crypto/scheduler: support DOCSIS security protocol

Add support to the cryptodev scheduler PMD for the DOCSIS security
protocol. This includes adding the following to the scheduler:
- synchronization

crypto/scheduler: support DOCSIS security protocol

Add support to the cryptodev scheduler PMD for the DOCSIS security
protocol. This includes adding the following to the scheduler:
- synchronization of worker's security capabilities
- retrieval of the scheduler's synchronized security capabilities
- retrieval of the security session size i.e. maximum session size
across all workers
- creation of security sessions on each worker
- deletion of security sessions on each worker

Signed-off-by: David Coyle <david.coyle@intel.com>
Signed-off-by: Kevin O'Sullivan <kevin.osullivan@intel.com>
Acked-by: Ciara Power <ciara.power@intel.com>
Acked-by: Anoob Joseph <anoobj@marvell.com>

show more ...

crypto/scheduler: use unified session

This patch updates the scheduler PMD to use unified session
data structure. Previously thanks to the private session
array in cryptodev sym session there are no

crypto/scheduler: use unified session

This patch updates the scheduler PMD to use unified session
data structure. Previously thanks to the private session
array in cryptodev sym session there are no necessary
change needed for scheduler PMD other than the way ops
are enqueued/dequeued. The patch inherits the same design
in the original session data structure to the scheduler PMD
so the cryptodev sym session can be as a linear buffer for
both session header and driver private data.

With the change there are inevitable extra cost on both memory
(64 bytes per session per driver type) and cycle count (set
the correct session for each cop based on the worker before
enqueue, and retrieve the original session after dequeue).

Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com>
Signed-off-by: Akhil Goyal <gakhil@marvell.com>
Acked-by: Kai Ji <kai.ji@intel.com>
Tested-by: Gagandeep Singh <g.singh@nxp.com>
Tested-by: David Coyle <david.coyle@intel.com>
Tested-by: Kevin O'Sullivan <kevin.osullivan@intel.com>

show more ...

cryptodev: move device-specific structures

The device specific structures - rte_cryptodev
and rte_cryptodev_data are moved to cryptodev_pmd.h
to hide it from the applications.

Signed-off-by: Akhil

cryptodev: move device-specific structures

The device specific structures - rte_cryptodev
and rte_cryptodev_data are moved to cryptodev_pmd.h
to hide it from the applications.

Signed-off-by: Akhil Goyal <gakhil@marvell.com>
Tested-by: Rebecca Troy <rebecca.troy@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

show more ...

crypto/scheduler: rename slave to worker

This patch replaces the usage of the word 'slave' with more
appropriate word 'worker' in QAT PMD and Scheduler PMD
as well as in their docs. Also the test ap

crypto/scheduler: rename slave to worker

This patch replaces the usage of the word 'slave' with more
appropriate word 'worker' in QAT PMD and Scheduler PMD
as well as in their docs. Also the test app was modified
to use the new wording.

The Scheduler PMD's public API was modified according to the
previous deprecation notice:
rte_cryptodev_scheduler_slave_attach is now called
rte_cryptodev_scheduler_worker_attach,
rte_cryptodev_scheduler_slave_detach is
rte_cryptodev_scheduler_worker_detach,
rte_cryptodev_scheduler_slaves_get is
rte_cryptodev_scheduler_workers_get.

Also, the configuration value RTE_CRYPTODEV_SCHEDULER_MAX_NB_SLAVES
was renamed to RTE_CRYPTODEV_SCHEDULER_MAX_NB_WORKERS.

Signed-off-by: Adam Dybkowski <adamx.dybkowski@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Acked-by: Akhil Goyal <akhil.goyal@nxp.com>

show more ...

crypto/scheduler: use ring peek API

scheduler PMD uses its own hand-made peek functions
that directly access rte_ring internals.
As now rte_ring has an API for that type of functionality -
change sc

crypto/scheduler: use ring peek API

scheduler PMD uses its own hand-made peek functions
that directly access rte_ring internals.
As now rte_ring has an API for that type of functionality -
change scheduler PMD to use API provided by rte_ring.

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>

show more ...

drivers: prefix global variables with module name

Some global variables are defined with generic names, add component name
as prefix to variables to prevent collusion with application variables.

Si

drivers: prefix global variables with module name

Some global variables are defined with generic names, add component name
as prefix to variables to prevent collusion with application variables.

Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Acked-by: Tianfei Zhang <tianfei.zhang@intel.com>

show more ...

add missing static keyword to globals

Some global variables can indeed be static, add static keyword to them.

Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Jerin Jacob <jerin.jacob

add missing static keyword to globals

Some global variables can indeed be static, add static keyword to them.

Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com>

show more ...

crypto/scheduler: add dynamic logging

Registered new dynamic logtype for driver and
replaced CS_LOG_ERR and RTE_LOG macros with
new CR_SCHED macro, which uses the new logtype.

Signed-off-by: Hari K

crypto/scheduler: add dynamic logging

Registered new dynamic logtype for driver and
replaced CS_LOG_ERR and RTE_LOG macros with
new CR_SCHED macro, which uses the new logtype.

Signed-off-by: Hari Kumar <hari.kumarx.vemula@intel.com>
Reviewed-by: Reshma Pattan <reshma.pattan@intel.com>
Reviewed-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>

show more ...

crypto/scheduler: fix 64-bit mask of workers cores

The list of workers cores was represented by 64-bit bitmask.
It doesn't work if system has cores with id higher than 63.
This fix changes list of w

crypto/scheduler: fix 64-bit mask of workers cores

The list of workers cores was represented by 64-bit bitmask.
It doesn't work if system has cores with id higher than 63.
This fix changes list of workers cores to array of uint16_t.
The size of array equals to RTE_MAX_LCORE.

Fixes: 4c07e0552f0a ("crypto/scheduler: add multicore scheduling mode")
Cc: stable@dpdk.org

Signed-off-by: Kirill Rybalchenko <kirill.rybalchenko@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>

show more ...

crypto/scheduler: fix possible duplicated ring names

This patch fixes the possible duplicated ring names in multi-core
scheduler. Originally two or more multi-core schedulers may have
same worker ri

crypto/scheduler: fix possible duplicated ring names

This patch fixes the possible duplicated ring names in multi-core
scheduler. Originally two or more multi-core schedulers may have
same worker ring names thus will cause initialization error.

Fixes: 4c07e0552f0a ("crypto/scheduler: add multicore scheduling mode")
Cc: stable@dpdk.org

Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>

show more ...

crypto/scheduler: fix multicore rings re-use

When scheduler mode changed from multicore to roundrobin and
back to multicore, scheduler tries to create memory rings with
the same name and fails. The

crypto/scheduler: fix multicore rings re-use

When scheduler mode changed from multicore to roundrobin and
back to multicore, scheduler tries to create memory rings with
the same name and fails. The fix allows to lookup and re-use
previously allocated memory rings.

Fixes: 4c07e0552f0a ("crypto/scheduler: add multicore scheduling mode")
Cc: stable@dpdk.org

Signed-off-by: Kirill Rybalchenko <kirill.rybalchenko@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
Tested-by: Reshma Pattan <reshma.pattan@intel.com>

show more ...

crypto/scheduler: fix memory leak

If private context creation fails, the memory
allocated for it and for some of the rings created
was being leaked.
In case of failure, it must be freed.

Fixes: 4c0

crypto/scheduler: fix memory leak

If private context creation fails, the memory
allocated for it and for some of the rings created
was being leaked.
In case of failure, it must be freed.

Fixes: 4c07e0552f0a ("crypto/scheduler: add multicore scheduling mode")
Cc: stable@dpdk.org

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>

show more ...

crypto/scheduler: set null pointer after freeing

When freeing memory, pointers should be set to NULL,
to avoid memory corruption/segmentation faults.

Fixes: 31439ee72b2c ("crypto/scheduler: add API

crypto/scheduler: set null pointer after freeing

When freeing memory, pointers should be set to NULL,
to avoid memory corruption/segmentation faults.

Fixes: 31439ee72b2c ("crypto/scheduler: add API implementations")
Fixes: 50e14527b9d1 ("crypto/scheduler: improve parameters parsing")
Fixes: 57523e682bb7 ("crypto/scheduler: register operation functions")
Fixes: a783aa634410 ("crypto/scheduler: add packet size based mode")
Fixes: 4c07e0552f0a ("crypto/scheduler: add multicore scheduling mode")
Cc: stable@dpdk.org

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>

show more ...

drivers: use SPDX tag for Intel copyright files

Replace the BSD license header with the SPDX tag for files
with only an Intel copyright on them.

Signed-off-by: Bruce Richardson <bruce.richardson@in

drivers: use SPDX tag for Intel copyright files

Replace the BSD license header with the SPDX tag for files
with only an Intel copyright on them.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>

show more ...

crypto/scheduler: fix multicore reordering

Operations can be dequeued from the reordering ring only after they
were dequeued from the crypto pmd with rte_cryptodev_dequeue_burst()
function. It is no

crypto/scheduler: fix multicore reordering

Operations can be dequeued from the reordering ring only after they
were dequeued from the crypto pmd with rte_cryptodev_dequeue_burst()
function. It is not correct to dequeue them when status just changed
from RTE_CRYPTO_OP_STATUS_NOT_PROCESSED to any other value, as the
operations still can be processed by crypto pmd internally.
Now multicore scheduler workers mark status of all dequeued from
crypto pmd operations with CRYPTO_OP_STATUS_BIT_COMPLETE bit set.
Scheduler will dequeue crypto operations from reordering ring only
when this status bit is set. Prior to put this operation to output
buffer, scheduler clears this bit, so the application gets
unmodified status from crypto pmd.

Fixes: 4c07e0552f0a ("crypto/scheduler: add multicore scheduling mode")

Signed-off-by: Kirill Rybalchenko <kirill.rybalchenko@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>

show more ...

crypto/scheduler: fix build with old gcc

Seen with gcc 4.9.2:
drivers/crypto/scheduler/scheduler_multicore.c:286:2: error:
'for' loop initial declarations are only allowed in C99 or C11 mode
for (

crypto/scheduler: fix build with old gcc

Seen with gcc 4.9.2:
drivers/crypto/scheduler/scheduler_multicore.c:286:2: error:
'for' loop initial declarations are only allowed in C99 or C11 mode
for (uint16_t i = 0; i < sched_ctx->nb_wc; i++)
^

Fixes: 4c07e0552f0a ("crypto/scheduler: add multicore scheduling mode")

Signed-off-by: Jan Blunck <jblunck@infradead.org>

show more ...

cryptodev: support device independent sessions

Change crypto device's session management to make it
device independent and simplify architecture when session
is intended to be used on more than one

cryptodev: support device independent sessions

Change crypto device's session management to make it
device independent and simplify architecture when session
is intended to be used on more than one device.

Sessions private data is agnostic to underlying device
by adding an indirection in the sessions private data
using the crypto driver identifier.
A single session can contain indirections to multiple device types.

New function rte_cryptodev_sym_session_init has been created,
to initialize the driver private session data per driver to be
used on a same session, and rte_cryptodev_sym_session_clear
to clear this data before calling rte_cryptodev_sym_session_free.

Signed-off-by: Slawomir Mrozowicz <slawomirx.mrozowicz@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
Acked-by: Akhil Goyal <akhil.goyal@nxp.com>

show more ...

crypto/scheduler: add multicore scheduling mode

Multi-core scheduling mode is a mode where scheduler distributes
crypto operations in a round-robin base, between several core
assigned as workers.

S

crypto/scheduler: add multicore scheduling mode

Multi-core scheduling mode is a mode where scheduler distributes
crypto operations in a round-robin base, between several core
assigned as workers.

Signed-off-by: Kirill Rybalchenko <kirill.rybalchenko@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>

show more ...