@@ -598,6 +598,7 @@ struct cftype {
int (*open)(struct kernfs_open_file *of);
void (*release)(struct kernfs_open_file *of);
+ void (*free)(struct kernfs_open_file *of);
/*
* read_u64() is a shortcut for the common case of returning a
@@ -25,7 +25,11 @@ 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);
-void psi_trigger_destroy(struct psi_trigger *t);
+void psi_trigger_disable(struct psi_trigger *t);
+static inline void psi_trigger_destroy(struct psi_trigger *t)
+{
+ kfree(t);
+}
__poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
poll_table *wait);
@@ -3895,6 +3895,13 @@ static void cgroup_pressure_release(struct kernfs_open_file *of)
{
struct cgroup_file_ctx *ctx = of->priv;
+ psi_trigger_disable(ctx->psi.trigger);
+}
+
+static void cgroup_pressure_free(struct kernfs_open_file *of)
+{
+ struct cgroup_file_ctx *ctx = of->priv;
+
psi_trigger_destroy(ctx->psi.trigger);
}
@@ -4055,7 +4062,21 @@ static void cgroup_file_release(struct kernfs_open_file *of)
if (cft->release)
cft->release(of);
put_cgroup_ns(ctx->ns);
- kfree(ctx);
+ /* Keep the context alive until cft->free is called */
+ if (!cft->free)
+ kfree(ctx);
+}
+
+static void cgroup_file_free(struct kernfs_open_file *of)
+{
+ struct cftype *cft = of_cft(of);
+
+ if (cft->free) {
+ struct cgroup_file_ctx *ctx = of->priv;
+
+ cft->free(of);
+ kfree(ctx);
+ }
}
static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
@@ -4158,6 +4179,7 @@ static struct kernfs_ops cgroup_kf_single_ops = {
.atomic_write_len = PAGE_SIZE,
.open = cgroup_file_open,
.release = cgroup_file_release,
+ .free = cgroup_file_free,
.write = cgroup_file_write,
.poll = cgroup_file_poll,
.seq_show = cgroup_seqfile_show,
@@ -4167,6 +4189,7 @@ static struct kernfs_ops cgroup_kf_ops = {
.atomic_write_len = PAGE_SIZE,
.open = cgroup_file_open,
.release = cgroup_file_release,
+ .free = cgroup_file_free,
.write = cgroup_file_write,
.poll = cgroup_file_poll,
.seq_start = cgroup_seqfile_start,
@@ -5294,6 +5317,7 @@ static struct cftype cgroup_psi_files[] = {
.write = cgroup_io_pressure_write,
.poll = cgroup_pressure_poll,
.release = cgroup_pressure_release,
+ .free = cgroup_pressure_free,
},
{
.name = "memory.pressure",
@@ -5302,6 +5326,7 @@ static struct cftype cgroup_psi_files[] = {
.write = cgroup_memory_pressure_write,
.poll = cgroup_pressure_poll,
.release = cgroup_pressure_release,
+ .free = cgroup_pressure_free,
},
{
.name = "cpu.pressure",
@@ -5310,6 +5335,7 @@ static struct cftype cgroup_psi_files[] = {
.write = cgroup_cpu_pressure_write,
.poll = cgroup_pressure_poll,
.release = cgroup_pressure_release,
+ .free = cgroup_pressure_free,
},
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
{
@@ -5319,6 +5345,7 @@ static struct cftype cgroup_psi_files[] = {
.write = cgroup_irq_pressure_write,
.poll = cgroup_pressure_poll,
.release = cgroup_pressure_release,
+ .free = cgroup_pressure_free,
},
#endif
{
@@ -622,7 +622,7 @@ static void psi_schedule_rtpoll_work(struct psi_group *group, unsigned long dela
task = rcu_dereference(group->rtpoll_task);
/*
- * kworker might be NULL in case psi_trigger_destroy races with
+ * kworker might be NULL in case psi_trigger_disable races with
* psi_task_change (hotpath) which can't use locks
*/
if (likely(task))
@@ -1372,7 +1372,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
return t;
}
-void psi_trigger_destroy(struct psi_trigger *t)
+void psi_trigger_disable(struct psi_trigger *t)
{
struct psi_group *group;
struct task_struct *task_to_destroy = NULL;
@@ -1386,11 +1386,10 @@ void psi_trigger_destroy(struct psi_trigger *t)
group = t->group;
/*
- * Wakeup waiters to stop polling and clear the queue to prevent it from
- * being accessed later. Can happen if cgroup is deleted from under a
- * polling process.
+ * Wakeup waiters to stop polling. Can happen if cgroup is deleted
+ * from under a polling process.
*/
- wake_up_pollfree(&t->event_wait);
+ wake_up_interruptible(&t->event_wait);
if (t->aggregator == PSI_AVGS) {
mutex_lock(&group->avgs_lock);
@@ -1446,7 +1445,6 @@ void psi_trigger_destroy(struct psi_trigger *t)
kthread_stop(task_to_destroy);
atomic_set(&group->rtpoll_scheduled, 0);
}
- kfree(t);
}
__poll_t psi_trigger_poll(void **trigger_ptr,
@@ -1573,6 +1571,7 @@ static int psi_fop_release(struct inode *inode, struct file *file)
{
struct seq_file *seq = file->private_data;
+ psi_trigger_disable(seq->private);
psi_trigger_destroy(seq->private);
return single_release(inode, file);
}
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 via this path: do_rmdir cgroup_rmdir kernfs_drain_open_files cgroup_file_release cgroup_pressure_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 a freed pointer. 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 destroying the trigger from inside kernfs_ops.free operation which is tied to the last fput() of the file. 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()") Reported-by: Lu Jialin <lujialin4@huawei.com> Closes: https://lore.kernel.org/all/20230613062306.101831-1-lujialin4@huawei.com/ Signed-off-by: Suren Baghdasaryan <surenb@google.com> --- include/linux/cgroup-defs.h | 1 + include/linux/psi.h | 6 +++++- kernel/cgroup/cgroup.c | 29 ++++++++++++++++++++++++++++- kernel/sched/psi.c | 13 ++++++------- 4 files changed, 40 insertions(+), 9 deletions(-)