2023-01-21 17:35:00

by Hyeonggon Yoo

Subject: [PATCH mm-unstable] mm/page_owner: record single timestamp value for high order allocations

When allocating a high-order page, separate allocation timestamp is
recorded for each sub-page resulting in different timestamp values between
them.

This behavior is not consistent with the behavior when recording free
timestamp and caused confusion when analyzing memory dumps. Record single
timestamp for the entire allocation, aligning with the behavior for
free timestamps.

Signed-off-by: Hyeonggon Yoo <[email protected]>
---
mm/page_owner.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index f0553bedb39d..80dc8f4050fa 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -163,6 +163,7 @@ static inline void __set_page_owner_handle(struct page_ext *page_ext,
{
struct page_owner *page_owner;
int i;
+ u64 ts_nsec = local_clock();

for (i = 0; i < (1 << order); i++) {
page_owner = get_page_owner(page_ext);
@@ -172,7 +173,7 @@ static inline void __set_page_owner_handle(struct page_ext *page_ext,
page_owner->last_migrate_reason = -1;
page_owner->pid = current->pid;
page_owner->tgid = current->tgid;
- page_owner->ts_nsec = local_clock();
+ page_owner->ts_nsec = ts_nsec;
strscpy(page_owner->comm, current->comm,
sizeof(page_owner->comm));
__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
--
2.34.1

2023-02-08 17:02:54

by Vlastimil Babka

Subject: Re: [PATCH mm-unstable] mm/page_owner: record single timestamp value for high order allocations

On 1/21/23 17:50, Hyeonggon Yoo wrote:
> When allocating a high-order page, separate allocation timestamp is
> recorded for each sub-page resulting in different timestamp values between
> them.
>
> This behavior is not consistent with the behavior when recording free
> timestamp and caused confusion when analyzing memory dumps. Record single
> timestamp for the entire allocation, aligning with the behavior for
> free timestamps.
>
> Signed-off-by: Hyeonggon Yoo <[email protected]>

Acked-by: Vlastimil Babka <[email protected]>

> ---
> mm/page_owner.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/mm/page_owner.c b/mm/page_owner.c
> index f0553bedb39d..80dc8f4050fa 100644
> --- a/mm/page_owner.c
> +++ b/mm/page_owner.c
> @@ -163,6 +163,7 @@ static inline void __set_page_owner_handle(struct page_ext *page_ext,
> {
> struct page_owner *page_owner;
> int i;
> + u64 ts_nsec = local_clock();
>
> for (i = 0; i < (1 << order); i++) {
> page_owner = get_page_owner(page_ext);
> @@ -172,7 +173,7 @@ static inline void __set_page_owner_handle(struct page_ext *page_ext,
> page_owner->last_migrate_reason = -1;
> page_owner->pid = current->pid;
> page_owner->tgid = current->tgid;
> - page_owner->ts_nsec = local_clock();
> + page_owner->ts_nsec = ts_nsec;
> strscpy(page_owner->comm, current->comm,
> sizeof(page_owner->comm));
> __set_bit(PAGE_EXT_OWNER, &page_ext->flags);