[PATCH OLK-5.10 1/3] sched/psi: use kernfs polling functions for PSI trigger polling

From: Suren Baghdasaryan surenb@google.com

mainline inclusion from mainline-v6.5-rc2 commit aff037078ecaecf34a7c2afab1341815f90fba5e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7DHPO

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

-------------------------------------------------

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 c2dbe32d5db5 ("sched/psi: Fix use-after-free in ep_remove_wait_queue()")

Fixes: 0e94682b73bf ("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 Conflict: include/linux/psi.h kernel/cgroup/cgroup.c kernel/sched/psi.c Signed-off-by: Lu Jialin lujialin4@huawei.com --- include/linux/psi.h | 5 +++-- include/linux/psi_types.h | 3 +++ kernel/cgroup/cgroup.c | 2 +- kernel/sched/psi.c | 27 ++++++++++++++++++++------- 4 files changed, 27 insertions(+), 10 deletions(-)

diff --git a/include/linux/psi.h b/include/linux/psi.h index d290f0493c33..41079ebe17a6 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -32,8 +32,9 @@ 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);

-struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, size_t nbytes, enum psi_res res); +struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, + size_t nbytes, enum psi_res res, + struct kernfs_open_file *of); void psi_trigger_destroy(struct psi_trigger *t);

__poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index c17aeb774e23..0b6e17e7f84f 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -173,6 +173,9 @@ struct psi_trigger { /* Wait queue for polling */ wait_queue_head_t event_wait;

+ /* Kernfs file for cgroup triggers */ + struct kernfs_open_file *of; + /* Pending event flag */ int event;

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 2bc5bae49d20..24657a31d264 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3718,7 +3718,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, }

psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; - new = psi_trigger_create(psi, buf, nbytes, res); + new = psi_trigger_create(psi, buf, nbytes, res, of); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 86321085f388..3033521bd97c 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -553,8 +553,12 @@ static u64 update_triggers(struct psi_group *group, u64 now) continue;

/* Generate an event */ - if (cmpxchg(&t->event, 0, 1) == 0) - wake_up_interruptible(&t->event_wait); + if (cmpxchg(&t->event, 0, 1) == 0) { + if (t->of) + kernfs_notify(t->of->kn); + else + wake_up_interruptible(&t->event_wait); + } t->last_event_time = now; }

@@ -1133,7 +1137,8 @@ static int psi_cpu_open(struct inode *inode, struct file *file) }

struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, size_t nbytes, enum psi_res res) + char *buf, size_t nbytes, enum psi_res res, + struct kernfs_open_file *of) { struct psi_trigger *t; enum psi_states state; @@ -1173,7 +1178,9 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,

t->event = 0; t->last_event_time = 0; - init_waitqueue_head(&t->event_wait); + t->of = of; + if (!of) + init_waitqueue_head(&t->event_wait);

mutex_lock(&group->trigger_lock);

@@ -1220,7 +1227,10 @@ void psi_trigger_destroy(struct psi_trigger *t) * being accessed later. Can happen if cgroup is deleted from under a * polling process. */ - wake_up_pollfree(&t->event_wait); + if (t->of) + kernfs_notify(t->of->kn); + else + wake_up_interruptible(&t->event_wait);

mutex_lock(&group->trigger_lock);

@@ -1283,7 +1293,10 @@ __poll_t psi_trigger_poll(void **trigger_ptr, if (!t) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;

- poll_wait(file, &t->event_wait, wait); + if (t->of) + kernfs_generic_poll(t->of, wait); + else + poll_wait(file, &t->event_wait, wait);

if (cmpxchg(&t->event, 1, 0) == 1) ret |= EPOLLPRI; @@ -1322,7 +1335,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, return -EBUSY; }

- new = psi_trigger_create(&psi_system, buf, nbytes, res); + new = psi_trigger_create(&psi_system, buf, nbytes, res, NULL); if (IS_ERR(new)) { mutex_unlock(&seq->lock); return PTR_ERR(new);