From ae2ad293d6be143ad223f5f947cca07bcbe42595 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 20 Jun 2023 16:07:47 +0800 Subject: [PATCH 1/2] sched/fair: Use recent_used_cpu to test p->cpus_ptr When checking whether a recently used CPU can be a potential idle candidate, recent_used_cpu should be used to test p->cpus_ptr as p->recent_used_cpu is not equal to recent_used_cpu and candidate decision is made based on recent_used_cpu here. Fixes: 89aafd67f28c ("sched/fair: Use prev instead of new target as recent_used_cpu") Signed-off-by: Miaohe Lin Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Phil Auld Acked-by: Mel Gorman Link: https://lore.kernel.org/r/20230620080747.359122-1-linmiaohe@huawei.com --- kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a80a73909dc2..b3e25be58e2b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7174,7 +7174,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) && - cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) && + cpumask_test_cpu(recent_used_cpu, p->cpus_ptr) && asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) { return recent_used_cpu; } From aff037078ecaecf34a7c2afab1341815f90fba5e Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 29 Jun 2023 17:56:12 -0700 Subject: [PATCH 2/2] 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 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 Signed-off-by: Suren Baghdasaryan Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230630005612.1014540-1-surenb@google.com --- include/linux/psi.h | 5 +++-- include/linux/psi_types.h | 3 +++ kernel/cgroup/cgroup.c | 2 +- kernel/sched/psi.c | 29 +++++++++++++++++++++-------- 4 files changed, 28 insertions(+), 11 deletions(-) diff --git a/include/linux/psi.h b/include/linux/psi.h index ab26200c2803..e0745873e3f2 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -23,8 +23,9 @@ 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 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, diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 040c089581c6..f1fd3a8044e0 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -137,6 +137,9 @@ 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 bfe3cd8ccf36..f55a40db065f 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3730,7 +3730,7 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, } psi = cgroup_psi(cgrp); - new = psi_trigger_create(psi, buf, res, of->file); + new = psi_trigger_create(psi, buf, res, of->file, 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 81fca77397f6..9bb3f2b3ccfc 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -493,8 +493,12 @@ static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total, 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; /* Reset threshold breach flag once event got generated */ t->pending_event = false; @@ -1271,8 +1275,9 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) return 0; } -struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, enum psi_res res, struct file *file) +struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, + enum psi_res res, struct file *file, + struct kernfs_open_file *of) { struct psi_trigger *t; enum psi_states state; @@ -1331,7 +1336,9 @@ 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); t->pending_event = false; t->aggregator = privileged ? PSI_POLL : PSI_AVGS; @@ -1388,7 +1395,10 @@ 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); if (t->aggregator == PSI_AVGS) { mutex_lock(&group->avgs_lock); @@ -1465,7 +1475,10 @@ __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; @@ -1535,7 +1548,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, return -EBUSY; } - new = psi_trigger_create(&psi_system, buf, res, file); + new = psi_trigger_create(&psi_system, buf, res, file, NULL); if (IS_ERR(new)) { mutex_unlock(&seq->lock); return PTR_ERR(new);