linux/ipc/namespace.c
Alexey Gladkov db7cfc3809 ipc: Free mq_sysctls if ipc namespace creation failed
The problem that Dmitry Vyukov pointed out is that if setup_ipc_sysctls fails,
mq_sysctls must be freed before return.

executing program
BUG: memory leak
unreferenced object 0xffff888112fc9200 (size 512):
  comm "syz-executor237", pid 3648, jiffies 4294970469 (age 12.270s)
  hex dump (first 32 bytes):
    ef d3 60 85 ff ff ff ff 0c 9b d2 12 81 88 ff ff  ..`.............
    04 00 00 00 a4 01 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff814b6eb3>] kmemdup+0x23/0x50 mm/util.c:129
    [<ffffffff82219a9b>] kmemdup include/linux/fortify-string.h:456 [inline]
    [<ffffffff82219a9b>] setup_mq_sysctls+0x4b/0x1c0 ipc/mq_sysctl.c:89
    [<ffffffff822197f2>] create_ipc_ns ipc/namespace.c:63 [inline]
    [<ffffffff822197f2>] copy_ipcs+0x292/0x390 ipc/namespace.c:91
    [<ffffffff8127de7c>] create_new_namespaces+0xdc/0x4f0 kernel/nsproxy.c:90
    [<ffffffff8127e89b>] unshare_nsproxy_namespaces+0x9b/0x120 kernel/nsproxy.c:226
    [<ffffffff8123f92e>] ksys_unshare+0x2fe/0x600 kernel/fork.c:3165
    [<ffffffff8123fc42>] __do_sys_unshare kernel/fork.c:3236 [inline]
    [<ffffffff8123fc42>] __se_sys_unshare kernel/fork.c:3234 [inline]
    [<ffffffff8123fc42>] __x64_sys_unshare+0x12/0x20 kernel/fork.c:3234
    [<ffffffff845aab45>] do_syscall_x64 arch/x86/entry/common.c:50 [inline]
    [<ffffffff845aab45>] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
    [<ffffffff8460006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

BUG: memory leak
unreferenced object 0xffff888112fd5f00 (size 256):
  comm "syz-executor237", pid 3648, jiffies 4294970469 (age 12.270s)
  hex dump (first 32 bytes):
    00 92 fc 12 81 88 ff ff 00 00 00 00 01 00 00 00  ................
    01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff816fea1b>] kmalloc include/linux/slab.h:605 [inline]
    [<ffffffff816fea1b>] kzalloc include/linux/slab.h:733 [inline]
    [<ffffffff816fea1b>] __register_sysctl_table+0x7b/0x7f0 fs/proc/proc_sysctl.c:1344
    [<ffffffff82219b7a>] setup_mq_sysctls+0x12a/0x1c0 ipc/mq_sysctl.c:112
    [<ffffffff822197f2>] create_ipc_ns ipc/namespace.c:63 [inline]
    [<ffffffff822197f2>] copy_ipcs+0x292/0x390 ipc/namespace.c:91
    [<ffffffff8127de7c>] create_new_namespaces+0xdc/0x4f0 kernel/nsproxy.c:90
    [<ffffffff8127e89b>] unshare_nsproxy_namespaces+0x9b/0x120 kernel/nsproxy.c:226
    [<ffffffff8123f92e>] ksys_unshare+0x2fe/0x600 kernel/fork.c:3165
    [<ffffffff8123fc42>] __do_sys_unshare kernel/fork.c:3236 [inline]
    [<ffffffff8123fc42>] __se_sys_unshare kernel/fork.c:3234 [inline]
    [<ffffffff8123fc42>] __x64_sys_unshare+0x12/0x20 kernel/fork.c:3234
    [<ffffffff845aab45>] do_syscall_x64 arch/x86/entry/common.c:50 [inline]
    [<ffffffff845aab45>] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
    [<ffffffff8460006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

BUG: memory leak
unreferenced object 0xffff888112fbba00 (size 256):
  comm "syz-executor237", pid 3648, jiffies 4294970469 (age 12.270s)
  hex dump (first 32 bytes):
    78 ba fb 12 81 88 ff ff 00 00 00 00 01 00 00 00  x...............
    01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff816fef49>] kmalloc include/linux/slab.h:605 [inline]
    [<ffffffff816fef49>] kzalloc include/linux/slab.h:733 [inline]
    [<ffffffff816fef49>] new_dir fs/proc/proc_sysctl.c:978 [inline]
    [<ffffffff816fef49>] get_subdir fs/proc/proc_sysctl.c:1022 [inline]
    [<ffffffff816fef49>] __register_sysctl_table+0x5a9/0x7f0 fs/proc/proc_sysctl.c:1373
    [<ffffffff82219b7a>] setup_mq_sysctls+0x12a/0x1c0 ipc/mq_sysctl.c:112
    [<ffffffff822197f2>] create_ipc_ns ipc/namespace.c:63 [inline]
    [<ffffffff822197f2>] copy_ipcs+0x292/0x390 ipc/namespace.c:91
    [<ffffffff8127de7c>] create_new_namespaces+0xdc/0x4f0 kernel/nsproxy.c:90
    [<ffffffff8127e89b>] unshare_nsproxy_namespaces+0x9b/0x120 kernel/nsproxy.c:226
    [<ffffffff8123f92e>] ksys_unshare+0x2fe/0x600 kernel/fork.c:3165
    [<ffffffff8123fc42>] __do_sys_unshare kernel/fork.c:3236 [inline]
    [<ffffffff8123fc42>] __se_sys_unshare kernel/fork.c:3234 [inline]
    [<ffffffff8123fc42>] __x64_sys_unshare+0x12/0x20 kernel/fork.c:3234
    [<ffffffff845aab45>] do_syscall_x64 arch/x86/entry/common.c:50 [inline]
    [<ffffffff845aab45>] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
    [<ffffffff8460006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

BUG: memory leak
unreferenced object 0xffff888112fbb900 (size 256):
  comm "syz-executor237", pid 3648, jiffies 4294970469 (age 12.270s)
  hex dump (first 32 bytes):
    78 b9 fb 12 81 88 ff ff 00 00 00 00 01 00 00 00  x...............
    01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff816fef49>] kmalloc include/linux/slab.h:605 [inline]
    [<ffffffff816fef49>] kzalloc include/linux/slab.h:733 [inline]
    [<ffffffff816fef49>] new_dir fs/proc/proc_sysctl.c:978 [inline]
    [<ffffffff816fef49>] get_subdir fs/proc/proc_sysctl.c:1022 [inline]
    [<ffffffff816fef49>] __register_sysctl_table+0x5a9/0x7f0 fs/proc/proc_sysctl.c:1373
    [<ffffffff82219b7a>] setup_mq_sysctls+0x12a/0x1c0 ipc/mq_sysctl.c:112
    [<ffffffff822197f2>] create_ipc_ns ipc/namespace.c:63 [inline]
    [<ffffffff822197f2>] copy_ipcs+0x292/0x390 ipc/namespace.c:91
    [<ffffffff8127de7c>] create_new_namespaces+0xdc/0x4f0 kernel/nsproxy.c:90
    [<ffffffff8127e89b>] unshare_nsproxy_namespaces+0x9b/0x120 kernel/nsproxy.c:226
    [<ffffffff8123f92e>] ksys_unshare+0x2fe/0x600 kernel/fork.c:3165
    [<ffffffff8123fc42>] __do_sys_unshare kernel/fork.c:3236 [inline]
    [<ffffffff8123fc42>] __se_sys_unshare kernel/fork.c:3234 [inline]
    [<ffffffff8123fc42>] __x64_sys_unshare+0x12/0x20 kernel/fork.c:3234
    [<ffffffff845aab45>] do_syscall_x64 arch/x86/entry/common.c:50 [inline]
    [<ffffffff845aab45>] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
    [<ffffffff8460006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

Reported-by: syzbot+b4b0d1b35442afbf6fd2@syzkaller.appspotmail.com
Signed-off-by: Alexey Gladkov <legion@kernel.org>
Link: https://lkml.kernel.org/r/000000000000f5004705e1db8bad@google.com
Link: https://lkml.kernel.org/r/20220622200729.2639663-1-legion@kernel.org
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2022-06-22 17:47:41 -05:00

239 lines
5.3 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* linux/ipc/namespace.c
* Copyright (C) 2006 Pavel Emelyanov <xemul@openvz.org> OpenVZ, SWsoft Inc.
*/
#include <linux/ipc.h>
#include <linux/msg.h>
#include <linux/ipc_namespace.h>
#include <linux/rcupdate.h>
#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/user_namespace.h>
#include <linux/proc_ns.h>
#include <linux/sched/task.h>
#include "util.h"
static struct ucounts *inc_ipc_namespaces(struct user_namespace *ns)
{
return inc_ucount(ns, current_euid(), UCOUNT_IPC_NAMESPACES);
}
static void dec_ipc_namespaces(struct ucounts *ucounts)
{
dec_ucount(ucounts, UCOUNT_IPC_NAMESPACES);
}
static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
struct ipc_namespace *old_ns)
{
struct ipc_namespace *ns;
struct ucounts *ucounts;
int err;
err = -ENOSPC;
ucounts = inc_ipc_namespaces(user_ns);
if (!ucounts)
goto fail;
err = -ENOMEM;
ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL_ACCOUNT);
if (ns == NULL)
goto fail_dec;
err = ns_alloc_inum(&ns->ns);
if (err)
goto fail_free;
ns->ns.ops = &ipcns_operations;
refcount_set(&ns->ns.count, 1);
ns->user_ns = get_user_ns(user_ns);
ns->ucounts = ucounts;
err = mq_init_ns(ns);
if (err)
goto fail_put;
err = -ENOMEM;
if (!setup_mq_sysctls(ns))
goto fail_put;
if (!setup_ipc_sysctls(ns))
goto fail_mq;
sem_init_ns(ns);
msg_init_ns(ns);
shm_init_ns(ns);
return ns;
fail_mq:
retire_mq_sysctls(ns);
fail_put:
put_user_ns(ns->user_ns);
ns_free_inum(&ns->ns);
fail_free:
kfree(ns);
fail_dec:
dec_ipc_namespaces(ucounts);
fail:
return ERR_PTR(err);
}
struct ipc_namespace *copy_ipcs(unsigned long flags,
struct user_namespace *user_ns, struct ipc_namespace *ns)
{
if (!(flags & CLONE_NEWIPC))
return get_ipc_ns(ns);
return create_ipc_ns(user_ns, ns);
}
/*
* free_ipcs - free all ipcs of one type
* @ns: the namespace to remove the ipcs from
* @ids: the table of ipcs to free
* @free: the function called to free each individual ipc
*
* Called for each kind of ipc when an ipc_namespace exits.
*/
void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
void (*free)(struct ipc_namespace *, struct kern_ipc_perm *))
{
struct kern_ipc_perm *perm;
int next_id;
int total, in_use;
down_write(&ids->rwsem);
in_use = ids->in_use;
for (total = 0, next_id = 0; total < in_use; next_id++) {
perm = idr_find(&ids->ipcs_idr, next_id);
if (perm == NULL)
continue;
rcu_read_lock();
ipc_lock_object(perm);
free(ns, perm);
total++;
}
up_write(&ids->rwsem);
}
static void free_ipc_ns(struct ipc_namespace *ns)
{
/* mq_put_mnt() waits for a grace period as kern_unmount()
* uses synchronize_rcu().
*/
mq_put_mnt(ns);
sem_exit_ns(ns);
msg_exit_ns(ns);
shm_exit_ns(ns);
retire_mq_sysctls(ns);
retire_ipc_sysctls(ns);
dec_ipc_namespaces(ns->ucounts);
put_user_ns(ns->user_ns);
ns_free_inum(&ns->ns);
kfree(ns);
}
static LLIST_HEAD(free_ipc_list);
static void free_ipc(struct work_struct *unused)
{
struct llist_node *node = llist_del_all(&free_ipc_list);
struct ipc_namespace *n, *t;
llist_for_each_entry_safe(n, t, node, mnt_llist)
free_ipc_ns(n);
}
/*
* The work queue is used to avoid the cost of synchronize_rcu in kern_unmount.
*/
static DECLARE_WORK(free_ipc_work, free_ipc);
/*
* put_ipc_ns - drop a reference to an ipc namespace.
* @ns: the namespace to put
*
* If this is the last task in the namespace exiting, and
* it is dropping the refcount to 0, then it can race with
* a task in another ipc namespace but in a mounts namespace
* which has this ipcns's mqueuefs mounted, doing some action
* with one of the mqueuefs files. That can raise the refcount.
* So dropping the refcount, and raising the refcount when
* accessing it through the VFS, are protected with mq_lock.
*
* (Clearly, a task raising the refcount on its own ipc_ns
* needn't take mq_lock since it can't race with the last task
* in the ipcns exiting).
*/
void put_ipc_ns(struct ipc_namespace *ns)
{
if (refcount_dec_and_lock(&ns->ns.count, &mq_lock)) {
mq_clear_sbinfo(ns);
spin_unlock(&mq_lock);
if (llist_add(&ns->mnt_llist, &free_ipc_list))
schedule_work(&free_ipc_work);
}
}
static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns)
{
return container_of(ns, struct ipc_namespace, ns);
}
static struct ns_common *ipcns_get(struct task_struct *task)
{
struct ipc_namespace *ns = NULL;
struct nsproxy *nsproxy;
task_lock(task);
nsproxy = task->nsproxy;
if (nsproxy)
ns = get_ipc_ns(nsproxy->ipc_ns);
task_unlock(task);
return ns ? &ns->ns : NULL;
}
static void ipcns_put(struct ns_common *ns)
{
return put_ipc_ns(to_ipc_ns(ns));
}
static int ipcns_install(struct nsset *nsset, struct ns_common *new)
{
struct nsproxy *nsproxy = nsset->nsproxy;
struct ipc_namespace *ns = to_ipc_ns(new);
if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
return -EPERM;
put_ipc_ns(nsproxy->ipc_ns);
nsproxy->ipc_ns = get_ipc_ns(ns);
return 0;
}
static struct user_namespace *ipcns_owner(struct ns_common *ns)
{
return to_ipc_ns(ns)->user_ns;
}
const struct proc_ns_operations ipcns_operations = {
.name = "ipc",
.type = CLONE_NEWIPC,
.get = ipcns_get,
.put = ipcns_put,
.install = ipcns_install,
.owner = ipcns_owner,
};