io_uring: add register/unregister napi function

This adds an api to register and unregister the napi for io-uring. If
the arg value is specified when unregistering, the current napi setting
for the busy poll timeout is copied into the user structure. If this is
not required, NULL can be passed as the arg value.

Signed-off-by: Stefan Roesch <shr@devkernel.io>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230608163839.2891748-7-shr@devkernel.io
Signed-off-by: Jens Axboe <axboe@kernel.dk>

include/uapi/linux/io_uring.h

@@ -571,6 +571,10 @@ enum {
 	/* return status information for a buffer group */
 	IORING_REGISTER_PBUF_STATUS		= 26,
 
+	/* set/clear busy poll settings */
+	IORING_REGISTER_NAPI			= 27,
+	IORING_UNREGISTER_NAPI			= 28,
+
 	/* this goes last */
 	IORING_REGISTER_LAST,
 
@@ -704,6 +708,14 @@ struct io_uring_buf_status {
 	__u32	resv[8];
 };
 
+/* argument for IORING_(UN)REGISTER_NAPI */
+struct io_uring_napi {
+	__u32	busy_poll_to;
+	__u8	prefer_busy_poll;
+	__u8	pad[3];
+	__u64	resv;
+};
+
 /*
  * io_uring_restriction->opcode values
  */

io_uring/napi.c

@@ -207,6 +207,58 @@ void io_napi_free(struct io_ring_ctx *ctx)
 	spin_unlock(&ctx->napi_lock);
 }
 
+/*
+ * io_napi_register() - Register napi with io-uring
+ * @ctx: pointer to io-uring context structure
+ * @arg: pointer to io_uring_napi structure
+ *
+ * Register napi in the io-uring context.
+ */
+int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	const struct io_uring_napi curr = {
+		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
+	};
+	struct io_uring_napi napi;
+
+	if (copy_from_user(&napi, arg, sizeof(napi)))
+		return -EFAULT;
+	if (napi.pad[0] || napi.pad[1] || napi.pad[2] || napi.resv)
+		return -EINVAL;
+
+	WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll);
+
+	if (copy_to_user(arg, &curr, sizeof(curr)))
+		return -EFAULT;
+
+	return 0;
+}
+
+/*
+ * io_napi_unregister() - Unregister napi with io-uring
+ * @ctx: pointer to io-uring context structure
+ * @arg: pointer to io_uring_napi structure
+ *
+ * Unregister napi. If arg has been specified copy the busy poll timeout and
+ * prefer busy poll setting to the passed in structure.
+ */
+int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	const struct io_uring_napi curr = {
+		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
+	};
+
+	if (arg && copy_to_user(arg, &curr, sizeof(curr)))
+		return -EFAULT;
+
+	WRITE_ONCE(ctx->napi_busy_poll_to, 0);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, false);
+	return 0;
+}
+
 /*
  * __io_napi_adjust_timeout() - Add napi id to the busy poll list
  * @ctx: pointer to io-uring context structure

io_uring/napi.h

@@ -12,6 +12,9 @@
 void io_napi_init(struct io_ring_ctx *ctx);
 void io_napi_free(struct io_ring_ctx *ctx);
 
+int io_register_napi(struct io_ring_ctx *ctx, void __user *arg);
+int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg);
+
 void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock);
 
 void __io_napi_adjust_timeout(struct io_ring_ctx *ctx,
@@ -68,6 +71,14 @@ static inline void io_napi_init(struct io_ring_ctx *ctx)
 static inline void io_napi_free(struct io_ring_ctx *ctx)
 {
 }
+static inline int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+static inline int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
 static inline bool io_napi(struct io_ring_ctx *ctx)
 {
 	return false;

io_uring/register.c

@@ -26,6 +26,7 @@
 #include "register.h"
 #include "cancel.h"
 #include "kbuf.h"
+#include "napi.h"
 
 #define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
 				 IORING_REGISTER_LAST + IORING_OP_LAST)
@@ -550,6 +551,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_register_pbuf_status(ctx, arg);
 		break;
+	case IORING_REGISTER_NAPI:
+		ret = -EINVAL;
+		if (!arg || nr_args != 1)
+			break;
+		ret = io_register_napi(ctx, arg);
+		break;
+	case IORING_UNREGISTER_NAPI:
+		ret = -EINVAL;
+		if (nr_args != 1)
+			break;
+		ret = io_unregister_napi(ctx, arg);
+		break;
 	default:
 		ret = -EINVAL;
 		break;