Age | Commit message (Collapse) | Author |
|
All code that attemots to access variables in BSS before relocation
(for example directly or indirectly by board_init_f()) needs to be
fixed. Especially timer.c needs to fix on most of the ARM platforms.
This patch makes timer related variables in gd_t available for
all ARM implementations.
Signed-off-by: Prafulla Wadaskar <prafulla@marvell.com>
Edited commit message.
Signed-off-by: Wolfgang Denk <wd@denx.de>
|
|
I doubt the stack_setup() was defective before:
we load the current location of _start and compare against destination
of relocate_code(). If we are already there we shoud skip the
relocation and jump over to clear_bss. Before the clear_bss was also skipped.
Signed-off-by: Andreas Bießmann <andreas.devel@googlemail.com>
|
|
r8 is used for global_data and should therefore be left alone!
For C code the compiler flag --fixed-r8 does the job, but in assembler
we need to be aware of that fact.
Signed-off-by: Andreas Bießmann <andreas.devel@googlemail.com>
|
|
In case we are still at relocation target address before relocation we
do not need to load the registers needed for relocation. We should
instead skip the whole relocation part and jump over to clear_bss
immediately.
Signed-off-by: Andreas Bießmann <andreas.devel@googlemail.com>
|
|
This patch uses r1 as scratch register for copy_loop(). Therefore we do
not longer need r7 for the storage of relocate_code()'s 'addr_moni' (the
destination address of relocation).
Therefore r7 can be used later on for other purposes.
Signed-off-by: Andreas Bießmann <andreas.devel@googlemail.com>
|
|
suggested from Daniel Hobi<daniel.hobi@schmid-telecom.ch>
Tested on following boards:
arm1136: qong
armv7: omap3_beagle
arm926ejs: magnesium, tx25
Signed-off-by: Heiko Schocher <hs@denx.de>
cc: Daniel Hobi <daniel.hobi@schmid-telecom.ch>
cc: Albert ARIBAUD <albert.aribaud@free.fr>
|
|
This patch fixes build errors in the vexpress system:
- Removed sys_proto.h requirement from syslib.c.
- Switched vexpress to the default armv7 linker script.
- Renamed TEXT_BASE to CONFIG_SYS_TEXT_BASE.
Signed-off-by: Matt Waddel <matt.waddel@linaro.org>
|
|
|
|
Reuse the gd->tbl value for timestamp and add gd->lastinc for lastinc
bss values in arm920t/at91/timer driver.
The usage of bss values in driver before initialisation of bss is
forbidden. In that special case some data in .rel.dyn gets corrupted by
the arm920t/at91/timer driver.
Signed-off-by: Andreas Bießmann <andreas.devel@googlemail.com>
|
|
Signed-off-by: Andreas Bießmann <biessmann@corscience.de>
|
|
The AT91SAM9G20 BOOT ROM apparently initializes PA23 and PA24 to multi drive
(open drain). Revert this, if those pins are going to be used for MII.
Signed-off-by: Reinhard Meyer <u-boot@emk-elektronik.de>
|
|
This fixes the compiling error for the board which doesn't have NOR flash
(so CONFIG_FLASH_BASE is not defined)
Signed-off-by: Haiying Wang <Haiying.Wang@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
|
|
|
|
|
|
Some systems need to relocate the env_addr pointer early because the
location it points to will get invalidated before env_relocate is
called. One example is on systems that might use a L2 or L3 cache
in SRAM mode and initialize that cache from SRAM mode back to being
a cache in cpu_init_r.
We set this on the 85xx boards that have support for NAND, SPI, or
SDHC/MMC boot support as they use a secondary cache in SRAM mode and
need the env_addr pointer relocated since we change from SRAM to normal
cache mode in cpu_init_r.
Also removed CONFIG_SYS_SPL as its not used anywhere.
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
|
|
|
|
|
|
After the removal of COLD/WARM start flags my mpc8321
board didn't boot anymore.
Trial and error suggests that map/remap_flash_by_xxx needs
to wait after updating LBLAWAR1 to make sure the the change has
reached the HW before continuing with the code that depends on it.
Final fix suggested by Scott Wood.
Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Acked-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Kim Phillips <kim.phillips@freescale.com>
|
|
By commit 6d8962e814c15807dd6ac5757904be2a02d187b8,
label of _start was not usable in start.S and build fail.
This change label from _start to _sh_start.
----
arch/sh/cpu/sh4/libsh4.o: In function `_start':
(.text+0x204): multiple definition of `_start'
arch/sh/cpu/sh4/start.o:(.text+0x0): first defined here
----
Signed-off-by: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.yj@renesas.com>
|
|
Because of count_value is set to tcnb4 register,
should be get from this register when call udelay function.
Signed-off-by: Minkyu Kang <mk7.kang@samsung.com>
|
|
With addition of "dram_init_banksize()" function from Heiko,Schocher
(commit ID: 561142af20f1fd7b425d9425730014e656defb91), the DRAM size
is getting configured wrongly to 512Mb (CS0 & CS1).
So fix it to 256Mb.
Signed-off-by: Vaibhav Hiremath <hvaibhav@ti.com>
Signed-off-by: Sandeep Paulraj <s-paulraj@ti.com>
|
|
When the cache is enabled in SDRAM we need to flush not only the global
data area but also the bd_info struct in relocate_code. This patch now
flushed the complete dcache (all dcache lines) via flush_dcache() instead
of adding a flush_dcache_range() call for bd_info since this is faster.
Signed-off-by: Stefan Roese <sr@denx.de>
|
|
Use the return value of cmd_usage instead of ignoring this
and returning a 1.
Signed-off-by: Thomas Weber <weber@corscience.de>
Acked-by: Mike Frysinger <vapier@gentoo.org>
|
|
Signed-off-by: Wolfgang Denk <wd@denx.de>
Acked-by: Stefan Roese <sr@denx.de>
|
|
Signed-off-by: Wolfgang Denk <wd@denx.de>
Acked-by: Stefan Roese <sr@denx.de>
|
|
Signed-off-by: Wolfgang Denk <wd@denx.de>
Acked-by: Stefan Roese <sr@denx.de>
|
|
Signed-off-by: Wolfgang Denk <wd@denx.de>
Acked-by: Stefan Roese <sr@denx.de>
|
|
Signed-off-by: Wolfgang Denk <wd@denx.de>
Acked-by: Stefan Roese <sr@denx.de>
|
|
Signed-off-by: Wolfgang Denk <wd@denx.de>
Cc: Anatolij Gustschin <agust@denx.de>
Cc: Timur Tabi <timur@freescale.com>
Acked-by: Stefan Roese <sr@denx.de>
|
|
Signed-off-by: Wolfgang Denk <wd@denx.de>
Acked-by: Stefan Roese <sr@denx.de>
|
|
Signed-off-by: Wolfgang Denk <wd@denx.de>
Acked-by: Stefan Roese <sr@denx.de>
|
|
Signed-off-by: Wolfgang Denk <wd@denx.de>
Cc: Kumar Gala <galak@kernel.crashing.org>
Acked-by: Stefan Roese <sr@denx.de>
|
|
Signed-off-by: Wolfgang Denk <wd@denx.de>
Cc: Kim Phillips <kim.phillips@freescale.com>
Cc: Haiying Wang <r54964@freescale.com>
|
|
This commit adapts 4xx boards for partial linking with --gc-sections.
Signed-off-by: Stefan Roese <sr@denx.de>
Signed-off-by: Wolfgang Denk <wd@denx.de>
Cc: Stefan Roese <sr@denx.de>
Cc: Tirumala Marri <tmarri@apm.com>
Cc: David Updegraff <dave@cray.com>
Cc: Matthias Fuchs <matthias.fuchs@esd-electronics.com>
Cc: Dirk Eibach <eibach@gdsys.de>
Cc: Larry Johnson <lrj@acm.org>
Cc: Peter De Schrijver <p2@mind.be>
Cc: Niklaus Giger <niklaus.giger@netstal.com>
Cc: Daniel Poirot <dan.poirot@windriver.com>
Acked-by: Stefan Roese <sr@denx.de>
|
|
The switch from archive libraries to partial linking has introduced a
number of problems, that are non-trivial to solve. For example, it is
no longer possible to include individual object files in the linker
script as we did before for example in the case of boards with
embedded environment to fill up the gap caused by the need to align
the environment on flash erase block boundaries.
The best (but unfortunately not easiest) approach to address this
problem is to enable -ffunction-sections (and -fdata-sections) so
we can again (and even in much finer granularity) place certain code
where we want it. When doing this step, it seems only consequent to
also add --gc-sections which has the added benefit of reducing the
memory footprint of the U-Boot image (both in flash and in RAM).
Unfortunately, this requires changes to a lot of linker scripts.
Signed-off-by: Wolfgang Denk <wd@denx.de>
Cc: Stefan Roese <sr@denx.de>
Cc: Kim Phillips <kim.phillips@freescale.com>
Cc: Andy Fleming <afleming@gmail.com>
Cc: Kumar Gala <galak@kernel.crashing.org>
Acked-by: Stefan Roese <sr@denx.de>
|
|
As we try to get rid of board specific config.mk files we must
provide a way for board specific settings of the LDSCRIPT variable
(path to the linker script) where needed.
We now implement the following hierarchy:
- Highest priority has a "#define CONFIG_SYS_LDCONFIG" in the board
config file.
- If CONFIG_SYS_LDCONFIG is not set, and the system is booting from
NAND (CONFIG_NAND_SPL is set), then a board specific linker
script board/$(BOARDDIR)/u-boot-nand.lds gets used.
- If we are not booting from NAND, we test if a processor specific
linker script arch/powerpc/cpu/$(CPU)/u-boot.lds exists; if so we
use that.
- As default, arch/powerpc/config.mk gets used.
Signed-off-by: Wolfgang Denk <wd@denx.de>
Cc: Stefan Roese <sr@denx.de>
Cc: Kim Phillips <kim.phillips@freescale.com>
Cc: Kumar Gala <kumar.gala@freescale.com>
Cc: Andy Fleming <afleming@gmail.com>
Acked-by: Stefan Roese <sr@denx.de>
|
|
Signed-off-by: Wolfgang Denk <wd@denx.de>
Cc: Stefan Roese <sr@denx.de>
Acked-by: Stefan Roese <sr@denx.de>
|
|
So far, only the BAB7xx board would call the initialise_w83c553f()
function for the WINBOND 83C553 chip, even though some other boards
(HIDDEN_DRAGON, Sandpoint8240, Sandpoint8245) enabled it in their
board configuration. These boards were also missing other config
settings needed for that, which resulted in build errors like this:
drivers/pci/libpci.o:(.got2+0x84): undefined reference to `ide_bus_offset'
Switch arch/powerpc/lib/board.c to call initialise_w83c553f() not on a
per-board base, but when a WINBOND_83C553 in enabled in a
configuration (like BAB7xx), and disable it in the boards that had
this set so far.
Signed-off-by: Wolfgang Denk <wd@denx.de>
Cc: Yusdi Santoso <yusdi_santoso@adaptec.com>
Cc: Jim Thompson <jim@musenki.com>
Acked-by: Stefan Roese <sr@denx.de>
|
|
|
|
The start.S file was only half-rewritten for ELF relocations.
This bugfix completes the rewrite.
Signed-off-by: Albert Aribaud <albert.aribaud@free.fr>
|
|
bulk addition of ELF relocation support to ARM cpus
arm946es, arm720t,arm920t, arm925t, arm_intcm, ixp,
lh7a40x, s3c44b0, and sa1100.
Signed-off-by: Albert Aribaud <albert.aribaud@free.fr>
|
|
We explicitly link in the initcode.o in the Blackfin linker script, so
there is no need to merge it into the main common object for the linker
to pull in itself. This also fixes duplicate symbol errors with the new
partial linking logic.
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
|
|
DECLARE_GLOBAL_DATA_PTR is currently defined within the scope
of function while it is a global pointer. Change the scope of
definition to replicate it's global scope. This seems to help
gcc 4.5 optimizations as well.
Signed-off-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Sandeep Paulraj <s-paulraj@ti.com>
|
|
|
|
The Blackfin on-chip BootROM requires that fill operations (which is
used for the bss) be aligned to 4 bytes (base addr and total len).
Plus, the Blackfin early init asm code assumes the same thing. So
rather than making things work for no real gain, make sure the bss
len is padded to 4 bytes in the linker script.
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
|
|
This lets the linker garbage collect these functions when they aren't
actually used by placing them into the standard .text.<func> section.
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
|
|
Before this commit, weak symbols were not overridden by non-weak symbols
found in archive libraries when linking with recent versions of
binutils. As stated in the System V ABI, "the link editor does not
extract archive members to resolve undefined weak symbols".
This commit changes all Makefiles to use partial linking (ld -r) instead
of creating library archives, which forces all symbols to participate in
linking, allowing non-weak symbols to override weak symbols as intended.
This approach is also used by Linux, from which the gmake function
cmd_link_o_target (defined in config.mk and used in all Makefiles) is
inspired.
The name of each former library archive is preserved except for
extensions which change from ".a" to ".o". This commit updates
references accordingly where needed, in particular in some linker
scripts.
This commit reveals board configurations that exclude some features but
include source files that depend these disabled features in the build,
resulting in undefined symbols. Known such cases include:
- disabling CMD_NET but not CMD_NFS;
- enabling CONFIG_OF_LIBFDT but not CONFIG_QE.
Signed-off-by: Sebastien Carlier <sebastien.carlier@gmail.com>
|
|
|
|
older ld emitted all ELF relocations in input sections named
.rel.dyn, whereas newer ld uses names of the form .rel*. The
linker script only collected .rel.dyn input sections. Rewrite
to collect all .rel* input sections.
Signed-off-by: Albert Aribaud <albert.aribaud@free.fr>
|
|
Tested on upcoming hydra (mpc5200 based) board.
Signed-off-by: Heiko Schocher <hs@denx.de>
|