file
index bf9eff88427a..d4dbc16a58a5 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o opdef.o kbuf.o rsrc.o notif.o \
 					advise.o openclose.o statx.o timeout.o \
 					cancel.o waitid.o register.o \
 					truncate.o memmap.o alloc_cache.o \
-					query.o
+					query.o loop.o
 
 obj-$(CONFIG_IO_URING_ZCRX)	+= zcrx.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 5c503a3f6ecc..aea27e3538bb 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -94,6 +94,7 @@
 #include "alloc_cache.h"
 #include "eventfd.h"
 #include "wait.h"
+#include "loop.h"
 
 #define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \
 			  IOSQE_IO_HARDLINK | IOSQE_ASYNC)
@@ -2557,6 +2558,11 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	if (unlikely(smp_load_acquire(&ctx->flags) & IORING_SETUP_R_DISABLED))
 		goto out;
 
+	if (io_has_loop_ops(ctx)) {
+		ret = io_run_loop(ctx);
+		goto out;
+	}
+
 	/*
 	 * For SQ polling, the thread will do all submissions and completions.
 	 * Just return the requested submit count, and wake the thread if
diff --git a/io_uring/loop.c b/io_uring/loop.c
new file mode 100644
index 000000000000..bf38f20f0537
--- /dev/null
+++ b/io_uring/loop.c
@@ -0,0 +1,88 @@
+#include "io_uring.h"
+#include "napi.h"
+#include "wait.h"
+#include "loop.h"
+
+struct iou_loop_state {
+	struct iou_loop_params		p;
+	struct io_ring_ctx		*ctx;
+};
+
+static inline int io_loop_nr_cqes(const struct io_ring_ctx *ctx,
+				  const struct iou_loop_state *ls)
+{
+	return ls->p.cq_wait_idx - READ_ONCE(ctx->rings->cq.tail);
+}
+
+static inline void io_loop_wait_finish(struct io_ring_ctx *ctx)
+{
+	__set_current_state(TASK_RUNNING);
+	atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT);
+}
+
+static void io_loop_wait(struct io_ring_ctx *ctx, struct iou_loop_state *ls,
+			 unsigned nr_wait)
+{
+	atomic_set(&ctx->cq_wait_nr, nr_wait);
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	if (unlikely(io_local_work_pending(ctx) ||
+		     io_loop_nr_cqes(ctx, ls) <= 0) ||
+		     READ_ONCE(ctx->check_cq)) {
+		io_loop_wait_finish(ctx);
+		return;
+	}
+
+	mutex_unlock(&ctx->uring_lock);
+	schedule();
+	io_loop_wait_finish(ctx);
+	mutex_lock(&ctx->uring_lock);
+}
+
+int io_run_loop(struct io_ring_ctx *ctx)
+{
+	struct iou_loop_state ls = {};
+	int ret = -EINVAL;
+
+	if (!io_allowed_run_tw(ctx))
+		return -EEXIST;
+	mutex_lock(&ctx->uring_lock);
+
+	while (true) {
+		unsigned nr_wait;
+		int step_res;
+
+		if (unlikely(!ctx->loop_step)) {
+			ret = -EFAULT;
+			goto out_unlock;
+		}
+		step_res = ctx->loop_step(ctx, &ls.p);
+		if (step_res == IOU_LOOP_STOP)
+			break;
+
+		nr_wait = io_loop_nr_cqes(ctx, &ls);
+		if (nr_wait > 0)
+			io_loop_wait(ctx, &ls, nr_wait);
+
+		if (task_work_pending(current)) {
+			mutex_unlock(&ctx->uring_lock);
+			io_run_task_work();
+			mutex_lock(&ctx->uring_lock);
+		}
+		if (task_sigpending(current)) {
+			ret = -EINTR;
+			goto out_unlock;
+		}
+
+		nr_wait = max(nr_wait, 0);
+		io_run_local_work_locked(ctx, nr_wait);
+
+		if (READ_ONCE(ctx->check_cq) & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
+			io_cqring_do_overflow_flush(ctx);
+	}
+
+	ret = 0;
+out_unlock:
+	mutex_unlock(&ctx->uring_lock);
+	return ret;
+}
diff --git a/io_uring/loop.h b/io_uring/loop.h
new file mode 100644
index 000000000000..d7718b9ce61e
--- /dev/null
+++ b/io_uring/loop.h
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_LOOP_H
+#define IOU_LOOP_H
+
+#include <linux/io_uring_types.h>
+
+struct iou_loop_params {
+	/*
+	 * The CQE index to wait for. Only serves as a hint and can still be
+	 * woken up earlier.
+	 */
+	__u32			cq_wait_idx;
+};
+
+enum {
+	IOU_LOOP_CONTINUE = 0,
+	IOU_LOOP_STOP,
+};
+
+static inline bool io_has_loop_ops(struct io_ring_ctx *ctx)
+{
+	return data_race(ctx->loop_step);
+}
+
+int io_run_loop(struct io_ring_ctx *ctx);
+
+#endif
-- 
2.52.0[PATCH v4 1/6] io_uring: introduce callback driven main loopPavel Begunkov <asml.silence@gmail.com> undefinedio-uring@vger.kernel.org undefined undefined