linux/kernel/pid_namespace.c

457 lines
11 KiB
C
Raw Normal View History

/*
* Pid namespaces
*
* Authors:
* (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc.
* (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM
* Many thanks to Oleg Nesterov for comments and help
*
*/
#include <linux/pid.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/syscalls.h>
#include <linux/cred.h>
#include <linux/err.h>
#include <linux/acct.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 09:04:11 +01:00
#include <linux/slab.h>
#include <linux/proc_ns.h>
pidns: add reboot_pid_ns() to handle the reboot syscall In the case of a child pid namespace, rebooting the system does not really makes sense. When the pid namespace is used in conjunction with the other namespaces in order to create a linux container, the reboot syscall leads to some problems. A container can reboot the host. That can be fixed by dropping the sys_reboot capability but we are unable to correctly to poweroff/ halt/reboot a container and the container stays stuck at the shutdown time with the container's init process waiting indefinitively. After several attempts, no solution from userspace was found to reliabily handle the shutdown from a container. This patch propose to make the init process of the child pid namespace to exit with a signal status set to : SIGINT if the child pid namespace called "halt/poweroff" and SIGHUP if the child pid namespace called "reboot". When the reboot syscall is called and we are not in the initial pid namespace, we kill the pid namespace for "HALT", "POWEROFF", "RESTART", and "RESTART2". Otherwise we return EINVAL. Returning EINVAL is also an easy way to check if this feature is supported by the kernel when invoking another 'reboot' option like CAD. By this way the parent process of the child pid namespace knows if it rebooted or not and can take the right decision. Test case: ========== #include <alloca.h> #include <stdio.h> #include <sched.h> #include <unistd.h> #include <signal.h> #include <sys/reboot.h> #include <sys/types.h> #include <sys/wait.h> #include <linux/reboot.h> static int do_reboot(void *arg) { int *cmd = arg; if (reboot(*cmd)) printf("failed to reboot(%d): %m\n", *cmd); } int test_reboot(int cmd, int sig) { long stack_size = 4096; void *stack = alloca(stack_size) + stack_size; int status; pid_t ret; ret = clone(do_reboot, stack, CLONE_NEWPID | SIGCHLD, &cmd); if (ret < 0) { printf("failed to clone: %m\n"); return -1; } if (wait(&status) < 0) { printf("unexpected wait error: %m\n"); return -1; } if (!WIFSIGNALED(status)) { printf("child process exited but was not signaled\n"); return -1; } if (WTERMSIG(status) != sig) { printf("signal termination is not the one expected\n"); return -1; } return 0; } int main(int argc, char *argv[]) { int status; status = test_reboot(LINUX_REBOOT_CMD_RESTART, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_RESTART2, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART2) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_HALT, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_HALT) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_POWER_OFF, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_POWERR_OFF) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_CAD_ON, -1); if (status >= 0) { printf("reboot(LINUX_REBOOT_CMD_CAD_ON) should have failed\n"); return 1; } printf("reboot(LINUX_REBOOT_CMD_CAD_ON) has failed as expected\n"); return 0; } [akpm@linux-foundation.org: tweak and add comments] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Tested-by: Serge Hallyn <serge.hallyn@canonical.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-28 23:42:51 +02:00
#include <linux/reboot.h>
#include <linux/export.h>
#include <linux/sched/task.h>
#include <linux/sched/signal.h>
struct pid_cache {
int nr_ids;
char name[16];
struct kmem_cache *cachep;
struct list_head list;
};
static LIST_HEAD(pid_caches_lh);
static DEFINE_MUTEX(pid_caches_mutex);
static struct kmem_cache *pid_ns_cachep;
/*
* creates the kmem cache to allocate pids from.
* @nr_ids: the number of numerical ids this pid will have to carry
*/
static struct kmem_cache *create_pid_cachep(int nr_ids)
{
struct pid_cache *pcache;
struct kmem_cache *cachep;
mutex_lock(&pid_caches_mutex);
list_for_each_entry(pcache, &pid_caches_lh, list)
if (pcache->nr_ids == nr_ids)
goto out;
pcache = kmalloc(sizeof(struct pid_cache), GFP_KERNEL);
if (pcache == NULL)
goto err_alloc;
snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids);
cachep = kmem_cache_create(pcache->name,
sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid),
0, SLAB_HWCACHE_ALIGN, NULL);
if (cachep == NULL)
goto err_cachep;
pcache->nr_ids = nr_ids;
pcache->cachep = cachep;
list_add(&pcache->list, &pid_caches_lh);
out:
mutex_unlock(&pid_caches_mutex);
return pcache->cachep;
err_cachep:
kfree(pcache);
err_alloc:
mutex_unlock(&pid_caches_mutex);
return NULL;
}
static void proc_cleanup_work(struct work_struct *work)
{
struct pid_namespace *ns = container_of(work, struct pid_namespace, proc_work);
pid_ns_release_proc(ns);
}
pidns: limit the nesting depth of pid namespaces 'struct pid' is a "variable sized struct" - a header with an array of upids at the end. The size of the array depends on a level (depth) of pid namespaces. Now a level of pidns is not limited, so 'struct pid' can be more than one page. Looks reasonable, that it should be less than a page. MAX_PIS_NS_LEVEL is not calculated from PAGE_SIZE, because in this case it depends on architectures, config options and it will be reduced, if someone adds a new fields in struct pid or struct upid. I suggest to set MAX_PIS_NS_LEVEL = 32, because it saves ability to expand "struct pid" and it's more than enough for all known for me use-cases. When someone finds a reasonable use case, we can add a config option or a sysctl parameter. In addition it will reduce the effect of another problem, when we have many nested namespaces and the oldest one starts dying. zap_pid_ns_processe will be called for each namespace and find_vpid will be called for each process in a namespace. find_vpid will be called minimum max_level^2 / 2 times. The reason of that is that when we found a bit in pidmap, we can't determine this pidns is top for this process or it isn't. vpid is a heavy operation, so a fork bomb, which create many nested namespace, can make a system inaccessible for a long time. For example my system becomes inaccessible for a few minutes with 4000 processes. [akpm@linux-foundation.org: return -EINVAL in response to excessive nesting, not -ENOMEM] Signed-off-by: Andrew Vagin <avagin@openvz.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-25 22:38:07 +02:00
/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
#define MAX_PID_NS_LEVEL 32
static struct ucounts *inc_pid_namespaces(struct user_namespace *ns)
{
return inc_ucount(ns, current_euid(), UCOUNT_PID_NAMESPACES);
}
static void dec_pid_namespaces(struct ucounts *ucounts)
{
dec_ucount(ucounts, UCOUNT_PID_NAMESPACES);
}
static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns,
struct pid_namespace *parent_pid_ns)
{
struct pid_namespace *ns;
unsigned int level = parent_pid_ns->level + 1;
struct ucounts *ucounts;
pidns: limit the nesting depth of pid namespaces 'struct pid' is a "variable sized struct" - a header with an array of upids at the end. The size of the array depends on a level (depth) of pid namespaces. Now a level of pidns is not limited, so 'struct pid' can be more than one page. Looks reasonable, that it should be less than a page. MAX_PIS_NS_LEVEL is not calculated from PAGE_SIZE, because in this case it depends on architectures, config options and it will be reduced, if someone adds a new fields in struct pid or struct upid. I suggest to set MAX_PIS_NS_LEVEL = 32, because it saves ability to expand "struct pid" and it's more than enough for all known for me use-cases. When someone finds a reasonable use case, we can add a config option or a sysctl parameter. In addition it will reduce the effect of another problem, when we have many nested namespaces and the oldest one starts dying. zap_pid_ns_processe will be called for each namespace and find_vpid will be called for each process in a namespace. find_vpid will be called minimum max_level^2 / 2 times. The reason of that is that when we found a bit in pidmap, we can't determine this pidns is top for this process or it isn't. vpid is a heavy operation, so a fork bomb, which create many nested namespace, can make a system inaccessible for a long time. For example my system becomes inaccessible for a few minutes with 4000 processes. [akpm@linux-foundation.org: return -EINVAL in response to excessive nesting, not -ENOMEM] Signed-off-by: Andrew Vagin <avagin@openvz.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-25 22:38:07 +02:00
int i;
int err;
err = -ENOSPC;
if (level > MAX_PID_NS_LEVEL)
goto out;
ucounts = inc_pid_namespaces(user_ns);
if (!ucounts)
pidns: limit the nesting depth of pid namespaces 'struct pid' is a "variable sized struct" - a header with an array of upids at the end. The size of the array depends on a level (depth) of pid namespaces. Now a level of pidns is not limited, so 'struct pid' can be more than one page. Looks reasonable, that it should be less than a page. MAX_PIS_NS_LEVEL is not calculated from PAGE_SIZE, because in this case it depends on architectures, config options and it will be reduced, if someone adds a new fields in struct pid or struct upid. I suggest to set MAX_PIS_NS_LEVEL = 32, because it saves ability to expand "struct pid" and it's more than enough for all known for me use-cases. When someone finds a reasonable use case, we can add a config option or a sysctl parameter. In addition it will reduce the effect of another problem, when we have many nested namespaces and the oldest one starts dying. zap_pid_ns_processe will be called for each namespace and find_vpid will be called for each process in a namespace. find_vpid will be called minimum max_level^2 / 2 times. The reason of that is that when we found a bit in pidmap, we can't determine this pidns is top for this process or it isn't. vpid is a heavy operation, so a fork bomb, which create many nested namespace, can make a system inaccessible for a long time. For example my system becomes inaccessible for a few minutes with 4000 processes. [akpm@linux-foundation.org: return -EINVAL in response to excessive nesting, not -ENOMEM] Signed-off-by: Andrew Vagin <avagin@openvz.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-25 22:38:07 +02:00
goto out;
pidns: limit the nesting depth of pid namespaces 'struct pid' is a "variable sized struct" - a header with an array of upids at the end. The size of the array depends on a level (depth) of pid namespaces. Now a level of pidns is not limited, so 'struct pid' can be more than one page. Looks reasonable, that it should be less than a page. MAX_PIS_NS_LEVEL is not calculated from PAGE_SIZE, because in this case it depends on architectures, config options and it will be reduced, if someone adds a new fields in struct pid or struct upid. I suggest to set MAX_PIS_NS_LEVEL = 32, because it saves ability to expand "struct pid" and it's more than enough for all known for me use-cases. When someone finds a reasonable use case, we can add a config option or a sysctl parameter. In addition it will reduce the effect of another problem, when we have many nested namespaces and the oldest one starts dying. zap_pid_ns_processe will be called for each namespace and find_vpid will be called for each process in a namespace. find_vpid will be called minimum max_level^2 / 2 times. The reason of that is that when we found a bit in pidmap, we can't determine this pidns is top for this process or it isn't. vpid is a heavy operation, so a fork bomb, which create many nested namespace, can make a system inaccessible for a long time. For example my system becomes inaccessible for a few minutes with 4000 processes. [akpm@linux-foundation.org: return -EINVAL in response to excessive nesting, not -ENOMEM] Signed-off-by: Andrew Vagin <avagin@openvz.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-25 22:38:07 +02:00
err = -ENOMEM;
ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
if (ns == NULL)
goto out_dec;
ns->pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
if (!ns->pidmap[0].page)
goto out_free;
ns->pid_cachep = create_pid_cachep(level + 1);
if (ns->pid_cachep == NULL)
goto out_free_map;
err = ns_alloc_inum(&ns->ns);
if (err)
goto out_free_map;
ns->ns.ops = &pidns_operations;
kref_init(&ns->kref);
ns->level = level;
ns->parent = get_pid_ns(parent_pid_ns);
ns->user_ns = get_user_ns(user_ns);
ns->ucounts = ucounts;
ns->nr_hashed = PIDNS_HASH_ADDING;
INIT_WORK(&ns->proc_work, proc_cleanup_work);
set_bit(0, ns->pidmap[0].page);
atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
for (i = 1; i < PIDMAP_ENTRIES; i++)
atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
return ns;
out_free_map:
kfree(ns->pidmap[0].page);
out_free:
kmem_cache_free(pid_ns_cachep, ns);
out_dec:
dec_pid_namespaces(ucounts);
out:
return ERR_PTR(err);
}
static void delayed_free_pidns(struct rcu_head *p)
{
struct pid_namespace *ns = container_of(p, struct pid_namespace, rcu);
dec_pid_namespaces(ns->ucounts);
put_user_ns(ns->user_ns);
kmem_cache_free(pid_ns_cachep, ns);
}
static void destroy_pid_namespace(struct pid_namespace *ns)
{
int i;
ns_free_inum(&ns->ns);
for (i = 0; i < PIDMAP_ENTRIES; i++)
kfree(ns->pidmap[i].page);
call_rcu(&ns->rcu, delayed_free_pidns);
}
struct pid_namespace *copy_pid_ns(unsigned long flags,
struct user_namespace *user_ns, struct pid_namespace *old_ns)
{
if (!(flags & CLONE_NEWPID))
return get_pid_ns(old_ns);
if (task_active_pid_ns(current) != old_ns)
return ERR_PTR(-EINVAL);
return create_pid_namespace(user_ns, old_ns);
}
static void free_pid_ns(struct kref *kref)
{
struct pid_namespace *ns;
ns = container_of(kref, struct pid_namespace, kref);
destroy_pid_namespace(ns);
}
void put_pid_ns(struct pid_namespace *ns)
{
struct pid_namespace *parent;
while (ns != &init_pid_ns) {
parent = ns->parent;
if (!kref_put(&ns->kref, free_pid_ns))
break;
ns = parent;
}
}
EXPORT_SYMBOL_GPL(put_pid_ns);
void zap_pid_ns_processes(struct pid_namespace *pid_ns)
{
int nr;
int rc;
struct task_struct *task, *me = current;
int init_pids = thread_group_leader(me) ? 1 : 2;
/* Don't allow any more processes into the pid namespace */
disable_pid_allocation(pid_ns);
/*
* Ignore SIGCHLD causing any terminated children to autoreap.
* This speeds up the namespace shutdown, plus see the comment
* below.
*/
spin_lock_irq(&me->sighand->siglock);
me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN;
spin_unlock_irq(&me->sighand->siglock);
/*
* The last thread in the cgroup-init thread group is terminating.
* Find remaining pid_ts in the namespace, signal and wait for them
* to exit.
*
* Note: This signals each threads in the namespace - even those that
* belong to the same thread group, To avoid this, we would have
* to walk the entire tasklist looking a processes in this
* namespace, but that could be unnecessarily expensive if the
* pid namespace has just a few processes. Or we need to
* maintain a tasklist for each pid namespace.
*
*/
read_lock(&tasklist_lock);
nr = next_pidmap(pid_ns, 1);
while (nr > 0) {
rcu_read_lock();
task = pid_task(find_vpid(nr), PIDTYPE_PID);
if (task && !__fatal_signal_pending(task))
send_sig_info(SIGKILL, SEND_SIG_FORCED, task);
rcu_read_unlock();
nr = next_pidmap(pid_ns, nr);
}
read_unlock(&tasklist_lock);
/*
* Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD.
* sys_wait4() will also block until our children traced from the
* parent namespace are detached and become EXIT_DEAD.
*/
do {
clear_thread_flag(TIF_SIGPENDING);
rc = sys_wait4(-1, NULL, __WALL, NULL);
} while (rc != -ECHILD);
pidns: guarantee that the pidns init will be the last pidns process reaped Today we have a twofold bug. Sometimes release_task on pid == 1 in a pid namespace can run before other processes in a pid namespace have had release task called. With the result that pid_ns_release_proc can be called before the last proc_flus_task() is done using upid->ns->proc_mnt, resulting in the use of a stale pointer. This same set of circumstances can lead to waitpid(...) returning for a processes started with clone(CLONE_NEWPID) before the every process in the pid namespace has actually exited. To fix this modify zap_pid_ns_processess wait until all other processes in the pid namespace have exited, even EXIT_DEAD zombies. The delay_group_leader and related tests ensure that the thread gruop leader will be the last thread of a process group to be reaped, or to become EXIT_DEAD and self reap. With the change to zap_pid_ns_processes we get the guarantee that pid == 1 in a pid namespace will be the last task that release_task is called on. With pid == 1 being the last task to pass through release_task pid_ns_release_proc can no longer be called too early nor can wait return before all of the EXIT_DEAD tasks in a pid namespace have exited. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Louis Rilling <louis.rilling@kerlabs.com> Cc: Mike Galbraith <efault@gmx.de> Acked-by: Pavel Emelyanov <xemul@parallels.com> Tested-by: Andrew Wagin <avagin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-20 21:53:03 +02:00
/*
* sys_wait4() above can't reap the EXIT_DEAD children but we do not
* really care, we could reparent them to the global init. We could
* exit and reap ->child_reaper even if it is not the last thread in
* this pid_ns, free_pid(nr_hashed == 0) calls proc_cleanup_work(),
* pid_ns can not go away until proc_kill_sb() drops the reference.
*
* But this ns can also have other tasks injected by setns()+fork().
* Again, ignoring the user visible semantics we do not really need
* to wait until they are all reaped, but they can be reparented to
* us and thus we need to ensure that pid->child_reaper stays valid
* until they all go away. See free_pid()->wake_up_process().
*
* We rely on ignored SIGCHLD, an injected zombie must be autoreaped
* if reparented.
pidns: guarantee that the pidns init will be the last pidns process reaped Today we have a twofold bug. Sometimes release_task on pid == 1 in a pid namespace can run before other processes in a pid namespace have had release task called. With the result that pid_ns_release_proc can be called before the last proc_flus_task() is done using upid->ns->proc_mnt, resulting in the use of a stale pointer. This same set of circumstances can lead to waitpid(...) returning for a processes started with clone(CLONE_NEWPID) before the every process in the pid namespace has actually exited. To fix this modify zap_pid_ns_processess wait until all other processes in the pid namespace have exited, even EXIT_DEAD zombies. The delay_group_leader and related tests ensure that the thread gruop leader will be the last thread of a process group to be reaped, or to become EXIT_DEAD and self reap. With the change to zap_pid_ns_processes we get the guarantee that pid == 1 in a pid namespace will be the last task that release_task is called on. With pid == 1 being the last task to pass through release_task pid_ns_release_proc can no longer be called too early nor can wait return before all of the EXIT_DEAD tasks in a pid namespace have exited. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Louis Rilling <louis.rilling@kerlabs.com> Cc: Mike Galbraith <efault@gmx.de> Acked-by: Pavel Emelyanov <xemul@parallels.com> Tested-by: Andrew Wagin <avagin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-20 21:53:03 +02:00
*/
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (pid_ns->nr_hashed == init_pids)
pidns: guarantee that the pidns init will be the last pidns process reaped Today we have a twofold bug. Sometimes release_task on pid == 1 in a pid namespace can run before other processes in a pid namespace have had release task called. With the result that pid_ns_release_proc can be called before the last proc_flus_task() is done using upid->ns->proc_mnt, resulting in the use of a stale pointer. This same set of circumstances can lead to waitpid(...) returning for a processes started with clone(CLONE_NEWPID) before the every process in the pid namespace has actually exited. To fix this modify zap_pid_ns_processess wait until all other processes in the pid namespace have exited, even EXIT_DEAD zombies. The delay_group_leader and related tests ensure that the thread gruop leader will be the last thread of a process group to be reaped, or to become EXIT_DEAD and self reap. With the change to zap_pid_ns_processes we get the guarantee that pid == 1 in a pid namespace will be the last task that release_task is called on. With pid == 1 being the last task to pass through release_task pid_ns_release_proc can no longer be called too early nor can wait return before all of the EXIT_DEAD tasks in a pid namespace have exited. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Louis Rilling <louis.rilling@kerlabs.com> Cc: Mike Galbraith <efault@gmx.de> Acked-by: Pavel Emelyanov <xemul@parallels.com> Tested-by: Andrew Wagin <avagin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-20 21:53:03 +02:00
break;
schedule();
}
__set_current_state(TASK_RUNNING);
pidns: guarantee that the pidns init will be the last pidns process reaped Today we have a twofold bug. Sometimes release_task on pid == 1 in a pid namespace can run before other processes in a pid namespace have had release task called. With the result that pid_ns_release_proc can be called before the last proc_flus_task() is done using upid->ns->proc_mnt, resulting in the use of a stale pointer. This same set of circumstances can lead to waitpid(...) returning for a processes started with clone(CLONE_NEWPID) before the every process in the pid namespace has actually exited. To fix this modify zap_pid_ns_processess wait until all other processes in the pid namespace have exited, even EXIT_DEAD zombies. The delay_group_leader and related tests ensure that the thread gruop leader will be the last thread of a process group to be reaped, or to become EXIT_DEAD and self reap. With the change to zap_pid_ns_processes we get the guarantee that pid == 1 in a pid namespace will be the last task that release_task is called on. With pid == 1 being the last task to pass through release_task pid_ns_release_proc can no longer be called too early nor can wait return before all of the EXIT_DEAD tasks in a pid namespace have exited. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Louis Rilling <louis.rilling@kerlabs.com> Cc: Mike Galbraith <efault@gmx.de> Acked-by: Pavel Emelyanov <xemul@parallels.com> Tested-by: Andrew Wagin <avagin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-20 21:53:03 +02:00
pidns: add reboot_pid_ns() to handle the reboot syscall In the case of a child pid namespace, rebooting the system does not really makes sense. When the pid namespace is used in conjunction with the other namespaces in order to create a linux container, the reboot syscall leads to some problems. A container can reboot the host. That can be fixed by dropping the sys_reboot capability but we are unable to correctly to poweroff/ halt/reboot a container and the container stays stuck at the shutdown time with the container's init process waiting indefinitively. After several attempts, no solution from userspace was found to reliabily handle the shutdown from a container. This patch propose to make the init process of the child pid namespace to exit with a signal status set to : SIGINT if the child pid namespace called "halt/poweroff" and SIGHUP if the child pid namespace called "reboot". When the reboot syscall is called and we are not in the initial pid namespace, we kill the pid namespace for "HALT", "POWEROFF", "RESTART", and "RESTART2". Otherwise we return EINVAL. Returning EINVAL is also an easy way to check if this feature is supported by the kernel when invoking another 'reboot' option like CAD. By this way the parent process of the child pid namespace knows if it rebooted or not and can take the right decision. Test case: ========== #include <alloca.h> #include <stdio.h> #include <sched.h> #include <unistd.h> #include <signal.h> #include <sys/reboot.h> #include <sys/types.h> #include <sys/wait.h> #include <linux/reboot.h> static int do_reboot(void *arg) { int *cmd = arg; if (reboot(*cmd)) printf("failed to reboot(%d): %m\n", *cmd); } int test_reboot(int cmd, int sig) { long stack_size = 4096; void *stack = alloca(stack_size) + stack_size; int status; pid_t ret; ret = clone(do_reboot, stack, CLONE_NEWPID | SIGCHLD, &cmd); if (ret < 0) { printf("failed to clone: %m\n"); return -1; } if (wait(&status) < 0) { printf("unexpected wait error: %m\n"); return -1; } if (!WIFSIGNALED(status)) { printf("child process exited but was not signaled\n"); return -1; } if (WTERMSIG(status) != sig) { printf("signal termination is not the one expected\n"); return -1; } return 0; } int main(int argc, char *argv[]) { int status; status = test_reboot(LINUX_REBOOT_CMD_RESTART, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_RESTART2, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART2) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_HALT, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_HALT) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_POWER_OFF, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_POWERR_OFF) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_CAD_ON, -1); if (status >= 0) { printf("reboot(LINUX_REBOOT_CMD_CAD_ON) should have failed\n"); return 1; } printf("reboot(LINUX_REBOOT_CMD_CAD_ON) has failed as expected\n"); return 0; } [akpm@linux-foundation.org: tweak and add comments] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Tested-by: Serge Hallyn <serge.hallyn@canonical.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-28 23:42:51 +02:00
if (pid_ns->reboot)
current->signal->group_exit_code = pid_ns->reboot;
acct_exit_ns(pid_ns);
return;
}
#ifdef CONFIG_CHECKPOINT_RESTORE
static int pid_ns_ctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct pid_namespace *pid_ns = task_active_pid_ns(current);
struct ctl_table tmp = *table;
if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
/*
* Writing directly to ns' last_pid field is OK, since this field
* is volatile in a living namespace anyway and a code writing to
* it should synchronize its usage with external means.
*/
tmp.data = &pid_ns->last_pid;
return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
}
extern int pid_max;
static int zero = 0;
static struct ctl_table pid_ns_ctl_table[] = {
{
.procname = "ns_last_pid",
.maxlen = sizeof(int),
.mode = 0666, /* permissions are checked in the handler */
.proc_handler = pid_ns_ctl_handler,
.extra1 = &zero,
.extra2 = &pid_max,
},
{ }
};
static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } };
#endif /* CONFIG_CHECKPOINT_RESTORE */
pidns: add reboot_pid_ns() to handle the reboot syscall In the case of a child pid namespace, rebooting the system does not really makes sense. When the pid namespace is used in conjunction with the other namespaces in order to create a linux container, the reboot syscall leads to some problems. A container can reboot the host. That can be fixed by dropping the sys_reboot capability but we are unable to correctly to poweroff/ halt/reboot a container and the container stays stuck at the shutdown time with the container's init process waiting indefinitively. After several attempts, no solution from userspace was found to reliabily handle the shutdown from a container. This patch propose to make the init process of the child pid namespace to exit with a signal status set to : SIGINT if the child pid namespace called "halt/poweroff" and SIGHUP if the child pid namespace called "reboot". When the reboot syscall is called and we are not in the initial pid namespace, we kill the pid namespace for "HALT", "POWEROFF", "RESTART", and "RESTART2". Otherwise we return EINVAL. Returning EINVAL is also an easy way to check if this feature is supported by the kernel when invoking another 'reboot' option like CAD. By this way the parent process of the child pid namespace knows if it rebooted or not and can take the right decision. Test case: ========== #include <alloca.h> #include <stdio.h> #include <sched.h> #include <unistd.h> #include <signal.h> #include <sys/reboot.h> #include <sys/types.h> #include <sys/wait.h> #include <linux/reboot.h> static int do_reboot(void *arg) { int *cmd = arg; if (reboot(*cmd)) printf("failed to reboot(%d): %m\n", *cmd); } int test_reboot(int cmd, int sig) { long stack_size = 4096; void *stack = alloca(stack_size) + stack_size; int status; pid_t ret; ret = clone(do_reboot, stack, CLONE_NEWPID | SIGCHLD, &cmd); if (ret < 0) { printf("failed to clone: %m\n"); return -1; } if (wait(&status) < 0) { printf("unexpected wait error: %m\n"); return -1; } if (!WIFSIGNALED(status)) { printf("child process exited but was not signaled\n"); return -1; } if (WTERMSIG(status) != sig) { printf("signal termination is not the one expected\n"); return -1; } return 0; } int main(int argc, char *argv[]) { int status; status = test_reboot(LINUX_REBOOT_CMD_RESTART, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_RESTART2, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART2) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_HALT, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_HALT) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_POWER_OFF, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_POWERR_OFF) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_CAD_ON, -1); if (status >= 0) { printf("reboot(LINUX_REBOOT_CMD_CAD_ON) should have failed\n"); return 1; } printf("reboot(LINUX_REBOOT_CMD_CAD_ON) has failed as expected\n"); return 0; } [akpm@linux-foundation.org: tweak and add comments] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Tested-by: Serge Hallyn <serge.hallyn@canonical.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-28 23:42:51 +02:00
int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
{
if (pid_ns == &init_pid_ns)
return 0;
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART2:
case LINUX_REBOOT_CMD_RESTART:
pid_ns->reboot = SIGHUP;
break;
case LINUX_REBOOT_CMD_POWER_OFF:
case LINUX_REBOOT_CMD_HALT:
pid_ns->reboot = SIGINT;
break;
default:
return -EINVAL;
}
read_lock(&tasklist_lock);
force_sig(SIGKILL, pid_ns->child_reaper);
read_unlock(&tasklist_lock);
do_exit(0);
/* Not reached */
return 0;
}
static inline struct pid_namespace *to_pid_ns(struct ns_common *ns)
{
return container_of(ns, struct pid_namespace, ns);
}
static struct ns_common *pidns_get(struct task_struct *task)
{
struct pid_namespace *ns;
rcu_read_lock();
ns = task_active_pid_ns(task);
if (ns)
get_pid_ns(ns);
rcu_read_unlock();
return ns ? &ns->ns : NULL;
}
static void pidns_put(struct ns_common *ns)
{
put_pid_ns(to_pid_ns(ns));
}
static int pidns_install(struct nsproxy *nsproxy, struct ns_common *ns)
{
struct pid_namespace *active = task_active_pid_ns(current);
struct pid_namespace *ancestor, *new = to_pid_ns(ns);
if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) ||
!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
return -EPERM;
/*
* Only allow entering the current active pid namespace
* or a child of the current active pid namespace.
*
* This is required for fork to return a usable pid value and
* this maintains the property that processes and their
* children can not escape their current pid namespace.
*/
if (new->level < active->level)
return -EINVAL;
ancestor = new;
while (ancestor->level > active->level)
ancestor = ancestor->parent;
if (ancestor != active)
return -EINVAL;
put_pid_ns(nsproxy->pid_ns_for_children);
nsproxy->pid_ns_for_children = get_pid_ns(new);
return 0;
}
static struct ns_common *pidns_get_parent(struct ns_common *ns)
{
struct pid_namespace *active = task_active_pid_ns(current);
struct pid_namespace *pid_ns, *p;
/* See if the parent is in the current namespace */
pid_ns = p = to_pid_ns(ns)->parent;
for (;;) {
if (!p)
return ERR_PTR(-EPERM);
if (p == active)
break;
p = p->parent;
}
return &get_pid_ns(pid_ns)->ns;
}
static struct user_namespace *pidns_owner(struct ns_common *ns)
{
return to_pid_ns(ns)->user_ns;
}
const struct proc_ns_operations pidns_operations = {
.name = "pid",
.type = CLONE_NEWPID,
.get = pidns_get,
.put = pidns_put,
.install = pidns_install,
.owner = pidns_owner,
.get_parent = pidns_get_parent,
};
static __init int pid_namespaces_init(void)
{
pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
#ifdef CONFIG_CHECKPOINT_RESTORE
register_sysctl_paths(kern_path, pid_ns_ctl_table);
#endif
return 0;
}
__initcall(pid_namespaces_init);