Fixes a problem described in 50252e4b5e989
("aio: fix use-after-free due to missing POLLFREE handling")
and copies the approach used there.
In short, we have to forcibly eject a poll entry when we meet POLLFREE.
We can't rely on io_poll_get_ownership() as can't wait for potentially
running tw handlers, so we use the fact that wqs are RCU freed. See
Eric's patch and comments for more details.
Reported-by: Eric Biggers <ebiggers@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20211209010455.42744-6-ebiggers@xxxxxxxxxx
Reported-and-tested-by: syzbot+5426c7ed6868c705ca14@xxxxxxxxxxxxxxxxxxxxxxxxx
Fixes: 221c5eb233823 ("io_uring: add support for IORING_OP_POLL")
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
---
fs/io_uring.c | 60 +++++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 51 insertions(+), 9 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index fa3277844d2e..bc424af1833b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -5462,12 +5462,14 @@ static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events,
static inline void io_poll_remove_entry(struct io_poll_iocb *poll)
{
- struct wait_queue_head *head = poll->head;
+ struct wait_queue_head *head = smp_load_acquire(&poll->head);
- spin_lock_irq(&head->lock);
- list_del_init(&poll->wait.entry);
- poll->head = NULL;
- spin_unlock_irq(&head->lock);
+ if (head) {
+ spin_lock_irq(&head->lock);
+ list_del_init(&poll->wait.entry);
+ poll->head = NULL;
+ spin_unlock_irq(&head->lock);
+ }
}
static void io_poll_remove_entries(struct io_kiocb *req)
@@ -5475,10 +5477,26 @@ static void io_poll_remove_entries(struct io_kiocb *req)
struct io_poll_iocb *poll = io_poll_get_single(req);
struct io_poll_iocb *poll_double = io_poll_get_double(req);
- if (poll->head)
- io_poll_remove_entry(poll);
- if (poll_double && poll_double->head)
+ /*
+ * While we hold the waitqueue lock and the waitqueue is nonempty,
+ * wake_up_pollfree() will wait for us. However, taking the waitqueue
+ * lock in the first place can race with the waitqueue being freed.
+ *
+ * We solve this as eventpoll does: by taking advantage of the fact that
+ * all users of wake_up_pollfree() will RCU-delay the actual free. If
+ * we enter rcu_read_lock() and see that the pointer to the queue is
+ * non-NULL, we can then lock it without the memory being freed out from
+ * under us.
+ *
+ * Keep holding rcu_read_lock() as long as we hold the queue lock, in
+ * case the caller deletes the entry from the queue, leaving it empty.
+ * In that case, only RCU prevents the queue memory from being freed.
+ */
+ rcu_read_lock();
+ io_poll_remove_entry(poll);
+ if (poll_double)
io_poll_remove_entry(poll_double);
+ rcu_read_unlock();
}
/*
@@ -5618,13 +5636,37 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
wait);
__poll_t mask = key_to_poll(key);
+ if (unlikely(mask & POLLFREE)) {
+ io_poll_mark_cancelled(req);
+ /* we have to kick tw in case it's not already */
+ io_poll_execute(req, 0);
+
+ /*
+ * If the waitqueue is being freed early but someone is already
+ * holds ownership over it, we have to tear down the request as
+ * best we can. That means immediately removing the request from
+ * its waitqueue and preventing all further accesses to the
+ * waitqueue via the request.
+ */
+ list_del_init(&poll->wait.entry);
+
+ /*
+ * Careful: this *must* be the last step, since as soon
+ * as req->head is NULL'ed out, the request can be
+ * completed and freed, since aio_poll_complete_work()
+ * will no longer need to take the waitqueue lock.
+ */
+ smp_store_release(&poll->head, NULL);
+ return 1;
+ }
+
/* for instances that support it check for an event match first */
if (mask && !(mask & poll->events))
return 0;
if (io_poll_get_ownership(req)) {
/* optional, saves extra locking for removal in tw handler */
- if (mask && poll->events & EPOLLONESHOT) {
+ if (mask && (poll->events & EPOLLONESHOT)) {
list_del_init(&poll->wait.entry);
poll->head = NULL;
}
