DM6467T (T for Turbo) is a newer and faster DM6467
part from TI. The new part supports 1080p video and
has the ARM running at 495MHz. More SoC information:

http://focus.ti.com/docs/prod/folders/print/tms320dm6467t.html

Spectrum Digital, Inc has a new EVM for this part.
It is _mostly_ same as the older DM6467 EVM except
for a 33MHz crystal input and THS8200 video encoder
for 1080p support.

The meat of this patch is dedicated to initializing
the crystal frequency from EVM board file.

Additional notes:
I did consider some alternative ways to make the crystal
input board specific including - (1) having board code
initialize the crystal frequency using the first member
of soc_info->cpu_clks array (2) introducing a new ref_clk_rate
member in soc_info structure.

But, the current way seems to be the simplest and least
intruding considering that both the clock array and SoC
info structure are actually private to the SoC file. Also
the fact that davinci_common_init() initializes both the
soc_info and clocks in one go.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Currently all the #defines and static variables in the
board-dm646x-evm.c file are located right at the start
of the file because of which the related code is not
together - making reading the code difficult.

This patch moves around the code keeping related code
together.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Leave a comment explaining the constant value of 27Mhz used
in include/mach/timex.h for all DaVinci platforms. Many of
the platforms actually run at 24MHz timer frequency (Eg.
EVMs of DM355, DM365 and OMAP-L1).

The comment also serves as a porting alert.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Create static map for internal SRAM and populate SRAM base
and size in soc_info structure to allow SRAM allocation
functions from arch/arm/mach-davinci/sram.c to work.

On DA850 SRAM is used for suspend-to-RAM implementation
in places where DDR2 cannot be accessed as its clocks are
stopped.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

On omap-l1 devices the PLL registers can be locked from
writes. Currently the cpufreq rate setting code unlocks
PLL0 before the write actually happens. With suspend
support getting added PLL1 registers need be be unlocked
as well.

To facilitate this, unlock both PLLs during the init time
itself.

This also obviates the need to unlock PLL registers for
each CPUFreq transtition.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

When suspend is supported, both cpuidle and suspend code
need to work on DDR2 registers. Instead of mapping the
DDR2 registers twice, do it once outside of cpuidle
driver and let cpuidle driver get the virtual base address
of DDR2 registers.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

psc.h contains register defines for PSC module which
need to be accessed in assembly code which helps the
DA850/OMAP-L138 SoC go to sleep. Shutting down DDR clock
using PSC is a part of the sleep procedure.

Also, the PLL related hardware definitions in clock.h are
needed in assembly code to bypass the DDR2 PLL.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

The motivation behind the change is to use the same
definitions in the assembly code responsible for
suspending the SoC, a part of which is to clock gate
the DDR2 clock.

Note that the assembly code cannot invoke the C function
meant for this. The main reason being that stack in DDR2
cannot be accessed while DDR2 clock is being clock gated.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Move defintions of DDR2 controller registers to memory.h
from cpuidle.c. The motivation behind the change is to be
able to use these defintions in assembly code that puts
DDR2 in self-refresh and enables the SoC to enter suspend
state.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

As suspend support is added, the code supporting
the suspend operation needs to bypass PLLs and
needs to access the same wait time values as the
PLL code in clock.c.

To facilitate this, move the PLL wait times to
clock.h where they can be accessed by suspend code.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

OMAP-L138 adds a second SYSCFG region having useful functionality
like deep sleep, pull up/down control and SATA clock stop.

This patch makes provision for accessing registers from second
SYSCFG region in da8xx code.

Note that OMAP-L137 has a single SYSCFG region.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch adds following changes:-
	1) add sub device configuration data for TVP5146 used by vpfe capture
	2) registers platform devices for vpfe_capture, isif and vpss
	3) defines hardware resources for the devices listed under 2)
	4) defines clock aliase for isif driver
	5) adding setup_pinmux() for isif
Signed-off-by: NMurali Karicheri <m-karicheri2@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This patch fixes power LED blinking and power-off on DNS-323 rev. B1.

GPIO pin 3 has to be set to 1 to stop power LED blinking and to allow the LED to be controlled via leds-gpio. This pin has to be also set to 1 for power-off to work.
To power-off the rev. B1 machine, pin 8 has to be set to 1 and then set to 0 to do actual power-off.

Tested on my DNS-323 rev. B1
Signed-off-by: NErik Benada <erikbenada@yahoo.ca>
Signed-off-by: NNicolas Pitre <nico@marvell.com>

OMAP GP timers keep running for a few cycles after they are stopped,
which can cause the timer to expire and generate an interrupt. The
pending interrupt will prevent e.g. OMAP from entering suspend, thus
we ack it manually.  Only applicable on OMAP2/3/4.
Signed-off-by: NTero Kristo <tero.kristo@nokia.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>
Signed-off-by: NTony Lindgren <tony@atomide.com>

Commit cfc38999f (backlight: Pass device through notify callback)
added a struct device argument to the notify callback, but didn't
update the user of it in mach-hmt.c
Signed-off-by: NPeter Korsgaard <jacmet@sunsite.dk>
Signed-off-by: NBen Dooks <ben-linux@fluff.org>

Fix following warning when CONFIG_DEBUG_FS wasn't selected:

arch/arm/mach-omap2/pm-debug.c:57: warning: 'pm_dbg_init' declared 'static' but never defined
Signed-off-by: NSergio Aguirre <saaguirre@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Currently, DSS does not wakeup when there is a DMA request.  DSS wake
up event must be enabled so that the DMA request to refill the FIFO
will wake up the CORE domain.
Signed-off-by: NSubramani Venkatesh <subramani.venkatesh@windriver.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

During suspend, the kernel timekeeping subsystem is shut down.  Before
suspend and upon resume, it uses a weak function
read_persistent_clock() to determine the amount of time that elapsed
during suspend.

This function was not implemented on OMAP, so from the timekeeping
subsystem perspective (and thus userspace as well) it appeared that no
time elapsed during suspend.

This patch uses the 32k sync timer as a the persistent clock.

NOTE: This does *NOT* fully handle wrapping of the 32k sync timer, so
      more than one wrapping of the 32k sync timer during suspend may
      cause problems.  Also note there are not interrupts when the 32k
      sync timer wraps, so something else has to be done.
Reported-by: NJon Hunter <jon-hunter@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Due to OMAP3 erratas 1.157, 1.185 the save of the last pad register
(ETK_D14 and ETK_D15) can fail sometimes when there is simultaneous
OCP access to the SCM register area. Fixed by writing the last
register to the save area.

Also, optimized the delay loop for the HW save to include an udelay(1),
which limits the number of unnecessary HW accesses to SCM register area
during the save.
Signed-off-by: NTero Kristo <tero.kristo@nokia.com>
Acked-by: NNishanth Menon <nm@ti.com>
Reviewed-by: NAnand Gadiyar <gadiyar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

val is an u64 pointer, we need an int to check the error.
Signed-off-by: NRoel Kluin <roel.kluin@gmail.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Wake-up from McBSP ports are needed, especially when the THRESHOLD
dma mode is in use for audio playback.
Signed-off-by: NPeter Ujfalusi <peter.ujfalusi@nokia.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

The PM debug code fails to build on when CONFIG_DEBUG_FS is not
enabled.

Build error log:
arch/arm/mach-omap2/built-in.o: In function `omap_sram_idle':
arch/arm/mach-omap2/pm34xx.c:449: undefined reference to `pm_dbg_regset_save'
arch/arm/mach-omap2/pm34xx.c:460: undefined reference to `pm_dbg_regset_save'
arch/arm/mach-omap2/built-in.o: In function `configure_vc':
arch/arm/mach-omap2/pm34xx.c:1237: undefined reference to `pm_dbg_regset_init'
arch/arm/mach-omap2/pm34xx.c:1238: undefined reference to `pm_dbg_regset_init'
make: *** [.tmp_vmlinux1] Error 1

This patch fixes the above errors.

Kernel booting is tested on omap zoom2 and zoom3 boards.
Signed-off-by: NManjunatha GK <manjugk@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

As part of Core domain context restoration while coming out of off mode
there are some registers being restored which are not required to be restored.
ROM code will have restored them already. Overwriting some of them can have
potential side effect. Eg: CM_CLKEN_PLL register should not be written while dpll is locked.
Tested on OMAP 3430 SDP for suspend/resume and off mode with sleep_while_idle enabled.
Signed-off-by: NVishwanath BS <vishwanath.bs@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Current value is stored on SDRAM and it is written back during wakeup.
Previously a static value of 0x72 was written there.
Signed-off-by: NTero Kristo <tero.kristo@nokia.com>
Acked-by: NThara Gopinath <thara@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Previously used u32 as temporary data storage that wraps around at 4.294s.
Signed-off-by: NTero Kristo <tero.kristo@nokia.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch removes code blocks that are repeated
in function prcm_setup_regs().
Signed-off-by: NSanjeev Premi <premi@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

OMAP interrupt controller goes to unknown state when there is right
combination of l3,l4 sleep/wake-up transitions, l4 autoidle in
interrupt controller and some interrupt. When this happens, interrupts
are not delivered to ARM anymore and ARM will remain in WFI (wait for
interrupt) until interrupt controller is forced to wake-up
(i.e. lauterbach).
Signed-off-by: NTero Kristo <tero.kristo@nokia.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Enable the auto-idle feature of the SCM block to save some additional
power.
Signed-off-by: NMika Westerberg <ext-mika.1.westerberg@nokia.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Suspending drivers may still generate interrupts just before their suspend is
completed. Any pending interrupts here will prevent sleep.
Signed-off-by: NTero Kristo <tero.kristo@nokia.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Don't assume that gpmc_l3_clk is on, enable it before touching
configuration registers.

Note that the current code assumes that this clock is always
enabled. We are already setting smart idle and L3 autogating
for GPMC clock in gpmc_init.
Signed-off-by: NOlof Johansson <olof@lixom.net>
Signed-off-by: NTony Lindgren <tony@atomide.com>

Commit 52650505 caused clock initialization
to fail on OMAP1 with "BUG: spinlock lockup on CPU#0" -- this is because
omap1_select_table_rate() and omap1_round_to_table_rate() call clk_get_rate()
with the clockfw spinlock held.  Fix by accessing the rate directly from
the internal clock framework functions.

Thanks to Tony Lindgren <tony@atomide.com> for reporting and testing the fix.
Signed-off-by: NPaul Walmsley <paul@pwsan.com>
Cc: Tony Lindgren <tony@atomide.com>

For all DPLL's the valid dividers are same as the values
to be programmed in the register. 0 is an invalid value.
The changes are generated by updating the script which autogenerates
the file modifed in the patch.
Signed-off-by: NRajendra Nayak <rnayak@ti.com>
Signed-off-by: NPaul Walmsley <paul@pwsan.com>

The CHIRONSS has its own local PRCM module and the register defines
need to use the CHIRONSS base and not the PRM base.
The changes are generated by updating the script which autogenerates
the file modifed in the patch.
Signed-off-by: NRajendra Nayak <rnayak@ti.com>
Signed-off-by: NPaul Walmsley <paul@pwsan.com>

The same flag and bits were tested twice.
Signed-off-by: NRoel Kluin <roel.kluin@gmail.com>
Signed-off-by: NTony Lindgren <tony@atomide.com>

We need to set the omap_chip.oc carefully for the clocks to work.

To fix this, set the omap_chip.oc in omap3_check_features() based
on the CONTROL_IDCODE and silicon revision registers.

Also add handling for 34xx es3.1.2 as es3.1 for now.

Fixes booting on at least overo board.

Based on an earlier patch by Paul Walmsley <paul@pwsan.com>.
Signed-off-by: NPaul Walmsley <paul@pwsan.com>
Signed-off-by: NTony Lindgren <tony@atomide.com>

Make the omap_mux_read and write available for board code,
and rename omap_mux_set_board_signals into omap_mux_write_array.
Also add the related prototypes and comments into mux.h.

In some cases we want to change the signals dynamically,
mostly for power management.

Note that we cannot use the signal names as they are set
__init to save memory.
Signed-off-by: NTony Lindgren <tony@atomide.com>

Looks like cmdline muxing got broken at some point when we
decided to limit muxing to __init code. Currently omap_mux_entry
list is not yet initialized when we try to initialize cmdline
muxing.

Fix this by calling omap_mux_init_list() before calling
omap_mux_set_cmdline_signals().
Reported-by: NPhilip Balister <philip@balister.org>
Tested-by: NPhilip Balister <philip@balister.org>
Signed-off-by: NTony Lindgren <tony@atomide.com>

The first thing that omap2_init_clksel_parent() does is check for
a non-zero .clksel field in the struct clk.  Therefore, it is
pointless calling this function on clocks where the clksel field
is unset.

Remove init calls to omap2_init_clksel_parent() on clocks without
a clksel field.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: NPaul Walmsley <paul@pwsan.com>

In the current implementation the sysconfig value is read into
 _sysc_cache once and an actual update to the sysconfig register
happens only if the new value paased is differnt from the one in _sysc_cache.
_sysc_cache is updated only if _HWMOD_SYSCONFIG_LOADED is not set.
This can lead to the follwing issue if off mode is enabled in modules
which employs "always-retore" mechanism of context save and restore.

        a. The module sets the sysconfig register through omap_device_enable.
           Here _sysc_cache is updated with the value written to the sysconfig
           register and left.
        b. The power domain containig the module enters off mode and the
           module context is lost.
        c. The module in use becomes active and calls omap_device_enable to
           enable itself. Here a read of sysconfig register does not happen
           as _HWMOD_SYSCONFIG_LOADED flag is set. The value to be written
           to the sysconfig register will be same as the one written in step a.
           Since _sysc_cache reflects the previous written value an update
           of the sysconfig register does not happen.
This means in modules which employs "always-restore" mechanism
after off , the sysconfig regsiters will never get updated.

This patch introduces a flag SYSC_NO_CACHE which if set ensures that the
sysconfig register is always read into _sysc_cache before an update is
attempted.

This flags need to be set only by modules which does not do a context save
but re-initializes the registers every time the module is accessed. This
includes modules like i2c, smartreflex etc.
Signed-off-by: NThara Gopinath <thara@ti.com>
[paul@pwsan.com: tweaked to apply on a different head, added flag comment]
Signed-off-by: NPaul Walmsley <paul@pwsan.com>