Skip to content

L
linux
Switch branch/tag
  1. 17 Oct, 2013 10 commits
    • Sachin Kamat's avatar
      usb: phy: twl6030-usb: Include linux/of.h header · 80d7d8a7
      Sachin Kamat authored 
      'of_match_ptr' is defined in linux/of.h. Include it explicitly to
avoid build breakage in the future.
Signed-off-by: default avatarSachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: default avatarFelipe Balbi <balbi@ti.com>
      80d7d8a7
    • Sebastian Andrzej Siewior's avatar
      usb: musb: cppi41: allow to defer probing if DMA isn't yet available · 48054147
      Sebastian Andrzej Siewior authored 
      If everything (musb, cppi41, phy) is built-in then musb will start
without the dma engine printing only

|musb-hdrc musb-hdrc.0.auto: Falied to request rx1.

The reason for this is that the musb device structs are created & probed
before those of the cppi41 device. So the cppi41 device is probed too
late.
As a workaround for this allow the musb_cppi41 part to defer the probe
if everything is fine except for the missing DMA controller. In case of
another error we continue.
Signed-off-by: default avatarSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: default avatarFelipe Balbi <balbi@ti.com>
      48054147
    • Sebastian Andrzej Siewior's avatar
      usb: musb: core: Call dma_controller_destroy() in error path only once. · 8d1aad74
      Sebastian Andrzej Siewior authored 
      In commit f3ce4d5b ("usb: musb: core: call dma_controller_destroy() in the err path")
I erroneously assumed that the dma controller is not removed in the
error patch. This was wrong because it happens later via musb_free().
That means the original commit can be reverted because it is wrong or we
do this, so it is more obvious.
Signed-off-by: default avatarSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: default avatarFelipe Balbi <balbi@ti.com>
      8d1aad74
    • Sebastian Andrzej Siewior's avatar
      usb: musb: core: properly free host / device structs in err path · 0d2dd7ea
      Sebastian Andrzej Siewior authored 
      The patch fixes two issues in the error path cleanup:
- in MUSB_PORT_MODE_DUAL_ROLE mode, if musb_gadget_setup() fails we
  never cleanup the host struct earlier allocated.
- if musb_init_debugfs() or sysfs_create_group() fails, then we never
  free the host part initialization, only device part.

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>
      0d2dd7ea
    • Andrzej Pietrasiewicz's avatar
      usb: gadget: f_mass_storage: style corrections, cleanup & simplification · 5bb7289d
      Andrzej Pietrasiewicz authored 
      Fix spacing, improve error code returned, remove unused #define,
use strtobool() instead of kstrtou8().
Acked-by: default avatarMichal Nazarewicz <mina86@mina86.com>
Signed-off-by: default avatarAndrzej Pietrasiewicz <andrzej.p@samsung.com>
Signed-off-by: default avatarKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: default avatarFelipe Balbi <balbi@ti.com>
      5bb7289d
    • Sebastian Andrzej Siewior's avatar
      usb: musb: dsps: run the timer only on OTG systems · 24616eb6
      Sebastian Andrzej Siewior authored 
      I introduced this check here because it looked wrong in HOST only
configurions. The timer would remove that session bit and will never
come back and so there would not be another session.
Now that I played with OTG for a while I belive this workaround is
only required for the OTG mode because we have to end the session and
then we have to try to start manually.
Therefore, this patch limits this timer to the OTG only port mode so we
don't need to poll around in device only mode.
Signed-off-by: default avatarSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: default avatarFelipe Balbi <balbi@ti.com>
      24616eb6
    • 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 14 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7