DPDK patches and discussions
 help / color / mirror / Atom feed
From: Pei Zhang <pezhang@redhat.com>
To: luca.boccassi@gmail.com
Cc: stable@dpdk.org, dev@dpdk.org,
	 Abhishek Marathe <Abhishek.Marathe@microsoft.com>,
	Akhil Goyal <akhil.goyal@nxp.com>,
	 Ali Alnubani <alialnu@nvidia.com>,
	benjamin.walker@intel.com,
	 David Christensen <drc@linux.vnet.ibm.com>,
	hariprasad.govindharajan@intel.com,
	Hemant Agrawal <hemant.agrawal@nxp.com>,
	Ian Stokes <ian.stokes@intel.com>,
	 Jerin Jacob <jerinj@marvell.com>,
	John McNamara <john.mcnamara@intel.com>,
	 Ju-Hyoung Lee <juhlee@microsoft.com>,
	Kevin Traynor <ktraynor@redhat.com>,
	 Luca Boccassi <bluca@debian.org>,
	pingx.yu@intel.com, "xu, qian" <qian.q.xu@intel.com>,
	 Raslan Darawsheh <rasland@nvidia.com>,
	Thomas Monjalon <thomas@monjalon.net>,
	yuan.peng@intel.com, "Chen, Zhaoyan" <zhaoyan.chen@intel.com>
Subject: Re: [dpdk-dev] 20.11.3 patches review and test
Date: Mon, 23 Aug 2021 10:37:56 +0800	[thread overview]
Message-ID: <CAMp7QkmrBYPNf6FB5_3c3wtzCMf4YhxsNV9_uAQPPY7fAV_H5Q@mail.gmail.com> (raw)
In-Reply-To: <20210809084331.2724583-1-luca.boccassi@gmail.com>

Hello Luca,

The testing with dpdk 20.11.3-rc1 from Red Hat looks good. We tested below
16 scenarios and all got PASS on RHEL8:

(1)Guest with device assignment(PF) throughput testing(1G hugepage size):
PASS
(2)Guest with device assignment(PF) throughput testing(2M hugepage size) :
PASS
(3)Guest with device assignment(VF) throughput testing: PASS
(4)PVP (host dpdk testpmd as vswitch) 1Q: throughput testing: PASS
(5)PVP vhost-user 2Q throughput testing: PASS
(6)PVP vhost-user 1Q - cross numa node throughput testing: PASS
(7)Guest with vhost-user 2 queues throughput testing: PASS
(8)vhost-user reconnect with dpdk-client, qemu-server: qemu reconnect: PASS
(9)vhost-user reconnect with dpdk-client, qemu-server: ovs reconnect: PASS
(10)PVP 1Q live migration testing: PASS
(11)PVP 1Q cross numa node live migration testing: PASS
(12)Guest with ovs+dpdk+vhost-user 1Q live migration testing: PASS
(13)Guest with ovs+dpdk+vhost-user 1Q live migration testing (2M): PASS
(14)Guest with ovs+dpdk+vhost-user 2Q live migration testing: PASS
(15)Host PF + DPDK testing: PASS
(16)Host VF + DPDK testing: PASS

Versions:

kernel 4.18
qemu 6.0

dpdk: git://dpdk.org/dpdk-stable
# git log -1
commit c5f4e9dd155a4c99e219a734315b899d4340d304 (HEAD, tag: v20.11.3-rc1)
Author: Luca Boccassi <luca.boccassi@microsoft.com>
Date:   Mon Aug 9 09:25:41 2021 +0100

    version: 20.11.3-rc1

    Signed-off-by: Luca Boccassi <luca.boccassi@microsoft.com>

# git branch
remotes/origin/20.11

NICs: X540-AT2 NIC(ixgbe, 10G)

Best regards,

Pei

On Mon, Aug 9, 2021 at 4:43 PM <luca.boccassi@gmail.com> wrote:

> Hi all,
>
> Here is a list of patches targeted for stable release 20.11.3.
>
> The planned date for the final release is August 23rd.
>
> Please help with testing and validation of your use cases and report
> any issues/results with reply-all to this mail. For the final release
> the fixes and reported validations will be added to the release notes.
>
> A release candidate tarball can be found at:
>
>     https://dpdk.org/browse/dpdk-stable/tag/?id=v20.11.3-rc1
>
> These patches are located at branch 20.11 of dpdk-stable repo:
>     https://dpdk.org/browse/dpdk-stable/
>
> Thanks.
>
> Luca Boccassi
>
> ---
> Abhinandan Gujjar (1):
>       test/crypto: fix mempool size for session-less
>
> Ajit Khaparde (3):
>       doc: fix default burst size in testpmd
>       net/bnxt: fix Rx interrupt setting
>       net/bnxt: fix ring allocation and free
>
> Akhil Goyal (1):
>       crypto/octeontx: fix freeing after device release
>
> Alexander Kozyrev (1):
>       net/mlx5: fix threshold for mbuf replenishment in MPRQ
>
> Anoob Joseph (1):
>       crypto/octeontx2: fix IPsec session member overlap
>
> Arek Kusztal (1):
>       crypto/qat: disable asymmetric crypto on GEN3
>
> Asaf Penso (1):
>       net/mlx5: fix flow engine type in function name
>
> Beilei Xing (2):
>       net/iavf: fix scalar Rx
>       net/i40e: fix flow director input set conflict
>
> Bing Zhao (1):
>       net/mlx5: fix queue leaking in hairpin auto bind check
>
> Chenbo Xia (1):
>       net/virtio: fix default duplex mode
>
> Cheng Jiang (1):
>       net/virtio: fix refill order in packed ring datapath
>
> Chengchang Tang (2):
>       net/hns3: fix VLAN strip log
>       net/hns3: fix residual MAC address entry
>
> Chenglian Sun (1):
>       examples/l2fwd: fix [no-]mac-updating options
>
> Chengwen Feng (3):
>       net/hns3: fix Arm SVE build with GCC 8.3
>       net/hns3: fix filter parsing comment
>       net/hns3: fix flow rule list in multi-process
>
> Christian Ehrhardt (1):
>       vfio: add stdbool include
>
> Ciara Power (1):
>       cryptodev: fix freeing after device release
>
> Dana Vardi (5):
>       crypto/mvsam: fix AES-GCM session parameters
>       crypto/mvsam: fix session data reset
>       crypto/mvsam: fix options parsing
>       net/mvpp2: fix port speed overflow
>       net/mvpp2: fix configured state dependency
>
> Dapeng Yu (8):
>       net/ice: fix default RSS key generation
>       net/i40e: fix use after free in FDIR release
>       net/i40e: fix multi-process shared data
>       net/ixgbe: fix flow entry access after freeing
>       net/softnic: fix connection memory leak
>       net/softnic: fix memory leak in arguments parsing
>       net/softnic: fix null dereference in arguments parsing
>       net/softnic: fix memory leak as profile is freed
>
> David Christensen (1):
>       bus/pci: fix IOVA as VA support for PowerNV
>
> David Hunt (1):
>       distributor: fix 128-bit write alignment
>
> David Marchand (6):
>       malloc: fix size annotation for NUMA-aware realloc
>       bus/pci: fix leak for unbound devices
>       drivers/net: fix memzone allocations for DMA memory
>       ipc: stop mp control thread on cleanup
>       net/ice: fix memzone leak when firmware is missing
>       net/octeontx/base: fix debug build with clang
>
> Dmitry Kozlyuk (6):
>       doc: add limitation for ConnectX-4 with L2 in mlx5 guide
>       doc: fix build on Windows with Meson 0.58
>       net/mlx5: fix Rx/Tx queue checks
>       net/mlx5: fix indirect action modify rollback
>       eal/windows: cleanup virt2phys handle
>       bus: clarify log for non-NUMA-aware devices
>
> Feifei Wang (2):
>       crypto/qat: fix Arm build with special memcpy
>       net/mlx5: fix r/w lock usage in DMA unmap
>
> Ferruh Yigit (2):
>       kni: fix crash on userspace VA for segmented packets
>       app/testpmd: fix help string for port reset
>
> Gaoxiang Liu (1):
>       net/virtio: fix interrupt handle leak
>
> Ghalem Boudour (1):
>       net/ena: enable multi-segment in Tx offload flags
>
> Gregory Etelson (5):
>       net/mlx5: fix RSS pattern expansion
>       net/mlx5: fix pattern expansion in RSS flow rules
>       net/mlx5: fix representor interrupt handler
>       app/testpmd: fix Tx checksum calculation for tunnel
>       app/testpmd: fix IPv4 checksum
>
> Guoyang Zhou (3):
>       net/hinic: increase protection of the VLAN
>       net/hinic/base: fix LRO
>       net/hinic: fix MTU consistency with firmware
>
> Haiyue Wang (1):
>       net/iavf: fix RSS key access out of bound
>
> Hemant Agrawal (1):
>       bus/dpaa: fix freeing in FMAN interface destructor
>
> Henry Nadeau (1):
>       doc: fix spelling
>
> Hongbo Zheng (4):
>       graph: fix memory leak in stats
>       graph: fix null dereference in stats
>       net/hns3: increase VF reset retry maximum
>       net/hns3: fix timing of clearing interrupt source
>
> Huisong Li (7):
>       net/hns3: fix delay for waiting to stop Rx/Tx
>       net/hns3: fix fake queue rollback
>       net/hns3: fix maximum queues on configuration failure
>       app/testpmd: change port link speed without stopping all
>       net/hns3: fix Tx prepare after stop
>       sched: fix profile allocation failure handling
>       sched: rework configuration failure handling
>
> Ivan Ilchenko (8):
>       bitmap: fix buffer overrun in bitmap init
>       net/virtio: fix Rx scatter offload
>       net/sfc: fix MAC stats lock in xstats query by ID
>       net/sfc: fix reading adapter state without locking
>       net/sfc: fix xstats query by ID according to ethdev
>       net/sfc: fix xstats query by unsorted list of IDs
>       net/sfc: fix MAC stats update for stopped device
>       net/virtio: report maximum MTU in device info
>
> Ivan Malov (2):
>       net/sfc: check ID overflow in action port ID
>       net/sfc: fix outer match in MAE backend
>
> Jan Viktorin (1):
>       ethdev: fix doc of flow action
>
> Jasvinder Singh (1):
>       doc: remove old deprecation notice for sched
>
> Jiayu Hu (1):
>       vhost: fix lock on device readiness notification
>
> Jie Zhou (2):
>       app/testpmd: fix type of FEC mode parsing output
>       eal/windows: check callback parameter of alarm functions
>
> Joyce Kong (2):
>       net/i40e: fix descriptor scan on Arm
>       doc: update atomic operation deprecation
>
> Juraj Linkeš (1):
>       net/virtio: fix aarch32 build
>
> Kai Ji (2):
>       app/crypto-perf: fix out-of-place mempool allocation
>       crypto/aesni_gcm: fix performance on some AVX512 CPUs
>
> Kalesh AP (16):
>       net/bnxt: fix error messages in VNIC prepare
>       net/bnxt: set flow error when free filter not available
>       net/bnxt: remove unnecessary code
>       net/bnxt: fix error handling in VNIC prepare
>       net/bnxt: set flow error after tunnel redirection free
>       net/bnxt: use common function to free VNIC resource
>       net/bnxt: fix check for PTP support in FW
>       net/bnxt: improve probing log message
>       net/bnxt: remove unnecessary comment
>       net/bnxt: cleanup code
>       net/bnxt: fix typo in log message
>       net/bnxt: fix auto-negociation on Whitney+
>       net/bnxt: invoke device removal event on recovery failure
>       net/bnxt: clear cached statistics
>       net/bnxt: remove workaround for default VNIC
>       net/bnxt: fix null dereference in interrupt handler
>
> Kevin Laatz (1):
>       raw/ioat: fix config script queue size calculation
>
> Kevin Traynor (1):
>       doc: fix typo in SPDX tag
>
> Lance Richardson (6):
>       net/bnxt: fix Rx burst size constraint
>       app/test: fix IPv6 header initialization
>       net/bnxt: fix ring and context memory allocation
>       net/bnxt: fix Tx descriptor status implementation
>       net/bnxt: fix scalar Tx completion handling
>       net/bnxt: fix missing barriers in completion handling
>
> Liang Ma (1):
>       net/mlx5: export PMD-specific API file
>
> Lior Margalit (5):
>       net/mlx5: fix IPIP multi-tunnel validation
>       net/mlx5: fix RSS expansion for GTP
>       net/mlx5: reject inner ethernet matching in GTP
>       net/mlx5: fix RSS flow rule with L4 mismatch
>       net/mlx5: fix default queue number in RSS flow rule
>
> Martin Havlik (2):
>       net/bonding: fix error message on flow verify
>       net/bonding: check flow setting
>
> Maxime Coquelin (4):
>       vhost: fix missing memory table NUMA realloc
>       vhost: fix missing guest pages table NUMA realloc
>       vhost: fix NUMA reallocation with multi-queue
>       vhost: fix crash on reconnect
>
> Michael Baum (5):
>       common/mlx5: fix memory region leak
>       regex/mlx5: fix size of setup constants
>       vdpa/mlx5: fix overflow in queue attribute
>       net/mlx5: fix overflow in mempool argument
>       regex/mlx5: fix redundancy in device removal
>
> Michael Shamis (1):
>       crypto/mvsam: fix capabilities
>
> Michal Krawczyk (1):
>       net/ena: trigger reset on Tx prepare failure
>
> Naga Harish K S V (1):
>       eventdev: fix event port setup in Tx adapter
>
> Nathan Skrzypczak (1):
>       net/memif: fix abstract socket address length
>
> Nick Connolly (1):
>       build: support drivers symlink on Windows
>
> Nipun Gupta (1):
>       net/dpaa: fix headroom in VSP case
>
> Nithin Dabilpuram (1):
>       net/octeontx2: use runtime LSO format indices
>
> Olivier Matz (3):
>       test/mbuf: fix virtual address conversion
>       net/tap: fix Rx checksum flags on IP options packets
>       net/tap: fix Rx checksum flags on TCP packets
>
> Owen Hilyard (4):
>       flow_classify: fix leaking rules on delete
>       rib: fix max depth IPv6 lookup
>       tests/cmdline: fix memory leaks
>       tests/eal: fix memory leak
>
> Pavan Nikhilesh (1):
>       mempool/octeontx2: fix shift calculation
>
> Qi Zhang (3):
>       net/iavf: fix handling of unsupported promiscuous
>       net/ice: fix data path selection in secondary process
>       net/ice: fix data path in secondary process
>
> Rebecca Troy (3):
>       test/crypto: fix autotest function parameters
>       test/crypto: fix typo in AES case
>       test/crypto: fix typo in ESN case
>
> Richael Zhuang (1):
>       test/power: fix CPU frequency check for intel_pstate
>
> Ruifeng Wang (3):
>       net/sfc: fix aarch32 build
>       net/bnxt: fix aarch32 build
>       net/mlx5: remove redundant operations in NEON Rx
>
> Sarosh Arif (1):
>       net/mlx5: fix typo in vectorized Rx comments
>
> Satha Rao (1):
>       net/octeontx2: fix TM node statistics query
>
> Satheesh Paul (2):
>       net/octeontx2: fix flow creation limit on CN98xx
>       net/octeontx2: fix default MCAM allocation size
>
> Somnath Kotur (2):
>       net/bnxt: workaround spurious zero stats in Thor
>       net/bnxt: detect bad opaque in Rx completion
>
> Steve Yang (1):
>       net/i40e: fix raw packet flow director
>
> Suanming Mou (1):
>       net/mlx5: workaround drop action with old kernel
>
> Tejasree Kondoj (1):
>       crypto/octeontx2: fix lookaside IPsec IV pointer
>
> Thierry Herbelot (6):
>       net/bnxt: check access to possible null pointer
>       vhost/crypto: check request pointer before dereference
>       net/pfe: remove unnecessary null check
>       net/sfc: fix outer L4 checksum Rx
>       test/crypto: fix mbuf reset after null check
>       table: fix bucket empty check
>
> Thomas Monjalon (1):
>       devtools: fix file listing in maintainers check
>
> Tudor Cornea (1):
>       net/ice: fix overflow in maximum packet length config
>
> Viacheslav Ovsiienko (11):
>       net/mlx5: fix switchdev mode recognition
>       common/mlx5: fix Netlink port name padding in probing
>       net/mlx5: fix multi-segment inline for the first segments
>       net/mlx5: fix TSO multi-segment inline length
>       common/mlx5: fix Netlink receive message buffer size
>       common/mlx5: use new port query API if available
>       common/mlx5: fix compatibility with OFED port query API
>       app/testpmd: fix offloads for newly attached port
>       net/mlx5: fix RoCE LAG bond device probing
>       net/mlx5: fix timestamp initialization on empty clock queue
>       net/mlx5: add Tx scheduling check on queue creation
>
> Weifeng Li (1):
>       net/bnxt: fix nested lock during bonding
>
> Xiao Wang (1):
>       vhost: check header for legacy dequeue offload
>
> Xiaoyu Min (5):
>       net/mlx5: fix match MPLS over GRE with key
>       net/mlx5: remove unsupported flow item MPLS over IP
>       net/mlx5: fix MPLS RSS expansion
>       net/mlx5: fix missing RSS expandable items
>       net/mlx5: fix missing RSS expansion of IPv6 frag
>
> Xiaoyun Li (1):
>       net/iavf: fix Tx threshold check
>
> Xueming Li (1):
>       vdpa/mlx5: fix TSO offload without checksum
>
> Yunjian Wang (1):
>       kni: fix mbuf allocation for kernel side use
>
> Yuying Zhang (1):
>       app/testpmd: fix MAC address after port reset
>
>

  parent reply	other threads:[~2021-08-23  2:38 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-09  8:43 luca.boccassi
2021-08-13 11:42 ` Jiang, YuX
2021-08-13 13:31   ` Luca Boccassi
2021-08-13 14:25     ` David Hunt
2021-08-23 15:30   ` Luca Boccassi
2021-08-26 10:09     ` Christian Ehrhardt
2021-08-26 12:20       ` Luca Boccassi
2021-08-19 12:10 ` Ali Alnubani
2021-08-19 14:31   ` Luca Boccassi
2021-08-23  2:37 ` Pei Zhang [this message]
2021-08-23 10:08   ` Luca Boccassi

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAMp7QkmrBYPNf6FB5_3c3wtzCMf4YhxsNV9_uAQPPY7fAV_H5Q@mail.gmail.com \
    --to=pezhang@redhat.com \
    --cc=Abhishek.Marathe@microsoft.com \
    --cc=akhil.goyal@nxp.com \
    --cc=alialnu@nvidia.com \
    --cc=benjamin.walker@intel.com \
    --cc=bluca@debian.org \
    --cc=dev@dpdk.org \
    --cc=drc@linux.vnet.ibm.com \
    --cc=hariprasad.govindharajan@intel.com \
    --cc=hemant.agrawal@nxp.com \
    --cc=ian.stokes@intel.com \
    --cc=jerinj@marvell.com \
    --cc=john.mcnamara@intel.com \
    --cc=juhlee@microsoft.com \
    --cc=ktraynor@redhat.com \
    --cc=luca.boccassi@gmail.com \
    --cc=pingx.yu@intel.com \
    --cc=qian.q.xu@intel.com \
    --cc=rasland@nvidia.com \
    --cc=stable@dpdk.org \
    --cc=thomas@monjalon.net \
    --cc=yuan.peng@intel.com \
    --cc=zhaoyan.chen@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).