On Wed, Sep 10, 2025 at 10:44:38AM +0800, Yafang Shao wrote:
> Since a task with MMF_DISABLE_THP_COMPLETELY cannot use THP, remove it from
> the khugepaged_mm_slot to stop khugepaged from processing it.
>
> After this change, the following semantic relationship always holds:
>
> MMF_VM_HUGEPAGE is set == task is in khugepaged mm_slot
> MMF_VM_HUGEPAGE is not set == task is not in khugepaged mm_slot
>
> Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx>
> Cc: Lance Yang <ioworker0@xxxxxxxxx>
(Obviously on basis of fixing issue bot reported).
> ---
> include/linux/khugepaged.h | 1 +
> kernel/sys.c | 6 ++++++
> mm/khugepaged.c | 19 +++++++++----------
> 3 files changed, 16 insertions(+), 10 deletions(-)
>
> diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
> index eb1946a70cff..6cb9107f1006 100644
> --- a/include/linux/khugepaged.h
> +++ b/include/linux/khugepaged.h
> @@ -19,6 +19,7 @@ extern void khugepaged_min_free_kbytes_update(void);
> extern bool current_is_khugepaged(void);
> extern int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
> bool install_pmd);
> +bool hugepage_pmd_enabled(void);
Need to provide a !CONFIG_TRANSPARENT_HUGEPAGE version, or to not invoke
this in a context where CONFIG_TRANSPARENT_HUGEPAGE is specified.
>
> static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
> {
> diff --git a/kernel/sys.c b/kernel/sys.c
> index a46d9b75880b..a1c1e8007f2d 100644
> --- a/kernel/sys.c
> +++ b/kernel/sys.c
> @@ -8,6 +8,7 @@
> #include <linux/export.h>
> #include <linux/mm.h>
> #include <linux/mm_inline.h>
> +#include <linux/khugepaged.h>
> #include <linux/utsname.h>
> #include <linux/mman.h>
> #include <linux/reboot.h>
> @@ -2493,6 +2494,11 @@ static int prctl_set_thp_disable(bool thp_disable, unsigned long flags,
> mm_flags_clear(MMF_DISABLE_THP_COMPLETELY, mm);
> mm_flags_clear(MMF_DISABLE_THP_EXCEPT_ADVISED, mm);
> }
> +
> + if (!mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm) &&
> + !mm_flags_test(MMF_VM_HUGEPAGE, mm) &&
> + hugepage_pmd_enabled())
> + __khugepaged_enter(mm);
Let's refactor this so it's not open-coded.
We can have:
void khugepaged_enter_mm(struct mm_struct *mm)
{
if (mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm))
return;
if (mm_flags_test(MMF_VM_HUGEPAGE, mm))
return;
if (!hugepage_pmd_enabled())
return;
__khugepaged_enter(mm);
}
void khugepaged_enter_vma(struct vm_area_struct *vma,
vm_flags_t vm_flags)
{
if (!thp_vma_allowable_order(vma, vm_flags, TVA_KHUGEPAGED, PMD_ORDER))
return;
khugepaged_enter_mm(vma->vm_mm);
}
Then just invoke khugepaged_enter_mm() here.
> mmap_write_unlock(current->mm);
> return 0;
> }
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 4ec324a4c1fe..88ac482fb3a0 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -413,7 +413,7 @@ static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm)
> mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm);
> }
>
> -static bool hugepage_pmd_enabled(void)
> +bool hugepage_pmd_enabled(void)
> {
> /*
> * We cover the anon, shmem and the file-backed case here; file-backed
> @@ -445,6 +445,7 @@ void __khugepaged_enter(struct mm_struct *mm)
>
> /* __khugepaged_exit() must not run from under us */
> VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm);
> + WARN_ON_ONCE(mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm));
Not sure why this needs to be a naked WARN_ON_ONCE()? Seems that'd be a
programmatic eror, so VM_WARN_ON_ONCE() more appropriate?
Can also change the VM_BUG_ON_MM() to VM_WARN_ON_ONCE_MM() while we're here.
> if (unlikely(mm_flags_test_and_set(MMF_VM_HUGEPAGE, mm)))
> return;
>
> @@ -472,7 +473,8 @@ void __khugepaged_enter(struct mm_struct *mm)
> void khugepaged_enter_vma(struct vm_area_struct *vma,
> vm_flags_t vm_flags)
> {
> - if (!mm_flags_test(MMF_VM_HUGEPAGE, vma->vm_mm) &&
> + if (!mm_flags_test(MMF_DISABLE_THP_COMPLETELY, vma->vm_mm) &&
> + !mm_flags_test(MMF_VM_HUGEPAGE, vma->vm_mm) &&
> hugepage_pmd_enabled()) {
> if (thp_vma_allowable_order(vma, vm_flags, TVA_KHUGEPAGED, PMD_ORDER))
> __khugepaged_enter(vma->vm_mm);
See above, we can refactor this.
> @@ -1451,16 +1453,13 @@ static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot)
>
> lockdep_assert_held(&khugepaged_mm_lock);
>
> - if (hpage_collapse_test_exit(mm)) {
> + if (hpage_collapse_test_exit_or_disable(mm)) {
> /* free mm_slot */
> hash_del(&slot->hash);
> list_del(&slot->mm_node);
>
> - /*
> - * Not strictly needed because the mm exited already.
> - *
> - * mm_flags_clear(MMF_VM_HUGEPAGE, mm);
> - */
> + /* If the mm is disabled, this flag must be cleared. */
> + mm_flags_clear(MMF_VM_HUGEPAGE, mm);
>
> /* khugepaged_mm_lock actually not necessary for the below */
> mm_slot_free(mm_slot_cache, mm_slot);
> @@ -2507,9 +2506,9 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
> VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot);
> /*
> * Release the current mm_slot if this mm is about to die, or
> - * if we scanned all vmas of this mm.
> + * if we scanned all vmas of this mm, or if this mm is disabled.
> */
> - if (hpage_collapse_test_exit(mm) || !vma) {
> + if (hpage_collapse_test_exit_or_disable(mm) || !vma) {
> /*
> * Make sure that if mm_users is reaching zero while
> * khugepaged runs here, khugepaged_exit will find
Seems reasonable, but makes me wonder if we actually always want to invoke
hpage_collapse_test_exit_or_disable()?
I guess the VM_BUG_ON() (though it should be a VM_WARN_ON_ONCE()) in
__khugepaged_enter() is a legit use, but the only other case is
retract_page_tables().
I wonder if we should change this also? Seems reasonable to.
> --
> 2.47.3
>
