[v5] khugepaged: mTHP support

[PATCH v5 09/12] khugepaged: avoid unnecessary mTHP collapse attempts

Posted by Nico Pache 9 months, 2 weeks ago

There are cases where, if an attempted collapse fails, all subsequent
orders are guaranteed to also fail. Avoid these collapse attempts by
bailing out early.

Signed-off-by: Nico Pache <npache@redhat.com>
---
 mm/khugepaged.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 86d1153ce9e8..5e6732cccb86 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1365,6 +1365,23 @@ static int khugepaged_scan_bitmap(struct mm_struct *mm, unsigned long address,
 				collapsed += (1 << order);
 				continue;
 			}
+			/*
+			 * Some ret values indicate all lower order will also
+			 * fail, dont trying to collapse smaller orders
+			 */
+			if (ret == SCAN_EXCEED_NONE_PTE ||
+				ret == SCAN_EXCEED_SWAP_PTE ||
+				ret == SCAN_EXCEED_SHARED_PTE ||
+				ret == SCAN_PTE_NON_PRESENT ||
+				ret == SCAN_PTE_UFFD_WP ||
+				ret == SCAN_ALLOC_HUGE_PAGE_FAIL ||
+				ret == SCAN_CGROUP_CHARGE_FAIL ||
+				ret == SCAN_COPY_MC ||
+				ret == SCAN_PAGE_LOCK ||
+				ret == SCAN_PAGE_COUNT)
+				goto next;
+			else
+				break;
 		}
 
 next:
-- 
2.48.1

Re: [PATCH v5 09/12] khugepaged: avoid unnecessary mTHP collapse attempts

Posted by Baolin Wang 9 months, 2 weeks ago


On 2025/4/29 02:12, Nico Pache wrote:
> There are cases where, if an attempted collapse fails, all subsequent
> orders are guaranteed to also fail. Avoid these collapse attempts by
> bailing out early.
> 
> Signed-off-by: Nico Pache <npache@redhat.com>
> ---
>   mm/khugepaged.c | 17 +++++++++++++++++
>   1 file changed, 17 insertions(+)
> 
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 86d1153ce9e8..5e6732cccb86 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -1365,6 +1365,23 @@ static int khugepaged_scan_bitmap(struct mm_struct *mm, unsigned long address,
>   				collapsed += (1 << order);
>   				continue;
>   			}
> +			/*
> +			 * Some ret values indicate all lower order will also
> +			 * fail, dont trying to collapse smaller orders
> +			 */
> +			if (ret == SCAN_EXCEED_NONE_PTE ||
> +				ret == SCAN_EXCEED_SWAP_PTE ||
> +				ret == SCAN_EXCEED_SHARED_PTE ||
> +				ret == SCAN_PTE_NON_PRESENT ||
> +				ret == SCAN_PTE_UFFD_WP ||
> +				ret == SCAN_ALLOC_HUGE_PAGE_FAIL ||
> +				ret == SCAN_CGROUP_CHARGE_FAIL ||
> +				ret == SCAN_COPY_MC ||
> +				ret == SCAN_PAGE_LOCK ||
> +				ret == SCAN_PAGE_COUNT)
> +				goto next;
> +			else
> +				break;

Better to merge this patch into patch 6, which can be helped to 
understand your logic.

Re: [PATCH v5 09/12] khugepaged: avoid unnecessary mTHP collapse attempts

Posted by Nico Pache 9 months, 2 weeks ago

On Wed, Apr 30, 2025 at 4:12 AM Baolin Wang
<baolin.wang@linux.alibaba.com> wrote:
>
>
>
> On 2025/4/29 02:12, Nico Pache wrote:
> > There are cases where, if an attempted collapse fails, all subsequent
> > orders are guaranteed to also fail. Avoid these collapse attempts by
> > bailing out early.
> >
> > Signed-off-by: Nico Pache <npache@redhat.com>
> > ---
> >   mm/khugepaged.c | 17 +++++++++++++++++
> >   1 file changed, 17 insertions(+)
> >
> > diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> > index 86d1153ce9e8..5e6732cccb86 100644
> > --- a/mm/khugepaged.c
> > +++ b/mm/khugepaged.c
> > @@ -1365,6 +1365,23 @@ static int khugepaged_scan_bitmap(struct mm_struct *mm, unsigned long address,
> >                               collapsed += (1 << order);
> >                               continue;
> >                       }
> > +                     /*
> > +                      * Some ret values indicate all lower order will also
> > +                      * fail, dont trying to collapse smaller orders
> > +                      */
> > +                     if (ret == SCAN_EXCEED_NONE_PTE ||
> > +                             ret == SCAN_EXCEED_SWAP_PTE ||
> > +                             ret == SCAN_EXCEED_SHARED_PTE ||
> > +                             ret == SCAN_PTE_NON_PRESENT ||
> > +                             ret == SCAN_PTE_UFFD_WP ||
> > +                             ret == SCAN_ALLOC_HUGE_PAGE_FAIL ||
> > +                             ret == SCAN_CGROUP_CHARGE_FAIL ||
> > +                             ret == SCAN_COPY_MC ||
> > +                             ret == SCAN_PAGE_LOCK ||
> > +                             ret == SCAN_PAGE_COUNT)
> > +                             goto next;
> > +                     else
> > +                             break;
>
> Better to merge this patch into patch 6, which can be helped to
> understand your logic.
Sounds good, it wasnt part of the original logic/RFCs so i separated
it out to get some review on it.
>