mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-16 16:54:20 +08:00
48519f0ae0
Currently the EDMA queue to be used by for servicing ASP through internal RAM is fixed to EDMAQ_0 and that to service internal RAM from external RAM is fixed to EDMAQ_1. This may not be the desirable configuration on all platforms. For example, on DM365, queue 0 has large fifo size and is more suitable for video transfers. Having audio and video transfers on the same queue may lead to starvation on audio side. platform data as defined currently passes a queue number to the driver but that remains unused inside the driver. Fix this by defining one queue each for ASP and RAM transfers in the platform data and using it inside the driver. Since EDMAQ_0 maps to 0, thats the queue that will be used if the asp queue number is not initialized. None of the platforms currently utilize ping-pong transfers through internal RAM so that functionality remains unchanged too. This patch has been tested on DM644x and OMAP-L138 EVMs. Signed-off-by: Sekhar Nori <nsekhar@ti.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> |
||
---|---|---|
.. | ||
include/mach | ||
board-da830-evm.c | ||
board-da850-evm.c | ||
board-dm355-evm.c | ||
board-dm355-leopard.c | ||
board-dm365-evm.c | ||
board-dm644x-evm.c | ||
board-dm646x-evm.c | ||
board-neuros-osd2.c | ||
board-sffsdr.c | ||
cdce949.c | ||
clock.c | ||
clock.h | ||
common.c | ||
cp_intc.c | ||
cpufreq.c | ||
cpuidle.c | ||
da830.c | ||
da850.c | ||
devices-da8xx.c | ||
devices.c | ||
dm355.c | ||
dm365.c | ||
dm644x.c | ||
dm646x.c | ||
dma.c | ||
gpio.c | ||
io.c | ||
irq.c | ||
Kconfig | ||
Makefile | ||
Makefile.boot | ||
mux.c | ||
mux.h | ||
pm.c | ||
psc.c | ||
serial.c | ||
sleep.S | ||
sram.c | ||
time.c | ||
usb.c |