summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--MAINTAINERS1
-rw-r--r--include/linux/pid.h7
-rw-r--r--include/linux/pid_namespace.h2
-rw-r--r--include/linux/sched/task.h3
-rw-r--r--include/uapi/linux/sched.h64
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/fork.c100
-rw-r--r--kernel/pid.c86
-rw-r--r--kernel/pid_namespace.c2
-rw-r--r--tools/testing/selftests/Makefile1
-rw-r--r--tools/testing/selftests/clone3/.gitignore3
-rw-r--r--tools/testing/selftests/clone3/Makefile6
-rw-r--r--tools/testing/selftests/clone3/clone3.c202
-rw-r--r--tools/testing/selftests/clone3/clone3_clear_sighand.c129
-rw-r--r--tools/testing/selftests/clone3/clone3_selftests.h63
-rw-r--r--tools/testing/selftests/clone3/clone3_set_tid.c397
-rw-r--r--tools/testing/selftests/pidfd/Makefile2
-rw-r--r--tools/testing/selftests/pidfd/pidfd_fdinfo_test.c296
18 files changed, 1308 insertions, 58 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index a5689e2c1aa5..3e833d20d0f5 100644
--- a/MAINTAINERS
+++ b/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
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 9645b1194c98..998ae7d24450 100644
--- a/include/linux/pid.h
+++ 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);
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 49538b172483..2ed6af88794b 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 4b1c3b664f51..f1879884238e 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 25b4fa00bad1..4a0217832464 100644
--- a/include/uapi/linux/sched.h
+++ b/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
diff --git a/kernel/exit.c b/kernel/exit.c
index a46a50d67002..f2d20ab74422 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1457,7 +1457,7 @@ repeat:
*/
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);
diff --git a/kernel/fork.c b/kernel/fork.c
index 13b38794efb5..35f91ee91057 100644
--- a/kernel/fork.c
+++ b/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)
diff --git a/kernel/pid.c b/kernel/pid.c
index 0a9f2e437217..2278e249141d 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();
@@ -299,7 +341,7 @@ static void __change_pid(struct task_struct *task, enum pid_type type,
*pid_ptr = new;
for (tmp = PIDTYPE_MAX; --tmp >= 0; )
- if (!hlist_empty(&pid->tasks[tmp]))
+ if (pid_has_task(pid, tmp))
return;
free_pid(pid);
@@ -497,7 +539,7 @@ static int pidfd_create(struct pid *pid)
*/
SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
{
- int fd, ret;
+ int fd;
struct pid *p;
if (flags)
@@ -510,13 +552,11 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
if (!p)
return -ESRCH;
- ret = 0;
- rcu_read_lock();
- if (!pid_task(p, PIDTYPE_TGID))
- ret = -EINVAL;
- rcu_read_unlock();
+ if (pid_has_task(p, PIDTYPE_TGID))
+ fd = pidfd_create(p);
+ else
+ fd = -EINVAL;
- fd = ret ?: pidfd_create(p);
put_pid(p);
return fd;
}
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index a6a79f85c81a..d40017e79ebe 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];
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 0b6b81ba4421..0fb95f25944d 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -5,6 +5,7 @@ TARGETS += bpf
TARGETS += breakpoints
TARGETS += capabilities
TARGETS += cgroup
+TARGETS += clone3
TARGETS += cpufreq
TARGETS += cpu-hotplug
TARGETS += drivers/dma-buf
diff --git a/tools/testing/selftests/clone3/.gitignore b/tools/testing/selftests/clone3/.gitignore
new file mode 100644
index 000000000000..0dc4f32c6cb8
--- /dev/null
+++ b/tools/testing/selftests/clone3/.gitignore
@@ -0,0 +1,3 @@
+clone3
+clone3_clear_sighand
+clone3_set_tid
diff --git a/tools/testing/selftests/clone3/Makefile b/tools/testing/selftests/clone3/Makefile
new file mode 100644
index 000000000000..cf976c732906
--- /dev/null
+++ b/tools/testing/selftests/clone3/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -g -I../../../../usr/include/
+
+TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid
+
+include ../lib.mk
diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c
new file mode 100644
index 000000000000..f14c269a5a18
--- /dev/null
+++ b/tools/testing/selftests/clone3/clone3.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Based on Christian Brauner's clone3() example */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <inttypes.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <sched.h>
+
+#include "../kselftest.h"
+#include "clone3_selftests.h"
+
+/*
+ * Different sizes of struct clone_args
+ */
+#ifndef CLONE3_ARGS_SIZE_V0
+#define CLONE3_ARGS_SIZE_V0 64
+#endif
+
+enum test_mode {
+ CLONE3_ARGS_NO_TEST,
+ CLONE3_ARGS_ALL_0,
+ CLONE3_ARGS_INVAL_EXIT_SIGNAL_BIG,
+ CLONE3_ARGS_INVAL_EXIT_SIGNAL_NEG,
+ CLONE3_ARGS_INVAL_EXIT_SIGNAL_CSIG,
+ CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG,
+};
+
+static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode)
+{
+ struct clone_args args = {
+ .flags = flags,
+ .exit_signal = SIGCHLD,
+ };
+
+ struct clone_args_extended {
+ struct clone_args args;
+ __aligned_u64 excess_space[2];
+ } args_ext;
+
+ pid_t pid = -1;
+ int status;
+
+ memset(&args_ext, 0, sizeof(args_ext));
+ if (size > sizeof(struct clone_args))
+ args_ext.excess_space[1] = 1;
+
+ if (size == 0)
+ size = sizeof(struct clone_args);
+
+ switch (test_mode) {
+ case CLONE3_ARGS_ALL_0:
+ args.flags = 0;
+ args.exit_signal = 0;
+ break;
+ case CLONE3_ARGS_INVAL_EXIT_SIGNAL_BIG:
+ args.exit_signal = 0xbadc0ded00000000ULL;
+ break;
+ case CLONE3_ARGS_INVAL_EXIT_SIGNAL_NEG:
+ args.exit_signal = 0x0000000080000000ULL;
+ break;
+ case CLONE3_ARGS_INVAL_EXIT_SIGNAL_CSIG:
+ args.exit_signal = 0x0000000000000100ULL;
+ break;
+ case CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG:
+ args.exit_signal = 0x00000000000000f0ULL;
+ break;
+ }
+
+ memcpy(&args_ext.args, &args, sizeof(struct clone_args));
+
+ pid = sys_clone3((struct clone_args *)&args_ext, size);
+ if (pid < 0) {
+ ksft_print_msg("%s - Failed to create new process\n",
+ strerror(errno));
+ return -errno;
+ }
+
+ if (pid == 0) {
+ ksft_print_msg("I am the child, my PID is %d\n", getpid());
+ _exit(EXIT_SUCCESS);
+ }
+
+ ksft_print_msg("I am the parent (%d). My child's pid is %d\n",
+ getpid(), pid);
+
+ if (waitpid(-1, &status, __WALL) < 0) {
+ ksft_print_msg("Child returned %s\n", strerror(errno));
+ return -errno;
+ }
+ if (WEXITSTATUS(status))
+ return WEXITSTATUS(status);
+
+ return 0;
+}
+
+static void test_clone3(uint64_t flags, size_t size, int expected,
+ enum test_mode test_mode)
+{
+ int ret;
+
+ ksft_print_msg(
+ "[%d] Trying clone3() with flags %#" PRIx64 " (size %zu)\n",
+ getpid(), flags, size);
+ ret = call_clone3(flags, size, test_mode);
+ ksft_print_msg("[%d] clone3() with flags says: %d expected %d\n",
+ getpid(), ret, expected);
+ if (ret != expected)
+ ksft_test_result_fail(
+ "[%d] Result (%d) is different than expected (%d)\n",
+ getpid(), ret, expected);
+ else
+ ksft_test_result_pass(
+ "[%d] Result (%d) matches expectation (%d)\n",
+ getpid(), ret, expected);
+}
+
+int main(int argc, char *argv[])
+{
+ pid_t pid;
+
+ uid_t uid = getuid();
+
+ test_clone3_supported();
+ ksft_print_header();
+ ksft_set_plan(17);
+
+ /* Just a simple clone3() should return 0.*/
+ test_clone3(0, 0, 0, CLONE3_ARGS_NO_TEST);
+
+ /* Do a clone3() in a new PID NS.*/
+ if (uid == 0)
+ test_clone3(CLONE_NEWPID, 0, 0, CLONE3_ARGS_NO_TEST);
+ else
+ ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n");
+
+ /* Do a clone3() with CLONE3_ARGS_SIZE_V0. */
+ test_clone3(0, CLONE3_ARGS_SIZE_V0, 0, CLONE3_ARGS_NO_TEST);
+
+ /* Do a clone3() with CLONE3_ARGS_SIZE_V0 - 8 */
+ test_clone3(0, CLONE3_ARGS_SIZE_V0 - 8, -EINVAL, CLONE3_ARGS_NO_TEST);
+
+ /* Do a clone3() with sizeof(struct clone_args) + 8 */
+ test_clone3(0, sizeof(struct clone_args) + 8, 0, CLONE3_ARGS_NO_TEST);
+
+ /* Do a clone3() with exit_signal having highest 32 bits non-zero */
+ test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_BIG);
+
+ /* Do a clone3() with negative 32-bit exit_signal */
+ test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_NEG);
+
+ /* Do a clone3() with exit_signal not fitting into CSIGNAL mask */
+ test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_CSIG);
+
+ /* Do a clone3() with NSIG < exit_signal < CSIG */
+ test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG);
+
+ test_clone3(0, sizeof(struct clone_args) + 8, 0, CLONE3_ARGS_ALL_0);
+
+ test_clone3(0, sizeof(struct clone_args) + 16, -E2BIG,
+ CLONE3_ARGS_ALL_0);
+
+ test_clone3(0, sizeof(struct clone_args) * 2, -E2BIG,
+ CLONE3_ARGS_ALL_0);
+
+ /* Do a clone3() with > page size */
+ test_clone3(0, getpagesize() + 8, -E2BIG, CLONE3_ARGS_NO_TEST);
+
+ /* Do a clone3() with CLONE3_ARGS_SIZE_V0 in a new PID NS. */
+ if (uid == 0)
+ test_clone3(CLONE_NEWPID, CLONE3_ARGS_SIZE_V0, 0,
+ CLONE3_ARGS_NO_TEST);
+ else
+ ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n");
+
+ /* Do a clone3() with CLONE3_ARGS_SIZE_V0 - 8 in a new PID NS */
+ test_clone3(CLONE_NEWPID, CLONE3_ARGS_SIZE_V0 - 8, -EINVAL,
+ CLONE3_ARGS_NO_TEST);
+
+ /* Do a clone3() with sizeof(struct clone_args) + 8 in a new PID NS */
+ if (uid == 0)
+ test_clone3(CLONE_NEWPID, sizeof(struct clone_args) + 8, 0,
+ CLONE3_ARGS_NO_TEST);
+ else
+ ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n");
+
+ /* Do a clone3() with > page size in a new PID NS */
+ test_clone3(CLONE_NEWPID, getpagesize() + 8, -E2BIG,
+ CLONE3_ARGS_NO_TEST);
+
+ return !ksft_get_fail_cnt() ? ksft_exit_pass() : ksft_exit_fail();
+}
diff --git a/tools/testing/selftests/clone3/clone3_clear_sighand.c b/tools/testing/selftests/clone3/clone3_clear_sighand.c
new file mode 100644
index 000000000000..9e1af8aa7698
--- /dev/null
+++ b/tools/testing/selftests/clone3/clone3_clear_sighand.c
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+
+#include "../kselftest.h"
+#include "clone3_selftests.h"
+
+#ifndef CLONE_CLEAR_SIGHAND
+#define CLONE_CLEAR_SIGHAND 0x100000000ULL
+#endif
+
+static void nop_handler(int signo)
+{
+}
+
+static int wait_for_pid(pid_t pid)
+{
+ int status, ret;
+
+again:
+ ret = waitpid(pid, &status, 0);
+ if (ret == -1) {
+ if (errno == EINTR)
+ goto again;
+
+ return -1;
+ }
+
+ if (!WIFEXITED(status))
+ return -1;
+
+ return WEXITSTATUS(status);
+}
+
+static void test_clone3_clear_sighand(void)
+{
+ int ret;
+ pid_t pid;
+ struct clone_args args = {};
+ struct sigaction act;
+
+ /*
+ * Check that CLONE_CLEAR_SIGHAND and CLONE_SIGHAND are mutually
+ * exclusive.
+ */
+ args.flags |= CLONE_CLEAR_SIGHAND | CLONE_SIGHAND;
+ args.exit_signal = SIGCHLD;
+ pid = sys_clone3(&args, sizeof(args));
+ if (pid > 0)
+ ksft_exit_fail_msg(
+ "clone3(CLONE_CLEAR_SIGHAND | CLONE_SIGHAND) succeeded\n");
+
+ act.sa_handler = nop_handler;
+ ret = sigemptyset(&act.sa_mask);
+ if (ret < 0)
+ ksft_exit_fail_msg("%s - sigemptyset() failed\n",
+ strerror(errno));
+
+ act.sa_flags = 0;
+
+ /* Register signal handler for SIGUSR1 */
+ ret = sigaction(SIGUSR1, &act, NULL);
+ if (ret < 0)
+ ksft_exit_fail_msg(
+ "%s - sigaction(SIGUSR1, &act, NULL) failed\n",
+ strerror(errno));
+
+ /* Register signal handler for SIGUSR2 */
+ ret = sigaction(SIGUSR2, &act, NULL);
+ if (ret < 0)
+ ksft_exit_fail_msg(
+ "%s - sigaction(SIGUSR2, &act, NULL) failed\n",
+ strerror(errno));
+
+ /* Check that CLONE_CLEAR_SIGHAND works. */
+ args.flags = CLONE_CLEAR_SIGHAND;
+ pid = sys_clone3(&args, sizeof(args));
+ if (pid < 0)
+ ksft_exit_fail_msg("%s - clone3(CLONE_CLEAR_SIGHAND) failed\n",
+ strerror(errno));
+
+ if (pid == 0) {
+ ret = sigaction(SIGUSR1, NULL, &act);
+ if (ret < 0)
+ exit(EXIT_FAILURE);
+
+ if (act.sa_handler != SIG_DFL)
+ exit(EXIT_FAILURE);
+
+ ret = sigaction(SIGUSR2, NULL, &act);
+ if (ret < 0)
+ exit(EXIT_FAILURE);
+
+ if (act.sa_handler != SIG_DFL)
+ exit(EXIT_FAILURE);
+
+ exit(EXIT_SUCCESS);
+ }
+
+ ret = wait_for_pid(pid);
+ if (ret)
+ ksft_exit_fail_msg(
+ "Failed to clear signal handler for child process\n");
+
+ ksft_test_result_pass("Cleared signal handlers for child process\n");
+}
+
+int main(int argc, char **argv)
+{
+ ksft_print_header();
+ test_clone3_supported();
+
+ ksft_set_plan(1);
+
+ test_clone3_clear_sighand();
+
+ return ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h
new file mode 100644
index 000000000000..a3f2c8ad8bcc
--- /dev/null
+++ b/tools/testing/selftests/clone3/clone3_selftests.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _CLONE3_SELFTESTS_H
+#define _CLONE3_SELFTESTS_H
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdint.h>
+#include <syscall.h>
+#include <linux/types.h>
+
+#define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr)))
+
+#ifndef __NR_clone3
+#define __NR_clone3 -1
+struct clone_args {
+ __aligned_u64 flags;
+ __aligned_u64 pidfd;
+ __aligned_u64 child_tid;
+ __aligned_u64 parent_tid;
+ __aligned_u64 exit_signal;
+ __aligned_u64 stack;
+ __aligned_u64 stack_size;
+ __aligned_u64 tls;
+ __aligned_u64 set_tid;
+ __aligned_u64 set_tid_size;
+};
+#endif
+
+static pid_t sys_clone3(struct clone_args *args, size_t size)
+{
+ fflush(stdout);
+ fflush(stderr);
+ return syscall(__NR_clone3, args, size);
+}
+
+static inline void test_clone3_supported(void)
+{
+ pid_t pid;
+ struct clone_args args = {};
+
+ if (__NR_clone3 < 0)
+ ksft_exit_skip("clone3() syscall is not supported\n");
+
+ /* Set to something that will always cause EINVAL. */
+ args.exit_signal = -1;
+ pid = sys_clone3(&args, sizeof(args));
+ if (!pid)
+ exit(EXIT_SUCCESS);
+
+ if (pid > 0) {
+ wait(NULL);
+ ksft_exit_fail_msg(
+ "Managed to create child process with invalid exit_signal\n");
+ }
+
+ if (errno == ENOSYS)
+ ksft_exit_skip("clone3() syscall is not supported\n");
+
+ ksft_print_msg("clone3() syscall supported\n");
+}
+
+#endif /* _CLONE3_SELFTESTS_H */
diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c
new file mode 100644
index 000000000000..25beb22f35b5
--- /dev/null
+++ b/tools/testing/selftests/clone3/clone3_set_tid.c
@@ -0,0 +1,397 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Based on Christian Brauner's clone3() example.
+ * These tests are assuming to be running in the host's
+ * PID namespace.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <sched.h>
+
+#include "../kselftest.h"
+#include "clone3_selftests.h"
+
+#ifndef MAX_PID_NS_LEVEL
+#define MAX_PID_NS_LEVEL 32
+#endif
+
+static int pipe_1[2];
+static int pipe_2[2];
+
+static void child_exit(int ret)
+{
+ fflush(stdout);
+ fflush(stderr);
+ _exit(ret);
+}
+
+static int call_clone3_set_tid(pid_t *set_tid,
+ size_t set_tid_size,
+ int flags,
+ int expected_pid,
+ bool wait_for_it)
+{
+ int status;
+ pid_t pid = -1;
+
+ struct clone_args args = {
+ .flags = flags,
+ .exit_signal = SIGCHLD,
+ .set_tid = ptr_to_u6