main changes:
1. Refactor FDIR configure function.
2. Merge flow seg info for tun/non-tun, distinguish inner/outer input_set.
3. Remove redundant segment info.
Zhirun Yan (2):
net/ice: refactor FDIR set conf function
net/ice: merge inner/outer flow seg info for FDIR
drivers/net/ice/ice_eth
For tunnel and non-tunnel packets, it can share the same seg_tun info.
seg_tun[1] can be used for supporting inner fields with tunnel flow rule
or for non-tunnel packets, seg_tun[0] only used for tunnel outer part.
Add outer_input_set to distinguish inner/outer input set. So we can
identify differe
The original set conf function in FDIR was very long. Refactor to
increase readability to make it clearer and allow for more convenient
further changes.
No functional change here.
Signed-off-by: Zhirun Yan
---
drivers/net/ice/ice_fdir_filter.c | 54 ++-
1 file change
> -Original Message-
> From: Jiang, JunyuX
> Sent: Monday, September 7, 2020 17:17
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Yang, Qiming
> ; Sun, GuinanX
> Subject: [PATCH v2 2/5] net/ice: add flow director enabled switch value
>
> From: Guinan Sun
>
> The commit adds fdir_enabled fla
Hi, Steve,
I am also coding on this part for large VF recently, and see that you sent a
fix patch, and I have some questions not quite clear, which are shown below in
inline.
Thanks!
Best Regards,
Xu Ting
> -Original Message-
> From: dev On Behalf Of SteveX Yang
> Sent: Friday, Septe
> -Original Message-
> From: Jiang, JunyuX
> Sent: Monday, September 7, 2020 17:17
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Yang, Qiming
> ; Sun, GuinanX
> Subject: [PATCH v2 3/5] net/ice: support flow mark in AVX path
>
> From: Guinan Sun
>
> Support Flow Director mark ID parsing fro
> -Original Message-
> From: Jiang, JunyuX
> Sent: Monday, September 7, 2020 17:17
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Yang, Qiming
> ; Sun, GuinanX
> Subject: [PATCH v2 5/5] net/ice: remove devargs flow-mark-support
>
> From: Guinan Sun
>
> Remove devargs "flow-mark-support".
P
> -Original Message-
> From: Sun, GuinanX
> Sent: Saturday, September 5, 2020 10:50
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Zhang, Qi Z ;
> Yang, Qiming ; Sun, GuinanX
> ; sta...@dpdk.org; Brandeburg, Jesse
>
> Subject: [PATCH 4/9] net/i40e/base: fix missing function header arguments
>
Please add IPPROTO_ICMP and IPPROTO_ICMPV6 definitions:
#define IPPROTO_IP 0
+#define IPPROTO_ICMP 1 /* Internet Ctrl Message Protocol */
#define IPPROTO_HOPOPTS 0
@@ -17,6 +18,7 @@
#define IPPROTO_AH 51 /* IP6 Auth Header */
+#define IPPROTO_ICMPV6 58 /* Interne
On Tue, Sep 08, 2020 at 12:06:40AM +0200, Thomas Monjalon wrote:
> The first 13 commits of this series are pushed to the main branch,
> making the make-based build an old story.
>
> The last 18 commits (devtools, app and doc) are pending
> for more reviews, especially because the doc rework is
> s
On Mon, Sep 07, 2020 at 10:20:13AM -0700, Stephen Hemminger wrote:
> On Mon, 7 Sep 2020 09:58:27 +0100
> Bruce Richardson wrote:
>
> > On Mon, Sep 07, 2020 at 09:54:29AM +0100, Ferruh Yigit wrote:
> > > On 9/6/2020 4:42 AM, Stephen Hemminger wrote:
> > > > This is an improved version of the set
On Tue, Sep 08, 2020 at 02:14:02AM +0200, Thomas Monjalon wrote:
> On Tue Sep 8, 2020 at 2:50 AM CEST, Thomas Monjalon wrote:
> > As decided in the Technical Board in November 2019,
> > the kernel module igb_uio is moved to the dpdk-kmods repository
> > in the /linux/igb_uio/ directory.
>
> The co
delay_us_sleep_autotest is failing on this patch. To replicate it, I
ran the same test on my system and it did not fail. Can this test be
re-run?
On Fri, Sep 4, 2020 at 11:23 AM Sarosh Arif wrote:
>
> diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
> index 30bee3324..8824ad174 100644
>
Direct crypto data-path service are a set of APIs that especially provided for
the external libraries/applications who want to take advantage of the rich
features provided by cryptodev, but not necessarily depend on cryptodev
operations, mempools, or mbufs in the their data-path implementations.
T
This patch adds data-path service APIs for enqueue and dequeue
operations to cryptodev. The APIs support flexible user-define
enqueue and dequeue behaviors and operation mode.
Signed-off-by: Fan Zhang
Signed-off-by: Piotr Bronowski
---
lib/librte_cryptodev/rte_crypto.h | 9 +
lib/
This patch updates programmer's guide to demonstrate the usage
and limitations of cryptodev symmetric crypto data-path service
APIs.
Signed-off-by: Fan Zhang
---
doc/guides/prog_guide/cryptodev_lib.rst | 90 +
doc/guides/rel_notes/release_20_11.rst | 7 ++
2 files chang
This patch adds the QAT test to use cryptodev symmetric crypto
direct APIs.
Signed-off-by: Fan Zhang
---
app/test/test_cryptodev.c | 461 +++---
app/test/test_cryptodev.h | 7 +
app/test/test_cryptodev_blockcipher.c | 51 ++-
3 files changed, 456 in
This patch updates QAT PMD to add crypto service API support.
Signed-off-by: Fan Zhang
---
drivers/common/qat/Makefile| 1 +
drivers/crypto/qat/meson.build | 1 +
drivers/crypto/qat/qat_sym.h | 13 +
drivers/crypto/qat/qat_sym_hw_dp.c | 947 +
d
> -Original Message-
> From: Guo, Jia
> Sent: Tuesday, September 8, 2020 11:59 AM
> To: Zhang, Qi Z ; Yang, Qiming
>
> Cc: Xu, Ting ; dev@dpdk.org; Zhang, Qi Z
> ; sta...@dpdk.org
> Subject: RE: [dpdk-dev] [PATCH] net/ice/base: fix wrong outer ipv6 ptype table
>
>
> > -Original M
08/09/2020 10:16, Bruce Richardson:
> On Tue, Sep 08, 2020 at 12:06:40AM +0200, Thomas Monjalon wrote:
> > The first 13 commits of this series are pushed to the main branch,
> > making the make-based build an old story.
> >
> > The last 18 commits (devtools, app and doc) are pending
> > for more r
Hello Aman,
On Mon, Sep 7, 2020 at 9:33 PM Aman Kumar wrote:
>
> add build config specific to AMD EPYC platform
>
> Signed-off-by: Aman Kumar
Make support has just been dropped from the main branch.
You will have to rework this series so that this feature is
handled/configured with meson or, ev
Avoid build failures on further restructuring.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc.c | 1 +
drivers/net/sfc/sfc.h | 1 +
drivers/net/sfc/sfc_dp_tx.h| 1 +
drivers/net/sfc/sfc_ef10.h | 2 ++
drivers/net/sfc/s
From: Steve Yang
When receiving the unsupported AQ messages, it's taken as an
error. It's not appropriate and triggers too much unnecessary print.
Fixes: 22b123a36d07 ("net/avf: initialize PMD")
Cc: sta...@dpdk.org
Signed-off-by: Steve Yang
Acked-by: Beilei Xing
Signed-off-by: Andrew Rybchenk
Management event queue polling is required in the case of
MCDI proxy authentication (client driver code).
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc_mcdi.c | 14 --
drivers/net/sfc/sfc_mcdi.h | 3 +++
2 files changed, 15 insertions(+), 2 delet
Network and vDPA drivers share libefx. So, libefx should be moved
to common drivers.
DPDK adaptation of the MCDI interface may be shared as well.
The new common driver name is sfc_efx since it a new home of
libefx base driver. sfc_ prefix is used to make it clear that
it is related to net/sfc (an
Prepare to move MCDI helpers to drivers/common.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc_log.h | 11 ---
drivers/net/sfc/sfc_mcdi.c | 21 -
2 files changed, 16 insertions(+), 16 deletions(-)
diff --git a/drivers/net/sfc/sfc_
Now MCDI helpers interface is independent from network driver and
may be moved into common driver.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc_mcdi.c | 47 +++---
1 file changed, 19 insertions(+), 28 deletions(-)
diff --git
Network driver logging macros depends on sfc_adapter which is
specific to the driver and cannot be used in common code.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc.h| 2 +
drivers/net/sfc/sfc_ethdev.c | 13 ++
drivers/net/sfc/sfc_log.h| 12
Prepare to avoid usage of the adapter context in common MCDI helpers.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc_mcdi.c | 19 +++
drivers/net/sfc/sfc_mcdi.h | 1 +
2 files changed, 12 insertions(+), 8 deletions(-)
diff --git a/drivers/net
MCDI helpers will be moved to common/sfc_efx and it is better
to do dummy renamings first before non-trivial changes.
Existing functionality should be split into common and network
driver specific parts. Prepare to do it.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/ne
This patch series resolves bugs in the event crypto adapter test
application.
Ankur Dwivedi (3):
test/event_crypto_adapter: return error with unsupported mode
test/event_crypto_adapter: fix function arguments
test/event_crypto_adapter: free resources during exit
app/test/test_event_crypto_
The capability of a event device should be checked before creating
a event crypto adapter in a particular mode. The test case returns
error if the mode is not supported.
Signed-off-by: Ankur Dwivedi
---
app/test/test_event_crypto_adapter.c | 30 ++--
1 file changed, 20 in
MC reboot handling is driver specific.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc_mcdi.c | 15 +--
drivers/net/sfc/sfc_mcdi.h | 3 +++
2 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/drivers/net/sfc/sfc_mcdi.c b/drivers/net/sfc
Implement dummy MCDI timeout handling which simply rejects
further MCDI requests.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc_mcdi.c | 15 +--
drivers/net/sfc/sfc_mcdi.h | 1 +
2 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/dri
MCDI helpers will be shared by net and vDPA drivers.
Prepare to move it to common/sfc_efx.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc.h | 23 +---
drivers/net/sfc/sfc_mcdi.c | 1 +
drivers/net/sfc/sfc_mcdi.h | 54 +
sfc_adapter is network driver specific structure which finally
should not be used in shared MCDI helpers interface.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc_mcdi.c | 13 -
1 file changed, 4 insertions(+), 9 deletions(-)
diff --git a/drivers/
Move libefx (base driver) into common driver.
Prepare to add vDPA driver which will use the common driver as well.
Signed-off-by: Andrew Rybchenko
---
MAINTAINERS | 1 +
drivers/common/Makefile | 4 +
drivers/common/meson.build
Net driver should use rte_eth_dma_zone_reserve(), but it is ethdev
specific API which is not available for vDPA.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc_mcdi.c | 46 +++---
drivers/net/sfc/sfc_mcdi.h | 12 ++
2 fi
The resources held by crypto adapter should be freed when the
test suite exits.
Signed-off-by: Ankur Dwivedi
---
app/test/test_event_crypto_adapter.c | 15 +++
1 file changed, 15 insertions(+)
diff --git a/app/test/test_event_crypto_adapter.c
b/app/test/test_event_crypto_adapter.c
The arguments passed to rte_event_crypto_adapter_caps_get() and
rte_event_crypto_adapter_create() are incorrect.
In the rte_event_crypto_adapter_caps_get(), event device id should
be the first argument and cryptodev id should be the second argument.
In the rte_event_crypto_adapter_create(), the ev
These helper will be reused by other libefx consumers, e.g. vDPA
driver.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/Makefile | 1 +
drivers/common/sfc_efx/meson.build| 1 +
.../sfc_efx/rte_common_sfc_efx_version.map|
A temporary session is created for sessionless crypto operations.
rte_cryptodev_sym_session_create() should be used for creating the
temporary session as it initializes the session structure in the
correct way. Also the session should be set to 0 before freeing it.
Fixes: 17ac2a72191b ("crypto/oct
From: Igor Romanov
Tunnel configuration may fail because of insufficient access rights
on a virtual function. Ignore the failure if a tunnel configuration
with empty UDP ports is requested.
Fixes: 17551f6dffcc ("net/sfc/base: add API to control UDP tunnel ports")
Cc: sta...@dpdk.org
Signed-off-
On 9/8/20 12:14 PM, Andrew Rybchenko wrote:
> From: Steve Yang
>
> When receiving the unsupported AQ messages, it's taken as an
> error. It's not appropriate and triggers too much unnecessary print.
>
> Fixes: 22b123a36d07 ("net/avf: initialize PMD")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Steve
08/09/2020 10:25, Bruce Richardson:
> On Tue, Sep 08, 2020 at 02:14:02AM +0200, Thomas Monjalon wrote:
> > On Tue Sep 8, 2020 at 2:50 AM CEST, Thomas Monjalon wrote:
> > > As decided in the Technical Board in November 2019,
> > > the kernel module igb_uio is moved to the dpdk-kmods repository
> > >
Hi Dekel,
On Thu, Aug 6, 2020 at 12:40 PM Dekel Peled wrote:
>
> In existing code the match on tagged/untagged packets is not explicit.
> Recent documentation update [1] describes the different patterns and
> clarifies the intended use of different patterns.
>
> This patch proposes an update to E
On Tue, Sep 08, 2020 at 11:27:23AM +0200, Thomas Monjalon wrote:
> 08/09/2020 10:25, Bruce Richardson:
> > On Tue, Sep 08, 2020 at 02:14:02AM +0200, Thomas Monjalon wrote:
> > > On Tue Sep 8, 2020 at 2:50 AM CEST, Thomas Monjalon wrote:
> > > > As decided in the Technical Board in November 2019,
>
On 9/7/2020 3:13 AM, Wei Hu (Xavier) wrote:
>
> On 2020/9/7 9:46, wangyunjian wrote:
>> From: Yunjian Wang
>>
>> This patch fixes (out-of-bounds access) coverity issue.
>>
>> Coverity issue: 349932
>> Fixes: 7d7f9f80bbfb ("net/hns3: support MAC address related operations")
>> Cc: sta...@dpdk.org
08/09/2020 11:34, Bruce Richardson:
> On Tue, Sep 08, 2020 at 11:27:23AM +0200, Thomas Monjalon wrote:
> > 08/09/2020 10:25, Bruce Richardson:
> > > On Tue, Sep 08, 2020 at 02:14:02AM +0200, Thomas Monjalon wrote:
> > > > On Tue Sep 8, 2020 at 2:50 AM CEST, Thomas Monjalon wrote:
> > > > > As decid
From: Alvin Zhang
Add headers for GTPU, now outer IP hash can be configured as input
sets for GTPU packet.
Signed-off-by: Alvin Zhang
---
drivers/net/iavf/iavf_hash.c | 13 +
1 file changed, 13 insertions(+)
diff --git a/drivers/net/iavf/iavf_hash.c b/drivers/net/iavf/iavf_hash.c
From: Alvin Zhang
Add patterns and headers for GTPC, now outer IP hash can be configured
as input sets for GTPC packet.
Signed-off-by: Alvin Zhang
---
drivers/net/iavf/iavf_generic_flow.c | 18 ++
drivers/net/iavf/iavf_generic_flow.h | 6 ++
drivers/net/iavf/iavf_hash.c
From: Alvin Zhang
Add GTPC header and its field selector.
Signed-off-by: Alvin Zhang
---
drivers/common/iavf/virtchnl.h | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/common/iavf/virtchnl.h b/drivers/common/iavf/virtchnl.h
index 79515ee..0042cc0 100644
--- a/drivers/common/iav
On 9/4/2020 1:51 PM, Ferruh Yigit wrote:
> On 9/4/2020 9:39 AM, Hemant Agrawal wrote:
>> DPAA platorm MAC interface is known as FMAN i.e. Frame Manager.
>> There are two ways to control it.
>> 1. Statically configure the queues and classification rules before the
>> start of the application using F
'__builtin_add_overflow' added to gcc in version 5, earlier versions
causing build error, like gcc 4.8.5 in RHEL7.
Replaced compiler builtin check with arithmetic check.
Fixes: cabb3c0f29f1 ("net/netvsc: check for overflow on packet info from host")
Reported-by: Raslan Darawsheh
Signed-off-by:
The crypto adapter callback functions and associated data structures
are added.
Signed-off-by: Ankur Dwivedi
---
drivers/crypto/octeontx2/meson.build | 4 +-
.../crypto/octeontx2/otx2_crypto_adapter.c| 77 +++
.../crypto/octeontx2/otx2_crypto_adapter.h| 21 +
Some functions are common across cryptodev pmd and the event
crypto adapter. This patch moves them into a helper file.
Signed-off-by: Ankur Dwivedi
---
drivers/crypto/octeontx2/otx2_cryptodev_ops.c | 65 +---
.../octeontx2/otx2_cryptodev_ops_helper.h | 74 +++
2 f
This patch series adds support for event crypto adapter in op new
mode in the OCTEON TX2 event PMD. The functionality has been
verified with event crypto adapter test application. Build with
meson and ninja is supported.
Ankur Dwivedi (3):
crypto/octeontx2: move functions to helper file
event/
In the op new mode of crypto adapter, the completed crypto operation
is submitted to the event device by the OCTEON TX2 crypto PMD.
During event device dequeue the result of crypto operation is checked.
Signed-off-by: Ankur Dwivedi
---
drivers/common/cpt/cpt_common.h | 1 +
driver
Hi Suanming Mou,
Thanks for the review.
> -Original Message-
> From: Suanming Mou
> Sent: Monday, September 7, 2020 2:32 PM
> To: Zhang, Roy Fan ; dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ; Kusztal,
> ArkadiuszX ; Dybkowski, AdamX
>
> Subject: Re: [dpdk-dev] [dpdk-dev v2 1/2
On Tue Sep 8, 2020 at 2:07 AM CEST, Thomas Monjalon wrote:
> From: Ciara Power
>
> Make is no longer supported for compiling DPDK, references are now
> removed in the documentation.
>
> Signed-off-by: Ciara Power
> Signed-off-by: Louise Kilheeney
> ---
> doc/guides/contributing/design.rst | 12
08/09/2020 11:55, Ferruh Yigit:
> On 9/4/2020 1:51 PM, Ferruh Yigit wrote:
> > Series applied to dpdk-next-net/main, thanks.
>
> Hi Hemant,
>
> I need to drop the series from next-net, since new files doesn't have the
> Makefile support, they are causing build error for Make and affecting CI
> r
rte_mempool_get_bulk is used to get bufs/many_bufs from the pool,
but at some locations when test fails the bufs/many_bufs are
not returned back to the pool.
Due to this, multiple executions of distributor_autotest gives the
following error message: Error getting mbufs from pool.
To resolve this is
Add minimum burst throughout the scheduler pipeline and a flush counter.
Replace ring API calls with local single threaded implementation
where possible.
Signed-off-by: Radu Nicolau
---
drivers/event/sw/sw_evdev.h | 11 +++-
drivers/event/sw/sw_evdev_scheduler.c | 83 ++
> A temporary session is created for sessionless crypto operations.
> rte_cryptodev_sym_session_create() should be used for creating the
> temporary session as it initializes the session structure in the correct way.
> Also the session should be set to 0 before freeing it.
>
> Fixes: 17ac2a72191
>
> The BPF lib was introduced in 18.05.
> There were no changes in it's public API since 19.11.
> It should be mature enough to remove it's 'experimental' tag.
>
> Signed-off-by: Conor Walsh
> ---
Acked-by: Konstantin Ananyev
> 2.25.1
> -Original Message-
> From: dev On Behalf Of Qiming Yang
> Sent: Wednesday, September 2, 2020 2:38 PM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Yang, Qiming
>
> Subject: [dpdk-dev] [PATCH 1/2] net/ice: add dcf port representor
> infrastructure
>
> Defines data structures and code to ini
> Since librte_ipsec was first introduced in 19.02 and there were no changes
> in it's public API since 19.11, it should be considered mature enough to
> remove the 'experimental' tag from it.
>
> Signed-off-by: Conor Walsh
> ---
Acked-by: Konstantin Ananyev
> 2.25.1
Hi,
> -Original Message-
> From: Michael Baum
> Sent: Thursday, September 3, 2020 1:14 PM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Slava Ovsiienko
> Subject: [PATCH v1 00/18] mlx5 Rx DevX/Verbs separation
>
> v1:
> Initial version
>
> Michael Baum (18):
> net/mlx5:
Hi, Ferruh Yigit
On 2020/9/4 18:34, Ferruh Yigit wrote:
On 8/25/2020 12:53 PM, Wei Hu (Xavier) wrote:
From: "Wei Hu (Xavier)"
According to rte_eth_rx_queue_setup and rte_eth_tx_queue_setup API
function, rx_queue_offload_capa and rx_offload_capa, tx_queue_offload_capa
and tx_offload_capa must
On 9/8/2020 9:36 AM, Sarosh Arif wrote:
> delay_us_sleep_autotest is failing on this patch. To replicate it, I
> ran the same test on my system and it did not fail. Can this test be
> re-run?
cc'ed lab people.
I clicked the 'rebuild' button for the test, but I can't see if it queued or
not...
>
Hi,
> -Original Message-
> From: Ferruh Yigit
> Sent: Tuesday, September 8, 2020 1:07 PM
> To: dev@dpdk.org; Stephen Hemminger ; NBU-
> Contact-kys ; NBU-Contact-haiyangz
> ; NBU-Contact-longli
> Cc: Ferruh Yigit ; Raslan Darawsheh
>
> Subject: [PATCH] net/netvsc: replace compiler built
On 9/7/2020 11:50 PM, Thomas Monjalon wrote:
> As decided in the Technical Board in November 2019,
> the kernel module igb_uio is moved to the dpdk-kmods repository
> in the /linux/igb_uio/ directory.
>
> Minutes of Technical Board meeting:
> https://mails.dpdk.org/archives/dev/2019-November/15176
On 9/8/2020 11:19 AM, Thomas Monjalon wrote:
> 08/09/2020 11:55, Ferruh Yigit:
>> On 9/4/2020 1:51 PM, Ferruh Yigit wrote:
>>> Series applied to dpdk-next-net/main, thanks.
>>
>> Hi Hemant,
>>
>> I need to drop the series from next-net, since new files doesn't have the
>> Makefile support, they are
On 9/3/2020 10:09 PM, Ferruh Yigit wrote:
> Hiding the 'struct eth_dev_ops' from applications.
>
> Removing relevant deprecation notice.
>
> Signed-off-by: Ferruh Yigit
> Acked-by: Andrew Rybchenko
Hi Thomas and all,
If there is no objection I am willing to merge this series soon to prevent m
Ability to distinguish ICMP identifier fields in packets.
Dstinguish ICMP sequence number field too.
Already supports ICMP code and type fields in current version.
Existing fields in ICMP header contain the required information.
ICMP header already is supported and no code change in RTE FLOW.
Exten
From: "Wei Hu (Xavier)"
Currently, offload capabilities are only enabled for all Rx/Tx queues
in hns3 PF/VF PMD driver, and offload capability only applied in a Rx/Tx
queue is not supported. So this patch moves 'DEV_TX_OFFLOAD_MBUF_FAST_FREE'
from tx_queue_offload_capa to tx_offload_capa.
Fixes:
From: Guy Kaneti
The L3 Forwarding with Regex application is a simple example of
packet processing using DPDK Regex framework.
The application performs L3 LPM based forwarding while using
Regex framework for pre-filtering decision.
Guy Kaneti (2):
examples/l3fwd-regex: add regex based l3fwd
From: Guy Kaneti
Add regex based l3fwd application
inline with normal l3fwd. only LPM is supported.
Signed-off-by: Guy Kaneti
---
MAINTAINERS|2 +
examples/l3fwd-regex/l3fwd.h | 207 ++
examples/l3fwd-regex/l3fwd_lpm.c | 461
examples/l3fw
From: Guy Kaneti
Adding the user guide for l3fwd regex application.
Signed-off-by: Guy Kaneti
---
MAINTAINERS | 1 +
doc/guides/sample_app_ug/index.rst| 1 +
doc/guides/sample_app_ug/intro.rst| 4 +
doc/guides/sample_app_ug/l3_for
Hi,
lizh wrote:
> Ability to distinguish ICMP identifier fields in packets.
> Dstinguish ICMP sequence number field too.
> Already supports ICMP code and type fields in current version.
> Existing fields in ICMP header contain the required information.
> ICMP header already is supported and no co
On Tue, Sep 8, 2020 at 12:07 AM Thomas Monjalon wrote:
>
> The first 13 commits of this series are pushed to the main branch,
> making the make-based build an old story.
>
[snip]
> doc/guides/rawdevs/octeontx2_ep.rst |8 -
> doc/guides/rel_notes/deprecation.rst |7 -
>
This patch marks the old igb-uio driver as unsecure when used
with the QAT PMD and updates all examples to recommend using
vfio-pci instead.
It also mentions security issues with the QAT CPM and provides
information about the new vfio-pci parameter 'disable_denylist'
available in Linux kernels 5.9
Hi Ajit,
Sorry for not inline, but for some reason this tread is in html format.
I think that the issue you are rising is a good one, but can be solved using
the new
context API that we are going to push into 20.11
https://patches.dpdk.org/cover/73555/
this will enable creating the sample action
On Mon, 7 Sep 2020 02:36:48 +
Suanming Mou wrote:
> Hi,
>
> Sorry for my late reply due to the vacation.
>
> > What is the performance impact of this for currently working applications
> > that
> > use a single thread to program flow rules. You are adding a couple of
> > system
> > calls
On Mon, 7 Sep 2020 09:56:50 +0800
Haiyue Wang wrote:
> Enlarge the L3 and tunnel header length from 8-bit to 16-bit to handle
> the bigger headers. And reorder the fields to avoid creating a structure
> hole.
>
> Signed-off-by: Haiyue Wang
> ---
> v2: use bit field to avoid creating a structur
On Tue, 8 Sep 2020 09:18:08 +0100
Bruce Richardson wrote:
> On Mon, Sep 07, 2020 at 10:20:13AM -0700, Stephen Hemminger wrote:
> > On Mon, 7 Sep 2020 09:58:27 +0100
> > Bruce Richardson wrote:
> >
> > > On Mon, Sep 07, 2020 at 09:54:29AM +0100, Ferruh Yigit wrote:
> > > > On 9/6/2020 4:42 A
08/09/2020 16:52, Stephen Hemminger:
> On Mon, 7 Sep 2020 02:36:48 +
> Suanming Mou wrote:
> > > What is the performance impact of this for currently working applications
> > > that
> > > use a single thread to program flow rules. You are adding a couple of
> > > system
> > > calls to what
This is an improved version of the setup of huge pages
bases on earlier DPDK setup.
Features:
* can display current hugepage settings.
* autodetects NUMA vs non NUMA
* allows setting different page sizes
recent kernels support multiple sizes.
* accepts a parameter in bytes (not pa
On Tue, Sep 1, 2020 at 4:50 PM Conor Walsh wrote:
>
> The BPF lib was introduced in 18.05.
> There were no changes in it's public API since 19.11.
> It should be mature enough to remove it's 'experimental' tag.
Should RTE_BPF_XTYPE_NUM be dropped?
--
David Marchand
On Tue, 8 Sep 2020 11:06:42 +0100
Ferruh Yigit wrote:
> '__builtin_add_overflow' added to gcc in version 5, earlier versions
> causing build error, like gcc 4.8.5 in RHEL7.
Sigh. Ok, but the security folks really like __builtin_add_overflow.
>
> On Tue, Sep 1, 2020 at 4:50 PM Conor Walsh wrote:
> >
> > The BPF lib was introduced in 18.05.
> > There were no changes in it's public API since 19.11.
> > It should be mature enough to remove it's 'experimental' tag.
>
> Should RTE_BPF_XTYPE_NUM be dropped?
Good catch, thanks.
Yes I agre
Hi Adam,
> -Original Message-
> From: Dybkowski, AdamX
> Sent: Tuesday, September 8, 2020 3:21 PM
> To: dev@dpdk.org; Trahe, Fiona ; akhil.go...@nxp.com;
> Mcnamara, John
>
> Cc: Dybkowski, AdamX
> Subject: [PATCH] doc: document vfio-pci usage with QAT PMD
>
> This patch marks the old
On Tue, 08 Sep 2020 17:03:53 +0200
Thomas Monjalon wrote:
> 08/09/2020 16:52, Stephen Hemminger:
> > On Mon, 7 Sep 2020 02:36:48 +
> > Suanming Mou wrote:
> > > > What is the performance impact of this for currently working
> > > > applications that
> > > > use a single thread to program
This patch marks the old igb-uio driver as unsecure when used
with the QAT PMD and updates all examples to recommend using
vfio-pci instead.
It also mentions security issues with the QAT CPM and provides
information about the new vfio-pci parameter 'disable_denylist'
available in Linux kernels 5.9
This patch marks the old igb-uio driver as unsecure when used
with the QAT PMD and updates all examples to recommend using
vfio-pci instead.
It also mentions security issues with the QAT CPM and provides
information about the new vfio-pci parameter 'disable_denylist'
available in Linux kernels 5.9
Replace behavior with RTE_LIBRTE_ARK_MIN_TX_PKTLEN
with a default value of 0.
Update documentation as needed.
Signed-off-by: Ed Czeck
---
v7:
-- add ARK_MIN_TX_PKTLEN to conditional expression
to avoid compile warning with icc.
-- restore CONFIG_RTE_LIBRTE_ARK_PMD doc as requested.
---
d
Use ARK_PMD_LOG in place of PMD_DRV_LOG, PMD_DEBUG_LOG, PMD_FUNC_LOG,
PMD_STATS_LOG, PMD_RX_LOG, and PMD_TX_LOG.
Review and adjust log levels and messages as needed.
Signed-off-by: Ed Czeck
---
doc/guides/nics/ark.rst | 13 --
drivers/net/ark/ark_ddm.c | 12 ++---
drivers/net/a
> -Original Message-
> From: Dybkowski, AdamX
> Sent: Tuesday, September 8, 2020 5:20 PM
> To: dev@dpdk.org; Trahe, Fiona ;
> akhil.go...@nxp.com; Mcnamara, John
> Cc: Dybkowski, AdamX
> Subject: [PATCH v2 0/1] doc: document vfio-pci usage with QAT PMD
>
>...
>
> doc/guides/cryptodevs
Some new APIs were added to the timer library in the 19.05 release, and
there have been no changes to their interfaces since then. These
functions can be considered stable enough to remove their 'experimental'
tag.
Signed-off-by: Erik Gabriel Carrillo
---
lib/librte_timer/rte_timer.h |
Tunnel Offload API provides hardware independent, unified model
to offload tunneled traffic. Key model elements are:
- apply matches to both outer and inner packet headers
during entire offload procedure;
- restore outer header of partially offloaded packet;
- model is implemented as a set of
1 - 100 of 194 matches
Mail list logo
