> -Original Message-
> From: Cao, Yahui
> Sent: Friday, July 7, 2023 2:22 PM
> To: Liu, Lingyu ; dev@dpdk.org; Zhang, Qi Z
> ; Xing, Beilei
> Subject: Re: [PATCH v4] doc: add iavf live migration guide
>
>
> On 7/7/2023 2:08 PM, Lingyu Liu wrote:
> > Add iavf live migration steps based
> -Original Message-
> From: Zhang, Yuying
> Sent: Friday, July 7, 2023 10:11 AM
> To: dev@dpdk.org; Zhang, Qi Z ; Yang, Qiming
>
> Cc: Zhang, Yuying
> Subject: [PATCH v1] net/ice: fix rss hash key generation
>
> Current code just generated 40 bytes standard rss hash key of ice drive
On 7/7/2023 2:08 PM, Lingyu Liu wrote:
Add iavf live migration steps based on KVM VFIO migration.
Signed-off-by: Lingyu Liu
---
v2: Fixed CI.
Added brief introduction about live migration.
Clarified this is iavf feature.
v3: Added intro and link about vfio live migration.
Adde
Add iavf live migration steps based on KVM VFIO migration.
Signed-off-by: Lingyu Liu
---
v2: Fixed CI.
Added brief introduction about live migration.
Clarified this is iavf feature.
v3: Added intro and link about vfio live migration.
Added description about kernel boot parameters.
Currently, all buses use the same eal allow and block options. Need to
allow both allow and block options for different buses to coexist.
It wouldn't be a problem for pci bus if both allow and block options
were present. When the first option occurs, the scan mode for pci bus is
set.
For example:
|<- mb->pkt_len - sqh_len ->|
|<-sa->hdr_len->|
|<- sa->hdr_l3_off ->||<- udph->dgram_len ->|
+++-+-+-+-+
| ETH| IP | UDP | ESP | payload | sqh |
+---
On 2023/7/6 16:52, David Marchand wrote:
On Tue, Jul 4, 2023 at 4:11 PM Thomas Monjalon wrote:
04/07/2023 10:04, Jie Hai:
On 2023/6/20 22:34, Thomas Monjalon wrote:
20/06/2023 10:14, Jie Hai:
On 2023/2/20 20:55, David Marchand wrote:
On Fri, Feb 10, 2023 at 3:50 AM Jie Hai wrote:
This p
Well, let me explain.
> >>> diff --git a/lib/ipsec/esp_outb.c b/lib/ipsec/esp_outb.c
> >>> index 9cbd9202f6..ec87b1dce2 100644
> >>> --- a/lib/ipsec/esp_outb.c
> >>> +++ b/lib/ipsec/esp_outb.c
> >>> @@ -198,7 +198,7 @@ outb_tun_pkt_prepare(struct rte_ipsec_sa *sa,
> >>> rte_be64_t sqc,
> >>>
Current code just generated 40 bytes standard rss
hash key of ice driver. The extended 12 bytes
were filled by hardware and were invalid for users.
This patch generate 52 bytes rss hash key for ice
driver just as other drivers.
Fixes: 50370662b727 ("net/ice: support device and queue ops")
Fixes: 2
在 2023/7/7 9:32, Long Li 写道:
Subject: RE: [PATCH] bus/vmbus: add support allow/block scan mode
Subject: Re: [PATCH] bus/vmbus: add support allow/block scan mode
On Thu, 9 Jun 2022 08:46:18 +
Xiaoming Jiang wrote:
bus/vmbus: add support allow/block scan mode
Signed-off-by: Xiaoming J
> Subject: RE: [PATCH] bus/vmbus: add support allow/block scan mode
>
> > Subject: Re: [PATCH] bus/vmbus: add support allow/block scan mode
> >
> > On Thu, 9 Jun 2022 08:46:18 +
> > Xiaoming Jiang wrote:
> >
> > > bus/vmbus: add support allow/block scan mode
> > >
> > > Signed-off-by: Xiaomi
> -Original Message-
> From: Yang, Qiming
> Sent: 2023年7月6日 10:17
> To: You, KaisenX ; dev@dpdk.org
> Cc: Zhou, YidingX ; sta...@dpdk.org
> Subject: RE: [PATCH] child process synchronization NIC startup parameters
>
> Hi, kaisen
> Your patch missed prefix app/test.
Thank you for your
From: Long Li
On a fatal CQE error when coalescing is used, update the correct index
and allow proceeding to the next CQE.
Fixes: 3409e0f172f6 ("net/mana: implement Rx CQE coalescing")
Signed-off-by: Long Li
---
drivers/net/mana/rx.c | 18 --
1 file changed, 8 insertions(+), 10
I updated the original patches to newer versions of DPDK (up to 22.xx).
Mathew S. Thoennes will be the long term maintainer however.
The uint128 was part of the original patch sent to me, I'm happy to remove it.
Best Regards
- David Miller
On Thu, Jul 6, 2023 at 5:49 PM Stephen Hemminger
wro
> Subject: Re: [PATCH] bus/vmbus: add support allow/block scan mode
>
> On Thu, 9 Jun 2022 08:46:18 +
> Xiaoming Jiang wrote:
>
> > bus/vmbus: add support allow/block scan mode
> >
> > Signed-off-by: Xiaoming Jiang
>
> Looks fine to me. Any comments from Long Li?
Xiaoming, I have trouble
Acked-by: Kai Ji
From: Nithin Dabilpuram
Sent: 01 July 2023 08:15
To: gak...@marvell.com
Cc: jer...@marvell.com ; dev@dpdk.org ;
Nithin Dabilpuram
Subject: [PATCH] doc: announce addition of new security IPsec SA option
Announce addition of new security IPsec S
On Fri, 15 Jul 2022 12:05:41 +
Amit Prakash Shukla wrote:
> Thanks Bruce for the review. Please find my comments in-line.
>
> > -Original Message-
> > From: Bruce Richardson
> > Sent: Thursday, July 14, 2022 4:31 PM
> > To: Amit Prakash Shukla
> > Cc: dev@dpdk.org; Jerin Jacob Koll
On Thu, 9 Jun 2022 08:46:18 +
Xiaoming Jiang wrote:
> bus/vmbus: add support allow/block scan mode
>
> Signed-off-by: Xiaoming Jiang
Looks fine to me. Any comments from Long Li?
On Fri, 28 Oct 2022 17:52:40 -0400
David Miller wrote:
> diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
> index cc8e7aa138..2a863f3d39 100644
> --- a/app/test-pmd/config.c
> +++ b/app/test-pmd/config.c
> @@ -245,9 +245,9 @@ nic_stats_display(portid_t port_id)
> static uint64_t p
On Thu, 19 Jan 2023 23:41:30 -0500
ok...@kernel.org wrote:
> From: Sinan Kaya
>
> Following up the codeql reported problems first submitted
> by Stephen Hemminger here:
>
> https://lore.kernel.org/all/20220527161210.77212d0b@hermes.local/t/
>
> Posting a series of fixes about potential null po
This patch updates the FreeBSD DPDK installation guide to detail
how users can find and install specific versions of DPDK using the
pkg package manager. The prior instructions did not highlight
'dpdk' is an alias and may not always point to the latest DPDK
version. The guide now includes steps to
On Thu, 29 Jun 2023 17:33:00 +
Bili Dong wrote:
> +
> +/**
> + * The following bytes access helper functions are expected to work
> + * without any particular input buffer alignment requirements.
> + */
> +
Probably need to avoid users getting tempted to use these helpers
ad exported API's?
On Thu, 29 Jun 2023 10:53:39 +0800
Weifeng Su wrote:
> In this scenario, the DPDK process invokes a script which
> inherits an open file descriptor (FD) for a UIO device.
> After the script execution is complete, the UIO device's
> close operation is called. However, in a new kernel version
> (86
On Thu, 9 Sep 2021 14:48:04 +0100
Ray Kinsella wrote:
> The symbol-tool script reports on the growth of symbols over releases
> and list expired symbols. The notify-symbol-maintainers script
> consumes the input from symbol-tool and generates email notifications
> of expired symbols.
>
> v2: re
On Wed, 5 Jul 2023 17:35:14 +0800
Kaisen You wrote:
> In meson_test, because the child process does not synchronize
> the NIC startup parameters of the parent process at startup,
> it uses all NICs bound by vfio as startup parameters by default,
> and an exception occurs in the subsequent hugefi
On Thu, 18 Nov 2021 18:56:13 +
wrote:
More tests is always good, this seemed to have gotten stalled.
Probably because most people don't have Nvidia GPU and DPDK.
> +static void
> +signal_handler(int signum)
> +{
> + if (signum == SIGINT || signum == SIGTERM) {
> + printf("\n\
On Mon, 1 Nov 2021 23:14:47 +0530
Harman Kalra wrote:
> Fixing the error logs level, as currently default level is
> set to debug. Due to this failure is not getting captured.
>
> Fixes: b7c984291611 ("interrupts: add allocator and accessors")
>
> Signed-off-by: Harman Kalra
> ---
> lib/eal/c
On Mon, 5 Apr 2021 21:39:52 +0200
Thomas Monjalon wrote:
> The description of the EAL options was printed before the application
> description provided via the hook.
> It is better to let the application print the global syntax
> and describes the detail of the EAL options below.
>
> Also, some
> > Subject: [PATCH] doc: announce deprecation for security ops
> >
> > Structure rte_security_ops and rte_security_ctx are meant to be used by
> > rte_security library and the PMDs associated.
> > These will be moved to an internal header in DPDK 23.11 release.
> >
> > Signed-off-by: Akhil Goyal
> default TAP mac address was changed in commit id:
> c3006be2acab49c6b77ae9c9ef04b061e5dacbd6
> reflect changes in ipsec test scripts.
>
> Fixes: c3006be2acab ("net/tap: set locally administered bit for fixed MAC
> address")
> Cc: d...@linux.vnet.ibm.com
> Cc: sta...@dpdk.org
>
> Signed-off-by:
> This series removes some unused defines throughout common qat drivers
> and crypto ipsec mb drivers. It also removes some defines that should
> have been removed previously.
>
> v3:
> Incorrect fixline
Series applied to dpdk-next-crypto
Thanks
On Mon, 21 Mar 2022 17:27:27 +0500
Fidaullah Noonari wrote:
> binding with vfio driver, when IOMMU is disabled, causes program to crash.
> this patch adds a flag for noiommmu-mode. when this is set, if IOMMU is
> disabled, it changes vfio into unsafe noiommu mode and prints warning
> message.
>
> > Subject: [PATCH v2] examples/ipsec-secgw: fix of socket id default value
> >
> > Due to recent changes to the default device socket ID, before being used as
> > an index for session mempool list, set socket ID to 0 if unknown (-1).
> >
> > Fixes: 7dcd73e37965 ("drivers/bus: set device NUMA node
> Due to recent changes to the default device socket ID,
> before being used as an index for session mempool list,
> the socket ID should be set to 0 if unknown (-1).
>
> Fixes: 7dcd73e37965 ("drivers/bus: set device NUMA node to unknown by
> default")
> Fixes: 64c469b9e7d8 ("app/crypto-perf: chec
On Wed, 01 Feb 2023 18:28:44 +0100
Thomas Monjalon wrote:
> 10/01/2023 15:56, Mohammad Iqbal Ahmad:
> > This patch fixes (Logically dead code) coverity issue.
> > This patch also fixes (Uninitialized scalar variable) coverity issue.
> >
> > Coverity issue: 381687
> > Coverity issue: 381686
> > F
Autogenerated with cocci/mtod-offset.cocci.
Signed-off-by: Stephen Hemminger
---
drivers/baseband/fpga_5gnr_fec/rte_fpga_5gnr_fec.c | 7 +++
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/baseband/fpga_5gnr_fec/rte_fpga_5gnr_fec.c
b/drivers/baseband/fpga_5gnr_fec/rte_
Autogenerated with cocci/mtod-offset.cocci.
Signed-off-by: Stephen Hemminger
---
drivers/net/mlx4/mlx4_rxtx.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/mlx4/mlx4_rxtx.c b/drivers/net/mlx4/mlx4_rxtx.c
index 059e432a63fc..d5feeb7f7e6d 100644
--- a/driver
Autogenerated with cocci/mtod-offset.cocci.
Signed-off-by: Stephen Hemminger
---
drivers/crypto/caam_jr/caam_jr.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/crypto/caam_jr/caam_jr.c b/drivers/crypto/caam_jr/caam_jr.c
index b55258689b49..9c96fd21a48d 10064
Autogenerated with cocci/mtod-offset.cocci
Signed-off-by: Stephen Hemminger
---
drivers/common/cpt/cpt_ucode.h | 10 --
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/drivers/common/cpt/cpt_ucode.h b/drivers/common/cpt/cpt_ucode.h
index b393be4cf661..87a3ac80b9da 100644
--
Autogenerated with cocci/mtod-offset.cocci
Signed-off-by: Stephen Hemminger
---
drivers/crypto/cnxk/cn9k_cryptodev_ops.c | 2 +-
drivers/crypto/cnxk/cnxk_se.h| 5 ++---
2 files changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/crypto/cnxk/cn9k_cryptodev_ops.c
b/drivers/
Initial patch generated with cocci/mtod-offset.
Additional manual cleanups to indentation and remove unnecessary
parenthesis.
Signed-off-by: Stephen Hemminger
---
drivers/crypto/ipsec_mb/pmd_kasumi.c | 16 ++---
drivers/crypto/ipsec_mb/pmd_snow3g.c | 35 +++-
driv
Auto generated with cocci/mtod-offset.cocci
Signed-off-by: Stephen Hemminger
---
drivers/crypto/qat/dev/qat_crypto_pmd_gens.h | 9 +
drivers/crypto/qat/qat_sym.h | 9 +
2 files changed, 10 insertions(+), 8 deletions(-)
diff --git a/drivers/crypto/qat/dev/qat_cryp
Automatically generated by cocci/mtod-offset.cocci.
Signed-off-by: Stephen Hemminger
---
drivers/net/nfp/flower/nfp_flower_cmsg.h | 3 ++-
drivers/net/nfp/flower/nfp_flower_ctrl.c | 4 ++--
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/net/nfp/flower/nfp_flower_cmsg.h
b
Automatically generated by cocci/mbuf-offset.cocci
Signed-off-by: Stephen Hemminger
---
drivers/net/tap/rte_eth_tap.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index bf98f7555990..ebddbae9fe9f 100644
--- a/
Automatically generated from cocci/mtod-offset.cocci
Signed-off-by: Stephen Hemminger
---
examples/l2fwd-crypto/main.c | 16 +---
examples/ptpclient/ptpclient.c | 18 +-
2 files changed, 18 insertions(+), 16 deletions(-)
diff --git a/examples/l2fwd-crypto/main.c b/
Based off patch generated by cocci/mtod-offset.cocci.
With some cleanup to shorten lines by using conditional
with omitted operand.
Signed-off-by: Stephen Hemminger
---
app/test/test_cryptodev.c | 66 +--
1 file changed, 36 insertions(+), 30 deletions(-)
diff
Use helper macro.
Signed-off-by: Stephen Hemminger
---
app/test-pmd/ieee1588fwd.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/app/test-pmd/ieee1588fwd.c b/app/test-pmd/ieee1588fwd.c
index 386d9f10e642..3371771751dd 100644
--- a/app/test-pmd/ieee1588fwd.c
+++ b/app/tes
Use the rte_pktmbuf_mtod_offset macro.
Change was automatically generated by cocci/mtod-offset.cocci.
Signed-off-by: Stephen Hemminger
---
lib/gso/gso_common.h | 11 +--
lib/gso/gso_tcp4.c| 8
lib/gso/gso_tunnel_tcp4.c | 12 ++--
lib/gso/gso_tunnel_udp4.c |
Use rte_pktmbuf_mtod_offset. Change was automatically generated
by cocci/mtod-offset.cocci.
Signed-off-by: Stephen Hemminger
---
lib/gro/gro_tcp.h| 2 +-
lib/gro/gro_tcp4.c | 2 +-
lib/gro/gro_udp4.c | 4 ++--
lib/gro/gro_vxlan_tcp4.c | 4 ++--
lib/gro/gro_vxlan_udp4.c | 4 ++
Run the coccinelle script for rte_pktmbuf_mtod_offset
against current main branch.
v3 - rebase to cover gro changes
Stephen Hemminger (14):
gro: use rte_pktmbuf_mtod_offset
gso: use rte_pktmbuf_mtod_offset
testpmd: use rte_pktmbuf_mtod_offset
test: cryptodev use rte_pktmbuf_mtod_offset
On Thu, 13 Jan 2022 05:31:18 +
Dharmik Thakkar wrote:
> Hi,
>
> Thank you for your valuable review comments and suggestions!
>
> I will be sending out a v2 in which I have increased the size of the mempool
> to 32GB by using division by sizeof(uintptr_t).
> However, I am seeing ~5% perform
On Thu, 06 Jul 2023 18:20:19 +0200
Thomas Monjalon wrote:
> >
> > This raises a more global issue.
> > rte_srand() overrides the system seed which is set during startup.
> > This is a bad thing, it reduces the entropy in the random number generator.
> >
> > There are two possible solutions to t
23/04/2023 06:58, Srikanth Yalavarthi:
> Updated ML application source files to have uniform code formatting
> style across. Remove extra blank lines. Fix typos in application help.
>
> Fixes: 8cb22a545447 ("app/mldev: fix debug build")
> Fixes: da6793390596 ("app/mldev: support inference validati
23/03/2023 17:21, Srikanth Yalavarthi:
> Application currently doesn't check for empty models list and
> filelist entries. This causes the app to report an incorrect
> error messages and test status when the lists are empty.
>
> Fixes: bbd272edcb14 ("app/mldev: add ordered inferences")
> Fixes: f6
Hi,
> -Original Message-
> From: Slava Ovsiienko
> Sent: Wednesday, July 5, 2023 6:31 PM
> To: dev@dpdk.org
> Cc: jer...@marvell.com; Raslan Darawsheh
> Subject: [PATCH v5 0/4] net/mlx5: introduce Tx datapath tracing
>
> The mlx5 provides the send scheduling on specific moment of time,
change define from RTE_LIB_SECURITY to BUILD_QAT_SYM as
RTE_ETHER_CRC_LEN value is protected by BUILD_QAT_SYM.
Fixes: ce7a737c8f02 ("crypto/qat: support cipher-CRC offload")
Cc: kevin.osulli...@intel.com
Signed-off-by: Brian Dooley
---
drivers/common/qat/qat_qp.c | 2 +-
1 file changed, 1 inser
removed AESNI_MB_DOCSIS_SEC_ENABLED defines as they are no longer used.
Fixes: 798f9d134519 ("crypto/ipsec_mb: remove security lib presence checks")
Cc: maxime.coque...@redhat.com
Signed-off-by: Brian Dooley
---
drivers/crypto/ipsec_mb/ipsec_mb_private.c | 4
drivers/crypto/ipsec_mb/pmd_
This series removes some unused defines throughout common qat drivers
and crypto ipsec mb drivers. It also removes some defines that should
have been removed previously.
v3:
Incorrect fixline
v2:
more defines removed in additional patch and changed fixline
Brian Dooley (2):
crypto/ipsec_mb: re
03/07/2023 17:54, Stephen Hemminger:
> On Wed, 21 Jun 2023 00:17:20 +0300
> Dmitry Kozlyuk wrote:
>
> > Seeding the global PRNG at sketch creation
> > does not make the sketch operation deterministic:
> > it uses rte_rand() later, the PRNG may be seeded again by that point.
> > On the other hand,
04/07/2023 00:31, Stephen Hemminger:
> On Thu, 18 Aug 2022 15:18:36 +0500
> Usman Tanveer wrote:
>
> > Hi,
> >
> > Can you please have a look and update the status?
>
> Looks OK to me.
>
> Acked-by: Stephen Hemminger
better title: examples/ethtool: remove stop before start
Applied, thanks.
Hi Brian,
> -Original Message-
> From: Brian Dooley
> Sent: Thursday 6 July 2023 17:05
> To: Ji, Kai ; De Lara Guarch, Pablo
>
> Cc: dev@dpdk.org; gak...@marvell.com; Dooley, Brian
> ; maxime.coque...@redhat.com
> Subject: [PATCH v2 1/2] crypto/ipsec_mb: remove unused defines
>
> remove
> -Original Message-
> From: Brian Dooley
> Sent: Thursday 6 July 2023 17:05
> To: Ji, Kai
> Cc: dev@dpdk.org; gak...@marvell.com; Dooley, Brian
> ; O'Sullivan, Kevin
> Subject: [PATCH v2 2/2] common/qat: change define header
>
> change define from RTE_LIB_SECURITY to BUILD_QAT_SYM a
change define from RTE_LIB_SECURITY to BUILD_QAT_SYM as
RTE_ETHER_CRC_LEN value is protected by BUILD_QAT_SYM.
Fixes: ce7a737c8f02 ("crypto/qat: support cipher-CRC offload")
Cc: kevin.osulli...@intel.com
Signed-off-by: Brian Dooley
---
drivers/common/qat/qat_qp.c | 2 +-
1 file changed, 1 inser
removed AESNI_MB_DOCSIS_SEC_ENABLED defines as they are no longer used.
Fixes: 66a9d8d0bc6d ("crypto/qat: remove security library presence checks")
Cc: maxime.coque...@redhat.com
Signed-off-by: Brian Dooley
---
drivers/crypto/ipsec_mb/ipsec_mb_private.c | 4
drivers/crypto/ipsec_mb/pmd_a
This series removes some unused defines throughout common qat drivers
and crypto ipsec mb drivers. It also removes some defines that should
have been removed previously.
v2:
more defines removed in additional patch and changed fixline
Brian Dooley (2):
crypto/ipsec_mb: remove unused defines
c
> -Original Message-
> From: Kai Ji
> Sent: Thursday 6 July 2023 12:01
> To: dev@dpdk.org
> Cc: gak...@marvell.com; sta...@dpdk.org; Ji, Kai ; Matz,
> Olivier
> Subject: [PATCH v2] examples/ipsec-secgw: fix of socket id default value
>
> Due to recent changes to the default device soc
06/07/2023 16:44, Stephen Hemminger:
> Trying to reach 500 patches by 23.08 release.
Impossible. It is 23.07 :)
Add NULL pointer check to params->name, which is later
copied into the hash datastructure. Without this check
the code segfaults on the strlcpy() of a NULL pointer.
Fixes: 48a399119619 ("hash: replace with cuckoo hash implementation")
Signed-off-by: Conor Fogarty
---
Cc: pablo.de.lara.gua...@in
Hi,
> -Original Message-
> From: Xueming Li
> Sent: Thursday, July 6, 2023 2:56 PM
> To: Matan Azrad ; Slava Ovsiienko
> ; Ori Kam ; Suanming Mou
>
> Cc: Xueming(Steven) Li ; dev@dpdk.org
> Subject: [PATCH v2] net/mlx5: support symmetric RSS hash function
>
> This patch supports symmetr
From: Xueming(Steven) Li
> This patch supports symmetric hash function that creating same hash result
> for bi-direction traffic which having reverse source and destination IP and L4
> port.
>
> Since the hash algorithom is different than spec(XOR), leave a warning in
> validation.
>
> Signed-
Hi,
> -Original Message-
> From: Itamar Gozlan
> Sent: Tuesday, July 4, 2023 7:05 PM
> To: Alex Vesker ; Slava Ovsiienko
> ; Matan Azrad ; NBU-
> Contact-Thomas Monjalon (EXTERNAL) ; Suanming
> Mou ; Ori Kam
> Cc: dev@dpdk.org
> Subject: [v3 1/5] net/mlx5/hws: remove unneeded new line fo
30/06/2023 19:09, Vladimir Medvedkin:
> Fixes: 28ebff11c2dc ("hash: add predictable RSS")
> Cc: sta...@dpdk.org
>
> Acked-by: Konstantin Ananyev
> Tested-by: Konstantin Ananyev
> Signed-off-by: Vladimir Medvedkin
I've just merged another patch from you where the explanation is useless.
Here th
On Thu, 06 Jul 2023 10:29:04 +0200
Thomas Monjalon wrote:
> 29/06/2023 18:27, Stephen Hemminger:
> > On Mon, 5 Apr 2021 21:39:50 +0200
> > Thomas Monjalon wrote:
> >
> > > After v4, this series is split in several parts.
> > > The remaining 4 patches of this series are low priority.
> > >
>
05/07/2023 03:33, fengchengwen:
> This is bugfix, suggest add Cc.
>
> With above add, Acked-by: Chengwen Feng
>
> On 2023/7/4 20:17, Fengnan Chang wrote:
> > When there is not enough space to memsegs, we should prompt
> > which configuration should be modified instead of printing
> > some number
03/07/2023 17:43, Vladimir Medvedkin:
> Fixed an issue that occurs when
> adding a default route as the first route.
>
> Bugzilla ID: 1160
> Fixes: 7dc7868b200d ("fib: add DIR24-8 dataplane algorithm")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Vladimir Medvedkin
Applied, thanks.
On 7/6/2023 12:38 PM, Ori Kam wrote:
>
>
>> -Original Message-
>> From: Bing Zhao
>> Sent: Saturday, July 1, 2023 12:27 PM
>> Subject: [PATCH v2] app/testpmd: add IP length field matching
>>
>> Added support of parsing IPv4 total length and IPv6 payload length
>> in the command line. The
> From: Kamalakshitha Aligeri [mailto:kamalakshitha.alig...@arm.com]
> Sent: Wednesday, 5 July 2023 19.18
>
> Integrated zero-copy put API in mempool cache in i40e PMD.
> On Ampere Altra server, l3fwd single core's performance improves by 5%
> with the new API
>
> Signed-off-by: Kamalakshitha Ali
> From: Feifei Wang [mailto:feifei.wa...@arm.com]
> Sent: Thursday, 6 July 2023 11.50
>
> Add 'rte_eth_recycle_rx_queue_info_get' and 'rte_eth_recycle_mbufs'
> APIs to recycle used mbufs from a transmit queue of an Ethernet device,
> and move these mbufs into a mbuf ring for a receive queue of an
removed AESNI_MB_DOCSIS_SEC_ENABLED defines as they are no longer used.
Fixes: fda5216fba55 ("crypto/aesni_mb: support DOCSIS protocol")
Cc: david.co...@intel.com
Signed-off-by: Brian Dooley
---
drivers/crypto/ipsec_mb/ipsec_mb_private.c | 4
drivers/crypto/ipsec_mb/pmd_aesni_mb.c |
On Mon, Jul 3, 2023 at 5:29 PM Thomas Monjalon wrote:
>
> 29/06/2023 14:58, christian.ehrha...@canonical.com:
> > From: Christian Ehrhardt
> >
> > By adding -j we build in parallel, to make building on multiprocessor
> > machines more effective. While that works it does also break
> > reproducibl
Add query for nic flow table support bit.
Fixes: 5f44fb1958e5 ("common/mlx5: query capability of registers")
Cc: bi...@nvidia.com
Signed-off-by: Ori Kam
Acked-by: Suanming Mou suanmi...@nvidia.com
---
drivers/common/mlx5/mlx5_devx_cmds.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drive
This patch supports symmetric hash function that creating same
hash result for bi-direction traffic which having reverse
source and destination IP and L4 port.
Since the hash algorithom is different than spec(XOR), leave a
warning in validation.
Signed-off-by: Xueming Li
---
doc/guides/nics/mlx
From: Michael Rossberg
ice only allowed to set peak information rate (PIR), while the hardware
also supports setting committed information rate (CIR). In many use
cases both values are needed, therefore add support for CIR.
Signed-off-by: Michael Rossberg
---
drivers/net/ice/ice_tm.c | 39
> -Original Message-
> From: Bing Zhao
> Sent: Saturday, July 1, 2023 12:27 PM
> Subject: [PATCH v2] app/testpmd: add IP length field matching
>
> Added support of parsing IPv4 total length and IPv6 payload length
> in the command line. The value of L3 length can be passed to the
> rte_
> -Original Message-
> From: Mattias Rönnblom
> Sent: Tuesday, July 4, 2023 10:44 PM
> To: Van Haaren, Harry ; Stephen Hemminger
>
> Cc: hof...@lysator.liu.se; dev@dpdk.org; Suanming Mou
> ; tho...@monjalon.net;
> david.march...@redhat.com; mattias.ronnblom
> ; sta...@dpdk.org
> Subject:
Due to recent changes to the default device socket ID, before
being used as an index for session mempool list,
set socket ID to 0 if unknown (-1).
Fixes: 7dcd73e37965 ("drivers/bus: set device NUMA node to unknown by default")
Cc: olivier.m...@6wind.com
Cc: sta...@dpdk.org
Signed-off-by: Kai Ji
Hi,
> -Original Message-
> From: Maayan Kashani
> Sent: Thursday, July 6, 2023 11:56 AM
> To: dev@dpdk.org
> Cc: Maayan Kashani ; Ori Kam ;
> Raslan Darawsheh ; Matan Azrad
> ; Slava Ovsiienko ; Suanming
> Mou
> Subject: [PATCH v3] net/mlx5: fix RSS expansion inner buffer overflow.
>
>
Hi Akhil,
> -Original Message-
> From: Akhil Goyal
> Sent: Tuesday 4 July 2023 20:45
> To: dev@dpdk.org
> Cc: tho...@monjalon.net; david.march...@redhat.com;
> jer...@marvell.com; ano...@marvell.com; ndabilpu...@marvell.com; De
> Lara Guarch, Pablo ;
> hemant.agra...@nxp.com; g.si...@nxp.
Due to recent changes to the default device socket ID,
before being used as an index for session mempool list,
the socket ID should be set to 0 if unknown (-1).
Fixes: 7dcd73e37965 ("drivers/bus: set device NUMA node to unknown by default")
Fixes: 64c469b9e7d8 ("app/crypto-perf: check range of soc
I've suggested 2 ways to do it
1. Data path enforcement by pcap pmd [PATCH v4]
http://patches.dpdk.org/project/dpdk/patch/20220606162147.57218-1-...@cgstowernetworks.com/
2. Control path only sets the underlying OS network interface MTU [PATCH v8]
http://patches.dpdk.org/project/dpdk/cover/2022062
03/07/2023 08:29, fengchengwen:
> Acked-by: Chengwen Feng
>
> On 2023/7/1 10:16, Stephen Hemminger wrote:
> > Simpler version of earlier patch which had a good idea, was just
> > implemented with more code than necessary.
> > If no device is specified don't start the capture loop.
> >
> > Report
On 7/6/2023 10:24 AM, Jiale, SongX wrote:
>> -Original Message-
>> From: Ferruh Yigit
>> Sent: Wednesday, July 5, 2023 10:32 PM
>> To: Singh, Aman Deep ; Zhang, Yuying
>> ; Burakov, Anatoly ;
>> Jie Hai
>> Cc: dev@dpdk.org; Thomas Monjalon ; David
>> Marchand ; sta...@dpdk.org; Jiale, Son
On 06-Jul-23 10:08 AM, Konstantin Ananyev wrote:
Hi Akhil,
Hi Konstantin,
Can you review this patch?
UDP header length is included in sa->hdr_len. Take care of that in
L3 header and pakcet length calculation.
Fixes: 01eef5907fc3 ("ipsec: support NAT-T")
Signed-off-by: Xiao Liang
---
li
> -Original Message-
> From: Ferruh Yigit
> Sent: Wednesday, July 5, 2023 5:32 PM
> To: Aman Singh ; Yuying Zhang
> ; Anatoly Burakov ;
> Jie Hai
> Cc: dev@dpdk.org; NBU-Contact-Thomas Monjalon (EXTERNAL)
> ; David Marchand ;
> sta...@dpdk.org; songx.ji...@intel.com; qiming.y...@intel.com
Thank you.
> -Original Message-
> From: Thomas Monjalon
> Sent: Thursday, July 6, 2023 5:37 PM
> To: Stephen Hemminger ; Bing Zhao
>
> Cc: dev@dpdk.org; Matan Azrad ; Slava Ovsiienko
> ; Ori Kam ; Suanming Mou
> ; Raslan Darawsheh ;
> dev@dpdk.org; Michael Baum
> Subject: Re: [PATCH 1/7
Define specific function implementation for ixgbe driver.
Currently, recycle buffer mode can support 128bit
vector path. And can be enabled both in fast free and
no fast free mode.
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Feifei Wang
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Naga
Add recycle mbufs engine for testpmd. This engine forward pkts with
I/O forward mode. But enable mbufs recycle feature to recycle used
txq mbufs for rxq mbuf ring, which can bypass mempool path and save
CPU cycles.
Suggested-by: Jerin Jacob
Signed-off-by: Feifei Wang
Reviewed-by: Ruifeng Wang
-
Define specific function implementation for i40e driver.
Currently, mbufs recycle mode can support 128bit
vector path and avx2 path. And can be enabled both in
fast free and no fast free mode.
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Feifei Wang
Reviewed-by: Ruifeng Wang
Reviewed-by: H
Add 'rte_eth_recycle_rx_queue_info_get' and 'rte_eth_recycle_mbufs'
APIs to recycle used mbufs from a transmit queue of an Ethernet device,
and move these mbufs into a mbuf ring for a receive queue of an Ethernet
device. This can bypass mempool 'put/get' operations hence saving CPU
cycles.
For eac
Currently, the transmit side frees the buffers into the lcore cache and
the receive side allocates buffers from the lcore cache. The transmit
side typically frees 32 buffers resulting in 32*8=256B of stores to
lcore cache. The receive side allocates 32 buffers and stores them in
the receive side so
1 - 100 of 126 matches
Mail list logo
