From 6287b7dae80944bfa37784a8f9d6861a4facaa6e Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sun, 4 Dec 2022 17:57:07 -0800 Subject: mm,thp,rmap: fix races between updates of subpages_mapcount 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. Link: https://lkml.kernel.org/r/4388158-3092-a960-ff2d-55f2b0fe4ef8@google.com Fixes: 4b51634cd16a ("mm,thp,rmap: subpages_mapcount COMPOUND_MAPPED if PMD-mapped") Signed-off-by: Hugh Dickins Cc: David Hildenbrand Cc: James Houghton Cc: Johannes Weiner Cc: John Hubbard Cc: "Kirill A . Shutemov" Cc: Linus Torvalds Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mike Kravetz Cc: Mina Almasry Cc: Muchun Song Cc: Naoya Horiguchi Cc: Peter Xu Cc: Sidhartha Kumar Cc: Vlastimil Babka Cc: Yang Shi Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- mm/rmap.c | 42 +++++++++++++++++++++++++++++++++--------- 1 file changed, 33 insertions(+), 9 deletions(-) (limited to 'mm/rmap.c') 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; + } } } -- cgit v1.2.3