This patch modifies the EDMA driver to expect the channel
controller (CC) infomation passed on by the platform as a fixed
size (EDMA_MAX_CC) array of pointers to structures.

Doing so helps catch errors of the sort where the resource
structure has information for more channel controllers than
the number channel controller info structures defined.

Such insufficient platform data would lead to illegal memory
accesses.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch helps get rid of the following sparse warnings
of the type:

  CHECK   arch/arm/mach-davinci/da830.c
arch/arm/mach-davinci/da830.c:1026:3: warning: Initializer entry defined twice
arch/arm/mach-davinci/da830.c:1027:3:   also defined here

coming from the irq priorities array init.

Apart from one instance of genuinie repetition, most are are instances
of multiple #defines of the same interrupt number. I have not
removed the multiple definitions from the irq.h file in the hope
that someone might decide to use them as shared interrupts at some
point of time. The priority initialization however needs to be done
only once and hence has been corrected.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

The register base address for the second serial port (UART1) was
wrong.
Signed-off-by: NThomas Koeller <thomas.koeller@baslerweb.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Added support for tnetv107x evaluation module.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch adds support for the tnetv107x gpio controller.

Key differences between davinci and tnetv107x controllers:
 - register map - davinci's controller is organized into banks of 32 gpios,
   tnetv107x has a single space with arrays of registers for in, out,
   direction, etc.
 - davinci's controller has separate set/clear registers for output, tnetv107x
   has a single direct mapped register.

This patch does not yet add gpio irq support on this controller.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

TNETV107X is a Texas Instruments SOC that shares a number of common features
with the Davinci architecture.  Some of the key differences between
traditional Davincis and this new SOC are as follow:

1. The SOCs clock architecture includes a new spread-spectrum PLL.  Some
elements of the clock architecture are reused from Davinci (e.g. LPSC), but
the PLL related code is overridden using existing interfaces in "struct clk".

2. The MMR layout on this SOC is substantially different from Davinci.
Consequently, the fixed I/O map is a whole lot more convoluted (more so than
DA8xx).  The net impact here is that IO_ADDRESS() will not work on this SoC,
and therefore all mappings have to be through ioremap().
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Added definitions for tnetv107x uart base addresses, and modified base address
selection for kernel decompressor to check for tnetv107x machine type.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch adopts a debug uart selection similar to the OMAP model.  During
the boot process, the uncompress code determines the physical and virtual base
addresses of the board-specific debug uart.  These addresses are then passed
on to the in-kernel debug macros through a small chunk of memory placed just
below the page tables (@0x80003ff8).
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

The touch screen controller in the TPS6507x chip needs values that are
dependent on the characteristics of the touch screen hardware being used
in the board design.  In addition, the board provides version information
that is exposed via the kernel input sub-system.
Signed-off-by: NTodd Fischer <todd.fischer@ridgerun.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Add mfd structure which refrences sub-driver initialization data. For example,
for a giving hardware implementation, the voltage regulator sub-driver
initialization data provides the mapping betten a voltage regulator and what
the output voltage is being used for.
Signed-off-by: NTodd Fischer <todd.fischer@ridgerun.com>
Acked-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: NLiam Girdwood <lrg@slimlogic.co.uk>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

On some platforms like DM355, the number of EDMA parameter slots available
for EDMA_SLOT_ANY usage are few.  In such cases, if MMC/SD uses 16 slots
for each instance of MMC controller, then the number of slots available
for other modules will be very few.

By passing the number of EDMA slots to be used in MMC driver from platform
data, EDMA slots available for other purposes can be controlled.

Most of the platforms will not use this platform data variable.  But on
DM355, as the number of EDMA resources available is limited, the number of
scatter- gather segments used inside the MMC driver can be 8 (passed as
platform data) instead of 16.  On DM355, when the number of scatter-gather
segments was reduced to 8, I saw a performance difference of about
0.25-0.4 Mbytes/sec during write.  Read performance variations were
negligible.
Signed-off-by: NSudhakar Rajashekhara <sudhakar.raj@ti.com>
Acked-by: NKevin Hilman <khilman@deeprootsystems.com>
Cc: <linux-mmc@vger.kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

DA8xx OHCI driver fails to load due to failing clk_get() call for the USB 2.0
clock. Arrange matching USB 2.0 clock by the clock name instead of the device.
(Adding another CLK() entry for "ohci.0" device won't do -- in the future I'll
also have to enable USB 2.0 clock to configure CPPI 4.1 module, in which case
I won't have any device at all.)
Signed-off-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

More complete AEMIF support for boards.
Signed-off-by: NThomas Koeller <thomas.koeller@baslerweb.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Added PINMUX configurations for the CLKOUT0 .. CLKOUT2
functions, for boards that want to use these clocks.
Signed-off-by: NThomas Koeller <thomas.koeller@baslerweb.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Board code may want to use them.
Signed-off-by: NThomas Koeller <thomas.koeller@baslerweb.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch allows for a more flexible ioremap() interception based on iotable
contents.

With this patch, the ioremap() interception code can properly translate
addresses only after davinci_soc_info has been initialized.  Consequently,
in soc-specific init functions, davinci_common_init() has to happen before any
ioremap() attempts. The da8xx init sequence has been suitably modified to meet
this restriction.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch modifies the pinmux implementation so as to ioremap() the pinmux
register area on first use.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch implements the following:

 - interrupt initialization uses ioremap() instead of passing a virtual address
   via davinci_soc_info.

 - machine definitions directly point to cp_intc_init() or davinci_irq_init()

 - davinci_intc_type and davinci_intc_base now get initialized in controller
   specific init functions instead of davinci_common_init()

 - minor fix in davinci_irq_init() to use intc_irq_num instead of
   DAVINCI_N_AINTC_IRQ
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch modifies the psc and clock control code to use ioremap()ed
registers.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch eliminates IO_ADDRESS() usage for Davinci timer definitions.  The
timer code has correspondingly been modified to ioremap() MMRs instead.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch replaces the jtag id base info in davinci_soc_info with a physical
address which is then ioremap()ed within common code.

This patch (in combination with a similar change for PSC) will allow us to
eliminate the SYSCFG nastiness in DA8xx code.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch modifies the RTC unlock code to use ioremap() maps instead of
IO_ADDRESS() translation.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch modifies the gpio_base definition in davinci_soc_info to be a
physical address, which is then ioremap()ed by the gpio initialization
function.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

In the edma driver, most of the long lines in 'if condition' are
broken after the logical operator '&&' except two instances.

This patch fixes that to bring consistency across the file.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch replaces occurences of (1 << x) with
BIT(x) as it makes for much better reading.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

In the edma driver, there are couple of instances where braces
are used for a single statement 'if' construct.

There are other instances where 'else' part of the if-else construct
does not use braces even if the 'if' part is a multi-line statement.

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

'edma_info' structure inside the edma driver represents
a single instance of edma channel controller. Call it
'edma_cc' instead. This also avoids readers confusing
it with an instance of edma_soc_info structre which
carries the platform data for a single channel controller
instance.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

With this patch, AR7 type uart ports are not reset via pwremu registers.  This
allows davinci_serial_init() reuse on tnetv107x soc.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch implements davinci serial cleanups towards having this code
reusable on tnetv107x.

The change reuses the platform data membase field to hold the remapped space.
By disabling the UPF_IOREMAP flag in the platform data, we prevent
the 8250 driver from repeating the ioremap.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

The uart pdata array is already terminated by a zero flag field.

This patch reuses this terminator and eliminates DAVINCI_MAX_NR_UARTS
definition.  This way, future platforms can have different number of uarts
initialized via davinci_serial_init().
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

The earlier watchdog reset mechanism had a couple of limitations.  First, it
embedded a reference to "davinci_wdt_device" inside common code.  This
forced all derived platforms (da8xx and tnetv107x) to define such a device.
This also would have caused problems in including multiple socs in a single
build due to symbol redefinition.

With this patch, davinci_watchdog_reset() now takes the platform device as an
argument.  The davinci_soc_info struct has been extended to include a reset
function and a watchdog platform_device.  arch_reset() then uses these
elements to reset the system in a SoC specific fashion.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Tested-by: NSandeep Paulraj <s-paulraj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Pinmux registers are sequential, and do not need to be enumerated out as they
currently are.  This reduces code volume and keeps things simple.

If some future SoC comes up with a discontiguous register map, PINMUX() can
then be expanded with local token pasting.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch eliminates the global gpio_lock, and implements a per-controller
lock instead.  This also switches to irqsave/irqrestore locks in case gpios
are manipulated in isr.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Tested-by: NSandeep Paulraj <s-paulraj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch allows for gpio controllers that deviate from those found on
traditional davinci socs.  davinci_soc_info has an added field to indicate the
soc-specific gpio controller type.  The gpio initialization code then bails
out if necessary.

More elements (tnetv107x) to be added later into enum davinci_gpio_type.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Tested-by: NSandeep Paulraj <s-paulraj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch renders the inlined gpio accessors in gpio.h independent of the
underlying controller's register layout.  This is done by including three new
fields in davinci_gpio_controller to hold the addresses of the set, clear, and
in data registers.

Other changes:

1. davinci_gpio_regs structure definition moved to gpio.c.  This structure is
no longer common across all davinci socs (davinci_gpio_controller is).

2. controller base address calculation code (gpio2controller()) moved to
gpio.c as this was no longer necessary for the inline implementation.

3. modified inline range checks to use davinci_soc_info.gpio_num instead of
DAVINCI_N_GPIO.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Tested-by: NSandeep Paulraj <s-paulraj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Renamed gpio types to something more sensible:
	struct gpio_controller	--> struct davinci_gpio_regs
	struct davinci_gpio	--> struct davinci_gpio_controller
	gpio2controller()	--> gpio2regs()
	irq2controller()	--> irq2regs()

This change also moves davinci_gpio_controller definition to gpio.h.
Eventually, the gpio registers structure will be moved to gpio.c and no longer
a common cross-soc definition.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Tested-by: NSandeep Paulraj <s-paulraj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

macroized repeated container_of()s to improve readability.
unified direction in/out functions.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Tested-by: NSandeep Paulraj <s-paulraj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

The IDE platform device is registered in three different places (2 board files
for DM644x and in dm646x.c for DM646x) while both the IDE base address and the
IDE IRQ are the same for both SoCs -- therefore,  the proper place for the IDE
platform seems to be in devices.c. Merge the IDE platform data and registration
code and create davinci_init_ide() in place of dm646x_init_ide()...
Signed-off-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

linux/compiler.h is required for __iomem
linux/types.h is required u32
Signed-off-by: NThomas Koeller <thomas.koeller@baslerweb.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch allows socs to override the divider ratio mask by setting an
optional field (div_ratio_mask) in the pll_data structure.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Tested-by: NSandeep Paulraj <s-paulraj@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>