Merge tag 'denywrite-for-5.15' of git://github.com/davidhildenbrand/linux

Pull MAP_DENYWRITE removal from David Hildenbrand:
 "Remove all in-tree usage of MAP_DENYWRITE from the kernel and remove
  VM_DENYWRITE.

  There are some (minor) user-visible changes:

   - We no longer deny write access to shared libaries loaded via legacy
     uselib(); this behavior matches modern user space e.g. dlopen().

   - We no longer deny write access to the elf interpreter after exec
     completed, treating it just like shared libraries (which it often
     is).

   - We always deny write access to the file linked via /proc/pid/exe:
     sys_prctl(PR_SET_MM_MAP/EXE_FILE) will fail if write access to the
     file cannot be denied, and write access to the file will remain
     denied until the link is effectivel gone (exec, termination,
     sys_prctl(PR_SET_MM_MAP/EXE_FILE)) -- just as if exec'ing the file.

  Cross-compiled for a bunch of architectures (alpha, microblaze, i386,
  s390x, ...) and verified via ltp that especially the relevant tests
  (i.e., creat07 and execve04) continue working as expected"

* tag 'denywrite-for-5.15' of git://github.com/davidhildenbrand/linux:
  fs: update documentation of get_write_access() and friends
  mm: ignore MAP_DENYWRITE in ksys_mmap_pgoff()
  mm: remove VM_DENYWRITE
  binfmt: remove in-tree usage of MAP_DENYWRITE
  kernel/fork: always deny write access to current MM exe_file
  kernel/fork: factor out replacing the current MM exe_file
  binfmt: don't use MAP_DENYWRITE when loading shared libraries via uselib()

1 files changed, 84 insertions, 11 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 695d1343a254..6d2e10a3df0b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -471,6 +471,20 @@ void free_task(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(free_task);
 
+static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+	struct file *exe_file;
+
+	exe_file = get_mm_exe_file(oldmm);
+	RCU_INIT_POINTER(mm->exe_file, exe_file);
+	/*
+	 * We depend on the oldmm having properly denied write access to the
+	 * exe_file already.
+	 */
+	if (exe_file && deny_write_access(exe_file))
+		pr_warn_once("deny_write_access() failed in %s\n", __func__);
+}
+
 #ifdef CONFIG_MMU
 static __latent_entropy int dup_mmap(struct mm_struct *mm,
 					struct mm_struct *oldmm)
@@ -494,7 +508,7 @@ 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));
+	dup_mm_exe_file(mm, oldmm);
 
 	mm->total_vm = oldmm->total_vm;
 	mm->data_vm = oldmm->data_vm;
@@ -557,12 +571,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
 		file = tmp->vm_file;
 		if (file) {
-			struct inode *inode = file_inode(file);
 			struct address_space *mapping = file->f_mapping;
 
 			get_file(file);
-			if (tmp->vm_flags & VM_DENYWRITE)
-				put_write_access(inode);
 			i_mmap_lock_write(mapping);
 			if (tmp->vm_flags & VM_SHARED)
 				mapping_allow_writable(mapping);
@@ -640,7 +651,7 @@ static inline void mm_free_pgd(struct mm_struct *mm)
 static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 {
 	mmap_write_lock(oldmm);
-	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+	dup_mm_exe_file(mm, oldmm);
 	mmap_write_unlock(oldmm);
 	return 0;
 }
@@ -1150,11 +1161,11 @@ void mmput_async(struct mm_struct *mm)
  *
  * Main users are mmput() and sys_execve(). Callers prevent concurrent
  * invocations: in mmput() nobody alive left, in execve task is single
- * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the
- * mm->exe_file, but does so without using set_mm_exe_file() in order
- * to avoid the need for any locks.
+ * threaded.
+ *
+ * Can only fail if new_exe_file != NULL.
  */
-void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 {
 	struct file *old_exe_file;
 
@@ -1165,11 +1176,73 @@ 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) {
+		/*
+		 * We expect the caller (i.e., sys_execve) to already denied
+		 * write access, so this is unlikely to fail.
+		 */
+		if (unlikely(deny_write_access(new_exe_file)))
+			return -EACCES;
 		get_file(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);
+	}
+	return 0;
+}
+
+/**
+ * replace_mm_exe_file - replace a reference to the mm's executable file
+ *
+ * This changes mm's executable file (shown as symlink /proc/[pid]/exe),
+ * dealing with concurrent invocation and without grabbing the mmap lock in
+ * write mode.
+ *
+ * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE).
+ */
+int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+{
+	struct vm_area_struct *vma;
+	struct file *old_exe_file;
+	int ret = 0;
+
+	/* Forbid mm->exe_file change if old file still mapped. */
+	old_exe_file = get_mm_exe_file(mm);
+	if (old_exe_file) {
+		mmap_read_lock(mm);
+		for (vma = mm->mmap; vma && !ret; vma = vma->vm_next) {
+			if (!vma->vm_file)
+				continue;
+			if (path_equal(&vma->vm_file->f_path,
+				       &old_exe_file->f_path))
+				ret = -EBUSY;
+		}
+		mmap_read_unlock(mm);
+		fput(old_exe_file);
+		if (ret)
+			return ret;
+	}
+
+	/* 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) {
+		/*
+		 * 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;
 }
 
 /**