12/10/2018 06:12, Jerin Jacob:
> -Original Message-
> > Date: Fri, 12 Oct 2018 10:24:16 +0800
> > From: Chao Zhu
> > To: 'Jerin Jacob'
> > CC: dev@dpdk.org, tho...@monjalon.net, gowrishanka...@linux.vnet.ibm.com,
> > ola.liljed...@arm.com
> > Subject: 答复: [dpdk-dev] [PATCH] eal/ppc64: ad
From: Dharmik Thakkar
Unit tests to check for hash lookup perf with lock-free enabled and
with lock-free disabled.
Unit tests performed with readers running in parallel with writers.
Tests include:
- hash lookup on existing keys with:
- hash add causing NO key-shifts of existing keys in the t
Add the flag to enable reader-writer concurrency during
run time. The rte_hash_del_xxx APIs do not free the keystore
element when this flag is enabled. Hence a new API,
rte_hash_free_key_with_position, to free the key store element
is added.
Signed-off-by: Honnappa Nagarahalli
Reviewed-by: Gavin
rte_hash_lookup_xxx APIs return the index of the element in
the key store. Application(reader) can use that index to reference
other data structures in its scope. Because of this, the
index should not be recycled till the application completes
using the index.
RTE_HASH_EXTRA_FLAGS_RECYCLE_ON_DEL is
This patch has dependency on the following patches in the order:
http://patchwork.dpdk.org/cover/45611/
http://patchwork.dpdk.org/project/dpdk/list/?series=1822
Currently, reader-writer concurrency problems in rte_hash are
addressed using reader-writer locks. Use of reader-writ
Reader-writer concurrency issue, caused by moving the keys
to their alternative locations during key insert, is solved
by introducing a global counter(tbl_chng_cnt) indicating a
change in table.
Signed-off-by: Honnappa Nagarahalli
Reviewed-by: Gavin Hu
Reviewed-by: Ola Liljedahl
Reviewed-by: St
Correct the key store array element alignment. This is required to
make 'pdata' in 'struct rte_hash_key' align on the correct boundary.
Signed-off-by: Honnappa Nagarahalli
Reviewed-by: Gavin Hu
Reviewed-by: Ola Liljedahl
Reviewed-by: Steve Capper
---
lib/librte_hash/rte_cuckoo_hash.c | 4 +++-
Only race condition that can occur is - using the key store element
before the key write is completed. Hence, while inserting the element
the release memory order is used. Any other race condition is caught
by the key comparison. Memory orderings are added only where needed.
For ex: reads in the w
RW concurrency is required with single writer and multiple reader
usecase as well. Hence, multi-writer should not be enabled by default when
RW concurrency is enabled.
Fixes: f2e3001b53ec ("hash: support read/write concurrency")
Cc: yipeng1.w...@intel.com
Signed-off-by: Honnappa Nagarahalli
Revi
-Original Message-
> Date: Fri, 12 Oct 2018 10:24:16 +0800
> From: Chao Zhu
> To: 'Jerin Jacob'
> CC: dev@dpdk.org, tho...@monjalon.net, gowrishanka...@linux.vnet.ibm.com,
> ola.liljed...@arm.com
> Subject: 答复: [dpdk-dev] [PATCH] eal/ppc64: add support for rte pause
> X-Mailer: Microsoft
-邮件原件-
发件人: Jerin Jacob
发送时间: 2018年10月7日 14:19
收件人: Chao Zhu
抄送: dev@dpdk.org; tho...@monjalon.net; gowrishanka...@linux.vnet.ibm.com;
ola.liljed...@arm.com; Jerin Jacob
主题: [dpdk-dev] [PATCH] eal/ppc64: add support for rte pause
Add support for rte_pause() implementation for ppc64.
S
+
+ if (get_freq_index(LOW) > total_avail_freqs[i])
+ return -1;
+
+ if (rte_get_master_lcore() != i) {
+ w->wrk_stats[i].lcore_id = i;
+ set_policy(&w->wrk_stats[i], policy);
+ }
+ }
On 2018年10月11日 22:22, Tiwei Bie wrote:
The notification can't be disabled in packed ring when
application tries to disable notification, because the
device event flags field is overwritten by an unexpected
value. This patch fixes this issue.
Fixes: b1cce26af1dc ("vhost: add notification for p
In the devargs syntax for device representors, it is possible to add
several devices at once: -w dbdf,representor=[0-3]
It will become a more frequent case when introducing wildcards
and ranges in the new devargs syntax.
If a devargs string is provided for probing, and updated with a bigger
range
The PCI mapping requires to know the PCI driver to use,
even before the probing is done. That's why the PCI driver is
referenced early inside the PCI device structure. See
commit 1d20a073fa5e ("bus/pci: reference driver structure before mapping")
However the rte_driver does not need to be referenc
This is a follow-up of an idea presented at Dublin
during the "hotplug talk".
The idea is to ease probing of range of ports attached
to the same rte_device.
I becomes possible to allow probing again the same device
but with a bigger range of ports in the devargs.
Instead of adding a parameter to
The function rte_dev_is_probed() is added in order to improve semantic
and enforce proper check of the probing status of a device.
It will answer this rte_device query:
Is it already successfully probed or not?
Signed-off-by: Thomas Monjalon
Reviewed-by: Andrew Rybchenko
---
drivers/bus/ifpga/
The helper rte_eth_dma_zone_reserve() is called by PMDs
when probing a new port.
It creates a new memzone with an unique name.
The name of this memzone was using the name of the driver
doing the probe.
In order to avoid assigning the driver before the end of the probing
(next patch), the driver na
On Thu, 11 Oct 2018 20:57:52 +0100
Ferruh Yigit wrote:
> +/*
> + * Wait until a lcore finished its job by sleeping.
> + * Sleep time will be times of 'usec'
> + */
> +int
> +rte_eal_wait_lcore_sleep(unsigned slave_id, size_t usec)
> +{
> + if (lcore_config[slave_id].state == WAIT)
> +
A Kbuild is also included to allow users to use DKMS natively without
additional code.
Signed-off-by: Luca Boccassi
---
build-tested on debian sid am64
kernel/linux/kni/Kbuild | 8 ++
kernel/linux/kni/meson.build | 51
kernel/linux/meson.build
From: Nithin Dabilpuram
Fix missing Tx outer udp checksum flag name
Fixes: e1b1ae51877c ("ethdev: add Tx offload outer UDP checksum definition")
Signed-off-by: Nithin Dabilpuram
Acked-by: Jerin Jacob
---
This patch is based on next-net tree. We could stash this patch.
---
lib/librte_mbuf/r
Fix missing PKT_TX_UDP_SEG ol_flag name and list updatation.
Fixes: 6d18505efaa6 ("vhost: support UDP Fragmentation Offload")
Cc: sta...@dpdk.org
Signed-off-by: Jerin Jacob
---
lib/librte_mbuf/rte_mbuf.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/lib/librte_mbuf/rte_mbuf.c b/lib/libr
This is to prevent sample applications to do busy wait while waiting for
worker threads to terminate. Should save cycles on master core.
By default a 1ms wait interval used.
Signed-off-by: Ferruh Yigit
---
examples/bbdev_app/main.c | 2 +-
examples/distributor/Makefile
It is common that sample applications call rte_eal_wait_lcore() while
waiting for worker threads to be terminated.
Mostly master lcore keeps waiting in this function.
The waiting app for termination is not a time critical task, app can
prefer a sleep version of the waiting to consume less cycles.
While debugging some virtio driver issues, saw:
Invalid port_id=3
but it was not clear which function was logging this because the
same log is being done in multiple places in ethdev.
Trivial fix is to prefix with function name as is done in other
drivers.
Signed-off-by: Stephen Hemminger
On 10/11/2018 3:51 PM, Andrew Rybchenko wrote:
> From: Ivan Malov
>
> Isolated mode prevents global RSS from being enabled and configured.
> However, an application may need to query default RSS key and hash
> functions when a flow rule with RSS action is added which does not
> contain custom RSS
> -Original Message-
> From: Trahe, Fiona
> Sent: Thursday, October 11, 2018 7:14 PM
> To: dev@dpdk.org
> Cc: akhil.go...@nxp.com; sta...@dpdk.org; Jozwiak, TomaszX
> ; Cel, TomaszX ;
> Trahe, Fiona
> Subject: [PATCH v3] drivers/qat: fix failure to create PMD
>
> If QAT crypto pmd failed
On 10/11/2018 3:49 PM, Andrew Rybchenko wrote:
> From: Ivan Malov
>
> Earlier a patch was made to support change of Rx queue
> number. That patch added goto label in wrong place
> because reconfiguration with the same number of queues
> results in skipping not only queue init but also RSS
> setti
I'm testing your series, and it gets stuck after 256 packets in transmit
path. When it happens, descs flags indicate it has been made available
by the driver (desc->flags = 0x80), but it is not consistent with the
expected wrap counter value (0).
Not sure this is the root cause, but it seems be
If QAT crypto pmd failed to be created due to reaching MAX
cryptodevs it prevented QAT comp PMD being created. And vice versa.
Change to warning in these cases and allow the other PMD to be created.
Fixes: c0c90bc4cade ("compress/qat: add create and destroy functions")
Cc: sta...@dpdk.org
Signed-
> On Oct 11, 2018, at 5:12 AM, Dekel Peled wrote:
>
> This patch adds glue functions for operations:
> - Create packet reformat (encap/decap) flow action.
> - Destroy flow action.
>
> The new operations depend on HAVE_IBV_FLOW_DV_SUPPORT.
>
> Signed-off-by: Dekel Peled
> ---
> drivers/net/ml
Enable dynamic huffman encoding in the QAT comp PMD.
Signed-off-by: Tomasz Jozwiak
Signed-off-by: Fiona Trahe
---
v3 changes:
- reverted to 1 buffer per intermediate buffer sgl
v2 changes:
- allocate 2 buffers per intermediate buffer sgl
- Compile out trace for debugging intermediate buffer
This patch adds telemetry as a dependecy to all applications. Without these
changes, the --telemetry flag will not be recognised and applications will
fail to run if they want to enable telemetry.
Signed-off-by: Bruce Richardson
Signed-off-by: Kevin Laatz
---
app/meson.build |
From: Ciara Power
This patch adds all documentation for telemetry.
A description on how to use the Telemetry API with a DPDK
application is given in this document.
It also adds the MAINTAINERS file entry for telemetry.
Signed-off-by: Ciara Power
Signed-off-by: Brian Archbold
Signed-off-by: K
From: Ciara Power
This patch adds a python script which can be used as a demo
client. The script is interactive and will allow the user to
register, request statistics, and unregister.
To run the script, an argument for the client file path must
be passed in: "python telemetry_client.py ".
This
From: Ciara Power
This patch adds functionality to enable/disable the selftest.
This functionality will be extended in future to make the
enabling/disabling more dynamic and remove this 'hardcoded' approach. We
are temporarily using this approach due to the design changes (vdev vs eal)
made to t
From: Ciara Power
This patch adds all tests for the Telemetry API.
The tests added include a parser test, selftest, and socket
messaging tests.
The parser tests pass valid and invalid messages to the parser
to ensure the correct return values are received.
The selftest tests basic functions in t
From: Ciara Power
This patch adds functionality to create a JSON message in
order to send it to a client socket.
When stats are requested by a client, they are retrieved from
the metrics library and encoded in JSON format.
Signed-off-by: Ciara Power
Signed-off-by: Brian Archbold
Signed-off-by
From: Ciara Power
This patch adds functionality to update the statistics in
the metrics library with values from the ethdev stats.
Values need to be updated before they are encoded into a JSON
message and sent to the client that requested them. The JSON encoding
will be added in a subsequent pat
From: Ciara Power
This patch adds the parser file. This is used to parse any
messages that are received on any of the client sockets.
Currently, the unregister functionality works using the parser.
Functionality relating to getting statistic values for certain ports
will be added in a subsequent
From: Ciara Power
This patch introduces clients to the telemetry API.
When a client makes a connection through the initial telemetry
socket, they can send a message through the socket to be
parsed. Register messages are expected through this socket, to
enable clients to register and have a clien
This patch makes the eal_get_runtime_dir() API public so it can be used
from outside EAL.
Signed-off-by: Kevin Laatz
---
Note: I have added rte_eal_get_runtime_dir() to the 18.11 version in the
.map file instead of the EXPERIMENTAL section as the function already
existed, we just renamed it and
This commit adds infrastructure to EAL that allows an application to
register it's init function with EAL. This allows libraries to be
initialized at the end of EAL init.
This infrastructure allows libraries that depend on EAL to be initialized
as part of EAL init, removing circular dependency iss
From: Ciara Power
This patch adds the infrastructure and initial code for the telemetry
library.
The telemetry init is registered with eal_init(). We can then check to see
if --telemetry was passed as an eal flag. If --telemetry was parsed, then
we call telemetry init at the end of eal init.
Co
This patchset introduces a Telemetry library for DPDK Service Assurance.
This library provides an easy way to query DPDK Ethdev metrics.
The telemetry library provides a method for a service assurance component
to retrieve metrics from a DPDK packet forwarding application.
Communicating from the s
From: Ciara Power
This patch adds the telemetry UNIX socket. It is used to
allow connections from external clients.
On the initial connection from a client, ethdev stats are
registered in the metrics library, to allow for their retrieval
at a later stage.
Signed-off-by: Ciara Power
Signed-off-
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Cristian Dumitrescu
> Sent: Thursday, October 11, 2018 12:41 PM
> To: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH v4 1/8] pipeline: add table action for packet tag
>
> This patch introduces the packet tag table ac
Hi Ferruh
> >> Subject: Re: [dpdk-dev] [PATCH v4 3/3] app/testpmd: set packet dump
> >> based on verbosity level
> >>
> >> On 10/7/2018 8:38 AM, Raslan Darawsheh wrote:
> >>> when changing verbosity level it will configure rx/tx callbacks to
> >>> dump packets based on the verbosity value as foll
On 10/10/2018 3:39 PM, Raslan Darawsheh wrote:
> @@ -2082,6 +2214,14 @@ rte_pmd_tap_probe(struct rte_vdev_device *dev)
> TAP_LOG(NOTICE, "Initializing pmd_tap for %s as %s",
> name, tap_name);
>
> + /* Register IPC feed callback */
> + ret = rte_mp_action_register(TAP_
On 10/10/2018 3:39 PM, Raslan Darawsheh wrote:
> fd's cannot be shared between processes, and each process need to have
> it's own fd's pointer.
>
> Signed-off-by: Raslan Darawsheh
> ---
> drivers/net/tap/rte_eth_tap.c | 93
> +--
> drivers/net/tap/rte_et
On 11.10.2018 12:24, Maxime Coquelin wrote:
> Return of message handling has now changed to an enum that can
> take non-negative value that is not zero in case a reply is
> needed. But the code checking the variable afterwards has not
> been updated, leading to success messages handling being
> tre
11/10/2018 17:41, Andrew Rybchenko:
> On 10/11/18 6:29 PM, Thomas Monjalon wrote:
> > 11/10/2018 15:15, Andrew Rybchenko:
> >> On 10/11/18 3:59 PM, Thomas Monjalon wrote:
> >>> 11/10/2018 13:54, Andrew Rybchenko:
> On 10/11/18 2:45 PM, Thomas Monjalon wrote:
> > 11/10/2018 12:53, Andrew Ry
On 11.10.2018 12:24, Maxime Coquelin wrote:
> As soon as some ancillary data (fds) are received, it is copied
> without checking its length.
>
> This patch adds the number of fds received to the message,
> which is set in read_vhost_message().
>
> This is preliminary work to support sending fds t
On 10/11/2018 4:24 PM, Iremonger, Bernard wrote:
> Hi Feruh,
>
>> -Original Message-
>> From: Yigit, Ferruh
>> Sent: Thursday, October 11, 2018 4:00 PM
>> To: Raslan Darawsheh ; Wu, Jingjing
>>
>> Cc: Thomas Monjalon ; dev@dpdk.org; Shahaf Shuler
>> ; Xueming(Steven) Li ; Ori
>> Kam ; jer
On 10/11/18 6:29 PM, Thomas Monjalon wrote:
11/10/2018 15:15, Andrew Rybchenko:
On 10/11/18 3:59 PM, Thomas Monjalon wrote:
11/10/2018 13:54, Andrew Rybchenko:
On 10/11/18 2:45 PM, Thomas Monjalon wrote:
11/10/2018 12:53, Andrew Rybchenko:
On 10/8/18 1:09 AM, Thomas Monjalon wrote:
The PCI
11/10/2018 15:15, Andrew Rybchenko:
> On 10/11/18 3:59 PM, Thomas Monjalon wrote:
> > 11/10/2018 13:54, Andrew Rybchenko:
> >> On 10/11/18 2:45 PM, Thomas Monjalon wrote:
> >>> 11/10/2018 12:53, Andrew Rybchenko:
> On 10/8/18 1:09 AM, Thomas Monjalon wrote:
> > The PCI mapping requires to
Hi Feruh,
> -Original Message-
> From: Yigit, Ferruh
> Sent: Thursday, October 11, 2018 4:00 PM
> To: Raslan Darawsheh ; Wu, Jingjing
>
> Cc: Thomas Monjalon ; dev@dpdk.org; Shahaf Shuler
> ; Xueming(Steven) Li ; Ori
> Kam ; jerin.ja...@caviumnetworks.com;
> david.march...@6wind.com; Irem
On 10/11/2018 04:22 PM, Tiwei Bie wrote:
The notification can't be disabled in packed ring when
application tries to disable notification, because the
device event flags field is overwritten by an unexpected
value. This patch fixes this issue.
Fixes: b1cce26af1dc ("vhost: add notification for
On 10/7/2018 8:38 AM, Raslan Darawsheh wrote:
> when changing verbosity level it will configure rx/tx callbacks to dump
> packets based on the verbosity value as following:
> 1- dump only received packets:
>testpmd> set verbose 1
> 2- dump only sent packets:
>testpmd> set ve
On 10/7/2018 8:38 AM, Raslan Darawsheh wrote:
> add new rx/tx callback functions to be used for dumping the packets.
>
> Signed-off-by: Raslan Darawsheh
<...>
> +uint16_t
> +dump_rx_pkts(uint16_t port_id, uint16_t queue, struct rte_mbuf *pkts[],
> + uint16_t nb_pkts, __rte_unused uint1
On 10/7/2018 8:38 AM, Raslan Darawsheh wrote:
> verbosity for the received/sent packets is needed in all of the
> forwarding engines so moving it to be in a separate function
+1, this is good idea.
> ---
> changes in v3:
> - add util.c in the mason.build file
> - restore missing check
> -Original Message-
> From: Yongseok Koh
> Sent: Thursday, October 4, 2018 2:48
> To: Slava Ovsiienko
> Cc: dev@dpdk.org; Shahaf Shuler
> Subject: Re: [dpdk-dev] [PATCH] net/mlx5: flow counters support on the
> Linux-rdma v19 base
>
> On Wed, Oct 03, 2018 at 03:29:12PM +, Slava Ovsi
From: Ivan Malov
If global RSS is not enabled in the multiqueue mode setting,
it will not be possible to change RSS configuration. However,
querying default RSS settings should be possible in any case since
it may be needed by RTE flow API users to find out what RSS settings
will be used by defau
From: Ivan Malov
Isolated mode prevents global RSS from being enabled and configured.
However, an application may need to query default RSS key and hash
functions when a flow rule with RSS action is added which does not
contain custom RSS key or hash function choice. In this case
global RSS key a
From: Ivan Malov
Earlier a patch was made to support change of Rx queue
number. That patch added goto label in wrong place
because reconfiguration with the same number of queues
results in skipping not only queue init but also RSS
settings. If a user configures device with RSS multiqueue
mode and
The notification can't be disabled in packed ring when
application tries to disable notification, because the
device event flags field is overwritten by an unexpected
value. This patch fixes this issue.
Fixes: b1cce26af1dc ("vhost: add notification for packed ring")
Cc: sta...@dpdk.org
Signed-off
Below are details and reasoning for proposed changes.
1.rte_cryptodev_sym_session_init()/ rte_cryptodev_sym_session_clear()
operate based on cytpodev device id, though inside
rte_cryptodev_sym_session device specific data is addressed
by driver id (not device id).
That creates a problem wi
On Thu, Oct 11, 2018 at 09:36:48AM -0400, Michael S. Tsirkin wrote:
> On Thu, Oct 11, 2018 at 09:34:06PM +0800, Jason Wang wrote:
> >
> >
> > On 2018年10月11日 21:06, Tiwei Bie wrote:
> > > The notification can't be disabled in packed ring when
> > > application tries to disable notification, becaus
Hi Adrian,
> -Original Message-
> From: Adrien Mazarguil
> Sent: Thursday, October 11, 2018 4:12 PM
> To: Ori Kam
> Cc: Andrew Rybchenko ; Ferruh Yigit
> ; step...@networkplumber.org; Declan Doherty
> ; dev@dpdk.org; Dekel Peled
> ; Thomas Monjalon ; Nélio
> Laranjeiro ; Yongseok Koh
>
On Thu, Oct 11, 2018 at 01:54:58PM +0200, Thomas Monjalon wrote:
> 18/09/2018 12:23, Thomas Monjalon:
> > 18/09/2018 12:15, Bruce Richardson:
> > > On Mon, Sep 17, 2018 at 09:58:59PM +0200, Thomas Monjalon wrote:
> > > > 17/09/2018 21:34, Bruce Richardson:
> > > > > On Mon, Sep 17, 2018 at 06:44:52
Change unit test app to check only for op->status =
RTE_CRYPTO_OP_STATUS_SUCCESS/ERROR instead of calling rsa_verify().
Signed-off-by: Ayuj Verma
Signed-off-by: Shally Verma
---
test/test/test_cryptodev_asym.c | 9 ++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/test/tes
Add tmp buffer to pass to OpenSSL sign API and memcmp output with
original plain text to verify signature match.
Set op->status = RTE_CRYPO_OP_STATUS_ERROR on signature mismatch.
Signed-off-by: Ayuj Verma
Signed-off-by: Akash Saxena
Signed-off-by: Shally Verma
---
drivers/crypto/openssl/rte_op
In lib cryptodev, RSA verify operation inputs plain message text and
corresponding signature and expected to return
RTE_CRYPTO_OP_STATUS_SUCCESS/FAILURE on a signature match/mismatch.
Current OpenSSL PMD RSA verify implementation overrides application passed
sign input by decrypted output which i
Thursday, October 11, 2018 4:22 PM, Jack Min:
> Subject: [PATCH v4] net/mlx5: rewrite IP address UDP/TCP port by E-Switch
>
> Offload the following rte_flow actions by inserting accordingly E-Switch rules
> via TC Flower driver
>
> - RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC
> - RTE_FLOW_ACTION_TYPE_SE
On 10/11, Ferruh Yigit wrote:
>On 10/10/2018 10:14 AM, Xiaolong Ye wrote:
>> As APIs in rte_vdpa.h are public, we need to add doxygen comments
>> to all APIs and structures.
>>
>> Signed-off-by: Xiaolong Ye
>
><...>
>
>> @@ -29,6 +32,9 @@ struct rte_vdpa_dev_addr {
>> };
>> };
>>
>> +/**
On Thu, Oct 11, 2018 at 09:34:06PM +0800, Jason Wang wrote:
>
>
> On 2018年10月11日 21:06, Tiwei Bie wrote:
> > The notification can't be disabled in packed ring when
> > application tries to disable notification, because the
> > device event flags field is overwritten by an unexpected
> > value. Th
On 2018年10月11日 21:06, Tiwei Bie wrote:
The notification can't be disabled in packed ring when
application tries to disable notification, because the
device event flags field is overwritten by an unexpected
value. This patch fixes this issue.
Fixes: b1cce26af1dc ("vhost: add notification for p
On 10/5/2018 1:20 PM, Iremonger, Bernard wrote:
>
>
>> -Original Message-
>> From: Kevin Traynor [mailto:ktray...@redhat.com]
>> Sent: Friday, October 5, 2018 10:55 AM
>> To: Jens Freimann ; dev@dpdk.org
>> Cc: ai...@redhat.com; jan.scheur...@ericsson.com; Richardson, Bruce
>> ; tho...@mo
rte_flow actions:
- RTE_FLOW_ACTION_TYPE_SET_MAC_SRC
- RTE_FLOW_ACTION_TYPE_SET_MAC_DST
added in order to offload to NIC
The rte_flow_itme_eth must be present in rte_flow pattern
Signed-off-by: Xiaoyu Min
Acked-by: Yongseok Koh
Acked-by: Andrew Rybchenko
---
doc/guides/prog_guide/rte_flow.rst
add commands to support following actions:
- RTE_FLOW_ACTION_TYPE_SET_MAC_SRC
- RTE_FLOW_ACTION_TYPE_SET_MAC_DST
Signed-off-by: Xiaoyu Min
Acked-by: Yongseok Koh
---
app/test-pmd/cmdline_flow.c | 50 +
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 8
2
Offload following modify MAC address actions to E-Switch
via TC-Flower driver
- RTE_FLOW_ACTION_TYPE_SET_MAC_SRC
- RTE_FLOW_ACTION_TYPE_SET_MAC_DST
The corresponding rte_flow_item_eth must be present in
rte_flow pattern
Only support modify outer layer MAC address
The example testpmd command is:
This series is for RFC[1] and depends on patch[2]
Patch 1 adds generic MAC address rewrite actions to flow API
Patch 2 adds testpmd commands for that
Patch 3 offloads these actions on Mellanox MLX5 by using E-Switch rule
[1]: https://patches.dpdk.org/patch/44005/
[2]: http://patches.dpdk.org/patc
On 10/10/2018 10:14 AM, Xiaolong Ye wrote:
> As APIs in rte_vdpa.h are public, we need to add doxygen comments
> to all APIs and structures.
>
> Signed-off-by: Xiaolong Ye
<...>
> @@ -29,6 +32,9 @@ struct rte_vdpa_dev_addr {
> };
> };
>
> +/**
> + * vdpa device operations
> + */
> str
rewrite TTL by decrease or just set it directly
it's not necessary to check if the final result
is zero or not
This is slightly different from the one defined
by openflow and more generic
Signed-off-by: Xiaoyu Min
Acked-by: Yongseok Koh
---
doc/guides/prog_guide/rte_flow.rst | 24 +
Offload following modify TTL actions to E-Switch via
TC-Flower driver
- RTE_FLOW_ACTION_TYPE_SET_TTL
- RTE_FLOW_ACTION_TYPE_DEC_TTL
The corresponding IP protocol rte_flow_item_ipv[4|6]
must be present in rte_flow pattern otherwith PMD
return error
The example testpmd commands are:
flow crea
This patch series is for RFC[1] and depends on patch[2]
Patch 1 adds generic TTL rewrite actions to flow API
Patch 2 adds corresponding testpmd commands
Patch 3 implements the offloading logic of E-Switch rules on Mellanox MLX5
[1]: https://patches.dpdk.org/patch/43617/
[2]: http://patches.dpdk.o
add commands which supports following TTL actions:
- RTE_FLOW_ACTION_TYPE_DEC_TTL
- RTE_FLOW_ACTION_TYPE_SET_TTL
Signed-off-by: Xiaoyu Min
Acked-by: Yongseok Koh
---
app/test-pmd/cmdline_flow.c | 34 +
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 5 +++
2 f
Hi Ferruh,
On 11.10.2018 16:11, Ferruh Yigit wrote:
> Hi Igor,
>
> Patchset mostly looks good to me, I put a few comments.
>
> Also I think patch 1/23 & 2/23 can be merged into single commit.
>
> And can you please follow the below format in patch title:
> : ,
>
> like:
>
> from: "net/atlant
Offload the following rte_flow actions by inserting accordingly
E-Switch rules via TC Flower driver
- RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC
- RTE_FLOW_ACTION_TYPE_SET_IPV4_DST
- RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC
- RTE_FLOW_ACTION_TYPE_SET_IPV6_DST
- RTE_FLOW_ACTION_TYPE_SET_TP_SRC
- RTE_FLOW_ACT
On 10/11/2018 03:06 PM, Tiwei Bie wrote:
The notification can't be disabled in packed ring when
application tries to disable notification, because the
device event flags field is overwritten by an unexpected
value. This patch fixes this issue.
Fixes: b1cce26af1dc ("vhost: add notification for
On 10/11/18 3:59 PM, Thomas Monjalon wrote:
11/10/2018 13:54, Andrew Rybchenko:
On 10/11/18 2:45 PM, Thomas Monjalon wrote:
11/10/2018 12:53, Andrew Rybchenko:
On 10/8/18 1:09 AM, Thomas Monjalon wrote:
The PCI mapping requires to know the PCI driver to use,
even before the probing is done. T
Hey Ori,
(removing most of the discussion, I'll only reply to the summary)
On Thu, Oct 11, 2018 at 08:48:05AM +, Ori Kam wrote:
> Hi Adrian,
>
> Thanks for your comments please see my answer below and inline.
>
> Due to a very short time limit and the fact that we have more than
> 4 patches
The notification can't be disabled in packed ring when
application tries to disable notification, because the
device event flags field is overwritten by an unexpected
value. This patch fixes this issue.
Fixes: b1cce26af1dc ("vhost: add notification for packed ring")
Cc: sta...@dpdk.org
Signed-off
On 10/11/2018 11:34 AM, Igor Russkikh wrote:
> Hello DPDK community!
>
> Aquantia would like to contribute PMD for aQtion AQC10X NIC family:
> https://www.aquantia.com/products/aqtion/chips/
> These are 10G ethernet NICs with various features.
>
> We do base this work on parts of the existing nat
This commit adds support for configuring flows destined to the mlx5
eswitch with 'count' action and for querying these counts at runtime.
It is possible to offload an interface flow rules to the hardware
using DPDK flow commands.
With mlx5 it is also possible to offload a limited set of flow rules
This commit refactors tc_flow as a preparation to coming commits
that sends different type of messages and expect differ type of replies
while still using the same underlying routines.
Signed-off-by: Moti Haimovsky
---
drivers/net/mlx5/mlx5.c | 18 +++
drivers/net/mlx5/mlx5.h
The following patches add support in mlx5 PMD for configuring and
reading flow counters from the device e-switch.
Moti Haimovsky (2):
net/mlx5: refactor TC-flow infrastructure
net/mlx5: support e-switch flow count action
drivers/net/mlx5/mlx5.c| 18 +-
drivers/net/mlx5/mlx5.h
On Thu, Oct 11, 2018 at 11:53:12AM +0100, Luca Boccassi wrote:
> On Thu, 2018-10-11 at 12:27 +0200, Thomas Monjalon wrote:
> > 28/08/2018 12:12, Luca Boccassi:
> > > From: Brian Russell
> > >
> > > In virtio_read_caps and vtpci_msix_detect, rte_pci_read_config
> > > returns
> > > the number of by
11/10/2018 13:54, Andrew Rybchenko:
> On 10/11/18 2:45 PM, Thomas Monjalon wrote:
> > 11/10/2018 12:53, Andrew Rybchenko:
> >> On 10/8/18 1:09 AM, Thomas Monjalon wrote:
> >>> The PCI mapping requires to know the PCI driver to use,
> >>> even before the probing is done. That's why the PCI driver is
On 10/11/2018 11:35 AM, Igor Russkikh wrote:
> From: Pavel Belous
>
> VLAN filters and VLAN offloads implementation.
>
> Signed-off-by: Igor Russkikh
> Signed-off-by: Pavel Belous
> ---
> doc/guides/nics/features/atlantic.ini | 2 +
> drivers/net/atlantic/atl_ethdev.c | 159
> +
1 - 100 of 231 matches
Mail list logo
