linux_dsm_epyc7002/include/linux/prctl.h
Cyrill Gorcunov 028ee4be34 c/r: prctl: add PR_SET_MM codes to set up mm_struct entries
When we restore a task we need to set up text, data and data heap sizes
from userspace to the values a task had at checkpoint time.  This patch
adds auxilary prctl codes for that.

While most of them have a statistical nature (their values are involved
into calculation of /proc/<pid>/statm output) the start_brk and brk values
are used to compute an allowed size of program data segment expansion.
Which means an arbitrary changes of this values might be dangerous
operation.  So to restrict access the following requirements applied to
prctl calls:

 - The process has to have CAP_SYS_ADMIN capability granted.
 - For all opcodes except start_brk/brk members an appropriate
   VMA area must exist and should fit certain VMA flags,
   such as:
   - code segment must be executable but not writable;
   - data segment must not be executable.

start_brk/brk values must not intersect with data segment and must not
exceed RLIMIT_DATA resource limit.

Still the main guard is CAP_SYS_ADMIN capability check.

Note the kernel should be compiled with CONFIG_CHECKPOINT_RESTORE support
otherwise these prctl calls will return -EINVAL.

[akpm@linux-foundation.org: cache current->mm in a local, saving 200 bytes text]
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrew Vagin <avagin@openvz.org>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Vasiliy Kulikov <segoon@openwall.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 20:13:13 -08:00

118 lines
4.0 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
#endif /* _LINUX_PRCTL_H */