Commit Graph

76 Commits

Author SHA1 Message Date
Mauro Carvalho Chehab
5c913c0571 V4L/DVB (7439): tuner-xc2028: Adds an option to allow forcing to load an specific firmware name
There are a number of different firmware versions and variants, shipped
together with boards.

This patch adds an extra parameter to the tuner-xc2028 to allow specifying for
an specific firmware name to be loaded. This helps to test for a firmware that
better fits some board.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-04-24 14:07:55 -03:00
Mauro Carvalho Chehab
b412ba781a V4L/DVB (7399): Removes video_dev from tuner-xc2028 config struct
The video_dev parameter, on tuner-xc2028 were used to pass i2c private data to
tuner_callback. Since the driver already have a pointer to i2c_adap->algo_data,
uses this instead.

This parameter were used also as a magic number to idenfity if two drivers are
trying to register the same xc3028 tuner. This occurs with boards with DVB
support, where both DVB and V4L drivers will share the same tuner.

Instead of using the algo_data as a private number, after this patch, the
driver will use i2c_adap->dev, with seems more consistent.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-04-24 14:07:53 -03:00
Mauro Carvalho Chehab
1fe8736955 V4L/DVB (7260): tuner-xc3028: Don't check return code for clock reset
Only tm6000 needs to be aware when a frequency is being changed. This seems
to improve channel change detection. Other bridges don't need this.
So, better to discard any errors if this fails, and proceed changing the
channels.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-04-24 14:07:45 -03:00
Michael Krufky
2756665c28 V4L/DVB (7135): remove PREFIX from users of tuner_foo printk macros
Store a pointer to the device name in the name field of
struct tuner_i2c_props, so that we can remove the
printk macros defined in tuner-i2c.h

Signed-off-by: Michael Krufky <mkrufky@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-04-24 13:42:26 -03:00
Adrian Bunk
29bec0bff5 V4L/DVB (7114): tuner-xc2028.c: make a function static
dump_firm_type_and_int_freq() can become static.

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-04-24 13:42:19 -03:00
Mauro Carvalho Chehab
40ae91a758 V4L/DVB (7200): Fix FM firmware loading
There's no need to load SCode table for FM.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-02-18 12:18:06 -03:00
Mauro Carvalho Chehab
0f6dac18cc V4L/DVB (6954): There isn't a MTS radio firmware
Try to load non-MTS firmware instead.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:04:33 -02:00
Chris Pascoe
ef207feddf V4L/DVB (6897): xc2028: ignore HAS_IF during specific S-Code type searches
If we are selecting the S-Code firmware to load by name, then we must mask
off the HAS_IF bit during the search.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:04:15 -02:00
Michael Krufky
7972f9880c V4L/DVB (6893): tuner-xc2028: fix xc2028_attach function
xc2028_attach was returning an integer when disabled from the build, where it
should instead be returning NULL.  Declare xc2028_attach as type dvb_frontend *
instead of void *.

The prototype declaration must be marked as extern in the header.

Signed-off-by: Michael Krufky <mkrufky@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:04:14 -02:00
Michael Krufky
d536c9df41 V4L/DVB (6875): tuner-xc2028: ATSC requires 1.75 MHz tuning offset
In my testing yesterday, I was using a scan file tailored specifically
for a unique test situation -- As it turns out, this scan file was bad,
and I will use the one included inside dvb-apps for testing for now on.

I've tested with other ATSC tuners just to confirm, using:

us-ATSC-center-frequencies-8VSB

Anyhow, as it turns out, the tuner-xc2028 *does* require a tuning offset
for ATSC.  Even though the linux-dvb api passes in center frequencies
from userspace, apparantly the xceive firmware is already factoring in
the tuning offset to center.

In order to make the device function using the same scan files /
channels.conf configurations as other atsc devices, we must offset by
1.75 MHz.

Signed-off-by: Michael Krufky <mkrufky@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:04:09 -02:00
Mauro Carvalho Chehab
3ac510e609 V4L/DVB (6858): Fix offset for ATSC
ATSC works with offset=0

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:04:03 -02:00
Chris Pascoe
3dfefc50ff V4L/DVB (6855): xc2028: select DTV78 firmware if tuning 7MHz VHF / 8MHz UHF
It seems that the DTV78 firmware is intended for use in locations where
VHF channels have 7MHz bandwidth and UHF channels have 8MHz bandwidth.
If we switch to DTV78 firmware when we detect this condition, we can
avoid firmware reloads when switching between VHF and UHF transponders.

Place the state for this in the control structure so that card drivers
can hint to us to use DTV78 firmware from the first tuning attempt.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:04:01 -02:00
Chris Pascoe
897b842296 V4L/DVB (6854): xc2028: be more specific about when applying offset for 7MHz channels
We have been inserting a mystery 500kHz offset for tuning 7MHz channels,
however some experimentation reveals it is only needed under certain
conditions with specific firmware combinations.  Document these and only
apply the offset when we know it is required.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:04:01 -02:00
Chris Pascoe
9ca01e780f V4L/DVB (6853): xc2028: check HAS_IF flag against table
When searching for the right S-Code table to load, check the HAS_IF flag
against the firmware we are checking instead of against the the "type"
requested.  We already ignore the scode type requested if the caller passed
an int_freq; this makes the search by frequency consistent with that behaviour.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:04:00 -02:00
Chris Pascoe
ad35ce9e3e V4L/DVB (6852): xc2028: s-code offset should not modify internal control structure
Don't modify the control structure that was provided at attach when applying
an offset to the S-Code, otherwise it will be incorrect on subsequent tunes.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:03:59 -02:00
Chris Pascoe
e026268870 V4L/DVB (6851): xc2028: include int_freq in firmware version display
Add "int_freq" to the debugging output when selecting firmware and the
HAS_IF flag when dumping firmware during load.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:03:59 -02:00
Mauro Carvalho Chehab
4bfae52b69 V4L/DVB (6827): Auto-selects D2633 for ATSC
ATSC standard-specific firmware is D2633 on both v2.5 and v2.7. Better to
auto-select this firmware, overriding ctrl.d2633.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:03:47 -02:00
Mauro Carvalho Chehab
5c15648a42 V4L/DVB (6683): Fix DVB compatibility
DVB-S is not supported. Also, there are some QAM6 firmwares for xc3028, but it
is reported that this doesn't work fine.

Thanks to Manu Abraham, Michael Krufky and Patrick Boettcher for their
insights.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:03:00 -02:00
Mauro Carvalho Chehab
63806eeb61 V4L/DVB (6677): Fix xc2028 driver for non OFDM
A previous patch implemented support for non-OFDM digital TV. However, the
previous bandwidth ofdm parameter were left at the code by mistake.

Thanks to Michael Krufky and Patrick Boettcher for noticing this mistake.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:58 -02:00
Mauro Carvalho Chehab
66c2d53db2 V4L/DVB (6676): Improve s-code support
s-code tables are related to IF frequency used for video demodulation.

The s-codes for analog are automatically loaded, according with video standard.
However, for digital, they will depend on the IF of the demoduler chip. IF of
the demoduler.

Before this patch, only a few IF's where possible to use. This patch allows
selecting any IF defined at firmware file.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:58 -02:00
Mauro Carvalho Chehab
b542dfdc9f V4L/DVB (6675): Allow selecting the proper SCode table for DTV
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:57 -02:00
Mauro Carvalho Chehab
d04aa54a27 V4L/DVB (6674): Add support for other DTV types
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:56 -02:00
Mauro Carvalho Chehab
d74cb25e42 V4L/DVB (6672): Add support for radio
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:54 -02:00
Mauro Carvalho Chehab
00deff1a07 V4L/DVB (6671): Avoids checking digital/analog at check_firmware
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: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:51 -02:00
Mauro Carvalho Chehab
cca8379811 V4L/DVB (6662): Fix standard selection for PAL
Not all 8MHz firmware are marked with F8MHz.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:40 -02:00
Mauro Carvalho Chehab
2800ae9cd6 V4L/DVB (6661): Remove firmware reload hack for analog
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: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:40 -02:00
Mauro Carvalho Chehab
71a2ee37e8 V4L/DVB (6660): Allow fully configuring xc3028 during xc2028_attach
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: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:39 -02:00
Mauro Carvalho Chehab
5add9a6f3c V4L/DVB (6659): Convert MTS to bitfield
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: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:39 -02:00
Mauro Carvalho Chehab
a5e9fe149a V4L/DVB (6658): Sets a default std, if not specified
Some drivers call set_frequency before selecting the video standard. Before
this patch, an invalid standard ID could be assumed.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:38 -02:00
Mauro Carvalho Chehab
c71d4bc512 V4L/DVB (6657): Fix standard selection for PAL/M, PAL/N, PAL/Nc and NTSC
Those standards use 6 MHz firmware.

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:37 -02:00
Chris Pascoe
1ad0b796a3 V4L/DVB (6652): xc2028: try non-8MHZ init1 firmware
When loading init1 firmware, there may not be an 8MHz specific version.
Load the non-8MHz version if it exists.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:35 -02:00
Chris Pascoe
11a9eff9b6 V4L/DVB (6651): xc2028: mask off type correctly when searching for standard-specific types
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:32 -02:00
Chris Pascoe
47bd5bc648 V4L/DVB (6650): xc2028: base firmwares should have std0
When loading BASE firmware, we must use std = 0.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:32 -02:00
Chris Pascoe
45819c381f V4L/DVB (6648): xc2028: add sleep hook
Add sleep method to enable putting the tuner into standby mode.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:31 -02:00
Chris Pascoe
8bf799a621 V4L/DVB (6647): xc2028: retry firmware load if tuner does not respond
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:31 -02:00
Chris Pascoe
e0f0b37a3e V4L/DVB (6646): xc2028: rework firmware (re)loading process
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:30 -02:00
Chris Pascoe
59a636e50f V4L/DVB (6645): xc2028: allow selection of D2633 firmware
Add a bit to select D2633 DTV firmware to struct xc2028_ctrl, so that it can
be enabled via .set_config.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:30 -02:00
Chris Pascoe
d7b22c5cfe V4L/DVB (6644): xc2028: use correct offset into scode firmware
When validating and loading SCODE firmware we need to take into account the
two-byte size header before each entry.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:29 -02:00
Chris Pascoe
b1535293dc V4L/DVB (6643): xc2028: use best match instead of first partial match during firmware selection
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:28 -02:00
Chris Pascoe
0a196b6fa9 V4L/DVB (6642): xc2028: don't duplicate max_len in priv
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:27 -02:00
Chris Pascoe
a44f1c43df V4L/DVB (6641): xc2028: correct tuner offset for 7MHz DTV
7MHz bandwidth DVB-T needs an adjusted offset at the PLL to ensure the IF
output is correctly centered.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:27 -02:00
Chris Pascoe
ddf1c5f1d7 V4L/DVB (6640): xc2028: correctly select 8MHz firmware
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:26 -02:00
Chris Pascoe
2ce4b3aa7c V4L/DVB (6639): xc2028: correct divisor length
The frequency divisor should only be four bytes long.  Also, display the
frequency and divisor correctly in the debug output.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:26 -02:00
Chris Pascoe
06fd82dc7b V4L/DVB (6638): xc2028: firmware loading cleanup
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:26 -02:00
Chris Pascoe
b32f9fb962 V4L/DVB (6637): xc2028: add missing break
Add break to stop us from following the default failure path even upon success.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:25 -02:00
Chris Pascoe
aa501be989 V4L/DVB (6636): xc2028: protect device list
Protect refcount changes and modifications to xc2028_list with a mutex.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:24 -02:00
Chris Pascoe
91240dd924 V4L/DVB (6635): xc2028: v4l2_std_id needs to be long long to display completely
Cast v4l2_std_id variables to unsigned long long so they will printk properly.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:23 -02:00
Chris Pascoe
3157ecef3b V4L/DVB (6634): xc2028: error messages missing whitespace
Fix some missing spaces in errors that may be emitted during attach failure.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:22 -02:00
Chris Pascoe
7d58d1117e V4L/DVB (6633): xc2028: make register reads atomic
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:22 -02:00
Chris Pascoe
e155d908f7 V4L/DVB (6632): xc2028: fix inverted logic in audio standard check
strcasecmp returns 0 on match, not true.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:22 -02:00