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>

The I2C macros have side effects and send_seq could cause a return from
a function with a mutex held.  Change them to behave like real functions.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

The saa7134-oss is deprecated for quite some time, it's the only remaining OSS
user outside of sound/oss/, and considering how few and what kind of
soundcards are left supported by OSS I hardly see any use cases left.
Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

The ability to read Hauppauge eeprom's was recently added to saa7134,
so we must build the tveeprom module.

Thanks to Matthias Schwarzott for pointing this out.
Signed-off-by: NMichael Krufky <mkrufky@linuxtv.org>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

The HVR-900 requires the MTS version of the xc3028 firmware in order
to get any sound. The below patch selects this firmware variant on
HVR-900 cards, as well as splitting the HVR-950 into its own entry
(since I don't know if it uses the MTS variant and it will have to be
split off eventually anyway).
Signed-off-by: NAidan Thornton <makosoft@googlemail.com>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

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

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

TM5600/TM6000 needs clock reset during firmware load. This patch adds the
capability of caling a callback method for this.

Also, avoids uneeded firmware loads.
Signed-off-by: NMichel Ludwig <michel.ludwig@gmail.com>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Removes uneeded parameters and adds an structure for passing the parameters

This patch is co-authored by Mauro Carvalho Chehab.
Signed-off-by: NMichel Ludwig <michel.ludwig@gmail.com>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Signed-off-by: NMichel Ludwig <michel.ludwig@gmail.com>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Increased size of dev->eedata from 128 to 256, since the Hauppauge data begins
at byte 128.  This has been tested on boards with smaller eeproms, and caused
no problems.

Added comments to distinguish between the various versions of the HVR1110.
Signed-off-by: NMichael Krufky <mkrufky@linuxtv.org>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Signed-off-by: NMichael Krufky <mkrufky@linuxtv.org>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

While there's no public API to define audio standard, adds a hack option for
select them. This is needed only for NICAM and A2 firmwares, since AM, BTSC and
EAIJ are already properly handled, on firmware version 2.7.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

s/STATE_NEEDS_INIT/VIDEOBUF_NEEDS_INIT/g
s/STATE_PREPARED/VIDEOBUF_PREPARED/g
s/STATE_QUEUED/VIDEOBUF_QUEUED/g
s/STATE_ACTIVE/VIDEOBUF_ACTIVE/g
s/STATE_DONE/VIDEOBUF_DONE/g
s/STATE_ERROR/VIDEOBUF_ERROR/g
s/STATE_IDLE/VIDEOBUF_IDLE/g
Signed-off-by: NBrandon Philips <bphilips@suse.de>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

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

Make the driver less verbose by default. It adds a debug parameter to make the
driver more verbose.
Also, error messages were using KERN_ERR level, instead of KERN_INFO.
A few printk messages were reviewed to make them more clear.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Some tuners, like xc3028, need to print error messages. Instead of declaring
local macros, create a tuner global macro for printing tuner errors.

To preserve CodingStyle on all tuner_macros, a few CodingStyle violations were
fixed at the other macros:
	- lines with more than 80 columns
	- two statements at the same line

The patch also removes the CodingStyle violation of having emacs declarations
inside de source code (CodingStyle chapter 18).
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Xceive 2028/3028 has a concept of scode/dcode.
Scode is a table of 16 values (each with 12 bytes i2c sequence).
Dcode is the entry of Scode table that should be used, given a certain
frequency.

The idea is that, depending on what frequency is selected, and according with a
country-based (or standard-based?) table, the Xceive should be "hacked" to
fine-tune that specific frequency.

By default, Scode=0 is used, for undefined frequencies. Also, Scode=0 seems to
be the most used value.

This patch adds the capability of selecting a scode. However, extra work will
be needed to allow auto-selecting the proper scode, for a given set of
frequencies.

I'm not sure what would be the proper way for implementing the dcode selection.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Firmware version 2.7 has other firmware types. This patch adds the capability
for the driver to work with those newer types.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Adds a new image sensor to the sn9c102 driver.
Signed-off-by: NLuca Risolia <luca.risolia@studio.unibo.it>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

With the conversion to the vidio_ioctl2, tvnorms array is not required anymore.

Also, removed some code from V4L1 time (VIDEO_MODE_foo), specied at the
non-used video_decoder.h.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

There were some vestiges of an old V4L1 I2C driver that were called by em28xx.
This patch removes this dead code, and replaces videodev.h to videodev2.h

Now, this driver doesn't require V4L1 anymore.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Uses the newer ioctl handler at videodev. This patch also cleans up some
bad logic at the driver and do CodingStyle and other cleanups at the
resulting driver.

Also, since VIDIOCMBUF were not working, the V4L1 compat code were removed.
The compat code will eventually be re-inserted, if we find a clean way for
implementing compatibility with the old API.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Backport read() fixes from Markus Rechberger.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

On some situations, closing an streaming application and re-opening were
returning -EBUSY.

Uses the same locking schema also present on cx88.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Allows shared access support for em28xx. Just one userspace application is
allowed to get stream. The other(s) application(s) can change V4L2 controls,
set video standards, etc.

This patch were splited from Markus Rechberger's tree and backported to 2.6.17
by Pádraig Brady.

The original patch were ported to the latest em28xx version and had CodingStyle
corrected to solve the issues pointed by scripts/checkpatch.pl.

Thanks to Pádraig Brady <P@draigBrady.com> for pointing this.
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

V4L: Int if: Set slave's master before attach, remove master argument

The master also now gets its own pointer from slave's structure.
Signed-off-by: NSakari Ailus <sakari.ailus@nokia.com>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>