AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-11-25 04:50:57 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
b12fb7f46a
linux_dsm_epyc7002/sound/firewire/fireworks/fireworks.h

235 lines
6.6 KiB
C
Raw Normal View History

ALSA: fireworks: Add skelton for Fireworks based devices This commit adds a new driver for devices based on Fireworks. This driver just creates/removes card instance according to callbacks. Fireworks is a board module which Echo Audio produced. This module consists of three chipsets: - Communication chipset for IEEE1394 PHY/Link and IEC 61883-1/6 - DSP or/and FPGA for signal processing - Flash Memory to store firmwares Current supported devices: - Mackie Onyx 400F/1200F - Echo AudioFire12/8(until 2009 July) - Echo AudioFire2/4/Pre8/8(since 2009 July) - Echo Fireworks 8/HDMI - Gibson Robot Interface pack/GoldTop Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:00 +07:00
/*
* fireworks.h - a part of driver for Fireworks based devices
*
* Copyright (c) 2009-2010 Clemens Ladisch
* Copyright (c) 2013-2014 Takashi Sakamoto
*
* Licensed under the terms of the GNU General Public License, version 2.
*/
#ifndef SOUND_FIREWORKS_H_INCLUDED
#define SOUND_FIREWORKS_H_INCLUDED
#include <linux/compat.h>
#include <linux/device.h>
#include <linux/firewire.h>
#include <linux/firewire-constants.h>
#include <linux/module.h>
#include <linux/mod_devicetable.h>
#include <linux/delay.h>
#include <linux/slab.h>
#include <sound/core.h>
#include <sound/initval.h>
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
#include <sound/pcm.h>
ALSA: fireworks: Add proc interface for debugging purpose This commit adds proc interface to output infomation for debugging. - firmware information - sampling rate and clock source - physical metering (linear value) Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:08 +07:00
#include <sound/info.h>
ALSA: fireworks: Add MIDI interface This commit adds a functionality to capture/playback MIDI messages. When no AMDTP streams are running, this driver starts AMDTP stream for MIDI stream at current sampling rate. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:09 +07:00
#include <sound/rawmidi.h>
ALSA: fireworks: Add PCM interface 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:11 +07:00
#include <sound/pcm_params.h>
ALSA: fireworks: Add hwdep interface 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:12 +07:00
#include <sound/firewire.h>
#include <sound/hwdep.h>
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
ALSA: fireworks: Add connection and stream management Fireworks manages connections by CMP and can transmit/receive AMDTP streams with a few quirks. This commit adds functionality to start/stop the streams. Major Fireworks products don't support 'SYT-Match' clock source mode, except for AudioFire12/8(till 2009 July) with firmware version 1.0. Already in previous commit, this driver don't support such old firmwares. So this commit adds support for non 'SYT-Match' clock source modes. I note that this driver has a short gap for MIDI streams when starting PCM stream. When AMDTP streams are running only for MIDI data and PCM data is going to be joined at different sampling rate, then AMDTP streams are stopped once and started again after changing sampling rate. Unfortunately, Fireworks is not fully compliant to IEC 61883-1/6. Some commits following to this commit add these quirks. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:02 +07:00
#include "../packets-buffer.h"
#include "../iso-resources.h"
ALSA: firewire-lib: add data block processing layer for AM824 format 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>
2015-09-19 09:21:55 +07:00
#include "../amdtp-am824.h"
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
#include "../cmp.h"
#include "../lib.h"
ALSA: fireworks: Add connection and stream management Fireworks manages connections by CMP and can transmit/receive AMDTP streams with a few quirks. This commit adds functionality to start/stop the streams. Major Fireworks products don't support 'SYT-Match' clock source mode, except for AudioFire12/8(till 2009 July) with firmware version 1.0. Already in previous commit, this driver don't support such old firmwares. So this commit adds support for non 'SYT-Match' clock source modes. I note that this driver has a short gap for MIDI streams when starting PCM stream. When AMDTP streams are running only for MIDI data and PCM data is going to be joined at different sampling rate, then AMDTP streams are stopped once and started again after changing sampling rate. Unfortunately, Fireworks is not fully compliant to IEC 61883-1/6. Some commits following to this commit add these quirks. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:02 +07:00
#define SND_EFW_MAX_MIDI_OUT_PORTS 2
#define SND_EFW_MAX_MIDI_IN_PORTS 2
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
#define SND_EFW_MULTIPLIER_MODES 3
#define HWINFO_NAME_SIZE_BYTES 32
#define HWINFO_MAX_CAPS_GROUPS 8
/*
* This should be greater than maximum bytes for EFW response content.
* Currently response against command for isochronous channel mapping is
* confirmed to be the maximum one. But for flexibility, use maximum data
* payload for asynchronous primary packets at S100 (Cable base rate) in
* IEEE Std 1394-1995.
*/
#define SND_EFW_RESPONSE_MAXIMUM_BYTES 0x200U
ALSA: fireworks: Add command/response functionality into hwdep interface 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:13 +07:00
extern unsigned int snd_efw_resp_buf_size;
extern bool snd_efw_resp_buf_debug;
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
struct snd_efw_phys_grp {
u8 type; /* see enum snd_efw_grp_type */
u8 count;
} __packed;
ALSA: fireworks: Add skelton for Fireworks based devices This commit adds a new driver for devices based on Fireworks. This driver just creates/removes card instance according to callbacks. Fireworks is a board module which Echo Audio produced. This module consists of three chipsets: - Communication chipset for IEEE1394 PHY/Link and IEC 61883-1/6 - DSP or/and FPGA for signal processing - Flash Memory to store firmwares Current supported devices: - Mackie Onyx 400F/1200F - Echo AudioFire12/8(until 2009 July) - Echo AudioFire2/4/Pre8/8(since 2009 July) - Echo Fireworks 8/HDMI - Gibson Robot Interface pack/GoldTop Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:00 +07:00
struct snd_efw {
struct snd_card *card;
struct fw_unit *unit;
int card_index;
struct mutex mutex;
spinlock_t lock;
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
ALSA: fireworks: delayed registration of sound card When some fireworks units are connected sequentially, userspace applications are involved at bus-reset state on IEEE 1394 bus. In the state, any communications can be canceled. Therefore, sound card registration should be delayed till the bus gets calm. This commit achieves it. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2016-03-31 06:47:06 +07:00
bool registered;
struct delayed_work dwork;
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
/* for transaction */
u32 seqnum;
bool resp_addr_changable;
ALSA: fireworks: Add connection and stream management Fireworks manages connections by CMP and can transmit/receive AMDTP streams with a few quirks. This commit adds functionality to start/stop the streams. Major Fireworks products don't support 'SYT-Match' clock source mode, except for AudioFire12/8(till 2009 July) with firmware version 1.0. Already in previous commit, this driver don't support such old firmwares. So this commit adds support for non 'SYT-Match' clock source modes. I note that this driver has a short gap for MIDI streams when starting PCM stream. When AMDTP streams are running only for MIDI data and PCM data is going to be joined at different sampling rate, then AMDTP streams are stopped once and started again after changing sampling rate. Unfortunately, Fireworks is not fully compliant to IEC 61883-1/6. Some commits following to this commit add these quirks. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:02 +07:00
ALSA: fireworks/firewire-lib: Add a quirk for wrong dbs in tx packets 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:05 +07:00
/* for quirks */
bool is_af9;
ALSA: fireworks/firewire-lib: add support for recent firmware quirk 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: Johannes Oertei <johannes.oertel@uni-due.de> Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Cc: <stable@vger.kernel.org> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2015-08-05 07:21:05 +07:00
bool is_fireworks3;
ALSA: fireworks/firewire-lib: Add a quirk for fixed interval of reported dbc 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:06 +07:00
u32 firmware_version;
ALSA: fireworks/firewire-lib: Add a quirk for wrong dbs in tx packets 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:05 +07:00
ALSA: fireworks: Add connection and stream management Fireworks manages connections by CMP and can transmit/receive AMDTP streams with a few quirks. This commit adds functionality to start/stop the streams. Major Fireworks products don't support 'SYT-Match' clock source mode, except for AudioFire12/8(till 2009 July) with firmware version 1.0. Already in previous commit, this driver don't support such old firmwares. So this commit adds support for non 'SYT-Match' clock source modes. I note that this driver has a short gap for MIDI streams when starting PCM stream. When AMDTP streams are running only for MIDI data and PCM data is going to be joined at different sampling rate, then AMDTP streams are stopped once and started again after changing sampling rate. Unfortunately, Fireworks is not fully compliant to IEC 61883-1/6. Some commits following to this commit add these quirks. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:02 +07:00
unsigned int midi_in_ports;
unsigned int midi_out_ports;
unsigned int supported_sampling_rate;
unsigned int pcm_capture_channels[SND_EFW_MULTIPLIER_MODES];
unsigned int pcm_playback_channels[SND_EFW_MULTIPLIER_MODES];
struct amdtp_stream tx_stream;
struct amdtp_stream rx_stream;
struct cmp_connection out_conn;
struct cmp_connection in_conn;
ALSA: fireworks: change type of substream counter from atomic_t to unsigned int 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>
2015-11-14 14:54:51 +07:00
unsigned int capture_substreams;
unsigned int playback_substreams;
ALSA: fireworks: Add proc interface for debugging purpose This commit adds proc interface to output infomation for debugging. - firmware information - sampling rate and clock source - physical metering (linear value) Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:08 +07:00
/* hardware metering parameters */
unsigned int phys_out;
unsigned int phys_in;
unsigned int phys_out_grp_count;
unsigned int phys_in_grp_count;
struct snd_efw_phys_grp phys_out_grps[HWINFO_MAX_CAPS_GROUPS];
struct snd_efw_phys_grp phys_in_grps[HWINFO_MAX_CAPS_GROUPS];
ALSA: fireworks: Add hwdep interface 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:12 +07:00
/* for uapi */
int dev_lock_count;
bool dev_lock_changed;
wait_queue_head_t hwdep_wait;
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
ALSA: fireworks: Add command/response functionality into hwdep interface 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:13 +07:00
/* response queue */
u8 *resp_buf;
u8 *pull_ptr;
u8 *push_ptr;
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
};
ALSA: fireworks: Add command/response functionality into hwdep interface 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:13 +07:00
int snd_efw_transaction_cmd(struct fw_unit *unit,
const void *cmd, unsigned int size);
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
int snd_efw_transaction_run(struct fw_unit *unit,
const void *cmd, unsigned int cmd_size,
void *resp, unsigned int resp_size);
int snd_efw_transaction_register(void);
void snd_efw_transaction_unregister(void);
void snd_efw_transaction_bus_reset(struct fw_unit *unit);
ALSA: fireworks: Add command/response functionality into hwdep interface 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:13 +07:00
void snd_efw_transaction_add_instance(struct snd_efw *efw);
void snd_efw_transaction_remove_instance(struct snd_efw *efw);
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
struct snd_efw_hwinfo {
u32 flags;
u32 guid_hi;
u32 guid_lo;
u32 type;
u32 version;
char vendor_name[HWINFO_NAME_SIZE_BYTES];
char model_name[HWINFO_NAME_SIZE_BYTES];
u32 supported_clocks;
u32 amdtp_rx_pcm_channels;
u32 amdtp_tx_pcm_channels;
u32 phys_out;
u32 phys_in;
u32 phys_out_grp_count;
struct snd_efw_phys_grp phys_out_grps[HWINFO_MAX_CAPS_GROUPS];
u32 phys_in_grp_count;
struct snd_efw_phys_grp phys_in_grps[HWINFO_MAX_CAPS_GROUPS];
u32 midi_out_ports;
u32 midi_in_ports;
u32 max_sample_rate;
u32 min_sample_rate;
u32 dsp_version;
u32 arm_version;
u32 mixer_playback_channels;
u32 mixer_capture_channels;
u32 fpga_version;
u32 amdtp_rx_pcm_channels_2x;
u32 amdtp_tx_pcm_channels_2x;
u32 amdtp_rx_pcm_channels_4x;
u32 amdtp_tx_pcm_channels_4x;
u32 reserved[16];
} __packed;
enum snd_efw_grp_type {
SND_EFW_CH_TYPE_ANALOG = 0,
SND_EFW_CH_TYPE_SPDIF = 1,
SND_EFW_CH_TYPE_ADAT = 2,
SND_EFW_CH_TYPE_SPDIF_OR_ADAT = 3,
SND_EFW_CH_TYPE_ANALOG_MIRRORING = 4,
SND_EFW_CH_TYPE_HEADPHONES = 5,
SND_EFW_CH_TYPE_I2S = 6,
SND_EFW_CH_TYPE_GUITAR = 7,
SND_EFW_CH_TYPE_PIEZO_GUITAR = 8,
SND_EFW_CH_TYPE_GUITAR_STRING = 9,
SND_EFW_CH_TYPE_DUMMY
};
struct snd_efw_phys_meters {
u32 status; /* guitar state/midi signal/clock input detect */
u32 reserved0;
u32 reserved1;
u32 reserved2;
u32 reserved3;
u32 out_meters;
u32 in_meters;
u32 reserved4;
u32 reserved5;
u32 values[0];
} __packed;
enum snd_efw_clock_source {
SND_EFW_CLOCK_SOURCE_INTERNAL = 0,
SND_EFW_CLOCK_SOURCE_SYTMATCH = 1,
SND_EFW_CLOCK_SOURCE_WORDCLOCK = 2,
SND_EFW_CLOCK_SOURCE_SPDIF = 3,
SND_EFW_CLOCK_SOURCE_ADAT_1 = 4,
SND_EFW_CLOCK_SOURCE_ADAT_2 = 5,
SND_EFW_CLOCK_SOURCE_CONTINUOUS = 6 /* internal variable clock */
};
enum snd_efw_transport_mode {
SND_EFW_TRANSPORT_MODE_WINDOWS = 0,
SND_EFW_TRANSPORT_MODE_IEC61883 = 1,
ALSA: fireworks: Add skelton for Fireworks based devices This commit adds a new driver for devices based on Fireworks. This driver just creates/removes card instance according to callbacks. Fireworks is a board module which Echo Audio produced. This module consists of three chipsets: - Communication chipset for IEEE1394 PHY/Link and IEC 61883-1/6 - DSP or/and FPGA for signal processing - Flash Memory to store firmwares Current supported devices: - Mackie Onyx 400F/1200F - Echo AudioFire12/8(until 2009 July) - Echo AudioFire2/4/Pre8/8(since 2009 July) - Echo Fireworks 8/HDMI - Gibson Robot Interface pack/GoldTop Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:00 +07:00
};
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
int snd_efw_command_set_resp_addr(struct snd_efw *efw,
u16 addr_high, u32 addr_low);
ALSA: fireworks: Use the same prototype for functions as actual declaration 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-05-27 22:14:39 +07:00
int snd_efw_command_set_tx_mode(struct snd_efw *efw,
enum snd_efw_transport_mode mode);
ALSA: fireworks: Add transaction and some commands Fireworks uses own command and response. This commit adds functionality to transact and adds some commands required for sound card instance and kernel streaming. There are two ways to deliver substance of this transaction: 1.AV/C vendor dependent command for command/response 2.Async transaction to specific addresses for command/response By way 1, I confirm AudioFire12 cannot correctly response to some commands with firmware version 5.0 or later. This is also confirmed by FFADO. So this driver implement way 2. The address for response gives an issue. When this driver allocate own callback function into the address, then no one can allocate its own callback function. This situation is not good for applications in user-land. This issue is solved in later commit. I note there is a command to change the address for response if the device supports. But this driver uses default value. So users should not execute this command as long as hoping this driver works correctly. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:01 +07:00
int snd_efw_command_get_hwinfo(struct snd_efw *efw,
struct snd_efw_hwinfo *hwinfo);
int snd_efw_command_get_phys_meters(struct snd_efw *efw,
struct snd_efw_phys_meters *meters,
unsigned int len);
int snd_efw_command_get_clock_source(struct snd_efw *efw,
enum snd_efw_clock_source *source);
int snd_efw_command_get_sampling_rate(struct snd_efw *efw, unsigned int *rate);
int snd_efw_command_set_sampling_rate(struct snd_efw *efw, unsigned int rate);
ALSA: fireworks: Add skelton for Fireworks based devices This commit adds a new driver for devices based on Fireworks. This driver just creates/removes card instance according to callbacks. Fireworks is a board module which Echo Audio produced. This module consists of three chipsets: - Communication chipset for IEEE1394 PHY/Link and IEC 61883-1/6 - DSP or/and FPGA for signal processing - Flash Memory to store firmwares Current supported devices: - Mackie Onyx 400F/1200F - Echo AudioFire12/8(until 2009 July) - Echo AudioFire2/4/Pre8/8(since 2009 July) - Echo Fireworks 8/HDMI - Gibson Robot Interface pack/GoldTop Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:00 +07:00
ALSA: fireworks: Add connection and stream management Fireworks manages connections by CMP and can transmit/receive AMDTP streams with a few quirks. This commit adds functionality to start/stop the streams. Major Fireworks products don't support 'SYT-Match' clock source mode, except for AudioFire12/8(till 2009 July) with firmware version 1.0. Already in previous commit, this driver don't support such old firmwares. So this commit adds support for non 'SYT-Match' clock source modes. I note that this driver has a short gap for MIDI streams when starting PCM stream. When AMDTP streams are running only for MIDI data and PCM data is going to be joined at different sampling rate, then AMDTP streams are stopped once and started again after changing sampling rate. Unfortunately, Fireworks is not fully compliant to IEC 61883-1/6. Some commits following to this commit add these quirks. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:02 +07:00
int snd_efw_stream_init_duplex(struct snd_efw *efw);
ALSA: fireworks/bebob: Change type of argument for sampling rate 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>
2014-05-27 22:14:40 +07:00
int snd_efw_stream_start_duplex(struct snd_efw *efw, unsigned int rate);
ALSA: fireworks: Add connection and stream management Fireworks manages connections by CMP and can transmit/receive AMDTP streams with a few quirks. This commit adds functionality to start/stop the streams. Major Fireworks products don't support 'SYT-Match' clock source mode, except for AudioFire12/8(till 2009 July) with firmware version 1.0. Already in previous commit, this driver don't support such old firmwares. So this commit adds support for non 'SYT-Match' clock source modes. I note that this driver has a short gap for MIDI streams when starting PCM stream. When AMDTP streams are running only for MIDI data and PCM data is going to be joined at different sampling rate, then AMDTP streams are stopped once and started again after changing sampling rate. Unfortunately, Fireworks is not fully compliant to IEC 61883-1/6. Some commits following to this commit add these quirks. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:02 +07:00
void snd_efw_stream_stop_duplex(struct snd_efw *efw);
void snd_efw_stream_update_duplex(struct snd_efw *efw);
void snd_efw_stream_destroy_duplex(struct snd_efw *efw);
ALSA: fireworks: Add hwdep interface 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:12 +07:00
void snd_efw_stream_lock_changed(struct snd_efw *efw);
int snd_efw_stream_lock_try(struct snd_efw *efw);
void snd_efw_stream_lock_release(struct snd_efw *efw);
ALSA: fireworks: Add connection and stream management Fireworks manages connections by CMP and can transmit/receive AMDTP streams with a few quirks. This commit adds functionality to start/stop the streams. Major Fireworks products don't support 'SYT-Match' clock source mode, except for AudioFire12/8(till 2009 July) with firmware version 1.0. Already in previous commit, this driver don't support such old firmwares. So this commit adds support for non 'SYT-Match' clock source modes. I note that this driver has a short gap for MIDI streams when starting PCM stream. When AMDTP streams are running only for MIDI data and PCM data is going to be joined at different sampling rate, then AMDTP streams are stopped once and started again after changing sampling rate. Unfortunately, Fireworks is not fully compliant to IEC 61883-1/6. Some commits following to this commit add these quirks. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:02 +07:00
ALSA: fireworks: Add proc interface for debugging purpose This commit adds proc interface to output infomation for debugging. - firmware information - sampling rate and clock source - physical metering (linear value) Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:08 +07:00
void snd_efw_proc_init(struct snd_efw *efw);
ALSA: fireworks: Add MIDI interface This commit adds a functionality to capture/playback MIDI messages. When no AMDTP streams are running, this driver starts AMDTP stream for MIDI stream at current sampling rate. Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:09 +07:00
int snd_efw_create_midi_devices(struct snd_efw *efw);
ALSA: fireworks: Add PCM interface 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:11 +07:00
int snd_efw_create_pcm_devices(struct snd_efw *efw);
int snd_efw_get_multiplier_mode(unsigned int sampling_rate, unsigned int *mode);
ALSA: fireworks: Add hwdep interface 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: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:12 +07:00
int snd_efw_create_hwdep_device(struct snd_efw *efw);
ALSA: fireworks: Add skelton for Fireworks based devices This commit adds a new driver for devices based on Fireworks. This driver just creates/removes card instance according to callbacks. Fireworks is a board module which Echo Audio produced. This module consists of three chipsets: - Communication chipset for IEEE1394 PHY/Link and IEC 61883-1/6 - DSP or/and FPGA for signal processing - Flash Memory to store firmwares Current supported devices: - Mackie Onyx 400F/1200F - Echo AudioFire12/8(until 2009 July) - Echo AudioFire2/4/Pre8/8(since 2009 July) - Echo Fireworks 8/HDMI - Gibson Robot Interface pack/GoldTop Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by: Takashi Iwai <tiwai@suse.de>
2014-04-25 20:45:00 +07:00
#define SND_EFW_DEV_ENTRY(vendor, model) \
{ \
.match_flags = IEEE1394_MATCH_VENDOR_ID | \
IEEE1394_MATCH_MODEL_ID, \
.vendor_id = vendor,\
.model_id = model \
}
#endif
Reference in New Issue Copy Permalink