From f45ec5ff16a75f96dac8c89862d75f1d8739efd4 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 6 Apr 2020 20:06:01 -0700 Subject: userfaultfd: wp: support swap and page migration For either swap and page migration, we all use the bit 2 of the entry to identify whether this entry is uffd write-protected. It plays a similar role as the existing soft dirty bit in swap entries but only for keeping the uffd-wp tracking for a specific PTE/PMD. Something special here is that when we want to recover the uffd-wp bit from a swap/migration entry to the PTE bit we'll also need to take care of the _PAGE_RW bit and make sure it's cleared, otherwise even with the _PAGE_UFFD_WP bit we can't trap it at all. In change_pte_range() we do nothing for uffd if the PTE is a swap entry. That can lead to data mismatch if the page that we are going to write protect is swapped out when sending the UFFDIO_WRITEPROTECT. This patch also applies/removes the uffd-wp bit even for the swap entries. Signed-off-by: Peter Xu Signed-off-by: Andrew Morton Cc: Andrea Arcangeli Cc: Bobby Powers Cc: Brian Geffon Cc: David Hildenbrand Cc: Denis Plotnikov Cc: "Dr . David Alan Gilbert" Cc: Hugh Dickins Cc: Jerome Glisse Cc: Johannes Weiner Cc: "Kirill A . Shutemov" Cc: Martin Cracauer Cc: Marty McFadden Cc: Maya Gokhale Cc: Mel Gorman Cc: Mike Kravetz Cc: Mike Rapoport Cc: Pavel Emelyanov Cc: Rik van Riel Cc: Shaohua Li Link: http://lkml.kernel.org/r/20200220163112.11409-11-peterx@redhat.com Signed-off-by: Linus Torvalds --- mm/mprotect.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) (limited to 'mm/mprotect.c') diff --git a/mm/mprotect.c b/mm/mprotect.c index e4fa41a24bec..1d823b050329 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -139,11 +139,11 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent); pages++; - } else if (IS_ENABLED(CONFIG_MIGRATION)) { + } else if (is_swap_pte(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); + pte_t newpte; if (is_write_migration_entry(entry)) { - pte_t newpte; /* * A protection check is difficult so * just be safe and disable write @@ -152,22 +152,28 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, newpte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(oldpte)) newpte = pte_swp_mksoft_dirty(newpte); - set_pte_at(vma->vm_mm, addr, pte, newpte); - - pages++; - } - - if (is_write_device_private_entry(entry)) { - pte_t newpte; - + if (pte_swp_uffd_wp(oldpte)) + newpte = pte_swp_mkuffd_wp(newpte); + } else if (is_write_device_private_entry(entry)) { /* * We do not preserve soft-dirtiness. See * copy_one_pte() for explanation. */ make_device_private_entry_read(&entry); newpte = swp_entry_to_pte(entry); - set_pte_at(vma->vm_mm, addr, pte, newpte); + if (pte_swp_uffd_wp(oldpte)) + newpte = pte_swp_mkuffd_wp(newpte); + } else { + newpte = oldpte; + } + if (uffd_wp) + newpte = pte_swp_mkuffd_wp(newpte); + else if (uffd_wp_resolve) + newpte = pte_swp_clear_uffd_wp(newpte); + + if (!pte_same(oldpte, newpte)) { + set_pte_at(vma->vm_mm, addr, pte, newpte); pages++; } } -- cgit v1.2.3-59-g8ed1b