Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Sun, 4 Dec 2022 17:57:07 -0800 (PST)
From:   Hugh Dickins <hughd@google.com>
To:     Andrew Morton <akpm@linux-foundation.org>
cc:     Linus Torvalds <torvalds@linux-foundation.org>,
        Johannes Weiner <hannes@cmpxchg.org>,
        "Kirill A. Shutemov" <kirill@shutemov.name>,
        Matthew Wilcox <willy@infradead.org>,
        David Hildenbrand <david@redhat.com>,
        Vlastimil Babka <vbabka@suse.cz>, Peter Xu <peterx@redhat.com>,
        Yang Shi <shy828301@gmail.com>,
        John Hubbard <jhubbard@nvidia.com>,
        Mike Kravetz <mike.kravetz@oracle.com>,
        Sidhartha Kumar <sidhartha.kumar@oracle.com>,
        Muchun Song <songmuchun@bytedance.com>,
        Miaohe Lin <linmiaohe@huawei.com>,
        Naoya Horiguchi <naoya.horiguchi@linux.dev>,
        Mina Almasry <almasrymina@google.com>,
        James Houghton <jthoughton@google.com>,
        Zach O'Keefe <zokeefe@google.com>,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH] mm,thp,rmap: fix races between updates of
 subpages_mapcount
Message-ID: <4388158-3092-a960-ff2d-55f2b0fe4ef8@google.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Precedence: bulk

Commit 4b51634cd16a, introducing the COMPOUND_MAPPED bit, paid attention
to the impossibility of subpages_mapcount ever appearing negative; but
did not attend to those races in which it can momentarily appear larger
than thought possible.

These arise from how page_remove_rmap() first decrements page->_mapcount
or compound_mapcount, then, if that transition goes negative (logical 0),
decrements subpages_mapcount.  The initial decrement lets a racing
page_add_*_rmap() reincrement _mapcount or compound_mapcount immediately,
and then in rare cases its corresponding increment of subpages_mapcount
may be completed before page_remove_rmap()'s decrement.  There could even
(with increasing unlikelihood) be a series of increments intermixed with
the decrements.

In practice, checking subpages_mapcount with a temporary WARN on range,
has caught values of 0x1000000 (2*COMPOUND_MAPPED, when move_pages() was
using remove_migration_pmd()) and 0x800201 (do_huge_pmd_wp_page() using
__split_huge_pmd()): page_add_anon_rmap() racing page_remove_rmap(), as
predicted.

I certainly found it harder to reason about than when bit_spin_locked,
but the easy case gives a clue to how to handle the harder case.  The
easy case being the three !(nr & COMPOUND_MAPPED) checks, which should
obviously be replaced by (nr < COMPOUND_MAPPED) checks - to count a
page as compound mapped, even while the bit in that position is 0.

The harder case is when trying to decide how many subpages are newly
covered or uncovered, when compound map is first added or last removed:
not knowing all that racily happened between first and second atomic ops.

But the easy way to handle that, is again to count the page as compound
mapped all the while that its subpages_mapcount indicates so - ignoring
the _mapcount or compound_mapcount transition while it is on the way to
being reversed.

Fixes: 4b51634cd16a ("mm,thp,rmap: subpages_mapcount COMPOUND_MAPPED if PMD-mapped")
Signed-off-by: Hugh Dickins <hughd@google.com>
---
 mm/rmap.c | 42 +++++++++++++++++++++++++++++++++---------
 1 file changed, 33 insertions(+), 9 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c
index 459dc1c44d8a..b616870a09be 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1232,7 +1232,7 @@ void page_add_anon_rmap(struct page *page,
 		if (first && PageCompound(page)) {
 			mapped = subpages_mapcount_ptr(compound_head(page));
 			nr = atomic_inc_return_relaxed(mapped);
-			nr = !(nr & COMPOUND_MAPPED);
+			nr = (nr < COMPOUND_MAPPED);
 		}
 	} else if (PageTransHuge(page)) {
 		/* That test is redundant: it's for safety or to optimize out */
@@ -1241,8 +1241,16 @@ void page_add_anon_rmap(struct page *page,
 		if (first) {
 			mapped = subpages_mapcount_ptr(page);
 			nr = atomic_add_return_relaxed(COMPOUND_MAPPED, mapped);
-			nr_pmdmapped = thp_nr_pages(page);
-			nr = nr_pmdmapped - (nr & SUBPAGES_MAPPED);
+			if (likely(nr < COMPOUND_MAPPED + COMPOUND_MAPPED)) {
+				nr_pmdmapped = thp_nr_pages(page);
+				nr = nr_pmdmapped - (nr & SUBPAGES_MAPPED);
+				/* Raced ahead of a remove and another add? */
+				if (unlikely(nr < 0))
+					nr = 0;
+			} else {
+				/* Raced ahead of a remove of COMPOUND_MAPPED */
+				nr = 0;
+			}
 		}
 	}
 
@@ -1330,7 +1338,7 @@ void page_add_file_rmap(struct page *page,
 		if (first && PageCompound(page)) {
 			mapped = subpages_mapcount_ptr(compound_head(page));
 			nr = atomic_inc_return_relaxed(mapped);
-			nr = !(nr & COMPOUND_MAPPED);
+			nr = (nr < COMPOUND_MAPPED);
 		}
 	} else if (PageTransHuge(page)) {
 		/* That test is redundant: it's for safety or to optimize out */
@@ -1339,8 +1347,16 @@ void page_add_file_rmap(struct page *page,
 		if (first) {
 			mapped = subpages_mapcount_ptr(page);
 			nr = atomic_add_return_relaxed(COMPOUND_MAPPED, mapped);
-			nr_pmdmapped = thp_nr_pages(page);
-			nr = nr_pmdmapped - (nr & SUBPAGES_MAPPED);
+			if (likely(nr < COMPOUND_MAPPED + COMPOUND_MAPPED)) {
+				nr_pmdmapped = thp_nr_pages(page);
+				nr = nr_pmdmapped - (nr & SUBPAGES_MAPPED);
+				/* Raced ahead of a remove and another add? */
+				if (unlikely(nr < 0))
+					nr = 0;
+			} else {
+				/* Raced ahead of a remove of COMPOUND_MAPPED */
+				nr = 0;
+			}
 		}
 	}
 
@@ -1387,7 +1403,7 @@ void page_remove_rmap(struct page *page,
 		if (last && PageCompound(page)) {
 			mapped = subpages_mapcount_ptr(compound_head(page));
 			nr = atomic_dec_return_relaxed(mapped);
-			nr = !(nr & COMPOUND_MAPPED);
+			nr = (nr < COMPOUND_MAPPED);
 		}
 	} else if (PageTransHuge(page)) {
 		/* That test is redundant: it's for safety or to optimize out */
@@ -1396,8 +1412,16 @@ void page_remove_rmap(struct page *page,
 		if (last) {
 			mapped = subpages_mapcount_ptr(page);
 			nr = atomic_sub_return_relaxed(COMPOUND_MAPPED, mapped);
-			nr_pmdmapped = thp_nr_pages(page);
-			nr = nr_pmdmapped - (nr & SUBPAGES_MAPPED);
+			if (likely(nr < COMPOUND_MAPPED)) {
+				nr_pmdmapped = thp_nr_pages(page);
+				nr = nr_pmdmapped - (nr & SUBPAGES_MAPPED);
+				/* Raced ahead of another remove and an add? */
+				if (unlikely(nr < 0))
+					nr = 0;
+			} else {
+				/* An add of COMPOUND_MAPPED raced ahead */
+				nr = 0;
+			}
 		}
 	}
 
-- 
2.35.3