From: Vishnu Razdan commit 297b5ccea4acacaa47c150f043bce695202afbf1 upstream. create_worker_cb() reserves an io-wq worker slot only after its task-work callback runs. If the callback is canceled before then, io_worker_cancel_cb() still decrements acct->nr_workers. When an existing worker retires with its creation callback pending, that worker has already decremented the same account's worker count. The resulting undercount permits worker creation beyond the account's configured limit. On an AST2600 OpenBMC system, an unchanged sensor daemon reached 4,291 threads with the original kernel. With an equivalent downstream fix, 25 passive samples under its normal workload showed 6-9 threads. Decrement nr_workers only when the canceled callback is not create_worker_cb(). Continuation callbacks still release their reserved slot, and both callback types retain the existing running-count, reference-count, and create-state cleanup. [ Backport: retain the existing worker->wqe->lock protecting worker accounting. ] Fixes: 1d5f5ea7cb7d ("io-wq: remove worker to owner tw dependency") Cc: stable@vger.kernel.org Assisted-by: Codex:gpt-5.6-sol Reviewed-by: Gabriel Krisman Bertazi Link: https://patch.msgid.link/20260811-vrazdan-io-wq-b4-submit-v1-1-719ced16c921@openai.com Signed-off-by: Vishnu Razdan --- Stable backport for linux-6.1.y. --- io_uring/io-wq.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 66fdd69fd6cb40..0c3de2fead81cc 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -201,9 +201,12 @@ static void io_worker_cancel_cb(struct io_worker *worker) struct io_wq *wq = wqe->wq; atomic_dec(&acct->nr_running); - raw_spin_lock(&worker->wqe->lock); - acct->nr_workers--; - raw_spin_unlock(&worker->wqe->lock); + /* create_worker_cb() has not reserved a worker slot yet. */ + if (worker->create_work.func != create_worker_cb) { + raw_spin_lock(&worker->wqe->lock); + acct->nr_workers--; + raw_spin_unlock(&worker->wqe->lock); + } io_worker_ref_put(wq); clear_bit_unlock(0, &worker->create_state); io_worker_release(worker); --- base-commit: 05208478041ccec1b348d25e1df5c4013608590e change-id: 20260825-stable-io-wq-6-1-y-2843d0afd0e4 Best regards, -- Vishnu Razdan