From b484a40dc1f16edb58e5430105a021e1916e6f27 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Fri, 1 Sep 2023 21:49:16 +0800
Subject: [PATCH] io_uring: fix IO hang in io_wq_put_and_exit from do_exit()
io_wq_put_and_exit() is called from do_exit(), but all FIXED_FILE requests
in io_wq aren't canceled in io_uring_cancel_generic() called from do_exit().
Meantime io_wq IO code path may share resource with normal iopoll code
path.
So if any HIPRI request is submittd via io_wq, this request may not get resouce
for moving on, given iopoll isn't possible in io_wq_put_and_exit().
The issue can be triggered when terminating 't/io_uring -n4 /dev/nullb0'
with default null_blk parameters.
Fix it by always cancelling all requests in io_wq by adding helper of
io_uring_cancel_wq(), and this way is reasonable because io_wq destroying
follows canceling requests immediately.
Closes: https://lore.kernel.org/linux-block/3893581.1691785261@warthog.procyon.org.uk/
Reported-by: David Howells <dhowells@redhat.com>
Cc: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230901134916.2415386-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/io_uring.c | 32 ++++++++++++++++++++++++++++++++
1 file changed, 32 insertions(+)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index e7675355048db..c6d9e46770733 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3290,6 +3290,37 @@ static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
return percpu_counter_sum(&tctx->inflight);
}
+static void io_uring_cancel_wq(struct io_uring_task *tctx)
+{
+ int ret;
+
+ if (!tctx->io_wq)
+ return;
+
+ /*
+ * FIXED_FILE request isn't tracked in do_exit(), and these
+ * requests may be submitted to our io_wq as iopoll, so have to
+ * cancel them before destroying io_wq for avoiding IO hang
+ */
+ do {
+ struct io_tctx_node *node;
+ unsigned long index;
+
+ ret = 0;
+ xa_for_each(&tctx->xa, index, node) {
+ struct io_ring_ctx *ctx = node->ctx;
+ struct io_task_cancel cancel = { .task = current, .all = true, };
+ enum io_wq_cancel cret;
+
+ io_iopoll_try_reap_events(ctx);
+ cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb,
+ &cancel, true);
+ ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
+ cond_resched();
+ }
+ } while (ret);
+}
+
/*
* Find any io_uring ctx that this task has registered or done IO on, and cancel
* requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation.
@@ -3361,6 +3392,7 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
finish_wait(&tctx->wait, &wait);
} while (1);
+ io_uring_cancel_wq(tctx);
io_uring_clean_tctx(tctx);
if (cancel_all) {
/*
--
GitLab