[PATCH RFC 3/7] kernel/fork: always deny write access to current MM exe_file

[David Hildenbrand <david@redhat.com>]

We want to remove VM_DENYWRITE only currently only used when mapping the
executable during exec. During exec, we already deny_write_access() the
executable, however, after exec completes the VMAs mapped
with VM_DENYWRITE effectively keeps write access denied via
deny_write_access().

Let's deny write access when setting the MM exe_file. With this change, we
can remove VM_DENYWRITE for mapping executables.

This represents a minor user space visible change:
sys_prctl(PR_SET_MM_EXE_FILE) can now fail if the file is already
opened writable. Also, after sys_prctl(PR_SET_MM_EXE_FILE), the file
cannot be opened writable. Note that we can already fail with -EACCES if
the file doesn't have execute permissions.

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 kernel/fork.c | 39 ++++++++++++++++++++++++++++++++++-----
 1 file changed, 34 insertions(+), 5 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 199463625adc..0681f2973667 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -472,6 +472,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 {
 	struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
 	struct rb_node **rb_link, *rb_parent;
+	struct file *exe_file;
 	int retval;
 	unsigned long charge;
 	LIST_HEAD(uf);
@@ -489,7 +490,10 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING);
 
 	/* No ordering required: file already has been exposed. */
-	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+	exe_file = get_mm_exe_file(oldmm);
+	RCU_INIT_POINTER(mm->exe_file, exe_file);
+	if (exe_file)
+		deny_write_access(exe_file);
 
 	mm->total_vm = oldmm->total_vm;
 	mm->data_vm = oldmm->data_vm;
@@ -634,8 +638,13 @@ static inline void mm_free_pgd(struct mm_struct *mm)
 #else
 static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 {
+	struct file *exe_file;
+
 	mmap_write_lock(oldmm);
-	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+	exe_file = get_mm_exe_file(oldmm);
+	RCU_INIT_POINTER(mm->exe_file, exe_file);
+	if (exe_file)
+		deny_write_access(exe_file);
 	mmap_write_unlock(oldmm);
 	return 0;
 }
@@ -1152,11 +1161,19 @@ void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 	 */
 	old_exe_file = rcu_dereference_raw(mm->exe_file);
 
-	if (new_exe_file)
+	if (new_exe_file) {
 		get_file(new_exe_file);
+		/*
+		 * exec code is required to deny_write_access() successfully,
+		 * so this cannot fail
+		 */
+		deny_write_access(new_exe_file);
+	}
 	rcu_assign_pointer(mm->exe_file, new_exe_file);
-	if (old_exe_file)
+	if (old_exe_file) {
+		allow_write_access(old_exe_file);
 		fput(old_exe_file);
+	}
 }
 
 int atomic_set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
@@ -1183,10 +1200,22 @@ int atomic_set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 	}
 
 	/* set the new file, lockless */
+	ret = deny_write_access(new_exe_file);
+	if (ret)
+		return -EACCES;
 	get_file(new_exe_file);
+
 	old_exe_file = xchg(&mm->exe_file, new_exe_file);
-	if (old_exe_file)
+	if (old_exe_file) {
+		/*
+		 * Don't race with dup_mmap() getting the file and disallowing
+		 * write access while someone might open the file writable.
+		 */
+		mmap_read_lock(mm);
+		allow_write_access(old_exe_file);
 		fput(old_exe_file);
+		mmap_read_unlock(mm);
+	}
 	return 0;
 }
 
-- 
2.30.2