Re: [PATCH v4 06/15] usb:hsotg:samsung: Sending ZLP packet for IN EP0 transfers

[Felipe Balbi <balbi@xxxxxx>]

On Wed, Apr 18, 2012 at 03:53:34PM +0200, Lukasz Majewski wrote:
> Hi Felipe,
> 
> 
> > On Tue, Apr 17, 2012 at 09:22:02AM +0200, Lukasz Majewski wrote:
> > > This commit targets following scenarios for IN requests:
> > > 
> > > 1. HOST requests e.g. 256B (which is a multiple of MPS = 64B).
> > > Then NO ZLP shall be sent, since host expects exact number of bytes.
> > > 
> > > 2. HOST requested 4096B, but our data for sending is 256B. In this
> > > situation ZLP shall be send to tell HOST that no more data is
> > > available and it shall not wait for more data. This prevents HOST
> > > from hanging.
> > > 
> > > Tested with:
> > > - DFU gadget (various size of the sent data - also packet = MPS)
> > > - Ethernet gadget (CDC and RNDIS)
> > > - Multi Function Gadget (g_multi)
> > > 
> > > HW:
> > > - Samsung's C210 Universal rev.0
> > > - Samsung's C110 GONI
> > > 
> > > Signed-off-by: Lukasz Majewski <l.majewski@xxxxxxxxxxx>
> > > Signed-off-by: Kyungmin Park <kyungmin.park@xxxxxxxxxxx>
> > 
> > is this is a bugfix ? If so, can you please split bugfixes and new
> > feature/cleanups into two different series ?
> > 
> 
> This patch series "brings to life" the hsotg driver. Before this patch
> set it was supposed to work only with S3C64xx Samsung SoC.
> 
> Those (now) 15 commits shall be treated as a single patch series, and
> we have agreed before Easter, that it is suitable for USB for-next. 
> 
> Moreover I'm trying to upgrade this driver to the Kernel newest API
> (udc_{start|stop}, regulators, platform independent code and now
> clocks). Due to that I think that for-next is the best option - more
> time for debugging and driver validation.

ok, sounds good to me. I will apply on my gadget branch for the next
merge window.

-- 
balbi

Attachment: signature.asc
Description: Digital signature