io_uring: move zc reporting from the hot path

Add custom tw and notif callbacks on top of usual bits also handling zc
reporting. That moves it from the hot path.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/40de4a6409042478e1f35adc4912e23226cb1b5c.1667557923.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/net.c

@@ -923,6 +923,9 @@ void io_send_zc_cleanup(struct io_kiocb *req)
 	}
 }
 
+#define IO_ZC_FLAGS_COMMON (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_FIXED_BUF)
+#define IO_ZC_FLAGS_VALID  (IO_ZC_FLAGS_COMMON | IORING_SEND_ZC_REPORT_USAGE)
+
 int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_sr_msg *zc = io_kiocb_to_cmd(req, struct io_sr_msg);
@@ -935,11 +938,6 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (req->flags & REQ_F_CQE_SKIP)
 		return -EINVAL;
 
-	zc->flags = READ_ONCE(sqe->ioprio);
-	if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST |
-			  IORING_RECVSEND_FIXED_BUF |
-			  IORING_SEND_ZC_REPORT_USAGE))
-		return -EINVAL;
 	notif = zc->notif = io_alloc_notif(ctx);
 	if (!notif)
 		return -ENOMEM;
@@ -947,6 +945,17 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	notif->cqe.res = 0;
 	notif->cqe.flags = IORING_CQE_F_NOTIF;
 	req->flags |= REQ_F_NEED_CLEANUP;
+
+	zc->flags = READ_ONCE(sqe->ioprio);
+	if (unlikely(zc->flags & ~IO_ZC_FLAGS_COMMON)) {
+		if (zc->flags & ~IO_ZC_FLAGS_VALID)
+			return -EINVAL;
+		if (zc->flags & IORING_SEND_ZC_REPORT_USAGE) {
+			io_notif_set_extended(notif);
+			io_notif_to_data(notif)->zc_report = true;
+		}
+	}
+
 	if (zc->flags & IORING_RECVSEND_FIXED_BUF) {
 		unsigned idx = READ_ONCE(sqe->buf_index);
 
@@ -956,9 +965,6 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		req->imu = READ_ONCE(ctx->user_bufs[idx]);
 		io_req_set_rsrc_node(notif, ctx, 0);
 	}
-	if (zc->flags & IORING_SEND_ZC_REPORT_USAGE) {
-		io_notif_to_data(notif)->zc_report = true;
-	}
 
 	if (req->opcode == IORING_OP_SEND_ZC) {
 		if (READ_ONCE(sqe->__pad3[0]))

io_uring/notif.c

@@ -18,11 +18,17 @@ static void __io_notif_complete_tw(struct io_kiocb *notif, bool *locked)
 		__io_unaccount_mem(ctx->user, nd->account_pages);
 		nd->account_pages = 0;
 	}
+	io_req_task_complete(notif, locked);
+}
+
+static void io_notif_complete_tw_ext(struct io_kiocb *notif, bool *locked)
+{
+	struct io_notif_data *nd = io_notif_to_data(notif);
 
 	if (nd->zc_report && (nd->zc_copied || !nd->zc_used))
 		notif->cqe.res |= IORING_NOTIF_USAGE_ZC_COPIED;
 
-	io_req_task_complete(notif, locked);
+	__io_notif_complete_tw(notif, locked);
 }
 
 static void io_tx_ubuf_callback(struct sk_buff *skb, struct ubuf_info *uarg,
@@ -31,15 +37,33 @@ static void io_tx_ubuf_callback(struct sk_buff *skb, struct ubuf_info *uarg,
 	struct io_notif_data *nd = container_of(uarg, struct io_notif_data, uarg);
 	struct io_kiocb *notif = cmd_to_io_kiocb(nd);
 
+	if (refcount_dec_and_test(&uarg->refcnt))
+		io_req_task_work_add(notif);
+}
+
+static void io_tx_ubuf_callback_ext(struct sk_buff *skb, struct ubuf_info *uarg,
+			     bool success)
+{
+	struct io_notif_data *nd = container_of(uarg, struct io_notif_data, uarg);
+
 	if (nd->zc_report) {
 		if (success && !nd->zc_used && skb)
 			WRITE_ONCE(nd->zc_used, true);
 		else if (!success && !nd->zc_copied)
 			WRITE_ONCE(nd->zc_copied, true);
 	}
+	io_tx_ubuf_callback(skb, uarg, success);
+}
 
-	if (refcount_dec_and_test(&uarg->refcnt))
+void io_notif_set_extended(struct io_kiocb *notif)
-		io_req_task_work_add(notif);
+{
+	struct io_notif_data *nd = io_notif_to_data(notif);
+
+	nd->zc_report = false;
+	nd->zc_used = false;
+	nd->zc_copied = false;
+	notif->io_task_work.func = io_notif_complete_tw_ext;
+	io_notif_to_data(notif)->uarg.callback = io_tx_ubuf_callback_ext;
 }
 
 struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx)
@@ -63,7 +87,6 @@ struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx)
 	nd->account_pages = 0;
 	nd->uarg.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN;
 	nd->uarg.callback = io_tx_ubuf_callback;
-	nd->zc_report = nd->zc_used = nd->zc_copied = false;
 	refcount_set(&nd->uarg.refcnt, 1);
 	return notif;
 }

io_uring/notif.h

@@ -19,6 +19,7 @@ struct io_notif_data {
 };
 
 struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx);
+void io_notif_set_extended(struct io_kiocb *notif);
 
 static inline struct io_notif_data *io_notif_to_data(struct io_kiocb *notif)
 {