Since check_firmware is called via analog or digital set freq routines, move
type selection to those routines. This avoids having several if's at the code,
and simplifies the source code.

A sideback effect is that implementing radio and other dvb types will become
simpler.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

move some tv-audio initialization code out of tvaudio thread,
and call it on resume too.
Signed-off-by: NMaxim Levitsky <maximlevitsky@gmail.com>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

First the saa7134_initdev waits between saa7134_hwinit1
and saa7134_hwinit2 , thus it is probably wise to do the same in saa7134_resume
some hardware probably needs this.

Call saa7134_irq_video_signalchange in .resume like in saa7134_resume to make
saa7134_resume mirror perfectly the saa7134_initdev although
this call isn't strictly necessary in the saa7134_initdev,
but it won't harm anyway.
Signed-off-by: NMaxim Levitsky <maximlevitsky@gmail.com>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

*dev->insuspend = 1 should be set before synchronize_irq
 *ACK interrupts after synchronize_irq, to make sure there aren't
 pending interrupts.
 *Add barrier before we restart interrupts so the handler will 100%
 see the dev->insuspend
Signed-off-by: NMaxim Levitsky <maximlevitsky@gmail.com>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

pci_save_state should be called before pci_set_power_state
and pci_restore_state after pci_set_power_state
Signed-off-by: NMaxim Levitsky <maximlevitsky@gmail.com>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Signed-off-by: NHans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

This patch removes a few remainders of the VID_HARDWARE_* removal.
Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
643d01fb38b6f376cced035549f4e193018776e7 

thanks to checkpatch.pl
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Not all 8MHz firmware are marked with F8MHz.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

On some cases, xc2028/xc3028 wents into "turn off" mode. It seems that this
happens when very weak signals are tuned. To solve this, specific standard
reaload were done previously. Christopher patches changed this behavior to a
complete firmware reload.

This patch removes the hack. A much cleaner solution for this trouble is just
to sent a xc2028/3028 software reset.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

xc3028 can be used on some DTV only designs (for example, DVB-S boards). Before
this patch, a DTV only board would need to call set_tuner_config callback.

This patch allows to optionally pass a xc3028_ctrl parameter, via xc3028_config
struct, fully initializing the driver for DTV.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Xc2028.3028 has two type of firmwares: audio-standard specific ones and
baseband MTS firmwares. MTS firmwares provide stereo decoding for 6 MHz
BTSC/EIAJ and for monoaural audio decoding on 8 MHz firmwares.

It seems that the option to use MTS or a standard-specific audio decoding
depends on the way xc2028/3028 is connected.

Instead of wasting 32 (or 64 bits) to signalize if the driver needs to use MTS
firmware, this patch converts it to a bitfield that can be shared with other
proprieties of xc2028/3028.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Some drivers call set_frequency before selecting the video standard. Before
this patch, an invalid standard ID could be assumed.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Those standards use 6 MHz firmware.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Whilst reanalysing my formulas I realised it was no longer possible to get the
right values for a 36.1667MHz IF due to rounding problems.

Storing frequencies in units of 0.1kHz makes it possible to calculate these
again correctly.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

There are at least three variants of the DViCO FusionHDTV DVB-T NANO that
share the same USB device ID.  The first (ZL10353 w/ firmware in ROM) is
already supported; the latter two both require firmware and have either
an MT352 or ZL10353 demodulator, and have a different IR receiver from the
first.

This introduces a new identify_state that can tell the difference between a
"warm" device which is running the embedded firmware, and a "cold" device
that needs us to upload firmware to it before it will work.  We patch the
uploaded device ID (like we do for other bluebird devices) to make it easy
to identify the particular device variant when it reattaches.

NB: These devices use a different firmware file from previous bluebird
    devices.  You need a new firmware file to make this work.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Rework the input frequency calculation so that it produces the right values
when the ADC oversamples the IF input.

This means MT352 devices can now process a near-zero IF (according to the,
specs 4.57MHz is supported with the default crystal).
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Add support for the DViCO FusionHDTV DVB-T NANO with zl10353 demodulator and
firmware in ROM on the device.

Again, this is based on the great work of Mike Krufky with my modifications
to use the in-tree XC2028 driver.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

When loading init1 firmware, there may not be an 8MHz specific version.
Load the non-8MHz version if it exists.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

When searching for standard-specific analog firmware, only certain
type bits are valid, much like for DTV.  Mask them off when finding
the firmware to load.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

When loading BASE firmware, we must use std = 0.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Add support for DViCO's Dual Digital 4 with xc3028 tuner, zl10353 DVB-T
demodulator and a new-style I2C IR remote control receiver.

This would not have been possible without the work of and advice from
Mike Krufky, who originally got the Dual Digital 4 and second-gen DVB-T
NANO devices working with the out-of-tree XC3028 driver.

I converted it to use the in-tree XC3028 driver (after making it suitable
for our use), and added the IR remote control support based on his advice.

NB: a firmware package is required to use this device.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Add sleep method to enable putting the tuner into standby mode.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

In practice, the tuner occasionally fails to respond correctly after a
firmware load.  Retry the firmware load if the firmware/hardware version
we read back from the tuner after programming does not match what we
expect.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Define a list of valid "firmware types" for each combination of BASE,
DTV and SCODEs.  By masking the appropriate firmware bits off we can
just use one "type" for the firmware searching and also flag when we
are looking for a BASE, DTV or SCODE type firmware.  This makes it
much easier to track if we need to change device modes or flash an
individual firmware part.

Add a structure to remember what firmware properties we have.  This
contains the currently loaded/wanted  base firmware (type), video std
(id), video std requested (std_req), scode file and number in use.

Incorporate said structure into the tuner private data.

When checking whether the current firmware needs to be reloaded, first
figure out exactly what "type" of firmware we want (base, std and
scode), and then proceed to load the appropriate matching base,
std-specific and scode records iff there are any changes required.
This removes guesswork from the process because we no longer need to
individually code a check for every tuning parameter's interactions.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Add a bit to select D2633 DTV firmware to struct xc2028_ctrl, so that it can
be enabled via .set_config.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

When validating and loading SCODE firmware we need to take into account the
two-byte size header before each entry.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Rather than picking the first video standard firmware that supports any of
the standards that the user has requested, try to select one that supports
as many of them as possible.  This improves the likelihood that the firmware
we select will support the user's desired TV standard.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

There is no need to duplicate the max_len field from the ctrl structure
in the private data.  If we use it directly from priv->ctrl, we can memcpy
the structure (apart from strings) to reduce maintenance as it grows.

Enforce a minimum max_len length of 8 data bytes (+ 1 address byte) as seems
to be required by the tuner.

Also, use kstrdup instead of open coding the string duplication.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

7MHz bandwidth DVB-T needs an adjusted offset at the PLL to ensure the IF
output is correctly centered.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

We were using priv->bandwidth to select the base firmware to load, not the
requested bandwidth value, oops.  Also, 7MHz Digital TV needs 8MHz base
firmware loaded.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

The frequency divisor should only be four bytes long.  Also, display the
frequency and divisor correctly in the debug output.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Hold the private lock over set_config and set priv->firm_size to 0 after a
failed firmware load to prevent firmware accidentally being freed on us.

Clean up the firmware load/error messages somewhat and rename priv->version
to priv->firm_version to make it clear which "version" it is.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Add break to stop us from following the default failure path even upon success.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Protect refcount changes and modifications to xc2028_list with a mutex.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Cast v4l2_std_id variables to unsigned long long so they will printk properly.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Fix some missing spaces in errors that may be emitted during attach failure.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Issuing register reads as a separate address write and data read transactions
means that other I2C activity could occur in between and state could get out
of sync.  Issue both the write and read in a single transaction so that the
i2c layer can prevent other users accessing the bus until we are complete.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

strcasecmp returns 0 on match, not true.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>