Re: [PATCH v3 05/18] selftests/mm: keep khugepaged out of the swapout the swap cases set up

On 12/08/2026 2:22 pm, Kiryl Shutsemau wrote:
> From: "Kiryl Shutsemau (Meta)" <[email protected]>
> 
> collapse_swapin_single_pte() and collapse_max_ptes_swap() page a range out
> and then require smaps to report exactly the count they asked for.  Two
> things keep it from arriving.  MADV_PAGEOUT is best effort, so the count
> often turns up a moment late.  And wait_for_scan() leaves MADV_HUGEPAGE
> behind, so khugepaged is still working on the range: collapsing one with up
> to max_ptes_swap pages swapped out means reading them back in, and the
> daemon empties the swap as fast as the case fills it.  On arm64 with 64K
> pages, where max_ptes_swap is 1024 pages, that is 64M a step and the case
> loses:
> 
>   # Swapout 1024 of 8192 pages... Fail
>   not ok 10 collapse_max_ptes_swap
> 
> Ask again for up to two seconds, with the range held out of the daemon's
> reach while asking.  The collapse each case runs next puts MADV_HUGEPAGE
> back, so only the setup is affected.
> 
> If the pages still will not go, skip.  is_swap_enabled() covers a machine
> with no swap; what is left -- swap too small, full, capped by a memcg, busy
> with writeback -- is not the kernel under test refusing.  An error from
> madvise() itself still ends the run.
> 
> Assisted-by: Claude-Code:claude-opus-5
> Signed-off-by: Kiryl Shutsemau (Meta) <[email protected]>
> ---
>  tools/testing/selftests/mm/khugepaged.c | 53 +++++++++++++++++++------
>  1 file changed, 41 insertions(+), 12 deletions(-)
> 
> diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c
> index c049ac997def..8458cd2ff0df 100644
> --- a/tools/testing/selftests/mm/khugepaged.c
> +++ b/tools/testing/selftests/mm/khugepaged.c
> @@ -241,6 +241,41 @@ static bool check_swap(void *addr, unsigned long size)
>  	return swap;
>  }
>  
> +/*
> + * Page the range out and wait for the swap count to say so.
> + *
> + * Two things get in the way.  MADV_PAGEOUT is best effort:
> + * shrink_folio_list() leaves a folio alone when it cannot reclaim it right
> + * away, and one still under writeback from an earlier pageout is the common
> + * case, so the count the caller asks for arrives a moment later.  And a range
> + * an earlier collapse left MADV_HUGEPAGE is one khugepaged is still working
> + * on: collapsing a range with up to max_ptes_swap pages swapped out means
> + * reading those pages back in, so the daemon undoes the pageout as fast as it
> + * is asked for.  Keep the range out of its reach; the collapse the caller runs
> + * next puts MADV_HUGEPAGE back.
> + *
> + * Failing to get the pages out is the machine's answer, not the kernel's --
> + * swap too small, swap full, a memcg cap, a folio still under writeback -- so
> + * callers skip rather than fail.  An error from madvise() is different, and
> + * ends the run here.
> + */
> +static bool swapout_range(void *p, unsigned long size)
> +{
> +	int i;
> +
> +	if (madvise(p, size, MADV_NOHUGEPAGE))
> +		ksft_exit_fail_perror("madvise(MADV_NOHUGEPAGE)");
> +
> +	for (i = 0; i < 40; i++) {
> +		if (madvise(p, size, MADV_PAGEOUT))
> +			ksft_exit_fail_perror("madvise(MADV_PAGEOUT)");
> +		if (check_swap(p, size))
> +			return true;
> +		usleep(50 * 1000);
> +	}
> +	return false;
> +}
> +
>  static void *alloc_mapping(int nr)
>  {
>  	void *p;
> @@ -855,12 +890,10 @@ static void collapse_swapin_single_pte(struct collapse_context *c, struct mem_op
>  	p = ops->setup_area(1);
>  	ops->fault(p, 0, hpage_pmd_size);
>  
> -	if (madvise(p, page_size, MADV_PAGEOUT))
> -		ksft_exit_fail_perror("madvise(MADV_PAGEOUT)");
> -	if (check_swap(p, page_size)) {
> +	if (swapout_range(p, page_size)) {
>  		success("OK");
>  	} else {
> -		fail("Fail");
> +		skip("Could not swap out");
>  		goto out;
>  	}
>  
> @@ -887,12 +920,10 @@ static void collapse_max_ptes_swap(struct collapse_context *c, struct mem_ops *o
>  	p = ops->setup_area(1);
>  	ops->fault(p, 0, hpage_pmd_size);
>  
> -	if (madvise(p, (max_ptes_swap + 1) * page_size, MADV_PAGEOUT))
> -		ksft_exit_fail_perror("madvise(MADV_PAGEOUT)");
> -	if (check_swap(p, (max_ptes_swap + 1) * page_size)) {
> +	if (swapout_range(p, (max_ptes_swap + 1) * page_size)) {
>  		success("OK");
>  	} else {
> -		fail("Fail");
> +		skip("Could not swap out");
>  		goto out;
>  	}
>  
> @@ -904,12 +935,10 @@ static void collapse_max_ptes_swap(struct collapse_context *c, struct mem_ops *o
>  		ops->fault(p, 0, hpage_pmd_size);
>  		ksft_print_msg("Swapout %d of %d pages...", max_ptes_swap,
>  		       hpage_pmd_nr);
> -		if (madvise(p, max_ptes_swap * page_size, MADV_PAGEOUT))
> -			ksft_exit_fail_perror("madvise(MADV_PAGEOUT)");
> -		if (check_swap(p, max_ptes_swap * page_size)) {
> +		if (swapout_range(p, max_ptes_swap * page_size)) {
>  			success("OK");
>  		} else {
> -			fail("Fail");
> +			skip("Could not swap out");
>  			goto out;
>  		}
>  

Reviewed-by: Muhammad Usama Anjum <[email protected]>
Tested-by: Muhammad Usama Anjum <[email protected]>

-- 
Thanks,
Usama