Merge tag 'for-6.2/io_uring-2022-12-08' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:

 - Always ensure proper ordering in case of CQ ring overflow, which then
   means we can remove some work-arounds for that (Dylan)

 - Support completion batching for multishot, greatly increasing the
   efficiency for those (Dylan)

 - Flag epoll/eventfd wakeups done from io_uring, so that we can easily
   tell if we're recursing into io_uring again.

   Previously, this would have resulted in repeated multishot
   notifications if we had a dependency there. That could happen if an
   eventfd was registered as the ring eventfd, and we multishot polled
   for events on it. Or if an io_uring fd was added to epoll, and
   io_uring had a multishot request for the epoll fd.

   Test cases here:
	https://git.kernel.dk/cgit/liburing/commit/?id=919755a7d0096fda08fb6d65ac54ad8d0fe027cd

   Previously these got terminated when the CQ ring eventually
   overflowed, now it's handled gracefully (me).

 - Tightening of the IOPOLL based completions (Pavel)

 - Optimizations of the networking zero-copy paths (Pavel)

 - Various tweaks and fixes (Dylan, Pavel)

* tag 'for-6.2/io_uring-2022-12-08' of git://git.kernel.dk/linux: (41 commits)
  io_uring: keep unlock_post inlined in hot path
  io_uring: don't use complete_post in kbuf
  io_uring: spelling fix
  io_uring: remove io_req_complete_post_tw
  io_uring: allow multishot polled reqs to defer completion
  io_uring: remove overflow param from io_post_aux_cqe
  io_uring: add lockdep assertion in io_fill_cqe_aux
  io_uring: make io_fill_cqe_aux static
  io_uring: add io_aux_cqe which allows deferred completion
  io_uring: allow defer completion for aux posted cqes
  io_uring: defer all io_req_complete_failed
  io_uring: always lock in io_apoll_task_func
  io_uring: remove iopoll spinlock
  io_uring: iopoll protect complete_post
  io_uring: inline __io_req_complete_put()
  io_uring: remove io_req_tw_post_queue
  io_uring: use io_req_task_complete() in timeout
  io_uring: hold locks for io_req_complete_failed
  io_uring: add completion locking for iopoll
  io_uring: kill io_cqring_ev_posted() and __io_cq_unlock_post()
  ...

1 files changed, 29 insertions, 14 deletions

diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 50bc3af44953..062899b1fe86 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -4,6 +4,7 @@
 #include <linux/errno.h>
 #include <linux/lockdep.h>
 #include <linux/io_uring_types.h>
+#include <uapi/linux/eventpoll.h>
 #include "io-wq.h"
 #include "slist.h"
 #include "filetable.h"
@@ -29,14 +30,11 @@ bool io_req_cqe_overflow(struct io_kiocb *req);
 int io_run_task_work_sig(struct io_ring_ctx *ctx);
 int __io_run_local_work(struct io_ring_ctx *ctx, bool *locked);
 int io_run_local_work(struct io_ring_ctx *ctx);
-void io_req_complete_failed(struct io_kiocb *req, s32 res);
-void __io_req_complete(struct io_kiocb *req, unsigned issue_flags);
-void io_req_complete_post(struct io_kiocb *req);
-void __io_req_complete_post(struct io_kiocb *req);
-bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags,
-		     bool allow_overflow);
-bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags,
-		     bool allow_overflow);
+void io_req_defer_failed(struct io_kiocb *req, s32 res);
+void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags);
+bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags);
+bool io_aux_cqe(struct io_ring_ctx *ctx, bool defer, u64 user_data, s32 res, u32 cflags,
+		bool allow_overflow);
 void __io_commit_cqring_flush(struct io_ring_ctx *ctx);
 
 struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages);
@@ -50,10 +48,9 @@ static inline bool io_req_ffs_set(struct io_kiocb *req)
 	return req->flags & REQ_F_FIXED_FILE;
 }
 
+void __io_req_task_work_add(struct io_kiocb *req, bool allow_local);
 bool io_is_uring_fops(struct file *file);
 bool io_alloc_async_data(struct io_kiocb *req);
-void io_req_task_work_add(struct io_kiocb *req);
-void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags);
 void io_req_task_queue(struct io_kiocb *req);
 void io_queue_iowq(struct io_kiocb *req, bool *dont_use);
 void io_req_task_complete(struct io_kiocb *req, bool *locked);
@@ -82,6 +79,11 @@ bool __io_alloc_req_refill(struct io_ring_ctx *ctx);
 bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
 			bool cancel_all);
 
+static inline void io_req_task_work_add(struct io_kiocb *req)
+{
+	__io_req_task_work_add(req, true);
+}
+
 #define io_for_each_link(pos, head) \
 	for (pos = (head); pos; pos = pos->link)
 
@@ -207,12 +209,18 @@ static inline void io_commit_cqring(struct io_ring_ctx *ctx)
 static inline void __io_cqring_wake(struct io_ring_ctx *ctx)
 {
 	/*
-	 * wake_up_all() may seem excessive, but io_wake_function() and
-	 * io_should_wake() handle the termination of the loop and only
-	 * wake as many waiters as we need to.
+	 * Trigger waitqueue handler on all waiters on our waitqueue. This
+	 * won't necessarily wake up all the tasks, io_should_wake() will make
+	 * that decision.
+	 *
+	 * Pass in EPOLLIN|EPOLL_URING_WAKE as the poll wakeup key. The latter
+	 * set in the mask so that if we recurse back into our own poll
+	 * waitqueue handlers, we know we have a dependency between eventfd or
+	 * epoll and should terminate multishot poll at that point.
 	 */
 	if (waitqueue_active(&ctx->cq_wait))
-		wake_up_all(&ctx->cq_wait);
+		__wake_up(&ctx->cq_wait, TASK_NORMAL, 0,
+				poll_to_key(EPOLL_URING_WAKE | EPOLLIN));
 }
 
 static inline void io_cqring_wake(struct io_ring_ctx *ctx)
@@ -369,4 +377,11 @@ static inline bool io_allowed_run_tw(struct io_ring_ctx *ctx)
 		      ctx->submitter_task == current);
 }
 
+static inline void io_req_queue_tw_complete(struct io_kiocb *req, s32 res)
+{
+	io_req_set_res(req, res, 0);
+	req->io_task_work.func = io_req_task_complete;
+	io_req_task_work_add(req);
+}
+
 #endif