- 26 May, 2014 38 commits
-
-
Takashi Sakamoto authored
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>
-
Takashi Sakamoto authored
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:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
This commit adds proc interface to get these information for debugging: - firmware information - stream formation - current clock source and sampling rate Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
Normal BeBoB firmware has a quirk. When receiving bus reset, it transmits packets with discontinuous value in dbc field. This causes two situation, one is to abort streaming by firewire-lib as a result of detecting the discontinuity. Another is to call driver's .update() because of bus reset. These two is generated independently. (The former depends on isochronous stream and the latter depends on IEEE1394 bus driver.) When BeBoB driver works with XRUN-recoverable applications, this situation looks like stream_start_duplex() call followed by stream_update_duplex() call because applications will call snd_pcm_prepare() immediately at XRUN. To update connections and streams at first, this commit use completion. When queueing error occurs, stream_start_duplex() is forced to wait maximum 1000msec. During this, when .update() is called, the completion is waken and stream_start_duplex() is processed without breaking connections. At bus reset, stream_start_duplex() shouldn't break/establish connections and stream_update_duplex() should update connections because a caller of fw_iso_resources_allocate() is responsible for calling fw_iso_resources_update() on bus reset. This commit also adds a flag, which has an effect to skip checking continuity for first packet. This flag is useful for BeBoB quirk to start handling packets during streaming. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
This commit adds management functionality for connections and streams. BeBoB uses CMP to manage connections and uses AMDTP for streams. This commit also adds some BridgeCo's AV/C extension commands. There are some BridgeCo's AV/C extension commands but this commit just uses below commands to get device's capability and status: 1.Extended Plug Info commands - Plug Channel Position Specific Data - Plug Type Specific Data - Cluster(Section) Info Specific Data - Plug Input Specific Data 2.Extended Stream Format Information commands - Extended Stream Format Information Command - List Request For Extended Plug Info commands for Cluster Info Specific Data, I pick up 'section' instead of 'cluster' from document to prevent from misunderstanding because 'cluster' is also used in IEC 61883-6. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
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:
David Henningsson <david.henningsson@canonical.com> Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
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>
-
Takashi Sakamoto authored
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>
-
Takashi Sakamoto authored
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>
-
Takashi Sakamoto authored
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:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
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>
-
Takashi Sakamoto authored
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>
-
Takashi Sakamoto authored
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:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
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>
-
Takashi Sakamoto authored
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>
-
Takashi Sakamoto authored
Fireworks has a quirk for the value of dbc field in transmitted packets. For Fireworks, dbc means the end of events in current packet. This is out of specification. For example, AudioFire4: CIP0 CIP1 Payload 01070092 90FFFFFF 02 0107009A 9001E17B 3A <- 010700A2 9001F6E5 3A 010700A2 90FFFFFF 02 010700AA 9001104F 3A <- 010700B2 900125B9 3A 010700BA 90013B23 3A 010700BA 90FFFFFF 02 010700C2 9001548E 3A <- 010700CA 900169F8 3A 010700CA 90FFFFFF 02 010700D2 90018362 3A <- 010700DA 900198CC 3A According to IEC 61883-1/6, a packet following to empty packet has the same value for its dbc. But for Fireworks, it's incremented and empty packet has the same value as previous packet in dbc field. This commit adds a flag for Fireworks and some codes to checking dbc continuity. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
Fireworks has a quirk to transmit empty packets with TAG0. This commit adds handling this quirk for full duplex stream synchronization. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
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>
-
Takashi Sakamoto authored
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>
-
Takashi Sakamoto authored
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>
-
Takashi Sakamoto authored
This commit adds three commands, which may be used by some firewire device drivers. These commands are defined in 'AV/C Digital Interface Command Set General Specification Version 4.2 (2004006, 1394TA)'. 1. PLUG INFO command (clause 10.1) 2. INPUT PLUG SIGNAL FORMAT command (clause 10.10) 3. OUTPUT PLUG SIGNAL FORMAT command (clause 10.11) By the command 1, the drivers can get the number of plugs for AV/C unit or subunit. By the command 2 and 3, the drivers can get/set sampling frequency. The 'firewire-speakers' already uses INPUT PLUG SIGNAL FORMAT command to set sampling rate. So this commit also affects the driver. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
Some devices based on BeBoB use this type of AV/C transaction. 'Deferred Transaction' is defined in 'AV/C Digital Interface Command Set General Specification' and is used by targets to make a response deferred during processing it. If a target may not be able to complete a command within 100msec since receiving the command, then the target shall return INTERIM response, to which final response will follow later. CONTROL/NOTIFY commands are allowed for deferred transaction. In the specification, devices allow to send INTERIM response just one time. But this commit allows to handle several INTERIM response with two reasons. One reason is to simplify codes, and another reason is to prepare for devices which is out of specification. There is an issue. In the specification, the interval between INTERIM response and final response is 'Unspecified interval'. The specification depends on each subunit specification for this interval. But we promise to finish this function for caller. In this reason, I use FCP_TIMEOUT_MS for this interval. Currently it's 125msec. When we find devices which needs more time for this interval, then let us add some codes to apply more interval for 'Unspecified interval'. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
Plug Control Registers have two fields related to the number of established connections, one is 'Broadcast connection counter' and another is 'Point-to-point connection counter'. The driver can know there are established connections or not to check these fields. This commit is for considering about JACK/FFADO streaming. Currently, when JACK/FFADO starts its streaming to the device, cmp_connection_establish() is failed expectedly. This seems to be enough but there are some devices which needs to change sampling frequency before trying to establish connections. For such devices, this functionality is needed. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
This patch adds some macros, codes with condition of direction and new functions to handle output connection. Once cmp_connection_init() is executed with its direction, CMP input and output connection can be handled by the same way. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
This patch adds 'direction' member to 'cmp_connection' structure to indicate the direction of connection. This patch also adds 'direction' argument to cmp_connection_init() function to determine the direction. The cmp_connection_init() function is exported and used in snd-firewire-speakers so this patch also affect it. This patch just add them. Actual implementation will be done by followed patches. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
Referring to IEC 61883-1, oMPR and iMPR, oPCR and iPCR have some fields with the same role in the same position. This patch renames some macros, variables and function arguments with "i" in its prefix to reuse them between oMPR and iMPR, oPCR and iPCR. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
Currently, drivers can bring XRUN state for PCM substreams when error to queue packets or detecting discontinuity of packet. The application may try to recover this state by calling snd_pcm_prepare(). Depending on each driver, .prepare() includes restart streaming. Then there is a state that PCM substreams are running but isochronous contexts are stopped. In this case, when .pointer() is called, it refers to error pointer. This commit is for a prevention of this bug. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
This commit adds common PCM constraints according to current firewire-lib implementation. 1.Maximum width for each sample is limited by 24. AM824 in IEC 61883-6 can deliver 24bit data. 2. Minimum time for period is 5msec. Apply the old value. For shorter latency, further works are needed. 3. In blocking mode, frames per period/buffer is aligned to 32. Each packet can include some frames depending on its sampling rate. In blocking mode, the number equals to SYT_INTERVAL. Currently firewire-lib can schedule snd_pcm_period_elapsed() for each packet. So, for accurate PCM interrupt, the number of frames per period/buffer should be aligned to SYT_INTERVAL. Currently firewire-lib is lack of better rules to achieve this. So LCM of each value of SYT_INTERVALs (=32) is applied. This can be improved for further work. [Fixed the compile error due to the missing "&" by tiwai] Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
In previous commit, AMDTP functionality in firewire-lib supports mapping for PCM data channels. With this mapping, firewire-lib can obsolete a flag, CIP_HI_DUALWIRE, but Dice driver still keeps dual wire mode. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
Some devices arrange the position of PCM/MIDI data channel in AMDTP packet. This commit allows drivers to set channel mapping. To be simple, the mapping table is an array with fixed length. Then the number of channels for PCM is restricted by 64 channels. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
Generally, the devices can synchronize to handle 'presentation timestamp' in CIP packets. This commit adds functionality to pick up this timestamp from in-packets transmitted by the device, then use it for out packets. In current implementation, this module generated the timestamp by itself. This is 'SYT Match' mode. Then drivers with this module acts as synchronization master. This commit allows this module to act as synchronization slave. This commit restricts this mechanism is only available in blocking mode because handling the timestamp in non-blocking mode is more complicated than in blocking mode. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
For duplex streams with synchronization, drivers should pick up 'presentation timestamp' from in-packets and use the timestamp for out-packets. This commit is preparation for this. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
For capturing/playbacking MIDI messages, this commit adds one MIDI conformant data channel. This data channel has multiplexed 8 MIDI data streams. So this data channel can transfer messages from/to 8 MIDI ports. And this commit allows to set PCM format even if AMDTP streams already start. I suppose the case that PCM substreams are going to be joined into AMDTP streams when AMDTP streams are already started for MIDI substreams. Each driver must count how many PCM/MIDI substreams use AMDTP streams to stop AMDTP streams. There are differences between specifications about MIDI conformant data. About the multiplexing, IEC 61883-6:2002, itself, has no information. It describes labels and bytes for MIDI messages and refers to MMA/AMEI RP-027 for 'successfull implementation'. MMA/AMEI RP-027 describes 8 MPX-MIDI data streams for one MIDI conformant data channel. IEC 61883-6:2005 adds 'sequence multiplexing' and apply this way and describe incompatibility between 2002 and 2005. So this commit applies IEC 61883-6:2005. When we find some devices compliant to IEC 61883-6:2002, then this difference should be handles as device quirk in additional work. About the number of bytes in an MIDI conformant data, IEC 61883-6:2002 describe 0,1,2,3 bytes. MMA/AMEI RP-027 describes 'MIDI1.0-1x-SPEED', 'MIDI1.0-2x-SPEED', 'MIDI1.0-3x-SPEED' modes and the maximum bytes for each mode corresponds to 1, 2, 3 bytes. The 'MIDI1.0-2x/3x-SPEED' modes are accompanied with 'negotiation procedure' and 'encapsulation details' but there is no specifications for them. So this commit implements 'MIDI1.0-1x-SPEED' mode for playback, but allows to pick up 1-3 bytes for capturing. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
For capturing PCM, this commit adds the functionality to handle in-stream. This is also applied for dual-wire mode. Currently, capturing 32bit samples are supported. When the sequence of in-packet has discontinuity of dbc, in-stream isn't handled and amdtp_streaming_error() returns true. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
Some codes can be reused to handle in-stream. This commit adds new functions. This commit also renames some functions to keep naming consistency. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
This patch adds 'direction' member to amdtp_stream structure to indicate its direction. This patch also adds 'direction' argument to amdtp_stream_init() function to determine its direction. The amdtp_stream_init() function is exported and used by firewire-speakers and dice so this patch also affects them. This patch just add them. Actual implementation will be done by followed patches. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
This patch adds some macros instead of fixed value for AMDTP according to IEC 61883-1/6. These macros will also be used by followed patches. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Takashi Sakamoto authored
This patch renames some functions, a structure and its member to reuse them in both AMDTP in/out stream. Signed-off-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
- 21 May, 2014 2 commits
-
-
Linus Torvalds authored
-
git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpcLinus Torvalds authored
Pull two powerpc fixes from Ben Herrenschmidt: "Here are a couple of fixes for 3.15. One from Anton fixes a nasty regression I introduced when trying to fix a loss of irq_work whose consequences is that we can completely lose timer interrupts on a CPU... not pretty. The other one is a change to our PCIe reset hook to use a firmware call instead of direct config space accesses to trigger a fundamental reset on the root port. This is necessary so that the FW gets a chance to disable the link down error monitoring, which would otherwise trip and cause subsequent fatal EEH error" * 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: powerpc: irq work racing with timer interrupt can result in timer interrupt hang powerpc/powernv: Reset root port in firmware
-