The core-eal-intr-thread-1896 received signal SIGSEGV, Segmentation fault：
#1 rte_i40e_dev_atomic_write_link_status (dev=0xa21940
, link=0x7f0d9e2b57d0)at
/usr/src/debug/dpdk-16.11/drivers/net/i40e/i40e_ethdev.c:712
#2 i40e_dev_link_update (dev=dev@entry=0xa21940
,wait_to_complete=wait_to_comp
From: Yunjian Wang
The nic's interrupt source has some active callbacks, when
the port hotplug. Add a retry to give more port's a chance
to uninit before returning an error.
Fixes: d42aaf30008b ("i40e: support port hotplug")
Signed-off-by: Yunjian Wang
---
drivers/net/i40e/i40e_ethdev.c | 16
On Thursday, March 03/08/18, 2018 at 19:20:14 +0530, Ferruh Yigit wrote:
> On 3/8/2018 1:44 PM, Ferruh Yigit wrote:
> > On 2/28/2018 6:04 PM, Rahul Lakkireddy wrote:
> >> Patch 1 reworks rte_eth_dev allocation for other ports under same PF.
> >>
> >> Patch 2 fixes secondary process initialization f
On Thursday, March 03/08/18, 2018 at 19:04:31 +0530, Ferruh Yigit wrote:
> On 2/28/2018 6:04 PM, Rahul Lakkireddy wrote:
> > From: Kumar Sanghvi
> >
> > Add firmware API for updating RSS hash configuration and key. Move
> > RSS hash configuration from cxgb4_write_rss() to a separate function
> >
If PMD delivers Rx packets with mbuf indirection, ol_flags should not be
overwritten. For mlx5 PMD, if Multi-Packet RQ is enabled, Rx packets could
be indirect mbufs.
Signed-off-by: Yongseok Koh
---
app/test-pmd/csumonly.c | 2 ++
app/test-pmd/macfwd.c | 2 ++
app/test-pmd/macswap.c | 2 ++
3
Multi-Packet RQ uses mbuf indirection and direct mbufs come from the
private Mempool (rxq->mprq_mp) of PMD. To properly release the Mempool, it
is better to empty the Tx completeion array (txq->elts) before releasing
it.
Signed-off-by: Yongseok Koh
---
drivers/net/mlx5/mlx5.c | 16 --
Multi-Packet Rx Queue (MPRQ a.k.a Striding RQ) can further save PCIe
bandwidth by posting a single large buffer for multiple packets. Instead of
posting a buffer per a packet, one large buffer is posted in order to
receive multiple packets on the buffer. A MPRQ buffer consists of multiple
fixed-siz
mlx5dv_create_wq() is added.
Signed-off-by: Yongseok Koh
---
drivers/net/mlx5/mlx5_glue.c | 9 +
drivers/net/mlx5/mlx5_glue.h | 4
2 files changed, 13 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_glue.c b/drivers/net/mlx5/mlx5_glue.c
index 1c4396ada..e33fc76b5 100644
--- a/driv
Filling in fields of mbuf becomes a separate inline function so that this
can be reused.
Signed-off-by: Yongseok Koh
---
drivers/net/mlx5/mlx5_rxtx.c | 84 +++-
1 file changed, 51 insertions(+), 33 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/
Multi-Packet Rx Queue (MPRQ a.k.a Striding RQ) can further save PCIe
bandwidth by posting a single large buffer for multiple packets. Instead of
posting a buffer per a packet, one large buffer is posted in order to
receive multiple packets on the buffer. A MPRQ buffer consists of multiple
fixed-siz
When attaching a mbuf, indirect mbuf has to point to start of buffer of
direct mbuf. By adding buf_off field to rte_mbuf, this becomes more
flexible. Indirect mbuf can point to any part of direct mbuf by calling
rte_pktmbuf_attach_at().
Possible use-cases could be:
- If a packet has multiple layer
Signed-off-by: Rosen Xu
Signed-off-by: Yanglong Wu
---
drivers/raw/ifpga_rawdev/Makefile | 63 +++
drivers/raw/ifpga_rawdev/ifpga_rawdev.c| 472 +
drivers/raw/ifpga_rawdev/ifpga_rawdev.h| 38 ++
drivers/raw/ifpga_rawdev/ifpga_rawde
On Fri, Mar 09, 2018 at 04:00:55PM +, Ferruh Yigit wrote:
[...]
> Series applied to dpdk-next-net/master, thanks.
>
> (typo in 2/10 fixed while applying)
Thanks a lot for fixing that. Adding "build with assert enabled" to our
checklist..
-Hyong
On Fri, Mar 09, 2018 at 03:57:46PM +, Ferruh Yigit wrote:
> On 3/9/2018 3:51 PM, Ananyev, Konstantin wrote:
[...]
> >> Is this work based on an application that uses max_rx_pkt_len and to make
> >> PMD
> >> compatible with that application? If so we can continue with patch, but if
> >> the
>
This V1 patchset contains the revised proposal to manage virtual
tunnel endpoints (vTEP) hardware accleration based on community
feedback on RFC
(http://dpdk.org/ml/archives/dev/2017-December/084676.html). This
proposal is purely enabled through rte_flow APIs with the
additions of some new features
Cc Declan and Pablo, the maintainers
09/03/2018 23:08, Luse, Paul E:
> Hi,
>
> I'm working on an SPDK module that uses the DPDK cryptodev framework,
> initially I'm using the AESNI PMD and have a few questions. in the doc it
> says that only in-place is supported however I see code in
> set_mb
Use strcmp to compare device names as the strncmp in original code
causes find_vdev to return -EEXIST for names that are prefix
of another. The creation of interfaces fails unpredictably based
on the order of their creation. An easy way hit this bug is to create
eth_vhost1 after eth_vhost11.
Sign
Some DPDK applications wrongly assume these requirements:
- no hotplug, i.e. ports are never detached
- all allocated ports are available to the application
Such application iterates over ports by its own mean.
The most common pattern is to request the port count and
assume ports with inde
Hi,
I'm working on an SPDK module that uses the DPDK cryptodev framework, initially
I'm using the AESNI PMD and have a few questions. in the doc it says that only
in-place is supported however I see code in set_mb_job_params() just after the
comment "Mutable crypto operation parameters" it appe
The drivers directory contains some sub-directories
for each kind of device (or bus, mem):
net, crypto, event, raw
They are not suffixed with "dev" because it is obvious.
For consistency, the sub-directory drivers/bbdev/
is renamed to drivers/baseband/.
Signed-off-by: Thomas Monjalon
---
This commit implements TCP segmentation offload in TAP.
Dpdk rte_gso library is used to segment large TCP payloads (e.g. 64K bytes)
into smaller MTU size buffers.
By supporting TSO offload capability in software a TAP device can be used
as a failsafe sub device and be paired with another PCI device
In past TAP implementation checksum offload calculations (for
IP/UDP/TCP) were skipped in case of a multi segments packet.
This commit improves TAP functionality by enabling checksum calculations
in multi segments cases.
The only restriction now is that the first segment must contain all
headers of
This RFC suggests TAP TSO (TSP segmentation offload) implementation in SW.
It uses dpdk library rte_gso which is also used by testpmd.
Dpdk rte_gso library segments large TCP payloads (e.g. 64K bytes)
into smaller MTU size buffers.
By supporting TSO offload capability in software a TAP device can b
On Fri, Mar 09, 2018 at 03:45:49PM +, Ferruh Yigit wrote:
> On 3/9/2018 3:16 PM, Neil Horman wrote:
> > On Fri, Mar 09, 2018 at 01:00:35PM +, Ferruh Yigit wrote:
> >> On 3/9/2018 12:36 PM, Neil Horman wrote:
> >>> On Fri, Mar 09, 2018 at 11:25:31AM +, Ferruh Yigit wrote:
> "struct
Update the unit test to check the working of new API.
Signed-off-by: Jasvinder Singh
---
test/test/test_sched.c | 91 ++
1 file changed, 69 insertions(+), 22 deletions(-)
diff --git a/test/test/test_sched.c b/test/test/test_sched.c
index 32e500b..
Add new API function to add more pipe configuration profiles
post initialization to the set of exisitng profiles specified during
the creation of scheduler port.
This API removes the current limitation that forces the user
to define the full set of pipe profiles as the part of port parameters
whil
Add example to build pipeline with hash table to classify the
ingress traffic.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Fan Zhang
---
examples/ip_pipeline/examples/flow.cli | 60 ++
1 file changed, 60 insertions(+)
create
On 3/7/2018 9:36 PM, Yongseok Koh wrote:
>
>> On Mar 6, 2018, at 8:28 AM, Ferruh Yigit wrote:
>>
>> It is not clear which per port offloads are enabled. Printing offloads
>> values at forwarding start.
>>
>> CRC strip offload value was printed in more verbose manner, it is
>> removed since Rx/Tx
Add example to built pipeline with LPM table to demonstrate layer 3
routing.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Reshma Pattan
---
examples/ip_pipeline/examples/route.cli | 60 +
1 file changed, 60 insertions(+)
crea
Add example to built pipeline with ACL table to demonstrate
the firewall operation.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/examples/firewall.cli | 59 ++
1 file changed, 59 insertions(+)
create mode 100644 examples
This patch add the configuration file for l2fwd example. It
includes commands to build the packet processing stage (pipeline),
defining action, add rules to its table, etc.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Kevin Laatz
---
examples/ip_pipeline/exa
Add example to illustrate the pipeline functioning with TAP
interface.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Kevin Laatz
---
examples/ip_pipeline/examples/tap.cli | 66 +++
1 file changed, 66 insertions(+)
create mode
Add example to illustrate the pipeline functioning with KNI
interface.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Kevin Laatz
---
examples/ip_pipeline/examples/kni.cli | 69 +++
1 file changed, 69 insertions(+)
create mode
Add command to read the ttl stats.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/cli.c | 22 +++
examples/ip_pipeline/pipeline.h | 7
examples/ip_pipeline/thread.c | 84 +
3 files changed,
Add command to update the dscp table for traffic meter and traffic
manager.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/cli.c | 154
examples/ip_pipeline/pipeline.h | 6 ++
examples/ip_pipeline/thread
Add command to read traffic meter stats.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/cli.c | 22 +++
examples/ip_pipeline/pipeline.h | 8
examples/ip_pipeline/thread.c | 88 +
3 files cha
Add commands to configure the traffic meter profile.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/cli.c | 232
examples/ip_pipeline/pipeline.h | 11 ++
examples/ip_pipeline/thread.c | 144
Add command to delete the pipeline table entry.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/cli.c | 145
examples/ip_pipeline/pipeline.h | 9 +++
examples/ip_pipeline/thread.c | 140
Add command to read the pipeline table entry stats.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Fan Zhang
---
examples/ip_pipeline/cli.c | 22 +++
examples/ip_pipeline/pipeline.h | 7
examples/ip_pipeline/thread.c | 84 +
Add commands to add pipeline table entries which contains match and
action part.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/cli.c | 1273 +++
examples/ip_pipeline/pipeline.h | 13 +
examples/ip_pipeline/t
Add commands to enable and disable the pipeline on the thread.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Fan Zhang
---
examples/ip_pipeline/cli.c| 102 +
examples/ip_pipeline/thread.c | 260 +-
e
Add commands to read the pipeline port in, port out
and table stats.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Fan Zhang
---
examples/ip_pipeline/cli.c | 256
examples/ip_pipeline/pipeline.h | 18 +++
exampl
Add commands to enable and disable the pipeline ports.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Fan Zhang
---
examples/ip_pipeline/cli.c | 112 +++
examples/ip_pipeline/pipeline.h | 8 ++
examples/ip_pipeline/thread.c | 1
Add threads data structure and initialisation functions to run
the pipeline.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/Makefile| 2 +-
examples/ip_pipeline/main.c | 8 ++
examples/ip_pipeline/meson.build | 1 +
examples/ip_pipeline
Add runtime thread functions for the pipeline.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/main.c | 6 ++
examples/ip_pipeline/thread.c | 193 ++
examples/ip_pipeline/thread.h | 5 +-
3 files changed, 2
Add pipeline object implementation to the application.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/Makefile| 1 +
examples/ip_pipeline/cli.c | 786 +
examples/ip_pipeline/cli.h | 2 -
examples/ip_
Add action profile object implementation to the application.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Fan Zhang
---
examples/ip_pipeline/Makefile| 3 +-
examples/ip_pipeline/cli.c | 309 +++
examples/ip_pip
Add kni object implementation to the application.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Kevin Laatz
---
examples/ip_pipeline/Makefile| 1 +
examples/ip_pipeline/cli.c | 65 +++
examples/ip_pipeline/kni.c | 165 ++
Add tap object implementation to the application
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Kevin Laatz
---
examples/ip_pipeline/Makefile| 1 +
examples/ip_pipeline/cli.c | 32 +
examples/ip_pipeline/main.c | 8
examples/i
Add swq object implementation to the application.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Kevin Laatz
---
examples/ip_pipeline/Makefile| 1 +
examples/ip_pipeline/cli.c | 55 +
examples/ip_pipeline/main.c | 8
Add traffic manager object implementation to the application.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/Makefile| 1 +
examples/ip_pipeline/cli.c | 360 +++
examples/ip_pipeline/main.c | 8 +
Add link object implementation to the application.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Fan Zhang
---
examples/ip_pipeline/Makefile| 1 +
examples/ip_pipeline/cli.c | 122 ++
examples/ip_pipeline/link.c | 268
CLI interface allowing connectivity with external agent(e.g. telnet,
netcat, Python script, etc) is added to the application.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/Makefile| 4 +-
examples/ip_pipeline/cli.c | 85 ++
examp
Add mempool object implementation to the application.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
Signed-off-by: Fan Zhang
---
examples/ip_pipeline/Makefile| 1 +
examples/ip_pipeline/cli.c | 109 ++-
examples/ip_pipeline/co
Add implementation of stats read action
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_pipeline_version.map | 1 +
lib/librte_pipeline/rte_table_action.c | 112 ++-
lib/librte_pipeline/rte_table_action.h | 78 +++
3 files cha
Add implementation of timestamp action.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_pipeline_version.map | 1 +
lib/librte_pipeline/rte_table_action.c | 79 +++-
lib/librte_pipeline/rte_table_action.h | 31 +++
3 files changed, 110
Add implementation of Network Address Translation(NAT) action.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_table_action.c | 162 +
lib/librte_pipeline/rte_table_action.h | 39
2 files changed, 201 insertions(+)
diff --git a/lib/librte
Add API to specify action related parameters such as action
handler, table entry data size, etc. for the pipeline table.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_pipeline_version.map | 1 +
lib/librte_pipeline/rte_table_action.c | 132 ++-
li
Add implementation of ttl update action.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_pipeline_version.map | 1 +
lib/librte_pipeline/rte_table_action.c | 155 +++
lib/librte_pipeline/rte_table_action.h | 66
3 files changed,
Add traffic metering action implementation.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/Makefile | 3 +-
lib/librte_pipeline/meson.build | 2 +-
lib/librte_pipeline/rte_pipeline_version.map | 4 +
lib/librte_pipeline/rte_table_action.c | 63
Add implementation of different type of packet encap
such as vlan, qinq, mpls, pppoe, etc.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_table_action.c | 440 -
lib/librte_pipeline/rte_table_action.h | 129 ++
2 files changed, 568 insertio
Add implementation of traffic manager action.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/Makefile | 2 +-
lib/librte_pipeline/meson.build| 2 +-
lib/librte_pipeline/rte_table_action.c | 130 -
lib/librte_pipeline/rte_table_act
This API provides a common set of actions for pipeline tables to speed up
application development.
Each match-action rule added to a pipeline table has associated data
that stores the action context. This data is input to the table
action handler called for every input packet that hits the rule as
Refactored the IP pipeline application. As result, the code base
size (lines of code) reduces by ~60%.
1. Moved table actions into the librte_pipeline library. As result,
the pre-fabricated pipelines from the application pipeline folder
were removed. The flexibility is greatly improved, as n
Hi Lee,
Thanks for investigating this.
> -Original Message-
> From: Lee Roberts [mailto:lee.robe...@hpe.com]
> Sent: Friday, March 9, 2018 6:01 PM
> To: Griffin, John ; Trahe, Fiona
> ; Jain, Deepak K
>
> Cc: dev@dpdk.org; Lee Roberts
> Subject: [PATCH] assign QAT cryptodev to correct N
rte_cryptodev_pmd_init_params should use NUMA node of the QAT device
for its socket_id rather than the socket_id of the initializing process.
Signed-off-by: Lee Roberts
---
drivers/crypto/qat/rte_qat_cryptodev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/crypto/q
Use existing defines instead of hardcoded vales.
Signed-off-by: Ferruh Yigit
---
drivers/net/dpaa/dpaa_ethdev.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/dpaa/dpaa_ethdev.c b/drivers/net/dpaa/dpaa_ethdev.c
index 9b69ef456..db493648a 100644
--- a/drivers/
Intention of the logic is:
If ETH_LINK_SPEED_FIXED is set in dev_conf, set link_autoneg to
ETH_LINK_FIXED, else set it to ETH_LINK_AUTONEG
ETH_LINK_SPEED_FIXED value is 1, and ETH_LINK_FIXED is 0;
Current logic is broken, fix it according above values.
Fixes: 48de41ca11f0 ("net/avf: enable link
Please ignore my comment,
I just checked that you have added a patch to convert the license to SPDX.
However, it is not the best way. A new patchset should have this change in the
individual patches itself.
Regards,
Hemant
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.or
Pass an rte_driver to the RTE_PMD_REGISTER_CRYPTO_DRIVER macro
rather than an unspecified container which holds an rte_driver.
All the macro actually needs is the rte_driver, not the
container holding it.
This paves the way for a later patch in which a driver
will be registered which does not natur
Hi Thomas,
>
> ping
>
> 01/03/2018 15:15, Thomas Monjalon:
> > 01/03/2018 07:10, Hemant Agrawal:
> > > On 2/28/2018 8:14 PM, Bruce Richardson wrote:
> > > > On Tue, Feb 27, 2018 at 10:55:52PM +0530, Hemant Agrawal wrote:
> > > >> +includes +=
> > > >> +include_directories('../../../lib/librte_ea
Hi Ravi,
Since 18.02, DPDK community will prefer all new submission to use SPDX
licensing tags.
Regards,
Hemant
On 3/9/2018 2:05 PM, Ravi Kumar wrote:
Signed-off-by: Ravi Kumar
---
..
diff --git a/drivers/crypto/ccp/Makefile b/drivers/crypto/ccp/Makefile
new file mode 100644
index 000.
Hi,
On 3/9/2018 3:35 PM, Ferruh Yigit wrote:
On 3/9/2018 9:39 AM, Tomasz Duszynski wrote:
Signed-off-by: Tomasz Duszynski
---
drivers/net/mrvl/Makefile | 35 ---
drivers/net/mrvl/mrvl_ethdev.c | 36
drivers/net/mrvl/m
Hi Thomas,
>
> As you know the config options should be declared in common_base and
> overwritten in common_linuxapp.
>
> That's why there is no need to add comments in common_linuxapp.
> And some of the options should be only in common_base, like
> CONFIG_RTE_LIBRTE_DPAA_HWDEBUG=n
>
> P
Hi,
As you know the config options should be declared in common_base
and overwritten in common_linuxapp.
That's why there is no need to add comments in common_linuxapp.
And some of the options should be only in common_base, like
CONFIG_RTE_LIBRTE_DPAA_HWDEBUG=n
Please try to move all the
Compression PMD using the Intel ISA-L library.
Features of this PMD:
- Stateless compression and decompression.
- Fixed/Semi-Dynamic compression,
- Supports 32K sliding window size,
- ISA-L levels 0 to 3,
- Adler32 & CRC32 checksums.
Signed-off-by: Lee Daly
---
This patch has de
ping
01/03/2018 15:15, Thomas Monjalon:
> 01/03/2018 07:10, Hemant Agrawal:
> > On 2/28/2018 8:14 PM, Bruce Richardson wrote:
> > > On Tue, Feb 27, 2018 at 10:55:52PM +0530, Hemant Agrawal wrote:
> > >> +includes += include_directories('../../../lib/librte_eal/linuxapp/eal')
> > >
> > > Is this n
Hi,
In DPDK 17.11, the ethdev offloads API has changed.
A dozen drivers are not yet converted to this new API.
We are in a transition period which is planned to close with
this 18.05 release.
As a PMD maintainer or contributor, you can improve your karma
by converting your PMD in the next few wee
Introduce new testpmd commands to load/unload RX/TX BPF-based filters.
Signed-off-by: Konstantin Ananyev
---
app/test-pmd/bpf_sup.h | 25 +
app/test-pmd/cmdline.c | 146 +
2 files changed, 171 insertions(+)
create mode 100644 app/test-pmd
Add few simple eBPF programs as an example.
Signed-off-by: Konstantin Ananyev
---
test/bpf/dummy.c | 20 ++
test/bpf/mbuf.h | 556 +++
test/bpf/t1.c| 53 ++
test/bpf/t2.c| 30 +++
test/bpf/t3.c| 36
5 files changed, 69
Introduce API to install BPF based filters on ethdev RX/TX path.
Current implementation is pure SW one, based on ethdev RX/TX
callback mechanism.
Signed-off-by: Konstantin Ananyev
---
lib/librte_bpf/Makefile| 2 +
lib/librte_bpf/bpf_pkt.c | 524 +++
Signed-off-by: Konstantin Ananyev
---
lib/librte_bpf/Makefile |3 +
lib/librte_bpf/bpf.c |4 +
lib/librte_bpf/bpf_jit_x86.c | 1329 ++
3 files changed, 1336 insertions(+)
create mode 100644 lib/librte_bpf/bpf_jit_x86.c
diff --git a/li
librte_bpf provides a framework to load and execute eBPF bytecode
inside user-space dpdk based applications.
It supports basic set of features from eBPF spec
(https://www.kernel.org/doc/Documentation/networking/filter.txt).
Not currently supported features:
- JIT
- cBPF
- tail-pointer call
- e
BPF is used quite intensively inside Linux (and BSD) kernels
for various different purposes and proved to be extremely useful.
BPF inside DPDK might also be used in a lot of places
for a lot of similar things.
As an example to:
- packet filtering/tracing (aka tcpdump)
- packet classification
- st
On 3/9/2018 4:13 PM, Ferruh Yigit wrote:
> On 3/9/2018 8:42 AM, Ravi Kumar wrote:
>> Signed-off-by: Ravi Kumar
>
> <...>
>
>> diff --git a/drivers/net/axgbe/Makefile b/drivers/net/axgbe/Makefile
>> new file mode 100644
>> index 000..c8a1e87
>> --- /dev/null
>> +++ b/drivers/net/axgbe/Makefil
On Thu, Mar 08, 2018 at 02:38:37PM +, Burakov, Anatoly wrote:
> On 08-Mar-18 12:12 PM, Bruce Richardson wrote:
> > On Wed, Feb 07, 2018 at 09:58:36AM +, Anatoly Burakov wrote:
> > > During lcore scan, find maximum socket ID and store it. This will
> > > break the ABI, so bump ABI version.
>
On 3/9/2018 8:42 AM, Ravi Kumar wrote:
> Signed-off-by: Ravi Kumar
<...>
> diff --git a/drivers/net/axgbe/Makefile b/drivers/net/axgbe/Makefile
> new file mode 100644
> index 000..c8a1e87
> --- /dev/null
> +++ b/drivers/net/axgbe/Makefile
> @@ -0,0 +1,146 @@
> +#
> +# Copyright (c) 2017 Ad
On 3/8/2018 2:46 AM, John Daley wrote:
> V2: rebase, submit as patchset instead of individual patches so they
> apply correctly.
> V3: try again submitting patches one at a time so they are applied
> in order (tester seems to be applying patches in order received
> instead of looking at patch ID).
On 3/9/2018 3:51 PM, Ananyev, Konstantin wrote:
>
> Hi everyone,
>
>> -Original Message-
>> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ferruh Yigit
>> Sent: Friday, March 9, 2018 3:04 PM
>> To: John Daley
>> Cc: dev@dpdk.org; Hyong Youb Kim
>> Subject: Re: [dpdk-dev] [PATCH v3
Hi everyone,
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ferruh Yigit
> Sent: Friday, March 9, 2018 3:04 PM
> To: John Daley
> Cc: dev@dpdk.org; Hyong Youb Kim
> Subject: Re: [dpdk-dev] [PATCH v3 03/10] net/enic: heed the requested max Rx
> packet size
>
On 3/9/2018 3:16 PM, Neil Horman wrote:
> On Fri, Mar 09, 2018 at 01:00:35PM +, Ferruh Yigit wrote:
>> On 3/9/2018 12:36 PM, Neil Horman wrote:
>>> On Fri, Mar 09, 2018 at 11:25:31AM +, Ferruh Yigit wrote:
"struct rte_eth_rxtx_callback" is defined as internal data structure and
us
Signed-off-by: Rosen Xu
---
drivers/raw/ifpga_rawdev/Makefile | 63 +++
drivers/raw/ifpga_rawdev/ifpga_rawdev.c| 472 +
drivers/raw/ifpga_rawdev/ifpga_rawdev.h| 38 ++
drivers/raw/ifpga_rawdev/ifpga_rawdev_example.c| 99 +
..
Signed-off-by: Rosen Xu
---
drivers/bus/ifpga/Makefile | 64
drivers/bus/ifpga/ifpga_bus.c | 573
drivers/bus/ifpga/ifpga_common.c| 154
drivers/bus/ifpga/ifpga_common.h| 25 ++
drivers/bus/ifpga/i
Signed-off-by: Rosen Xu
---
lib/librte_eal/common/eal_common_bus.c | 14 +-
1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/lib/librte_eal/common/eal_common_bus.c
b/lib/librte_eal/common/eal_common_bus.c
index 3e022d5..e3bcebe 100644
--- a/lib/librte_eal/common/eal_comm
Signed-off-by: Rosen Xu
---
lib/librte_eal/common/eal_common_options.c | 8 +++-
lib/librte_eal/common/eal_options.h| 2 ++
2 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/lib/librte_eal/common/eal_common_options.c
b/lib/librte_eal/common/eal_common_options.c
index 9f2f
With Partial Reconfigure(PR) parts of Bitstream, Field Programmable Gate
Array(FPGA) not only provides one kinds of accelerator but also provides many
types of accelerators at the same time.
How DPDK fully support FPGA?
- We use Rawdev to provide FPGA PR
- DPDK Driver will not bind to PCI Devi
Thanks a lot Rivet, I have modified it, pls see my newest patch.
-Original Message-
From: Gaëtan Rivet [mailto:gaetan.ri...@6wind.com]
Sent: Tuesday, March 06, 2018 18:06
To: Xu, Rosen
Cc: dev@dpdk.org; Doherty, Declan ; Zhang, Tianfei
Subject: Re: [dpdk-dev] [RFC 1/4] drivers/bus/ifpg
On Fri, Mar 09, 2018 at 01:00:35PM +, Ferruh Yigit wrote:
> On 3/9/2018 12:36 PM, Neil Horman wrote:
> > On Fri, Mar 09, 2018 at 11:25:31AM +, Ferruh Yigit wrote:
> >> "struct rte_eth_rxtx_callback" is defined as internal data structure and
> >> used as named opaque type.
> >>
> >> So the f
On 3/8/2018 2:46 AM, John Daley wrote:
> From: Hyong Youb Kim
>
> Currently, enic completely ignores the requested max Rx packet size
> (rxmode.max_rx_pkt_len). The desired behavior is that the NIC hardware
> drops packets larger than the requested size, even though they are
> still smaller than
On 3/8/2018 2:46 AM, John Daley wrote:
> From: Hyong Youb Kim
>
> Currently, when more than 1 receive queues are configured, the driver
> always enables RSS with the driver's own default hash type, key, and
> RETA. The user is unable to change any of the RSS settings. Address
> this by implementi
1 - 100 of 182 matches
Mail list logo
