From: Peter Xu Subject: mm/hugetlb: handle UFFDIO_WRITEPROTECT This starts from passing cp_flags into hugetlb_change_protection() so hugetlb will be able to handle MM_CP_UFFD_WP[_RESOLVE] requests. huge_pte_clear_uffd_wp() is introduced to handle the case where the UFFDIO_WRITEPROTECT is requested upon migrating huge page entries. Link: https://lkml.kernel.org/r/20220405014906.14708-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 6 ++++-- mm/hugetlb.c | 13 ++++++++++++- mm/mprotect.c | 3 ++- mm/userfaultfd.c | 8 ++++++++ 4 files changed, 26 insertions(+), 4 deletions(-) --- a/include/linux/hugetlb.h~mm-hugetlb-handle-uffdio_writeprotect +++ a/include/linux/hugetlb.h @@ -211,7 +211,8 @@ struct page *follow_huge_pgd(struct mm_s int pmd_huge(pmd_t pmd); int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot); + unsigned long address, unsigned long end, pgprot_t newprot, + unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); @@ -397,7 +398,8 @@ static inline void move_hugetlb_state(st static inline unsigned long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, - unsigned long end, pgprot_t newprot) + unsigned long end, pgprot_t newprot, + unsigned long cp_flags) { return 0; } --- a/mm/hugetlb.c~mm-hugetlb-handle-uffdio_writeprotect +++ a/mm/hugetlb.c @@ -6220,7 +6220,8 @@ long follow_hugetlb_page(struct mm_struc } unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot) + unsigned long address, unsigned long end, + pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; @@ -6230,6 +6231,8 @@ unsigned long hugetlb_change_protection( unsigned long pages = 0; bool shared_pmd = false; struct mmu_notifier_range range; + bool uffd_wp = cp_flags & MM_CP_UFFD_WP; + bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; /* * In the case of shared PMDs, the area to flush could be beyond @@ -6276,6 +6279,10 @@ unsigned long hugetlb_change_protection( entry = make_readable_migration_entry( swp_offset(entry)); newpte = swp_entry_to_pte(entry); + if (uffd_wp) + newpte = pte_swp_mkuffd_wp(newpte); + else if (uffd_wp_resolve) + newpte = pte_swp_clear_uffd_wp(newpte); set_huge_swap_pte_at(mm, address, ptep, newpte, huge_page_size(h)); pages++; @@ -6290,6 +6297,10 @@ unsigned long hugetlb_change_protection( old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = huge_pte_modify(old_pte, newprot); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); + if (uffd_wp) + pte = huge_pte_mkuffd_wp(huge_pte_wrprotect(pte)); + else if (uffd_wp_resolve) + pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; } --- a/mm/mprotect.c~mm-hugetlb-handle-uffdio_writeprotect +++ a/mm/mprotect.c @@ -460,7 +460,8 @@ unsigned long change_protection(struct m BUG_ON((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL); if (is_vm_hugetlb_page(vma)) - pages = hugetlb_change_protection(vma, start, end, newprot); + pages = hugetlb_change_protection(vma, start, end, newprot, + cp_flags); else pages = change_protection_range(tlb, vma, start, end, newprot, cp_flags); --- a/mm/userfaultfd.c~mm-hugetlb-handle-uffdio_writeprotect +++ a/mm/userfaultfd.c @@ -705,6 +705,7 @@ int mwriteprotect_range(struct mm_struct atomic_t *mmap_changing) { struct vm_area_struct *dst_vma; + unsigned long page_mask; struct mmu_gather tlb; pgprot_t newprot; int err; @@ -742,6 +743,13 @@ int mwriteprotect_range(struct mm_struct if (!vma_is_anonymous(dst_vma)) goto out_unlock; + if (is_vm_hugetlb_page(dst_vma)) { + err = -EINVAL; + page_mask = vma_kernel_pagesize(dst_vma) - 1; + if ((start & page_mask) || (len & page_mask)) + goto out_unlock; + } + if (enable_wp) newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE)); else _