Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
ublk selftests: add --no_ublk_fixed_fd for not using registered ublk char device
Add a new command line option --no_ublk_fixed_fd that excludes the ublk
control device (/dev/ublkcN) from io_uring's registered files array.
When this option is used, only backing files are registered starting
from index 1, while the ublk control device is accessed using its raw
file descriptor.
Add ublk_get_registered_fd() helper function that returns the appropriate
file descriptor for use with io_uring operations.
Key optimizations implemented:
- Cache UBLKS_Q_NO_UBLK_FIXED_FD flag in ublk_queue.flags to avoid
reading dev->no_ublk_fixed_fd in fast path
- Cache ublk char device fd in ublk_queue.ublk_fd for fast access
- Update ublk_get_registered_fd() to use ublk_queue * parameter
- Update io_uring_prep_buf_register/unregister() to use ublk_queue *
- Replace ublk_device * access with ublk_queue * access in fast paths
Also pass --no_ublk_fixed_fd to test_stress_04.sh for covering
plain ublk char device mode.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250827121602.2619736-3-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
authored by
Ming Lei
and committed by
Jens Axboe
9b2785ea
c5c5eb24
+74
-33
+5
-5
tools/testing/selftests/ublk/file_backed.c
+5
-5
tools/testing/selftests/ublk/file_backed.c
···
20
20
struct io_uring_sqe *sqe[1];
21
21
22
22
ublk_io_alloc_sqes(t, sqe, 1);
23
-
io_uring_prep_fsync(sqe[0], 1 /*fds[1]*/, IORING_FSYNC_DATASYNC);
23
+
io_uring_prep_fsync(sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/, IORING_FSYNC_DATASYNC);
24
24
io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE);
25
25
/* bit63 marks us as tgt io */
26
26
sqe[0]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
···
42
42
if (!sqe[0])
43
43
return -ENOMEM;
44
44
45
-
io_uring_prep_rw(op, sqe[0], 1 /*fds[1]*/,
45
+
io_uring_prep_rw(op, sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/,
46
46
addr,
47
47
iod->nr_sectors << 9,
48
48
iod->start_sector << 9);
···
56
56
57
57
ublk_io_alloc_sqes(t, sqe, 3);
58
58
59
-
io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
59
+
io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
60
60
sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
61
61
sqe[0]->user_data = build_user_data(tag,
62
62
ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
63
63
64
-
io_uring_prep_rw(op, sqe[1], 1 /*fds[1]*/, 0,
64
+
io_uring_prep_rw(op, sqe[1], ublk_get_registered_fd(q, 1) /*fds[1]*/, 0,
65
65
iod->nr_sectors << 9,
66
66
iod->start_sector << 9);
67
67
sqe[1]->buf_index = tag;
68
68
sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK;
69
69
sqe[1]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
70
70
71
-
io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
71
+
io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
72
72
sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
73
73
74
74
return 2;
+31
-7
tools/testing/selftests/ublk/kublk.c
+31
-7
tools/testing/selftests/ublk/kublk.c
···
432
432
}
433
433
}
434
434
435
-
static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
435
+
static int ublk_queue_init(struct ublk_queue *q, unsigned long long extra_flags)
436
436
{
437
437
struct ublk_dev *dev = q->dev;
438
438
int depth = dev->dev_info.queue_depth;
···
445
445
q->q_depth = depth;
446
446
q->flags = dev->dev_info.flags;
447
447
q->flags |= extra_flags;
448
+
449
+
/* Cache fd in queue for fast path access */
450
+
q->ublk_fd = dev->fds[0];
448
451
449
452
cmd_buf_size = ublk_queue_cmd_buf_sz(q);
450
453
off = UBLKSRV_CMD_BUF_OFFSET + q->q_id * ublk_queue_max_cmd_buf_sz();
···
484
481
return -ENOMEM;
485
482
}
486
483
487
-
static int ublk_thread_init(struct ublk_thread *t)
484
+
static int ublk_thread_init(struct ublk_thread *t, unsigned long long extra_flags)
488
485
{
489
486
struct ublk_dev *dev = t->dev;
487
+
unsigned long long flags = dev->dev_info.flags | extra_flags;
490
488
int ring_depth = dev->tgt.sq_depth, cq_depth = dev->tgt.cq_depth;
491
489
int ret;
492
490
···
516
512
517
513
io_uring_register_ring_fd(&t->ring);
518
514
519
-
ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds);
515
+
if (flags & UBLKS_Q_NO_UBLK_FIXED_FD) {
516
+
/* Register only backing files starting from index 1, exclude ublk control device */
517
+
if (dev->nr_fds > 1) {
518
+
ret = io_uring_register_files(&t->ring, &dev->fds[1], dev->nr_fds - 1);
519
+
} else {
520
+
/* No backing files to register, skip file registration */
521
+
ret = 0;
522
+
}
523
+
} else {
524
+
ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds);
525
+
}
520
526
if (ret) {
521
527
ublk_err("ublk dev %d thread %d register files failed %d\n",
522
528
t->dev->dev_info.dev_id, t->idx, ret);
···
640
626
641
627
/* These fields should be written once, never change */
642
628
ublk_set_sqe_cmd_op(sqe[0], cmd_op);
643
-
sqe[0]->fd = 0; /* dev->fds[0] */
629
+
sqe[0]->fd = ublk_get_registered_fd(q, 0); /* dev->fds[0] */
644
630
sqe[0]->opcode = IORING_OP_URING_CMD;
645
-
sqe[0]->flags = IOSQE_FIXED_FILE;
631
+
if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD)
632
+
sqe[0]->flags = 0; /* Use raw FD, not fixed file */
633
+
else
634
+
sqe[0]->flags = IOSQE_FIXED_FILE;
646
635
sqe[0]->rw_flags = 0;
647
636
cmd->tag = io->tag;
648
637
cmd->q_id = q->q_id;
···
849
832
unsigned idx;
850
833
sem_t *ready;
851
834
cpu_set_t *affinity;
835
+
unsigned long long extra_flags;
852
836
};
853
837
854
838
static void *ublk_io_handler_fn(void *data)
···
862
844
t->dev = info->dev;
863
845
t->idx = info->idx;
864
846
865
-
ret = ublk_thread_init(t);
847
+
ret = ublk_thread_init(t, info->extra_flags);
866
848
if (ret) {
867
849
ublk_err("ublk dev %d thread %u init failed\n",
868
850
dev_id, t->idx);
···
952
934
953
935
if (ctx->auto_zc_fallback)
954
936
extra_flags = UBLKS_Q_AUTO_BUF_REG_FALLBACK;
937
+
if (ctx->no_ublk_fixed_fd)
938
+
extra_flags |= UBLKS_Q_NO_UBLK_FIXED_FD;
955
939
956
940
for (i = 0; i < dinfo->nr_hw_queues; i++) {
957
941
dev->q[i].dev = dev;
···
971
951
tinfo[i].dev = dev;
972
952
tinfo[i].idx = i;
973
953
tinfo[i].ready = &ready;
954
+
tinfo[i].extra_flags = extra_flags;
974
955
975
956
/*
976
957
* If threads are not tied 1:1 to queues, setting thread
···
1492
1471
printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n",
1493
1472
exe, recovery ? "recover" : "add");
1494
1473
printf("\t[--foreground] [--quiet] [-z] [--auto_zc] [--auto_zc_fallback] [--debug_mask mask] [-r 0|1 ] [-g]\n");
1495
-
printf("\t[-e 0|1 ] [-i 0|1]\n");
1474
+
printf("\t[-e 0|1 ] [-i 0|1] [--no_ublk_fixed_fd]\n");
1496
1475
printf("\t[--nthreads threads] [--per_io_tasks]\n");
1497
1476
printf("\t[target options] [backfile1] [backfile2] ...\n");
1498
1477
printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
···
1555
1534
{ "size", 1, NULL, 's'},
1556
1535
{ "nthreads", 1, NULL, 0 },
1557
1536
{ "per_io_tasks", 0, NULL, 0 },
1537
+
{ "no_ublk_fixed_fd", 0, NULL, 0 },
1558
1538
{ 0, 0, 0, 0 }
1559
1539
};
1560
1540
const struct ublk_tgt_ops *ops = NULL;
···
1635
1613
ctx.nthreads = strtol(optarg, NULL, 10);
1636
1614
if (!strcmp(longopts[option_idx].name, "per_io_tasks"))
1637
1615
ctx.per_io_tasks = 1;
1616
+
if (!strcmp(longopts[option_idx].name, "no_ublk_fixed_fd"))
1617
+
ctx.no_ublk_fixed_fd = 1;
1638
1618
break;
1639
1619
case '?':
1640
1620
/*
+31
-14
tools/testing/selftests/ublk/kublk.h
+31
-14
tools/testing/selftests/ublk/kublk.h
···
77
77
unsigned int recovery:1;
78
78
unsigned int auto_zc_fallback:1;
79
79
unsigned int per_io_tasks:1;
80
+
unsigned int no_ublk_fixed_fd:1;
80
81
81
82
int _evtfd;
82
83
int _shmid;
···
167
166
168
167
/* borrow one bit of ublk uapi flags, which may never be used */
169
168
#define UBLKS_Q_AUTO_BUF_REG_FALLBACK (1ULL << 63)
169
+
#define UBLKS_Q_NO_UBLK_FIXED_FD (1ULL << 62)
170
170
__u64 flags;
171
+
int ublk_fd; /* cached ublk char device fd */
171
172
struct ublk_io ios[UBLK_QUEUE_DEPTH];
172
173
};
173
174
···
276
273
return nr_sqes;
277
274
}
278
275
279
-
static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe,
280
-
int dev_fd, int tag, int q_id, __u64 index)
276
+
static inline int ublk_get_registered_fd(struct ublk_queue *q, int fd_index)
277
+
{
278
+
if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD) {
279
+
if (fd_index == 0)
280
+
/* Return the raw ublk FD for index 0 */
281
+
return q->ublk_fd;
282
+
/* Adjust index for backing files (index 1 becomes 0, etc.) */
283
+
return fd_index - 1;
284
+
}
285
+
return fd_index;
286
+
}
287
+
288
+
static inline void __io_uring_prep_buf_reg_unreg(struct io_uring_sqe *sqe,
289
+
struct ublk_queue *q, int tag, int q_id, __u64 index)
281
290
{
282
291
struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd;
292
+
int dev_fd = ublk_get_registered_fd(q, 0);
283
293
284
294
io_uring_prep_read(sqe, dev_fd, 0, 0, 0);
285
295
sqe->opcode = IORING_OP_URING_CMD;
286
-
sqe->flags |= IOSQE_FIXED_FILE;
287
-
sqe->cmd_op = UBLK_U_IO_REGISTER_IO_BUF;
296
+
if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD)
297
+
sqe->flags &= ~IOSQE_FIXED_FILE;
298
+
else
299
+
sqe->flags |= IOSQE_FIXED_FILE;
288
300
289
301
cmd->tag = tag;
290
302
cmd->addr = index;
291
303
cmd->q_id = q_id;
292
304
}
293
305
294
-
static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe,
295
-
int dev_fd, int tag, int q_id, __u64 index)
306
+
static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe,
307
+
struct ublk_queue *q, int tag, int q_id, __u64 index)
296
308
{
297
-
struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd;
309
+
__io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index);
310
+
sqe->cmd_op = UBLK_U_IO_REGISTER_IO_BUF;
311
+
}
298
312
299
-
io_uring_prep_read(sqe, dev_fd, 0, 0, 0);
300
-
sqe->opcode = IORING_OP_URING_CMD;
301
-
sqe->flags |= IOSQE_FIXED_FILE;
313
+
static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe,
314
+
struct ublk_queue *q, int tag, int q_id, __u64 index)
315
+
{
316
+
__io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index);
302
317
sqe->cmd_op = UBLK_U_IO_UNREGISTER_IO_BUF;
303
-
304
-
cmd->tag = tag;
305
-
cmd->addr = index;
306
-
cmd->q_id = q_id;
307
318
}
308
319
309
320
static inline void *ublk_get_sqe_cmd(const struct io_uring_sqe *sqe)
+2
-2
tools/testing/selftests/ublk/null.c
+2
-2
tools/testing/selftests/ublk/null.c
···
63
63
64
64
ublk_io_alloc_sqes(t, sqe, 3);
65
65
66
-
io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
66
+
io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
67
67
sqe[0]->user_data = build_user_data(tag,
68
68
ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
69
69
sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
···
71
71
__setup_nop_io(tag, iod, sqe[1], q->q_id);
72
72
sqe[1]->flags |= IOSQE_IO_HARDLINK;
73
73
74
-
io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
74
+
io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
75
75
sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
76
76
77
77
// buf register is marked as IOSQE_CQE_SKIP_SUCCESS
+2
-2
tools/testing/selftests/ublk/stripe.c
+2
-2
tools/testing/selftests/ublk/stripe.c
···
142
142
ublk_io_alloc_sqes(t, sqe, s->nr + extra);
143
143
144
144
if (zc) {
145
-
io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, io->buf_index);
145
+
io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, io->buf_index);
146
146
sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
147
147
sqe[0]->user_data = build_user_data(tag,
148
148
ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
···
168
168
if (zc) {
169
169
struct io_uring_sqe *unreg = sqe[s->nr + 1];
170
170
171
-
io_uring_prep_buf_unregister(unreg, 0, tag, q->q_id, io->buf_index);
171
+
io_uring_prep_buf_unregister(unreg, q, tag, q->q_id, io->buf_index);
172
172
unreg->user_data = build_user_data(
173
173
tag, ublk_cmd_op_nr(unreg->cmd_op), 0, q->q_id, 1);
174
174
}
+3
-3
tools/testing/selftests/ublk/test_stress_04.sh
+3
-3
tools/testing/selftests/ublk/test_stress_04.sh
···
28
28
_create_backfile 1 128M
29
29
_create_backfile 2 128M
30
30
31
-
ublk_io_and_kill_daemon 8G -t null -q 4 -z &
32
-
ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
31
+
ublk_io_and_kill_daemon 8G -t null -q 4 -z --no_ublk_fixed_fd &
32
+
ublk_io_and_kill_daemon 256M -t loop -q 4 -z --no_ublk_fixed_fd "${UBLK_BACKFILES[0]}" &
33
33
ublk_io_and_kill_daemon 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
34
34
35
35
if _have_feature "AUTO_BUF_REG"; then
36
36
ublk_io_and_kill_daemon 8G -t null -q 4 --auto_zc &
37
37
ublk_io_and_kill_daemon 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" &
38
-
ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
38
+
ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc --no_ublk_fixed_fd "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
39
39
ublk_io_and_kill_daemon 8G -t null -q 4 -z --auto_zc --auto_zc_fallback &
40
40
fi
41
41