From a06247c6804f1a7c86a2e5398a4c1f1db1471848 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 11 Jan 2022 15:23:09 -0800 Subject: psi: Fix uaf issue when psi trigger is destroyed while being polled With write operation on psi files replacing old trigger with a new one, the lifetime of its waitqueue is totally arbitrary. Overwriting an existing trigger causes its waitqueue to be freed and pending poll() will stumble on trigger->event_wait which was destroyed. Fix this by disallowing to redefine an existing psi trigger. If a write operation is used on a file descriptor with an already existing psi trigger, the operation will fail with EBUSY error. Also bypass a check for psi_disabled in the psi_trigger_destroy as the flag can be flipped after the trigger is created, leading to a memory leak. Fixes: 0e94682b73bf ("psi: introduce psi monitor") Reported-by: syzbot+cdb5dd11c97cc532efad@syzkaller.appspotmail.com Suggested-by: Linus Torvalds Analyzed-by: Eric Biggers Signed-off-by: Suren Baghdasaryan Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Eric Biggers Acked-by: Johannes Weiner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220111232309.1786347-1-surenb@google.com --- kernel/sched/psi.c | 66 ++++++++++++++++++++++++------------------------------ 1 file changed, 29 insertions(+), 37 deletions(-) (limited to 'kernel/sched/psi.c') diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index a679613a7cb7..c137c4d6983e 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1162,7 +1162,6 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, t->event = 0; t->last_event_time = 0; init_waitqueue_head(&t->event_wait); - kref_init(&t->refcount); mutex_lock(&group->trigger_lock); @@ -1191,15 +1190,19 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, return t; } -static void psi_trigger_destroy(struct kref *ref) +void psi_trigger_destroy(struct psi_trigger *t) { - struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount); - struct psi_group *group = t->group; + struct psi_group *group; struct task_struct *task_to_destroy = NULL; - if (static_branch_likely(&psi_disabled)) + /* + * We do not check psi_disabled since it might have been disabled after + * the trigger got created. + */ + if (!t) return; + group = t->group; /* * Wakeup waiters to stop polling. Can happen if cgroup is deleted * from under a polling process. @@ -1235,9 +1238,9 @@ static void psi_trigger_destroy(struct kref *ref) mutex_unlock(&group->trigger_lock); /* - * Wait for both *trigger_ptr from psi_trigger_replace and - * poll_task RCUs to complete their read-side critical sections - * before destroying the trigger and optionally the poll_task + * Wait for psi_schedule_poll_work RCU to complete its read-side + * critical section before destroying the trigger and optionally the + * poll_task. */ synchronize_rcu(); /* @@ -1254,18 +1257,6 @@ static void psi_trigger_destroy(struct kref *ref) kfree(t); } -void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new) -{ - struct psi_trigger *old = *trigger_ptr; - - if (static_branch_likely(&psi_disabled)) - return; - - rcu_assign_pointer(*trigger_ptr, new); - if (old) - kref_put(&old->refcount, psi_trigger_destroy); -} - __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait) { @@ -1275,24 +1266,15 @@ __poll_t psi_trigger_poll(void **trigger_ptr, if (static_branch_likely(&psi_disabled)) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - rcu_read_lock(); - - t = rcu_dereference(*(void __rcu __force **)trigger_ptr); - if (!t) { - rcu_read_unlock(); + t = smp_load_acquire(trigger_ptr); + if (!t) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - } - kref_get(&t->refcount); - - rcu_read_unlock(); poll_wait(file, &t->event_wait, wait); if (cmpxchg(&t->event, 1, 0) == 1) ret |= EPOLLPRI; - kref_put(&t->refcount, psi_trigger_destroy); - return ret; } @@ -1316,14 +1298,24 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, buf[buf_size - 1] = '\0'; - new = psi_trigger_create(&psi_system, buf, nbytes, res); - if (IS_ERR(new)) - return PTR_ERR(new); - seq = file->private_data; + /* Take seq->lock to protect seq->private from concurrent writes */ mutex_lock(&seq->lock); - psi_trigger_replace(&seq->private, new); + + /* Allow only one trigger per file descriptor */ + if (seq->private) { + mutex_unlock(&seq->lock); + return -EBUSY; + } + + new = psi_trigger_create(&psi_system, buf, nbytes, res); + if (IS_ERR(new)) { + mutex_unlock(&seq->lock); + return PTR_ERR(new); + } + + smp_store_release(&seq->private, new); mutex_unlock(&seq->lock); return nbytes; @@ -1358,7 +1350,7 @@ static int psi_fop_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; - psi_trigger_replace(&seq->private, NULL); + psi_trigger_destroy(seq->private); return single_release(inode, file); } -- cgit v1.2.3 From 44585f7bc0cb01095bc2ad4258049c02bbad21ef Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Sat, 29 Jan 2022 13:41:20 -0800 Subject: psi: fix "defined but not used" warnings when CONFIG_PROC_FS=n When CONFIG_PROC_FS is disabled psi code generates the following warnings: kernel/sched/psi.c:1364:30: warning: 'psi_cpu_proc_ops' defined but not used [-Wunused-const-variable=] 1364 | static const struct proc_ops psi_cpu_proc_ops = { | ^~~~~~~~~~~~~~~~ kernel/sched/psi.c:1355:30: warning: 'psi_memory_proc_ops' defined but not used [-Wunused-const-variable=] 1355 | static const struct proc_ops psi_memory_proc_ops = { | ^~~~~~~~~~~~~~~~~~~ kernel/sched/psi.c:1346:30: warning: 'psi_io_proc_ops' defined but not used [-Wunused-const-variable=] 1346 | static const struct proc_ops psi_io_proc_ops = { | ^~~~~~~~~~~~~~~ Make definitions of these structures and related functions conditional on CONFIG_PROC_FS config. Link: https://lkml.kernel.org/r/20220119223940.787748-3-surenb@google.com Fixes: 0e94682b73bf ("psi: introduce psi monitor") Signed-off-by: Suren Baghdasaryan Reported-by: kernel test robot Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched/psi.c | 79 ++++++++++++++++++++++++++++-------------------------- 1 file changed, 41 insertions(+), 38 deletions(-) (limited to 'kernel/sched/psi.c') diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index c137c4d6983e..e14358178849 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1082,44 +1082,6 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) return 0; } -static int psi_io_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_IO); -} - -static int psi_memory_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_MEM); -} - -static int psi_cpu_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_CPU); -} - -static int psi_open(struct file *file, int (*psi_show)(struct seq_file *, void *)) -{ - if (file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) - return -EPERM; - - return single_open(file, psi_show, NULL); -} - -static int psi_io_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_io_show); -} - -static int psi_memory_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_memory_show); -} - -static int psi_cpu_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_cpu_show); -} - struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res) { @@ -1278,6 +1240,45 @@ __poll_t psi_trigger_poll(void **trigger_ptr, return ret; } +#ifdef CONFIG_PROC_FS +static int psi_io_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IO); +} + +static int psi_memory_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_MEM); +} + +static int psi_cpu_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_CPU); +} + +static int psi_open(struct file *file, int (*psi_show)(struct seq_file *, void *)) +{ + if (file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) + return -EPERM; + + return single_open(file, psi_show, NULL); +} + +static int psi_io_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_io_show); +} + +static int psi_memory_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_memory_show); +} + +static int psi_cpu_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_cpu_show); +} + static ssize_t psi_write(struct file *file, const char __user *user_buf, size_t nbytes, enum psi_res res) { @@ -1392,3 +1393,5 @@ static int __init psi_proc_init(void) return 0; } module_init(psi_proc_init); + +#endif /* CONFIG_PROC_FS */ -- cgit v1.2.3