io_uring/bpf-ops: implement bpf ops registration

Implement BPF struct ops registration. It's registered off the BPF
path, and can be removed by BPF as well as io_uring. To protect it,
introduce a global lock synchronising registration. ctx->uring_lock can
be nested under it. ctx->bpf_ops is write protected by both locks and
so it's safe to read it under either of them.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://patch.msgid.link/1f46bffd76008de49cbafa2ad77d348810a4f69e.1772109579.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: isilence

include/linux/io_uring_types.h

@@ -8,6 +8,9 @@
 #include <linux/llist.h>
 #include <uapi/linux/io_uring.h>
 
+struct iou_loop_params;
+struct io_uring_bpf_ops;
+
 enum {
 	/*
 	 * A hint to not wake right away but delay until there are enough of
@@ -488,6 +491,8 @@ struct io_ring_ctx {
 	DECLARE_HASHTABLE(napi_ht, 4);
 #endif
 
+	struct io_uring_bpf_ops		*bpf_ops;
+
 	/*
 	 * Protection for resize vs mmap races - both the mmap and resize
 	 * side will need to grab this lock, to prevent either side from

io_uring/bpf-ops.c

@@ -5,10 +5,11 @@
 
 #include "io_uring.h"
 #include "register.h"
+#include "loop.h"
 #include "memmap.h"
 #include "bpf-ops.h"
-#include "loop.h"
 
+static DEFINE_MUTEX(io_bpf_ctrl_mutex);
 static const struct btf_type *loop_params_type;
 
 __bpf_kfunc_start_defs();
@@ -143,16 +144,103 @@ static int bpf_io_init_member(const struct btf_type *t,
 			       const struct btf_member *member,
 			       void *kdata, const void *udata)
 {
+	u32 moff = __btf_member_bit_offset(t, member) / 8;
+	const struct io_uring_bpf_ops *uops = udata;
+	struct io_uring_bpf_ops *ops = kdata;
+
+	switch (moff) {
+	case offsetof(struct io_uring_bpf_ops, ring_fd):
+		ops->ring_fd = uops->ring_fd;
+		return 1;
+	}
+	return 0;
+}
+
+static int io_install_bpf(struct io_ring_ctx *ctx, struct io_uring_bpf_ops *ops)
+{
+	if (ctx->flags & (IORING_SETUP_SQPOLL | IORING_SETUP_IOPOLL))
+		return -EOPNOTSUPP;
+	if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN))
+		return -EOPNOTSUPP;
+
+	if (ctx->bpf_ops)
+		return -EBUSY;
+	if (WARN_ON_ONCE(!ops->loop_step))
+		return -EINVAL;
+
+	ops->priv = ctx;
+	ctx->bpf_ops = ops;
+	ctx->loop_step = ops->loop_step;
 	return 0;
 }
 
 static int bpf_io_reg(void *kdata, struct bpf_link *link)
 {
-	return -EOPNOTSUPP;
+	struct io_uring_bpf_ops *ops = kdata;
+	struct io_ring_ctx *ctx;
+	struct file *file;
+	int ret = -EBUSY;
+
+	file = io_uring_register_get_file(ops->ring_fd, false);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+	ctx = file->private_data;
+
+	scoped_guard(mutex, &io_bpf_ctrl_mutex) {
+		guard(mutex)(&ctx->uring_lock);
+		ret = io_install_bpf(ctx, ops);
+	}
+
+	fput(file);
+	return ret;
+}
+
+static void io_eject_bpf(struct io_ring_ctx *ctx)
+{
+	struct io_uring_bpf_ops *ops = ctx->bpf_ops;
+
+	if (WARN_ON_ONCE(!ops))
+		return;
+	if (WARN_ON_ONCE(ops->priv != ctx))
+		return;
+
+	ops->priv = NULL;
+	ctx->bpf_ops = NULL;
+	ctx->loop_step = NULL;
 }
 
 static void bpf_io_unreg(void *kdata, struct bpf_link *link)
 {
+	struct io_uring_bpf_ops *ops = kdata;
+	struct io_ring_ctx *ctx;
+
+	guard(mutex)(&io_bpf_ctrl_mutex);
+	ctx = ops->priv;
+	if (ctx) {
+		guard(mutex)(&ctx->uring_lock);
+		if (WARN_ON_ONCE(ctx->bpf_ops != ops))
+			return;
+
+		io_eject_bpf(ctx);
+	}
+}
+
+void io_unregister_bpf_ops(struct io_ring_ctx *ctx)
+{
+	/*
+	 * ->bpf_ops is write protected by io_bpf_ctrl_mutex and uring_lock,
+	 * and read protected by either. Try to avoid taking the global lock
+	 * for rings that never had any bpf installed.
+	 */
+	scoped_guard(mutex, &ctx->uring_lock) {
+		if (!ctx->bpf_ops)
+			return;
+	}
+
+	guard(mutex)(&io_bpf_ctrl_mutex);
+	guard(mutex)(&ctx->uring_lock);
+	if (ctx->bpf_ops)
+		io_eject_bpf(ctx);
 }
 
 static struct bpf_struct_ops bpf_ring_ops = {

io_uring/bpf-ops.h

@@ -17,4 +17,12 @@ struct io_uring_bpf_ops {
 	void *priv;
 };
 
+#ifdef CONFIG_IO_URING_BPF_OPS
+void io_unregister_bpf_ops(struct io_ring_ctx *ctx);
+#else
+static inline void io_unregister_bpf_ops(struct io_ring_ctx *ctx)
+{
+}
+#endif
+
 #endif /* IOU_BPF_OPS_H */

io_uring/io_uring.c

@@ -2148,6 +2148,7 @@ static __cold void io_req_caches_free(struct io_ring_ctx *ctx)
 
 static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 {
+	io_unregister_bpf_ops(ctx);
 	io_sq_thread_finish(ctx);
 
 	mutex_lock(&ctx->uring_lock);