remarkable-linux/include/linux/init_task.h
Andrew G. Morgan 3898b1b4eb 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 08:58:26 -07:00

215 lines
5.9 KiB
C

#ifndef _LINUX__INIT_TASK_H
#define _LINUX__INIT_TASK_H
#include <linux/file.h>
#include <linux/rcupdate.h>
#include <linux/irqflags.h>
#include <linux/utsname.h>
#include <linux/lockdep.h>
#include <linux/ipc.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/securebits.h>
#include <net/net_namespace.h>
#define INIT_FDTABLE \
{ \
.max_fds = NR_OPEN_DEFAULT, \
.fd = &init_files.fd_array[0], \
.close_on_exec = (fd_set *)&init_files.close_on_exec_init, \
.open_fds = (fd_set *)&init_files.open_fds_init, \
.rcu = RCU_HEAD_INIT, \
.next = NULL, \
}
#define INIT_FILES \
{ \
.count = ATOMIC_INIT(1), \
.fdt = &init_files.fdtab, \
.fdtab = INIT_FDTABLE, \
.file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock), \
.next_fd = 0, \
.close_on_exec_init = { { 0, } }, \
.open_fds_init = { { 0, } }, \
.fd_array = { NULL, } \
}
#define INIT_KIOCTX(name, which_mm) \
{ \
.users = ATOMIC_INIT(1), \
.dead = 0, \
.mm = &which_mm, \
.user_id = 0, \
.next = NULL, \
.wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.wait), \
.ctx_lock = __SPIN_LOCK_UNLOCKED(name.ctx_lock), \
.reqs_active = 0U, \
.max_reqs = ~0U, \
}
#define INIT_MM(name) \
{ \
.mm_rb = RB_ROOT, \
.pgd = swapper_pg_dir, \
.mm_users = ATOMIC_INIT(2), \
.mm_count = ATOMIC_INIT(1), \
.mmap_sem = __RWSEM_INITIALIZER(name.mmap_sem), \
.page_table_lock = __SPIN_LOCK_UNLOCKED(name.page_table_lock), \
.mmlist = LIST_HEAD_INIT(name.mmlist), \
.cpu_vm_mask = CPU_MASK_ALL, \
}
#define INIT_SIGNALS(sig) { \
.count = ATOMIC_INIT(1), \
.wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
.shared_pending = { \
.list = LIST_HEAD_INIT(sig.shared_pending.list), \
.signal = {{0}}}, \
.posix_timers = LIST_HEAD_INIT(sig.posix_timers), \
.cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \
.rlim = INIT_RLIMITS, \
}
extern struct nsproxy init_nsproxy;
#define INIT_NSPROXY(nsproxy) { \
.pid_ns = &init_pid_ns, \
.count = ATOMIC_INIT(1), \
.uts_ns = &init_uts_ns, \
.mnt_ns = NULL, \
INIT_NET_NS(net_ns) \
INIT_IPC_NS(ipc_ns) \
.user_ns = &init_user_ns, \
}
#define INIT_SIGHAND(sighand) { \
.count = ATOMIC_INIT(1), \
.action = { { { .sa_handler = NULL, } }, }, \
.siglock = __SPIN_LOCK_UNLOCKED(sighand.siglock), \
.signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(sighand.signalfd_wqh), \
}
extern struct group_info init_groups;
#define INIT_STRUCT_PID { \
.count = ATOMIC_INIT(1), \
.tasks = { \
{ .first = &init_task.pids[PIDTYPE_PID].node }, \
{ .first = &init_task.pids[PIDTYPE_PGID].node }, \
{ .first = &init_task.pids[PIDTYPE_SID].node }, \
}, \
.rcu = RCU_HEAD_INIT, \
.level = 0, \
.numbers = { { \
.nr = 0, \
.ns = &init_pid_ns, \
.pid_chain = { .next = NULL, .pprev = NULL }, \
}, } \
}
#define INIT_PID_LINK(type) \
{ \
.node = { \
.next = NULL, \
.pprev = &init_struct_pid.tasks[type].first, \
}, \
.pid = &init_struct_pid, \
}
#ifdef CONFIG_AUDITSYSCALL
#define INIT_IDS \
.loginuid = -1, \
.sessionid = -1,
#else
#define INIT_IDS
#endif
#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
/*
* Because of the reduced scope of CAP_SETPCAP when filesystem
* capabilities are in effect, it is safe to allow CAP_SETPCAP to
* be available in the default configuration.
*/
# define CAP_INIT_BSET CAP_FULL_SET
#else
# define CAP_INIT_BSET CAP_INIT_EFF_SET
#endif
/*
* INIT_TASK is used to set up the first task table, touch at
* your own risk!. Base=0, limit=0x1fffff (=2MB)
*/
#define INIT_TASK(tsk) \
{ \
.state = 0, \
.stack = &init_thread_info, \
.usage = ATOMIC_INIT(2), \
.flags = 0, \
.lock_depth = -1, \
.prio = MAX_PRIO-20, \
.static_prio = MAX_PRIO-20, \
.normal_prio = MAX_PRIO-20, \
.policy = SCHED_NORMAL, \
.cpus_allowed = CPU_MASK_ALL, \
.mm = NULL, \
.active_mm = &init_mm, \
.se = { \
.group_node = LIST_HEAD_INIT(tsk.se.group_node), \
}, \
.rt = { \
.run_list = LIST_HEAD_INIT(tsk.rt.run_list), \
.time_slice = HZ, \
.nr_cpus_allowed = NR_CPUS, \
}, \
.tasks = LIST_HEAD_INIT(tsk.tasks), \
.ptrace_children= LIST_HEAD_INIT(tsk.ptrace_children), \
.ptrace_list = LIST_HEAD_INIT(tsk.ptrace_list), \
.real_parent = &tsk, \
.parent = &tsk, \
.children = LIST_HEAD_INIT(tsk.children), \
.sibling = LIST_HEAD_INIT(tsk.sibling), \
.group_leader = &tsk, \
.group_info = &init_groups, \
.cap_effective = CAP_INIT_EFF_SET, \
.cap_inheritable = CAP_INIT_INH_SET, \
.cap_permitted = CAP_FULL_SET, \
.cap_bset = CAP_INIT_BSET, \
.securebits = SECUREBITS_DEFAULT, \
.user = INIT_USER, \
.comm = "swapper", \
.thread = INIT_THREAD, \
.fs = &init_fs, \
.files = &init_files, \
.signal = &init_signals, \
.sighand = &init_sighand, \
.nsproxy = &init_nsproxy, \
.pending = { \
.list = LIST_HEAD_INIT(tsk.pending.list), \
.signal = {{0}}}, \
.blocked = {{0}}, \
.alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \
.journal_info = NULL, \
.cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \
.fs_excl = ATOMIC_INIT(0), \
.pi_lock = __SPIN_LOCK_UNLOCKED(tsk.pi_lock), \
.pids = { \
[PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \
[PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \
[PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \
}, \
.dirties = INIT_PROP_LOCAL_SINGLE(dirties), \
INIT_IDS \
INIT_TRACE_IRQFLAGS \
INIT_LOCKDEP \
}
#define INIT_CPU_TIMERS(cpu_timers) \
{ \
LIST_HEAD_INIT(cpu_timers[0]), \
LIST_HEAD_INIT(cpu_timers[1]), \
LIST_HEAD_INIT(cpu_timers[2]), \
}
#endif