| Age | Commit message (Collapse) | Author |
|---|
|
With the growing number of Intel crypto drivers, it makes sense to
group them all into a single drivers/crypto/intel/ directory.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
The thread to arbiter mapping for 4xxx devices does not allow to
achieve optimal performance for the compression service as it makes
all the engines to compete for the same resources.
Update the logic so that a custom optimal mapping is used for the
compression service.
Signed-off-by: Shashank Gupta <shashank.gupta@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
QAT_402xx is a derivative of 4xxx. Add support for that device in the
qat_4xxx driver by including the DIDs (both PF and VF), extending the
probe and the firmware loader.
402xx uses different firmware images than 4xxx. To allow that the logic
that selects the firmware images was modified.
Signed-off-by: Damian Muszynski <damian.muszynski@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
The sysfs `state` attribute is not protected against race conditions.
If multiple processes perform a device state transition on the same
device in parallel, unexpected behaviors might occur.
For transitioning the device state, adf_sysfs.c calls the functions
adf_dev_init(), adf_dev_start(), adf_dev_stop() and adf_dev_shutdown()
which are unprotected and interdependent on each other. To perform a
state transition, these functions needs to be called in a specific
order:
* device up: adf_dev_init() -> adf_dev_start()
* device down: adf_dev_stop() -> adf_dev_shutdown()
This change introduces the functions adf_dev_up() and adf_dev_down()
which wrap the state machine functions and protect them with a
per-device lock. These are then used in adf_sysfs.c instead of the
individual state transition functions.
Fixes: 5ee52118ac14 ("crypto: qat - expose device state through sysfs for 4xxx")
Signed-off-by: Shashank Gupta <shashank.gupta@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Add infrastructure for implementing the acomp APIs in the QAT driver and
expose the deflate algorithm for QAT GEN2 devices.
This adds
(1) the compression service which includes logic to create, allocate
and handle compression instances;
(2) logic to create configuration entries at probe time for the
compression instances;
(3) updates to the firmware API for allowing the compression service;
and;
(4) a back-end for deflate that implements the acomp api for QAT GEN2
devices.
The implementation configures the device to produce data compressed
statically, optimized for throughput over compression ratio.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Adam Guerin <adam.guerin@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Expose the device state through an attribute in sysfs and allow to
change it. This is to stop and shutdown a QAT device in order to change
its configuration.
The state attribute has been added to a newly created `qat` attribute
group which will contain all _QAT specific_ attributes.
The logic that implements the sysfs entries is part of a new file,
adf_sysfs.c. This exposes an entry point to allow the driver to create
attributes.
The function that creates the sysfs attributes is called from the probe
function of the driver and not in the state machine init function to
allow the change of states even if the device is in the down state.
In order to restore the device configuration between a transition from
down to up, the function that configures the devices has been abstracted
into the HW data structure.
The `state` attribute is only exposed for qat_4xxx devices.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Co-developed-by: Tomasz Kowallik <tomaszx.kowalik@intel.com>
Signed-off-by: Tomasz Kowallik <tomaszx.kowalik@intel.com>
Reviewed-by: Adam Guerin <adam.guerin@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Vladis Dronov <vdronov@redhat.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
QAT_401xx is a derivative of 4xxx. Add support for that device in the
qat_4xxx driver by including the DIDs (both PF and VF), extending the
probe and the firmware loader.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Srinivas Kerekare <srinivas.kerekare@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
As a consequence of the refactored VF2PF interrupt handling logic, a
function that disables specific VF2PF interrupts is no longer needed.
Instead, a simpler function that disables all the interrupts, also
hiding the device specific amount of VFs to be disabled from the
pfvf_ops users, would be sufficient.
This patch replaces disable_vf2pf_interrupts() with the new
disable_all_vf2pf_interrupts(), which doesn't need any argument and
disables all the VF2PF interrupts.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Change the VF2PF interrupt handler in the PF ISR and the definition of
the internal PFVF API to correct the current implementation, which can
result in missed interrupts.
More specifically, current HW generations consider a write to the mask
register, regardless of the value, as an acknowledge of any pending
VF2PF interrupt. Therefore, if there is an interrupt between the source
register read and the mask register write, such interrupt will not be
delivered and silently acknowledged, resulting in a lost VF2PF message.
To work around the problem, rather than disabling specific interrupts,
disable all the interrupts and re-enable only the ones that we are not
serving (excluding the already disabled ones too). This will force any
other pending interrupt to be triggered and be serviced by a subsequent
ISR.
This new approach requires, however, changes to the interrupt related
pfvf_ops functions. In particular, get_vf2pf_sources() has now been
removed in favor of disable_pending_vf2pf_interrupts(), which not only
retrieves and returns the pending (and enabled) sources, but also
disables them.
As a consequence, introduce the adf_disable_pending_vf2pf_interrupts()
utility in place of adf_disable_vf2pf_interrupts_irq(), which is no
longer needed.
Cc: stable@vger.kernel.org
Fixes: 993161d ("crypto: qat - fix handling of VF to PF interrupts")
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Add support for HW QAT Power Management (PM) feature.
This feature is enabled at init time (1) by sending an admin message to
the firmware, targeting the admin AE, that sets the idle time before
the device changes state and (2) by unmasking the PM source of interrupt
in ERRMSK2.
The interrupt handler is extended to handle a PM interrupt which
is triggered by HW when a PM transition occurs. In this case, the
driver responds acknowledging the transaction using the HOST_MSG
mailbox.
Signed-off-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Co-developed-by: Marcinx Malinowski <marcinx.malinowski@intel.com>
Signed-off-by: Marcinx Malinowski <marcinx.malinowski@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Marco Chiappero <marco.chiappero@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Add the logic required to enable the compression service for 4xxx devices.
This allows to load the compression firmware image and report
the appropriate compression capabilities.
The firmware image selection for a given device is based on the
'ServicesEnabled' key stored in the internal configuration, which is
added statically at the probe of the device according to the following
rule, by default:
- odd numbered devices assigned to compression services
- even numbered devices assigned to crypto services
In addition, restore the 'ServicesEnabled' key, if present, when SRIOV
is enabled on the device.
Signed-off-by: Tomasz Kowalik <tomaszx.kowalik@intel.com>
Co-developed-by: Mateuszx Potrola <mateuszx.potrola@intel.com>
Signed-off-by: Mateuszx Potrola <mateuszx.potrola@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Marco Chiappero <marco.chiappero@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
The original design and current implementation of the PFVF protocol
expects the sender to both acquire and relinquish the ownership of the
shared CSR by setting and clearing the "in use" pattern on the remote
half of the register when sending a message. This happens regardless of
the acknowledgment of the reception, to guarantee changes, including
collisions, are surely detected.
However, in the case of a request that requires a response, collisions
can also be detected by the lack of a reply. This can be exploited to
speed up and simplify the above behaviour, letting the receiver both
acknowledge the message and release the CSR in a single transaction:
1) the sender can return as soon as the message has been acknowledged
2) the receiver doesn't have to wait long before acquiring ownership
of the CSR for the response message, greatly improving the overall
throughput.
Howerver, this improvement cannot be leveraged for fire-and-forget
notifications, as it would be impossible for the sender to clearly
distinguish between a collision and an ack immediately followed by a new
message.
This patch implements this optimization in a new version of the protocol
(v3), which applies the fast-ack logic only whenever possible and
guarantees backward compatibility with older versions. For requests, a
new retry loop guarantees a correct behaviour.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Allow the VF driver to get the supported device capabilities through PFVF,
by adding a new block message, the Capability Summary.
This messages allows to exchange the capability through masks, which
report, depending on the Capability Summary version, up to the following
information:
- algorithms and/or services that are supported by the device (e.g.
symmetric crypto, data compression, etc.)
- (extended) compression capabilities, with details about the compression
service (e.g. if compress and verify is supported by this device)
- the frequency of the device
This patch supports the latest Capabilities Summary version 3 for VFs,
but will limit support for the PF driver to version 2. This change also
increases the PFVF protocol to version 2.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
This driver relies on either the FW (on the PF) or the PF (on the VF) to
know how crypto services and rings map to one another. Store this
information so that it can be referenced in the future at runtime for
checks or extensions.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
This patch adds an entry for storing the PFVF protocol version for both
PF and VFs. While not currently used, knowing and storing the remote
protocol version enables more complex compatibility checks and/or newer
features for compatible PFVF endpoints in the future.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
This implementation of the PFVF protocol was designed around the GEN2
devices and its CSR format. In order to support future generations,
which come with differently sized fields, change the definition of the PFVF
message and make it abstract by means of a new pfvf_message struct. Also,
introduce some utilities to translate to and from the new message format
and the device specific CSR format.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Currently PF and VF share the same send and receive logic for the PFVF
protocol. However, the inner behaviour still depends on the specific
direction, requiring a test to determine the if the sender is a PF or a
VF. Moreover the vf_nr parameter is only required for PF2VF messages and
ignored for the opposite direction.
Make the GEN2 send and recv completely direction agnostic, by calculating
and determining any direction specific input in the caller instead, and
feeding the send and the receive functions with the same arguments for
both PF and VF. In order to accommodate for this change, the API of the
pfvf_ops send and recv has been modified to remove any reference to vf_nr.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Add support for triggering a HW reset of a specific ring pair.
Being a device specific feature, add it to the hw_device_data struct.
This feature is supported only by QAT GEN4 devices.
This patch is based on earlier work done by Zelin Deng.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Get compression extended capabilities mask from firmware through the
init/admin channel.
These capabilities are stored in the accel_dev structure and will be
communicated to VF through the PFVF channel.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Marco Chiappero <marco.chiappero@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Remove min_iov_compat_ver field as for now all versions are compatible.
Compatibility is determined by a series of rules and dynamic conditions
such as specific configurations.
In any case the minimum version requirement for compatibility is
an inadequate and obsolete approach which should be removed.
At this time compatibility can be assured across the currently available
versions.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Currently, any PF response to a VF request is fully parsed during the
interrupt handling. This way the individual response values are stored
into the accel_dev structure, preventing the caller to access and decode
the full response message itself.
Change this behavior, by letting the API return back the entire message
to the caller, in order to:
- keep correlated code together, that is, the (building of the)
request and the (decoding of the) response;
- avoid polluting the accel_dev data structure with unnecessary and at
times temporary values; only the entire message is stored in a
temporary buffer.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Refactor the PFVF receive logic so it is common between PF and VF and
make it device specific.
This is in preparation for the introduction of PFVF support in the
qat_4xxx driver since the receive logic differs between QAT GEN2 and
QAT GEN4 devices.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Co-developed-by: Marco Chiappero <marco.chiappero@intel.com>
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Make the PFVF send function device specific.
This is in preparation for the introduction of PFVF support in the
qat_4xxx driver since the send logic differs between QAT GEN2 and
QAT GEN4 devices.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Add the function get_vf2pf_offset() to adf_pfvf_ops to differentiate the
CSRs used for pf2vf and vf2pf.
Offsets may or may not be direction specific depending on QAT
generation. Since in QAT GEN2 the CSR is not direction specific, i.e.
there is a single mailbox register shared for pf2vf and vf2pf, both
get_vf2pf_offset() and get_vf2pf_offset() will return the same offset.
This change is to make the direction explicit, so it is easier to
understand and debug and also in preparation for the introduction of
PFVF support in the qat_4xxx driver since QAT GEN4 devices have a
separate CSR for pf2vf and vf2pf communications.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Add pfvf_ops structure to isolate PFVF related functions inside the
adf_hw_device_data structure.
For GEN2, the structure is populated using one of the two helper
functions, adf_gen2_init_pf_pfvf_ops() or adf_gen2_init_vf_pfvf_ops(),
for the PF and VF driver respectively.
For the DH895XCC PF driver, the structure is populated using
adf_gen2_init_pf_pfvf_ops() but some of the functions are then
overwritten.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Currently, VF to PF interrupt handling is based on the DH895XCC device
behavior, which is not entirely common to all devices.
In order to make interrupt detection and handling correct for all of the
supported devices, make the interrupt handling device specific by:
- introducing get_vf2pf_sources() for getting a 32 bits long value
where each bit represents a vf2pf interrupt;
- adding the device [enable|disable]_vf2pf_interrupts to hw_data;
- defining [enable|disable]_vf2pf_interrupts for all the devices that
are currently supported, using only their required and specific
ERRSOU|ERRMASK registers (DH895XCC has 32 interrupts spread across
ERRSOU3 and ERRSOU5, C62X/C3XXX has 16 in ERRSOU3 only, etc).
Code has been shared by different devices wherever possible.
This patch is based on earlier work done by Salvatore Benedetto.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
After reset or boot, QAT 4xxx devices are inactive and require to be
explicitly activated.
This is done by writing the DRV_ACTIVE bit in the PM_INTERRUPT register
and polling the PM_INIT_STATE to make sure that the transaction has
completed properly.
If this is not done, the driver will fail the initialization sequence
reporting the following message:
[ 22.081193] 4xxx 0000:f7:00.0: enabling device (0140 -> 0142)
[ 22.720285] QAT: AE0 is inactive!!
[ 22.720287] QAT: failed to get device out of reset
[ 22.720288] 4xxx 0000:f7:00.0: qat_hal_clr_reset error
[ 22.720290] 4xxx 0000:f7:00.0: Failed to init the AEs
[ 22.720290] 4xxx 0000:f7:00.0: Failed to initialise Acceleration Engine
[ 22.720789] 4xxx 0000:f7:00.0: Resetting device qat_dev0
[ 22.825099] 4xxx: probe of 0000:f7:00.0 failed with error -14
The patch also temporarily disables the power management source of
interrupt, to avoid possible spurious interrupts as the power management
feature is not fully supported.
The device init function has been added to adf_dev_init(), and not in the
probe of 4xxx to make sure that the device is re-enabled in case of
reset.
Note that the error code reported by hw_data->init_device() in
adf_dev_init() has been shadowed for consistency with the other calls
in the same function.
Fixes: 8c8268166e83 ("crypto: qat - add qat_4xxx driver")
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Remove packed attribute from structures that do not need to be packed.
These are just used internally and not shared with firmware.
This also fixes a series of warning when compiling the driver with the
flag -Waddress-of-packed-member, similar to the following:
drivers/crypto/qat/qat_c62xvf/adf_c62xvf_hw_data.c:102:28: warning: taking address of packed member 'csr_ops' of class or structure 'adf_hw_device_data' may result in an unaligned pointer value
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Change the irq allocation logic so that it is possible to free only the
allocated irqs in case of error.
A new flag is introduced for every PF/VF interrupt. This flag is set to
"true" only when the interrupt is requested.
During clean up, devm_free_irq() is only called if this flag is set.
Signed-off-by: Maksim Lukoshkov <maksim.lukoshkov@intel.com>
Co-developed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Signed-off-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Replace deprecated MSI enable and disable respectively and update
handling of return values.
Signed-off-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Co-developed-by: Gupta Shashank <shashank.gupta@intel.com>
Signed-off-by: Gupta Shashank <shashank.gupta@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
All QAT GEN2 devices share the same register offset for masking interrupts,
so they don't need any complex device specific infrastructure.
Remove this function in favor of a constant in order to simplify the code.
Also, future generations may require a more complex device specific
handling, making the current approach obsolete anyway.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Currently all the functions related to the activation of the PFVF
protocol, both on PF and VF, include the direction specific "vf2pf"
name.
Replace the existing naming schema with:
- a direction agnostic naming, that applies to both PF and VF, for the
function pointer ("pfvf")
- a direction specific naming schema for the implementations ("pf2vf" or
"vf2pf")
In particular this patch renames:
- adf_pf_enable_vf2pf_comms() in adf_enable_pf2vf_comms()
- enable_vf2pf_comms() in enable_pfvf_comms()
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
In the PF interrupt handler, the interrupt is disabled for a set of VFs
by writing to the interrupt source mask register, ERRMSK.
The interrupt is re-enabled in the bottom half handler by writing to the
same CSR. This is done through the functions enable_vf2pf_interrupts()
and disable_vf2pf_interrupts() which perform a read-modify-write
operation on the ERRMSK registers to mask and unmask the source of
interrupt.
There can be a race condition where the top half handler for one VF
interrupt runs just as the bottom half for another VF is about to
re-enable the interrupt. Depending on whether the top or bottom half
updates the CSR first, this would result either in a spurious interrupt
or in the interrupt not being re-enabled.
This patch protects the access of ERRMSK with a spinlock.
The functions adf_enable_vf2pf_interrupts() and
adf_disable_vf2pf_interrupts() have been changed to acquire a spin lock
before accessing and modifying the ERRMSK registers. These functions use
spin_lock_irqsave() to disable IRQs and avoid potential deadlocks.
In addition, the function adf_disable_vf2pf_interrupts_irq() has been
added. This uses spin_lock() and it is meant to be used in the top half
only.
Signed-off-by: Kanchana Velusamy <kanchanax.velusamy@intel.com>
Co-developed-by: Marco Chiappero <marco.chiappero@intel.com>
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
The PF driver uses the tasklet vf2pf_bh_tasklet to schedule a workqueue
to handle the vf2vf protocol (pf2vf_resp_wq).
Since the tasklet is only used to schedule the workqueue, this patch
removes it and schedules the pf2vf_resp_wq workqueue directly for the
top half.
Signed-off-by: Svyatoslav Pankratov <svyatoslav.pankratov@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Marco Chiappero <marco.chiappero@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
There is a chance that the PFVF handler, adf_vf2pf_req_hndl(), runs
twice for the same request when multiple interrupts come simultaneously
from different VFs.
Since the source VF is identified by a positional bit set in the ERRSOU
registers and that is not cleared until the bottom half completes, new
top halves from other VFs may reschedule a second bottom half for
previous interrupts.
This patch solves the problem in the ISR handler by not considering
sources with already disabled interrupts (and processing pending), as
set in the ERRMSK registers.
Also, move some definitions where actually needed.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Enable the detection of hangs by setting watchdog timers (WDTs) on
generations that supports that feature.
The default timeout value comes from HW specs. WTDs are reset each time
an accelerator wins arbitration and is able to send/read a command to/from
an accelerator.
The value has added significant margin to make sure there are no spurious
timeouts. The scope of watchdog is per QAT device.
If a timeout is detected, the firmware resets the accelerator and
returns a response descriptor with an appropriate error code.
Signed-off-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
The hardware specific function adf_get_arbiter_mapping() modifies
the static array thrd_to_arb_map to disable mappings for AEs
that are disabled. This static array is used for each device
of the same type. If the ae mask is not identical for all devices
of the same type then the arbiter mapping returned by
adf_get_arbiter_mapping() may be wrong.
This patch fixes this problem by ensuring the static arbiter
mapping is unchanged and the device arbiter mapping is re-calculated
each time based on the static mapping.
Signed-off-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Add support for QAT 4xxx devices.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Add an hook to initialize the vector routing table with the default
values before MSIx is enabled.
The new function set_msix_rttable() is called only if present in the
struct adf_hw_device_data of the device. This is to allow for QAT
devices that do not support that functionality.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Introduce support for devices that require multiple firmware images.
If a device requires more than a firmware image to operate, load the
image to the appropriate Acceleration Engine (AE).
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Add support for the QAT gen4 devices in the firmware loader.
Signed-off-by: Jack Xu <jack.xu@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Change type of ae_mask in adf_hw_device_data to allow for devices with
more than 16 Acceleration Engines (AEs).
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Abstract writes to the service arbiter enable register.
This is in preparation for the introduction of the qat_4xxx driver since
the arbitration enable register differes between QAT GEN2 and QAT GEN4
devices.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Maksim Lukoshkov <maksim.lukoshkov@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Abstract the implementation of BUILD_RING_BASE_ADDR.
This is in preparation for the introduction of the qat_4xxx driver since
the value of the ring base differs between QAT GEN2 and QAT GEN4
devices.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Maksim Lukoshkov <maksim.lukoshkov@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Add logic to detect device capabilities for c62x, c3xxx and dh895xcc.
Read fuses, straps and legfuses CSRs and build the device capabilities
mask. This will be used to understand if a certain service is supported
by a device.
This patch is based on earlier work done by Conor McLoughlin.
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
The arbiter configuration, the offset to the arbiter config CSR and the
offset to the worker thread to service arbiter CSR are going to be
different in QAT GEN4 devices although the logic that uses them is the
same across all QAT generations.
This patch reworks the gen-specific parts of the arbiter access code by
introducing the arb_info structure, that contains the values that are
generation specific, and a function in the structure adf_hw_device_data,
get_arb_info(), that allows to get them.
Since the arbiter values for QAT GEN2 devices (c62x, c3xxx and
dh895xcc) are the same, a single function, adf_gen2_get_arb_info() is
provided in adf_gen2_hw_data.c and referenced by each QAT GEN2 driver.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Introduce admin AE mask. If this mask set, the fw constant message is
sent only to engines that belong to that set, otherwise it is sent to
all engines.
This is in preparation for the qat_4xxx driver where the constant message
should be sent only to admin engines.
In GEN2 devices (c62x, c3xxx and dh895xcc), the admin AE mask is 0 and
the fw constants message is sent to all AEs.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Abstract access to admin interface and move generation specific code into
adf_gen2_hw_data.c in preparation for the introduction of the qat_4xxx
driver.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
Abstract access to transport CSRs and move generation specific code into
adf_gen2_hw_data.c in preparation for the introduction of the qat_4xxx
driver.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
|
The number of AE2FUNC_MAP registers is different in every QAT device
(c62x, c3xxx and dh895xcc) although the logic and the register offsets
are the same across devices.
This patch separates the logic that configures the iov threads in a
common function that takes as input the number of AE2FUNC_MAP registers
supported by a device. The function is then added to the
adf_hw_device_data structure of each device, and called with the
appropriate parameters.
The configure iov thread logic is added to a new file,
adf_gen2_hw_data.c, that is going to contain code that is shared across
QAT GEN2 devices.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
|
