ebec18a6d3
Userspace service managers/supervisors need to track their started services. Many services daemonize by double-forking and get implicitly re-parented to PID 1. The service manager will no longer be able to receive the SIGCHLD signals for them, and is no longer in charge of reaping the children with wait(). All information about the children is lost at the moment PID 1 cleans up the re-parented processes. With this prctl, a service manager process can mark itself as a sort of 'sub-init', able to stay as the parent for all orphaned processes created by the started services. All SIGCHLD signals will be delivered to the service manager. Receiving SIGCHLD and doing wait() is in cases of a service-manager much preferred over any possible asynchronous notification about specific PIDs, because the service manager has full access to the child process data in /proc and the PID can not be re-used until the wait(), the service-manager itself is in charge of, has happened. As a side effect, the relevant parent PID information does not get lost by a double-fork, which results in a more elaborate process tree and 'ps' output: before: # ps afx 253 ? Ss 0:00 /bin/dbus-daemon --system --nofork 294 ? Sl 0:00 /usr/libexec/polkit-1/polkitd 328 ? S 0:00 /usr/sbin/modem-manager 608 ? Sl 0:00 /usr/libexec/colord 658 ? Sl 0:00 /usr/libexec/upowerd 819 ? Sl 0:00 /usr/libexec/imsettings-daemon 916 ? Sl 0:00 /usr/libexec/udisks-daemon 917 ? S 0:00 \_ udisks-daemon: not polling any devices after: # ps afx 294 ? Ss 0:00 /bin/dbus-daemon --system --nofork 426 ? Sl 0:00 \_ /usr/libexec/polkit-1/polkitd 449 ? S 0:00 \_ /usr/sbin/modem-manager 635 ? Sl 0:00 \_ /usr/libexec/colord 705 ? Sl 0:00 \_ /usr/libexec/upowerd 959 ? Sl 0:00 \_ /usr/libexec/udisks-daemon 960 ? S 0:00 | \_ udisks-daemon: not polling any devices 977 ? Sl 0:00 \_ /usr/libexec/packagekitd This prctl is orthogonal to PID namespaces. PID namespaces are isolated from each other, while a service management process usually requires the services to live in the same namespace, to be able to talk to each other. Users of this will be the systemd per-user instance, which provides init-like functionality for the user's login session and D-Bus, which activates bus services on-demand. Both need init-like capabilities to be able to properly keep track of the services they start. Many thanks to Oleg for several rounds of review and insights. [akpm@linux-foundation.org: fix comment layout and spelling] [akpm@linux-foundation.org: add lengthy code comment from Oleg] Reviewed-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Lennart Poettering <lennart@poettering.net> Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Acked-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
127 lines
4.2 KiB
C
127 lines
4.2 KiB
C
#ifndef _LINUX_PRCTL_H
|
|
#define _LINUX_PRCTL_H
|
|
|
|
/* Values to pass as first argument to prctl() */
|
|
|
|
#define PR_SET_PDEATHSIG 1 /* Second arg is a signal */
|
|
#define PR_GET_PDEATHSIG 2 /* Second arg is a ptr to return the signal */
|
|
|
|
/* Get/set current->mm->dumpable */
|
|
#define PR_GET_DUMPABLE 3
|
|
#define PR_SET_DUMPABLE 4
|
|
|
|
/* Get/set unaligned access control bits (if meaningful) */
|
|
#define PR_GET_UNALIGN 5
|
|
#define PR_SET_UNALIGN 6
|
|
# define PR_UNALIGN_NOPRINT 1 /* silently fix up unaligned user accesses */
|
|
# define PR_UNALIGN_SIGBUS 2 /* generate SIGBUS on unaligned user access */
|
|
|
|
/* Get/set whether or not to drop capabilities on setuid() away from
|
|
* uid 0 (as per security/commoncap.c) */
|
|
#define PR_GET_KEEPCAPS 7
|
|
#define PR_SET_KEEPCAPS 8
|
|
|
|
/* Get/set floating-point emulation control bits (if meaningful) */
|
|
#define PR_GET_FPEMU 9
|
|
#define PR_SET_FPEMU 10
|
|
# define PR_FPEMU_NOPRINT 1 /* silently emulate fp operations accesses */
|
|
# define PR_FPEMU_SIGFPE 2 /* don't emulate fp operations, send SIGFPE instead */
|
|
|
|
/* Get/set floating-point exception mode (if meaningful) */
|
|
#define PR_GET_FPEXC 11
|
|
#define PR_SET_FPEXC 12
|
|
# define PR_FP_EXC_SW_ENABLE 0x80 /* Use FPEXC for FP exception enables */
|
|
# define PR_FP_EXC_DIV 0x010000 /* floating point divide by zero */
|
|
# define PR_FP_EXC_OVF 0x020000 /* floating point overflow */
|
|
# define PR_FP_EXC_UND 0x040000 /* floating point underflow */
|
|
# define PR_FP_EXC_RES 0x080000 /* floating point inexact result */
|
|
# define PR_FP_EXC_INV 0x100000 /* floating point invalid operation */
|
|
# define PR_FP_EXC_DISABLED 0 /* FP exceptions disabled */
|
|
# define PR_FP_EXC_NONRECOV 1 /* async non-recoverable exc. mode */
|
|
# define PR_FP_EXC_ASYNC 2 /* async recoverable exception mode */
|
|
# define PR_FP_EXC_PRECISE 3 /* precise exception mode */
|
|
|
|
/* Get/set whether we use statistical process timing or accurate timestamp
|
|
* based process timing */
|
|
#define PR_GET_TIMING 13
|
|
#define PR_SET_TIMING 14
|
|
# define PR_TIMING_STATISTICAL 0 /* Normal, traditional,
|
|
statistical process timing */
|
|
# define PR_TIMING_TIMESTAMP 1 /* Accurate timestamp based
|
|
process timing */
|
|
|
|
#define PR_SET_NAME 15 /* Set process name */
|
|
#define PR_GET_NAME 16 /* Get process name */
|
|
|
|
/* Get/set process endian */
|
|
#define PR_GET_ENDIAN 19
|
|
#define PR_SET_ENDIAN 20
|
|
# define PR_ENDIAN_BIG 0
|
|
# define PR_ENDIAN_LITTLE 1 /* True little endian mode */
|
|
# define PR_ENDIAN_PPC_LITTLE 2 /* "PowerPC" pseudo little endian */
|
|
|
|
/* Get/set process seccomp mode */
|
|
#define PR_GET_SECCOMP 21
|
|
#define PR_SET_SECCOMP 22
|
|
|
|
/* Get/set the capability bounding set (as per security/commoncap.c) */
|
|
#define PR_CAPBSET_READ 23
|
|
#define PR_CAPBSET_DROP 24
|
|
|
|
/* Get/set the process' ability to use the timestamp counter instruction */
|
|
#define PR_GET_TSC 25
|
|
#define PR_SET_TSC 26
|
|
# define PR_TSC_ENABLE 1 /* allow the use of the timestamp counter */
|
|
# define PR_TSC_SIGSEGV 2 /* throw a SIGSEGV instead of reading the TSC */
|
|
|
|
/* Get/set securebits (as per security/commoncap.c) */
|
|
#define PR_GET_SECUREBITS 27
|
|
#define PR_SET_SECUREBITS 28
|
|
|
|
/*
|
|
* Get/set the timerslack as used by poll/select/nanosleep
|
|
* A value of 0 means "use default"
|
|
*/
|
|
#define PR_SET_TIMERSLACK 29
|
|
#define PR_GET_TIMERSLACK 30
|
|
|
|
#define PR_TASK_PERF_EVENTS_DISABLE 31
|
|
#define PR_TASK_PERF_EVENTS_ENABLE 32
|
|
|
|
/*
|
|
* Set early/late kill mode for hwpoison memory corruption.
|
|
* This influences when the process gets killed on a memory corruption.
|
|
*/
|
|
#define PR_MCE_KILL 33
|
|
# define PR_MCE_KILL_CLEAR 0
|
|
# define PR_MCE_KILL_SET 1
|
|
|
|
# define PR_MCE_KILL_LATE 0
|
|
# define PR_MCE_KILL_EARLY 1
|
|
# define PR_MCE_KILL_DEFAULT 2
|
|
|
|
#define PR_MCE_KILL_GET 34
|
|
|
|
/*
|
|
* Tune up process memory map specifics.
|
|
*/
|
|
#define PR_SET_MM 35
|
|
# define PR_SET_MM_START_CODE 1
|
|
# define PR_SET_MM_END_CODE 2
|
|
# define PR_SET_MM_START_DATA 3
|
|
# define PR_SET_MM_END_DATA 4
|
|
# define PR_SET_MM_START_STACK 5
|
|
# define PR_SET_MM_START_BRK 6
|
|
# define PR_SET_MM_BRK 7
|
|
|
|
/*
|
|
* Set specific pid that is allowed to ptrace the current task.
|
|
* A value of 0 mean "no process".
|
|
*/
|
|
#define PR_SET_PTRACER 0x59616d61
|
|
# define PR_SET_PTRACER_ANY ((unsigned long)-1)
|
|
|
|
#define PR_SET_CHILD_SUBREAPER 36
|
|
#define PR_GET_CHILD_SUBREAPER 37
|
|
|
|
#endif /* _LINUX_PRCTL_H */
|