> -邮件原件-
> 发件人: dev 代表 Honnappa Nagarahalli
> 发送时间: Saturday, July 31, 2021 3:59 AM
> 收件人: dev@dpdk.org; Honnappa Nagarahalli
> ; tho...@monjalon.net;
> konstantin.anan...@intel.com; Feifei Wang (Arm Technology China)
>
> 抄送: Ruifeng Wang ; nd
> 主题: [dpdk-dev] [PATCH] doc: announce the d
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Thomas Monjalon
> Sent: Wednesday, 4 August 2021 15.30
>
> A bug with segmented packets has been discovered but the agreement
> to apply the fix is not concluded at the time of DPDK 21.08 release.
> This bug seems to be in DPDK for many years
> Subject: [PATCH] doc: announce restructuring of crypto session structs
>
> The structures rte_cryptodev_sym_session and rte_cryptodev_asym_session are
> not used by the application directly. The application just need an opaque
> pointer
> which it can attach to rte_crypto_op while enqueue.
> He
Reduced max chunk pool cache size from RTE_MEMPOOL_CACHE_MAX_SIZE(512)
to 128.
If chunk pool cache is empty, it gets filled during arm. Filling 512
entries at a time will fail arm if timeout is shorter.
Fixes: 0e792433d051 ("event/cnxk: create and free timer adapter")
Signed-off-by: Shijith Thot
> Subject: [EXT] Re: [PATCH] doc: announce changes in security session struct
>
>
> On Tue, Aug 3, 2021 at 5:36 AM Ananyev, Konstantin
> wrote:
> >
> >
> > > The structure rte_security_session is not directly used
> > > by the application. The application just need an opaque
> > > pointer to att
In crypto adapter metadata, reserved bytes in request info structure is
a space holder for response info. It enforces an order of operation if
the structures are updated using memcpy to avoid overwriting response
info. It is logical to move the reserved space out of request info. It
also solves the
On 6/29/2021 6:56 PM, Narcisa Ana Maria Vasile wrote:
From: Narcisa Vasile
rte_cpuset_t describes a set of CPUs by using an array of masks
named '_bits'. Each element in the '_bits' array represents
a bit mask, with each bit corresponding to a CPU.
The maximum number of CPUs is given by 'CPU_
2021-08-04 14:28 (UTC-0500), Sergey Madaminov:
> I've taken a look at this issue. As Dmitry said it is related to the bug
> within meson with having slashes escaping characters. It matters for the
> current meson build files in the DPDK for Windows as there is a reliance on
> strings for some file
From: Shahaf Shuler
For net/mlx4:
- removing Shahaf Shuler
- add Viacheslav Ovsiienko
For net/mlx5:
- removing Shahaf Shuler
Signed-off-by: Viacheslav Ovsiienko
---
MAINTAINERS | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/MAINTAINERS b/MAINTAIN
Hi again,
This is exactly the error with 0.58 that I was talking about. Try 0.57.2.
On Wed, Aug 4, 2021, 21:32 William Tu wrote:
> Hi,
> I got DPDK compiled on Windows, but suddenly I got this error when
> compiling DPDK on windows again. (And I don't know why it worked
> before...)
> [3/183] "
Hi,
I got DPDK compiled on Windows, but suddenly I got this error when
compiling DPDK on windows again. (And I don't know why it worked
before...)
[3/183] "clang" @lib/rte_eal-21.dll.rsp
FAILED: lib/rte_eal-21.dll
"clang" @lib/rte_eal-21.dll.rsp
clang: error: no such file or directory: 'librte_kvar
Corrected two typos that got added in the most recent merge.
Signed-off-by: Henry Nadeau
---
doc/guides/sample_app_ug/ioat.rst| 2 +-
doc/guides/sample_app_ug/vmdq_forwarding.rst | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/guides/sample_app_ug/ioat.rst
On Wed, Aug 4, 2021 at 6:30 AM Thomas Monjalon wrote:
>
> A bug with segmented packets has been discovered but the agreement
> to apply the fix is not concluded at the time of DPDK 21.08 release.
> This bug seems to be in DPDK for many years and should be fixed in 21.11.
>
> Suggested-by: Olivier
> Subject: [PATCH] doc: announce change in crypto adapter metadata
>
> In crypto adapter metadata, first 8 bytes of request info is a space
> holder for response info. For better clarity, reserved field should be
> removed from request info. New space for response info can be made by
> changing ty
In crypto adapter metadata, first 8 bytes of request info is a space
holder for response info. For better clarity, reserved field should be
removed from request info. New space for response info can be made by
changing type of event crypto metadata to structure from union.
Signed-off-by: Shijith T
> > IPsec xform struct would be updated to include IPsec SA lifetime
> > configuration. The existing member 'esn_soft_limit' would only track
> > ESN. And as sequence number control is getting introduced,
> > 'esn_soft_limit' may not indicate the number of packets processed.
> > Replace that wit
> Subject: [PATCH] doc: announce SA config option struct changes
>
> From: Archana Muniganti
>
> Propose new fields to support offloads like
> - IPsec inner checksum(L3/L4)
> - IPsec tunnel header verification
> - TSO
> - etc
> in the structure ``rte_security_ipsec_sa_options``.
>
> Signed-off-
https://bugs.dpdk.org/show_bug.cgi?id=777
Bug ID: 777
Summary: Potential error(e.g., resource leak, deadlock) due to
the unreleased lock pdata->i2c_mutex
Product: DPDK
Version: 20.11
Hardware: All
OS: All
https://bugs.dpdk.org/show_bug.cgi?id=776
Bug ID: 776
Summary: Potential error(e.g., resource leak, deadlock) due to
the unreleased lock pdata->phy_mutex
Product: DPDK
Version: 20.11
Hardware: All
OS: All
> IPsec xform struct would be updated to include IPsec SA lifetime
> configuration. The existing member 'esn_soft_limit' would only track
> ESN. And as sequence number control is getting introduced,
> 'esn_soft_limit' may not indicate the number of packets processed.
> Replace that with a new struc
> -Original Message-
> From: Kinsella, Ray
> Sent: Wednesday, August 4, 2021 8:14 PM
> To: Xueming(Steven) Li ; dpdk-dev
> Subject: Re: [PATCH v6 2/2] bus/auxiliary: introduce auxiliary bus
>
>
>
> On 04/08/2021 13:11, Xueming(Steven) Li wrote:
> >
> >
> >> -Original Message-
https://bugs.dpdk.org/show_bug.cgi?id=775
Bug ID: 775
Summary: Potential error(e.g., resource leak, deadlock) due to
the unreleased lock
Product: DPDK
Version: 20.11
Hardware: All
OS: All
Status:
Add tested platforms with Mellanox NICs to the 21.08 release notes.
Signed-off-by: Raslan Darawsheh
---
doc/guides/rel_notes/release_21_08.rst | 119 +
1 file changed, 119 insertions(+)
diff --git a/doc/guides/rel_notes/release_21_08.rst
b/doc/guides/rel_notes/release_2
https://bugs.dpdk.org/show_bug.cgi?id=774
Bug ID: 774
Summary: Potential deadlock error due to the unrelased lock
Product: DPDK
Version: 21.08
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
A new DPDK release candidate is ready for testing:
https://git.dpdk.org/dpdk/tag/?id=v21.08-rc4
There are 26 new patches in this snapshot,
for last critical fixes and some documentation updates.
Release notes:
https://doc.dpdk.org/guides/rel_notes/release_21_08.html
Please check
04/08/2021 13:34, jer...@marvell.com:
> --- a/doc/guides/prog_guide/traffic_metering_and_policing.rst
> +++ b/doc/guides/prog_guide/traffic_metering_and_policing.rst
> @@ -14,12 +14,13 @@ SW or mixed HW-SW implementation.
>
> The main features are:
>
> -* Part of DPDK rte_ethdev API
> -* Capabil
> -Original Message-
> From: Andrew Rybchenko
> Sent: Wednesday, August 4, 2021 8:28 PM
> To: Xueming(Steven) Li
> Cc: dev@dpdk.org; Ray Kinsella
> Subject: Re: [dpdk-dev] [PATCH 1/2] doc: announce eth queue release callback
> parameter change
>
> On 8/2/21 4:10 PM, Xueming Li wrote:
02/08/2021 14:36, Akhil Goyal:
> > One reserved byte in rte_crypto_op struct would be used to indicate
> > warnings and other information from the crypto/security operation. This
> > field will be used to communicate events such as soft expiry with IPsec
> > in lookaside mode.
> >
> > Signed-off-b
This script tracks the growth of stable and experimental symbols
over releases since v19.11. The script has the ability to
count the added symbols between two dpdk releases, and to
list experimental symbols present in two dpdk releases
(expired symbols).
example usages:
Count symbols added since
Hi Aaron,
>From: Aaron Conole
>Sent: Wednesday 14 July 2021 17:41
>To: dev@dpdk.org
>Cc: David Marchand ; Richardson, Bruce
>; Yigit, Ferruh ;
>Power, Ciara
>Subject: [PATCH v4] guides: add a guide for developing unit tests
>
>The DPDK testing infrastructure includes a comprehensive set of libra
This script tracks the growth of stable and experimental symbols
over releases since v19.11. The script has the ability to
count the added symbols between two dpdk releases, and to
list experimental symbols present in two dpdk releases
(expired symbols).
example usages:
Count symbols added since
2021-06-29 18:56 (UTC-0700), Narcisa Ana Maria Vasile:
> From: Narcisa Vasile
>
> rte_cpuset_t describes a set of CPUs by using an array of masks
> named '_bits'. Each element in the '_bits' array represents
> a bit mask, with each bit corresponding to a CPU.
> The maximum number of CPUs is given
> > > > The APIs which are internal to PMD and cryptodev library can be
> > > > marked as internal so that ABI checking do not shout for changes in
> > > > APIs which are internal to DPDK.
> > > >
> > > > Signed-off-by: Akhil Goyal
> > > Acked-by: Ajit Khaparde
> > Acked-by: Matan Azrad
> Acked-
> > > > Announce changes to add 2 unions. The first union will provide integral
> > > > and
> > > > bits access to version and IHL. The second union will provide integral
> > > > and
> > > bits
> > > > access to fragment flags and offset.
> > > >
> > > > Signed-off-by: Gregory Etelson
> > > Acke
> > > Moving struct rte_intr_handle as an internal structure to
> > > avoid any ABI breakages in future. Since this structure defines
> > > some static arrays and changing respective macros breaks the ABI.
> > > Eg:
> > > Currently RTE_MAX_RXTX_INTR_VEC_ID imposes a limit of maximum 512
> > > MSI-X
> > > The mbuf offload flags do not match the DPDK namespace (they are
> > > not prefixed by RTE_). Announce their rename in 21.11, and the
> > > removal of the old names in 22.11.
> > >
> > > A draft coccinelle script is provided to anticipate what the
> > > renaming will be.
> > >
> > > Signed-of
04/08/2021 15:53, Kinsella, Ray:
> On 04/08/2021 14:12, Thomas Monjalon wrote:
> > 04/08/2021 15:00, Xueming(Steven) Li:
> >> From: Kinsella, Ray
> >>> On 04/08/2021 13:11, Xueming(Steven) Li wrote:
> From: Kinsella, Ray
> > Its not strictly a depreciation notice though, you are not brea
> -Original Message-
> From: Kinsella, Ray
> Sent: Wednesday, August 4, 2021 5:50 PM
> To: Xueming(Steven) Li
> Cc: dev@dpdk.org; Wang Haiyue ; NBU-Contact-Thomas
> Monjalon ; Neil Horman
>
> Subject: Re: [PATCH v6 2/2] bus/auxiliary: introduce auxiliary bus
>
>
>
> On 25/06/2021 1
On 04/08/2021 14:12, Thomas Monjalon wrote:
> 04/08/2021 15:00, Xueming(Steven) Li:
>> From: Kinsella, Ray
>>> On 04/08/2021 13:11, Xueming(Steven) Li wrote:
From: Kinsella, Ray
> Its not strictly a depreciation notice though, you are not breaking
> anything right.
> Since yo
A bug with segmented packets has been discovered but the agreement
to apply the fix is not concluded at the time of DPDK 21.08 release.
This bug seems to be in DPDK for many years and should be fixed in 21.11.
Suggested-by: Olivier Matz
Signed-off-by: Thomas Monjalon
---
doc/guides/rel_notes/re
04/08/2021 15:00, Xueming(Steven) Li:
> From: Kinsella, Ray
> > On 04/08/2021 13:11, Xueming(Steven) Li wrote:
> > > From: Kinsella, Ray
> > >> Its not strictly a depreciation notice though, you are not breaking
> > >> anything right.
> > >> Since you are not breaking anything, don't think the n
04/08/2021 14:54, Raslan Darawsheh:
> Add tested platforms with Mellanox NICs to the 21.08 release notes.
>
> Signed-off-by: Raslan Darawsheh
Applied, thanks.
04/08/2021 16:20, Yan Xia:
> Add tested Intel platforms with Intel NICs to v21.08 release note.
>
> Signed-off-by: Yan Xia
Applied, thanks.
04/08/2021 13:38, Jiang, YuX:
> Hi Thomas and all,
> Update the test status for Intel part. Till now dpdk21.08-rc3 test is
> finished. No critical issue is found.
> One bug about https://bugs.dpdk.org/show_bug.cgi?id=768 is found, Nvidia's
> Dev. is working on it.
No, there is no work on NVIDIA
02/08/2021 07:32, Churchill Khangar:
> This patch fixes the memcpy function call which was incorrect and led
> to memory corruption for tables with more that just a few actions.
>
> Fixes: 742b0a57f50e4 ("pipeline: add table statistics to SWX")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Churchill K
On 8/4/21 11:08 AM, Slava Ovsiienko wrote:
-Original Message-
From: dev On Behalf Of Xueming Li
Sent: Monday, August 2, 2021 16:11
Cc: dev@dpdk.org; Xueming(Steven) Li ; Ray Kinsella
Subject: [dpdk-dev] [PATCH 2/2] doc: announce eth new offload flag and
group field
To support shared Rx
On 8/2/21 4:10 PM, Xueming Li wrote:
This patch announces the parameter change of eth_queue_release_t
callback API to eth_dev_ops in DPDK v21.11.
[1] mail list discussion:
https://mails.dpdk.org/archives/dev/2021-July/215654.html
Signed-off-by: Xueming Li
---
doc/guides/rel_notes/deprecation
On 04/08/2021 13:11, Xueming(Steven) Li wrote:
>
>
>> -Original Message-
>> From: Kinsella, Ray
>> Sent: Wednesday, August 4, 2021 7:46 PM
>> To: Xueming(Steven) Li
>> Subject: Re: [PATCH v6 2/2] bus/auxiliary: introduce auxiliary bus
>>
>>
>>
>> On 04/08/2021 12:21, Xueming(Steven)
On 8/3/21 9:10 PM, Ajit Khaparde wrote:
On Tue, Aug 3, 2021 at 1:58 AM Ori Kam wrote:
In the current implementation,
the action rte_flow_action_modify_field is not well defined
for fields larger than 64 bits (for example IPv6 source)
In addition, the byte order is also not well defined.
Both
> -Original Message-
> From: dev On Behalf Of Xueming Li
> Sent: Monday, August 2, 2021 16:11
> Cc: dev@dpdk.org; Xueming(Steven) Li ; Ray Kinsella
>
> Subject: [dpdk-dev] [PATCH 2/2] doc: announce eth new offload flag and
> group field
>
> To support shared Rx queue, this patch announce
PCI, vmbus, and auxiliary drivers printed a warning
when NUMA node had been reported as (-1) or not reported by OS:
EAL: Invalid NUMA socket, default to 0
This message and its level might confuse users because the configuration
is valid and nothing happens that requires attention or interve
On 04/08/2021 11:39, Thomas Monjalon wrote:
> 04/08/2021 11:34, Ray Kinsella:
>> Clarifying the ABI policy on the promotion of experimental APIS to stable.
>> We have a fair number of APIs that have been experimental for more than
>> 2 years. This policy amendment indicates that these APIs shoul
Hi Thomas and all,
Update the test status for Intel part. Till now dpdk21.08-rc3 test is finished.
No critical issue is found.
One bug about https://bugs.dpdk.org/show_bug.cgi?id=768 is found, Nvidia's Dev.
is working on it.
# Basic Intel(R) NIC testing
* Build or compile:
*Build: cover t
From: Jerin Jacob
Added a diagram to document meter library components
and added text for steps performed by the application to
configure the traffic meter and policing library.
Signed-off-by: Jerin Jacob
---
- Fix long lines in svg file to avoid patch apply issue
doc/guides/prog_guide/img/me
When an RTE flow uses a meter without any modify packet action,
there will be an internal drop flow with meter counter created,
matching the same 5-tuple as the original flow.
In this case, the meter flow count action is wrongly reused as the
original flow counter, leading to wrong flow statistics
Meters in one hierarchy might support different domains. For
example, one meter may support ingress only, but the root meter
can support all the domains.
If the later meter in the meter hierarchy wrongly doesn't inherit
the first meter's domains, it will lead to invalid domain table
access.
Fix i
1. fix the wrong flow statistics when flow contains both count/meter.
2. fix the wrong meter domain access when meters in hierarchy support
different domains.
Shun Hao (2):
net/mlx5: fix meter flow counter traslation
net/mlx5: fix domains detection in meter hierarchy
drivers/net/mlx5/mlx5_fl
From: Ajit Khaparde
> > The APIs which are internal to PMD and cryptodev library
> > can be marked as internal so that ABI checking do not
> > shout for changes in APIs which are internal to DPDK.
> >
> > Signed-off-by: Akhil Goyal
> Acked-by: Ajit Khaparde
Acked-by: Matan Azrad
04/08/2021 11:34, Ray Kinsella:
> Clarifying the ABI policy on the promotion of experimental APIS to stable.
> We have a fair number of APIs that have been experimental for more than
> 2 years. This policy amendment indicates that these APIs should be
> promoted or removed, or should at least form
A core dump is being generated with the following call stack:
0 _mm256_storeu_si256 (__A=..., __P=0x80)
1 rte_mov32 (src=0x2299c9140 "", dst=0x80)
2 rte_memcpy_aligned (n=60, src=0x2299c9140, dst=0x80)
3 rte_memcpy (n=60, src=0x2299c9140, dst=0x80)
4 mprq_buf_to_pkt (strd_cnt=1, strd_idx=0, buf=0x2
> >Updates the Minimal SW and HW Version offload support information for
> >Metering hierarchy.
> >
> >Signed-off-by: Jiawei Wang
> Acked-by: Asaf Penso
Squashed and applied, thanks.
On 25/06/2021 12:47, Xueming Li wrote:
> Auxiliary bus [1] provides a way to split function into child-devices
> representing sub-domains of functionality. Each auxiliary device
> represents a part of its parent functionality.
>
> Auxiliary device is identified by unique device name, sysfs path
On 06/07/2021 12:29, Radu Nicolau wrote:
> Add telemetry support for ipsec SAs
>
> Signed-off-by: Declan Doherty
> Signed-off-by: Radu Nicolau
> Signed-off-by: Abhijit Sinha
> Signed-off-by: Daniel Martin Buckley
> ---
> lib/ipsec/esp_inb.c | 1 +
> lib/ipsec/esp_outb.c | 12 +-
> lib
On 05/07/2021 16:21, Anatoly Burakov wrote:
> Use RTM and WAITPKG instructions to perform a wait-for-writes similar to
> what UMWAIT does, but without the limitation of having to listen for
> just one event. This works because the optimized power state used by the
> TPAUSE instruction will cause
On 25/06/2021 12:47, Xueming Li wrote:
> Auxiliary bus [1] provides a way to split function into child-devices
> representing sub-domains of functionality. Each auxiliary device
> represents a part of its parent functionality.
>
> Auxiliary device is identified by unique device name, sysfs path
03/08/2021 21:07, Ori Kam:
> MLX5 RegEx is only supported with FW version XX.30.1004 or lower.
>
> Signed-off-by: Ori Kam
> Acked-by: Asaf Penso
Applied, thanks.
> > UDP protocol reserves 0 checksum value for special purposes.
> > Other protocols, like IPv4, TCP and SCTP must calculate checksum value
> > in software or offload checksum calculation to hardware.
> >
> > If IPv4 TX checksum offload was off and header checksum was set to 0,
> > testpmd csum eng
Clarifying the ABI policy on the promotion of experimental APIS to stable.
We have a fair number of APIs that have been experimental for more than
2 years. This policy amendment indicates that these APIs should be
promoted or removed, or should at least form a conservation between the
maintainer an
04/08/2021 10:03, Dmitry Kozlyuk:
> PCI, vmbus, and auxiliary drivers printed a warning
> when NUMA node had been reported as (-1) or not reported by OS:
>
> EAL: Invalid NUMA socket, default to 0
>
> This message and its level might confuse users because the configuration
> is valid and no
03/08/2021 17:06, Gregory Etelson:
> The routine mlx5_eth_find_next() and related iterating macro
> MLX5_ETH_FOREACH_DEV is used to iterate through sibling devices (all
> representors share the same configuration and switching domain) on top
> of specified root device.
>
> The root device paramete
04/08/2021 09:26, Shun Hao:
> 1. fix the wrong flow statistics when flow contains both count/meter.
> 2. fix the wrong meter domain access when meters in hierarchy support
> different domains.
>
> Shun Hao (2):
> net/mlx5: fix meter flow counter traslation
> net/mlx5: fix domains detection in
04/08/2021 10:48, Min Hu (Connor):
> 在 2021/8/4 15:54, Thomas Monjalon 写道:
> > 04/08/2021 03:20, Min Hu (Connor):
> >> Hi, all,
> >> Features could be backport to TLS version? It is surprising.
> >
> > No it cannot, but you skipped the interesting part of the message:
> > "
> > They are not
在 2021/8/4 15:54, Thomas Monjalon 写道:
04/08/2021 03:20, Min Hu (Connor):
Hi, all,
Features could be backport to TLS version? It is surprising.
No it cannot, but you skipped the interesting part of the message:
"
They are not for LTS upstream, just for customer to cherrypick.
"
Hi, Th
>
> From: Ajit Khaparde
> > > The APIs which are internal to PMD and cryptodev library can be
> > > marked as internal so that ABI checking do not shout for changes in
> > > APIs which are internal to DPDK.
> > >
> > > Signed-off-by: Akhil Goyal
> > Acked-by: Ajit Khaparde
> Acked-by: Matan Azra
From: Zhihong Peng
This patch fixes the wrong way to obtain virtqueue.
The end of virtqueue cannot be judged based on whether
the array is NULL.
Fixes: 4e8169eb0d2d (net/virtio: fix Rx scatter offload)
Cc: sta...@dpdk.org
Signed-off-by: Zhihong Peng
---
drivers/net/virtio/virtio_ethdev.c | 4
https://bugs.dpdk.org/show_bug.cgi?id=773
Thomas Monjalon (ad...@dpdk.org) changed:
What|Removed |Added
CC||ad...@dpdk.org
Stat
04/08/2021 03:20, Min Hu (Connor):
> Hi, all,
> Features could be backport to TLS version? It is surprising.
No it cannot, but you skipped the interesting part of the message:
"
They are not for LTS upstream, just for customer to cherrypick.
"
> 在 2021/8/3 16:37, Wenjun Wu 写道:
> > enable Qin
https://bugs.dpdk.org/show_bug.cgi?id=773
Bug ID: 773
Summary: Technical Help
Product: DPDK
Version: 21.05
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
Priority: Normal
Com
https://bugs.dpdk.org/show_bug.cgi?id=772
Bug ID: 772
Summary: [dpdk-21.08]
vswitch_sample_cbdma/vm2vm_fwd_test_with_two_cbdma_cha
nnels: forward 8k packet failed when relaunch
dpdk-vhost
Product: DPDK
79 matches
Mail list logo
