linux-stable/include/linux/psi.h
Suren Baghdasaryan aff037078e sched/psi: use kernfs polling functions for PSI trigger polling
Destroying psi trigger in cgroup_file_release causes UAF issues when
a cgroup is removed from under a polling process. This is happening
because cgroup removal causes a call to cgroup_file_release while the
actual file is still alive. Destroying the trigger at this point would
also destroy its waitqueue head and if there is still a polling process
on that file accessing the waitqueue, it will step on the freed pointer:

do_select
  vfs_poll
                           do_rmdir
                             cgroup_rmdir
                               kernfs_drain_open_files
                                 cgroup_file_release
                                   cgroup_pressure_release
                                     psi_trigger_destroy
                                       wake_up_pollfree(&t->event_wait)
// vfs_poll is unblocked
                                       synchronize_rcu
                                       kfree(t)
  poll_freewait -> UAF access to the trigger's waitqueue head

Patch [1] fixed this issue for epoll() case using wake_up_pollfree(),
however the same issue exists for synchronous poll() case.
The root cause of this issue is that the lifecycles of the psi trigger's
waitqueue and of the file associated with the trigger are different. Fix
this by using kernfs_generic_poll function when polling on cgroup-specific
psi triggers. It internally uses kernfs_open_node->poll waitqueue head
with its lifecycle tied to the file's lifecycle. This also renders the
fix in [1] obsolete, so revert it.

[1] commit c2dbe32d5d ("sched/psi: Fix use-after-free in ep_remove_wait_queue()")

Fixes: 0e94682b73 ("psi: introduce psi monitor")
Closes: https://lore.kernel.org/all/20230613062306.101831-1-lujialin4@huawei.com/
Reported-by: Lu Jialin <lujialin4@huawei.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230630005612.1014540-1-surenb@google.com
2023-07-10 09:52:30 +02:00

70 lines
1.8 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PSI_H
#define _LINUX_PSI_H
#include <linux/jump_label.h>
#include <linux/psi_types.h>
#include <linux/sched.h>
#include <linux/poll.h>
#include <linux/cgroup-defs.h>
#include <linux/cgroup.h>
struct seq_file;
struct css_set;
#ifdef CONFIG_PSI
extern struct static_key_false psi_disabled;
extern struct psi_group psi_system;
void psi_init(void);
void psi_memstall_enter(unsigned long *flags);
void psi_memstall_leave(unsigned long *flags);
int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf,
enum psi_res res, struct file *file,
struct kernfs_open_file *of);
void psi_trigger_destroy(struct psi_trigger *t);
__poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
poll_table *wait);
#ifdef CONFIG_CGROUPS
static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
{
return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
}
int psi_cgroup_alloc(struct cgroup *cgrp);
void psi_cgroup_free(struct cgroup *cgrp);
void cgroup_move_task(struct task_struct *p, struct css_set *to);
void psi_cgroup_restart(struct psi_group *group);
#endif
#else /* CONFIG_PSI */
static inline void psi_init(void) {}
static inline void psi_memstall_enter(unsigned long *flags) {}
static inline void psi_memstall_leave(unsigned long *flags) {}
#ifdef CONFIG_CGROUPS
static inline int psi_cgroup_alloc(struct cgroup *cgrp)
{
return 0;
}
static inline void psi_cgroup_free(struct cgroup *cgrp)
{
}
static inline void cgroup_move_task(struct task_struct *p, struct css_set *to)
{
rcu_assign_pointer(p->cgroups, to);
}
static inline void psi_cgroup_restart(struct psi_group *group) {}
#endif
#endif /* CONFIG_PSI */
#endif /* _LINUX_PSI_H */