On Thu, Jan 6, 2022 at 5:54 PM Morten Brørup wrote:
>
> A flush threshold for the mempool cache was introduced in DPDK version
> 1.3, but rte_mempool_do_generic_get() was not completely updated back
> then.
>
> The incompleteness did not cause any functional bugs, so this patch
> could be consider
29/11/2021 17:08, Josh Soref:
> -* dequeueing once we've filled up the queue, we have to benchmark it
> +* dequeuing once we've filled up the queue, we have to benchmark it
I think "dequeueing" is correct.
29/11/2021 17:08, Josh Soref:
> -* external phy devices registred through kerenl apis
> +* external phy devices registred through kernel apis
another spelling to fix:
"registred"
and while at it, "apis" should be "APIs"
- * When set to zero, simple forwaring path is eanbl
In csum forwarding mode, software UDP/TCP csum calculation only takes
the first segment into account while using the whole packet length so
the calculation will read invalid memory region with multi-segments
packets and will get wrong value.
This patch fixes this issue.
Signed-off-by: Xiaoyun Li
Add functions to call rte_raw_cksum_mbuf() to calculate IPv4/6
UDP/TCP checksum in mbuf which can be over multi-segments.
Signed-off-by: Xiaoyun Li
Acked-by: Aman Singh
Tested-by: Sunil Pai G
---
doc/guides/rel_notes/release_22_03.rst | 11 ++
lib/net/rte_ip.h | 186
Added functions to calculate UDP/TCP checksum for packets which may be
over multi-segments and fix the checksum issue with testpmd csum
forwarding mode.
Xiaoyun Li (2):
net: add functions to calculate UDP/TCP cksum in mbuf
testpmd: fix l4 sw csum over multi segments
---
v5:
* Fixed commit lo
On Tue, Nov 30, 2021 at 11:20 AM Ashwin Sekhar T K wrote:
>
> Update the CPU directive in ROC NPA assembly code snippets.
>
> Signed-off-by: Ashwin Sekhar T K
Update the git commit as
common/cnxk: update CPU directive in NPA assembly code
Use arch_extension instead of .cpu directive i
On 1/4/2022 9:10 PM, Li, Xiaoyun wrote:
Hi
-Original Message-
From: Li, Xiaoyun
Sent: Tuesday, January 4, 2022 15:19
To: Singh, Aman Deep; Yigit, Ferruh
;olivier.m...@6wind.com;
m...@smartsharesystems.com; Ananyev, Konstantin
;step...@networkplumber.org;
Medvedkin, Vladimir
Cc:dev@dpdk
> From: Olivier Matz [mailto:olivier.m...@6wind.com]
> Sent: Thursday, 6 January 2022 13.41
>
> On Thu, Jan 06, 2022 at 11:50:54AM +0100, Morten Brørup wrote:
> > > From: Olivier Matz [mailto:olivier.m...@6wind.com]
> > > Sent: Thursday, 6 January 2022 10.49
> >
> > Thank you for the thorough expl
On Thu, Jan 06, 2022 at 11:50:54AM +0100, Morten Brørup wrote:
> > From: Olivier Matz [mailto:olivier.m...@6wind.com]
> > Sent: Thursday, 6 January 2022 10.49
>
> Thank you for the thorough explanation, Olivier.
>
> Somewhat exotic scenarios, but they do make sense!
>
> As you might have guessed
On Tue, Nov 30, 2021 at 11:17 AM Ashwin Sekhar T K wrote:
>
> Before issuing the batch alloc, we clear the first word of
> cache lines so that NPA can update the status. Make sure that
> this line clear is flushed before the batch alloc is issued.
>
> Signed-off-by: Ashwin Sekhar T K
Changed cas
On Tue, Nov 30, 2021 at 11:11 AM Ashwin Sekhar T K wrote:
>
> When PLT_CACHE_LINE_SIZE is set to 64B, the memzone size reserved for
> NPA stack could be a multiple of 64B. In such a case, when NDC SYNC
> is initiated for the NPA LF, it could go and corrupt an additional
> 64B bytes as NDC flushes
A flush threshold for the mempool cache was introduced in DPDK version
1.3, but rte_mempool_do_generic_get() was not completely updated back
then.
The incompleteness did not cause any functional bugs, so this patch
could be considered refactoring for the purpose of cleaning up.
This patch complet
> From: Olivier Matz [mailto:olivier.m...@6wind.com]
> Sent: Thursday, 6 January 2022 10.49
Thank you for the thorough explanation, Olivier.
Somewhat exotic scenarios, but they do make sense!
As you might have guessed, I was wondering if rte_pktmbuf_reset_headroom()
could be optimized by simply
Hi Andrzej,
On Mon, Jan 03, 2022 at 03:22:01PM +0100, Andrzej Ostruszka wrote:
> ring: fix off by 1 mistake
I suggest something less scary for the title:
ring: optimize corner case for enqueue/dequeue
> When enqueueing/dequeueing to/from the ring we try to optimize by manual
> loop unrolling.
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Thursday, 6 January 2022 10.49
>
> 06/01/2022 09:23, Morten Brørup:
> > > From: Bruce Richardson [mailto:bruce.richard...@intel.com]
> > > Sent: Wednesday, 25 September 2019 16.56
> > >
> > > Add support for a new build option to turn of
> > Akhil Goyal (8):
> > ethdev: introduce IP reassembly offload
> > ethdev: add dev op for IP reassembly configuration
> > ethdev: add mbuf dynfield for incomplete IP reassembly
> > security: add IPsec option for IP reassembly
> > app/test: add unit cases for inline IPsec offload
> > a
On Mon, Jan 3, 2022 at 4:08 PM Akhil Goyal wrote:
>
> As discussed in the RFC[1] sent in 21.11, a new offload is
> introduced in ethdev for IP reassembly.
>
> This patchset add the RX offload and an application to test it.
> Currently, the offload is tested along with inline IPsec processing.
> It
Hi Morten,
On Thu, Jan 06, 2022 at 10:29:11AM +0100, Morten Brørup wrote:
> Hi Olivier,
>
> The data_room_size parameter description for the mbuf pool creation functions
> says:
> "Size of data buffer in each mbuf, including RTE_PKTMBUF_HEADROOM."
>
> Furthermore, both rte_mbuf_data_iova_defaul
06/01/2022 09:23, Morten Brørup:
> > From: Bruce Richardson [mailto:bruce.richard...@intel.com]
> > Sent: Wednesday, 25 September 2019 16.56
> >
> > Add support for a new build option to turn off certain drivers. Any
> > other
> > drivers which depend on the one being disabled will also be disable
On Wed, Jan 5, 2022 at 7:30 PM Tomasz Duszynski wrote:
>
> This series introduces a new rawdevice PMD which allows
> to manage userspace GPIOs and install custom GPIO interrupt
> handlers which bypass kernel. This is especially useful for
> applications that, besides providing standard dataplane f
Hi Olivier,
The data_room_size parameter description for the mbuf pool creation functions
says:
"Size of data buffer in each mbuf, including RTE_PKTMBUF_HEADROOM."
Furthermore, both rte_mbuf_data_iova_default() and rte_mbuf_data_addr_default()
simply add RTE_PKTMBUF_HEADROOM to the return value
Hi,
> -Original Message-
> From: Michael Baum
> Sent: Thursday, December 16, 2021 8:41 PM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Slava Ovsiienko ; Michael
> Baum ; sta...@dpdk.org
> Subject: [PATCH] common/mlx5: fix missing validation in devargs parsing
>
> From: Mic
Hi,
> -Original Message-
> From: Michael Baum
> Sent: Wednesday, December 8, 2021 4:52 PM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Slava Ovsiienko ; Michael
> Baum ; sta...@dpdk.org
> Subject: [PATCH] net/mlx5: fix the memory socket selection in ASO
> management
>
> Fr
Hi,
> -Original Message-
> From: Michael Baum
> Sent: Thursday, November 25, 2021 12:03 AM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Slava Ovsiienko ; Michael
> Baum ; sta...@dpdk.org
> Subject: [PATCH] common/mlx5: fix error handling in multi-class probe
>
> From: Mich
Hi Stephen,
Thanks for getting back. But I am looking at storing logs with timestamps in a
file, basically something similar to syslog. Could you help me with that ?
Regards,
Soumya
On 1/5/22, 8:17 AM, "Stephen Hemminger" wrote:
WARNING: This email originated from outside of Gigamon. Use
reported by code analysis tool C++test (version 10.4):
> /build/dpdk-20.11/drivers/net/nfp/nfpcore/nfp_target.h
> 375 Condition "island < 1" is always evaluated to false
> 415 Condition "island < 1" is always evaluated to false
> 547 Condition "target < 0" is always evaluated to false
All o
reported by code analysis tool C++test (version 10.4):
> /build/dpdk-20.11/drivers/net/nfp/nfp_net.c
> 546 Conditions "(hw->ctrl &NFP_NET_CFG_CTRL_ENABLE) &&
!! (hw->cap &NFP_NET_CFG_C" is always evaluated to false
> 547 Condition "! (hw->cap &NFP_NET_CFG_C" is always evaluated to fals
reported by code analysis tool C++test (version 10.4):
> /build/dpdk-20.11/drivers/bus/ifpga/ifpga_bus.c
> 67Condition "afu_dev" is always evaluated to true
> 81Condition "afu_dev" is always evaluated to true
The "for" loop already checks that afu_dev is not NULL.
Fixes: 05fa3d4a6539 ("b
> From: Bruce Richardson [mailto:bruce.richard...@intel.com]
> Sent: Wednesday, 25 September 2019 16.56
>
> Add support for a new build option to turn off certain drivers. Any
> other
> drivers which depend on the one being disabled will also be disabled
> with a
> suitable debug message.
>
> Sig
30 matches
Mail list logo
