diff --git a/include/linux/pid.h b/include/linux/pid.h
index 034e3cd60dc0680daf9720371440125cfb0bbf0b..998ae7d2445092aefc4d88f20c4e37db8380c5b2 100644
--- a/include/linux/pid.h
+++ b/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);
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 49538b172483c4f519100e1617f42d0f897bfbaa..2ed6af88794b0bf9adffdcf861cf9f0358305630 100644
--- a/include/linux/pid_namespace.h
+++ b/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;
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 4b1c3b664f517e5e35e6f581282e432649f734d7..f1879884238e95690e6010f81cac1a158ddb8af0 100644
--- a/include/linux/sched/task.h
+++ b/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;
};
/*
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 1d500ed03c63ee5ff442d9b989d7008e1131c63c..a0b1c224c72b556a86d8e7f92fdffca86c622e13 100644
--- a/include/uapi/linux/sched.h
+++ b/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
diff --git a/kernel/fork.c b/kernel/fork.c
index 954e875e72b10caca2a5c01673247e1ca7b8ef14..417570263f1fb80b50976121b751cf32b06873b3 100644
--- a/kernel/fork.c
+++ b/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)
diff --git a/kernel/pid.c b/kernel/pid.c
index 7b5f6c963d72ca7774d8a5c9d38725a4ed5942a2..2278e249141dbad205f598c5857e6ea83b159077 100644
--- a/kernel/pid.c
+++ b/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();
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index a6a79f85c81a8972d1c9c3674aea9aeff691f192..d40017e79ebe505174693bdeeb936f442ee66938 100644
--- a/kernel/pid_namespace.c
+++ b/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];