Re: [PATCHv2] mm: khugepaged: make scan loops suspend aware

[Nico Pache <npache@redhat.com>]

On Tue, Feb 10, 2026 at 8:15 PM Sergey Senozhatsky
<senozhatsky@chromium.org> wrote:
>
> A number of khugepaaged's loops, e.g. khugepaged_scan_mm_slot(),
> are time unbound, which can become problematic during system
> suspend:
>
> PM: suspend entry (s2idle)
> Filesystems sync: 0.003 seconds
> Freezing user space processes
> Freezing user space processes completed (elapsed 0.003 seconds)
> OOM killer disabled.
> Freezing remaining freezable tasks
> Freezing remaining freezable tasks failed after 20.004 seconds (1 tasks refusing to freeze, wq_busy=0):
> task:khugepaged      state:D stack:0     pid:1345  ppid:2      flags:0x00004000
> Call Trace:
>  <TASK>
>  schedule+0x523/0x16a0
>  schedule_timeout+0x23b/0x6e0
>  io_schedule_timeout+0x3f/0x80
>  wait_for_completion_io_timeout+0xe4/0x170
>  submit_bio_wait+0x79/0xc0
>  swap_readpage+0x150/0x2d0
>  swap_cluster_readahead+0x3be/0x750
>  shmem_swapin+0xa7/0x100
>  shmem_swapin_folio+0xcd/0x2e0
>  shmem_get_folio+0x237/0x580
>  collapse_file+0x247/0x1280
>  hpage_collapse_scan_file+0x26e/0x380
>  khugepaged+0x43b/0x810
>  kthread+0xfb/0x120
>  </TASK>
>
> Make hpage_collapse_test_exit_or_disable() suspend aware so
> that khugepaaged's scan loops can terminate in a timely manner
> and let system enter the sleep state.
>
> Co-developed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>

Hi Sergey!

Thank you for reporting this and taking the time to investigate a fix.

Here are some simple review points then I'll comment on the code below.

- We usually send "To:" the mailing lists and "CC:" to all other people.
- Your subject contains "PATCHv2" there should be a space there
- It would be worth noting the "HOW" in the commit message

> ---
>
> v1->v2: Actually pass "cc" to hpage_collapse_test_exit_or_disable()
>
>  mm/khugepaged.c | 22 +++++++++++++++-------
>  1 file changed, 15 insertions(+), 7 deletions(-)
>
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index eff9e3061925..d32a5ad27097 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -392,10 +392,18 @@ static inline int hpage_collapse_test_exit(struct mm_struct *mm)
>         return atomic_read(&mm->mm_users) == 0;
>  }
>
> -static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm)
> +static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm,
> +                                               struct collapse_control *cc)
>  {
> +       bool was_frozen = false;
> +
> +       if (cc->is_khugepaged &&
> +           unlikely(kthread_freezable_should_stop(&was_frozen)))
> +               return 1;
> +
>         return hpage_collapse_test_exit(mm) ||
> -               mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm);
> +               mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm) ||
> +               was_frozen;

I dont really understand the freezer code, and there are few examples
of this. But given how other callers do it, this seems correct.

>  }
>
>  static bool hugepage_pmd_enabled(void)
> @@ -895,7 +903,7 @@ static enum scan_result hugepage_vma_revalidate(struct mm_struct *mm, unsigned l
>         enum tva_type type = cc->is_khugepaged ? TVA_KHUGEPAGED :
>                                  TVA_FORCED_COLLAPSE;
>
> -       if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
> +       if (unlikely(hpage_collapse_test_exit_or_disable(mm, cc)))
>                 return SCAN_ANY_PROCESS;
>
>         *vmap = vma = find_vma(mm, address);
> @@ -2420,7 +2428,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
>                 goto breakouterloop_mmap_lock;
>
>         progress++;
> -       if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
> +       if (unlikely(hpage_collapse_test_exit_or_disable(mm, cc)))
>                 goto breakouterloop;
>
>         vma_iter_init(&vmi, mm, khugepaged_scan.address);
> @@ -2428,7 +2436,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
>                 unsigned long hstart, hend;
>
>                 cond_resched();
> -               if (unlikely(hpage_collapse_test_exit_or_disable(mm))) {
> +               if (unlikely(hpage_collapse_test_exit_or_disable(mm, cc))) {
>                         progress++;
>                         break;
>                 }
> @@ -2450,7 +2458,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
>                         bool mmap_locked = true;
>
>                         cond_resched();
> -                       if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
> +                       if (unlikely(hpage_collapse_test_exit_or_disable(mm, cc)))
>                                 goto breakouterloop;
>
>                         VM_BUG_ON(khugepaged_scan.address < hstart ||
> @@ -2468,7 +2476,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
>                                 fput(file);
>                                 if (*result == SCAN_PTE_MAPPED_HUGEPAGE) {
>                                         mmap_read_lock(mm);
> -                                       if (hpage_collapse_test_exit_or_disable(mm))
> +                                       if (hpage_collapse_test_exit_or_disable(mm, cc))
>                                                 goto breakouterloop;
>                                         *result = try_collapse_pte_mapped_thp(mm,
>                                                 khugepaged_scan.address, false);
> --
> 2.53.0.239.g8d8fc8a987-goog
>