[PATCH io_uring 00/16] zcrx update for-7.3

[Pavel Begunkov <asml.silence@gmail.com>]

zcrx update for 7.3. Patch 1 fixes RQ processing over-throttling,
which shows up with larger page sizes. Patches 2-5 makes the RQ
use more scalable for multi-CPU setups, including softirq running
on a different CPU from CPU. Patches 9-16 implement dynamic area
provisioning.

Pavel Begunkov (16):
  io_uring/zcrx: scale refilling with large pages
  io_uring/zcrx: move RQ head/tail to separate cache lines
  io_uring/zcrx: add RQ iterator
  io_uring/zcrx: cache RQ tail
  io_uring/zcrx: coalesce same-niov RQEs on refill
  io_uring/zcrx: constify area_reg on import
  io_urint/zcrx: narrow var scope in io_zcrx_recv_skb()
  io_uring/zcrx: don't reload skb_shinfo
  io_uring/zcrx: add helper for deriving area token
  io_uring/zcrx: don't pass ifq_reg to area creation
  io_uring/zcrx: split dmabuf unmap and release
  io_uring/zcrx: unmap under netdev lock
  io_uring/zcrx: move freelist lock to struct zcrx
  io_uring/zcrx: keep array of areas
  io_uring/zcrx: lock area creation with pp_lock
  io_uring/zcrx: add dynamic area provisioning

 include/uapi/linux/io_uring/zcrx.h |   7 +
 io_uring/query.c                   |   2 +-
 io_uring/zcrx.c                    | 398 +++++++++++++++++++++--------
 io_uring/zcrx.h                    |  15 +-
 4 files changed, 305 insertions(+), 117 deletions(-)

-- 
2.54.0