usb: musb: dsps: move try_idle to start hook

The timer is initialized right after musb is probed. There is actually
no need to have this timer running because _nothing_ will happen until
we have the gadget loaded. Also we need this timer only if we run in OTG
mode _and_ we need it also after the gadget has been replaced with
another one.

I've been looking at am35x.c, da8xx.c, omap2430.c, tusb6010.c. da8xx
seem to have the same problem as dsps and doing mostly the same thing.
tusb6010 seem to do something different and do some actual "idle / power
saving" work so I am not too comfortable to remove
musb_platform_try_idle() from musb_gadget_setup().

Therefore this patch does not start the timer if there is no gadget
active (which is at musb_gadget_setup() at time). In order to have the
timer active after the gadget is loaded it will be triggered from
dsps_musb_enable().

Cc: stable@vger.kernel.org # v3.11
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Felipe Balbi <balbi@ti.com>

drivers/usb/musb/musb_dsps.c

@@ -121,6 +121,7 @@ struct dsps_glue {
 	unsigned long last_timer;    /* last timer data for each instance */
 };
 
+static void dsps_musb_try_idle(struct musb *musb, unsigned long timeout);
 /**
  * dsps_musb_enable - enable interrupts
  */
@@ -143,6 +144,7 @@ static void dsps_musb_enable(struct musb *musb)
 	/* Force the DRVVBUS IRQ so we can start polling for ID change. */
 	dsps_writel(reg_base, wrp->coreintr_set,
 		    (1 << wrp->drvvbus) << wrp->usb_shift);
+	dsps_musb_try_idle(musb, 0);
 }
 
 /**
@@ -234,6 +236,9 @@ static void dsps_musb_try_idle(struct musb *musb, unsigned long timeout)
 	if (musb->port_mode == MUSB_PORT_MODE_HOST)
 		return;
 
+	if (!musb->g.dev.driver)
+		return;
+
 	if (time_after(glue->last_timer, timeout) &&
 				timer_pending(&glue->timer)) {
 		dev_dbg(musb->controller,