@@ -8678,6 +8678,13 @@ static void io_tctx_exit_cb(struct callback_head *cb)
complete(&work->completion);
}
+static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
+{
+ struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+ return req->ctx == data;
+}
+
static void io_ring_exit_work(struct work_struct *work)
{
struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work);
@@ -8694,6 +8701,17 @@ static void io_ring_exit_work(struct work_struct *work)
*/
do {
io_uring_try_cancel_requests(ctx, NULL, NULL);
+ if (ctx->sq_data) {
+ struct io_sq_data *sqd = ctx->sq_data;
+ struct task_struct *tsk;
+
+ io_sq_thread_park(sqd);
+ tsk = sqd->thread;
+ if (tsk && tsk->io_uring && tsk->io_uring->io_wq)
+ io_wq_cancel_cb(tsk->io_uring->io_wq,
+ io_cancel_ctx_cb, ctx, true);
+ io_sq_thread_unpark(sqd);
+ }
WARN_ON_ONCE(time_after(jiffies, timeout));
} while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20));
@@ -8843,13 +8861,6 @@ static bool io_cancel_defer_files(struct io_ring_ctx *ctx,
return true;
}
-static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
-{
- struct io_kiocb *req = container_of(work, struct io_kiocb, work);
-
- return req->ctx == data;
-}
-
static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
{
struct io_tctx_node *node;
After closing an SQPOLL ring, io_ring_exit_work() kicks in and starts doing cancellations via io_uring_try_cancel_requests(). It will go through io_uring_try_cancel_iowq(), which uses ctx->tctx_list, but as SQPOLL task don't have a ctx note, its io-wq won't be reachable and so is left not cancelled. It will eventually cancelled when one of the tasks dies, but if a thread group survives for long and changes rings, it will spawn lots of unreclaimed resources and live locked works. Cancel SQPOLL task's io-wq separately in io_ring_exit_work(). Cc: stable@vger.kernel.org Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> --- fs/io_uring.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-)