All the drivers that use the "mite" module now allocate a `struct
mite_struct` dynamically instead of searching the `mite_devices` list
populated during initialization of the "mite" module.

Remove the list of devices and the function that prints available NI
devices on the list (`mite_list_devices()`).  The list node and `used`
members in `struct mite_struct` are now redundant, so remove them.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Allocate `struct mite_device` dynamically instead of searching for
one on the `mite_devices` list constructed by the "mite" module.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Allocate `struct mite_device` dynamically instead of searching for
one on the `mite_devices` list constructed by the "mite" module.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Allocate `struct mite_device` dynamically instead of searching for
one on the `mite_devices` list constructed by the "mite" module.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

This driver's comedi `detach` handler (`ni_670x_detach()`) calls
`free_irq()` but the driver doesn't call `request_irq()` anywhere.
Remove the spurious call.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Allocate `struct mite_device` dynamically instead of searching for
one on the `mite_devices` list constructed by the "mite" module.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Allocate `struct mite_device` dynamically instead of searching for
one on the `mite_devices` list constructed by the "mite" module.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Allocate `struct mite_device` dynamically instead of searching for
one on the `mite_devices` list constructed by the "mite" module.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Allocate `struct mite_device` dynamically instead of searching for
one on the `mite_devices` list constructed by the "mite" module.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Add `mite_alloc()` to allow drivers to allocate and initialize a `struct
mite_struct` dynamically and export it.  Add `mite_free()`, which is
currently just an inline wrapper for `kfree()`.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Replace the `printk()` calls in this module with `dev_...()` calls where
possible or `pr_...()` calls otherwise.

Rework the normally ifdefed out (by the `DEBUG_MITE` macro)
`mite_dump_regs()` to dump register offsets instead of remapped
addresses.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

The static inline functions `MITE_IODWBSR_1_WSIZE_bits()` and `CR_RL()`
in "mite.h" work out a base-2 logarithm using a `while` loop.  Change
them to use `ilog2()`.  Also change `CR_RL()` to clamp the maximum value
instead of printing an error.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

The `mite_alloc_ring()` and `mite_free_ring()` static inline functions
in "mite.h" are reasonably large.  Transfer them to "mite.c" and export
them.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Declare some non-exported functions in "mite.c" `static` and remove
their declarations from "mite.h".
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert this PCI driver to use the comedi `attach_pci` callback instead
of the `attach` callback for PCI auto-configuration.  There is no need
to support manual attachment of PCI devices supported by this driver, so
remove the `attach` callback altogether.

Note that this driver still uses the list of PCI "mite" devices created
by the "mite" module.  This will be dealt with by a later patch once
dynamic allocation of "mite" structures has been implemented.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Add a semi-colon after the macro call
`module_comedi_pci_driver(ni_pcimio_driver, ni_pcimio_pci_driver)`.  It
compiles with or without the semicolon but it ought to have it.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

`ni_E_init()` doesn't use the second parameter pointing to a `struct
comedi_devconfig` passed from a comedi `attach` handler, so remove the
parameter.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert this PCI driver to use the comedi `attach_pci` callback instead
of the `attach` callback for PCI auto-configuration.  There is no need
to support manual attachment of PCI devices supported by this driver, so
remove the `attach` callback altogether.

Note that this driver still uses the list of PCI "mite" devices created
by the "mite" module.  This will be dealt with by a later patch once
dynamic allocation of "mite" structures has been implemented.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

The PCI-6534 needs three firmware files loading to work with the driver.
That is currently done by passing the firmware data using the
`COMEDI_DEVCONFIG` ioctl that uses the comedi `attach()` hook in the
driver.  This doesn't work for auto-configured PCI devices (which also
currently use the `attach()` hook in this driver, but doesn't have the
firmware-loading options set in the `struct comedi_devconfig *`
parameter).

Change the driver to request the firmware files using
`request_firmware()`, ignoring any firmware-loading options set in the
`struct comedi_devconfig`.

The PCI-6534 has a main FPGA which needs to be loaded first, and two
"scarabs".  Scarab A is loaded with firmware to support digital input
mode, and scarab B is loaded with firmware to support digital output
mode.

I don't think the order of loading the scarab firmwares matters as long
as they are loaded with the correct firmware files.  This update loads
scarab B first, whereas the original code loaded scarab A first.  The
firmware files are loaded in the following order:

A) main FPGA: "ni6534a.bin" (FW_PCI_6534_MAIN)
B) scarab B: "niscrb02.bin" (FW_PCI_6534_SCARAB_DO)
C) scarab A: "niscrb01.bin" (FW_PCI_6534_SCARAB_DI)

The required firmware files can be found in the
"comedi-nonfree-firmware" tar-ball at
<http://www.comedi.org/download/comedi-nonfree-firmware-2007.06.22.tar.gz>.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert the `printk()` calls in this driver to use the `dev_...()` calls
where possible, or the `pr_...()` calls otherwise.  Combine
non-line-terminated prints into single-line prints.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert this PCI driver to use the comedi `attach_pci` callback instead
of the `attach` callback for PCI auto-configuration.  Remove support for
manual attachment of PCI boards supported by this driver.  The `attach`
callback is still needed to manually attach ISA boards, but print an
error if an attempt is made to manually attach a PCI board.

Note that this driver still uses the list of PCI "mite" devices created
by the "mite" module.  This will be dealt with by a later patch once
dynamic allocation of "mite" structures has been implemented.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Move the `labpc_driver` and `labpc_pci_table` variables nearer the
module initialization code near the bottom of the module for aesthetic
reasons and to avoid a forward declaration of `labpc_attach()`.

As a consequence, to avoid having to add a forward declaration of the
`labpc_driver` variable, change code that uses
`labpc_driver.driver_name` to use `DRV_NAME` instead, and change code
that uses `labpc_driver.num_names` to use `ARRAY_SIZE(labpc_boards)`
instead.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Use the macro `module_comedi_pci_driver(comedi_driver, pci_driver)` to
register the module as a Comedi PCI driver if the module supports PCI
devices, otherwise use `module_comedi_driver(comedi_driver)` to register
it as an ordinary Comedi driver.  Rename variables and functions that
have prefix `driver_` for consistency.  Set the `name` member of the
`struct pci_driver` variable in its initializer instead of initializing
it in the module initialization function.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert the `printk()` calls in this driver to use the `dev_...()` calls
where possible, or the `pr_...()` calls otherwise.  Remove the ifdefed
out code that prints the EEPROM contents.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert this PCI driver to use the comedi `attach_pci` callback instead
of the `attach` callback for PCI auto-configuration.  There is no need
to support manual attachment of PCI devices supported by this driver, so
remove the `attach` callback altogether.

Note that this driver still uses the list of PCI "mite" devices created
by the "mite" module.  This will be dealt with by a later patch once
dynamic allocation of "mite" structures has been implemented.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert this PCI driver to use the comedi `attach_pci` callback instead
of the `attach` callback for PCI auto-configuration.  There is no need
to support manual attachment of PCI devices supported by this driver, so
remove the `attach` callback altogether.

Note that this driver still uses the list of PCI "mite" devices created
by the "mite" module.  This will be dealt with by a later patch once
dynamic allocation of "mite" structures has been implemented.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Use the macro `module_comedi_pci_driver(comedi_driver, pci_driver)` to
register the module as a Comedi PCI driver.  Rename variables and
functions that have prefix `driver_` for consistency.  Set the `name`
member of the `struct pci_driver` variable in its initializer instead of
initializing it in the module initialization function.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert the `printk()` calls in this drivers to use the `dev_...()`
calls instead.  Replace some `printk()` calls in the comedi `attach()`
handler (`ni_660x_attach()`) with a single `dev_info()` at the end.
Remove some `printk()` calls before `BUG()` calls.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert this PCI driver to use the comedi `attach_pci` callback instead
of the `attach` callback for PCI auto-configuration.  There is no need
to support manual attachment of PCI devices supported by this driver, so
remove the `attach` callback altogether.

Note that this driver still uses the list of PCI "mite" devices created
by the "mite" module.  This will be dealt with by a later patch once
dynamic allocation of "mite" structures has been implemented.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Move the `struct comedi_driver ni_65xx_driver` variable further down the
function to be closer to the `module_comedi_pci_driver()` module call
and to avoid having to forward declare `ni_65xx_attach()` and
`ni_65xx_detach()`.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Use the macro `module_comedi_pci_driver(comedi_driver, pci_driver)` to
register the module as a Comedi PCI driver.  Rename variables and
functions that have prefix `driver_` for consistency.  Set the `name`
member of the `struct pci_driver` variable in its initializer instead of
initializing it in the module initialization function.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert the `printk()` calls in this drivers to use the `dev_...()`
calls instead.  Remove the initial `printk()` call in the comedi
`attach()` handler (`ni_65xx_attach()`) as it's a bit redundant - the
board type and contents of a board ID register are printed later in the
function.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert this PCI driver to use the comedi `attach_pci` callback instead
of the `attach` callback for PCI auto-configuration.  There is no need
to support manual attachment of PCI devices supported by this driver, so
remove the `attach` callback altogether.

Note that this driver still uses the list of PCI "mite" devices created
by the "mite" module.  This will be dealt with by a later patch once
dynamic allocation of "mite" structures has been implemented.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Move the `struct comedi_driver ni6527_driver` variable further down the
function to be closer to the `module_comedi_pci_driver()` module call
and to avoid having to forward declare `ni6527_attach()` and
`ni6527_detach()`.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Use the macro `module_comedi_pci_driver(comedi_driver, pci_driver)` to
register the module as a Comedi PCI driver.  Rename variables and
functions that have prefix `driver_` for consistency.  Set the `name`
member of the `struct pci_driver` variable in its initializer instead of
initializing it in the module initialization function.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Change the driver name string used in data structures, kernel messages,
etc. from "ni6527" to "ni_6527" to match the module name.  Use a macro
`DRIVER_NAME` that expands to this string literal.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Convert the `printk()` calls in this drivers to use the `dev_...()`
calls instead.  Remove the initial `printk()` call in the comedi
`attach()` handler (`ni6527_attach()`) as it's a bit redundant - the
board type and contents of a board ID register are printed later in the
function.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

This pulls in the staging tree fixes in 3.6-rc6 into our branch to resolve the
merge issues.
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Pull mfd fixes from Samuel Ortiz:
 "This is the remaining MFD fixes for 3.6, with 5 pending fixes:

   - A tps65217 build error fix.
   - A lcp_ich regression fix caused by the MFD driver failing to
     initialize the watchdog sub device due to ACPI conflicts.
   - 2 MAX77693 interrupt handling bug fixes.
   - An MFD core fix, adding an IRQ domain argument to the MFD device
     addition API in order to prevent silent and potentially harmful
     remapping behaviour changes for drivers supporting non-DT
     platforms."

* tag 'mfd-for-linus-3.6-2' of git://git.kernel.org/pub/scm/linux/kernel/git/sameo/mfd-2.6:
  mfd: MAX77693: Fix NULL pointer error when initializing irqs
  mfd: MAX77693: Fix interrupt handling bug
  mfd: core: Push irqdomain mapping out into devices
  mfd: lpc_ich: Fix a 3.5 kernel regression for iTCO_wdt driver
  mfd: Move tps65217 regulator plat data handling to regulator