usb: musb: omap2430: fix omap_musb_mailbox glue check again

Commit 80ab72e1 (usb: musb: omap2430: fix the readiness check
in omap_musb_mailbox) made the check incorrect, as we will lose the
glue/link status during the normal built-in probe order (twl4030_usb is
probed after musb omap2430, but before musb core is ready).

As a result, if you boot with USB cable on and load g_ether, the
connection does not work as the code thinks the cable is off and the
phy gets powered down immediately. This is a major regression in 3.9-rc1.

So the proper check should be: exit if _glue is NULL, but if it's
initialized we memorize the status, and then check if the musb core
is ready.

Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: Felipe Balbi <balbi@ti.com>

1 files changed, 7 insertions, 3 deletions

diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index 1762354fe793..2a39c110d3d5 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -237,9 +237,13 @@ void omap_musb_mailbox(enum omap_musb_vbus_id_status status)
 {
         struct omap2430_glue    *glue = _glue;
 
-        if (glue && glue_to_musb(glue)) {
-                glue->status = status;
-        } else {
+        if (!glue) {
+                pr_err("%s: musb core is not yet initialized\n", __func__);
+                return;
+        }
+        glue->status = status;
+
+        if (!glue_to_musb(glue)) {
                 pr_err("%s: musb core is not yet ready\n", __func__);
                 return;
         }