From: Sebastian Andrzej Siewior Date: Tue, 15 Oct 2013 16:29:25 +0000 (+0200) Subject: usb: musb: dsps: redo the otg timer X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=0f901c980110cd69b63670096465b35377e73b1c;p=linux-beck.git usb: musb: dsps: redo the otg timer According to the comments, we rely on the OTG timer because the core does not expose some important OTG details. So far this is all I know. After playing with OTG I stumbled over a problem: musb is recognized as a B-device without a problem. Whenever a cable is plugged, the VBUS rises, musb recognizes this as a starting session, sets the MUSB_DEVCTL_SESSION bit by itself and a RESET interrupt occurs, the session starts. Good. After a disconnect, the timer is started and re-starts itself because it remains in B_IDLE with the BDEVICE set. I didn't figure the the reason or the need for it. Nothing changes here except for OTG state from B to A device if the BDEVICE bit disappears. This doesn't make much sense to me because nothing happens after this. _IF_ we receive an interrupt before the state change then we may act on wrong condition. Plugging a B-device (and letting MUSB act as host) doesn't work here. The reason seems to be that the MUSB tries to start a session, it fails and then it removes the bit. So we never start as a host. This patch sets the MUSB_DEVCTL_SESSION bit in the IDLE state so musb can try to establish a session as host. After the bit is set, musb tries to start a session and if it fails it clears the bit. Therefore it will try over and over again until a session either as host or as device is established. The readout of the MUSB_DEVCTL register after the removal the MUSB_DEVCTL_SESSION (in A_WAIT_BCON) has been removed because it did not contain the BDEVICE bit set (in the second read) leading to A_IDLE. After plugging a host musb assumed that it is also a host and complained about a missing reset. However a third read of the register has has the BDEVICE bit set so it seems that it is not stable. This mostly what da8xx.c is doing except that we set the timer also after A_WAIT_BCON so the session bit can be triggered. Whit this change I was able to keep am335x-evm in OTG mode and plug in either a HOST or a DEVICE and in a random order and the device was recognized. Cc: stable@vger.kernel.org # v3.11 Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Felipe Balbi --- diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index 9efba94c35f2..e1da6702078a 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -209,6 +209,7 @@ static void otg_timer(unsigned long _musb) const struct dsps_musb_wrapper *wrp = glue->wrp; u8 devctl; unsigned long flags; + int skip_session = 0; /* * We poll because DSPS IP's won't expose several OTG-critical @@ -221,10 +222,12 @@ static void otg_timer(unsigned long _musb) spin_lock_irqsave(&musb->lock, flags); switch (musb->xceiv->state) { case OTG_STATE_A_WAIT_BCON: - devctl &= ~MUSB_DEVCTL_SESSION; - dsps_writeb(musb->mregs, MUSB_DEVCTL, devctl); + dsps_writeb(musb->mregs, MUSB_DEVCTL, 0); + skip_session = 1; + /* fall */ - devctl = dsps_readb(musb->mregs, MUSB_DEVCTL); + case OTG_STATE_A_IDLE: + case OTG_STATE_B_IDLE: if (devctl & MUSB_DEVCTL_BDEVICE) { musb->xceiv->state = OTG_STATE_B_IDLE; MUSB_DEV_MODE(musb); @@ -232,20 +235,15 @@ static void otg_timer(unsigned long _musb) musb->xceiv->state = OTG_STATE_A_IDLE; MUSB_HST_MODE(musb); } + if (!(devctl & MUSB_DEVCTL_SESSION) && !skip_session) + dsps_writeb(mregs, MUSB_DEVCTL, MUSB_DEVCTL_SESSION); + mod_timer(&glue->timer, jiffies + wrp->poll_seconds * HZ); break; case OTG_STATE_A_WAIT_VFALL: musb->xceiv->state = OTG_STATE_A_WAIT_VRISE; dsps_writel(musb->ctrl_base, wrp->coreintr_set, MUSB_INTR_VBUSERROR << wrp->usb_shift); break; - case OTG_STATE_B_IDLE: - devctl = dsps_readb(mregs, MUSB_DEVCTL); - if (devctl & MUSB_DEVCTL_BDEVICE) - mod_timer(&glue->timer, - jiffies + wrp->poll_seconds * HZ); - else - musb->xceiv->state = OTG_STATE_A_IDLE; - break; default: break; }