On Fri, 19 Jun 2026 16:01:56 +0800
[email protected] wrote:
> From: Jie Liu <[email protected]>
>
> This patch set implements core functionality for the SXE2 PMD,
> including basic driver framework, data path setup, and advanced
> offload features (VLAN, RSS,TM, PTP etc.).
>
> V19:
> - remove software statistics devargs
>
> Jie Liu (23):
> net/sxe2: remove software statistics devargs
> net/sxe2: support AVX512 vectorized path for Rx and Tx
> net/sxe2: add AVX2 vector data path for Rx and Tx
> net/sxe2: add supported packet types get callback
> net/sxe2: add link update callback
> net/sxe2: support L2 filtering and MAC config
> drivers: support RSS feature
> net/sxe2: support TM hierarchy and shaping
> net/sxe2: support IPsec inline protocol offload
> net/sxe2: support statistics and multi-process
> drivers: interrupt handling
> net/sxe2: add NEON vec Rx/Tx burst functions
> drivers: add support for VF representors
> net/sxe2: add support for custom UDP tunnel ports
> net/sxe2: support firmware version reading
> net/sxe2: implement get monitor address
> common/sxe2: add shared SFP module definitions
> net/sxe2: support SFP module info and EEPROM access
> net/sxe2: implement private dump info
> net/sxe2: add mbuf validation in Tx debug mode
> common/sxe2: add callback for memory event handling
> net/sxe2: add private devargs parsing
> net/sxe2: update sxe2 feature matrix docs
>
> doc/guides/nics/features/sxe2.ini | 56 +
> doc/guides/nics/sxe2.rst | 164 ++
> drivers/common/sxe2/sxe2_common.c | 156 ++
> drivers/common/sxe2/sxe2_common.h | 4 +
> drivers/common/sxe2/sxe2_flow_public.h | 633 +++++++
> drivers/common/sxe2/sxe2_ioctl_chnl.c | 178 +-
> drivers/common/sxe2/sxe2_ioctl_chnl_func.h | 18 +
> drivers/common/sxe2/sxe2_msg.h | 118 ++
> drivers/net/sxe2/meson.build | 52 +
> drivers/net/sxe2/sxe2_cmd_chnl.c | 1587 +++++++++++++++-
> drivers/net/sxe2/sxe2_cmd_chnl.h | 139 ++
> drivers/net/sxe2/sxe2_drv_cmd.h | 523 +++++-
> drivers/net/sxe2/sxe2_dump.c | 302 +++
> drivers/net/sxe2/sxe2_dump.h | 12 +
> drivers/net/sxe2/sxe2_ethdev.c | 1513 ++++++++++++++-
> drivers/net/sxe2/sxe2_ethdev.h | 112 +-
> drivers/net/sxe2/sxe2_ethdev_repr.c | 609 ++++++
> drivers/net/sxe2/sxe2_ethdev_repr.h | 32 +
> drivers/net/sxe2/sxe2_filter.c | 895 +++++++++
> drivers/net/sxe2/sxe2_filter.h | 100 +
> drivers/net/sxe2/sxe2_flow.c | 1394 ++++++++++++++
> drivers/net/sxe2/sxe2_flow.h | 30 +
> drivers/net/sxe2/sxe2_flow_define.h | 144 ++
> drivers/net/sxe2/sxe2_flow_parse_action.c | 1182 ++++++++++++
> drivers/net/sxe2/sxe2_flow_parse_action.h | 23 +
> drivers/net/sxe2/sxe2_flow_parse_engine.c | 106 ++
> drivers/net/sxe2/sxe2_flow_parse_engine.h | 13 +
> drivers/net/sxe2/sxe2_flow_parse_pattern.c | 1935 +++++++++++++++++++
> drivers/net/sxe2/sxe2_flow_parse_pattern.h | 46 +
> drivers/net/sxe2/sxe2_ipsec.c | 1565 ++++++++++++++++
> drivers/net/sxe2/sxe2_ipsec.h | 254 +++
> drivers/net/sxe2/sxe2_irq.c | 1026 ++++++++++
> drivers/net/sxe2/sxe2_irq.h | 25 +
> drivers/net/sxe2/sxe2_mac.c | 530 ++++++
> drivers/net/sxe2/sxe2_mac.h | 84 +
> drivers/net/sxe2/sxe2_mp.c | 414 ++++
> drivers/net/sxe2/sxe2_mp.h | 67 +
> drivers/net/sxe2/sxe2_queue.c | 17 +-
> drivers/net/sxe2/sxe2_queue.h | 15 +-
> drivers/net/sxe2/sxe2_rss.c | 584 ++++++
> drivers/net/sxe2/sxe2_rss.h | 81 +
> drivers/net/sxe2/sxe2_rx.c | 93 +-
> drivers/net/sxe2/sxe2_rx.h | 2 +
> drivers/net/sxe2/sxe2_security.c | 335 ++++
> drivers/net/sxe2/sxe2_security.h | 77 +
> drivers/net/sxe2/sxe2_stats.c | 586 ++++++
> drivers/net/sxe2/sxe2_stats.h | 39 +
> drivers/net/sxe2/sxe2_switchdev.c | 332 ++++
> drivers/net/sxe2/sxe2_switchdev.h | 33 +
> drivers/net/sxe2/sxe2_tm.c | 1151 ++++++++++++
> drivers/net/sxe2/sxe2_tm.h | 76 +
> drivers/net/sxe2/sxe2_tx.c | 7 +
> drivers/net/sxe2/sxe2_txrx.c | 1968 +++++++++++++++++++-
> drivers/net/sxe2/sxe2_txrx.h | 8 +
> drivers/net/sxe2/sxe2_txrx_check_mbuf.c | 595 ++++++
> drivers/net/sxe2/sxe2_txrx_check_mbuf.h | 38 +
> drivers/net/sxe2/sxe2_txrx_poll.c | 281 ++-
> drivers/net/sxe2/sxe2_txrx_vec.c | 46 +-
> drivers/net/sxe2/sxe2_txrx_vec.h | 38 +-
> drivers/net/sxe2/sxe2_txrx_vec_avx2.c | 748 ++++++++
> drivers/net/sxe2/sxe2_txrx_vec_avx512.c | 868 +++++++++
> drivers/net/sxe2/sxe2_txrx_vec_common.h | 53 +-
> drivers/net/sxe2/sxe2_txrx_vec_neon.c | 691 +++++++
> drivers/net/sxe2/sxe2_txrx_vec_sse.c | 29 +-
> drivers/net/sxe2/sxe2_vsi.c | 146 ++
> drivers/net/sxe2/sxe2_vsi.h | 12 +-
> drivers/net/sxe2/sxe2vf_regs.h | 85 +
> 67 files changed, 24809 insertions(+), 266 deletions(-)
> create mode 100644 drivers/common/sxe2/sxe2_flow_public.h
> create mode 100644 drivers/common/sxe2/sxe2_msg.h
> create mode 100644 drivers/net/sxe2/sxe2_dump.c
> create mode 100644 drivers/net/sxe2/sxe2_dump.h
> create mode 100644 drivers/net/sxe2/sxe2_ethdev_repr.c
> create mode 100644 drivers/net/sxe2/sxe2_ethdev_repr.h
> create mode 100644 drivers/net/sxe2/sxe2_filter.c
> create mode 100644 drivers/net/sxe2/sxe2_filter.h
> create mode 100644 drivers/net/sxe2/sxe2_flow.c
> create mode 100644 drivers/net/sxe2/sxe2_flow.h
> create mode 100644 drivers/net/sxe2/sxe2_flow_define.h
> create mode 100644 drivers/net/sxe2/sxe2_flow_parse_action.c
> create mode 100644 drivers/net/sxe2/sxe2_flow_parse_action.h
> create mode 100644 drivers/net/sxe2/sxe2_flow_parse_engine.c
> create mode 100644 drivers/net/sxe2/sxe2_flow_parse_engine.h
> create mode 100644 drivers/net/sxe2/sxe2_flow_parse_pattern.c
> create mode 100644 drivers/net/sxe2/sxe2_flow_parse_pattern.h
> create mode 100644 drivers/net/sxe2/sxe2_ipsec.c
> create mode 100644 drivers/net/sxe2/sxe2_ipsec.h
> create mode 100644 drivers/net/sxe2/sxe2_irq.c
> create mode 100644 drivers/net/sxe2/sxe2_mac.c
> create mode 100644 drivers/net/sxe2/sxe2_mac.h
> create mode 100644 drivers/net/sxe2/sxe2_mp.c
> create mode 100644 drivers/net/sxe2/sxe2_mp.h
> create mode 100644 drivers/net/sxe2/sxe2_rss.c
> create mode 100644 drivers/net/sxe2/sxe2_rss.h
> create mode 100644 drivers/net/sxe2/sxe2_security.c
> create mode 100644 drivers/net/sxe2/sxe2_security.h
> create mode 100644 drivers/net/sxe2/sxe2_stats.c
> create mode 100644 drivers/net/sxe2/sxe2_stats.h
> create mode 100644 drivers/net/sxe2/sxe2_switchdev.c
> create mode 100644 drivers/net/sxe2/sxe2_switchdev.h
> create mode 100644 drivers/net/sxe2/sxe2_tm.c
> create mode 100644 drivers/net/sxe2/sxe2_tm.h
> create mode 100644 drivers/net/sxe2/sxe2_txrx_check_mbuf.c
> create mode 100644 drivers/net/sxe2/sxe2_txrx_check_mbuf.h
> create mode 100644 drivers/net/sxe2/sxe2_txrx_vec_avx2.c
> create mode 100644 drivers/net/sxe2/sxe2_txrx_vec_avx512.c
> create mode 100644 drivers/net/sxe2/sxe2_txrx_vec_neon.c
> create mode 100644 drivers/net/sxe2/sxe2vf_regs.h
>
This is look much better, there are a few minor things that you probably
want to address before I merge it.
The (overly verbose) AI feedback is...
[PATCH v4 00/23] sxe2 driver feature additions
This is in good shape. Substantive structural progress on essentially
everything I raised against v3.
Verified across the assembled tree:
- All 23 commits build cleanly end-to-end. git bisect now works. This is
the first revision of the series where that's been true.
- No LLM citation placeholders remain in commit messages. The v3 19/20
message with "[citation:1][citation:3][citation:5]" markers and the
"approximately X%" placeholder are both gone.
- The atomic-sw-stats fix is properly placed. 01/23 is a clean standalone
cleanup commit that removes RTE_ATOMIC qualifiers from
sxe2_rxq_sw_stats, replaces the atomic load/store/fetch_add calls with
plain operations, removes the if(sw_stats_en) gating, removes the now-
unused #include <rte_stdatomic.h>, and renames high_performance_mode to
no_sched_mode to match the devargs string. Verified zero atomic
operations on sw_stats remain in the assembled tree.
- drv-sw-stats devarg removed entirely (defined, parsed, but unused in
v3 - now gone).
- All surviving devargs are documented in doc/guides/nics/sxe2.rst with
substantive explanations covering what each parameter does, valid
values, defaults, and trade-offs.
- The v3 19/20 patch is split into 21/23 (memseg-walk callback
infrastructure, common/sxe2 only) and 22/23 (devargs parsing,
net/sxe2). Both commit messages now describe one thing each.
- The 469-entry runtime ptype-table initialiser is now a file-scope
`static const alignas(RTE_CACHE_LINE_SIZE) uint32_t
sxe2_ptype_tbl[]` with C99 designated initialisers.
- Patch 02/23 (AVX512) scope is tightened - dropped from 13 files to 6,
and the files it touches are all AVX512-related now.
- The v3 03/20 patch is split into 04/23 ("supported packet types") and
05/23 ("link update callback"), addressing the scope-drift complaint.
Three remaining items, none blocking:
[PATCH v4 04/23] subject still does not match content
The commit message says the patch adds `dev_supported_ptypes_get`, and
the patch adds that callback - but it also creates the entire 1793-line
drivers/net/sxe2/sxe2_txrx.c with the Tx/Rx framework, packet-type
constant table, classification helpers, etc. The ptype callback is a
small piece of what this patch does. Either rename the subject to
something like "net/sxe2: add Rx/Tx framework and packet types callback"
(more honest) or split the txrx framework into a separate prior commit
with ptype-callback registration as a small follow-up.
[PATCH v4 04/23] ptype table refactor is incomplete
The static const table is correct, but adapter->ptype_tbl is still
declared in struct sxe2_adapter and sxe2_init_ptype_tbl() now just
memcpy's the const table into the per-adapter copy at init. The vec
paths in sxe2_txrx_vec_avx2.c, _avx512.c, _sse.c and the poll path all
read through rxq->vsi->adapter->ptype_tbl[] rather than the file-scope
const. To finish: remove the adapter field, remove sxe2_init_ptype_tbl,
and have all readers reference sxe2_ptype_tbl directly. The inner-loop
saves one indirection per packet, and per-port memory drops by
SXE2_MAX_PTYPE_NUM * 4 bytes.
[PATCH v4 22/23] flow-duplicate-pattern still defaults to 1
This devarg now has good documentation, but the documentation
clarifies the design objection rather than resolving it: a boolean
that toggles "duplicate rte_flow rules are rejected with EEXIST" vs
"duplicate rte_flow rules are accepted" is a per-boot toggle for
standard-API contract semantics. Standard APIs shouldn't behave
differently based on a vendor devarg. Pick one policy (rejecting
duplicates with EEXIST is what every other PMD does), apply it
unconditionally, and remove the devarg. The
switch_pattern_dup_allow rule metadata can stay if hardware needs it
internally - just don't expose the policy as a boot-time knob.
The other surviving devargs are acceptable as posted:
- no-sched-mode: kernel-coexistence rationale documented, defensible.
- rx-low-latency: ITR throttling threshold, well-documented trade-off,
precedent in other PMDs.
- function-flow-direct: DPDK/kernel flow-table coexistence policy with
no rte_flow analogue. The documentation explains this clearly.
- fnav-stat-type: hardware counter-mode selection. The cleaner long-
term shape would be separate xstats names, but the current form is
documented and reasonable for now.
- sched-layer-mode: hardware-imposed TM hierarchy cap. Should ideally
be exposed via rte_tm_capabilities_get and selected at hierarchy
build time rather than via devarg; worth raising as a future rte_tm
enhancement.
Minor cosmetic:
In sxe2_parse_no_sched_mode() (22/23) the local variable is still
named `high_performance_mode`. The struct field rename in 01/23
didn't propagate to this parser local. Cosmetic.
Once 22/23 drops flow-duplicate-pattern and 04/23's subject is
either renamed or split, I'd consider this ready.
