ibmveth receives on a single RX queue with one interrupt, so all of a
virtual ethernet adapter's receive processing runs on one CPU. Power11
firmware can give the adapter several RX queues, each with its own
interrupt and buffers.

This series only reshapes the existing RX path: open/close, buffer
pools, interrupts, replenish and poll now take a queue index.
IBMVETH_MAX_RX_QUEUES stays 1, so every loop runs once. Same
hypercalls, same ethtool behaviour, no new ABI. Multi-queue enable
is a later series.

Patches 1-5 move the open/close path onto per-queue helpers. Patch 6
moves LAN registration and teardown out of open()/close(). Patch 7
passes the queue index through replenish and poll. Patch 8 splits poll
into per-slot helpers.

This series was split from an earlier posting of the full multi-queue
work [1], which was too large to review as one [2]. Two related bug
fixes go to net-next in a separate thread; neither depends on the
other, and they apply in either order.

Tested: PowerVM LPAR, one RX queue. ifdown/up under iperf3, MTU
change, ethtool -L rx 2 rejected, TX shrink under traffic.

[1] https://lore.kernel.org/netdev/[email protected]/
[2] https://lore.kernel.org/netdev/[email protected]/

Mingming Cao (8):
  ibmveth: Prepare MQ RX adapter data structures
  ibmveth: Refactor RX resource allocation for MQ RX bring-up
  ibmveth: Refactor buffer pool management for per-queue MQ RX
  ibmveth: Refactor RX interrupt control for MQ RX queues
  ibmveth: Refactor TX resource allocation in open/close paths
  ibmveth: Add RX queue register helpers for MQ
  ibmveth: Pass the RX queue index through replenish and poll
  ibmveth: Split RX poll into per-slot helpers for MQ

 drivers/net/ethernet/ibm/ibmveth.c | 1344 +++++++++++++++++++---------
 drivers/net/ethernet/ibm/ibmveth.h |   15 +-
 2 files changed, 928 insertions(+), 431 deletions(-)


base-commit: 6bc9aed3994cb04708fef02dd6d2f1cc5c5e8229
-- 
2.50.1 (Apple Git-155)


Reply via email to