When any of AMDTP stream data are not initialized and private data is
going to be released, WARN_ON() in amdtp_stream_destroy() is hit and
dump messages. This may take users irritated.

This commit fixes the bug to skip releasing when it's not initialized.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

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

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

Setting the format of PCM substream to AMDTP stream structure is important
to set a handler to copy actual PCM samples between buffers. The
processing should be in data block processing layer because essentially
it has no relationship to packet streaming.

This commit renames PCM format setting function to prepare for integrating
AM824 layer.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

In IEC 61883-6, PCM frames are transferred in Multi Bit Linear Audio data
channel. The data channel transfers 16/20/24 bit PCM samples. Thus, PCM
substream has a constrain about it.

This commit moves codes related to the constraint from packet streaming
layer to AM824 data block processing layer.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

In later commit, data block processing layer will be newly added. This
layer will be named as 'amdtp-am824'.

This commit renames current amdtp file to amdtp-stream, to distinguish it
from the new layer.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Some vendor specific protocol uses its own value for fmt/fdf fields in
CIP header.

This commit support to set arbitrary values for the fields.

In IEC 61883-6, NO-DATA code is defined for FDF field. A packet with this
code includes no data even if it includes some data blocks. This commit
still leaves a condition to handle this special packet.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

ALSA: firewire-lib: add helper functions as interfaces between packet streaming layer and data block processing layer

ALSA PCM framework uses PCM buffer with a concept of 'period' to
synchronize userspace operations to hardware for nearly-realtime
processing. Each driver implements snd_pcm_period_elapsed() to tell across
of the period boundary to ALSA PCM middleware. To call the function, some
drivers utilize hardware interrupt handlers, the others count handled PCM
frames.

Drivers for sound units on IEEE 1394 bus are the latter. They use two
buffers; PCM buffer and DMA buffer for IEEE 1394 isochronous packet. PCM
frames are copied between these two buffers and 'amdtp_stream' structure
counts the handled PCM frames. Then, snd_pcm_period_elapsed() is called if
required.

Essentially, packet streaming layer should not be responsible for PCM
frame processing. The PCM frame processing should be handled in each data
block processing layer as a result of handling data blocks. Although, PCM
frame counting is a common work for all of protocols which ALSA firewire
stack is going to support.

This commit adds two new helper functions as interfaces between packet
streaming layer to data block processing layer. In future, each data block
processing layer implements these functions. The packet streaming layer
calls data block processing layer per packet by calling the functions. The
data block processing layer processes data blocks and PCM frames, and
returns the number of processed PCM frames. Then the packet streaming layer
calculates handled PCM frames and calls snd_pcm_period_elapsed().
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

In future commit, interface between data block processing layer and packet
stream processing layer is defined. These two layers communicate the
number of data blocks and the number of PCM frames.

The data block processing layer has a responsibility for calculating the
number of PCM frames. Therefore, 'dual wire' of Dice quirk should be
handled in data block processing layer.

This commit adds a member of 'frame_multiplier'. This member represents
the ratio of the number of PCM frames against the number of data blocks.
Usually, the value of this member is 1, while it's 2 in Dice's 'dual wire'.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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 6eb6c81e
("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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Fireworks uses TSB43CB43(IceLynx-Micro) as its IEC 61883-1/6 interface.
This chip includes ARM7 core, and loads and runs program. The firmware
is stored in on-board memory and loaded every powering-on from it.

Echo Audio ships several versions of firmwares for each model. These
firmwares have each quirk and the quirk changes a sequence of packets.

As long as I investigated, AudioFire2/AudioFire4/AudioFirePre8 have a
quirk to transfer a first packet with 0x02 in its dbc field. This causes
ALSA Fireworks driver to detect discontinuity. In this case, firmware
version 5.7.0, 5.7.3 and 5.8.0 are used.

Payload  CIP      CIP
quadlets header1  header2
02       00050002 90ffffff <-
42       0005000a 90013000
42       00050012 90014400
42       0005001a 90015800
02       0005001a 90ffffff
42       00050022 90019000
42       0005002a 9001a400
42       00050032 9001b800
02       00050032 90ffffff
42       0005003a 9001d000
42       00050042 9001e400
42       0005004a 9001f800
02       0005004a 90ffffff
(AudioFire2 with firmware version 5.7.)

$ dmesg
snd-fireworks fw1.0: Detect discontinuity of CIP: 00 02

These models, AudioFire8 (since Jul 2009 ) and Gibson Robot Interface
Pack series uses the same ARM binary as their firmware. Thus, this
quirk may be observed among them.

This commit adds a new member for AMDTP structure. This member represents
the value of dbc field in a first AMDTP packet. Drivers can set it with
a preferred value according to model's quirk.
Tested-by: NJohannes Oertei <johannes.oertel@uni-due.de>
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Cc: <stable@vger.kernel.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When detecting packet discontinuity, handle_in_packet() returns minus value
and this value is assigned to unsigned int variable, then the variable has
huge value. As a result, the variable causes buffer-over-run in
handle_out_packet(). This brings invalid page request and system hangup.

This commit fixes the bug to add a new argument into handle_in_packet()
and the number of handled data blocks is assignd to it. The function
return value is just used to check error.

I also considered to change the type of local variable to 'int' in
in_stream_callback(). This idea is based on type-conversion in C standard,
while it may cause future problems when adding more works. Thus, I dropped
this idea.

Fixes: 6fc6b9ce('ALSA: firewire-lib: pass the number of data blocks in incoming packets to outgoing packets')
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When detecting zero in 'dbs' field of CIP header, this packet streaming
should be aborted because of avoiding division-by-zero. This is an error
in an aspect of IEC 61883-1, thus protocol error.

This commit use EPROTO instead of EIO. Actually, the returned value is
not used for userspace and this commit has no effect.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Acked-by: NClemens Ladisch <clemens@ladisch.de>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When detecting invalid value in 'dbs' field of CIP header or packet
discontinuity, current implementation reports the status by err_info().
In most cases this state is caused by model-specific issue due to
vendor's customization and should be reported to developers.

This commit use dev_err() instead of dev_info() for this purpose.
In the cases, packet streaming is aborted, thus no message floading
occurs.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Acked-by: NClemens Ladisch <clemens@ladisch.de>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Some macros include my misunderstanding for IEC 61883-1 or -6.
Additionally, some fixed values appear on codes.

This commit replaces these with macros with proper names.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Acked-by: NClemens Ladisch <clemens@ladisch.de>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The naming rule for local functions was inconsistent. This commit
rename them with a consistent manner.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Acked-by: NClemens Ladisch <clemens@ladisch.de>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Former patches allow non-blocking streams to synchronize with timestamp.
This patch removes the restriction.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

In previous commit, error handling for incoming packet processing is
outside of packetization. This is nice for reading the codes.

This commit applies this idea for outgoing packet processing, too.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Current implementation reuses the value of syt field in incoming packet to
outgoing packet for full duplex timestamp synchronization, while the number
of data blocks in outgoing packets refers to hard-coded table and the
synchronization cannot be applied to non-blocking stream.

This commit passes the number of data blocks from incoming packet
processing to outgoing packet processing for the synchronization. For
normal mode, isochronous callback handler is changed to generate the values
of syt and data blocks.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This function is called according to conditions between the value of
syt and streaming mode(blocking or non-blocking).

To simplify caller's work, this commit push these conditions to the
function.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

In IEC 61883-6, the number of data blocks in a packet is limited up to
the value of SYT_INTERVAL. Current implementation is compliant to the
limitation, while it can cause buffer-over-run when the value of dbs
field in received packet is illegally large.

This commit adds a validator to detect such illegal packets to prevent
the buffer-over-run. Actually, the buffer is aligned to the size of memory
 page, thus this issue hardly causes system errors due to the room to page
alignment, as long as a few packets includes such jumbo payload; i.e.
a packet to several received packets.

Here, Behringer F-Control Audio 202 (based on OXFW 960) has a quirk to
postpone transferring isochronous packet till finish handling any
asynchronous packets. In this case, this model is lazy, transfers no
packets according to several cycle-start packets. After finishing, this
model pushes required data in next isochronous packet. As a result, the
packet include more data blocks than IEC 61883-6 defines.

To continue to support this model, this commit adds a new flag to extend
the length of calculated payload. This flag allows the size of payload
5 times as large as IEC 61883-6 defines. As a result, packets from this
model passed the validator successfully.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Change 'propper' to 'proper'
Change 'paramters' to 'parameters'
Change 'SYT_INTEVAL' to 'SYT_INTERVAL'
Change 'aligh'/'alighed' to 'align'/'aligned'
Signed-off-by: NYannick Guerrini <yguerrini@tomshardware.fr>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

AMDTP helper functions increment/decrement reference counter for an
instance of FireWire unit, while it's complicated for each driver to
process error state.

In previous commit, each driver has the role of reference counting. This
commit removes this role from the helper function.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Cc: <stable@vger.kernel.org> # 3.19+
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The sign for microsecond (U+0085, MICRO SIGN) was encoded to '0x c2 b5'
by UTF-8 character encoding scheme. But the byte sequence was converted
to '0x c3 82 c2 b5' in a previous commit. As a result, the byte
sequence cannot represent microsecond sign in UTF-8 or ASCII. This
may confuse developers.

This commit replaces the sign to string expression with 'microseconds'
to purge superfluous troubles.

Fixes: 5c697e5b("ALSA: firewire-lib: remove rx_blocks_for_midi quirk")
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Do no send MIDI bytes at the full rate at which FireWire packets happen
to be sent, but restrict them to the actual rate of a real MIDI port.
This is required by the specification, and prevents data loss when the
device's buffer overruns.
Signed-off-by: NClemens Ladisch <clemens@ladisch.de>
Reviewed-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Tested-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi 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: NClemens Ladisch <clemens@ladisch.de>
Reviewed-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Tested-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Add a new helper function snd_pcm_stop_xrun() to the standard sequnce
lock/snd_pcm_stop(XRUN)/unlock by a single call, and replace the
existing open codes with this helper.

The function checks the PCM running state to prevent setting the wrong
state, too, for more safety.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

In IEC 61883-6, one data block transfers one event. In ALSA, the event equals one PCM frame,
hence one data block transfers one PCM frame. But Dice has a quirk at higher sampling rate
(176.4/192.0 kHz) that one data block transfers two PCM frames.

Commit 10550bea ("ALSA: dice/firewire-lib: Keep dualwire mode but obsolete
CIP_HI_DUALWIRE") moved some codes related to this quirk into Dice driver. But the commit
forgot to add arrangements for PCM period interrupts and DMA pointer updates. As a result, Dice
driver cannot work correctly at higher sampling rate.

This commit adds 'double_pcm_frames' parameter to amdtp structure for this quirk. When this
parameter is set, PCM period interrupts and DMA pointer updates occur at double speed than in
IEC 61883-6.
Reported-by: NDaniel Robbins <drobbins@funtoo.org>
Fixes: 10550bea ("ALSA: dice/firewire-lib: Keep dualwire mode but obsolete CIP_HI_DUALWIRE")
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Cc: <stable@vger.kernel.org> # 3.16
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

According to AM824 in IEC 61883-6:2002, 2 bits in LSB of label for Raw Audio
data means Valid Length Code (VBL). Ths value is:
- b00 for 24 bits sample (label is 0x40)
- b01 for 20 bits sample (label is 0x41)
- b10 for 16 bits sample (label is 0x42)

But current firewire-lib apply 24 bits label for both of 16/24 bits samples.

As long as developers investigate BeBoB/Fireworks/OXFW/Dice, all of them
have a behaviour to ignore the label. They can generate correct sound even
if firewire-lib gives wrong label (i.e. 0xff). On BeBoB, this is not only
for Raw Audio data channel, but also for IEC 60958 Conformant data channel.

So there is little possibility of regression.
Acked-by: NClemens Ladisch <clemens@ladisch.de>
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>

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>

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>

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>

Fireworks has a quirk to reset data block counter at bus reset.

This commit adds a flag of CIP_SKIP_DBC_ZERO_CHECK. This flag has an effect
to skip checking dbc continuity when dbc is zero.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Fireworks firmware version 5.5 reports fix interval for dbc in each packet.

For example, AudioFire4:
CIP0     CIP1     Payload
00070000 900484FF 72
00070008 9004A8FF 72
00070008 90FFFFFF 02
00070010 9004D0FF 72
00070018 9004C4FF 72
00070020 9004E8FF 72
00070020 90FFFFFF 02
00070028 900410FE 72

The interval of each dbc should be 16 except for empty packet but it's still 8.

This commit adds a flag for this quirk and codes to refer to a fixed value.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

One of Fireworks firmware, named  as 'AudioFire9', seems to transmit
packets with wrong value of dbs. It's always 0x11 but actual size of
data block is different.

This commit adds a flag for this quirk and some codes to calculate
correct size.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>