From: Pavel Begunkov <asml.silence@gmail.com>

Add an option to wrap a zcrx instance into a file and expose it to the
user space. Currently, users can't do anything meaningful with the file,
but it'll be used in a next patch to import it into another io_uring
instance. It's implemented as a new op called ZCRX_CTRL_EXPORT for the
IORING_REGISTER_ZCRX_CTRL registration opcode.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
---
 include/uapi/linux/io_uring.h |  2 ++
 io_uring/zcrx.c               | 62 +++++++++++++++++++++++++++++++----
 2 files changed, 58 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 8b4935b983e7..34bd32402902 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -1082,6 +1082,8 @@ struct io_uring_zcrx_ifq_reg {
 };
 
 enum zcrx_ctrl_op {
+	ZCRX_CTRL_EXPORT,
+
 	__ZCRX_CTRL_LAST,
 };
 
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index e9981478bcf6..17ce49536f41 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -8,6 +8,7 @@
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/skbuff_ref.h>
+#include <linux/anon_inodes.h>
 
 #include <net/page_pool/helpers.h>
 #include <net/page_pool/memory_provider.h>
@@ -586,6 +587,15 @@ static void io_zcrx_scrub(struct io_zcrx_ifq *ifq)
 	}
 }
 
+static void zcrx_unregister(struct io_zcrx_ifq *ifq)
+{
+	if (refcount_dec_and_test(&ifq->user_refs)) {
+		io_close_queue(ifq);
+		io_zcrx_scrub(ifq);
+	}
+	io_put_zcrx_ifq(ifq);
+}
+
 struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ctx,
 					    unsigned int id)
 {
@@ -596,6 +606,46 @@ struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ctx,
 	return ifq ? &ifq->region : NULL;
 }
 
+static int zcrx_box_release(struct inode *inode, struct file *file)
+{
+	struct io_zcrx_ifq *ifq = file->private_data;
+
+	zcrx_unregister(ifq);
+	return 0;
+}
+
+static const struct file_operations zcrx_box_fops = {
+	.owner		= THIS_MODULE,
+	.release	= zcrx_box_release,
+};
+
+static int export_zcrx(struct io_ring_ctx *ctx, struct io_zcrx_ifq *ifq,
+		       struct zcrx_ctrl *ctrl)
+{
+	struct file *file;
+	int fd = -1;
+
+	if (!mem_is_zero(&ctrl->resv, sizeof(ctrl->resv)))
+		return -EINVAL;
+	fd = get_unused_fd_flags(O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+	refcount_inc(&ifq->refs);
+	refcount_inc(&ifq->user_refs);
+
+	file = anon_inode_create_getfile("[zcrx]", &zcrx_box_fops,
+					 ifq, O_CLOEXEC, NULL);
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		zcrx_unregister(ifq);
+		return PTR_ERR(file);
+	}
+
+	fd_install(fd, file);
+	return fd;
+}
+
 int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args)
 {
 	struct zcrx_ctrl ctrl;
@@ -612,6 +662,11 @@ int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args)
 	if (!ifq)
 		return -ENXIO;
 
+	switch (ctrl.op) {
+	case ZCRX_CTRL_EXPORT:
+		return export_zcrx(ctx, ifq, &ctrl);
+	}
+
 	return -EINVAL;
 }
 
@@ -757,12 +812,7 @@ void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx)
 		}
 		if (!ifq)
 			break;
-
-		if (refcount_dec_and_test(&ifq->user_refs)) {
-			io_close_queue(ifq);
-			io_zcrx_scrub(ifq);
-		}
-		io_put_zcrx_ifq(ifq);
+		zcrx_unregister(ifq);
 	}
 
 	xa_destroy(&ctx->zcrx_ctxs);
-- 
2.47.3