADF - map exists, but area maps something that isn't a file.
* -EAGAIN - a kernel resource was temporarily unavailable.
*/
SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
{
unsigned long end, tmp;
struct vm_area_struct *vma, *prev;
int unmapped_error = 0;
int error = -EINVAL;
int write;
size_t len;
struct blk_plug plug;
#ifdef CONFIG_MEMORY_FAILURE
if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE)
return madvise_hwpoison(behavior, start, start+len_in);
#endif
if (!madvise_behavior_valid(behavior))
return error;
if (start & ~PAGE_MASK)
return error;
len = (len_in + ~PAGE_MASK) & PAGE_MASK;
/* Check to see whether len was rounded up from small -ve to zero */
if (len_in && !len)
return error;
end = start + len;
if (end < start)
return error;
error = 0;
if (end == start)
return error;
write = madvise_need_mmap_write(behavior);
if (write)
down_write(&current->mm->mmap_sem);
else
down_read(&current->mm->mmap_sem);
/*
* If the interval [start,end) covers some unmapped address
* ranges, just ignore them, but return -ENOMEM at the end.
* - different from the way of handling in mlock etc.
*/
vma = find_vma_prev(current->mm, start, &prev);
if (vma && start > vma->vm_start)
prev = vma;
blk_start_plug(&plug);
for (;;) {
/* Still start < end. */
error = -ENOMEM;
if (!vma)
goto out;
/* Here start < (end|vma->vm_end). */
if (start < vma->vm_start) {
unmapped_error = -ENOMEM;
start = vma->vm_start;
if (start >= end)
goto out;
}
/* Here vma->vm_start <= start < (end|vma->vm_end) */
tmp = vma->vm_end;
if (end < tmp)
tmp = end;
/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
error = madvise_vma(vma, &prev, start, tmp, behavior);
if (error)
goto out;
start = tmp;
if (prev && start < prev->vm_end)
start = prev->vm_end;
error = unmapped_error;
if (start >= end)
goto out;
if (prev)
vma = prev->vm_next;
else /* madvise_remove dropped mmap_sem */
vma = find_vma(current->mm, start);
}
out:
blk_finish_plug(&plug);
if (write)
up_write(&current->mm->mmap_sem);
else
up_read(&current->mm->mmap_sem);
return error;
}