[PATCH v4 12/12] io_uring/zcrx: share an ifq between rings

[David Wei <dw@davidwei.uk>]

Add a way to share an ifq from a src ring that is real (i.e. bound to a
HW RX queue) with other rings. This is done by passing a new flag
IORING_ZCRX_IFQ_REG_IMPORT in the registration struct
io_uring_zcrx_ifq_reg, alongside the fd of an exported zcrx ifq.

Signed-off-by: David Wei <dw@davidwei.uk>
---
 include/uapi/linux/io_uring.h |  4 +++
 io_uring/zcrx.c               | 63 +++++++++++++++++++++++++++++++++--
 2 files changed, 65 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 34bd32402902..0ead7f6b2094 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -1063,6 +1063,10 @@ struct io_uring_zcrx_area_reg {
 	__u64	__resv2[2];
 };
 
+enum io_uring_zcrx_ifq_reg_flags {
+	IORING_ZCRX_IFQ_REG_IMPORT	= 1,
+};
+
 /*
  * Argument for IORING_REGISTER_ZCRX_IFQ
  */
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 17ce49536f41..5a0af9dd6a8e 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -625,6 +625,11 @@ static int export_zcrx(struct io_ring_ctx *ctx, struct io_zcrx_ifq *ifq,
 	struct file *file;
 	int fd = -1;
 
+	if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN))
+		return -EINVAL;
+	if (!(ctx->flags & (IORING_SETUP_CQE32|IORING_SETUP_CQE_MIXED)))
+		return -EINVAL;
+
 	if (!mem_is_zero(&ctrl->resv, sizeof(ctrl->resv)))
 		return -EINVAL;
 	fd = get_unused_fd_flags(O_CLOEXEC);
@@ -646,6 +651,58 @@ static int export_zcrx(struct io_ring_ctx *ctx, struct io_zcrx_ifq *ifq,
 	return fd;
 }
 
+static int import_zcrx(struct io_ring_ctx *ctx,
+		       struct io_uring_zcrx_ifq_reg __user *arg,
+		       struct io_uring_zcrx_ifq_reg *reg)
+{
+	struct io_zcrx_ifq *ifq;
+	struct file *file;
+	int fd, ret;
+	u32 id;
+
+	if (reg->if_rxq || reg->rq_entries || reg->area_ptr || reg->region_ptr)
+		return -EINVAL;
+
+	fd = reg->if_idx;
+	CLASS(fd, f)(fd);
+	if (fd_empty(f))
+		return -EBADF;
+
+	file = fd_file(f);
+	if (file->f_op != &zcrx_box_fops || !file->private_data)
+		return -EBADF;
+
+	ifq = file->private_data;
+	refcount_inc(&ifq->refs);
+	refcount_inc(&ifq->user_refs);
+
+	scoped_guard(mutex, &ctx->mmap_lock) {
+		ret = xa_alloc(&ctx->zcrx_ctxs, &id, NULL, xa_limit_31b, GFP_KERNEL);
+		if (ret)
+			goto err;
+	}
+
+	reg->zcrx_id = id;
+	if (copy_to_user(arg, reg, sizeof(*reg))) {
+		ret = -EFAULT;
+		goto err_xa_erase;
+	}
+
+	scoped_guard(mutex, &ctx->mmap_lock) {
+		ret = -ENOMEM;
+		if (xa_store(&ctx->zcrx_ctxs, id, ifq, GFP_KERNEL))
+			goto err_xa_erase;
+	}
+
+	return 0;
+err_xa_erase:
+	scoped_guard(mutex, &ctx->mmap_lock)
+		xa_erase(&ctx->zcrx_ctxs, id);
+err:
+	zcrx_unregister(ifq);
+	return ret;
+}
+
 int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args)
 {
 	struct zcrx_ctrl ctrl;
@@ -695,11 +752,13 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 		return -EINVAL;
 	if (copy_from_user(&reg, arg, sizeof(reg)))
 		return -EFAULT;
-	if (copy_from_user(&rd, u64_to_user_ptr(reg.region_ptr), sizeof(rd)))
-		return -EFAULT;
 	if (!mem_is_zero(&reg.__resv, sizeof(reg.__resv)) ||
 	    reg.__resv2 || reg.zcrx_id)
 		return -EINVAL;
+	if (reg.flags & IORING_ZCRX_IFQ_REG_IMPORT)
+		return import_zcrx(ctx, arg, &reg);
+	if (copy_from_user(&rd, u64_to_user_ptr(reg.region_ptr), sizeof(rd)))
+		return -EFAULT;
 	if (reg.if_rxq == -1 || !reg.rq_entries || reg.flags)
 		return -EINVAL;
 	if (reg.rq_entries > IO_RQ_MAX_ENTRIES) {
-- 
2.47.3