[alsa-devel] [RFC][PATCH 0/2] ALSA: fireworks/firewire-lib: add support for recent firmware quirk
Some users have reported current ALSA Fireworks driver stops packet streaming due to detecting discontinuity.
[alsa-devel] ALSA snd-fireworks Echo AudioFire 2 http://mailman.alsa-project.org/pipermail/alsa-devel/2014-August/080379.html
[alsa-devel] AudioFire4 quirk http://mailman.alsa-project.org/pipermail/alsa-devel/2015-July/095697.html
As long as I investigate, this issue depends on firmware version installed in these devices. While, it's not clear that which version of firmwares for which model has this quirk. At least, firmware version 5.7.0, 5.7.3 and 5.8.0 for AudioFire2/AudioFire4/AudioFirePre8 have this quirk.
This patchset applies a solution for this issue, with my assumption that 'the same firmware binary has the same quirk'. These models, AudioFire8 (since Jul 2009) and Gibson Robot Interface Pack (RIP) series uses the same firmware binary in driver package.
Takashi Sakamoto (2): Revert "ALSA: fireworks: add support for AudioFire2 quirk" ALSA: fireworks/firewire-lib: add support for recent firmware quirk
sound/firewire/amdtp.c | 5 +++-- sound/firewire/amdtp.h | 2 ++ sound/firewire/fireworks/fireworks.c | 10 ++++++++-- sound/firewire/fireworks/fireworks.h | 2 +- sound/firewire/fireworks/fireworks_stream.c | 12 +++++++++--- 5 files changed, 23 insertions(+), 8 deletions(-)
This reverts commit 9c6893e0be38b6ca9a56a854226e51dee0a16a5a.
Signed-off-by: Takashi Sakamoto o-takashi@sakamocchi.jp --- sound/firewire/fireworks/fireworks.c | 2 -- sound/firewire/fireworks/fireworks.h | 1 - sound/firewire/fireworks/fireworks_stream.c | 3 --- 3 files changed, 6 deletions(-)
diff --git a/sound/firewire/fireworks/fireworks.c b/sound/firewire/fireworks/fireworks.c index c670db4..2682e7e 100644 --- a/sound/firewire/fireworks/fireworks.c +++ b/sound/firewire/fireworks/fireworks.c @@ -248,8 +248,6 @@ efw_probe(struct fw_unit *unit, err = get_hardware_info(efw); if (err < 0) goto error; - if (entry->model_id == MODEL_ECHO_AUDIOFIRE_2) - efw->is_af2 = true; if (entry->model_id == MODEL_ECHO_AUDIOFIRE_9) efw->is_af9 = true;
diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h index c33252b..4f0201a 100644 --- a/sound/firewire/fireworks/fireworks.h +++ b/sound/firewire/fireworks/fireworks.h @@ -70,7 +70,6 @@ struct snd_efw { bool resp_addr_changable;
/* for quirks */ - bool is_af2; bool is_af9; u32 firmware_version;
diff --git a/sound/firewire/fireworks/fireworks_stream.c b/sound/firewire/fireworks/fireworks_stream.c index a0762dd..c55db1b 100644 --- a/sound/firewire/fireworks/fireworks_stream.c +++ b/sound/firewire/fireworks/fireworks_stream.c @@ -172,9 +172,6 @@ int snd_efw_stream_init_duplex(struct snd_efw *efw) efw->tx_stream.flags |= CIP_DBC_IS_END_EVENT; /* Fireworks reset dbc at bus reset. */ efw->tx_stream.flags |= CIP_SKIP_DBC_ZERO_CHECK; - /* AudioFire2 starts packets with non-zero dbc. */ - if (efw->is_af2) - efw->tx_stream.flags |= CIP_SKIP_INIT_DBC_CHECK; /* AudioFire9 always reports wrong dbs. */ if (efw->is_af9) efw->tx_stream.flags |= CIP_WRONG_DBS;
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.)
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.
Signed-off-by: Takashi Sakamoto o-takashi@sakamocchi.jp --- sound/firewire/amdtp.c | 5 +++-- sound/firewire/amdtp.h | 2 ++ sound/firewire/fireworks/fireworks.c | 8 ++++++++ sound/firewire/fireworks/fireworks.h | 1 + sound/firewire/fireworks/fireworks_stream.c | 9 +++++++++ 5 files changed, 23 insertions(+), 2 deletions(-)
diff --git a/sound/firewire/amdtp.c b/sound/firewire/amdtp.c index 7bb988f..2a153d2 100644 --- a/sound/firewire/amdtp.c +++ b/sound/firewire/amdtp.c @@ -740,8 +740,9 @@ static int handle_in_packet(struct amdtp_stream *s, s->data_block_counter != UINT_MAX) data_block_counter = s->data_block_counter;
- if (((s->flags & CIP_SKIP_DBC_ZERO_CHECK) && data_block_counter == 0) || - (s->data_block_counter == UINT_MAX)) { + if (((s->flags & CIP_SKIP_DBC_ZERO_CHECK) && + data_block_counter == s->tx_first_dbc) || + s->data_block_counter == UINT_MAX) { lost = false; } else if (!(s->flags & CIP_DBC_IS_END_EVENT)) { lost = data_block_counter != s->data_block_counter; diff --git a/sound/firewire/amdtp.h b/sound/firewire/amdtp.h index 26b9093..b2cf9e7 100644 --- a/sound/firewire/amdtp.h +++ b/sound/firewire/amdtp.h @@ -157,6 +157,8 @@ struct amdtp_stream {
/* quirk: fixed interval of dbc between previos/current packets. */ unsigned int tx_dbc_interval; + /* quirk: indicate the value of dbc field in a first packet. */ + unsigned int tx_first_dbc;
bool callbacked; wait_queue_head_t callback_wait; diff --git a/sound/firewire/fireworks/fireworks.c b/sound/firewire/fireworks/fireworks.c index 2682e7e..c94a432 100644 --- a/sound/firewire/fireworks/fireworks.c +++ b/sound/firewire/fireworks/fireworks.c @@ -248,8 +248,16 @@ efw_probe(struct fw_unit *unit, err = get_hardware_info(efw); if (err < 0) goto error; + /* AudioFire8 (since 2009) and AudioFirePre8 */ if (entry->model_id == MODEL_ECHO_AUDIOFIRE_9) efw->is_af9 = true; + /* These models uses the same firmware. */ + if (entry->model_id == MODEL_ECHO_AUDIOFIRE_2 || + entry->model_id == MODEL_ECHO_AUDIOFIRE_4 || + entry->model_id == MODEL_ECHO_AUDIOFIRE_9 || + entry->model_id == MODEL_GIBSON_RIP || + entry->model_id == MODEL_GIBSON_GOLDTOP) + efw->is_fireworks3 = true;
snd_efw_proc_init(efw);
diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h index 4f0201a..084d414 100644 --- a/sound/firewire/fireworks/fireworks.h +++ b/sound/firewire/fireworks/fireworks.h @@ -71,6 +71,7 @@ struct snd_efw {
/* for quirks */ bool is_af9; + bool is_fireworks3; u32 firmware_version;
unsigned int midi_in_ports; diff --git a/sound/firewire/fireworks/fireworks_stream.c b/sound/firewire/fireworks/fireworks_stream.c index c55db1b..7e353f1 100644 --- a/sound/firewire/fireworks/fireworks_stream.c +++ b/sound/firewire/fireworks/fireworks_stream.c @@ -172,6 +172,15 @@ int snd_efw_stream_init_duplex(struct snd_efw *efw) efw->tx_stream.flags |= CIP_DBC_IS_END_EVENT; /* Fireworks reset dbc at bus reset. */ efw->tx_stream.flags |= CIP_SKIP_DBC_ZERO_CHECK; + /* + * But Recent firmwares starts packets with non-zero dbc. + * Driver version 5.7.6 installs firmware version 5.7.3. + */ + if (efw->is_fireworks3 && + (efw->firmware_version == 0x5070000 || + efw->firmware_version == 0x5070300 || + efw->firmware_version == 0x5080000)) + efw->tx_stream.tx_first_dbc = 0x02; /* AudioFire9 always reports wrong dbs. */ if (efw->is_af9) efw->tx_stream.flags |= CIP_WRONG_DBS;
Hi,
On Aug 04 2015 08:40, Takashi Sakamoto wrote:
I pushed 'fireworks3-quirk' branch to my repository. It's nice to test with your models if you have a enough time. https://github.com/takaswie/snd-firewire-improve/tree/fireworks3-quirk
In this repository, another developing line is running (amdtp-variants). I have a plan to post a part of them in this kernel developing cycle.
Regards
Takashi Sakamoto
participants (2)
-
Johannes Oertel
-
Takashi Sakamoto