2011-11-11 23:55:49 +00:00
|
|
|
#
|
|
|
|
|
# 64-bit system call numbers and entry vectors
|
|
|
|
|
#
|
|
|
|
|
# The format is:
|
|
|
|
|
# <number> <abi> <name> <entry point>
|
|
|
|
|
#
|
2018-04-09 10:51:44 +00:00
|
|
|
# The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls
|
|
|
|
|
#
|
2012-02-14 22:18:50 +00:00
|
|
|
# The abi is "common", "64" or "x32" for this file.
|
2011-11-11 23:55:49 +00:00
|
|
|
#
|
2020-03-13 19:51:38 +00:00
|
|
|
0 common read sys_read
|
|
|
|
|
1 common write sys_write
|
|
|
|
|
2 common open sys_open
|
|
|
|
|
3 common close sys_close
|
|
|
|
|
4 common stat sys_newstat
|
|
|
|
|
5 common fstat sys_newfstat
|
|
|
|
|
6 common lstat sys_newlstat
|
|
|
|
|
7 common poll sys_poll
|
|
|
|
|
8 common lseek sys_lseek
|
|
|
|
|
9 common mmap sys_mmap
|
|
|
|
|
10 common mprotect sys_mprotect
|
|
|
|
|
11 common munmap sys_munmap
|
|
|
|
|
12 common brk sys_brk
|
|
|
|
|
13 64 rt_sigaction sys_rt_sigaction
|
|
|
|
|
14 common rt_sigprocmask sys_rt_sigprocmask
|
|
|
|
|
15 64 rt_sigreturn sys_rt_sigreturn
|
|
|
|
|
16 64 ioctl sys_ioctl
|
|
|
|
|
17 common pread64 sys_pread64
|
|
|
|
|
18 common pwrite64 sys_pwrite64
|
|
|
|
|
19 64 readv sys_readv
|
|
|
|
|
20 64 writev sys_writev
|
|
|
|
|
21 common access sys_access
|
|
|
|
|
22 common pipe sys_pipe
|
|
|
|
|
23 common select sys_select
|
|
|
|
|
24 common sched_yield sys_sched_yield
|
|
|
|
|
25 common mremap sys_mremap
|
|
|
|
|
26 common msync sys_msync
|
|
|
|
|
27 common mincore sys_mincore
|
|
|
|
|
28 common madvise sys_madvise
|
|
|
|
|
29 common shmget sys_shmget
|
|
|
|
|
30 common shmat sys_shmat
|
|
|
|
|
31 common shmctl sys_shmctl
|
|
|
|
|
32 common dup sys_dup
|
|
|
|
|
33 common dup2 sys_dup2
|
|
|
|
|
34 common pause sys_pause
|
|
|
|
|
35 common nanosleep sys_nanosleep
|
|
|
|
|
36 common getitimer sys_getitimer
|
|
|
|
|
37 common alarm sys_alarm
|
|
|
|
|
38 common setitimer sys_setitimer
|
|
|
|
|
39 common getpid sys_getpid
|
|
|
|
|
40 common sendfile sys_sendfile64
|
|
|
|
|
41 common socket sys_socket
|
|
|
|
|
42 common connect sys_connect
|
|
|
|
|
43 common accept sys_accept
|
|
|
|
|
44 common sendto sys_sendto
|
|
|
|
|
45 64 recvfrom sys_recvfrom
|
|
|
|
|
46 64 sendmsg sys_sendmsg
|
|
|
|
|
47 64 recvmsg sys_recvmsg
|
|
|
|
|
48 common shutdown sys_shutdown
|
|
|
|
|
49 common bind sys_bind
|
|
|
|
|
50 common listen sys_listen
|
|
|
|
|
51 common getsockname sys_getsockname
|
|
|
|
|
52 common getpeername sys_getpeername
|
|
|
|
|
53 common socketpair sys_socketpair
|
|
|
|
|
54 64 setsockopt sys_setsockopt
|
|
|
|
|
55 64 getsockopt sys_getsockopt
|
|
|
|
|
56 common clone sys_clone
|
|
|
|
|
57 common fork sys_fork
|
|
|
|
|
58 common vfork sys_vfork
|
|
|
|
|
59 64 execve sys_execve
|
|
|
|
|
60 common exit sys_exit
|
|
|
|
|
61 common wait4 sys_wait4
|
|
|
|
|
62 common kill sys_kill
|
|
|
|
|
63 common uname sys_newuname
|
|
|
|
|
64 common semget sys_semget
|
|
|
|
|
65 common semop sys_semop
|
|
|
|
|
66 common semctl sys_semctl
|
|
|
|
|
67 common shmdt sys_shmdt
|
|
|
|
|
68 common msgget sys_msgget
|
|
|
|
|
69 common msgsnd sys_msgsnd
|
|
|
|
|
70 common msgrcv sys_msgrcv
|
|
|
|
|
71 common msgctl sys_msgctl
|
|
|
|
|
72 common fcntl sys_fcntl
|
|
|
|
|
73 common flock sys_flock
|
|
|
|
|
74 common fsync sys_fsync
|
|
|
|
|
75 common fdatasync sys_fdatasync
|
|
|
|
|
76 common truncate sys_truncate
|
|
|
|
|
77 common ftruncate sys_ftruncate
|
|
|
|
|
78 common getdents sys_getdents
|
|
|
|
|
79 common getcwd sys_getcwd
|
|
|
|
|
80 common chdir sys_chdir
|
|
|
|
|
81 common fchdir sys_fchdir
|
|
|
|
|
82 common rename sys_rename
|
|
|
|
|
83 common mkdir sys_mkdir
|
|
|
|
|
84 common rmdir sys_rmdir
|
|
|
|
|
85 common creat sys_creat
|
|
|
|
|
86 common link sys_link
|
|
|
|
|
87 common unlink sys_unlink
|
|
|
|
|
88 common symlink sys_symlink
|
|
|
|
|
89 common readlink sys_readlink
|
|
|
|
|
90 common chmod sys_chmod
|
|
|
|
|
91 common fchmod sys_fchmod
|
|
|
|
|
92 common chown sys_chown
|
|
|
|
|
93 common fchown sys_fchown
|
|
|
|
|
94 common lchown sys_lchown
|
|
|
|
|
95 common umask sys_umask
|
|
|
|
|
96 common gettimeofday sys_gettimeofday
|
|
|
|
|
97 common getrlimit sys_getrlimit
|
|
|
|
|
98 common getrusage sys_getrusage
|
|
|
|
|
99 common sysinfo sys_sysinfo
|
|
|
|
|
100 common times sys_times
|
|
|
|
|
101 64 ptrace sys_ptrace
|
|
|
|
|
102 common getuid sys_getuid
|
|
|
|
|
103 common syslog sys_syslog
|
|
|
|
|
104 common getgid sys_getgid
|
|
|
|
|
105 common setuid sys_setuid
|
|
|
|
|
106 common setgid sys_setgid
|
|
|
|
|
107 common geteuid sys_geteuid
|
|
|
|
|
108 common getegid sys_getegid
|
|
|
|
|
109 common setpgid sys_setpgid
|
|
|
|
|
110 common getppid sys_getppid
|
|
|
|
|
111 common getpgrp sys_getpgrp
|
|
|
|
|
112 common setsid sys_setsid
|
|
|
|
|
113 common setreuid sys_setreuid
|
|
|
|
|
114 common setregid sys_setregid
|
|
|
|
|
115 common getgroups sys_getgroups
|
|
|
|
|
116 common setgroups sys_setgroups
|
|
|
|
|
117 common setresuid sys_setresuid
|
|
|
|
|
118 common getresuid sys_getresuid
|
|
|
|
|
119 common setresgid sys_setresgid
|
|
|
|
|
120 common getresgid sys_getresgid
|
|
|
|
|
121 common getpgid sys_getpgid
|
|
|
|
|
122 common setfsuid sys_setfsuid
|
|
|
|
|
123 common setfsgid sys_setfsgid
|
|
|
|
|
124 common getsid sys_getsid
|
|
|
|
|
125 common capget sys_capget
|
|
|
|
|
126 common capset sys_capset
|
|
|
|
|
127 64 rt_sigpending sys_rt_sigpending
|
|
|
|
|
128 64 rt_sigtimedwait sys_rt_sigtimedwait
|
|
|
|
|
129 64 rt_sigqueueinfo sys_rt_sigqueueinfo
|
|
|
|
|
130 common rt_sigsuspend sys_rt_sigsuspend
|
|
|
|
|
131 64 sigaltstack sys_sigaltstack
|
|
|
|
|
132 common utime sys_utime
|
|
|
|
|
133 common mknod sys_mknod
|
2011-11-11 23:55:49 +00:00
|
|
|
134 64 uselib
|
2020-03-13 19:51:38 +00:00
|
|
|
135 common personality sys_personality
|
|
|
|
|
136 common ustat sys_ustat
|
|
|
|
|
137 common statfs sys_statfs
|
|
|
|
|
138 common fstatfs sys_fstatfs
|
|
|
|
|
139 common sysfs sys_sysfs
|
|
|
|
|
140 common getpriority sys_getpriority
|
|
|
|
|
141 common setpriority sys_setpriority
|
|
|
|
|
142 common sched_setparam sys_sched_setparam
|
|
|
|
|
143 common sched_getparam sys_sched_getparam
|
|
|
|
|
144 common sched_setscheduler sys_sched_setscheduler
|
|
|
|
|
145 common sched_getscheduler sys_sched_getscheduler
|
|
|
|
|
146 common sched_get_priority_max sys_sched_get_priority_max
|
|
|
|
|
147 common sched_get_priority_min sys_sched_get_priority_min
|
|
|
|
|
148 common sched_rr_get_interval sys_sched_rr_get_interval
|
|
|
|
|
149 common mlock sys_mlock
|
|
|
|
|
150 common munlock sys_munlock
|
|
|
|
|
151 common mlockall sys_mlockall
|
|
|
|
|
152 common munlockall sys_munlockall
|
|
|
|
|
153 common vhangup sys_vhangup
|
|
|
|
|
154 common modify_ldt sys_modify_ldt
|
|
|
|
|
155 common pivot_root sys_pivot_root
|
2020-08-15 00:31:07 +00:00
|
|
|
156 64 _sysctl sys_ni_syscall
|
2020-03-13 19:51:38 +00:00
|
|
|
157 common prctl sys_prctl
|
|
|
|
|
158 common arch_prctl sys_arch_prctl
|
|
|
|
|
159 common adjtimex sys_adjtimex
|
|
|
|
|
160 common setrlimit sys_setrlimit
|
|
|
|
|
161 common chroot sys_chroot
|
|
|
|
|
162 common sync sys_sync
|
|
|
|
|
163 common acct sys_acct
|
|
|
|
|
164 common settimeofday sys_settimeofday
|
|
|
|
|
165 common mount sys_mount
|
|
|
|
|
166 common umount2 sys_umount
|
|
|
|
|
167 common swapon sys_swapon
|
|
|
|
|
168 common swapoff sys_swapoff
|
|
|
|
|
169 common reboot sys_reboot
|
|
|
|
|
170 common sethostname sys_sethostname
|
|
|
|
|
171 common setdomainname sys_setdomainname
|
|
|
|
|
172 common iopl sys_iopl
|
|
|
|
|
173 common ioperm sys_ioperm
|
2011-11-11 23:55:49 +00:00
|
|
|
174 64 create_module
|
2020-03-13 19:51:38 +00:00
|
|
|
175 common init_module sys_init_module
|
|
|
|
|
176 common delete_module sys_delete_module
|
2011-11-11 23:55:49 +00:00
|
|
|
177 64 get_kernel_syms
|
|
|
|
|
178 64 query_module
|
2020-03-13 19:51:38 +00:00
|
|
|
179 common quotactl sys_quotactl
|
2011-11-11 23:55:49 +00:00
|
|
|
180 64 nfsservctl
|
2012-02-14 22:18:50 +00:00
|
|
|
181 common getpmsg
|
|
|
|
|
182 common putpmsg
|
|
|
|
|
183 common afs_syscall
|
|
|
|
|
184 common tuxcall
|
|
|
|
|
185 common security
|
2020-03-13 19:51:38 +00:00
|
|
|
186 common gettid sys_gettid
|
|
|
|
|
187 common readahead sys_readahead
|
|
|
|
|
188 common setxattr sys_setxattr
|
|
|
|
|
189 common lsetxattr sys_lsetxattr
|
|
|
|
|
190 common fsetxattr sys_fsetxattr
|
|
|
|
|
191 common getxattr sys_getxattr
|
|
|
|
|
192 common lgetxattr sys_lgetxattr
|
|
|
|
|
193 common fgetxattr sys_fgetxattr
|
|
|
|
|
194 common listxattr sys_listxattr
|
|
|
|
|
195 common llistxattr sys_llistxattr
|
|
|
|
|
196 common flistxattr sys_flistxattr
|
|
|
|
|
197 common removexattr sys_removexattr
|
|
|
|
|
198 common lremovexattr sys_lremovexattr
|
|
|
|
|
199 common fremovexattr sys_fremovexattr
|
|
|
|
|
200 common tkill sys_tkill
|
|
|
|
|
201 common time sys_time
|
|
|
|
|
202 common futex sys_futex
|
|
|
|
|
203 common sched_setaffinity sys_sched_setaffinity
|
|
|
|
|
204 common sched_getaffinity sys_sched_getaffinity
|
2011-11-11 23:55:49 +00:00
|
|
|
205 64 set_thread_area
|
2020-03-13 19:51:38 +00:00
|
|
|
206 64 io_setup sys_io_setup
|
|
|
|
|
207 common io_destroy sys_io_destroy
|
|
|
|
|
208 common io_getevents sys_io_getevents
|
|
|
|
|
209 64 io_submit sys_io_submit
|
|
|
|
|
210 common io_cancel sys_io_cancel
|
2011-11-11 23:55:49 +00:00
|
|
|
211 64 get_thread_area
|
2023-07-10 18:51:24 +00:00
|
|
|
212 common lookup_dcookie
|
2020-03-13 19:51:38 +00:00
|
|
|
213 common epoll_create sys_epoll_create
|
2011-11-11 23:55:49 +00:00
|
|
|
214 64 epoll_ctl_old
|
|
|
|
|
215 64 epoll_wait_old
|
2020-03-13 19:51:38 +00:00
|
|
|
216 common remap_file_pages sys_remap_file_pages
|
|
|
|
|
217 common getdents64 sys_getdents64
|
|
|
|
|
218 common set_tid_address sys_set_tid_address
|
|
|
|
|
219 common restart_syscall sys_restart_syscall
|
|
|
|
|
220 common semtimedop sys_semtimedop
|
|
|
|
|
221 common fadvise64 sys_fadvise64
|
|
|
|
|
222 64 timer_create sys_timer_create
|
|
|
|
|
223 common timer_settime sys_timer_settime
|
|
|
|
|
224 common timer_gettime sys_timer_gettime
|
|
|
|
|
225 common timer_getoverrun sys_timer_getoverrun
|
|
|
|
|
226 common timer_delete sys_timer_delete
|
|
|
|
|
227 common clock_settime sys_clock_settime
|
|
|
|
|
228 common clock_gettime sys_clock_gettime
|
|
|
|
|
229 common clock_getres sys_clock_getres
|
|
|
|
|
230 common clock_nanosleep sys_clock_nanosleep
|
|
|
|
|
231 common exit_group sys_exit_group
|
|
|
|
|
232 common epoll_wait sys_epoll_wait
|
|
|
|
|
233 common epoll_ctl sys_epoll_ctl
|
|
|
|
|
234 common tgkill sys_tgkill
|
|
|
|
|
235 common utimes sys_utimes
|
2011-11-11 23:55:49 +00:00
|
|
|
236 64 vserver
|
2020-03-13 19:51:38 +00:00
|
|
|
237 common mbind sys_mbind
|
|
|
|
|
238 common set_mempolicy sys_set_mempolicy
|
|
|
|
|
239 common get_mempolicy sys_get_mempolicy
|
|
|
|
|
240 common mq_open sys_mq_open
|
|
|
|
|
241 common mq_unlink sys_mq_unlink
|
|
|
|
|
242 common mq_timedsend sys_mq_timedsend
|
|
|
|
|
243 common mq_timedreceive sys_mq_timedreceive
|
|
|
|
|
244 64 mq_notify sys_mq_notify
|
|
|
|
|
245 common mq_getsetattr sys_mq_getsetattr
|
|
|
|
|
246 64 kexec_load sys_kexec_load
|
|
|
|
|
247 64 waitid sys_waitid
|
|
|
|
|
248 common add_key sys_add_key
|
|
|
|
|
249 common request_key sys_request_key
|
|
|
|
|
250 common keyctl sys_keyctl
|
|
|
|
|
251 common ioprio_set sys_ioprio_set
|
|
|
|
|
252 common ioprio_get sys_ioprio_get
|
|
|
|
|
253 common inotify_init sys_inotify_init
|
|
|
|
|
254 common inotify_add_watch sys_inotify_add_watch
|
|
|
|
|
255 common inotify_rm_watch sys_inotify_rm_watch
|
|
|
|
|
256 common migrate_pages sys_migrate_pages
|
|
|
|
|
257 common openat sys_openat
|
|
|
|
|
258 common mkdirat sys_mkdirat
|
|
|
|
|
259 common mknodat sys_mknodat
|
|
|
|
|
260 common fchownat sys_fchownat
|
|
|
|
|
261 common futimesat sys_futimesat
|
|
|
|
|
262 common newfstatat sys_newfstatat
|
|
|
|
|
263 common unlinkat sys_unlinkat
|
|
|
|
|
264 common renameat sys_renameat
|
|
|
|
|
265 common linkat sys_linkat
|
|
|
|
|
266 common symlinkat sys_symlinkat
|
|
|
|
|
267 common readlinkat sys_readlinkat
|
|
|
|
|
268 common fchmodat sys_fchmodat
|
|
|
|
|
269 common faccessat sys_faccessat
|
|
|
|
|
270 common pselect6 sys_pselect6
|
|
|
|
|
271 common ppoll sys_ppoll
|
|
|
|
|
272 common unshare sys_unshare
|
|
|
|
|
273 64 set_robust_list sys_set_robust_list
|
|
|
|
|
274 64 get_robust_list sys_get_robust_list
|
|
|
|
|
275 common splice sys_splice
|
|
|
|
|
276 common tee sys_tee
|
|
|
|
|
277 common sync_file_range sys_sync_file_range
|
|
|
|
|
278 64 vmsplice sys_vmsplice
|
|
|
|
|
279 64 move_pages sys_move_pages
|
|
|
|
|
280 common utimensat sys_utimensat
|
|
|
|
|
281 common epoll_pwait sys_epoll_pwait
|
|
|
|
|
282 common signalfd sys_signalfd
|
|
|
|
|
283 common timerfd_create sys_timerfd_create
|
|
|
|
|
284 common eventfd sys_eventfd
|
|
|
|
|
285 common fallocate sys_fallocate
|
|
|
|
|
286 common timerfd_settime sys_timerfd_settime
|
|
|
|
|
287 common timerfd_gettime sys_timerfd_gettime
|
|
|
|
|
288 common accept4 sys_accept4
|
|
|
|
|
289 common signalfd4 sys_signalfd4
|
|
|
|
|
290 common eventfd2 sys_eventfd2
|
|
|
|
|
291 common epoll_create1 sys_epoll_create1
|
|
|
|
|
292 common dup3 sys_dup3
|
|
|
|
|
293 common pipe2 sys_pipe2
|
|
|
|
|
294 common inotify_init1 sys_inotify_init1
|
|
|
|
|
295 64 preadv sys_preadv
|
|
|
|
|
296 64 pwritev sys_pwritev
|
|
|
|
|
297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo
|
|
|
|
|
298 common perf_event_open sys_perf_event_open
|
|
|
|
|
299 64 recvmmsg sys_recvmmsg
|
|
|
|
|
300 common fanotify_init sys_fanotify_init
|
|
|
|
|
301 common fanotify_mark sys_fanotify_mark
|
|
|
|
|
302 common prlimit64 sys_prlimit64
|
|
|
|
|
303 common name_to_handle_at sys_name_to_handle_at
|
|
|
|
|
304 common open_by_handle_at sys_open_by_handle_at
|
|
|
|
|
305 common clock_adjtime sys_clock_adjtime
|
|
|
|
|
306 common syncfs sys_syncfs
|
|
|
|
|
307 64 sendmmsg sys_sendmmsg
|
|
|
|
|
308 common setns sys_setns
|
|
|
|
|
309 common getcpu sys_getcpu
|
|
|
|
|
310 64 process_vm_readv sys_process_vm_readv
|
|
|
|
|
311 64 process_vm_writev sys_process_vm_writev
|
|
|
|
|
312 common kcmp sys_kcmp
|
|
|
|
|
313 common finit_module sys_finit_module
|
|
|
|
|
314 common sched_setattr sys_sched_setattr
|
|
|
|
|
315 common sched_getattr sys_sched_getattr
|
|
|
|
|
316 common renameat2 sys_renameat2
|
|
|
|
|
317 common seccomp sys_seccomp
|
|
|
|
|
318 common getrandom sys_getrandom
|
|
|
|
|
319 common memfd_create sys_memfd_create
|
|
|
|
|
320 common kexec_file_load sys_kexec_file_load
|
|
|
|
|
321 common bpf sys_bpf
|
|
|
|
|
322 64 execveat sys_execveat
|
|
|
|
|
323 common userfaultfd sys_userfaultfd
|
|
|
|
|
324 common membarrier sys_membarrier
|
|
|
|
|
325 common mlock2 sys_mlock2
|
|
|
|
|
326 common copy_file_range sys_copy_file_range
|
|
|
|
|
327 64 preadv2 sys_preadv2
|
|
|
|
|
328 64 pwritev2 sys_pwritev2
|
|
|
|
|
329 common pkey_mprotect sys_pkey_mprotect
|
|
|
|
|
330 common pkey_alloc sys_pkey_alloc
|
|
|
|
|
331 common pkey_free sys_pkey_free
|
|
|
|
|
332 common statx sys_statx
|
|
|
|
|
333 common io_pgetevents sys_io_pgetevents
|
|
|
|
|
334 common rseq sys_rseq
|
2018-12-31 13:38:26 +00:00
|
|
|
# don't use numbers 387 through 423, add new calls after the last
|
|
|
|
|
# 'common' entry
|
2020-03-13 19:51:38 +00:00
|
|
|
424 common pidfd_send_signal sys_pidfd_send_signal
|
|
|
|
|
425 common io_uring_setup sys_io_uring_setup
|
|
|
|
|
426 common io_uring_enter sys_io_uring_enter
|
|
|
|
|
427 common io_uring_register sys_io_uring_register
|
|
|
|
|
428 common open_tree sys_open_tree
|
|
|
|
|
429 common move_mount sys_move_mount
|
|
|
|
|
430 common fsopen sys_fsopen
|
|
|
|
|
431 common fsconfig sys_fsconfig
|
|
|
|
|
432 common fsmount sys_fsmount
|
|
|
|
|
433 common fspick sys_fspick
|
|
|
|
|
434 common pidfd_open sys_pidfd_open
|
|
|
|
|
435 common clone3 sys_clone3
|
2019-05-24 09:31:44 +00:00
|
|
|
436 common close_range sys_close_range
|
2020-03-13 19:51:38 +00:00
|
|
|
437 common openat2 sys_openat2
|
|
|
|
|
438 common pidfd_getfd sys_pidfd_getfd
|
2020-05-14 14:44:25 +00:00
|
|
|
439 common faccessat2 sys_faccessat2
|
mm/madvise: introduce process_madvise() syscall: an external memory hinting API
There is usecase that System Management Software(SMS) want to give a
memory hint like MADV_[COLD|PAGEEOUT] to other processes and in the
case of Android, it is the ActivityManagerService.
The information required to make the reclaim decision is not known to the
app. Instead, it is known to the centralized userspace
daemon(ActivityManagerService), and that daemon must be able to initiate
reclaim on its own without any app involvement.
To solve the issue, this patch introduces a new syscall
process_madvise(2). It uses pidfd of an external process to give the
hint. It also supports vector address range because Android app has
thousands of vmas due to zygote so it's totally waste of CPU and power if
we should call the syscall one by one for each vma.(With testing 2000-vma
syscall vs 1-vector syscall, it showed 15% performance improvement. I
think it would be bigger in real practice because the testing ran very
cache friendly environment).
Another potential use case for the vector range is to amortize the cost
ofTLB shootdowns for multiple ranges when using MADV_DONTNEED; this could
benefit users like TCP receive zerocopy and malloc implementations. In
future, we could find more usecases for other advises so let's make it
happens as API since we introduce a new syscall at this moment. With
that, existing madvise(2) user could replace it with process_madvise(2)
with their own pid if they want to have batch address ranges support
feature.
ince it could affect other process's address range, only privileged
process(PTRACE_MODE_ATTACH_FSCREDS) or something else(e.g., being the same
UID) gives it the right to ptrace the process could use it successfully.
The flag argument is reserved for future use if we need to extend the API.
I think supporting all hints madvise has/will supported/support to
process_madvise is rather risky. Because we are not sure all hints make
sense from external process and implementation for the hint may rely on
the caller being in the current context so it could be error-prone. Thus,
I just limited hints as MADV_[COLD|PAGEOUT] in this patch.
If someone want to add other hints, we could hear the usecase and review
it for each hint. It's safer for maintenance rather than introducing a
buggy syscall but hard to fix it later.
So finally, the API is as follows,
ssize_t process_madvise(int pidfd, const struct iovec *iovec,
unsigned long vlen, int advice, unsigned int flags);
DESCRIPTION
The process_madvise() system call is used to give advice or directions
to the kernel about the address ranges from external process as well as
local process. It provides the advice to address ranges of process
described by iovec and vlen. The goal of such advice is to improve
system or application performance.
The pidfd selects the process referred to by the PID file descriptor
specified in pidfd. (See pidofd_open(2) for further information)
The pointer iovec points to an array of iovec structures, defined in
<sys/uio.h> as:
struct iovec {
void *iov_base; /* starting address */
size_t iov_len; /* number of bytes to be advised */
};
The iovec describes address ranges beginning at address(iov_base)
and with size length of bytes(iov_len).
The vlen represents the number of elements in iovec.
The advice is indicated in the advice argument, which is one of the
following at this moment if the target process specified by pidfd is
external.
MADV_COLD
MADV_PAGEOUT
Permission to provide a hint to external process is governed by a
ptrace access mode PTRACE_MODE_ATTACH_FSCREDS check; see ptrace(2).
The process_madvise supports every advice madvise(2) has if target
process is in same thread group with calling process so user could
use process_madvise(2) to extend existing madvise(2) to support
vector address ranges.
RETURN VALUE
On success, process_madvise() returns the number of bytes advised.
This return value may be less than the total number of requested
bytes, if an error occurred. The caller should check return value
to determine whether a partial advice occurred.
FAQ:
Q.1 - Why does any external entity have better knowledge?
Quote from Sandeep
"For Android, every application (including the special SystemServer)
are forked from Zygote. The reason of course is to share as many
libraries and classes between the two as possible to benefit from the
preloading during boot.
After applications start, (almost) all of the APIs end up calling into
this SystemServer process over IPC (binder) and back to the
application.
In a fully running system, the SystemServer monitors every single
process periodically to calculate their PSS / RSS and also decides
which process is "important" to the user for interactivity.
So, because of how these processes start _and_ the fact that the
SystemServer is looping to monitor each process, it does tend to *know*
which address range of the application is not used / useful.
Besides, we can never rely on applications to clean things up
themselves. We've had the "hey app1, the system is low on memory,
please trim your memory usage down" notifications for a long time[1].
They rely on applications honoring the broadcasts and very few do.
So, if we want to avoid the inevitable killing of the application and
restarting it, some way to be able to tell the OS about unimportant
memory in these applications will be useful.
- ssp
Q.2 - How to guarantee the race(i.e., object validation) between when
giving a hint from an external process and get the hint from the target
process?
process_madvise operates on the target process's address space as it
exists at the instant that process_madvise is called. If the space
target process can run between the time the process_madvise process
inspects the target process address space and the time that
process_madvise is actually called, process_madvise may operate on
memory regions that the calling process does not expect. It's the
responsibility of the process calling process_madvise to close this
race condition. For example, the calling process can suspend the
target process with ptrace, SIGSTOP, or the freezer cgroup so that it
doesn't have an opportunity to change its own address space before
process_madvise is called. Another option is to operate on memory
regions that the caller knows a priori will be unchanged in the target
process. Yet another option is to accept the race for certain
process_madvise calls after reasoning that mistargeting will do no
harm. The suggested API itself does not provide synchronization. It
also apply other APIs like move_pages, process_vm_write.
The race isn't really a problem though. Why is it so wrong to require
that callers do their own synchronization in some manner? Nobody
objects to write(2) merely because it's possible for two processes to
open the same file and clobber each other's writes --- instead, we tell
people to use flock or something. Think about mmap. It never
guarantees newly allocated address space is still valid when the user
tries to access it because other threads could unmap the memory right
before. That's where we need synchronization by using other API or
design from userside. It shouldn't be part of API itself. If someone
needs more fine-grained synchronization rather than process level,
there were two ideas suggested - cookie[2] and anon-fd[3]. Both are
applicable via using last reserved argument of the API but I don't
think it's necessary right now since we have already ways to prevent
the race so don't want to add additional complexity with more
fine-grained optimization model.
To make the API extend, it reserved an unsigned long as last argument
so we could support it in future if someone really needs it.
Q.3 - Why doesn't ptrace work?
Injecting an madvise in the target process using ptrace would not work
for us because such injected madvise would have to be executed by the
target process, which means that process would have to be runnable and
that creates the risk of the abovementioned race and hinting a wrong
VMA. Furthermore, we want to act the hint in caller's context, not the
callee's, because the callee is usually limited in cpuset/cgroups or
even freezed state so they can't act by themselves quick enough, which
causes more thrashing/kill. It doesn't work if the target process are
ptraced(e.g., strace, debugger, minidump) because a process can have at
most one ptracer.
[1] https://developer.android.com/topic/performance/memory"
[2] process_getinfo for getting the cookie which is updated whenever
vma of process address layout are changed - Daniel Colascione -
https://lore.kernel.org/lkml/20190520035254.57579-1-minchan@kernel.org/T/#m7694416fd179b2066a2c62b5b139b14e3894e224
[3] anonymous fd which is used for the object(i.e., address range)
validation - Michal Hocko -
https://lore.kernel.org/lkml/20200120112722.GY18451@dhcp22.suse.cz/
[minchan@kernel.org: fix process_madvise build break for arm64]
Link: http://lkml.kernel.org/r/20200303145756.GA219683@google.com
[minchan@kernel.org: fix build error for mips of process_madvise]
Link: http://lkml.kernel.org/r/20200508052517.GA197378@google.com
[akpm@linux-foundation.org: fix patch ordering issue]
[akpm@linux-foundation.org: fix arm64 whoops]
[minchan@kernel.org: make process_madvise() vlen arg have type size_t, per Florian]
[akpm@linux-foundation.org: fix i386 build]
[sfr@canb.auug.org.au: fix syscall numbering]
Link: https://lkml.kernel.org/r/20200905142639.49fc3f1a@canb.auug.org.au
[sfr@canb.auug.org.au: madvise.c needs compat.h]
Link: https://lkml.kernel.org/r/20200908204547.285646b4@canb.auug.org.au
[minchan@kernel.org: fix mips build]
Link: https://lkml.kernel.org/r/20200909173655.GC2435453@google.com
[yuehaibing@huawei.com: remove duplicate header which is included twice]
Link: https://lkml.kernel.org/r/20200915121550.30584-1-yuehaibing@huawei.com
[minchan@kernel.org: do not use helper functions for process_madvise]
Link: https://lkml.kernel.org/r/20200921175539.GB387368@google.com
[akpm@linux-foundation.org: pidfd_get_pid() gained an argument]
[sfr@canb.auug.org.au: fix up for "iov_iter: transparently handle compat iovecs in import_iovec"]
Link: https://lkml.kernel.org/r/20200928212542.468e1fef@canb.auug.org.au
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <christian@brauner.io>
Cc: Daniel Colascione <dancol@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Dias <joaodias@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: SeongJae Park <sj38.park@gmail.com>
Cc: SeongJae Park <sjpark@amazon.de>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sonny Rao <sonnyrao@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Florian Weimer <fw@deneb.enyo.de>
Cc: <linux-man@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200302193630.68771-3-minchan@kernel.org
Link: http://lkml.kernel.org/r/20200508183320.GA125527@google.com
Link: http://lkml.kernel.org/r/20200622192900.22757-4-minchan@kernel.org
Link: https://lkml.kernel.org/r/20200901000633.1920247-4-minchan@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-17 23:14:59 +00:00
|
|
|
440 common process_madvise sys_process_madvise
|
2020-12-18 22:05:41 +00:00
|
|
|
441 common epoll_pwait2 sys_epoll_pwait2
|
fs: add mount_setattr()
This implements the missing mount_setattr() syscall. While the new mount
api allows to change the properties of a superblock there is currently
no way to change the properties of a mount or a mount tree using file
descriptors which the new mount api is based on. In addition the old
mount api has the restriction that mount options cannot be applied
recursively. This hasn't changed since changing mount options on a
per-mount basis was implemented in [1] and has been a frequent request
not just for convenience but also for security reasons. The legacy
mount syscall is unable to accommodate this behavior without introducing
a whole new set of flags because MS_REC | MS_REMOUNT | MS_BIND |
MS_RDONLY | MS_NOEXEC | [...] only apply the mount option to the topmost
mount. Changing MS_REC to apply to the whole mount tree would mean
introducing a significant uapi change and would likely cause significant
regressions.
The new mount_setattr() syscall allows to recursively clear and set
mount options in one shot. Multiple calls to change mount options
requesting the same changes are idempotent:
int mount_setattr(int dfd, const char *path, unsigned flags,
struct mount_attr *uattr, size_t usize);
Flags to modify path resolution behavior are specified in the @flags
argument. Currently, AT_EMPTY_PATH, AT_RECURSIVE, AT_SYMLINK_NOFOLLOW,
and AT_NO_AUTOMOUNT are supported. If useful, additional lookup flags to
restrict path resolution as introduced with openat2() might be supported
in the future.
The mount_setattr() syscall can be expected to grow over time and is
designed with extensibility in mind. It follows the extensible syscall
pattern we have used with other syscalls such as openat2(), clone3(),
sched_{set,get}attr(), and others.
The set of mount options is passed in the uapi struct mount_attr which
currently has the following layout:
struct mount_attr {
__u64 attr_set;
__u64 attr_clr;
__u64 propagation;
__u64 userns_fd;
};
The @attr_set and @attr_clr members are used to clear and set mount
options. This way a user can e.g. request that a set of flags is to be
raised such as turning mounts readonly by raising MOUNT_ATTR_RDONLY in
@attr_set while at the same time requesting that another set of flags is
to be lowered such as removing noexec from a mount tree by specifying
MOUNT_ATTR_NOEXEC in @attr_clr.
Note, since the MOUNT_ATTR_<atime> values are an enum starting from 0,
not a bitmap, users wanting to transition to a different atime setting
cannot simply specify the atime setting in @attr_set, but must also
specify MOUNT_ATTR__ATIME in the @attr_clr field. So we ensure that
MOUNT_ATTR__ATIME can't be partially set in @attr_clr and that @attr_set
can't have any atime bits set if MOUNT_ATTR__ATIME isn't set in
@attr_clr.
The @propagation field lets callers specify the propagation type of a
mount tree. Propagation is a single property that has four different
settings and as such is not really a flag argument but an enum.
Specifically, it would be unclear what setting and clearing propagation
settings in combination would amount to. The legacy mount() syscall thus
forbids the combination of multiple propagation settings too. The goal
is to keep the semantics of mount propagation somewhat simple as they
are overly complex as it is.
The @userns_fd field lets user specify a user namespace whose idmapping
becomes the idmapping of the mount. This is implemented and explained in
detail in the next patch.
[1]: commit 2e4b7fcd9260 ("[PATCH] r/o bind mounts: honor mount writer counts at remount")
Link: https://lore.kernel.org/r/20210121131959.646623-35-christian.brauner@ubuntu.com
Cc: David Howells <dhowells@redhat.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-api@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:53 +00:00
|
|
|
442 common mount_setattr sys_mount_setattr
|
2021-05-31 16:42:58 +00:00
|
|
|
443 common quotactl_fd sys_quotactl_fd
|
2021-04-22 15:41:19 +00:00
|
|
|
444 common landlock_create_ruleset sys_landlock_create_ruleset
|
|
|
|
|
445 common landlock_add_rule sys_landlock_add_rule
|
|
|
|
|
446 common landlock_restrict_self sys_landlock_restrict_self
|
2021-07-08 01:08:11 +00:00
|
|
|
447 common memfd_secret sys_memfd_secret
|
2021-09-02 22:00:33 +00:00
|
|
|
448 common process_mrelease sys_process_mrelease
|
2021-09-23 17:11:06 +00:00
|
|
|
449 common futex_waitv sys_futex_waitv
|
2022-01-14 22:08:21 +00:00
|
|
|
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
|
cachestat: implement cachestat syscall
There is currently no good way to query the page cache state of large file
sets and directory trees. There is mincore(), but it scales poorly: the
kernel writes out a lot of bitmap data that userspace has to aggregate,
when the user really doesn not care about per-page information in that
case. The user also needs to mmap and unmap each file as it goes along,
which can be quite slow as well.
Some use cases where this information could come in handy:
* Allowing database to decide whether to perform an index scan or
direct table queries based on the in-memory cache state of the
index.
* Visibility into the writeback algorithm, for performance issues
diagnostic.
* Workload-aware writeback pacing: estimating IO fulfilled by page
cache (and IO to be done) within a range of a file, allowing for
more frequent syncing when and where there is IO capacity, and
batching when there is not.
* Computing memory usage of large files/directory trees, analogous to
the du tool for disk usage.
More information about these use cases could be found in the following
thread:
https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/
This patch implements a new syscall that queries cache state of a file and
summarizes the number of cached pages, number of dirty pages, number of
pages marked for writeback, number of (recently) evicted pages, etc. in a
given range. Currently, the syscall is only wired in for x86
architecture.
NAME
cachestat - query the page cache statistics of a file.
SYNOPSIS
#include <sys/mman.h>
struct cachestat_range {
__u64 off;
__u64 len;
};
struct cachestat {
__u64 nr_cache;
__u64 nr_dirty;
__u64 nr_writeback;
__u64 nr_evicted;
__u64 nr_recently_evicted;
};
int cachestat(unsigned int fd, struct cachestat_range *cstat_range,
struct cachestat *cstat, unsigned int flags);
DESCRIPTION
cachestat() queries the number of cached pages, number of dirty
pages, number of pages marked for writeback, number of evicted
pages, number of recently evicted pages, in the bytes range given by
`off` and `len`.
An evicted page is a page that is previously in the page cache but
has been evicted since. A page is recently evicted if its last
eviction was recent enough that its reentry to the cache would
indicate that it is actively being used by the system, and that
there is memory pressure on the system.
These values are returned in a cachestat struct, whose address is
given by the `cstat` argument.
The `off` and `len` arguments must be non-negative integers. If
`len` > 0, the queried range is [`off`, `off` + `len`]. If `len` ==
0, we will query in the range from `off` to the end of the file.
The `flags` argument is unused for now, but is included for future
extensibility. User should pass 0 (i.e no flag specified).
Currently, hugetlbfs is not supported.
Because the status of a page can change after cachestat() checks it
but before it returns to the application, the returned values may
contain stale information.
RETURN VALUE
On success, cachestat returns 0. On error, -1 is returned, and errno
is set to indicate the error.
ERRORS
EFAULT cstat or cstat_args points to an invalid address.
EINVAL invalid flags.
EBADF invalid file descriptor.
EOPNOTSUPP file descriptor is of a hugetlbfs file
[nphamcs@gmail.com: replace rounddown logic with the existing helper]
Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com
Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Brian Foster <bfoster@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
|
|
|
451 common cachestat sys_cachestat
|
2023-07-11 16:16:05 +00:00
|
|
|
452 common fchmodat2 sys_fchmodat2
|
2023-08-31 19:20:12 +00:00
|
|
|
453 64 map_shadow_stack sys_map_shadow_stack
|
2023-09-21 10:45:10 +00:00
|
|
|
454 common futex_wake sys_futex_wake
|
2023-09-21 10:45:12 +00:00
|
|
|
455 common futex_wait sys_futex_wait
|
2023-09-21 10:45:15 +00:00
|
|
|
456 common futex_requeue sys_futex_requeue
|
2023-10-25 14:02:04 +00:00
|
|
|
457 common statmount sys_statmount
|
|
|
|
|
458 common listmount sys_listmount
|
lsm/stable-6.8 PR 20240105
-----BEGIN PGP SIGNATURE-----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=Py+n
-----END PGP SIGNATURE-----
Merge tag 'lsm-pr-20240105' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm
Pull security module updates from Paul Moore:
- Add three new syscalls: lsm_list_modules(), lsm_get_self_attr(), and
lsm_set_self_attr().
The first syscall simply lists the LSMs enabled, while the second and
third get and set the current process' LSM attributes. Yes, these
syscalls may provide similar functionality to what can be found under
/proc or /sys, but they were designed to support multiple,
simultaneaous (stacked) LSMs from the start as opposed to the current
/proc based solutions which were created at a time when only one LSM
was allowed to be active at a given time.
We have spent considerable time discussing ways to extend the
existing /proc interfaces to support multiple, simultaneaous LSMs and
even our best ideas have been far too ugly to support as a kernel
API; after +20 years in the kernel, I felt the LSM layer had
established itself enough to justify a handful of syscalls.
Support amongst the individual LSM developers has been nearly
unanimous, with a single objection coming from Tetsuo (TOMOYO) as he
is worried that the LSM_ID_XXX token concept will make it more
difficult for out-of-tree LSMs to survive. Several members of the LSM
community have demonstrated the ability for out-of-tree LSMs to
continue to exist by picking high/unused LSM_ID values as well as
pointing out that many kernel APIs rely on integer identifiers, e.g.
syscalls (!), but unfortunately Tetsuo's objections remain.
My personal opinion is that while I have no interest in penalizing
out-of-tree LSMs, I'm not going to penalize in-tree development to
support out-of-tree development, and I view this as a necessary step
forward to support the push for expanded LSM stacking and reduce our
reliance on /proc and /sys which has occassionally been problematic
for some container users. Finally, we have included the linux-api
folks on (all?) recent revisions of the patchset and addressed all of
their concerns.
- Add a new security_file_ioctl_compat() LSM hook to handle the 32-bit
ioctls on 64-bit systems problem.
This patch includes support for all of the existing LSMs which
provide ioctl hooks, although it turns out only SELinux actually
cares about the individual ioctls. It is worth noting that while
Casey (Smack) and Tetsuo (TOMOYO) did not give explicit ACKs to this
patch, they did both indicate they are okay with the changes.
- Fix a potential memory leak in the CALIPSO code when IPv6 is disabled
at boot.
While it's good that we are fixing this, I doubt this is something
users are seeing in the wild as you need to both disable IPv6 and
then attempt to configure IPv6 labeled networking via
NetLabel/CALIPSO; that just doesn't make much sense.
Normally this would go through netdev, but Jakub asked me to take
this patch and of all the trees I maintain, the LSM tree seemed like
the best fit.
- Update the LSM MAINTAINERS entry with additional information about
our process docs, patchwork, bug reporting, etc.
I also noticed that the Lockdown LSM is missing a dedicated
MAINTAINERS entry so I've added that to the pull request. I've been
working with one of the major Lockdown authors/contributors to see if
they are willing to step up and assume a Lockdown maintainer role;
hopefully that will happen soon, but in the meantime I'll continue to
look after it.
- Add a handful of mailmap entries for Serge Hallyn and myself.
* tag 'lsm-pr-20240105' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm: (27 commits)
lsm: new security_file_ioctl_compat() hook
lsm: Add a __counted_by() annotation to lsm_ctx.ctx
calipso: fix memory leak in netlbl_calipso_add_pass()
selftests: remove the LSM_ID_IMA check in lsm/lsm_list_modules_test
MAINTAINERS: add an entry for the lockdown LSM
MAINTAINERS: update the LSM entry
mailmap: add entries for Serge Hallyn's dead accounts
mailmap: update/replace my old email addresses
lsm: mark the lsm_id variables are marked as static
lsm: convert security_setselfattr() to use memdup_user()
lsm: align based on pointer length in lsm_fill_user_ctx()
lsm: consolidate buffer size handling into lsm_fill_user_ctx()
lsm: correct error codes in security_getselfattr()
lsm: cleanup the size counters in security_getselfattr()
lsm: don't yet account for IMA in LSM_CONFIG_COUNT calculation
lsm: drop LSM_ID_IMA
LSM: selftests for Linux Security Module syscalls
SELinux: Add selfattr hooks
AppArmor: Add selfattr hooks
Smack: implement setselfattr and getselfattr hooks
...
2024-01-09 20:57:46 +00:00
|
|
|
459 common lsm_get_self_attr sys_lsm_get_self_attr
|
|
|
|
|
460 common lsm_set_self_attr sys_lsm_set_self_attr
|
|
|
|
|
461 common lsm_list_modules sys_lsm_list_modules
|
2012-05-31 23:26:44 +00:00
|
|
|
|
2012-02-14 22:18:50 +00:00
|
|
|
#
|
2020-10-12 02:51:21 +00:00
|
|
|
# Due to a historical design error, certain syscalls are numbered differently
|
|
|
|
|
# in x32 as compared to native x86_64. These syscalls have numbers 512-547.
|
|
|
|
|
# Do not add new syscalls to this range. Numbers 548 and above are available
|
|
|
|
|
# for non-x32 use.
|
2012-02-14 22:18:50 +00:00
|
|
|
#
|
2020-03-13 19:51:38 +00:00
|
|
|
512 x32 rt_sigaction compat_sys_rt_sigaction
|
|
|
|
|
513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn
|
|
|
|
|
514 x32 ioctl compat_sys_ioctl
|
2020-09-25 04:51:43 +00:00
|
|
|
515 x32 readv sys_readv
|
|
|
|
|
516 x32 writev sys_writev
|
2020-03-13 19:51:38 +00:00
|
|
|
517 x32 recvfrom compat_sys_recvfrom
|
|
|
|
|
518 x32 sendmsg compat_sys_sendmsg
|
|
|
|
|
519 x32 recvmsg compat_sys_recvmsg
|
|
|
|
|
520 x32 execve compat_sys_execve
|
|
|
|
|
521 x32 ptrace compat_sys_ptrace
|
|
|
|
|
522 x32 rt_sigpending compat_sys_rt_sigpending
|
|
|
|
|
523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
|
|
|
|
|
524 x32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo
|
|
|
|
|
525 x32 sigaltstack compat_sys_sigaltstack
|
|
|
|
|
526 x32 timer_create compat_sys_timer_create
|
|
|
|
|
527 x32 mq_notify compat_sys_mq_notify
|
|
|
|
|
528 x32 kexec_load compat_sys_kexec_load
|
|
|
|
|
529 x32 waitid compat_sys_waitid
|
|
|
|
|
530 x32 set_robust_list compat_sys_set_robust_list
|
|
|
|
|
531 x32 get_robust_list compat_sys_get_robust_list
|
2020-09-25 04:51:44 +00:00
|
|
|
532 x32 vmsplice sys_vmsplice
|
2021-09-08 22:18:25 +00:00
|
|
|
533 x32 move_pages sys_move_pages
|
2020-03-13 19:51:38 +00:00
|
|
|
534 x32 preadv compat_sys_preadv64
|
|
|
|
|
535 x32 pwritev compat_sys_pwritev64
|
|
|
|
|
536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo
|
|
|
|
|
537 x32 recvmmsg compat_sys_recvmmsg_time64
|
|
|
|
|
538 x32 sendmmsg compat_sys_sendmmsg
|
2020-09-25 04:51:45 +00:00
|
|
|
539 x32 process_vm_readv sys_process_vm_readv
|
|
|
|
|
540 x32 process_vm_writev sys_process_vm_writev
|
2020-07-17 06:23:15 +00:00
|
|
|
541 x32 setsockopt sys_setsockopt
|
|
|
|
|
542 x32 getsockopt sys_getsockopt
|
2020-03-13 19:51:38 +00:00
|
|
|
543 x32 io_setup compat_sys_io_setup
|
|
|
|
|
544 x32 io_submit compat_sys_io_submit
|
|
|
|
|
545 x32 execveat compat_sys_execveat
|
|
|
|
|
546 x32 preadv2 compat_sys_preadv64v2
|
|
|
|
|
547 x32 pwritev2 compat_sys_pwritev64v2
|
2020-10-12 02:51:21 +00:00
|
|
|
# This is the end of the legacy x32 range. Numbers 548 and above are
|
|
|
|
|
# not special and are not to be used for x32-specific syscalls.
|