Eric Zhang [Wed, 29 Aug 2018 15:55:21 +0000 (11:55 -0400)]
net/virtio-user: check negotiated features before set
This patch checks negotiated features to see if necessary to offload
before set the tap device offload capabilities. It also checks if kernel
support the TUNSETOFFLOAD operation.
Fixes:
5e97e4202563 ("net/virtio-user: enable offloading")
Cc: stable@dpdk.org
Signed-off-by: Eric Zhang <eric.zhang@windriver.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
Ilya Maximets [Wed, 15 Aug 2018 14:54:39 +0000 (17:54 +0300)]
vhost: fix zmbufs array leak after NUMA realloc
'numa_realloc()' allocates 'zmbufs' even if zero copy mode
is not configured. This leads to memory leak, because array
is freed only for zero copy case.
Fixes:
2651726defb7 ("vhost: do deep copy while reallocating queue")
CC: stable@dpdk.org
Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
Rami Rosen [Sat, 25 Aug 2018 19:22:40 +0000 (22:22 +0300)]
examples/vhost: remove unnecessary constant
This patch removes an unnecessary definition of MAX_PRINT_BUFF
in examples/vhost/main.c, since it is no longer being used.
Fixes:
68363d85857d ("examples/vhost: remove the non-working zero copy code")
Cc: stable@dpdk.org
Signed-off-by: Rami Rosen <ramirose@gmail.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
Rami Rosen [Fri, 24 Aug 2018 07:43:02 +0000 (10:43 +0300)]
doc: fix wrong usage of bind command
This patch fixes wrong usage of bind command in vhost.rst.
Using "dpdk-devbind.py -b=uio_pci_generic 0000:00:04.0" gives
an error of "unbind failed". It should be "-b uio_pci_generic" so
it will work correctly.
Fixes:
a971c509a523 ("doc: update vhost sample guide")
Cc: stable@dpdk.org
Signed-off-by: Rami Rosen <ramirose@gmail.com>
Acked-by: Zhiyong Yang <zhiyong.yang@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Xueming Li [Thu, 23 Aug 2018 23:10:33 +0000 (07:10 +0800)]
net/mlx5: fix interrupt completion queue index wrapping
Rxq cq_ci was 16 bits while hardware is expecting to wrap
around 24 bits, this caused interrupt failure after burst of packets.
Fixes:
43e9d9794cde ("net/mlx5: support upstream rdma-core")
Cc: stable@dpdk.org
Signed-off-by: Xueming Li <xuemingl@mellanox.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
Luca Boccassi [Mon, 3 Sep 2018 14:18:11 +0000 (15:18 +0100)]
net/ixgbe: do not return internal code
In case of a temporary failure the ixgbe driver can return the internal
error IXGBE_ERR_RESET_FAILED to the application. Instead, return
-EAGAIN as per the public API specification.
Fixes:
cddaf87a1ecb ("lib: fix unused values")
Cc: stable@dpdk.org
Signed-off-by: Luca Boccassi <bluca@debian.org>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Shagun Agrawal [Mon, 27 Aug 2018 12:53:31 +0000 (18:23 +0530)]
net/cxgbe: fix memory access when parsing flow match items
Coverity issue: 293096
Fixes:
ee61f5113b17 ("net/cxgbe: parse and validate flows")
Cc: stable@dpdk.org
Signed-off-by: Shagun Agrawal <shaguna@chelsio.com>
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Yaroslav Brustinov [Wed, 8 Aug 2018 09:45:21 +0000 (12:45 +0300)]
net/e1000: fix Tx offload capability typos
Fix rx/tx typos in igb_get_tx_port_offloads_capa and
igb_get_tx_queue_offloads_capa.
Fixes:
e5c05e6590ea ("net/e1000: convert to new Tx offloads API")
Cc: stable@dpdk.org
Signed-off-by: Yaroslav Brustinov <ybrustin@cisco.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Beilei Xing [Mon, 3 Sep 2018 05:40:56 +0000 (13:40 +0800)]
doc: update i40e guide for GTPv1 package release
Add link of GTPv1 package release.
Signed-off-by: Beilei Xing <beilei.xing@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Jia Yu [Mon, 20 Aug 2018 05:18:45 +0000 (22:18 -0700)]
net/bonding: fix buffer corruption in packets
When bond slave devices cannot transmit all packets in bufs array,
tx_burst callback shall merge the un-transmitted packets back to
bufs array. Recent merge logic introduced a bug which causes
invalid mbuf addresses being written to bufs array.
When caller frees the un-transmitted packets, due to invalid addresses,
application will crash.
The fix is avoid shifting mbufs, and directly write un-transmitted
packets back to bufs array.
Fixes:
09150784a776 ("net/bonding: burst mode hash calculation")
Cc: stable@dpdk.org
Signed-off-by: Jia Yu <jyu@vmware.com>
Acked-by: Chas Williams <chas3@att.com>
Stephen Hemminger [Thu, 16 Aug 2018 22:37:14 +0000 (15:37 -0700)]
ethdev: fix port ownership logs
The rte_eth_dev_owner_unset function always generates a log
message because the unset value for owner id is 0.
Also, when rte_eth_dev_owner_delete is called with a valid
owner id, the log message should be at NOTICE not ERROR
severity.
Fixes:
5b7ba31148a8 ("ethdev: add port ownership")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Matan Azrad <matan@mellanox.com>
Alejandro Lucero [Fri, 24 Aug 2018 14:25:36 +0000 (15:25 +0100)]
net/nfp: fix live MAC changes not supported
Some NFP firmwares support live changes to the MAC address, but
this is not always true and the firmware advertises it accordingly.
This patch checks if firmware does not support live changes and
sets RTE_ETH_DEV_NOLIVE_MAC_ADDR in that case.
Cc: stable@dpdk.org
Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
Alejandro Lucero [Fri, 24 Aug 2018 14:25:35 +0000 (15:25 +0100)]
ethdev: fix MAC changes when live change not supported
Current code assumes a MAC change can occur when the port has been
started. In fact, there are some NICs which require this port state
for being successful, but other NICs not always support MAC change
in that case.
This patch supports a new device flag for a device advertising this
limitation, and if the flag is set, the MAC is changed before the
port starts.
Fixes:
af75078fece3 ("first public release")
Cc: stable@dpdk.org
Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Natalie Samsonov [Fri, 24 Aug 2018 18:30:03 +0000 (20:30 +0200)]
net/mvpp2: support VLAN for parser offload
Add VLAN packet type support for parser offload.
Signed-off-by: Natalie Samsonov <nsamsono@marvell.com>
Reviewed-by: Shlomi Gridish <sgridish@marvell.com>
Reviewed-by: Dmitri Epshtein <dima@marvell.com>
Reviewed-by: Yuval Caduri <cyuval@marvell.com>
Natalie Samsonov [Fri, 24 Aug 2018 18:30:02 +0000 (20:30 +0200)]
net/mvpp2: make private variables static
Mark internal variables static to avoid potential redefinition
errors later on.
Signed-off-by: Natalie Samsonov <nsamsono@marvell.com>
Reviewed-by: Yelena Krivosheev <yelena@marvell.com>
Natalie Samsonov [Fri, 24 Aug 2018 18:30:01 +0000 (20:30 +0200)]
net/mvpp2: fix comments and error messages
Fix comments and error messages.
Fixes:
7235341d7517 ("net/mrvl: support classifier")
Cc: stable@dpdk.org
Signed-off-by: Natalie Samsonov <nsamsono@marvell.com>
Reviewed-by: Liron Himi <lironh@marvell.com>
Tomasz Duszynski [Fri, 24 Aug 2018 18:30:00 +0000 (20:30 +0200)]
net/mvpp2: fix array initialization
Fix used_bpools array initialization by using range initializer.
This way all necessary variables are properly initialized regardless
of PP2_NUM_PKT_PROC value.
Fixes:
0ddc9b815b11 ("net/mrvl: add net PMD skeleton")
Cc: stable@dpdk.org
Signed-off-by: Tomasz Duszynski <tdu@semihalf.com>
Liron Himi [Fri, 24 Aug 2018 18:29:59 +0000 (20:29 +0200)]
net/mvpp2: use common code to initialize DMA
Use common code to initialize MUSDK DMA memory buffers.
Signed-off-by: Liron Himi <lironh@marvell.com>
Reviewed-by: Natalie Samsonov <nsamsono@marvell.com>
Liron Himi [Fri, 24 Aug 2018 18:29:58 +0000 (20:29 +0200)]
common/mvep: add common code for Marvell drivers
Add MVEP (Marvell Embedded Processors) to drivers/common which
will keep code reused by current and future MRVL PMDs.
Right now we have only common DMA memory initialization routines there.
Signed-off-by: Liron Himi <lironh@marvell.com>
Signed-off-by: Tomasz Duszynski <tdu@semihalf.com>
Reviewed-by: Natalie Samsonov <nsamsono@marvell.com>
Shahaf Shuler [Tue, 14 Aug 2018 11:17:21 +0000 (14:17 +0300)]
net/mlx5: fix RSS flow action hash type selection
On the code after the below commits, the criteria to select the IPV4 or
IPV6 hash functions was the existence of some ETH_RSS_IPV4 RSS types on
the flow rule.
The check is wrong. For example ETH_RSS_NONFRAG_IPV4_TCP will not select
the IPV4 hash which will cause the packet to be spread in a bad way.
Fix it by adding the corresponding types needed for each hash selection.
Fixes:
592f05b29a25 ("net/mlx5: add RSS flow action")
Fixes:
fd0b70316bca ("net/mlx5: support inner RSS computation")
Cc: stable@dpdk.org
Reported-by: Yaroslav Brustinov <ybrustin@cisco.com>
Signed-off-by: Shahaf Shuler <shahafs@mellanox.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
Shahaf Shuler [Mon, 13 Aug 2018 06:47:57 +0000 (09:47 +0300)]
net/mlx5: disable ConnectX-4 Lx Multi Packet Send by default
On ConnectX-4 Lx the Multi Packet Send (MPW) feature is considered
un-secure, as on some cases were the application provides incorrect mbufs
on the Tx burst the host or NIC can get stuck.
Hence, disabling the feature by default for this specific NIC.
Users can still enable this feature and enjoy the performance gain
(mostly for low number of cores) by using the txq_mpw_en devarg.
This patch will impact the out of the box performance of some application
using ConnectX-4 Lx for the sack of security and robustness.
Since we need different defaults based on the underlying device the mpw
field in the configuration struct was extended to contain also the
MLX5_ARG_UNSET option.
Cc: stable@dpdk.org
Signed-off-by: Shahaf Shuler <shahafs@mellanox.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
Adrien Mazarguil [Mon, 6 Aug 2018 14:25:42 +0000 (16:25 +0200)]
net/mlx5: fix artificial L4 limitation on switch flow rules
Partial bit-masks are in fact supported on TCP/UDP source/destination
ports. Remove unnecessary check.
Fixes:
2bfc777e07 ("net/mlx5: add L2-L4 pattern items to switch flow rules")
Cc: stable@dpdk.org
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Ilya Maximets [Fri, 10 Aug 2018 07:24:54 +0000 (10:24 +0300)]
vhost: suppress error if NUMA is not available
It's a common case that 'get_mempolicy' fails on systems
without NUMA support. No need to flag an error in log for
this situation.
Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Ilya Maximets [Thu, 23 Aug 2018 08:05:54 +0000 (11:05 +0300)]
doc: fix style and syntax in flow API guide
Fixes:
3e0ceb9f17ff ("doc: add basic howto for flow API")
Cc: stable@dpdk.org
Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Jerin Jacob [Fri, 17 Aug 2018 14:30:22 +0000 (20:00 +0530)]
net/octeontx: fix packet corruption on Tx
LMTST does not guarantee packet content get synced with L2C when
HW access the packet for transmitting.
Adding coherent IO write barrier will make sure HW sees the correct
packet if its modified.
Fixes:
9e747589bd4c ("net/octeontx: add packet transmit burst function")
Cc: stable@dpdk.org
Reported-by: Vikas Aggarwal <vikas.aggarwal@caviumnetworks.com>
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: Santosh Shukla <santosh.shukla@caviumnetworks.com>
Stephen Hemminger [Tue, 14 Aug 2018 16:45:25 +0000 (09:45 -0700)]
net/netvsc: resize event buffer as needed
The event buffer was changed to be a fixed size value,
had a couple of issues. The big one is that rte_free was still
being called for a pointer that was not setup with rte_malloc().
The event buffer was also too small to handle heavy receive
traffic; and running the event buffer out would crash
the application.
Fix by going back to a dynamically resized event buffer.
And grow it by 25% to avoid lots of realloc's.
Fixes:
530af95a7849 ("bus/vmbus: avoid signalling host on read")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Stephen Hemminger [Thu, 9 Aug 2018 17:50:08 +0000 (10:50 -0700)]
net/netvsc: implement free Tx mbuf on demand
Add tx_done_cleanup ethdev hook to allow application to
control if/when it wants completions to be handled.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Stephen Hemminger [Thu, 9 Aug 2018 17:50:07 +0000 (10:50 -0700)]
net/netvsc: set lower host latency
Tune the vmbus connection so the host scans faster. This improves
transmit performance. The host default value is 100us but setting
to 50us reduces packet loss significantly.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Stephen Hemminger [Thu, 9 Aug 2018 17:50:06 +0000 (10:50 -0700)]
bus/vmbus: add host latency tuning function
Add vmbus API to allow tuning the scan interval on the host side.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Stephen Hemminger [Thu, 9 Aug 2018 17:50:05 +0000 (10:50 -0700)]
net/netvsc: fix chimney buffer size error handling
Fix the error handling in setting up transmit buffer.
If setting up chimney buffer fails, then it is not connected so
no need to send disconnect.
Allow for some unused area if full area is not used.
Fixes:
4e9c73e96e83 ("net/netvsc: add Hyper-V network device")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Yunjian Wang [Tue, 7 Aug 2018 08:10:46 +0000 (16:10 +0800)]
net/bonding: support matching QinQ ethertype
We assume VLAN ethtertype is 0x8100 in get_vlan_offset() function,
but it could be 0x88A8 if QinQ is supported.
Fixes:
06fe78b98ccd ("bond: add mode 6")
Cc: stable@dpdk.org
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Acked-by: Chas Williams <chas3@att.com>
Ilia Kurakin [Thu, 19 Jul 2018 12:21:42 +0000 (15:21 +0300)]
ethdev: change vtune profiling approach
The patch changes rx_burst profiling approach:
1. VTune's instrumentation is removed
2. empty hook callback for profiling is added
This way all VTune-specific logic moves to the VTune side.
Hook is enabled only when CONFIG_RTE_ETHDEV_PROFILE_WITH_VTUNE option
is turned on. VTune uses this hook to attach to the polling cycle. It
is not possible to attach to the rx_burst directly, as it is inline.
Signed-off-by: Ilia Kurakin <ilia.kurakin@intel.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Konstantin Ananyev [Fri, 24 Aug 2018 16:47:06 +0000 (17:47 +0100)]
acl: forbid rule with priority zero
If user specifies priority=0 for some of ACL rules
that can cause rte_acl_classify to return wrong results.
The reason is that priority zero is used internally for no-match nodes.
See more details at: https://bugs.dpdk.org/show_bug.cgi?id=79.
The simplest way to overcome the issue is just not allow zero
to be a valid priority for the rule.
Fixes:
dc276b5780c2 ("acl: new library")
Cc: stable@dpdk.org
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Qi Zhang [Mon, 3 Sep 2018 08:49:29 +0000 (16:49 +0800)]
bus/vdev: fix error log on secondary device scan
When a secondary process handles VDEV_SCAN_ONE mp action, it is possible
the device is already be inserted. This happens when we have multiple
secondary processes which cause multiple broadcasts from primary during
bus->scan. So we don't need to log any error for -EEXIST.
Bugzilla ID: 84
Fixes:
cdb068f031c6 ("bus/vdev: scan by multi-process channel")
Cc: stable@dpdk.org
Reported-by: Gage Eads <gage.eads@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Gage Eads <gage.eads@intel.com>
Tiwei Bie [Wed, 15 Aug 2018 07:20:15 +0000 (15:20 +0800)]
malloc: fix potential null pointer dereference
We need to do the NULL pointer check first after malloc().
Fixes:
07dcbfe0101f ("malloc: support multiprocess memory hotplug")
Cc: stable@dpdk.org
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Honnappa Nagarahalli [Sun, 2 Sep 2018 18:35:28 +0000 (13:35 -0500)]
build: enable ARM NEON flag when __aarch64__ defined
GCC version 4.8.5 does not pre-define __ARM_NEON. NEON is not
optional for ArmV8. Hence NEON related code can be enabled
when __aarch64__ is defined.
Bugzilla ID: 82
Cc: stable@dpdk.org
Reported-by: Raslan Darawsheh <rasland@mellanox.com>
Reported-by: Thomas F Herbert <therbert@redhat.com>
Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Jerin Jacob [Mon, 3 Sep 2018 09:31:10 +0000 (15:01 +0530)]
mk: disable OcteonTx for buggy compilers only on arm64
Disable octeontx for gcc 4.8.5 as the compiler is emitting "internal
compiler error" for aarch64. The GCC "internal compiler error" was
observed only for arm64 architecture so disable the PMD only
for arm64.
Fixes:
4f760550a093 ("mk: disable OcteonTx for buggy compilers")
Cc: stable@dpdk.org
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Hemant Agrawal [Mon, 27 Aug 2018 08:52:23 +0000 (14:22 +0530)]
bus/fslmc: fix undefined reference of memsegs
This patch fix the undefined reference issue with rte_dpaa2_memsegs
when compiled in shared lib mode with EXTRA_CFLAGS="-g -O0"
Bugzilla ID: 61
Fixes:
365fb925d3b3 ("bus/fslmc: optimize physical to virtual address search")
Cc: stable@dpdk.org
Reported-by: Keith Wiles <keith.wiles@intel.com>
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Neil Horman [Thu, 16 Aug 2018 11:08:01 +0000 (07:08 -0400)]
devtools: relax rule for identifying symbol section
It was reported recently that some patches that add symbols to an
existing EXPERIMENTAL section of a version map file generate errors
because the check-symbol-change script was identifying the section as
"@@" rather than EXPERIMENTAL. This was fairly clearly due to the fact
that the rule identifying the version section expected the whole section
to be added, rather than having it already exist, with only new symbols
being added to the existing section. This led the match rule to misread
the format of that line and pull the wrong word out of it.
The fix is to relax the rule slightly. Rather than assume that the
section must exist on a line that was added, allow the section name to
be set by any line that ends in a '{', which should be correct, given
our coding practices. The section name is then extracted as the next to
the last word on the line ( $(NF-1) ).
Fixes:
4bec48184e33 ("devtools: add checks for ABI symbol addition")
Cc: stable@dpdk.org
Reported-by: Nikhil Rao <nikhil.rao@intel.com>
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Tested-by: Nikhil Rao <nikhil.rao@intel.com>
Thomas Monjalon [Sat, 11 Aug 2018 21:58:03 +0000 (23:58 +0200)]
version: 18.11-rc0
Start version numbering for a new release cycle,
and introduce a template file for release notes.
The release notes comments have a new block to suggest
the order of items, inspired by Ferruh's proposal.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: John McNamara <john.mcnamara@intel.com>
Thomas Monjalon [Thu, 9 Aug 2018 21:11:26 +0000 (23:11 +0200)]
version: 18.08.0
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
John McNamara [Thu, 9 Aug 2018 12:08:43 +0000 (13:08 +0100)]
doc: update release notes for 18.08
Fix grammar, spelling and formatting of DPDK 18.08 release notes.
Signed-off-by: John McNamara <john.mcnamara@intel.com>
Hemant Agrawal [Fri, 27 Jul 2018 04:54:18 +0000 (10:24 +0530)]
doc: add SPDX and copyright to release notes
using "The DPDK Contributors" as decided by techboard.
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Hemant Agrawal [Tue, 5 Jun 2018 07:50:24 +0000 (13:20 +0530)]
doc: add SPDX and copyright to contributing guide
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Pablo de Lara [Fri, 20 Apr 2018 09:53:38 +0000 (10:53 +0100)]
examples/performance-thread: convert to SPDX tags
Convert dual license headers with Intel and Dmitry Vyukov
names to SPDX.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Dmitry Vyukov <dvyukov@gmail.com>
Yipeng Wang [Thu, 26 Jul 2018 17:56:01 +0000 (10:56 -0700)]
hash: add more accurate thread-safety comments
Describing the thread-safety support more accurately for
API documentation.
Fixes:
f2e3001b53ec ("hash: support read/write concurrency")
Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Yipeng Wang [Thu, 26 Jul 2018 17:56:00 +0000 (10:56 -0700)]
doc: add multithread description to hash library
Added multithreading related description into programmer
guide of hash library.
Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Marvin Liu [Tue, 31 Jul 2018 16:00:39 +0000 (00:00 +0800)]
doc: describe --builtin-net-driver option in vhost app
Very simple version of vhost-user driver in vhost sample will be used if
builtin-net-driver option is enabled. This driver is based on generic
vhost lib APIs. Unfortunately, the implementation is incompatible with
QEMU as protocol feature is not supported.
Signed-off-by: Marvin Liu <yong.liu@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Shreyansh Jain [Fri, 25 May 2018 12:07:33 +0000 (17:37 +0530)]
doc: move and update experimental API process
Experimental API text has been moved into a sub-section of ABI Policy.
A paragraph has been added to explain the process for removal of an
experimental tag.
Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Acked-by: Luca Boccassi <bluca@debian.org>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Gavin Hu [Thu, 9 Aug 2018 01:58:03 +0000 (09:58 +0800)]
maintainers: claim maintainership for ARM v7 and v8
Claim the maintainership as Jianbo Liu is not working on this any more.
Aslo remove the co-maintainership for Marvel mvpp2 amd mrvl crypto driver
and doc.
Cc: stable@dpdk.org
Signed-off-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Song Zhu <song.zhu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Bruce Richardson [Thu, 9 Aug 2018 15:22:35 +0000 (16:22 +0100)]
mk: fix permissions when using make install
When using make install, the permissions of the resulting file should be
those of the user using make install, not those of the user who ran the
build. This would not be the case when a user explicitly runs:
"make && sudo make install"
Fix this by changing "cp -a", which preserves all attributes, to
"cp -dR --preserve=timestamp", and by adding the flags
"--no-same-owner --no-same-permissions" to the calls to tar.
Fixes:
1fa0fd9d6b42 ("mk: allow to specify DESTDIR in build rule")
Fixes:
6b62a72a70d0 ("mk: install a standard cutomizable tree")
Fixes:
576de42b83e5 ("doc: render and install man pages")
Cc: stable@dpdk.org
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Thomas Monjalon [Sun, 5 Aug 2018 09:38:47 +0000 (11:38 +0200)]
devtools: fix symbol check for dash
The script check-symbol-change.sh was not running when
/bin/sh redirects to dash.
Fixes:
4bec48184e33 ("devtools: add checks for ABI symbol addition")
Cc: nhorman@tuxdriver.com
Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Tested-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Rami Rosen [Sun, 5 Aug 2018 20:03:28 +0000 (23:03 +0300)]
ethdev: fix a doxygen comment for port allocation
This patch fixes a doxygen comment of the rte_eth_dev_allocate()
method. There is no parameter named "type" for this
method; so this patch removes the doxygen comment about it.
Fixes:
6751f6deb798 ("ethdev: get rid of device type")
Cc: stable@dpdk.org
Signed-off-by: Rami Rosen <rami.rosen@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Rami Rosen [Wed, 8 Aug 2018 18:40:54 +0000 (21:40 +0300)]
bus/pci: remove unneeded EAL private include
This trivial patch removes an uneeded include
from drivers/bus/pci/linux/pci.c.
Signed-off-by: Rami Rosen <rami.rosen@intel.com>
Rami Rosen [Tue, 7 Aug 2018 19:09:14 +0000 (22:09 +0300)]
bus/pci: remove useless forward declaration
This patch removes the forward declaration of rte_pci_remove_device()
method. In the past, this forward decalaration was needed for
rte_pci_detach(), which is now removed from pci_common.c.
Fixes:
e690338a7b85 ("bus/pci: remove unused function to detach by address")
Signed-off-by: Rami Rosen <rami.rosen@intel.com>
Drocula Lambda [Thu, 9 Aug 2018 12:09:06 +0000 (12:09 +0000)]
kni: fix build on RHEL 7.5
This patch fixes compilation errors on Centos 7.5 when
CONFIG_RTE_KNI_KMOD_ETHTOOL is set to 'y'.
On RHEL75 ndo_change_mtu has changed to ndo_change_mtu_rh74.
See commit
37d477b6863e5c06 ("kni: fix build on RHEL 7.5")
Signed-off-by: Drocula Lambda <quzeyao@gmail.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Dan Gora [Thu, 28 Jun 2018 22:58:38 +0000 (15:58 -0700)]
kni: fix crash with null name
Fix a segmentation fault which occurs when the kni_autotest is run
in the 'test' application.
This segmenation fault occurs when rte_kni_get() is called with a
NULL value for 'name'.
Fixes:
0c6bc8ef70ba ("kni: memzone pool for alloc and release")
Cc: stable@dpdk.org
Signed-off-by: Dan Gora <dg@adax.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Adrien Mazarguil [Fri, 3 Aug 2018 14:37:52 +0000 (16:37 +0200)]
doc: announce deprecation of flow copy function
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Thomas Monjalon [Wed, 8 Aug 2018 22:28:57 +0000 (00:28 +0200)]
doc: update deprecation notice about devargs
The devargs parsing function has changed in 18.08.
The devargs rework should be completed in 18.11.
Fixes:
a23bc2c4e01b ("devargs: add non-variadic parsing function")
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Olivier Matz [Tue, 7 Aug 2018 21:34:43 +0000 (23:34 +0200)]
eal: remove experimental tag for user mbuf pool ops
Remove experimental tag from rte_eal_mbuf_user_pool_ops().
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Santosh Shukla <santosh.shukla@caviumnetworks.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Olivier Matz [Tue, 7 Aug 2018 21:34:42 +0000 (23:34 +0200)]
eal: remove deprecated function for mbuf pool ops
rte_eal_mbuf_default_mempool_ops() is replaced by
rte_mbuf_best_mempool_ops().
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Santosh Shukla <santosh.shukla@caviumnetworks.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Thomas Monjalon [Wed, 8 Aug 2018 18:37:36 +0000 (20:37 +0200)]
doc: fix PDF build
The SVG images must be referenced without their extension,
because it is converted to PNG for PDF.
Fixes:
54c4cbb6ccf1 ("doc: add graphics to bbdev guide")
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Amr Mokhtar <amr.mokhtar@intel.com>
Lijuan Tu [Mon, 6 Aug 2018 10:56:31 +0000 (18:56 +0800)]
doc: add tested Intel platforms with Intel NICs
Add tested Intel platforms with Intel NICs to the release note.
Signed-off-by: Lijuan Tu <lijuan.tu@intel.com>
Raslan Darawsheh [Wed, 8 Aug 2018 15:32:57 +0000 (18:32 +0300)]
doc: add tested platforms with Mellanox NICs
Signed-off-by: Raslan Darawsheh <rasland@mellanox.com>
Shahaf Shuler [Sun, 5 Aug 2018 11:13:17 +0000 (14:13 +0300)]
doc: update release notes for Mellanox drivers
Signed-off-by: Shahaf Shuler <shahafs@mellanox.com>
Yongseok Koh [Wed, 8 Aug 2018 19:32:47 +0000 (12:32 -0700)]
net/mlx5: fix minimum size of multi-packet Rx queue
The size of Rx queue is determined by dividing the number of descriptors by
the number of strides. As device can't support single slot queue, if the
number of descriptors is same as the number of strides, MPRQ shouldn't be
enabled. Otherwise, this will cause HW fault. For example, if rxd is set to
512 with testpmd on ConnectX-4 Lx, PMD can't receive more than 512 packets
because the minimum number of strides for ConnectX-4 Lx is 512. Users have
to configure larger number of descriptors in this case.
Fixes:
7d6bf6b866b8 ("net/mlx5: add Multi-Packet Rx support")
Cc: stable@dpdk.org
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Rasesh Mody [Wed, 8 Aug 2018 05:38:35 +0000 (22:38 -0700)]
net/qede: bump version to 2.9.0.1
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Shahed Shaikh [Wed, 8 Aug 2018 05:38:34 +0000 (22:38 -0700)]
net/qede: fix ntuple filter configuration
PMD did not pass down the intended queue id while
configuring the ntuple filter.
Fixes:
622075356e8f ("net/qede: support ntuple and flow director filter")
Cc: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>
Cristian Dumitrescu [Mon, 6 Aug 2018 15:24:16 +0000 (16:24 +0100)]
examples/ip_pipeline: fix RSS
After adding RSS hash offload checks, flags that are not supported by
the current device result in RSS configuration failing as opposed to
unsupported flags being silently discarded. This fix is making sure
that only device supported flags are passed to RSS configuration.
Fixes:
aa1a6d87f15d ("ethdev: force RSS offload rules again")
Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Tested-by: Yuan Peng <yuan.peng@intel.com>
Matan Azrad [Mon, 6 Aug 2018 10:58:47 +0000 (10:58 +0000)]
net/tap: fix zeroed flow mask configurations
The rte_flow meaning of zero flow mask configuration is to match all
the range of the item value.
For example, the flow eth / ipv4 dst spec 1.2.3.4 dst mask 0.0.0.0
should much all the ipv4 traffic from the rte_flow API perspective.
>From some kernel perspectives the above rule means to ignore all the
ipv4 traffic (e.g. Ubuntu 16.04, 4.15.10).
Due to the fact that the tap PMD should provide the rte_flow meaning,
it is necessary to ignore the spec in case the mask is zero when it
forwards such like flows to the kernel.
So, the above rule should be translated to eth / ipv4 to get the
correct meaning.
Ignore spec configurations when the mask is zero.
Fixes:
de96fe68ae95 ("net/tap: add basic flow API patterns and actions")
Cc: stable@dpdk.org
Signed-off-by: Matan Azrad <matan@mellanox.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Pablo de Lara [Tue, 7 Aug 2018 02:00:04 +0000 (03:00 +0100)]
hash: fix doxygen of return values
rte_hash_lookup_data() and rte_hash_lookup_with_hash_data()
functions return the index of the table where the key is stored
when this is found, and not 0 as the Doxygen currently states.
Also, these functions, and rte_hash_get_key_with_position()
return negative values when keys are not found (-EINVAL and -ENOENT),
where the minus sign was missing.
Bugzilla ID: 78
Fixes:
473d1bebce43 ("hash: allow to store data in hash table")
Fixes:
6dc34e0afe7a ("hash: retrieve a key given its position")
Cc: stable@dpdk.org
Reported-by: Petr Houska <t-pehous@microsoft.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Stephen Hemminger [Mon, 6 Aug 2018 16:31:07 +0000 (09:31 -0700)]
doc: clarify usage of netvsc PMD
Since netvsc PMD does not support SR-IOV accelerated networking,
it is not recommended for use on Azure. Make this clear in the
guide.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Stephen Hemminger [Mon, 6 Aug 2018 18:22:44 +0000 (11:22 -0700)]
net/netvsc: report checksum failures
The host will notify netvsc device about failed UDP and TCP
checksum. Propagate that information into the mbuf.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Stephen Hemminger [Mon, 6 Aug 2018 18:22:43 +0000 (11:22 -0700)]
net/netvsc: support packet type
The Netvsc PMD was not filling in the packet type information.
Fixes:
4e9c73e96e83 ("net/netvsc: add Hyper-V network device")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Stephen Hemminger [Mon, 6 Aug 2018 18:11:08 +0000 (11:11 -0700)]
bus/vmbus: handle EOF on IRQ read
This function is not used by netvsc driver yet.
Still the code should handle case where device driver returns
zero (due to rescind).
Coverity issue: 302871
Fixes:
831dba47bd36 ("bus/vmbus: add Hyper-V virtual bus support")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Stephen Hemminger [Mon, 6 Aug 2018 18:11:07 +0000 (11:11 -0700)]
bus/vmbus: make sure path is null terminated
Use strlcpy rather than strncpy to avoid any issues about
null termination.
Coverity issue 302859
Fixes:
831dba47bd36 ("bus/vmbus: add Hyper-V virtual bus support")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Stephen Hemminger [Mon, 6 Aug 2018 18:11:06 +0000 (11:11 -0700)]
bus/vmbus: close directory in error path
Fix bug reported by Coverity where directory being scanned was
not closed in error path (leaking file descriptor).
Coverity issue: 302848
Fixes:
831dba47bd36 ("bus/vmbus: add Hyper-V virtual bus support")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Thomas Monjalon [Mon, 6 Aug 2018 10:51:19 +0000 (12:51 +0200)]
ethdev: bump library version
The old offload API is removed in 18.08,
so the library version must be increased,
in order to show the incompatibility with 18.05 one.
Fixes:
ab3ce1e0c193 ("ethdev: remove old offload API")
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com>
Thomas Monjalon [Sun, 5 Aug 2018 23:45:20 +0000 (01:45 +0200)]
version: 18.08-rc3
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Anatoly Burakov [Wed, 1 Aug 2018 12:07:16 +0000 (13:07 +0100)]
doc: add deprecation notice for external memory
Due to the upcoming external memory support [1], some API and ABI
changes will be required. In addition, although the changes called
out in the deprecation notice are not yet present in form of code
in the published RFC itself, they are based on consensus on the
mailing list [2] on how to best implement this feature.
[1] http://patches.dpdk.org/project/dpdk/list/?series=453&state=*
[2] https://mails.dpdk.org/archives/dev/2018-July/108002.html
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
Acked-by: Zhihong Wang <zhihong.wang@intel.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Kevin Traynor [Wed, 1 Aug 2018 15:30:49 +0000 (16:30 +0100)]
meter: remove experimental tag from profile API
As per guideline that new APIs must be experimental
for at least one release, it is now possible to remove
the experimental tag from:
rte_meter_srtcm_profile_config()
rte_meter_trtcm_profile_config()
Signed-off-by: Kevin Traynor <ktraynor@redhat.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Andrew Rybchenko [Wed, 11 Jul 2018 14:14:10 +0000 (15:14 +0100)]
eal: deprecate device attach and detach functions
Hotplug functions should be used directly to add and remove devices.
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Andrew Rybchenko [Wed, 11 Jul 2018 14:14:09 +0000 (15:14 +0100)]
ethdev: deprecate attach and detach functions
These functions are buggy from the very beginning and should not be used.
Generic EAL hotplug mechanisms should be used instead.
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Andrew Rybchenko [Wed, 11 Jul 2018 14:14:08 +0000 (15:14 +0100)]
app/pdump: use EAL hotplug instead of ethdev attach
rte_eth_dev_attach() is to be deprecated.
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Andrew Rybchenko [Fri, 27 Jul 2018 13:46:05 +0000 (14:46 +0100)]
mempool: fold memory size calculation helper
rte_mempool_calc_mem_size_helper() was introduced to avoid
code duplication and used in deprecated rte_mempool_mem_size() and
rte_mempool_op_calc_mem_size_default(). Now the first one is removed
and it is better to fold the helper into the second one to make it
more readable.
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Andrew Rybchenko [Fri, 27 Jul 2018 13:46:04 +0000 (14:46 +0100)]
mempool: remove deprecated functions
Functions rte_mempool_populate_phys(), rte_mempool_virt2phy() and
rte_mempool_populate_phys_tab() are just wrappers for corresponding
IOVA functions and were deprecated in v17.11.
Functions rte_mempool_xmem_create(), rte_mempool_xmem_size(),
rte_mempool_xmem_usage() and rte_mempool_populate_iova_tab() were
deprecated in v18.05 and removal was announced earlier in v18.02.
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Rosen Xu [Tue, 31 Jul 2018 12:52:40 +0000 (20:52 +0800)]
examples/flow_filtering: add flow director config for i40e
Rte_fdir_conf of rte_eth_conf should be initialized before
port initialization. It is a workaround solution when working
with Intel I40e.
Fixes:
4a3ef59a10c8 ("examples/flow_filtering: add simple demo of flow API")
Cc: stable@dpdk.org
Signed-off-by: Rosen Xu <rosen.xu@intel.com>
Acked-by: Ori Kam <orika@mellanox.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Gage Eads [Mon, 30 Jul 2018 15:10:00 +0000 (10:10 -0500)]
examples/multi_process: remove l2fwd fork example
l2fwd_fork relies on a multiprocess model that DPDK does not support
(calling rte_eal_init() before fork()), in particular in light of recent
EAL changes like the multiproess communication channel.
This example can mislead users into thinking this is a supported
multiprocess model; hence, this commit removes this example and the
corresponding user guide documentation as well.
This patch was made following this mailing list discussion:
http://mails.dpdk.org/archives/dev/2018-July/108106.html
Signed-off-by: Gage Eads <gage.eads@intel.com>
Kevin Laatz [Fri, 20 Jul 2018 13:09:06 +0000 (14:09 +0100)]
doc: add PCI address naming in IP pipeline guide
Add a note to the 'link' command in the IP Pipeline documentation
specifying the PCI device name format required to run the application.
Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Jerin Jacob [Tue, 17 Jul 2018 17:14:17 +0000 (22:44 +0530)]
eal: fix bitmap documentation
n_bits comes as first argument, align doxygen comment.
n_bit need to not be multiple of 512 as n_bits
are rounding to RTE_BITMAP_CL_BIT_SIZE.
Fixes:
14456f59e9f7 ("doc: fix doxygen warnings in QoS API")
Fixes:
de3cfa2c9823 ("sched: initial import")
Cc: stable@dpdk.org
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Honnappa Nagarahalli [Tue, 17 Jul 2018 04:52:44 +0000 (23:52 -0500)]
ring: clarify preemptible nature of algorithm
rte_ring implementation is not preemptible only under certain
circumstances. This clarification is helpful for data plane and
control plane communication using rte_ring.
Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Ola Liljedahl <ola.liljedahl@arm.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Pablo de Lara [Thu, 2 Aug 2018 00:35:04 +0000 (01:35 +0100)]
mempool: check for zero size creation
Currently, a mempool can be created if the number of
objects is zero. However, in this scenario,
rte_mempool_create should return NULL,
as the mempool created is useless otherwise.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Kevin Traynor [Thu, 2 Aug 2018 18:39:41 +0000 (19:39 +0100)]
ethdev: decrease log level for unneeded actions
Change log level of messages from ERR to INFO where
the post condition of the API is success, but no action
was actually needed as the condition already existed.
e.g. calling rte_eth_dev_start() for a device that is
already started.
Fixes:
bea1e0c70cfc ("ethdev: convert static log type usage to dynamic")
Signed-off-by: Kevin Traynor <ktraynor@redhat.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Tomasz Jozwiak [Thu, 2 Aug 2018 15:09:26 +0000 (17:09 +0200)]
common/qat: fix offset greater than first segment
This patch fixes sgl filling to handle offset
greater than first sgl segment
Fixes:
1947bd18580b ("compress/qat: support scatter-gather buffers")
Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Tomasz Jozwiak [Thu, 2 Aug 2018 15:09:25 +0000 (17:09 +0200)]
compress/qat: fix buffer lengths in offset case
Fixed lengths for src and dest buffers
Fixes:
32842f2a6d7d ("compress/qat: create FW request and process response")
Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Pablo de Lara [Thu, 2 Aug 2018 08:44:39 +0000 (09:44 +0100)]
app/crypto-perf: fix auth IV offset
Auth IV offset was not being set when creating the crypto session.
Fixes:
acf8616901b5 ("cryptodev: add auth IV")
Cc: stable@dpdk.org
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Lee Daly [Wed, 1 Aug 2018 13:23:43 +0000 (14:23 +0100)]
compress/isal: fix offset check
This commit fixes an offset check in decompression which was checking
destination offset size against dst data_len rather than checking
against dst pkt_len as required, to support single and multi-segment
buffers.
Fixes:
788e748d3845 ("compress/isal: support chained mbufs")
Signed-off-by: Lee Daly <lee.daly@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Harry van Haaren [Thu, 2 Aug 2018 14:43:29 +0000 (15:43 +0100)]
event: fix ring init failure handling
This commit fixes a bug in a 32-bit environment where the
generic ring_init() would fail, but given the interaction
with memzones the next iteration of the event_ring_autotest
would actually *pass* because the ring in question would
exist already an be looked-up.
This commit rightly error checks the result of ring_init(),
and calls rte_free() on the memory as required.
Fixes:
dc39e2f359b5 ("eventdev: add ring structure for events")
Cc: stable@dpdk.org
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Yongseok Koh [Thu, 2 Aug 2018 21:00:07 +0000 (14:00 -0700)]
net/mlx5: fix minimum number of Multi-Packet RQ buffers
If MPRQ is enabled, a PMD-private mempool is allocated. For ConnectX-4 Lx,
the minimum number of strides is 512 which ConnectX-5 supports 8. This
results in quite small number of elements for the MPRQ mempool. For
example, if the size of Rx ring is configured as 512, only one MPRQ buffer
can cover the whole ring. If there's only one Rx queue is configured. In
the following code in mlx5_mprq_alloc_mp(), desc is 1 and obj_num will be
36 as a result.
desc *= 4;
obj_num = desc + MLX5_MPRQ_MP_CACHE_SZ * priv->rxqs_n;
However, rte_mempool_create_empty() has a sanity check to refuse large
per-lcore cache size compared to the number of elements. Cache flush
threshold should not exceed the number of elements of a mempool. For the
above example, the threshold is 32 * 1.5 = 48 which is larger than 36 and
it fails to create the mempool.
Fixes:
7d6bf6b866b8 ("net/mlx5: add Multi-Packet Rx support")
Cc: stable@dpdk.org
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Yongseok Koh [Fri, 3 Aug 2018 22:00:56 +0000 (15:00 -0700)]
net/mlx5: fix check for MPLS-in-GRE
Multiple tunnel isn't allowed but MPLS over GRE should be accepted.
Fixes:
a4a5cd21d20a ("net/mlx5: add flow MPLS item")
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>