In former commit, drivers in ALSA firewire stack always starts IT context
before IR context. If IR context starts after packets are transmitted by
peer unit, packet discontinuity may be detected because the context starts
in the middle of packet streaming. This situation is rare because IT
context usually starts immediately. However, it's better to solve this
issue. This is suppressed with CIP_SKIP_INIT_DBC_CHECK flag.
This commit enables the same feature as CIP_SKIP_INIT_DBC_CHECK.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Windows driver for BeBoB-based models mostly wait for transmitted packets,
then transfer packets to the models. This looks for the relationship
between incoming packets and outgoing packets to synchronize the sequence
of presentation timestamp.
However, the sequence between packets of both direction has no
relationship. Even if receiving NO-DATA packets, the drivers transfer
packets with meaningful value in SYT field. Additionally, the order of
starting packets is always the same, independently of the source of clock.
The corresponding driver is expected as a generator of presentation
timestamp and these models can select it as a source of sampling clock.
This commit drops reusing SYT sequence from ALSA bebob driver. The driver
always transfer packets with presentation timestamp generated by ALSA
firewire stack, without re-using the sequence of value in SYT field in
incoming packets to outgoing packets.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
DM1000/DM1100/DM1500 chipsets transfer packets with discontinue value in
'dbc' field of CIP header. For ALSA bebob driver, this makes its bus-reset
handler meaningless, because the discontinuity is detected quite earlier
than executing the handler.
This commit gives up updating streams at the bus reset handler.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
The counter is incremented/decremented in critical section protected with
mutex. Therefore, no need to use atomic_t.
This commit changes the type to unsigned int.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Currently, critical section is protected by mutex in functions of
fireworks_stream.c. Callers increments/decrements substreams counter
before calling the functions. Moving mutex to the callers code allows
to change type of the substream counter from atomic_t to unsigned int.
This commit is a preparation for obsoleting usage of atomic_t for
substream counter.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
At bus-reset, DM1000/DM1100/DM1500 chipsets transfer packets with
discontinuous value in 'dbc' field of CIP header. In this case, packet
streaming layer in firewire-lib module stops streaming and set XRUN to PCM
substream.
In ALSA, PCM applications are notified the XRUN status by the return value
of ALSA PCM interface. They can recover this state by executing
snd_pcm_prepare(), then PCM drivers' prepare handler is called, and start
new PCM substream. For ALSA BeBoB driver, the handler establishes new
connections and start new AMDTP streaming.
Unfortunately, neither the PCM applications nor the driver know the reason
of XRUN. The driver gets to know the reason when update handler is called
by IEEE 1394 bus driver. As long as I tested, the order of below events are
not fixed:
* Detecting packet discontinuity in tasklet context of OHCI 1394 driver
* Calling prepare handler in process context of ALSA PCM application
* Calling update handler in kthread context of IEEE 1394 bus driver
The unpredictable order is disadvantage for the driver to be compliant to
CMP. In IEC 61883-1, new CMP establish operations should be done 1 sec
(isoc_resource_delay) after bus-reset. Within 1 sec, CMP restore
operations are allowed. For this reason, in former commit ('b6bc812327aa:
ALSA: bebob/firewire-lib: Add a quirk for discontinuity at bus reset'),
the process context is forced to wait for executing update handler. The
process context wait for bus-reset up to 1 sec. This commit solves the
issue, while causes more disadvantages. For PCM applications, calling
snd_pcm_prepare() for recovering XRUN state takes more time and the driver
got a bit complicated code, while the recovery is not always successful.
As long as I tested, DM1000/DM1100/DM1500 and BeBoB firmware can allow
drivers to establish new connections just after bus reset. Furthermore,
any FCP transactions are handled correctly. Therefore, the driver don't
need to wait for bus reset handler for starting new streaming.
This commit removes the codes to reduce maintenance cost.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
The return type "unsigned int" was used by the get_formation_index function
despite of the aspect that it will eventually return a negative error code.
So, change to signed int and get index by reference in the parameters.
Done with the help of Coccinelle.
[Fix the missing braces suggested by Julia Lawall -- tiwai]
Signed-off-by: Lucas Tanure <tanure@linux.com>
Reviewed-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Tested-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
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: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Reviewed-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
This commit renames some macros just related to AM824 format. In later
commit, they're moved to AM824 layer.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
In IEC 61883-6, several types of data are available in AM824 format. The
data is transferred in each data channel. The position of data channel in
data block differs depending on model.
Current implementation has an array to map the index of data channel in an
data block to the position of actual data channel. The implementation
allows each driver to access the mapping directly.
In later commit, the mapping is in specific structure pushed into an
opaque pointer. Helper functions are required.
This commit adds the helper functions for this purpose. In IEC 61883-6,
AM824 format supports many data types, while this specification easily
causes over-engineering. Current AM824 implementation is allowed to handle
two types of data, Multi Bit Linear Audio data (=PCM samples) and MIDI
conformant data (=MIDI messages).
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
The value of FDF field in CIP header is protocol-dependent. Thus, it's
better to allow data block processing layer to decide the value in any
timing.
In AM824 data format, the value of FDF field in CIP header indicates
N-flag and Nominal Sampling Frequency Code (sfc). The N-flag is for
switching 'Clock-based rate control mode' and 'Command-based rate control
mode'. In our implementation, 'Clock-based rate control mode' is just
supported. Therefore, When sampling transfer frequency is decided, then
the FDF can be set.
This commit replaces 'amdtp_stream_set_parameters' with
'amdtp_am824_set_parameters' to set the FDF. This is the same timing
to decide the ration between the number of data blocks and the number of
PCM frames.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
This commit adds data block processing layer for AM824 format. The new
layer initializes streaming layer with its value for fmt field.
Currently, most implementation of data block processing still remains
streaming layer. In later commits, these codes will be moved to the layer.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
In IEC 61883-6, one data block represents one event. In ALSA, the event is
one PCM frame. Therefore, when processing one data block, current
implementation counts one PCM frame.
On the other hand, Dice platform has a quirk called as 'dual wire' at
higher sampling rate. In detail, see comment of commit 6eb6c81eee
("ALSA: dice: Split stream functionality into a file").
Currently, to handle this quirk, AMDTP stream structure has a
'double_pcm_frames' member. When this is enabled, two PCM frames are
counted. Each driver set this flag by accessing the structure member
directly.
In future commit, some members related to AM824 data block will be moved
to specific structure, to separate packet streaming layer and data block
processing layer. The access will be limited by opaque pointer.
For this reason, this commit adds an argument into
amdtp_stream_set_parameter() to set the flag.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Currently, amdtp_stream_set_parameters() returns no error even if wrong
arguments are given. This is not good for streaming layer because drivers
can continue processing ignoring capability of streaming layer.
This commit changes this function to return error code.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Behringer FCA610 transmits packets with periodic noisy PCM samples
when receiving no streams, and generates a bit noisy sound.
ALSA BeBoB driver is programmed to establish both in/out connections
when starting streaming, then transfers packets as userspace applications
requested. This means that there's a case that one of incoming/outgoing
streams is running, to save CPU and bandwidth usage. Although, it's natural
to start transferring packets in both direction.
This commit makes this driver to keeps duplex streams always.
Tested-by: Kim Tore Jensen <kim@incendio.no>
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Behringer FCA610 and UFX1604 is confirmed to require more time till
transmitting packets after establishing connections. This seems to
be a quirk of DM1500 ASIC which ArchWave produced.
For this quirk, this commit extends the time to wait up to 2 seconds.
As a result, in worst cases, below userspace functions require 2 seconds
to return.
- snd_pcm_prepare()
- snd_pcm_hw_params()
- snd_pcm_recover()
Tested-by: Kim Tore Jensen <kim@incendio.no>
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
In previous commits, this driver can detect the source of clock as mush
as possible. SYT-Match mode is also available.
This commit purge the restriction.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
This commit changes function prototype and its processing. As a result,
function caller can execute additional processing according to detected
clock source.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
With BeBoB version 3, current ALSA BeBoB driver detects the type of
current clock signal source wrongly. This is due to a lack of proper
implementation to parse the information.
This commit renews the parser. As a result, this driver detects
SYT-Match clock signal, thus it can start streams with two modes;
SYT-Match mode and the others. SYT-Match mode will be supported in future
commits.
There's a constrain about detected internal/external clock source.
When detecting external clock source, this driver allows userspace
applications to use current sampling rate only. This is due to consider
abour synchronization to external clock sources such as S/PDIF, ADAT or
word-clock.
According to several information from some devices, I guesss that the
internal clock of most devices synchronize to IEEE 1394 cycle start
packet. In this case, by a usual way, it's detect as 'Sync type
of output Music Sub-Unit' connected to 'Sync type of PCR output Unit
(oPCR)', and this driver judges it as internal clock. Therefore,
userspace applications is allowed to request arbitrary supported sampling
rates.
On the other hand, several devices based on BeBoB version 3 have
additional internal clock. In this case, by a usual way, it's detect as
'Sync/Additional type of External input Unit'. Unfortunately, there's no
way to distinguish this sync type from the other external clock sources
such as word-clock. In this case, this driver handles it as external and
userspace applications is forced to use current sampling rate.
I note that when the source of clock is detected as 'Isochronous stream
type of input PCR[0]', it's under 'SYT-Match' mode. In this mode, the
synchronization clock is generated according to SYT-series in received
packets. In this case, this driver generates the series by myself. I
experienced this mode often make the device silent suddenly during
playbacking. This means that the mode is easy to lost synchronization.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
A part of these drivers, especially BeBoB driver, are programmed to wait
some events. Thus the drivers should not destroy any data in .remove()
context.
This commit moves some destructors from 'struct fw_driver.remove()' to
'struct snd_card.private_free()' to shutdown safely.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Cc: <stable@vger.kernel.org> # 3.19+
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Currently stream destructor in each driver has a problem to be called in
a context in which sound card object is released, because the destructors
call amdtp_stream_pcm_abort() and touch PCM runtime data.
The PCM runtime data is destroyed in application's context with
snd_pcm_close(), on the other hand PCM substream data is destroyed after
sound card object is released, in most case after all of ALSA character
devices are released. When PCM runtime is destroyed and PCM substream is
remained, amdtp_stream_pcm_abort() touches PCM runtime data and causes
Null-pointer-dereference.
This commit changes stream destructors and allows each driver to call
it after releasing runtime.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Cc: <stable@vger.kernel.org> # 3.19+
Signed-off-by: Takashi Iwai <tiwai@suse.de>
There are several devices that expect to receive MIDI data only in the
first eight data blocks of a packet. If the driver restricts the data
rate to the allowed rate (as mandated by the specification, but not yet
implemented by this driver), this happens naturally. Therefore, there
is no reason to ever try to use more data packets with any device.
Signed-off-by: Clemens Ladisch <clemens@ladisch.de>
Reviewed-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Tested-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
snd_bebob_stream_check_internal_clock() may get an id from
saffirepro_both_clk_src_get (via clk_src->get()) that was uninitialized.
a) make logic in saffirepro_both_clk_src_get explicit
b) test if id used in snd_bebob_stream_check_internal_clock matches array size
[fixed missing signed prefix to *_maps[] by tiwai]
Signed-off-by: Christian Vogel <vogelchr@vogel.cx>
Reviewed-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
All assignment for local variables in these functions are not related to
critical section.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
ARRAY_SIZE() was intended here instead of sizeof(). The
"bridgeco_freq_table" array holds integers so the original condition is
never true.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewd-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Tested-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Currently bebob driver apply Raw Audio Data channel (in IEC 61883-1:2002,
Multi Bit Linear Audio Data channel in IEC 61883-6:20005) to IEC 60958
Conformant Data channel because both fireworks and bebob based devices
can handle it by ignoring each label.
This patch improves a comment about this.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
The second argument of snd_efw_command_get_sampling_rate() means sampling
rate and its type is 'unsigned int'. But 'int' variable is passed as parameter.
It's better to apply the same type for the variable as its argument.
Similally, the type of variable for snd_efw_command_get_clock_source() and
avc_bridgeco_get_plug_type() should be the same type as each argument.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Originally, I intent to this argument given with 'struct snd_pcm_runtime.rate'
or params_rate(). They return value of 'unsigned int'. So 'unsigned int' is
better for the type of this argument.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
The firmwares for M-Audio Firewire 410/1814 and ProjectMix I/O has a quirk to
ignore MIDI messages in data blocks more than 8. This commit uses a flag which
Fireworks uses for a similar quirk.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
M-Audio Firewire 1814 has a quirk, ProjectMix I/O also has. They transmit
empty packet with wrong value of dbc incremented by 8 at high sampling rate.
According to IEC 61883-1, this value should be the same as the one in
previous packet.
This commit adds a flag named as CIP_EMPTY_HAS_WRONG_DBC. With flag, the value
of dbc in empty packet is overwittern by an expected value.
This is an example of this quirk:
CIP Header 0 CIP Header 1 Payload size
010D0000 9004F759 210
010D0010 90040B59 210
010D0020 90042359 210
01020028 9004FFFF 2 <-
010D0030 90043759 210
010D0040 90044B59 210
010D0050 90046359 210
01020058 9004FFFF 2 <-
010D0060 90047759 210
010D0070 90048B59 210
010D0080 9004A359 210
01020088 9004FFFF 2 <-
010D0090 9004B759 210
010D00A0 9004CB59 210
010D00B0 9004E359 210
010200B8 9004FFFF 2 <-
010D00C0 9004F759 210
010D00D0 90040B59 210
010D00E0 90042359 210
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
This commit allows this driver to support some models which M-Audio produces
with DM1000 but its firmware is special. They are:
- Firewire 1814
- ProjectMix I/O
They have heavily customized firmware. The usual operations can't be applied to
them. For this reason, this commit adds a model specific member to 'struct
snd_bebob' and some model specific functions. Some parameters are write-only so
this commit also adds control interface for applications to set them.
M-Audio special firmware quirks:
- Just after powering on, they wait to download firmware. This state is
changed when receiving cue. Then bus reset is generated and the device is
recognized as a different model with the uploaded firmware.
- They don't respond against BridgeCo AV/C extension commands. So drivers
can't get their stream formations and so on.
- They do not start to transmit packets only by establishing connection but
also by receiving SIGNAL FORMAT command.
- After booting up, they often fail to send response against driver's request
due to mismatch of gap_count.
This module don't support to upload firmware.
Tested-by: Darren Anderson <darrena092@gmail.com> (ProjectMix I/O)
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
This commit allows this driver to support some models which M-Audio produces
with DM1000/DM1000E with usual firmware. They are:
- Firewire 410
- Firewire AudioPhile
- Firewire Solo
- Ozonic
- NRV10
- FirewireLightBridge
According to a person who worked in BridgeCo, some models are produced with
'Pre-BeBoB'. This means that these products were released before BeBoB was
officially produced, and later BeBoB specification was formed. So these models
have some quirks.
M-Audio usual firmware quirks:
- Just after powering on, 'Firewire 410' waits to download firmware. This
state is changed when receiving cue. Then bus reset is generated and the
device is recognized as a different model with the uploaded firmware.
- 'Firewire Audiophile' also waits to download firmware but its
vendor id/model id is the same as the one after loading firmware.
- The information of channel mapping for MIDI conformant data channel is
invalid against BridgeCo specification.
This commit adds some codes for these quirks but don't support to upload
firmware.
This commit also adds specific operations to get metering information. The
metering information also includes status of clock synchronization if the model
supports to switch source of clock.
The specification of FirewireLightBridge is unknown. So in this time, normal
operations are applied for this model.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
This commit is for some devices which have its own operations or quirks.
Many functionality should be implemented in user land. Then this commit adds
functionality related to stream such as sampling frequency or clock source. For
help to debug, this commit adds the functionality to get metering information
if it's available.
To help these functionalities, this commit adds some AV/C commands defined in
'AV/C Audio Subunit Specification (1394TA).
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
This interface is designed for mixer/control application. By using hwdep
interface, the 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 <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Normal BeBoB firmware has a quirk. When receiving bus reset, it transmits
packets with discontinuous value in dbc field.
This causes two situation, one is to abort streaming by firewire-lib as a
result of detecting the discontinuity. Another is to call driver's .update()
because of bus reset. These two is generated independently. (The former
depends on isochronous stream and the latter depends on IEEE1394 bus driver.)
When BeBoB driver works with XRUN-recoverable applications, this situation
looks like stream_start_duplex() call followed by stream_update_duplex() call
because applications will call snd_pcm_prepare() immediately at XRUN.
To update connections and streams at first, this commit use completion. When
queueing error occurs, stream_start_duplex() is forced to wait maximum
1000msec. During this, when .update() is called, the completion is waken and
stream_start_duplex() is processed without breaking connections.
At bus reset, stream_start_duplex() shouldn't break/establish connections and
stream_update_duplex() should update connections because a caller of
fw_iso_resources_allocate() is responsible for calling
fw_iso_resources_update() on bus reset.
This commit also adds a flag, which has an effect to skip checking continuity
for first packet. This flag is useful for BeBoB quirk to start handling packets
during streaming.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
This commit adds management functionality for connections and streams.
BeBoB uses CMP to manage connections and uses AMDTP for streams.
This commit also adds some BridgeCo's AV/C extension commands. There are some
BridgeCo's AV/C extension commands but this commit just uses below commands
to get device's capability and status:
1.Extended Plug Info commands
- Plug Channel Position Specific Data
- Plug Type Specific Data
- Cluster(Section) Info Specific Data
- Plug Input Specific Data
2.Extended Stream Format Information commands
- Extended Stream Format Information Command - List Request
For Extended Plug Info commands for Cluster Info Specific Data, I pick up
'section' instead of 'cluster' from document to prevent from misunderstanding
because 'cluster' is also used in IEC 61883-6.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
