From: Linus Torvalds Date: Thu, 11 Jul 2019 17:09:44 +0000 (-0700) Subject: Merge tag 'clone3-v5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner... X-Git-Tag: v5.15~5992 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=8f6ccf6159aed1f04c6d179f61f6fb2691261e84;p=platform%2Fkernel%2Flinux-starfive.git Merge tag 'clone3-v5.3' of git://git./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 --- 8f6ccf6159aed1f04c6d179f61f6fb2691261e84 diff --cc arch/arm/tools/syscall.tbl index 81e6e18,e99a82b..6da7dc4 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@@ -447,4 -447,4 +447,5 @@@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick -436 common clone3 sys_clone3 +434 common pidfd_open sys_pidfd_open ++435 common clone3 sys_clone3 diff --cc arch/arm64/include/asm/unistd.h index ede7b88,e4e0523..2629a68 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@@ -38,7 -44,7 +38,7 @@@ #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 437 ++#define __NR_compat_syscalls 436 #endif #define __ARCH_WANT_SYS_CLONE diff --cc arch/arm64/include/asm/unistd32.h index 5241592,b144ea6..94ab29c --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@@ -875,8 -886,8 +875,10 @@@ __SYSCALL(__NR_fsconfig, sys_fsconfig __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) -#define __NR_clone3 436 +#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 diff --cc arch/microblaze/kernel/syscalls/syscall.tbl index ad706f8,3110440..09b0cd7 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@@ -439,4 -439,4 +439,5 @@@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick -436 common clone3 sys_clone3 +434 common pidfd_open sys_pidfd_open ++435 common clone3 sys_clone3 diff --cc arch/x86/entry/syscalls/syscall_32.tbl index 43e4429,80e2621..c00019a --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@@ -438,4 -438,4 +438,5 @@@ 431 i386 fsconfig sys_fsconfig __ia32_sys_fsconfig 432 i386 fsmount sys_fsmount __ia32_sys_fsmount 433 i386 fspick sys_fspick __ia32_sys_fspick -436 i386 clone3 sys_clone3 __ia32_sys_clone3 +434 i386 pidfd_open sys_pidfd_open __ia32_sys_pidfd_open ++435 i386 clone3 sys_clone3 __ia32_sys_clone3 diff --cc arch/x86/entry/syscalls/syscall_64.tbl index 1bee0a7,7968f0b..c29976e --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@@ -355,7 -355,7 +355,8 @@@ 431 common fsconfig __x64_sys_fsconfig 432 common fsmount __x64_sys_fsmount 433 common fspick __x64_sys_fspick -436 common clone3 __x64_sys_clone3/ptregs +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 diff --cc arch/xtensa/kernel/syscalls/syscall.tbl index 782b819,b2767c8..25f4de7 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@@ -404,4 -404,4 +404,5 @@@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick -436 common clone3 sys_clone3 +434 common pidfd_open sys_pidfd_open ++435 common clone3 sys_clone3 diff --cc include/uapi/asm-generic/unistd.h index e5684a4,45bc876..9acfff0 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@@ -844,11 -844,11 +844,13 @@@ __SYSCALL(__NR_fsconfig, sys_fsconfig __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) -#define __NR_clone3 436 +#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 437 ++#define __NR_syscalls 436 /* * 32 bit systems traditionally used different diff --cc kernel/fork.c index 187c02c,98abea9..8f3e2d9 --- a/kernel/fork.c +++ b/kernel/fork.c @@@ -1781,7 -1768,7 +1776,8 @@@ static __latent_entropy struct task_str 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 @@@ -2056,17 -2044,7 +2050,17 @@@ goto bad_fork_free_pid; pidfd = retval; + + pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, + O_RDWR | O_CLOEXEC); + if (IS_ERR(pidfile)) { + put_unused_fd(pidfd); + retval = PTR_ERR(pidfile); + goto bad_fork_free_pid; + } + 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; }