Avoid unnecessary assembly functions when they can easily be written
in C.

Also remove dc_read() as it is nowhere referenced
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>

All complex case have been removed and we now only support
MPC866 and MPC885 families.

So check_CPU() can be made a lot simpler.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>

reginfo command is calling mpc8xx_reginfo(), mpc85xx_reginfo()
or mpc86xx_reginfo() based on CONFIG_ symbol.
As those 3 functions can't me defined at the same time, let's
rename them print_reginfo() to avoid the #ifdefs
The name is kept generic as it is not at all dependent on
powerpc arch and any other arch could want to also print
such information.

In addition, as the Makefile compiles cmd/reginfo.c only when
CONFIG_CMD_REGINFO is set, there is no need to enclose the U_BOOT_CMD
definition inside a #ifdef CONFIG_CMD_REGINFO

Lets all remove the #ifdefs around the U_BOOT_CMD as this
file is only compiled when CONFIG_CMD_REGINFO is defined

Finally, this is a PowerPC-only command, disable it on a number of
non-PowerPC platforms.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NTom Rini <trini@konsulko.com>

set_msr() and get_msr() are defined and used twice.
This patch moves them into ppc.h
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>

In order to avoid TBU increment due to TBL reaching its max
and wrapping, reset TBL before resetting TBU
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>

The actions inside #ifdef CONFIG_8xx in arch/powerpc/lib/time.c
can be performed before, in a 8xx dedicated function.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>

This function has never been used, at least since the beginning
of the git repository
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>

divider is calculated based on SCCR_DFBRG, with:
SCCR_DFBRG 00 => divider 1  = 1 << 0
SCCR_DFBRG 01 => divider 4  = 1 << 2
SCCR_DFBRG 10 => divider 16 = 1 << 4
SCCR_DFBRG 11 => divider 64 = 1 << 6

This can be easily converted to a single shift operation:
divider = 1 << (SCCR_DFBRG * 2)
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>

It is possible to flag MAC addresses as locally administred. In this
case they don't need to be unique. This is only allowed for interfaces
which have no connection to the outside. For the TEGR1 board we use
this feature.

Cc: Heiko Schocher <hs@denx.de>
Signed-off-by: NHolger Brunck <holger.brunck@keymile.com>

If we rebrand the IVM and ethaddr was set previously we need to change
ethaddr. Otherwise we end up with a wrong MAC adress for the ethernet
interface.

Cc: Heiko Schocher <hs@denx.de>
Signed-off-by: NHolger Brunck <holger.brunck@keymile.com>

It is annoying to have to set up and maintain two sets of toolchains, one
for buildman and one for moveconfig.

Adjust moveconfig to make use to buildman's toolchains. This should make
things easier.

One missing feature is the ability to specify the toolchain on the command
line with a special environment variable, e.g. CROSS_COMPILE_ARM. I'm not
sure if that is useful, but if it is it could be implemented in buildman.
Signed-off-by: NSimon Glass <sjg@chromium.org>
Reviewed-by: NPhilipp Tomsich <philipp.tomsich@theobroma-systems.com>
Tested-by: NPhilipp Tomsich <philipp.tomsich@theobroma-systems.com>

Add an option to specify 'all' to enable all flags. Also print an error
if an unrecognised flag is used. At present it just prints usage
information which is not very helpful.
Signed-off-by: NSimon Glass <sjg@chromium.org>

Disable RNG and add TEE to FDT used on HS devices.
Signed-off-by: NAndrew F. Davis <afd@ti.com>

Add support for loading a TEE and setting up firewalled regions to
AM43xx HS boards.
Signed-off-by: NAndrew F. Davis <afd@ti.com>

Similar to what is done with OMAP5 class boards we need to
perform fixups common to this SoC class, add support for this here
and add HS fixups.
Signed-off-by: NAndrew F. Davis <afd@ti.com>

If a firmware node is already present in the FDT we will fail to create
one and so fail to add our OP-TEE node, make this fixup first check for
a firmware node and then only try to add one if it is not found.
Signed-off-by: NAndrew F. Davis <afd@ti.com>

Some of the fixups currently done for OMAP5 class boards are common to
other OMAP family devices, move these to fdt-common.c.
Signed-off-by: NAndrew F. Davis <afd@ti.com>

TEE loading and firewall setup are common to all omap2 devices, move
these function out of omap5 and into mach-omap2. This allows us
to use these functions from other omap class devices.
Signed-off-by: NAndrew F. Davis <afd@ti.com>

When running a 'make clean' or carelessly removing u-boot.cfg, all
future make invocations (until autoconf is regenerated) will print
an error for a missing u-boot.cfg due to missing rules and dependencies.

This commit adds (i) an explicit rule dependency from all (which will
invokes the configuration checker) to cfg, and (b) adds a rule to
invoke scripts/Makefile.autoconf to regenerate u-boot.cfg.
Signed-off-by: NPhilipp Tomsich <philipp.tomsich@theobroma-systems.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>
Tested-by: NBin Meng <bmeng.cn@gmail.com>

FreeBSD recently switch to it's BSDL dtc. While it support most of the
features of the GPL one it still lacks the incbin directive.
Add the possibility to specify which dtc we want to use for compiling dts
and generating fit image.
Signed-off-by: NEmmanuel Vadot <manu@bidouilliste.com>
Acked-by: NSimon Glass <sjg@chromium.org>

The Odroid C2 has two GiB of memory with two reserved regions.
reg = <0x0 0x0 0x0 0x1000000>;
reg = <0x0 0x10000000 0x0 0x200000>;

Patch
bfcef28a (arm: add initial support for Amlogic Meson and
ODROID-C2) provided function dram_init_banksize to reserve the
first 16 MiB of RAM for firmware in function dram_init_banksize
in arch/arm/mach-meson/board.c and defined
CONFIG_NR_DRAM_BANKS = 1.

With this patch dram_init_banksize is changed to additionally
reserve the 2MiB region for the ARM Trusted Firmware (BL31).
CONFIG_NR_DRAM_BANKS is set to 2.

Cc: Andreas Färber <afaerber@suse.de>
Signed-off-by: NHeinrich Schuchardt <xypron.glpk@gmx.de>

The env_nand, env_mmc and env_ubi implementations all implement
redundancy using an identical serial-number scheme. This commit
migrates them to use the implementation in env_common, which is
functionally identical.
Signed-off-by: NFiach Antaw <fiach.antaw@uqconnect.edu.au>
Reviewed-by: NTom Rini <trini@konsulko.com>

All current environments that implement redundancy use almost
identical implementations. This patch implements the env_nand
implementation as a function in env_common, and updates the
env_export function to export an env_nand-style 'flags' field by
default.
Signed-off-by: NFiach Antaw <fiach.antaw@uqconnect.edu.au>
Reviewed-by: NTom Rini <trini@konsulko.com>

If one does not already have a rule to create a custom device node when
a given device enumerates it can be useful to have udev create a
bus path based node to the entry in /dev/bus/usb that was just
enumerated.  Given that DFU itself does not require a /dev entry it is a
good idea to provide a rule that will generate one.
Signed-off-by: NTom Rini <trini@konsulko.com>

Closing a file descriptor does not guarantee that the data has been
successfully saved to disk, as the kernel might defer the write.
Signed-off-by: NMichael Heimpold <mhei@heimpold.de>

DTB is encoded in big endian.  When we retrieve property values,
we need to use fdt32_to_cpu (aka be32_to_cpu) for endian conversion.
This is a bit error-prone, but sparse is useful to detect endian
mismatch.

We need to use (fdt32_t *) instead of (u32 *) for a pointer of a
property value.  Otherwise sparse warns "cast to restricted __be32".
Signed-off-by: NMasahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: NJaehoon Chung <jh80.chung@samsung.com>

This function is only used in common/spl/spl_mmc.c[
Signed-off-by: NMasahiro Yamada <yamada.masahiro@socionext.com>
Reviewed-by: NBin Meng <bmeng.cn@gmail.com>
Signed-off-by: NJaehoon Chung <jh80.chung@samsung.com>

get_enable should be able to return error values. Hence change
the return type to integer.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

get_enable should be able to return error values. Hence change
the return type to integer.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

get_enable should be able to return error values. Hence change
the return type to integer.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

get_enable should be able to return error values. Hence change
the return type to integer.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

get_enable should be able to return error values. Hence change
the return type to integer.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

get_enable should be able to return error values. Hence change
the return type to integer.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

get_enable should be able to return error values. Hence change
the return type to integer.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

get_enable should be able to return error values. Hence change
the return type to integer.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

get_enable should be able to return error values. Hence change
the return type to integer.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

get_enable should be able to return error values. Hence change
the return type to integer.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

get_enable should be able to return error values. Hence change
the return type to integer.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

Change get_enable return type to int so errors can be returned.
Signed-off-by: NKeerthy <j-keerthy@ti.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>

According to MMC spec, the write_counter is 4-byte length,
use 'int' instead of 'long' type for the 'long' is not 4-byte
in 64 bit CPU.
Signed-off-by: NJason Zhu <jason.zhu@rock-chips.com>
Signed-off-by: NKever Yang <kever.yang@rock-chips.com>
Reviewed-by: NSimon Glass <sjg@chromium.org>
Signed-off-by: NJaehoon Chung <jh80.chung@samsung.com>