The Allwinner reset controller has 32-bit registers, but resource_size
is measured in bytes, not number of registers.
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Acked-by: Chen-Yu Tsai <wens@csie.org>
The Allwinner reset controller has 32-bit registers, so translating
the reset cell number into a register and bit offset should not use
any architecture dependent data size. Otherwise this breaks for 64-bit
architectures like arm64.
Fix this by making it clear that it's the hardware register width which
matters here in the calculation.
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Acked-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
The Kconfig currently controlling compilation of this code is:
drivers/reset/Kconfig:config RESET_SUNXI
drivers/reset/Kconfig: bool "Allwinner SoCs Reset Driver" if COMPILE_TEST && !ARCH_SUNXI
drivers/reset/Kconfig: default ARCH_SUNXI
or
arch/arm/mach-sunxi/Kconfig:menuconfig ARCH_SUNXI
arch/arm/mach-sunxi/Kconfig: bool "Allwinner SoCs" if ARCH_MULTI_V7
...meaning that it currently is not being built as a module by anyone.
Lets remove the few remaining traces of modular macro usage, so that
when reading the driver there is no doubt it is builtin-only.
Since module_platform_driver() uses the same init level priority as
builtin_platform_driver() the init ordering remains unchanged with
this commit.
Also note that MODULE_DEVICE_TABLE is a no-op for non-modular code.
We also delete the MODULE_LICENSE tag etc. since all that information
is already contained at the top of the file in the comments.
Cc: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Use devm_reset_controller_register() for the reset controller
registration and drop the .remove callback.
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
The sunxi_reset_ops structure is never modified. Make it const.
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Acked-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Currently, reset_controller_register() always return 0, but it would
be better to check its return code.
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Acked-by: Sören Brinkmann <soren.brinkmann@xilinx.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Since this array is static const, it should be marked as __initconst.
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Acked-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Call spin_lock_init() before the spinlocks are used, both in early init
and probe functions preventing a lockdep splat.
I have been observing lockdep complaining [1] during boot on my a80 optimus [2]
when CONFIG_PROVE_LOCKING has been enabled. This patch resolves the splat,
and has been tested on a few other sunxi platforms without issue.
[1] http://storage.kernelci.org/next/next-20150107/arm-multi_v7_defconfig+CONFIG_PROVE_LOCKING=y/lab-tbaker/boot-sun9i-a80-optimus.html
[2] http://kernelci.org/boot/?a80-optimus
Signed-off-by: Tyler Baker <tyler.baker@linaro.org>
Cc: <stable@vger.kernel.org>
Acked-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Olof Johansson <olof@lixom.net>
The current implementation uses sunxi_reset_init function for both early
init and platform device probe.
The sunxi_reset_init function uses DT to retrieve device resources, which
will be an issue if reset controllers are registered from an MFD device
that define resources from mfd_cell definition.
Moreover, we can make of devm functions when we're in the probe context.
Signed-off-by: Boris BREZILLON <boris.brezillon@free-electrons.com>
Acked-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Acked-by: Philipp Zabel <p.zabel@pengutronix.de>
The Allwinner A31 and most of the other Allwinner SoCs have an IP
maintaining a few other IPs in the SoC in reset by default. Among these
IPs are the A31's High Speed Timers, hence why we can't use the regular
driver construct in every cases, and need to call the registering
function directly during machine initialisation.
Apart from this, the implementation is fairly straightforward, and could
easily be moved to a generic MMIO-based reset controller driver if the
need ever arise.
Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Acked-by: Philipp Zabel <p.zabel@pengutronix.de>
Philipp Zabel