static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
pmd_t *dst_pmd,
struct vm_area_struct *dst_vma,
unsigned long dst_addr,
unsigned long src_addr,
struct page **page,
bool zeropage)
{
ssize_t err;
if (vma_is_anonymous(dst_vma)) {
if (!zeropage)
err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
dst_addr, src_addr, page);
else
err = mfill_zeropage_pte(dst_mm, dst_pmd,
dst_vma, dst_addr);
} else {
if (!zeropage)
err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd,
dst_vma, dst_addr,
src_addr, page);
else
err = shmem_mfill_zeropage_pte(dst_mm, dst_pmd,
dst_vma, dst_addr);
}
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 bool __oom_reap_task(struct task_struct *tsk)
{
struct mmu_gather tlb;
struct vm_area_struct *vma;
struct mm_struct *mm = NULL;
struct task_struct *p;
struct zap_details details = {.check_swap_entries = true,
.ignore_dirty = true};
bool ret = true;
/*
* We have to make sure to not race with the victim exit path
* and cause premature new oom victim selection:
* __oom_reap_task exit_mm
* atomic_inc_not_zero
* mmput
* atomic_dec_and_test
* exit_oom_victim
* [...]
* out_of_memory
* select_bad_process
* # no TIF_MEMDIE task selects new victim
* unmap_page_range # frees some memory
*/
mutex_lock(&oom_lock);
/*
* Make sure we find the associated mm_struct even when the particular
* thread has already terminated and cleared its mm.
* We might have race with exit path so consider our work done if there
* is no mm.
*/
p = find_lock_task_mm(tsk);
if (!p)
goto unlock_oom;
mm = p->mm;
atomic_inc(&mm->mm_users);
task_unlock(p);
if (!down_read_trylock(&mm->mmap_sem)) {
ret = false;
goto unlock_oom;
}
tlb_gather_mmu(&tlb, mm, 0, -1);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
if (is_vm_hugetlb_page(vma))
continue;
/*
* mlocked VMAs require explicit munlocking before unmap.
* Let's keep it simple here and skip such VMAs.
*/
if (vma->vm_flags & VM_LOCKED)
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))
unmap_page_range(&tlb, vma, vma->vm_start, vma->vm_end,
&details);
}
tlb_finish_mmu(&tlb, 0, -1);
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
K(get_mm_counter(mm, MM_FILEPAGES)),
K(get_mm_counter(mm, MM_SHMEMPAGES)));
up_read(&mm->mmap_sem);
/*
* This task can be safely ignored because we cannot do much more
* to release its memory.
*/
set_bit(MMF_OOM_REAPED, &mm->flags);
unlock_oom:
mutex_unlock(&oom_lock);
/*
* Drop our reference but make sure the mmput slow path is called from a
* different context because we shouldn't risk we get stuck there and
* put the oom_reaper out of the way.
*/
if (mm)
mmput_async(mm);
return ret;
}
#define MAX_OOM_REAP_RETRIES 10
static void oom_reap_task(struct task_struct *tsk)
{
int attempts = 0;
/* Retry the down_read_trylock(mmap_sem) a few times */
while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task(tsk))
schedule_timeout_idle(HZ/10);
if (attempts > MAX_OOM_REAP_RETRIES) {
pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
task_pid_nr(tsk), tsk->comm);
debug_show_all_locks();
}
/*
* Clear TIF_MEMDIE because the task shouldn't be sitting on a
* reasonably reclaimable memory anymore or it is not a good candidate
* for the oom victim right now because it cannot release its memory
* itself nor by the oom reaper.
*/
tsk->oom_reaper_list = NULL;
exit_oom_victim(tsk);
/* Drop a reference taken by wake_oom_reaper */
put_task_struct(tsk);
}
static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
unsigned long dst_start,
unsigned long src_start,
unsigned long len,
bool zeropage,
bool *mmap_changing)
{
struct vm_area_struct *dst_vma;
ssize_t err;
pmd_t *dst_pmd;
unsigned long src_addr, dst_addr;
long copied;
struct page *page;
/*
* Sanitize the command parameters:
*/
BUG_ON(dst_start & ~PAGE_MASK);
BUG_ON(len & ~PAGE_MASK);
/* Does the address range wrap, or is the span zero-sized? */
BUG_ON(src_start + len <= src_start);
BUG_ON(dst_start + len <= dst_start);
src_addr = src_start;
dst_addr = dst_start;
copied = 0;
page = NULL;
retry:
down_read(&dst_mm->mmap_sem);
/*
* If memory mappings are changing because of non-cooperative
* operation (e.g. mremap) running in parallel, bail out and
* request the user to retry later
*/
err = -EAGAIN;
if (mmap_changing && READ_ONCE(*mmap_changing))
goto out_unlock;
/*
* Make sure the vma is not shared, that the dst range is
* both valid and fully within a single existing vma.
*/
err = -ENOENT;
dst_vma = find_vma(dst_mm, dst_start);
if (!dst_vma)
goto out_unlock;
/*
* Check the vma is registered in uffd, this is required to
* enforce the VM_MAYWRITE check done at uffd registration
* time.
*/
if (!dst_vma->vm_userfaultfd_ctx.ctx)
goto out_unlock;
if (dst_start < dst_vma->vm_start ||
dst_start + len > dst_vma->vm_end)
goto out_unlock;
err = -EINVAL;
/*
* shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but
* it will overwrite vm_ops, so vma_is_anonymous must return false.
*/
if (WARN_ON_ONCE(vma_is_anonymous(dst_vma) &&
dst_vma->vm_flags & VM_SHARED))
goto out_unlock;
/*
* If this is a HUGETLB vma, pass off to appropriate routine
*/
if (is_vm_hugetlb_page(dst_vma))
return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start,
src_start, len, zeropage);
if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
goto out_unlock;
/*
* Ensure the dst_vma has a anon_vma or this page
* would get a NULL anon_vma when moved in the
* dst_vma.
*/
err = -ENOMEM;
if (!(dst_vma->vm_flags & VM_SHARED) &&
unlikely(anon_vma_prepare(dst_vma)))
goto out_unlock;
while (src_addr < src_start + len) {
pmd_t dst_pmdval;
BUG_ON(dst_addr >= dst_start + len);
dst_pmd = mm_alloc_pmd(dst_mm, dst_addr);
if (unlikely(!dst_pmd)) {
err = -ENOMEM;
break;
}
dst_pmdval = pmd_read_atomic(dst_pmd);
/*
* If the dst_pmd is mapped as THP don't
* override it and just be strict.
*/
if (unlikely(pmd_trans_huge(dst_pmdval))) {
err = -EEXIST;
break;
}
if (unlikely(pmd_none(dst_pmdval)) &&
unlikely(__pte_alloc(dst_mm, dst_pmd, dst_addr))) {
err = -ENOMEM;
break;
}
/* If an huge pmd materialized from under us fail */
if (unlikely(pmd_trans_huge(*dst_pmd))) {
err = -EFAULT;
break;
}
BUG_ON(pmd_none(*dst_pmd));
BUG_ON(pmd_trans_huge(*dst_pmd));
err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
src_addr, &page, zeropage);
cond_resched();
if (unlikely(err == -ENOENT)) {
void *page_kaddr;
up_read(&dst_mm->mmap_sem);
BUG_ON(!page);
page_kaddr = kmap(page);
err = copy_from_user(page_kaddr,
(const void __user *) src_addr,
PAGE_SIZE);
kunmap(page);
if (unlikely(err)) {
err = -EFAULT;
goto out;
}
goto retry;
} else
BUG_ON(page);
if (!err) {
dst_addr += PAGE_SIZE;
src_addr += PAGE_SIZE;
copied += PAGE_SIZE;
if (fatal_signal_pending(current))
err = -EINTR;
}
if (err)
break;
}
out_unlock:
up_read(&dst_mm->mmap_sem);
out:
if (page)
put_page(page);
BUG_ON(copied < 0);
BUG_ON(err > 0);
BUG_ON(!copied && !err);
return copied ? copied : err;
}
static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
unsigned long dst_start,
unsigned long src_start,
unsigned long len,
bool zeropage)
{
struct vm_area_struct *dst_vma;
ssize_t err;
pmd_t *dst_pmd;
unsigned long src_addr, dst_addr;
long copied;
struct page *page;
/*
* Sanitize the command parameters:
*/
BUG_ON(dst_start & ~PAGE_MASK);
BUG_ON(len & ~PAGE_MASK);
/* Does the address range wrap, or is the span zero-sized? */
BUG_ON(src_start + len <= src_start);
BUG_ON(dst_start + len <= dst_start);
src_addr = src_start;
dst_addr = dst_start;
copied = 0;
page = NULL;
retry:
down_read(&dst_mm->mmap_sem);
/*
* Make sure the vma is not shared, that the dst range is
* both valid and fully within a single existing vma.
*/
err = -ENOENT;
dst_vma = find_vma(dst_mm, dst_start);
if (!dst_vma)
goto out_unlock;
/*
* Be strict and only allow __mcopy_atomic on userfaultfd
* registered ranges to prevent userland errors going
* unnoticed. As far as the VM consistency is concerned, it
* would be perfectly safe to remove this check, but there's
* no useful usage for __mcopy_atomic ouside of userfaultfd
* registered ranges. This is after all why these are ioctls
* belonging to the userfaultfd and not syscalls.
*/
if (!dst_vma->vm_userfaultfd_ctx.ctx)
goto out_unlock;
if (dst_start < dst_vma->vm_start ||
dst_start + len > dst_vma->vm_end)
goto out_unlock;
err = -EINVAL;
/*
* shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but
* it will overwrite vm_ops, so vma_is_anonymous must return false.
*/
if (WARN_ON_ONCE(vma_is_anonymous(dst_vma) &&
dst_vma->vm_flags & VM_SHARED))
goto out_unlock;
/*
* If this is a HUGETLB vma, pass off to appropriate routine
*/
if (is_vm_hugetlb_page(dst_vma))
return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start,
src_start, len, zeropage);
if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
goto out_unlock;
/*
* Ensure the dst_vma has a anon_vma or this page
* would get a NULL anon_vma when moved in the
* dst_vma.
*/
err = -ENOMEM;
if (vma_is_anonymous(dst_vma) && unlikely(anon_vma_prepare(dst_vma)))
goto out_unlock;
while (src_addr < src_start + len) {
pmd_t dst_pmdval;
BUG_ON(dst_addr >= dst_start + len);
dst_pmd = mm_alloc_pmd(dst_mm, dst_addr);
if (unlikely(!dst_pmd)) {
err = -ENOMEM;
break;
}
dst_pmdval = pmd_read_atomic(dst_pmd);
/*
* If the dst_pmd is mapped as THP don't
* override it and just be strict.
*/
if (unlikely(pmd_trans_huge(dst_pmdval))) {
err = -EEXIST;
break;
}
if (unlikely(pmd_none(dst_pmdval)) &&
unlikely(__pte_alloc(dst_mm, dst_pmd, dst_addr))) {
err = -ENOMEM;
break;
}
/* If an huge pmd materialized from under us fail */
if (unlikely(pmd_trans_huge(*dst_pmd))) {
err = -EFAULT;
break;
}
BUG_ON(pmd_none(*dst_pmd));
BUG_ON(pmd_trans_huge(*dst_pmd));
err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
src_addr, &page, zeropage);
cond_resched();
if (unlikely(err == -EFAULT)) {
void *page_kaddr;
up_read(&dst_mm->mmap_sem);
BUG_ON(!page);
page_kaddr = kmap(page);
err = copy_from_user(page_kaddr,
(const void __user *) src_addr,
PAGE_SIZE);
kunmap(page);
if (unlikely(err)) {
err = -EFAULT;
goto out;
}
goto retry;
} else
BUG_ON(page);
if (!err) {
dst_addr += PAGE_SIZE;
src_addr += PAGE_SIZE;
copied += PAGE_SIZE;
if (fatal_signal_pending(current))
err = -EINTR;
}
if (err)
break;
}
out_unlock:
up_read(&dst_mm->mmap_sem);
out:
if (page)
put_page(page);
BUG_ON(copied < 0);
BUG_ON(err > 0);
BUG_ON(!copied && !err);
return copied ? copied : err;
}
