Linux-kselftest 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>,
	"Christoph Hellwig" <hch@infradead.org>,
	"Dan Williams" <dan.j.williams@intel.com>,
	"Dave Chinner" <david@fromorbit.com>,
	"Ira Weiny" <ira.weiny@intel.com>, "Jan Kara" <jack@suse.cz>,
	"Jason Gunthorpe" <jgg@ziepe.ca>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Jérôme Glisse" <jglisse@redhat.com>,
	"Kirill A . Shutemov" <kirill@shutemov.name>,
	"Michal Hocko" <mhocko@suse.com>,
	"Mike Kravetz" <mike.kravetz@oracle.com>,
	"Shuah Khan" <shuah@kernel.org>,
	"Vlastimil Babka" <vbabka@suse.cz>,
	"Matthew Wilcox" <willy@infradead.org>,
	linux-doc@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kselftest@vger.kernel.org, linux-rdma@vger.kernel.org,
	linux-mm@kvack.org, LKML <linux-kernel@vger.kernel.org>,
	"John Hubbard" <jhubbard@nvidia.com>
Subject: [PATCH v4 10/12] mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting
Date: Tue, 4 Feb 2020 15:41:15 -0800
Message-ID: <20200204234117.2974687-11-jhubbard@nvidia.com> (raw)
In-Reply-To: <20200204234117.2974687-1-jhubbard@nvidia.com>

Now that pages are "DMA-pinned" via pin_user_page*(), and unpinned via
unpin_user_pages*(), we need some visibility into whether all of this is
working correctly.

Add two new fields to /proc/vmstat:

    nr_foll_pin_acquired
    nr_foll_pin_released

These are documented in Documentation/core-api/pin_user_pages.rst.
They represent the number of pages (since boot time) that have been
pinned ("nr_foll_pin_acquired") and unpinned ("nr_foll_pin_released"),
via pin_user_pages*() and unpin_user_pages*().

In the absence of long-running DMA or RDMA operations that hold pages
pinned, the above two fields will normally be equal to each other.

Also: update Documentation/core-api/pin_user_pages.rst, to remove an
earlier (now confirmed untrue) claim about a performance problem with
/proc/vmstat.

Also: updated Documentation/core-api/pin_user_pages.rst to rename the
new /proc/vmstat entries, to the names listed here.

Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 Documentation/core-api/pin_user_pages.rst |  8 ++------
 include/linux/mmzone.h                    |  2 ++
 mm/gup.c                                  | 10 ++++++++++
 mm/vmstat.c                               |  2 ++
 4 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst
index dd21ea140ef4..194204d74a50 100644
--- a/Documentation/core-api/pin_user_pages.rst
+++ b/Documentation/core-api/pin_user_pages.rst
@@ -208,12 +208,8 @@ has the following new calls to exercise the new pin*() wrapper functions:
 You can monitor how many total dma-pinned pages have been acquired and released
 since the system was booted, via two new /proc/vmstat entries: ::
 
-    /proc/vmstat/nr_foll_pin_requested
-    /proc/vmstat/nr_foll_pin_requested
-
-Those are both going to show zero, unless CONFIG_DEBUG_VM is set. This is
-because there is a noticeable performance drop in unpin_user_page(), when they
-are activated.
+    /proc/vmstat/nr_foll_pin_acquired
+    /proc/vmstat/nr_foll_pin_released
 
 Other diagnostics
 =================
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 462f6873905a..4bca42eeb439 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -243,6 +243,8 @@ enum node_stat_item {
 	NR_DIRTIED,		/* page dirtyings since bootup */
 	NR_WRITTEN,		/* page writings since bootup */
 	NR_KERNEL_MISC_RECLAIMABLE,	/* reclaimable non-slab kernel pages */
+	NR_FOLL_PIN_ACQUIRED,	/* via: pin_user_page(), gup flag: FOLL_PIN */
+	NR_FOLL_PIN_RELEASED,	/* pages returned via unpin_user_page() */
 	NR_VM_NODE_STAT_ITEMS
 };
 
diff --git a/mm/gup.c b/mm/gup.c
index 4d0d94405639..7c543849181b 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -86,6 +86,8 @@ static __maybe_unused struct page *try_grab_compound_head(struct page *page,
 	if (flags & FOLL_GET)
 		return try_get_compound_head(page, refs);
 	else if (flags & FOLL_PIN) {
+		int orig_refs = refs;
+
 		/*
 		 * When pinning a compound page of order > 1 (which is what
 		 * hpage_pincount_available() checks for), use an exact count to
@@ -104,6 +106,9 @@ static __maybe_unused struct page *try_grab_compound_head(struct page *page,
 		if (hpage_pincount_available(page))
 			hpage_pincount_add(page, refs);
 
+		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED,
+				    orig_refs);
+
 		return page;
 	}
 
@@ -158,6 +163,8 @@ bool __must_check try_grab_page(struct page *page, unsigned int flags)
 		 * once, so that the page really is pinned.
 		 */
 		page_ref_add(page, refs);
+
+		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1);
 	}
 
 	return true;
@@ -178,6 +185,7 @@ static bool __unpin_devmap_managed_user_page(struct page *page)
 
 	count = page_ref_sub_return(page, refs);
 
+	mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1);
 	/*
 	 * devmap page refcounts are 1-based, rather than 0-based: if
 	 * refcount is 1, then the page is free and the refcount is
@@ -228,6 +236,8 @@ void unpin_user_page(struct page *page)
 
 	if (page_ref_sub_and_test(page, refs))
 		__put_page(page);
+
+	mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1);
 }
 EXPORT_SYMBOL(unpin_user_page);
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 78d53378db99..c9c0d71f917f 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1168,6 +1168,8 @@ const char * const vmstat_text[] = {
 	"nr_dirtied",
 	"nr_written",
 	"nr_kernel_misc_reclaimable",
+	"nr_foll_pin_acquired",
+	"nr_foll_pin_released",
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
-- 
2.25.0


  parent reply index

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-04 23:41 [PATCH v4 00/12] mm/gup: track FOLL_PIN pages John Hubbard
2020-02-04 23:41 ` [PATCH v4 01/12] mm: dump_page(): better diagnostics for compound pages John Hubbard
2020-02-04 23:41 ` [PATCH v4 02/12] mm/gup: split get_user_pages_remote() into two routines John Hubbard
2020-02-04 23:41 ` [PATCH v4 03/12] mm/gup: pass a flags arg to __gup_device_* functions John Hubbard
2020-02-04 23:41 ` [PATCH v4 04/12] mm: introduce page_ref_sub_return() John Hubbard
2020-02-05  9:23   ` Jan Kara
2020-02-05 11:23   ` Kirill A. Shutemov
2020-02-04 23:41 ` [PATCH v4 05/12] mm/gup: pass gup flags to two more routines John Hubbard
2020-02-04 23:41 ` [PATCH v4 06/12] mm/gup: require FOLL_GET for get_user_pages_fast() John Hubbard
2020-02-04 23:41 ` [PATCH v4 07/12] mm/gup: track FOLL_PIN pages John Hubbard
2020-02-05 11:35   ` Kirill A. Shutemov
2020-02-04 23:41 ` [PATCH v4 08/12] mm/gup: page->hpage_pinned_refcount: exact pin counts for huge pages John Hubbard
2020-02-04 23:41 ` [PATCH v4 09/12] mm: dump_page(): better diagnostics for huge pinned pages John Hubbard
2020-02-04 23:41 ` John Hubbard [this message]
2020-02-05  9:37   ` [PATCH v4 10/12] mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting Jan Kara
2020-02-05 23:13     ` John Hubbard
2020-02-05 11:43   ` Kirill A. Shutemov
2020-02-05 23:58     ` John Hubbard
2020-02-04 23:41 ` [PATCH v4 11/12] mm/gup_benchmark: support pin_user_pages() and related calls John Hubbard
2020-02-05 11:46   ` Kirill A. Shutemov
2020-02-04 23:41 ` [PATCH v4 12/12] selftests/vm: run_vmtests: invoke gup_benchmark with basic FOLL_PIN coverage John Hubbard

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=20200204234117.2974687-11-jhubbard@nvidia.com \
    --to=jhubbard@nvidia.com \
    --cc=akpm@linux-foundation.org \
    --cc=corbet@lwn.net \
    --cc=dan.j.williams@intel.com \
    --cc=david@fromorbit.com \
    --cc=hch@infradead.org \
    --cc=ira.weiny@intel.com \
    --cc=jack@suse.cz \
    --cc=jgg@ziepe.ca \
    --cc=jglisse@redhat.com \
    --cc=kirill@shutemov.name \
    --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-mm@kvack.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=shuah@kernel.org \
    --cc=vbabka@suse.cz \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    /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-kselftest Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-kselftest/0 linux-kselftest/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-kselftest linux-kselftest/ https://lore.kernel.org/linux-kselftest \
		linux-kselftest@vger.kernel.org
	public-inbox-index linux-kselftest

Example config snippet for mirrors

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


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