General:
# Add High-performance CTF based native tracer support.
RFC: https://www.mail-archive.com/dev@dpdk.org/msg154457.html
- Infrastructure to enable trace for dpdk library and applications
- UT and performance test cases for tracer
- Add trace points to ethdev, cryptodev, and eventdev
Hi Xiang,
> -Original Message-
> From: Wang Xiang
> Sent: Thursday, February 27, 2020 11:26 AM
> To: Ori Kam
> Cc: Jerin Jacob ; Jerin Jacob ;
> dpdk-dev ; Pavan Nikhilesh ;
> Shahaf Shuler ; Hemant Agrawal
> ; Opher Reviv ; Alex
> Rosenbaum ; dov...@marvell.com; Prasun Kapoor
> ; Nipun
Patch updates eventdev and adapters feature matrices for octeontx2
platform.
Signed-off-by: Sunil Kumar Kori
---
v4:
- Rebased to 20.02
v3:
- Removed .txt files to generate tables.
v2:
- Review comments incorporated
doc/guides/eventdevs/features/octeontx2.ini | 9 +
1 file changed, 9
Patch updates eventdev and adapters feature matrices for octeontx
platform.
Signed-off-by: Sunil Kumar Kori
---
v4:
- Rebased to 20.02
v3:
- Removed .txt files to generate tables.
v2:
- Review comments incorporated
doc/guides/eventdevs/features/octeontx.ini | 8
1 file changed, 8 in
Patch adds skeleton for feature matrices for event dev
and Rx/Tx adapters.
Along with, .ini files are added for all supported PMDs.
Signed-off-by: Sunil Kumar Kori
---
v4:
- Rebased to 20.02
v3:
- Removed .txt files to generate tables.
- Use conf.py script to generate tables.
- Add .ini file
From: Selwin Sebastian
Enable scattered rx support and add jumbo packet transmit capability
Signed-off-by: Selwin Sebastian
---
doc/guides/nics/features/axgbe.ini | 1 +
drivers/net/axgbe/axgbe_common.h | 2 +
drivers/net/axgbe/axgbe_ethdev.c | 18 +++-
drivers/net/axgbe/axgbe_rxtx.c
From: Nic Chautru
Supports for FEC 5G PMD Driver on FPGA card PAC N3000
Signed-off-by: Nic Chautru
---
config/common_base |5 +
doc/guides/bbdevs/fpga_5gnr_fec.rst| 297 +++
doc/guides/bbdevs/index.rst|1 +
driver
From: Nic Chautru
Adding missing overview page in documentation with
comparison of feature set by PMD implementation.
Signed-off-by: Nic Chautru
---
.gitignore | 1 +
doc/guides/bbdevs/features/default.ini | 16
doc/guides/bbdevs/featur
From: Nic Chautru
Adding capacity to initialize the device driver from
the test-bbdev environment for the new device
FPGA for 5GNR FEC.
Signed-off-by: Nic Chautru
---
app/test-bbdev/Makefile | 3 +++
app/test-bbdev/meson.build | 3 +++
app/test-bbdev/test_bbdev_perf.c | 58 +++
From: Nic Chautru
Adding functionality to validate HARQ for different
devices implementation.
Adding capacity to fetch HARQ data when required as
part of this validation.
Signed-off-by: Nic Chautru
---
app/test-bbdev/test_bbdev_perf.c | 552 -
app/test-bbd
From: Nic Chautru
Update related to the changes introduced by the
previous commits.
Signed-off-by: Nic Chautru
---
doc/guides/tools/testbbdev.rst | 337 +++--
1 file changed, 291 insertions(+), 46 deletions(-)
diff --git a/doc/guides/tools/testbbdev.rst b/d
From: Nic Chautru
Adding support for the offload latency tests when
using the LDPC encoder and decoder operations.
Signed-off-by: Nic Chautru
---
app/test-bbdev/test_bbdev_perf.c | 26 +++---
1 file changed, 19 insertions(+), 7 deletions(-)
diff --git a/app/test-bbdev/test
From: Nic Chautru
Adding missing implementation for the interrupt tests
for LDPC encoder and decoders.
Signed-off-by: Nic Chautru
---
app/test-bbdev/test_bbdev_perf.c | 202 ++-
1 file changed, 200 insertions(+), 2 deletions(-)
diff --git a/app/test-bbdev/t
From: Nic Chautru
This exposes the HARQ buffer size at the device driver level
instead of using the capability of a specific operation.
This is currently not yet used by a device until
future commit.
Signed-off-by: Nic Chautru
---
drivers/baseband/turbo_sw/bbdev_turbo_software.c | 2 +-
lib/l
From: Nic Chautru
The actual LLR representation was incorrectly assumed to be 2
instead of 4. This would impact wireless performance but is not
critical to be back ported on LTS branches.
Fixes: c769c711757a ("baseband/turbo_sw: extend for 5G")
Signed-off-by: Nic Chautru
---
drivers/baseband/
From: Nic Chautru
Self-contained and cosmetic renaming of macro to be more explict.
Signed-off-by: Nic Chautru
---
app/test-bbdev/test_bbdev_perf.c | 51 +++-
1 file changed, 19 insertions(+), 32 deletions(-)
diff --git a/app/test-bbdev/test_bbdev_perf.c b/
From: Nic Chautru
Includes support for BLER wireless performance test with
new arguments for SNR and number of iterations for 5G.
Signed-off-by: Nic Chautru
---
app/test-bbdev/main.c| 29 ++-
app/test-bbdev/main.h| 9 +-
app/test-bbdev/test_bbdev_perf.c | 523 +++
From: Nic Chautru
Adding capability flag for device variants when HARQ buffer
may or may not include the filler bits.
Minor cosmetic changes in same file.
Signed-off-by: Nic Chautru
---
lib/librte_bbdev/rte_bbdev.h| 2 ++
lib/librte_bbdev/rte_bbdev_op.h | 12 ++--
2 files changed,
From: Nic Chautru
This is to support cases when the input data for
decoding a code block is larger than 64kB and would
not fit as a contiguous block of data into one
mbuf. In that case the length from the opearation
supersedes the mbug default structure.
Signed-off-by: Nic Chautru
---
app/test
This set includes extending support for the bbdev device drivers
for 20.05 and notably add a new baseband PMD for FPGA 5GNR
FEC implementation.
Documentation is updated as well accordingly.
Nic Chautru (14):
bbdev: add capability flag for filler bits inclusion in HARQ
bbdev: expose device
Clang on Windows doesn't use pthread for now, while MinGW does. Removing
`-pthread` option with MS linker fixes the following warning:
clang: warning: argument unused during compilation: '-pthread'
[-Wunused-command-line-argument]
Option `--no-as-needed` is meaningless for PE output.
MinGW-w64 linker does not mimic MS linker options, so the build system
must differentiate between linkers on Windows. Use GNU linker options
with GCC and MS linker options with Clang.
MinGW-w64 by default uses MSVCRT stdio, which does not comply to ANSI,
most notably its formatting and string hand
Instructions for different toolchains presented as options on the
corresponging steps of the guide, so that common parts may be reused.
Signed-off-by: Dmitry Kozlyuk
---
doc/guides/windows_gsg/build_dpdk.rst | 62 +++
1 file changed, 53 insertions(+), 9 deletions(-)
diff
Add Meson configuration to cross-compile for Windows using MinGW-w64.
It may require adjustments in some cases, but at least it provides
the foundation.
Signed-off-by: Dmitry Kozlyuk
---
config/x86/meson_mingw.txt | 13 +
1 file changed, 13 insertions(+)
create mode 100644 config/x8
Disable bundled getopt implementation and GNU extensions shim when
building in GNU environment.
Signed-off-by: Dmitry Kozlyuk
---
lib/librte_eal/meson.build | 3 +++
lib/librte_eal/windows/eal/eal.c| 6 --
lib/librte_eal/windows/eal/include/getopt.h | 4
lib
This patch series add support for building DPDK using MinGW-w64.
MinGW-w64 provides GNU toolchain and independent platform SDK on
Windows. It also supports cross-compilation to Windows from POSIX
systems by providing cross tollchains and libraries [0]. It does NOT
emulate a full POSIX environment,
When using __attribute__((format(...)) on functions, GCC on Windows
assumes MS-specific format string by default, even if the underlying
stdio implementation is ANSI-compliant (either MS Unicersal CRT
or MinGW implementation). Wrap attribute into a macro that forces
GNU-specific format string when
Mixed case in Windows header names causes errors when cross-compiling
from Linux with case-sensitive filesystem using MinGW, because MinGW
distribution provides all platform SDK headers in lowercase. The change
does not affect Windows native builds on case-insensitive filesystems
(NTFS default).
R
Finally managed to run l2fwd with virtio PMD. Providing details as promised.
1. For some reason, when l2fwd is running, virtual screen stops updating. The
system itself is NOT frozen: l2fwd forwards packets, processes can be
launched using QEMU guest agent, input is received and processed. Since
Ok，more info will be update to this patch
> -Original Message-
> From: Ye, Xiaolong
> Sent: Thursday, February 27, 2020 11:09 AM
> To: Zhao1, Wei
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: Re: [PATCH] net/ixgbe: fix issue for change definitions of bool
>
> Hi,
>
> On 02/27, Wei Zha
Hi,
On 02/27, Wei Zhao wrote:
>We had better not to change code in base folder, that patch will
>introduce a bug for etag/etag_strip for x550 NIC. So change back
>to the aboriginal definition.
>
>Cc: sta...@dpdk.org
>Fixes: ad43b7bce95b ("net/ixgbe: avoid multiple definitions of bool")
I think th
On Tue, Feb 25, 2020 at 5:51 PM Tiwei Bie wrote:
>
> On Tue, Feb 25, 2020 at 12:44:48PM -0800, Yifeng Sun wrote:
> > >
> > > +int rte_vhost_get_kickfd(int vid, uint16_t queue_id)
>
> Introducing rte_vhost_get_kickfd() may not help much, we already
> have rte_vhost_get_vhost_vring() to do that.
>
>
Hi Ori,
Thanks for the comments.
Hyperscan supports both start_offset and end_offset modes with most
users choosing end_offset for rule coverage and performance reasons.
I'm OK to have the default behavior with start_offset and len.
It'll be good to change RTE_REGEX_DEV_CFG_MATCH_AS_START to
RTE
Hi, Wei
On 02/27, Wei Zhao wrote:
>We had better not to change code in base folder, that patch will
>introduce a bug for etag/etag_strip for x550 NIC. So change back
Could you elaborate the details of this bug?
Thanks,
Xiaolong
>to the aboriginal definition.
>
>Cc: sta...@dpdk.org
>Fixes: ad43b
We had better not to change code in base folder, that patch will
introduce a bug for etag/etag_strip for x550 NIC. So change back
to the aboriginal definition.
Cc: sta...@dpdk.org
Fixes: ad43b7bce95b ("net/ixgbe: avoid multiple definitions of bool")
Signed-off-by: Wei Zhao
---
drivers/net/ixgbe
> > +/**
> > + * @internal Reserve ring elements to enqueue several objects on the ring
> > + *
> > + * @param r
> > + * A pointer to the ring structure.
> > + * @param esize
> > + * The size of ring element, in bytes. It must be a multiple of 4.
> > + * This must be the same value used while
Hi Dey,
The changes look good, however rte/RTE prefix need to be used. The patch
doesn’t compile with latest dpdk.
s/ether_type/rte_ether_type/
s/ETHER_TYPE_VLAN/RTE_ETHER_TYPE_VLAN/
s/vlan_hdr/rte_vlan_hdr/
For the subject line, s/bnx2x/net\/bnx2x/ is preferred.
Also, the inclusion footer in t
Hi Honnappa,
> Add scatter gather APIs to avoid intermediate memcpy. Serial
> dequeue APIs are added to support access to ring elements
> before actual dequeue.
>
> Signed-off-by: Honnappa Nagarahalli
> Reviewed-by: Gavin Hu
> Reviewed-by: Ola Liljedahl
> ---
> lib/librte_ring/Makefile
Bare metal PowerNV systems include a DPDK supported IOMMU that allows
IOVA=VA support. Test for the platform type and report virtual address
support if running on a PowerNV system.
Signed-off-by: David Christensen
---
drivers/bus/pci/linux/pci.c | 29 +
1 file changed
Hi Tiwei,
Thanks a lot for your comment. I will take a look at rte_vhost_get_vhost_vring.
Best,
Yifeng
On Tue, Feb 25, 2020 at 5:51 PM Tiwei Bie wrote:
>
> On Tue, Feb 25, 2020 at 12:44:48PM -0800, Yifeng Sun wrote:
> > >
> > > +int rte_vhost_get_kickfd(int vid, uint16_t queue_id)
>
> Introduci
Hi Honnappa,
Your description below looks correct to me. For the current implementation, I
referenced a couple of existing DPDK libraries, but primarily the rte_service
library. However, I agree that allocating the timer data structs only as
needed would be a good idea.
You are also correct
26/02/2020 17:35, Jerin Jacob:
> On Wed, Feb 26, 2020 at 8:31 PM Ferruh Yigit wrote:
> >
> > Signed-off-by: Ferruh Yigit
>
> Acked-by: Jerin Jacob
Acked-by: Thomas Monjalon
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ananyev,
> Konstantin
>
> > > > > More and more customers use(/try to use) DPDK based apps within
> > > > > overcommitted systems (multiple acttive threads over same
> pysical cores):
> > > > > VM, container deployments, etc.
> > > > > T
In case of bnx2xvf pmd, tx packets can support vland id in 2 ways :
1. setting the mbuf ol_flags=PKT_TX_VLAN_PKT and passing the
vlanid in mbuf->vlan_tci.
2. the tx packet itself has the vlan id included in the packet.
The first case is working as expected but the second case where
the vlan id is i
On Wed, Feb 26, 2020 at 8:31 PM Ferruh Yigit wrote:
>
> Signed-off-by: Ferruh Yigit
> ---
> Cc: Andrew Rybchenko
> Cc: Thomas Monjalon
> Cc: Olivier Matz
> ---
Acked-by: Jerin Jacob
> doc/guides/rel_notes/deprecation.rst | 5 +
> 1 file changed, 5 insertions(+)
>
> diff --git a/doc/gu
On Wed, Feb 26, 2020 at 10:00 PM Olivier Matz wrote:
>
> On Mon, Feb 17, 2020 at 05:46:42PM +0100, Thomas Monjalon wrote:
> > Write first lines of the README file about the intent (upstream first)
> > and the licenses allowed so far in DPDK.
> >
> > Signed-off-by: Thomas Monjalon
>
> Acked-by: Ol
On Mon, Feb 17, 2020 at 05:46:42PM +0100, Thomas Monjalon wrote:
> Write first lines of the README file about the intent (upstream first)
> and the licenses allowed so far in DPDK.
>
> Signed-off-by: Thomas Monjalon
Acked-by: Olivier Matz
Signed-off-by: Ferruh Yigit
---
Cc: Andrew Rybchenko
Cc: Thomas Monjalon
Cc: Olivier Matz
---
doc/guides/rel_notes/deprecation.rst | 5 +
1 file changed, 5 insertions(+)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/guides/rel_notes/deprecation.rst
index 1339f54f5..9d68de0f6 10
On Wed, Feb 26, 2020 at 2:55 PM Thomas Monjalon wrote:
>
> 26/02/2020 14:38, David Marchand:
> > Start a new release cycle with empty release notes.
> > ABI must now be checked with v20.02 as a reference.
> >
> > Signed-off-by: David Marchand
> > ---
> > .travis.yml|
26/02/2020 14:38, David Marchand:
> Start a new release cycle with empty release notes.
> ABI must now be checked with v20.02 as a reference.
>
> Signed-off-by: David Marchand
> ---
> .travis.yml| 4 +
> ABI_VERSION| 2 +-
> VERSION
With this patch, the promiscuous and multicast fields are initialized as
enabled for vhost PMD by default, this allows the devices to be used when
running applications that attempt to enable promiscuous or multicast mode.
Similar things have done for other virtual PMDs by commit f165210321c4
("driv
Hi, David
On 02/26, David Marchand wrote:
>On Wed, Feb 26, 2020 at 10:15 AM Sivaprasad Tummala
> wrote:
>>
>> l2fwd application exits, if return for rte_eth_promiscuous_enable
>> is not success. But for vHost PMD, promiscuous enable returns "Not
>> Supported".
>
>Could the vhost pmd announce that
Start a new release cycle with empty release notes.
ABI must now be checked with v20.02 as a reference.
Signed-off-by: David Marchand
---
.travis.yml| 4 +
ABI_VERSION| 2 +-
VERSION| 2 +-
doc/guides/r
> > > > > >> + /* Get core ID */
> > > > > >> + lcore_id = rte_lcore_id();
> > > > > >> +
> > > > > >> + /* Get socket ID */
> > > > > >> + socket_id = rte_lcore_to_socket_id(lcore_id);
> > > > > >> +
> > > > > >> + /* Save routing table */
> > > > > >> + lconf.rt.rt4_ctx = socket_ctx[socket
From: Zhu Tao
Setting LINK UP or LINK DOWN is divided into two parts, with
the main task done in a separate thread, which can take up
to 9 seconds. If cancel the thread in execution, may cause state
inconsistencies. Therefore, must wait for the previous setting
to exit normally before setting the
Hi all,
The DPDK QoS scheduler has a 4-stage pipeline for enqueuing the packets.
This is used for hiding the latency of prefetching the data structures.
Why is there no pipeline for dequeuing the packets?
How does the dequeue function maintain the state of a packet? In other
words, if I want to bac
> -Original Message-
> From: O'loingsigh, Mairtin
> Sent: Wednesday, February 26, 2020 9:04 AM
> To: Trahe, Fiona ; akhil.go...@nxp.com
> Cc: dev@dpdk.org; O'loingsigh, Mairtin
> Subject: [PATCH v2 2/2] test/crypto: Add AES-256 DOCSIS test vectors
>
> This patch adds test vectors for
> -Original Message-
> From: O'loingsigh, Mairtin
> Sent: Wednesday, February 26, 2020 9:04 AM
> To: Trahe, Fiona ; akhil.go...@nxp.com
> Cc: dev@dpdk.org; O'loingsigh, Mairtin
> Subject: [PATCH v2 1/2] crypto/qat: support DOCSIS AES-256
>
> This patch adds support for DOCSIS AES-256
Hi Akhil,
Please see my answer below.
Thanks,
Lukasz
On 26.02.2020 07:04, Akhil Goyal wrote:
> Hi Lukasz,
>
>>>
>>> Is it not possible to use the existing functions for finding routes,
>>> checking
>> packet types and checking security policies.
>>> It will be very difficult to manage two sepa
Added vHost PMD arguments 'linear-buffer' and 'ext-buffer'
to configure 'RTE_VHOST_USER_LINEARBUF_SUPPORT' and
'RTE_VHOST_USER_EXTBUF_SUPPORT' flags in the vhost library
Signed-off-by: Sivaprasad Tummala
---
doc/guides/nics/vhost.rst | 10 ++
drivers/net/vhost/rte_eth_vhost.c |
> -Original Message-
> From: dev On Behalf Of Ophir Munk
> Sent: Wednesday, February 26, 2020 10:28
> To: dev@dpdk.org
> Cc: Thomas Monjalon ; Raslan Darawsheh
> ; Ophir Munk
> Subject: [dpdk-dev] [PATCH v1] net/mlx5: fix VLAN PCP item calculation
>
> The VLAN 16 bits tci field contains
GL_SWR_PM_UP_THR value lack in X722 caused configure register write not be
called. This is the root cause of performance drop. This patch add support
for:
Device-ID ValueComments
0x37D00x03030303 4x10G FPK
Fixes: 3320d4a240da ("net/i40e: workaround performance degradation")
Cc: s
On Wed, Feb 26, 2020 at 10:15 AM Sivaprasad Tummala
wrote:
>
> l2fwd application exits, if return for rte_eth_promiscuous_enable
> is not success. But for vHost PMD, promiscuous enable returns "Not
> Supported".
Could the vhost pmd announce that it is already in promiscuous mode?
Like in f1652103
l2fwd application exits, if return for rte_eth_promiscuous_enable
is not success. But for vHost PMD, promiscuous enable returns "Not
Supported".
This patch validates success and no support of promiscuous enable.
Signed-off-by: Sivaprasad Tummala
---
examples/l2fwd/main.c | 2 +-
1 file changed,
This patch adds support for DOCSIS AES-256 when using qat
Signed-off-by: Mairtin o Loingsigh
---
drivers/crypto/qat/qat_sym_capabilities.h | 4 ++--
drivers/crypto/qat/qat_sym_session.c | 12 ++--
2 files changed, 12 insertions(+), 4 deletions(-)
diff --git a/drivers/crypto/qat/qa
This patch adds test vectors for AES-256 and sets QAT as the
target PMD.
Signed-off-by: Mairtin o Loingsigh
---
app/test/test_cryptodev_aes_test_vectors.h | 176 +
1 file changed, 176 insertions(+)
diff --git a/app/test/test_cryptodev_aes_test_vectors.h
b/app/test/test_cryp
To match the pools/queues configuration, the pools/queues output
should start from VMDQ base queue. This patch fixed the issue.
Fixes: 6bb97df521aa ("examples/vmdq: new app")
Cc: sta...@dpdk.org
Signed-off-by: Junyu Jiang
---
examples/vmdq/main.c | 9 +
1 file changed, 5 insertions(+),
Hi Xiang,
> -Original Message-
> From: dev On Behalf Of Wang Xiang
> Sent: Wednesday, February 26, 2020 11:03 AM
> To: Ori Kam
> Cc: Jerin Jacob ; Jerin Jacob ;
> dpdk-dev ; Pavan Nikhilesh ;
> Shahaf Shuler ; Hemant Agrawal
> ; Opher Reviv ; Alex
> Rosenbaum ; dov...@marvell.com; Prasu
The VLAN 16 bits tci field contains both values of PCP and VID. When
extracting any one of them - it is required not to affect the other one.
Previous to this commit in routine flow_dev_get_vlan_info_from_items()
we calcualted the PCP as follows:
(1) vlan->vlan_tci &= MLX5DV_FLOW_VLAN_PCP_MASK;
To match the pools/queues configuration, the pools/queues output
should start from VMDQ base queue. This patch fixed the issue.
Fixes: 6bb97df521aa ("examples/vmdq: new app")
Cc: sta...@dpdk.org
Signed-off-by: Junyu Jiang
---
examples/vmdq/main.c | 9 +
1 file changed, 5 insertions(+),
70 matches
Mail list logo
