* [PATCH v2] mm: fix is_pinnable_page against on cma page
@ 2022-05-05 6:44 Minchan Kim
2022-05-07 19:23 ` Andrew Morton
0 siblings, 1 reply; 3+ messages in thread
From: Minchan Kim @ 2022-05-05 6:44 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-mm, LKML, Paul E . McKenney, John Hubbard, John Dias,
Minchan Kim, David Hildenbrand
Pages on CMA area could have MIGRATE_ISOLATE as well as MIGRATE_CMA
so current is_pinnable_page could miss CMA pages which has MIGRATE_
ISOLATE. It ends up putting CMA pages longterm pinning possible on
pin_user_pages APIs so CMA allocation fails.
The CMA allocation path protects the migration type change race
using zone->lock but what GUP path need to know is just whether the
page is on CMA area or not rather than exact type. Thus, we don't
need zone->lock but just checks the migratype in either of
(MIGRATE_ISOLATE and MIGRATE_CMA).
Adding the MIGRATE_ISOLATE check in is_pinnable_page could cause
rejecting of pinning the page on MIGRATE_ISOLATE pageblock even
thouth it's neither CMA nor movable zone if the page is temporarily
unmovable. However, the migration failure is general issue, not
only come from MIGRATE_ISOLATE and the MIGRATE_ISOLATE is also
transient state like other temporal refcount holding of pages.
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
* from v1 - https://lore.kernel.org/all/20220502173558.2510641-1-minchan@kernel.org/
* fix build warning - lkp
* fix refetching issue of migration type
* add side effect on !ZONE_MOVABLE and !MIGRATE_CMA in description - david
include/linux/mm.h | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6acca5cecbc5..e77758e2035e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1625,8 +1625,18 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
#ifdef CONFIG_MIGRATION
static inline bool is_pinnable_page(struct page *page)
{
- return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) ||
- is_zero_pfn(page_to_pfn(page));
+#ifdef CONFIG_CMA
+ /*
+ * use volatile to use local variable mt instead of
+ * refetching mt value.
+ */
+ volatile int mt = get_pageblock_migratetype(page);
+
+ if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
+ return false;
+#endif
+
+ return !(is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page)));
}
#else
static inline bool is_pinnable_page(struct page *page)
--
2.36.0.512.ge40c2bad7a-goog
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH v2] mm: fix is_pinnable_page against on cma page
2022-05-05 6:44 [PATCH v2] mm: fix is_pinnable_page against on cma page Minchan Kim
@ 2022-05-07 19:23 ` Andrew Morton
2022-05-08 0:19 ` David Hildenbrand
0 siblings, 1 reply; 3+ messages in thread
From: Andrew Morton @ 2022-05-07 19:23 UTC (permalink / raw)
To: Minchan Kim
Cc: linux-mm, LKML, Paul E . McKenney, John Hubbard, John Dias,
David Hildenbrand
On Wed, 4 May 2022 23:44:29 -0700 Minchan Kim <minchan@kernel.org> wrote:
> Pages on CMA area could have MIGRATE_ISOLATE as well as MIGRATE_CMA
> so current is_pinnable_page could miss CMA pages which has MIGRATE_
> ISOLATE. It ends up putting CMA pages longterm pinning possible on
> pin_user_pages APIs so CMA allocation fails.
>
> The CMA allocation path protects the migration type change race
> using zone->lock but what GUP path need to know is just whether the
> page is on CMA area or not rather than exact type. Thus, we don't
> need zone->lock but just checks the migratype in either of
> (MIGRATE_ISOLATE and MIGRATE_CMA).
>
> Adding the MIGRATE_ISOLATE check in is_pinnable_page could cause
> rejecting of pinning the page on MIGRATE_ISOLATE pageblock even
> thouth it's neither CMA nor movable zone if the page is temporarily
"though"
> unmovable. However, the migration failure is general issue, not
> only come from MIGRATE_ISOLATE and the MIGRATE_ISOLATE is also
> transient state like other temporal refcount holding of pages.
>
> ...
>
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1625,8 +1625,18 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
> #ifdef CONFIG_MIGRATION
> static inline bool is_pinnable_page(struct page *page)
> {
> - return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) ||
> - is_zero_pfn(page_to_pfn(page));
> +#ifdef CONFIG_CMA
> + /*
> + * use volatile to use local variable mt instead of
> + * refetching mt value.
> + */
> + volatile int mt = get_pageblock_migratetype(page);
> +
> + if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
> + return false;
> +#endif
Open-coded use of `volatile' draws unwelcome attention.
What are we trying to do here? Prevent the compiler from rerunning all
of get_pageblock_migratetype() (really __get_pfnblock_flags_mask())
twice? That would be pretty dumb of it?
Would a suitably-commented something like
int __mt = get_pageblock_migratetype(page);
int mt = __READ_ONCE(__mt);
express this better?
> +
> + return !(is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page)));
> }
> #else
> static inline bool is_pinnable_page(struct page *page)
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH v2] mm: fix is_pinnable_page against on cma page
2022-05-07 19:23 ` Andrew Morton
@ 2022-05-08 0:19 ` David Hildenbrand
0 siblings, 0 replies; 3+ messages in thread
From: David Hildenbrand @ 2022-05-08 0:19 UTC (permalink / raw)
To: Andrew Morton, Minchan Kim
Cc: linux-mm, LKML, Paul E . McKenney, John Hubbard, John Dias
On 07.05.22 21:23, Andrew Morton wrote:
> On Wed, 4 May 2022 23:44:29 -0700 Minchan Kim <minchan@kernel.org> wrote:
>
>> Pages on CMA area could have MIGRATE_ISOLATE as well as MIGRATE_CMA
>> so current is_pinnable_page could miss CMA pages which has MIGRATE_
>> ISOLATE. It ends up putting CMA pages longterm pinning possible on
>> pin_user_pages APIs so CMA allocation fails.
>>
>> The CMA allocation path protects the migration type change race
>> using zone->lock but what GUP path need to know is just whether the
>> page is on CMA area or not rather than exact type. Thus, we don't
>> need zone->lock but just checks the migratype in either of
>> (MIGRATE_ISOLATE and MIGRATE_CMA).
>>
>> Adding the MIGRATE_ISOLATE check in is_pinnable_page could cause
>> rejecting of pinning the page on MIGRATE_ISOLATE pageblock even
>> thouth it's neither CMA nor movable zone if the page is temporarily
>
> "though"
>
>> unmovable. However, the migration failure is general issue, not
>> only come from MIGRATE_ISOLATE and the MIGRATE_ISOLATE is also
>> transient state like other temporal refcount holding of pages.
>>
>> ...
>>
>> --- a/include/linux/mm.h
>> +++ b/include/linux/mm.h
>> @@ -1625,8 +1625,18 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
>> #ifdef CONFIG_MIGRATION
>> static inline bool is_pinnable_page(struct page *page)
>> {
>> - return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) ||
>> - is_zero_pfn(page_to_pfn(page));
>> +#ifdef CONFIG_CMA
>> + /*
>> + * use volatile to use local variable mt instead of
>> + * refetching mt value.
>> + */
>> + volatile int mt = get_pageblock_migratetype(page);
>> +
>> + if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
>> + return false;
>> +#endif
>
> Open-coded use of `volatile' draws unwelcome attention.
>
> What are we trying to do here? Prevent the compiler from rerunning all
> of get_pageblock_migratetype() (really __get_pfnblock_flags_mask())
> twice? That would be pretty dumb of it?
>
> Would a suitably-commented something like
>
> int __mt = get_pageblock_migratetype(page);
> int mt = __READ_ONCE(__mt);
>
> express this better?
Yes, we want READ_ONCE I think. Apart from that LGTM.
--
Thanks,
David / dhildenb
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2022-05-08 0:19 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-05-05 6:44 [PATCH v2] mm: fix is_pinnable_page against on cma page Minchan Kim
2022-05-07 19:23 ` Andrew Morton
2022-05-08 0:19 ` David Hildenbrand
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.