From: David Brownell Date: Fri, 23 Mar 2007 13:56:36 +0000 (-0400) Subject: musb_hdrc: Update host side EP0 handling for correctness X-Git-Tag: v2.6.21-omap1~73 X-Git-Url: http://git.openpandora.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=ea4c46f2bab83dea26ce343763fc65270ca537a6;p=pandora-kernel.git musb_hdrc: Update host side EP0 handling for correctness Update host side EP0 handling for correctness: handle zero-length data stages and continuations of ep0out transfers explicitly, clean up the state machine a bit. This means that the full set of host-side ep0 tests pass. Usbtest cases #9 and #10 were ok before; now case #14 works too. There is however a curious protocol problem in some full speed tests, at least on DaVinci: sometimes the controller won't ack an IN DATA packet, causing a retry. If the peripheral doesn't resend that data correctly, that causes a test failure. (And my test rig doesn't resend correctly...) This is based on a patch from "ZHENG LEI " against 2.6.10 code, resolving some of the ep0out problems. Signed-off-by: David Brownell --- Reading git-diff-tree failed