Add two kfuncs that should cover most of the needs:

1. bpf_io_uring_submit_sqes(), which allows to submit io_uring requests.
   It mirrors the normal user space submission path and follows all
   related io_uring_enter(2) rules. i.e. SQEs are taken from the SQ
   according to head/tail values. In case of IORING_SETUP_SQ_REWIND,
   it'll submit first N entries.

2. bpf_io_uring_get_region() returns a pointer to the specified region,
   where io_uring regions are kernel-userspace shared chunks of memory.
   It takes the size as an argument, which should be a load time
   constant. There are 3 types of regions:
   - IOU_REGION_SQ returns the submission queue.
   - IOU_REGION_CQ stores the CQ, SQ/CQ headers and the sqarray. In
     other words, it gives same memory that would normally be mmap'ed
     with IORING_FEAT_SINGLE_MMAP enabled IORING_OFF_SQ_RING.
   - IOU_REGION_MEM represents the memory / parameter region. It can be
     used to store request indirect parameters and for kernel - user
     communication.

It intentionally provides a thin but flexible API and expects BPF
programs to implement CQ/SQ header parsing, CQ walking, etc. That
mirrors how the normal user space works with rings and should help
to minimise kernel / kfunc helpers changes while introducing new generic
io_uring features.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 io_uring/bpf-ops.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++
 io_uring/bpf-ops.h |  6 ++++++
 2 files changed, 59 insertions(+)

diff --git a/io_uring/bpf-ops.c b/io_uring/bpf-ops.c
index 7db07eda5a48..ad4e3dc889ba 100644
--- a/io_uring/bpf-ops.c
+++ b/io_uring/bpf-ops.c
@@ -4,11 +4,56 @@
 
 #include "io_uring.h"
 #include "register.h"
+#include "memmap.h"
 #include "bpf-ops.h"
 #include "loop.h"
 
 static const struct btf_type *loop_params_type;
 
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_io_uring_submit_sqes(struct io_ring_ctx *ctx, u32 nr)
+{
+	return io_submit_sqes(ctx, nr);
+}
+
+__bpf_kfunc
+__u8 *bpf_io_uring_get_region(struct io_ring_ctx *ctx, __u32 region_id,
+			      const size_t rdwr_buf_size)
+{
+	struct io_mapped_region *r;
+
+	switch (region_id) {
+	case IOU_REGION_MEM:
+		r = &ctx->param_region;
+		break;
+	case IOU_REGION_CQ:
+		r = &ctx->ring_region;
+		break;
+	case IOU_REGION_SQ:
+		r = &ctx->sq_region;
+		break;
+	default:
+		return NULL;
+	}
+
+	if (unlikely(rdwr_buf_size > io_region_size(r)))
+		return NULL;
+	return io_region_get_ptr(r);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(io_uring_kfunc_set)
+BTF_ID_FLAGS(func, bpf_io_uring_submit_sqes, KF_SLEEPABLE | KF_TRUSTED_ARGS);
+BTF_ID_FLAGS(func, bpf_io_uring_get_region, KF_RET_NULL | KF_TRUSTED_ARGS);
+BTF_KFUNCS_END(io_uring_kfunc_set)
+
+static const struct btf_kfunc_id_set bpf_io_uring_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set = &io_uring_kfunc_set,
+};
+
 static int io_bpf_ops__loop_step(struct io_ring_ctx *ctx,
 				 struct iou_loop_params *lp)
 {
@@ -68,12 +113,20 @@ io_lookup_struct_type(struct btf *btf, const char *name)
 
 static int bpf_io_init(struct btf *btf)
 {
+	int ret;
+
 	loop_params_type = io_lookup_struct_type(btf, "iou_loop_params");
 	if (!loop_params_type) {
 		pr_err("io_uring: Failed to locate iou_loop_params\n");
 		return -EINVAL;
 	}
 
+	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+					&bpf_io_uring_kfunc_set);
+	if (ret) {
+		pr_err("io_uring: Failed to register kfuncs (%d)\n", ret);
+		return ret;
+	}
 	return 0;
 }
 
diff --git a/io_uring/bpf-ops.h b/io_uring/bpf-ops.h
index e8a08ae2df0a..b9e589ad519a 100644
--- a/io_uring/bpf-ops.h
+++ b/io_uring/bpf-ops.h
@@ -4,6 +4,12 @@
 
 #include <linux/io_uring_types.h>
 
+enum {
+	IOU_REGION_MEM,
+	IOU_REGION_CQ,
+	IOU_REGION_SQ,
+};
+
 struct io_uring_bpf_ops {
 	int (*loop_step)(struct io_ring_ctx *ctx, struct iou_loop_params *lp);
 
-- 
2.52.0