From:   Peter Xu <peterx@redhat.com>
To:     linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc:     Nadav Amit <nadav.amit@gmail.com>, peterx@redhat.com,
        Alistair Popple <apopple@nvidia.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Mike Kravetz <mike.kravetz@oracle.com>,
        Mike Rapoport <rppt@linux.vnet.ibm.com>,
        Matthew Wilcox <willy@infradead.org>,
        Jerome Glisse <jglisse@redhat.com>,
        Axel Rasmussen <axelrasmussen@google.com>,
        "Kirill A . Shutemov" <kirill@shutemov.name>,
        David Hildenbrand <david@redhat.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Hugh Dickins <hughd@google.com>
Subject: [PATCH v6 14/23] mm/hugetlb: Handle UFFDIO_WRITEPROTECT
Date:   Mon, 15 Nov 2021 16:02:00 +0800
Message-Id: <20211115080200.74866-1-peterx@redhat.com>
In-Reply-To: <20211115075522.73795-1-peterx@redhat.com>
References: <20211115075522.73795-1-peterx@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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.

Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 include/linux/hugetlb.h |  6 ++++--
 mm/hugetlb.c            | 13 ++++++++++++-
 mm/mprotect.c           |  3 ++-
 mm/userfaultfd.c        |  8 ++++++++
 4 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 4da0c4b4159a..a46011510e49 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -210,7 +210,8 @@ 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);
@@ -391,7 +392,8 @@ 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;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8146240eefc6..7fc213c0ebf8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6127,7 +6127,8 @@ 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;
@@ -6137,6 +6138,8 @@ 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
@@ -6178,6 +6181,10 @@ 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++;
@@ -6192,6 +6199,10 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 			old_pte = huge_ptep_modify_prot_start(vma, address, ptep);
 			pte = pte_mkhuge(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++;
 		}
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 0d4bf755cee8..1cc4a6d1886b 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -441,7 +441,8 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 	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(vma, start, end, newprot,
 						cp_flags);
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 6174a212c72f..037f82719e64 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -690,6 +690,7 @@ 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;
 	pgprot_t newprot;
 	int err;
 
@@ -726,6 +727,13 @@ 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
-- 
2.32.0