On 07.03.2013 13:51, Daniel Mack wrote:
> On 04.03.2013 00:53, Daniel Mack wrote:
>> Hi Peter,
>>
>> On 03.03.2013 23:24, Peter Korsgaard wrote:
>>>>>>>> "Daniel" == Daniel Mack <zonque-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> writes:
>>>
>>> Hi,
>>>
>>>  Daniel> On my board, the USB is purely used as host interface, with a
>>>  Daniel> type B plug soldered. In the DT, I'm using the following
>>>  Daniel> sniplet in accordance to the documentation of the bindings:
>>>
>>>  Daniel> 	usb_otg_hs: usb@47400000 {
>>>  Daniel> 		compatible = "ti,musb-am33xx";
>>>  Daniel> 		reg = <0x47400000 0x1000	/* usbss */
>>>  Daniel> 		       0x47401000 0x800		/* musb instance 0 */
>>>  Daniel> 		       0x47401800 0x800>;	/* musb instance 1 */
>>>  Daniel> 		interrupt-parent = <&intc>;
>>>  Daniel> 		interrupts = <17		/* usbss */
>>>  Daniel> 			      18		/* musb instance 0 */
>>>  19> ;		/* musb instance 1 */
>>>  Daniel> 		multipoint = <1>;
>>>  Daniel> 		num-eps = <16>;
>>>  Daniel> 		ram-bits = <12>;
>>>  Daniel> 		port0-mode = <3>;
>>>  Daniel> 		port1-mode = <3>;
>>>  Daniel> 		power = <250>;
>>>  Daniel> 		ti,hwmods = "usb_otg_hs";
>>>  Daniel> 	};
>>>
>>>  Daniel> The relevant config options are
>>>
>>>  Daniel> CONFIG_USB_MUSB_HDRC=y
>>>  Daniel> # CONFIG_USB_MUSB_TUSB6010 is not set
>>>  Daniel> # CONFIG_USB_MUSB_OMAP2PLUS is not set
>>>  Daniel> # CONFIG_USB_MUSB_AM35X is not set
>>>  Daniel> CONFIG_USB_MUSB_DSPS=y
>>>  Daniel> CONFIG_MUSB_PIO_ONLY=y
>>>  Daniel> CONFIG_USB_GADGET=y
>>>  Daniel> CONFIG_USB_GADGET_DEBUG=y
>>>  Daniel> CONFIG_USB_GADGET_DEBUG_FILES=y
>>>  Daniel> CONFIG_USB_GADGET_DEBUG_FS=y
>>>  Daniel> CONFIG_USB_GADGET_VBUS_DRAW=2
>>>  Daniel> CONFIG_USB_GADGET_STORAGE_NUM_BUFFERS=2
>>>  Daniel> CONFIG_USB_GADGET_MUSB_HDRC=y
>>>
>>> Ehh, I'm confused here. You talk about host mode, a single 'B' (gadget)
>>> connector
>>
>> I'm sorry for the confusion caused. This is a stupid mistake - I'm in
>> fact talking about an 'A' type plug of course (host mode).
>>
>>> and your device tree mentions 2 OTG ports.
>>
>> That's what I said in a follow up - the same happens for mode '1'.
>>
>>> What is the configuration exactly?
>>
>> Again to summarize: host-only mode, type 'A' plug.
>>
>> The gadget driver is is enabled in the config because the only
>> occurrence of usb_add_hcd() in the musb driver is in the gagdget part,
>> so supposedly, there has to be a gadget driver loaded in order to make
>> the host interface going.
> 
> Just be clear: I'd happily help and dig for the reason of this, I'd just
> need to know how things are _supposed_ to work ...

So I dug a little on this topic, and restored the behaviour I need with
the attached patch.

The funny part is that the value set in the port0-mode/port1-mode DT
properties are not even looked at by the code.

I know this patch reintroduces bits that have been intentionally removed
before, in particular by 032ec49f53 ("usb: musb: drop useless board_mode
usage"), but I don't know how this usb driver is supposed to work in
host mode without taking the configured port mode into account. If
anyone can explain to me which information I'm missing here, I can
happily test a patch. For now, this works for me.


Thanks,
Daniel