Commit Graph

3313 Commits

Author SHA1 Message Date
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
Maxim Levitsky
f36224d399 V4L/DVB (6670): V4L: saa7134: tvaudio cleanups
move some tv-audio initialization code out of tvaudio thread,
and call it on resume too.

Signed-off-by: Maxim Levitsky <maximlevitsky@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:46 -02:00
Maxim Levitsky
5c01203fd2 V4L/DVB (6669): Add few missing bits of code to saa7134_resume
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: Maxim Levitsky <maximlevitsky@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:45 -02:00
Maxim Levitsky
3203cb86d2 V4L/DVB (6668): Fix theoretical races between IRQ handler and .suspend/resume
*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: Maxim Levitsky <maximlevitsky@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:44 -02:00
Maxim Levitsky
0d65cd4f2b V4L/DVB (6667): Fix access to configuration space while in D3
pci_save_state should be called before pci_set_power_state
and pci_restore_state after pci_set_power_state

Signed-off-by: Maxim Levitsky <maximlevitsky@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:43 -02:00
Adrian Bunk
4c5efc1778 V4L/DVB (6665a): finish the VID_HARDWARE_* removal
This patch removes a few remainders of the VID_HARDWARE_* removal.

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
643d01fb38b6f376cced035549f4e193018776e7
2008-01-25 19:02:42 -02:00
Mauro Carvalho Chehab
c23f5949c0 V4L/DVB (6665): Fix CodingStyle
thanks to checkpatch.pl

Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:41 -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
a1dcd9de64 V4L/DVB (6656): zl10353: store frequencies in 0.1kHz to eliminate rounding errors
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:37 -02:00
Chris Pascoe
702a67624e V4L/DVB (6655): Add support for MT352-based DViCO FusionHDTV DVB-T NANO devices
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:37 -02:00
Chris Pascoe
c6e62a3a39 V4L/DVB (6654): mt352: support oversampled IF input
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:36 -02:00
Chris Pascoe
5ccaf90501 V4L/DVB (6653): Add support for the DViCO FusionHDTV NANO2 w/ZL10353 and firmware
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:36 -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
aeb012bbf4 V4L/DVB (6649): Add support for the DViCO FusionHDTV Dual Digital 4
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: 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
Chris Pascoe
47cc5b7810 V4L/DVB (6631): xc2028: eliminate i2c macro side-effects
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:21 -02:00
Chris Pascoe
794604c3ef V4L/DVB (6630): zl10353: calculate input frequency register instead of using hardcoded value
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:21 -02:00
Chris Pascoe
58d834ea89 V4L/DVB (6628): zl10353: Improve support for boards without a tuner on secondary i2c
Issue FSM_GO instead of TUNER_GO if there is no tuner attached to the
secondary i2c bus.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:21 -02:00
Chris Pascoe
a644e4a3e9 V4L/DVB (6627): CXUSB: handle write then read from different address
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:20 -02:00
Chris Pascoe
272479d7ab V4L/DVB (6626): CXUSB: support only-read i2c requests
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:20 -02:00
Chris Pascoe
13e001dfe3 V4L/DVB (6625): CXUSB: i2c transfer failure notification
The i2c master_xfer routine should return a negative result if not all
transfers completed successfully.

Signed-off-by: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:20 -02:00
Chris Pascoe
b17f109df1 V4L/DVB (6624): CXUSB: return control message transfer result to caller
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: Chris Pascoe <c.pascoe@itee.uq.edu.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:17 -02:00
Adrian Bunk
166fb6b472 V4L/DVB (6623): remove saa7134-oss
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: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:17 -02:00
Michael Krufky
255c1887cc V4L/DVB (6622): tda827x: prevent possible NULL pointer dereference in tda827xa_lna_gain
If tda827x_config hasn't been defined, exit the function.

Signed-off-by: Michael Krufky <mkrufky@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
2008-01-25 19:02:17 -02:00