- 25 Jan, 2008 40 commits
-
-
Chris Pascoe authored
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>
-
Chris Pascoe authored
7MHz bandwidth DVB-T needs an adjusted offset at the PLL to ensure the IF output is correctly centered. Signed-off-by:
-
Chris Pascoe authored
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 authored
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 authored
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 authored
Add break to stop us from following the default failure path even upon success. Signed-off-by:
-
Chris Pascoe authored
Protect refcount changes and modifications to xc2028_list with a mutex. Signed-off-by:
-
Chris Pascoe authored
Cast v4l2_std_id variables to unsigned long long so they will printk properly. Signed-off-by:
-
Chris Pascoe authored
Fix some missing spaces in errors that may be emitted during attach failure. Signed-off-by:
-
Chris Pascoe authored
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 authored
strcasecmp returns 0 on match, not true. Signed-off-by:
-
Chris Pascoe authored
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 authored
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 authored
Issue FSM_GO instead of TUNER_GO if there is no tuner attached to the secondary i2c bus. Signed-off-by:
-
Chris Pascoe authored
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 authored
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 authored
The i2c master_xfer routine should return a negative result if not all transfers completed successfully. Signed-off-by:
-
Chris Pascoe authored
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: -
Adrian Bunk authored
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:
-
Michael Krufky authored
If tda827x_config hasn't been defined, exit the function. Signed-off-by:
Michael Krufky <mkrufky@linuxtv.org> Signed-off-by:
-
Michael Krufky authored
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:
-
Michael Krufky authored
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:
-
Aidan Thornton authored
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:
Aidan Thornton <makosoft@googlemail.com> Signed-off-by:
-
Joe Perches authored
Signed-off-by:
Joe Perches <joe@perches.com> Signed-off-by:
-
Joe Perches authored
Signed-off-by:
-
Joe Perches authored
Signed-off-by:
-
Mauro Carvalho Chehab authored
Signed-off-by: -
Mauro Carvalho Chehab authored
Signed-off-by: -
Michel Ludwig authored
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:
Michel Ludwig <michel.ludwig@gmail.com> Signed-off-by:
-
Michel Ludwig authored
Removes uneeded parameters and adds an structure for passing the parameters This patch is co-authored by Mauro Carvalho Chehab. Signed-off-by:
-
Michel Ludwig authored
Signed-off-by:
-
Michael Krufky authored
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:
-
Michael Krufky authored
Signed-off-by:
-
Mauro Carvalho Chehab authored
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: -
Brandon Philips authored
Signed-off-by:
Brandon Philips <bphilips@suse.de> Signed-off-by:
-
Brandon Philips authored
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:
-
Mauro Carvalho Chehab authored
Signed-off-by: -
Mauro Carvalho Chehab authored
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: -
Mauro Carvalho Chehab authored
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: -
Mauro Carvalho Chehab authored
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:
-
