linux/arch/x86/kernel/syscall_table_32.S

339 lines
8.1 KiB
ArmAsm
Raw Normal View History

ENTRY(sys_call_table)
.long sys_restart_syscall /* 0 - old "setup()" system call, used for restarting */
.long sys_exit
.long ptregs_fork
.long sys_read
.long sys_write
.long sys_open /* 5 */
.long sys_close
.long sys_waitpid
.long sys_creat
.long sys_link
.long sys_unlink /* 10 */
.long ptregs_execve
.long sys_chdir
.long sys_time
.long sys_mknod
.long sys_chmod /* 15 */
.long sys_lchown16
.long sys_ni_syscall /* old break syscall holder */
.long sys_stat
.long sys_lseek
.long sys_getpid /* 20 */
.long sys_mount
.long sys_oldumount
.long sys_setuid16
.long sys_getuid16
.long sys_stime /* 25 */
.long sys_ptrace
.long sys_alarm
.long sys_fstat
.long sys_pause
.long sys_utime /* 30 */
.long sys_ni_syscall /* old stty syscall holder */
.long sys_ni_syscall /* old gtty syscall holder */
.long sys_access
.long sys_nice
.long sys_ni_syscall /* 35 - old ftime syscall holder */
.long sys_sync
.long sys_kill
.long sys_rename
.long sys_mkdir
.long sys_rmdir /* 40 */
.long sys_dup
.long sys_pipe
.long sys_times
.long sys_ni_syscall /* old prof syscall holder */
.long sys_brk /* 45 */
.long sys_setgid16
.long sys_getgid16
.long sys_signal
.long sys_geteuid16
.long sys_getegid16 /* 50 */
.long sys_acct
.long sys_umount /* recycled never used phys() */
.long sys_ni_syscall /* old lock syscall holder */
.long sys_ioctl
.long sys_fcntl /* 55 */
.long sys_ni_syscall /* old mpx syscall holder */
.long sys_setpgid
.long sys_ni_syscall /* old ulimit syscall holder */
.long sys_olduname
.long sys_umask /* 60 */
.long sys_chroot
.long sys_ustat
.long sys_dup2
.long sys_getppid
.long sys_getpgrp /* 65 */
.long sys_setsid
.long sys_sigaction
.long sys_sgetmask
.long sys_ssetmask
.long sys_setreuid16 /* 70 */
.long sys_setregid16
.long sys_sigsuspend
.long sys_sigpending
.long sys_sethostname
.long sys_setrlimit /* 75 */
.long sys_old_getrlimit
.long sys_getrusage
.long sys_gettimeofday
.long sys_settimeofday
.long sys_getgroups16 /* 80 */
.long sys_setgroups16
.long old_select
.long sys_symlink
.long sys_lstat
.long sys_readlink /* 85 */
.long sys_uselib
.long sys_swapon
.long sys_reboot
.long sys_old_readdir
.long old_mmap /* 90 */
.long sys_munmap
.long sys_truncate
.long sys_ftruncate
.long sys_fchmod
.long sys_fchown16 /* 95 */
.long sys_getpriority
.long sys_setpriority
.long sys_ni_syscall /* old profil syscall holder */
.long sys_statfs
.long sys_fstatfs /* 100 */
.long sys_ioperm
.long sys_socketcall
.long sys_syslog
.long sys_setitimer
.long sys_getitimer /* 105 */
.long sys_newstat
.long sys_newlstat
.long sys_newfstat
.long sys_uname
.long ptregs_iopl /* 110 */
.long sys_vhangup
.long sys_ni_syscall /* old "idle" system call */
.long ptregs_vm86old
.long sys_wait4
.long sys_swapoff /* 115 */
.long sys_sysinfo
.long sys_ipc
.long sys_fsync
.long ptregs_sigreturn
.long ptregs_clone /* 120 */
.long sys_setdomainname
.long sys_newuname
.long sys_modify_ldt
.long sys_adjtimex
.long sys_mprotect /* 125 */
.long sys_sigprocmask
.long sys_ni_syscall /* old "create_module" */
.long sys_init_module
.long sys_delete_module
.long sys_ni_syscall /* 130: old "get_kernel_syms" */
.long sys_quotactl
.long sys_getpgid
.long sys_fchdir
.long sys_bdflush
.long sys_sysfs /* 135 */
.long sys_personality
.long sys_ni_syscall /* reserved for afs_syscall */
.long sys_setfsuid16
.long sys_setfsgid16
.long sys_llseek /* 140 */
.long sys_getdents
.long sys_select
.long sys_flock
.long sys_msync
.long sys_readv /* 145 */
.long sys_writev
.long sys_getsid
.long sys_fdatasync
.long sys_sysctl
.long sys_mlock /* 150 */
.long sys_munlock
.long sys_mlockall
.long sys_munlockall
.long sys_sched_setparam
.long sys_sched_getparam /* 155 */
.long sys_sched_setscheduler
.long sys_sched_getscheduler
.long sys_sched_yield
.long sys_sched_get_priority_max
.long sys_sched_get_priority_min /* 160 */
.long sys_sched_rr_get_interval
.long sys_nanosleep
.long sys_mremap
.long sys_setresuid16
.long sys_getresuid16 /* 165 */
.long ptregs_vm86
.long sys_ni_syscall /* Old sys_query_module */
.long sys_poll
.long sys_nfsservctl
.long sys_setresgid16 /* 170 */
.long sys_getresgid16
.long sys_prctl
.long ptregs_rt_sigreturn
.long sys_rt_sigaction
.long sys_rt_sigprocmask /* 175 */
.long sys_rt_sigpending
.long sys_rt_sigtimedwait
.long sys_rt_sigqueueinfo
.long sys_rt_sigsuspend
.long sys_pread64 /* 180 */
.long sys_pwrite64
.long sys_chown16
.long sys_getcwd
.long sys_capget
.long sys_capset /* 185 */
.long ptregs_sigaltstack
.long sys_sendfile
.long sys_ni_syscall /* reserved for streams1 */
.long sys_ni_syscall /* reserved for streams2 */
.long ptregs_vfork /* 190 */
.long sys_getrlimit
.long sys_mmap2
.long sys_truncate64
.long sys_ftruncate64
.long sys_stat64 /* 195 */
.long sys_lstat64
.long sys_fstat64
.long sys_lchown
.long sys_getuid
.long sys_getgid /* 200 */
.long sys_geteuid
.long sys_getegid
.long sys_setreuid
.long sys_setregid
.long sys_getgroups /* 205 */
.long sys_setgroups
.long sys_fchown
.long sys_setresuid
.long sys_getresuid
.long sys_setresgid /* 210 */
.long sys_getresgid
.long sys_chown
.long sys_setuid
.long sys_setgid
.long sys_setfsuid /* 215 */
.long sys_setfsgid
.long sys_pivot_root
.long sys_mincore
.long sys_madvise
.long sys_getdents64 /* 220 */
.long sys_fcntl64
.long sys_ni_syscall /* reserved for TUX */
.long sys_ni_syscall
.long sys_gettid
.long sys_readahead /* 225 */
.long sys_setxattr
.long sys_lsetxattr
.long sys_fsetxattr
.long sys_getxattr
.long sys_lgetxattr /* 230 */
.long sys_fgetxattr
.long sys_listxattr
.long sys_llistxattr
.long sys_flistxattr
.long sys_removexattr /* 235 */
.long sys_lremovexattr
.long sys_fremovexattr
.long sys_tkill
.long sys_sendfile64
.long sys_futex /* 240 */
.long sys_sched_setaffinity
.long sys_sched_getaffinity
.long sys_set_thread_area
.long sys_get_thread_area
.long sys_io_setup /* 245 */
.long sys_io_destroy
.long sys_io_getevents
.long sys_io_submit
.long sys_io_cancel
.long sys_fadvise64 /* 250 */
[PATCH] remove sys_set_zone_reclaim() This removes sys_set_zone_reclaim() for now. While i'm sure Martin is trying to solve a real problem, we must not hard-code an incomplete and insufficient approach into a syscall, because syscalls are pretty much for eternity. I am quite strongly convinced that this syscall must not hit v2.6.13 in its current form. Firstly, the syscall lacks basic syscall design: e.g. it allows the global setting of VM policy for unprivileged users. (!) [ Imagine an Oracle installation and a SAP installation on the same NUMA box fighting over the 'optimal' setting for this flag. What will they do? Will they try to set the flag to their own preferred value every second or so? ] Secondly, it was added based on a single datapoint from Martin: http://marc.theaimsgroup.com/?l=linux-mm&m=111763597218177&w=2 where Martin characterizes the numbers the following way: ' Run-to-run variability for "make -j" is huge, so these numbers aren't terribly useful except to see that with reclaim the benchmark still finishes in a reasonable amount of time. ' in other words: the fundamental problem has likely not been solved, only a tendential move into the right direction has been observed, and a handful of numbers were picked out of a set of hugely variable results, without showing the variability data. How much variance is there run-to-run? I'd really suggest to first walk the walk and see what's needed to get stable & predictable kernel compilation numbers on that NUMA box, before adding random syscalls to tune a particular aspect of the VM ... which approach might not even matter once the whole picture has been analyzed and understood! The third, most important point is that the syscall exposes VM tuning internals in a completely unstructured way. What sense does it make to have a _GLOBAL_ per-node setting for 'should we go to another node for reclaim'? If then it might make sense to do this per-app, via numalib or so. The change is minimalistic in that it doesnt remove the syscall and the underlying infrastructure changes, only the user-visible changes. We could perhaps add a CAP_SYS_ADMIN-only sysctl for this hack, a'ka /proc/sys/vm/swappiness, but even that looks quite counterproductive when the generic approach is that we are trying to reduce the number of external factors in the VM balance picture. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-08-01 11:39:13 +00:00
.long sys_ni_syscall
.long sys_exit_group
.long sys_lookup_dcookie
.long sys_epoll_create
.long sys_epoll_ctl /* 255 */
.long sys_epoll_wait
.long sys_remap_file_pages
.long sys_set_tid_address
.long sys_timer_create
.long sys_timer_settime /* 260 */
.long sys_timer_gettime
.long sys_timer_getoverrun
.long sys_timer_delete
.long sys_clock_settime
.long sys_clock_gettime /* 265 */
.long sys_clock_getres
.long sys_clock_nanosleep
.long sys_statfs64
.long sys_fstatfs64
.long sys_tgkill /* 270 */
.long sys_utimes
.long sys_fadvise64_64
.long sys_ni_syscall /* sys_vserver */
.long sys_mbind
.long sys_get_mempolicy
.long sys_set_mempolicy
.long sys_mq_open
.long sys_mq_unlink
.long sys_mq_timedsend
.long sys_mq_timedreceive /* 280 */
.long sys_mq_notify
.long sys_mq_getsetattr
.long sys_kexec_load
.long sys_waitid
.long sys_ni_syscall /* 285 */ /* available */
.long sys_add_key
.long sys_request_key
.long sys_keyctl
.long sys_ioprio_set
.long sys_ioprio_get /* 290 */
.long sys_inotify_init
.long sys_inotify_add_watch
.long sys_inotify_rm_watch
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 09:00:51 +00:00
.long sys_migrate_pages
.long sys_openat /* 295 */
.long sys_mkdirat
.long sys_mknodat
.long sys_fchownat
.long sys_futimesat
.long sys_fstatat64 /* 300 */
.long sys_unlinkat
.long sys_renameat
.long sys_linkat
.long sys_symlinkat
.long sys_readlinkat /* 305 */
.long sys_fchmodat
.long sys_faccessat
.long sys_pselect6
.long sys_ppoll
.long sys_unshare /* 310 */
.long sys_set_robust_list
.long sys_get_robust_list
.long sys_splice
[PATCH] sys_sync_file_range() Remove the recently-added LINUX_FADV_ASYNC_WRITE and LINUX_FADV_WRITE_WAIT fadvise() additions, do it in a new sys_sync_file_range() syscall instead. Reasons: - It's more flexible. Things which would require two or three syscalls with fadvise() can be done in a single syscall. - Using fadvise() in this manner is something not covered by POSIX. The patch wires up the syscall for x86. The sycall is implemented in the new fs/sync.c. The intention is that we can move sys_fsync(), sys_fdatasync() and perhaps sys_sync() into there later. Documentation for the syscall is in fs/sync.c. A test app (sync_file_range.c) is in http://www.zip.com.au/~akpm/linux/patches/stuff/ext3-tools.tar.gz. The available-to-GPL-modules do_sync_file_range() is for knfsd: "A COMMIT can say NFS_DATA_SYNC or NFS_FILE_SYNC. I can skip the ->fsync call for NFS_DATA_SYNC which is hopefully the more common." Note: the `async' writeout mode SYNC_FILE_RANGE_WRITE will turn synchronous if the queue is congested. This is trivial to fix: add a new flag bit, set wbc->nonblocking. But I'm not sure that we want to expose implementation details down to that level. Note: it's notable that we can sync an fd which wasn't opened for writing. Same with fsync() and fdatasync()). Note: the code takes some care to handle attempts to sync file contents outside the 16TB offset on 32-bit machines. It makes such attempts appear to succeed, for best 32-bit/64-bit compatibility. Perhaps it should make such requests fail... Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Ulrich Drepper <drepper@redhat.com> Cc: Neil Brown <neilb@cse.unsw.edu.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-31 10:30:42 +00:00
.long sys_sync_file_range
.long sys_tee /* 315 */
.long sys_vmsplice
.long sys_move_pages
.long sys_getcpu
.long sys_epoll_pwait
utimensat implementation Implement utimensat(2) which is an extension to futimesat(2) in that it a) supports nano-second resolution for the timestamps b) allows to selectively ignore the atime/mtime value c) allows to selectively use the current time for either atime or mtime d) supports changing the atime/mtime of a symlink itself along the lines of the BSD lutimes(3) functions For this change the internally used do_utimes() functions was changed to accept a timespec time value and an additional flags parameter. Additionally the sys_utime function was changed to match compat_sys_utime which already use do_utimes instead of duplicating the work. Also, the completely missing futimensat() functionality is added. We have such a function in glibc but we have to resort to using /proc/self/fd/* which not everybody likes (chroot etc). Test application (the syscall number will need per-arch editing): #include <errno.h> #include <fcntl.h> #include <time.h> #include <sys/time.h> #include <stddef.h> #include <syscall.h> #define __NR_utimensat 280 #define UTIME_NOW ((1l << 30) - 1l) #define UTIME_OMIT ((1l << 30) - 2l) int main(void) { int status = 0; int fd = open("ttt", O_RDWR|O_CREAT|O_EXCL, 0666); if (fd == -1) error (1, errno, "failed to create test file \"ttt\""); struct stat64 st1; if (fstat64 (fd, &st1) != 0) error (1, errno, "fstat failed"); struct timespec t[2]; t[0].tv_sec = 0; t[0].tv_nsec = 0; t[1].tv_sec = 0; t[1].tv_nsec = 0; if (syscall(__NR_utimensat, AT_FDCWD, "ttt", t, 0) != 0) error (1, errno, "utimensat failed"); struct stat64 st2; if (fstat64 (fd, &st2) != 0) error (1, errno, "fstat failed"); if (st2.st_atim.tv_sec != 0 || st2.st_atim.tv_nsec != 0) { puts ("atim not reset to zero"); status = 1; } if (st2.st_mtim.tv_sec != 0 || st2.st_mtim.tv_nsec != 0) { puts ("mtim not reset to zero"); status = 1; } if (status != 0) goto out; t[0] = st1.st_atim; t[1].tv_sec = 0; t[1].tv_nsec = UTIME_OMIT; if (syscall(__NR_utimensat, AT_FDCWD, "ttt", t, 0) != 0) error (1, errno, "utimensat failed"); if (fstat64 (fd, &st2) != 0) error (1, errno, "fstat failed"); if (st2.st_atim.tv_sec != st1.st_atim.tv_sec || st2.st_atim.tv_nsec != st1.st_atim.tv_nsec) { puts ("atim not set"); status = 1; } if (st2.st_mtim.tv_sec != 0 || st2.st_mtim.tv_nsec != 0) { puts ("mtim changed from zero"); status = 1; } if (status != 0) goto out; t[0].tv_sec = 0; t[0].tv_nsec = UTIME_OMIT; t[1] = st1.st_mtim; if (syscall(__NR_utimensat, AT_FDCWD, "ttt", t, 0) != 0) error (1, errno, "utimensat failed"); if (fstat64 (fd, &st2) != 0) error (1, errno, "fstat failed"); if (st2.st_atim.tv_sec != st1.st_atim.tv_sec || st2.st_atim.tv_nsec != st1.st_atim.tv_nsec) { puts ("mtim changed from original time"); status = 1; } if (st2.st_mtim.tv_sec != st1.st_mtim.tv_sec || st2.st_mtim.tv_nsec != st1.st_mtim.tv_nsec) { puts ("mtim not set"); status = 1; } if (status != 0) goto out; sleep (2); t[0].tv_sec = 0; t[0].tv_nsec = UTIME_NOW; t[1].tv_sec = 0; t[1].tv_nsec = UTIME_NOW; if (syscall(__NR_utimensat, AT_FDCWD, "ttt", t, 0) != 0) error (1, errno, "utimensat failed"); if (fstat64 (fd, &st2) != 0) error (1, errno, "fstat failed"); struct timeval tv; gettimeofday(&tv,NULL); if (st2.st_atim.tv_sec <= st1.st_atim.tv_sec || st2.st_atim.tv_sec > tv.tv_sec) { puts ("atim not set to NOW"); status = 1; } if (st2.st_mtim.tv_sec <= st1.st_mtim.tv_sec || st2.st_mtim.tv_sec > tv.tv_sec) { puts ("mtim not set to NOW"); status = 1; } if (symlink ("ttt", "tttsym") != 0) error (1, errno, "cannot create symlink"); t[0].tv_sec = 0; t[0].tv_nsec = 0; t[1].tv_sec = 0; t[1].tv_nsec = 0; if (syscall(__NR_utimensat, AT_FDCWD, "tttsym", t, AT_SYMLINK_NOFOLLOW) != 0) error (1, errno, "utimensat failed"); if (lstat64 ("tttsym", &st2) != 0) error (1, errno, "lstat failed"); if (st2.st_atim.tv_sec != 0 || st2.st_atim.tv_nsec != 0) { puts ("symlink atim not reset to zero"); status = 1; } if (st2.st_mtim.tv_sec != 0 || st2.st_mtim.tv_nsec != 0) { puts ("symlink mtim not reset to zero"); status = 1; } if (status != 0) goto out; t[0].tv_sec = 1; t[0].tv_nsec = 0; t[1].tv_sec = 1; t[1].tv_nsec = 0; if (syscall(__NR_utimensat, fd, NULL, t, 0) != 0) error (1, errno, "utimensat failed"); if (fstat64 (fd, &st2) != 0) error (1, errno, "fstat failed"); if (st2.st_atim.tv_sec != 1 || st2.st_atim.tv_nsec != 0) { puts ("atim not reset to one"); status = 1; } if (st2.st_mtim.tv_sec != 1 || st2.st_mtim.tv_nsec != 0) { puts ("mtim not reset to one"); status = 1; } if (status == 0) puts ("all OK"); out: close (fd); unlink ("ttt"); unlink ("tttsym"); return status; } [akpm@linux-foundation.org: add missing i386 syscall table entry] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Cc: Alexey Dobriyan <adobriyan@openvz.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 07:33:25 +00:00
.long sys_utimensat /* 320 */
.long sys_signalfd
.long sys_timerfd_create
.long sys_eventfd
sys_fallocate() implementation on i386, x86_64 and powerpc fallocate() is a new system call being proposed here which will allow applications to preallocate space to any file(s) in a file system. Each file system implementation that wants to use this feature will need to support an inode operation called ->fallocate(). Applications can use this feature to avoid fragmentation to certain level and thus get faster access speed. With preallocation, applications also get a guarantee of space for particular file(s) - even if later the the system becomes full. Currently, glibc provides an interface called posix_fallocate() which can be used for similar cause. Though this has the advantage of working on all file systems, but it is quite slow (since it writes zeroes to each block that has to be preallocated). Without a doubt, file systems can do this more efficiently within the kernel, by implementing the proposed fallocate() system call. It is expected that posix_fallocate() will be modified to call this new system call first and incase the kernel/filesystem does not implement it, it should fall back to the current implementation of writing zeroes to the new blocks. ToDos: 1. Implementation on other architectures (other than i386, x86_64, and ppc). Patches for s390(x) and ia64 are already available from previous posts, but it was decided that they should be added later once fallocate is in the mainline. Hence not including those patches in this take. 2. Changes to glibc, a) to support fallocate() system call b) to make posix_fallocate() and posix_fallocate64() call fallocate() Signed-off-by: Amit Arora <aarora@in.ibm.com>
2007-07-18 01:42:44 +00:00
.long sys_fallocate
.long sys_timerfd_settime /* 325 */
.long sys_timerfd_gettime
flag parameters: signalfd This patch adds the new signalfd4 syscall. It extends the old signalfd syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is SFD_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name SFD_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <signal.h> #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_signalfd4 # ifdef __x86_64__ # define __NR_signalfd4 289 # elif defined __i386__ # define __NR_signalfd4 327 # else # error "need __NR_signalfd4" # endif #endif #define SFD_CLOEXEC O_CLOEXEC int main (void) { sigset_t ss; sigemptyset (&ss); sigaddset (&ss, SIGUSR1); int fd = syscall (__NR_signalfd4, -1, &ss, 8, 0); if (fd == -1) { puts ("signalfd4(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("signalfd4(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_signalfd4, -1, &ss, 8, SFD_CLOEXEC); if (fd == -1) { puts ("signalfd4(SFD_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("signalfd4(SFD_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:29:24 +00:00
.long sys_signalfd4
flag parameters: eventfd This patch adds the new eventfd2 syscall. It extends the old eventfd syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is EFD_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name EFD_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_eventfd2 # ifdef __x86_64__ # define __NR_eventfd2 290 # elif defined __i386__ # define __NR_eventfd2 328 # else # error "need __NR_eventfd2" # endif #endif #define EFD_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_eventfd2, 1, 0); if (fd == -1) { puts ("eventfd2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("eventfd2(0) sets close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_eventfd2, 1, EFD_CLOEXEC); if (fd == -1) { puts ("eventfd2(EFD_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("eventfd2(EFD_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:29:25 +00:00
.long sys_eventfd2
flag parameters add-on: remove epoll_create size param Remove the size parameter from the new epoll_create syscall and renames the syscall itself. The updated test program follows. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <time.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_epoll_create2 # ifdef __x86_64__ # define __NR_epoll_create2 291 # elif defined __i386__ # define __NR_epoll_create2 329 # else # error "need __NR_epoll_create2" # endif #endif #define EPOLL_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_epoll_create2, 0); if (fd == -1) { puts ("epoll_create2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("epoll_create2(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_epoll_create2, EPOLL_CLOEXEC); if (fd == -1) { puts ("epoll_create2(EPOLL_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:29:43 +00:00
.long sys_epoll_create1
flag parameters: dup2 This patch adds the new dup3 syscall. It extends the old dup2 syscall by one parameter which is meant to hold a flag value. Support for the O_CLOEXEC flag is added in this patch. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <time.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_dup3 # ifdef __x86_64__ # define __NR_dup3 292 # elif defined __i386__ # define __NR_dup3 330 # else # error "need __NR_dup3" # endif #endif int main (void) { int fd = syscall (__NR_dup3, 1, 4, 0); if (fd == -1) { puts ("dup3(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("dup3(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_dup3, 1, 4, O_CLOEXEC); if (fd == -1) { puts ("dup3(O_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("dup3(O_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:29:29 +00:00
.long sys_dup3 /* 330 */
flag parameters: pipe This patch introduces the new syscall pipe2 which is like pipe but it also takes an additional parameter which takes a flag value. This patch implements the handling of O_CLOEXEC for the flag. I did not add support for the new syscall for the architectures which have a special sys_pipe implementation. I think the maintainers of those archs have the chance to go with the unified implementation but that's up to them. The implementation introduces do_pipe_flags. I did that instead of changing all callers of do_pipe because some of the callers are written in assembler. I would probably screw up changing the assembly code. To avoid breaking code do_pipe is now a small wrapper around do_pipe_flags. Once all callers are changed over to do_pipe_flags the old do_pipe function can be removed. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_pipe2 # ifdef __x86_64__ # define __NR_pipe2 293 # elif defined __i386__ # define __NR_pipe2 331 # else # error "need __NR_pipe2" # endif #endif int main (void) { int fd[2]; if (syscall (__NR_pipe2, fd, 0) != 0) { puts ("pipe2(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { printf ("pipe2(0) set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); if (syscall (__NR_pipe2, fd, O_CLOEXEC) != 0) { puts ("pipe2(O_CLOEXEC) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { printf ("pipe2(O_CLOEXEC) does not set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:29:30 +00:00
.long sys_pipe2
flag parameters: inotify_init This patch introduces the new syscall inotify_init1 (note: the 1 stands for the one parameter the syscall takes, as opposed to no parameter before). The values accepted for this parameter are function-specific and defined in the inotify.h header. Here the values must match the O_* flags, though. In this patch CLOEXEC support is introduced. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_inotify_init1 # ifdef __x86_64__ # define __NR_inotify_init1 294 # elif defined __i386__ # define __NR_inotify_init1 332 # else # error "need __NR_inotify_init1" # endif #endif #define IN_CLOEXEC O_CLOEXEC int main (void) { int fd; fd = syscall (__NR_inotify_init1, 0); if (fd == -1) { puts ("inotify_init1(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("inotify_init1(0) set close-on-exit"); return 1; } close (fd); fd = syscall (__NR_inotify_init1, IN_CLOEXEC); if (fd == -1) { puts ("inotify_init1(IN_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("inotify_init1(O_CLOEXEC) does not set close-on-exit"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:29:32 +00:00
.long sys_inotify_init1
preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:59:23 +00:00
.long sys_preadv
.long sys_pwritev
.long sys_rt_tgsigqueueinfo /* 335 */
.long sys_perf_counter_open