selftests: ublk: enable zero copy for null target

Enable zero copy for null target so that we can evaluate performance
from zero copy or not.

Also this should be the simplest ublk zero copy implementation, which
can be served as zc example.

Add test for covering 'add -t null -z'.

Signed-off-by: Ming Lei <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

Author: Ming Lei

tools/testing/selftests/ublk/Makefile

@@ -6,6 +6,7 @@ LDLIBS += -lpthread -lm -luring
 TEST_PROGS := test_generic_01.sh
 
 TEST_PROGS += test_null_01.sh
+TEST_PROGS += test_null_02.sh
 TEST_PROGS += test_loop_01.sh
 TEST_PROGS += test_loop_02.sh
 TEST_PROGS += test_loop_03.sh

tools/testing/selftests/ublk/kublk.h

@@ -198,6 +198,11 @@ static inline unsigned int user_data_to_tgt_data(__u64 user_data)
 	return (user_data >> 24) & 0xffff;
 }
 
+static inline unsigned short ublk_cmd_op_nr(unsigned int op)
+{
+	return _IOC_NR(op);
+}
+
 static inline void ublk_err(const char *fmt, ...)
 {
 	va_list ap;

tools/testing/selftests/ublk/null.c

@@ -2,6 +2,14 @@
 
 #include "kublk.h"
 
+#ifndef IORING_NOP_INJECT_RESULT
+#define IORING_NOP_INJECT_RESULT        (1U << 0)
+#endif
+
+#ifndef IORING_NOP_FIXED_BUFFER
+#define IORING_NOP_FIXED_BUFFER         (1U << 3)
+#endif
+
 static int ublk_null_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
 {
 	const struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
@@ -20,19 +28,79 @@ static int ublk_null_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
 		},
 	};
 
+	if (info->flags & UBLK_F_SUPPORT_ZERO_COPY)
+		dev->tgt.sq_depth = dev->tgt.cq_depth = 2 * info->queue_depth;
 	return 0;
 }
 
+static int null_queue_zc_io(struct ublk_queue *q, int tag)
+{
+	const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+	unsigned ublk_op = ublksrv_get_op(iod);
+	struct io_uring_sqe *sqe[3];
+
+	ublk_queue_alloc_sqes(q, sqe, 3);
+
+	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, tag);
+	sqe[0]->user_data = build_user_data(tag,
+			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, 1);
+	sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
+
+	io_uring_prep_nop(sqe[1]);
+	sqe[1]->buf_index = tag;
+	sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK;
+	sqe[1]->rw_flags = IORING_NOP_FIXED_BUFFER | IORING_NOP_INJECT_RESULT;
+	sqe[1]->len = iod->nr_sectors << 9; 	/* injected result */
+	sqe[1]->user_data = build_user_data(tag, ublk_op, 0, 1);
+
+	io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, tag);
+	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, 1);
+
+	// buf register is marked as IOSQE_CQE_SKIP_SUCCESS
+	return 2;
+}
+
+static void ublk_null_io_done(struct ublk_queue *q, int tag,
+		const struct io_uring_cqe *cqe)
+{
+	unsigned op = user_data_to_op(cqe->user_data);
+	struct ublk_io *io = ublk_get_io(q, tag);
+
+	if (cqe->res < 0 || op != ublk_cmd_op_nr(UBLK_U_IO_UNREGISTER_IO_BUF)) {
+		if (!io->result)
+			io->result = cqe->res;
+		if (cqe->res < 0)
+			ublk_err("%s: io failed op %x user_data %lx\n",
+					__func__, op, cqe->user_data);
+	}
+
+	/* buffer register op is IOSQE_CQE_SKIP_SUCCESS */
+	if (op == ublk_cmd_op_nr(UBLK_U_IO_REGISTER_IO_BUF))
+		io->tgt_ios += 1;
+
+	if (ublk_completed_tgt_io(q, tag))
+		ublk_complete_io(q, tag, io->result);
+}
+
 static int ublk_null_queue_io(struct ublk_queue *q, int tag)
 {
 	const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+	int zc = ublk_queue_use_zc(q);
+	int queued;
+
+	if (!zc) {
+		ublk_complete_io(q, tag, iod->nr_sectors << 9);
+		return 0;
+	}
 
-	ublk_complete_io(q, tag, iod->nr_sectors << 9);
+	queued = null_queue_zc_io(q, tag);
+	ublk_queued_tgt_io(q, tag, queued);
 	return 0;
 }
 
 const struct ublk_tgt_ops null_tgt_ops = {
 	.name = "null",
 	.init_tgt = ublk_null_tgt_init,
 	.queue_io = ublk_null_queue_io,
+	.tgt_io_done = ublk_null_io_done,
 };

tools/testing/selftests/ublk/test_null_02.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="null_02"
+ERR_CODE=0
+
+_prep_test "null" "basic IO test with zero copy"
+
+dev_id=$(_add_ublk_dev -t null -z)
+_check_add_dev $TID $?
+
+# run fio over the two disks
+fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio --rw=readwrite --iodepth=32 --size=256M > /dev/null 2>&1
+ERR_CODE=$?
+
+_cleanup_test "null"
+
+_show_result $TID $ERR_CODE