The IORING_SETUP_COOP_TASKRUN flag reduces interprocessor interrupts
when an io_uring event occurs on a different CPU. The idea is that the
QEMU thread will wait for a CQE anyway, so there is no need to interrupt
the CPU that it is on.

The IORING_SETUP_TASKRUN_FLAG ensures that QEMU's io_uring CQ ring
polling still works with COOP_TASKRUN. The kernel will set a flag in the
SQ ring (this is not a typo, the flag is located in the SQ ring even
though it pertains to the CQ ring) that can be polled from userspace.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 util/fdmon-io_uring.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/util/fdmon-io_uring.c b/util/fdmon-io_uring.c
index 4798439097..649dc18907 100644
--- a/util/fdmon-io_uring.c
+++ b/util/fdmon-io_uring.c
@@ -428,13 +428,16 @@ static int fdmon_io_uring_wait(AioContext *ctx, AioHandlerList *ready_list,
 
 static bool fdmon_io_uring_need_wait(AioContext *ctx)
 {
+    struct io_uring *ring = &ctx->fdmon_io_uring;
+
     /* Have io_uring events completed? */
-    if (io_uring_cq_ready(&ctx->fdmon_io_uring)) {
+    if (io_uring_cq_ready(ring) ||
+        IO_URING_READ_ONCE(*ring->sq.kflags) & IORING_SQ_TASKRUN) {
         return true;
     }
 
     /* Are there pending sqes to submit? */
-    if (io_uring_sq_ready(&ctx->fdmon_io_uring)) {
+    if (io_uring_sq_ready(ring)) {
         return true;
     }
 
@@ -465,7 +468,7 @@ void fdmon_io_uring_setup(AioContext *ctx, Error **errp)
 {
     int ret;
     /* TODO only enable these flags if they are available in the host's kernel headers */
-    unsigned flags = 0;
+    unsigned flags = IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG;
 
     ctx->io_uring_fd_tag = NULL;
 
-- 
2.50.1