From: John Hubbard <jhubbard@nvidia•com>
To: Andrew Morton <akpm@linux-foundation•org>
Cc: "Michal Hocko" <mhocko@suse•com>, "Jan Kara" <jack@suse•cz>,
kvm@vger•kernel.org, linux-doc@vger•kernel.org,
"David Airlie" <airlied@linux•ie>,
"Dave Chinner" <david@fromorbit•com>,
dri-devel@lists•freedesktop.org,
LKML <linux-kernel@vger•kernel.org>,
linux-mm@kvack•org, "Paul Mackerras" <paulus@samba•org>,
linux-kselftest@vger•kernel.org,
"Ira Weiny" <ira.weiny@intel•com>,
"Christoph Hellwig" <hch@lst•de>,
"Jonathan Corbet" <corbet@lwn•net>,
linux-rdma@vger•kernel.org,
"Christoph Hellwig" <hch@infradead•org>,
"Jason Gunthorpe" <jgg@ziepe•ca>,
"Vlastimil Babka" <vbabka@suse•cz>,
"Björn Töpel" <bjorn.topel@intel•com>,
linux-media@vger•kernel.org, "Shuah Khan" <shuah@kernel•org>,
"John Hubbard" <jhubbard@nvidia•com>,
linux-block@vger•kernel.org, "Jérôme Glisse" <jglisse@redhat•com>,
"Al Viro" <viro@zeniv•linux.org.uk>,
"Dan Williams" <dan.j.williams@intel•com>,
"Mauro Carvalho Chehab" <mchehab@kernel•org>,
"Magnus Karlsson" <magnus.karlsson@intel•com>,
"Jens Axboe" <axboe@kernel•dk>,
netdev@vger•kernel.org,
"Alex Williamson" <alex.williamson@redhat•com>,
"Daniel Vetter" <daniel@ffwll•ch>,
linux-fsdevel@vger•kernel.org, bpf@vger•kernel.org,
linuxppc-dev@lists•ozlabs.org,
"David S . Miller" <davem@davemloft•net>,
"Mike Kravetz" <mike.kravetz@oracle•com>
Subject: [PATCH v6 05/24] mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages
Date: Tue, 19 Nov 2019 00:16:24 -0800 [thread overview]
Message-ID: <20191119081643.1866232-6-jhubbard@nvidia.com> (raw)
In-Reply-To: <20191119081643.1866232-1-jhubbard@nvidia.com>
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 checking
what kind of page it is, and what kind of refcount handling it
requires.
* 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.
Cc: Christoph Hellwig <hch@lst•de>
Suggested-by: Jérôme Glisse <jglisse@redhat•com>
Reviewed-by: Dan Williams <dan.j.williams@intel•com>
Reviewed-by: Jan Kara <jack@suse•cz>
Signed-off-by: Ira Weiny <ira.weiny@intel•com>
Signed-off-by: John Hubbard <jhubbard@nvidia•com>
---
include/linux/mm.h | 27 ++++++++++++++++++++++++---
mm/memremap.c | 16 ++--------------
2 files changed, 26 insertions(+), 17 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a2adf95b3f9c..96228376139c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -967,9 +967,10 @@ static inline bool is_zone_device_page(const struct page *page)
#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;
@@ -978,7 +979,6 @@ static inline bool put_devmap_managed_page(struct page *page)
switch (page->pgmap->type) {
case MEMORY_DEVICE_PRIVATE:
case MEMORY_DEVICE_FS_DAX:
- __put_devmap_managed_page(page);
return true;
default:
break;
@@ -986,6 +986,27 @@ static inline bool put_devmap_managed_page(struct page *page)
return false;
}
+static inline bool put_devmap_managed_page(struct page *page)
+{
+ bool is_devmap = page_is_devmap_managed(page);
+
+ if (is_devmap) {
+ int 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);
+ }
+
+ return is_devmap;
+}
+
#else /* CONFIG_DEV_PAGEMAP_OPS */
static inline bool put_devmap_managed_page(struct page *page)
{
diff --git a/mm/memremap.c b/mm/memremap.c
index e899fa876a62..2ba773859031 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -411,20 +411,8 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
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);
@@ -461,5 +449,5 @@ void __put_devmap_managed_page(struct page *page)
page->mapping = NULL;
page->pgmap->ops->page_free(page);
}
-EXPORT_SYMBOL(__put_devmap_managed_page);
+EXPORT_SYMBOL(free_devmap_managed_page);
#endif /* CONFIG_DEV_PAGEMAP_OPS */
--
2.24.0
next prev parent reply other threads:[~2019-11-19 8:37 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-19 8:16 [PATCH v6 00/24] mm/gup: track dma-pinned pages: FOLL_PIN John Hubbard
2019-11-19 8:16 ` [PATCH v6 01/24] mm/gup: pass flags arg to __gup_device_* functions John Hubbard
2019-11-19 8:16 ` [PATCH v6 02/24] mm/gup: factor out duplicate code from four routines John Hubbard
2019-11-19 10:19 ` Jan Kara
2019-11-19 8:16 ` [PATCH v6 03/24] mm/gup: move try_get_compound_head() to top, fix minor issues John Hubbard
2019-11-19 8:16 ` [PATCH v6 04/24] mm: Cleanup __put_devmap_managed_page() vs ->page_free() John Hubbard
2019-11-19 8:16 ` John Hubbard [this message]
2019-11-19 8:16 ` [PATCH v6 06/24] goldish_pipe: rename local pin_user_pages() routine John Hubbard
2019-11-19 8:16 ` [PATCH v6 07/24] IB/umem: use get_user_pages_fast() to pin DMA pages John Hubbard
2019-11-19 8:16 ` [PATCH v6 08/24] media/v4l2-core: set pages dirty upon releasing DMA buffers John Hubbard
2019-11-19 8:16 ` [PATCH v6 09/24] vfio, mm: fix get_user_pages_remote() and FOLL_LONGTERM John Hubbard
2019-11-19 8:16 ` [PATCH v6 10/24] mm/gup: introduce pin_user_pages*() and FOLL_PIN John Hubbard
2019-11-19 8:16 ` [PATCH v6 11/24] goldish_pipe: convert to pin_user_pages() and put_user_page() John Hubbard
2019-11-19 8:16 ` [PATCH v6 12/24] IB/{core, hw, umem}: set FOLL_PIN via pin_user_pages*(), fix up ODP John Hubbard
2019-11-19 8:16 ` [PATCH v6 13/24] mm/process_vm_access: set FOLL_PIN via pin_user_pages_remote() John Hubbard
2019-11-19 8:16 ` [PATCH v6 14/24] drm/via: set FOLL_PIN via pin_user_pages_fast() John Hubbard
2019-11-19 8:16 ` [PATCH v6 15/24] fs/io_uring: set FOLL_PIN via pin_user_pages() John Hubbard
2019-11-19 16:10 ` Jens Axboe
2019-11-20 7:03 ` John Hubbard
2019-11-19 8:16 ` [PATCH v6 16/24] net/xdp: " John Hubbard
2019-11-19 8:16 ` [PATCH v6 17/24] mm/gup: track FOLL_PIN pages John Hubbard
2019-11-19 11:37 ` Jan Kara
2019-11-20 7:17 ` John Hubbard
2019-11-19 8:16 ` [PATCH v6 18/24] media/v4l2-core: pin_user_pages (FOLL_PIN) and put_user_page() conversion John Hubbard
2019-11-19 8:16 ` [PATCH v6 19/24] vfio, mm: " John Hubbard
2019-11-19 8:16 ` [PATCH v6 20/24] powerpc: book3s64: convert to pin_user_pages() and put_user_page() John Hubbard
2019-11-19 8:16 ` [PATCH v6 21/24] mm/gup_benchmark: use proper FOLL_WRITE flags instead of hard-coding "1" John Hubbard
2019-11-19 8:16 ` [PATCH v6 22/24] mm/gup_benchmark: support pin_user_pages() and related calls John Hubbard
2019-11-19 8:16 ` [PATCH v6 23/24] selftests/vm: run_vmtests: invoke gup_benchmark with basic FOLL_PIN coverage John Hubbard
2019-11-19 8:16 ` [PATCH v6 24/24] mm, tree-wide: rename put_user_page*() to unpin_user_page*() John Hubbard
2019-11-19 11:39 ` Jan Kara
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191119081643.1866232-6-jhubbard@nvidia.com \
--to=jhubbard@nvidia$(echo .)com \
--cc=airlied@linux$(echo .)ie \
--cc=akpm@linux-foundation$(echo .)org \
--cc=alex.williamson@redhat$(echo .)com \
--cc=axboe@kernel$(echo .)dk \
--cc=bjorn.topel@intel$(echo .)com \
--cc=bpf@vger$(echo .)kernel.org \
--cc=corbet@lwn$(echo .)net \
--cc=dan.j.williams@intel$(echo .)com \
--cc=daniel@ffwll$(echo .)ch \
--cc=davem@davemloft$(echo .)net \
--cc=david@fromorbit$(echo .)com \
--cc=dri-devel@lists$(echo .)freedesktop.org \
--cc=hch@infradead$(echo .)org \
--cc=hch@lst$(echo .)de \
--cc=ira.weiny@intel$(echo .)com \
--cc=jack@suse$(echo .)cz \
--cc=jgg@ziepe$(echo .)ca \
--cc=jglisse@redhat$(echo .)com \
--cc=kvm@vger$(echo .)kernel.org \
--cc=linux-block@vger$(echo .)kernel.org \
--cc=linux-doc@vger$(echo .)kernel.org \
--cc=linux-fsdevel@vger$(echo .)kernel.org \
--cc=linux-kernel@vger$(echo .)kernel.org \
--cc=linux-kselftest@vger$(echo .)kernel.org \
--cc=linux-media@vger$(echo .)kernel.org \
--cc=linux-mm@kvack$(echo .)org \
--cc=linux-rdma@vger$(echo .)kernel.org \
--cc=linuxppc-dev@lists$(echo .)ozlabs.org \
--cc=magnus.karlsson@intel$(echo .)com \
--cc=mchehab@kernel$(echo .)org \
--cc=mhocko@suse$(echo .)com \
--cc=mike.kravetz@oracle$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=paulus@samba$(echo .)org \
--cc=shuah@kernel$(echo .)org \
--cc=vbabka@suse$(echo .)cz \
--cc=viro@zeniv$(echo .)linux.org.uk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox