diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-10-09 14:58:15 -0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-10-09 14:58:15 -0400 |
commit | ea584595fc85e65796335033dfca25ed655cd0ed (patch) | |
tree | 79d444c507472f6c66d887ad332e7c1784eeb4de /include/linux/spi | |
parent | 782d59c5dfc5ac39ac8cfb4c6dd40597938dde9c (diff) | |
parent | a092e19b688be88f7329bd05f90cb92ebe1a4f5b (diff) | |
download | linux-ea584595fc85e65796335033dfca25ed655cd0ed.tar.gz linux-ea584595fc85e65796335033dfca25ed655cd0ed.tar.bz2 linux-ea584595fc85e65796335033dfca25ed655cd0ed.zip |
Merge tag 'gpio-v3.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio
Pull GPIO changes from Linus Walleij:
"This is the bulk of GPIO changes for the v3.18 development cycle:
- Increase the default ARCH_NR_GPIO from 256 to 512. This was done
to avoid having a custom <asm/gpio.h> header for the x86
architecture - GPIO is custom and complicated enough as it is
already! We want to move to a radix to store the descriptors going
forward, and finally get rid of this fixed array size altogether.
- Endgame patching of the gpio_remove() semantics initiated by
Abdoulaye Berthe. It is not accepted by the system that the
removal of a GPIO chip fails during eg reboot or shutdown, and
therefore the return value has now painfully been refactored away.
For special cases like GPIO expanders on a hot-pluggable bus like
USB, we may later add some gpiochip_try_remove() call, but for the
cases we have now, return values are moot.
- Some incremental refactoring of the gpiolib core and ACPI GPIO
library for more descriptor usage.
- Refactor the chained IRQ handler set-up method to handle also
threaded, nested interrupts and set up the parent IRQ correctly.
Switch STMPE and TC3589x drivers to use this registration method.
- Add a .irq_not_threaded flag to the struct gpio_chip, so that also
GPIO expanders that block but are still not using threaded IRQ
handlers.
- New drivers for the ARM64 X-Gene SoC GPIO controller.
- The syscon GPIO driver has been improved to handle the "DSP GPIO"
found on the TI Keystone 2 SoC:s.
- ADNP driver switched to use gpiolib irqchip helpers.
- Refactor the DWAPB driver to support being instantiated from and
MFD cell (platform device).
- Incremental feature improvement in the Zynq, MCP23S08, DWAPB, OMAP,
Xilinx and Crystalcove drivers.
- Various minor fixes"
* tag 'gpio-v3.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio: (52 commits)
gpio: pch: Build context save/restore only for PM
pinctrl: abx500: get rid of unused variable
gpio: ks8695: fix 'else should follow close brace '}''
gpio: stmpe: add verbose debug code
gpio: stmpe: fix up interrupt enable logic
gpio: staticize xway_stp_init()
gpio: handle also nested irqchips in the chained handler set-up
gpio: set parent irq on chained handlers
gpiolib: irqchip: use irq_find_mapping while removing irqchip
gpio: crystalcove: support virtual GPIO
pinctrl: bcm281xx: make Kconfig dependency more strict
gpio: kona: enable only on BCM_MOBILE or for compile testing
gpio, bcm-kona, LLVMLinux: Remove use of __initconst
gpio: Fix ngpio in gpio-xilinx driver
gpio: dwapb: fix pointer to integer cast
gpio: xgene: Remove unneeded #ifdef CONFIG_OF guard
gpio: xgene: Remove unneeded forward declation for struct xgene_gpio
gpio: xgene: Fix missing spin_lock_init()
gpio: ks8695: fix switch case indentation
gpiolib: add irq_not_threaded flag to gpio_chip
...
Diffstat (limited to 'include/linux/spi')
-rw-r--r-- | include/linux/spi/mcp23s08.h | 18 |
1 files changed, 18 insertions, 0 deletions
diff --git a/include/linux/spi/mcp23s08.h b/include/linux/spi/mcp23s08.h index 2d676d5aaa89..aa07d7b32568 100644 --- a/include/linux/spi/mcp23s08.h +++ b/include/linux/spi/mcp23s08.h @@ -22,4 +22,22 @@ struct mcp23s08_platform_data { * base to base+15 (or base+31 for s17 variant). */ unsigned base; + /* Marks the device as a interrupt controller. + * NOTE: The interrupt functionality is only supported for i2c + * versions of the chips. The spi chips can also do the interrupts, + * but this is not supported by the linux driver yet. + */ + bool irq_controller; + + /* Sets the mirror flag in the IOCON register. Devices + * with two interrupt outputs (these are the devices ending with 17 and + * those that have 16 IOs) have two IO banks: IO 0-7 form bank 1 and + * IO 8-15 are bank 2. These chips have two different interrupt outputs: + * One for bank 1 and another for bank 2. If irq-mirror is set, both + * interrupts are generated regardless of the bank that an input change + * occurred on. If it is not set, the interrupt are only generated for + * the bank they belong to. + * On devices with only one interrupt output this property is useless. + */ + bool mirror; }; |