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.comSigned-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/hugetlb.h

@@ -211,7 +211,8 @@ struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
 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(struct page *oldpage,
 
 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;
 }

mm/hugetlb.c

@@ -6233,7 +6233,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 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;
@@ -6243,6 +6244,8 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	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
@@ -6289,6 +6292,10 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 					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++;
@@ -6303,6 +6310,10 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 			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++;
 		}

mm/mprotect.c

@@ -460,7 +460,8 @@ unsigned long change_protection(struct mmu_gather *tlb,
 	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);

mm/userfaultfd.c

@@ -705,6 +705,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 			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 *dst_mm, unsigned long start,
 	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