[PATCH 11/28] io_uring: optimise io_cqring_wait() hot path

[Pavel Begunkov <asml.silence@gmail.com>]

Turns out we always init struct io_wait_queue in io_cqring_wait(), even
if it's not used after, i.e. there are already enough of CQEs. And often
it's exactly what happens, for instance, requests may have been
completed inline, or in case of io_uring_enter(submit=N, wait=1).

It shows up in my profiler, so optimise it by delaying the struct init.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 fs/io_uring.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 0f49736cd2b4..0fd04d25c520 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7062,15 +7062,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 			  const sigset_t __user *sig, size_t sigsz,
 			  struct __kernel_timespec __user *uts)
 {
-	struct io_wait_queue iowq = {
-		.wq = {
-			.private	= current,
-			.func		= io_wake_function,
-			.entry		= LIST_HEAD_INIT(iowq.wq.entry),
-		},
-		.ctx		= ctx,
-		.to_wait	= min_events,
-	};
+	struct io_wait_queue iowq;
 	struct io_rings *rings = ctx->rings;
 	signed long timeout = MAX_SCHEDULE_TIMEOUT;
 	int ret;
@@ -7104,7 +7096,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 		timeout = timespec64_to_jiffies(&ts);
 	}
 
+	init_waitqueue_func_entry(&iowq.wq, io_wake_function);
+	iowq.wq.private = current;
+	INIT_LIST_HEAD(&iowq.wq.entry);
+	iowq.ctx = ctx;
+	iowq.to_wait = min_events;
 	iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
+
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
 		/* if we can't even flush overflow, don't wait for more */
-- 
2.32.0