From 55fd6fccad3172c0feaaa817f0a1283629ff183e Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:14 -0800 Subject: mm/khugepaged: write-lock VMA while collapsing a huge page Protect VMA from concurrent page fault handler while collapsing a huge page. Page fault handler needs a stable PMD to use PTL and relies on per-VMA lock to prevent concurrent PMD changes. pmdp_collapse_flush(), set_huge_pmd() and collapse_and_free_pmd() can modify a PMD, which will not be detected by a page fault handler without proper locking. Before this patch, page tables can be walked under any one of the mmap_lock, the mapping lock, and the anon_vma lock; so when khugepaged unlinks and frees page tables, it must ensure that all of those either are locked or don't exist. This patch adds a fourth lock under which page tables can be traversed, and so khugepaged must also lock out that one. [surenb@google.com: vm_lock/i_mmap_rwsem inversion in retract_page_tables] Link: https://lkml.kernel.org/r/20230303213250.3555716-1-surenb@google.com [surenb@google.com: build fix] Link: https://lkml.kernel.org/r/CAJuCfpFjWhtzRE1X=J+_JjgJzNKhq-=JT8yTBSTHthwp0pqWZw@mail.gmail.com Link: https://lkml.kernel.org/r/20230227173632.3292573-16-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/khugepaged.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'mm/khugepaged.c') diff --git a/mm/khugepaged.c b/mm/khugepaged.c index c7317678cb10..bee7fd7db380 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1056,6 +1056,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, if (result != SCAN_SUCCEED) goto out_up_write; + vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, @@ -1517,6 +1518,9 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, goto drop_hpage; } + /* Lock the vma before taking i_mmap and page table locks */ + vma_start_write(vma); + /* * We need to lock the mapping so that from here on, only GUP-fast and * hardware page walks can access the parts of the page tables that @@ -1694,6 +1698,10 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff, result = SCAN_PTE_MAPPED_HUGEPAGE; if ((cc->is_khugepaged || is_target) && mmap_write_trylock(mm)) { + /* trylock for the same lock inversion as above */ + if (!vma_try_start_write(vma)) + goto unlock_next; + /* * Re-check whether we have an ->anon_vma, because * collapse_and_free_pmd() requires that either no -- cgit