@@ -1617,6 +1617,51 @@ static void aio_poll_put_work(struct work_struct *work)
iocb_put(iocb);
}
+/*
+ * Safely lock the waitqueue which the request is on, synchronizing with the
+ * case where the ->poll() provider decides to free its waitqueue early.
+ *
+ * Returns true on success, meaning that req->head->lock was locked, req->wait
+ * is on req->head, and an RCU read lock was taken. Returns false if the
+ * request was already removed from its waitqueue (which might no longer exist).
+ */
+static bool poll_iocb_lock_wq(struct poll_iocb *req)
+{
+ wait_queue_head_t *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, then check whether the request is still on the queue.
+ *
+ * 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();
+ head = smp_load_acquire(&req->head);
+ if (head) {
+ spin_lock(&head->lock);
+ if (!list_empty(&req->wait.entry))
+ return true;
+ spin_unlock(&head->lock);
+ }
+ rcu_read_unlock();
+ return false;
+}
+
+static void poll_iocb_unlock_wq(struct poll_iocb *req)
+{
+ spin_unlock(&req->head->lock);
+ rcu_read_unlock();
+}
+
static void aio_poll_complete_work(struct work_struct *work)
{
struct poll_iocb *req = container_of(work, struct poll_iocb, work);
@@ -1636,24 +1681,25 @@ static void aio_poll_complete_work(struct work_struct *work)
* avoid further branches in the fast path.
*/
spin_lock_irq(&ctx->ctx_lock);
- spin_lock(&req->head->lock);
- if (!mask && !READ_ONCE(req->cancelled)) {
- /*
- * The request isn't actually ready to be completed yet.
- * Reschedule completion if another wakeup came in.
- */
- if (req->work_need_resched) {
- schedule_work(&req->work);
- req->work_need_resched = false;
- } else {
- req->work_scheduled = false;
+ if (poll_iocb_lock_wq(req)) {
+ if (!mask && !READ_ONCE(req->cancelled)) {
+ /*
+ * The request isn't actually ready to be completed yet.
+ * Reschedule completion if another wakeup came in.
+ */
+ if (req->work_need_resched) {
+ schedule_work(&req->work);
+ req->work_need_resched = false;
+ } else {
+ req->work_scheduled = false;
+ }
+ poll_iocb_unlock_wq(req);
+ spin_unlock_irq(&ctx->ctx_lock);
+ return;
}
- spin_unlock(&req->head->lock);
- spin_unlock_irq(&ctx->ctx_lock);
- return;
- }
- list_del_init(&req->wait.entry);
- spin_unlock(&req->head->lock);
+ list_del_init(&req->wait.entry);
+ poll_iocb_unlock_wq(req);
+ } /* else, POLLFREE has freed the waitqueue, so we must complete */
list_del_init(&iocb->ki_list);
iocb->ki_res.res = mangle_poll(mask);
spin_unlock_irq(&ctx->ctx_lock);
@@ -1667,13 +1713,14 @@ static int aio_poll_cancel(struct kiocb *iocb)
struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
struct poll_iocb *req = &aiocb->poll;
- spin_lock(&req->head->lock);
- WRITE_ONCE(req->cancelled, true);
- if (!req->work_scheduled) {
- schedule_work(&aiocb->poll.work);
- req->work_scheduled = true;
- }
- spin_unlock(&req->head->lock);
+ if (poll_iocb_lock_wq(req)) {
+ WRITE_ONCE(req->cancelled, true);
+ if (!req->work_scheduled) {
+ schedule_work(&aiocb->poll.work);
+ req->work_scheduled = true;
+ }
+ poll_iocb_unlock_wq(req);
+ } /* else, the request was force-cancelled by POLLFREE already */
return 0;
}
@@ -1725,7 +1772,8 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
*
* Don't remove the request from the waitqueue here, as it might
* not actually be complete yet (we won't know until vfs_poll()
- * is called), and we must not miss any wakeups.
+ * is called), and we must not miss any wakeups. POLLFREE is an
+ * exception to this; see below.
*/
if (req->work_scheduled) {
req->work_need_resched = true;
@@ -1733,6 +1781,28 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
schedule_work(&req->work);
req->work_scheduled = true;
}
+
+ /*
+ * If the waitqueue is being freed early but we can't complete
+ * the request inline, 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. We also need to schedule the
+ * completion work (done above). Also mark the request as
+ * cancelled, to potentially skip an unneeded call to ->poll().
+ */
+ if (mask & POLLFREE) {
+ WRITE_ONCE(req->cancelled, true);
+ list_del_init(&req->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(&req->head, NULL);
+ }
}
return 1;
}
@@ -1740,6 +1810,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
struct aio_poll_table {
struct poll_table_struct pt;
struct aio_kiocb *iocb;
+ bool queued;
int error;
};
@@ -1750,11 +1821,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head,
struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt);
/* multiple wait queues per file are not supported */
- if (unlikely(pt->iocb->poll.head)) {
+ if (unlikely(pt->queued)) {
pt->error = -EINVAL;
return;
}
+ pt->queued = true;
pt->error = 0;
pt->iocb->poll.head = head;
add_wait_queue(head, &pt->iocb->poll.wait);
@@ -1786,6 +1858,7 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
apt.pt._qproc = aio_poll_queue_proc;
apt.pt._key = req->events;
apt.iocb = aiocb;
+ apt.queued = false;
apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */
/* initialized the list so that we can do list_empty checks */
@@ -1794,9 +1867,10 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
mask = vfs_poll(req->file, &apt.pt) & req->events;
spin_lock_irq(&ctx->ctx_lock);
- if (likely(req->head)) {
- spin_lock(&req->head->lock);
- if (list_empty(&req->wait.entry) || req->work_scheduled) {
+ if (likely(apt.queued)) {
+ bool on_queue = poll_iocb_lock_wq(req);
+
+ if (!on_queue || req->work_scheduled) {
/*
* aio_poll_wake() already either scheduled the async
* completion work, or completed the request inline.
@@ -1812,7 +1886,7 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
} else if (cancel) {
/* Cancel if possible (may be too late though). */
WRITE_ONCE(req->cancelled, true);
- } else if (!list_empty(&req->wait.entry)) {
+ } else if (on_queue) {
/*
* Actually waiting for an event, so add the request to
* active_reqs so that it can be cancelled if needed.
@@ -1820,7 +1894,8 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
aiocb->ki_cancel = aio_poll_cancel;
}
- spin_unlock(&req->head->lock);
+ if (on_queue)
+ poll_iocb_unlock_wq(req);
}
if (mask) { /* no async, we'd stolen it */
aiocb->ki_res.res = mangle_poll(mask);
@@ -29,7 +29,7 @@
#define POLLRDHUP 0x2000
#endif
-#define POLLFREE (__force __poll_t)0x4000 /* currently only for epoll */
+#define POLLFREE (__force __poll_t)0x4000
#define POLL_BUSY_LOOP (__force __poll_t)0x8000