The interrupt can be used for error recovery.
Signed-off-by: NPeter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

McASP1 TX interrupt is 30, not 32 on DM646x DMSoC.

While at it remove the bogus AEMIF interrupt entry from
dm646x_default_priorities[]. AEMIF interrupt on DM6467 is
60 not 30 and the entry for the correct interrupt number
is already present in the same table.
Signed-off-by: NPeter Ujfalusi <peter.ujfalusi@ti.com>
[nsekhar@ti.com: remove bogus entry from dm646x_default_priorities[]]
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

Add names to the DMA resources and remove the RX DMA dummy part for McASP1.
Signed-off-by: NPeter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

The following parameters are no longer needed by the edma driver since the
information can be obtained from the IP's CCCFG register:
n_channel, n_region, n_slot and n_tc.
Remove the initialization of n_cc as well since in this context it has no
meaning. We have separate edma_soc_info struct/eDMA3_CC instance so this
member does not make any sense (and the driver no longer uses it).
Signed-off-by: NPeter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

It is ignored by the edma driver since we are just setting back the default
mapping of TC -> Queue.
Signed-off-by: NPeter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

Fix multiple watchdog device registration on da8xx devices
due to davinci_init_devices blindly registering watchdog
device.

Fix this by getting rid of the initcall and instead registering
watchdog for each soc.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

As we switch to use the watchdog core which permits more than one
active watchdog in the system, rename platform driver to
"davinci-wdt" to be identifiable.
Acked-by: NWim Van Sebroeck <wim@iguana.be>
Reviewed-by: NGuenter Roeck <linux@roeck-us.net>
Signed-off-by: NIvan Khoronzhuk <ivan.khoronzhuk@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

As the davinci-gpio driver is migrated to use irqdomain
there is no need to pass the irq base for the gpio driver.
This patch removes this variable from davinci_gpio_platform_data
and also the refrences from the machine file.
Signed-off-by: NLad, Prabhakar <prabhakar.csengg@gmail.com>
Acked-by: NLinus Walleij <linus.walleij@linaro.org>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

The ASoC McASP driver looks for the mem resources by name
"mpu" and "dat" regions.
Change/add the needed name for the mem resources so the driver can pick the
correct resource.
Signed-off-by: NPeter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

The davinci_gpio_register() function expects the number of
resources as the second parameter, but sizeof() resources
was passed to it due to which it was causing unexpected
behaviour. This patch fixes the same by passing the
ARRAY_SIZE() of resources.
Reported-by: NGrygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: NLad, Prabhakar <prabhakar.csengg@gmail.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

DaVinci GPIO driver now uses platform device model.
Add a GPIO platform register API to convert the
traditional DaVinci  SoCs to use the new model.

While at it, also group related include files together
wherever that was not the case.
Signed-off-by: NPhilip Avinash <avinashphilip@ti.com>
Acked-by: NLinus Walleij <linus.walleij@linaro.org>
Signed-off-by: NLad, Prabhakar <prabhakar.csengg@gmail.com>
[nsekhar@ti.com: move function declaration to local header,
		 simplify commit message, merge SoC specific
		 portions from other patches into this patch]
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

This patch removes the clock alias for mdio device and adds a entry
in clock lookup table, this entry can now be used by both DT and
non-DT case.
Signed-off-by: NLad, Prabhakar <prabhakar.csengg@gmail.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

Get rid of davinci_serial_setup_clk() since its not called
from multiple places now. Instead initialize clock in
davinci_serial_init() itself. This also helps get rid of
"serial_dev" member of struct davinci_soc_info.
Signed-off-by: NManjunathappa, Prakash <prakash.pm@ti.com>
Suggested-by: NSekhar Nori <nsekhar@ti.com>
[nsekhar@ti.com: split removal of davinci_serial_setup_clk()
		 into a separate patch.]
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

"struct davinci_uart_config" was introduced to specify
UART ports brought out or enabled on the board. But
none of the boards use it for that purpose and we are
not going to add anymore board files, so remove the
structure.
Signed-off-by: NManjunathappa, Prakash <prakash.pm@ti.com>
Suggested-by: NSekhar Nori <nsekhar@ti.com>
[nsekhar@ti.com: split patch to remove davinci_serial_setup_clk()
		 changes.]
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

For modules having single clock, clk_get should be done with dev_id.
But current davinci implementation handles multiple instances
of the UART devices with single platform_device_register. Hence clk_get
is based on con_id rather than dev_id, this is not correct. Do
platform_device_register for each instance and clk_get on dev_id.
Signed-off-by: NManjunathappa, Prakash <prakash.pm@ti.com>
[nsekhar@ti.com: actually stop using con_id in clk_get(), squash the
		 patch adding OF aux data into this one]
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

Adds support for parsing the TI EDMA DT data into the required EDMA
private API platform data. Enables runtime PM support to initialize
the EDMA hwmod. Enables build on OMAP.

Changes by Joel:
* Setup default one-to-one mapping for queue_priority and queue_tc
mapping as discussed in [1].
* Split out xbar stuff to separate patch. [1]
* Dropped unused DT helper to convert to array
* Fixed dangling pointer issue with Sekhar's changes

[1] https://patchwork.kernel.org/patch/2226761/Signed-off-by: NMatt Porter <mporter@ti.com>
[nsekhar@ti.com: fix checkpatch errors, build breakages. Introduce
edma_setup_info_from_dt() as part of that effort]
Signed-off-by: NJoel A Fernandes <joelagnel@ti.com>
Acked-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

Move mach-davinci/dma.c to common/edma.c so it can be used
by OMAP (specifically AM33xx) as well.
Signed-off-by: NMatt Porter <mporter@ti.com>
Acked-by: Chris Ball <cjb@laptop.org> # davinci_mmc.c
Acked-by: NMark Brown <broonie@linaro.org>
Acked-by: NOlof Johansson <olof@lixom.net>
[nsekhar@ti.com: dropped davinci sffsdr changes]
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

The current davinci init sets up SRAM in iotables. There has been
an observed failure to boot a da850 with 128K specified in the
iotable.

Make the davinci sram allocator do an ioremap of the region
specified by the entries in davinci_soc_info before registering
with gen_pool_add_virt(). Remove all iotable SRAM mappings and
SRAM_VIRT.

Regression tested suspend/resume on AM180x EVM.
Signed-off-by: NBen Gardiner <bengardiner@nanometrics.ca>
Signed-off-by: NMatt Porter <mporter@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

Davinci McASP header & driver are shared by few OMAP platforms (like
TI81xx, AM335x). Splitting asp header into Davinci platform specific
header and Audio specific header helps to share them across platforms.

Audio specific defines is moved to to common
<linux/platform_data/davinci_asp.h> so that the header can be
accessed by all related platforms.

While here, correct the header usage (remove multiple header
re-definitions and unused headers) and remove platform names from
structures comments and enum. Also some some coding style errors.
Signed-off-by: NHebbar, Gururaja <gururaja.hebbar@ti.com>
Acked-by: NVaibhav Bedia <vaibhav.bedia@ti.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>

There are instances of IO_ADDRESS() being used for system module
(sysmod) register access. Eliminate this in favor of a ioremap()
based access. ioremap() the entire sysmod address space once during
boot-up and provide a helper macro to access specific register
offsets within the address space.

With this, also eliminate ioremap() of specific sysmodule registers
related to VPIF happening in DM646x EVM code.

While at it, also eliminate some duplicate sysmod register offset macros
defined in code and place offset definitions at one place in davinci.h
Signed-off-by: NManjunath Hadli <manjunath.hadli@ti.com>
Acked-by: NArnd Bergmann <arnd@arndb.de>
[nsekhar@ti.com: removed the addition of ifndef __ASSEMBLER__
in davinci.h, eliminate IO_ADDRESS() usage left out in dm646x.c,
cleanup VPIF sysmodule register access as part of this patch and
keep all sysmod offsets in davinci.h Also, convert the WARN_ON()
on failure to setup sysmod base to BUG_ON()]
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

Remove individual platform header files for dm365, dm355, dm644x
and dm646x and consolidate it into a single and common
header file davinci.h placed in arch/arm/mach-davinci.

This reduces the pollution in the include/mach and is consistent
with Russell's suggestions as part of his "pet peaves" mail.
(See #4 in: http://lists.infradead.org/pipermail/linux-arm-kernel/2011-November/071516.html)

While at it, fix the forward declaration of spi_board_info,
and include the right header file instead.

The further patches in the series take  advantage of this consolidation
for easy implementation of IO_ADDRESS elimination.
Signed-off-by: NManjunath Hadli <manjunath.hadli@ti.com>
[nsekhar@ti.com: make davinci.h the first local include file,
fix forward declaration of spi_board_info and add back Deep Root
Systems, LLC copyright]
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

Move register base addresses and offsets used only in dm646x.c
from arch/arm/mach-davinci/include/mach/dm646x.h in to the C
file as these definitions are used only in C file.

This helps reduce code in arch/arm/mach-davinci/include/mach/
which is not really needed by rest of the kernel.
Signed-off-by: NManjunath Hadli <manjunath.hadli@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

Rather than using DaVinci specific davinci_soc_info based
restart hook, use the restart hook available in the machine
descriptor instead.

Tested on DM365 and AM18x EVMs.

v2:
Changed to use restart hook in machine descriptor
per Russell's comment.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Fix the incorrect classification of DSP clock into a
seperate DSP domain on DM646x.

Per the reference guide (http://www.ti.com/lit/ug/spruep9e/spruep9e.pdf)
there is only one "AlwaysON" power domain on DM6467.
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

Davinci platforms may define a default queue for each channel
controller. If one is not defined, the default queue is set to EVENTQ_1.
However, there's no way to distinguish between an unset default queue to
one that is set to EVENTQ_0, as EVENTQ_0 = 0.

Explicitly specify the default queue for all channel controllers on all
Davinci platforms to EVENTQ_1, and don't overwrite it in the EDMA probe
function.

One exception is the DA850 board, for which EVENTQ_1 is not a valid
option for its second channel controller. Use EVENTQ_0 instead for that
channel controller.
Signed-off-by: NIdo Yariv <ido@wizery.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>

The <mach/gpio.h> file is included from upper directories
and deal with generic GPIO and gpiolib stuff. Break out the
platform and driver specific defines and functions into its own
header file.

Cc: Sekhar Nori <nsekhar@ti.com>
Cc: Kevin Hilman <khilman@ti.com>
Signed-off-by: NLinus Walleij <linus.walleij@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The DM6467 and DM6467T EVMs use different reference clock
frequencies. This difference is currently supported by having
the SoC code call a public board routine which sets up the reference
clock frequency. This does not scale as more boards are added.

Instead, use the clk_set_rate() API to setup the reference clock
frequency to a different value from the board file.
Suggested-by: NKevin Hilman <khilman@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Acked-by: NKevin Hilman <khilman@ti.com>

Remove linux/mm.h inclusion from netdevice.h -- it's unused (I've checked manually).

To prevent mm.h inclusion via other channels also extract "enum dma_data_direction"
definition into separate header. This tiny piece is what gluing netdevice.h with mm.h
via "netdevice.h => dmaengine.h => dma-mapping.h => scatterlist.h => mm.h".
Removal of mm.h from scatterlist.h was tried and was found not feasible
on most archs, so the link was cutoff earlier.

Hope people are OK with tiny include file.

Note, that mm_types.h is still dragged in, but it is a separate story.
Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On Davinci SRAM is mapped as MT_DEVICE becasue of the section
mapping pre-requisite instead of intended MT_MEMORY_NONCACHED

Since the section mapping limitation gets fixed with first
patch in this series, the MT_MEMORY_NONCACHED can be used now.
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: NKevin Hilman <khilman@deeprootsystems.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This patch removes davinci architecture code that has now been rendered
useless by the previous patches in the MDIO separation series.

In addition, the earlier phy_mask definitions have been replaced with
corresponding phy_id definitions.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Tested-by: NMichael Williamson <michael.williamson@criticallink.com>
Tested-by: NCaglar Akyuz <caglarakyuz@gmail.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

This patch adds mdio platform devices on SoCs that have the necessary
hardware.  Clock lookup entries (aliases) have also been added, so that the
MDIO and EMAC drivers can independently enable/disable a shared underlying
clock.  Further, the EMAC MMR region has been split down into separate MDIO
and EMAC regions.
Signed-off-by: NCyril Chemparathy <cyril@ti.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Tested-by: NMichael Williamson <michael.williamson@criticallink.com>
Tested-by: NCaglar Akyuz <caglarakyuz@gmail.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

Not all the channels and slots available on the DM646x EVM
are used by the devices on the EVM. These resources can be
used by the DSP to speed up codec operations.

This patch reserves these channels for the DSP.
Signed-off-by: NSudhakar Rajashekhara <sudhakar.raj@ti.com>
Signed-off-by: NSekhar Nori <nsekhar@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

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 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 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 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>

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>