forked from Minki/linux
fcf634098c
The basic idea behind cross memory attach is to allow MPI programs doing intra-node communication to do a single copy of the message rather than a double copy of the message via shared memory. The following patch attempts to achieve this by allowing a destination process, given an address and size from a source process, to copy memory directly from the source process into its own address space via a system call. There is also a symmetrical ability to copy from the current process's address space into a destination process's address space. - Use of /proc/pid/mem has been considered, but there are issues with using it: - Does not allow for specifying iovecs for both src and dest, assuming preadv or pwritev was implemented either the area read from or written to would need to be contiguous. - Currently mem_read allows only processes who are currently ptrace'ing the target and are still able to ptrace the target to read from the target. This check could possibly be moved to the open call, but its not clear exactly what race this restriction is stopping (reason appears to have been lost) - Having to send the fd of /proc/self/mem via SCM_RIGHTS on unix domain socket is a bit ugly from a userspace point of view, especially when you may have hundreds if not (eventually) thousands of processes that all need to do this with each other - Doesn't allow for some future use of the interface we would like to consider adding in the future (see below) - Interestingly reading from /proc/pid/mem currently actually involves two copies! (But this could be fixed pretty easily) As mentioned previously use of vmsplice instead was considered, but has problems. Since you need the reader and writer working co-operatively if the pipe is not drained then you block. Which requires some wrapping to do non blocking on the send side or polling on the receive. In all to all communication it requires ordering otherwise you can deadlock. And in the example of many MPI tasks writing to one MPI task vmsplice serialises the copying. There are some cases of MPI collectives where even a single copy interface does not get us the performance gain we could. For example in an MPI_Reduce rather than copy the data from the source we would like to instead use it directly in a mathops (say the reduce is doing a sum) as this would save us doing a copy. We don't need to keep a copy of the data from the source. I haven't implemented this, but I think this interface could in the future do all this through the use of the flags - eg could specify the math operation and type and the kernel rather than just copying the data would apply the specified operation between the source and destination and store it in the destination. Although we don't have a "second user" of the interface (though I've had some nibbles from people who may be interested in using it for intra process messaging which is not MPI). This interface is something which hardware vendors are already doing for their custom drivers to implement fast local communication. And so in addition to this being useful for OpenMPI it would mean the driver maintainers don't have to fix things up when the mm changes. There was some discussion about how much faster a true zero copy would go. Here's a link back to the email with some testing I did on that: http://marc.info/?l=linux-mm&m=130105930902915&w=2 There is a basic man page for the proposed interface here: http://ozlabs.org/~cyeoh/cma/process_vm_readv.txt This has been implemented for x86 and powerpc, other architecture should mainly (I think) just need to add syscall numbers for the process_vm_readv and process_vm_writev. There are 32 bit compatibility versions for 64-bit kernels. For arch maintainers there are some simple tests to be able to quickly verify that the syscalls are working correctly here: http://ozlabs.org/~cyeoh/cma/cma-test-20110718.tgz Signed-off-by: Chris Yeoh <yeohc@au1.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: James Morris <jmorris@namei.org> Cc: <linux-man@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
402 lines
11 KiB
C
402 lines
11 KiB
C
#ifndef _ASM_X86_UNISTD_32_H
|
|
#define _ASM_X86_UNISTD_32_H
|
|
|
|
/*
|
|
* This file contains the system call numbers.
|
|
*/
|
|
|
|
#define __NR_restart_syscall 0
|
|
#define __NR_exit 1
|
|
#define __NR_fork 2
|
|
#define __NR_read 3
|
|
#define __NR_write 4
|
|
#define __NR_open 5
|
|
#define __NR_close 6
|
|
#define __NR_waitpid 7
|
|
#define __NR_creat 8
|
|
#define __NR_link 9
|
|
#define __NR_unlink 10
|
|
#define __NR_execve 11
|
|
#define __NR_chdir 12
|
|
#define __NR_time 13
|
|
#define __NR_mknod 14
|
|
#define __NR_chmod 15
|
|
#define __NR_lchown 16
|
|
#define __NR_break 17
|
|
#define __NR_oldstat 18
|
|
#define __NR_lseek 19
|
|
#define __NR_getpid 20
|
|
#define __NR_mount 21
|
|
#define __NR_umount 22
|
|
#define __NR_setuid 23
|
|
#define __NR_getuid 24
|
|
#define __NR_stime 25
|
|
#define __NR_ptrace 26
|
|
#define __NR_alarm 27
|
|
#define __NR_oldfstat 28
|
|
#define __NR_pause 29
|
|
#define __NR_utime 30
|
|
#define __NR_stty 31
|
|
#define __NR_gtty 32
|
|
#define __NR_access 33
|
|
#define __NR_nice 34
|
|
#define __NR_ftime 35
|
|
#define __NR_sync 36
|
|
#define __NR_kill 37
|
|
#define __NR_rename 38
|
|
#define __NR_mkdir 39
|
|
#define __NR_rmdir 40
|
|
#define __NR_dup 41
|
|
#define __NR_pipe 42
|
|
#define __NR_times 43
|
|
#define __NR_prof 44
|
|
#define __NR_brk 45
|
|
#define __NR_setgid 46
|
|
#define __NR_getgid 47
|
|
#define __NR_signal 48
|
|
#define __NR_geteuid 49
|
|
#define __NR_getegid 50
|
|
#define __NR_acct 51
|
|
#define __NR_umount2 52
|
|
#define __NR_lock 53
|
|
#define __NR_ioctl 54
|
|
#define __NR_fcntl 55
|
|
#define __NR_mpx 56
|
|
#define __NR_setpgid 57
|
|
#define __NR_ulimit 58
|
|
#define __NR_oldolduname 59
|
|
#define __NR_umask 60
|
|
#define __NR_chroot 61
|
|
#define __NR_ustat 62
|
|
#define __NR_dup2 63
|
|
#define __NR_getppid 64
|
|
#define __NR_getpgrp 65
|
|
#define __NR_setsid 66
|
|
#define __NR_sigaction 67
|
|
#define __NR_sgetmask 68
|
|
#define __NR_ssetmask 69
|
|
#define __NR_setreuid 70
|
|
#define __NR_setregid 71
|
|
#define __NR_sigsuspend 72
|
|
#define __NR_sigpending 73
|
|
#define __NR_sethostname 74
|
|
#define __NR_setrlimit 75
|
|
#define __NR_getrlimit 76 /* Back compatible 2Gig limited rlimit */
|
|
#define __NR_getrusage 77
|
|
#define __NR_gettimeofday 78
|
|
#define __NR_settimeofday 79
|
|
#define __NR_getgroups 80
|
|
#define __NR_setgroups 81
|
|
#define __NR_select 82
|
|
#define __NR_symlink 83
|
|
#define __NR_oldlstat 84
|
|
#define __NR_readlink 85
|
|
#define __NR_uselib 86
|
|
#define __NR_swapon 87
|
|
#define __NR_reboot 88
|
|
#define __NR_readdir 89
|
|
#define __NR_mmap 90
|
|
#define __NR_munmap 91
|
|
#define __NR_truncate 92
|
|
#define __NR_ftruncate 93
|
|
#define __NR_fchmod 94
|
|
#define __NR_fchown 95
|
|
#define __NR_getpriority 96
|
|
#define __NR_setpriority 97
|
|
#define __NR_profil 98
|
|
#define __NR_statfs 99
|
|
#define __NR_fstatfs 100
|
|
#define __NR_ioperm 101
|
|
#define __NR_socketcall 102
|
|
#define __NR_syslog 103
|
|
#define __NR_setitimer 104
|
|
#define __NR_getitimer 105
|
|
#define __NR_stat 106
|
|
#define __NR_lstat 107
|
|
#define __NR_fstat 108
|
|
#define __NR_olduname 109
|
|
#define __NR_iopl 110
|
|
#define __NR_vhangup 111
|
|
#define __NR_idle 112
|
|
#define __NR_vm86old 113
|
|
#define __NR_wait4 114
|
|
#define __NR_swapoff 115
|
|
#define __NR_sysinfo 116
|
|
#define __NR_ipc 117
|
|
#define __NR_fsync 118
|
|
#define __NR_sigreturn 119
|
|
#define __NR_clone 120
|
|
#define __NR_setdomainname 121
|
|
#define __NR_uname 122
|
|
#define __NR_modify_ldt 123
|
|
#define __NR_adjtimex 124
|
|
#define __NR_mprotect 125
|
|
#define __NR_sigprocmask 126
|
|
#define __NR_create_module 127
|
|
#define __NR_init_module 128
|
|
#define __NR_delete_module 129
|
|
#define __NR_get_kernel_syms 130
|
|
#define __NR_quotactl 131
|
|
#define __NR_getpgid 132
|
|
#define __NR_fchdir 133
|
|
#define __NR_bdflush 134
|
|
#define __NR_sysfs 135
|
|
#define __NR_personality 136
|
|
#define __NR_afs_syscall 137 /* Syscall for Andrew File System */
|
|
#define __NR_setfsuid 138
|
|
#define __NR_setfsgid 139
|
|
#define __NR__llseek 140
|
|
#define __NR_getdents 141
|
|
#define __NR__newselect 142
|
|
#define __NR_flock 143
|
|
#define __NR_msync 144
|
|
#define __NR_readv 145
|
|
#define __NR_writev 146
|
|
#define __NR_getsid 147
|
|
#define __NR_fdatasync 148
|
|
#define __NR__sysctl 149
|
|
#define __NR_mlock 150
|
|
#define __NR_munlock 151
|
|
#define __NR_mlockall 152
|
|
#define __NR_munlockall 153
|
|
#define __NR_sched_setparam 154
|
|
#define __NR_sched_getparam 155
|
|
#define __NR_sched_setscheduler 156
|
|
#define __NR_sched_getscheduler 157
|
|
#define __NR_sched_yield 158
|
|
#define __NR_sched_get_priority_max 159
|
|
#define __NR_sched_get_priority_min 160
|
|
#define __NR_sched_rr_get_interval 161
|
|
#define __NR_nanosleep 162
|
|
#define __NR_mremap 163
|
|
#define __NR_setresuid 164
|
|
#define __NR_getresuid 165
|
|
#define __NR_vm86 166
|
|
#define __NR_query_module 167
|
|
#define __NR_poll 168
|
|
#define __NR_nfsservctl 169
|
|
#define __NR_setresgid 170
|
|
#define __NR_getresgid 171
|
|
#define __NR_prctl 172
|
|
#define __NR_rt_sigreturn 173
|
|
#define __NR_rt_sigaction 174
|
|
#define __NR_rt_sigprocmask 175
|
|
#define __NR_rt_sigpending 176
|
|
#define __NR_rt_sigtimedwait 177
|
|
#define __NR_rt_sigqueueinfo 178
|
|
#define __NR_rt_sigsuspend 179
|
|
#define __NR_pread64 180
|
|
#define __NR_pwrite64 181
|
|
#define __NR_chown 182
|
|
#define __NR_getcwd 183
|
|
#define __NR_capget 184
|
|
#define __NR_capset 185
|
|
#define __NR_sigaltstack 186
|
|
#define __NR_sendfile 187
|
|
#define __NR_getpmsg 188 /* some people actually want streams */
|
|
#define __NR_putpmsg 189 /* some people actually want streams */
|
|
#define __NR_vfork 190
|
|
#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */
|
|
#define __NR_mmap2 192
|
|
#define __NR_truncate64 193
|
|
#define __NR_ftruncate64 194
|
|
#define __NR_stat64 195
|
|
#define __NR_lstat64 196
|
|
#define __NR_fstat64 197
|
|
#define __NR_lchown32 198
|
|
#define __NR_getuid32 199
|
|
#define __NR_getgid32 200
|
|
#define __NR_geteuid32 201
|
|
#define __NR_getegid32 202
|
|
#define __NR_setreuid32 203
|
|
#define __NR_setregid32 204
|
|
#define __NR_getgroups32 205
|
|
#define __NR_setgroups32 206
|
|
#define __NR_fchown32 207
|
|
#define __NR_setresuid32 208
|
|
#define __NR_getresuid32 209
|
|
#define __NR_setresgid32 210
|
|
#define __NR_getresgid32 211
|
|
#define __NR_chown32 212
|
|
#define __NR_setuid32 213
|
|
#define __NR_setgid32 214
|
|
#define __NR_setfsuid32 215
|
|
#define __NR_setfsgid32 216
|
|
#define __NR_pivot_root 217
|
|
#define __NR_mincore 218
|
|
#define __NR_madvise 219
|
|
#define __NR_madvise1 219 /* delete when C lib stub is removed */
|
|
#define __NR_getdents64 220
|
|
#define __NR_fcntl64 221
|
|
/* 223 is unused */
|
|
#define __NR_gettid 224
|
|
#define __NR_readahead 225
|
|
#define __NR_setxattr 226
|
|
#define __NR_lsetxattr 227
|
|
#define __NR_fsetxattr 228
|
|
#define __NR_getxattr 229
|
|
#define __NR_lgetxattr 230
|
|
#define __NR_fgetxattr 231
|
|
#define __NR_listxattr 232
|
|
#define __NR_llistxattr 233
|
|
#define __NR_flistxattr 234
|
|
#define __NR_removexattr 235
|
|
#define __NR_lremovexattr 236
|
|
#define __NR_fremovexattr 237
|
|
#define __NR_tkill 238
|
|
#define __NR_sendfile64 239
|
|
#define __NR_futex 240
|
|
#define __NR_sched_setaffinity 241
|
|
#define __NR_sched_getaffinity 242
|
|
#define __NR_set_thread_area 243
|
|
#define __NR_get_thread_area 244
|
|
#define __NR_io_setup 245
|
|
#define __NR_io_destroy 246
|
|
#define __NR_io_getevents 247
|
|
#define __NR_io_submit 248
|
|
#define __NR_io_cancel 249
|
|
#define __NR_fadvise64 250
|
|
/* 251 is available for reuse (was briefly sys_set_zone_reclaim) */
|
|
#define __NR_exit_group 252
|
|
#define __NR_lookup_dcookie 253
|
|
#define __NR_epoll_create 254
|
|
#define __NR_epoll_ctl 255
|
|
#define __NR_epoll_wait 256
|
|
#define __NR_remap_file_pages 257
|
|
#define __NR_set_tid_address 258
|
|
#define __NR_timer_create 259
|
|
#define __NR_timer_settime (__NR_timer_create+1)
|
|
#define __NR_timer_gettime (__NR_timer_create+2)
|
|
#define __NR_timer_getoverrun (__NR_timer_create+3)
|
|
#define __NR_timer_delete (__NR_timer_create+4)
|
|
#define __NR_clock_settime (__NR_timer_create+5)
|
|
#define __NR_clock_gettime (__NR_timer_create+6)
|
|
#define __NR_clock_getres (__NR_timer_create+7)
|
|
#define __NR_clock_nanosleep (__NR_timer_create+8)
|
|
#define __NR_statfs64 268
|
|
#define __NR_fstatfs64 269
|
|
#define __NR_tgkill 270
|
|
#define __NR_utimes 271
|
|
#define __NR_fadvise64_64 272
|
|
#define __NR_vserver 273
|
|
#define __NR_mbind 274
|
|
#define __NR_get_mempolicy 275
|
|
#define __NR_set_mempolicy 276
|
|
#define __NR_mq_open 277
|
|
#define __NR_mq_unlink (__NR_mq_open+1)
|
|
#define __NR_mq_timedsend (__NR_mq_open+2)
|
|
#define __NR_mq_timedreceive (__NR_mq_open+3)
|
|
#define __NR_mq_notify (__NR_mq_open+4)
|
|
#define __NR_mq_getsetattr (__NR_mq_open+5)
|
|
#define __NR_kexec_load 283
|
|
#define __NR_waitid 284
|
|
/* #define __NR_sys_setaltroot 285 */
|
|
#define __NR_add_key 286
|
|
#define __NR_request_key 287
|
|
#define __NR_keyctl 288
|
|
#define __NR_ioprio_set 289
|
|
#define __NR_ioprio_get 290
|
|
#define __NR_inotify_init 291
|
|
#define __NR_inotify_add_watch 292
|
|
#define __NR_inotify_rm_watch 293
|
|
#define __NR_migrate_pages 294
|
|
#define __NR_openat 295
|
|
#define __NR_mkdirat 296
|
|
#define __NR_mknodat 297
|
|
#define __NR_fchownat 298
|
|
#define __NR_futimesat 299
|
|
#define __NR_fstatat64 300
|
|
#define __NR_unlinkat 301
|
|
#define __NR_renameat 302
|
|
#define __NR_linkat 303
|
|
#define __NR_symlinkat 304
|
|
#define __NR_readlinkat 305
|
|
#define __NR_fchmodat 306
|
|
#define __NR_faccessat 307
|
|
#define __NR_pselect6 308
|
|
#define __NR_ppoll 309
|
|
#define __NR_unshare 310
|
|
#define __NR_set_robust_list 311
|
|
#define __NR_get_robust_list 312
|
|
#define __NR_splice 313
|
|
#define __NR_sync_file_range 314
|
|
#define __NR_tee 315
|
|
#define __NR_vmsplice 316
|
|
#define __NR_move_pages 317
|
|
#define __NR_getcpu 318
|
|
#define __NR_epoll_pwait 319
|
|
#define __NR_utimensat 320
|
|
#define __NR_signalfd 321
|
|
#define __NR_timerfd_create 322
|
|
#define __NR_eventfd 323
|
|
#define __NR_fallocate 324
|
|
#define __NR_timerfd_settime 325
|
|
#define __NR_timerfd_gettime 326
|
|
#define __NR_signalfd4 327
|
|
#define __NR_eventfd2 328
|
|
#define __NR_epoll_create1 329
|
|
#define __NR_dup3 330
|
|
#define __NR_pipe2 331
|
|
#define __NR_inotify_init1 332
|
|
#define __NR_preadv 333
|
|
#define __NR_pwritev 334
|
|
#define __NR_rt_tgsigqueueinfo 335
|
|
#define __NR_perf_event_open 336
|
|
#define __NR_recvmmsg 337
|
|
#define __NR_fanotify_init 338
|
|
#define __NR_fanotify_mark 339
|
|
#define __NR_prlimit64 340
|
|
#define __NR_name_to_handle_at 341
|
|
#define __NR_open_by_handle_at 342
|
|
#define __NR_clock_adjtime 343
|
|
#define __NR_syncfs 344
|
|
#define __NR_sendmmsg 345
|
|
#define __NR_setns 346
|
|
#define __NR_process_vm_readv 347
|
|
#define __NR_process_vm_writev 348
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#define NR_syscalls 349
|
|
|
|
#define __ARCH_WANT_IPC_PARSE_VERSION
|
|
#define __ARCH_WANT_OLD_READDIR
|
|
#define __ARCH_WANT_OLD_STAT
|
|
#define __ARCH_WANT_STAT64
|
|
#define __ARCH_WANT_SYS_ALARM
|
|
#define __ARCH_WANT_SYS_GETHOSTNAME
|
|
#define __ARCH_WANT_SYS_IPC
|
|
#define __ARCH_WANT_SYS_PAUSE
|
|
#define __ARCH_WANT_SYS_SGETMASK
|
|
#define __ARCH_WANT_SYS_SIGNAL
|
|
#define __ARCH_WANT_SYS_TIME
|
|
#define __ARCH_WANT_SYS_UTIME
|
|
#define __ARCH_WANT_SYS_WAITPID
|
|
#define __ARCH_WANT_SYS_SOCKETCALL
|
|
#define __ARCH_WANT_SYS_FADVISE64
|
|
#define __ARCH_WANT_SYS_GETPGRP
|
|
#define __ARCH_WANT_SYS_LLSEEK
|
|
#define __ARCH_WANT_SYS_NICE
|
|
#define __ARCH_WANT_SYS_OLD_GETRLIMIT
|
|
#define __ARCH_WANT_SYS_OLD_UNAME
|
|
#define __ARCH_WANT_SYS_OLD_MMAP
|
|
#define __ARCH_WANT_SYS_OLD_SELECT
|
|
#define __ARCH_WANT_SYS_OLDUMOUNT
|
|
#define __ARCH_WANT_SYS_SIGPENDING
|
|
#define __ARCH_WANT_SYS_SIGPROCMASK
|
|
#define __ARCH_WANT_SYS_RT_SIGACTION
|
|
#define __ARCH_WANT_SYS_RT_SIGSUSPEND
|
|
|
|
/*
|
|
* "Conditional" syscalls
|
|
*
|
|
* What we want is __attribute__((weak,alias("sys_ni_syscall"))),
|
|
* but it doesn't work on all toolchains, so we just do it by hand
|
|
*/
|
|
#ifndef cond_syscall
|
|
#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
|
|
#endif
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif /* _ASM_X86_UNISTD_32_H */
|