android_kernel_xiaomi_sm8350/kernel/sys.c

1806 lines
42 KiB
C
Raw Normal View History

/*
* linux/kernel/sys.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/utsname.h>
#include <linux/mman.h>
#include <linux/smp_lock.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/prctl.h>
#include <linux/highuid.h>
#include <linux/fs.h>
#include <linux/resource.h>
#include <linux/kernel.h>
#include <linux/kexec.h>
#include <linux/workqueue.h>
#include <linux/capability.h>
#include <linux/device.h>
#include <linux/key.h>
#include <linux/times.h>
#include <linux/posix-timers.h>
#include <linux/security.h>
#include <linux/dcookies.h>
#include <linux/suspend.h>
#include <linux/tty.h>
#include <linux/signal.h>
#include <linux/cn_proc.h>
#include <linux/getcpu.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/seccomp.h>
#include <linux/cpu.h>
#include <linux/compat.h>
#include <linux/syscalls.h>
#include <linux/kprobes.h>
#include <linux/user_namespace.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/unistd.h>
#ifndef SET_UNALIGN_CTL
# define SET_UNALIGN_CTL(a,b) (-EINVAL)
#endif
#ifndef GET_UNALIGN_CTL
# define GET_UNALIGN_CTL(a,b) (-EINVAL)
#endif
#ifndef SET_FPEMU_CTL
# define SET_FPEMU_CTL(a,b) (-EINVAL)
#endif
#ifndef GET_FPEMU_CTL
# define GET_FPEMU_CTL(a,b) (-EINVAL)
#endif
#ifndef SET_FPEXC_CTL
# define SET_FPEXC_CTL(a,b) (-EINVAL)
#endif
#ifndef GET_FPEXC_CTL
# define GET_FPEXC_CTL(a,b) (-EINVAL)
#endif
#ifndef GET_ENDIAN
# define GET_ENDIAN(a,b) (-EINVAL)
#endif
#ifndef SET_ENDIAN
# define SET_ENDIAN(a,b) (-EINVAL)
#endif
#ifndef GET_TSC_CTL
# define GET_TSC_CTL(a) (-EINVAL)
#endif
#ifndef SET_TSC_CTL
# define SET_TSC_CTL(a) (-EINVAL)
#endif
/*
* this is where the system-wide overflow UID and GID are defined, for
* architectures that now have 32-bit UID/GID but didn't in the past
*/
int overflowuid = DEFAULT_OVERFLOWUID;
int overflowgid = DEFAULT_OVERFLOWGID;
#ifdef CONFIG_UID16
EXPORT_SYMBOL(overflowuid);
EXPORT_SYMBOL(overflowgid);
#endif
/*
* the same as above, but for filesystems which can only store a 16-bit
* UID and GID. as such, this is needed on all architectures
*/
int fs_overflowuid = DEFAULT_FS_OVERFLOWUID;
int fs_overflowgid = DEFAULT_FS_OVERFLOWUID;
EXPORT_SYMBOL(fs_overflowuid);
EXPORT_SYMBOL(fs_overflowgid);
/*
* this indicates whether you can reboot with ctrl-alt-del: the default is yes
*/
int C_A_D = 1;
struct pid *cad_pid;
EXPORT_SYMBOL(cad_pid);
/*
* If set, this is used for preparing the system to power off.
*/
void (*pm_power_off_prepare)(void);
static int set_one_prio(struct task_struct *p, int niceval, int error)
{
int no_nice;
if (p->uid != current->euid &&
p->euid != current->euid && !capable(CAP_SYS_NICE)) {
error = -EPERM;
goto out;
}
if (niceval < task_nice(p) && !can_nice(p, niceval)) {
error = -EACCES;
goto out;
}
no_nice = security_task_setnice(p, niceval);
if (no_nice) {
error = no_nice;
goto out;
}
if (error == -ESRCH)
error = 0;
set_user_nice(p, niceval);
out:
return error;
}
asmlinkage long sys_setpriority(int which, int who, int niceval)
{
struct task_struct *g, *p;
struct user_struct *user;
int error = -EINVAL;
struct pid *pgrp;
if (which > PRIO_USER || which < PRIO_PROCESS)
goto out;
/* normalize: avoid signed division (rounding problems) */
error = -ESRCH;
if (niceval < -20)
niceval = -20;
if (niceval > 19)
niceval = 19;
read_lock(&tasklist_lock);
switch (which) {
case PRIO_PROCESS:
if (who)
p = find_task_by_vpid(who);
else
p = current;
if (p)
error = set_one_prio(p, niceval, error);
break;
case PRIO_PGRP:
if (who)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
error = set_one_prio(p, niceval, error);
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
user = current->user;
if (!who)
who = current->uid;
else
if ((who != current->uid) && !(user = find_user(who)))
goto out_unlock; /* No processes for this user */
do_each_thread(g, p)
if (p->uid == who)
error = set_one_prio(p, niceval, error);
while_each_thread(g, p);
if (who != current->uid)
free_uid(user); /* For find_user() */
break;
}
out_unlock:
read_unlock(&tasklist_lock);
out:
return error;
}
/*
* Ugh. To avoid negative return values, "getpriority()" will
* not return the normal nice-value, but a negated value that
* has been offset by 20 (ie it returns 40..1 instead of -20..19)
* to stay compatible.
*/
asmlinkage long sys_getpriority(int which, int who)
{
struct task_struct *g, *p;
struct user_struct *user;
long niceval, retval = -ESRCH;
struct pid *pgrp;
if (which > PRIO_USER || which < PRIO_PROCESS)
return -EINVAL;
read_lock(&tasklist_lock);
switch (which) {
case PRIO_PROCESS:
if (who)
p = find_task_by_vpid(who);
else
p = current;
if (p) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
}
break;
case PRIO_PGRP:
if (who)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
user = current->user;
if (!who)
who = current->uid;
else
if ((who != current->uid) && !(user = find_user(who)))
goto out_unlock; /* No processes for this user */
do_each_thread(g, p)
if (p->uid == who) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
}
while_each_thread(g, p);
if (who != current->uid)
free_uid(user); /* for find_user() */
break;
}
out_unlock:
read_unlock(&tasklist_lock);
return retval;
}
/**
* emergency_restart - reboot the system
*
* Without shutting down any hardware or taking any locks
* reboot the system. This is called when we know we are in
* trouble so this is our best effort to reboot. This is
* safe to call in interrupt context.
*/
void emergency_restart(void)
{
machine_emergency_restart();
}
EXPORT_SYMBOL_GPL(emergency_restart);
void kernel_restart_prepare(char *cmd)
{
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 04:16:30 -05:00
blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
system_state = SYSTEM_RESTART;
device_shutdown();
sysdev_shutdown();
}
/**
* kernel_restart - reboot the system
* @cmd: pointer to buffer containing command to execute for restart
* or %NULL
*
* Shutdown everything and perform a clean reboot.
* This is not safe to call in interrupt context.
*/
void kernel_restart(char *cmd)
{
kernel_restart_prepare(cmd);
if (!cmd)
printk(KERN_EMERG "Restarting system.\n");
else
printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
machine_restart(cmd);
}
EXPORT_SYMBOL_GPL(kernel_restart);
static void kernel_shutdown_prepare(enum system_states state)
{
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 04:16:30 -05:00
blocking_notifier_call_chain(&reboot_notifier_list,
(state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
system_state = state;
device_shutdown();
}
/**
* kernel_halt - halt the system
*
* Shutdown everything and perform a clean system halt.
*/
void kernel_halt(void)
{
kernel_shutdown_prepare(SYSTEM_HALT);
sysdev_shutdown();
printk(KERN_EMERG "System halted.\n");
machine_halt();
}
EXPORT_SYMBOL_GPL(kernel_halt);
/**
* kernel_power_off - power_off the system
*
* Shutdown everything and perform a clean system power_off.
*/
void kernel_power_off(void)
{
kernel_shutdown_prepare(SYSTEM_POWER_OFF);
if (pm_power_off_prepare)
pm_power_off_prepare();
disable_nonboot_cpus();
sysdev_shutdown();
printk(KERN_EMERG "Power down.\n");
machine_power_off();
}
EXPORT_SYMBOL_GPL(kernel_power_off);
/*
* Reboot system call: for obvious reasons only root may call it,
* and even root needs to set up some magic numbers in the registers
* so that some mistake won't make this reboot the whole machine.
* You can also set the meaning of the ctrl-alt-del-key here.
*
* reboot doesn't sync: do that yourself before calling this.
*/
asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user * arg)
{
char buffer[256];
/* We only trust the superuser with rebooting the system. */
if (!capable(CAP_SYS_BOOT))
return -EPERM;
/* For safety, we require "magic" arguments. */
if (magic1 != LINUX_REBOOT_MAGIC1 ||
(magic2 != LINUX_REBOOT_MAGIC2 &&
magic2 != LINUX_REBOOT_MAGIC2A &&
magic2 != LINUX_REBOOT_MAGIC2B &&
magic2 != LINUX_REBOOT_MAGIC2C))
return -EINVAL;
[PATCH] Don't attempt to power off if power off is not implemented The problem. It is expected that /sbin/halt -p works exactly like /sbin/halt, when the kernel does not implement power off functionality. The kernel can do a lot of work in the reboot notifiers and in device_shutdown before we even get to machine_power_off. Some of that shutdown is not safe if you are leaving the power on, and it definitely gets in the way of using sysrq or pressing ctrl-alt-del. Since the shutdown happens in generic code there is no way to fix this in architecture specific code :( Some machines are kernel oopsing today because of this. The simple solution is to turn LINUX_REBOOT_CMD_POWER_OFF into LINUX_REBOOT_CMD_HALT if power_off functionality is not implemented. This has the unfortunate side effect of disabling the power off functionality on architectures that leave pm_power_off to null and still implement something in machine_power_off. And it will break the build on some architectures that don't have a pm_power_off variable at all. On both counts I say tough. For architectures like alpha that don't implement the pm_power_off variable pm_power_off is declared in linux/pm.h and it is a generic part of our power management code, and all architectures should implement it. For architectures like parisc that have a default power off method in machine_power_off if pm_power_off is not implemented or fails. It is easy enough to set the pm_power_off variable. And nothing bad happens there, the machines just stop powering off. The current semantics are impossible without a flag at the top level so we can avoid the problem code if a power off is not implemented. pm_power_off is as good a flag as any with the bonus that it works without modification on at least x86, x86_64, powerpc, and ppc today. Andrew can you pick this up and put this in the mm tree. Kernels that don't compile or don't power off seem saner than kernels that oops or panic. Until we get the arch specific patches for the problem architectures this probably isn't smart to push into the stable kernel. Unfortunately I don't have the time at the moment to walk through every architecture and make them work. And even if I did I couldn't test it :( From: Hirokazu Takata <takata@linux-m32r.org> Add pm_power_off() for build fix of arch/m32r/kernel/process.c. From: Miklos Szeredi <miklos@szeredi.hu> UML build fix Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Hayato Fujiwara <fujiwara@linux-m32r.org> Signed-off-by: Hirokazu Takata <takata@linux-m32r.org> Signed-off-by: Miklos Szeredi <miklos@szeredi.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 04:03:46 -05:00
/* Instead of trying to make the power_off code look like
* halt when pm_power_off is not set do it the easy way.
*/
if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
cmd = LINUX_REBOOT_CMD_HALT;
lock_kernel();
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART:
kernel_restart(NULL);
break;
case LINUX_REBOOT_CMD_CAD_ON:
C_A_D = 1;
break;
case LINUX_REBOOT_CMD_CAD_OFF:
C_A_D = 0;
break;
case LINUX_REBOOT_CMD_HALT:
kernel_halt();
unlock_kernel();
do_exit(0);
break;
case LINUX_REBOOT_CMD_POWER_OFF:
kernel_power_off();
unlock_kernel();
do_exit(0);
break;
case LINUX_REBOOT_CMD_RESTART2:
if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) {
unlock_kernel();
return -EFAULT;
}
buffer[sizeof(buffer) - 1] = '\0';
kernel_restart(buffer);
break;
kexec jump This patch provides an enhancement to kexec/kdump. It implements the following features: - Backup/restore memory used by the original kernel before/after kexec. - Save/restore CPU state before/after kexec. The features of this patch can be used as a general method to call program in physical mode (paging turning off). This can be used to call BIOS code under Linux. kexec-tools needs to be patched to support kexec jump. The patches and the precompiled kexec can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-src_git_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-patches_git_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec_git_kh10 Usage example of calling some physical mode code and return: 1. Compile and install patched kernel with following options selected: CONFIG_X86_32=y CONFIG_KEXEC=y CONFIG_PM=y CONFIG_KEXEC_JUMP=y 2. Build patched kexec-tool or download the pre-built one. 3. Build some physical mode executable named such as "phy_mode" 4. Boot kernel compiled in step 1. 5. Load physical mode executable with /sbin/kexec. The shell command line can be as follow: /sbin/kexec --load-preserve-context --args-none phy_mode 6. Call physical mode executable with following shell command line: /sbin/kexec -e Implementation point: To support jumping without reserving memory. One shadow backup page (source page) is allocated for each page used by kexeced code image (destination page). When do kexec_load, the image of kexeced code is loaded into source pages, and before executing, the destination pages and the source pages are swapped, so the contents of destination pages are backupped. Before jumping to the kexeced code image and after jumping back to the original kernel, the destination pages and the source pages are swapped too. C ABI (calling convention) is used as communication protocol between kernel and called code. A flag named KEXEC_PRESERVE_CONTEXT for sys_kexec_load is added to indicate that the loaded kernel image is used for jumping back. Now, only the i386 architecture is supported. Signed-off-by: Huang Ying <ying.huang@intel.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 22:45:07 -04:00
#ifdef CONFIG_KEXEC
case LINUX_REBOOT_CMD_KEXEC:
kexec jump This patch provides an enhancement to kexec/kdump. It implements the following features: - Backup/restore memory used by the original kernel before/after kexec. - Save/restore CPU state before/after kexec. The features of this patch can be used as a general method to call program in physical mode (paging turning off). This can be used to call BIOS code under Linux. kexec-tools needs to be patched to support kexec jump. The patches and the precompiled kexec can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-src_git_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-patches_git_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec_git_kh10 Usage example of calling some physical mode code and return: 1. Compile and install patched kernel with following options selected: CONFIG_X86_32=y CONFIG_KEXEC=y CONFIG_PM=y CONFIG_KEXEC_JUMP=y 2. Build patched kexec-tool or download the pre-built one. 3. Build some physical mode executable named such as "phy_mode" 4. Boot kernel compiled in step 1. 5. Load physical mode executable with /sbin/kexec. The shell command line can be as follow: /sbin/kexec --load-preserve-context --args-none phy_mode 6. Call physical mode executable with following shell command line: /sbin/kexec -e Implementation point: To support jumping without reserving memory. One shadow backup page (source page) is allocated for each page used by kexeced code image (destination page). When do kexec_load, the image of kexeced code is loaded into source pages, and before executing, the destination pages and the source pages are swapped, so the contents of destination pages are backupped. Before jumping to the kexeced code image and after jumping back to the original kernel, the destination pages and the source pages are swapped too. C ABI (calling convention) is used as communication protocol between kernel and called code. A flag named KEXEC_PRESERVE_CONTEXT for sys_kexec_load is added to indicate that the loaded kernel image is used for jumping back. Now, only the i386 architecture is supported. Signed-off-by: Huang Ying <ying.huang@intel.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 22:45:07 -04:00
{
int ret;
ret = kernel_kexec();
unlock_kernel();
return ret;
}
#endif
#ifdef CONFIG_HIBERNATION
case LINUX_REBOOT_CMD_SW_SUSPEND:
{
int ret = hibernate();
unlock_kernel();
return ret;
}
#endif
default:
unlock_kernel();
return -EINVAL;
}
unlock_kernel();
return 0;
}
2006-11-22 09:55:48 -05:00
static void deferred_cad(struct work_struct *dummy)
{
kernel_restart(NULL);
}
/*
* This function gets called by ctrl-alt-del - ie the keyboard interrupt.
* As it's called within an interrupt, it may NOT sync: the only choice
* is whether to reboot at once, or just ignore the ctrl-alt-del.
*/
void ctrl_alt_del(void)
{
2006-11-22 09:55:48 -05:00
static DECLARE_WORK(cad_work, deferred_cad);
if (C_A_D)
schedule_work(&cad_work);
else
kill_cad_pid(SIGINT, 1);
}
/*
* Unprivileged users may change the real gid to the effective gid
* or vice versa. (BSD-style)
*
* If you set the real gid at all, or set the effective gid to a value not
* equal to the real gid, then the saved gid is set to the new effective gid.
*
* This makes it possible for a setgid program to completely drop its
* privileges, which is often a useful assertion to make when you are doing
* a security audit over a program.
*
* The general idea is that a program which uses just setregid() will be
* 100% compatible with BSD. A program which uses just setgid() will be
* 100% compatible with POSIX with saved IDs.
*
* SMP: There are not races, the GIDs are checked only by filesystem
* operations (as far as semantic preservation is concerned).
*/
asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
{
int old_rgid = current->gid;
int old_egid = current->egid;
int new_rgid = old_rgid;
int new_egid = old_egid;
int retval;
retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE);
if (retval)
return retval;
if (rgid != (gid_t) -1) {
if ((old_rgid == rgid) ||
(current->egid==rgid) ||
capable(CAP_SETGID))
new_rgid = rgid;
else
return -EPERM;
}
if (egid != (gid_t) -1) {
if ((old_rgid == egid) ||
(current->egid == egid) ||
(current->sgid == egid) ||
capable(CAP_SETGID))
new_egid = egid;
else
return -EPERM;
}
if (new_egid != old_egid) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
if (rgid != (gid_t) -1 ||
(egid != (gid_t) -1 && egid != old_rgid))
current->sgid = new_egid;
current->fsgid = new_egid;
current->egid = new_egid;
current->gid = new_rgid;
key_fsgid_changed(current);
proc_id_connector(current, PROC_EVENT_GID);
return 0;
}
/*
* setgid() is implemented like SysV w/ SAVED_IDS
*
* SMP: Same implicit races as above.
*/
asmlinkage long sys_setgid(gid_t gid)
{
int old_egid = current->egid;
int retval;
retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID);
if (retval)
return retval;
if (capable(CAP_SETGID)) {
if (old_egid != gid) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->gid = current->egid = current->sgid = current->fsgid = gid;
} else if ((gid == current->gid) || (gid == current->sgid)) {
if (old_egid != gid) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->egid = current->fsgid = gid;
}
else
return -EPERM;
key_fsgid_changed(current);
proc_id_connector(current, PROC_EVENT_GID);
return 0;
}
static int set_user(uid_t new_ruid, int dumpclear)
{
struct user_struct *new_user;
new_user = alloc_uid(current->nsproxy->user_ns, new_ruid);
if (!new_user)
return -EAGAIN;
if (atomic_read(&new_user->processes) >=
current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
new_user != current->nsproxy->user_ns->root_user) {
free_uid(new_user);
return -EAGAIN;
}
switch_uid(new_user);
if (dumpclear) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->uid = new_ruid;
return 0;
}
/*
* Unprivileged users may change the real uid to the effective uid
* or vice versa. (BSD-style)
*
* If you set the real uid at all, or set the effective uid to a value not
* equal to the real uid, then the saved uid is set to the new effective uid.
*
* This makes it possible for a setuid program to completely drop its
* privileges, which is often a useful assertion to make when you are doing
* a security audit over a program.
*
* The general idea is that a program which uses just setreuid() will be
* 100% compatible with BSD. A program which uses just setuid() will be
* 100% compatible with POSIX with saved IDs.
*/
asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
{
int old_ruid, old_euid, old_suid, new_ruid, new_euid;
int retval;
retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE);
if (retval)
return retval;
new_ruid = old_ruid = current->uid;
new_euid = old_euid = current->euid;
old_suid = current->suid;
if (ruid != (uid_t) -1) {
new_ruid = ruid;
if ((old_ruid != ruid) &&
(current->euid != ruid) &&
!capable(CAP_SETUID))
return -EPERM;
}
if (euid != (uid_t) -1) {
new_euid = euid;
if ((old_ruid != euid) &&
(current->euid != euid) &&
(current->suid != euid) &&
!capable(CAP_SETUID))
return -EPERM;
}
if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0)
return -EAGAIN;
if (new_euid != old_euid) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->fsuid = current->euid = new_euid;
if (ruid != (uid_t) -1 ||
(euid != (uid_t) -1 && euid != old_ruid))
current->suid = current->euid;
current->fsuid = current->euid;
key_fsuid_changed(current);
proc_id_connector(current, PROC_EVENT_UID);
return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE);
}
/*
* setuid() is implemented like SysV with SAVED_IDS
*
* Note that SAVED_ID's is deficient in that a setuid root program
* like sendmail, for example, cannot set its uid to be a normal
* user and then switch back, because if you're root, setuid() sets
* the saved uid too. If you don't like this, blame the bright people
* in the POSIX committee and/or USG. Note that the BSD-style setreuid()
* will allow a root program to temporarily drop privileges and be able to
* regain them by swapping the real and effective uid.
*/
asmlinkage long sys_setuid(uid_t uid)
{
int old_euid = current->euid;
int old_ruid, old_suid, new_suid;
int retval;
retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID);
if (retval)
return retval;
old_ruid = current->uid;
old_suid = current->suid;
new_suid = old_suid;
if (capable(CAP_SETUID)) {
if (uid != old_ruid && set_user(uid, old_euid != uid) < 0)
return -EAGAIN;
new_suid = uid;
} else if ((uid != current->uid) && (uid != new_suid))
return -EPERM;
if (old_euid != uid) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->fsuid = current->euid = uid;
current->suid = new_suid;
key_fsuid_changed(current);
proc_id_connector(current, PROC_EVENT_UID);
return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID);
}
/*
* This function implements a generic ability to update ruid, euid,
* and suid. This allows you to implement the 4.4 compatible seteuid().
*/
asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
{
int old_ruid = current->uid;
int old_euid = current->euid;
int old_suid = current->suid;
int retval;
retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
if (retval)
return retval;
if (!capable(CAP_SETUID)) {
if ((ruid != (uid_t) -1) && (ruid != current->uid) &&
(ruid != current->euid) && (ruid != current->suid))
return -EPERM;
if ((euid != (uid_t) -1) && (euid != current->uid) &&
(euid != current->euid) && (euid != current->suid))
return -EPERM;
if ((suid != (uid_t) -1) && (suid != current->uid) &&
(suid != current->euid) && (suid != current->suid))
return -EPERM;
}
if (ruid != (uid_t) -1) {
if (ruid != current->uid && set_user(ruid, euid != current->euid) < 0)
return -EAGAIN;
}
if (euid != (uid_t) -1) {
if (euid != current->euid) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->euid = euid;
}
current->fsuid = current->euid;
if (suid != (uid_t) -1)
current->suid = suid;
key_fsuid_changed(current);
proc_id_connector(current, PROC_EVENT_UID);
return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES);
}
asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid)
{
int retval;
if (!(retval = put_user(current->uid, ruid)) &&
!(retval = put_user(current->euid, euid)))
retval = put_user(current->suid, suid);
return retval;
}
/*
* Same as above, but for rgid, egid, sgid.
*/
asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
{
int retval;
retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES);
if (retval)
return retval;
if (!capable(CAP_SETGID)) {
if ((rgid != (gid_t) -1) && (rgid != current->gid) &&
(rgid != current->egid) && (rgid != current->sgid))
return -EPERM;
if ((egid != (gid_t) -1) && (egid != current->gid) &&
(egid != current->egid) && (egid != current->sgid))
return -EPERM;
if ((sgid != (gid_t) -1) && (sgid != current->gid) &&
(sgid != current->egid) && (sgid != current->sgid))
return -EPERM;
}
if (egid != (gid_t) -1) {
if (egid != current->egid) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->egid = egid;
}
current->fsgid = current->egid;
if (rgid != (gid_t) -1)
current->gid = rgid;
if (sgid != (gid_t) -1)
current->sgid = sgid;
key_fsgid_changed(current);
proc_id_connector(current, PROC_EVENT_GID);
return 0;
}
asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid)
{
int retval;
if (!(retval = put_user(current->gid, rgid)) &&
!(retval = put_user(current->egid, egid)))
retval = put_user(current->sgid, sgid);
return retval;
}
/*
* "setfsuid()" sets the fsuid - the uid used for filesystem checks. This
* is used for "access()" and for the NFS daemon (letting nfsd stay at
* whatever uid it wants to). It normally shadows "euid", except when
* explicitly set by setfsuid() or for access..
*/
asmlinkage long sys_setfsuid(uid_t uid)
{
int old_fsuid;
old_fsuid = current->fsuid;
if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS))
return old_fsuid;
if (uid == current->uid || uid == current->euid ||
uid == current->suid || uid == current->fsuid ||
capable(CAP_SETUID)) {
if (uid != old_fsuid) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->fsuid = uid;
}
key_fsuid_changed(current);
proc_id_connector(current, PROC_EVENT_UID);
security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS);
return old_fsuid;
}
/*
* Samma svenska..
*/
asmlinkage long sys_setfsgid(gid_t gid)
{
int old_fsgid;
old_fsgid = current->fsgid;
if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS))
return old_fsgid;
if (gid == current->gid || gid == current->egid ||
gid == current->sgid || gid == current->fsgid ||
capable(CAP_SETGID)) {
if (gid != old_fsgid) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->fsgid = gid;
key_fsgid_changed(current);
proc_id_connector(current, PROC_EVENT_GID);
}
return old_fsgid;
}
asmlinkage long sys_times(struct tms __user * tbuf)
{
/*
* In the SMP world we might just be unlucky and have one of
* the times increment as we use it. Since the value is an
* atomically safe type this is just fine. Conceptually its
* as if the syscall took an instant longer to occur.
*/
if (tbuf) {
struct tms tmp;
struct task_struct *tsk = current;
struct task_struct *t;
cputime_t utime, stime, cutime, cstime;
spin_lock_irq(&tsk->sighand->siglock);
utime = tsk->signal->utime;
stime = tsk->signal->stime;
t = tsk;
do {
utime = cputime_add(utime, t->utime);
stime = cputime_add(stime, t->stime);
t = next_thread(t);
} while (t != tsk);
cutime = tsk->signal->cutime;
cstime = tsk->signal->cstime;
spin_unlock_irq(&tsk->sighand->siglock);
tmp.tms_utime = cputime_to_clock_t(utime);
tmp.tms_stime = cputime_to_clock_t(stime);
tmp.tms_cutime = cputime_to_clock_t(cutime);
tmp.tms_cstime = cputime_to_clock_t(cstime);
if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
return -EFAULT;
}
return (long) jiffies_64_to_clock_t(get_jiffies_64());
}
/*
* This needs some heavy checking ...
* I just haven't the stomach for it. I also don't fully
* understand sessions/pgrp etc. Let somebody who does explain it.
*
* OK, I think I have the protection semantics right.... this is really
* only important on a multi-user system anyway, to make sure one user
* can't send a signal to a process owned by another. -TYT, 12/12/91
*
* Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
* LBT 04.03.94
*/
asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
{
struct task_struct *p;
struct task_struct *group_leader = current->group_leader;
struct pid *pgrp;
int err;
if (!pid)
pid = task_pid_vnr(group_leader);
if (!pgid)
pgid = pid;
if (pgid < 0)
return -EINVAL;
/* From this point forward we keep holding onto the tasklist lock
* so that our parent does not change from under us. -DaveM
*/
write_lock_irq(&tasklist_lock);
err = -ESRCH;
p = find_task_by_vpid(pid);
if (!p)
goto out;
err = -EINVAL;
if (!thread_group_leader(p))
goto out;
if (same_thread_group(p->real_parent, group_leader)) {
err = -EPERM;
if (task_session(p) != task_session(group_leader))
goto out;
err = -EACCES;
if (p->did_exec)
goto out;
} else {
err = -ESRCH;
if (p != group_leader)
goto out;
}
err = -EPERM;
if (p->signal->leader)
goto out;
pgrp = task_pid(p);
if (pgid != pid) {
struct task_struct *g;
pgrp = find_vpid(pgid);
g = pid_task(pgrp, PIDTYPE_PGID);
if (!g || task_session(g) != task_session(group_leader))
goto out;
}
err = security_task_setpgid(p, pgid);
if (err)
goto out;
if (task_pgrp(p) != pgrp) {
change_pid(p, PIDTYPE_PGID, pgrp);
set_task_pgrp(p, pid_nr(pgrp));
}
err = 0;
out:
/* All paths lead to here, thus we are safe. -DaveM */
write_unlock_irq(&tasklist_lock);
return err;
}
asmlinkage long sys_getpgid(pid_t pid)
{
struct task_struct *p;
struct pid *grp;
int retval;
rcu_read_lock();
if (!pid)
grp = task_pgrp(current);
else {
retval = -ESRCH;
p = find_task_by_vpid(pid);
if (!p)
goto out;
grp = task_pgrp(p);
if (!grp)
goto out;
retval = security_task_getpgid(p);
if (retval)
goto out;
}
retval = pid_vnr(grp);
out:
rcu_read_unlock();
return retval;
}
#ifdef __ARCH_WANT_SYS_GETPGRP
asmlinkage long sys_getpgrp(void)
{
return sys_getpgid(0);
}
#endif
asmlinkage long sys_getsid(pid_t pid)
{
struct task_struct *p;
struct pid *sid;
int retval;
rcu_read_lock();
if (!pid)
sid = task_session(current);
else {
retval = -ESRCH;
p = find_task_by_vpid(pid);
if (!p)
goto out;
sid = task_session(p);
if (!sid)
goto out;
retval = security_task_getsid(p);
if (retval)
goto out;
}
retval = pid_vnr(sid);
out:
rcu_read_unlock();
return retval;
}
asmlinkage long sys_setsid(void)
{
struct task_struct *group_leader = current->group_leader;
struct pid *sid = task_pid(group_leader);
pid_t session = pid_vnr(sid);
int err = -EPERM;
write_lock_irq(&tasklist_lock);
/* Fail if I am already a session leader */
if (group_leader->signal->leader)
goto out;
/* Fail if a process group id already exists that equals the
* proposed session id.
*/
if (pid_task(sid, PIDTYPE_PGID))
goto out;
group_leader->signal->leader = 1;
__set_special_pids(sid);
[PATCH] tty: ->signal->tty locking Fix the locking of signal->tty. Use ->sighand->siglock to protect ->signal->tty; this lock is already used by most other members of ->signal/->sighand. And unless we are 'current' or the tasklist_lock is held we need ->siglock to access ->signal anyway. (NOTE: sys_unshare() is broken wrt ->sighand locking rules) Note that tty_mutex is held over tty destruction, so while holding tty_mutex any tty pointer remains valid. Otherwise the lifetime of ttys are governed by their open file handles. This leaves some holes for tty access from signal->tty (or any other non file related tty access). It solves the tty SLAB scribbles we were seeing. (NOTE: the change from group_send_sig_info to __group_send_sig_info needs to be examined by someone familiar with the security framework, I think it is safe given the SEND_SIG_PRIV from other __group_send_sig_info invocations) [schwidefsky@de.ibm.com: 3270 fix] [akpm@osdl.org: various post-viro fixes] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Alan Cox <alan@redhat.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Roland McGrath <roland@redhat.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jan Kara <jack@ucw.cz> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 05:36:04 -05:00
spin_lock(&group_leader->sighand->siglock);
group_leader->signal->tty = NULL;
[PATCH] tty: ->signal->tty locking Fix the locking of signal->tty. Use ->sighand->siglock to protect ->signal->tty; this lock is already used by most other members of ->signal/->sighand. And unless we are 'current' or the tasklist_lock is held we need ->siglock to access ->signal anyway. (NOTE: sys_unshare() is broken wrt ->sighand locking rules) Note that tty_mutex is held over tty destruction, so while holding tty_mutex any tty pointer remains valid. Otherwise the lifetime of ttys are governed by their open file handles. This leaves some holes for tty access from signal->tty (or any other non file related tty access). It solves the tty SLAB scribbles we were seeing. (NOTE: the change from group_send_sig_info to __group_send_sig_info needs to be examined by someone familiar with the security framework, I think it is safe given the SEND_SIG_PRIV from other __group_send_sig_info invocations) [schwidefsky@de.ibm.com: 3270 fix] [akpm@osdl.org: various post-viro fixes] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Alan Cox <alan@redhat.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Roland McGrath <roland@redhat.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jan Kara <jack@ucw.cz> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 05:36:04 -05:00
spin_unlock(&group_leader->sighand->siglock);
err = session;
out:
write_unlock_irq(&tasklist_lock);
return err;
}
/*
* Supplementary group IDs
*/
/* init to 2 - one for init_task, one to ensure it is never freed */
struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
struct group_info *groups_alloc(int gidsetsize)
{
struct group_info *group_info;
int nblocks;
int i;
nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
/* Make sure we always allocate at least one indirect block pointer */
nblocks = nblocks ? : 1;
group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
if (!group_info)
return NULL;
group_info->ngroups = gidsetsize;
group_info->nblocks = nblocks;
atomic_set(&group_info->usage, 1);
if (gidsetsize <= NGROUPS_SMALL)
group_info->blocks[0] = group_info->small_block;
else {
for (i = 0; i < nblocks; i++) {
gid_t *b;
b = (void *)__get_free_page(GFP_USER);
if (!b)
goto out_undo_partial_alloc;
group_info->blocks[i] = b;
}
}
return group_info;
out_undo_partial_alloc:
while (--i >= 0) {
free_page((unsigned long)group_info->blocks[i]);
}
kfree(group_info);
return NULL;
}
EXPORT_SYMBOL(groups_alloc);
void groups_free(struct group_info *group_info)
{
if (group_info->blocks[0] != group_info->small_block) {
int i;
for (i = 0; i < group_info->nblocks; i++)
free_page((unsigned long)group_info->blocks[i]);
}
kfree(group_info);
}
EXPORT_SYMBOL(groups_free);
/* export the group_info to a user-space array */
static int groups_to_user(gid_t __user *grouplist,
struct group_info *group_info)
{
int i;
unsigned int count = group_info->ngroups;
for (i = 0; i < group_info->nblocks; i++) {
unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
unsigned int len = cp_count * sizeof(*grouplist);
if (copy_to_user(grouplist, group_info->blocks[i], len))
return -EFAULT;
grouplist += NGROUPS_PER_BLOCK;
count -= cp_count;
}
return 0;
}
/* fill a group_info from a user-space array - it must be allocated already */
static int groups_from_user(struct group_info *group_info,
gid_t __user *grouplist)
{
int i;
unsigned int count = group_info->ngroups;
for (i = 0; i < group_info->nblocks; i++) {
unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
unsigned int len = cp_count * sizeof(*grouplist);
if (copy_from_user(group_info->blocks[i], grouplist, len))
return -EFAULT;
grouplist += NGROUPS_PER_BLOCK;
count -= cp_count;
}
return 0;
}
/* a simple Shell sort */
static void groups_sort(struct group_info *group_info)
{
int base, max, stride;
int gidsetsize = group_info->ngroups;
for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1)
; /* nothing */
stride /= 3;
while (stride) {
max = gidsetsize - stride;
for (base = 0; base < max; base++) {
int left = base;
int right = left + stride;
gid_t tmp = GROUP_AT(group_info, right);
while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
GROUP_AT(group_info, right) =
GROUP_AT(group_info, left);
right = left;
left -= stride;
}
GROUP_AT(group_info, right) = tmp;
}
stride /= 3;
}
}
/* a simple bsearch */
[PATCH] Keys: Make request-key create an authorisation key The attached patch makes the following changes: (1) There's a new special key type called ".request_key_auth". This is an authorisation key for when one process requests a key and another process is started to construct it. This type of key cannot be created by the user; nor can it be requested by kernel services. Authorisation keys hold two references: (a) Each refers to a key being constructed. When the key being constructed is instantiated the authorisation key is revoked, rendering it of no further use. (b) The "authorising process". This is either: (i) the process that called request_key(), or: (ii) if the process that called request_key() itself had an authorisation key in its session keyring, then the authorising process referred to by that authorisation key will also be referred to by the new authorisation key. This means that the process that initiated a chain of key requests will authorise the lot of them, and will, by default, wind up with the keys obtained from them in its keyrings. (2) request_key() creates an authorisation key which is then passed to /sbin/request-key in as part of a new session keyring. (3) When request_key() is searching for a key to hand back to the caller, if it comes across an authorisation key in the session keyring of the calling process, it will also search the keyrings of the process specified therein and it will use the specified process's credentials (fsuid, fsgid, groups) to do that rather than the calling process's credentials. This allows a process started by /sbin/request-key to find keys belonging to the authorising process. (4) A key can be read, even if the process executing KEYCTL_READ doesn't have direct read or search permission if that key is contained within the keyrings of a process specified by an authorisation key found within the calling process's session keyring, and is searchable using the credentials of the authorising process. This allows a process started by /sbin/request-key to read keys belonging to the authorising process. (5) The magic KEY_SPEC_*_KEYRING key IDs when passed to KEYCTL_INSTANTIATE or KEYCTL_NEGATE will specify a keyring of the authorising process, rather than the process doing the instantiation. (6) One of the process keyrings can be nominated as the default to which request_key() should attach new keys if not otherwise specified. This is done with KEYCTL_SET_REQKEY_KEYRING and one of the KEY_REQKEY_DEFL_* constants. The current setting can also be read using this call. (7) request_key() is partially interruptible. If it is waiting for another process to finish constructing a key, it can be interrupted. This permits a request-key cycle to be broken without recourse to rebooting. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-Off-By: Benoit Boissinot <benoit.boissinot@ens-lyon.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 01:00:56 -04:00
int groups_search(struct group_info *group_info, gid_t grp)
{
unsigned int left, right;
if (!group_info)
return 0;
left = 0;
right = group_info->ngroups;
while (left < right) {
unsigned int mid = (left+right)/2;
int cmp = grp - GROUP_AT(group_info, mid);
if (cmp > 0)
left = mid + 1;
else if (cmp < 0)
right = mid;
else
return 1;
}
return 0;
}
/* validate and set current->group_info */
int set_current_groups(struct group_info *group_info)
{
int retval;
struct group_info *old_info;
retval = security_task_setgroups(group_info);
if (retval)
return retval;
groups_sort(group_info);
get_group_info(group_info);
task_lock(current);
old_info = current->group_info;
current->group_info = group_info;
task_unlock(current);
put_group_info(old_info);
return 0;
}
EXPORT_SYMBOL(set_current_groups);
asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
{
int i = 0;
/*
* SMP: Nobody else can change our grouplist. Thus we are
* safe.
*/
if (gidsetsize < 0)
return -EINVAL;
/* no need to grab task_lock here; it cannot change */
i = current->group_info->ngroups;
if (gidsetsize) {
if (i > gidsetsize) {
i = -EINVAL;
goto out;
}
if (groups_to_user(grouplist, current->group_info)) {
i = -EFAULT;
goto out;
}
}
out:
return i;
}
/*
* SMP: Our groups are copy-on-write. We can set them safely
* without another task interfering.
*/
asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist)
{
struct group_info *group_info;
int retval;
if (!capable(CAP_SETGID))
return -EPERM;
if ((unsigned)gidsetsize > NGROUPS_MAX)
return -EINVAL;
group_info = groups_alloc(gidsetsize);
if (!group_info)
return -ENOMEM;
retval = groups_from_user(group_info, grouplist);
if (retval) {
put_group_info(group_info);
return retval;
}
retval = set_current_groups(group_info);
put_group_info(group_info);
return retval;
}
/*
* Check whether we're fsgid/egid or in the supplemental group..
*/
int in_group_p(gid_t grp)
{
int retval = 1;
if (grp != current->fsgid)
retval = groups_search(current->group_info, grp);
return retval;
}
EXPORT_SYMBOL(in_group_p);
int in_egroup_p(gid_t grp)
{
int retval = 1;
if (grp != current->egid)
retval = groups_search(current->group_info, grp);
return retval;
}
EXPORT_SYMBOL(in_egroup_p);
DECLARE_RWSEM(uts_sem);
asmlinkage long sys_newuname(struct new_utsname __user * name)
{
int errno = 0;
down_read(&uts_sem);
if (copy_to_user(name, utsname(), sizeof *name))
errno = -EFAULT;
up_read(&uts_sem);
return errno;
}
asmlinkage long sys_sethostname(char __user *name, int len)
{
int errno;
char tmp[__NEW_UTS_LEN];
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
down_write(&uts_sem);
errno = -EFAULT;
if (!copy_from_user(tmp, name, len)) {
memcpy(utsname()->nodename, tmp, len);
utsname()->nodename[len] = 0;
errno = 0;
}
up_write(&uts_sem);
return errno;
}
#ifdef __ARCH_WANT_SYS_GETHOSTNAME
asmlinkage long sys_gethostname(char __user *name, int len)
{
int i, errno;
if (len < 0)
return -EINVAL;
down_read(&uts_sem);
i = 1 + strlen(utsname()->nodename);
if (i > len)
i = len;
errno = 0;
if (copy_to_user(name, utsname()->nodename, i))
errno = -EFAULT;
up_read(&uts_sem);
return errno;
}
#endif
/*
* Only setdomainname; getdomainname can be implemented by calling
* uname()
*/
asmlinkage long sys_setdomainname(char __user *name, int len)
{
int errno;
char tmp[__NEW_UTS_LEN];
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
down_write(&uts_sem);
errno = -EFAULT;
if (!copy_from_user(tmp, name, len)) {
memcpy(utsname()->domainname, tmp, len);
utsname()->domainname[len] = 0;
errno = 0;
}
up_write(&uts_sem);
return errno;
}
asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim)
{
if (resource >= RLIM_NLIMITS)
return -EINVAL;
else {
struct rlimit value;
task_lock(current->group_leader);
value = current->signal->rlim[resource];
task_unlock(current->group_leader);
return copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
}
}
#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT
/*
* Back compatibility for getrlimit. Needed for some apps.
*/
asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim)
{
struct rlimit x;
if (resource >= RLIM_NLIMITS)
return -EINVAL;
task_lock(current->group_leader);
x = current->signal->rlim[resource];
task_unlock(current->group_leader);
if (x.rlim_cur > 0x7FFFFFFF)
x.rlim_cur = 0x7FFFFFFF;
if (x.rlim_max > 0x7FFFFFFF)
x.rlim_max = 0x7FFFFFFF;
return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0;
}
#endif
asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
{
struct rlimit new_rlim, *old_rlim;
unsigned long it_prof_secs;
int retval;
if (resource >= RLIM_NLIMITS)
return -EINVAL;
if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
return -EFAULT;
if (new_rlim.rlim_cur > new_rlim.rlim_max)
return -EINVAL;
old_rlim = current->signal->rlim + resource;
if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
!capable(CAP_SYS_RESOURCE))
return -EPERM;
if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
return -EPERM;
retval = security_task_setrlimit(resource, &new_rlim);
if (retval)
return retval;
CPU time limit patch / setrlimit(RLIMIT_CPU, 0) cheat fix As discovered here today, the change in Kernel 2.6.17 intended to inhibit users from setting RLIMIT_CPU to 0 (as that is equivalent to unlimited) by "cheating" and setting it to 1 in such a case, does not make a difference, as the check is done in the wrong place (too late), and only applies to the profiling code. On all systems I checked running kernels above 2.6.17, no matter what the hard and soft CPU time limits were before, a user could escape them by issuing in the shell (sh/bash/zsh) "ulimit -t 0", and then the user's process was not ever killed. Attached is a trivial patch to fix that. Simply moving the check to a slightly earlier location (specifically, before the line that actually assigns the limit - *old_rlim = new_rlim), does the trick. Do note that at least the zsh (but not ash, dash, or bash) shell has the problem of "caching" the limits set by the ulimit command, so when running zsh the fix will not immediately be evident - after entering "ulimit -t 0", "ulimit -a" will show "-t: cpu time (seconds) 0", even though the actual limit as returned by getrlimit(...) will be 1. It can be verified by opening a subshell (which will not have the values of the parent shell in cache) and checking in it, or just by running a CPU intensive command like "echo '65536^1048576' | bc" and verifying that it dumps core after one second. Regardless of whether that is a misfeature in the shell, perhaps it would be better to return -EINVAL from setrlimit in such a case instead of cheating and setting to 1, as that does not really reflect the actual state of the process anymore. I do not however know what the ground for that decision was in the original 2.6.17 change, and whether there would be any "backward" compatibility issues, so I preferred not to touch that right now. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 03:30:31 -04:00
if (resource == RLIMIT_CPU && new_rlim.rlim_cur == 0) {
/*
* The caller is asking for an immediate RLIMIT_CPU
* expiry. But we use the zero value to mean "it was
* never set". So let's cheat and make it one second
* instead
*/
new_rlim.rlim_cur = 1;
}
task_lock(current->group_leader);
*old_rlim = new_rlim;
task_unlock(current->group_leader);
if (resource != RLIMIT_CPU)
goto out;
/*
* RLIMIT_CPU handling. Note that the kernel fails to return an error
* code if it rejected the user's attempt to set RLIMIT_CPU. This is a
* very long-standing error, and fixing it now risks breakage of
* applications, so we live with it
*/
if (new_rlim.rlim_cur == RLIM_INFINITY)
goto out;
it_prof_secs = cputime_to_secs(current->signal->it_prof_expires);
if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) {
unsigned long rlim_cur = new_rlim.rlim_cur;
cputime_t cputime;
cputime = secs_to_cputime(rlim_cur);
read_lock(&tasklist_lock);
spin_lock_irq(&current->sighand->siglock);
set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
spin_unlock_irq(&current->sighand->siglock);
read_unlock(&tasklist_lock);
}
out:
return 0;
}
/*
* It would make sense to put struct rusage in the task_struct,
* except that would make the task_struct be *really big*. After
* task_struct gets moved into malloc'ed memory, it would
* make sense to do this. It will make moving the rest of the information
* a lot simpler! (Which we're not doing right now because we're not
* measuring them yet).
*
* When sampling multiple threads for RUSAGE_SELF, under SMP we might have
* races with threads incrementing their own counters. But since word
* reads are atomic, we either get new values or old values and we don't
* care which for the sums. We always take the siglock to protect reading
* the c* fields from p->signal from races with exit.c updating those
* fields when reaping, so a sample either gets all the additions of a
* given child after it's reaped, or none so this sample is before reaping.
*
* Locking:
* We need to take the siglock for CHILDEREN, SELF and BOTH
* for the cases current multithreaded, non-current single threaded
* non-current multithreaded. Thread traversal is now safe with
* the siglock held.
* Strictly speaking, we donot need to take the siglock if we are current and
* single threaded, as no one else can take our signal_struct away, no one
* else can reap the children to update signal->c* counters, and no one else
* can race with the signal-> fields. If we do not take any lock, the
* signal-> fields could be read out of order while another thread was just
* exiting. So we should place a read memory barrier when we avoid the lock.
* On the writer side, write memory barrier is implied in __exit_signal
* as __exit_signal releases the siglock spinlock after updating the signal->
* fields. But we don't do this yet to keep things simple.
*
*/
static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r,
cputime_t *utimep, cputime_t *stimep)
{
*utimep = cputime_add(*utimep, t->utime);
*stimep = cputime_add(*stimep, t->stime);
r->ru_nvcsw += t->nvcsw;
r->ru_nivcsw += t->nivcsw;
r->ru_minflt += t->min_flt;
r->ru_majflt += t->maj_flt;
r->ru_inblock += task_io_get_inblock(t);
r->ru_oublock += task_io_get_oublock(t);
}
static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
{
struct task_struct *t;
unsigned long flags;
cputime_t utime, stime;
memset((char *) r, 0, sizeof *r);
utime = stime = cputime_zero;
if (who == RUSAGE_THREAD) {
accumulate_thread_rusage(p, r, &utime, &stime);
goto out;
}
if (!lock_task_sighand(p, &flags))
return;
switch (who) {
case RUSAGE_BOTH:
case RUSAGE_CHILDREN:
utime = p->signal->cutime;
stime = p->signal->cstime;
r->ru_nvcsw = p->signal->cnvcsw;
r->ru_nivcsw = p->signal->cnivcsw;
r->ru_minflt = p->signal->cmin_flt;
r->ru_majflt = p->signal->cmaj_flt;
r->ru_inblock = p->signal->cinblock;
r->ru_oublock = p->signal->coublock;
if (who == RUSAGE_CHILDREN)
break;
case RUSAGE_SELF:
utime = cputime_add(utime, p->signal->utime);
stime = cputime_add(stime, p->signal->stime);
r->ru_nvcsw += p->signal->nvcsw;
r->ru_nivcsw += p->signal->nivcsw;
r->ru_minflt += p->signal->min_flt;
r->ru_majflt += p->signal->maj_flt;
r->ru_inblock += p->signal->inblock;
r->ru_oublock += p->signal->oublock;
t = p;
do {
accumulate_thread_rusage(t, r, &utime, &stime);
t = next_thread(t);
} while (t != p);
break;
default:
BUG();
}
unlock_task_sighand(p, &flags);
out:
cputime_to_timeval(utime, &r->ru_utime);
cputime_to_timeval(stime, &r->ru_stime);
}
int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
{
struct rusage r;
k_getrusage(p, who, &r);
return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
}
asmlinkage long sys_getrusage(int who, struct rusage __user *ru)
{
if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN &&
who != RUSAGE_THREAD)
return -EINVAL;
return getrusage(current, who, ru);
}
asmlinkage long sys_umask(int mask)
{
mask = xchg(&current->fs->umask, mask & S_IRWXUGO);
return mask;
}
capabilities: introduce per-process capability bounding set The capability bounding set is a set beyond which capabilities cannot grow. Currently cap_bset is per-system. It can be manipulated through sysctl, but only init can add capabilities. Root can remove capabilities. By default it includes all caps except CAP_SETPCAP. This patch makes the bounding set per-process when file capabilities are enabled. It is inherited at fork from parent. Noone can add elements, CAP_SETPCAP is required to remove them. One example use of this is to start a safer container. For instance, until device namespaces or per-container device whitelists are introduced, it is best to take CAP_MKNOD away from a container. The bounding set will not affect pP and pE immediately. It will only affect pP' and pE' after subsequent exec()s. It also does not affect pI, and exec() does not constrain pI'. So to really start a shell with no way of regain CAP_MKNOD, you would do prctl(PR_CAPBSET_DROP, CAP_MKNOD); cap_t cap = cap_get_proc(); cap_value_t caparray[1]; caparray[0] = CAP_MKNOD; cap_set_flag(cap, CAP_INHERITABLE, 1, caparray, CAP_DROP); cap_set_proc(cap); cap_free(cap); The following test program will get and set the bounding set (but not pI). For instance ./bset get (lists capabilities in bset) ./bset drop cap_net_raw (starts shell with new bset) (use capset, setuid binary, or binary with file capabilities to try to increase caps) ************************************************************ cap_bound.c ************************************************************ #include <sys/prctl.h> #include <linux/capability.h> #include <sys/types.h> #include <unistd.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #ifndef PR_CAPBSET_READ #define PR_CAPBSET_READ 23 #endif #ifndef PR_CAPBSET_DROP #define PR_CAPBSET_DROP 24 #endif int usage(char *me) { printf("Usage: %s get\n", me); printf(" %s drop <capability>\n", me); return 1; } #define numcaps 32 char *captable[numcaps] = { "cap_chown", "cap_dac_override", "cap_dac_read_search", "cap_fowner", "cap_fsetid", "cap_kill", "cap_setgid", "cap_setuid", "cap_setpcap", "cap_linux_immutable", "cap_net_bind_service", "cap_net_broadcast", "cap_net_admin", "cap_net_raw", "cap_ipc_lock", "cap_ipc_owner", "cap_sys_module", "cap_sys_rawio", "cap_sys_chroot", "cap_sys_ptrace", "cap_sys_pacct", "cap_sys_admin", "cap_sys_boot", "cap_sys_nice", "cap_sys_resource", "cap_sys_time", "cap_sys_tty_config", "cap_mknod", "cap_lease", "cap_audit_write", "cap_audit_control", "cap_setfcap" }; int getbcap(void) { int comma=0; unsigned long i; int ret; printf("i know of %d capabilities\n", numcaps); printf("capability bounding set:"); for (i=0; i<numcaps; i++) { ret = prctl(PR_CAPBSET_READ, i); if (ret < 0) perror("prctl"); else if (ret==1) printf("%s%s", (comma++) ? ", " : " ", captable[i]); } printf("\n"); return 0; } int capdrop(char *str) { unsigned long i; int found=0; for (i=0; i<numcaps; i++) { if (strcmp(captable[i], str) == 0) { found=1; break; } } if (!found) return 1; if (prctl(PR_CAPBSET_DROP, i)) { perror("prctl"); return 1; } return 0; } int main(int argc, char *argv[]) { if (argc<2) return usage(argv[0]); if (strcmp(argv[1], "get")==0) return getbcap(); if (strcmp(argv[1], "drop")!=0 || argc<3) return usage(argv[0]); if (capdrop(argv[2])) { printf("unknown capability\n"); return 1; } return execl("/bin/bash", "/bin/bash", NULL); } ************************************************************ [serue@us.ibm.com: fix typo] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andrew G. Morgan <morgan@kernel.org> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Casey Schaufler <casey@schaufler-ca.com>a Signed-off-by: "Serge E. Hallyn" <serue@us.ibm.com> Tested-by: Jiri Slaby <jirislaby@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 01:29:45 -05:00
asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
long error = 0;
capabilities: implement per-process securebits Filesystem capability support makes it possible to do away with (set)uid-0 based privilege and use capabilities instead. That is, with filesystem support for capabilities but without this present patch, it is (conceptually) possible to manage a system with capabilities alone and never need to obtain privilege via (set)uid-0. Of course, conceptually isn't quite the same as currently possible since few user applications, certainly not enough to run a viable system, are currently prepared to leverage capabilities to exercise privilege. Further, many applications exist that may never get upgraded in this way, and the kernel will continue to want to support their setuid-0 base privilege needs. Where pure-capability applications evolve and replace setuid-0 binaries, it is desirable that there be a mechanisms by which they can contain their privilege. In addition to leveraging the per-process bounding and inheritable sets, this should include suppressing the privilege of the uid-0 superuser from the process' tree of children. The feature added by this patch can be leveraged to suppress the privilege associated with (set)uid-0. This suppression requires CAP_SETPCAP to initiate, and only immediately affects the 'current' process (it is inherited through fork()/exec()). This reimplementation differs significantly from the historical support for securebits which was system-wide, unwieldy and which has ultimately withered to a dead relic in the source of the modern kernel. With this patch applied a process, that is capable(CAP_SETPCAP), can now drop all legacy privilege (through uid=0) for itself and all subsequently fork()'d/exec()'d children with: prctl(PR_SET_SECUREBITS, 0x2f); This patch represents a no-op unless CONFIG_SECURITY_FILE_CAPABILITIES is enabled at configure time. [akpm@linux-foundation.org: fix uninitialised var warning] [serue@us.ibm.com: capabilities: use cap_task_prctl when !CONFIG_SECURITY] Signed-off-by: Andrew G. Morgan <morgan@kernel.org> Acked-by: Serge Hallyn <serue@us.ibm.com> Reviewed-by: James Morris <jmorris@namei.org> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: Paul Moore <paul.moore@hp.com> Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 05:13:40 -04:00
if (security_task_prctl(option, arg2, arg3, arg4, arg5, &error))
return error;
switch (option) {
case PR_SET_PDEATHSIG:
if (!valid_signal(arg2)) {
error = -EINVAL;
break;
}
current->pdeath_signal = arg2;
break;
case PR_GET_PDEATHSIG:
error = put_user(current->pdeath_signal, (int __user *)arg2);
break;
case PR_GET_DUMPABLE:
error = get_dumpable(current->mm);
break;
case PR_SET_DUMPABLE:
[PATCH] Fix prctl privilege escalation and suid_dumpable (CVE-2006-2451) Based on a patch from Ernie Petrides During security research, Red Hat discovered a behavioral flaw in core dump handling. A local user could create a program that would cause a core file to be dumped into a directory they would not normally have permissions to write to. This could lead to a denial of service (disk consumption), or allow the local user to gain root privileges. The prctl() system call should never allow to set "dumpable" to the value 2. Especially not for non-privileged users. This can be split into three cases: 1) running as root -- then core dumps will already be done as root, and so prctl(PR_SET_DUMPABLE, 2) is not useful 2) running as non-root w/setuid-to-root -- this is the debatable case 3) running as non-root w/setuid-to-non-root -- then you definitely do NOT want "dumpable" to get set to 2 because you have the privilege escalation vulnerability With case #2, the only potential usefulness is for a program that has designed to run with higher privilege (than the user invoking it) that wants to be able to create root-owned root-validated core dumps. This might be useful as a debugging aid, but would only be safe if the program had done a chdir() to a safe directory. There is no benefit to a production setuid-to-root utility, because it shouldn't be dumping core in the first place. If this is true, then the same debugging aid could also be accomplished with the "suid_dumpable" sysctl. Signed-off-by: Marcel Holtmann <marcel@holtmann.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-12 07:12:00 -04:00
if (arg2 < 0 || arg2 > 1) {
error = -EINVAL;
break;
}
set_dumpable(current->mm, arg2);
break;
case PR_SET_UNALIGN:
error = SET_UNALIGN_CTL(current, arg2);
break;
case PR_GET_UNALIGN:
error = GET_UNALIGN_CTL(current, arg2);
break;
case PR_SET_FPEMU:
error = SET_FPEMU_CTL(current, arg2);
break;
case PR_GET_FPEMU:
error = GET_FPEMU_CTL(current, arg2);
break;
case PR_SET_FPEXC:
error = SET_FPEXC_CTL(current, arg2);
break;
case PR_GET_FPEXC:
error = GET_FPEXC_CTL(current, arg2);
break;
case PR_GET_TIMING:
error = PR_TIMING_STATISTICAL;
break;
case PR_SET_TIMING:
if (arg2 != PR_TIMING_STATISTICAL)
error = -EINVAL;
break;
case PR_SET_NAME: {
struct task_struct *me = current;
unsigned char ncomm[sizeof(me->comm)];
ncomm[sizeof(me->comm)-1] = 0;
if (strncpy_from_user(ncomm, (char __user *)arg2,
sizeof(me->comm)-1) < 0)
return -EFAULT;
set_task_comm(me, ncomm);
return 0;
}
case PR_GET_NAME: {
struct task_struct *me = current;
unsigned char tcomm[sizeof(me->comm)];
get_task_comm(tcomm, me);
if (copy_to_user((char __user *)arg2, tcomm, sizeof(tcomm)))
return -EFAULT;
return 0;
}
case PR_GET_ENDIAN:
error = GET_ENDIAN(current, arg2);
break;
case PR_SET_ENDIAN:
error = SET_ENDIAN(current, arg2);
break;
case PR_GET_SECCOMP:
error = prctl_get_seccomp();
break;
case PR_SET_SECCOMP:
error = prctl_set_seccomp(arg2);
break;
case PR_GET_TSC:
error = GET_TSC_CTL(arg2);
break;
case PR_SET_TSC:
error = SET_TSC_CTL(arg2);
break;
default:
error = -EINVAL;
break;
}
return error;
}
asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep,
struct getcpu_cache __user *unused)
{
int err = 0;
int cpu = raw_smp_processor_id();
if (cpup)
err |= put_user(cpu, cpup);
if (nodep)
err |= put_user(cpu_to_node(cpu), nodep);
return err ? -EFAULT : 0;
}
char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
static void argv_cleanup(char **argv, char **envp)
{
argv_free(argv);
}
/**
* orderly_poweroff - Trigger an orderly system poweroff
* @force: force poweroff if command execution fails
*
* This may be called from any context to trigger a system shutdown.
* If the orderly shutdown fails, it will force an immediate shutdown.
*/
int orderly_poweroff(bool force)
{
int argc;
char **argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc);
static char *envp[] = {
"HOME=/",
"PATH=/sbin:/bin:/usr/sbin:/usr/bin",
NULL
};
int ret = -ENOMEM;
struct subprocess_info *info;
if (argv == NULL) {
printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
__func__, poweroff_cmd);
goto out;
}
info = call_usermodehelper_setup(argv[0], argv, envp, GFP_ATOMIC);
if (info == NULL) {
argv_free(argv);
goto out;
}
call_usermodehelper_setcleanup(info, argv_cleanup);
ret = call_usermodehelper_exec(info, UMH_NO_WAIT);
out:
if (ret && force) {
printk(KERN_WARNING "Failed to start orderly shutdown: "
"forcing the issue\n");
/* I guess this should try to kick off some daemon to
sync and poweroff asap. Or not even bother syncing
if we're doing an emergency shutdown? */
emergency_sync();
kernel_power_off();
}
return ret;
}
EXPORT_SYMBOL_GPL(orderly_poweroff);