5 files changed, 199 insertions, 51 deletions

diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index a43212036257..64a6c952091e 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -237,6 +237,14 @@ COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags,
 		       unsigned long, newsp, int __user *, parent_tidptr,
 		       unsigned long, tls_val, int __user *, child_tidptr)
 {
-	return _do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr,
-			tls_val);
+	struct kernel_clone_args args = {
+		.flags		= (clone_flags & ~CSIGNAL),
+		.child_tid	= child_tidptr,
+		.parent_tid	= parent_tidptr,
+		.exit_signal	= (clone_flags & CSIGNAL),
+		.stack		= newsp,
+		.tls		= tls_val,
+	};
+
+	return _do_fork(&args);
 }
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index f1227f2c38a4..109a0df5af39 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -8,11 +8,26 @@
  */
 
 #include <linux/sched.h>
+#include <linux/uaccess.h>
 
 struct task_struct;
 struct rusage;
 union thread_union;
 
+/* All the bits taken by the old clone syscall. */
+#define CLONE_LEGACY_FLAGS 0xffffffffULL
+
+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;
+};
+
 /*
  * This serializes "schedule()" and also protects
  * the run-queue from deletions/modifications (but
@@ -73,7 +88,7 @@ extern void do_group_exit(int);
 extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
-extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
+extern long _do_fork(struct kernel_clone_args *kargs);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index e2870fe1be5b..60a81f374ca3 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -70,6 +70,7 @@ struct sigaltstack;
 struct rseq;
 union bpf_attr;
 struct io_uring_params;
+struct clone_args;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -852,6 +853,9 @@ asmlinkage long sys_clone(unsigned long, unsigned long, int __user *,
 	       int __user *, unsigned long);
 #endif
 #endif
+
+asmlinkage long sys_clone3(struct clone_args __user *uargs, size_t size);
+
 asmlinkage long sys_execve(const char __user *filename,
 		const char __user *const __user *argv,
 		const char __user *const __user *envp);
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index ed4ee170bee2..f5331dbdcaa2 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -2,6 +2,8 @@
 #ifndef _UAPI_LINUX_SCHED_H
 #define _UAPI_LINUX_SCHED_H
 
+#include <linux/types.h>
+
 /*
  * cloning flags:
  */
@@ -32,6 +34,20 @@
 #define CLONE_IO		0x80000000	/* Clone io context */
 
 /*
+ * Arguments for the clone3 syscall
+ */
+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;
+};
+
+/*
  * Scheduling policies
  */
 #define SCHED_NORMAL		0
diff --git a/kernel/fork.c b/kernel/fork.c
index b4cba953040a..08ff131f26b4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1760,19 +1760,15 @@ 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;
+	u64 clone_flags = args->flags;
 
 	/*
 	 * Don't allow sharing the root directory with processes in a different
@@ -1821,27 +1817,12 @@ static __latent_entropy struct task_struct *copy_process(
 	}
 
 	if (clone_flags & CLONE_PIDFD) {
-		int reserved;
-
 		/*
-		 * - 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))
-			return ERR_PTR(-EINVAL);
-
-		/*
-		 * Verify that parent_tidptr is sane so we can potentially
-		 * reuse it later.
-		 */
-		if (get_user(reserved, parent_tidptr))
-			return ERR_PTR(-EFAULT);
-
-		if (reserved != 0)
+		if (clone_flags & (CLONE_DETACHED | CLONE_THREAD))
 			return ERR_PTR(-EINVAL);
 	}
 
@@ -1874,11 +1855,11 @@ 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);
 
@@ -2037,7 +2018,8 @@ 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;
 
@@ -2062,7 +2044,7 @@ static __latent_entropy struct task_struct *copy_process(
 			goto bad_fork_free_pid;
 
 		pidfd = retval;
-		retval = put_user(pidfd, parent_tidptr);
+		retval = put_user(pidfd, args->pidfd);
 		if (retval)
 			goto bad_fork_put_pidfd;
 	}
@@ -2105,7 +2087,7 @@ 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;
 	}
@@ -2313,8 +2295,11 @@ 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);
@@ -2334,13 +2319,9 @@ 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;
@@ -2356,7 +2337,7 @@ 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;
@@ -2365,8 +2346,7 @@ 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))
@@ -2382,7 +2362,7 @@ 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;
@@ -2414,8 +2394,16 @@ 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
 
@@ -2424,15 +2412,25 @@ 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;
@@ -2443,8 +2441,12 @@ 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
 
@@ -2472,7 +2474,110 @@ 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);
+}
+
+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