The patch titled
Subject: mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages
has been added to the -mm tree. Its filename is
mm-devmap-refactor-1-based-refcounting-for-zone_device-pages.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-devmap-refactor-1-based-refcounting-for-zone_device-pages.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-devmap-refactor-1-based-refcounting-for-zone_device-pages.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: John Hubbard <jhubbard@xxxxxxxxxx>
Subject: mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages
An upcoming patch changes and complicates the refcounting and especially
the "put page" aspects of it. In order to keep everything clean, refactor
the devmap page release routines:
* Rename put_devmap_managed_page() to page_is_devmap_managed(), and
limit the functionality to "read only": return a bool, with no side
effects.
* Add a new routine, put_devmap_managed_page(), to handle decrementing
the refcount for ZONE_DEVICE pages.
* Change callers (just release_pages() and put_page()) to check
page_is_devmap_managed() before calling the new
put_devmap_managed_page() routine. This is a performance point:
put_page() is a hot path, so we need to avoid non- inline function calls
where possible.
* Rename __put_devmap_managed_page() to free_devmap_managed_page(), and
limit the functionality to unconditionally freeing a devmap page.
This is originally based on a separate patch by Ira Weiny, which applied
to an early version of the put_user_page() experiments. Since then,
Jérôme Glisse suggested the refactoring described above.
Link: http://lkml.kernel.org/r/20200107224558.2362728-5-jhubbard@xxxxxxxxxx
Signed-off-by: Ira Weiny <ira.weiny@xxxxxxxxx>
Signed-off-by: John Hubbard <jhubbard@xxxxxxxxxx>
Suggested-by: Jérôme Glisse <jglisse@xxxxxxxxxx>
Reviewed-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Reviewed-by: Jan Kara <jack@xxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Kirill A. Shutemov <kirill@xxxxxxxxxxxxx>
Cc: Alex Williamson <alex.williamson@xxxxxxxxxx>
Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Björn Töpel <bjorn.topel@xxxxxxxxx>
Cc: Daniel Vetter <daniel.vetter@xxxxxxxx>
Cc: Hans Verkuil <hverkuil-cisco@xxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Leon Romanovsky <leonro@xxxxxxxxxxxx>
Cc: Mauro Carvalho Chehab <mchehab@xxxxxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm.h | 18 +++++++++++++-----
mm/memremap.c | 15 +--------------
mm/swap.c | 27 ++++++++++++++++++++++++++-
3 files changed, 40 insertions(+), 20 deletions(-)
--- a/include/linux/mm.h~mm-devmap-refactor-1-based-refcounting-for-zone_device-pages
+++ a/include/linux/mm.h
@@ -952,9 +952,10 @@ static inline bool is_zone_device_page(c
#endif
#ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page);
+void free_devmap_managed_page(struct page *page);
DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
-static inline bool put_devmap_managed_page(struct page *page)
+
+static inline bool page_is_devmap_managed(struct page *page)
{
if (!static_branch_unlikely(&devmap_managed_key))
return false;
@@ -963,7 +964,6 @@ static inline bool put_devmap_managed_pa
switch (page->pgmap->type) {
case MEMORY_DEVICE_PRIVATE:
case MEMORY_DEVICE_FS_DAX:
- __put_devmap_managed_page(page);
return true;
default:
break;
@@ -971,11 +971,17 @@ static inline bool put_devmap_managed_pa
return false;
}
+void put_devmap_managed_page(struct page *page);
+
#else /* CONFIG_DEV_PAGEMAP_OPS */
-static inline bool put_devmap_managed_page(struct page *page)
+static inline bool page_is_devmap_managed(struct page *page)
{
return false;
}
+
+static inline void put_devmap_managed_page(struct page *page)
+{
+}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
static inline bool is_device_private_page(const struct page *page)
@@ -1028,8 +1034,10 @@ static inline void put_page(struct page
* need to inform the device driver through callback. See
* include/linux/memremap.h and HMM for details.
*/
- if (put_devmap_managed_page(page))
+ if (page_is_devmap_managed(page)) {
+ put_devmap_managed_page(page);
return;
+ }
if (put_page_testzero(page))
__put_page(page);
--- a/mm/memremap.c~mm-devmap-refactor-1-based-refcounting-for-zone_device-pages
+++ a/mm/memremap.c
@@ -431,20 +431,8 @@ struct dev_pagemap *get_dev_pagemap(unsi
EXPORT_SYMBOL_GPL(get_dev_pagemap);
#ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page)
+void free_devmap_managed_page(struct page *page)
{
- int count = page_ref_dec_return(page);
-
- /* still busy */
- if (count > 1)
- return;
-
- /* only triggered by the dev_pagemap shutdown path */
- if (count == 0) {
- __put_page(page);
- return;
- }
-
/* notify page idle for dax */
if (!is_device_private_page(page)) {
wake_up_var(&page->_refcount);
@@ -481,5 +469,4 @@ void __put_devmap_managed_page(struct pa
page->mapping = NULL;
page->pgmap->ops->page_free(page);
}
-EXPORT_SYMBOL(__put_devmap_managed_page);
#endif /* CONFIG_DEV_PAGEMAP_OPS */
--- a/mm/swap.c~mm-devmap-refactor-1-based-refcounting-for-zone_device-pages
+++ a/mm/swap.c
@@ -813,8 +813,10 @@ void release_pages(struct page **pages,
* processing, and instead, expect a call to
* put_page_testzero().
*/
- if (put_devmap_managed_page(page))
+ if (page_is_devmap_managed(page)) {
+ put_devmap_managed_page(page);
continue;
+ }
}
page = compound_head(page);
@@ -1102,3 +1104,26 @@ void __init swap_setup(void)
* _really_ don't want to cluster much more
*/
}
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+void put_devmap_managed_page(struct page *page)
+{
+ int count;
+
+ if (WARN_ON_ONCE(!page_is_devmap_managed(page)))
+ return;
+
+ count = page_ref_dec_return(page);
+
+ /*
+ * devmap page refcounts are 1-based, rather than 0-based: if
+ * refcount is 1, then the page is free and the refcount is
+ * stable because nobody holds a reference on the page.
+ */
+ if (count == 1)
+ free_devmap_managed_page(page);
+ else if (!count)
+ __put_page(page);
+}
+EXPORT_SYMBOL(put_devmap_managed_page);
+#endif
_
Patches currently in -mm which might be from jhubbard@xxxxxxxxxx are
mm-gup-factor-out-duplicate-code-from-four-routines.patch
mm-gup-move-try_get_compound_head-to-top-fix-minor-issues.patch
mm-devmap-refactor-1-based-refcounting-for-zone_device-pages.patch
goldish_pipe-rename-local-pin_user_pages-routine.patch
mm-fix-get_user_pages_remotes-handling-of-foll_longterm.patch
vfio-fix-foll_longterm-use-simplify-get_user_pages_remote-call.patch
mm-gup-allow-foll_force-for-get_user_pages_fast.patch
ib-umem-use-get_user_pages_fast-to-pin-dma-pages.patch
media-v4l2-core-set-pages-dirty-upon-releasing-dma-buffers.patch
mm-gup-introduce-pin_user_pages-and-foll_pin.patch
goldish_pipe-convert-to-pin_user_pages-and-put_user_page.patch
ib-corehwumem-set-foll_pin-via-pin_user_pages-fix-up-odp.patch
mm-process_vm_access-set-foll_pin-via-pin_user_pages_remote.patch
drm-via-set-foll_pin-via-pin_user_pages_fast.patch
fs-io_uring-set-foll_pin-via-pin_user_pages.patch
net-xdp-set-foll_pin-via-pin_user_pages.patch
media-v4l2-core-pin_user_pages-foll_pin-and-put_user_page-conversion.patch
vfio-mm-pin_user_pages-foll_pin-and-put_user_page-conversion.patch
powerpc-book3s64-convert-to-pin_user_pages-and-put_user_page.patch
mm-gup_benchmark-use-proper-foll_write-flags-instead-of-hard-coding-1.patch
mm-tree-wide-rename-put_user_page-to-unpin_user_page.patch
