Merge tag 'threads-v5.5' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull thread management updates from Christian Brauner:

 - A pidfd's fdinfo file currently contains the field "Pid:\t<pid>"
   where <pid> is the pid of the process in the pid namespace of the
   procfs instance the fdinfo file for the pidfd was opened in.

   The fdinfo file has now gained a new "NSpid:\t<ns-pid1>[\t<ns-pid2>[...]]"
   field which lists the pids of the process in all child pid namespaces
   provided the pid namespace of the procfs instance it is looked up
   under has an ancestoral relationship with the pid namespace of the
   process. If it does not 0 will be shown and no further pid namespaces
   will be listed. Tests included. (Christian Kellner)

 - If the process the pidfd references has already exited, print -1 for
   the Pid and NSpid fields in the pidfd's fdinfo file. Tests included.
   (me)

 - Add CLONE_CLEAR_SIGHAND. This lets callers clear all signal handler
   that are not SIG_DFL or SIG_IGN at process creation time. This
   originated as a feature request from glibc to improve performance and
   elimate races in their posix_spawn() implementation. Tests included.
   (me)

 - Add support for choosing a specific pid for a process with clone3().
   This is the feature which was part of the thread update for v5.4 but
   after a discussion at LPC in Lisbon we decided to delay it for one
   more cycle in order to make the interface more generic. This has now
   done. It is now possible to choose a specific pid in a whole pid
   namespaces (sub)hierarchy instead of just one pid namespace. In order
   to choose a specific pid the caller must have CAP_SYS_ADMIN in all
   owning user namespaces of the target pid namespaces. Tests included.
   (Adrian Reber)

 - Test improvements and extensions. (Andrei Vagin, me)

* tag 'threads-v5.5' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  selftests/clone3: skip if clone3() is ENOSYS
  selftests/clone3: check that all pids are released on error paths
  selftests/clone3: report a correct number of fails
  selftests/clone3: flush stdout and stderr before clone3() and _exit()
  selftests: add tests for clone3() with *set_tid
  fork: extend clone3() to support setting a PID
  selftests: add tests for clone3()
  tests: test CLONE_CLEAR_SIGHAND
  clone3: add CLONE_CLEAR_SIGHAND
  pid: use pid_has_task() in pidfd_open()
  exit: use pid_has_task() in do_wait()
  pid: use pid_has_task() in __change_pid()
  test: verify fdinfo for pidfd of reaped process
  pidfd: check pid has attached task in fdinfo
  pidfd: add tests for NSpid info in fdinfo
  pidfd: add NSpid entries to fdinfo

Author: torvalds

MAINTAINERS

@@ -12861,6 +12861,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux.git
 F:	samples/pidfd/
 F:	tools/testing/selftests/pidfd/
+F:	tools/testing/selftests/clone3/
 K:	(?i)pidfd
 K:	(?i)clone3
 K:	\b(clone_args|kernel_clone_args)\b

include/linux/pid.h

@@ -85,6 +85,10 @@ static inline struct pid *get_pid(struct pid *pid)
 
 extern void put_pid(struct pid *pid);
 extern struct task_struct *pid_task(struct pid *pid, enum pid_type);
+static inline bool pid_has_task(struct pid *pid, enum pid_type type)
+{
+	return !hlist_empty(&pid->tasks[type]);
+}
 extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type);
 
 extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type);
@@ -120,7 +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

@@ -33,31 +33,48 @@
 #define CLONE_NEWNET		0x40000000	/* New network namespace */
 #define CLONE_IO		0x80000000	/* Clone io context */
 
+/* Flags for the clone3() syscall. */
+#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
+
 #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.
- *               Note, @stack is expected to point to the
- *               lowest address. The stack direction will be
- *               determined by the kernel and set up
- *               appropriately based on @stack_size.
- * @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.
+ *                Note, @stack is expected to point to the
+ *                lowest address. The stack direction will be
+ *                determined by the kernel and set up
+ *                appropriately based on @stack_size.
+ * @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
@@ -72,10 +89,13 @@ 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/exit.c

@@ -1457,7 +1457,7 @@ static long do_wait(struct wait_opts *wo)
 	 */
 	wo->notask_error = -ECHILD;
 	if ((wo->wo_type < PIDTYPE_MAX) &&
-	   (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type])))
+	   (!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type)))
 		goto notask;
 
 	set_current_state(TASK_INTERRUPTIBLE);

kernel/fork.c

@@ -1517,6 +1517,11 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
 	spin_lock_irq(&current->sighand->siglock);
 	memcpy(sig->action, current->sighand->action, sizeof(sig->action));
 	spin_unlock_irq(&current->sighand->siglock);
+
+	/* Reset all signal handler not set to SIG_IGN to SIG_DFL. */
+	if (clone_flags & CLONE_CLEAR_SIGHAND)
+		flush_signal_handlers(tsk, 0);
+
 	return 0;
 }
 
@@ -1695,12 +1700,68 @@ static int pidfd_release(struct inode *inode, struct file *file)
 }
 
 #ifdef CONFIG_PROC_FS
+/**
+ * pidfd_show_fdinfo - print information about a pidfd
+ * @m: proc fdinfo file
+ * @f: file referencing a pidfd
+ *
+ * Pid:
+ * This function will print the pid that a given pidfd refers to in the
+ * pid namespace of the procfs instance.
+ * If the pid namespace of the process is not a descendant of the pid
+ * namespace of the procfs instance 0 will be shown as its pid. This is
+ * similar to calling getppid() on a process whose parent is outside of
+ * its pid namespace.
+ *
+ * NSpid:
+ * If pid namespaces are supported then this function will also print
+ * the pid of a given pidfd refers to for all descendant pid namespaces
+ * starting from the current pid namespace of the instance, i.e. the
+ * Pid field and the first entry in the NSpid field will be identical.
+ * If the pid namespace of the process is not a descendant of the pid
+ * namespace of the procfs instance 0 will be shown as its first NSpid
+ * entry and no others will be shown.
+ * Note that this differs from the Pid and NSpid fields in
+ * /proc/<pid>/status where Pid and NSpid are always shown relative to
+ * the  pid namespace of the procfs instance. The difference becomes
+ * obvious when sending around a pidfd between pid namespaces from a
+ * different branch of the tree, i.e. where no ancestoral relation is
+ * present between the pid namespaces:
+ * - create two new pid namespaces ns1 and ns2 in the initial pid
+ *   namespace (also take care to create new mount namespaces in the
+ *   new pid namespace and mount procfs)
+ * - create a process with a pidfd in ns1
+ * - send pidfd from ns1 to ns2
+ * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid
+ *   have exactly one entry, which is 0
+ */
 static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
 {
-	struct pid_namespace *ns = proc_pid_ns(file_inode(m->file));
 	struct pid *pid = f->private_data;
+	struct pid_namespace *ns;
+	pid_t nr = -1;
+
+	if (likely(pid_has_task(pid, PIDTYPE_PID))) {
+		ns = proc_pid_ns(file_inode(m->file));
+		nr = pid_nr_ns(pid, ns);
+	}
+
+	seq_put_decimal_ll(m, "Pid:\t", nr);
+
+#ifdef CONFIG_PID_NS
+	seq_put_decimal_ll(m, "\nNSpid:\t", nr);
+	if (nr > 0) {
+		int i;
 
-	seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns));
+		/* If nr is non-zero it means that 'pid' is valid and that
+		 * ns, i.e. the pid namespace associated with the procfs
+		 * instance, is in the pid namespace hierarchy of pid.
+		 * Start at one below the already printed level.
+		 */
+		for (i = ns->level + 1; i <= pid->level; i++)
+			seq_put_decimal_ll(m, "\t", pid->numbers[i].nr);
+	}
+#endif
 	seq_putc(m, '\n');
 }
 #endif
@@ -2026,7 +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;
@@ -2529,6 +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;
@@ -2539,6 +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
@@ -2556,8 +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;
 }
 
@@ -2591,11 +2671,8 @@ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs)
 
 static bool clone3_args_valid(struct kernel_clone_args *kargs)
 {
-	/*
-	 * All lower bits of the flag word are taken.
-	 * Verify that no other unknown flags are passed along.
-	 */
-	if (kargs->flags & ~CLONE_LEGACY_FLAGS)
+	/* Verify that no unknown flags are passed along. */
+	if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND))
 		return false;
 
 	/*
@@ -2605,6 +2682,10 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs)
 	if (kargs->flags & (CLONE_DETACHED | CSIGNAL))
 		return false;
 
+	if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) ==
+	    (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND))
+		return false;
+
 	if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) &&
 	    kargs->exit_signal)
 		return false;
@@ -2631,6 +2712,9 @@ 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)