android_kernel_xiaomi_sm8350/kernel/pid_namespace.c
Vasily Averin 0569920e43 memcg: enable accounting for pids in nested pid namespaces
commit fab827dbee8c2e06ca4ba000fa6c48bcf9054aba upstream.

Commit 5d097056c9 ("kmemcg: account certain kmem allocations to memcg")
enabled memcg accounting for pids allocated from init_pid_ns.pid_cachep,
but forgot to adjust the setting for nested pid namespaces.  As a result,
pid memory is not accounted exactly where it is really needed, inside
memcg-limited containers with their own pid namespaces.

Pid was one the first kernel objects enabled for memcg accounting.
init_pid_ns.pid_cachep marked by SLAB_ACCOUNT and we can expect that any
new pids in the system are memcg-accounted.

Though recently I've noticed that it is wrong.  nested pid namespaces
creates own slab caches for pid objects, nested pids have increased size
because contain id both for all parent and for own pid namespaces.  The
problem is that these slab caches are _NOT_ marked by SLAB_ACCOUNT, as a
result any pids allocated in nested pid namespaces are not
memcg-accounted.

Pid struct in nested pid namespace consumes up to 500 bytes memory, 100000
such objects gives us up to ~50Mb unaccounted memory, this allow container
to exceed assigned memcg limits.

Link: https://lkml.kernel.org/r/8b6de616-fd1a-02c6-cbdb-976ecdcfa604@virtuozzo.com
Fixes: 5d097056c9 ("kmemcg: account certain kmem allocations to memcg")
Cc: stable@vger.kernel.org
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-09-22 12:26:37 +02:00

470 lines
12 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* 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 <linux/slab.h>
#include <linux/proc_ns.h>
#include <linux/reboot.h>
#include <linux/export.h>
#include <linux/sched/task.h>
#include <linux/sched/signal.h>
#include <linux/idr.h>
static DEFINE_MUTEX(pid_caches_mutex);
static struct kmem_cache *pid_ns_cachep;
/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
#define MAX_PID_NS_LEVEL 32
/* Write once array, filled from the beginning. */
static struct kmem_cache *pid_cache[MAX_PID_NS_LEVEL];
/*
* creates the kmem cache to allocate pids from.
* @level: pid namespace level
*/
static struct kmem_cache *create_pid_cachep(unsigned int level)
{
/* Level 0 is init_pid_ns.pid_cachep */
struct kmem_cache **pkc = &pid_cache[level - 1];
struct kmem_cache *kc;
char name[4 + 10 + 1];
unsigned int len;
kc = READ_ONCE(*pkc);
if (kc)
return kc;
snprintf(name, sizeof(name), "pid_%u", level + 1);
len = sizeof(struct pid) + level * sizeof(struct upid);
mutex_lock(&pid_caches_mutex);
/* Name collision forces to do allocation under mutex. */
if (!*pkc)
*pkc = kmem_cache_create(name, len, 0,
SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, 0);
mutex_unlock(&pid_caches_mutex);
/* current can fail, but someone else can succeed. */
return READ_ONCE(*pkc);
}
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);
}
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;
int err;
err = -EINVAL;
if (!in_userns(parent_pid_ns->user_ns, user_ns))
goto out;
err = -ENOSPC;
if (level > MAX_PID_NS_LEVEL)
goto out;
ucounts = inc_pid_namespaces(user_ns);
if (!ucounts)
goto out;
err = -ENOMEM;
ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
if (ns == NULL)
goto out_dec;
idr_init(&ns->idr);
ns->pid_cachep = create_pid_cachep(level);
if (ns->pid_cachep == NULL)
goto out_free_idr;
err = ns_alloc_inum(&ns->ns);
if (err)
goto out_free_idr;
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->pid_allocated = PIDNS_ADDING;
INIT_WORK(&ns->proc_work, proc_cleanup_work);
return ns;
out_free_idr:
idr_destroy(&ns->idr);
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)
{
ns_free_inum(&ns->ns);
idr_destroy(&ns->idr);
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;
struct pid *pid;
/* 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.
*
*/
rcu_read_lock();
read_lock(&tasklist_lock);
nr = 2;
idr_for_each_entry_continue(&pid_ns->idr, pid, nr) {
task = pid_task(pid, PIDTYPE_PID);
if (task && !__fatal_signal_pending(task))
group_send_sig_info(SIGKILL, SEND_SIG_PRIV, task, PIDTYPE_MAX);
}
read_unlock(&tasklist_lock);
rcu_read_unlock();
/*
* Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD.
* kernel_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 = kernel_wait4(-1, NULL, __WALL, NULL);
} while (rc != -ECHILD);
/*
* kernel_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(pid_allocated == 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.
*/
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
if (pid_ns->pid_allocated == init_pids)
break;
schedule();
}
__set_current_state(TASK_RUNNING);
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;
int ret, next;
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.
*/
next = idr_get_cursor(&pid_ns->idr) - 1;
tmp.data = &next;
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (!ret && write)
idr_set_cursor(&pid_ns->idr, next + 1);
return ret;
}
extern int pid_max;
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 = SYSCTL_ZERO,
.extra2 = &pid_max,
},
{ }
};
static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } };
#endif /* CONFIG_CHECKPOINT_RESTORE */
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);
send_sig(SIGKILL, pid_ns->child_reaper, 1);
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 struct ns_common *pidns_for_children_get(struct task_struct *task)
{
struct pid_namespace *ns = NULL;
task_lock(task);
if (task->nsproxy) {
ns = task->nsproxy->pid_ns_for_children;
get_pid_ns(ns);
}
task_unlock(task);
if (ns) {
read_lock(&tasklist_lock);
if (!ns->child_reaper) {
put_pid_ns(ns);
ns = NULL;
}
read_unlock(&tasklist_lock);
}
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,
};
const struct proc_ns_operations pidns_for_children_operations = {
.name = "pid_for_children",
.real_ns_name = "pid",
.type = CLONE_NEWPID,
.get = pidns_for_children_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);