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 15/23] mm/hugetlb: Handle pte markers in page faults
Date:   Mon, 15 Nov 2021 16:02:14 +0800
Message-Id: <20211115080214.74926-1-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

Allow hugetlb code to handle pte markers just like none ptes.  It's mostly
there, we just need to make sure we don't assume hugetlb_no_page() only handles
none pte, so when detecting pte change we should use pte_same() rather than
pte_none().  We need to pass in the old_pte to do the comparison.

Check the original pte to see whether it's a pte marker, if it is, we should
recover uffd-wp bit on the new pte to be installed, so that the next write will
be trapped by uffd.

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 mm/hugetlb.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7fc213c0ebf8..e8d01277af0f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5361,7 +5361,8 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma,
 static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 			struct vm_area_struct *vma,
 			struct address_space *mapping, pgoff_t idx,
-			unsigned long address, pte_t *ptep, unsigned int flags)
+			unsigned long address, pte_t *ptep,
+			pte_t old_pte, unsigned int flags)
 {
 	struct hstate *h = hstate_vma(vma);
 	vm_fault_t ret = VM_FAULT_SIGBUS;
@@ -5487,7 +5488,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 
 	ptl = huge_pte_lock(h, mm, ptep);
 	ret = 0;
-	if (!huge_pte_none(huge_ptep_get(ptep)))
+	/* If pte changed from under us, retry */
+	if (!pte_same(huge_ptep_get(ptep), old_pte))
 		goto backout;
 
 	if (anon_rmap) {
@@ -5497,6 +5499,12 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 		page_dup_rmap(page, true);
 	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
 				&& (vma->vm_flags & VM_SHARED)));
+	/*
+	 * If this pte was previously wr-protected, keep it wr-protected even
+	 * if populated.
+	 */
+	if (unlikely(is_pte_marker_uffd_wp(old_pte)))
+		new_pte = huge_pte_wrprotect(huge_pte_mkuffd_wp(new_pte));
 	set_huge_pte_at(mm, haddr, ptep, new_pte);
 
 	hugetlb_count_add(pages_per_huge_page(h), mm);
@@ -5614,8 +5622,10 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 	entry = huge_ptep_get(ptep);
-	if (huge_pte_none(entry)) {
-		ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags);
+	/* PTE markers should be handled the same way as none pte */
+	if (huge_pte_none_mostly(entry)) {
+		ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep,
+				      entry, flags);
 		goto out_mutex;
 	}
 
-- 
2.32.0