[PATCH V2] selftests: ublk: cap nthreads to kernel's actual nr_hw_queues

[PATCH V2] selftests: ublk: cap nthreads to kernel's actual nr_hw_queues

[Ming Lei]

dev->nthreads is derived from the user-requested queue count before the
ADD command, but the kernel may reduce nr_hw_queues (capped to
nr_cpu_ids). When the VM has fewer CPUs than requested queues, the
daemon creates more handler threads than there are kernel queues.

In non-batch mode, the extra threads access uninitialized queues
(q_depth=0), submit zero io_uring SQEs, and block forever in
io_cqring_wait. In batch mode, the extra threads cause similar hangs
during device removal.

In both cases, the stuck threads prevent the daemon from closing the
char device, holding the last ublk_device reference and causing
ublk_ctrl_del_dev() to hang in wait_event_interruptible().

Fix by capping dev->nthreads to the kernel-returned nr_hw_queues after
the ADD command completes. per_io_tasks mode is excluded because threads
interleave across all queues, so nthreads > nr_hw_queues is valid.

Fixes: abe54c160346 ("selftests: ublk: kublk: decouple ublk_queues from ublk server threads")
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
---
V2:
	- fix email address & signed-off-by

 tools/testing/selftests/ublk/kublk.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index fbd9b1e7342a..0b23c09daea5 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -1735,6 +1735,17 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
 		goto fail;
 	}
 
+	/*
+	 * The kernel may reduce nr_hw_queues (e.g. capped to nr_cpu_ids).
+	 * Cap nthreads to the actual queue count to avoid creating extra
+	 * handler threads that will hang during device removal.
+	 *
+	 * per_io_tasks mode is excluded: threads interleave across all
+	 * queues so nthreads > nr_hw_queues is valid and intentional.
+	 */
+	if (!ctx->per_io_tasks && dev->nthreads > info->nr_hw_queues)
+		dev->nthreads = info->nr_hw_queues;
+
 	ret = ublk_start_daemon(ctx, dev);
 	ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\n", __func__, ret);
 	if (ret < 0)
-- 
2.53.0

Re: [PATCH V2] selftests: ublk: cap nthreads to kernel's actual nr_hw_queues

[Jens Axboe]

On Wed, 13 May 2026 18:19:40 +0800, Ming Lei wrote:
> dev->nthreads is derived from the user-requested queue count before the
> ADD command, but the kernel may reduce nr_hw_queues (capped to
> nr_cpu_ids). When the VM has fewer CPUs than requested queues, the
> daemon creates more handler threads than there are kernel queues.
> 
> In non-batch mode, the extra threads access uninitialized queues
> (q_depth=0), submit zero io_uring SQEs, and block forever in
> io_cqring_wait. In batch mode, the extra threads cause similar hangs
> during device removal.
> 
> [...]

Applied, thanks!

[1/1] selftests: ublk: cap nthreads to kernel's actual nr_hw_queues
      commit: 87d0740b7c4cc847be1b6f307ab6d8547cb1a726

Best regards,
-- 
Jens Axboe