From: Zi Yan <ziy@nvidia.com>
During migration in a memory compaction, free pages are placed in an array
of page lists based on their order. But the desired free page order (i.e.,
the order of a source page) might not be always present, thus leading to
migration failures and premature compaction termination. Split a high
order free pages when source migration page has a lower order to increase
migration successful rate.
Note: merging free pages when a migration fails and a lower order free
page is returned via compaction_free() is possible, but there is too much
work. Since the free pages are not buddy pages, it is hard to identify
these free pages using existing PFN-based page merging algorithm.
Signed-off-by: Zi Yan <ziy@nvidia.com>
---
mm/compaction.c | 37 ++++++++++++++++++++++++++++++++++++-
1 file changed, 36 insertions(+), 1 deletion(-)
diff --git a/mm/compaction.c b/mm/compaction.c
index 58a4e3fb72ec..fa9993c8a389 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1832,9 +1832,43 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
struct compact_control *cc = (struct compact_control *)data;
struct folio *dst;
int order = folio_order(src);
+ bool has_isolated_pages = false;
+again:
if (!cc->freepages[order].nr_pages) {
- isolate_freepages(cc);
+ int i;
+
+ for (i = order + 1; i < NR_PAGE_ORDERS; i++) {
+ if (cc->freepages[i].nr_pages) {
+ struct page *freepage =
+ list_first_entry(&cc->freepages[i].pages,
+ struct page, lru);
+
+ int start_order = i;
+ unsigned long size = 1 << start_order;
+
+ list_del(&freepage->lru);
+ cc->freepages[i].nr_pages--;
+
+ while (start_order > order) {
+ start_order--;
+ size >>= 1;
+
+ list_add(&freepage[size].lru,
+ &cc->freepages[start_order].pages);
+ cc->freepages[start_order].nr_pages++;
+ set_page_private(&freepage[size], start_order);
+ }
+ dst = (struct folio *)freepage;
+ goto done;
+ }
+ }
+ if (!has_isolated_pages) {
+ isolate_freepages(cc);
+ has_isolated_pages = true;
+ goto again;
+ }
+
if (!cc->freepages[order].nr_pages)
return NULL;
}
@@ -1842,6 +1876,7 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
dst = list_first_entry(&cc->freepages[order].pages, struct folio, lru);
cc->freepages[order].nr_pages--;
list_del(&dst->lru);
+done:
post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
if (order)
prep_compound_page(&dst->page, order);
--
2.43.0On 2/2/24 17:15, Zi Yan wrote:
> From: Zi Yan <ziy@nvidia.com>
>
> During migration in a memory compaction, free pages are placed in an array
> of page lists based on their order. But the desired free page order (i.e.,
> the order of a source page) might not be always present, thus leading to
> migration failures and premature compaction termination. Split a high
> order free pages when source migration page has a lower order to increase
> migration successful rate.
>
> Note: merging free pages when a migration fails and a lower order free
> page is returned via compaction_free() is possible, but there is too much
> work. Since the free pages are not buddy pages, it is hard to identify
> these free pages using existing PFN-based page merging algorithm.
>
> Signed-off-by: Zi Yan <ziy@nvidia.com>
> ---
> mm/compaction.c | 37 ++++++++++++++++++++++++++++++++++++-
> 1 file changed, 36 insertions(+), 1 deletion(-)
>
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 58a4e3fb72ec..fa9993c8a389 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -1832,9 +1832,43 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
> struct compact_control *cc = (struct compact_control *)data;
> struct folio *dst;
> int order = folio_order(src);
> + bool has_isolated_pages = false;
>
> +again:
> if (!cc->freepages[order].nr_pages) {
> - isolate_freepages(cc);
> + int i;
> +
> + for (i = order + 1; i < NR_PAGE_ORDERS; i++) {
You could probably just start with a loop that finds the start_order (and do
the isolate_freepages() attempt if there's none) and then handle the rest
outside of the loop. No need to separately handle the case where you have
the exact order available?
> + if (cc->freepages[i].nr_pages) {
> + struct page *freepage =
> + list_first_entry(&cc->freepages[i].pages,
> + struct page, lru);
> +
> + int start_order = i;
> + unsigned long size = 1 << start_order;
> +
> + list_del(&freepage->lru);
> + cc->freepages[i].nr_pages--;
> +
> + while (start_order > order) {
With exact order available this while loop will just be skipped and that's
all the difference to it?
> + start_order--;
> + size >>= 1;
> +
> + list_add(&freepage[size].lru,
> + &cc->freepages[start_order].pages);
> + cc->freepages[start_order].nr_pages++;
> + set_page_private(&freepage[size], start_order);
> + }
> + dst = (struct folio *)freepage;
> + goto done;
> + }
> + }
> + if (!has_isolated_pages) {
> + isolate_freepages(cc);
> + has_isolated_pages = true;
> + goto again;
> + }
> +
> if (!cc->freepages[order].nr_pages)
> return NULL;
> }
> @@ -1842,6 +1876,7 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
> dst = list_first_entry(&cc->freepages[order].pages, struct folio, lru);
> cc->freepages[order].nr_pages--;
> list_del(&dst->lru);
> +done:
> post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
> if (order)
> prep_compound_page(&dst->page, order);
On 9 Feb 2024, at 13:43, Vlastimil Babka wrote:
> On 2/2/24 17:15, Zi Yan wrote:
>> From: Zi Yan <ziy@nvidia.com>
>>
>> During migration in a memory compaction, free pages are placed in an array
>> of page lists based on their order. But the desired free page order (i.e.,
>> the order of a source page) might not be always present, thus leading to
>> migration failures and premature compaction termination. Split a high
>> order free pages when source migration page has a lower order to increase
>> migration successful rate.
>>
>> Note: merging free pages when a migration fails and a lower order free
>> page is returned via compaction_free() is possible, but there is too much
>> work. Since the free pages are not buddy pages, it is hard to identify
>> these free pages using existing PFN-based page merging algorithm.
>>
>> Signed-off-by: Zi Yan <ziy@nvidia.com>
>> ---
>> mm/compaction.c | 37 ++++++++++++++++++++++++++++++++++++-
>> 1 file changed, 36 insertions(+), 1 deletion(-)
>>
>> diff --git a/mm/compaction.c b/mm/compaction.c
>> index 58a4e3fb72ec..fa9993c8a389 100644
>> --- a/mm/compaction.c
>> +++ b/mm/compaction.c
>> @@ -1832,9 +1832,43 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
>> struct compact_control *cc = (struct compact_control *)data;
>> struct folio *dst;
>> int order = folio_order(src);
>> + bool has_isolated_pages = false;
>>
>> +again:
>> if (!cc->freepages[order].nr_pages) {
>> - isolate_freepages(cc);
>> + int i;
>> +
>> + for (i = order + 1; i < NR_PAGE_ORDERS; i++) {
>
> You could probably just start with a loop that finds the start_order (and do
> the isolate_freepages() attempt if there's none) and then handle the rest
> outside of the loop. No need to separately handle the case where you have
> the exact order available?
Like this?
if (list_empty(&cc->freepages[order].pages)) {
int start_order;
for (start_order = order + 1; start_order < NR_PAGE_ORDERS;
start_order++)
if (!list_empty(&cc->freepages[start_order].pages))
break;
/* no free pages in the list */
if (start_order == NR_PAGE_ORDERS) {
if (!has_isolated_pages) {
isolate_freepages(cc);
has_isolated_pages = true;
goto again;
} else
return NULL;
}
struct page *freepage =
list_first_entry(&cc->freepages[start_order].pages,
struct page, lru);
unsigned long size = 1 << start_order;
list_del(&freepage->lru);
while (start_order > order) {
start_order--;
size >>= 1;
list_add(&freepage[size].lru,
&cc->freepages[start_order].pages);
set_page_private(&freepage[size], start_order);
}
dst = (struct folio *)freepage;
goto done;
}
>
>> + if (cc->freepages[i].nr_pages) {
>> + struct page *freepage =
>> + list_first_entry(&cc->freepages[i].pages,
>> + struct page, lru);
>> +
>> + int start_order = i;
>> + unsigned long size = 1 << start_order;
>> +
>> + list_del(&freepage->lru);
>> + cc->freepages[i].nr_pages--;
>> +
>> + while (start_order > order) {
>
> With exact order available this while loop will just be skipped and that's
> all the difference to it?
>
>> + start_order--;
>> + size >>= 1;
>> +
>> + list_add(&freepage[size].lru,
>> + &cc->freepages[start_order].pages);
>> + cc->freepages[start_order].nr_pages++;
>> + set_page_private(&freepage[size], start_order);
>> + }
>> + dst = (struct folio *)freepage;
>> + goto done;
>> + }
>> + }
>> + if (!has_isolated_pages) {
>> + isolate_freepages(cc);
>> + has_isolated_pages = true;
>> + goto again;
>> + }
>> +
>> if (!cc->freepages[order].nr_pages)
>> return NULL;
>> }
>> @@ -1842,6 +1876,7 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
>> dst = list_first_entry(&cc->freepages[order].pages, struct folio, lru);
>> cc->freepages[order].nr_pages--;
>> list_del(&dst->lru);
>> +done:
>> post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
>> if (order)
>> prep_compound_page(&dst->page, order);
--
Best Regards,
Yan, Zi
On 2/9/24 20:57, Zi Yan wrote:
> On 9 Feb 2024, at 13:43, Vlastimil Babka wrote:
>
>> On 2/2/24 17:15, Zi Yan wrote:
>>> From: Zi Yan <ziy@nvidia.com>
>>>
>>> During migration in a memory compaction, free pages are placed in an array
>>> of page lists based on their order. But the desired free page order (i.e.,
>>> the order of a source page) might not be always present, thus leading to
>>> migration failures and premature compaction termination. Split a high
>>> order free pages when source migration page has a lower order to increase
>>> migration successful rate.
>>>
>>> Note: merging free pages when a migration fails and a lower order free
>>> page is returned via compaction_free() is possible, but there is too much
>>> work. Since the free pages are not buddy pages, it is hard to identify
>>> these free pages using existing PFN-based page merging algorithm.
>>>
>>> Signed-off-by: Zi Yan <ziy@nvidia.com>
>>> ---
>>> mm/compaction.c | 37 ++++++++++++++++++++++++++++++++++++-
>>> 1 file changed, 36 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/mm/compaction.c b/mm/compaction.c
>>> index 58a4e3fb72ec..fa9993c8a389 100644
>>> --- a/mm/compaction.c
>>> +++ b/mm/compaction.c
>>> @@ -1832,9 +1832,43 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
>>> struct compact_control *cc = (struct compact_control *)data;
>>> struct folio *dst;
>>> int order = folio_order(src);
>>> + bool has_isolated_pages = false;
>>>
>>> +again:
>>> if (!cc->freepages[order].nr_pages) {
>>> - isolate_freepages(cc);
>>> + int i;
>>> +
>>> + for (i = order + 1; i < NR_PAGE_ORDERS; i++) {
>>
>> You could probably just start with a loop that finds the start_order (and do
>> the isolate_freepages() attempt if there's none) and then handle the rest
>> outside of the loop. No need to separately handle the case where you have
>> the exact order available?
> Like this?
Almost/
> if (list_empty(&cc->freepages[order].pages)) {
You don't need to do that under that if ().
> int start_order;
>
> for (start_order = order + 1; start_order < NR_PAGE_ORDERS;
Just do start_order = order; ... (not order + 1).
The rest should just work.
> start_order++)
> if (!list_empty(&cc->freepages[start_order].pages))
> break;
>
> /* no free pages in the list */
> if (start_order == NR_PAGE_ORDERS) {
> if (!has_isolated_pages) {
> isolate_freepages(cc);
> has_isolated_pages = true;
> goto again;
> } else
> return NULL;
> }
>
> struct page *freepage =
> list_first_entry(&cc->freepages[start_order].pages,
> struct page, lru);
>
> unsigned long size = 1 << start_order;
>
> list_del(&freepage->lru);
>
> while (start_order > order) {
> start_order--;
> size >>= 1;
>
> list_add(&freepage[size].lru,
> &cc->freepages[start_order].pages);
> set_page_private(&freepage[size], start_order);
> }
> dst = (struct folio *)freepage;
> goto done;
> }
>
>>
>>> + if (cc->freepages[i].nr_pages) {
>>> + struct page *freepage =
>>> + list_first_entry(&cc->freepages[i].pages,
>>> + struct page, lru);
>>> +
>>> + int start_order = i;
>>> + unsigned long size = 1 << start_order;
>>> +
>>> + list_del(&freepage->lru);
>>> + cc->freepages[i].nr_pages--;
>>> +
>>> + while (start_order > order) {
>>
>> With exact order available this while loop will just be skipped and that's
>> all the difference to it?
>>
>>> + start_order--;
>>> + size >>= 1;
>>> +
>>> + list_add(&freepage[size].lru,
>>> + &cc->freepages[start_order].pages);
>>> + cc->freepages[start_order].nr_pages++;
>>> + set_page_private(&freepage[size], start_order);
>>> + }
>>> + dst = (struct folio *)freepage;
>>> + goto done;
>>> + }
>>> + }
>>> + if (!has_isolated_pages) {
>>> + isolate_freepages(cc);
>>> + has_isolated_pages = true;
>>> + goto again;
>>> + }
>>> +
>>> if (!cc->freepages[order].nr_pages)
>>> return NULL;
>>> }
>>> @@ -1842,6 +1876,7 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
>>> dst = list_first_entry(&cc->freepages[order].pages, struct folio, lru);
>>> cc->freepages[order].nr_pages--;
>>> list_del(&dst->lru);
>>> +done:
>>> post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
>>> if (order)
>>> prep_compound_page(&dst->page, order);
>
>
> --
> Best Regards,
> Yan, Zi
© 2016 - 2026 Red Hat, Inc.