From: Ira Weiny <[email protected]>
release_pages() is an optimized version of a loop around put_page().
Unfortunately for devmap pages the logic is not entirely correct in
release_pages(). This is because device pages can be more than type
MEMORY_DEVICE_PUBLIC. There are in fact 4 types, private, public, FS
DAX, and PCI P2PDMA. Some of these have specific needs to "put" the
page while others do not.
This logic to handle any special needs is contained in
put_devmap_managed_page(). Therefore all devmap pages should be
processed by this function where we can contain the correct logic for a
page put.
Handle all device type pages within release_pages() by calling
put_devmap_managed_page() on all devmap pages. If
put_devmap_managed_page() returns true the page has been put and we
continue with the next page. A false return of
put_devmap_managed_page() means the page did not require special
processing and should fall to "normal" processing.
This was found via code inspection while determining if release_pages()
and the new put_user_pages() could be interchangeable.[1]
[1] https://lore.kernel.org/lkml/[email protected]/
Cc: Jérôme Glisse <[email protected]>
Cc: Michal Hocko <[email protected]>
Reviewed-by: Dan Williams <[email protected]>
Reviewed-by: John Hubbard <[email protected]>
Signed-off-by: Ira Weiny <[email protected]>
---
Changes from V3:
Update comment to the one provided by John
Changes from V2:
Update changelog for more clarity as requested by Michal
Update comment WRT "failing" of put_devmap_managed_page()
Changes from V1:
Add comment clarifying that put_devmap_managed_page() can still
fail.
Add Reviewed-by tags.
mm/swap.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/mm/swap.c b/mm/swap.c
index 7ede3eddc12a..607c48229a1d 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -740,15 +740,20 @@ void release_pages(struct page **pages, int nr)
if (is_huge_zero_page(page))
continue;
- /* Device public page can not be huge page */
- if (is_device_public_page(page)) {
+ if (is_zone_device_page(page)) {
if (locked_pgdat) {
spin_unlock_irqrestore(&locked_pgdat->lru_lock,
flags);
locked_pgdat = NULL;
}
- put_devmap_managed_page(page);
- continue;
+ /*
+ * ZONE_DEVICE pages that return 'false' from
+ * put_devmap_managed_page() do not require special
+ * processing, and instead, expect a call to
+ * put_page_testzero().
+ */
+ if (put_devmap_managed_page(page))
+ continue;
}
page = compound_head(page);
--
2.20.1
Sorry for a late reply.
On Wed 05-06-19 14:49:22, [email protected] wrote:
> From: Ira Weiny <[email protected]>
>
> release_pages() is an optimized version of a loop around put_page().
> Unfortunately for devmap pages the logic is not entirely correct in
> release_pages(). This is because device pages can be more than type
> MEMORY_DEVICE_PUBLIC. There are in fact 4 types, private, public, FS
> DAX, and PCI P2PDMA. Some of these have specific needs to "put" the
> page while others do not.
>
> This logic to handle any special needs is contained in
> put_devmap_managed_page(). Therefore all devmap pages should be
> processed by this function where we can contain the correct logic for a
> page put.
>
> Handle all device type pages within release_pages() by calling
> put_devmap_managed_page() on all devmap pages. If
> put_devmap_managed_page() returns true the page has been put and we
> continue with the next page. A false return of
> put_devmap_managed_page() means the page did not require special
> processing and should fall to "normal" processing.
>
> This was found via code inspection while determining if release_pages()
> and the new put_user_pages() could be interchangeable.[1]
This is much more clear than the previous version I've looked at. Thanks
a lot!
>
> [1] https://lore.kernel.org/lkml/[email protected]/
>
> Cc: J?r?me Glisse <[email protected]>
> Cc: Michal Hocko <[email protected]>
> Reviewed-by: Dan Williams <[email protected]>
> Reviewed-by: John Hubbard <[email protected]>
> Signed-off-by: Ira Weiny <[email protected]>
Acked-by: Michal Hocko <[email protected]>
>
> ---
> Changes from V3:
> Update comment to the one provided by John
>
> Changes from V2:
> Update changelog for more clarity as requested by Michal
> Update comment WRT "failing" of put_devmap_managed_page()
>
> Changes from V1:
> Add comment clarifying that put_devmap_managed_page() can still
> fail.
> Add Reviewed-by tags.
>
> mm/swap.c | 13 +++++++++----
> 1 file changed, 9 insertions(+), 4 deletions(-)
>
> diff --git a/mm/swap.c b/mm/swap.c
> index 7ede3eddc12a..607c48229a1d 100644
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -740,15 +740,20 @@ void release_pages(struct page **pages, int nr)
> if (is_huge_zero_page(page))
> continue;
>
> - /* Device public page can not be huge page */
> - if (is_device_public_page(page)) {
> + if (is_zone_device_page(page)) {
> if (locked_pgdat) {
> spin_unlock_irqrestore(&locked_pgdat->lru_lock,
> flags);
> locked_pgdat = NULL;
> }
> - put_devmap_managed_page(page);
> - continue;
> + /*
> + * ZONE_DEVICE pages that return 'false' from
> + * put_devmap_managed_page() do not require special
> + * processing, and instead, expect a call to
> + * put_page_testzero().
> + */
> + if (put_devmap_managed_page(page))
> + continue;
> }
>
> page = compound_head(page);
> --
> 2.20.1
>
--
Michal Hocko
SUSE Labs
On Wed, Jun 05, 2019 at 02:49:22PM -0700, [email protected] wrote:
> From: Ira Weiny <[email protected]>
>
> release_pages() is an optimized version of a loop around put_page().
> Unfortunately for devmap pages the logic is not entirely correct in
> release_pages(). This is because device pages can be more than type
> MEMORY_DEVICE_PUBLIC. There are in fact 4 types, private, public, FS
> DAX, and PCI P2PDMA. Some of these have specific needs to "put" the
> page while others do not.
>
> This logic to handle any special needs is contained in
> put_devmap_managed_page(). Therefore all devmap pages should be
> processed by this function where we can contain the correct logic for a
> page put.
>
> Handle all device type pages within release_pages() by calling
> put_devmap_managed_page() on all devmap pages. If
> put_devmap_managed_page() returns true the page has been put and we
> continue with the next page. A false return of
> put_devmap_managed_page() means the page did not require special
> processing and should fall to "normal" processing.
>
> This was found via code inspection while determining if release_pages()
> and the new put_user_pages() could be interchangeable.[1]
>
> [1] https://lore.kernel.org/lkml/[email protected]/
>
> Cc: Jérôme Glisse <[email protected]>
> Cc: Michal Hocko <[email protected]>
> Reviewed-by: Dan Williams <[email protected]>
> Reviewed-by: John Hubbard <[email protected]>
> Signed-off-by: Ira Weiny <[email protected]>
>
> ---
> Changes from V3:
> Update comment to the one provided by John
>
> Changes from V2:
> Update changelog for more clarity as requested by Michal
> Update comment WRT "failing" of put_devmap_managed_page()
>
> Changes from V1:
> Add comment clarifying that put_devmap_managed_page() can still
> fail.
> Add Reviewed-by tags.
>
> mm/swap.c | 13 +++++++++----
> 1 file changed, 9 insertions(+), 4 deletions(-)
Andrew,
As per the discussion on the hmm thread I took this patch into the
hmm.git as the conflict that was created with CH's rework was tricky -
the resolution is simple, but keeping Ira's hunk instead of the delete
is, IMHO, subtle.
Regards,
Jason