On Tue, Mar 07 2017, Baolin Wang wrote: > On 3 March 2017 at 10:23, NeilBrown <neilb@xxxxxxxx> wrote: > >> >> I understand your reluctance to change drivers that you cannot test. >> An alternative it do change all the >> atomic_notifier_call_chain(.*notifier, >> calls that don't pass a pointer to vbus_draw to pass NULL, and to >> declare the passing of NULL to be deprecated (so hopefully people won't >> use it in new code). >> Then any notification callback that expects a current can just ignore >> calls where the pointer is NULL. > > I am afraid if it is enough to send out vbus draw information from USB > phy driver, for example you will miss super speed (900mA), which need > get the speed information from gadget driver. When the gadget driver determines that 900mA is available, it calls usb_phy_set_power() which calls the ->set_power() method on the usb_phy. The usb_phy the uses the notifier to inform all interested parties that 900mA is available. NeilBrown
Attachment:
signature.asc
Description: PGP signature
