Hi,

On Thu, Aug 21, 2014 at 7:48 PM, Tony Lindgren [off-list ref] wrote:

Commit 249751f22380 ("usb: phy: twl4030-usb: poll for ID disconnect")
added twl4030_id_workaround_work() to deal with lost interrupts
after ID pin goes down. However, this currently only works for the
insertion. The PHY interrupts are not working after disconnecting
an USB-A device from the board, and the deeper idle states for
omap are blocked as the USB controller stays busy.

The issue can be solved by calling delayed work from twl4030_usb_irq()
when ID pin is down and the PHY is not asleep like we already do
in twl4030_id_workaround_work().

The way it is supposed to work is that after plugging in the cable
twl4030_phy_power_on() sees ID_GROUND and kicks off id_workaround_work
every second. When cable is unplugged, twl4030_id_workaround_work()
sees changes in STS_HW_CONDITIONS register and triggers events.
Doesn't that work for you, why do you need to trigger it from
twl4030_usb_irq() too?

But as both twl4030_usb_irq() and twl4030_id_workaround_work()
already do pretty much the same thing, let's call twl4030_usb_irq()
from twl4030_id_workaround_work() instead of adding some more
duplicate code.

The difference is the sysfs_notify() call, so now every time
id_workaround_work triggers (around once per second while the cable is
plugged) userspace will now get useless uevent. Haven't actually
checked if it really happens though, so I might be wrong.


-- 
Gražvydas