Merge tag 'clone3-v5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull clone3 system call from Christian Brauner:
 "This adds the clone3 syscall which is an extensible successor to clone
  after we snagged the last flag with CLONE_PIDFD during the 5.2 merge
  window for clone(). It cleanly supports all of the flags from clone()
  and thus all legacy workloads.

  There are few user visible differences between clone3 and clone.
  First, CLONE_DETACHED will cause EINVAL with clone3 so we can reuse
  this flag. Second, the CSIGNAL flag is deprecated and will cause
  EINVAL to be reported. It is superseeded by a dedicated "exit_signal"
  argument in struct clone_args thus freeing up even more flags. And
  third, clone3 gives CLONE_PIDFD a dedicated return argument in struct
  clone_args instead of abusing CLONE_PARENT_SETTID's parent_tidptr
  argument.

  The clone3 uapi is designed to be easy to handle on 32- and 64 bit:

    /* uapi */
    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;
    };

  and a separate kernel struct is used that uses proper kernel typing:

    /* kernel internal */
    struct kernel_clone_args {
            u64 flags;
            int __user *pidfd;
            int __user *child_tid;
            int __user *parent_tid;
            int exit_signal;
            unsigned long stack;
            unsigned long stack_size;
            unsigned long tls;
    };

  The system call comes with a size argument which enables the kernel to
  detect what version of clone_args userspace is passing in. clone3
  validates that any additional bytes a given kernel does not know about
  are set to zero and that the size never exceeds a page.

  A nice feature is that this patchset allowed us to cleanup and
  simplify various core kernel codepaths in kernel/fork.c by making the
  internal _do_fork() function take struct kernel_clone_args even for
  legacy clone().

  This patch also unblocks the time namespace patchset which wants to
  introduce a new CLONE_TIMENS flag.

  Note, that clone3 has only been wired up for x86{_32,64}, arm{64}, and
  xtensa. These were the architectures that did not require special
  massaging.

  Other architectures treat fork-like system calls individually and
  after some back and forth neither Arnd nor I felt confident that we
  dared to add clone3 unconditionally to all architectures. We agreed to
  leave this up to individual architecture maintainers. This is why
  there's an additional patch that introduces __ARCH_WANT_SYS_CLONE3
  which any architecture can set once it has implemented support for
  clone3. The patch also adds a cond_syscall(clone3) for architectures
  such as nios2 or h8300 that generate their syscall table by simply
  including asm-generic/unistd.h. The hope is to get rid of
  __ARCH_WANT_SYS_CLONE3 and cond_syscall() rather soon"

* tag 'clone3-v5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  arch: handle arches who do not yet define clone3
  arch: wire-up clone3() syscall
  fork: add clone3

1 files changed, 155 insertions, 36 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 187c02ce534c..8f3e2d97d771 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1768,20 +1768,16 @@ static __always_inline void delayed_free_task(struct task_struct *tsk)
  * flags). The actual kick-off is left to the caller.
  */
 static __latent_entropy struct task_struct *copy_process(
-                                        unsigned long clone_flags,
-                                        unsigned long stack_start,
-                                        unsigned long stack_size,
-                                        int __user *parent_tidptr,
-                                        int __user *child_tidptr,
                                         struct pid *pid,
                                         int trace,
-                                        unsigned long tls,
-                                        int node)
+                                        int node,
+                                        struct kernel_clone_args *args)
 {
         int pidfd = -1, retval;
         struct task_struct *p;
         struct multiprocess_signals delayed;
         struct file *pidfile = NULL;
+        u64 clone_flags = args->flags;
 
         /*
          * Don't allow sharing the root directory with processes in a different
@@ -1831,14 +1827,11 @@ static __latent_entropy struct task_struct *copy_process(
 
         if (clone_flags & CLONE_PIDFD) {
                 /*
-                 * - CLONE_PARENT_SETTID is useless for pidfds and also
-                 *   parent_tidptr is used to return pidfds.
                  * - CLONE_DETACHED is blocked so that we can potentially
                  *   reuse it later for CLONE_PIDFD.
                  * - CLONE_THREAD is blocked until someone really needs it.
                  */
-                if (clone_flags &
-                    (CLONE_DETACHED | CLONE_PARENT_SETTID | CLONE_THREAD))
+                if (clone_flags & (CLONE_DETACHED | CLONE_THREAD))
                         return ERR_PTR(-EINVAL);
         }
 
@@ -1871,11 +1864,11 @@ static __latent_entropy struct task_struct *copy_process(
          * p->set_child_tid which is (ab)used as a kthread's data pointer for
          * kernel threads (PF_KTHREAD).
          */
-        p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
+        p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL;
         /*
          * Clear TID on mm_release()?
          */
-        p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;
+        p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL;
 
         ftrace_graph_init_task(p);
 
@@ -2031,7 +2024,8 @@ static __latent_entropy struct task_struct *copy_process(
         retval = copy_io(clone_flags, p);
         if (retval)
                 goto bad_fork_cleanup_namespaces;
-        retval = copy_thread_tls(clone_flags, stack_start, stack_size, p, tls);
+        retval = copy_thread_tls(clone_flags, args->stack, args->stack_size, p,
+                                 args->tls);
         if (retval)
                 goto bad_fork_cleanup_io;
 
@@ -2066,7 +2060,7 @@ static __latent_entropy struct task_struct *copy_process(
                 }
                 get_pid(pid);   /* held by pidfile now */
 
-                retval = put_user(pidfd, parent_tidptr);
+                retval = put_user(pidfd, args->pidfd);
                 if (retval)
                         goto bad_fork_put_pidfd;
         }
@@ -2109,7 +2103,7 @@ static __latent_entropy struct task_struct *copy_process(
                 if (clone_flags & CLONE_PARENT)
                         p->exit_signal = current->group_leader->exit_signal;
                 else
-                        p->exit_signal = (clone_flags & CSIGNAL);
+                        p->exit_signal = args->exit_signal;
                 p->group_leader = p;
                 p->tgid = p->pid;
         }
@@ -2322,8 +2316,11 @@ static inline void init_idle_pids(struct task_struct *idle)
 struct task_struct *fork_idle(int cpu)
 {
         struct task_struct *task;
-        task = copy_process(CLONE_VM, 0, 0, NULL, NULL, &init_struct_pid, 0, 0,
-                            cpu_to_node(cpu));
+        struct kernel_clone_args args = {
+                .flags = CLONE_VM,
+        };
+
+        task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args);
         if (!IS_ERR(task)) {
                 init_idle_pids(task);
                 init_idle(task, cpu);
@@ -2343,13 +2340,9 @@ struct mm_struct *copy_init_mm(void)
  * It copies the process, and if successful kick-starts
  * it and waits for it to finish using the VM if required.
  */
-long _do_fork(unsigned long clone_flags,
-              unsigned long stack_start,
-              unsigned long stack_size,
-              int __user *parent_tidptr,
-              int __user *child_tidptr,
-              unsigned long tls)
+long _do_fork(struct kernel_clone_args *args)
 {
+        u64 clone_flags = args->flags;
         struct completion vfork;
         struct pid *pid;
         struct task_struct *p;
@@ -2365,7 +2358,7 @@ long _do_fork(unsigned long clone_flags,
         if (!(clone_flags & CLONE_UNTRACED)) {
                 if (clone_flags & CLONE_VFORK)
                         trace = PTRACE_EVENT_VFORK;
-                else if ((clone_flags & CSIGNAL) != SIGCHLD)
+                else if (args->exit_signal != SIGCHLD)
                         trace = PTRACE_EVENT_CLONE;
                 else
                         trace = PTRACE_EVENT_FORK;
@@ -2374,8 +2367,7 @@ long _do_fork(unsigned long clone_flags,
                         trace = 0;
         }
 
-        p = copy_process(clone_flags, stack_start, stack_size, parent_tidptr,
-                         child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
+        p = copy_process(NULL, trace, NUMA_NO_NODE, args);
         add_latent_entropy();
 
         if (IS_ERR(p))
@@ -2391,7 +2383,7 @@ long _do_fork(unsigned long clone_flags,
         nr = pid_vnr(pid);
 
         if (clone_flags & CLONE_PARENT_SETTID)
-                put_user(nr, parent_tidptr);
+                put_user(nr, args->parent_tid);
 
         if (clone_flags & CLONE_VFORK) {
                 p->vfork_done = &vfork;
@@ -2423,8 +2415,16 @@ long do_fork(unsigned long clone_flags,
               int __user *parent_tidptr,
               int __user *child_tidptr)
 {
-        return _do_fork(clone_flags, stack_start, stack_size,
-                        parent_tidptr, child_tidptr, 0);
+        struct kernel_clone_args args = {
+                .flags          = (clone_flags & ~CSIGNAL),
+                .child_tid      = child_tidptr,
+                .parent_tid     = parent_tidptr,
+                .exit_signal    = (clone_flags & CSIGNAL),
+                .stack          = stack_start,
+                .stack_size     = stack_size,
+        };
+
+        return _do_fork(&args);
 }
 #endif
 
@@ -2433,15 +2433,25 @@ long do_fork(unsigned long clone_flags,
  */
 pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 {
-        return _do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn,
-                (unsigned long)arg, NULL, NULL, 0);
+        struct kernel_clone_args args = {
+                .flags          = ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL),
+                .exit_signal    = (flags & CSIGNAL),
+                .stack          = (unsigned long)fn,
+                .stack_size     = (unsigned long)arg,
+        };
+
+        return _do_fork(&args);
 }
 
 #ifdef __ARCH_WANT_SYS_FORK
 SYSCALL_DEFINE0(fork)
 {
 #ifdef CONFIG_MMU
-        return _do_fork(SIGCHLD, 0, 0, NULL, NULL, 0);
+        struct kernel_clone_args args = {
+                .exit_signal = SIGCHLD,
+        };
+
+        return _do_fork(&args);
 #else
         /* can not support in nommu mode */
         return -EINVAL;
@@ -2452,8 +2462,12 @@ SYSCALL_DEFINE0(fork)
 #ifdef __ARCH_WANT_SYS_VFORK
 SYSCALL_DEFINE0(vfork)
 {
-        return _do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
-                        0, NULL, NULL, 0);
+        struct kernel_clone_args args = {
+                .flags          = CLONE_VFORK | CLONE_VM,
+                .exit_signal    = SIGCHLD,
+        };
+
+        return _do_fork(&args);
 }
 #endif
 
@@ -2481,7 +2495,112 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
                  unsigned long, tls)
 #endif
 {
-        return _do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr, tls);
+        struct kernel_clone_args args = {
+                .flags          = (clone_flags & ~CSIGNAL),
+                .pidfd          = parent_tidptr,
+                .child_tid      = child_tidptr,
+                .parent_tid     = parent_tidptr,
+                .exit_signal    = (clone_flags & CSIGNAL),
+                .stack          = newsp,
+                .tls            = tls,
+        };
+
+        /* clone(CLONE_PIDFD) uses parent_tidptr to return a pidfd */
+        if ((clone_flags & CLONE_PIDFD) && (clone_flags & CLONE_PARENT_SETTID))
+                return -EINVAL;
+
+        return _do_fork(&args);
+}
+#endif
+
+#ifdef __ARCH_WANT_SYS_CLONE3
+noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
+                                              struct clone_args __user *uargs,
+                                              size_t size)
+{
+        struct clone_args args;
+
+        if (unlikely(size > PAGE_SIZE))
+                return -E2BIG;
+
+        if (unlikely(size < sizeof(struct clone_args)))
+                return -EINVAL;
+
+        if (unlikely(!access_ok(uargs, size)))
+                return -EFAULT;
+
+        if (size > sizeof(struct clone_args)) {
+                unsigned char __user *addr;
+                unsigned char __user *end;
+                unsigned char val;
+
+                addr = (void __user *)uargs + sizeof(struct clone_args);
+                end = (void __user *)uargs + size;
+
+                for (; addr < end; addr++) {
+                        if (get_user(val, addr))
+                                return -EFAULT;
+                        if (val)
+                                return -E2BIG;
+                }
+
+                size = sizeof(struct clone_args);
+        }
+
+        if (copy_from_user(&args, uargs, size))
+                return -EFAULT;
+
+        *kargs = (struct kernel_clone_args){
+                .flags          = args.flags,
+                .pidfd          = u64_to_user_ptr(args.pidfd),
+                .child_tid      = u64_to_user_ptr(args.child_tid),
+                .parent_tid     = u64_to_user_ptr(args.parent_tid),
+                .exit_signal    = args.exit_signal,
+                .stack          = args.stack,
+                .stack_size     = args.stack_size,
+                .tls            = args.tls,
+        };
+
+        return 0;
+}
+
+static bool clone3_args_valid(const 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)
+                return false;
+
+        /*
+         * - make the CLONE_DETACHED bit reuseable for clone3
+         * - make the CSIGNAL bits reuseable for clone3
+         */
+        if (kargs->flags & (CLONE_DETACHED | CSIGNAL))
+                return false;
+
+        if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) &&
+            kargs->exit_signal)
+                return false;
+
+        return true;
+}
+
+SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
+{
+        int err;
+
+        struct kernel_clone_args kargs;
+
+        err = copy_clone_args_from_user(&kargs, uargs, size);
+        if (err)
+                return err;
+
+        if (!clone3_args_valid(&kargs))
+                return -EINVAL;
+
+        return _do_fork(&kargs);
 }
 #endif