- 11 Oct, 2015 8 commits
-
-
Takashi Sakamoto authored
ALSA: firewire-digi00x: add support of asynchronous transaction for outgoing MIDI messages to physical controls In previous commit, asynchronous transaction for incoming MIDI messages from physical controls is supported. The physical controls may be controlled by receiving MIDI messages at a certain address. This commit supports asynchronous transaction for this purpose. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
ALSA: firewire-digi00x: add support of asynchronous transaction for incoming MIDI messages from physical controls Digi 00x series has two types of model; rack and console. The console models have physical controls. The model can transmit control messages. These control messages are transferred by asynchronous transactions to registered address. This commit supports the asynchronous transaction. Signed-off-by:
-
Takashi Sakamoto authored
This commit adds MIDI functionality to capture/playback MIDI messages from/to physical MIDI ports. These messages are transferred in isochronous packets. When no substreams request AMDTP streams to run, this driver starts the streams at current sampling rate. When other substreams start at different sampling rate, the streams are stopped temporarily, then start again at requested sampling rate. This operation can generate missing MIDI bytes, thus it's preferable to start PCM substreams at favorite sampling rate in advance. Digi 002/003 console also has a set of MIDI port for physical controls. These ports are added in later commits. Signed-off-by:
-
Takashi Sakamoto authored
In Digi 002/003 protocol, MIDI messages are transferred in the last data channel of data blocks. Although this data channel has a label of 0x80, it's not fully MIDI conformant data channel especially because the Counter field always zero independently of included MIDI bytes. The 4th byte of the data channel in LSB tells the number of included MIDI bytes. This byte also includes the number of MIDI port. Therefore, the data format in this data channel is: * 1st: 0x80 as label * 2nd: MIDI bytes * 3rd: 0 or MIDI bytes * 4th: the number of MIDI byte and the number of MIDI port This commit adds support of MIDI messages in data block processing layer. Like AM824 data format, this data channel has a capability to transfer more MIDI messages than the capability of phisical MIDI bus. Therefore, a throttle for data rate is required to prevent devices' internal buffer to overflow. Signed-off-by:
-
Takashi Sakamoto authored
Original code for 'DoubleOhThree' encoding was written with '__u8' type, while the type is usually used to export something to userspace. This commit replaces the type with 'u8'. Signed-off-by:
-
Keith A. Milner authored
This patch enables interrupt transfer mode for MIDI ports on newer Boss/Roland devices such as the GT-100/001 which support interrupt transfer on both IN and OUT MIDI endpoints. Previously this wasn't being enabled for these devices as the code was specifically looking for the scenario where the IN endpoint supported interrupt transfer and the OUT endpoint was bulk transfer. Newer devices support interrupt transfer for both endpoints. This has been tested on Boss devices GT-001, BR-80 and JS-8 and Roland VS-20. It would benefit from some regresison testing with other devices if possible. Signed-off-by:
Keith A. Milner <maillist@superlative.org> Signed-off-by:
-
Takashi Sakamoto authored
In firewire-lib, isochronous packet streaming is stopped when detecting wrong value for FMT field of CIP headers. Although this is appropriate to IEC 61883-1 and 6, some BeBoB based devices with vendors' customization use invalid value to FMT field of CIP headers in the beginning of streaming. $ journalctl snd-bebob fw1.0: Detect unexpected protocol: 01000000 8000ffff I got this log with M-Audio FireWire 1814. In this line, the value of FMT field is 0x00, while it should be 0x10 in usual AMDTP. Except for the beginning, these devices continue to transfer packets with valid value for FMT field, except for the beginning. Therefore, in this case, firewire-lib should continue to process packets. The former implementation of firewire-lib performs it. This commit loosens the handling of wrong value, to continue packet processing in the case. Fixes: 414ba022 ('ALSA: firewire-lib: add support arbitrary value for fmt/fdf fields in CIP header') Signed-off-by:
-
Julia Lawall authored
The structures of type snd_bebob_clock_spec, snd_bebob_rate_spec, snd_bebob_meter_spec, and snd_bebob_spec are never modified after they are initialized. Make them all const. Done with the help of Coccinelle. Signed-off-by:
Julia Lawall <Julia.Lawall@lip6.fr> Tested-by:
-
- 09 Oct, 2015 6 commits
-
-
Takashi Sakamoto authored
Currently, when asynchronous transactions finish in error state and retries, work scheduling and work running also continues. This should be canceled at fatal error because it can cause endless loop. This commit enables to cancel transferring MIDI messages when transactions encounter fatal errors. This is achieved by setting error state. Signed-off-by:
-
Takashi Sakamoto authored
Typically, the target devices have internal buffer to adjust output of received MIDI messages for MIDI serial bus, while the capacity of the buffer is limited. IEEE 1394 transactions can transfer more MIDI messages than MIDI serial bus can. This can cause buffer over flow in device side. This commit adds throttle to limit MIDI data rate by counting intervals between two MIDI messages. Usual MIDI messages consists of two or three bytes. This requires 1.302 to 1.953 mili-seconds interval between these messages. This commit uses kernel monotonic time service to calculate the time of next transaction. Signed-off-by:
-
Takashi Sakamoto authored
Currently, when two MIDI trigger callbacks can be called immediately, transactions for the second MIDI messages can be postpone till next trigger callback. This is not good for real-time message transmission. This commit schedules work again at response handling callback if the MIDI substream still includes untransferred MIDI messages. Signed-off-by:
-
Takashi Sakamoto authored
Currently, when waiting for a response, callers can start another transaction by scheduling another work. This is not good for error processing of transaction, especially the first response is too late. This commit serialize request/response transactions, by adding one boolean member to represent idling state. Signed-off-by:
-
Takashi Sakamoto authored
Some models receive MIDI messages via IEEE 1394 asynchronous transactions. In this case, MIDI messages are transferred in fixed-length payload. It's nice that firewire-lib module has common helper functions. This commit implements this idea. Each driver adds 'struct snd_fw_async_midi_port' in its instance structure. In probing, it should call snd_fw_async_midi_port_init() to initialize the structure with some parameters such as target address, the length of payload in a transaction and a pointer for callback function to fill the payload buffer. At 'struct snd_rawmidi_ops.trigger()' callback, it should call 'snd_fw_async_midi_port_run()' to start transactions. Each driver should ensure that the lifetime of MIDI substream continues till calling 'snd_fw_async_midi_port_finish()'. The helper functions support retries to transferring MIDI messages when transmission errors occur. When transactions are successful, the helper functions call 'snd_rawmidi_transmit_ack()' internally to consume MIDI bytes in the buffer. Therefore, Each driver is expected to use 'snd_rawmidi_transmit_peek()' to tell the number of bytes to transfer to return value of 'fill' callback. Signed-off-by:
-
Kosuke Tatsukawa authored
snd_seq_oss_readq_put_event() seems to be missing a memory barrier which might cause the waker to not notice the waiter and miss sending a wake_up as in the following figure. snd_seq_oss_readq_put_event snd_seq_oss_readq_wait ------------------------------------------------------------------------ /* wait_event_interruptible_timeout */ /* __wait_event_interruptible_timeout */ /* ___wait_event */ for (;;) { prepare_to_wait_event(&wq, &__wait, state); spin_lock_irqsave(&q->lock, flags); if (waitqueue_active(&q->midi_sleep)) /* The CPU might reorder the test for the waitqueue up here, before prior writes complete */ if ((q->qlen>0 || q->head==q->tail) ... __ret = schedule_timeout(__ret) if (q->qlen >= q->maxlen - 1) { memcpy(&q->q[q->tail], ev, sizeof(*ev)); q->tail = (q->tail + 1) % q->maxlen; q->qlen++; ------------------------------------------------------------------------ There are two other place in sound/core/seq/oss/ which have similar code. The attached patch removes the call to waitqueue_active() leaving just wake_up() behind. This fixes the problem because the call to spin_lock_irqsave() in wake_up() will be an ACQUIRE operation. I found this issue when I was looking through the linux source code for places calling waitqueue_active() before wake_up*(), but without preceding memory barriers, after sending a patch to fix a similar issue in drivers/tty/n_tty.c (Details about the original issue can be found here: https://lkml.org/lkml/2015/9/28/849). Signed-off-by:Kosuke Tatsukawa <tatsu@ab.jp.nec.com> Signed-off-by:
-
- 08 Oct, 2015 2 commits
-
-
Vinod Koul authored
Now that we have introduced the core fns we should make hda use these helpers Signed-off-by:
Vinod Koul <vinod.koul@intel.com> Signed-off-by:
-
Subhransu S. Prusty authored
The current codec helpers are local to hda code and needs to be moved to core so that other users can use it. The helpers to read/write the codec and to check the power state of widgets is copied Signed-off-by:
Subhransu S. Prusty <subhransu.s.prusty@intel.com> Signed-off-by:
-
- 05 Oct, 2015 2 commits
-
-
Jeeja KP authored
if the stream is decoupled and both link and host are used, while releasing the stream, need to check if link and host stream are not in use. This patch adds fix to check if the host/link stream is in used before coupling it back when releasing the stream. Signed-off-by:
Jeeja KP <jeeja.kp@intel.com> Signed-off-by:
-
Subhransu S. Prusty authored
Bits in LOSIDV need to be set to map the stream id for specific link. Fixing this by setting the required bits in the register. Signed-off-by:
-
- 04 Oct, 2015 1 commit
-
-
Takashi Sakamoto authored
Current ALSA BeBoB drivers has an entry for this model, while the value of vendor ID seems to be wrong according to an user's report. The vendor had released no updated firmware, thus we can judge that this model had not changed the content of its config ROM. It's reasonable to fix the ID according to the report. $ ./linux-firewire-utils/src/crpp < /sys/bus/firewire/devices/fw1/config_rom ROM header and bus information block ----------------------------------------------------------------- 400 0425720f bus_info_length 4, crc_length 37, crc 29199 404 31333934 bus_name "1394" 408 f0646122 irmc 1, cmc 1, isc 1, bmc 1, pmc 0, cyc_clk_acc 100, max_rec 6 (128), max_rom 1, gen 2, spd 2 (S400) 40c 00000ff2 company_id 00000f | 410 00004697 device_id f200004697 | EUI-64 00000ff200004697 root directory ----------------------------------------------------------------- 414 000859be directory_length 8, crc 22974 418 04000082 hardware version 41c 0c0083c0 node capabilities per IEEE 1394 420 03000ff2 vendor 424 8100000a --> descriptor leaf at 44c 428 17010065 model 42c 8100000d --> descriptor leaf at 460 430 13000910 version 434 d1000001 --> unit directory at 438 unit directory at 438 ----------------------------------------------------------------- 438 0004ccec directory_length 4, crc 52460 43c 1200a02d specifier id: 1394 TA 440 13010001 version: AV/C 444 17010065 model 448 8100000d --> descriptor leaf at 47c descriptor leaf at 44c ----------------------------------------------------------------- 44c 0004152a leaf_length 4, crc 5418 450 00000000 textual descriptor 454 00000000 minimal ASCII 458 4d61636b "Mack" 45c 69650000 "ie" descriptor leaf at 460 ----------------------------------------------------------------- 460 000612b5 leaf_length 6, crc 4789 464 00000000 textual descriptor 468 00000000 minimal ASCII 46c 4f6e7978 "Onyx" 470 20466972 " Fir" 474 65776972 "ewir" 478 65000000 "e" descriptor leaf at 47c ----------------------------------------------------------------- 47c 000612b5 leaf_length 6, crc 4789 480 00000000 textual descriptor 484 00000000 minimal ASCII 488 4f6e7978 "Onyx" 48c 20466972 " Fir" 490 65776972 "ewir" 494 65000000 "e" $ cat /proc/asound/card3/firewire/firmware Manufacturer: bridgeCo Protocol Ver: 1 Build Ver: 0 GUID: 0x00000FF200004697 Model ID: 0x82 Model Rev: 1 Firmware Date: 20040430 Firmware Time: 131527 Firmware ID: 0x10065 Firmware Ver: 2320 Base Addr: 0x20080000 Max Size: 1572864 Loader Date: 20040430 Loader Time: 112036 Reported-by:Andrzej Gansiniec <andrzej@gansiniec.pl> Signed-off-by:
-
- 02 Oct, 2015 7 commits
-
-
Takashi Sakamoto authored
This commit adds hwdep interface so as the other IEEE 1394 sound devices has. This interface is designed for mixer/control applications. By using this interface, an application can get information about firewire node, can lock/unlock kernel streaming and can get notification at starting/stopping kernel streaming. Signed-off-by:
-
Takashi Sakamoto authored
This commit adds PCM functionality to transmit/receive PCM samples. When one of PCM substreams are running or external clock source is selected, current sampling rate is used. Else, the sampling rate is changed as an userspace application requests. Signed-off-by:
-
Takashi Sakamoto authored
This commit adds streaming functionality for both direction. To utilize the sequence of the number of data blocks in packets, full duplex with synchronization is applied. Besides, TASCAM FireWire series allows drivers to decide which PCM data channels are enabled. For convenience, this driver always enable whole the data channels. Signed-off-by:
-
Takashi Sakamoto authored
TASCAM FireWire series uses non-blocking transmission for AMDTP packet streaming, while the format of data blocks is unique. The CIP headers includes specific value in FMT field and no SYT information. In transmitted packets, the first data channel represents event counter, and the last data channel has status and control information. The rest has 24bit PCM samples with right padding. In received packets, all of data channels include 16, 24, 32bit PCM samples. There's no other kind of information. This commit adds support for this protocol. For convenience, the size of PCM samples in outgoing packet is limited by 16 and 24bit. The status and control information will be supported in future commits. Signed-off-by:
-
Takashi Sakamoto authored
TASCAM FireWire series has certain registers for firmware information. This commit adds proc node to show the information. Signed-off-by:
-
Takashi Sakamoto authored
TASCAM FireWire series doesn't tell drivers their capabilities, thus the drivers should have model-dependent parameters and apply it to detected devices. This commit adds a structure to represent such parameters. Signed-off-by:
-
Takashi Sakamoto authored
This commit adds a new driver for TASCAM FireWire series. In this commit, this driver just creates/removes card instance according to bus event. More functionalities will be added in following commits. TASCAM FireWire series consists of: * PDI 1394P23 for IEEE 1394 PHY layer * PDI 1394L40 for IEEE 1394 LINK layer and IEC 61883 interface * XILINX XC9536XL * XILINX Spartan-II XC2S100 * ATMEL AT91M42800A Ilya Zimnovich had investigated TASCAM FireWire series in 2011, and discover some features of his FW-1804. You can see a part of his research in FFADO project. http://subversion.ffado.org/wiki/Tascam A part of my work are based on Ilya's investigation, while this series doesn't support the FW-1804, because of a lack of config ROM information and its protocol detail, especially for PCM channels. I observed that FW-1884 and FW-1082 don't work properly with 1394 OHCI controller based on VT6315. The controller can actually communicate packets to these models, while these models generate no sounds. It may be due to the PHY/LINK layer issues. Using 1394 OHCI controller produced by the other vendors such as Texas Instruments may work. Or adding another node on the bus. Signed-off-by:
-
- 30 Sep, 2015 9 commits
-
-
Takashi Sakamoto authored
Digi 002/003 family uses asynchronous transaction for messaging. The address to transmit this message is stored on a certain register. This commit allocates a range of address on OHCI 1394 host controller to handle the messaging. As long as I know, the purpose of this message seems to notify lost of synchronization. While, the meaning of content of the message is not clear. Actual examples of this messaging: * When clock source is set as internal: - 0x00007051 - 0x00007052 - 0x00007054 - 0x00007057 - 0x00007058 * When clock source is set as somewhat external: - 0x00009000 - 0x00009010 - 0x00009020 - 0x00009021 - 0x00009022 The lost often occurs when using internal clock source. In this case, users hear sounds with quite short gap every several minutes. In fact, the lost is recovered temporarily. When using with external clock source, the lost seems not to occur. The mechanism is not clear yet. Signed-off-by:
-
Takashi Sakamoto authored
This commit adds hwdep interface so as the other sound drivers for units on IEEE 1394 bus have. This interface is designed for mixer/control applications. By using this interface, an application can get information about firewire node, can lock/unlock kernel streaming and can get notification at starting/stopping kernel streaming. Signed-off-by:
-
Takashi Sakamoto authored
This commit adds PCM functionality to transmit/receive PCM samples. Any PCM substreams are jointed because incoming/outgoing AMDTP streams are bound. When one of PCM substream is running or external clock source is selected, current sampling rate is used. Else, the sampling rate is changed as an userspace application requests. Signed-off-by:
-
Takashi Sakamoto authored
This commit adds proc node to show current clock status for debugging. As long as testing Digi 002 rack, registers can show local clock rate, local clock source. When external clock input such as S/PDIF is connected, the registers show the detection and external clock rate. Additionally, the registers show the mode of optical digital input interface. Although, a tester with Digi 003 rack reports this makes no sense. Further investigation is required for Digi 003 series. Besides, in Digi 002 rack, the S/PDIF format must be IEC 60958-4, so-called professional. Signed-off-by:
-
Takashi Sakamoto authored
This commit adds a functionality to manage streaming. The streaming is not controlled by CMP in IEC 61883-6. It's controlled by IEEE 1394 write transaction to certain addresses. Several clock sources are available, while there're no differences about packet transmission. The value of SYT field in transmitted packets is always zero. Thus, streams in both direction don't build synchronization. And the device always requires received packets to transmit packets. This driver keeps to transfer outgoing stream even if they're not required. Signed-off-by:
-
Takashi Sakamoto authored
Digi 002/003 family uses its own format for data blocks. The format is quite similar to AM824 in IEC 61883-6, while there're some differences: * The Valid Bit Length (VBL) code is always 0x40 in Multi-bit Linear Audio (MBLA) data channel. * The first data channel includes MIDI messages, against IEC 61883-6 recommendation. * The Counter field is always zero in MIDI conformant data channel. * Sequence multiplexing in IEC 61883-6 is not applied to the MIDI conformant data channel. * PCM samples are scrambled in received AMDTP packets. We call the way as Double-Oh-Three (DOT). The algorithm was discovered by Robin Gareus and Damien Zammit in 2012. This commit adds data processing layer to satisfy these differences. There's a quirk about transmission mode for received packets. When this driver applies non-blocking mode to outgoing packets with isochronous channel 2 or more, after 15 to 20 seconds since playbacking, any PCM samples causes noisy sound on the device. With isochronous channel 0 or 1, this doesn't occur. As long as I investigated, this quirk is not observed when applying blocking mode to the received packets. This driver applies blocking mode to outgoing packets, while non-blocking mode to incoming packgets. Signed-off-by:
-
Takashi Sakamoto authored
This commit adds a new driver for Digidesign 002/003 family. This commit just creates/removes card instance according to bus event. More functions will be added in following commits. Digidesign 002/003 family consists of: * Agere FW802B for IEEE 1394 PHY layer * PDI 1394L40 for IEEE 1394 LINK layer and IEC 61883 interface * ALTERA ACEX EP1K50 for IEC 61883 layer and DSP controller * ADSP-21065L for signal processing [minor cleanup using skip_spaces() by tiwai] Signed-off-by:
-
Takashi Iwai authored
-
Takashi Iwai authored
The lack of const leads to a compile warning after merging i915 upstream tree: drivers/gpu/drm/i915/intel_audio.c:147:13: note: expected 'struct drm_display_mode *' but argument is of type 'const struct drm_display_mode *' Reported-by:
kbuild test robot <fengguang.wu@intel.com> Reviewed-by:
Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by:
-
- 29 Sep, 2015 5 commits
-
-
kbuild test robot authored
Signed-off-by:
-
Takashi Iwai authored
snd_pcm_release_substream() always calls hw_free op when the stream was opened. This is superfluous in most cases because it's been already released via explicit hw_free ioctl. Although this double call is usually OK as this callback should be written to be called multiple times, it's better to avoid superfluous calls. Reported-by:
-
Takashi Iwai authored
-
Takashi Sakamoto authored
This commit moves the codes related to data block processing from packet streaming layer to AM824 layer. Each driver initializes amdtp stream structure for AM824 data block by calling amdtp_am824_init(). Then, a memory block is allocated for AM824 specific structure. This memory block is released by calling amdtp_stream_destroy(). When setting streaming parameters, it calls amdtp_am824_set_parameters(). When starting packet streaming, it calls amdtp_stream_start(). When stopping packet streaming, it calls amdtp_stream_stop(). Signed-off-by:
-
Takashi Sakamoto authored
This commit renames some macros just related to AM824 format. In later commit, they're moved to AM824 layer. Signed-off-by:
-
