Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
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 05/23] mm/shmem: Take care of UFFDIO_COPY_MODE_WP
Date:   Mon,  4 Apr 2022 21:48:41 -0400
Message-Id: <20220405014841.14185-1-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

Pass wp_copy into shmem_mfill_atomic_pte() through the stack, then apply the
UFFD_WP bit properly when the UFFDIO_COPY on shmem is with UFFDIO_COPY_MODE_WP.
wp_copy lands mfill_atomic_install_pte() finally.

Note: we must do pte_wrprotect() if !writable in mfill_atomic_install_pte(), as
mk_pte() could return a writable pte (e.g., when VM_SHARED on a shmem file).

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 include/linux/shmem_fs.h |  4 ++--
 mm/shmem.c               |  4 ++--
 mm/userfaultfd.c         | 23 ++++++++++++++++++-----
 3 files changed, 22 insertions(+), 9 deletions(-)

diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 3e915cc550bc..a68f982f22d1 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -145,11 +145,11 @@ extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 				  struct vm_area_struct *dst_vma,
 				  unsigned long dst_addr,
 				  unsigned long src_addr,
-				  bool zeropage,
+				  bool zeropage, bool wp_copy,
 				  struct page **pagep);
 #else /* !CONFIG_SHMEM */
 #define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \
-			       src_addr, zeropage, pagep)       ({ BUG(); 0; })
+			       src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; })
 #endif /* CONFIG_SHMEM */
 #endif /* CONFIG_USERFAULTFD */
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 7004c7f55716..9efb8a96d75e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2319,7 +2319,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 			   struct vm_area_struct *dst_vma,
 			   unsigned long dst_addr,
 			   unsigned long src_addr,
-			   bool zeropage,
+			   bool zeropage, bool wp_copy,
 			   struct page **pagep)
 {
 	struct inode *inode = file_inode(dst_vma->vm_file);
@@ -2392,7 +2392,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 		goto out_release;
 
 	ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
-				       page, true, false);
+				       page, true, wp_copy);
 	if (ret)
 		goto out_delete_from_cache;
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index dae25d985d15..b1c875b77fbb 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -77,10 +77,19 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 	 * Always mark a PTE as write-protected when needed, regardless of
 	 * VM_WRITE, which the user might change.
 	 */
-	if (wp_copy)
+	if (wp_copy) {
 		_dst_pte = pte_mkuffd_wp(_dst_pte);
-	else if (writable)
+		writable = false;
+	}
+
+	if (writable)
 		_dst_pte = pte_mkwrite(_dst_pte);
+	else
+		/*
+		 * We need this to make sure write bit removed; as mk_pte()
+		 * could return a pte with write bit set.
+		 */
+		_dst_pte = pte_wrprotect(_dst_pte);
 
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
 
@@ -95,7 +104,12 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 	}
 
 	ret = -EEXIST;
-	if (!pte_none(*dst_pte))
+	/*
+	 * We allow to overwrite a pte marker: consider when both MISSING|WP
+	 * registered, we firstly wr-protect a none pte which has no page cache
+	 * page backing it, then access the page.
+	 */
+	if (!pte_none_mostly(*dst_pte))
 		goto out_unlock;
 
 	if (page_in_cache) {
@@ -479,11 +493,10 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 			err = mfill_zeropage_pte(dst_mm, dst_pmd,
 						 dst_vma, dst_addr);
 	} else {
-		VM_WARN_ON_ONCE(wp_copy);
 		err = shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma,
 					     dst_addr, src_addr,
 					     mode != MCOPY_ATOMIC_NORMAL,
-					     page);
+					     wp_copy, page);
 	}
 
 	return err;
-- 
2.32.0