Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
From:   Lorenzo Stoakes <lstoakes@gmail.com>
To:     linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        Andrew Morton <akpm@linux-foundation.org>
Cc:     Mike Kravetz <mike.kravetz@oracle.com>,
        Muchun Song <muchun.song@linux.dev>,
        Alexander Viro <viro@zeniv.linux.org.uk>,
        Christian Brauner <brauner@kernel.org>,
        Matthew Wilcox <willy@infradead.org>,
        Hugh Dickins <hughd@google.com>,
        Andy Lutomirski <luto@kernel.org>, Jan Kara <jack@suse.cz>,
        linux-fsdevel@vger.kernel.org, bpf@vger.kernel.org,
        Lorenzo Stoakes <lstoakes@gmail.com>
Subject: [PATCH v4 3/3] mm: perform the mapping_map_writable() check after call_mmap()
Date:   Thu, 12 Oct 2023 18:04:30 +0100
Message-ID: <55e413d20678a1bb4c7cce889062bbb07b0df892.1697116581.git.lstoakes@gmail.com>
In-Reply-To: <cover.1697116581.git.lstoakes@gmail.com>
References: <cover.1697116581.git.lstoakes@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

In order for a F_SEAL_WRITE sealed memfd mapping to have an opportunity to
clear VM_MAYWRITE, we must be able to invoke the appropriate vm_ops->mmap()
handler to do so. We would otherwise fail the mapping_map_writable() check
before we had the opportunity to avoid it.

This patch moves this check after the call_mmap() invocation. Only memfd
actively denies write access causing a potential failure here (in
memfd_add_seals()), so there should be no impact on non-memfd cases.

This patch makes the userland-visible change that MAP_SHARED, PROT_READ
mappings of an F_SEAL_WRITE sealed memfd mapping will now succeed.

There is a delicate situation with cleanup paths assuming that a writable
mapping must have occurred in circumstances where it may now not have. In
order to ensure we do not accidentally mark a writable file unwritable by
mistake, we explicitly track whether we have a writable mapping and
unmap only if we do.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=217238
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
---
 mm/mmap.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/mm/mmap.c b/mm/mmap.c
index 0041e3631f6c..7f45a08e7973 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2752,6 +2752,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	unsigned long charged = 0;
 	unsigned long end = addr + len;
 	unsigned long merge_start = addr, merge_end = end;
+	bool writable_file_mapping = false;
 	pgoff_t vm_pgoff;
 	int error;
 	VMA_ITERATOR(vmi, mm, addr);
@@ -2846,17 +2847,19 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	vma->vm_pgoff = pgoff;
 
 	if (file) {
-		if (is_shared_maywrite(vm_flags)) {
-			error = mapping_map_writable(file->f_mapping);
-			if (error)
-				goto free_vma;
-		}
-
 		vma->vm_file = get_file(file);
 		error = call_mmap(file, vma);
 		if (error)
 			goto unmap_and_free_vma;
 
+		if (vma_is_shared_maywrite(vma)) {
+			error = mapping_map_writable(file->f_mapping);
+			if (error)
+				goto close_and_free_vma;
+
+			writable_file_mapping = true;
+		}
+
 		/*
 		 * Expansion is handled above, merging is handled below.
 		 * Drivers should not alter the address of the VMA.
@@ -2920,8 +2923,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	mm->map_count++;
 	if (vma->vm_file) {
 		i_mmap_lock_write(vma->vm_file->f_mapping);
-		if (vma_is_shared_maywrite(vma))
+		if (vma_is_shared_maywrite(vma)) {
 			mapping_allow_writable(vma->vm_file->f_mapping);
+			writable_file_mapping = true;
+		}
 
 		flush_dcache_mmap_lock(vma->vm_file->f_mapping);
 		vma_interval_tree_insert(vma, &vma->vm_file->f_mapping->i_mmap);
@@ -2937,7 +2942,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 
 	/* Once vma denies write, undo our temporary denial count */
 unmap_writable:
-	if (file && is_shared_maywrite(vm_flags))
+	if (writable_file_mapping)
 		mapping_unmap_writable(file->f_mapping);
 	file = vma->vm_file;
 	ksm_add_vma(vma);
@@ -2985,7 +2990,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		unmap_region(mm, &vmi.mas, vma, prev, next, vma->vm_start,
 			     vma->vm_end, vma->vm_end, true);
 	}
-	if (file && is_shared_maywrite(vm_flags))
+	if (writable_file_mapping)
 		mapping_unmap_writable(file->f_mapping);
 free_vma:
 	vm_area_free(vma);
-- 
2.42.0