[PATCH v4 3/5] um: Do a double clone to disable rseq

[benjamin at sipsolutions.net]

From: Benjamin Berg <benjamin.berg at intel.com>

Newer glibc versions are enabling rseq support by default. This remains
enabled in the cloned child process, potentially causing the host kernel
to write/read memory in the child.

It appears that this was purely not an issue because the used memory
area happened to be above TASK_SIZE and remains mapped.

Note that a better approach would be to exec a small static binary that
does not link with other libraries. Using a memfd and execveat the
binary could be embedded into UML itself and it would result in an
entirely clean execution environment for userspace.

Signed-off-by: Benjamin Berg <benjamin.berg at intel.com>

---

v2: Improved clone logic using CLONE_VFORK
v3: Undo incorrect change in child wait loop
v4: Do not use WNOHANG in wait for CLONE_VFORK, this seems to fail on
    older host kernel versions.
---
 arch/um/os-Linux/skas/process.c | 53 ++++++++++++++++++++++++++++++---
 1 file changed, 49 insertions(+), 4 deletions(-)

diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index 41a288dcfc34..8fa2d06faef4 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -255,6 +255,32 @@ static int userspace_tramp(void *stack)
 int userspace_pid[NR_CPUS];
 int kill_userspace_mm[NR_CPUS];
 
+struct tramp_data {
+	int pid;
+	void *clone_sp;
+	void *stack;
+};
+
+static int userspace_tramp_clone_vm(void *data)
+{
+	struct tramp_data *tramp_data = data;
+
+	/*
+	 * At this point we are still in the same VM as the parent, but rseq
+	 * has been disabled for this process.
+	 * Continue with the clone into the new userspace process, the kernel
+	 * continues as soon as this process quits (CLONE_VFORK).
+	 */
+
+	tramp_data->pid = clone(userspace_tramp, tramp_data->clone_sp,
+				CLONE_PARENT | CLONE_FILES | SIGCHLD,
+				tramp_data->stack);
+	if (tramp_data->pid < 0)
+		tramp_data->pid = -errno;
+
+	exit(0);
+}
+
 /**
  * start_userspace() - prepare a new userspace process
  * @stub_stack:	pointer to the stub stack.
@@ -268,9 +294,10 @@ int kill_userspace_mm[NR_CPUS];
  */
 int start_userspace(unsigned long stub_stack)
 {
+	struct tramp_data tramp_data;
 	void *stack;
 	unsigned long sp;
-	int pid, status, n, flags, err;
+	int pid, status, n, err;
 
 	/* setup a temporary stack page */
 	stack = mmap(NULL, UM_KERN_PAGE_SIZE,
@@ -286,10 +313,13 @@ int start_userspace(unsigned long stub_stack)
 	/* set stack pointer to the end of the stack page, so it can grow downwards */
 	sp = (unsigned long)stack + UM_KERN_PAGE_SIZE;
 
-	flags = CLONE_FILES | SIGCHLD;
+	tramp_data.stack = (void *) stub_stack;
+	tramp_data.clone_sp = (void *) sp;
+	tramp_data.pid = -EINVAL;
 
-	/* clone into new userspace process */
-	pid = clone(userspace_tramp, (void *) sp, flags, (void *) stub_stack);
+	/* first stage CLONE_VM clone using VFORK and no signal notification */
+	pid = clone(userspace_tramp_clone_vm, (void *) sp,
+		    CLONE_VM | CLONE_FILES | CLONE_VFORK, &tramp_data);
 	if (pid < 0) {
 		err = -errno;
 		printk(UM_KERN_ERR "%s : clone failed, errno = %d\n",
@@ -297,6 +327,21 @@ int start_userspace(unsigned long stub_stack)
 		return err;
 	}
 
+	CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL));
+	if (n < 0 || !WIFEXITED(status) || WEXITSTATUS(status)) {
+		err = -errno;
+		printk(UM_KERN_ERR "%s : wait failed, errno = %d, status = %d\n",
+		       __func__, n < 0 ? errno : 0, status);
+		goto out_kill;
+	}
+
+	pid = tramp_data.pid;
+	if (pid < 0) {
+		printk(UM_KERN_ERR "%s : second clone failed, errno = %d\n",
+		       __func__, -pid);
+		return pid;
+	}
+
 	do {
 		CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL));
 		if (n < 0) {
-- 
2.45.1