linux-toradex.git/drivers/usb/renesas_usbhs, branch v3.4.2

Merge branch 'next' of git://git.infradead.org/users/vkoul/slave-dma

2012-03-29T22:34:57+00:00

Pull slave-dmaengine update from Vinod Koul:
 "This includes the cookie cleanup by Russell, the addition of context
  parameter for dmaengine APIs, more arm dmaengine driver cleanup by
  moving code to dmaengine, this time for imx by Javier and pl330 by
  Boojin along with the usual driver fixes."

Fix up some fairly trivial conflicts with various other cleanups.

* 'next' of git://git.infradead.org/users/vkoul/slave-dma: (67 commits)
  dmaengine: imx: fix the build failure on x86_64
  dmaengine: i.MX: Fix merge of cookie branch.
  dmaengine: i.MX: Add support for interleaved transfers.
  dmaengine: imx-dma: use 'dev_dbg' and 'dev_warn' for messages.
  dmaengine: imx-dma: remove 'imx_dmav1_baseaddr' and 'dma_clk'.
  dmaengine: imx-dma: remove unused arg of imxdma_sg_next.
  dmaengine: imx-dma: remove internal structure.
  dmaengine: imx-dma: remove 'resbytes' field of 'internal' structure.
  dmaengine: imx-dma: remove 'in_use' field of 'internal' structure.
  dmaengine: imx-dma: remove sg member from internal structure.
  dmaengine: imx-dma: remove 'imxdma_setup_sg_hw' function.
  dmaengine: imx-dma: remove 'imxdma_config_channel_hw' function.
  dmaengine: imx-dma: remove 'imxdma_setup_mem2mem_hw' function.
  dmaengine: imx-dma: remove dma_mode member of internal structure.
  dmaengine: imx-dma: remove data member from internal structure.
  dmaengine: imx-dma: merge old dma-v1.c with imx-dma.c
  dmaengine: at_hdmac: add slave config operation
  dmaengine: add context parameter to prep_slave_sg and prep_dma_cyclic
  dmaengine/dma_slave: introduce inline wrappers
  dma: imx-sdma: Treat firmware messages as warnings instead of erros
  ...

dmaengine/dma_slave: introduce inline wrappers

2012-03-21T13:50:22+00:00

Add inline wrappers for device_prep_slave_sg() and device_prep_dma_cyclic()
interfaces to hide new parameter from current users of affected interfaces.
Convert current users to use new wrappers instead of direct calls.
Suggested by Russell King [https://lkml.org/lkml/2012/2/3/269].

Signed-off-by: Alexandre Bounine 
Signed-off-by: Vinod Koul

Merge tag 'gadget-for-v3.4' of git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb into usb-next

2012-03-01T17:20:28+00:00

USB: Gadget: changes for 3.4

This merge is rather big. Here's what it contains:

For am5536udc we have just simple coding style fixes. Nothing that has any
potential to cause any issues going forward.

With mv_udc, there's only one single change removing an unneeded NULL check.

at91_udc also only saw a single change this merge window, and that's only
removing a duplicated header.

The Renesas controller has a few more involved changes. Support for SUDMAC was
added, there's now a special handling of IRQ resources for when the IRQ line is
shared between Renesas controller and SUDMAC, we also had a bug fix where
Renesas controller would sleep in atomic context while doing DMA transfers from
a tasklet. There were also a set of minor cleanups.

The FSL UDC also had a scheduling in atomic context bug fix, but that's all.

Thanks to Sebastian, the dummy_hcd now works better than ever with support for
scatterlists and streams. Sebastian also added SuperSpeed descriptors to the
serial gadgets.

The highlight on this merge is the addition of a generic API for mapping and
unmapping usb_requests. This will avoid code duplication on all UDC controllers
and also kills all the defines for DMA_ADDR_INVALID which UDC controllers
sprinkled around. A few of the UDC controllers were already converted to use
this new API.

Conflicts:
	drivers/usb/dwc3/gadget.c

usb: renesas: gadget: use generic map/unmap routines

2012-02-28T12:49:06+00:00

those routines have everything we need to map/unmap
USB requests and it's better to use them.

Tested-by: Kuninori Morimoto 
Signed-off-by: Felipe Balbi

usb: renesas_usbhs: bugfix: add .release function to gpriv->gadget.dev

2012-02-24T10:22:39+00:00

This patch fixup below warning on device_unregister()

renesas_usbhs renesas_usbhs.1: host probed
renesas_usbhs renesas_usbhs.1: gadget probed
renesas_usbhs renesas_usbhs.1: irq request err
------------[ cut here ]------------
WARNING: at ${LINUX}/drivers/base/core.c:1)
Device 'gadget' does not have a release() function, it is broken and must be fi.
Modules linked in:
[] (unwind_backtrace+0x0/0xe4) from [] (warn_slowpath_commo)
[] (warn_slowpath_common+0x4c/0x64) from [] (warn_slowpath_)
[] (warn_slowpath_fmt+0x2c/0x3c) from [] (device_release+0x)
[] (device_release+0x70/0x84) from [] (kobject_cleanup+0x58)
[] (kobject_cleanup+0x58/0x6c) from [] (usbhs_mod_gadget_re)
[] (usbhs_mod_gadget_remove+0x3c/0x6c) from [] (usbhs_mod_p)
[] (usbhs_mod_probe+0x68/0x80) from [] (usbhs_probe+0x1cc/0)
...

Cc: stable@vger.kernel.org
Signed-off-by: Kuninori Morimoto 
Signed-off-by: Felipe Balbi

usb: renesas: fix scheduling in atomic context bug

2012-02-14T11:44:53+00:00

The current renesas_usbhs driver triggers

BUG: scheduling while atomic: ksoftirqd/0/3/0x00000102

with enabled CONFIG_DEBUG_ATOMIC_SLEEP, by submitting DMA transfers from
an atomic (tasklet) context, which is not supported by the shdma dmaengine
driver. Fix it by switching to a work.

Signed-off-by: Guennadi Liakhovetski 
Signed-off-by: Felipe Balbi

usb: renesas_usbhs: (cosmetic) simplify list operations

2012-02-14T11:44:27+00:00

list.h already provide helpers to find the first entry and to move list
nodes to the tail of another list. This patch simply uses those helpers,
no functional changes.

Signed-off-by: Guennadi Liakhovetski 
Signed-off-by: Felipe Balbi

usb: renesas: silence uninitialized variable report in usbhsg_recip_run_handle()

2012-01-24T13:43:06+00:00

In drivers/usb/renesas_usbhs/mod_gadget.c::usbhsg_recip_run_handle()
the Coverity Prevent checker currently flags a warning about possibly
uninitialized use of 'ret' i usbhsg_recip_run_handle(). It does this
since it assumes we take one of the non-default branches in the switch
and then subsequently take the false branch in the 'if (func)' case
below. This exact scenario will never happen, but Coverity can't see
that for some reason. This patch initializes 'ret' to '0' when it is
declared which should shut up this report and won't really hurt - so
why not? At least then it's clear that 'ret' is always initialized..

Signed-off-by: Jesper Juhl 
Signed-off-by: Felipe Balbi

usb: renesas_usbhs: add support for SUDMAC

2012-01-24T09:33:04+00:00

The SUDMAC uses 8-bit width only. So, when the driver uses SUDMAC,
we have to clear the MBW_32.

Signed-off-by: Yoshihiro Shimoda 
Signed-off-by: Felipe Balbi

usb: renesas_usbhs: add IRQ resource decoding for IRQF_SHARED

2012-01-24T09:32:56+00:00

In case of the SH7757, the irq number of USB module and SUDMAC
are the same. So, we have to set the IRQF_SHARED in such a case.

Signed-off-by: Yoshihiro Shimoda 
Signed-off-by: Felipe Balbi