fork: extend clone3() to support setting a PID

The main motivation to add set_tid to clone3() is CRIU.

To restore a process with the same PID/TID CRIU currently uses
/proc/sys/kernel/ns_last_pid. It writes the desired (PID - 1) to
ns_last_pid and then (quickly) does a clone(). This works most of the
time, but it is racy. It is also slow as it requires multiple syscalls.

Extending clone3() to support *set_tid makes it possible restore a
process using CRIU without accessing /proc/sys/kernel/ns_last_pid and
race free (as long as the desired PID/TID is available).

This clone3() extension places the same restrictions (CAP_SYS_ADMIN)
on clone3() with *set_tid as they are currently in place for ns_last_pid.

The original version of this change was using a single value for
set_tid. At the 2019 LPC, after presenting set_tid, it was, however,
decided to change set_tid to an array to enable setting the PID of a
process in multiple PID namespaces at the same time. If a process is
created in a PID namespace it is possible to influence the PID inside
and outside of the PID namespace. Details also in the corresponding
selftest.

To create a process with the following PIDs:

      PID NS level         Requested PID
        0 (host)              31496
        1                        42
        2                         1

For that example the two newly introduced parameters to struct
clone_args (set_tid and set_tid_size) would need to be:

  set_tid[0] = 1;
  set_tid[1] = 42;
  set_tid[2] = 31496;
  set_tid_size = 3;

If only the PIDs of the two innermost nested PID namespaces should be
defined it would look like this:

  set_tid[0] = 1;
  set_tid[1] = 42;
  set_tid_size = 2;

The PID of the newly created process would then be the next available
free PID in the PID namespace level 0 (host) and 42 in the PID namespace
at level 1 and the PID of the process in the innermost PID namespace
would be 1.

The set_tid array is used to specify the PID of a process starting
from the innermost nested PID namespaces up to set_tid_size PID namespaces.

set_tid_size cannot be larger then the current PID namespace level.

Signed-off-by: Adrian Reber <areber@redhat.com>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com>
Acked-by: Andrei Vagin <avagin@gmail.com>
Link: https://lore.kernel.org/r/20191115123621.142252-1-areber@redhat.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

include/linux/pid.h

@@ -124,7 +124,8 @@ extern struct pid *find_vpid(int nr);
 extern struct pid *find_get_pid(int nr);
 extern struct pid *find_ge_pid(int nr, struct pid_namespace *);
 
-extern struct pid *alloc_pid(struct pid_namespace *ns);
+extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
+			     size_t set_tid_size);
 extern void free_pid(struct pid *pid);
 extern void disable_pid_allocation(struct pid_namespace *ns);
 

include/linux/pid_namespace.h

@@ -12,6 +12,8 @@
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 
+/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
+#define MAX_PID_NS_LEVEL 32
 
 struct fs_pin;
 

include/linux/sched/task.h

@@ -26,6 +26,9 @@ struct kernel_clone_args {
 	unsigned long stack;
 	unsigned long stack_size;
 	unsigned long tls;
+	pid_t *set_tid;
+	/* Number of elements in *set_tid */
+	size_t set_tid_size;
 };
 
 /*

include/uapi/linux/sched.h

@@ -39,24 +39,38 @@
 #ifndef __ASSEMBLY__
 /**
  * struct clone_args - arguments for the clone3 syscall
- * @flags:       Flags for the new process as listed above.
- *               All flags are valid except for CSIGNAL and
- *               CLONE_DETACHED.
- * @pidfd:       If CLONE_PIDFD is set, a pidfd will be
- *               returned in this argument.
- * @child_tid:   If CLONE_CHILD_SETTID is set, the TID of the
- *               child process will be returned in the child's
- *               memory.
- * @parent_tid:  If CLONE_PARENT_SETTID is set, the TID of
- *               the child process will be returned in the
- *               parent's memory.
- * @exit_signal: The exit_signal the parent process will be
- *               sent when the child exits.
- * @stack:       Specify the location of the stack for the
- *               child process.
- * @stack_size:  The size of the stack for the child process.
- * @tls:         If CLONE_SETTLS is set, the tls descriptor
- *               is set to tls.
+ * @flags:        Flags for the new process as listed above.
+ *                All flags are valid except for CSIGNAL and
+ *                CLONE_DETACHED.
+ * @pidfd:        If CLONE_PIDFD is set, a pidfd will be
+ *                returned in this argument.
+ * @child_tid:    If CLONE_CHILD_SETTID is set, the TID of the
+ *                child process will be returned in the child's
+ *                memory.
+ * @parent_tid:   If CLONE_PARENT_SETTID is set, the TID of
+ *                the child process will be returned in the
+ *                parent's memory.
+ * @exit_signal:  The exit_signal the parent process will be
+ *                sent when the child exits.
+ * @stack:        Specify the location of the stack for the
+ *                child process.
+ * @stack_size:   The size of the stack for the child process.
+ * @tls:          If CLONE_SETTLS is set, the tls descriptor
+ *                is set to tls.
+ * @set_tid:      Pointer to an array of type *pid_t. The size
+ *                of the array is defined using @set_tid_size.
+ *                This array is used to select PIDs/TIDs for
+ *                newly created processes. The first element in
+ *                this defines the PID in the most nested PID
+ *                namespace. Each additional element in the array
+ *                defines the PID in the parent PID namespace of
+ *                the original PID namespace. If the array has
+ *                less entries than the number of currently
+ *                nested PID namespaces only the PIDs in the
+ *                corresponding namespaces are set.
+ * @set_tid_size: This defines the size of the array referenced
+ *                in @set_tid. This cannot be larger than the
+ *                kernel's limit of nested PID namespaces.
  *
  * The structure is versioned by size and thus extensible.
  * New struct members must go at the end of the struct and
@@ -71,10 +85,13 @@ struct clone_args {
 	__aligned_u64 stack;
 	__aligned_u64 stack_size;
 	__aligned_u64 tls;
+	__aligned_u64 set_tid;
+	__aligned_u64 set_tid_size;
 };
 #endif
 
 #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
+#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
 
 /*
  * Scheduling policies

kernel/fork.c

@@ -2087,7 +2087,8 @@ static __latent_entropy struct task_struct *copy_process(
 	stackleak_task_init(p);
 
 	if (pid != &init_struct_pid) {
-		pid = alloc_pid(p->nsproxy->pid_ns_for_children);
+		pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid,
+				args->set_tid_size);
 		if (IS_ERR(pid)) {
 			retval = PTR_ERR(pid);
 			goto bad_fork_cleanup_thread;
@@ -2590,6 +2591,7 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 {
 	int err;
 	struct clone_args args;
+	pid_t *kset_tid = kargs->set_tid;
 
 	if (unlikely(usize > PAGE_SIZE))
 		return -E2BIG;
@@ -2600,6 +2602,15 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 	if (err)
 		return err;
 
+	if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL))
+		return -EINVAL;
+
+	if (unlikely(!args.set_tid && args.set_tid_size > 0))
+		return -EINVAL;
+
+	if (unlikely(args.set_tid && args.set_tid_size == 0))
+		return -EINVAL;
+
 	/*
 	 * Verify that higher 32bits of exit_signal are unset and that
 	 * it is a valid signal
@@ -2617,8 +2628,16 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 		.stack		= args.stack,
 		.stack_size	= args.stack_size,
 		.tls		= args.tls,
+		.set_tid_size	= args.set_tid_size,
 	};
 
+	if (args.set_tid &&
+		copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid),
+			(kargs->set_tid_size * sizeof(pid_t))))
+		return -EFAULT;
+
+	kargs->set_tid = kset_tid;
+
 	return 0;
 }
 
@@ -2662,6 +2681,9 @@ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
 	int err;
 
 	struct kernel_clone_args kargs;
+	pid_t set_tid[MAX_PID_NS_LEVEL];
+
+	kargs.set_tid = set_tid;
 
 	err = copy_clone_args_from_user(&kargs, uargs, size);
 	if (err)

kernel/pid.c

@@ -157,7 +157,8 @@ void free_pid(struct pid *pid)
 	call_rcu(&pid->rcu, delayed_put_pid);
 }
 
-struct pid *alloc_pid(struct pid_namespace *ns)
+struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
+		      size_t set_tid_size)
 {
 	struct pid *pid;
 	enum pid_type type;
@@ -166,6 +167,17 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 	struct upid *upid;
 	int retval = -ENOMEM;
 
+	/*
+	 * set_tid_size contains the size of the set_tid array. Starting at
+	 * the most nested currently active PID namespace it tells alloc_pid()
+	 * which PID to set for a process in that most nested PID namespace
+	 * up to set_tid_size PID namespaces. It does not have to set the PID
+	 * for a process in all nested PID namespaces but set_tid_size must
+	 * never be greater than the current ns->level + 1.
+	 */
+	if (set_tid_size > ns->level + 1)
+		return ERR_PTR(-EINVAL);
+
 	pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
 	if (!pid)
 		return ERR_PTR(retval);
@@ -174,24 +186,54 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 	pid->level = ns->level;
 
 	for (i = ns->level; i >= 0; i--) {
-		int pid_min = 1;
+		int tid = 0;
+
+		if (set_tid_size) {
+			tid = set_tid[ns->level - i];
+
+			retval = -EINVAL;
+			if (tid < 1 || tid >= pid_max)
+				goto out_free;
+			/*
+			 * Also fail if a PID != 1 is requested and
+			 * no PID 1 exists.
+			 */
+			if (tid != 1 && !tmp->child_reaper)
+				goto out_free;
+			retval = -EPERM;
+			if (!ns_capable(tmp->user_ns, CAP_SYS_ADMIN))
+				goto out_free;
+			set_tid_size--;
+		}
 
 		idr_preload(GFP_KERNEL);
 		spin_lock_irq(&pidmap_lock);
 
-		/*
-		 * init really needs pid 1, but after reaching the maximum
-		 * wrap back to RESERVED_PIDS
-		 */
-		if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS)
-			pid_min = RESERVED_PIDS;
-
-		/*
-		 * Store a null pointer so find_pid_ns does not find
-		 * a partially initialized PID (see below).
-		 */
-		nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
-				      pid_max, GFP_ATOMIC);
+		if (tid) {
+			nr = idr_alloc(&tmp->idr, NULL, tid,
+				       tid + 1, GFP_ATOMIC);
+			/*
+			 * If ENOSPC is returned it means that the PID is
+			 * alreay in use. Return EEXIST in that case.
+			 */
+			if (nr == -ENOSPC)
+				nr = -EEXIST;
+		} else {
+			int pid_min = 1;
+			/*
+			 * init really needs pid 1, but after reaching the
+			 * maximum wrap back to RESERVED_PIDS
+			 */
+			if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS)
+				pid_min = RESERVED_PIDS;
+
+			/*
+			 * Store a null pointer so find_pid_ns does not find
+			 * a partially initialized PID (see below).
+			 */
+			nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
+					      pid_max, GFP_ATOMIC);
+		}
 		spin_unlock_irq(&pidmap_lock);
 		idr_preload_end();
 

kernel/pid_namespace.c

@@ -26,8 +26,6 @@
 
 static DEFINE_MUTEX(pid_caches_mutex);
 static struct kmem_cache *pid_ns_cachep;
-/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
-#define MAX_PID_NS_LEVEL 32
 /* Write once array, filled from the beginning. */
 static struct kmem_cache *pid_cache[MAX_PID_NS_LEVEL];