/**
* __replace_page - replace page in vma by new page.
* based on replace_page in mm/ksm.c
*
* @vma: vma that holds the pte pointing to page
* @addr: address the old @page is mapped at
* @page: the cowed page we are replacing by kpage
* @kpage: the modified page we replace page by
*
* Returns 0 on success, -EFAULT on failure.
*/
static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
struct page *old_page, struct page *new_page)
{
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
pte_t *ptep;
int err;
/* For mmu_notifiers */
const unsigned long mmun_start = addr;
const unsigned long mmun_end = addr + PAGE_SIZE;
struct mem_cgroup *memcg;
err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL, &memcg,
false);
if (err)
return err;
/* For try_to_free_swap() and munlock_vma_page() below */
lock_page(old_page);
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
err = -EAGAIN;
ptep = page_check_address(old_page, mm, addr, &ptl, 0);
if (!ptep) {
mem_cgroup_cancel_charge(new_page, memcg, false);
goto unlock;
}
get_page(new_page);
page_add_new_anon_rmap(new_page, vma, addr, false);
mem_cgroup_commit_charge(new_page, memcg, false, false);
lru_cache_add_active_or_unevictable(new_page, vma);
if (!PageAnon(old_page)) {
dec_mm_counter(mm, mm_counter_file(old_page));
inc_mm_counter(mm, MM_ANONPAGES);
}
flush_cache_page(vma, addr, pte_pfn(*ptep));
ptep_clear_flush_notify(vma, addr, ptep);
set_pte_at_notify(mm, addr, ptep, mk_pte(new_page, vma->vm_page_prot));
page_remove_rmap(old_page, false);
if (!page_mapped(old_page))
try_to_free_swap(old_page);
pte_unmap_unlock(ptep, ptl);
if (vma->vm_flags & VM_LOCKED)
munlock_vma_page(old_page);
put_page(old_page);
err = 0;
unlock:
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
unlock_page(old_page);
return err;
}
bool __oom_reap_task_mm(struct mm_struct *mm)
{
struct vm_area_struct *vma;
bool ret = true;
/*
* Tell all users of get_user/copy_from_user etc... that the content
* is no longer stable. No barriers really needed because unmapping
* should imply barriers already and the reader would hit a page fault
* if it stumbled over a reaped memory.
*/
set_bit(MMF_UNSTABLE, &mm->flags);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
if (!can_madv_dontneed_vma(vma))
continue;
/*
* Only anonymous pages have a good chance to be dropped
* without additional steps which we cannot afford as we
* are OOM already.
*
* We do not even care about fs backed pages because all
* which are reclaimable have already been reclaimed and
* we do not want to block exit_mmap by keeping mm ref
* count elevated without a good reason.
*/
if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
struct mmu_notifier_range range;
struct mmu_gather tlb;
mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0,
vma, mm, vma->vm_start,
vma->vm_end);
tlb_gather_mmu(&tlb, mm, range.start, range.end);
if (mmu_notifier_invalidate_range_start_nonblock(&range)) {
tlb_finish_mmu(&tlb, range.start, range.end);
ret = false;
continue;
}
unmap_page_range(&tlb, vma, range.start, range.end, NULL);
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb, range.start, range.end);
}
}
return ret;
}
static ssize_t clear_refs_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
struct task_struct *task;
char buffer[PROC_NUMBUF];
struct mm_struct *mm;
struct vm_area_struct *vma;
enum clear_refs_types type;
int itype;
int rv;
memset(buffer, 0, sizeof(buffer));
if (count > sizeof(buffer) - 1)
count = sizeof(buffer) - 1;
if (copy_from_user(buffer, buf, count))
return -EFAULT;
rv = kstrtoint(strstrip(buffer), 10, &itype);
if (rv < 0)
return rv;
type = (enum clear_refs_types)itype;
if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST)
return -EINVAL;
if (type == CLEAR_REFS_SOFT_DIRTY) {
soft_dirty_cleared = true;
pr_warn_once("The pagemap bits 55-60 has changed their meaning!"
" See the linux/Documentation/vm/pagemap.txt for "
"details.\n");
}
task = get_proc_task(file_inode(file));
if (!task)
return -ESRCH;
mm = get_task_mm(task);
if (mm) {
struct clear_refs_private cp = {
.type = type,
};
struct mm_walk clear_refs_walk = {
.pmd_entry = clear_refs_pte_range,
.test_walk = clear_refs_test_walk,
.mm = mm,
.private = &cp,
};
if (type == CLEAR_REFS_MM_HIWATER_RSS) {
/*
* Writing 5 to /proc/pid/clear_refs resets the peak
* resident set size to this mm's current rss value.
*/
down_write(&mm->mmap_sem);
reset_mm_hiwater_rss(mm);
up_write(&mm->mmap_sem);
goto out_mm;
}
down_read(&mm->mmap_sem);
if (type == CLEAR_REFS_SOFT_DIRTY) {
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (!(vma->vm_flags & VM_SOFTDIRTY))
continue;
up_read(&mm->mmap_sem);
down_write(&mm->mmap_sem);
for (vma = mm->mmap; vma; vma = vma->vm_next) {
vma->vm_flags &= ~VM_SOFTDIRTY;
vma_set_page_prot(vma);
}
downgrade_write(&mm->mmap_sem);
break;
}
mmu_notifier_invalidate_range_start(mm, 0, -1);
}
walk_page_range(0, ~0UL, &clear_refs_walk);
if (type == CLEAR_REFS_SOFT_DIRTY)
mmu_notifier_invalidate_range_end(mm, 0, -1);
flush_tlb_mm(mm);
up_read(&mm->mmap_sem);
out_mm:
mmput(mm);
}
put_task_struct(task);
return count;
}
