selftests: ublk: kublk: plumb q_id in io_uring user_data

Currently, when we process CQEs, we know which ublk_queue we are working
on because we know which ring we are working on, and ublk_queues and
rings are in 1:1 correspondence. However, as we decouple ublk_queues
from ublk server threads, ublk_queues and rings will no longer be in 1:1
correspondence - each ublk server thread will have a ring, and each
thread may issue commands against more than one ublk_queue. So in order
to know which ublk_queue a CQE refers to, plumb that information in the
associated SQE's user_data.

Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250529-ublk_task_per_io-v8-2-e9d3b119336a@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: ps-ushankar

tools/testing/selftests/ublk/fault_inject.c

@@ -48,7 +48,7 @@ static int ublk_fault_inject_queue_io(struct ublk_queue *q, int tag)
 
 	ublk_queue_alloc_sqes(q, &sqe, 1);
 	io_uring_prep_timeout(sqe, &ts, 1, 0);
-	sqe->user_data = build_user_data(tag, ublksrv_get_op(iod), 0, 1);
+	sqe->user_data = build_user_data(tag, ublksrv_get_op(iod), 0, q->q_id, 1);
 
 	ublk_queued_tgt_io(q, tag, 1);
 

tools/testing/selftests/ublk/file_backed.c

@@ -22,7 +22,7 @@ static int loop_queue_flush_io(struct ublk_queue *q, const struct ublksrv_io_des
 	io_uring_prep_fsync(sqe[0], 1 /*fds[1]*/, IORING_FSYNC_DATASYNC);
 	io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE);
 	/* bit63 marks us as tgt io */
-	sqe[0]->user_data = build_user_data(tag, ublk_op, 0, 1);
+	sqe[0]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
 	return 1;
 }
 
@@ -48,7 +48,7 @@ static int loop_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_de
 			sqe[0]->buf_index = tag;
 		io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE);
 		/* bit63 marks us as tgt io */
-		sqe[0]->user_data = build_user_data(tag, ublk_op, 0, 1);
+		sqe[0]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
 		return 1;
 	}
 
@@ -57,17 +57,17 @@ static int loop_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_de
 	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, tag);
 	sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
 	sqe[0]->user_data = build_user_data(tag,
-			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, 1);
+			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
 
 	io_uring_prep_rw(op, sqe[1], 1 /*fds[1]*/, 0,
 		iod->nr_sectors << 9,
 		iod->start_sector << 9);
 	sqe[1]->buf_index = tag;
 	sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK;
-	sqe[1]->user_data = build_user_data(tag, ublk_op, 0, 1);
+	sqe[1]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 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);
+	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
 
 	return 2;
 }

tools/testing/selftests/ublk/kublk.c

@@ -627,7 +627,7 @@ int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
 	if (q->state & UBLKSRV_AUTO_BUF_REG)
 		ublk_set_auto_buf_reg(q, sqe[0], tag);
 
-	user_data = build_user_data(tag, _IOC_NR(cmd_op), 0, 0);
+	user_data = build_user_data(tag, _IOC_NR(cmd_op), 0, q->q_id, 0);
 	io_uring_sqe_set_data64(sqe[0], user_data);
 
 	io->flags = 0;
@@ -673,10 +673,11 @@ static inline void ublksrv_handle_tgt_cqe(struct ublk_queue *q,
 		q->tgt_ops->tgt_io_done(q, tag, cqe);
 }
 
-static void ublk_handle_cqe(struct io_uring *r,
+static void ublk_handle_cqe(struct ublk_dev *dev,
 		struct io_uring_cqe *cqe, void *data)
 {
-	struct ublk_queue *q = container_of(r, struct ublk_queue, ring);
+	unsigned q_id = user_data_to_q_id(cqe->user_data);
+	struct ublk_queue *q = &dev->q[q_id];
 	unsigned tag = user_data_to_tag(cqe->user_data);
 	unsigned cmd_op = user_data_to_op(cqe->user_data);
 	int fetch = (cqe->res != UBLK_IO_RES_ABORT) &&
@@ -727,17 +728,17 @@ static void ublk_handle_cqe(struct io_uring *r,
 	}
 }
 
-static int ublk_reap_events_uring(struct io_uring *r)
+static int ublk_reap_events_uring(struct ublk_queue *q)
 {
 	struct io_uring_cqe *cqe;
 	unsigned head;
 	int count = 0;
 
-	io_uring_for_each_cqe(r, head, cqe) {
-		ublk_handle_cqe(r, cqe, NULL);
+	io_uring_for_each_cqe(&q->ring, head, cqe) {
+		ublk_handle_cqe(q->dev, cqe, NULL);
 		count += 1;
 	}
-	io_uring_cq_advance(r, count);
+	io_uring_cq_advance(&q->ring, count);
 
 	return count;
 }
@@ -756,7 +757,7 @@ static int ublk_process_io(struct ublk_queue *q)
 		return -ENODEV;
 
 	ret = io_uring_submit_and_wait(&q->ring, 1);
-	reapped = ublk_reap_events_uring(&q->ring);
+	reapped = ublk_reap_events_uring(q);
 
 	ublk_dbg(UBLK_DBG_QUEUE, "submit result %d, reapped %d stop %d idle %d\n",
 			ret, reapped, (q->state & UBLKSRV_QUEUE_STOPPING),

tools/testing/selftests/ublk/kublk.h

@@ -49,7 +49,8 @@
 #define UBLKSRV_IO_IDLE_SECS		20
 
 #define UBLK_IO_MAX_BYTES               (1 << 20)
-#define UBLK_MAX_QUEUES                 32
+#define UBLK_MAX_QUEUES_SHIFT		5
+#define UBLK_MAX_QUEUES                 (1 << UBLK_MAX_QUEUES_SHIFT)
 #define UBLK_QUEUE_DEPTH                1024
 
 #define UBLK_DBG_DEV            (1U << 0)
@@ -225,11 +226,14 @@ static inline int is_target_io(__u64 user_data)
 }
 
 static inline __u64 build_user_data(unsigned tag, unsigned op,
-		unsigned tgt_data, unsigned is_target_io)
+		unsigned tgt_data, unsigned q_id, unsigned is_target_io)
 {
-	assert(!(tag >> 16) && !(op >> 8) && !(tgt_data >> 16));
+	/* we only have 7 bits to encode q_id */
+	_Static_assert(UBLK_MAX_QUEUES_SHIFT <= 7);
+	assert(!(tag >> 16) && !(op >> 8) && !(tgt_data >> 16) && !(q_id >> 7));
 
-	return tag | (op << 16) | (tgt_data << 24) | (__u64)is_target_io << 63;
+	return tag | (op << 16) | (tgt_data << 24) |
+		(__u64)q_id << 56 | (__u64)is_target_io << 63;
 }
 
 static inline unsigned int user_data_to_tag(__u64 user_data)
@@ -247,6 +251,11 @@ static inline unsigned int user_data_to_tgt_data(__u64 user_data)
 	return (user_data >> 24) & 0xffff;
 }
 
+static inline unsigned int user_data_to_q_id(__u64 user_data)
+{
+	return (user_data >> 56) & 0x7f;
+}
+
 static inline unsigned short ublk_cmd_op_nr(unsigned int op)
 {
 	return _IOC_NR(op);

tools/testing/selftests/ublk/null.c

@@ -43,7 +43,7 @@ static int ublk_null_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
 }
 
 static void __setup_nop_io(int tag, const struct ublksrv_io_desc *iod,
-		struct io_uring_sqe *sqe)
+		struct io_uring_sqe *sqe, int q_id)
 {
 	unsigned ublk_op = ublksrv_get_op(iod);
 
@@ -52,7 +52,7 @@ static void __setup_nop_io(int tag, const struct ublksrv_io_desc *iod,
 	sqe->flags |= IOSQE_FIXED_FILE;
 	sqe->rw_flags = IORING_NOP_FIXED_BUFFER | IORING_NOP_INJECT_RESULT;
 	sqe->len = iod->nr_sectors << 9; 	/* injected result */
-	sqe->user_data = build_user_data(tag, ublk_op, 0, 1);
+	sqe->user_data = build_user_data(tag, ublk_op, 0, q_id, 1);
 }
 
 static int null_queue_zc_io(struct ublk_queue *q, int tag)
@@ -64,14 +64,14 @@ static int null_queue_zc_io(struct ublk_queue *q, int tag)
 
 	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);
+			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
 	sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
 
-	__setup_nop_io(tag, iod, sqe[1]);
+	__setup_nop_io(tag, iod, sqe[1], q->q_id);
 	sqe[1]->flags |= IOSQE_IO_HARDLINK;
 
 	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);
+	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
 
 	// buf register is marked as IOSQE_CQE_SKIP_SUCCESS
 	return 2;
@@ -83,7 +83,7 @@ static int null_queue_auto_zc_io(struct ublk_queue *q, int tag)
 	struct io_uring_sqe *sqe[1];
 
 	ublk_queue_alloc_sqes(q, sqe, 1);
-	__setup_nop_io(tag, iod, sqe[0]);
+	__setup_nop_io(tag, iod, sqe[0], q->q_id);
 	return 1;
 }
 

tools/testing/selftests/ublk/stripe.c

@@ -144,7 +144,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_
 		io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, tag);
 		sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
 		sqe[0]->user_data = build_user_data(tag,
-			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, 1);
+			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
 	}
 
 	for (i = zc; i < s->nr + extra - zc; i++) {
@@ -162,13 +162,14 @@ static int stripe_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_
 				sqe[i]->flags |= IOSQE_IO_HARDLINK;
 		}
 		/* bit63 marks us as tgt io */
-		sqe[i]->user_data = build_user_data(tag, ublksrv_get_op(iod), i - zc, 1);
+		sqe[i]->user_data = build_user_data(tag, ublksrv_get_op(iod), i - zc, q->q_id, 1);
 	}
 	if (zc) {
 		struct io_uring_sqe *unreg = sqe[s->nr + 1];
 
 		io_uring_prep_buf_unregister(unreg, 0, tag, q->q_id, tag);
-		unreg->user_data = build_user_data(tag, ublk_cmd_op_nr(unreg->cmd_op), 0, 1);
+		unreg->user_data = build_user_data(
+			tag, ublk_cmd_op_nr(unreg->cmd_op), 0, q->q_id, 1);
 	}
 
 	/* register buffer is skip_success */
@@ -185,7 +186,7 @@ static int handle_flush(struct ublk_queue *q, const struct ublksrv_io_desc *iod,
 	for (i = 0; i < conf->nr_files; i++) {
 		io_uring_prep_fsync(sqe[i], i + 1, IORING_FSYNC_DATASYNC);
 		io_uring_sqe_set_flags(sqe[i], IOSQE_FIXED_FILE);
-		sqe[i]->user_data = build_user_data(tag, UBLK_IO_OP_FLUSH, 0, 1);
+		sqe[i]->user_data = build_user_data(tag, UBLK_IO_OP_FLUSH, 0, q->q_id, 1);
 	}
 	return conf->nr_files;
 }