23.11.7 patches review and test

23.11.7 patches review and test

[Shani Peretz]

Hi all,

Here is a list of patches targeted for stable release 23.11.7.

The planned date for the final release is 30 April 2026.

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=v23.11.7-rc1

These patches are located at branch 23.11 of dpdk-stable repo:
    https://dpdk.org/browse/dpdk-stable/

Thanks.

Shani

---
Aarnav JP (2):
      examples/packet_ordering: fix format specifier for port ID
      examples/ptpclient: fix format specifier for port ID

Anatoly Burakov (12):
      net/ixgbe: fix memory leak in security flows
      net/ixgbe: fix potential null dereference with IPsec config
      net/ixgbe: fix potential null dereference in IPsec flow
      net/ixgbe: fix pointer handling in IPsec
      net/i40e: move filter config to flow create
      net/i40e: fix IPv6 GTPU handling
      net/iavf: fix memory leak on egress IPsec flows
      net/iavf: fix memory leak on uninit
      net/iavf: fix IPv4 flow subscription
      net/ice: fix memory leak in DCF QoS bandwidth config
      net/ice: fix memory leak in FDIR flow parsing
      net/iavf: fix struct size in IPsec status get

Anurag Mandal (3):
      app/testpmd: fix function names in logs
      net/i40e: fix QinQ stripping
      net/iavf: fix deletion of primary MAC address

Ashok Kumar Natarajan (5):
      net/axgbe: fix MAC TCR speed select field width
      net/axgbe: add 100 Mbps MAC speed select
      net/axgbe: fix auto-negotiation capabilities
      net/axgbe: fix SGMII auto-negotiation status bits
      net/axgbe: fix 100M SGMII mode

Bruce Richardson (31):
      net/iavf: revert check for PF Rx timestamp support
      rcu: fix build with MSVC
      test/red: fix some undefined behaviour
      test/timer: fix hang on secondary process failure
      buildtools/test: suppress empty output
      eal: fix variable shadowing
      bbdev: fix variable shadowing
      ethdev: fix variable shadowing
      eventdev: fix variable shadowing
      net: fix variable shadowing
      pcapng: fix variable shadowing
      pipeline: fix variable shadowing
      power: fix variable shadowing
      table: fix variable shadowing
      bus/pci: fix variable shadowing
      net/cpfl: fix variable shadowing
      net/e1000: fix variable shadowing
      net/i40e: fix variable shadowing
      net/ice: fix variable shadowing
      net/ixgbe: fix variable shadowing
      app/graph: fix variable shadowing
      app/pdump: fix variable shadowing
      app/testpmd: fix variable shadowing
      config/arm: fix 32-bit build
      hash: fix maybe-uninitialized warnings on build
      net/intel: fix memory leak on Tx queue setup failure
      test: fix dependencies on net null driver
      hash: fix overflow of 32-bit offsets
      test/security: skip inline protocol test if no HW support
      net/bonding: clamp Rx free threshold for small rings
      usertools/pmdinfo: fix search for PMD info string

Chengwen Feng (2):
      net/hns3: fix outer UDP checksum with simple BD
      eal: introduce more macros for bit definition

Ciara Loftus (7):
      doc: fix TSO and checksum offload feature status for ice
      doc: fix TSO feature status for iavf
      doc: fix inline crypto feature status for iavf
      doc: fix TSO feature status for i40e
      net/i40e: validate raw flow items before dereferencing
      doc: remove references to obsolete testpmd flag
      net/i40e: fix raw flow item validation

Congjie Zhou (1):
      eal/linux: fix fbarray name collision in containers

Dariusz Sosnowski (10):
      app/testpmd: fix flow queue job leaks
      net/mlx5: fix flow mark reading after reconfigure
      net/mlx5: fix shared Rx queue limitations
      common/mlx5: fix bonding check
      net/mlx5: fix bonding check
      net/mlx5: fix probing to allow BlueField Socket Direct
      net/mlx5: fix VLAN strip info for CQE compression
      net/mlx5: fix flex item capability check
      common/mlx5: fix error logging for queue modify
      net/mlx5: report share group and queue ID

David Marchand (9):
      bus/ifpga: fix const pointer in device name parsing
      crypto/caam_jr: fix const pointer in UIO filename parsing
      net/enetfec: fix const pointer in UIO filename parsing
      net/memif: fix const pointer in socket check
      app/procinfo: fix const pointer in collectd format
      net/tap: remove log when running without multiprocess
      net/af_xdp: fix external mbuf transmit
      common/mlx5: fix MAC deletion on Linux
      examples/vm_power_manager: fix format specifier for port ID

Emma Finn (1):
      examples/fips_validation: fix dangling pointers

Garvit Varshney (1):
      crypto/cnxk: return decrypted data for RSA verify

Gregory Etelson (3):
      net: fix packet type for stacked VLAN
      net/mlx5: fix MPESW PF probe for any number of ports
      net/mlx5: fix IPv6 SRH flex node header length

Itai Sharoni (1):
      net/mlx5/windows: fix MAC address ownership tracking

Ivan Malov (4):
      common/sfc_efx/base: fix flow control on legacy MCDI
      net/sfc: rework capability check that is done on FEC set
      net/sfc: drop AUTO from FEC capabilities and fix comment
      net/sfc: fix reporting status of autonegotiation

Jacob Keller (1):
      net/iavf: negotiate PTP before reporting Rx timestamping

John McNamara (1):
      net/i40e: fix unused variable

Kai Ji (1):
      crypto/openssl: fix SM2 public key buffer overflow

Kevin Traynor (5):
      eal/linux: handle interrupt epoll events
      interrupts: add interrupt event info
      net/mlx5: check DevX disconnect/error interrupt events
      examples/ipsec-secgw: fix build with glibc 2.43
      examples/vm_power: check truncation of socket path

Liangxing Wang (1):
      app/dma-perf: fix reversed CPU copy

Long Li (14):
      net/netvsc: fix race conditions on VF add/remove events
      net/netvsc: support multi-process VF device removal
      net/mana: fix PD resource leak on device close
      net/netvsc: fix devargs memory leak on hotplug
      net/mana: fix fast-path ops setup in secondary process
      net/mlx5: fix fast-path ops setup in secondary process
      net/mlx4: fix fast-path ops setup in secondary process
      net/netvsc: fix subchannel leak on device removal
      net/netvsc: fix double-free of primary Rx queue on uninit
      net/netvsc: fix resource leak on init failure
      net/netvsc: fix event callback leak on Rx filter failure
      net/netvsc: fix resource leaks on MTU change
      net/mana: fix CQE suppression handling on error completions
      net/netvsc: switch data path to synthetic on device stop

Luca Boccassi (1):
      test/debug: fix IOVA mode on PPC64 without huge pages

Maayan Kashani (1):
      net/mlx5: fix redundant control rules in promiscuous mode

Maciej Paczkowski (1):
      net/ice/base: fix integer types in comparisons

Marat Khalili (6):
      bpf: fix x86 call stack alignment for external calls
      bpf: disallow empty program
      bpf: fix add/subtract overflow
      bpf: fix starting with conditional jump
      bitops: allow variable as first argument of shift macros
      bpf: fix signed shift overflows in ARM JIT

Martin Spinler (5):
      net/nfb: use constant values for max Rx/Tx queues count
      net/nfb: fix bad pointer access in queue stats
      net/nfb: use process private variable for internal
      net/nfb: fix resources release
      net/nfb: stop only started queues in fail path

Maxime Coquelin (3):
      vhost: fix virtqueue array size for control queue
      vhost: fix descriptor chain bounds check in control queue
      vhost: fix mmap error check in VDUSE IOTLB miss handler

Maxime Leroy (8):
      net/dpaa2: warn on Rx descriptor limit in high perf mode
      net/dpaa2: fix resource leak on soft parser failure
      net/dpaa2: fix link after port stop/start
      net/dpaa2: fix spurious VLAN insertion on non-VLAN packet
      net/dpaa2: fix L4 packet type in slow parse path
      net/dpaa2: fix L3/L4 checksum offload flags
      net/dpaa2: fix burst mode info
      net/dpaa2: add SG table walk upper bound in Rx

Morten Brørup (2):
      eal: fix cache guard for pedantic compilation
      mbuf: fix packet data read

Nithinsen Kaithakadan (1):
      test/crypto: fix mbuf segment number

Pavan Nikhilesh (1):
      event/cnxk: fix Rx offload flags

Piotr Krzewinski (1):
      cryptodev: fix memory corruption in secondary process

Radu Nicolau (1):
      pdcp: add digest physical address

Rahul Bhansali (1):
      event/cnxk: fix crash on CN10K

Rakesh Kudurumalla (2):
      common/cnxk: fix engine capabilities fetch logic
      examples/l2fwd-jobstats: fix stats availability

Robin Jarry (3):
      net/iavf: fix reported max Tx and Rx queues
      telemetry: fix adding dict in container array
      hash: avoid leaking entries on RCU defer queue failure

Rongwei Liu (1):
      net/mlx5: fix job leak on indirect meter creation failure

Sergei Iashin (1):
      eventdev/eth_rx: fix crash with telemetry

Shaiq Wani (1):
      net/idpf: fix typo in CQ scan threshold macro name

Shani Peretz (6):
      examples/ethtool: fix size of mempool name
      net/mlx5/hws: fix stack alignment for ASan compatibility
      net/mlx5/hws: fix null dereference in rule skip
      net/mlx5: allow MTU mismatch for running shared queue
      app/testpmd: fix memory leak in port flow configure
      net/mlx5: fix meter ASO action leak on release to pool

Song Yoong Siang (3):
      net/e1000: use device timestamp for clock read in igc
      net/e1000: fix allocation of context desc for launch time
      net/e1000: fix igc launch time calculation

Sriram Yagnaraman (2):
      net/memif: fix descriptor Tx flags corruption
      net/memif: fix multi-segment Rx corruption

Stephen Hemminger (26):
      bus/fslmc: fix const pointer in device name parsing
      common/cnxk: fix array out-of-bounds
      examples/fips_validation: fix RSA memcpy
      net/bnxt: fix build with GCC 16
      test/table: avoid input line overflow
      test/crypto: check for vdev args overflow
      pcapng: document return values
      pcapng: use malloc instead of fixed buffer size
      pcapng: chain additional mbuf when comment exceeds tailroom
      test/pcapng: skip test if null driver missing
      net/mlx5: fix use-after-free in ASO management init
      net/tap: use correct length for interface names
      net/tap: fix resource leaks in secondary process probe
      net/tap: free IPC reply buffer on queue count mismatch
      net/tap: fix use-after-free on remote flow creation failure
      net/tap: free remote flow when implicit rule already exists
      test/pcapng: fix for Windows
      test: add pause to synchronization spinloops
      test/atomic: scale test based on core count
      test/mcslock: scale test based on core count
      test/stack: scale test based on core count
      test/timer: scale test based on core count
      test/timer: replace volatile with C11 atomics
      test: add file-prefix for all fast-tests on Linux
      test/trace: fix parallel execution with traces enabled
      examples/vmdq_dcb: initialize all configuration structures

Talluri Chaitanyababu (1):
      app/testpmd: fix DCB forwarding TC mismatch handling

Thierry Herbelot (1):
      net/intel: update key length when getting RSS key

Thomas Monjalon (4):
      common/mlx5: fix variable shadowing
      net/mvpp2: fix variable shadowing
      eal/x86: fix TSC frequency query
      examples/ethtool: fix error message about ports limit

Venkatesh Vemula (1):
      net/intel: fix comma operator warnings

Viacheslav Ovsiienko (2):
      net/mlx5: fix flex parser creation length attribute
      net/mlx5: fix send skew settings when using wait on time

Vipin Varghese (1):
      app/dma-perf: fix buffer overflow with high core count

Vladimir Medvedkin (1):
      fib: fix prefix addition handling

Xavier Guillaume (1):
      net/af_packet: fix MTU set data size calculation

Xiaoyu Min (1):
      net/mlx5: fix HW flow counter query

Yang Xu (1):
      net/mlx5: fix port down in link detection failure

Yunjian Wang (1):
      net/mlx5: fix memory leak after device spawn failure

Re: 23.11.7 patches review and test

[Ali Alnubani]

On 4/21/26 9:46 AM, Shani Peretz wrote:

> Hi all,
>
> Here is a list of patches targeted for stable release 23.11.7.
>
> The planned date for the final release is 30 April 2026.
>
> 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=v23.11.7-rc1
>
> These patches are located at branch 23.11 of dpdk-stable repo:
>      https://dpdk.org/browse/dpdk-stable/
>
> Thanks.
>
> Shani
>
> ---
Hello,

We ran the following functional tests with Nvidia hardware on v23.11.7-rc1:
- Basic functionality:
   Send and receive multiple types of traffic.
- testpmd xstats counter test.
- testpmd timestamp test.
- Changing/checking link status through testpmd.
- rte_flow tests (See https://doc.dpdk.org/guides/nics/mlx5.html for 
supported features)
- RSS tests.
- VLAN filtering, stripping, and insertion tests.
- Checksum and TSO tests.
- ptype tests.
- link_status_interrupt example application tests.
- l3fwd-power example application tests.
- Multi-process example applications tests.
- Hardware LRO tests.
- Buffer Split tests.
- Tx scheduling tests.

Testing environments:
- NIC: ConnectX-6 Dx / OS: Ubuntu 22.04 / Driver: 
MLNX_OFED_LINUX-23.10-6.1.6.1 / Firmware: 22.39.5124
- NIC: ConnectX-7 / OS: Ubuntu 22.04 / Driver: 
MLNX_OFED_LINUX-23.10-6.1.6.1 / Firmware: 28.39.5124
- DPU: BlueField-2 / DOCA SW version: 2.5.5 / Firmware: 24.39.5124

We don't see new issues caused by the changes in this release.

Thanks,
Ali

RE: 23.11.7 patches review and test

[Xu, HailinX]

> -----Original Message-----
> From: Shani Peretz <shperetz@nvidia.com>
> Sent: Tuesday, April 21, 2026 2:47 PM
> To: stable@dpdk.org
> Cc: dev@dpdk.org; Abhishek Marathe <Abhishek.Marathe@microsoft.com>;
> Ali Alnubani <alialnu@nvidia.com>; benjamin.walker@intel.com; David
> Christensen <drc@linux.vnet.ibm.com>; Hemant Agrawal
> <hemant.agrawal@nxp.com>; Ian Stokes <ian.stokes@intel.com>; Jerin Jacob
> <jerinj@marvell.com>; Mcnamara, John <john.mcnamara@intel.com>; Ju-
> Hyoung Lee <juhlee@microsoft.com>; Kevin Traynor <ktraynor@redhat.com>;
> Luca Boccassi <bluca@debian.org>; Pei Zhang <pezhang@redhat.com>;
> qian.q.xu@intel.com; Raslan Darawsheh <rasland@nvidia.com>; Thomas
> Monjalon <thomas@monjalon.net>; Yanghang Liu <yanghliu@redhat.com>;
> yuan.peng@intel.com; zhaoyan.chen@intel.com
> Subject: 23.11.7 patches review and test
> 
> Hi all,
> 
> Here is a list of patches targeted for stable release 23.11.7.
> 
> The planned date for the final release is 30 April 2026.
> 
> 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=v23.11.7-rc1
> 
> These patches are located at branch 23.11 of dpdk-stable repo:
>     https://dpdk.org/browse/dpdk-stable/
> 
> Thanks.
> 
> Shani
> 
> ---
Update the test status for Intel part. dpdk23.11.7-rc1 all validation test done. found 1 new issue and fixed.

DPDK build failed with clang21.1.8 on Fedora43:  -- Fixed

* Build & CFLAG compile: cover the build test with latest GCC/Clang version on the following OS(all passed)
  - Ubuntu25.04/Ubuntu24.04.3
  - RHEL9.6/RHEL10
  - Fedora43
  - FreeBSD15
  - SUSE16
  - OpenAnolis8.10
  - AzureLinux3.0

* Function tests: All test done and passed
  - i40E-(XXV710, X722) PF/VF: test scenarios including basic/RTE_FLOW/TSO/Jumboframe/checksum offload/mac_filter/VLAN/VXLAN/RSS, etc. 
  - IXGBE-(82599) PF/VF: test scenarios including basic/RTE_FLOW/TSO/Jumboframe/checksum offload/mac_filter/VLAN/VXLAN/RSS, etc. 
  - ICE-(E810, E2100) PF/VF: test scenarios including basic/Switch/Package Management/Flow Director/Advanced Tx/Advanced RSS/ACL/DCF/Flexible Descriptor, etc.
  - IPsec: test scenarios including ipsec/ipsec-gw/ipsec library basic test - QAT&SW/FIB library, etc.
  - Virtio: both function and performance test are covered. Such as PVP/Virtio_loopback/virtio-user loopback/virtio-net VM2VM perf testing/VMAWARE ESXI 8.0, etc.
  - Cryptodev: test scenarios including Cryptodev API testing/CompressDev ISA-L/QAT/ZLIB PMD Testing/FIPS, etc.
  - DLB: test scenarios including DLB2.0 and DLB2.5
  - Other: test scenarios including AF_XDP, Power, CBDMA, DSA

* Performance test: All test done and passed
  - Thoughput Performance
  - Cryptodev Latency
  - PF/VF NIC single core
  - XXV710/E810 NIC Performance


Regards,
Xu, Hailin

Re: 23.11.7 patches review and test

[Kevin Traynor]

On 4/21/26 7:46 AM, Shani Peretz wrote:
> Hi all,
> 
> Here is a list of patches targeted for stable release 23.11.7.
> 
> The planned date for the final release is 30 April 2026.
> 
> 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=v23.11.7-rc1
> 
> These patches are located at branch 23.11 of dpdk-stable repo:
>     https://dpdk.org/browse/dpdk-stable/
> 
> Thanks.
> 

Hi Shani,

As discussed on thread [0] there was a quite serious regression caused
by "net: fix packet type for stacked VLAN"

As discussion on the fix is ongoing, I would suggest to just revert this
patch for your release.

It doesn't require a new RC and re-validation as it's an isolated issue
(and there wasn't test cases to catch before Robin's new patch anyway)

thanks,
Kevin.

[0] https://mails.dpdk.org/archives/dev/2026-April/336248.html

> Shani
> 
> ---
> Aarnav JP (2):
>       examples/packet_ordering: fix format specifier for port ID
>       examples/ptpclient: fix format specifier for port ID
> 
> Anatoly Burakov (12):
>       net/ixgbe: fix memory leak in security flows
>       net/ixgbe: fix potential null dereference with IPsec config
>       net/ixgbe: fix potential null dereference in IPsec flow
>       net/ixgbe: fix pointer handling in IPsec
>       net/i40e: move filter config to flow create
>       net/i40e: fix IPv6 GTPU handling
>       net/iavf: fix memory leak on egress IPsec flows
>       net/iavf: fix memory leak on uninit
>       net/iavf: fix IPv4 flow subscription
>       net/ice: fix memory leak in DCF QoS bandwidth config
>       net/ice: fix memory leak in FDIR flow parsing
>       net/iavf: fix struct size in IPsec status get
> 
> Anurag Mandal (3):
>       app/testpmd: fix function names in logs
>       net/i40e: fix QinQ stripping
>       net/iavf: fix deletion of primary MAC address
> 
> Ashok Kumar Natarajan (5):
>       net/axgbe: fix MAC TCR speed select field width
>       net/axgbe: add 100 Mbps MAC speed select
>       net/axgbe: fix auto-negotiation capabilities
>       net/axgbe: fix SGMII auto-negotiation status bits
>       net/axgbe: fix 100M SGMII mode
> 
> Bruce Richardson (31):
>       net/iavf: revert check for PF Rx timestamp support
>       rcu: fix build with MSVC
>       test/red: fix some undefined behaviour
>       test/timer: fix hang on secondary process failure
>       buildtools/test: suppress empty output
>       eal: fix variable shadowing
>       bbdev: fix variable shadowing
>       ethdev: fix variable shadowing
>       eventdev: fix variable shadowing
>       net: fix variable shadowing
>       pcapng: fix variable shadowing
>       pipeline: fix variable shadowing
>       power: fix variable shadowing
>       table: fix variable shadowing
>       bus/pci: fix variable shadowing
>       net/cpfl: fix variable shadowing
>       net/e1000: fix variable shadowing
>       net/i40e: fix variable shadowing
>       net/ice: fix variable shadowing
>       net/ixgbe: fix variable shadowing
>       app/graph: fix variable shadowing
>       app/pdump: fix variable shadowing
>       app/testpmd: fix variable shadowing
>       config/arm: fix 32-bit build
>       hash: fix maybe-uninitialized warnings on build
>       net/intel: fix memory leak on Tx queue setup failure
>       test: fix dependencies on net null driver
>       hash: fix overflow of 32-bit offsets
>       test/security: skip inline protocol test if no HW support
>       net/bonding: clamp Rx free threshold for small rings
>       usertools/pmdinfo: fix search for PMD info string
> 
> Chengwen Feng (2):
>       net/hns3: fix outer UDP checksum with simple BD
>       eal: introduce more macros for bit definition
> 
> Ciara Loftus (7):
>       doc: fix TSO and checksum offload feature status for ice
>       doc: fix TSO feature status for iavf
>       doc: fix inline crypto feature status for iavf
>       doc: fix TSO feature status for i40e
>       net/i40e: validate raw flow items before dereferencing
>       doc: remove references to obsolete testpmd flag
>       net/i40e: fix raw flow item validation
> 
> Congjie Zhou (1):
>       eal/linux: fix fbarray name collision in containers
> 
> Dariusz Sosnowski (10):
>       app/testpmd: fix flow queue job leaks
>       net/mlx5: fix flow mark reading after reconfigure
>       net/mlx5: fix shared Rx queue limitations
>       common/mlx5: fix bonding check
>       net/mlx5: fix bonding check
>       net/mlx5: fix probing to allow BlueField Socket Direct
>       net/mlx5: fix VLAN strip info for CQE compression
>       net/mlx5: fix flex item capability check
>       common/mlx5: fix error logging for queue modify
>       net/mlx5: report share group and queue ID
> 
> David Marchand (9):
>       bus/ifpga: fix const pointer in device name parsing
>       crypto/caam_jr: fix const pointer in UIO filename parsing
>       net/enetfec: fix const pointer in UIO filename parsing
>       net/memif: fix const pointer in socket check
>       app/procinfo: fix const pointer in collectd format
>       net/tap: remove log when running without multiprocess
>       net/af_xdp: fix external mbuf transmit
>       common/mlx5: fix MAC deletion on Linux
>       examples/vm_power_manager: fix format specifier for port ID
> 
> Emma Finn (1):
>       examples/fips_validation: fix dangling pointers
> 
> Garvit Varshney (1):
>       crypto/cnxk: return decrypted data for RSA verify
> 
> Gregory Etelson (3):
>       net: fix packet type for stacked VLAN
>       net/mlx5: fix MPESW PF probe for any number of ports
>       net/mlx5: fix IPv6 SRH flex node header length
> 
> Itai Sharoni (1):
>       net/mlx5/windows: fix MAC address ownership tracking
> 
> Ivan Malov (4):
>       common/sfc_efx/base: fix flow control on legacy MCDI
>       net/sfc: rework capability check that is done on FEC set
>       net/sfc: drop AUTO from FEC capabilities and fix comment
>       net/sfc: fix reporting status of autonegotiation
> 
> Jacob Keller (1):
>       net/iavf: negotiate PTP before reporting Rx timestamping
> 
> John McNamara (1):
>       net/i40e: fix unused variable
> 
> Kai Ji (1):
>       crypto/openssl: fix SM2 public key buffer overflow
> 
> Kevin Traynor (5):
>       eal/linux: handle interrupt epoll events
>       interrupts: add interrupt event info
>       net/mlx5: check DevX disconnect/error interrupt events
>       examples/ipsec-secgw: fix build with glibc 2.43
>       examples/vm_power: check truncation of socket path
> 
> Liangxing Wang (1):
>       app/dma-perf: fix reversed CPU copy
> 
> Long Li (14):
>       net/netvsc: fix race conditions on VF add/remove events
>       net/netvsc: support multi-process VF device removal
>       net/mana: fix PD resource leak on device close
>       net/netvsc: fix devargs memory leak on hotplug
>       net/mana: fix fast-path ops setup in secondary process
>       net/mlx5: fix fast-path ops setup in secondary process
>       net/mlx4: fix fast-path ops setup in secondary process
>       net/netvsc: fix subchannel leak on device removal
>       net/netvsc: fix double-free of primary Rx queue on uninit
>       net/netvsc: fix resource leak on init failure
>       net/netvsc: fix event callback leak on Rx filter failure
>       net/netvsc: fix resource leaks on MTU change
>       net/mana: fix CQE suppression handling on error completions
>       net/netvsc: switch data path to synthetic on device stop
> 
> Luca Boccassi (1):
>       test/debug: fix IOVA mode on PPC64 without huge pages
> 
> Maayan Kashani (1):
>       net/mlx5: fix redundant control rules in promiscuous mode
> 
> Maciej Paczkowski (1):
>       net/ice/base: fix integer types in comparisons
> 
> Marat Khalili (6):
>       bpf: fix x86 call stack alignment for external calls
>       bpf: disallow empty program
>       bpf: fix add/subtract overflow
>       bpf: fix starting with conditional jump
>       bitops: allow variable as first argument of shift macros
>       bpf: fix signed shift overflows in ARM JIT
> 
> Martin Spinler (5):
>       net/nfb: use constant values for max Rx/Tx queues count
>       net/nfb: fix bad pointer access in queue stats
>       net/nfb: use process private variable for internal
>       net/nfb: fix resources release
>       net/nfb: stop only started queues in fail path
> 
> Maxime Coquelin (3):
>       vhost: fix virtqueue array size for control queue
>       vhost: fix descriptor chain bounds check in control queue
>       vhost: fix mmap error check in VDUSE IOTLB miss handler
> 
> Maxime Leroy (8):
>       net/dpaa2: warn on Rx descriptor limit in high perf mode
>       net/dpaa2: fix resource leak on soft parser failure
>       net/dpaa2: fix link after port stop/start
>       net/dpaa2: fix spurious VLAN insertion on non-VLAN packet
>       net/dpaa2: fix L4 packet type in slow parse path
>       net/dpaa2: fix L3/L4 checksum offload flags
>       net/dpaa2: fix burst mode info
>       net/dpaa2: add SG table walk upper bound in Rx
> 
> Morten Brørup (2):
>       eal: fix cache guard for pedantic compilation
>       mbuf: fix packet data read
> 
> Nithinsen Kaithakadan (1):
>       test/crypto: fix mbuf segment number
> 
> Pavan Nikhilesh (1):
>       event/cnxk: fix Rx offload flags
> 
> Piotr Krzewinski (1):
>       cryptodev: fix memory corruption in secondary process
> 
> Radu Nicolau (1):
>       pdcp: add digest physical address
> 
> Rahul Bhansali (1):
>       event/cnxk: fix crash on CN10K
> 
> Rakesh Kudurumalla (2):
>       common/cnxk: fix engine capabilities fetch logic
>       examples/l2fwd-jobstats: fix stats availability
> 
> Robin Jarry (3):
>       net/iavf: fix reported max Tx and Rx queues
>       telemetry: fix adding dict in container array
>       hash: avoid leaking entries on RCU defer queue failure
> 
> Rongwei Liu (1):
>       net/mlx5: fix job leak on indirect meter creation failure
> 
> Sergei Iashin (1):
>       eventdev/eth_rx: fix crash with telemetry
> 
> Shaiq Wani (1):
>       net/idpf: fix typo in CQ scan threshold macro name
> 
> Shani Peretz (6):
>       examples/ethtool: fix size of mempool name
>       net/mlx5/hws: fix stack alignment for ASan compatibility
>       net/mlx5/hws: fix null dereference in rule skip
>       net/mlx5: allow MTU mismatch for running shared queue
>       app/testpmd: fix memory leak in port flow configure
>       net/mlx5: fix meter ASO action leak on release to pool
> 
> Song Yoong Siang (3):
>       net/e1000: use device timestamp for clock read in igc
>       net/e1000: fix allocation of context desc for launch time
>       net/e1000: fix igc launch time calculation
> 
> Sriram Yagnaraman (2):
>       net/memif: fix descriptor Tx flags corruption
>       net/memif: fix multi-segment Rx corruption
> 
> Stephen Hemminger (26):
>       bus/fslmc: fix const pointer in device name parsing
>       common/cnxk: fix array out-of-bounds
>       examples/fips_validation: fix RSA memcpy
>       net/bnxt: fix build with GCC 16
>       test/table: avoid input line overflow
>       test/crypto: check for vdev args overflow
>       pcapng: document return values
>       pcapng: use malloc instead of fixed buffer size
>       pcapng: chain additional mbuf when comment exceeds tailroom
>       test/pcapng: skip test if null driver missing
>       net/mlx5: fix use-after-free in ASO management init
>       net/tap: use correct length for interface names
>       net/tap: fix resource leaks in secondary process probe
>       net/tap: free IPC reply buffer on queue count mismatch
>       net/tap: fix use-after-free on remote flow creation failure
>       net/tap: free remote flow when implicit rule already exists
>       test/pcapng: fix for Windows
>       test: add pause to synchronization spinloops
>       test/atomic: scale test based on core count
>       test/mcslock: scale test based on core count
>       test/stack: scale test based on core count
>       test/timer: scale test based on core count
>       test/timer: replace volatile with C11 atomics
>       test: add file-prefix for all fast-tests on Linux
>       test/trace: fix parallel execution with traces enabled
>       examples/vmdq_dcb: initialize all configuration structures
> 
> Talluri Chaitanyababu (1):
>       app/testpmd: fix DCB forwarding TC mismatch handling
> 
> Thierry Herbelot (1):
>       net/intel: update key length when getting RSS key
> 
> Thomas Monjalon (4):
>       common/mlx5: fix variable shadowing
>       net/mvpp2: fix variable shadowing
>       eal/x86: fix TSC frequency query
>       examples/ethtool: fix error message about ports limit
> 
> Venkatesh Vemula (1):
>       net/intel: fix comma operator warnings
> 
> Viacheslav Ovsiienko (2):
>       net/mlx5: fix flex parser creation length attribute
>       net/mlx5: fix send skew settings when using wait on time
> 
> Vipin Varghese (1):
>       app/dma-perf: fix buffer overflow with high core count
> 
> Vladimir Medvedkin (1):
>       fib: fix prefix addition handling
> 
> Xavier Guillaume (1):
>       net/af_packet: fix MTU set data size calculation
> 
> Xiaoyu Min (1):
>       net/mlx5: fix HW flow counter query
> 
> Yang Xu (1):
>       net/mlx5: fix port down in link detection failure
> 
> Yunjian Wang (1):
>       net/mlx5: fix memory leak after device spawn failure
> 

Re: 23.11.7 patches review and test

[Thomas Monjalon]

30/04/2026 11:32, Kevin Traynor:
> On 4/21/26 7:46 AM, Shani Peretz wrote:
> > The planned date for the final release is 30 April 2026.
> 
> As discussed on thread [0] there was a quite serious regression caused
> by "net: fix packet type for stacked VLAN"
> 
> As discussion on the fix is ongoing, I would suggest to just revert this
> patch for your release.

I agree the revert is the best option here.

> It doesn't require a new RC and re-validation as it's an isolated issue
> (and there wasn't test cases to catch before Robin's new patch anyway)

I suppose 24.11.5 and 25.11.1 are also impacted?

Re: 23.11.7 patches review and test

[Kevin Traynor]

On 4/30/26 10:58 AM, Thomas Monjalon wrote:
> 30/04/2026 11:32, Kevin Traynor:
>> On 4/21/26 7:46 AM, Shani Peretz wrote:
>>> The planned date for the final release is 30 April 2026.
>>
>> As discussed on thread [0] there was a quite serious regression caused
>> by "net: fix packet type for stacked VLAN"
>>
>> As discussion on the fix is ongoing, I would suggest to just revert this
>> patch for your release.
> 
> I agree the revert is the best option here.
> 
>> It doesn't require a new RC and re-validation as it's an isolated issue
>> (and there wasn't test cases to catch before Robin's new patch anyway)
> 
> I suppose 24.11.5 and 25.11.1 are also impacted?
> 
> 

Yes, I was hoping we would have a fix in a few days and we could add and
re-release. Given that there's now discussion on the patch and what
functionality is needed, it's probably best to just revert and release a
new 24.11/25.11.

RE: 23.11.7 patches review and test

[Shani Peretz]

> -----Original Message-----
> From: Ali Alnubani <alialnu@nvidia.com>
> Sent: Wednesday, 29 April 2026 20:58
> To: Shani Peretz <shperetz@nvidia.com>; stable@dpdk.org
> Cc: dev@dpdk.org; Abhishek Marathe <Abhishek.Marathe@microsoft.com>;
> benjamin.walker@intel.com; David Christensen <drc@linux.vnet.ibm.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>; Pei Zhang
> <pezhang@redhat.com>; qian.q.xu@intel.com; Raslan Darawsheh
> <rasland@nvidia.com>; NBU-Contact-Thomas Monjalon (EXTERNAL)
> <thomas@monjalon.net>; Yanghang Liu <yanghliu@redhat.com>;
> yuan.peng@intel.com; zhaoyan.chen@intel.com
> Subject: Re: 23.11.7 patches review and test
> 
> On 4/21/26 9:46 AM, Shani Peretz wrote:
> 
> > Hi all,
> >
> > Here is a list of patches targeted for stable release 23.11.7.
> >
> > The planned date for the final release is 30 April 2026.
> >
> > 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=v23.11.7-rc1
> >
> > These patches are located at branch 23.11 of dpdk-stable repo:
> >      https://dpdk.org/browse/dpdk-stable/
> >
> > Thanks.
> >
> > Shani
> >
> > ---
> Hello,
> 
> We ran the following functional tests with Nvidia hardware on v23.11.7-rc1:
> - Basic functionality:
>    Send and receive multiple types of traffic.
> - testpmd xstats counter test.
> - testpmd timestamp test.
> - Changing/checking link status through testpmd.
> - rte_flow tests (See https://doc.dpdk.org/guides/nics/mlx5.html for supported
> features)
> - RSS tests.
> - VLAN filtering, stripping, and insertion tests.
> - Checksum and TSO tests.
> - ptype tests.
> - link_status_interrupt example application tests.
> - l3fwd-power example application tests.
> - Multi-process example applications tests.
> - Hardware LRO tests.
> - Buffer Split tests.
> - Tx scheduling tests.
> 
> Testing environments:
> - NIC: ConnectX-6 Dx / OS: Ubuntu 22.04 / Driver:
> MLNX_OFED_LINUX-23.10-6.1.6.1 / Firmware: 22.39.5124
> - NIC: ConnectX-7 / OS: Ubuntu 22.04 / Driver:
> MLNX_OFED_LINUX-23.10-6.1.6.1 / Firmware: 28.39.5124
> - DPU: BlueField-2 / DOCA SW version: 2.5.5 / Firmware: 24.39.5124
> 
> We don't see new issues caused by the changes in this release.
> 
> Thanks,
> Ali

Thanks Ali!

RE: 23.11.7 patches review and test

[Shani Peretz]

> -----Original Message-----
> From: Xu, HailinX <hailinx.xu@intel.com>
> Sent: Thursday, 30 April 2026 4:30
> To: Shani Peretz <shperetz@nvidia.com>; stable@dpdk.org
> Cc: dev@dpdk.org; Abhishek Marathe <Abhishek.Marathe@microsoft.com>; Ali
> Alnubani <alialnu@nvidia.com>; benjamin.walker@intel.com; David Christensen
> <drc@linux.vnet.ibm.com>; Hemant Agrawal <hemant.agrawal@nxp.com>; Ian
> Stokes <ian.stokes@intel.com>; Jerin Jacob <jerinj@marvell.com>; Mcnamara,
> John <john.mcnamara@intel.com>; Ju-Hyoung Lee <juhlee@microsoft.com>;
> Kevin Traynor <ktraynor@redhat.com>; Luca Boccassi <bluca@debian.org>; Pei
> Zhang <pezhang@redhat.com>; qian.q.xu@intel.com; Raslan Darawsheh
> <rasland@nvidia.com>; NBU-Contact-Thomas Monjalon (EXTERNAL)
> <thomas@monjalon.net>; Yanghang Liu <yanghliu@redhat.com>;
> yuan.peng@intel.com; zhaoyan.chen@intel.com; Puttaswamy, Rajesh T
> <rajesh.t.puttaswamy@intel.com>
> Subject: RE: 23.11.7 patches review and test
> 
> External email: Use caution opening links or attachments
> 
> 
> > -----Original Message-----
> > From: Shani Peretz <shperetz@nvidia.com>
> > Sent: Tuesday, April 21, 2026 2:47 PM
> > To: stable@dpdk.org
> > Cc: dev@dpdk.org; Abhishek Marathe <Abhishek.Marathe@microsoft.com>;
> > Ali Alnubani <alialnu@nvidia.com>; benjamin.walker@intel.com; David
> > Christensen <drc@linux.vnet.ibm.com>; Hemant Agrawal
> > <hemant.agrawal@nxp.com>; Ian Stokes <ian.stokes@intel.com>; Jerin
> > Jacob <jerinj@marvell.com>; Mcnamara, John <john.mcnamara@intel.com>;
> > Ju- Hyoung Lee <juhlee@microsoft.com>; Kevin Traynor
> > <ktraynor@redhat.com>; Luca Boccassi <bluca@debian.org>; Pei Zhang
> > <pezhang@redhat.com>; qian.q.xu@intel.com; Raslan Darawsheh
> > <rasland@nvidia.com>; Thomas Monjalon <thomas@monjalon.net>;
> Yanghang
> > Liu <yanghliu@redhat.com>; yuan.peng@intel.com; zhaoyan.chen@intel.com
> > Subject: 23.11.7 patches review and test
> >
> > Hi all,
> >
> > Here is a list of patches targeted for stable release 23.11.7.
> >
> > The planned date for the final release is 30 April 2026.
> >
> > 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=v23.11.7-rc1
> >
> > These patches are located at branch 23.11 of dpdk-stable repo:
> >     https://dpdk.org/browse/dpdk-stable/
> >
> > Thanks.
> >
> > Shani
> >
> > ---
> Update the test status for Intel part. dpdk23.11.7-rc1 all validation test done.
> found 1 new issue and fixed.
> 
> DPDK build failed with clang21.1.8 on Fedora43:  -- Fixed
> 
> * Build & CFLAG compile: cover the build test with latest GCC/Clang version on
> the following OS(all passed)
>   - Ubuntu25.04/Ubuntu24.04.3
>   - RHEL9.6/RHEL10
>   - Fedora43
>   - FreeBSD15
>   - SUSE16
>   - OpenAnolis8.10
>   - AzureLinux3.0
> 
> * Function tests: All test done and passed
>   - i40E-(XXV710, X722) PF/VF: test scenarios including
> basic/RTE_FLOW/TSO/Jumboframe/checksum
> offload/mac_filter/VLAN/VXLAN/RSS, etc.
>   - IXGBE-(82599) PF/VF: test scenarios including
> basic/RTE_FLOW/TSO/Jumboframe/checksum
> offload/mac_filter/VLAN/VXLAN/RSS, etc.
>   - ICE-(E810, E2100) PF/VF: test scenarios including basic/Switch/Package
> Management/Flow Director/Advanced Tx/Advanced RSS/ACL/DCF/Flexible
> Descriptor, etc.
>   - IPsec: test scenarios including ipsec/ipsec-gw/ipsec library basic test -
> QAT&SW/FIB library, etc.
>   - Virtio: both function and performance test are covered. Such as
> PVP/Virtio_loopback/virtio-user loopback/virtio-net VM2VM perf
> testing/VMAWARE ESXI 8.0, etc.
>   - Cryptodev: test scenarios including Cryptodev API testing/CompressDev ISA-
> L/QAT/ZLIB PMD Testing/FIPS, etc.
>   - DLB: test scenarios including DLB2.0 and DLB2.5
>   - Other: test scenarios including AF_XDP, Power, CBDMA, DSA
> 
> * Performance test: All test done and passed
>   - Thoughput Performance
>   - Cryptodev Latency
>   - PF/VF NIC single core
>   - XXV710/E810 NIC Performance
> 
> 
> Regards,
> Xu, Hailin

Thanks Xu, updated in the release notes

Re: 23.11.7 patches review and test

[Kevin Traynor]

On 4/30/26 12:02 PM, Kevin Traynor wrote:
> On 4/30/26 10:58 AM, Thomas Monjalon wrote:
>> 30/04/2026 11:32, Kevin Traynor:
>>> On 4/21/26 7:46 AM, Shani Peretz wrote:
>>>> The planned date for the final release is 30 April 2026.
>>>
>>> As discussed on thread [0] there was a quite serious regression caused
>>> by "net: fix packet type for stacked VLAN"
>>>
>>> As discussion on the fix is ongoing, I would suggest to just revert this
>>> patch for your release.
>>
>> I agree the revert is the best option here.
>>
>>> It doesn't require a new RC and re-validation as it's an isolated issue
>>> (and there wasn't test cases to catch before Robin's new patch anyway)
>>
>> I suppose 24.11.5 and 25.11.1 are also impacted?
>>
>>
> 
> Yes, I was hoping we would have a fix in a few days and we could add and
> re-release. Given that there's now discussion on the patch and what
> functionality is needed, it's probably best to just revert and release a
> new 24.11/25.11.

Hi Luca. Are you planning to do a 24.11 release with revert for above
issue ? If you have a time issue, let me know and I can help out.

Re: 23.11.7 patches review and test

[Luca Boccassi]

On Fri, 15 May 2026 at 11:32, Kevin Traynor <ktraynor@redhat.com> wrote:
>
> On 4/30/26 12:02 PM, Kevin Traynor wrote:
> > On 4/30/26 10:58 AM, Thomas Monjalon wrote:
> >> 30/04/2026 11:32, Kevin Traynor:
> >>> On 4/21/26 7:46 AM, Shani Peretz wrote:
> >>>> The planned date for the final release is 30 April 2026.
> >>>
> >>> As discussed on thread [0] there was a quite serious regression caused
> >>> by "net: fix packet type for stacked VLAN"
> >>>
> >>> As discussion on the fix is ongoing, I would suggest to just revert this
> >>> patch for your release.
> >>
> >> I agree the revert is the best option here.
> >>
> >>> It doesn't require a new RC and re-validation as it's an isolated issue
> >>> (and there wasn't test cases to catch before Robin's new patch anyway)
> >>
> >> I suppose 24.11.5 and 25.11.1 are also impacted?
> >>
> >>
> >
> > Yes, I was hoping we would have a fix in a few days and we could add and
> > re-release. Given that there's now discussion on the patch and what
> > functionality is needed, it's probably best to just revert and release a
> > new 24.11/25.11.
>
> Hi Luca. Are you planning to do a 24.11 release with revert for above
> issue ? If you have a time issue, let me know and I can help out.

Hi, is it strictly necessary? Could it wait for the next one?

Re: 23.11.7 patches review and test

[Kevin Traynor]

On 5/15/26 1:36 PM, Luca Boccassi wrote:
> On Fri, 15 May 2026 at 11:32, Kevin Traynor <ktraynor@redhat.com> wrote:
>>
>> On 4/30/26 12:02 PM, Kevin Traynor wrote:
>>> On 4/30/26 10:58 AM, Thomas Monjalon wrote:
>>>> 30/04/2026 11:32, Kevin Traynor:
>>>>> On 4/21/26 7:46 AM, Shani Peretz wrote:
>>>>>> The planned date for the final release is 30 April 2026.
>>>>>
>>>>> As discussed on thread [0] there was a quite serious regression caused
>>>>> by "net: fix packet type for stacked VLAN"
>>>>>
>>>>> As discussion on the fix is ongoing, I would suggest to just revert this
>>>>> patch for your release.
>>>>
>>>> I agree the revert is the best option here.
>>>>
>>>>> It doesn't require a new RC and re-validation as it's an isolated issue
>>>>> (and there wasn't test cases to catch before Robin's new patch anyway)
>>>>
>>>> I suppose 24.11.5 and 25.11.1 are also impacted?
>>>>
>>>>
>>>
>>> Yes, I was hoping we would have a fix in a few days and we could add and
>>> re-release. Given that there's now discussion on the patch and what
>>> functionality is needed, it's probably best to just revert and release a
>>> new 24.11/25.11.
>>
>> Hi Luca. Are you planning to do a 24.11 release with revert for above
>> issue ? If you have a time issue, let me know and I can help out.
> 
> Hi, is it strictly necessary? Could it wait for the next one?
> 

It's a user visible regression from the previous release that impacts
tap device with VLAN, causing good packets to be discarded. It's also
visible to any application using the net API in a similar way. Given the
effort is low as it's just a revert and we don't need validation teams
involved, then I think it's worthwhile.