netdev - [PATCH bpf-next 00/10] xsk: stop softirq processing on full XSK Rx queue

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20220405110631.404427-1-maciej.fijalkowski@intel.com>
Date:   Tue,  5 Apr 2022 13:06:21 +0200
From:   Maciej Fijalkowski <maciej.fijalkowski@...el.com>
To:     bpf@...r.kernel.org, ast@...nel.org, daniel@...earbox.net,
        magnus.karlsson@...el.com, bjorn@...nel.org
Cc:     netdev@...r.kernel.org, brouer@...hat.com, maximmi@...dia.com,
        alexandr.lobakin@...el.com,
        Maciej Fijalkowski <maciej.fijalkowski@...el.com>
Subject: [PATCH bpf-next 00/10] xsk: stop softirq processing on full XSK Rx queue

Hi!

This is a revival of Bjorn's idea [0] to break NAPI loop when XSK Rx
queue gets full which in turn makes it impossible to keep on
successfully producing descriptors to XSK Rx ring. By breaking out of
the driver side immediately we will give the user space opportunity for
consuming descriptors from XSK Rx ring and therefore provide room in the
ring so that HW Rx -> XSK Rx redirection can be done.

Maxim asked and Jesper agreed on simplifying Bjorn's original API used
for detecting the event of interest, so let's just simply check for
-ENOBUFS within Intel's ZC drivers after an attempt to redirect a buffer
to XSK Rx. No real need for redirect API extension.

One might ask why it is still relevant even after having proper busy
poll support in place - here is the justification.

For xdpsock that was:
- run for l2fwd scenario,
- app/driver processing took place on the same core in busy poll
  with 2048 budget,
- HW ring sizes Tx 256, Rx 2048,

this work improved throughput by 78% and reduced Rx queue full statistic
bump by 99%.

For testing ice, make sure that you have [1] present on your side.

This set, besides the work described above, also carries also
improvements around return codes in various XSK paths and lastly a minor
optimization for xskq_cons_has_entries(), a helper that might be used
when XSK Rx batching would make it to the kernel.

Thanks!
MF

[0]: https://lore.kernel.org/bpf/20200904135332.60259-1-bjorn.topel@gmail.com/
[1]: https://lore.kernel.org/netdev/20220317175727.340251-1-maciej.fijalkowski@intel.com/

Björn Töpel (1):
  xsk: improve xdp_do_redirect() error codes

Maciej Fijalkowski (9):
  xsk: diversify return codes in xsk_rcv_check()
  ice: xsk: terminate NAPI when XSK Rx queue gets full
  i40e: xsk: terminate NAPI when XSK Rx queue gets full
  ixgbe: xsk: terminate NAPI when XSK Rx queue gets full
  ice: xsk: diversify return values from xsk_wakeup call paths
  i40e: xsk: diversify return values from xsk_wakeup call paths
  ixgbe: xsk: diversify return values from xsk_wakeup call paths
  ice: xsk: avoid refilling single Rx descriptors
  xsk: drop ternary operator from xskq_cons_has_entries

 .../ethernet/intel/i40e/i40e_txrx_common.h    |  1 +
 drivers/net/ethernet/intel/i40e/i40e_xsk.c    | 27 +++++++++------
 drivers/net/ethernet/intel/ice/ice_txrx.h     |  1 +
 drivers/net/ethernet/intel/ice/ice_xsk.c      | 34 ++++++++++++-------
 .../ethernet/intel/ixgbe/ixgbe_txrx_common.h  |  1 +
 drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c  | 29 ++++++++++------
 net/xdp/xsk.c                                 |  4 +--
 net/xdp/xsk_queue.h                           |  4 +--
 8 files changed, 64 insertions(+), 37 deletions(-)

-- 
2.33.1