1149 lines
29 KiB
C
1149 lines
29 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* 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/page_idle.h>
|
|
#include <linux/userfaultfd_k.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/falloc.h>
|
|
#include <linux/fadvise.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/pagewalk.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/swapops.h>
|
|
#include <linux/shmem_fs.h>
|
|
#include <linux/mmu_notifier.h>
|
|
|
|
#include <asm/tlb.h>
|
|
|
|
#include "internal.h"
|
|
|
|
struct madvise_walk_private {
|
|
struct mmu_gather *tlb;
|
|
bool pageout;
|
|
};
|
|
|
|
/*
|
|
* 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_COLD:
|
|
case MADV_PAGEOUT:
|
|
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_WIPEONFORK:
|
|
/* MADV_WIPEONFORK is only supported on anonymous memory. */
|
|
if (vma->vm_file || vma->vm_flags & VM_SHARED) {
|
|
error = -EINVAL;
|
|
goto out;
|
|
}
|
|
new_flags |= VM_WIPEONFORK;
|
|
break;
|
|
case MADV_KEEPONFORK:
|
|
new_flags &= ~VM_WIPEONFORK;
|
|
break;
|
|
case MADV_DONTDUMP:
|
|
new_flags |= VM_DONTDUMP;
|
|
break;
|
|
case MADV_DODUMP:
|
|
if (!is_vm_hugetlb_page(vma) && 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_convert_errno;
|
|
break;
|
|
case MADV_HUGEPAGE:
|
|
case MADV_NOHUGEPAGE:
|
|
error = hugepage_madvise(vma, &new_flags, behavior);
|
|
if (error)
|
|
goto out_convert_errno;
|
|
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) {
|
|
if (unlikely(mm->map_count >= sysctl_max_map_count)) {
|
|
error = -ENOMEM;
|
|
goto out;
|
|
}
|
|
error = __split_vma(mm, vma, start, 1);
|
|
if (error)
|
|
goto out_convert_errno;
|
|
}
|
|
|
|
if (end != vma->vm_end) {
|
|
if (unlikely(mm->map_count >= sysctl_max_map_count)) {
|
|
error = -ENOMEM;
|
|
goto out;
|
|
}
|
|
error = __split_vma(mm, vma, end, 0);
|
|
if (error)
|
|
goto out_convert_errno;
|
|
}
|
|
|
|
success:
|
|
/*
|
|
* vm_flags is protected by the mmap_sem held in write mode.
|
|
*/
|
|
vma->vm_flags = new_flags;
|
|
|
|
out_convert_errno:
|
|
/*
|
|
* madvise() returns EAGAIN if kernel resources, such as
|
|
* slab, are temporarily unavailable.
|
|
*/
|
|
if (error == -ENOMEM)
|
|
error = -EAGAIN;
|
|
out:
|
|
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, false);
|
|
if (page)
|
|
put_page(page);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct mm_walk_ops swapin_walk_ops = {
|
|
.pmd_entry = swapin_walk_pmd_entry,
|
|
};
|
|
|
|
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 (!xa_is_value(page)) {
|
|
if (page)
|
|
put_page(page);
|
|
continue;
|
|
}
|
|
swap = radix_to_swp_entry(page);
|
|
page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
|
|
NULL, 0, false);
|
|
if (page)
|
|
put_page(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;
|
|
loff_t offset;
|
|
|
|
*prev = vma;
|
|
#ifdef CONFIG_SWAP
|
|
if (!file) {
|
|
walk_page_range(vma->vm_mm, start, end, &swapin_walk_ops, vma);
|
|
lru_add_drain(); /* Push any new pages onto the LRU now */
|
|
return 0;
|
|
}
|
|
|
|
if (shmem_mapping(file->f_mapping)) {
|
|
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;
|
|
}
|
|
|
|
/*
|
|
* Filesystem's fadvise may need to take various locks. 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.
|
|
*/
|
|
*prev = NULL; /* tell sys_madvise we drop mmap_sem */
|
|
get_file(file);
|
|
up_read(¤t->mm->mmap_sem);
|
|
offset = (loff_t)(start - vma->vm_start)
|
|
+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
|
|
vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
|
|
fput(file);
|
|
down_read(¤t->mm->mmap_sem);
|
|
return 0;
|
|
}
|
|
|
|
static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
|
|
unsigned long addr, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
struct madvise_walk_private *private = walk->private;
|
|
struct mmu_gather *tlb = private->tlb;
|
|
bool pageout = private->pageout;
|
|
struct mm_struct *mm = tlb->mm;
|
|
struct vm_area_struct *vma = walk->vma;
|
|
pte_t *orig_pte, *pte, ptent;
|
|
spinlock_t *ptl;
|
|
struct page *page = NULL;
|
|
LIST_HEAD(page_list);
|
|
|
|
if (fatal_signal_pending(current))
|
|
return -EINTR;
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
if (pmd_trans_huge(*pmd)) {
|
|
pmd_t orig_pmd;
|
|
unsigned long next = pmd_addr_end(addr, end);
|
|
|
|
tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
|
|
ptl = pmd_trans_huge_lock(pmd, vma);
|
|
if (!ptl)
|
|
return 0;
|
|
|
|
orig_pmd = *pmd;
|
|
if (is_huge_zero_pmd(orig_pmd))
|
|
goto huge_unlock;
|
|
|
|
if (unlikely(!pmd_present(orig_pmd))) {
|
|
VM_BUG_ON(thp_migration_supported() &&
|
|
!is_pmd_migration_entry(orig_pmd));
|
|
goto huge_unlock;
|
|
}
|
|
|
|
page = pmd_page(orig_pmd);
|
|
if (next - addr != HPAGE_PMD_SIZE) {
|
|
int err;
|
|
|
|
if (page_mapcount(page) != 1)
|
|
goto huge_unlock;
|
|
|
|
get_page(page);
|
|
spin_unlock(ptl);
|
|
lock_page(page);
|
|
err = split_huge_page(page);
|
|
unlock_page(page);
|
|
put_page(page);
|
|
if (!err)
|
|
goto regular_page;
|
|
return 0;
|
|
}
|
|
|
|
if (pmd_young(orig_pmd)) {
|
|
pmdp_invalidate(vma, addr, pmd);
|
|
orig_pmd = pmd_mkold(orig_pmd);
|
|
|
|
set_pmd_at(mm, addr, pmd, orig_pmd);
|
|
tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
|
|
}
|
|
|
|
ClearPageReferenced(page);
|
|
test_and_clear_page_young(page);
|
|
if (pageout) {
|
|
if (!isolate_lru_page(page)) {
|
|
if (PageUnevictable(page))
|
|
putback_lru_page(page);
|
|
else
|
|
list_add(&page->lru, &page_list);
|
|
}
|
|
} else
|
|
deactivate_page(page);
|
|
huge_unlock:
|
|
spin_unlock(ptl);
|
|
if (pageout)
|
|
reclaim_pages(&page_list);
|
|
return 0;
|
|
}
|
|
|
|
if (pmd_trans_unstable(pmd))
|
|
return 0;
|
|
regular_page:
|
|
#endif
|
|
tlb_change_page_size(tlb, PAGE_SIZE);
|
|
orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
|
|
flush_tlb_batched_pending(mm);
|
|
arch_enter_lazy_mmu_mode();
|
|
for (; addr < end; pte++, addr += PAGE_SIZE) {
|
|
ptent = *pte;
|
|
|
|
if (pte_none(ptent))
|
|
continue;
|
|
|
|
if (!pte_present(ptent))
|
|
continue;
|
|
|
|
page = vm_normal_page(vma, addr, ptent);
|
|
if (!page)
|
|
continue;
|
|
|
|
/*
|
|
* Creating a THP page is expensive so split it only if we
|
|
* are sure it's worth. Split it if we are only owner.
|
|
*/
|
|
if (PageTransCompound(page)) {
|
|
if (page_mapcount(page) != 1)
|
|
break;
|
|
get_page(page);
|
|
if (!trylock_page(page)) {
|
|
put_page(page);
|
|
break;
|
|
}
|
|
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);
|
|
break;
|
|
}
|
|
unlock_page(page);
|
|
put_page(page);
|
|
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
|
|
pte--;
|
|
addr -= PAGE_SIZE;
|
|
continue;
|
|
}
|
|
|
|
VM_BUG_ON_PAGE(PageTransCompound(page), page);
|
|
|
|
if (pte_young(ptent)) {
|
|
ptent = ptep_get_and_clear_full(mm, addr, pte,
|
|
tlb->fullmm);
|
|
ptent = pte_mkold(ptent);
|
|
set_pte_at(mm, addr, pte, ptent);
|
|
tlb_remove_tlb_entry(tlb, pte, addr);
|
|
}
|
|
|
|
/*
|
|
* We are deactivating a page for accelerating reclaiming.
|
|
* VM couldn't reclaim the page unless we clear PG_young.
|
|
* As a side effect, it makes confuse idle-page tracking
|
|
* because they will miss recent referenced history.
|
|
*/
|
|
ClearPageReferenced(page);
|
|
test_and_clear_page_young(page);
|
|
if (pageout) {
|
|
if (!isolate_lru_page(page)) {
|
|
if (PageUnevictable(page))
|
|
putback_lru_page(page);
|
|
else
|
|
list_add(&page->lru, &page_list);
|
|
}
|
|
} else
|
|
deactivate_page(page);
|
|
}
|
|
|
|
arch_leave_lazy_mmu_mode();
|
|
pte_unmap_unlock(orig_pte, ptl);
|
|
if (pageout)
|
|
reclaim_pages(&page_list);
|
|
cond_resched();
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct mm_walk_ops cold_walk_ops = {
|
|
.pmd_entry = madvise_cold_or_pageout_pte_range,
|
|
};
|
|
|
|
static void madvise_cold_page_range(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
unsigned long addr, unsigned long end)
|
|
{
|
|
struct madvise_walk_private walk_private = {
|
|
.pageout = false,
|
|
.tlb = tlb,
|
|
};
|
|
|
|
tlb_start_vma(tlb, vma);
|
|
walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private);
|
|
tlb_end_vma(tlb, vma);
|
|
}
|
|
|
|
static long madvise_cold(struct vm_area_struct *vma,
|
|
struct vm_area_struct **prev,
|
|
unsigned long start_addr, unsigned long end_addr)
|
|
{
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
struct mmu_gather tlb;
|
|
|
|
*prev = vma;
|
|
if (!can_madv_lru_vma(vma))
|
|
return -EINVAL;
|
|
|
|
lru_add_drain();
|
|
tlb_gather_mmu(&tlb, mm, start_addr, end_addr);
|
|
madvise_cold_page_range(&tlb, vma, start_addr, end_addr);
|
|
tlb_finish_mmu(&tlb, start_addr, end_addr);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void madvise_pageout_page_range(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
unsigned long addr, unsigned long end)
|
|
{
|
|
struct madvise_walk_private walk_private = {
|
|
.pageout = true,
|
|
.tlb = tlb,
|
|
};
|
|
|
|
tlb_start_vma(tlb, vma);
|
|
walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private);
|
|
tlb_end_vma(tlb, vma);
|
|
}
|
|
|
|
static inline bool can_do_pageout(struct vm_area_struct *vma)
|
|
{
|
|
if (vma_is_anonymous(vma))
|
|
return true;
|
|
if (!vma->vm_file)
|
|
return false;
|
|
/*
|
|
* paging out pagecache only for non-anonymous mappings that correspond
|
|
* to the files the calling process could (if tried) open for writing;
|
|
* otherwise we'd be including shared non-exclusive mappings, which
|
|
* opens a side channel.
|
|
*/
|
|
return inode_owner_or_capable(file_inode(vma->vm_file)) ||
|
|
inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0;
|
|
}
|
|
|
|
static long madvise_pageout(struct vm_area_struct *vma,
|
|
struct vm_area_struct **prev,
|
|
unsigned long start_addr, unsigned long end_addr)
|
|
{
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
struct mmu_gather tlb;
|
|
|
|
*prev = vma;
|
|
if (!can_madv_lru_vma(vma))
|
|
return -EINVAL;
|
|
|
|
if (!can_do_pageout(vma))
|
|
return 0;
|
|
|
|
lru_add_drain();
|
|
tlb_gather_mmu(&tlb, mm, start_addr, end_addr);
|
|
madvise_pageout_page_range(&tlb, vma, start_addr, end_addr);
|
|
tlb_finish_mmu(&tlb, start_addr, end_addr);
|
|
|
|
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;
|
|
|
|
tlb_change_page_size(tlb, PAGE_SIZE);
|
|
orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
|
|
flush_tlb_batched_pending(mm);
|
|
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;
|
|
}
|
|
unlock_page(page);
|
|
put_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);
|
|
tlb_remove_tlb_entry(tlb, pte, addr);
|
|
}
|
|
mark_page_lazyfree(page);
|
|
}
|
|
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 const struct mm_walk_ops madvise_free_walk_ops = {
|
|
.pmd_entry = madvise_free_pte_range,
|
|
};
|
|
|
|
static int madvise_free_single_vma(struct vm_area_struct *vma,
|
|
unsigned long start_addr, unsigned long end_addr)
|
|
{
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
struct mmu_notifier_range range;
|
|
struct mmu_gather tlb;
|
|
|
|
/* MADV_FREE works for only anon vma at the moment */
|
|
if (!vma_is_anonymous(vma))
|
|
return -EINVAL;
|
|
|
|
range.start = max(vma->vm_start, start_addr);
|
|
if (range.start >= vma->vm_end)
|
|
return -EINVAL;
|
|
range.end = min(vma->vm_end, end_addr);
|
|
if (range.end <= vma->vm_start)
|
|
return -EINVAL;
|
|
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
|
|
range.start, range.end);
|
|
|
|
lru_add_drain();
|
|
tlb_gather_mmu(&tlb, mm, range.start, range.end);
|
|
update_hiwater_rss(mm);
|
|
|
|
mmu_notifier_invalidate_range_start(&range);
|
|
tlb_start_vma(&tlb, vma);
|
|
walk_page_range(vma->vm_mm, range.start, range.end,
|
|
&madvise_free_walk_ops, &tlb);
|
|
tlb_end_vma(&tlb, vma);
|
|
mmu_notifier_invalidate_range_end(&range);
|
|
tlb_finish_mmu(&tlb, range.start, range.end);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* 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_single_vma(struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
zap_page_range(vma, start, end - start);
|
|
return 0;
|
|
}
|
|
|
|
static long madvise_dontneed_free(struct vm_area_struct *vma,
|
|
struct vm_area_struct **prev,
|
|
unsigned long start, unsigned long end,
|
|
int behavior)
|
|
{
|
|
*prev = vma;
|
|
if (!can_madv_lru_vma(vma))
|
|
return -EINVAL;
|
|
|
|
if (!userfaultfd_remove(vma, start, end)) {
|
|
*prev = NULL; /* mmap_sem has been dropped, prev is stale */
|
|
|
|
down_read(¤t->mm->mmap_sem);
|
|
vma = find_vma(current->mm, start);
|
|
if (!vma)
|
|
return -ENOMEM;
|
|
if (start < vma->vm_start) {
|
|
/*
|
|
* This "vma" under revalidation is the one
|
|
* with the lowest vma->vm_start where start
|
|
* is also < vma->vm_end. If start <
|
|
* vma->vm_start it means an hole materialized
|
|
* in the user address space within the
|
|
* virtual range passed to MADV_DONTNEED
|
|
* or MADV_FREE.
|
|
*/
|
|
return -ENOMEM;
|
|
}
|
|
if (!can_madv_lru_vma(vma))
|
|
return -EINVAL;
|
|
if (end > vma->vm_end) {
|
|
/*
|
|
* Don't fail if end > vma->vm_end. If the old
|
|
* vma was splitted while the mmap_sem was
|
|
* released the effect of the concurrent
|
|
* operation may not cause madvise() to
|
|
* have an undefined result. There may be an
|
|
* adjacent next vma that we'll walk
|
|
* next. userfaultfd_remove() will generate an
|
|
* UFFD_EVENT_REMOVE repetition on the
|
|
* end-vma->vm_end range, but the manager can
|
|
* handle a repetition fine.
|
|
*/
|
|
end = vma->vm_end;
|
|
}
|
|
VM_WARN_ON(start >= end);
|
|
}
|
|
|
|
if (behavior == MADV_DONTNEED)
|
|
return madvise_dontneed_single_vma(vma, start, end);
|
|
else if (behavior == MADV_FREE)
|
|
return madvise_free_single_vma(vma, start, end);
|
|
else
|
|
return -EINVAL;
|
|
}
|
|
|
|
/*
|
|
* 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);
|
|
if (userfaultfd_remove(vma, start, end)) {
|
|
/* mmap_sem was not released by userfaultfd_remove() */
|
|
up_read(¤t->mm->mmap_sem);
|
|
}
|
|
error = vfs_fallocate(f,
|
|
FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
|
|
offset, end - start);
|
|
fput(f);
|
|
down_read(¤t->mm->mmap_sem);
|
|
return error;
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
/*
|
|
* Error injection support for memory error handling.
|
|
*/
|
|
static int madvise_inject_error(int behavior,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
struct page *page;
|
|
struct zone *zone;
|
|
unsigned long size;
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
|
|
|
|
for (; start < end; start += size) {
|
|
unsigned long pfn;
|
|
int ret;
|
|
|
|
ret = get_user_pages_fast(start, 1, 0, &page);
|
|
if (ret != 1)
|
|
return ret;
|
|
pfn = page_to_pfn(page);
|
|
|
|
/*
|
|
* When soft offlining hugepages, after migrating the page
|
|
* we dissolve it, therefore in the second loop "page" will
|
|
* no longer be a compound page.
|
|
*/
|
|
size = page_size(compound_head(page));
|
|
|
|
if (PageHWPoison(page)) {
|
|
put_page(page);
|
|
continue;
|
|
}
|
|
|
|
if (behavior == MADV_SOFT_OFFLINE) {
|
|
pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n",
|
|
pfn, start);
|
|
|
|
ret = soft_offline_page(pfn, MF_COUNT_INCREASED);
|
|
if (ret)
|
|
return ret;
|
|
continue;
|
|
}
|
|
|
|
pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
|
|
pfn, start);
|
|
|
|
/*
|
|
* Drop the page reference taken by get_user_pages_fast(). In
|
|
* the absence of MF_COUNT_INCREASED the memory_failure()
|
|
* routine is responsible for pinning the page to prevent it
|
|
* from being released back to the page allocator.
|
|
*/
|
|
put_page(page);
|
|
ret = memory_failure(pfn, 0);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
|
|
/* Ensure that all poisoned pages are removed from per-cpu lists */
|
|
for_each_populated_zone(zone)
|
|
drain_all_pages(zone);
|
|
|
|
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_COLD:
|
|
return madvise_cold(vma, prev, start, end);
|
|
case MADV_PAGEOUT:
|
|
return madvise_pageout(vma, prev, start, end);
|
|
case MADV_FREE:
|
|
case MADV_DONTNEED:
|
|
return madvise_dontneed_free(vma, prev, start, end, behavior);
|
|
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:
|
|
case MADV_COLD:
|
|
case MADV_PAGEOUT:
|
|
#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:
|
|
case MADV_WIPEONFORK:
|
|
case MADV_KEEPONFORK:
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
case MADV_SOFT_OFFLINE:
|
|
case MADV_HWPOISON:
|
|
#endif
|
|
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_FREE - the application marks pages in the given range as lazy free,
|
|
* where actual purges are postponed until memory pressure happens.
|
|
* 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_WIPEONFORK - present the child process with zero-filled memory in this
|
|
* range after a fork.
|
|
* MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK
|
|
* MADV_HWPOISON - trigger memory error handler as if the given memory range
|
|
* were corrupted by unrecoverable hardware memory failure.
|
|
* MADV_SOFT_OFFLINE - try to soft-offline the given range of memory.
|
|
* 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.
|
|
* MADV_HUGEPAGE - the application wants to back the given range by transparent
|
|
* huge pages in the future. Existing pages might be coalesced and
|
|
* new pages might be allocated as THP.
|
|
* MADV_NOHUGEPAGE - mark the given range as not worth being backed by
|
|
* transparent huge pages so the existing pages will not be
|
|
* coalesced into THP and new pages will not be allocated as THP.
|
|
* MADV_DONTDUMP - the application wants to prevent pages in the given range
|
|
* from being included in its core dump.
|
|
* MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
|
|
*
|
|
* 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,
|
|
* or the specified address range includes file, Huge TLB,
|
|
* MAP_SHARED or VMPFNMAP range.
|
|
* -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.
|
|
*/
|
|
int do_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;
|
|
|
|
start = untagged_addr(start);
|
|
|
|
if (!madvise_behavior_valid(behavior))
|
|
return error;
|
|
|
|
if (!PAGE_ALIGNED(start))
|
|
return error;
|
|
len = PAGE_ALIGN(len_in);
|
|
|
|
/* 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;
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE)
|
|
return madvise_inject_error(behavior, start, start + len_in);
|
|
#endif
|
|
|
|
write = madvise_need_mmap_write(behavior);
|
|
if (write) {
|
|
if (down_write_killable(¤t->mm->mmap_sem))
|
|
return -EINTR;
|
|
} else {
|
|
down_read(¤t->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(¤t->mm->mmap_sem);
|
|
else
|
|
up_read(¤t->mm->mmap_sem);
|
|
|
|
return error;
|
|
}
|
|
|
|
SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
|
|
{
|
|
return do_madvise(start, len_in, behavior);
|
|
}
|