This patch does a few small cleanups around the atmel mci platform code
and in the atmel-mci driver.  The platform changes simply removes an
unused variable, uses the fact that by the end we always have some form
of platform data and notes that GPIO_PIN_NONE != 0.  This last point
could cause the incorrect attempt to twice reserve pin PA0.

While we've got the hood up, add linux/err.h to the atmel-mci.c include
list.  It needs it and generally pulls it by voodoo but I did once
stumble across a config which don't build.

This is against Linus' latest git.
Signed-off-by: NBen Nizette <bn@niasdigital.com>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

Commit 7d2be074
(atmel-mci: Driver for Atmel on-chip MMC controllers)
causes build errors like:

<--  snip  -->

...
  CC      arch/avr32/boards/atstk1000/atstk1003.o
/home/bunk/linux/kernel-2.6/git/linux-2.6/arch/avr32/boards/atstk1000/atstk1003.c: In function 'atstk1003_init':
/home/bunk/linux/kernel-2.6/git/linux-2.6/arch/avr32/boards/atstk1000/atstk1003.c:157: error: too few arguments to function 'at32_add_device_mci'
make[2]: *** [arch/avr32/boards/atstk1000/atstk1003.o] Error 1

<--  snip  -->
Reported-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

This is a driver for the MMC controller on the AP7000 chips from
Atmel. It should in theory work on AT91 systems too with some
tweaking, but since the DMA interface is quite different, it's not
entirely clear if it's worth merging this with the at91_mci driver.

This driver has been around for a while in BSPs and kernel sources
provided by Atmel, but this particular version uses the generic DMA
Engine framework (with the slave extensions) instead of an
avr32-only DMA controller framework.

This driver can also use PIO transfers when no DMA channels are
available, and for transfers where using DMA may be difficult or
impractical for some reason (e.g. the DMA setup overhead is usually
not worth it for very short transfers, and badly aligned buffers or
lengths are difficult to handle.)

Currently, the driver only support PIO transfers. DMA support has been
split out to a separate patch to hopefully make it easier to review.

The driver has been tested using mmc-block and ext3fs on several SD,
SDHC and MMC+ cards. Reads and writes work fine, with read transfer
rates up to 3.5 MiB/s on fast cards with debugging disabled.

The driver has also been tested using the mmc_test module on the same
cards. All tests except 7, 9, 15 and 17 succeed. The first two are
unsupported by all the cards I have, so I don't know if the driver
handles this correctly. The last two fail because the hardware flags a
Data CRC Error instead of a Data Timeout error. I'm not sure how to deal
with that.

Documentation for this controller can be found in many data sheets from
Atmel, including the AT32AP7000 data sheet which can be found here:

http://www.atmel.com/dyn/products/datasheets.asp?family_id=682Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>
Signed-off-by: NPierre Ossman <drzeus@drzeus.cx>

Signed-off-by: NHans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

Andrew Morton reported this against linux-next:

ERROR: ".save_stack_trace" [tests/backtracetest.ko] undefined!
Reported-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Implement Standby support. In this mode, we'll suspend all drivers,
put the SDRAM in self-refresh mode and switch off the HSB bus
("frozen" mode.)

Implement Suspend-to-mem support. In this mode, we suspend all
drivers, put the SDRAM into self-refresh mode and switch off all
internal clocks except the 32 kHz oscillator ("stop" mode.)

The lowest-level suspend code runs from a small portion of SRAM
allocated at startup time. This gets rid of a small potential race
with the SDRAM where we might try to enter self-refresh mode in the
middle of an icache burst. We also relocate all interrupt and
exception handlers to SRAM during the small window when we enter and
exit the low-power modes.

We don't need to do any special tricks to start and stop the PLL. The
main clock is automatically gated by hardware until the PLL is stable.
Signed-off-by: NHaavard Skinnemoen <hskinnemoen@atmel.com>

This makes the intc show up in sysfs (probably not very useful), and
allows us to easily add suspend/resume support later.
Signed-off-by: NHaavard Skinnemoen <hskinnemoen@atmel.com>

Add SRAM allocator for avr32, which is just a thin wrapper around
genalloc.
Signed-off-by: NHaavard Skinnemoen <hskinnemoen@atmel.com>

The SDRAM controller needs a clock in order to respond to our
commands, and suspend doesn't work very well without the SDRAM in
self-refresh mode.
Signed-off-by: NHaavard Skinnemoen <hskinnemoen@atmel.com>

Use a quicklist to allocate process PGDs. This is expected to be
slightly faster since we need to copy entries from swapper_pg_dir,
which can stay around for pages on the PGD quick list.
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

Expand the per-process PGDs so that they cover the kernel virtual
memory area as well. This simplifies the TLB miss handler fastpath
since it doesn't have to check for kernel addresses anymore.

If a TLB miss happens on a kernel address and a second-level page
table can't be found, we check swapper_pg_dir and copy the PGD entry
into the user PGD if it can be found there.
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

Instead of storing physical addresses along with page flags in the
PGD, store virtual addresses and use NULL to indicate a not present
second-level page table. A non-page-aligned page table indicates a bad
PMD.

This simplifies the TLB miss handler since it no longer has to check
the Present bit and no longer has to convert the PGD entry from
physical to virtual address. Instead, it has to check for a NULL
entry, which is slightly cheaper than either.
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

swapper_pg_dir is stored in .bss, so it must already be zeroed out
when we get there.
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

This and the following patches aim to optimize the code dealing with
page tables and TLB operations. Each patch reduces the time it takes
to gzip a 16 MB file slightly, but I expect things like fork() and
mmap() will improve somewhat more.

This patch deals with the low-level TLB operations:

  * Remove unused _TLBEHI_I define
  * Use gcc builtins instead of inline assembly
  * Remove a few unnecessary pipeline flushes and nops
  * Introduce NR_TLB_ENTRIES define and use it instead of hardcoding it
    to 32 a few places throughout the code.
  * Use sysreg bitops instead of hardcoded shifts and masks
  * Make a few needlessly global functions static
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

The only thing left in at32ap.c is some PDC stuff. Rename the file to
reflect what it actually does.
Signed-off-by: NHaavard Skinnemoen <hskinnemoen@atmel.com>

Combine at32_clock_init() and at32_portmux_init() into
setup_platform() and remove setup_platform() from at32ap.c. No
functional change since all setup_platform() ever did was call those
two functions.
Signed-off-by: NHaavard Skinnemoen <hskinnemoen@atmel.com>

Kill the special exception handler sections .tlbx.ex.text,
.tlbr.ex.text, tlbw.ex.text and .scall.text. Use .org instead to place
the handlers at the required offsets from EVBA.
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

Remove lots of unneeded #includes, add #include <linux/kernel.h> and
sort alphabetically.
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

The name "mck" causes a conflict on AT91. Call it "pwm_clk" instead.
Signed-off-by: NSedji Gaouaou <sedji.gaouaou@atmel.com>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

This is a minor tweak to the at32ap700x pin configuration for the SPI
input pin (MISO), enabling the on-chip weak pullup (typical 190K) to

  (a) ensure a fixed data value for missing or input-only slaves;

  (b) prevent power waste associated with inputs floating near VDDIO/2.

Atmel's boards have no external pullup or pulldown on these pins, so
it's unlikely other boards would address these issues with external
pulldowns.  Were there trouble, board-specific code could turn off
the relevant pullup(s).
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

Basic I2C initialization for the NGW100 board:

  - Provide empty i2c device table. Daughtercards may add devices,
    and the ATtiny24 could do stuff too.

  - Set up EXTINT(3) so the ATtiny24 can interrupt the AP7000.
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

This patch adds the PS/2 interface (PSIF) to the device code, split into
two platform devices, one for each port.

The function for adding the PSIF platform device is also added to the
board header file.
Signed-off-by: NHans-Christian Egtvedt <hcegtvedt@atmel.com>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

This patch lets the board code choose which pin out to use for the LCD
interface.

On AT32AP7000 the LCDC is wired to two sets of pins, which lets the user
choose between dual ethernet and 32-bit EBI. For the ATNGW100 board it
is vital to have the choice to select the alternative pinout since this
pinout is routed to the external headers.

Update ATSTK1002 and ATSTK1004 to use the new interface.
Signed-off-by: NHans-Christian Egtvedt <hcegtvedt@atmel.com>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

On the odd chance some code uses a pin as a GPIO IRQ without calling
gpio_request() or gpio_direction_input(), the debug dump should still
show its pin status.
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

__raw_readsb() should always use byte accesses, never halfword accesses,
to I/O memory.
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

A signal handler should be able to change the signal stack used for the
next signal by altering the ucontext_t passed as a parameter to the
handler. This does not currently work on avr32 since it doesn't update
the in-kernel signal context from the ucontext_t upon signal handler
return.

Fix it by adding a call to do_sigaltstack() from sys_rt_sigreturn(),
bringing it in line with most other architectures.
Signed-off-by: NMartin Koegler <mkoegler@auto.tuwien.ac.at>
[haavard.skinnemoen@atmel.com: changed patch description]
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

On our custom board we have other oscillator rates than on atngw100 and
atstk100x.

Currently these rates are hardcoded in arch/avr32/mach-at32ap/at32ap700x.c.

This patch moves them into board specific code.
Signed-off-by: NAlex Raimondi <raimondi@miromico.ch>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

Fixes one of two ext4 build problems:
ERROR: "empty_zero_page" [fs/ext4/ext4dev.ko] undefined!
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

Move the AP7 cpufreq init to late_initcall() so that we don't try to
bring up cpufreq until the governor is ready. x86 also uses
late_initcall() for this.
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

Just provide reasonable defaults for the new stuff. Tickless and
hrtimers are turned on for all boards except ATSTK1004.
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

This patch fixes the following build error:

<--  snip  -->

...
  MODPOST 1327 modules
ERROR: "strnlen_user" [drivers/input/misc/uinput.ko] undefined!
...
make[2]: *** [__modpost] Error 1

<--  snip  -->
Reported-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

This patch fixes the following build error:

<--  snip  -->

...
  MODPOST 61 modules
ERROR: "copy_page" [fs/fuse/fuse.ko] undefined!
...
make[2]: *** [__modpost] Error 1

<--  snip  -->

Also add an empty line since *_page aren't "String functions".
Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

Signed-off-by: NJan Beulich <jbeulich@novell.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

This replaces the duplicated arch-specific versions of "sys_pipe()" with
one unified implementation.  This removes almost 250 lines of duplicated
code.

It's marked __weak, so that *if* an architecture wants to override the
default implementation it can do so by simply having its own replacement
version, since many architectures use alternate calling conventions for
the 'pipe()' system call for legacy reasons (ie traditional UNIX
implementations often return the two file descriptors in registers)

I still haven't changed the cris version even though Linus says the BKL
isn't needed.  The arch maintainer can easily do it if there are really
no obstacles.
Signed-off-by: NUlrich Drepper <drepper@redhat.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Cc: Haavard Skinnemoen <hskinnemoen@atmel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Use proc_create() to make sure that ->proc_fops be setup before gluing PDE to
main tree.
Signed-off-by: NDenis V. Lunev <den@openvz.org>
Cc: Haavard Skinnemoen <hskinnemoen@atmel.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

If the user specified a fixed framebuffer address on the command line, it may
have been initialized already with a splash image or something, so we
shouldn't clear it.

Therefore, we should only initialize the framebuffer if we allocated it
ourselves.  This patch also updates the AVR32 setup code to clear the
framebuffer if it allocated it itself, i.e.  the user didn't provide a fixed
address or the reservation failed.

I've updated the at91 platform code as well so that it initializes the
framebuffer if it is located in SRAM, but I haven't tested that it actually
works.
Signed-off-by: NHaavard Skinnemoen <hskinnemoen@atmel.com>
Cc: "Antonino A. Daplas" <adaplas@pol.net>
Cc: Nicolas FERRE <nicolas.ferre@rfo.atmel.com>
Cc: Andrew Victor <andrew@sanpeople.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch adds in the indirect call to pm_power_off(), as is done in
other architectures (e.g. ARM).

Tested on NGW100, with custom board with GPIO control over main DC
power.
Signed-off-by: NPeter Ma <pma@mediamatech.com>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

Signed-off-by: NJohannes Weiner <hannes@saeurebad.de>
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>