of_clk_init() ends up calling into pm_qos_update_request() very early during boot where irq is expected to stay disabled. pm_qos_update_request() uses cancel_delayed_work_sync() which correctly assumes that irq is enabled on invocation and unconditionally disables and re-enables it.
Gate cancel_delayed_work_sync() invocation with kevented_up() to avoid enabling irq unexpectedly during early boot. Signed-off-by: Tejun Heo <t...@kernel.org> Reported-and-tested-by: Qiao Zhou <qiaoz...@asrmicro.com> Link: http://lkml.kernel.org/r/d2501c4c-8e7b-bea3-1b01-000b36b5d...@asrmicro.com --- Rafael, can you please route this patch? Thanks. kernel/power/qos.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 97b0df7..168ff44 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -482,7 +482,16 @@ void pm_qos_update_request(struct pm_qos_request *req, return; } - cancel_delayed_work_sync(&req->work); + /* + * This function may be called very early during boot, for example, + * from of_clk_init(), where irq needs to stay disabled. + * cancel_delayed_work_sync() assumes that irq is enabled on + * invocation and re-enables it on return. Avoid calling it until + * workqueue is initialized. + */ + if (keventd_up()) + cancel_delayed_work_sync(&req->work); + __pm_qos_update_request(req, new_value); } EXPORT_SYMBOL_GPL(pm_qos_update_request);
