io_uring: enable option to only trigger eventfd for async completions

If an application is using eventfd notifications with poll to know when
new SQEs can be issued, it's expecting the following read/writes to
complete inline. And with that, it knows that there are events available,
and don't want spurious wakeups on the eventfd for those requests.

This adds IORING_REGISTER_EVENTFD_ASYNC, which works just like
IORING_REGISTER_EVENTFD, except it only triggers notifications for events
that happen from async completions (IRQ, or io-wq worker completions).
Any completions inline from the submission itself will not trigger
notifications.

Suggested-by: Mark Papadakis <markuspapadakis@icloud.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 42bf83b3fbd547c36f780cb235e299f9f5156b43..70656762244fedf99dd69ec583066bc2c0a97ee2 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -206,6 +206,7 @@ struct io_ring_ctx {
                int                     account_mem: 1;
                int                     cq_overflow_flushed: 1;
                int                     drain_next: 1;
+               int                     eventfd_async: 1;
 
                /*
                 * Ring buffer of indices into array of io_uring_sqe, which is
@@ -963,13 +964,20 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
        return &rings->cqes[tail & ctx->cq_mask];
 }
 
+static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx)
+{
+       if (!ctx->eventfd_async)
+               return true;
+       return io_wq_current_is_worker() || in_interrupt();
+}
+
 static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
 {
        if (waitqueue_active(&ctx->wait))
                wake_up(&ctx->wait);
        if (waitqueue_active(&ctx->sqo_wait))
                wake_up(&ctx->sqo_wait);
-       if (ctx->cq_ev_fd)
+       if (ctx->cq_ev_fd && io_should_trigger_evfd(ctx))
                eventfd_signal(ctx->cq_ev_fd, 1);
 }
 
@@ -6556,10 +6564,17 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
                ret = io_sqe_files_update(ctx, arg, nr_args);
                break;
        case IORING_REGISTER_EVENTFD:
+       case IORING_REGISTER_EVENTFD_ASYNC:
                ret = -EINVAL;
                if (nr_args != 1)
                        break;
                ret = io_eventfd_register(ctx, arg);
+               if (ret)
+                       break;
+               if (opcode == IORING_REGISTER_EVENTFD_ASYNC)
+                       ctx->eventfd_async = 1;
+               else
+                       ctx->eventfd_async = 0;
                break;
        case IORING_UNREGISTER_EVENTFD:
                ret = -EINVAL;

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 0fe270ab191c5ddd93b130c3cc27b23a3ce2fcbd..66772a90a7f2dd55a5a77725026554321728c047 100644 (file)
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -192,6 +192,7 @@ struct io_uring_params {
 #define IORING_REGISTER_EVENTFD                4
 #define IORING_UNREGISTER_EVENTFD      5
 #define IORING_REGISTER_FILES_UPDATE   6
+#define IORING_REGISTER_EVENTFD_ASYNC  7
 
 struct io_uring_files_update {
        __u32 offset;