linux-kernel - [PATCH v3 10/12] mm/gup: /proc/vmstat: pin_user_pages (FOLL

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20200201034029.4063170-11-jhubbard@nvidia.com>
Date:   Fri, 31 Jan 2020 19:40:27 -0800
From:   John Hubbard <jhubbard@...dia.com>
To:     Andrew Morton <akpm@...ux-foundation.org>
CC:     Al Viro <viro@...iv.linux.org.uk>,
        Christoph Hellwig <hch@...radead.org>,
        Dan Williams <dan.j.williams@...el.com>,
        Dave Chinner <david@...morbit.com>,
        Ira Weiny <ira.weiny@...el.com>, Jan Kara <jack@...e.cz>,
        Jason Gunthorpe <jgg@...pe.ca>,
        Jonathan Corbet <corbet@....net>,
        Jérôme Glisse <jglisse@...hat.com>,
        "Kirill A . Shutemov" <kirill@...temov.name>,
        Michal Hocko <mhocko@...e.com>,
        Mike Kravetz <mike.kravetz@...cle.com>,
        Shuah Khan <shuah@...nel.org>,
        Vlastimil Babka <vbabka@...e.cz>,
        Matthew Wilcox <willy@...radead.org>,
        <linux-doc@...r.kernel.org>, <linux-fsdevel@...r.kernel.org>,
        <linux-kselftest@...r.kernel.org>, <linux-rdma@...r.kernel.org>,
        <linux-mm@...ck.org>, LKML <linux-kernel@...r.kernel.org>,
        John Hubbard <jhubbard@...dia.com>
Subject: [PATCH v3 10/12] mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting

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_requested
    nr_foll_pin_returned

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_requested") and unpinned ("nr_foll_pin_returned"),
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.

Signed-off-by: John Hubbard <jhubbard@...dia.com>
---
 include/linux/mmzone.h |  2 ++
 mm/gup.c               | 21 +++++++++++++++++++++
 mm/vmstat.c            |  2 ++
 3 files changed, 25 insertions(+)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c2bc309d1634..01d690586206 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_REQUESTED,	/* via: pin_user_page(), gup flag: FOLL_PIN */
+	NR_FOLL_PIN_RETURNED,	/* pages returned via unpin_user_page() */
 	NR_VM_NODE_STAT_ITEMS
 };
 
diff --git a/mm/gup.c b/mm/gup.c
index c10d0d051c5b..9fe61d15fc0e 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -29,6 +29,19 @@ struct follow_page_context {
 	unsigned int page_mask;
 };
 
+#ifdef CONFIG_DEBUG_VM
+static inline void __update_proc_vmstat(struct page *page,
+					enum node_stat_item item, int count)
+{
+	mod_node_page_state(page_pgdat(page), item, count);
+}
+#else
+static inline void __update_proc_vmstat(struct page *page,
+					enum node_stat_item item, int count)
+{
+}
+#endif
+
 static void hpage_pincount_add(struct page *page, int refs)
 {
 	VM_BUG_ON_PAGE(!hpage_pincount_available(page), page);
@@ -86,6 +99,8 @@ 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 +119,7 @@ static __maybe_unused struct page *try_grab_compound_head(struct page *page,
 		if (hpage_pincount_available(page))
 			hpage_pincount_add(page, refs);
 
+		__update_proc_vmstat(page, NR_FOLL_PIN_REQUESTED, orig_refs);
 		return page;
 	}
 
@@ -158,6 +174,8 @@ 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);
+
+		__update_proc_vmstat(page, NR_FOLL_PIN_REQUESTED, 1);
 	}
 
 	return true;
@@ -178,6 +196,7 @@ static bool __unpin_devmap_managed_user_page(struct page *page)
 
 	count = page_ref_sub_return(page, refs);
 
+	__update_proc_vmstat(page, NR_FOLL_PIN_RETURNED, 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 +247,8 @@ void unpin_user_page(struct page *page)
 
 	if (page_ref_sub_and_test(page, refs))
 		__put_page(page);
+
+	__update_proc_vmstat(page, NR_FOLL_PIN_RETURNED, 1);
 }
 EXPORT_SYMBOL(unpin_user_page);
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 78d53378db99..b56808bae1b4 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_requested",
+	"nr_foll_pin_returned",
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
-- 
2.25.0