There was a typo here so we return directly instead of freeing "hwinfo".
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Reviewd-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Tested-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

We checked "err" earlier.  These things seem to be left over code.
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Reviewd-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Tested-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This issue was reported by coccicheck using the semantic patch
at scripts/coccinelle/api/resource_size.cocci
Signed-off-by: NBenoit Taine <benoit.taine@lip6.fr>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This is a merge of big firewire audio stack updates by Takashi Sakamoto.

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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Currently mutex_unlock() is called in module's cleanup function. But after
cleaned up, this mutex is automatically released. So this function call
is meaningless.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Some variables were declared without static even if they're not referred
to from external files. This commit make them local symbols for better
information-hiding by file unit.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

To suppress 'sparse' warning.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

According to coding rule.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This commit adds suffix to register values of each device, to supress 'sparse'
warnings. Additionally, this commit changes offset values with integer literal.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

There are two modes for Fireworks, IEC 61883 compliant or Windows.
So it's better to use enum type instead of int to express the intension,
even if C language specification defines to handle enum variables as usual
integer.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The return value of memdup_user() should be passed to return correct error.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

__be32 value should not be assigned directly to bool value.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This commit fixes a big for loop count with array. The limitation of loop
count should be calcurated with the number of elements in the array, not
with the number of bytes.

Aditionally, this commit apply the same declaration as a prototype in header
for the array.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

'texts' is only used as source in strcpy
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When CONFIG_PM is disabled, the CONFIG_SND_HDA_POWER_SAVE_DEFAULT symbol
does not get defined, which causes a build error for the hda-tegra driver:

hda/hda_tegra.c:80:25: error: 'CONFIG_SND_HDA_POWER_SAVE_DEFAULT' undeclared here (not in a function)
 static int power_save = CONFIG_SND_HDA_POWER_SAVE_DEFAULT;
                         ^
/git/arm-soc/sound/pci/hda/hda_tegra.c:235:13: warning: 'hda_tegra_disable_clocks' defined but not used [-Wunused-function]
 static void hda_tegra_disable_clocks(struct hda_tegra *data)
             ^

This works around the problem by not referencing that macro
when CONFIG_PM is disabled. Instead, we assume that it's disabled
unconditionally and cannot be enabled at runtime.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Cc: Dylan Reid <dgreid@chromium.org>
Cc: Stephen Warren <swarren@nvidia.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When headphones are plugged in, force AFG and node 0x02
("Headphone Playback Volume") to D0 to avoid pop noises.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=76611Signed-off-by: NGabriele Mazzotta <gabriele.mzt@gmail.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

In post commit, a quirk of this firmware about transactions is reported.
This commit apply a workaround for this quirk.

They often fail transactions due to gap_count mismatch. This state is changed
by generating bus reset.

The fw_schedule_bus_reset() is an exported symbol in firewire-core. But there
are no header for public. This commit moves its prototype from
drivers/firewire/core.h to include/linux/firewire.h.

This mismatch still affects bus management before generating this bus reset.
It still takes a time to call driver's probe() because transactions are still
often failed.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Just powering on, these devices below wait to download firmware.
 - Firewire Audiophile
 - Firewire 410
 - Firewire 1814
 - ProjectMix I/O

But firmware version 5058 or later, flash memory in the device stores the
firmware. So this driver can enable these devices by sending a certain cue to
load the firmware.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

ALSA: bebob/firewire-lib: Add a quirk of wrong dbc in empty packet for M-Audio special Firewire series

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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This commit allows this driver to support all of models which Focusrite
produces with DM1000/BeBoB. They are:
 - Saffire
 - Saffire LE
 - SaffirePro 10 I/O
 - SaffirePro 26 I/O

This commit adds Focusrite specific operations:
1. Get source of clock
2. Get/Set sampling frequency
3. Get metering information

The driver uses these functionalities to read/write specific address by async
transaction.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This commit allows this driver to support all of models which Yamaha produced
with DM1000/BeBoB. They are:
 - GO44
 - GO46

This commit adds Yamaha specific operations. To get source of clock, AV/C Audio
Subunit command is used.

I note that their appearances are similar to some models of TerraTec; 'Go44' is
similar to 'PHASE 24 FW' and 'GO46' is similar to 'PHASE X24 FW'. But their
combination of Audio/Music subunits is a bit different.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This commit allows this driver to support all of models which Terratec produced
with DM1000/BeBoB. They are:
 - PHASE 24 FW
 - PHASE X24 FW
 - PHASE 88 Rack FW
 - EWS MIC2
 - EWS MIC4
 - Aureon 7.1 Firewire

For Phase series, this commit adds a Terratec specific operation. To get source
of clock. AV/C Audio Subunit command is used.

For EWS series and Aureon, this module uses normal operations.

Tested-by: Maximilian Engelhardt <maxi@daemonizer.de> (PHASE 24 FW)
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This commit adds a functionality to capture/playback PCM samples.

When AMDTP stream is already running for PCM or the source of clock is not
internal, available sampling rate is limited at current one.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This commit adds a functionality to capture/playback MIDI messages.

When no AMDTP streams are running, this module starts AMDTP stream at current
sampling rate for MIDI substream.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This commit adds proc interface to get these information for debugging:
 - firmware information
 - stream formation
 - current clock source and sampling rate
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This commit adds a new driver for BeBoB based devices with no specific
operations. Currently this driver just create/remove card instance according
to callbacks.

BeBoB is 'BridgeCo enhanced Breakout Box'. This is installed to firewire
devices with DM1000/DM1100/DM1500 chipset. It gives common way for host
system to handle BeBoB based devices.

Current supported devices:
 - Edirol FA-66/FA-101
 - PreSonus FIREBOX/FIREPOD/FP10/Inspire1394
 - BridgeCo RDAudio1/Audio5
 - Mackie Onyx 1220/1620/1640 (Firewire I/O Card)
 - Mackie d.2 (Firewire Option)
 - Stanton FinalScratch 2 (ScratchAmp)
 - Tascam IF-FW DM
 - Behringer XENIX UFX 1204/1604
 - Behringer Digital Mixer X32 series (X-UF Card)
 - Apogee Rosetta 200/Rosetta 400 (X-FireWire card)
 - Apogee DA-16X/AD-16X/DD-16X (X-FireWire card)
 - Apogee Ensemble
 - ESI Quotafire610
 - AcousticReality eARMasterOne
 - CME MatrixKFW
 - Phonix Helix Board 12 MkII/18 MkII/24 MkII
 - Phonic Helix Board 12 Universal/18 Universal/24 Universal
 - Lynx Aurora 8/16 (LT-FW)
 - ICON FireXon
 - PrismSound Orpheus/ADA-8XR

Devices possible to be supported if identifying IDs:
 - Apogee Mini-Me Firewire/Mini-DAC Firewire
 - Behringer F-Control Audio 610/1616
 - Cakewalk Sonar Power Studio 66
 - CME UF400e
 - ESI Quotafire XL
 - Infrasonic DewX/Windy6
 - Mackie Digital X Bus x.200/400
 - Phonic Helix Board 12/18/24
 - Phonic FireFly 202/302
 - Rolf Spuler Firewire Guitar
Tested-by: NDavid Henningsson <david.henningsson@canonical.com>
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This commit adds two functionality for hwdep interface, adds two parameters for
this driver, add a node for proc interface.

To receive responses from devices, this driver already allocate own callback
into initial memory space in host controller. This means no one can allocate
its own callback to the address. So this driver must give a way for user
applications to receive responses.

This commit adds a functionality to receive responses via hwdep interface. The
application can receive responses to read from this interface. To achieve this,
this commit adds a buffer to queue responses. The default size of this buffer is
1024 bytes. This size can be changed to give preferrable size to
'resp_buf_size' parameter for this driver. The application should notice rest
of space in this buffer because this driver don't push responses when this
buffer has no space.

Additionaly, this commit adds a functionality to transmit commands via hwdep
interface. The application can transmit commands to write into this interface.
I note that the application can transmit one command at once, but can receive
as many responses as possible untill the user-buffer is full.

When using these interfaces, the application must keep maximum number of
sequence number in command within the number in firewire.h because this driver
uses this number to distinguish the response is against the command by the
application or this driver.

Usually responses against commands which the application transmits are pushed
into this buffer. But to enable 'resp_buf_debug' parameter for this driver, all
responses are pushed into the buffer. When using this mode, I reccomend to
expand the size of buffer.

Finally this commit adds a new node into proc interface to output status of the
buffer.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This interface is designed for mixer/control application. To use 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This commit adds a functionality to capture/playback PCM samples.

When AMDTP stream is already running for PCM or the source of clock is not
internal, available sampling rate is limited at current one.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Fireworks has a quirk to ignore MIDI messages in data blocks more than 8.
This commit adds a flag for this quirk and codes to skip 8 or more data
blocks to transfer MIDI messages.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>