summaryrefslogtreecommitdiff
path: root/drivers/dma
diff options
context:
space:
mode:
authorSebastian Andrzej Siewior <bigeasy@linutronix.de>2013-07-05 16:51:33 +0400
committerFelipe Balbi <balbi@ti.com>2013-08-09 18:35:44 +0400
commit97238b35d5bbb5d5312d83c30a429824b777619f (patch)
tree0c2940aa58416bda0139de29f822b4eefd0cdecc /drivers/dma
parente96bdc3dafe471375e2e780e319e3ead2d9ad4a7 (diff)
downloadlinux-97238b35d5bbb5d5312d83c30a429824b777619f.tar.xz
usb: musb: dsps: use proper child nodes
This moves the two instances from the big node into two child nodes. The glue layer ontop does almost nothing. There is one devices containing the control module for USB (2) phy, (2) usb and later the dma engine. The usb device is the "glue device" which contains the musb device as a child. This is what we do ever since. The new file musb_am335x is just here to prob the new bus and populate child devices. There are a lot of changes to the dsps file as a result of the changes: - musb_core_offset This is gone. The device tree provides memory ressources information for the device there is no need to "fix" things - instances This is gone as well. If we have two instances then we have have two child enabled nodes in the device tree. For instance the SoC in beagle bone has two USB instances but only one has been wired up so there is no need to load and init the second instance since it won't be used. - dsps_glue is now per glue device In the past there was one of this structs but with an array of two and each instance accessed its variable depending on the platform device id. - no unneeded copy of structs I do not know why struct dsps_musb_wrapper is copied but it is not necessary. The same goes for musb_hdrc_platform_data which allocated on demand and then again by platform_device_add_data(). One copy is enough. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Felipe Balbi <balbi@ti.com>
Diffstat (limited to 'drivers/dma')
0 files changed, 0 insertions, 0 deletions