- 26 1月, 2008 40 次提交
-
-
由 Maxim Levitsky 提交于
*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: NMaxim Levitsky <maximlevitsky@gmail.com> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Maxim Levitsky 提交于
pci_save_state should be called before pci_set_power_state and pci_restore_state after pci_set_power_state Signed-off-by: NMaxim Levitsky <maximlevitsky@gmail.com> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Hans Verkuil 提交于
Signed-off-by: NHans Verkuil <hverkuil@xs4all.nl> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Adrian Bunk 提交于
This patch removes a few remainders of the VID_HARDWARE_* removal. Signed-off-by: NAdrian Bunk <bunk@kernel.org> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org> 643d01fb38b6f376cced035549f4e193018776e7
-
由 Mauro Carvalho Chehab 提交于
thanks to checkpatch.pl Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Mauro Carvalho Chehab 提交于
Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Mauro Carvalho Chehab 提交于
Not all 8MHz firmware are marked with F8MHz. Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Mauro Carvalho Chehab 提交于
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: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Mauro Carvalho Chehab 提交于
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: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Mauro Carvalho Chehab 提交于
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: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Mauro Carvalho Chehab 提交于
Some drivers call set_frequency before selecting the video standard. Before this patch, an invalid standard ID could be assumed. Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Mauro Carvalho Chehab 提交于
Those standards use 6 MHz firmware. Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
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: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
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: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
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: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
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: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
When loading init1 firmware, there may not be an 8MHz specific version. Load the non-8MHz version if it exists. Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
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: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
When loading BASE firmware, we must use std = 0. Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
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: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
Add sleep method to enable putting the tuner into standby mode. Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
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: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
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: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
Add a bit to select D2633 DTV firmware to struct xc2028_ctrl, so that it can be enabled via .set_config. Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
When validating and loading SCODE firmware we need to take into account the two-byte size header before each entry. Signed-off-by: NChris Pascoe <c.pascoe@itee.uq.edu.au> Signed-off-by: NMauro Carvalho Chehab <mchehab@infradead.org>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-
由 Chris Pascoe 提交于
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>
-