linux_old1/kernel/capability.c

248 lines
6.1 KiB
C
Raw Normal View History

/*
* linux/kernel/capability.c
*
* Copyright (C) 1997 Andrew Main <zefram@fysh.org>
*
V3 file capabilities: alter behavior of cap_setpcap The non-filesystem capability meaning of CAP_SETPCAP is that a process, p1, can change the capabilities of another process, p2. This is not the meaning that was intended for this capability at all, and this implementation came about purely because, without filesystem capabilities, there was no way to use capabilities without one process bestowing them on another. Since we now have a filesystem support for capabilities we can fix the implementation of CAP_SETPCAP. The most significant thing about this change is that, with it in effect, no process can set the capabilities of another process. The capabilities of a program are set via the capability convolution rules: pI(post-exec) = pI(pre-exec) pP(post-exec) = (X(aka cap_bset) & fP) | (pI(post-exec) & fI) pE(post-exec) = fE ? pP(post-exec) : 0 at exec() time. As such, the only influence the pre-exec() program can have on the post-exec() program's capabilities are through the pI capability set. The correct implementation for CAP_SETPCAP (and that enabled by this patch) is that it can be used to add extra pI capabilities to the current process - to be picked up by subsequent exec()s when the above convolution rules are applied. Here is how it works: Let's say we have a process, p. It has capability sets, pE, pP and pI. Generally, p, can change the value of its own pI to pI' where (pI' & ~pI) & ~pP = 0. That is, the only new things in pI' that were not present in pI need to be present in pP. The role of CAP_SETPCAP is basically to permit changes to pI beyond the above: if (pE & CAP_SETPCAP) { pI' = anything; /* ie., even (pI' & ~pI) & ~pP != 0 */ } This capability is useful for things like login, which (say, via pam_cap) might want to raise certain inheritable capabilities for use by the children of the logged-in user's shell, but those capabilities are not useful to or needed by the login program itself. One such use might be to limit who can run ping. You set the capabilities of the 'ping' program to be "= cap_net_raw+i", and then only shells that have (pI & CAP_NET_RAW) will be able to run it. Without CAP_SETPCAP implemented as described above, login(pam_cap) would have to also have (pP & CAP_NET_RAW) in order to raise this capability and pass it on through the inheritable set. Signed-off-by: Andrew Morgan <morgan@kernel.org> Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: Casey Schaufler <casey@schaufler-ca.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-18 18:05:59 +08:00
* Integrated into 2.1.97+, Andrew G. Morgan <morgan@kernel.org>
* 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net>
*/
#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/security.h>
#include <linux/syscalls.h>
pid namespaces: define is_global_init() and is_container_init() is_init() is an ambiguous name for the pid==1 check. Split it into is_global_init() and is_container_init(). A cgroup init has it's tsk->pid == 1. A global init also has it's tsk->pid == 1 and it's active pid namespace is the init_pid_ns. But rather than check the active pid namespace, compare the task structure with 'init_pid_ns.child_reaper', which is initialized during boot to the /sbin/init process and never changes. Changelog: 2.6.22-rc4-mm2-pidns1: - Use 'init_pid_ns.child_reaper' to determine if a given task is the global init (/sbin/init) process. This would improve performance and remove dependence on the task_pid(). 2.6.21-mm2-pidns2: - [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc, ppc,avr32}/traps.c for the _exception() call to is_global_init(). This way, we kill only the cgroup if the cgroup's init has a bug rather than force a kernel panic. [akpm@linux-foundation.org: fix comment] [sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c] [bunk@stusta.de: kernel/pid.c: remove unused exports] [sukadev@us.ibm.com: Fix capability.c to work with threaded init] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Acked-by: Pavel Emelianov <xemul@openvz.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Herbert Poetzel <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:52 +08:00
#include <linux/pid_namespace.h>
#include <asm/uaccess.h>
/*
* This lock protects task->cap_* for all tasks including current.
* Locking rule: acquire this prior to tasklist_lock.
*/
static DEFINE_SPINLOCK(task_capability_lock);
/*
* For sys_getproccap() and sys_setproccap(), any of the three
* capability set pointers may be NULL -- indicating that that set is
* uninteresting and/or not to be changed.
*/
/**
* sys_capget - get the capabilities of a given process.
* @header: pointer to struct that contains capability version and
* target pid data
* @dataptr: pointer to struct that contains the effective, permitted,
* and inheritable capabilities that are returned
*
* Returns 0 on success and < 0 on error.
*/
asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
{
int ret = 0;
pid_t pid;
__u32 version;
struct task_struct *target;
struct __user_cap_data_struct data;
if (get_user(version, &header->version))
return -EFAULT;
if (version != _LINUX_CAPABILITY_VERSION) {
if (put_user(_LINUX_CAPABILITY_VERSION, &header->version))
return -EFAULT;
return -EINVAL;
}
if (get_user(pid, &header->pid))
return -EFAULT;
if (pid < 0)
return -EINVAL;
spin_lock(&task_capability_lock);
read_lock(&tasklist_lock);
if (pid && pid != task_pid_vnr(current)) {
target = find_task_by_vpid(pid);
if (!target) {
ret = -ESRCH;
goto out;
}
} else
target = current;
ret = security_capget(target, &data.effective, &data.inheritable, &data.permitted);
out:
read_unlock(&tasklist_lock);
spin_unlock(&task_capability_lock);
if (!ret && copy_to_user(dataptr, &data, sizeof data))
return -EFAULT;
return ret;
}
/*
* cap_set_pg - set capabilities for all processes in a given process
* group. We call this holding task_capability_lock and tasklist_lock.
*/
static inline int cap_set_pg(int pgrp_nr, kernel_cap_t *effective,
kernel_cap_t *inheritable,
kernel_cap_t *permitted)
{
struct task_struct *g, *target;
int ret = -EPERM;
int found = 0;
struct pid *pgrp;
pgrp = find_vpid(pgrp_nr);
do_each_pid_task(pgrp, PIDTYPE_PGID, g) {
target = g;
while_each_thread(g, target) {
if (!security_capset_check(target, effective,
inheritable,
permitted)) {
security_capset_set(target, effective,
inheritable,
permitted);
ret = 0;
}
found = 1;
}
} while_each_pid_task(pgrp, PIDTYPE_PGID, g);
if (!found)
ret = 0;
return ret;
}
/*
* cap_set_all - set capabilities for all processes other than init
* and self. We call this holding task_capability_lock and tasklist_lock.
*/
static inline int cap_set_all(kernel_cap_t *effective,
kernel_cap_t *inheritable,
kernel_cap_t *permitted)
{
struct task_struct *g, *target;
int ret = -EPERM;
int found = 0;
do_each_thread(g, target) {
pid namespaces: define is_global_init() and is_container_init() is_init() is an ambiguous name for the pid==1 check. Split it into is_global_init() and is_container_init(). A cgroup init has it's tsk->pid == 1. A global init also has it's tsk->pid == 1 and it's active pid namespace is the init_pid_ns. But rather than check the active pid namespace, compare the task structure with 'init_pid_ns.child_reaper', which is initialized during boot to the /sbin/init process and never changes. Changelog: 2.6.22-rc4-mm2-pidns1: - Use 'init_pid_ns.child_reaper' to determine if a given task is the global init (/sbin/init) process. This would improve performance and remove dependence on the task_pid(). 2.6.21-mm2-pidns2: - [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc, ppc,avr32}/traps.c for the _exception() call to is_global_init(). This way, we kill only the cgroup if the cgroup's init has a bug rather than force a kernel panic. [akpm@linux-foundation.org: fix comment] [sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c] [bunk@stusta.de: kernel/pid.c: remove unused exports] [sukadev@us.ibm.com: Fix capability.c to work with threaded init] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Acked-by: Pavel Emelianov <xemul@openvz.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Herbert Poetzel <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:52 +08:00
if (target == current || is_container_init(target->group_leader))
continue;
found = 1;
if (security_capset_check(target, effective, inheritable,
permitted))
continue;
ret = 0;
security_capset_set(target, effective, inheritable, permitted);
} while_each_thread(g, target);
if (!found)
ret = 0;
return ret;
}
/**
* sys_capset - set capabilities for a process or a group of processes
* @header: pointer to struct that contains capability version and
* target pid data
* @data: pointer to struct that contains the effective, permitted,
* and inheritable capabilities
*
* Set capabilities for a given process, all processes, or all
* processes in a given process group.
*
* The restrictions on setting capabilities are specified as:
*
* [pid is for the 'target' task. 'current' is the calling task.]
*
* I: any raised capabilities must be a subset of the (old current) permitted
* P: any raised capabilities must be a subset of the (old current) permitted
* E: must be set to a subset of (new target) permitted
*
* Returns 0 on success and < 0 on error.
*/
asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
{
kernel_cap_t inheritable, permitted, effective;
__u32 version;
struct task_struct *target;
int ret;
pid_t pid;
if (get_user(version, &header->version))
return -EFAULT;
if (version != _LINUX_CAPABILITY_VERSION) {
if (put_user(_LINUX_CAPABILITY_VERSION, &header->version))
return -EFAULT;
return -EINVAL;
}
if (get_user(pid, &header->pid))
return -EFAULT;
if (pid && pid != task_pid_vnr(current) && !capable(CAP_SETPCAP))
return -EPERM;
if (copy_from_user(&effective, &data->effective, sizeof(effective)) ||
copy_from_user(&inheritable, &data->inheritable, sizeof(inheritable)) ||
copy_from_user(&permitted, &data->permitted, sizeof(permitted)))
return -EFAULT;
spin_lock(&task_capability_lock);
read_lock(&tasklist_lock);
if (pid > 0 && pid != task_pid_vnr(current)) {
target = find_task_by_vpid(pid);
if (!target) {
ret = -ESRCH;
goto out;
}
} else
target = current;
ret = 0;
/* having verified that the proposed changes are legal,
we now put them into effect. */
if (pid < 0) {
if (pid == -1) /* all procs other than current and init */
ret = cap_set_all(&effective, &inheritable, &permitted);
else /* all procs in process group */
ret = cap_set_pg(-pid, &effective, &inheritable,
&permitted);
} else {
ret = security_capset_check(target, &effective, &inheritable,
&permitted);
if (!ret)
security_capset_set(target, &effective, &inheritable,
&permitted);
}
out:
read_unlock(&tasklist_lock);
spin_unlock(&task_capability_lock);
return ret;
}
int __capable(struct task_struct *t, int cap)
{
if (security_capable(t, cap) == 0) {
t->flags |= PF_SUPERPRIV;
return 1;
}
return 0;
}
int capable(int cap)
{
return __capable(current, cap);
}
EXPORT_SYMBOL(capable);