Remove unneeded 'struct davinci_clk' wrapper around 'struct
clk_lookup' and use clk_lookup directly.
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Remove unneeded 'struct davinci_clk' wrapper around 'struct clk_lookup'
and use clkdev_add_table() to add the list of clocks in one go.
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch adds the generic Voice Codec support for the DM365 based
platforms.
Signed-off-by: NMiguel Aguilar <miguel.aguilar@ridgerun.com>
Acked-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

When supporting I2C/SPI based on-board PLLs like CDCE949,
it is essential that clk->set_rate be able to sleep.

Currently, this is not possible because clk->set_rate is
called from within spin-lock in clk_set_rate

This patch brings clk->set_rate outside of the spin-lock
and lets the individual set_rate implementations achieve
serialization through appropiate means.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Patch adds SDA and SCL pin numbers to the i2c platform data
structure for Davinci DM355 and DM6446. This at present is
used for i2c bus recovery.
TODO: Add SDA and SCL pin number information to include all
Davinci platforms such as dm355-leopard, dm365, dm646x, da8xx etc.
Signed-off-by: NPhilby John <pjohn@in.mvista.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Currently da850/omap-l138 supports only one channel controller
instance of EDMA though EDMA driver as such supports multiple
channel controller instances. This patch adds platform data
for the 2nd EDMA channel controller. As, the platform data
differ between da830/omap-l137 and da850/omap-l138, existing
code has been re-shuffled to accommodate this.
Signed-off-by: NSudhakar Rajashekhara <sudhakar.raj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Currently, the edma_noevent list is passed from platform data.
But on some architectures, there will be many EDMA channels
which will not be used at all. This patch scans all the
platform devices and then builds a list of events which are
not being used. The unused event list will be used to allocate
EDMA channels in case of EDMA_CHANNEL_ANY usage instead of the
edma_noevent being used earlier for this purpose.

This patch is based on David Brownells's suggestion at
http://article.gmane.org/gmane.linux.davinci/15176.
Signed-off-by: NSudhakar Rajashekhara <sudhakar.raj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Though edma_alloc_channel api was looping through the available
channel controllers in EDMA_CHANNEL_ANY case, it was never
returning the channel for 2nd channel controller, if 1st
channel controller had no free channels. This issue has
been fixed with this patch.
Signed-off-by: NSudhakar Rajashekhara <sudhakar.raj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Some architectures have only one channel controller, but the
edma_alloc_channel api loops twice to findout the free channel
available in EDMA_CHANNEL_ANY case. A new variable has been
introduced to keep count of number of channel controllers being
used on a particular architecture.
Signed-off-by: NSudhakar Rajashekhara <sudhakar.raj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Currently, edma_alloc_channel api is returning the channel
number without prepending the controller on which the
channel was allocated. So, if a channel is allocated on
2nd controller, calls subsequent to edma_alloc_channel would
never know that channel was allocated on the 2nd controller,
and continue to operate on 1st controller, resulting in edma
failure. This patch fixes this issue.
Signed-off-by: NSudhakar Rajashekhara <sudhakar.raj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch adds the CDCE949 reference oscillator to
the davinci clock list.

On the DM6467T EVM, the CDCE949 is responsible for
generating the pixel clock for display. On the DM6467
EVM, this pixel clock was being obtained from an
internal source. This is not possible on the DM6467T
EVM because of the presence of a 33MHz oscillator.

The TSIF module also requires the CDCE949 to generate
the data clocks.

The actual clock definitions will be added by patches
adding support for DM6467T VPIF and TSIF. This patch
mearly lays the foundation for that work.
Signed-off-by: NNageswari Srinivasan <nageswari@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch adds support for TI's CDCE949 - a clock
synthesizer with 4 PLLs and 9 outputs.

It is used on DM6467 EVM. On the EVM, it generates
clocks required for VPIF, TSIF and Audio modules.

This patch adds it as part of the DaVinci clock framework.

Testing:
The various frequency outputs on Y1 have been tested using
a out-of-tree VPIF video driver supporting HD video.
The register values for Y5 frequency outputs have been
derived from TSIF driver sources in MontaVista LSP kernel,
but actual output has not been tested for lack of TSIF
driver which actually works on the latest kernel.
Signed-off-by: NNageswari Srinivasan <nageswari@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch adds support for registering for suspend-to-RAM
functionality on da850/omap-l138 SoCs.

da850 supports wakeup based on external event and RTC
alarm.

Currently only RTC alarm based wakeup is supported.
Support for wakeup based on external event will be
added as later improvements.

For scheduling an alarm event on RTC some useful code
is present in Documentation/rtc.txt
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch adds core power management (suspend-to-RAM)
support for DaVinci SoCs.

The code depends on the the "deepsleep" feature to suspend
the SoC and saves power by gating the input clock.

The wakeup can be based on an external event as supported
by the SoC.

Assembly code (in sleep.S) is added to aid gating DDR2
clocks. Code doing this work should not be accessing DDR2.
The assembly code is relocated to SRAM by the code in pm.c

The support has been validated on DA850/OMAP-L138 only
though the code is (hopefully) generic enough that other
SoCs supporting deepsleep feature simply requires SoC
specific code to start using this driver.

Note that all the device drivers don't support suspend/resume
still and are being worked on.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

In DM365 Q0, Q1 and Q2 are used by codecs.
LSP drivers should use Q3.
This patch changes the default queue for DM365.
Signed-off-by: NSandeep Paulraj <s-paulraj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Some modules do not have PSC to control their clocks.
The 'lpsc' field in the clk structure is 0 for such clocks.

In the clock disable function check for CLK PSC flag before
disabling the PSC. If this is not taken care of then it may
so happen that module controlled by LPSC 0 is erroneously disabled.
Signed-off-by: NChaithrika U S <chaithrika@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

When programming the DMA engine, the next pointers must be
programmed with physical address as seen from the DMA master
address space. This address may be different from physical
address of the buffer RAM area. This patch abstracts the
buffer address translation logic.
Signed-off-by: NSriramakrishnan <srk@ti.com>
Acked-by: NChaithrika U S <chaithrika@ti.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

On certain SOCs, the EMAC controller is interfaced with a wrapper logic
for handling interrupts. This  patch implements a platform
specific hook to cater to platforms that require custom interrupt
handling logic
Signed-off-by: NSriramakrishnan <srk@ti.com>
Acked-by: NChaithrika U S <chaithrika@ti.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

The davinci EMAC peripheral is also available on other TI
platforms -notably TI AM3517 SoC. This patch modifies the
config option and the platform structure header files so that
the driver can be reused on non-davinci platforms as well.
Signed-off-by: NSriramakrishnan <srk@ti.com>
Acked-by: NChaithrika U S <chaithrika@ti.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch initializes the platform data to enable 4-bit
ecc support on DA850/OMAP-L138.
Signed-off-by: NSudhakar Rajashekhara <sudhakar.raj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

On DA850/OMAP-L138, NOR flash partition was starting from offset
ZERO erasing the UBL and u-boot when the complete NOR is erased.
This patch moves the start of the partition to 512K, after the
bootloaders and u-boot env variables.

This patch also creates a new partition on NOR Flash to store
Linux kernel image.
Signed-off-by: NSudhakar Rajashekhara <sudhakar.raj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Move /proc/davinci_clocks to /sys/kernel/debug/davinci_clocks
(debugfs).

debugfs is more suited for this since the clock dump is
debug information.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch modifies clock dump to take care of
clock tress rooted at multiple oscillators.
Current code assumes the entire tree is rooted
on a single oscillator. When using off-chip
clock synthesizers, some of the clocks can
be obtained from a different on-board oscillator.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

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>

asic3 also needs tmio_core or otherwise will fail to build.
Signed-off-by: NDmitry Artamonow <mad_soft@inbox.ru>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
  Input: update multi-touch protocol documentation
  Input: add the ABS_MT_PRESSURE event
  Input: winbond-cir - remove dmesg spam
  Input: lifebook - add another Lifebook DMI signature
  Input: ad7879 - support auxiliary GPIOs via gpiolib

After memory pressure has forced it to dip into the reserves, 2.6.32's
5f8dcc21 "page-allocator: split per-cpu
list into one-list-per-migrate-type" has been returning MIGRATE_RESERVE
pages to the MIGRATE_MOVABLE free_list: in some sense depleting reserves.

Fix that in the most straightforward way (which, considering the overheads
of alternative approaches, is Mel's preference): the right migratetype is
already in page_private(page), but free_pcppages_bulk() wasn't using it.

How did this bug show up?  As a 20% slowdown in my tmpfs loop kbuild
swapping tests, on PowerMac G5 with SLUB allocator.  Bisecting to that
commit was easy, but explaining the magnitude of the slowdown not easy.

The same effect appears, but much less markedly, with SLAB, and even
less markedly on other machines (the PowerMac divides into fewer zones
than x86, I think that may be a factor).  We guess that lumpy reclaim
of short-lived high-order pages is implicated in some way, and probably
this bug has been tickling a poor decision somewhere in page reclaim.

But instrumentation hasn't told me much, I've run out of time and
imagination to determine exactly what's going on, and shouldn't hold up
the fix any longer: it's valid, and might even fix other misbehaviours.
Signed-off-by: NHugh Dickins <hugh.dickins@tiscali.co.uk>
Acked-by: NMel Gorman <mel@csn.ul.ie>
Cc: stable@kernel.org
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>