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

arch/arm/include/asm/unistd.h

@@ -37,6 +37,7 @@
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
 
 /*
  * Unimplemented (or alternatively implemented) syscalls

arch/arm/tools/syscall.tbl

@@ -448,3 +448,4 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
+435	common	clone3				sys_clone3

arch/arm64/include/asm/unistd.h

@@ -38,10 +38,11 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		435
+#define __NR_compat_syscalls		436
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
 
 #ifndef __COMPAT_SYSCALL_NR
 #include <uapi/asm/unistd.h>

arch/arm64/include/asm/unistd32.h

@@ -877,6 +877,8 @@ __SYSCALL(__NR_fsmount, sys_fsmount)
 __SYSCALL(__NR_fspick, sys_fspick)
 #define __NR_pidfd_open 434
 __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
+#define __NR_clone3 435
+__SYSCALL(__NR_clone3, sys_clone3)
 
 /*
  * Please add new compat syscalls above this comment and update

arch/microblaze/kernel/syscalls/syscall.tbl

@@ -440,3 +440,4 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
+435	common	clone3				sys_clone3

arch/x86/entry/syscalls/syscall_32.tbl

@@ -439,3 +439,4 @@
 432	i386	fsmount			sys_fsmount			__ia32_sys_fsmount
 433	i386	fspick			sys_fspick			__ia32_sys_fspick
 434	i386	pidfd_open		sys_pidfd_open			__ia32_sys_pidfd_open
+435	i386	clone3			sys_clone3			__ia32_sys_clone3

arch/x86/entry/syscalls/syscall_64.tbl

@@ -356,6 +356,7 @@
 432	common	fsmount			__x64_sys_fsmount
 433	common	fspick			__x64_sys_fspick
 434	common	pidfd_open		__x64_sys_pidfd_open
+435	common	clone3			__x64_sys_clone3/ptregs
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

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);
 }

arch/x86/include/asm/unistd.h

@@ -54,5 +54,6 @@
 # define __ARCH_WANT_SYS_FORK
 # define __ARCH_WANT_SYS_VFORK
 # define __ARCH_WANT_SYS_CLONE
+# define __ARCH_WANT_SYS_CLONE3
 
 #endif /* _ASM_X86_UNISTD_H */

arch/xtensa/include/asm/unistd.h

@@ -3,6 +3,7 @@
 #define _XTENSA_UNISTD_H
 
 #define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
 #include <uapi/asm/unistd.h>
 
 #define __ARCH_WANT_NEW_STAT

arch/xtensa/kernel/syscalls/syscall.tbl

@@ -405,3 +405,4 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
+435	common	clone3				sys_clone3

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);

include/linux/syscalls.h

@@ -68,6 +68,7 @@ struct sigaltstack;
 struct rseq;
 union bpf_attr;
 struct io_uring_params;
+struct clone_args;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -850,6 +851,9 @@ 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);

include/uapi/asm-generic/unistd.h

@@ -846,9 +846,11 @@ __SYSCALL(__NR_fsmount, sys_fsmount)
 __SYSCALL(__NR_fspick, sys_fspick)
 #define __NR_pidfd_open 434
 __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
+#define __NR_clone3 435
+__SYSCALL(__NR_clone3, sys_clone3)
 
 #undef __NR_syscalls
-#define __NR_syscalls 435
+#define __NR_syscalls 436
 
 /*
  * 32 bit systems traditionally used different

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:
  */
@@ -31,6 +33,20 @@
 #define CLONE_NEWNET		0x40000000	/* New network namespace */
 #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
  */