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>

Now we know the zl10353's correct ADC clock, we can calculate the input
frequency registers correctly instead of just blindly setting them.
Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>

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>