Pablo de Lara [Mon, 17 Jul 2017 08:29:53 +0000 (09:29 +0100)]
cryptodev: reorder auth transform
IV was positioned differently in authentication
transform structure, compared to the other two
transforms (cipher and AEAD).
To keep consistency, digest length is moved to
the end of the transform.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Pablo de Lara [Mon, 17 Jul 2017 08:29:52 +0000 (09:29 +0100)]
cryptodev: rename ADD field
Additional Authenticated Data (AAD) is called "aad" in most
places of cryptodev, but it was called "add_auth_data"
in the AEAD transform transform (aead_xform).
This field is renamed to "aad_length" in order to keep
consistency.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Older generations of QuickAssist hardware
may not support all algorithms supported by newer
generations. When sessions were specific to the device
this only needed to be handled on session creation.
With device-agnostic sessions, a session created
for a newer device may get routed to an older device which
can't support it.
This patch adds an enum to define QAT device generations
and uses this to detect and handle the above case on the
data path.
It also renames the capabilities structures and #defines
to match the generation names and adds the generation
to the device table in the documentation.
Pablo de Lara [Fri, 14 Jul 2017 06:48:47 +0000 (07:48 +0100)]
crypto/aesni_mb: fix zero burst dequeue
In the unlikely scenario that an application
calls rte_cryptodev_dequeue_burst with nb_ops = 0,
there was a job leak, as a job would be created
but would not be populated, as no operation is passed.
Fixes: 0f548b50a160 ("crypto/aesni_mb: process crypto op on dequeue") Cc: stable@dpdk.org Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Declan Doherty <declan.doherty@intel.com>
Pablo de Lara [Fri, 14 Jul 2017 07:06:52 +0000 (08:06 +0100)]
cryptodev: fix KASUMI F9 expected parameters
For KASUMI F9 algorithm, COUNT, FRESH and DIRECTION
input values need to be contiguous with
the message, as described in the KASUMI and QAT PMD
documentation.
Before, the COUNT and FRESH values were set
as part of the AAD (now IV), but always set before
the beginning of the message.
Since now the IV is set after the crypto operation,
it is not possible to have these values in the
expected location.
Therefore, as these are required to be contiguous,
cryptodev API will expect these them to be passed
as a single buffer, already constructed, so
authentication IV parameters not needed anymore.
Fixes: 681f540da52b ("cryptodev: do not use AAD in wireless algorithms") Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Pablo de Lara [Thu, 13 Jul 2017 05:36:50 +0000 (06:36 +0100)]
doc: extend installation section for SNOW3G/KASUMI
SNOW3G and KASUMI SW libraries encrypt buffers
assuming that they are padded to a specific block size.
This behaviour can be changed to avoid buffer overflow,
by modifying the Makefile of these libraries.
Therefore, the Installation section in the SNOW3G and
KASUMI documentation has been extended, to document
this case.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Declan Doherty <declan.doherty@intel.com>
Pablo de Lara [Thu, 13 Jul 2017 05:36:49 +0000 (06:36 +0100)]
doc: add missing algorithm in limitations for QAT
For KASUMI, SNOW3G and ZUC algorithms, offsets and lengths
of the data to cipher or authenticate is provided in bits,
but QAT does not support non-byte aligned values,
although only KASUMI and SNOW3G were mentioned.
Fixes: d9b7d5bbc845 ("crypto/qat: add ZUC EEA3/EIA3 capability") Cc: stable@dpdk.org Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Declan Doherty <declan.doherty@intel.com>
Pablo de Lara [Thu, 13 Jul 2017 05:36:48 +0000 (06:36 +0100)]
doc: remove incorrect limitation on AESNI-MB PMD
AESNI MB PMD supports sessionless operations,
but the documentation was stating that only
operations with session were supported.
Fixes: 924e84f87306 ("aesni_mb: add driver for multi buffer based crypto") Cc: stable@dpdk.org Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Declan Doherty <declan.doherty@intel.com>
Pablo de Lara [Thu, 13 Jul 2017 05:36:47 +0000 (06:36 +0100)]
doc: remove incorrect limitation on QAT PMD
QAT supports authentication only operations,
for any authentication algorithm (such as SHA1-HMAC),
as long as it is supported by QAT, so it means
that it is not necessary to create a chained operation
in order to use these algorithms.
Fixes: 1703e94ac5ce ("qat: add driver for QuickAssist devices") CC: stable@dpdk.org Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com> Acked-by: Declan Doherty <declan.doherty@intel.com>
Pablo de Lara [Tue, 11 Jul 2017 06:30:43 +0000 (07:30 +0100)]
cryptodev: remove AAD size in auth capabilities
Additional Authenticated Data (AAD) was removed from the
authentication parameters, but still the supported size
was part of the authentication capabilities of a PMD.
Fixes: 4428eda8bb75 ("cryptodev: remove AAD from authentication structure") Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Declan Doherty <declan.doherty@intel.com>
Pablo de Lara [Thu, 13 Jul 2017 03:35:12 +0000 (04:35 +0100)]
crypto/aesni_mb: fix possible crypto job leak
When dequeueing operations from an AESNI-MB device,
crypto jobs are dequeued from the internal scheduler
in the Multi-buffer library.
If the number of jobs available to retrieve
are higher than the number of crypto operations
that are required, then an extra job is retrieved
(due to an incorrect conditional), but not used.
This leads to a job leak and the operation associated
to that job will not be ever dequeued.
Fixes: 0f548b50a160 ("crypto/aesni_mb: process crypto op on dequeue") Cc: stable@dpdk.org Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Declan Doherty <declan.doherty@intel.com>
Fan Zhang [Fri, 7 Jul 2017 05:17:30 +0000 (06:17 +0100)]
crypto/scheduler: fix slave name parsing
This patch fixes the incorrect index checking in parse_slave
function.
Fixes: 503e9c5afb38 ("crypto/scheduler: register as vdev driver") 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>
Pablo de Lara [Fri, 7 Jul 2017 04:36:56 +0000 (05:36 +0100)]
doc: fix crypto scheduler command line examples
Sample command lines for crypto scheduler were not correct,
due to:
- Typo in "crypto_scheduler" driver name
- Multiple virtual devices require having unique names,
driver name + a suffix, otherwise, just a single device is
created.
Fixes: d58a3f312545 ("crypto/scheduler: add documentation") Cc: stable@dpdk.org Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: John McNamara <john.mcnamara@intel.com>
Harry van Haaren [Mon, 17 Jul 2017 16:09:47 +0000 (17:09 +0100)]
eventdev: fix memory realloc check in port config
This commit fixes the check to use the just reallocated
links_map variable, instead of stale dev->data->links_map.
Later the new variable is written to the dev->data->links_map,
so the stale-ness is only temporary.
Coverity issue: 143456 Fixes: 4f0804bbdfb9 ("eventdev: implement the northbound APIs") Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> Reviewed-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Burst mode capability flag was introduced in 73e6b8c9 for event drivers.
DPAA2 event driver supports burst mode so this patch adds this capability
flag in DPAA2 event driver
Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com> Reviewed-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Daniel Mrzyglod [Wed, 19 Jul 2017 14:31:17 +0000 (16:31 +0200)]
net/bonding: add other aggregator modes
This patch add support for setting additional aggregator modes for
IEEE802.3AD in similar manner that are supported in kernel mode.
This will add support for other manner:
stable - default mode taken from IEEE802.11AX this is default
aggregator mode
bandwidth - takes aggregator with highest bandwidth
count - takes aggregator with biggest number of slaves
Signed-off-by: Daniel Mrzyglod <danielx.t.mrzyglod@intel.com> Acked-by: Declan Doherty <declan.doherty@intel.com>
Qiming Yang [Tue, 18 Jul 2017 02:28:34 +0000 (10:28 +0800)]
net/ixgbe: fix Rx/Tx queue interrupt for x550 devices
x550 devices don't map interrupt vector before enabling Rx/Tx queue
interrupt.
Because of this interrupt mode is not working for x550 devices.
Fixes: d2e72774e58c ("ixgbe/base: support X550") Cc: stable@dpdk.org Signed-off-by: Qiming Yang <qiming.yang@intel.com> Acked-by: Wei Dai <wei.dai@intel.com>
Listen to INTR_RMV events issued by slaves.
Add atomic flags on slave queues to detect use of slave bursts function.
If a removal is detected, set the recollection flag on this slave.
During a slave upkeep round, if its recollection flag is set and its
burst functions are not in use by any thread, remove that slave.
Signed-off-by: Gaetan Rivet <gaetan.rivet@6wind.com> Acked-by: Olga Shern <olgas@mellanox.com>
Add the "exec" device type.
The parameters given to this type of device will be executed in a shell.
The output of this command is then used as a definition for a device.
That command can be re-interpreted if the related device is not
plugged-in. It allows for a device definition to react to system
changes (e.g. changing PCI bus for a given device).
Signed-off-by: Gaetan Rivet <gaetan.rivet@6wind.com> Acked-by: Olga Shern <olgas@mellanox.com>
Introduce the fail-safe poll mode driver initialization and enable its
build infrastructure.
This PMD allows for applications to benefit from true hot-plugging
support without having to implement it.
It intercepts and manages Ethernet device removal events issued by
slave PMDs and re-initializes them transparently when brought back.
It also allows defining a contingency to the removal of a device, by
designating a fail-over device that will take on transmitting operations
if the preferred device is removed.
Applications only see a fail-safe instance, without caring for
underlying activity ensuring their continued operations.
Signed-off-by: Gaetan Rivet <gaetan.rivet@6wind.com> Acked-by: Olga Shern <olgas@mellanox.com>
net/ixgbe: support 82599ES SCTP packet drop action
82599ES can support SCTP packet drop action, but the
configuration is different from TCP or UDP packet, so
it need to rework some FDIR related code to adapt
drop action rule of SCTP packet.
Previously SW workaround for GL_SWR_PRI_JOIN_MAP is added for X710
performance. As new FW version 6.0 supports ADQ,
value for GL_SWR_PRI_JOIN_MAP should be changed, otherwise
ehtertype filter will be impacted.
Remove checks of Linux kernel version
in order to support kernel with backported features.
the expected behavior with a kernel that doesn't support flower
and other bits is the following:
-flow validate can return successfully
-flow create using the same rule fails.
Using the "remote" feature without kernel flower does not fail silently.
The TAP instance is not initialized if the requested parameters cannot
be satisfied.
it has been tested on an old kernel without required support:
PMD: Kernel refused TC filter rule creation (2): No such file or directory
PMD: tap0 failed to create implicit rules.
PMD: Can't set up remote feature: No such file of directory(2)
PMD: TAP Unable to initialize net_tap0
PF driver and VF driver communicated with each other by virtual
channel message. When VF sends message to PF to enable some
offload capability, PF should response if it is successful or not.
VIRTCHNL_OP_ENABLE_VLAN_STRIPPING is a new added message and the
old PF driver doesn’t support that. So no response is received by
DPDK VF. Then VF is blocked on this message and cannot roll back.
This patch clears pending command on VF side when the waiting duration
expires to avoid blocking following communication.
Fixes: 5f0b95d59a98 ("net/i40e: support VLAN stripping for VF") Cc: stable@dpdk.org Signed-off-by: Beilei Xing <beilei.xing@intel.com>
net/mlx5: change start pointer of compressed completion
On a host having 128B cacheline size, some devices insert 64B padding in
each completion entry to avoid partial cacheline write by HW. But, as the
padding is ahead of completion data, casting a completion entry to
compressed mini-completions must start from the middle of the completion.
Jerin Jacob [Tue, 11 Jul 2017 13:54:26 +0000 (19:24 +0530)]
net/thunderx: update sq config register field
cq_limit field is added in cn88xx-pass2 and subsequent
versions. Reflect the change in the sq_config structure.
This change is backward compatible as the old pass versions
ignore this field.
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Ivan Malov [Sat, 8 Jul 2017 15:16:55 +0000 (16:16 +0100)]
net/sfc: request MAC stats upload immediately on port start
If MAC stats refresh is arranged to be done by periodic DMA,
the first DMA transaction is unlikely to occur right on the
port start; if the user tries to get stats right after port
start and before the transaction occurs, bogus figures will
be collected; a one-off stats upload on port start is a fix
Fixes: 1caab2f1e684 ("net/sfc: add basic statistics") Cc: stable@dpdk.org Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Changpeng Liu [Thu, 20 Jul 2017 09:16:29 +0000 (17:16 +0800)]
examples/vhost_scsi: introduce a new sample app
vhost-user protocol is common to many virtio devices, such as
virtio_net/virtio_scsi/virtio_blk. Since DPDK vhost library
removed the NET specific data structures, the vhost library
is common to other virtio devices, such as virtio-scsi.
Here we introduce a simple memory based block device that
can be presented to Guest VM through vhost-user-scsi-pci
controller. Similar with vhost-net, the sample application
will process the I/Os sent via virt rings.
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Zhiyong Yang [Mon, 10 Jul 2017 08:06:48 +0000 (16:06 +0800)]
vhost: fix initialization
Exception handling is executed in the normal path and it will cause
vhost-user init failure.
Fixes: d6983a70e259 ("vhost: check return of pthread calls") Reported-by: Lei Yao <lei.a.yao@intel.com> Signed-off-by: Zhiyong Yang <zhiyong.yang@intel.com> Tested-by: Lei Yao <lei.a.yao@intel.com> Reviewed-by: Jens Freimann <jfreimann@redhat.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
This commit broke the rte_devargs API by changing the meaning of
the rte_devtype enum.
Restore the previous API, unit tests and function calls.
Introduce parallel enum that acts as translation between previous API
and current structures.
Restoring the previous API means that -w and -b are not usable anymore
with any bus having implemented the "parse" operation. Only PCI devices
can be used with -w and -b, virtual devices are declared using vdev.
The prior scan should link the relevant rte_devargs to the newly
allocated rte_device. As such, it is useless to pass device arguments to
the plug callback. Those arguments are available within the devargs
field of the rte_device structure.
The device handle is already known and does not have to be infered from
the PCI address. The relevant helpers are already available within the
PCI bus to avoid searching for a handle already known.
Additionally, rte_memcpy.h was erroneously included.
When an application requests the use of a PCI device, it can currently
interchangeably use either the longform DomBDF format (0000:00:00.0) or
the shorter BDF format (00:00.0).
When a device is inserted via the hotplug API, it must first be scanned
and then will be identified by its name using `find_device`. The name of
the device must match the name given by the user to be found and then
probed.
A new function sets the expected name for a scanned PCI device. It was
previously generated from parsing the PCI address. This canonical name
is superseded when an rte_devargs exists describing the device. In such
case, the device takes the given name found within the rte_devargs.
As the rte_devargs is linked to the rte_pci_device during scanning, it
can be avoided during the probe. Additionally, this fixes the issue of
the rte_devargs lookup not being done within rte_pci_probe_one.
Fixes: beec692c5157 ("eal: add name field to generic device") Cc: stable@dpdk.org Signed-off-by: Gaetan Rivet <gaetan.rivet@6wind.com>
The hotplug API requires a few properties that were not previously
explicitly enforced:
- Idempotency, two consecutive scans should result in the same state.
- Upon returning, internal devices are now allocated and available
through the new `find_device` operator, meaning that they should be
identifiable.
The current rte_eal_hotplug_add implementation identifies devices by
their names, as it is readily available and easy to define.
The device name must be passed to the internal rte_device handle in
order to be available during scan, when it is then assigned to the
device. The current way of passing down this information from the device
declaration is through the global rte_devargs list.
Furthermore, the rte_device cannot take a bus-specific generated name,
as it is then not identifiable by the `find_device` operator. The device
must take the user-defined name. Ideally, an rte_device name should not
change during its existence.
This commit generates a new rte_devargs associated with the plugged
device and inserts it in the global rte_devargs list. It consequently
releases it upon device removal.
Some buses will operate either in whitelist or blacklist mode.
This mode is currently passed down by the rte_eal_devargs_add function
with the devtype argument.
When inserting devices using the hotplug API, the implicit assumption is
that this device is being whitelisted, meaning that it is explicitly
requested by the application to be used. This can conflict with the
initial bus configuration.
While the rte_eal_devargs_add API is being deprecated soon, it cannot
be modified at the moment to accommodate this situation.
As such, this new experimental API offers a bare interface for inserting
rte_devargs without directly manipulating the global rte_devargs list.
This new function expects a fully-formed rte_devargs, previously parsed
and allocated.
It does not check whether the new rte_devargs is compatible with current
bus configuration, but will replace any eventual existing one for the same
device, allowing the hotplug operation to proceed. i.e. a previously
blacklisted device can be redefined as being whitelisted.
Hotplug support introduces the possibility of removing devices from the
system. Allocated resources must be freed.
Extend the rte_devargs API to allow freeing allocated resources.
This API is experimental and bound to change. It is currently designed
as a symetrical to rte_eal_devargs_add(), but the latter will evolve
shortly anyway.
Its DEVTYPE parameter is currently only used to specify scan policies,
and those will evolve in the next release. This evolution should
rationalize the rte_devargs API.
As such, the proposed API here is not the most convenient, but is
taylored to follow the current design and integrate easily with its main
use within rte_eal_hotplug_* functions.
This method must be implemented to allow using a unified, generic API to
hotplug devices, including virtual ones.
VDEV devices actually exist unattached after performing a scan on the
rte_devargs list. As such it makes sense to be able to perform a device
hotplug afterward.
Finally, missing this generic interface forces the EAL to be dependent
on vdev-specific API, which hinders the plan of moving the vdev bus to
drivers/bus.
The public API (struct rte_metric_name) includes the NULL terminator
byte in RTE_METRICS_MAX_NAME_LENGTH but the library itself internally
excludes it. This makes it possible for an application to receive an
unterminated name string. Fix be enforcing the NULL termination of all
name strings to the length that the public API expects.
Harry van Haaren [Mon, 17 Jul 2017 15:21:54 +0000 (16:21 +0100)]
service: add -S corelist option
This commit allows the -S (captial 's') to be used to indicate
a corelist for Services. This is a "nice to have" patch, and does
not modify any of the service core functionality.
Suggested-by: Jerin Jacob <jerin.jacob@caviumnetworks.com> Suggested-by: Thomas Monjalon <thomas@monjalon.net> Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com>
Jerin Jacob [Mon, 10 Jul 2017 16:59:46 +0000 (22:29 +0530)]
ethdev: introduce lock-free Tx queue capability
Introducing the DEV_TX_OFFLOAD_MT_LOCKFREE TX capability flag.
if a PMD advertises DEV_TX_OFFLOAD_MT_LOCKFREE capable, multiple threads
can invoke rte_eth_tx_burst() concurrently on the same tx queue without
SW lock. This PMD feature will be useful in the following use cases and
found in the OCTEON family of NPUs.
1) Remove explicit spinlock in some applications where lcores
to TX queues are not mapped 1:1.
example: OVS has such instance
https://github.com/openvswitch/ovs/blob/master/lib/netdev-dpdk.c#L299
https://github.com/openvswitch/ovs/blob/master/lib/netdev-dpdk.c#L1859
See the the usage of tx_lock spinlock.
2) In the eventdev use case, avoid dedicating a separate TX core for
transmitting and thus enables more scaling as all workers can
send the packets.
Harry van Haaren [Tue, 11 Jul 2017 14:19:31 +0000 (15:19 +0100)]
event/sw: add service capability
This commit shows how easy it is to enable a specific
DPDK component with a service callback, in order to get
CPU cycles for it.
The beauty of this method is that the service is unaware
of how much CPU time it is getting - the application can
decide how to split and slice cores and map them to the
registered services.
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Harry van Haaren [Tue, 11 Jul 2017 14:19:30 +0000 (15:19 +0100)]
service: add unit tests
Add a bunch of unit tests, to ensure that the service
core functions are operating as expected.
As part of these tests a dummy service is registered which
allows identifying if a service callback has been invoked
by using the CPU tick counter. This allows identifying if
functions to start and stop service lcores are actually having
effect.
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Harry van Haaren [Tue, 11 Jul 2017 14:19:28 +0000 (15:19 +0100)]
service: initialize with EAL
This commit shows the changes required in rte_eal_init()
to transparently launch the service threads. The threads
are launched into the service worker functions here because
after rte_eal_init() the application is not gauranteed to
call any other DPDK API.
As the registration of services happens at initialization
time, the services that require CPU time are already available
when we reach the end of rte_eal_init().
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Harry van Haaren [Tue, 11 Jul 2017 14:19:27 +0000 (15:19 +0100)]
service: introduce service cores concept
Add header files, update .map files with new service
functions, and add the service header to the doxygen
for building.
This service header API allows DPDK to use services as
a concept of something that requires CPU cycles. An example
is a PMD that runs in software to schedule events, where a
hardware version exists that does not require a CPU.
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
git.droids-corp.org / dpdk.git / log