Skip to content

L
linux
Switch branch/tag
  1. 17 Oct, 2013 4 commits
    • Sebastian Andrzej Siewior's avatar
      usb: musb: dsps: redo the otg timer · 0f901c98
      Sebastian Andrzej Siewior authored 
      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: default avatarSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: default avatarFelipe Balbi <balbi@ti.com>
      0f901c98
    • Sebastian Andrzej Siewior's avatar
      usb: musb: dsps: remove declartion for dsps_musb_try_idle() · 807d0d2b
      Sebastian Andrzej Siewior authored 
      This patch moves dsps_musb_try_idle() before dsps_musb_enable() so the
declaration (of dsps_musb_try_idle() can be removed.
Signed-off-by: default avatarSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: default avatarFelipe Balbi <balbi@ti.com>
      807d0d2b
    • Sebastian Andrzej Siewior's avatar
      usb: musb: dsps: move try_idle to start hook · 8b9fcce2
      Sebastian Andrzej Siewior authored 
      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: default avatarSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: default avatarFelipe Balbi <balbi@ti.com>
      8b9fcce2
    • Sebastian Andrzej Siewior's avatar
      usb: musb: call musb_start() only once in OTG mode · ae44df2e
      Sebastian Andrzej Siewior authored 
      In commit 001dd84a ("usb: musb: start musb on the udc side, too") it was
ensured that the state engine is started also in OTG mode after a
removal / insertion of the gadget.
Unfortunately this change also introduced a bug: If the device is
configured as OTG and it connected with a remote host _without_ loading
a gadget then we bug() later (because musb->otg->gadget is not
initialized).
Initially I assumed it might be nice to have the host part of musb in
OTG mode working without having a gadget loaded. This bug and fact that
it wasn't working like this before the host/gadget split made me realize
that this was a silly idea.
This patch now introduces back the old behavior where in OTG mode the
host mode is only working after the gadget has been loaded.

Cc: stable@vger.kernel.org # v3.11
Cc: Daniel Mack <zonque@gmail.com>
Signed-off-by: default avatarSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: default avatarFelipe Balbi <balbi@ti.com>
      ae44df2e
  3. 15 Oct, 2013 10 commits
  5. 11 Oct, 2013 6 commits
  7. 10 Oct, 2013 20 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7