Declan Doherty [Fri, 11 Mar 2016 01:36:54 +0000 (01:36 +0000)]
cryptodev: add capabilities discovery
This patch add a mechanism for discovery of crypto device features and supported
crypto operations and algorithms. It also provides a method for a crypto PMD to
publish any data range limitations it may have for the operations and algorithms
it supports.
The parameter feature_flags added to rte_cryptodev struct is used to capture
features such as operations supported (symmetric crypto, operation chaining etc)
as well parameter such as whether the device is hardware accelerated or uses
SIMD instructions.
The capabilities parameter allows a PMD to define an array of supported operations
with any limitation which that implementation may have.
Finally the rte_cryptodev_info struct has been extended to allow retrieval of
these parameter using the existing rte_cryptodev_info_get() API.
Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Panu Matilainen [Fri, 11 Mar 2016 09:13:48 +0000 (11:13 +0200)]
mk: fix build without crypto
If the experimental CONFIG_RTE_LIBRTE_CRYPTODEV is disabled,
build of any crypto pmds will fail because of the missing dependency.
This has been present for a while now but hidden until the addition
of null_crypto since all the other crypto pmds have been disabled
by default.
Conditionalize the entire drivers/crypto directory on
CONFIG_RTE_LIBRTE_CRYPTODEV to fix.
Declan Doherty [Fri, 11 Mar 2016 01:04:10 +0000 (01:04 +0000)]
null_crypto: add driver for null crypto operations
This patch provides the implementation of a NULL crypto PMD, which supports
NULL cipher and NULL authentication operations, which can be chained together
as follows:
- Authentication Only
- Cipher Only
- Authentication then Cipher
- Cipher then Authentication
As this is a NULL operation device the crypto operations which are submitted for
processing are not actually modified and are stored in a queue pairs processed
packets ring ready for collection when rte_cryptodev_burst_dequeue() is called.
The patch also contains the related unit tests function to test the PMDs
supported operations.
Thomas Monjalon [Thu, 10 Mar 2016 22:35:37 +0000 (23:35 +0100)]
maintainers: add doc for crypto devices
Fixes: 1703e94ac5ce ("qat: add driver for QuickAssist devices") Fixes: 924e84f87306 ("aesni_mb: add driver for multi buffer based crypto") Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
John Griffin [Tue, 8 Mar 2016 16:22:15 +0000 (16:22 +0000)]
qat: fix AES-GCM decryption
AES GCM on the cryptodev API was giving invalid results
in some cases, due to an incorrect IV setting.
Added AES GCM in the QAT supported algorithms,
as encryption/decryption is fully functional.
Fixes: 1703e94ac5ce ("qat: add driver for QuickAssist devices") Signed-off-by: John Griffin <john.griffin@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
John Griffin [Tue, 8 Mar 2016 16:22:17 +0000 (16:22 +0000)]
qat: remove AES-GMAC
Remove support for AES GMAC support for which was added to
the code in error. AES GMAC will be added in a subsequent release
when testing completes.
Fixes: 1703e94ac5ce ("qat: add driver for QuickAssist devices") Signed-off-by: John Griffin <john.griffin@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Declan Doherty [Thu, 10 Mar 2016 16:41:46 +0000 (16:41 +0000)]
aesni_gcm: add driver for AES-GCM crypto operations
This patch provides the implementation of an AES-NI accelerated crypto PMD
which is dependent on Intel's multi-buffer library, see the white paper
"Fast Multi-buffer IPsec Implementations on Intel® Architecture Processors"
This PMD supports AES_GCM authenticated encryption and authenticated
decryption using 128-bit AES keys
The patch also contains the related unit tests functions
Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: John Griffin <john.griffin@intel.com>
Pablo de Lara [Thu, 10 Mar 2016 16:33:12 +0000 (16:33 +0000)]
snow3g: add driver for SNOW 3G library
Added new SW PMD which makes use of the libsso SW library,
which provides wireless algorithms SNOW 3G UEA2 and UIA2
in software.
This PMD supports cipher-only, hash-only and chained operations
("cipher then hash" and "hash then cipher") of the following
algorithms:
- RTE_CRYPTO_SYM_CIPHER_SNOW3G_UEA2
- RTE_CRYPTO_SYM_AUTH_SNOW3G_UIA2
The SNOW 3G hash and cipher algorithms, which are enabled
by this crypto PMD are implemented by Intel's libsso software
library. For library download and build instructions,
see the documentation included (doc/guides/cryptodevs/snow3g.rst)
The patch also contains the related unit tests function to test the PMD
supported operations.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Deepak Kumar Jain <deepak.k.jain@intel.com>
Declan Doherty [Thu, 10 Mar 2016 15:41:12 +0000 (15:41 +0000)]
cryptodev: change burst API to be crypto op oriented
This patch modifies the crypto burst enqueue/dequeue APIs to operate on bursts
rte_crypto_op's rather than the current implementation which operates on
rte_mbuf bursts, this simplifies the burst processing in the crypto PMDs and the
use of crypto operations in general, including new functions for managing
rte_crypto_op pools.
These changes continues the separation of the symmetric operation parameters
from the more general operation parameters, which will simplify the integration
of asymmetric crypto operations in the future.
PMDs, unit tests and sample applications are also modified to work with the
modified and new API.
Signed-off-by: Declan Doherty <declan.doherty@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Deepak Kumar Jain <deepak.k.jain@intel.com>
Fiona Trahe [Thu, 10 Mar 2016 15:41:10 +0000 (15:41 +0000)]
cryptodev: extract symmetric operations
This patch splits symmetric specific definitions and
functions away from the common crypto APIs to facilitate the future extension
and expansion of the cryptodev framework, in order to allow asymmetric
crypto operations to be introduced at a later date, as well as to clean the
logical structure of the public includes. The patch also introduces the _sym
prefix to symmetric specific structure and functions to improve clarity in
the API.
Signed-off-by: Fiona Trahe <fiona.trahe@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Deepak Kumar Jain <deepak.k.jain@intel.com>
Fiona Trahe [Thu, 10 Mar 2016 15:41:09 +0000 (15:41 +0000)]
cryptodev: clean up
- Fixed >80char lines in test file
- Removed unused elements from stats struct
- Removed unused objects in rte_cryptodev_pmd.h
- Renamed variables
- Replaced leading spaces with tabs
- Improved performance results display in test
Signed-off-by: Fiona Trahe <fiona.trahe@intel.com> Signed-off-by: Declan Doherty <declan.doherty@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Deepak Kumar Jain <deepak.k.jain@intel.com>
Jasvinder Singh [Tue, 8 Mar 2016 18:07:49 +0000 (18:07 +0000)]
pipeline: add new functions for action handlers
Two new pipeline API functions have been added to the library. The packet
hijack API function can be called by any input/output port or table action
handler to remove selected packets from the burst of packets read from one
of the pipeline input ports and then either send these packets out through
any pipeline output port or drop them.
Another packet drop API function can be used by the pipeline action
handlers (port in/out, table) to drop the packets selected using packet
mask. This function updates the drop statistics counters correctly.
Jasvinder Singh [Tue, 8 Mar 2016 18:07:48 +0000 (18:07 +0000)]
pipeline: support packet redirection at action handlers
Currently, there is no mechanism that allows the pipeline ports (in/out)
and table action handlers to override the default forwarding decision
(as previously configured per input port or in the table entry). The port
(in/out) and table action handler prototypes have been changed to allow
pipeline action handlers (port in/out, table) to remove the selected
packets from the further pipeline processing and to take full ownership
for these packets. This feature will be helpful to implement functions
such as exception handling (e.g. TTL =0), load balancing etc.
Huawei Xie [Tue, 8 Mar 2016 15:33:43 +0000 (23:33 +0800)]
virtio: skip error when probing kernel managed device
virtio PMD could use IO port to configure the virtio device without
using UIO/VFIO driver in legacy mode.
There are two issues with previous implementation:
1) virtio PMD will take over the virtio device(s) blindly even if not
intended for DPDK.
2) driver conflict between virtio PMD and virtio-net kernel driver.
This patch checks if there is kernel driver other than UIO/VFIO managing
the virtio device before using port IO.
If legacy_virtio_resource_init fails and kernel driver other than
VFIO/UIO is managing the device, return 1 to tell the upper layer we
don't take over this device.
For all other IO port mapping errors, return -1.
Note than if VFIO/UIO fails, now we don't fall back to port IO.
Fixes: da978dfdc43b ("virtio: use port IO to get PCI resource") Signed-off-by: Huawei Xie <huawei.xie@intel.com> Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Acked-by: David Marchand <david.marchand@6wind.com>
Add introductions on how to enable Vector FM10K Rx/Tx functions,
the preconditions and assumptions on Rx/Tx configuration parameters.
The new content also lists the limitations of vector, so app/customer
can do better to select best Rx/Tx functions.
Signed-off-by: Chen Jing D(Mark) <jing.d.chen@intel.com> Acked-by: John McNamara <john.mcnamara@intel.com>
This patch adds a note to the ixgbe PMD guide, stating
the minimum time that statistics must be polled from
the hardware in order to avoid register values becoming
saturated and "sticking" to the max value.
Reported-by: Jerry Zhang <jerry.zhang@intel.com> Tested-by: Marcin Kerlin <marcinx.kerlin@intel.com> Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> Acked-by: Marcin Kerlin <marcinx.kerlin@intel.com>
This patch adds a new function to the EAL API:
int rte_eal_primary_proc_alive(const char *path);
The function indicates if a primary process is alive right now.
This functionality is implemented by testing for a write-
lock on the config file, and the function tests for a lock.
The use case for this functionality is that a secondary
process can wait until a primary process starts by polling
the function and waiting. When the primary is running, the
secondary continues to poll to detect if the primary process
has quit unexpectedly, the secondary process can detect this.
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> Acked-by: Maryam Tahhan <maryam.tahhan@intel.com>
This patch fixes a race-condition when a primary and
secondary process simultaneously probe PCI devices.
This is implemented by moving the rte_eal_mcfg_complete()
function call in rte_eal_init() until after rte_eal_pci_probe().
The memory mapping of PCI device in the secondary process *must*
happen after the primary has finished doing the mapping as it
relies on information written by the primary.
The end result is that the secondary process waits longer,
until the primary has completed its PCI probing, and then
notifies the secondary process.
This race-condition became visible during the development of
a function that allows a secondary process to be polling until
a primary process exists. The secondary would then probe PCI
devices at the same time, causing an error during rte_eal_init()
Linux EAL: Fixes: 916e4f4f4e45 ("memory: fix for multi process support")
BSD EAL: Fixes: 764bf26873b9 ("add FreeBSD support") Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> Acked-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
Helin Zhang [Mon, 22 Feb 2016 03:59:44 +0000 (11:59 +0800)]
pci: remove config of extended tag
Remove pci configuration of 'extended tag' and 'max read request
size', as they are not required by all devices and it lets PMD to
configure them if necessary.
In addition, 'pci_config_space_set()' is deprecated.
This patch sets a timestamp on each lcore when it is registered
for keepalive. This causes the first values read by the monitor
to show time since the core was registered, instead of the delta
between 0 and the timestamp counter.
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> Acked-by: Remy Horton <remy.horton@intel.com>
This patch fixes some mismatches between the keepalive code
and the docs. Struct names, and descriptions are not in line
with the codebase.
Fixes: e64833f2273a ("examples/l2fwd-keepalive: add sample application") Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> Acked-by: John McNamara <john.mcnamara@intel.com>
MANY references in the sample applications user guide are wrong because
they are hard-coded and section numbers have changed over the time.
This patch changes thoses references to dynamic ones, in this way if
section numbers change the reference get updated automatically.
Signed-off-by: Mauricio Vasquez B <mauricio.vasquezbernal@studenti.polito.it>
Fan Zhang [Tue, 1 Mar 2016 10:35:52 +0000 (10:35 +0000)]
examples/ip_pipeline: add link identification
This patch adds link identification feature to packet framework. To
identify a link, user can use both existing port-mask option, or specify
PCI device in every LINK section in the configuration file.
Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com> Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Fan Zhang [Mon, 22 Feb 2016 14:07:04 +0000 (14:07 +0000)]
examples/ip_pipeline: measure CPU utilization
This patch adds CPU utilization measurement and idle cycle rate
computation to packet framework. The measurement is done by measuring
the cycles spent while a thread pulls zero packet from RX queue. These
cycles are treated as idle cycles (or headroom). A CLI command is added
to display idle cycle rate of specific thread. The CLI command format is
shown as following:
t <thread_id> headroom
Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com> Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Fixes: 5f4cd47309d6 ("port: add ring writer nodrop") Fixes: d58f69c54172 ("port: add ring multi reader or writer") Signed-off-by: Jasvinder Singh <jasvinder.singh@intel.com>
Harry van Haaren [Tue, 16 Feb 2016 13:40:03 +0000 (13:40 +0000)]
doc: add gcc-multilib as linux package hint
When compiling for i686 targets compilation could fail
if the 32bit libc6-dev package is not installed. The
gcc-multilib packages is a meta-package that will pull
in the necessary dependencies, making setup easier for
beginners.
Reported-by: Weichun Chen <weichunx.chen@intel.com> Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> Acked-by: Daniel Mrzyglod <danielx.t.mrzyglod@intel.com> Acked-by: John McNamara <john.mcnamara@intel.com>
Stephen Hurd [Wed, 13 Jan 2016 22:23:36 +0000 (14:23 -0800)]
app/testpmd: fix numa socket detection
Previously, max_socket was set to the highest numbered socket with
an enabled lcore. The intent is to set it to the highest socket
regardless of it being enabled.
Fixes: 7acf894d07d1 ("app/testpmd: detect numa socket count") Signed-off-by: Stephen Hurd <shurd@broadcom.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Wang Xiao W [Fri, 5 Feb 2016 04:50:23 +0000 (12:50 +0800)]
app/testpmd: fix error message when setting Tx VLAN
When using testpmd, sometimes we forget the right order of port_id and
vid in "tx_vlan set (port_id) vlan_id[, vlan_id_outer]\n" command, and
input "tx_vlan set 51 0", we'll get a strange prompt saying "Error, as
QinQ has been enabled.".
In cmd_tx_vlan_set_parsed function, the first thing we do is checking
the port's vlan_offload capability, rather than checking validity of the
port_id, therefore if it's an invalid port_id we'll get the above wrong
message. We should always make sure that we get a valid port_id before
we do other things.
It's the similar issue for cmd_tx_vlan_set_qinq_parsed function.
Fixes: 92ebda07ee58 ("app/testpmd: add qinq stripping and insertion") Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Jerin Jacob [Wed, 2 Mar 2016 13:20:59 +0000 (18:50 +0530)]
eal/arm: check support of armv8.1 atomics
armv8.1 adds support for new atomic instructions.
Linux kernel v4.3 onwards, the presence of atomic instruction
support can detect through HWCAP_ATOMICS
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com> Reviewed-by: Jan Viktorin <viktorin@rehivetech.com>
Keith Wiles [Fri, 4 Mar 2016 18:11:12 +0000 (12:11 -0600)]
config: remove duplicate information
In order to cleanup the configuration files some and reduce
the number of duplicate configuration information. Add a new
file called common_base which contains just about all of the
configuration lines in one place. Then have the common_bsdapp,
common_linuxapp files include this one file. Then in those OS
specific files add the delta configuration lines.
Signed-off-by: Keith Wiles <keith.wiles@intel.com> Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Jingjing Wu [Mon, 1 Feb 2016 02:48:21 +0000 (10:48 +0800)]
ethdev: fix byte order consistency of flow director
Fixed issue of byte order in ethdev library that the structure
for setting fdir's mask and flow entry is inconsist and made
inputs of mask be in big endian.
Fixes: 2d4c1a9ea2ac ("ethdev: add new flow director masks") Fixes: 76c6f89e80d4 ("ixgbe: support new flow director masks") Reported-by: Yaacov Hazan <yaacovh@mellanox.com> Signed-off-by: Jingjing Wu <jingjing.wu@intel.com> Acked-by: Zhe Tao <zhe.tao@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Bruce Richardson [Tue, 24 Nov 2015 14:25:56 +0000 (14:25 +0000)]
lpm: merge tbl24 and tbl8 structures
The tbl8 and tbl24 structures were essentially identical except for
slightly different names for one or two fields. Merge these two
structures into a single structure definition.
Two fields have been renamed as part of this change: the
"ext_entry" field in the tbl24 has been renamed to "valid_group" to match
the tbl8 value to make the merge easier, and the "tbl8_gindex" field has
been renamed to "group_idx". The "valid_group" field now serves two
purposes: in a tbl8 it indicates if the group, i.e. the tbl8, is valid,
and in a tbl24, it indicates if the "group_idx" is valid, i.e. whether
the value is a next_hop or a tbl8 index. [The name "group_idx" was used
to make this latter link between the fields clearer]
Suggested-by: Vladimir Medvedkin <medvedkinv@gmail.com> Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Ravi Kerur [Fri, 4 Mar 2016 09:09:40 +0000 (10:09 +0100)]
mbuf: get DMA address
Macros RTE_MBUF_DATA_DMA_ADDR and RTE_MBUF_DATA_DMA_ADDR_DEFAULT
are defined in each PMD driver file. Convert macros to inline
functions and move them to common lib/librte_mbuf/rte_mbuf.h file.
PMD drivers include rte_mbuf.h file directly/indirectly hence no
additioanl header file inclusion is necessary.
Signed-off-by: Ravi Kerur <rkerur@gmail.com> Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Marc Sune [Wed, 2 Mar 2016 23:52:02 +0000 (00:52 +0100)]
cmdline: fix missing include
cmdline_parse_*.h headers use struct cmdline_token_hdr /
cmdline_parse_token_hdr_t which is defined in cmdline_parse.h, but
do not include it, forcing manual inclusion.
This commit includes cmdline_parse.h in all cmdline_parse_*.h.
Signed-off-by: Marc Sune <marcdevel@gmail.com> Acked-by: Olivier Matz <olivier.matz@6wind.com>
Santosh Shukla [Tue, 1 Mar 2016 10:02:18 +0000 (15:32 +0530)]
virtio: restrict vector Rx/Tx to x86 SSSE3
Temporary implementation to let virtio operate in non-vec mode for archs
which doesn't support _ssse_ cpuflag.
todo:
1) Move virtio_recv_pkts_vec() implementation to
drivers/virtio/virtio_vec_<arch>.h file.
2) Remove use_simple_rxtx flag, so that virtio/virtio_vec_<arch>.h
files to provide vectored/non-vectored rx/tx apis.
Ralf Hoffmann [Thu, 7 Jan 2016 14:54:02 +0000 (15:54 +0100)]
eal/linux: change hugepage sorting to avoid overlapping memcpy
with only one hugepage or already sorted hugepage addresses, the sort
function called memcpy with same src and dst pointer. Debugging with
valgrind will issue a warning about overlapping area. This patch changes
the sort method to qsort to avoid this behavior. The separate sort
function is no longer necessary.
Yi Lu [Thu, 28 Jan 2016 14:16:40 +0000 (14:16 +0000)]
eal/linux: fix build with hpet
Fix compile error when enable CONFIG_RTE_LIBEAL_USE_HPET.
Error messages:
lib/librte_eal/linuxapp/eal/eal_timer.c: In function ‘rte_eal_hpet_init’:
lib/librte_eal/linuxapp/eal/eal_timer.c:222:2: error:
implicit declaration of function ‘rte_thread_setname’
Fixes: badb3688ffa8 ("eal/linux: fix build with glibc < 2.12") Signed-off-by: Yi Lu <luyi68@live.com> Acked-by: David Marchand <david.marchand@6wind.com>
Thomas Monjalon [Wed, 2 Mar 2016 15:35:29 +0000 (16:35 +0100)]
mk: fix error message
When specifying a wrong directory with RTE_SDK and RTE_TARGET
to build an application, the error message about missing config
file was wrong.
Fixes: 6b62a72a70d0 ("mk: install a standard cutomizable tree") Reported-by: Steeven Lee <steeven@gmail.com> Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Panu Matilainen [Thu, 12 Feb 2015 15:18:20 +0000 (17:18 +0200)]
mk: stop on warning only in developer build
Add RTE_DEVEL_BUILD make-variable which can be used to do things
differently when doing development vs building a release,
autodetected from source root .git presence and overridable via
commandline. It is used it to enable -Werror compiler flag and may
be extended to other checks.
Failing build on warnings is a useful developer tool but its bad
for release tarballs which can and do get built with newer
compilers than what was used/available during development. Compilers
routinely add new warnings so code which built silently with cc X
might no longer do so with X+1. This doesn't make the existing code
any more buggier and failing the build in this case does not help
to improve the quality of an already released version either.
This change the default flags which can be tuned with EXTRA_CFLAGS.
Signed-off-by: Panu Matilainen <pmatilai@redhat.com> Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com> Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Panu Matilainen [Tue, 24 Nov 2015 14:31:17 +0000 (16:31 +0200)]
mk: replace the combined library with a linker script
The physically linked-together combined library has been an increasing
source of problems, as was predicted when library and symbol versioning
was introduced. Replace the complex and fragile construction with a
simple linker script which achieves the same without all the problems,
remove the related kludges from eg mlx drivers.
Since creating the linker script is practically zero cost, remove the
config option and just create it always.
Based on a patch by Sergio Gonzales Monroy, linker script approach
initially suggested by Neil Horman.
Suggested-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com> Suggested-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Panu Matilainen <pmatilai@redhat.com> Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Didier Pallard [Fri, 19 Feb 2016 11:00:31 +0000 (12:00 +0100)]
hash: fix CRC32c computation
Fix crc32c hash functions to return a valid crc32c value for
data lengths not multiple of 4 bytes.
ARM code is not tested.
Fixes: af75078fece3 ("first public release") Signed-off-by: Didier Pallard <didier.pallard@6wind.com> Acked-by: David Marchand <david.marchand@6wind.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Didier Pallard [Fri, 19 Feb 2016 11:00:30 +0000 (12:00 +0100)]
app/test: fix CRC hash values
Add some small key lengths (below 4 bytes), and fix odd key lengths
expected returned values for CRC computation to match real CRC values.
Fixes: 6298d2c55ae8 ("app/test: add new functional tests for hash functions") Signed-off-by: Didier Pallard <didier.pallard@6wind.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Huawei Xie [Sun, 28 Feb 2016 12:44:56 +0000 (20:44 +0800)]
mbuf: provide bulk allocation
rte_pktmbuf_alloc_bulk allocates a bulk of packet mbufs.
There is related thread about this bulk API.
http://dpdk.org/dev/patchwork/patch/4718/
Thanks to Konstantin's loop unrolling.
Attached the wiki page about duff's device. It explains the performance
optimization through loop unwinding, and also the most dramatic use of
case label fall-through.
https://en.wikipedia.org/wiki/Duff%27s_device
In this implementation, while() loop is used because we could not assume
count is strictly positive. Using while() loop saves one line of check.
Yuanhan Liu [Mon, 22 Feb 2016 14:36:11 +0000 (22:36 +0800)]
vhost: broadcast RARP by injecting in receiving mbuf array
Broadcast RARP packet by injecting it to receiving mbuf array at
rte_vhost_dequeue_burst().
Commit 33226236a35e ("vhost: handle request to send RARP") iterates
all host interfaces and then broadcast it by all of them. It did
notify the switches about the new location of the migrated VM, however,
the mac learning table in the target host is wrong (at least in my
test with OVS):
$ ovs-appctl fdb/show ovsbr0
port VLAN MAC Age
1 0 b6:3c:72:71:cd:4d 10
LOCAL 0 b6:3c:72:71:cd:4e 10
LOCAL 0 52:54:00:12:34:68 9
1 0 56:f6:64:2c:bc:c0 1
Where 52:54:00:12:34:68 is the mac of the VM. As you can see from the
above, the port learned is "LOCAL", which is the "ovsbr0" port. That
is reasonable, since we indeed send the pkt by the "ovsbr0" interface.
The wrong mac table lead all the packets to the VM go to the "ovsbr0"
in the end, which ends up with all packets being lost, until the guest
send a ARP quest (or reply) to refresh the mac learning table.
Jianfeng then came up with a solution I have thought of firstly but NAKed
by myself, concerning it has potential issues [0]. The solution is as title
stated: broadcast the RARP packet by injecting it to the receiving mbuf
arrays at rte_vhost_dequeue_burst(). The re-bring of that idea made me
think it twice; it looked like a false concern to me then. And I had done
a rough verification: it worked as expected.
Another note is that while preparing this version, I found that DPDK has
some ARP related structures and macros defined. So, use them instead of
the one from standard header files here.
Cc: Thibaut Collet <thibaut.collet@6wind.com> Suggested-by: Jianfeng Tan <jianfeng.tan@intel.com> Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
rte_get_log_type and rte_get_log_level functions has been available
for many versions. But they are missing from the shared library map
and therefore do not get exported correctly.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Tomasz Kulasek [Mon, 29 Feb 2016 10:33:07 +0000 (11:33 +0100)]
examples/l3fwd: rework exact-match
Current implementation of Exact-Match uses different execution path than
for LPM. Unifying them allows to reuse big part of LPM code and sightly
increase performance of Exact-Match.
Main changes:
-------------
* Packet classification stage is separated from the rest of path for both
LPM and EM.
* Packet processing, modifying and transmit part is the same for LPM and EM
and mostly based on the current LPM implementation.
* Shared code is moved to the common file "l3fwd_sse.h".
* While sequential packet classification in EM path, seems to be faster
than using multi hash lookup, used before, it is used by default. Old
implementation is moved to the file l3fwd_em_hlm_sse.h and can be enabled
with HASH_LOOKUP_MULTI global define in compilation time.
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Marcin Kerlin [Fri, 12 Feb 2016 16:04:41 +0000 (17:04 +0100)]
jobstats: add abort function
This patch adds new function rte_jobstats_abort.
It marks *job* as finished and time of this work will be add to management
time instead of execution time.
This function should be used instead of rte_jobstats_finish if condition
occurs, condition is defined by the application for example when receiving
n>0 packets.
Example of usage is added to the example l2fwd-jobstats.
At maximum load do-while loop inside Idle job will be execute once because
one or more jobs waiting to be executed, so this time should not be include
as the execution time by calling rte_jobstats_abort().
Signed-off-by: Marcin Kerlin <marcinx.kerlin@intel.com> Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
Jan Viktorin [Tue, 16 Feb 2016 18:35:06 +0000 (19:35 +0100)]
mk: fix armv7 machine name
The CONFIG_RTE_MACHINE must not contain hyphens to work correctly. This was
initially done only for the file name defconfig_arm-armv7a-linuxapp-gcc. This
patch fixes install-sdk goal. Otherwise, it creates a wrong directory for this
platform.
Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Jianfeng Tan [Tue, 19 Jan 2016 19:18:11 +0000 (03:18 +0800)]
examples/vhost: fix out of sequence packets
Issue description: when packets go through vhost example to virtio
device and come back to another virtio device or physical NIC, the
sequence of packets will be changed.
Reported-by: Thomas Long <thomas.long@intel.com> Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com> Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Jianfeng Tan [Thu, 18 Feb 2016 00:08:39 +0000 (08:08 +0800)]
examples/vhost: fix mbuf allocation
How to reproduce:
1. Start vhost-switch
./examples/vhost/build/vhost-switch -c 0x3 -n 4 -- -p 1 --stat 0
2. Start VM with a virtio port
$ $QEMU -smp cores=2,sockets=1 -m 4G -cpu host -enable-kvm \
-chardev socket,id=char1,path=<path to vhost-user socket> \
-device virtio-net-pci,netdev=vhostuser1 \
-netdev vhost-user,id=vhostuser1,chardev=char1
-object memory-backend-file,id=mem,size=4G,mem-path=<hugetlbfs path>,share=on \
-numa node,memdev=mem -mem-prealloc \
-hda <path to VM img>
3. Start l2fwd in VM
$ ./examples/l2fwd/build/l2fwd -c 0x1 -n 4 -m 1024 -- -p 0x1
4. Use ixia to inject packets in a small data bit rate.
Error:
vhost-switch keeps printing error message:
failed to allocate memory for mbuf.
Root cause:
How many mbufs allocated for a port is calculated by below formula.
NUM_MBUFS_PER_PORT = ((MAX_QUEUES*RTE_TEST_RX_DESC_DEFAULT) + \
(num_switching_cores*MAX_PKT_BURST) + \
(num_switching_cores*RTE_TEST_TX_DESC_DEFAULT) +\
(num_switching_cores*MBUF_CACHE_SIZE))
We suppose num_switching_cores is 1 and MBUF_CACHE_SIZE is 128.
And when initializing port, master core fills mbuf mempool cache,
so there would be some left in that cache, for example 121.
So total mbufs which can be used is:
(MAX_PKT_BURST + MBUF_CACHE_SIZE - 121) = (32 + 128 - 121) = 39.
What makes it worse is that there is a buffer to store mbufs
(which will be tx_burst to physical port), if it occupies some mbufs,
there will be possible < 32 mbufs left, so vhost dequeue prints out
this msg.
In all, it fails to include master core's mbuf mempool cache.
Reported-by: Qian Xu <qian.q.xu@intel.com> Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Ravi Kerur [Thu, 25 Feb 2016 10:24:24 +0000 (11:24 +0100)]
examples/l3fwd: modularize
The main problem with l3fwd is that it is too monolithic with everything
being in one file, and the various options all controlled by compile time
flags. This means that it's hard to read and understand, and when making
any changes, you need to go to a lot of work to try and ensure you cover
all the code paths, since a compile of the app will not touch large parts
of the l3fwd codebase.
Following changes were done to fix the issues mentioned above
- Split out the various lpm and hash specific functionality into separate
files, so that l3fwd code has one file for common code e.g. args
processing, mempool creation, and then individual files for the various
forwarding approaches.
Following are new file lists
main.c (Common code for args processing, memppol creation, etc)
l3fwd_em.c (Hash/Exact match aka 'EM' functionality)
l3fwd_em_sse.h (SSE4_1 buffer optimizated 'EM' code)
l3fwd_lpm.c (Longest Prefix Match aka 'LPM' functionality)
l3fwd_lpm_sse.h (SSE4_1 buffer optimizated 'LPM' code)
l3fwd.h (Common include for 'EM' and 'LPM')
- The choosing of the lpm/hash path should be done at runtime, not
compile time, via a command-line argument. This will ensure that
both code paths get compiled in a single go
Following examples show runtime options provided
Select 'LPM' or 'EM' based on run time selection f.e.
> l3fwd -c 0x1 -n 1 -- -p 0x1 -E ... (EM)
> l3fwd -c 0x1 -n 1 -- -p 0x1 -L ... (LPM)
Options "E" and "L" are mutualy-exclusive.
If none selected, "L" is default.
Signed-off-by: Ravi Kerur <rkerur@gmail.com> Signed-off-by: Piotr Azarewicz <piotrx.t.azarewicz@intel.com> Tested-by: Tomasz Kulasek <tomaszx.kulasek@intel.com> Acked-by: Tomasz Kulasek <tomaszx.kulasek@intel.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Reshma Pattan [Tue, 5 Jan 2016 16:34:58 +0000 (16:34 +0000)]
ethdev: support unidirectional configuration
User should be able to configure ethdev with zero rx/tx queues,
but both should not be zero.
After above change, rte_eth_dev_tx_queue_config,
rte_eth_dev_rx_queue_config should allocate memory for rx/tx queues only
when number of rx/tx queues are nonzero.
Signed-off-by: Reshma Pattan <reshma.pattan@intel.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Reshma Pattan [Tue, 5 Jan 2016 16:34:56 +0000 (16:34 +0000)]
ethdev: allow full control from secondary process
Macros RTE_PROC_PRIMARY_OR_ERR_RET and RTE_PROC_PRIMARY_OR_RET
are blocking the secondary process from using the APIs.
API access should be given to both secondary and primary.
Reported-by: Sean Harte <sean.harte@intel.com> Signed-off-by: Reshma Pattan <reshma.pattan@intel.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
git.droids-corp.org / dpdk.git / log