Issue FSM_GO instead of TUNER_GO if there is no tuner attached to the
secondary i2c bus.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

The path to perform a read immediately after a write was not checking that
the address being read from was the same as the one that was written.

Handling this case correctly should mean that we now can handle more than
two i2c messages at a time.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Any i2c read request that was not immediately preceded by a write request was
incorrectly taking the write path.  Add the capability to handle individual
read requests.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

The i2c master_xfer routine should return a negative result if not all
transfers completed successfully.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Callers to cxusb_ctrl_msg currently do not receive any indication that their
transfer failed.  Return the true return code from dvb_usb_generic_{rw,write}.
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>

If tda827x_config hasn't been defined, exit the function.
Signed-off-by: NMichael Krufky <mkrufky@linuxtv.org>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Fix the following oops:

[  750.807586] CPU:    1
[  750.807587] EIP:    0060:[<f9dde2a3>]    Tainted: P       VLI
[  750.807589] EFLAGS: 00010296   (2.6.22-14-generic #1)
[  750.807599] EIP is at tda827x_probe_version+0xc3/0x130 [tda827x]
[  750.807603] eax: 00000000   ebx: f5a45a00   ecx: 00000000   edx: 00000001
[  750.807607] esi: f9de05ac   edi: e9b897e0   ebp: ed8015ac   esp: ed735f58
[  750.807611] ds: 007b   es: 007b   fs: 00d8  gs: 0000  ss: 0068
[  750.807615] Process kdvb-fe-1 (pid: 10662, ti=ed734000 task=d3b76530 task.ti=ed734000)
[  750.807618] Stack: f9e23972 00000038 ed735fd0 00010060 41ae0001 ed735f73 88b89608 e9b89608
[  750.807629]        e9b89608 ed801400 f9dde338 e9b89608 f9b2a46b 000000ae 00000a18 d3b76640
[  750.807639]        fffffffc f9b2bad6 00000003 f4433e68 e962b8c0 f4433e64 00000292 ed735fd0
[  750.807649] Call Trace:
[  750.807653]  [<f9e23972>] tda10046_init+0x2d2/0x6c0 [tda1004x]
[  750.807700]  [<f9dde338>] tda827x_initial_init+0x8/0x20 [tda827x]
[  750.807713]  [<f9b2a46b>] dvb_frontend_init+0x2b/0x60 [dvb_core]
[  750.807745]  [<f9b2bad6>] dvb_frontend_thread+0x66/0x2f0 [dvb_core]
[  750.807780]  [complete+64/96] complete+0x40/0x60
[  750.807805]  [<f9b2ba70>] dvb_frontend_thread+0x0/0x2f0 [dvb_core]
[  750.807822]  [kthread+66/112] kthread+0x42/0x70
[  750.807828]  [kthread+0/112] kthread+0x0/0x70
[  750.807841]  [kernel_thread_helper+7/16] kernel_thread_helper+0x7/0x10
[  750.807869]  =======================
[  750.807872] Code: 8b 74 24 20 8b 7c 24 24 83 c4 28 c3 8b 0d 00 0c de f9 85 c9 75 42 be e0 04 de f9 81 c7 0c 01 00 00 b9 33 00 00 00 f3 a5 8b 43 08 <c7> 40 14 50 e3 dd f9 8b 5c 24 1c 31 c0 8b 74 24 20 8b 7c 24 24
[  750.807925] EIP: [<f9dde2a3>] tda827x_probe_version+0xc3/0x130 [tda827x] SS:ESP 0068:ed735f58
Signed-off-by: NMichael Krufky <mkrufky@linuxtv.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: NJoe Perches <joe@perches.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>

Signed-off-by: NBrandon Philips <bphilips@suse.de>
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>

MT2266 :
- support for VHF
- Minor enhancements
Signed-off-by: NOlivier DANET <odanet@caramail.com>
Signed-off-by: NPatrick Boettcher <pb@linuxtv.org>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Signed-off-by: Ndominik <dominik95@free.fr>
Signed-off-by: NPatrick Boettcher <pb@linuxtv.org>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

Add remote controller support for Leadtek Winfast DTV Dongle based on
DiB7700P, MT2060 and using last drivers (6040:6a79c243aecc), firmware
dvb-usb-dib0700-03-pre1.fw
Signed-off-by: NJaroslav Barton <djaara@djaara.net>
Signed-off-by: NPatrick Boettcher <pb@linuxtv.org>
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>

This patch makes some needlessly global debug variables static.

opera1.h became so small that I removed it.
Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Reviewed-by: NMichael Krufky <mkrufky@linuxtv.org>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>