linux_dsm_epyc7002/include/uapi/asm-generic/unistd.h

798 lines
26 KiB
C
Raw Normal View History

License cleanup: add SPDX license identifier to uapi header files with no license Many user space API headers are missing licensing information, which makes it hard for compliance tools to determine the correct license. By default are files without license information under the default license of the kernel, which is GPLV2. Marking them GPLV2 would exclude them from being included in non GPLV2 code, which is obviously not intended. The user space API headers fall under the syscall exception which is in the kernels COPYING file: NOTE! This copyright does *not* cover user programs that use kernel services by normal system calls - this is merely considered normal use of the kernel, and does *not* fall under the heading of "derived work". otherwise syscall usage would not be possible. Update the files which contain no license information with an SPDX license identifier. The chosen identifier is 'GPL-2.0 WITH Linux-syscall-note' which is the officially assigned identifier for the Linux syscall exception. SPDX license identifiers are a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. See the previous patch in this series for the methodology of how this patch was researched. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 21:08:43 +07:00
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#include <asm/bitsperlong.h>
/*
* This file contains the system call numbers, based on the
* layout of the x86-64 architecture, which embeds the
* pointer to the syscall in the table.
*
* As a basic principle, no duplication of functionality
* should be added, e.g. we don't use lseek when llseek
* is present. New architectures should use this file
* and implement the less feature-full calls in user space.
*/
#ifndef __SYSCALL
#define __SYSCALL(x, y)
#endif
#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT)
#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32)
#else
#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64)
#endif
#ifdef __SYSCALL_COMPAT
#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp)
#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp)
#else
#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys)
#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64)
#endif
#define __NR_io_setup 0
__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup)
#define __NR_io_destroy 1
__SYSCALL(__NR_io_destroy, sys_io_destroy)
#define __NR_io_submit 2
__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
#define __NR_io_cancel 3
__SYSCALL(__NR_io_cancel, sys_io_cancel)
#define __NR_io_getevents 4
__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)
/* fs/xattr.c */
#define __NR_setxattr 5
__SYSCALL(__NR_setxattr, sys_setxattr)
#define __NR_lsetxattr 6
__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
#define __NR_fsetxattr 7
__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
#define __NR_getxattr 8
__SYSCALL(__NR_getxattr, sys_getxattr)
#define __NR_lgetxattr 9
__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
#define __NR_fgetxattr 10
__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
#define __NR_listxattr 11
__SYSCALL(__NR_listxattr, sys_listxattr)
#define __NR_llistxattr 12
__SYSCALL(__NR_llistxattr, sys_llistxattr)
#define __NR_flistxattr 13
__SYSCALL(__NR_flistxattr, sys_flistxattr)
#define __NR_removexattr 14
__SYSCALL(__NR_removexattr, sys_removexattr)
#define __NR_lremovexattr 15
__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
#define __NR_fremovexattr 16
__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
/* fs/dcache.c */
#define __NR_getcwd 17
__SYSCALL(__NR_getcwd, sys_getcwd)
/* fs/cookies.c */
#define __NR_lookup_dcookie 18
__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie)
/* fs/eventfd.c */
#define __NR_eventfd2 19
__SYSCALL(__NR_eventfd2, sys_eventfd2)
/* fs/eventpoll.c */
#define __NR_epoll_create1 20
__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
#define __NR_epoll_ctl 21
__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
#define __NR_epoll_pwait 22
__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait)
/* fs/fcntl.c */
#define __NR_dup 23
__SYSCALL(__NR_dup, sys_dup)
#define __NR_dup3 24
__SYSCALL(__NR_dup3, sys_dup3)
#define __NR3264_fcntl 25
__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64)
/* fs/inotify_user.c */
#define __NR_inotify_init1 26
__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
#define __NR_inotify_add_watch 27
__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
#define __NR_inotify_rm_watch 28
__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
/* fs/ioctl.c */
#define __NR_ioctl 29
__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl)
/* fs/ioprio.c */
#define __NR_ioprio_set 30
__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
#define __NR_ioprio_get 31
__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
/* fs/locks.c */
#define __NR_flock 32
__SYSCALL(__NR_flock, sys_flock)
/* fs/namei.c */
#define __NR_mknodat 33
__SYSCALL(__NR_mknodat, sys_mknodat)
#define __NR_mkdirat 34
__SYSCALL(__NR_mkdirat, sys_mkdirat)
#define __NR_unlinkat 35
__SYSCALL(__NR_unlinkat, sys_unlinkat)
#define __NR_symlinkat 36
__SYSCALL(__NR_symlinkat, sys_symlinkat)
#define __NR_linkat 37
__SYSCALL(__NR_linkat, sys_linkat)
#ifdef __ARCH_WANT_RENAMEAT
/* renameat is superseded with flags by renameat2 */
#define __NR_renameat 38
__SYSCALL(__NR_renameat, sys_renameat)
#endif /* __ARCH_WANT_RENAMEAT */
/* fs/namespace.c */
#define __NR_umount2 39
__SYSCALL(__NR_umount2, sys_umount)
#define __NR_mount 40
__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
#define __NR_pivot_root 41
__SYSCALL(__NR_pivot_root, sys_pivot_root)
/* fs/nfsctl.c */
#define __NR_nfsservctl 42
__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
/* fs/open.c */
#define __NR3264_statfs 43
__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \
compat_sys_statfs64)
#define __NR3264_fstatfs 44
__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \
compat_sys_fstatfs64)
#define __NR3264_truncate 45
__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \
compat_sys_truncate64)
#define __NR3264_ftruncate 46
__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \
compat_sys_ftruncate64)
#define __NR_fallocate 47
__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate)
#define __NR_faccessat 48
__SYSCALL(__NR_faccessat, sys_faccessat)
#define __NR_chdir 49
__SYSCALL(__NR_chdir, sys_chdir)
#define __NR_fchdir 50
__SYSCALL(__NR_fchdir, sys_fchdir)
#define __NR_chroot 51
__SYSCALL(__NR_chroot, sys_chroot)
#define __NR_fchmod 52
__SYSCALL(__NR_fchmod, sys_fchmod)
#define __NR_fchmodat 53
__SYSCALL(__NR_fchmodat, sys_fchmodat)
#define __NR_fchownat 54
__SYSCALL(__NR_fchownat, sys_fchownat)
#define __NR_fchown 55
__SYSCALL(__NR_fchown, sys_fchown)
#define __NR_openat 56
__SC_COMP(__NR_openat, sys_openat, compat_sys_openat)
#define __NR_close 57
__SYSCALL(__NR_close, sys_close)
#define __NR_vhangup 58
__SYSCALL(__NR_vhangup, sys_vhangup)
/* fs/pipe.c */
#define __NR_pipe2 59
__SYSCALL(__NR_pipe2, sys_pipe2)
/* fs/quota.c */
#define __NR_quotactl 60
__SYSCALL(__NR_quotactl, sys_quotactl)
/* fs/readdir.c */
#define __NR_getdents64 61
__SYSCALL(__NR_getdents64, sys_getdents64)
/* fs/read_write.c */
#define __NR3264_lseek 62
__SC_3264(__NR3264_lseek, sys_llseek, sys_lseek)
#define __NR_read 63
__SYSCALL(__NR_read, sys_read)
#define __NR_write 64
__SYSCALL(__NR_write, sys_write)
#define __NR_readv 65
__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
#define __NR_writev 66
__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
#define __NR_pread64 67
__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
#define __NR_pwrite64 68
__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64)
#define __NR_preadv 69
__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv)
#define __NR_pwritev 70
__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
/* fs/sendfile.c */
#define __NR3264_sendfile 71
__SYSCALL(__NR3264_sendfile, sys_sendfile64)
/* fs/select.c */
#define __NR_pselect6 72
__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6)
#define __NR_ppoll 73
__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll)
/* fs/signalfd.c */
#define __NR_signalfd4 74
__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
/* fs/splice.c */
#define __NR_vmsplice 75
__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
#define __NR_splice 76
__SYSCALL(__NR_splice, sys_splice)
#define __NR_tee 77
__SYSCALL(__NR_tee, sys_tee)
/* fs/stat.c */
#define __NR_readlinkat 78
__SYSCALL(__NR_readlinkat, sys_readlinkat)
#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64)
#define __NR3264_fstatat 79
__SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat)
#define __NR3264_fstat 80
__SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat)
#endif
/* fs/sync.c */
#define __NR_sync 81
__SYSCALL(__NR_sync, sys_sync)
#define __NR_fsync 82
__SYSCALL(__NR_fsync, sys_fsync)
#define __NR_fdatasync 83
__SYSCALL(__NR_fdatasync, sys_fdatasync)
#ifdef __ARCH_WANT_SYNC_FILE_RANGE2
#define __NR_sync_file_range2 84
__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \
compat_sys_sync_file_range2)
#else
#define __NR_sync_file_range 84
__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
compat_sys_sync_file_range)
#endif
/* fs/timerfd.c */
#define __NR_timerfd_create 85
__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
#define __NR_timerfd_settime 86
__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \
compat_sys_timerfd_settime)
#define __NR_timerfd_gettime 87
__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \
compat_sys_timerfd_gettime)
/* fs/utimes.c */
#define __NR_utimensat 88
__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat)
/* kernel/acct.c */
#define __NR_acct 89
__SYSCALL(__NR_acct, sys_acct)
/* kernel/capability.c */
#define __NR_capget 90
__SYSCALL(__NR_capget, sys_capget)
#define __NR_capset 91
__SYSCALL(__NR_capset, sys_capset)
/* kernel/exec_domain.c */
#define __NR_personality 92
__SYSCALL(__NR_personality, sys_personality)
/* kernel/exit.c */
#define __NR_exit 93
__SYSCALL(__NR_exit, sys_exit)
#define __NR_exit_group 94
__SYSCALL(__NR_exit_group, sys_exit_group)
#define __NR_waitid 95
__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid)
/* kernel/fork.c */
#define __NR_set_tid_address 96
__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
#define __NR_unshare 97
__SYSCALL(__NR_unshare, sys_unshare)
/* kernel/futex.c */
#define __NR_futex 98
__SC_COMP(__NR_futex, sys_futex, compat_sys_futex)
#define __NR_set_robust_list 99
__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
compat_sys_set_robust_list)
#define __NR_get_robust_list 100
__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
compat_sys_get_robust_list)
/* kernel/hrtimer.c */
#define __NR_nanosleep 101
__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep)
/* kernel/itimer.c */
#define __NR_getitimer 102
__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer)
#define __NR_setitimer 103
__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer)
/* kernel/kexec.c */
#define __NR_kexec_load 104
__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load)
/* kernel/module.c */
#define __NR_init_module 105
__SYSCALL(__NR_init_module, sys_init_module)
#define __NR_delete_module 106
__SYSCALL(__NR_delete_module, sys_delete_module)
/* kernel/posix-timers.c */
#define __NR_timer_create 107
__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
#define __NR_timer_gettime 108
__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime)
#define __NR_timer_getoverrun 109
__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
#define __NR_timer_settime 110
__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime)
#define __NR_timer_delete 111
__SYSCALL(__NR_timer_delete, sys_timer_delete)
#define __NR_clock_settime 112
__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime)
#define __NR_clock_gettime 113
__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime)
#define __NR_clock_getres 114
__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres)
#define __NR_clock_nanosleep 115
__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \
compat_sys_clock_nanosleep)
/* kernel/printk.c */
#define __NR_syslog 116
__SYSCALL(__NR_syslog, sys_syslog)
/* kernel/ptrace.c */
#define __NR_ptrace 117
__SYSCALL(__NR_ptrace, sys_ptrace)
/* kernel/sched/core.c */
#define __NR_sched_setparam 118
__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
#define __NR_sched_setscheduler 119
__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
#define __NR_sched_getscheduler 120
__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
#define __NR_sched_getparam 121
__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
#define __NR_sched_setaffinity 122
__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \
compat_sys_sched_setaffinity)
#define __NR_sched_getaffinity 123
__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \
compat_sys_sched_getaffinity)
#define __NR_sched_yield 124
__SYSCALL(__NR_sched_yield, sys_sched_yield)
#define __NR_sched_get_priority_max 125
__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
#define __NR_sched_get_priority_min 126
__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
#define __NR_sched_rr_get_interval 127
__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \
compat_sys_sched_rr_get_interval)
/* kernel/signal.c */
#define __NR_restart_syscall 128
__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
#define __NR_kill 129
__SYSCALL(__NR_kill, sys_kill)
#define __NR_tkill 130
__SYSCALL(__NR_tkill, sys_tkill)
#define __NR_tgkill 131
__SYSCALL(__NR_tgkill, sys_tgkill)
#define __NR_sigaltstack 132
__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack)
#define __NR_rt_sigsuspend 133
__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend)
#define __NR_rt_sigaction 134
__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
#define __NR_rt_sigprocmask 135
__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask)
#define __NR_rt_sigpending 136
__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending)
#define __NR_rt_sigtimedwait 137
__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \
compat_sys_rt_sigtimedwait)
#define __NR_rt_sigqueueinfo 138
__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
compat_sys_rt_sigqueueinfo)
#define __NR_rt_sigreturn 139
__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn)
/* kernel/sys.c */
#define __NR_setpriority 140
__SYSCALL(__NR_setpriority, sys_setpriority)
#define __NR_getpriority 141
__SYSCALL(__NR_getpriority, sys_getpriority)
#define __NR_reboot 142
__SYSCALL(__NR_reboot, sys_reboot)
#define __NR_setregid 143
__SYSCALL(__NR_setregid, sys_setregid)
#define __NR_setgid 144
__SYSCALL(__NR_setgid, sys_setgid)
#define __NR_setreuid 145
__SYSCALL(__NR_setreuid, sys_setreuid)
#define __NR_setuid 146
__SYSCALL(__NR_setuid, sys_setuid)
#define __NR_setresuid 147
__SYSCALL(__NR_setresuid, sys_setresuid)
#define __NR_getresuid 148
__SYSCALL(__NR_getresuid, sys_getresuid)
#define __NR_setresgid 149
__SYSCALL(__NR_setresgid, sys_setresgid)
#define __NR_getresgid 150
__SYSCALL(__NR_getresgid, sys_getresgid)
#define __NR_setfsuid 151
__SYSCALL(__NR_setfsuid, sys_setfsuid)
#define __NR_setfsgid 152
__SYSCALL(__NR_setfsgid, sys_setfsgid)
#define __NR_times 153
__SC_COMP(__NR_times, sys_times, compat_sys_times)
#define __NR_setpgid 154
__SYSCALL(__NR_setpgid, sys_setpgid)
#define __NR_getpgid 155
__SYSCALL(__NR_getpgid, sys_getpgid)
#define __NR_getsid 156
__SYSCALL(__NR_getsid, sys_getsid)
#define __NR_setsid 157
__SYSCALL(__NR_setsid, sys_setsid)
#define __NR_getgroups 158
__SYSCALL(__NR_getgroups, sys_getgroups)
#define __NR_setgroups 159
__SYSCALL(__NR_setgroups, sys_setgroups)
#define __NR_uname 160
__SYSCALL(__NR_uname, sys_newuname)
#define __NR_sethostname 161
__SYSCALL(__NR_sethostname, sys_sethostname)
#define __NR_setdomainname 162
__SYSCALL(__NR_setdomainname, sys_setdomainname)
#define __NR_getrlimit 163
__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
#define __NR_setrlimit 164
__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
#define __NR_getrusage 165
__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
#define __NR_umask 166
__SYSCALL(__NR_umask, sys_umask)
#define __NR_prctl 167
__SYSCALL(__NR_prctl, sys_prctl)
#define __NR_getcpu 168
__SYSCALL(__NR_getcpu, sys_getcpu)
/* kernel/time.c */
#define __NR_gettimeofday 169
__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
#define __NR_settimeofday 170
__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
#define __NR_adjtimex 171
__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex)
/* kernel/timer.c */
#define __NR_getpid 172
__SYSCALL(__NR_getpid, sys_getpid)
#define __NR_getppid 173
__SYSCALL(__NR_getppid, sys_getppid)
#define __NR_getuid 174
__SYSCALL(__NR_getuid, sys_getuid)
#define __NR_geteuid 175
__SYSCALL(__NR_geteuid, sys_geteuid)
#define __NR_getgid 176
__SYSCALL(__NR_getgid, sys_getgid)
#define __NR_getegid 177
__SYSCALL(__NR_getegid, sys_getegid)
#define __NR_gettid 178
__SYSCALL(__NR_gettid, sys_gettid)
#define __NR_sysinfo 179
__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
/* ipc/mqueue.c */
#define __NR_mq_open 180
__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
#define __NR_mq_unlink 181
__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
#define __NR_mq_timedsend 182
__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend)
#define __NR_mq_timedreceive 183
__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \
compat_sys_mq_timedreceive)
#define __NR_mq_notify 184
__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
#define __NR_mq_getsetattr 185
__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr)
/* ipc/msg.c */
#define __NR_msgget 186
__SYSCALL(__NR_msgget, sys_msgget)
#define __NR_msgctl 187
__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl)
#define __NR_msgrcv 188
__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv)
#define __NR_msgsnd 189
__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
/* ipc/sem.c */
#define __NR_semget 190
__SYSCALL(__NR_semget, sys_semget)
#define __NR_semctl 191
__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
#define __NR_semtimedop 192
__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop)
#define __NR_semop 193
__SYSCALL(__NR_semop, sys_semop)
/* ipc/shm.c */
#define __NR_shmget 194
__SYSCALL(__NR_shmget, sys_shmget)
#define __NR_shmctl 195
__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl)
#define __NR_shmat 196
__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat)
#define __NR_shmdt 197
__SYSCALL(__NR_shmdt, sys_shmdt)
/* net/socket.c */
#define __NR_socket 198
__SYSCALL(__NR_socket, sys_socket)
#define __NR_socketpair 199
__SYSCALL(__NR_socketpair, sys_socketpair)
#define __NR_bind 200
__SYSCALL(__NR_bind, sys_bind)
#define __NR_listen 201
__SYSCALL(__NR_listen, sys_listen)
#define __NR_accept 202
__SYSCALL(__NR_accept, sys_accept)
#define __NR_connect 203
__SYSCALL(__NR_connect, sys_connect)
#define __NR_getsockname 204
__SYSCALL(__NR_getsockname, sys_getsockname)
#define __NR_getpeername 205
__SYSCALL(__NR_getpeername, sys_getpeername)
#define __NR_sendto 206
__SYSCALL(__NR_sendto, sys_sendto)
#define __NR_recvfrom 207
__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)
#define __NR_setsockopt 208
__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt)
#define __NR_getsockopt 209
__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt)
#define __NR_shutdown 210
__SYSCALL(__NR_shutdown, sys_shutdown)
#define __NR_sendmsg 211
__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg)
#define __NR_recvmsg 212
__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg)
/* mm/filemap.c */
#define __NR_readahead 213
__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead)
/* mm/nommu.c, also with MMU */
#define __NR_brk 214
__SYSCALL(__NR_brk, sys_brk)
#define __NR_munmap 215
__SYSCALL(__NR_munmap, sys_munmap)
#define __NR_mremap 216
__SYSCALL(__NR_mremap, sys_mremap)
/* security/keys/keyctl.c */
#define __NR_add_key 217
__SYSCALL(__NR_add_key, sys_add_key)
#define __NR_request_key 218
__SYSCALL(__NR_request_key, sys_request_key)
#define __NR_keyctl 219
__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl)
/* arch/example/kernel/sys_example.c */
#define __NR_clone 220
__SYSCALL(__NR_clone, sys_clone)
#define __NR_execve 221
__SC_COMP(__NR_execve, sys_execve, compat_sys_execve)
#define __NR3264_mmap 222
__SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap)
/* mm/fadvise.c */
#define __NR3264_fadvise64 223
__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64)
/* mm/, CONFIG_MMU only */
#ifndef __ARCH_NOMMU
#define __NR_swapon 224
__SYSCALL(__NR_swapon, sys_swapon)
#define __NR_swapoff 225
__SYSCALL(__NR_swapoff, sys_swapoff)
#define __NR_mprotect 226
__SYSCALL(__NR_mprotect, sys_mprotect)
#define __NR_msync 227
__SYSCALL(__NR_msync, sys_msync)
#define __NR_mlock 228
__SYSCALL(__NR_mlock, sys_mlock)
#define __NR_munlock 229
__SYSCALL(__NR_munlock, sys_munlock)
#define __NR_mlockall 230
__SYSCALL(__NR_mlockall, sys_mlockall)
#define __NR_munlockall 231
__SYSCALL(__NR_munlockall, sys_munlockall)
#define __NR_mincore 232
__SYSCALL(__NR_mincore, sys_mincore)
#define __NR_madvise 233
__SYSCALL(__NR_madvise, sys_madvise)
#define __NR_remap_file_pages 234
__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
#define __NR_mbind 235
__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind)
#define __NR_get_mempolicy 236
__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy)
#define __NR_set_mempolicy 237
__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy)
#define __NR_migrate_pages 238
__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages)
#define __NR_move_pages 239
__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages)
#endif
#define __NR_rt_tgsigqueueinfo 240
__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
compat_sys_rt_tgsigqueueinfo)
#define __NR_perf_event_open 241
__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
#define __NR_accept4 242
__SYSCALL(__NR_accept4, sys_accept4)
#define __NR_recvmmsg 243
__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
/*
* Architectures may provide up to 16 syscalls of their own
* starting with this value.
*/
#define __NR_arch_specific_syscall 244
#define __NR_wait4 260
__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
#define __NR_prlimit64 261
__SYSCALL(__NR_prlimit64, sys_prlimit64)
#define __NR_fanotify_init 262
__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
#define __NR_fanotify_mark 263
__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
#define __NR_name_to_handle_at 264
__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
#define __NR_open_by_handle_at 265
__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
compat_sys_open_by_handle_at)
#define __NR_clock_adjtime 266
__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
#define __NR_syncfs 267
__SYSCALL(__NR_syncfs, sys_syncfs)
#define __NR_setns 268
__SYSCALL(__NR_setns, sys_setns)
#define __NR_sendmmsg 269
__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
#define __NR_process_vm_readv 270
__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
compat_sys_process_vm_readv)
#define __NR_process_vm_writev 271
__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
compat_sys_process_vm_writev)
#define __NR_kcmp 272
__SYSCALL(__NR_kcmp, sys_kcmp)
#define __NR_finit_module 273
__SYSCALL(__NR_finit_module, sys_finit_module)
#define __NR_sched_setattr 274
__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
#define __NR_sched_getattr 275
__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
#define __NR_renameat2 276
__SYSCALL(__NR_renameat2, sys_renameat2)
#define __NR_seccomp 277
__SYSCALL(__NR_seccomp, sys_seccomp)
random: introduce getrandom(2) system call The getrandom(2) system call was requested by the LibreSSL Portable developers. It is analoguous to the getentropy(2) system call in OpenBSD. The rationale of this system call is to provide resiliance against file descriptor exhaustion attacks, where the attacker consumes all available file descriptors, forcing the use of the fallback code where /dev/[u]random is not available. Since the fallback code is often not well-tested, it is better to eliminate this potential failure mode entirely. The other feature provided by this new system call is the ability to request randomness from the /dev/urandom entropy pool, but to block until at least 128 bits of entropy has been accumulated in the /dev/urandom entropy pool. Historically, the emphasis in the /dev/urandom development has been to ensure that urandom pool is initialized as quickly as possible after system boot, and preferably before the init scripts start execution. This is because changing /dev/urandom reads to block represents an interface change that could potentially break userspace which is not acceptable. In practice, on most x86 desktop and server systems, in general the entropy pool can be initialized before it is needed (and in modern kernels, we will printk a warning message if not). However, on an embedded system, this may not be the case. And so with this new interface, we can provide the functionality of blocking until the urandom pool has been initialized. Any userspace program which uses this new functionality must take care to assure that if it is used during the boot process, that it will not cause the init scripts or other portions of the system startup to hang indefinitely. SYNOPSIS #include <linux/random.h> int getrandom(void *buf, size_t buflen, unsigned int flags); DESCRIPTION The system call getrandom() fills the buffer pointed to by buf with up to buflen random bytes which can be used to seed user space random number generators (i.e., DRBG's) or for other cryptographic uses. It should not be used for Monte Carlo simulations or other programs/algorithms which are doing probabilistic sampling. If the GRND_RANDOM flags bit is set, then draw from the /dev/random pool instead of the /dev/urandom pool. The /dev/random pool is limited based on the entropy that can be obtained from environmental noise, so if there is insufficient entropy, the requested number of bytes may not be returned. If there is no entropy available at all, getrandom(2) will either block, or return an error with errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags. If the GRND_RANDOM bit is not set, then the /dev/urandom pool will be used. Unlike using read(2) to fetch data from /dev/urandom, if the urandom pool has not been sufficiently initialized, getrandom(2) will block (or return -1 with the errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags). The getentropy(2) system call in OpenBSD can be emulated using the following function: int getentropy(void *buf, size_t buflen) { int ret; if (buflen > 256) goto failure; ret = getrandom(buf, buflen, 0); if (ret < 0) return ret; if (ret == buflen) return 0; failure: errno = EIO; return -1; } RETURN VALUE On success, the number of bytes that was filled in the buf is returned. This may not be all the bytes requested by the caller via buflen if insufficient entropy was present in the /dev/random pool, or if the system call was interrupted by a signal. On error, -1 is returned, and errno is set appropriately. ERRORS EINVAL An invalid flag was passed to getrandom(2) EFAULT buf is outside the accessible address space. EAGAIN The requested entropy was not available, and getentropy(2) would have blocked if the GRND_NONBLOCK flag was not set. EINTR While blocked waiting for entropy, the call was interrupted by a signal handler; see the description of how interrupted read(2) calls on "slow" devices are handled with and without the SA_RESTART flag in the signal(7) man page. NOTES For small requests (buflen <= 256) getrandom(2) will not return EINTR when reading from the urandom pool once the entropy pool has been initialized, and it will return all of the bytes that have been requested. This is the recommended way to use getrandom(2), and is designed for compatibility with OpenBSD's getentropy() system call. However, if you are using GRND_RANDOM, then getrandom(2) may block until the entropy accounting determines that sufficient environmental noise has been gathered such that getrandom(2) will be operating as a NRBG instead of a DRBG for those people who are working in the NIST SP 800-90 regime. Since it may block for a long time, these guarantees do *not* apply. The user may want to interrupt a hanging process using a signal, so blocking until all of the requested bytes are returned would be unfriendly. For this reason, the user of getrandom(2) MUST always check the return value, in case it returns some error, or if fewer bytes than requested was returned. In the case of !GRND_RANDOM and small request, the latter should never happen, but the careful userspace code (and all crypto code should be careful) should check for this anyway! Finally, unless you are doing long-term key generation (and perhaps not even then), you probably shouldn't be using GRND_RANDOM. The cryptographic algorithms used for /dev/urandom are quite conservative, and so should be sufficient for all purposes. The disadvantage of GRND_RANDOM is that it can block, and the increased complexity required to deal with partially fulfilled getrandom(2) requests. Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Zach Brown <zab@zabbo.net>
2014-07-17 15:13:05 +07:00
#define __NR_getrandom 278
__SYSCALL(__NR_getrandom, sys_getrandom)
#define __NR_memfd_create 279
__SYSCALL(__NR_memfd_create, sys_memfd_create)
#define __NR_bpf 280
__SYSCALL(__NR_bpf, sys_bpf)
syscalls: implement execveat() system call This patchset adds execveat(2) for x86, and is derived from Meredydd Luff's patch from Sept 2012 (https://lkml.org/lkml/2012/9/11/528). The primary aim of adding an execveat syscall is to allow an implementation of fexecve(3) that does not rely on the /proc filesystem, at least for executables (rather than scripts). The current glibc version of fexecve(3) is implemented via /proc, which causes problems in sandboxed or otherwise restricted environments. Given the desire for a /proc-free fexecve() implementation, HPA suggested (https://lkml.org/lkml/2006/7/11/556) that an execveat(2) syscall would be an appropriate generalization. Also, having a new syscall means that it can take a flags argument without back-compatibility concerns. The current implementation just defines the AT_EMPTY_PATH and AT_SYMLINK_NOFOLLOW flags, but other flags could be added in future -- for example, flags for new namespaces (as suggested at https://lkml.org/lkml/2006/7/11/474). Related history: - https://lkml.org/lkml/2006/12/27/123 is an example of someone realizing that fexecve() is likely to fail in a chroot environment. - http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=514043 covered documenting the /proc requirement of fexecve(3) in its manpage, to "prevent other people from wasting their time". - https://bugzilla.redhat.com/show_bug.cgi?id=241609 described a problem where a process that did setuid() could not fexecve() because it no longer had access to /proc/self/fd; this has since been fixed. This patch (of 4): Add a new execveat(2) system call. execveat() is to execve() as openat() is to open(): it takes a file descriptor that refers to a directory, and resolves the filename relative to that. In addition, if the filename is empty and AT_EMPTY_PATH is specified, execveat() executes the file to which the file descriptor refers. This replicates the functionality of fexecve(), which is a system call in other UNIXen, but in Linux glibc it depends on opening "/proc/self/fd/<fd>" (and so relies on /proc being mounted). The filename fed to the executed program as argv[0] (or the name of the script fed to a script interpreter) will be of the form "/dev/fd/<fd>" (for an empty filename) or "/dev/fd/<fd>/<filename>", effectively reflecting how the executable was found. This does however mean that execution of a script in a /proc-less environment won't work; also, script execution via an O_CLOEXEC file descriptor fails (as the file will not be accessible after exec). Based on patches by Meredydd Luff. Signed-off-by: David Drysdale <drysdale@google.com> Cc: Meredydd Luff <meredydd@senatehouse.org> Cc: Shuah Khan <shuah.kh@samsung.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Rich Felker <dalias@aerifal.cx> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-13 07:57:29 +07:00
#define __NR_execveat 281
__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
#define __NR_userfaultfd 282
__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
#define __NR_membarrier 283
sys_membarrier(): system-wide memory barrier (generic, x86) Here is an implementation of a new system call, sys_membarrier(), which executes a memory barrier on all threads running on the system. It is implemented by calling synchronize_sched(). It can be used to distribute the cost of user-space memory barriers asymmetrically by transforming pairs of memory barriers into pairs consisting of sys_membarrier() and a compiler barrier. For synchronization primitives that distinguish between read-side and write-side (e.g. userspace RCU [1], rwlocks), the read-side can be accelerated significantly by moving the bulk of the memory barrier overhead to the write-side. The existing applications of which I am aware that would be improved by this system call are as follows: * Through Userspace RCU library (http://urcu.so) - DNS server (Knot DNS) https://www.knot-dns.cz/ - Network sniffer (http://netsniff-ng.org/) - Distributed object storage (https://sheepdog.github.io/sheepdog/) - User-space tracing (http://lttng.org) - Network storage system (https://www.gluster.org/) - Virtual routers (https://events.linuxfoundation.org/sites/events/files/slides/DPDK_RCU_0MQ.pdf) - Financial software (https://lkml.org/lkml/2015/3/23/189) Those projects use RCU in userspace to increase read-side speed and scalability compared to locking. Especially in the case of RCU used by libraries, sys_membarrier can speed up the read-side by moving the bulk of the memory barrier cost to synchronize_rcu(). * Direct users of sys_membarrier - core dotnet garbage collector (https://github.com/dotnet/coreclr/issues/198) Microsoft core dotnet GC developers are planning to use the mprotect() side-effect of issuing memory barriers through IPIs as a way to implement Windows FlushProcessWriteBuffers() on Linux. They are referring to sys_membarrier in their github thread, specifically stating that sys_membarrier() is what they are looking for. To explain the benefit of this scheme, let's introduce two example threads: Thread A (non-frequent, e.g. executing liburcu synchronize_rcu()) Thread B (frequent, e.g. executing liburcu rcu_read_lock()/rcu_read_unlock()) In a scheme where all smp_mb() in thread A are ordering memory accesses with respect to smp_mb() present in Thread B, we can change each smp_mb() within Thread A into calls to sys_membarrier() and each smp_mb() within Thread B into compiler barriers "barrier()". Before the change, we had, for each smp_mb() pairs: Thread A Thread B previous mem accesses previous mem accesses smp_mb() smp_mb() following mem accesses following mem accesses After the change, these pairs become: Thread A Thread B prev mem accesses prev mem accesses sys_membarrier() barrier() follow mem accesses follow mem accesses As we can see, there are two possible scenarios: either Thread B memory accesses do not happen concurrently with Thread A accesses (1), or they do (2). 1) Non-concurrent Thread A vs Thread B accesses: Thread A Thread B prev mem accesses sys_membarrier() follow mem accesses prev mem accesses barrier() follow mem accesses In this case, thread B accesses will be weakly ordered. This is OK, because at that point, thread A is not particularly interested in ordering them with respect to its own accesses. 2) Concurrent Thread A vs Thread B accesses Thread A Thread B prev mem accesses prev mem accesses sys_membarrier() barrier() follow mem accesses follow mem accesses In this case, thread B accesses, which are ensured to be in program order thanks to the compiler barrier, will be "upgraded" to full smp_mb() by synchronize_sched(). * Benchmarks On Intel Xeon E5405 (8 cores) (one thread is calling sys_membarrier, the other 7 threads are busy looping) 1000 non-expedited sys_membarrier calls in 33s =3D 33 milliseconds/call. * User-space user of this system call: Userspace RCU library Both the signal-based and the sys_membarrier userspace RCU schemes permit us to remove the memory barrier from the userspace RCU rcu_read_lock() and rcu_read_unlock() primitives, thus significantly accelerating them. These memory barriers are replaced by compiler barriers on the read-side, and all matching memory barriers on the write-side are turned into an invocation of a memory barrier on all active threads in the process. By letting the kernel perform this synchronization rather than dumbly sending a signal to every process threads (as we currently do), we diminish the number of unnecessary wake ups and only issue the memory barriers on active threads. Non-running threads do not need to execute such barrier anyway, because these are implied by the scheduler context switches. Results in liburcu: Operations in 10s, 6 readers, 2 writers: memory barriers in reader: 1701557485 reads, 2202847 writes signal-based scheme: 9830061167 reads, 6700 writes sys_membarrier: 9952759104 reads, 425 writes sys_membarrier (dyn. check): 7970328887 reads, 425 writes The dynamic sys_membarrier availability check adds some overhead to the read-side compared to the signal-based scheme, but besides that, sys_membarrier slightly outperforms the signal-based scheme. However, this non-expedited sys_membarrier implementation has a much slower grace period than signal and memory barrier schemes. Besides diminishing the number of wake-ups, one major advantage of the membarrier system call over the signal-based scheme is that it does not need to reserve a signal. This plays much more nicely with libraries, and with processes injected into for tracing purposes, for which we cannot expect that signals will be unused by the application. An expedited version of this system call can be added later on to speed up the grace period. Its implementation will likely depend on reading the cpu_curr()->mm without holding each CPU's rq lock. This patch adds the system call to x86 and to asm-generic. [1] http://urcu.so membarrier(2) man page: MEMBARRIER(2) Linux Programmer's Manual MEMBARRIER(2) NAME membarrier - issue memory barriers on a set of threads SYNOPSIS #include <linux/membarrier.h> int membarrier(int cmd, int flags); DESCRIPTION The cmd argument is one of the following: MEMBARRIER_CMD_QUERY Query the set of supported commands. It returns a bitmask of supported commands. MEMBARRIER_CMD_SHARED Execute a memory barrier on all threads running on the system. Upon return from system call, the caller thread is ensured that all running threads have passed through a state where all memory accesses to user-space addresses match program order between entry to and return from the system call (non-running threads are de facto in such a state). This covers threads from all pro=E2=80=90 cesses running on the system. This command returns 0. The flags argument needs to be 0. For future extensions. All memory accesses performed in program order from each targeted thread is guaranteed to be ordered with respect to sys_membarrier(). If we use the semantic "barrier()" to represent a compiler barrier forcing memory accesses to be performed in program order across the barrier, and smp_mb() to represent explicit memory barriers forcing full memory ordering across the barrier, we have the following ordering table for each pair of barrier(), sys_membarrier() and smp_mb(): The pair ordering is detailed as (O: ordered, X: not ordered): barrier() smp_mb() sys_membarrier() barrier() X X O smp_mb() X O O sys_membarrier() O O O RETURN VALUE On success, these system calls return zero. On error, -1 is returned, and errno is set appropriately. For a given command, with flags argument set to 0, this system call is guaranteed to always return the same value until reboot. ERRORS ENOSYS System call is not implemented. EINVAL Invalid arguments. Linux 2015-04-15 MEMBARRIER(2) Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Nicholas Miell <nmiell@comcast.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Howells <dhowells@redhat.com> Cc: Pranith Kumar <bobby.prani@gmail.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Shuah Khan <shuahkh@osg.samsung.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-12 03:07:39 +07:00
__SYSCALL(__NR_membarrier, sys_membarrier)
#define __NR_mlock2 284
__SYSCALL(__NR_mlock2, sys_mlock2)
#define __NR_copy_file_range 285
__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
#define __NR_preadv2 286
__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2)
#define __NR_pwritev2 287
__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2)
#define __NR_pkey_mprotect 288
__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
#define __NR_pkey_alloc 289
__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
#define __NR_pkey_free 290
__SYSCALL(__NR_pkey_free, sys_pkey_free)
#define __NR_statx 291
__SYSCALL(__NR_statx, sys_statx)
#define __NR_io_pgetevents 292
__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
#define __NR_rseq 293
__SYSCALL(__NR_rseq, sys_rseq)
#define __NR_kexec_file_load 294
__SYSCALL(__NR_kexec_file_load, sys_kexec_file_load)
Add io_uring IO interface The submission queue (SQ) and completion queue (CQ) rings are shared between the application and the kernel. This eliminates the need to copy data back and forth to submit and complete IO. IO submissions use the io_uring_sqe data structure, and completions are generated in the form of io_uring_cqe data structures. The SQ ring is an index into the io_uring_sqe array, which makes it possible to submit a batch of IOs without them being contiguous in the ring. The CQ ring is always contiguous, as completion events are inherently unordered, and hence any io_uring_cqe entry can point back to an arbitrary submission. Two new system calls are added for this: io_uring_setup(entries, params) Sets up an io_uring instance for doing async IO. On success, returns a file descriptor that the application can mmap to gain access to the SQ ring, CQ ring, and io_uring_sqes. io_uring_enter(fd, to_submit, min_complete, flags, sigset, sigsetsize) Initiates IO against the rings mapped to this fd, or waits for them to complete, or both. The behavior is controlled by the parameters passed in. If 'to_submit' is non-zero, then we'll try and submit new IO. If IORING_ENTER_GETEVENTS is set, the kernel will wait for 'min_complete' events, if they aren't already available. It's valid to set IORING_ENTER_GETEVENTS and 'min_complete' == 0 at the same time, this allows the kernel to return already completed events without waiting for them. This is useful only for polling, as for IRQ driven IO, the application can just check the CQ ring without entering the kernel. With this setup, it's possible to do async IO with a single system call. Future developments will enable polled IO with this interface, and polled submission as well. The latter will enable an application to do IO without doing ANY system calls at all. For IRQ driven IO, an application only needs to enter the kernel for completions if it wants to wait for them to occur. Each io_uring is backed by a workqueue, to support buffered async IO as well. We will only punt to an async context if the command would need to wait for IO on the device side. Any data that can be accessed directly in the page cache is done inline. This avoids the slowness issue of usual threadpools, since cached data is accessed as quickly as a sync interface. Sample application: http://git.kernel.dk/cgit/fio/plain/t/io_uring.c Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-01-08 00:46:33 +07:00
#define __NR_io_uring_setup 425
__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
#define __NR_io_uring_enter 426
__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
#undef __NR_syscalls
Add io_uring IO interface The submission queue (SQ) and completion queue (CQ) rings are shared between the application and the kernel. This eliminates the need to copy data back and forth to submit and complete IO. IO submissions use the io_uring_sqe data structure, and completions are generated in the form of io_uring_cqe data structures. The SQ ring is an index into the io_uring_sqe array, which makes it possible to submit a batch of IOs without them being contiguous in the ring. The CQ ring is always contiguous, as completion events are inherently unordered, and hence any io_uring_cqe entry can point back to an arbitrary submission. Two new system calls are added for this: io_uring_setup(entries, params) Sets up an io_uring instance for doing async IO. On success, returns a file descriptor that the application can mmap to gain access to the SQ ring, CQ ring, and io_uring_sqes. io_uring_enter(fd, to_submit, min_complete, flags, sigset, sigsetsize) Initiates IO against the rings mapped to this fd, or waits for them to complete, or both. The behavior is controlled by the parameters passed in. If 'to_submit' is non-zero, then we'll try and submit new IO. If IORING_ENTER_GETEVENTS is set, the kernel will wait for 'min_complete' events, if they aren't already available. It's valid to set IORING_ENTER_GETEVENTS and 'min_complete' == 0 at the same time, this allows the kernel to return already completed events without waiting for them. This is useful only for polling, as for IRQ driven IO, the application can just check the CQ ring without entering the kernel. With this setup, it's possible to do async IO with a single system call. Future developments will enable polled IO with this interface, and polled submission as well. The latter will enable an application to do IO without doing ANY system calls at all. For IRQ driven IO, an application only needs to enter the kernel for completions if it wants to wait for them to occur. Each io_uring is backed by a workqueue, to support buffered async IO as well. We will only punt to an async context if the command would need to wait for IO on the device side. Any data that can be accessed directly in the page cache is done inline. This avoids the slowness issue of usual threadpools, since cached data is accessed as quickly as a sync interface. Sample application: http://git.kernel.dk/cgit/fio/plain/t/io_uring.c Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-01-08 00:46:33 +07:00
#define __NR_syscalls 427
/*
* 32 bit systems traditionally used different
* syscalls for off_t and loff_t arguments, while
* 64 bit systems only need the off_t version.
* For new 32 bit platforms, there is no need to
* implement the old 32 bit off_t syscalls, so
* they take different names.
* Here we map the numbers so that both versions
* use the same syscall table layout.
*/
#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT)
#define __NR_fcntl __NR3264_fcntl
#define __NR_statfs __NR3264_statfs
#define __NR_fstatfs __NR3264_fstatfs
#define __NR_truncate __NR3264_truncate
#define __NR_ftruncate __NR3264_ftruncate
#define __NR_lseek __NR3264_lseek
#define __NR_sendfile __NR3264_sendfile
#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64)
#define __NR_newfstatat __NR3264_fstatat
#define __NR_fstat __NR3264_fstat
#endif
#define __NR_mmap __NR3264_mmap
#define __NR_fadvise64 __NR3264_fadvise64
#ifdef __NR3264_stat
#define __NR_stat __NR3264_stat
#define __NR_lstat __NR3264_lstat
#endif
#else
#define __NR_fcntl64 __NR3264_fcntl
#define __NR_statfs64 __NR3264_statfs
#define __NR_fstatfs64 __NR3264_fstatfs
#define __NR_truncate64 __NR3264_truncate
#define __NR_ftruncate64 __NR3264_ftruncate
#define __NR_llseek __NR3264_lseek
#define __NR_sendfile64 __NR3264_sendfile
#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64)
#define __NR_fstatat64 __NR3264_fstatat
#define __NR_fstat64 __NR3264_fstat
#endif
#define __NR_mmap2 __NR3264_mmap
#define __NR_fadvise64_64 __NR3264_fadvise64
#ifdef __NR3264_stat
#define __NR_stat64 __NR3264_stat
#define __NR_lstat64 __NR3264_lstat
#endif
#endif