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>
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>
The fixup procedure just stored a constant value in the
fixup table rather than just adjusting the table.
Although that doesn't seem to do any harm, it prevents
relocation more that once.
Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Use CONFIG_SYS_MONITOR_BASE instead of CONFIG_SYS_TEXT_BASE in early
init code so we can share the same code with NAND or NOR boot and not
have additional ifdefs in here.
Signed-off-by: Haiying Wang <Haiying.Wang@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Fix u-boot-nand.lds and u-boot-nand_spl.lds according to:
Author: Peter Tyser <ptyser@xes-inc.com>
Date: Wed Sep 29 14:05:56 2010 -0500
commit fbe53f59bd
85xx: Use gc-sections to reduce image size
Signed-off-by: Haiying Wang <Haiying.Wang@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
CONFIG_SYS_GBL_DATA_SIZE has always been just a bad workarond for not
being able to use "sizeof(struct global_data)" in assembler files.
Recent experience has shown that manual synchronization is not
reliable enough. This patch renames CONFIG_SYS_GBL_DATA_SIZE into
GENERATED_GBL_DATA_SIZE which gets automatically generated by the
asm-offsets tool. In the result, all definitions of this value can be
deleted from the board config files. We have to make sure that all
files that reference such data include the new <asm-offsets.h> file.
No other changes have been done yet, but it is obvious that similar
changes / simplifications can be done for other, related macro
definitions as well.
Signed-off-by: Wolfgang Denk <wd@denx.de>
Acked-by: Kumar Gala <galak@kernel.crashing.org>
CONFIG_SYS_INIT_RAM_END was a misnomer as it suggests this might be
some end address; to make the meaning more clear we rename it into
CONFIG_SYS_INIT_RAM_SIZE
No other code changes are performed in this patch, only minor editing
of white space (due to the changed length) and the comments was done,
where noticed.
Note that the code for the PATI and cmi_mpc5xx board configurations
looks seriously broken. Last known maintainers on Cc:
Signed-off-by: Wolfgang Denk <wd@denx.de>
Cc: Denis Peter <d.peter@mpl.ch>
Cc: Martin Winistoerfer <martinwinistoerfer@gmx.ch>
Acked-by: Kumar Gala <galak@kernel.crashing.org>
Commit 29c6fbe "MPC5121: Add USB EHCI support" renamed
CONFIG_SYS_MPC8xxx_USB_ADDR into CONFIG_SYS_FSL_USB_ADDR but missed
to update arch/powerpc/cpu/mpc83xx/cpu_init.c, resulting in:
cpu_init.c: In function 'cpu_init_f':
cpu_init.c:332: error: 'CONFIG_SYS_MPC8xxx_USB_ADDR' undeclared (first use in this function)
cpu_init.c:332: error: (Each undeclared identifier is reported only once
cpu_init.c:332: error: for each function it appears in.)
make[1]: *** [/work/wd/tmp-ppc/arch/powerpc/cpu/mpc83xx/cpu_init.o] Error 1
Fix this.
Signed-off-by: Wolfgang Denk <wd@denx.de>
Cc: Kim Phillips <kim.phillips@freescale.com>
On an XPedite5370 over 11KBytes were saved:
Before:
text data bss dec hex filename
332456 33364 33476 399296 617c0 ./u-boot
After:
text data bss dec hex filename
321075 33836 33476 388387 5ed23 ./u-boot
Signed-off-by: Peter Tyser <ptyser@xes-inc.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
On an XPedite5170 over 11KBytes were saved:
Before:
text data bss dec hex filename
319488 28700 33204 381392 5d1d0 ./u-boot
After:
text data bss dec hex filename
307663 29144 33204 370011 5a55b ./u-boot
Signed-off-by: Peter Tyser <ptyser@xes-inc.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Previously io_sel=0xe incorrect stated PCIE1 was enabled. Also add
support for the mpc8640's PCIE2 interface.
Signed-off-by: Peter Tyser <ptyser@xes-inc.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Some OSes require that secondary cores not be initialized when they
are booted (eg VxWorks). By default when U-Boot is compiled with the
CONFIG_MP option all secondary cores are brought out of reset and held
in spinloops. Setting the "mp_holdoff" environment variable to 'yes'
or '1' will cause U-Boot to leave secondary cores in their default
state.
Signed-off-by: Aaron Sierra <asierra@xes-inc.com>
Signed-off-by: Peter Tyser <ptyser@xes-inc.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
When DDR controller interleaving is eabled and less than all bank (chip-select)
interleaving is seletected, the unused chip-select should be disabled.
Signed-off-by: York Sun <yorksun@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
The memory test is performed after DDR initialization when U-boot stills runs
in flash and cache. On recent mpc85xx platforms, the total memory can be more
than 2GB. To cover whole memory, it needs be mapped 2GB at a time using a
sliding TLB window. After the testing, DDR is remapped with up to 2GB memory
from the lowest address as normal.
If memory test fails, DDR DIMM SPD and DDR controller registers are dumped for
further debugging.
Signed-off-by: York Sun <yorksun@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
A worker function setup_ddr_tlbs_phys() is introduced to implement more
control on physical address mapping.
Signed-off-by: York Sun <yorksun@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Add a common helper that will set the PHY connection type based on enum.
We use this on eTSEC, UCC, and will with Fman in the future.
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
The fixup routine must not fixup NULL pointers.
Problem can be seen by
char *testfun(void) __attribute__((weak));
char *(*myfun)(void) = testfun;
Then add
printf("myfun:%p, &myfun:%p\n", myfun, &myfun);
before relocation and after relocation.
myfun should be NULL in both cases but it is not.
Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Now that warm booting is not supported, there isn't a need for the
BOOTFLAG_COLD and BOOTFLAG_WARM defines, so remove them.
Note that this change makes the board info bd_bootflags field useless.
It will always be set to 0, but we leave it around so that we don't
break the board info structure that some OSes are expecting to be passed
from U-Boot.
Signed-off-by: Peter Tyser <ptyser@xes-inc.com>
The change is currently needed to be able to remove the board
configuration scripting from the top level Makefile and replace it by
a simple, table driven script.
Moving this configuration setting into the "CONFIG_*" name space is
also desirable because it is needed if we ever should move forward to
a Kconfig driven configuration system.
Signed-off-by: Wolfgang Denk <wd@denx.de>
pumping line-rate traffic though a p4080 rev.2, which
is configured to encrypt packets prior to forwarding through
an IPsec tunnel, gets this error:
of_platform ffe302000.jq: DECO: desc idx 22: LIODN error. DECO was trying
to share from itself or from another DECO but the two Non-SEQ LIODN
values didn't match or the "shared from" DECO's Descriptor required that
the SEQ LIODNs be the same and they aren't.
Since high traffic rates cause DECOs to begin to start sharing
shared descriptors amongst themselves, and DECOs inherit job queue
LIODNs when accessing shared descriptors, and a recently discovered
rev.2 h/w erratum requires all sharing job queues in a partition
have same liodn assignment, reassign the first job queue's liodn
assignment to the rest.
Signed-off-by: Kim Phillips <kim.phillips@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
The PCU_E board has long reached EOL, and support for it is no longer
relevant in current versions of U-Boot. Remove it.
Signed-off-by: Wolfgang Denk <wd@denx.de>
APM821XX is a new line of SoCs which are derivatives of
PPC44X family of processors. This patch adds support of CPU, cache,
tlb, 32k ocm, bootstraps, PLB and AHB bus.
Signed-off-by: Tirumala R Marri <tmarri@apm.com>
Signed-off-by: Stefan Roese <sr@denx.de>
Commit 800eb0964 "POST cleanup." removed file
arch/powerpc/cpu/mpc512x/common.c but failed to remove the reference
to it from arch/powerpc/cpu/mpc512x/Makefile which causes somewhat
obscure build errors:
make[1]: *** No rule to make target `/work/wd/tmp-ppc/arch/powerpc/cpu/mpc512x/.depend', needed by `_depend'. Stop.
Fix these.
Signed-off-by: Wolfgang Denk <wd@denx.de>
Move common code to the fsl_diu_fb.c file and remove obsolete
code from board files (aria, mpc8610hpcd and pdm360ng).
Move fsl_diu_fb.h file to the include directory.
Signed-off-by: Anatolij Gustschin <agust@denx.de>
This change lays the groundwork for the BOOTFLAG_* flags being removed.
This change has the small affect of delaying 100ms on PCI initialization
after a warm boot as opposed to the optimal 1ms on some boards.
Signed-off-by: Peter Tyser <ptyser@xes-inc.com>
included the mpc8308_p1m board.
Signed-off-by: Kim Phillips <kim.phillips@freescale.com>
Configuring for MPC8308RDB board...
pcie.c: In function 'mpc83xx_pcie_register_hose':
pcie.c:143: warning: assignment makes pointer from integer without a cast
Signed-off-by: Kim Phillips <kim.phillips@freescale.com>
This patch adds support for setting PCIE clocks in cpu_init.c by
providing CONFIG_SYS_SCCR_PCIEXP{1,2} in configuration.
Signed-off-by: Ilya Yanok <yanok@emcraft.com>
Signed-off-by: Kim Phillips <kim.phillips@freescale.com>
MPC8308 has only one PCIE host controller so we want it to compile
without CONFIG_SYS_PCIE2_CFG_{BASE,SIZE} defined.
Signed-off-by: Ilya Yanok <yanok@emcraft.com>
Signed-off-by: Kim Phillips <kim.phillips@freescale.com>
By default the trace broadcast is enabled on 44x systems.
To reduce power consumption when instruction tracing is
not needed, disable trace broadcast.
Check External Debug Mode (EDM) bit to detect if it should be
disabled or not.
Resetting system via a debugger will set the DBCR0[EDM] bit.
Resetting via u-boot or OS will not.
Signed-off-by: Victor Gallardo <vgallardo@apm.com>
Signed-off-by: Stefan Roese <sr@denx.de>
This patch cleans the PVR detection code in check_cpu() up a bit.
Basically the strings are better seperated, resulting in an easier
to understand and maintain code version.
The #ifdef's couldn't be removed easily because of two reasons:
- Some SoC revisions have the same PVR, so need a way to differentiate
between those two SoC's.
- In some case statements registers only available in this SoC variant
are referenced.
Instead I moved the CONFIG_440 #ifdef a bit, so that 405 platforms don't
add this 440 detection code and vice versa. Resulting in this U-Boot
image size change:
405EX (Kilauea): 408 bytes less
440EPx (Sequoia): 604 bytes less
460EX (Canyonlands): 564 bytes less
Signed-off-by: Stefan Roese <sr@denx.de>
Cc: Wolfgang Denk <wd@denx.de>
This patch removes the PPC4xx UART driver. Instead the common NS16550
driver is used, since all PPC4xx SoC's use this peripheral device.
The file 4xx_uart.c now only implements the UART clock calculation
function which also sets the SoC internal UART divisors.
All PPC4xx board config headers are changed to use this common NS16550
driver now.
Tested on these boards:
acadia, canyonlands, katmai, kilauea, sequoia, zeus
Signed-off-by: Stefan Roese <sr@denx.de>
This cleanup is done by creating header files for all SoC versions and
moving the SoC specific defines into these special headers. This way the
common header ppc405.h and ppc440.h can be cleaned up finally.
As a part from this cleanup, the GPIO definitions for PPC405EP are
corrected. The high and low parts of the registers (for example
CONFIG_SYS_GPIO0_OSRL vs. CONFIG_SYS_GPIO0_OSRH) have been defined in
the wrong order. This patch now fixes this issue by switching these
xxxH and xxxL values. This brings the GPIO 405EP port in sync with all
other PPC4xx ports.
Signed-off-by: Stefan Roese <sr@denx.de>
This patch starts a bit PPC4xx header cleanup. First patch mostly
touches PPC440 files. A later patch will touch the PPC405 files as well.
This cleanup is done by creating header files for all SoC versions and
moving the SoC specific defines into these special headers. This way the
common header ppc405.h and ppc440.h can be cleaned up finally.
Signed-off-by: Stefan Roese <sr@denx.de>
