09 Jan, 2012
5 commits
-
Add PFC support for a 32-bit unlock register. Needed to
drive the r8a7779 PFC that comes with a funky PMMR register.Signed-off-by: Magnus Damm
Signed-off-by: Paul Mundt -
Add support for variable config reg hardware by adding
the macro PINMUX_CFG_REG_VAR(). The width of each bitfield
needs to be passed to the macro, and the correct space must
be consumed by each bitfield in the enum table following the
macro. Data registers still need to have fixed bitfields.Signed-off-by: Magnus Damm
Signed-off-by: Paul Mundt -
Add a helper function for shared config reg access
calculations. This allows us to reduce the amount
of duplicated code, and at the same time prepare
for a common place for future variable bitwidth
config reg support.Signed-off-by: Magnus Damm
Signed-off-by: Paul Mundt -
Update the way the PFC code is passing bitfield
selection between configure register functions.Convert the code from using index only to bitfield
number and selected value. First step towards future
variable bitfield width support.Signed-off-by: Magnus Damm
Signed-off-by: Paul Mundt -
Introduce gpio_read_bit() for data register read access
and modify sh_gpio_get_value() to make use of the new
function instead of gpio_read_reg(). The purpose of
this change is to update the code to only use the
gpio_read_reg() function for config register access.Signed-off-by: Magnus Damm
Signed-off-by: Paul Mundt
09 Dec, 2011
1 commit
-
Add support for non-entity mapped PFC registers through
the use of struct resource and ioremap()/iounmap().The PFC main data structure gets updated with a pointer
to a struct resources array that point out all register
windows used by the PFC instance. The register definitions
are kept as physical addresses but the PFC code will do
transparent conversion into virtual addresses whenever
register windows are specified using with struct resource.To introduce as little performance penalty as possible the
virtual address of each data register is cached in memory.
The virtual address of each configuration register is however
calculated during run time. This because the configuration
is considered slow path so focus is instead put on keeping
memory foot print as small as possible.The PFC register access code is in this patch updated from
__raw_readN() / __raw_writeN() into ioreadN() / iowriteN().This patch is needed to support the PFC block in r8a7779.
Signed-off-by: Magnus Damm
Signed-off-by: Paul Mundt
28 Oct, 2011
2 commits
-
Add GPIO IRQ support to the shared PFC code in drivers/sh/pfc.c
The enums pointed out by a certain GPIO will be matched against
a table for IRQ to enum mappings.Only the shared PFC code is updated by this patch. SoC specific
changes are also needed to allow platforms to make use of this
feature.Signed-off-by: Magnus Damm
Signed-off-by: Paul Mundt -
Clean up the f_width shift code in get_config_reg().
Reported-by: Ryusuke Sakato
Signed-off-by: Magnus Damm
Signed-off-by: Paul Mundt
04 Oct, 2010
2 commits
-
The gpiolib debugfs entry takes a hammer approach and iterates over all
of the potential GPIOs, regardless of their type. The SH PFC code on the
other hand contains a variable mismash of input/output/function types
spread out sparsely, leading to situations where the debug code can
trigger an out of range enum for the type. Since we already have an error
path for out of range enums, we can just hand that up to the higher level
instead of the current BUG() behaviour.Signed-off-by: Paul Mundt
-
Presently the pinmux code is a one-way thing, but there's nothing
preventing an unregistration if no one has grabbed any of the pins.
This will permit us to save a bit of memory on systems that require pin
demux for certain peripherals in the case where registration of those
peripherals fails, or they are otherwise not attached to the system.Signed-off-by: Paul Mundt
20 Jan, 2010
1 commit
-
This patch updates the PFC code with some clarifying
comments together with a functional change. The change
allows function type of GPIO to select any type of enum
in their MARK lists. Without this patch only function
type of enums are allowed in MARK lists.Signed-off-by: Magnus Damm
Signed-off-by: Paul Mundt
09 Dec, 2009
1 commit
-
!!value works out to an int while we were still using %ld, so fix this up
and shut gcc up.Signed-off-by: Paul Mundt
30 Nov, 2009
3 commits
-
For some reason this was using pr_info() nested under an ifdef DEBUG.
While this is appealing in that it circumvents the effort necessary to
change ones loglevel, it's not terribly practical. So, convert it over
to pr_debug().Signed-off-by: Paul Mundt
-
Now that the PFC code is exposed for other architectures, use the common
__raw_xxx() routines instead of the ctrl_xxx() ones. This will be needed
for ARM-based SH-Mobiles amongst others.Signed-off-by: Paul Mundt
-
This file breaks out the SuperH PFC code from
arch/sh/kernel/gpio.c + arch/sh/include/asm/gpio.h
to drivers/sh/pfc.c + include/linux/sh_pfc.h.Similar to the INTC stuff. The non-SuperH specific
file location makes it possible to share the code
between multiple architectures.Signed-off-by: Magnus Damm
Signed-off-by: Paul Mundt