Merge tag 'io_uring-6.3-2023-03-03' of git://git.kernel.dk/linux

Pull more io_uring updates from Jens Axboe:
 "Here's a set of fixes/changes that didn't make the first cut, either
  because they got queued before I sent the early merge request, or
  fixes that came in afterwards. In detail:

   - Don't set MSG_NOSIGNAL on recv/recvmsg opcodes, as AF_PACKET will
     error out (David)

   - Fix for spurious poll wakeups (me)

   - Fix for a file leak for buffered reads in certain conditions
     (Joseph)

   - Don't allow registered buffers of mixed types (Pavel)

   - Improve handling of huge pages for registered buffers (Pavel)

   - Provided buffer ring size calculation fix (Wojciech)

   - Minor cleanups (me)"

* tag 'io_uring-6.3-2023-03-03' of git://git.kernel.dk/linux:
  io_uring/poll: don't pass in wake func to io_init_poll_iocb()
  io_uring: fix fget leak when fs don't support nowait buffered read
  io_uring/poll: allow some retries for poll triggering spuriously
  io_uring: remove MSG_NOSIGNAL from recvmsg
  io_uring/rsrc: always initialize 'folio' to NULL
  io_uring/rsrc: optimise registered huge pages
  io_uring/rsrc: optimise single entry advance
  io_uring/rsrc: disallow multi-source reg buffers
  io_uring: remove unused wq_list_merge
  io_uring: fix size calculation when registering buf ring
  io_uring/rsrc: fix a comment in io_import_fixed()
  io_uring: rename 'in_idle' to 'in_cancel'
  io_uring: consolidate the put_ref-and-return section of adding work

1 files changed, 19 insertions, 7 deletions

diff --git a/io_uring/poll.c b/io_uring/poll.c
index 8339a92b4510..795facbd0e9f 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -51,6 +51,9 @@ struct io_poll_table {
 
 #define IO_WQE_F_DOUBLE		1
 
+static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+			void *key);
+
 static inline struct io_kiocb *wqe_to_req(struct wait_queue_entry *wqe)
 {
 	unsigned long priv = (unsigned long)wqe->private;
@@ -164,15 +167,14 @@ static void io_poll_tw_hash_eject(struct io_kiocb *req, bool *locked)
 	}
 }
 
-static void io_init_poll_iocb(struct io_poll *poll, __poll_t events,
-			      wait_queue_func_t wake_func)
+static void io_init_poll_iocb(struct io_poll *poll, __poll_t events)
 {
 	poll->head = NULL;
 #define IO_POLL_UNMASK	(EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP)
 	/* mask in events that we always want/need */
 	poll->events = events | IO_POLL_UNMASK;
 	INIT_LIST_HEAD(&poll->wait.entry);
-	init_waitqueue_func_entry(&poll->wait, wake_func);
+	init_waitqueue_func_entry(&poll->wait, io_poll_wake);
 }
 
 static inline void io_poll_remove_entry(struct io_poll *poll)
@@ -508,7 +510,7 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt,
 
 		/* mark as double wq entry */
 		wqe_private |= IO_WQE_F_DOUBLE;
-		io_init_poll_iocb(poll, first->events, first->wait.func);
+		io_init_poll_iocb(poll, first->events);
 		if (!io_poll_double_prepare(req)) {
 			/* the request is completing, just back off */
 			kfree(poll);
@@ -569,7 +571,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 
 	INIT_HLIST_NODE(&req->hash_node);
 	req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
-	io_init_poll_iocb(poll, mask, io_poll_wake);
+	io_init_poll_iocb(poll, mask);
 	poll->file = req->file;
 	req->apoll_events = poll->events;
 
@@ -650,6 +652,14 @@ static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
 	__io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll);
 }
 
+/*
+ * We can't reliably detect loops in repeated poll triggers and issue
+ * subsequently failing. But rather than fail these immediately, allow a
+ * certain amount of retries before we give up. Given that this condition
+ * should _rarely_ trigger even once, we should be fine with a larger value.
+ */
+#define APOLL_MAX_RETRY		128
+
 static struct async_poll *io_req_alloc_apoll(struct io_kiocb *req,
 					     unsigned issue_flags)
 {
@@ -665,14 +675,18 @@ static struct async_poll *io_req_alloc_apoll(struct io_kiocb *req,
 		if (entry == NULL)
 			goto alloc_apoll;
 		apoll = container_of(entry, struct async_poll, cache);
+		apoll->poll.retries = APOLL_MAX_RETRY;
 	} else {
 alloc_apoll:
 		apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
 		if (unlikely(!apoll))
 			return NULL;
+		apoll->poll.retries = APOLL_MAX_RETRY;
 	}
 	apoll->double_poll = NULL;
 	req->apoll = apoll;
+	if (unlikely(!--apoll->poll.retries))
+		return NULL;
 	return apoll;
 }
 
@@ -694,8 +708,6 @@ int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
 		return IO_APOLL_ABORTED;
 	if (!file_can_poll(req->file))
 		return IO_APOLL_ABORTED;
-	if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED)
-		return IO_APOLL_ABORTED;
 	if (!(req->flags & REQ_F_APOLL_MULTISHOT))
 		mask |= EPOLLONESHOT;