summaryrefslogtreecommitdiff
path: root/include/linux/sched
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-07-11 10:09:44 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-07-11 10:09:44 -0700
commit8f6ccf6159aed1f04c6d179f61f6fb2691261e84 (patch)
tree449c6d9cddc6f94c6450a18885b6a06e8a67d845 /include/linux/sched
parent5450e8a316a64cddcbc15f90733ebc78aa736545 (diff)
parentd68dbb0c9ac8b1ff52eb09aa58ce6358400fa939 (diff)
downloadlinux-next-8f6ccf6159aed1f04c6d179f61f6fb2691261e84.tar.gz
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
Diffstat (limited to 'include/linux/sched')
-rw-r--r--include/linux/sched/task.h17
1 files changed, 16 insertions, 1 deletions
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);