From ce3ea91e9d2ef75d4d1572f1bd8626642011c557 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 26 Oct 2023 02:01:40 +0000 Subject: [PATCH 1/3] sched/psi: use kernfs polling functions for PSI trigger polling 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/?id=aff037078ecaecf34a7c2afab1341815f90fba5e ------------------------------------------------- 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 Conflict: include/linux/psi.h kernel/cgroup/cgroup.c kernel/sched/psi.c Signed-off-by: Lu Jialin --- 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 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 d0a4a1c4c38d..262688aa2b7f 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 25f7d46ad7bd..962fe88bb5f9 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; } @@ -1132,8 +1136,9 @@ static int psi_cpu_open(struct inode *inode, struct file *file) return single_open(file, psi_cpu_show, NULL); } -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) { 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); @@ -1219,7 +1226,10 @@ void psi_trigger_destroy(struct psi_trigger *t) * Wakeup waiters to stop polling. Can happen if cgroup is deleted * from under a polling process. */ - wake_up_interruptible(&t->event_wait); + if (t->of) + kernfs_notify(t->of->kn); + else + wake_up_interruptible(&t->event_wait); mutex_lock(&group->trigger_lock); @@ -1282,7 +1292,10 @@ __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; @@ -1321,7 +1334,7 @@ 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); -- Gitee From 0d1b656532d92d6b81182fa0aac323a3ef5c6750 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Oct 2023 02:01:41 +0000 Subject: [PATCH 2/3] kernfs: add stub helper for kernfs_generic_poll() mainline inclusion from mainline-v6.6-rc1 commit 79038a99445f69c5d28494dd4f8c6f0509f65b2e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7DHPO Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=79038a99445f69c5d28494dd4f8c6f0509f65b2e ------------------------------------------------- In some randconfig builds, kernfs ends up being disabled, so there is no prototype for kernfs_generic_poll() In file included from kernel/sched/build_utility.c:97: kernel/sched/psi.c:1479:3: error: implicit declaration of function 'kernfs_generic_poll' is invalid in C99 [-Werror,-Wimplicit-function-declaration] kernfs_generic_poll(t->of, wait); ^ Add a stub helper for it, as we have it for other kernfs functions. Fixes: aff037078ecae ("sched/psi: use kernfs polling functions for PSI trigger polling") Fixes: 147e1a97c4a0b ("fs: kernfs: add poll file operation") Signed-off-by: Arnd Bergmann Reviewed-by: Chengming Zhou Link: https://lore.kernel.org/r/20230724121823.1357562-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Lu Jialin --- include/linux/kernfs.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 7240d00ace86..e2aa4910365d 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -510,6 +510,10 @@ static inline int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { return -ENOSYS; } +static inline __poll_t kernfs_generic_poll(struct kernfs_open_file *of, + struct poll_table_struct *pt) +{ return -ENOSYS; } + static inline void kernfs_notify(struct kernfs_node *kn) { } static inline int kernfs_xattr_get(struct kernfs_node *kn, const char *name, -- Gitee From 9c1a4076f971c6e94f3146337fa7f991618c874e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 26 Oct 2023 02:01:42 +0000 Subject: [PATCH 3/3] sched/psi: Select KERNFS as needed mainline inclusion from mainline-v6.6-rc1 commit 98dfdd9ee93995a408192dbbf3dd219ba23e3738 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7DHPO Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=98dfdd9ee93995a408192dbbf3dd219ba23e3738 ------------------------------------------------- Users of KERNFS should select it to enforce its being built, so do this to prevent a build error. In file included from ../kernel/sched/build_utility.c:97: ../kernel/sched/psi.c: In function 'psi_trigger_poll': ../kernel/sched/psi.c:1479:17: error: implicit declaration of function 'kernfs_generic_poll' [-Werror=implicit-function-declaration] 1479 | kernfs_generic_poll(t->of, wait); Fixes: aff037078eca ("sched/psi: use kernfs polling functions for PSI trigger polling") Reported-by: kernel test robot Signed-off-by: Randy Dunlap Signed-off-by: Peter Zijlstra (Intel) Acked-by: Suren Baghdasaryan Link: lore.kernel.org/r/202307310732.r65EQFY0-lkp@intel.com Signed-off-by: Lu Jialin --- init/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/init/Kconfig b/init/Kconfig index b137a6c043ac..2eb3f376ff4f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -603,6 +603,7 @@ config TASK_IO_ACCOUNTING config PSI bool "Pressure stall information tracking" + select KERNFS help Collect metrics that indicate how overcommitted the CPU, memory, and IO capacity are in the system. -- Gitee