Re: [PATCH mm-unstable v15 12/13] mm/khugepaged: run khugepaged for all orders

[Lorenzo Stoakes (Oracle)]

On Wed, Feb 25, 2026 at 08:26:50PM -0700, Nico Pache wrote:
> From: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
>
> If any order (m)THP is enabled we should allow running khugepaged to
> attempt scanning and collapsing mTHPs. In order for khugepaged to operate
> when only mTHP sizes are specified in sysfs, we must modify the predicate
> function that determines whether it ought to run to do so.
>
> This function is currently called hugepage_pmd_enabled(), this patch
> renames it to hugepage_enabled() and updates the logic to check to
> determine whether any valid orders may exist which would justify
> khugepaged running.
>
> We must also update collapse_allowable_orders() to check all orders if
> the vma is anonymous and the collapse is khugepaged.
>
> After this patch khugepaged mTHP collapse is fully enabled.
>
> Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
> Signed-off-by: Nico Pache <npache@xxxxxxxxxx>

This looks good to me, so:

Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@xxxxxxxxxx>

> ---
>  mm/khugepaged.c | 30 ++++++++++++++++++------------
>  1 file changed, 18 insertions(+), 12 deletions(-)
>
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 388d3f2537e2..e8bfcc1d0c9a 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -434,23 +434,23 @@ static inline int collapse_test_exit_or_disable(struct mm_struct *mm)
>  		mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm);
>  }
>
> -static bool hugepage_pmd_enabled(void)
> +static bool hugepage_enabled(void)
>  {
>  	/*
>  	 * We cover the anon, shmem and the file-backed case here; file-backed
>  	 * hugepages, when configured in, are determined by the global control.
> -	 * Anon pmd-sized hugepages are determined by the pmd-size control.
> +	 * Anon hugepages are determined by its per-size mTHP control.

Well also PMD right? I mean this terminology sucks because in a sense mTHP
includes PMD... :)

>  	 * Shmem pmd-sized hugepages are also determined by its pmd-size control,
>  	 * except when the global shmem_huge is set to SHMEM_HUGE_DENY.
>  	 */
>  	if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
>  	    hugepage_global_enabled())
>  		return true;
> -	if (test_bit(PMD_ORDER, &huge_anon_orders_always))
> +	if (READ_ONCE(huge_anon_orders_always))
>  		return true;
> -	if (test_bit(PMD_ORDER, &huge_anon_orders_madvise))
> +	if (READ_ONCE(huge_anon_orders_madvise))
>  		return true;
> -	if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) &&
> +	if (READ_ONCE(huge_anon_orders_inherit) &&
>  	    hugepage_global_enabled())
>  		return true;
>  	if (IS_ENABLED(CONFIG_SHMEM) && shmem_hpage_pmd_enabled())
> @@ -521,8 +521,14 @@ static unsigned int collapse_max_ptes_none(unsigned int order)
>  static unsigned long collapse_allowable_orders(struct vm_area_struct *vma,
>  			vm_flags_t vm_flags, bool is_khugepaged)
>  {
> +	unsigned long orders;
>  	enum tva_type tva_flags = is_khugepaged ? TVA_KHUGEPAGED : TVA_FORCED_COLLAPSE;
> -	unsigned long orders = BIT(HPAGE_PMD_ORDER);
> +
> +	/* If khugepaged is scanning an anonymous vma, allow mTHP collapse */
> +	if (is_khugepaged && vma_is_anonymous(vma))
> +		orders = THP_ORDERS_ALL_ANON;
> +	else
> +		orders = BIT(HPAGE_PMD_ORDER);
>
>  	return thp_vma_allowable_orders(vma, vm_flags, tva_flags, orders);
>  }
> @@ -531,7 +537,7 @@ void khugepaged_enter_vma(struct vm_area_struct *vma,
>  			  vm_flags_t vm_flags)
>  {
>  	if (!mm_flags_test(MMF_VM_HUGEPAGE, vma->vm_mm) &&
> -	    hugepage_pmd_enabled()) {
> +	    hugepage_enabled()) {
>  		if (collapse_allowable_orders(vma, vm_flags, /*is_khugepaged=*/true))
>  			__khugepaged_enter(vma->vm_mm);
>  	}
> @@ -2929,7 +2935,7 @@ static unsigned int collapse_scan_mm_slot(unsigned int pages, enum scan_result *
>
>  static int khugepaged_has_work(void)
>  {
> -	return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled();
> +	return !list_empty(&khugepaged_scan.mm_head) && hugepage_enabled();
>  }
>
>  static int khugepaged_wait_event(void)
> @@ -3002,7 +3008,7 @@ static void khugepaged_wait_work(void)
>  		return;
>  	}
>
> -	if (hugepage_pmd_enabled())
> +	if (hugepage_enabled())
>  		wait_event_freezable(khugepaged_wait, khugepaged_wait_event());
>  }
>
> @@ -3033,7 +3039,7 @@ static void set_recommended_min_free_kbytes(void)
>  	int nr_zones = 0;
>  	unsigned long recommended_min;
>
> -	if (!hugepage_pmd_enabled()) {
> +	if (!hugepage_enabled()) {
>  		calculate_min_free_kbytes();
>  		goto update_wmarks;
>  	}
> @@ -3083,7 +3089,7 @@ int start_stop_khugepaged(void)
>  	int err = 0;
>
>  	mutex_lock(&khugepaged_mutex);
> -	if (hugepage_pmd_enabled()) {
> +	if (hugepage_enabled()) {
>  		if (!khugepaged_thread)
>  			khugepaged_thread = kthread_run(khugepaged, NULL,
>  							"khugepaged");
> @@ -3109,7 +3115,7 @@ int start_stop_khugepaged(void)
>  void khugepaged_min_free_kbytes_update(void)
>  {
>  	mutex_lock(&khugepaged_mutex);
> -	if (hugepage_pmd_enabled() && khugepaged_thread)
> +	if (hugepage_enabled() && khugepaged_thread)
>  		set_recommended_min_free_kbytes();
>  	mutex_unlock(&khugepaged_mutex);
>  }
> --
> 2.53.0
>