Linux-RDMA Archive on lore.kernel.org
 help / color / Atom feed
From: John Hubbard <jhubbard@nvidia.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: "Al Viro" <viro@zeniv.linux.org.uk>,
	"Alex Williamson" <alex.williamson@redhat.com>,
	"Benjamin Herrenschmidt" <benh@kernel.crashing.org>,
	"Björn Töpel" <bjorn.topel@intel.com>,
	"Christoph Hellwig" <hch@infradead.org>,
	"Dan Williams" <dan.j.williams@intel.com>,
	"Daniel Vetter" <daniel@ffwll.ch>,
	"Dave Chinner" <david@fromorbit.com>,
	"David Airlie" <airlied@linux.ie>,
	"David S . Miller" <davem@davemloft.net>,
	"Ira Weiny" <ira.weiny@intel.com>, "Jan Kara" <jack@suse.cz>,
	"Jason Gunthorpe" <jgg@ziepe.ca>, "Jens Axboe" <axboe@kernel.dk>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Jérôme Glisse" <jglisse@redhat.com>,
	"Kirill A . Shutemov" <kirill@shutemov.name>,
	"Magnus Karlsson" <magnus.karlsson@intel.com>,
	"Mauro Carvalho Chehab" <mchehab@kernel.org>,
	"Michael Ellerman" <mpe@ellerman.id.au>,
	"Michal Hocko" <mhocko@suse.com>,
	"Mike Kravetz" <mike.kravetz@oracle.com>,
	"Paul Mackerras" <paulus@samba.org>,
	"Shuah Khan" <shuah@kernel.org>,
	"Vlastimil Babka" <vbabka@suse.cz>,
	bpf@vger.kernel.org, dri-devel@lists.freedesktop.org,
	kvm@vger.kernel.org, linux-block@vger.kernel.org,
	linux-doc@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kselftest@vger.kernel.org, linux-media@vger.kernel.org,
	linux-rdma@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	netdev@vger.kernel.org, linux-mm@kvack.org,
	LKML <linux-kernel@vger.kernel.org>,
	"John Hubbard" <jhubbard@nvidia.com>,
	"Christoph Hellwig" <hch@lst.de>
Subject: [PATCH v12 04/22] mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages
Date: Tue, 7 Jan 2020 14:45:40 -0800
Message-ID: <20200107224558.2362728-5-jhubbard@nvidia.com> (raw)
In-Reply-To: <20200107224558.2362728-1-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
  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.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
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 | 18 +++++++++++++-----
 mm/memremap.c      | 15 +--------------
 mm/swap.c          | 27 ++++++++++++++++++++++++++-
 3 files changed, 40 insertions(+), 20 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80a9162b406c..e2032ff640eb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -952,9 +952,10 @@ 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;
@@ -963,7 +964,6 @@ 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;
@@ -971,11 +971,17 @@ static inline bool put_devmap_managed_page(struct page *page)
 	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 *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);
diff --git a/mm/memremap.c b/mm/memremap.c
index f915d074ac20..4c723d2049d5 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 +449,4 @@ void __put_devmap_managed_page(struct page *page)
 	page->mapping = NULL;
 	page->pgmap->ops->page_free(page);
 }
-EXPORT_SYMBOL(__put_devmap_managed_page);
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
diff --git a/mm/swap.c b/mm/swap.c
index 5341ae93861f..cf39d24ada2a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -813,8 +813,10 @@ void release_pages(struct page **pages, int nr)
 			 * 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
-- 
2.24.1


  parent reply index

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-07 22:45 [PATCH v12 00/22] mm/gup: prereqs to track dma-pinned pages: FOLL_PIN John Hubbard
2020-01-07 22:45 ` [PATCH v12 01/22] mm/gup: factor out duplicate code from four routines John Hubbard
2020-01-07 22:45 ` [PATCH v12 02/22] mm/gup: move try_get_compound_head() to top, fix minor issues John Hubbard
2020-01-07 22:45 ` [PATCH v12 03/22] mm: Cleanup __put_devmap_managed_page() vs ->page_free() John Hubbard
2020-01-07 22:45 ` John Hubbard [this message]
2020-01-15 15:23   ` [PATCH v12 04/22] mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages Christoph Hellwig
2020-01-15 21:19     ` John Hubbard
2020-01-16  9:37       ` Christoph Hellwig
2020-01-16 20:30         ` John Hubbard
2020-01-07 22:45 ` [PATCH v12 05/22] goldish_pipe: rename local pin_user_pages() routine John Hubbard
2020-01-15 15:23   ` Christoph Hellwig
2020-01-07 22:45 ` [PATCH v12 06/22] mm: fix get_user_pages_remote()'s handling of FOLL_LONGTERM John Hubbard
2020-01-15 15:24   ` Christoph Hellwig
2020-01-07 22:45 ` [PATCH v12 07/22] vfio: fix FOLL_LONGTERM use, simplify get_user_pages_remote() call John Hubbard
2020-01-07 22:45 ` [PATCH v12 08/22] mm/gup: allow FOLL_FORCE for get_user_pages_fast() John Hubbard
2020-01-15 15:25   ` Christoph Hellwig
2020-01-07 22:45 ` [PATCH v12 09/22] IB/umem: use get_user_pages_fast() to pin DMA pages John Hubbard
2020-01-07 22:45 ` [PATCH v12 10/22] media/v4l2-core: set pages dirty upon releasing DMA buffers John Hubbard
2020-01-07 22:45 ` [PATCH v12 11/22] mm/gup: introduce pin_user_pages*() and FOLL_PIN John Hubbard
2020-01-15 15:30   ` Christoph Hellwig
2020-01-15 21:34     ` John Hubbard
2020-01-07 22:45 ` [PATCH v12 12/22] goldish_pipe: convert to pin_user_pages() and put_user_page() John Hubbard
2020-01-07 22:45 ` [PATCH v12 13/22] IB/{core,hw,umem}: set FOLL_PIN via pin_user_pages*(), fix up ODP John Hubbard
2020-01-07 22:45 ` [PATCH v12 14/22] mm/process_vm_access: set FOLL_PIN via pin_user_pages_remote() John Hubbard
2020-01-07 22:45 ` [PATCH v12 15/22] drm/via: set FOLL_PIN via pin_user_pages_fast() John Hubbard
2020-01-07 22:45 ` [PATCH v12 16/22] fs/io_uring: set FOLL_PIN via pin_user_pages() John Hubbard
2020-01-07 22:45 ` [PATCH v12 17/22] net/xdp: " John Hubbard
2020-01-07 22:45 ` [PATCH v12 18/22] media/v4l2-core: pin_user_pages (FOLL_PIN) and put_user_page() conversion John Hubbard
2020-01-07 22:45 ` [PATCH v12 19/22] vfio, mm: " John Hubbard
2020-01-07 22:45 ` [PATCH v12 20/22] powerpc: book3s64: convert to pin_user_pages() and put_user_page() John Hubbard
2020-01-07 22:45 ` [PATCH v12 21/22] mm/gup_benchmark: use proper FOLL_WRITE flags instead of hard-coding "1" John Hubbard
2020-01-07 22:45 ` [PATCH v12 22/22] mm, tree-wide: rename put_user_page*() to unpin_user_page*() John Hubbard
2020-01-15 15:26   ` Christoph Hellwig
2020-01-09 22:07 ` [PATCH v12 00/22] mm/gup: prereqs to track dma-pinned pages: FOLL_PIN John Hubbard
2020-01-14 20:15   ` John Hubbard
2020-01-14 23:29     ` Andrew Morton

Reply instructions:

You may reply publically 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=20200107224558.2362728-5-jhubbard@nvidia.com \
    --to=jhubbard@nvidia.com \
    --cc=airlied@linux.ie \
    --cc=akpm@linux-foundation.org \
    --cc=alex.williamson@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=benh@kernel.crashing.org \
    --cc=bjorn.topel@intel.com \
    --cc=bpf@vger.kernel.org \
    --cc=corbet@lwn.net \
    --cc=dan.j.williams@intel.com \
    --cc=daniel@ffwll.ch \
    --cc=davem@davemloft.net \
    --cc=david@fromorbit.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=hch@infradead.org \
    --cc=hch@lst.de \
    --cc=ira.weiny@intel.com \
    --cc=jack@suse.cz \
    --cc=jgg@ziepe.ca \
    --cc=jglisse@redhat.com \
    --cc=kirill@shutemov.name \
    --cc=kvm@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-media@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=magnus.karlsson@intel.com \
    --cc=mchehab@kernel.org \
    --cc=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=mpe@ellerman.id.au \
    --cc=netdev@vger.kernel.org \
    --cc=paulus@samba.org \
    --cc=shuah@kernel.org \
    --cc=vbabka@suse.cz \
    --cc=viro@zeniv.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-RDMA Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-rdma/0 linux-rdma/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-rdma linux-rdma/ https://lore.kernel.org/linux-rdma \
		linux-rdma@vger.kernel.org
	public-inbox-index linux-rdma

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-rdma


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git