Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
From:   Peter Xu <peterx@redhat.com>
To:     linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc:     Mike Kravetz <mike.kravetz@oracle.com>,
        Nadav Amit <nadav.amit@gmail.com>,
        Matthew Wilcox <willy@infradead.org>,
        Mike Rapoport <rppt@linux.vnet.ibm.com>,
        David Hildenbrand <david@redhat.com>,
        Hugh Dickins <hughd@google.com>,
        Jerome Glisse <jglisse@redhat.com>,
        "Kirill A . Shutemov" <kirill@shutemov.name>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Axel Rasmussen <axelrasmussen@google.com>,
        Alistair Popple <apopple@nvidia.com>, peterx@redhat.com
Subject: [PATCH v8 16/23] mm/hugetlb: Allow uffd wr-protect none ptes
Date:   Mon,  4 Apr 2022 21:49:12 -0400
Message-Id: <20220405014912.14815-1-peterx@redhat.com>
In-Reply-To: <20220405014646.13522-1-peterx@redhat.com>
References: <20220405014646.13522-1-peterx@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Teach hugetlbfs code to wr-protect none ptes just in case the page cache
existed for that pte.  Meanwhile we also need to be able to recognize a uffd-wp
marker pte and remove it for uffd_wp_resolve.

Since at it, introduce a variable "psize" to replace all references to the huge
page size fetcher.

Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 mm/hugetlb.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9317b790161d..578c48ef931a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6225,7 +6225,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	pte_t *ptep;
 	pte_t pte;
 	struct hstate *h = hstate_vma(vma);
-	unsigned long pages = 0;
+	unsigned long pages = 0, psize = huge_page_size(h);
 	bool shared_pmd = false;
 	struct mmu_notifier_range range;
 	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
@@ -6245,13 +6245,19 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 
 	mmu_notifier_invalidate_range_start(&range);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
-	for (; address < end; address += huge_page_size(h)) {
+	for (; address < end; address += psize) {
 		spinlock_t *ptl;
-		ptep = huge_pte_offset(mm, address, huge_page_size(h));
+		ptep = huge_pte_offset(mm, address, psize);
 		if (!ptep)
 			continue;
 		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
+			/*
+			 * When uffd-wp is enabled on the vma, unshare
+			 * shouldn't happen at all.  Warn about it if it
+			 * happened due to some reason.
+			 */
+			WARN_ON_ONCE(uffd_wp || uffd_wp_resolve);
 			pages++;
 			spin_unlock(ptl);
 			shared_pmd = true;
@@ -6281,12 +6287,20 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 				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));
+						     newpte, psize);
 				pages++;
 			}
 			spin_unlock(ptl);
 			continue;
 		}
+		if (unlikely(pte_marker_uffd_wp(pte))) {
+			/*
+			 * This is changing a non-present pte into a none pte,
+			 * no need for huge_ptep_modify_prot_start/commit().
+			 */
+			if (uffd_wp_resolve)
+				huge_pte_clear(mm, address, ptep, psize);
+		}
 		if (!huge_pte_none(pte)) {
 			pte_t old_pte;
 			unsigned int shift = huge_page_shift(hstate_vma(vma));
@@ -6300,6 +6314,12 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 				pte = huge_pte_clear_uffd_wp(pte);
 			huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte);
 			pages++;
+		} else {
+			/* None pte */
+			if (unlikely(uffd_wp))
+				/* Safe to modify directly (none->non-present). */
+				set_huge_pte_at(mm, address, ptep,
+						make_pte_marker(PTE_MARKER_UFFD_WP));
 		}
 		spin_unlock(ptl);
 	}
-- 
2.32.0